From 84a0f3eb5c9626e4fee6614e4ea74d2a79ba1431 Mon Sep 17 00:00:00 2001
From: bbauvin <baptiste.bauvin@centrale-marseille.fr>
Date: Thu, 8 Sep 2016 10:01:59 -0400
Subject: [PATCH] Woring with fake data 1 iter of gs and mono-multi core Mumbo
untested
---
Code/MonoMutliViewClassifiers/ExecClassif.py | 47 +-
.../Monoview/ExecClassifMonoView.py | 3 +-
.../EarlyFusionPackage/WeightedLinear.py | 9 +-
.../LateFusionPackage/WeightedLinear.py | 5 +-
.../Multiview/GetMultiviewDb.py | 59 +
.../Multiview/Mumbo/Mumbo.py | 2 +-
.../ResultAnalysis.py | 4 +-
...hyl_MiRNA__RNASeq_Clinic-MultiOmic-LOG.log | 224 ++
...ionTree-Non-Oui-learnRate0.7-MultiOmic.txt | 54 +
...daboost-Non-Oui-learnRate0.7-MultiOmic.txt | 57 +
...mForest-Non-Oui-learnRate0.7-MultiOmic.txt | 54 +
...k-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log | 2211 +++++++++++++
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...4Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...4Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ults-SVMPoly-Non-Oui-learnRate0.7-Fake.txt | 54 +
...sults-SVMRBF-Non-Oui-learnRate0.7-Fake.txt | 54 +
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...5Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...5Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ults-SVMPoly-Non-Oui-learnRate0.7-Fake.txt | 54 +
...sults-SVMRBF-Non-Oui-learnRate0.7-Fake.txt | 54 +
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...6Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...6Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ults-SVMPoly-Non-Oui-learnRate0.7-Fake.txt | 54 +
...sults-SVMRBF-Non-Oui-learnRate0.7-Fake.txt | 54 +
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...7Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...7Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 32 +
...k-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log | 2394 ++++++++++++++
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...7Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...8Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...8Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ults-SVMPoly-Non-Oui-learnRate0.7-Fake.txt | 54 +
...sults-SVMRBF-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...9Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ults-SVMPoly-Non-Oui-learnRate0.7-Fake.txt | 54 +
...sults-SVMRBF-Non-Oui-learnRate0.7-Fake.txt | 54 +
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...0Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...0Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...1Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ults-SVMPoly-Non-Oui-learnRate0.7-Fake.txt | 54 +
...sults-SVMRBF-Non-Oui-learnRate0.7-Fake.txt | 54 +
...2Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 32 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 32 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 32 +
...k-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log | 32 +
...k-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log | 2842 +++++++++++++++++
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...4Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...5Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...5Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ults-SVMPoly-Non-Oui-learnRate0.7-Fake.txt | 54 +
...sults-SVMRBF-Non-Oui-learnRate0.7-Fake.txt | 54 +
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...6Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ults-SVMPoly-Non-Oui-learnRate0.7-Fake.txt | 54 +
...sults-SVMRBF-Non-Oui-learnRate0.7-Fake.txt | 54 +
...7Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...7Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...lts-Adaboost-Non-Oui-learnRate0.7-Fake.txt | 57 +
...DecisionTree-Non-Oui-learnRate0.7-Fake.txt | 54 +
...8Results-KNN-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RandomForest-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ults-SVMPoly-Non-Oui-learnRate0.7-Fake.txt | 54 +
...sults-SVMRBF-Non-Oui-learnRate0.7-Fake.txt | 54 +
...9Results-SGD-Non-Oui-learnRate0.7-Fake.txt | 54 +
...ts-SVMLinear-Non-Oui-learnRate0.7-Fake.txt | 54 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 32 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 32 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 32 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 32 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 31 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 28 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 28 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 28 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 28 +
...RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt | 28 +
.../Fake-accuracy_score-20160908-100014.png | Bin 0 -> 164514 bytes
.../Results/Fake-f1_score-20160908-100017.png | Bin 0 -> 167745 bytes
.../Fake-fbeta_score-20160908-100019.png | Bin 0 -> 169262 bytes
.../Fake-hamming_loss-20160908-100022.png | Bin 0 -> 164153 bytes
...ccard_similarity_score-20160908-100026.png | Bin 0 -> 165112 bytes
.../Results/Fake-log_loss-20160908-100029.png | Bin 0 -> 159723 bytes
...Fake-matthews_corrcoef-20160908-100031.png | Bin 0 -> 160552 bytes
.../Fake-precision_score-20160908-100034.png | Bin 0 -> 168171 bytes
.../Fake-recall_score-20160908-100037.png | Bin 0 -> 166427 bytes
.../Fake-roc_auc_score-20160908-100040.png | Bin 0 -> 167357 bytes
.../Fake-zero_one_loss-20160908-100043.png | Bin 0 -> 164993 bytes
130 files changed, 13290 insertions(+), 30 deletions(-)
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160907-162651-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-MultiOmic-LOG.log
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160907-162716Results-DecisionTree-Non-Oui-learnRate0.7-MultiOmic.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160907-162717Results-Adaboost-Non-Oui-learnRate0.7-MultiOmic.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160907-162719Results-RandomForest-Non-Oui-learnRate0.7-MultiOmic.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095527-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095534Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095534Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095534Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095534Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095535Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095535Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095535Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095535Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095536Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095536Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095536Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095536Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095537Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095537Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095537Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095537Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095537Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095537Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095538Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095622-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095627Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095627Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095627Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095628Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095628Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095628Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095628Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095629Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095630Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095630Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095630Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095630Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095630Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095630Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095631Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095631Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095631Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095631Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095631Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095631Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095632Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095632Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095633Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095633Results-Fusion-LateFusion-MajorityVoting-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095634Results-Fusion-LateFusion-SVMForLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095845-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-095958-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100004Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100004Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100004Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100004Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100005Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100005Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100005Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100006Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100006Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100006Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100007Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100007Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100007Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100007Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100008Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100008Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100008Results-KNN-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100008Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100008Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100008Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100009Results-SGD-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100009Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100010Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100010Results-Fusion-LateFusion-MajorityVoting-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100011Results-Fusion-LateFusion-SVMForLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100011Results-Fusion-LateFusion-WeightedLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100012Results-Fusion-EarlyFusion-WeightedLinear-Adaboost-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100012Results-Fusion-EarlyFusion-WeightedLinear-DecisionTree-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-KNN-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-RandomForest-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-SVMLinear-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-accuracy_score-20160908-100014.png
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-f1_score-20160908-100017.png
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-fbeta_score-20160908-100019.png
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-hamming_loss-20160908-100022.png
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-jaccard_similarity_score-20160908-100026.png
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-log_loss-20160908-100029.png
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-matthews_corrcoef-20160908-100031.png
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-precision_score-20160908-100034.png
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-recall_score-20160908-100037.png
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-roc_auc_score-20160908-100040.png
create mode 100644 Code/MonoMutliViewClassifiers/Results/Fake-zero_one_loss-20160908-100043.png
diff --git a/Code/MonoMutliViewClassifiers/ExecClassif.py b/Code/MonoMutliViewClassifiers/ExecClassif.py
index 34ab48ff..b58cb129 100644
--- a/Code/MonoMutliViewClassifiers/ExecClassif.py
+++ b/Code/MonoMutliViewClassifiers/ExecClassif.py
@@ -311,26 +311,29 @@ else:
bestClassifiers.append(classifiersNames[viewIndex][np.argmax(np.array(accuracies[viewIndex]))])
bestClassifiersConfigs.append(classifiersConfigs[viewIndex][np.argmax(np.array(accuracies[viewIndex]))])
monoviewTime = time.time()-dataBaseTime
+print resultsMonoview
try:
if benchmark["Multiview"]:
- try:
- if benchmark["Multiview"]["Mumbo"]:
- for combination in itertools.combinations_with_replacement(range(len(benchmark["Multiview"]["Mumbo"])), NB_VIEW):
- classifiersNames = [benchmark["Multiview"]["Mumbo"][index] for index in combination]
- arguments = {"CL_type": "Mumbo",
- "views": args.views.split(":"),
- "NB_VIEW": len(args.views.split(":")),
- "NB_CLASS": len(args.CL_classes.split(":")),
- "LABELS_NAMES": args.CL_classes.split(":"),
- "MumboKWARGS": {"classifiersNames": classifiersNames,
- "maxIter":int(args.MU_iter[0]), "minIter":int(args.MU_iter[1]),
- "threshold":args.MU_iter[2],
- "classifiersConfigs": [argument.split(":") for argument in args.MU_config]}}
- argumentDictionaries["Multiview"].append(arguments)
- except:
- pass
-# bestClassifiers = ["DecisionTree", "DecisionTree", "DecisionTree", "DecisionTree"]
-
+ # try:
+ # if benchmark["Multiview"]["Mumbo"]:
+ # for combination in itertools.combinations_with_replacement(range(len(benchmark["Multiview"]["Mumbo"])), NB_VIEW):
+ # classifiersNames = [benchmark["Multiview"]["Mumbo"][index] for index in combination]
+ # arguments = {"CL_type": "Mumbo",
+ # "views": args.views.split(":"),
+ # "NB_VIEW": len(args.views.split(":")),
+ # "NB_CLASS": len(args.CL_classes.split(":")),
+ # "LABELS_NAMES": args.CL_classes.split(":"),
+ # "MumboKWARGS": {"classifiersNames": classifiersNames,
+ # "maxIter":int(args.MU_iter[0]), "minIter":int(args.MU_iter[1]),
+ # "threshold":args.MU_iter[2],
+ # "classifiersConfigs": [argument.split(":") for argument in args.MU_config]}}
+ # argumentDictionaries["Multiview"].append(arguments)
+ # except:
+ # pass
+ # bestClassifiers = ["DecisionTree", "DecisionTree", "DecisionTree", "DecisionTree"]
+ # monoviewTime = 0
+ # resultsMonoview = []
+ # bestClassifiersConfigs = []
try:
if benchmark["Multiview"]["Fusion"]:
try:
@@ -368,6 +371,7 @@ try:
pass
except:
pass
+# resultsMultiview = []
if nbCores>1:
resultsMultiview = []
nbExperiments = len(argumentDictionaries["Multiview"])
@@ -375,12 +379,12 @@ if nbCores>1:
resultsMultiview += Parallel(n_jobs=nbCores)(
delayed(ExecMultiview_multicore)(coreIndex, args.name, args.CL_split, args.CL_nbFolds, args.type, args.pathF,
LABELS_DICTIONARY, gridSearch=gridSearch,
- metrics=metrics, **argumentDictionaries["Multiview"][stepIndex*nbCores+coreIndex])
+ metrics=metrics, nIter=args.CL_GS_iter, **argumentDictionaries["Multiview"][stepIndex*nbCores+coreIndex])
for coreIndex in range(min(nbCores, nbExperiments - (stepIndex + 1) * nbCores)))
else:
resultsMultiview = [ExecMultiview(DATASET, args.name, args.CL_split, args.CL_nbFolds, 1, args.type, args.pathF,
LABELS_DICTIONARY, gridSearch=gridSearch,
- metrics=metrics, **arguments) for arguments in argumentDictionaries["Multiview"]]
+ metrics=metrics, nIter=args.CL_GS_iter, **arguments) for arguments in argumentDictionaries["Multiview"]]
multiviewTime = time.time()-monoviewTime
if nbCores>1:
logging.debug("Start:\t Deleting "+str(nbCores)+" temporary datasets for multiprocessing")
@@ -390,6 +394,7 @@ if nbCores>1:
times = [dataBaseTime, monoviewTime, multiviewTime]
# times=[]
results = (resultsMonoview, resultsMultiview)
+logging.debug("Start:\t Analyze Results")
resultAnalysis(benchmark, results, args.name, times, metrics)
-
+logging.debug("Done:\t Analyze Results")
diff --git a/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py b/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py
index 577a4999..154a52c6 100644
--- a/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py
+++ b/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py
@@ -107,6 +107,7 @@ def ExecMonoview(X, Y, name, learningRate, nbFolds, nbCores, databaseType, path,
clKWARGS, classLabelsNames, X.shape,
y_train, y_train_pred, y_test, y_test_pred, t_end)
cl_desc = [value for key, value in sorted(clKWARGS.iteritems())]
+ print cl_desc
logging.debug("Done:\t Getting Results")
logging.info(stringAnalysis)
labelsString = "-".join(classLabelsNames)
@@ -132,7 +133,7 @@ def ExecMonoview(X, Y, name, learningRate, nbFolds, nbCores, databaseType, path,
logging.info("Done:\t Result Analysis")
viewIndex = args["viewIndex"]
- return viewIndex, [CL_type, cl_desc.append(feat), metricsScores]
+ return viewIndex, [CL_type, cl_desc+[feat], metricsScores]
# # Classification Report with Precision, Recall, F1 , Support
# logging.debug("Info:\t Classification report:")
# filename = datetime.datetime.now().strftime("%Y_%m_%d") + "-CMV-" + name + "-" + feat + "-Report"
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py
index 7af341b5..61707487 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py
@@ -34,12 +34,11 @@ class WeightedLinear(EarlyFusionClassifier):
self.weights = self.weights/float(max(self.weights))
self.makeMonoviewData_hdf5(DATASET, weights=self.weights, usedIndices=trainIndices)
monoviewClassifierModule = getattr(MonoviewClassifiers, self.monoviewClassifierName)
- print self.monoviewClassifiersConfig
self.monoviewClassifier = monoviewClassifierModule.fit(self.monoviewData, DATASET.get("labels")[trainIndices],
- NB_CORES=self.nbCores, **self.monoviewClassifiersConfig)
- #**dict((str(configIndex), config) for configIndex, config in
- # enumerate(self.monoviewClassifiersConfig
- # )))
+ NB_CORES=self.nbCores, #**self.monoviewClassifiersConfig)
+ **dict((str(configIndex), config) for configIndex, config in
+ enumerate(self.monoviewClassifiersConfig
+ )))
def predict_hdf5(self, DATASET, usedIndices=None):
self.weights = self.weights/float(max(self.weights))
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
index d3e05e42..9bb535f0 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
@@ -26,7 +26,10 @@ class WeightedLinear(LateFusionClassifier):
def __init__(self, NB_CORES=1, **kwargs):
LateFusionClassifier.__init__(self, kwargs['classifiersNames'], kwargs['classifiersConfigs'],
NB_CORES=NB_CORES)
- self.weights = np.array(map(float, kwargs['fusionMethodConfig'][0]))
+ if kwargs['fusionMethodConfig'][0]==None:
+ self.weights = np.ones(len(kwargs["classifiersNames"]), dtype=float)
+ else:
+ self.weights = np.array(map(float, kwargs['fusionMethodConfig'][0]))
def predict_hdf5(self, DATASET, usedIndices=None):
self.weights = self.weights/float(max(self.weights))
diff --git a/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py b/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py
index b944ffa9..8a60070a 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py
@@ -1,4 +1,5 @@
import numpy as np
+import math
from string import digits
import os
import random
@@ -259,6 +260,54 @@ def getMultiOmicDBcsv(features, path, name, NB_CLASS, LABELS_NAMES):
return datasetFile, labelDictionary
+def findClosestPowerOfTwo(k):
+ power=1
+ while k-power>0:
+ power = 2*power
+ if abs(k-power)<abs(k-power/2):
+ return power
+ else:
+ return power/2
+
+
+def getVector(matrix):
+ argmax = [0,0]
+ n = len(matrix)
+ maxi = 0
+ for i in range(n):
+ for j in range(n):
+ if j==i+1:
+ value = (i+1)*(n-j)
+ if value>maxi:
+ maxi= value
+ argmax = [i,j]
+ i,j = argmax
+ vector = np.zeros(n, dtype=bool)
+ vector[:i+1]=np.ones(i+1, dtype=bool)
+ matrixSup = [i+1, j+1]
+ matrixInf = [i+1, j+1]
+ return vector, matrixSup, matrixInf
+
+
+def easyFactorize(targetMatrix, k, t=0):
+ n = len(targetMatrix)
+ if math.log(k+1, 2)%1==0.0:
+ pass
+ else:
+ k = findClosestPowerOfTwo(k)-1
+ if k==1:
+ t=1
+ return t, getVector(targetMatrix)[0]
+ vector, matrixSup, matrixInf = getVector(targetMatrix)
+ t, vectorSup = easyFactorize(targetMatrix[:matrixSup[0], :matrixSup[1]], (k-1)/2, t)
+ t, vectorInf = easyFactorize(targetMatrix[matrixInf[0]:, matrixInf[0]:], (k-1)/2, t)
+ factor = np.zeros((n,2*t+1), dtype=bool)
+ factor[:matrixSup[0], :t] = vectorSup.reshape(factor[:matrixSup[0], :t].shape)
+ factor[matrixInf[0]:, t:2*t] = vectorInf.reshape(factor[matrixInf[0]:, t:2*t].shape)
+ factor[:, 2*t] = vector
+ return 2*t+1, factor
+
+
def getModifiedMultiOmicDBcsv(features, path, name, NB_CLASS, LABELS_NAMES):
datasetFile = h5py.File(path+"ModifiedMultiOmic.hdf5", "w")
@@ -307,6 +356,16 @@ def getModifiedMultiOmicDBcsv(features, path, name, NB_CLASS, LABELS_NAMES):
mrnaseqDset.attrs["name"] = "SRNASeq"
logging.debug("Done:\t Getting Sorted RNASeq Data")
+ logging.debug("Start:\t Getting Binarized RNASeq Data")
+ factorizedBaseMatrix = np.genfromtxt(path+"factorMatrix.csv", delimiter=',')
+ brnaseqDset = datasetFile.create_dataset("View5", len(modifiedRNASeq), len(factorizedBaseMatrix.flatten()))
+ for patientIndex, patientSortedArray in enumerate(modifiedRNASeq):
+ patientMatrix = np.zeros(factorizedBaseMatrix.shape, dtype=bool)
+ for lineIndex, geneIndex in enumerate(patientSortedArray):
+ patientMatrix[geneIndex]=factorizedBaseMatrix[lineIndex]
+ brnaseqDset[patientIndex] = patientMatrix.flatten()
+ logging.debug("Done:\t Getting Binarized RNASeq Data")
+
# logging.debug("Start:\t Getting Binned RNASeq Data")
# SRNASeq = datasetFile["View4"][...]
# nbBins = 372
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py
index 9a894de3..7214759a 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py
@@ -50,7 +50,7 @@ def gridSearch_hdf5(DATASET, classificationKWARGS, learningIndices, metric=None,
classifiersNames = classificationKWARGS["classifiersNames"]
bestSettings = []
for classifierIndex, classifierName in enumerate(classifiersNames):
- logging.debug("\tStart:\t Gridsearch for "+classifierName+" on "+DATASET.get("View"+str(classifierIndex)).attrs["name"])
+ logging.debug("\tStart:\t Random search for "+classifierName+" on "+DATASET.get("View"+str(classifierIndex)).attrs["name"])
classifierModule = globals()[classifierName] # Permet d'appeler une fonction avec une string
classifierMethod = getattr(classifierModule, "gridSearch")
bestSettings.append(classifierMethod(DATASET.get("View"+str(classifierIndex))[learningIndices],
diff --git a/Code/MonoMutliViewClassifiers/ResultAnalysis.py b/Code/MonoMutliViewClassifiers/ResultAnalysis.py
index ff02817f..9782f7d5 100644
--- a/Code/MonoMutliViewClassifiers/ResultAnalysis.py
+++ b/Code/MonoMutliViewClassifiers/ResultAnalysis.py
@@ -20,7 +20,9 @@ def resultAnalysis(benchmark, results, name, times, metrics):
for metric in metrics:
mono, multi = results
names = [res[1][0]+"-"+res[1][1][-1] for res in mono]
- names+=[type_ if type_ != "Fusion" else a["fusionType"]+"-"+a["fusionMethod"] for type_, a, b in multi]
+ names+=[type_ for type_, a, b in multi if type_ != "Fusion"]
+ names+=[ "Late-"+str(a["fusionMethod"]) for type_, a, b in multi if type_ == "Fusion" and a["fusionType"] != "EarlyFusion"]
+ names+=[ "Early-"+a["fusionMethod"]+"-"+a["classifiersNames"][0] for type_, a, b in multi if type_ == "Fusion" and a["fusionType"] != "LateFusion"]
nbResults = len(mono)+len(multi)
validationScores = [float(res[1][2][metric[0]][2]) for res in mono]
validationScores += [float(scores[metric[0]][2]) for a, b, scores in multi]
diff --git a/Code/MonoMutliViewClassifiers/Results/20160907-162651-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-MultiOmic-LOG.log b/Code/MonoMutliViewClassifiers/Results/20160907-162651-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-MultiOmic-LOG.log
new file mode 100644
index 00000000..7790e9fe
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160907-162651-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-MultiOmic-LOG.log
@@ -0,0 +1,224 @@
+2016-09-07 16:26:51,762 DEBUG: Start: Creating 2 temporary datasets for multiprocessing
+2016-09-07 16:26:51,762 WARNING: WARNING : /!\ This may use a lot of HDD storage space : 0.273145851562 Gbytes /!\
+2016-09-07 16:27:02,716 DEBUG: Start: Creating datasets for multiprocessing
+2016-09-07 16:27:02,972 INFO: Start: Finding all available mono- & multiview algorithms
+2016-09-07 16:27:04,713 DEBUG: ### Main Programm for Classification MonoView
+2016-09-07 16:27:04,714 DEBUG: ### Classification - Database:MultiOmic Feature:Methyl train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-07 16:27:04,714 DEBUG: Start: Determine Train/Test split
+2016-09-07 16:27:04,911 DEBUG: Info: Shape X_train:(242, 25978), Length of y_train:242
+2016-09-07 16:27:04,911 DEBUG: Info: Shape X_test:(105, 25978), Length of y_test:105
+2016-09-07 16:27:04,911 DEBUG: Done: Determine Train/Test split
+2016-09-07 16:27:04,911 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-07 16:27:06,463 DEBUG: ### Main Programm for Classification MonoView
+2016-09-07 16:27:06,464 DEBUG: ### Classification - Database:MultiOmic Feature:Methyl train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-07 16:27:06,464 DEBUG: Start: Determine Train/Test split
+2016-09-07 16:27:06,499 DEBUG: Info: Shape X_train:(242, 25978), Length of y_train:242
+2016-09-07 16:27:06,499 DEBUG: Info: Shape X_test:(105, 25978), Length of y_test:105
+2016-09-07 16:27:06,499 DEBUG: Done: Determine Train/Test split
+2016-09-07 16:27:06,499 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-07 16:27:14,206 DEBUG: Done: RandomSearch best settings
+2016-09-07 16:27:14,206 DEBUG: Start: Training
+2016-09-07 16:27:15,153 DEBUG: Done: RandomSearch best settings
+2016-09-07 16:27:15,153 DEBUG: Start: Training
+2016-09-07 16:27:16,232 DEBUG: Info: Time for Training: 13.1729319096[s]
+2016-09-07 16:27:16,232 DEBUG: Done: Training
+2016-09-07 16:27:16,233 DEBUG: Start: Predicting
+2016-09-07 16:27:16,348 DEBUG: Done: Predicting
+2016-09-07 16:27:16,348 DEBUG: Start: Getting Results
+2016-09-07 16:27:16,926 DEBUG: Done: Getting Results
+2016-09-07 16:27:16,926 INFO: Classification on MultiOmic database for Methyl with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.771428571429
+
+Database configuration :
+ - Database name : MultiOmic
+ - View name : Methyl View shape : (347, 25978)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 9
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.771428571429
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.586206896552
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.586206896552
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.228571428571
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.771428571429
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.440385506051
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.68
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.515151515152
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.70202020202
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.228571428571
+
+
+ Classification took 0:00:13
+2016-09-07 16:27:16,964 INFO: Done: Result Analysis
+2016-09-07 16:27:17,029 DEBUG: Info: Time for Training: 13.9593689442[s]
+2016-09-07 16:27:17,029 DEBUG: Done: Training
+2016-09-07 16:27:17,029 DEBUG: Start: Predicting
+2016-09-07 16:27:17,043 DEBUG: Done: Predicting
+2016-09-07 16:27:17,043 DEBUG: Start: Getting Results
+2016-09-07 16:27:17,076 DEBUG: Done: Getting Results
+2016-09-07 16:27:17,076 INFO: Classification on MultiOmic database for Methyl with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.790476190476
+
+Database configuration :
+ - Database name : MultiOmic
+ - View name : Methyl View shape : (347, 25978)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 14, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.790476190476
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.592592592593
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.592592592593
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.209523809524
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.790476190476
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.482108339669
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.761904761905
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.484848484848
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.707702020202
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.209523809524
+
+
+ Classification took 0:00:13
+2016-09-07 16:27:17,076 INFO: Done: Result Analysis
+2016-09-07 16:27:18,338 DEBUG: ### Main Programm for Classification MonoView
+2016-09-07 16:27:18,339 DEBUG: ### Classification - Database:MultiOmic Feature:Methyl train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-07 16:27:18,339 DEBUG: Start: Determine Train/Test split
+2016-09-07 16:27:18,379 DEBUG: Info: Shape X_train:(242, 25978), Length of y_train:242
+2016-09-07 16:27:18,379 DEBUG: Info: Shape X_test:(105, 25978), Length of y_test:105
+2016-09-07 16:27:18,379 DEBUG: Done: Determine Train/Test split
+2016-09-07 16:27:18,379 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-07 16:27:18,521 DEBUG: ### Main Programm for Classification MonoView
+2016-09-07 16:27:18,522 DEBUG: ### Classification - Database:MultiOmic Feature:Methyl train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-07 16:27:18,522 DEBUG: Start: Determine Train/Test split
+2016-09-07 16:27:18,570 DEBUG: Info: Shape X_train:(242, 25978), Length of y_train:242
+2016-09-07 16:27:18,571 DEBUG: Info: Shape X_test:(105, 25978), Length of y_test:105
+2016-09-07 16:27:18,571 DEBUG: Done: Determine Train/Test split
+2016-09-07 16:27:18,571 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-07 16:27:18,830 DEBUG: Done: RandomSearch best settings
+2016-09-07 16:27:18,830 DEBUG: Start: Training
+2016-09-07 16:27:18,913 DEBUG: Info: Time for Training: 1.72966194153[s]
+2016-09-07 16:27:18,914 DEBUG: Done: Training
+2016-09-07 16:27:18,914 DEBUG: Start: Predicting
+2016-09-07 16:27:18,924 DEBUG: Done: Predicting
+2016-09-07 16:27:18,924 DEBUG: Start: Getting Results
+2016-09-07 16:27:19,006 DEBUG: Done: Getting Results
+2016-09-07 16:27:19,006 INFO: Classification on MultiOmic database for Methyl with RandomForest
+
+accuracy_score on train : 0.97520661157
+accuracy_score on test : 0.761904761905
+
+Database configuration :
+ - Database name : MultiOmic
+ - View name : Methyl View shape : (347, 25978)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 6, max_depth : 9
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.97520661157
+ - Score on test : 0.761904761905
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.949152542373
+ - Score on test : 0.468085106383
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.949152542373
+ - Score on test : 0.468085106383
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0247933884298
+ - Score on test : 0.238095238095
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.97520661157
+ - Score on test : 0.761904761905
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.932999668908
+ - Score on test : 0.398313753408
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.965517241379
+ - Score on test : 0.785714285714
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.933333333333
+ - Score on test : 0.333333333333
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.961172161172
+ - Score on test : 0.645833333333
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0247933884298
+ - Score on test : 0.238095238095
+
+
+ Classification took 0:00:01
+2016-09-07 16:27:19,007 INFO: Done: Result Analysis
diff --git a/Code/MonoMutliViewClassifiers/Results/20160907-162716Results-DecisionTree-Non-Oui-learnRate0.7-MultiOmic.txt b/Code/MonoMutliViewClassifiers/Results/20160907-162716Results-DecisionTree-Non-Oui-learnRate0.7-MultiOmic.txt
new file mode 100644
index 00000000..e9719acf
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160907-162716Results-DecisionTree-Non-Oui-learnRate0.7-MultiOmic.txt
@@ -0,0 +1,54 @@
+Classification on MultiOmic database for Methyl with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.771428571429
+
+Database configuration :
+ - Database name : MultiOmic
+ - View name : Methyl View shape : (347, 25978)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 9
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.771428571429
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.586206896552
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.586206896552
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.228571428571
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.771428571429
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.440385506051
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.68
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.515151515152
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.70202020202
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.228571428571
+
+
+ Classification took 0:00:13
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160907-162717Results-Adaboost-Non-Oui-learnRate0.7-MultiOmic.txt b/Code/MonoMutliViewClassifiers/Results/20160907-162717Results-Adaboost-Non-Oui-learnRate0.7-MultiOmic.txt
new file mode 100644
index 00000000..32fa654f
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160907-162717Results-Adaboost-Non-Oui-learnRate0.7-MultiOmic.txt
@@ -0,0 +1,57 @@
+Classification on MultiOmic database for Methyl with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.790476190476
+
+Database configuration :
+ - Database name : MultiOmic
+ - View name : Methyl View shape : (347, 25978)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 14, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.790476190476
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.592592592593
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.592592592593
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.209523809524
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.790476190476
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.482108339669
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.761904761905
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.484848484848
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.707702020202
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.209523809524
+
+
+ Classification took 0:00:13
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160907-162719Results-RandomForest-Non-Oui-learnRate0.7-MultiOmic.txt b/Code/MonoMutliViewClassifiers/Results/20160907-162719Results-RandomForest-Non-Oui-learnRate0.7-MultiOmic.txt
new file mode 100644
index 00000000..97c69cd4
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160907-162719Results-RandomForest-Non-Oui-learnRate0.7-MultiOmic.txt
@@ -0,0 +1,54 @@
+Classification on MultiOmic database for Methyl with RandomForest
+
+accuracy_score on train : 0.97520661157
+accuracy_score on test : 0.761904761905
+
+Database configuration :
+ - Database name : MultiOmic
+ - View name : Methyl View shape : (347, 25978)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 6, max_depth : 9
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.97520661157
+ - Score on test : 0.761904761905
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.949152542373
+ - Score on test : 0.468085106383
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.949152542373
+ - Score on test : 0.468085106383
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0247933884298
+ - Score on test : 0.238095238095
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.97520661157
+ - Score on test : 0.761904761905
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.932999668908
+ - Score on test : 0.398313753408
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.965517241379
+ - Score on test : 0.785714285714
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.933333333333
+ - Score on test : 0.333333333333
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.961172161172
+ - Score on test : 0.645833333333
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0247933884298
+ - Score on test : 0.238095238095
+
+
+ Classification took 0:00:01
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095527-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log b/Code/MonoMutliViewClassifiers/Results/20160908-095527-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
new file mode 100644
index 00000000..52d4e73f
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095527-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
@@ -0,0 +1,2211 @@
+2016-09-08 09:55:28,079 DEBUG: Start: Creating 2 temporary datasets for multiprocessing
+2016-09-08 09:55:28,079 WARNING: WARNING : /!\ This may use a lot of HDD storage space : 0.00010290625 Gbytes /!\
+2016-09-08 09:55:33,093 DEBUG: Start: Creating datasets for multiprocessing
+2016-09-08 09:55:33,096 INFO: Start: Finding all available mono- & multiview algorithms
+2016-09-08 09:55:33,343 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:33,343 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:33,343 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 09:55:33,343 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 09:55:33,343 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:33,343 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:33,383 DEBUG: Info: Shape X_train:(210, 8), Length of y_train:210
+2016-09-08 09:55:33,383 DEBUG: Info: Shape X_train:(210, 8), Length of y_train:210
+2016-09-08 09:55:33,383 DEBUG: Info: Shape X_test:(90, 8), Length of y_test:90
+2016-09-08 09:55:33,384 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:33,384 DEBUG: Info: Shape X_test:(90, 8), Length of y_test:90
+2016-09-08 09:55:33,384 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:33,384 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:33,384 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:33,415 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:33,415 DEBUG: Start: Training
+2016-09-08 09:55:33,417 DEBUG: Info: Time for Training: 0.0742340087891[s]
+2016-09-08 09:55:33,417 DEBUG: Done: Training
+2016-09-08 09:55:33,417 DEBUG: Start: Predicting
+2016-09-08 09:55:33,439 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:33,440 DEBUG: Start: Training
+2016-09-08 09:55:33,445 DEBUG: Info: Time for Training: 0.102918863297[s]
+2016-09-08 09:55:33,446 DEBUG: Done: Training
+2016-09-08 09:55:33,446 DEBUG: Start: Predicting
+2016-09-08 09:55:33,583 DEBUG: Done: Predicting
+2016-09-08 09:55:33,583 DEBUG: Done: Predicting
+2016-09-08 09:55:33,584 DEBUG: Start: Getting Results
+2016-09-08 09:55:33,584 DEBUG: Start: Getting Results
+2016-09-08 09:55:34,228 DEBUG: Done: Getting Results
+2016-09-08 09:55:34,228 INFO: Classification on Fake database for View0 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.477777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 4, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.477777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.505263157895
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.505263157895
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.522222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.477777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0418655345164
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.470588235294
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.545454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.479249011858
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.522222222222
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:34,228 DEBUG: Done: Getting Results
+2016-09-08 09:55:34,228 INFO: Classification on Fake database for View0 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.484210526316
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.484210526316
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0867214643554
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.450980392157
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.522727272727
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.457015810277
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:34,228 INFO: Done: Result Analysis
+2016-09-08 09:55:34,228 INFO: Done: Result Analysis
+2016-09-08 09:55:34,286 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:34,286 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:34,287 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 09:55:34,287 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 09:55:34,287 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:34,287 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:34,287 DEBUG: Info: Shape X_train:(210, 8), Length of y_train:210
+2016-09-08 09:55:34,287 DEBUG: Info: Shape X_train:(210, 8), Length of y_train:210
+2016-09-08 09:55:34,288 DEBUG: Info: Shape X_test:(90, 8), Length of y_test:90
+2016-09-08 09:55:34,288 DEBUG: Info: Shape X_test:(90, 8), Length of y_test:90
+2016-09-08 09:55:34,288 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:34,288 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:34,288 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:34,288 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:34,320 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:34,320 DEBUG: Start: Training
+2016-09-08 09:55:34,321 DEBUG: Info: Time for Training: 0.0349078178406[s]
+2016-09-08 09:55:34,321 DEBUG: Done: Training
+2016-09-08 09:55:34,321 DEBUG: Start: Predicting
+2016-09-08 09:55:34,326 DEBUG: Done: Predicting
+2016-09-08 09:55:34,326 DEBUG: Start: Getting Results
+2016-09-08 09:55:34,371 DEBUG: Done: Getting Results
+2016-09-08 09:55:34,371 INFO: Classification on Fake database for View0 with KNN
+
+accuracy_score on train : 0.661904761905
+accuracy_score on test : 0.477777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.661904761905
+ - Score on test : 0.477777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.727969348659
+ - Score on test : 0.534653465347
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.727969348659
+ - Score on test : 0.534653465347
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.338095238095
+ - Score on test : 0.522222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.661904761905
+ - Score on test : 0.477777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.290672377783
+ - Score on test : -0.0399755963154
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.68345323741
+ - Score on test : 0.473684210526
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.77868852459
+ - Score on test : 0.613636363636
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.639344262295
+ - Score on test : 0.480731225296
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.338095238095
+ - Score on test : 0.522222222222
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:34,371 INFO: Done: Result Analysis
+2016-09-08 09:55:34,386 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:34,387 DEBUG: Start: Training
+2016-09-08 09:55:34,397 DEBUG: Info: Time for Training: 0.11102604866[s]
+2016-09-08 09:55:34,397 DEBUG: Done: Training
+2016-09-08 09:55:34,397 DEBUG: Start: Predicting
+2016-09-08 09:55:34,400 DEBUG: Done: Predicting
+2016-09-08 09:55:34,401 DEBUG: Start: Getting Results
+2016-09-08 09:55:34,429 DEBUG: Done: Getting Results
+2016-09-08 09:55:34,429 INFO: Classification on Fake database for View0 with RandomForest
+
+accuracy_score on train : 0.895238095238
+accuracy_score on test : 0.477777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 4, max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.895238095238
+ - Score on test : 0.477777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.905982905983
+ - Score on test : 0.515463917526
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.905982905983
+ - Score on test : 0.515463917526
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.104761904762
+ - Score on test : 0.522222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.895238095238
+ - Score on test : 0.477777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.791868570857
+ - Score on test : -0.0411594726194
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.946428571429
+ - Score on test : 0.471698113208
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.868852459016
+ - Score on test : 0.568181818182
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.900335320417
+ - Score on test : 0.479743083004
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.104761904762
+ - Score on test : 0.522222222222
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:34,430 INFO: Done: Result Analysis
+2016-09-08 09:55:34,537 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:34,537 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 09:55:34,537 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:34,537 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:34,538 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 09:55:34,538 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:34,538 DEBUG: Info: Shape X_train:(210, 8), Length of y_train:210
+2016-09-08 09:55:34,538 DEBUG: Info: Shape X_test:(90, 8), Length of y_test:90
+2016-09-08 09:55:34,538 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:34,538 DEBUG: Info: Shape X_train:(210, 8), Length of y_train:210
+2016-09-08 09:55:34,538 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:34,538 DEBUG: Info: Shape X_test:(90, 8), Length of y_test:90
+2016-09-08 09:55:34,538 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:34,539 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:34,668 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:34,668 DEBUG: Start: Training
+2016-09-08 09:55:34,686 DEBUG: Info: Time for Training: 0.148998022079[s]
+2016-09-08 09:55:34,686 DEBUG: Done: Training
+2016-09-08 09:55:34,686 DEBUG: Start: Predicting
+2016-09-08 09:55:34,689 DEBUG: Done: Predicting
+2016-09-08 09:55:34,689 DEBUG: Start: Getting Results
+2016-09-08 09:55:34,699 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:34,699 DEBUG: Start: Training
+2016-09-08 09:55:34,700 DEBUG: Info: Time for Training: 0.164316892624[s]
+2016-09-08 09:55:34,700 DEBUG: Done: Training
+2016-09-08 09:55:34,700 DEBUG: Start: Predicting
+2016-09-08 09:55:34,711 DEBUG: Done: Predicting
+2016-09-08 09:55:34,711 DEBUG: Start: Getting Results
+2016-09-08 09:55:34,727 DEBUG: Done: Getting Results
+2016-09-08 09:55:34,727 INFO: Classification on Fake database for View0 with SVMLinear
+
+accuracy_score on train : 0.490476190476
+accuracy_score on test : 0.377777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.490476190476
+ - Score on test : 0.377777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.563265306122
+ - Score on test : 0.416666666667
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.563265306122
+ - Score on test : 0.416666666667
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.509523809524
+ - Score on test : 0.622222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.490476190476
+ - Score on test : 0.377777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.0481411286791
+ - Score on test : -0.244017569898
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.560975609756
+ - Score on test : 0.384615384615
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.565573770492
+ - Score on test : 0.454545454545
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.475968703428
+ - Score on test : 0.379446640316
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.509523809524
+ - Score on test : 0.622222222222
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:34,727 INFO: Done: Result Analysis
+2016-09-08 09:55:34,737 DEBUG: Done: Getting Results
+2016-09-08 09:55:34,737 INFO: Classification on Fake database for View0 with SGD
+
+accuracy_score on train : 0.614285714286
+accuracy_score on test : 0.466666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.614285714286
+ - Score on test : 0.466666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.749226006192
+ - Score on test : 0.630769230769
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.749226006192
+ - Score on test : 0.630769230769
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.385714285714
+ - Score on test : 0.533333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.614285714286
+ - Score on test : 0.466666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.201498784613
+ - Score on test : -0.112653159931
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.601990049751
+ - Score on test : 0.476744186047
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.991803278689
+ - Score on test : 0.931818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.541356184799
+ - Score on test : 0.476778656126
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.385714285714
+ - Score on test : 0.533333333333
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:34,738 INFO: Done: Result Analysis
+2016-09-08 09:55:34,880 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:34,881 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:34,881 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMPoly
+2016-09-08 09:55:34,881 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMRBF
+2016-09-08 09:55:34,881 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:34,881 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:34,881 DEBUG: Info: Shape X_train:(210, 8), Length of y_train:210
+2016-09-08 09:55:34,881 DEBUG: Info: Shape X_train:(210, 8), Length of y_train:210
+2016-09-08 09:55:34,882 DEBUG: Info: Shape X_test:(90, 8), Length of y_test:90
+2016-09-08 09:55:34,882 DEBUG: Info: Shape X_test:(90, 8), Length of y_test:90
+2016-09-08 09:55:34,882 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:34,882 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:34,882 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:34,882 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:34,928 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:34,928 DEBUG: Start: Training
+2016-09-08 09:55:34,928 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:34,929 DEBUG: Start: Training
+2016-09-08 09:55:34,944 DEBUG: Info: Time for Training: 0.0635361671448[s]
+2016-09-08 09:55:34,944 DEBUG: Done: Training
+2016-09-08 09:55:34,944 DEBUG: Start: Predicting
+2016-09-08 09:55:34,945 DEBUG: Info: Time for Training: 0.0647149085999[s]
+2016-09-08 09:55:34,945 DEBUG: Done: Training
+2016-09-08 09:55:34,945 DEBUG: Start: Predicting
+2016-09-08 09:55:34,947 DEBUG: Done: Predicting
+2016-09-08 09:55:34,947 DEBUG: Start: Getting Results
+2016-09-08 09:55:34,950 DEBUG: Done: Predicting
+2016-09-08 09:55:34,950 DEBUG: Start: Getting Results
+2016-09-08 09:55:34,979 DEBUG: Done: Getting Results
+2016-09-08 09:55:34,979 INFO: Classification on Fake database for View0 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.468085106383
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.468085106383
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.109345881217
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.44
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.445652173913
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:34,980 INFO: Done: Result Analysis
+2016-09-08 09:55:34,995 DEBUG: Done: Getting Results
+2016-09-08 09:55:34,995 INFO: Classification on Fake database for View0 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.616822429907
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.616822429907
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.106710653456
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.52380952381
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.75
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.548913043478
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:34,995 INFO: Done: Result Analysis
+2016-09-08 09:55:35,123 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:35,123 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:35,123 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 09:55:35,123 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 09:55:35,123 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:35,123 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:35,124 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 09:55:35,125 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 09:55:35,125 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 09:55:35,125 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:35,125 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 09:55:35,125 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:35,125 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:35,125 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:35,163 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:35,163 DEBUG: Start: Training
+2016-09-08 09:55:35,165 DEBUG: Info: Time for Training: 0.0432438850403[s]
+2016-09-08 09:55:35,165 DEBUG: Done: Training
+2016-09-08 09:55:35,165 DEBUG: Start: Predicting
+2016-09-08 09:55:35,168 DEBUG: Done: Predicting
+2016-09-08 09:55:35,168 DEBUG: Start: Getting Results
+2016-09-08 09:55:35,177 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:35,177 DEBUG: Start: Training
+2016-09-08 09:55:35,181 DEBUG: Info: Time for Training: 0.0592088699341[s]
+2016-09-08 09:55:35,181 DEBUG: Done: Training
+2016-09-08 09:55:35,181 DEBUG: Start: Predicting
+2016-09-08 09:55:35,184 DEBUG: Done: Predicting
+2016-09-08 09:55:35,184 DEBUG: Start: Getting Results
+2016-09-08 09:55:35,215 DEBUG: Done: Getting Results
+2016-09-08 09:55:35,215 INFO: Classification on Fake database for View1 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.422222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.48
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.48
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.154858431981
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.428571428571
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.545454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.424901185771
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:35,216 INFO: Done: Result Analysis
+2016-09-08 09:55:35,220 DEBUG: Done: Getting Results
+2016-09-08 09:55:35,220 INFO: Classification on Fake database for View1 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.422222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 4, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.48
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.48
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.154858431981
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.428571428571
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.545454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.424901185771
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:35,220 INFO: Done: Result Analysis
+2016-09-08 09:55:35,370 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:35,370 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 09:55:35,370 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:35,370 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:35,370 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 09:55:35,370 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:35,371 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 09:55:35,371 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 09:55:35,371 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 09:55:35,371 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:35,371 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 09:55:35,371 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:35,371 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:35,371 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:35,402 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:35,403 DEBUG: Start: Training
+2016-09-08 09:55:35,403 DEBUG: Info: Time for Training: 0.0339629650116[s]
+2016-09-08 09:55:35,403 DEBUG: Done: Training
+2016-09-08 09:55:35,403 DEBUG: Start: Predicting
+2016-09-08 09:55:35,409 DEBUG: Done: Predicting
+2016-09-08 09:55:35,409 DEBUG: Start: Getting Results
+2016-09-08 09:55:35,450 DEBUG: Done: Getting Results
+2016-09-08 09:55:35,450 INFO: Classification on Fake database for View1 with KNN
+
+accuracy_score on train : 0.571428571429
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.571428571429
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.6484375
+ - Score on test : 0.541666666667
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.6484375
+ - Score on test : 0.541666666667
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.428571428571
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.571428571429
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.103477711187
+ - Score on test : 0.0260018722022
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.619402985075
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.680327868852
+ - Score on test : 0.590909090909
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.550391207154
+ - Score on test : 0.512845849802
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.428571428571
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:35,450 INFO: Done: Result Analysis
+2016-09-08 09:55:35,480 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:35,481 DEBUG: Start: Training
+2016-09-08 09:55:35,491 DEBUG: Info: Time for Training: 0.121489048004[s]
+2016-09-08 09:55:35,491 DEBUG: Done: Training
+2016-09-08 09:55:35,491 DEBUG: Start: Predicting
+2016-09-08 09:55:35,495 DEBUG: Done: Predicting
+2016-09-08 09:55:35,495 DEBUG: Start: Getting Results
+2016-09-08 09:55:35,527 DEBUG: Done: Getting Results
+2016-09-08 09:55:35,527 INFO: Classification on Fake database for View1 with RandomForest
+
+accuracy_score on train : 0.9
+accuracy_score on test : 0.477777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 4, max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.9
+ - Score on test : 0.477777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.909090909091
+ - Score on test : 0.356164383562
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.909090909091
+ - Score on test : 0.356164383562
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.1
+ - Score on test : 0.522222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.9
+ - Score on test : 0.477777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.805030105216
+ - Score on test : -0.0560191732057
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.963302752294
+ - Score on test : 0.448275862069
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.860655737705
+ - Score on test : 0.295454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.907600596125
+ - Score on test : 0.473814229249
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.1
+ - Score on test : 0.522222222222
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:35,528 INFO: Done: Result Analysis
+2016-09-08 09:55:35,610 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:35,610 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:35,610 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 09:55:35,610 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 09:55:35,610 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:35,610 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:35,611 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 09:55:35,611 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 09:55:35,611 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 09:55:35,611 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 09:55:35,611 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:35,611 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:35,611 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:35,611 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:35,656 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:35,656 DEBUG: Start: Training
+2016-09-08 09:55:35,657 DEBUG: Info: Time for Training: 0.0472548007965[s]
+2016-09-08 09:55:35,657 DEBUG: Done: Training
+2016-09-08 09:55:35,657 DEBUG: Start: Predicting
+2016-09-08 09:55:35,660 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:35,661 DEBUG: Start: Training
+2016-09-08 09:55:35,680 DEBUG: Done: Predicting
+2016-09-08 09:55:35,680 DEBUG: Start: Getting Results
+2016-09-08 09:55:35,681 DEBUG: Info: Time for Training: 0.0712029933929[s]
+2016-09-08 09:55:35,681 DEBUG: Done: Training
+2016-09-08 09:55:35,681 DEBUG: Start: Predicting
+2016-09-08 09:55:35,684 DEBUG: Done: Predicting
+2016-09-08 09:55:35,684 DEBUG: Start: Getting Results
+2016-09-08 09:55:35,704 DEBUG: Done: Getting Results
+2016-09-08 09:55:35,704 INFO: Classification on Fake database for View1 with SGD
+
+accuracy_score on train : 0.609523809524
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.609523809524
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.745341614907
+ - Score on test : 0.661417322835
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.745341614907
+ - Score on test : 0.661417322835
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.390476190476
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.609523809524
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.172644893682
+ - Score on test : 0.118036588599
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.506024096386
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.983606557377
+ - Score on test : 0.954545454545
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.537257824143
+ - Score on test : 0.53162055336
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.390476190476
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:35,704 INFO: Done: Result Analysis
+2016-09-08 09:55:35,714 DEBUG: Done: Getting Results
+2016-09-08 09:55:35,715 INFO: Classification on Fake database for View1 with SVMLinear
+
+accuracy_score on train : 0.542857142857
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.542857142857
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.606557377049
+ - Score on test : 0.584905660377
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.606557377049
+ - Score on test : 0.584905660377
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.457142857143
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.542857142857
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0611028315946
+ - Score on test : 0.0330758927464
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.606557377049
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.606557377049
+ - Score on test : 0.704545454545
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.530551415797
+ - Score on test : 0.515316205534
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.457142857143
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:35,715 INFO: Done: Result Analysis
+2016-09-08 09:55:35,860 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:35,860 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:35,860 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMRBF
+2016-09-08 09:55:35,860 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMPoly
+2016-09-08 09:55:35,860 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:35,860 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:35,861 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 09:55:35,861 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 09:55:35,861 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 09:55:35,861 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 09:55:35,861 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:35,861 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:35,861 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:35,861 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:35,908 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:35,908 DEBUG: Start: Training
+2016-09-08 09:55:35,910 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:35,910 DEBUG: Start: Training
+2016-09-08 09:55:35,925 DEBUG: Info: Time for Training: 0.0658419132233[s]
+2016-09-08 09:55:35,925 DEBUG: Done: Training
+2016-09-08 09:55:35,925 DEBUG: Start: Predicting
+2016-09-08 09:55:35,926 DEBUG: Info: Time for Training: 0.06693816185[s]
+2016-09-08 09:55:35,926 DEBUG: Done: Training
+2016-09-08 09:55:35,926 DEBUG: Start: Predicting
+2016-09-08 09:55:35,929 DEBUG: Done: Predicting
+2016-09-08 09:55:35,929 DEBUG: Start: Getting Results
+2016-09-08 09:55:35,932 DEBUG: Done: Predicting
+2016-09-08 09:55:35,932 DEBUG: Start: Getting Results
+2016-09-08 09:55:35,962 DEBUG: Done: Getting Results
+2016-09-08 09:55:35,962 INFO: Classification on Fake database for View1 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.358208955224
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.358208955224
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0385036888617
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.521739130435
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.272727272727
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.516798418972
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:35,962 INFO: Done: Result Analysis
+2016-09-08 09:55:35,967 DEBUG: Done: Getting Results
+2016-09-08 09:55:35,967 INFO: Classification on Fake database for View1 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.645161290323
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.645161290323
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0628694613462
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.909090909091
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.51976284585
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:35,967 INFO: Done: Result Analysis
+2016-09-08 09:55:36,109 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:36,109 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 09:55:36,110 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:36,110 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:36,110 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 09:55:36,111 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:36,111 DEBUG: Info: Shape X_train:(210, 7), Length of y_train:210
+2016-09-08 09:55:36,111 DEBUG: Info: Shape X_test:(90, 7), Length of y_test:90
+2016-09-08 09:55:36,111 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:36,111 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:36,112 DEBUG: Info: Shape X_train:(210, 7), Length of y_train:210
+2016-09-08 09:55:36,112 DEBUG: Info: Shape X_test:(90, 7), Length of y_test:90
+2016-09-08 09:55:36,112 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:36,112 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:36,145 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:36,145 DEBUG: Start: Training
+2016-09-08 09:55:36,146 DEBUG: Info: Time for Training: 0.0371689796448[s]
+2016-09-08 09:55:36,146 DEBUG: Done: Training
+2016-09-08 09:55:36,146 DEBUG: Start: Predicting
+2016-09-08 09:55:36,149 DEBUG: Done: Predicting
+2016-09-08 09:55:36,149 DEBUG: Start: Getting Results
+2016-09-08 09:55:36,159 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:36,159 DEBUG: Start: Training
+2016-09-08 09:55:36,163 DEBUG: Info: Time for Training: 0.0549581050873[s]
+2016-09-08 09:55:36,163 DEBUG: Done: Training
+2016-09-08 09:55:36,163 DEBUG: Start: Predicting
+2016-09-08 09:55:36,166 DEBUG: Done: Predicting
+2016-09-08 09:55:36,166 DEBUG: Start: Getting Results
+2016-09-08 09:55:36,197 DEBUG: Done: Getting Results
+2016-09-08 09:55:36,197 INFO: Classification on Fake database for View2 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.466666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.441860465116
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.441860465116
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.533333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.068316965625
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.452380952381
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.431818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.465909090909
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.533333333333
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:36,197 INFO: Done: Result Analysis
+2016-09-08 09:55:36,208 DEBUG: Done: Getting Results
+2016-09-08 09:55:36,208 INFO: Classification on Fake database for View2 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 4, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.436781609195
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.436781609195
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0899876638096
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.441860465116
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.431818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455039525692
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:36,209 INFO: Done: Result Analysis
+2016-09-08 09:55:36,356 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:36,356 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 09:55:36,356 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:36,356 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:36,357 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 09:55:36,357 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:36,357 DEBUG: Info: Shape X_train:(210, 7), Length of y_train:210
+2016-09-08 09:55:36,357 DEBUG: Info: Shape X_test:(90, 7), Length of y_test:90
+2016-09-08 09:55:36,357 DEBUG: Info: Shape X_train:(210, 7), Length of y_train:210
+2016-09-08 09:55:36,358 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:36,358 DEBUG: Info: Shape X_test:(90, 7), Length of y_test:90
+2016-09-08 09:55:36,358 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:36,358 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:36,358 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:36,387 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:36,388 DEBUG: Start: Training
+2016-09-08 09:55:36,388 DEBUG: Info: Time for Training: 0.0327939987183[s]
+2016-09-08 09:55:36,388 DEBUG: Done: Training
+2016-09-08 09:55:36,388 DEBUG: Start: Predicting
+2016-09-08 09:55:36,394 DEBUG: Done: Predicting
+2016-09-08 09:55:36,394 DEBUG: Start: Getting Results
+2016-09-08 09:55:36,437 DEBUG: Done: Getting Results
+2016-09-08 09:55:36,437 INFO: Classification on Fake database for View2 with KNN
+
+accuracy_score on train : 0.619047619048
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.619047619048
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.705882352941
+ - Score on test : 0.619469026549
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.705882352941
+ - Score on test : 0.619469026549
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.380952380952
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.619047619048
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.189221481343
+ - Score on test : 0.0665679839847
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.64
+ - Score on test : 0.507246376812
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.786885245902
+ - Score on test : 0.795454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.586624441133
+ - Score on test : 0.528162055336
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.380952380952
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:36,437 INFO: Done: Result Analysis
+2016-09-08 09:55:36,463 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:36,463 DEBUG: Start: Training
+2016-09-08 09:55:36,473 DEBUG: Info: Time for Training: 0.11700296402[s]
+2016-09-08 09:55:36,473 DEBUG: Done: Training
+2016-09-08 09:55:36,473 DEBUG: Start: Predicting
+2016-09-08 09:55:36,477 DEBUG: Done: Predicting
+2016-09-08 09:55:36,477 DEBUG: Start: Getting Results
+2016-09-08 09:55:36,509 DEBUG: Done: Getting Results
+2016-09-08 09:55:36,509 INFO: Classification on Fake database for View2 with RandomForest
+
+accuracy_score on train : 0.890476190476
+accuracy_score on test : 0.4
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 4, max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.890476190476
+ - Score on test : 0.4
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.904564315353
+ - Score on test : 0.357142857143
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.904564315353
+ - Score on test : 0.357142857143
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.109523809524
+ - Score on test : 0.6
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.890476190476
+ - Score on test : 0.4
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.77645053118
+ - Score on test : -0.20378096045
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.915966386555
+ - Score on test : 0.375
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.893442622951
+ - Score on test : 0.340909090909
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.889903129657
+ - Score on test : 0.39871541502
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.109523809524
+ - Score on test : 0.6
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:36,509 INFO: Done: Result Analysis
+2016-09-08 09:55:36,597 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:36,597 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 09:55:36,597 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:36,597 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:36,598 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 09:55:36,598 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:36,598 DEBUG: Info: Shape X_train:(210, 7), Length of y_train:210
+2016-09-08 09:55:36,598 DEBUG: Info: Shape X_test:(90, 7), Length of y_test:90
+2016-09-08 09:55:36,598 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:36,598 DEBUG: Info: Shape X_train:(210, 7), Length of y_train:210
+2016-09-08 09:55:36,598 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:36,598 DEBUG: Info: Shape X_test:(90, 7), Length of y_test:90
+2016-09-08 09:55:36,599 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:36,599 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:36,645 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:36,645 DEBUG: Start: Training
+2016-09-08 09:55:36,646 DEBUG: Info: Time for Training: 0.0489931106567[s]
+2016-09-08 09:55:36,646 DEBUG: Done: Training
+2016-09-08 09:55:36,646 DEBUG: Start: Predicting
+2016-09-08 09:55:36,651 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:36,651 DEBUG: Start: Training
+2016-09-08 09:55:36,658 DEBUG: Done: Predicting
+2016-09-08 09:55:36,658 DEBUG: Start: Getting Results
+2016-09-08 09:55:36,670 DEBUG: Info: Time for Training: 0.0731010437012[s]
+2016-09-08 09:55:36,670 DEBUG: Done: Training
+2016-09-08 09:55:36,670 DEBUG: Start: Predicting
+2016-09-08 09:55:36,674 DEBUG: Done: Predicting
+2016-09-08 09:55:36,674 DEBUG: Start: Getting Results
+2016-09-08 09:55:36,682 DEBUG: Done: Getting Results
+2016-09-08 09:55:36,683 INFO: Classification on Fake database for View2 with SGD
+
+accuracy_score on train : 0.590476190476
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.715231788079
+ - Score on test : 0.676923076923
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.715231788079
+ - Score on test : 0.676923076923
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0945615027077
+ - Score on test : 0.210925065403
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.511627906977
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.885245901639
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.533532041729
+ - Score on test : 0.54347826087
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:36,683 INFO: Done: Result Analysis
+2016-09-08 09:55:36,702 DEBUG: Done: Getting Results
+2016-09-08 09:55:36,703 INFO: Classification on Fake database for View2 with SVMLinear
+
+accuracy_score on train : 0.533333333333
+accuracy_score on test : 0.433333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.433333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.604838709677
+ - Score on test : 0.484848484848
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.604838709677
+ - Score on test : 0.484848484848
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.566666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.433333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0354605635154
+ - Score on test : -0.131720304791
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.595238095238
+ - Score on test : 0.436363636364
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.614754098361
+ - Score on test : 0.545454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.517604321908
+ - Score on test : 0.435770750988
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.566666666667
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:36,703 INFO: Done: Result Analysis
+2016-09-08 09:55:36,843 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:36,843 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMPoly
+2016-09-08 09:55:36,843 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:36,843 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:36,843 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMRBF
+2016-09-08 09:55:36,843 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:36,843 DEBUG: Info: Shape X_train:(210, 7), Length of y_train:210
+2016-09-08 09:55:36,844 DEBUG: Info: Shape X_train:(210, 7), Length of y_train:210
+2016-09-08 09:55:36,844 DEBUG: Info: Shape X_test:(90, 7), Length of y_test:90
+2016-09-08 09:55:36,844 DEBUG: Info: Shape X_test:(90, 7), Length of y_test:90
+2016-09-08 09:55:36,844 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:36,844 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:36,844 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:36,844 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:36,891 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:36,891 DEBUG: Start: Training
+2016-09-08 09:55:36,892 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:36,892 DEBUG: Start: Training
+2016-09-08 09:55:36,907 DEBUG: Info: Time for Training: 0.0647799968719[s]
+2016-09-08 09:55:36,907 DEBUG: Done: Training
+2016-09-08 09:55:36,907 DEBUG: Start: Predicting
+2016-09-08 09:55:36,908 DEBUG: Info: Time for Training: 0.0657360553741[s]
+2016-09-08 09:55:36,908 DEBUG: Done: Training
+2016-09-08 09:55:36,908 DEBUG: Start: Predicting
+2016-09-08 09:55:36,910 DEBUG: Done: Predicting
+2016-09-08 09:55:36,910 DEBUG: Start: Getting Results
+2016-09-08 09:55:36,913 DEBUG: Done: Predicting
+2016-09-08 09:55:36,913 DEBUG: Start: Getting Results
+2016-09-08 09:55:36,946 DEBUG: Done: Getting Results
+2016-09-08 09:55:36,946 INFO: Classification on Fake database for View2 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.4
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.357142857143
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.357142857143
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.6
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.20378096045
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.375
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.340909090909
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.39871541502
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.6
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:36,946 INFO: Done: Result Analysis
+2016-09-08 09:55:36,952 DEBUG: Done: Getting Results
+2016-09-08 09:55:36,952 INFO: Classification on Fake database for View2 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.466666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.538461538462
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.538461538462
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.533333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0628694613462
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.636363636364
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.470355731225
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.533333333333
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:36,952 INFO: Done: Result Analysis
+2016-09-08 09:55:37,093 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:37,093 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:37,093 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 09:55:37,093 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:37,093 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 09:55:37,093 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:37,093 DEBUG: Info: Shape X_train:(210, 6), Length of y_train:210
+2016-09-08 09:55:37,093 DEBUG: Info: Shape X_train:(210, 6), Length of y_train:210
+2016-09-08 09:55:37,094 DEBUG: Info: Shape X_test:(90, 6), Length of y_test:90
+2016-09-08 09:55:37,094 DEBUG: Info: Shape X_test:(90, 6), Length of y_test:90
+2016-09-08 09:55:37,094 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:37,094 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:37,094 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:37,094 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:37,124 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:37,124 DEBUG: Start: Training
+2016-09-08 09:55:37,125 DEBUG: Info: Time for Training: 0.0331890583038[s]
+2016-09-08 09:55:37,126 DEBUG: Done: Training
+2016-09-08 09:55:37,126 DEBUG: Start: Predicting
+2016-09-08 09:55:37,128 DEBUG: Done: Predicting
+2016-09-08 09:55:37,128 DEBUG: Start: Getting Results
+2016-09-08 09:55:37,139 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:37,139 DEBUG: Start: Training
+2016-09-08 09:55:37,142 DEBUG: Info: Time for Training: 0.0498540401459[s]
+2016-09-08 09:55:37,142 DEBUG: Done: Training
+2016-09-08 09:55:37,142 DEBUG: Start: Predicting
+2016-09-08 09:55:37,145 DEBUG: Done: Predicting
+2016-09-08 09:55:37,145 DEBUG: Start: Getting Results
+2016-09-08 09:55:37,172 DEBUG: Done: Getting Results
+2016-09-08 09:55:37,172 INFO: Classification on Fake database for View3 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588235294118
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588235294118
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0763602735229
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.51724137931
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.681818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.536561264822
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:37,173 INFO: Done: Result Analysis
+2016-09-08 09:55:37,183 DEBUG: Done: Getting Results
+2016-09-08 09:55:37,184 INFO: Classification on Fake database for View3 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 4, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.576923076923
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.576923076923
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0314347306731
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.681818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.514822134387
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:37,184 INFO: Done: Result Analysis
+2016-09-08 09:55:37,335 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:37,335 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:37,335 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 09:55:37,335 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 09:55:37,335 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:37,335 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:37,336 DEBUG: Info: Shape X_train:(210, 6), Length of y_train:210
+2016-09-08 09:55:37,336 DEBUG: Info: Shape X_train:(210, 6), Length of y_train:210
+2016-09-08 09:55:37,336 DEBUG: Info: Shape X_test:(90, 6), Length of y_test:90
+2016-09-08 09:55:37,336 DEBUG: Info: Shape X_test:(90, 6), Length of y_test:90
+2016-09-08 09:55:37,336 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:37,336 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:37,336 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:37,336 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:37,365 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:37,365 DEBUG: Start: Training
+2016-09-08 09:55:37,365 DEBUG: Info: Time for Training: 0.0312879085541[s]
+2016-09-08 09:55:37,365 DEBUG: Done: Training
+2016-09-08 09:55:37,366 DEBUG: Start: Predicting
+2016-09-08 09:55:37,370 DEBUG: Done: Predicting
+2016-09-08 09:55:37,371 DEBUG: Start: Getting Results
+2016-09-08 09:55:37,421 DEBUG: Done: Getting Results
+2016-09-08 09:55:37,422 INFO: Classification on Fake database for View3 with KNN
+
+accuracy_score on train : 0.590476190476
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.681481481481
+ - Score on test : 0.601941747573
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.681481481481
+ - Score on test : 0.601941747573
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.127350050081
+ - Score on test : 0.100829966549
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.621621621622
+ - Score on test : 0.525423728814
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.754098360656
+ - Score on test : 0.704545454545
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.558867362146
+ - Score on test : 0.547924901186
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:37,422 INFO: Done: Result Analysis
+2016-09-08 09:55:37,439 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:37,439 DEBUG: Start: Training
+2016-09-08 09:55:37,449 DEBUG: Info: Time for Training: 0.114704847336[s]
+2016-09-08 09:55:37,449 DEBUG: Done: Training
+2016-09-08 09:55:37,449 DEBUG: Start: Predicting
+2016-09-08 09:55:37,452 DEBUG: Done: Predicting
+2016-09-08 09:55:37,453 DEBUG: Start: Getting Results
+2016-09-08 09:55:37,485 DEBUG: Done: Getting Results
+2016-09-08 09:55:37,485 INFO: Classification on Fake database for View3 with RandomForest
+
+accuracy_score on train : 0.9
+accuracy_score on test : 0.577777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 4, max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.9
+ - Score on test : 0.577777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.910638297872
+ - Score on test : 0.586956521739
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.910638297872
+ - Score on test : 0.586956521739
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.1
+ - Score on test : 0.422222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.9
+ - Score on test : 0.577777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.800522373751
+ - Score on test : 0.157426051223
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.946902654867
+ - Score on test : 0.5625
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.877049180328
+ - Score on test : 0.613636363636
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.904433681073
+ - Score on test : 0.578557312253
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.1
+ - Score on test : 0.422222222222
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:37,486 INFO: Done: Result Analysis
+2016-09-08 09:55:37,579 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:37,579 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 09:55:37,579 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:55:37,579 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:37,579 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 09:55:37,579 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:55:37,579 DEBUG: Info: Shape X_train:(210, 6), Length of y_train:210
+2016-09-08 09:55:37,580 DEBUG: Info: Shape X_test:(90, 6), Length of y_test:90
+2016-09-08 09:55:37,580 DEBUG: Info: Shape X_train:(210, 6), Length of y_train:210
+2016-09-08 09:55:37,580 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:37,580 DEBUG: Info: Shape X_test:(90, 6), Length of y_test:90
+2016-09-08 09:55:37,580 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:55:37,580 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:37,580 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:55:37,625 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:37,625 DEBUG: Start: Training
+2016-09-08 09:55:37,626 DEBUG: Info: Time for Training: 0.0474660396576[s]
+2016-09-08 09:55:37,626 DEBUG: Done: Training
+2016-09-08 09:55:37,626 DEBUG: Start: Predicting
+2016-09-08 09:55:37,627 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:55:37,627 DEBUG: Start: Training
+2016-09-08 09:55:37,643 DEBUG: Info: Time for Training: 0.0650768280029[s]
+2016-09-08 09:55:37,644 DEBUG: Done: Training
+2016-09-08 09:55:37,644 DEBUG: Start: Predicting
+2016-09-08 09:55:37,647 DEBUG: Done: Predicting
+2016-09-08 09:55:37,647 DEBUG: Start: Getting Results
+2016-09-08 09:55:37,652 DEBUG: Done: Predicting
+2016-09-08 09:55:37,652 DEBUG: Start: Getting Results
+2016-09-08 09:55:37,675 DEBUG: Done: Getting Results
+2016-09-08 09:55:37,675 INFO: Classification on Fake database for View3 with SGD
+
+accuracy_score on train : 0.590476190476
+accuracy_score on test : 0.488888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.488888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.739393939394
+ - Score on test : 0.65671641791
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.739393939394
+ - Score on test : 0.65671641791
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.511111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.488888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.115457436228
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.586538461538
+ - Score on test : 0.488888888889
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.511363636364
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.511111111111
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:37,675 INFO: Done: Result Analysis
+2016-09-08 09:55:37,686 DEBUG: Done: Getting Results
+2016-09-08 09:55:37,686 INFO: Classification on Fake database for View3 with SVMLinear
+
+accuracy_score on train : 0.495238095238
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.495238095238
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.595419847328
+ - Score on test : 0.550458715596
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.595419847328
+ - Score on test : 0.550458715596
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.504761904762
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.495238095238
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.0682438863041
+ - Score on test : -0.0882242643891
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.557142857143
+ - Score on test : 0.461538461538
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.639344262295
+ - Score on test : 0.681818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.467399403875
+ - Score on test : 0.4604743083
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.504761904762
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 09:55:37,686 INFO: Done: Result Analysis
+2016-09-08 09:55:37,978 INFO: ### Main Programm for Multiview Classification
+2016-09-08 09:55:37,979 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Mumbo ; Cores : 1
+2016-09-08 09:55:37,980 INFO: Info: Shape of View0 :(300, 8)
+2016-09-08 09:55:37,981 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 09:55:37,982 INFO: Info: Shape of View2 :(300, 7)
+2016-09-08 09:55:37,983 INFO: Info: Shape of View3 :(300, 6)
+2016-09-08 09:55:37,983 INFO: Done: Read Database Files
+2016-09-08 09:55:37,983 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 09:55:37,987 INFO: ### Main Programm for Multiview Classification
+2016-09-08 09:55:37,987 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 09:55:37,987 INFO: Done: Determine validation split
+2016-09-08 09:55:37,987 INFO: Start: Determine 5 folds
+2016-09-08 09:55:37,988 INFO: Info: Shape of View0 :(300, 8)
+2016-09-08 09:55:37,988 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 09:55:37,989 INFO: Info: Shape of View2 :(300, 7)
+2016-09-08 09:55:37,989 INFO: Info: Shape of View3 :(300, 6)
+2016-09-08 09:55:37,989 INFO: Done: Read Database Files
+2016-09-08 09:55:37,989 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 09:55:37,993 INFO: Done: Determine validation split
+2016-09-08 09:55:37,993 INFO: Start: Determine 5 folds
+2016-09-08 09:55:37,995 INFO: Info: Length of Learning Sets: 170
+2016-09-08 09:55:37,995 INFO: Info: Length of Testing Sets: 41
+2016-09-08 09:55:37,995 INFO: Info: Length of Validation Set: 89
+2016-09-08 09:55:37,995 INFO: Done: Determine folds
+2016-09-08 09:55:37,995 INFO: Start: Learning with Mumbo and 5 folds
+2016-09-08 09:55:37,996 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 09:55:37,996 DEBUG: Start: Random search for DecisionTree on View0
+2016-09-08 09:55:37,999 INFO: Info: Length of Learning Sets: 170
+2016-09-08 09:55:38,000 INFO: Info: Length of Testing Sets: 41
+2016-09-08 09:55:38,000 INFO: Info: Length of Validation Set: 89
+2016-09-08 09:55:38,000 INFO: Done: Determine folds
+2016-09-08 09:55:38,000 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 09:55:38,000 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 09:55:38,000 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:55:38,054 DEBUG: Done: Random search for SGD
+2016-09-08 09:55:38,054 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:55:38,107 DEBUG: Done: Random search for SGD
+2016-09-08 09:55:38,107 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:55:38,157 DEBUG: Done: Random search for SGD
+2016-09-08 09:55:38,157 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:55:38,212 DEBUG: Done: Random search for SGD
+2016-09-08 09:55:38,284 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 09:55:38,284 INFO: Start: Classification
+2016-09-08 09:55:38,284 INFO: Start: Fold number 1
+2016-09-08 09:55:38,311 INFO: Start: Classification
+2016-09-08 09:55:38,336 INFO: Done: Fold number 1
+2016-09-08 09:55:38,337 INFO: Start: Fold number 2
+2016-09-08 09:55:38,363 INFO: Start: Classification
+2016-09-08 09:55:38,389 INFO: Done: Fold number 2
+2016-09-08 09:55:38,389 INFO: Start: Fold number 3
+2016-09-08 09:55:38,416 INFO: Start: Classification
+2016-09-08 09:55:38,443 INFO: Done: Fold number 3
+2016-09-08 09:55:38,443 INFO: Start: Fold number 4
+2016-09-08 09:55:38,470 INFO: Start: Classification
+2016-09-08 09:55:38,496 INFO: Done: Fold number 4
+2016-09-08 09:55:38,496 INFO: Start: Fold number 5
+2016-09-08 09:55:38,523 INFO: Start: Classification
+2016-09-08 09:55:38,549 INFO: Done: Fold number 5
+2016-09-08 09:55:38,549 INFO: Done: Classification
+2016-09-08 09:55:38,549 INFO: Info: Time for Classification: 0[s]
+2016-09-08 09:55:38,550 INFO: Start: Result Analysis for Fusion
+2016-09-08 09:55:38,681 INFO: Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 57.1764705882
+ -On Test : 52.6829268293
+ -On Validation : 52.1348314607
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Bayesian Inference using a weight for each view : 0.322967175445, 0.0184701333132, 0.322597810111, 0.335964881131
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : modified_huber, penalty : elasticnet
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 09:55:38,682 INFO: Done: Result Analysis
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..0d0cf3ff
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View0 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.477777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 4, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.477777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.505263157895
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.505263157895
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.522222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.477777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0418655345164
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.470588235294
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.545454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.479249011858
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.522222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..9f126a9e
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.484210526316
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.484210526316
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0867214643554
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.450980392157
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.522727272727
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.457015810277
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..79be41be
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with KNN
+
+accuracy_score on train : 0.661904761905
+accuracy_score on test : 0.477777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.661904761905
+ - Score on test : 0.477777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.727969348659
+ - Score on test : 0.534653465347
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.727969348659
+ - Score on test : 0.534653465347
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.338095238095
+ - Score on test : 0.522222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.661904761905
+ - Score on test : 0.477777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.290672377783
+ - Score on test : -0.0399755963154
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.68345323741
+ - Score on test : 0.473684210526
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.77868852459
+ - Score on test : 0.613636363636
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.639344262295
+ - Score on test : 0.480731225296
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.338095238095
+ - Score on test : 0.522222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..bbd62487
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with RandomForest
+
+accuracy_score on train : 0.895238095238
+accuracy_score on test : 0.477777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 4, max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.895238095238
+ - Score on test : 0.477777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.905982905983
+ - Score on test : 0.515463917526
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.905982905983
+ - Score on test : 0.515463917526
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.104761904762
+ - Score on test : 0.522222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.895238095238
+ - Score on test : 0.477777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.791868570857
+ - Score on test : -0.0411594726194
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.946428571429
+ - Score on test : 0.471698113208
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.868852459016
+ - Score on test : 0.568181818182
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.900335320417
+ - Score on test : 0.479743083004
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.104761904762
+ - Score on test : 0.522222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..fd413a5d
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SGD
+
+accuracy_score on train : 0.614285714286
+accuracy_score on test : 0.466666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.614285714286
+ - Score on test : 0.466666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.749226006192
+ - Score on test : 0.630769230769
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.749226006192
+ - Score on test : 0.630769230769
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.385714285714
+ - Score on test : 0.533333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.614285714286
+ - Score on test : 0.466666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.201498784613
+ - Score on test : -0.112653159931
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.601990049751
+ - Score on test : 0.476744186047
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.991803278689
+ - Score on test : 0.931818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.541356184799
+ - Score on test : 0.476778656126
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.385714285714
+ - Score on test : 0.533333333333
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..7b2f009c
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SVMLinear
+
+accuracy_score on train : 0.490476190476
+accuracy_score on test : 0.377777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.490476190476
+ - Score on test : 0.377777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.563265306122
+ - Score on test : 0.416666666667
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.563265306122
+ - Score on test : 0.416666666667
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.509523809524
+ - Score on test : 0.622222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.490476190476
+ - Score on test : 0.377777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.0481411286791
+ - Score on test : -0.244017569898
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.560975609756
+ - Score on test : 0.384615384615
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.565573770492
+ - Score on test : 0.454545454545
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.475968703428
+ - Score on test : 0.379446640316
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.509523809524
+ - Score on test : 0.622222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..db536ff6
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.468085106383
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.468085106383
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.109345881217
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.44
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.445652173913
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..4251899b
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095534Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 8)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.616822429907
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.616822429907
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.106710653456
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.52380952381
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.75
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.548913043478
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..a32b018a
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View1 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.422222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 4, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.48
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.48
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.154858431981
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.428571428571
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.545454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.424901185771
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..b096d574
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.422222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.48
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.48
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.154858431981
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.428571428571
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.545454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.424901185771
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..376343e6
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with KNN
+
+accuracy_score on train : 0.571428571429
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.571428571429
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.6484375
+ - Score on test : 0.541666666667
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.6484375
+ - Score on test : 0.541666666667
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.428571428571
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.571428571429
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.103477711187
+ - Score on test : 0.0260018722022
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.619402985075
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.680327868852
+ - Score on test : 0.590909090909
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.550391207154
+ - Score on test : 0.512845849802
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.428571428571
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..c3e2e299
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with RandomForest
+
+accuracy_score on train : 0.9
+accuracy_score on test : 0.477777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 4, max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.9
+ - Score on test : 0.477777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.909090909091
+ - Score on test : 0.356164383562
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.909090909091
+ - Score on test : 0.356164383562
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.1
+ - Score on test : 0.522222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.9
+ - Score on test : 0.477777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.805030105216
+ - Score on test : -0.0560191732057
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.963302752294
+ - Score on test : 0.448275862069
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.860655737705
+ - Score on test : 0.295454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.907600596125
+ - Score on test : 0.473814229249
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.1
+ - Score on test : 0.522222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..1bd711b4
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SGD
+
+accuracy_score on train : 0.609523809524
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.609523809524
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.745341614907
+ - Score on test : 0.661417322835
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.745341614907
+ - Score on test : 0.661417322835
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.390476190476
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.609523809524
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.172644893682
+ - Score on test : 0.118036588599
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.506024096386
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.983606557377
+ - Score on test : 0.954545454545
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.537257824143
+ - Score on test : 0.53162055336
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.390476190476
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..6b6c9c97
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SVMLinear
+
+accuracy_score on train : 0.542857142857
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.542857142857
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.606557377049
+ - Score on test : 0.584905660377
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.606557377049
+ - Score on test : 0.584905660377
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.457142857143
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.542857142857
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0611028315946
+ - Score on test : 0.0330758927464
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.606557377049
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.606557377049
+ - Score on test : 0.704545454545
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.530551415797
+ - Score on test : 0.515316205534
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.457142857143
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..5bc5811d
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.358208955224
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.358208955224
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0385036888617
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.521739130435
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.272727272727
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.516798418972
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..ccd0f1ad
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095535Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.645161290323
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.645161290323
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0628694613462
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.909090909091
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.51976284585
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..9deb12f3
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View2 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 4, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.436781609195
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.436781609195
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0899876638096
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.441860465116
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.431818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455039525692
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..183d0919
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.466666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.441860465116
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.441860465116
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.533333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.068316965625
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.452380952381
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.431818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.465909090909
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.533333333333
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..8cf553cc
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with KNN
+
+accuracy_score on train : 0.619047619048
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.619047619048
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.705882352941
+ - Score on test : 0.619469026549
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.705882352941
+ - Score on test : 0.619469026549
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.380952380952
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.619047619048
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.189221481343
+ - Score on test : 0.0665679839847
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.64
+ - Score on test : 0.507246376812
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.786885245902
+ - Score on test : 0.795454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.586624441133
+ - Score on test : 0.528162055336
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.380952380952
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..f74150b1
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with RandomForest
+
+accuracy_score on train : 0.890476190476
+accuracy_score on test : 0.4
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 4, max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.890476190476
+ - Score on test : 0.4
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.904564315353
+ - Score on test : 0.357142857143
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.904564315353
+ - Score on test : 0.357142857143
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.109523809524
+ - Score on test : 0.6
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.890476190476
+ - Score on test : 0.4
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.77645053118
+ - Score on test : -0.20378096045
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.915966386555
+ - Score on test : 0.375
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.893442622951
+ - Score on test : 0.340909090909
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.889903129657
+ - Score on test : 0.39871541502
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.109523809524
+ - Score on test : 0.6
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..608729cd
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SGD
+
+accuracy_score on train : 0.590476190476
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.715231788079
+ - Score on test : 0.676923076923
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.715231788079
+ - Score on test : 0.676923076923
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0945615027077
+ - Score on test : 0.210925065403
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.511627906977
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.885245901639
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.533532041729
+ - Score on test : 0.54347826087
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..59671aee
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SVMLinear
+
+accuracy_score on train : 0.533333333333
+accuracy_score on test : 0.433333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.433333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.604838709677
+ - Score on test : 0.484848484848
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.604838709677
+ - Score on test : 0.484848484848
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.566666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.433333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0354605635154
+ - Score on test : -0.131720304791
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.595238095238
+ - Score on test : 0.436363636364
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.614754098361
+ - Score on test : 0.545454545455
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.517604321908
+ - Score on test : 0.435770750988
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.566666666667
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..a085f760
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.4
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.357142857143
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.357142857143
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.6
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.20378096045
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.375
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.340909090909
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.39871541502
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.6
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..cf24b718
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095536Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.466666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 7)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.538461538462
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.538461538462
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.533333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0628694613462
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.636363636364
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.470355731225
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.533333333333
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..b93b2e14
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View3 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 4, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.576923076923
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.576923076923
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0314347306731
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.681818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.514822134387
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..ed86c3be
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588235294118
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588235294118
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0763602735229
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.51724137931
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.681818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.536561264822
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..81a8c71b
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with KNN
+
+accuracy_score on train : 0.590476190476
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.681481481481
+ - Score on test : 0.601941747573
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.681481481481
+ - Score on test : 0.601941747573
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.127350050081
+ - Score on test : 0.100829966549
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.621621621622
+ - Score on test : 0.525423728814
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.754098360656
+ - Score on test : 0.704545454545
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.558867362146
+ - Score on test : 0.547924901186
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..5a7ef634
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with RandomForest
+
+accuracy_score on train : 0.9
+accuracy_score on test : 0.577777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 4, max_depth : 20
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.9
+ - Score on test : 0.577777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.910638297872
+ - Score on test : 0.586956521739
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.910638297872
+ - Score on test : 0.586956521739
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.1
+ - Score on test : 0.422222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.9
+ - Score on test : 0.577777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.800522373751
+ - Score on test : 0.157426051223
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.946902654867
+ - Score on test : 0.5625
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.877049180328
+ - Score on test : 0.613636363636
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.904433681073
+ - Score on test : 0.578557312253
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.1
+ - Score on test : 0.422222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..616ff06f
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with SGD
+
+accuracy_score on train : 0.590476190476
+accuracy_score on test : 0.488888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.488888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.739393939394
+ - Score on test : 0.65671641791
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.739393939394
+ - Score on test : 0.65671641791
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.511111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.590476190476
+ - Score on test : 0.488888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.115457436228
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.586538461538
+ - Score on test : 0.488888888889
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.511363636364
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.409523809524
+ - Score on test : 0.511111111111
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..226afbe8
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095537Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with SVMLinear
+
+accuracy_score on train : 0.495238095238
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 6)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 6107
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.495238095238
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.595419847328
+ - Score on test : 0.550458715596
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.595419847328
+ - Score on test : 0.550458715596
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.504761904762
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.495238095238
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.0682438863041
+ - Score on test : -0.0882242643891
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.557142857143
+ - Score on test : 0.461538461538
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.639344262295
+ - Score on test : 0.681818181818
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.467399403875
+ - Score on test : 0.4604743083
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.504761904762
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095538Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095538Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..d2af511d
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095538Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,32 @@
+ Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 57.1764705882
+ -On Test : 52.6829268293
+ -On Validation : 52.1348314607
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Bayesian Inference using a weight for each view : 0.322967175445, 0.0184701333132, 0.322597810111, 0.335964881131
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : modified_huber, penalty : elasticnet
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095622-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log b/Code/MonoMutliViewClassifiers/Results/20160908-095622-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
new file mode 100644
index 00000000..e8dd4634
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095622-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
@@ -0,0 +1,2394 @@
+2016-09-08 09:56:22,282 DEBUG: Start: Creating 2 temporary datasets for multiprocessing
+2016-09-08 09:56:22,282 WARNING: WARNING : /!\ This may use a lot of HDD storage space : 0.0001661875 Gbytes /!\
+2016-09-08 09:56:27,294 DEBUG: Start: Creating datasets for multiprocessing
+2016-09-08 09:56:27,298 INFO: Start: Finding all available mono- & multiview algorithms
+2016-09-08 09:56:27,351 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:27,351 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 09:56:27,351 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:27,352 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:27,352 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 09:56:27,352 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:27,352 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:27,352 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:27,352 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:27,353 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:27,353 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:27,353 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:27,353 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:27,354 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:27,389 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:27,389 DEBUG: Start: Training
+2016-09-08 09:56:27,391 DEBUG: Info: Time for Training: 0.0395510196686[s]
+2016-09-08 09:56:27,391 DEBUG: Done: Training
+2016-09-08 09:56:27,391 DEBUG: Start: Predicting
+2016-09-08 09:56:27,393 DEBUG: Done: Predicting
+2016-09-08 09:56:27,393 DEBUG: Start: Getting Results
+2016-09-08 09:56:27,403 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:27,403 DEBUG: Start: Training
+2016-09-08 09:56:27,407 DEBUG: Info: Time for Training: 0.0563409328461[s]
+2016-09-08 09:56:27,407 DEBUG: Done: Training
+2016-09-08 09:56:27,407 DEBUG: Start: Predicting
+2016-09-08 09:56:27,410 DEBUG: Done: Predicting
+2016-09-08 09:56:27,410 DEBUG: Start: Getting Results
+2016-09-08 09:56:27,440 DEBUG: Done: Getting Results
+2016-09-08 09:56:27,440 INFO: Classification on Fake database for View0 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.377777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.377777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.348837209302
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.348837209302
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.622222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.377777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.245415911539
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.365853658537
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.376804380289
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.622222222222
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:27,441 INFO: Done: Result Analysis
+2016-09-08 09:56:27,452 DEBUG: Done: Getting Results
+2016-09-08 09:56:27,452 INFO: Classification on Fake database for View0 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.377777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 10, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.377777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.622222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.377777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.249628898234
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.325581395349
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.341463414634
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.37481333997
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.622222222222
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:27,452 INFO: Done: Result Analysis
+2016-09-08 09:56:27,595 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:27,595 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:27,595 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 09:56:27,595 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 09:56:27,595 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:27,595 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:27,596 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:27,596 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:27,596 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:27,596 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:27,596 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:27,596 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:27,596 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:27,596 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:27,627 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:27,627 DEBUG: Start: Training
+2016-09-08 09:56:27,628 DEBUG: Info: Time for Training: 0.0337619781494[s]
+2016-09-08 09:56:27,628 DEBUG: Done: Training
+2016-09-08 09:56:27,628 DEBUG: Start: Predicting
+2016-09-08 09:56:27,635 DEBUG: Done: Predicting
+2016-09-08 09:56:27,635 DEBUG: Start: Getting Results
+2016-09-08 09:56:27,676 DEBUG: Done: Getting Results
+2016-09-08 09:56:27,676 INFO: Classification on Fake database for View0 with KNN
+
+accuracy_score on train : 0.609523809524
+accuracy_score on test : 0.422222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 42
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.609523809524
+ - Score on test : 0.422222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.467532467532
+ - Score on test : 0.212121212121
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.467532467532
+ - Score on test : 0.212121212121
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.390476190476
+ - Score on test : 0.577777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.609523809524
+ - Score on test : 0.422222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.237135686833
+ - Score on test : -0.218615245335
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.692307692308
+ - Score on test : 0.28
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.352941176471
+ - Score on test : 0.170731707317
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.602396514161
+ - Score on test : 0.401692384271
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.390476190476
+ - Score on test : 0.577777777778
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:27,676 INFO: Done: Result Analysis
+2016-09-08 09:56:27,921 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:27,921 DEBUG: Start: Training
+2016-09-08 09:56:27,970 DEBUG: Info: Time for Training: 0.375941991806[s]
+2016-09-08 09:56:27,970 DEBUG: Done: Training
+2016-09-08 09:56:27,970 DEBUG: Start: Predicting
+2016-09-08 09:56:27,976 DEBUG: Done: Predicting
+2016-09-08 09:56:27,977 DEBUG: Start: Getting Results
+2016-09-08 09:56:28,010 DEBUG: Done: Getting Results
+2016-09-08 09:56:28,011 INFO: Classification on Fake database for View0 with RandomForest
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 19, max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.423529411765
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.423529411765
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0912478416452
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.409090909091
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.439024390244
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.454206072673
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:28,011 INFO: Done: Result Analysis
+2016-09-08 09:56:28,143 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:28,143 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 09:56:28,143 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:28,143 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:28,143 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 09:56:28,144 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:28,144 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:28,144 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:28,144 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:28,144 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:28,144 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:28,144 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:28,144 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:28,145 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:28,189 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:28,189 DEBUG: Start: Training
+2016-09-08 09:56:28,190 DEBUG: Info: Time for Training: 0.0481970310211[s]
+2016-09-08 09:56:28,190 DEBUG: Done: Training
+2016-09-08 09:56:28,190 DEBUG: Start: Predicting
+2016-09-08 09:56:28,195 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:28,195 DEBUG: Start: Training
+2016-09-08 09:56:28,214 DEBUG: Info: Time for Training: 0.0711450576782[s]
+2016-09-08 09:56:28,214 DEBUG: Done: Training
+2016-09-08 09:56:28,214 DEBUG: Start: Predicting
+2016-09-08 09:56:28,216 DEBUG: Done: Predicting
+2016-09-08 09:56:28,216 DEBUG: Start: Getting Results
+2016-09-08 09:56:28,217 DEBUG: Done: Predicting
+2016-09-08 09:56:28,217 DEBUG: Start: Getting Results
+2016-09-08 09:56:28,239 DEBUG: Done: Getting Results
+2016-09-08 09:56:28,239 INFO: Classification on Fake database for View0 with SGD
+
+accuracy_score on train : 0.485714285714
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : l1
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:28,239 INFO: Done: Result Analysis
+2016-09-08 09:56:28,250 DEBUG: Done: Getting Results
+2016-09-08 09:56:28,250 INFO: Classification on Fake database for View0 with SVMLinear
+
+accuracy_score on train : 0.52380952381
+accuracy_score on test : 0.477777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.477777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.532710280374
+ - Score on test : 0.459770114943
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.532710280374
+ - Score on test : 0.459770114943
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.522222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.477777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0496545019224
+ - Score on test : -0.0426484477255
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.508928571429
+ - Score on test : 0.434782608696
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.558823529412
+ - Score on test : 0.487804878049
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.524782135076
+ - Score on test : 0.478596316575
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.522222222222
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:28,250 INFO: Done: Result Analysis
+2016-09-08 09:56:28,387 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:28,387 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:28,387 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMPoly
+2016-09-08 09:56:28,387 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMRBF
+2016-09-08 09:56:28,387 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:28,387 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:28,388 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:28,388 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:28,388 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:28,388 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:28,388 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:28,388 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:28,388 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:28,388 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:28,433 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:28,433 DEBUG: Start: Training
+2016-09-08 09:56:28,438 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:28,438 DEBUG: Start: Training
+2016-09-08 09:56:28,450 DEBUG: Info: Time for Training: 0.0634729862213[s]
+2016-09-08 09:56:28,450 DEBUG: Done: Training
+2016-09-08 09:56:28,450 DEBUG: Start: Predicting
+2016-09-08 09:56:28,455 DEBUG: Info: Time for Training: 0.0687439441681[s]
+2016-09-08 09:56:28,455 DEBUG: Done: Training
+2016-09-08 09:56:28,455 DEBUG: Start: Predicting
+2016-09-08 09:56:28,455 DEBUG: Done: Predicting
+2016-09-08 09:56:28,455 DEBUG: Start: Getting Results
+2016-09-08 09:56:28,459 DEBUG: Done: Predicting
+2016-09-08 09:56:28,459 DEBUG: Start: Getting Results
+2016-09-08 09:56:28,491 DEBUG: Done: Getting Results
+2016-09-08 09:56:28,491 INFO: Classification on Fake database for View0 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.422222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.409090909091
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.409090909091
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.152357995542
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.382978723404
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.439024390244
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.423593827775
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:28,492 INFO: Done: Result Analysis
+2016-09-08 09:56:28,505 DEBUG: Done: Getting Results
+2016-09-08 09:56:28,505 INFO: Classification on Fake database for View0 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.475
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.475
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0555284586866
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.487179487179
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.463414634146
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.52762568442
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:28,505 INFO: Done: Result Analysis
+2016-09-08 09:56:28,637 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:28,638 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 09:56:28,638 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:28,638 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:28,638 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 09:56:28,638 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:28,638 DEBUG: Info: Shape X_train:(210, 19), Length of y_train:210
+2016-09-08 09:56:28,638 DEBUG: Info: Shape X_test:(90, 19), Length of y_test:90
+2016-09-08 09:56:28,638 DEBUG: Info: Shape X_train:(210, 19), Length of y_train:210
+2016-09-08 09:56:28,639 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:28,639 DEBUG: Info: Shape X_test:(90, 19), Length of y_test:90
+2016-09-08 09:56:28,639 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:28,639 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:28,639 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:28,677 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:28,677 DEBUG: Start: Training
+2016-09-08 09:56:28,680 DEBUG: Info: Time for Training: 0.0427668094635[s]
+2016-09-08 09:56:28,680 DEBUG: Done: Training
+2016-09-08 09:56:28,680 DEBUG: Start: Predicting
+2016-09-08 09:56:28,683 DEBUG: Done: Predicting
+2016-09-08 09:56:28,683 DEBUG: Start: Getting Results
+2016-09-08 09:56:28,691 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:28,691 DEBUG: Start: Training
+2016-09-08 09:56:28,696 DEBUG: Info: Time for Training: 0.0597720146179[s]
+2016-09-08 09:56:28,696 DEBUG: Done: Training
+2016-09-08 09:56:28,696 DEBUG: Start: Predicting
+2016-09-08 09:56:28,699 DEBUG: Done: Predicting
+2016-09-08 09:56:28,699 DEBUG: Start: Getting Results
+2016-09-08 09:56:28,734 DEBUG: Done: Getting Results
+2016-09-08 09:56:28,734 INFO: Classification on Fake database for View1 with DecisionTree
+
+accuracy_score on train : 0.957142857143
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.957142857143
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.957746478873
+ - Score on test : 0.444444444444
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.957746478873
+ - Score on test : 0.444444444444
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0428571428571
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.957142857143
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.917792101918
+ - Score on test : -0.104031856645
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.918918918919
+ - Score on test : 0.408163265306
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.487804878049
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.958333333333
+ - Score on test : 0.447984071677
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0428571428571
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:28,734 INFO: Done: Result Analysis
+2016-09-08 09:56:28,741 DEBUG: Done: Getting Results
+2016-09-08 09:56:28,741 INFO: Classification on Fake database for View1 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 10, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.390243902439
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.390243902439
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.119960179194
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.390243902439
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.390243902439
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.440019910403
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:28,741 INFO: Done: Result Analysis
+2016-09-08 09:56:28,882 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:28,883 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 09:56:28,883 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:28,883 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:28,883 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 09:56:28,884 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:28,884 DEBUG: Info: Shape X_train:(210, 19), Length of y_train:210
+2016-09-08 09:56:28,884 DEBUG: Info: Shape X_test:(90, 19), Length of y_test:90
+2016-09-08 09:56:28,884 DEBUG: Info: Shape X_train:(210, 19), Length of y_train:210
+2016-09-08 09:56:28,884 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:28,885 DEBUG: Info: Shape X_test:(90, 19), Length of y_test:90
+2016-09-08 09:56:28,885 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:28,885 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:28,885 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:28,919 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:28,919 DEBUG: Start: Training
+2016-09-08 09:56:28,920 DEBUG: Info: Time for Training: 0.0378148555756[s]
+2016-09-08 09:56:28,920 DEBUG: Done: Training
+2016-09-08 09:56:28,920 DEBUG: Start: Predicting
+2016-09-08 09:56:28,927 DEBUG: Done: Predicting
+2016-09-08 09:56:28,927 DEBUG: Start: Getting Results
+2016-09-08 09:56:28,967 DEBUG: Done: Getting Results
+2016-09-08 09:56:28,967 INFO: Classification on Fake database for View1 with KNN
+
+accuracy_score on train : 0.561904761905
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 42
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.561904761905
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.559139784946
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.559139784946
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.438095238095
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.561904761905
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.133359904768
+ - Score on test : 0.104395047556
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.5390625
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.676470588235
+ - Score on test : 0.634146341463
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.565087145969
+ - Score on test : 0.551767048283
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.438095238095
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:28,967 INFO: Done: Result Analysis
+2016-09-08 09:56:29,211 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:29,212 DEBUG: Start: Training
+2016-09-08 09:56:29,260 DEBUG: Info: Time for Training: 0.377947092056[s]
+2016-09-08 09:56:29,261 DEBUG: Done: Training
+2016-09-08 09:56:29,261 DEBUG: Start: Predicting
+2016-09-08 09:56:29,267 DEBUG: Done: Predicting
+2016-09-08 09:56:29,267 DEBUG: Start: Getting Results
+2016-09-08 09:56:29,300 DEBUG: Done: Getting Results
+2016-09-08 09:56:29,300 INFO: Classification on Fake database for View1 with RandomForest
+
+accuracy_score on train : 0.995238095238
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 19, max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.995073891626
+ - Score on test : 0.516853932584
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.995073891626
+ - Score on test : 0.516853932584
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.990510833227
+ - Score on test : 0.0506833064614
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.479166666667
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.990196078431
+ - Score on test : 0.560975609756
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.995098039216
+ - Score on test : 0.525385764062
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:29,300 INFO: Done: Result Analysis
+2016-09-08 09:56:29,434 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:29,435 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 09:56:29,435 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:29,435 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:29,435 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 09:56:29,435 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:29,436 DEBUG: Info: Shape X_train:(210, 19), Length of y_train:210
+2016-09-08 09:56:29,436 DEBUG: Info: Shape X_test:(90, 19), Length of y_test:90
+2016-09-08 09:56:29,436 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:29,436 DEBUG: Info: Shape X_train:(210, 19), Length of y_train:210
+2016-09-08 09:56:29,436 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:29,436 DEBUG: Info: Shape X_test:(90, 19), Length of y_test:90
+2016-09-08 09:56:29,437 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:29,437 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:29,483 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:29,483 DEBUG: Start: Training
+2016-09-08 09:56:29,484 DEBUG: Info: Time for Training: 0.0506761074066[s]
+2016-09-08 09:56:29,484 DEBUG: Done: Training
+2016-09-08 09:56:29,484 DEBUG: Start: Predicting
+2016-09-08 09:56:29,491 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:29,491 DEBUG: Start: Training
+2016-09-08 09:56:29,511 DEBUG: Done: Predicting
+2016-09-08 09:56:29,511 DEBUG: Start: Getting Results
+2016-09-08 09:56:29,520 DEBUG: Info: Time for Training: 0.0860919952393[s]
+2016-09-08 09:56:29,520 DEBUG: Done: Training
+2016-09-08 09:56:29,521 DEBUG: Start: Predicting
+2016-09-08 09:56:29,526 DEBUG: Done: Predicting
+2016-09-08 09:56:29,526 DEBUG: Start: Getting Results
+2016-09-08 09:56:29,539 DEBUG: Done: Getting Results
+2016-09-08 09:56:29,539 INFO: Classification on Fake database for View1 with SGD
+
+accuracy_score on train : 0.485714285714
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : l1
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:29,540 INFO: Done: Result Analysis
+2016-09-08 09:56:29,553 DEBUG: Done: Getting Results
+2016-09-08 09:56:29,554 INFO: Classification on Fake database for View1 with SVMLinear
+
+accuracy_score on train : 0.514285714286
+accuracy_score on test : 0.577777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.577777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.547619047619
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.547619047619
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.422222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.577777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0294117647059
+ - Score on test : 0.152357995542
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.53488372093
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.529411764706
+ - Score on test : 0.560975609756
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.514705882353
+ - Score on test : 0.576406172225
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.422222222222
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:29,554 INFO: Done: Result Analysis
+2016-09-08 09:56:29,683 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:29,684 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:29,684 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMRBF
+2016-09-08 09:56:29,684 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMPoly
+2016-09-08 09:56:29,684 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:29,684 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:29,685 DEBUG: Info: Shape X_train:(210, 19), Length of y_train:210
+2016-09-08 09:56:29,685 DEBUG: Info: Shape X_train:(210, 19), Length of y_train:210
+2016-09-08 09:56:29,685 DEBUG: Info: Shape X_test:(90, 19), Length of y_test:90
+2016-09-08 09:56:29,685 DEBUG: Info: Shape X_test:(90, 19), Length of y_test:90
+2016-09-08 09:56:29,686 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:29,686 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:29,686 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:29,686 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:29,756 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:29,756 DEBUG: Start: Training
+2016-09-08 09:56:29,762 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:29,762 DEBUG: Start: Training
+2016-09-08 09:56:29,781 DEBUG: Info: Time for Training: 0.0979940891266[s]
+2016-09-08 09:56:29,781 DEBUG: Done: Training
+2016-09-08 09:56:29,781 DEBUG: Start: Predicting
+2016-09-08 09:56:29,788 DEBUG: Info: Time for Training: 0.105060100555[s]
+2016-09-08 09:56:29,788 DEBUG: Done: Training
+2016-09-08 09:56:29,788 DEBUG: Start: Predicting
+2016-09-08 09:56:29,790 DEBUG: Done: Predicting
+2016-09-08 09:56:29,790 DEBUG: Start: Getting Results
+2016-09-08 09:56:29,793 DEBUG: Done: Predicting
+2016-09-08 09:56:29,794 DEBUG: Start: Getting Results
+2016-09-08 09:56:29,827 DEBUG: Done: Getting Results
+2016-09-08 09:56:29,827 DEBUG: Done: Getting Results
+2016-09-08 09:56:29,827 INFO: Classification on Fake database for View1 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.394366197183
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.394366197183
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0157759322964
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.341463414634
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.507466401195
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:29,827 INFO: Classification on Fake database for View1 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0193709711057
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.44
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.268292682927
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.491289198606
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:29,827 INFO: Done: Result Analysis
+2016-09-08 09:56:29,828 INFO: Done: Result Analysis
+2016-09-08 09:56:29,934 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:29,934 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 09:56:29,934 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:29,934 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:29,935 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 09:56:29,935 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:29,935 DEBUG: Info: Shape X_train:(210, 20), Length of y_train:210
+2016-09-08 09:56:29,935 DEBUG: Info: Shape X_test:(90, 20), Length of y_test:90
+2016-09-08 09:56:29,936 DEBUG: Info: Shape X_train:(210, 20), Length of y_train:210
+2016-09-08 09:56:29,936 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:29,936 DEBUG: Info: Shape X_test:(90, 20), Length of y_test:90
+2016-09-08 09:56:29,936 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:29,936 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:29,936 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:29,974 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:29,974 DEBUG: Start: Training
+2016-09-08 09:56:29,976 DEBUG: Info: Time for Training: 0.0422959327698[s]
+2016-09-08 09:56:29,976 DEBUG: Done: Training
+2016-09-08 09:56:29,976 DEBUG: Start: Predicting
+2016-09-08 09:56:29,979 DEBUG: Done: Predicting
+2016-09-08 09:56:29,979 DEBUG: Start: Getting Results
+2016-09-08 09:56:29,988 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:29,988 DEBUG: Start: Training
+2016-09-08 09:56:29,994 DEBUG: Info: Time for Training: 0.0606279373169[s]
+2016-09-08 09:56:29,994 DEBUG: Done: Training
+2016-09-08 09:56:29,994 DEBUG: Start: Predicting
+2016-09-08 09:56:29,997 DEBUG: Done: Predicting
+2016-09-08 09:56:29,997 DEBUG: Start: Getting Results
+2016-09-08 09:56:30,029 DEBUG: Done: Getting Results
+2016-09-08 09:56:30,029 INFO: Classification on Fake database for View2 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.433333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.385542168675
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.385542168675
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.140124435511
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.380952380952
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.390243902439
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.429815828771
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:30,029 INFO: Done: Result Analysis
+2016-09-08 09:56:30,043 DEBUG: Done: Getting Results
+2016-09-08 09:56:30,043 INFO: Classification on Fake database for View2 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 10, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.375
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.375
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.124563839757
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.384615384615
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.365853658537
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.438028870085
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:30,044 INFO: Done: Result Analysis
+2016-09-08 09:56:30,185 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:30,186 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 09:56:30,186 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:30,186 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:30,186 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 09:56:30,186 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:30,187 DEBUG: Info: Shape X_train:(210, 20), Length of y_train:210
+2016-09-08 09:56:30,187 DEBUG: Info: Shape X_train:(210, 20), Length of y_train:210
+2016-09-08 09:56:30,187 DEBUG: Info: Shape X_test:(90, 20), Length of y_test:90
+2016-09-08 09:56:30,187 DEBUG: Info: Shape X_test:(90, 20), Length of y_test:90
+2016-09-08 09:56:30,187 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:30,187 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:30,187 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:30,188 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:30,236 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:30,237 DEBUG: Start: Training
+2016-09-08 09:56:30,238 DEBUG: Info: Time for Training: 0.0538048744202[s]
+2016-09-08 09:56:30,238 DEBUG: Done: Training
+2016-09-08 09:56:30,238 DEBUG: Start: Predicting
+2016-09-08 09:56:30,249 DEBUG: Done: Predicting
+2016-09-08 09:56:30,249 DEBUG: Start: Getting Results
+2016-09-08 09:56:30,288 DEBUG: Done: Getting Results
+2016-09-08 09:56:30,288 INFO: Classification on Fake database for View2 with KNN
+
+accuracy_score on train : 0.542857142857
+accuracy_score on test : 0.588888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 42
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.542857142857
+ - Score on test : 0.588888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.323943661972
+ - Score on test : 0.327272727273
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.323943661972
+ - Score on test : 0.327272727273
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.457142857143
+ - Score on test : 0.411111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.542857142857
+ - Score on test : 0.588888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0866552427925
+ - Score on test : 0.161417724438
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.575
+ - Score on test : 0.642857142857
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.225490196078
+ - Score on test : 0.219512195122
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.534041394336
+ - Score on test : 0.558735689398
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.457142857143
+ - Score on test : 0.411111111111
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:30,289 INFO: Done: Result Analysis
+2016-09-08 09:56:30,545 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:30,545 DEBUG: Start: Training
+2016-09-08 09:56:30,594 DEBUG: Info: Time for Training: 0.40927195549[s]
+2016-09-08 09:56:30,594 DEBUG: Done: Training
+2016-09-08 09:56:30,594 DEBUG: Start: Predicting
+2016-09-08 09:56:30,600 DEBUG: Done: Predicting
+2016-09-08 09:56:30,600 DEBUG: Start: Getting Results
+2016-09-08 09:56:30,633 DEBUG: Done: Getting Results
+2016-09-08 09:56:30,633 INFO: Classification on Fake database for View2 with RandomForest
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.588888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 19, max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.55421686747
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.55421686747
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.411111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.172919516163
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.547619047619
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.560975609756
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.586610253858
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.411111111111
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:30,633 INFO: Done: Result Analysis
+2016-09-08 09:56:30,727 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:30,727 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 09:56:30,727 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:30,727 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:30,728 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 09:56:30,728 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:30,728 DEBUG: Info: Shape X_train:(210, 20), Length of y_train:210
+2016-09-08 09:56:30,728 DEBUG: Info: Shape X_test:(90, 20), Length of y_test:90
+2016-09-08 09:56:30,728 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:30,728 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:30,728 DEBUG: Info: Shape X_train:(210, 20), Length of y_train:210
+2016-09-08 09:56:30,728 DEBUG: Info: Shape X_test:(90, 20), Length of y_test:90
+2016-09-08 09:56:30,729 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:30,729 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:30,773 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:30,773 DEBUG: Start: Training
+2016-09-08 09:56:30,774 DEBUG: Info: Time for Training: 0.0476858615875[s]
+2016-09-08 09:56:30,774 DEBUG: Done: Training
+2016-09-08 09:56:30,774 DEBUG: Start: Predicting
+2016-09-08 09:56:30,779 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:30,779 DEBUG: Start: Training
+2016-09-08 09:56:30,796 DEBUG: Done: Predicting
+2016-09-08 09:56:30,796 DEBUG: Start: Getting Results
+2016-09-08 09:56:30,800 DEBUG: Info: Time for Training: 0.0737199783325[s]
+2016-09-08 09:56:30,800 DEBUG: Done: Training
+2016-09-08 09:56:30,801 DEBUG: Start: Predicting
+2016-09-08 09:56:30,804 DEBUG: Done: Predicting
+2016-09-08 09:56:30,804 DEBUG: Start: Getting Results
+2016-09-08 09:56:30,819 DEBUG: Done: Getting Results
+2016-09-08 09:56:30,819 INFO: Classification on Fake database for View2 with SGD
+
+accuracy_score on train : 0.485714285714
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : l1
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:30,819 INFO: Done: Result Analysis
+2016-09-08 09:56:30,833 DEBUG: Done: Getting Results
+2016-09-08 09:56:30,833 INFO: Classification on Fake database for View2 with SVMLinear
+
+accuracy_score on train : 0.533333333333
+accuracy_score on test : 0.588888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.588888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.514851485149
+ - Score on test : 0.543209876543
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.514851485149
+ - Score on test : 0.543209876543
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.411111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.588888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0654069940168
+ - Score on test : 0.169618786115
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.52
+ - Score on test : 0.55
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.509803921569
+ - Score on test : 0.536585365854
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.532679738562
+ - Score on test : 0.584619213539
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.411111111111
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:30,833 INFO: Done: Result Analysis
+2016-09-08 09:56:30,973 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:30,973 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:30,974 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMPoly
+2016-09-08 09:56:30,974 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMRBF
+2016-09-08 09:56:30,974 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:30,974 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:30,974 DEBUG: Info: Shape X_train:(210, 20), Length of y_train:210
+2016-09-08 09:56:30,974 DEBUG: Info: Shape X_train:(210, 20), Length of y_train:210
+2016-09-08 09:56:30,974 DEBUG: Info: Shape X_test:(90, 20), Length of y_test:90
+2016-09-08 09:56:30,974 DEBUG: Info: Shape X_test:(90, 20), Length of y_test:90
+2016-09-08 09:56:30,975 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:30,975 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:30,975 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:30,975 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:31,020 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:31,020 DEBUG: Start: Training
+2016-09-08 09:56:31,024 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:31,024 DEBUG: Start: Training
+2016-09-08 09:56:31,039 DEBUG: Info: Time for Training: 0.0657398700714[s]
+2016-09-08 09:56:31,039 DEBUG: Done: Training
+2016-09-08 09:56:31,039 DEBUG: Start: Predicting
+2016-09-08 09:56:31,043 DEBUG: Info: Time for Training: 0.0697932243347[s]
+2016-09-08 09:56:31,043 DEBUG: Done: Training
+2016-09-08 09:56:31,043 DEBUG: Start: Predicting
+2016-09-08 09:56:31,045 DEBUG: Done: Predicting
+2016-09-08 09:56:31,045 DEBUG: Start: Getting Results
+2016-09-08 09:56:31,047 DEBUG: Done: Predicting
+2016-09-08 09:56:31,047 DEBUG: Start: Getting Results
+2016-09-08 09:56:31,077 DEBUG: Done: Getting Results
+2016-09-08 09:56:31,077 INFO: Classification on Fake database for View2 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588235294118
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588235294118
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0350036509618
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.448717948718
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.853658536585
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.488053758089
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:31,077 INFO: Done: Result Analysis
+2016-09-08 09:56:31,077 DEBUG: Done: Getting Results
+2016-09-08 09:56:31,077 INFO: Classification on Fake database for View2 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.453333333333
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.453333333333
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0695369227879
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.414634146341
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533847685416
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:31,078 INFO: Done: Result Analysis
+2016-09-08 09:56:31,220 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:31,220 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:31,220 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 09:56:31,220 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 09:56:31,221 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:31,221 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:31,221 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:31,221 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:31,221 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:31,221 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:31,221 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:31,222 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:31,222 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:31,222 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:31,257 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:31,257 DEBUG: Start: Training
+2016-09-08 09:56:31,259 DEBUG: Info: Time for Training: 0.0391139984131[s]
+2016-09-08 09:56:31,259 DEBUG: Done: Training
+2016-09-08 09:56:31,259 DEBUG: Start: Predicting
+2016-09-08 09:56:31,262 DEBUG: Done: Predicting
+2016-09-08 09:56:31,262 DEBUG: Start: Getting Results
+2016-09-08 09:56:31,270 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:31,270 DEBUG: Start: Training
+2016-09-08 09:56:31,274 DEBUG: Info: Time for Training: 0.0547120571136[s]
+2016-09-08 09:56:31,275 DEBUG: Done: Training
+2016-09-08 09:56:31,275 DEBUG: Start: Predicting
+2016-09-08 09:56:31,277 DEBUG: Done: Predicting
+2016-09-08 09:56:31,277 DEBUG: Start: Getting Results
+2016-09-08 09:56:31,302 DEBUG: Done: Getting Results
+2016-09-08 09:56:31,302 INFO: Classification on Fake database for View3 with DecisionTree
+
+accuracy_score on train : 0.985714285714
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.985714285714
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.985507246377
+ - Score on test : 0.516853932584
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.985507246377
+ - Score on test : 0.516853932584
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0142857142857
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.985714285714
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.971825315808
+ - Score on test : 0.0506833064614
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.971428571429
+ - Score on test : 0.479166666667
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.560975609756
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.986111111111
+ - Score on test : 0.525385764062
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0142857142857
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:31,303 INFO: Done: Result Analysis
+2016-09-08 09:56:31,313 DEBUG: Done: Getting Results
+2016-09-08 09:56:31,314 INFO: Classification on Fake database for View3 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 10, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511627906977
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511627906977
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.066931612238
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.488888888889
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.536585365854
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533598805376
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:31,314 INFO: Done: Result Analysis
+2016-09-08 09:56:31,468 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:31,468 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 09:56:31,468 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:31,468 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:31,469 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 09:56:31,469 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:31,469 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:31,469 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:31,469 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:31,469 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:31,469 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:31,469 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:31,470 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:31,470 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:31,503 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:31,503 DEBUG: Start: Training
+2016-09-08 09:56:31,504 DEBUG: Info: Time for Training: 0.0364670753479[s]
+2016-09-08 09:56:31,504 DEBUG: Done: Training
+2016-09-08 09:56:31,504 DEBUG: Start: Predicting
+2016-09-08 09:56:31,511 DEBUG: Done: Predicting
+2016-09-08 09:56:31,511 DEBUG: Start: Getting Results
+2016-09-08 09:56:31,565 DEBUG: Done: Getting Results
+2016-09-08 09:56:31,565 INFO: Classification on Fake database for View3 with KNN
+
+accuracy_score on train : 0.533333333333
+accuracy_score on test : 0.588888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 42
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.588888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.505050505051
+ - Score on test : 0.543209876543
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.505050505051
+ - Score on test : 0.543209876543
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.411111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.588888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0644812208979
+ - Score on test : 0.169618786115
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.520833333333
+ - Score on test : 0.55
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.490196078431
+ - Score on test : 0.536585365854
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.532135076253
+ - Score on test : 0.584619213539
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.411111111111
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:31,565 INFO: Done: Result Analysis
+2016-09-08 09:56:31,800 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:31,800 DEBUG: Start: Training
+2016-09-08 09:56:31,848 DEBUG: Info: Time for Training: 0.380412101746[s]
+2016-09-08 09:56:31,848 DEBUG: Done: Training
+2016-09-08 09:56:31,848 DEBUG: Start: Predicting
+2016-09-08 09:56:31,855 DEBUG: Done: Predicting
+2016-09-08 09:56:31,855 DEBUG: Start: Getting Results
+2016-09-08 09:56:31,882 DEBUG: Done: Getting Results
+2016-09-08 09:56:31,882 INFO: Classification on Fake database for View3 with RandomForest
+
+accuracy_score on train : 0.995238095238
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 19, max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.99512195122
+ - Score on test : 0.488372093023
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.99512195122
+ - Score on test : 0.488372093023
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.990515975943
+ - Score on test : 0.0223105374127
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.990291262136
+ - Score on test : 0.466666666667
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.512195121951
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.99537037037
+ - Score on test : 0.511199601792
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:31,882 INFO: Done: Result Analysis
+2016-09-08 09:56:32,016 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:32,016 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:56:32,016 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 09:56:32,016 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 09:56:32,016 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:32,016 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:56:32,017 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:32,017 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:56:32,017 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:32,017 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:56:32,017 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:32,017 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:56:32,017 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:32,017 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:56:32,062 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:32,062 DEBUG: Start: Training
+2016-09-08 09:56:32,062 DEBUG: Info: Time for Training: 0.04727602005[s]
+2016-09-08 09:56:32,063 DEBUG: Done: Training
+2016-09-08 09:56:32,063 DEBUG: Start: Predicting
+2016-09-08 09:56:32,066 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:56:32,067 DEBUG: Start: Training
+2016-09-08 09:56:32,075 DEBUG: Done: Predicting
+2016-09-08 09:56:32,076 DEBUG: Start: Getting Results
+2016-09-08 09:56:32,089 DEBUG: Info: Time for Training: 0.0742139816284[s]
+2016-09-08 09:56:32,090 DEBUG: Done: Training
+2016-09-08 09:56:32,090 DEBUG: Start: Predicting
+2016-09-08 09:56:32,093 DEBUG: Done: Predicting
+2016-09-08 09:56:32,093 DEBUG: Start: Getting Results
+2016-09-08 09:56:32,100 DEBUG: Done: Getting Results
+2016-09-08 09:56:32,100 INFO: Classification on Fake database for View3 with SGD
+
+accuracy_score on train : 0.485714285714
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : l1
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:32,100 INFO: Done: Result Analysis
+2016-09-08 09:56:32,122 DEBUG: Done: Getting Results
+2016-09-08 09:56:32,122 INFO: Classification on Fake database for View3 with SVMLinear
+
+accuracy_score on train : 0.552380952381
+accuracy_score on test : 0.566666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.552380952381
+ - Score on test : 0.566666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.520408163265
+ - Score on test : 0.506329113924
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.520408163265
+ - Score on test : 0.506329113924
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.447619047619
+ - Score on test : 0.433333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.552380952381
+ - Score on test : 0.566666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.10237359911
+ - Score on test : 0.121459622637
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.542553191489
+ - Score on test : 0.526315789474
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.487804878049
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.550925925926
+ - Score on test : 0.560228969637
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.447619047619
+ - Score on test : 0.433333333333
+
+
+ Classification took 0:00:00
+2016-09-08 09:56:32,122 INFO: Done: Result Analysis
+2016-09-08 09:56:32,424 INFO: ### Main Programm for Multiview Classification
+2016-09-08 09:56:32,425 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 09:56:32,426 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 09:56:32,426 INFO: Info: Shape of View1 :(300, 19)
+2016-09-08 09:56:32,427 INFO: Info: Shape of View2 :(300, 20)
+2016-09-08 09:56:32,427 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 09:56:32,428 INFO: Done: Read Database Files
+2016-09-08 09:56:32,428 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 09:56:32,431 INFO: ### Main Programm for Multiview Classification
+2016-09-08 09:56:32,432 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 09:56:32,432 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 09:56:32,433 INFO: Done: Determine validation split
+2016-09-08 09:56:32,433 INFO: Start: Determine 5 folds
+2016-09-08 09:56:32,433 INFO: Info: Shape of View1 :(300, 19)
+2016-09-08 09:56:32,434 INFO: Info: Shape of View2 :(300, 20)
+2016-09-08 09:56:32,434 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 09:56:32,434 INFO: Done: Read Database Files
+2016-09-08 09:56:32,434 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 09:56:32,439 INFO: Done: Determine validation split
+2016-09-08 09:56:32,439 INFO: Start: Determine 5 folds
+2016-09-08 09:56:32,445 INFO: Info: Length of Learning Sets: 169
+2016-09-08 09:56:32,445 INFO: Info: Length of Testing Sets: 42
+2016-09-08 09:56:32,445 INFO: Info: Length of Validation Set: 89
+2016-09-08 09:56:32,445 INFO: Done: Determine folds
+2016-09-08 09:56:32,445 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 09:56:32,445 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 09:56:32,445 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:32,448 INFO: Info: Length of Learning Sets: 169
+2016-09-08 09:56:32,448 INFO: Info: Length of Testing Sets: 42
+2016-09-08 09:56:32,449 INFO: Info: Length of Validation Set: 89
+2016-09-08 09:56:32,449 INFO: Done: Determine folds
+2016-09-08 09:56:32,449 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 09:56:32,449 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 09:56:32,449 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:32,500 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:32,501 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:32,504 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:32,504 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:32,551 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:32,551 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:32,556 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:32,556 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:32,600 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:32,600 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:32,607 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:32,607 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:32,651 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:32,660 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:32,717 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 09:56:32,717 INFO: Start: Classification
+2016-09-08 09:56:32,717 INFO: Start: Fold number 1
+2016-09-08 09:56:32,745 INFO: Start: Classification
+2016-09-08 09:56:32,751 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 09:56:32,751 INFO: Start: Classification
+2016-09-08 09:56:32,751 INFO: Start: Fold number 1
+2016-09-08 09:56:32,771 INFO: Done: Fold number 1
+2016-09-08 09:56:32,772 INFO: Start: Fold number 2
+2016-09-08 09:56:32,778 INFO: Start: Classification
+2016-09-08 09:56:32,798 INFO: Start: Classification
+2016-09-08 09:56:32,824 INFO: Done: Fold number 2
+2016-09-08 09:56:32,824 INFO: Start: Fold number 3
+2016-09-08 09:56:32,847 INFO: Done: Fold number 1
+2016-09-08 09:56:32,848 INFO: Start: Fold number 2
+2016-09-08 09:56:32,850 INFO: Start: Classification
+2016-09-08 09:56:32,874 INFO: Start: Classification
+2016-09-08 09:56:32,876 INFO: Done: Fold number 3
+2016-09-08 09:56:32,877 INFO: Start: Fold number 4
+2016-09-08 09:56:32,903 INFO: Start: Classification
+2016-09-08 09:56:32,928 INFO: Done: Fold number 4
+2016-09-08 09:56:32,928 INFO: Start: Fold number 5
+2016-09-08 09:56:32,944 INFO: Done: Fold number 2
+2016-09-08 09:56:32,944 INFO: Start: Fold number 3
+2016-09-08 09:56:32,955 INFO: Start: Classification
+2016-09-08 09:56:32,971 INFO: Start: Classification
+2016-09-08 09:56:32,981 INFO: Done: Fold number 5
+2016-09-08 09:56:32,981 INFO: Done: Classification
+2016-09-08 09:56:32,981 INFO: Info: Time for Classification: 0[s]
+2016-09-08 09:56:32,981 INFO: Start: Result Analysis for Fusion
+2016-09-08 09:56:33,041 INFO: Done: Fold number 3
+2016-09-08 09:56:33,041 INFO: Start: Fold number 4
+2016-09-08 09:56:33,068 INFO: Start: Classification
+2016-09-08 09:56:33,109 INFO: Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 64.9704142012
+ -On Test : 42.380952381
+ -On Validation : 48.7640449438
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Bayesian Inference using a weight for each view : 0.241839908393, 0.362121620258, 0.0533308084229, 0.342707662926
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : elasticnet
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 09:56:33,109 INFO: Done: Result Analysis
+2016-09-08 09:56:33,137 INFO: Done: Fold number 4
+2016-09-08 09:56:33,137 INFO: Start: Fold number 5
+2016-09-08 09:56:33,163 INFO: Start: Classification
+2016-09-08 09:56:33,229 INFO: Done: Fold number 5
+2016-09-08 09:56:33,229 INFO: Done: Classification
+2016-09-08 09:56:33,229 INFO: Info: Time for Classification: 0[s]
+2016-09-08 09:56:33,229 INFO: Start: Result Analysis for Fusion
+2016-09-08 09:56:33,351 INFO: Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 62.2485207101
+ -On Test : 47.619047619
+ -On Validation : 52.1348314607
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Majority Voting
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : elasticnet
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 09:56:33,351 INFO: Done: Result Analysis
+2016-09-08 09:56:33,471 INFO: ### Main Programm for Multiview Classification
+2016-09-08 09:56:33,471 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 09:56:33,472 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 09:56:33,472 INFO: Info: Shape of View1 :(300, 19)
+2016-09-08 09:56:33,473 INFO: Info: Shape of View2 :(300, 20)
+2016-09-08 09:56:33,473 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 09:56:33,473 INFO: Done: Read Database Files
+2016-09-08 09:56:33,474 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 09:56:33,478 INFO: ### Main Programm for Multiview Classification
+2016-09-08 09:56:33,478 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 09:56:33,479 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 09:56:33,480 INFO: Info: Shape of View1 :(300, 19)
+2016-09-08 09:56:33,481 INFO: Done: Determine validation split
+2016-09-08 09:56:33,481 INFO: Start: Determine 5 folds
+2016-09-08 09:56:33,481 INFO: Info: Shape of View2 :(300, 20)
+2016-09-08 09:56:33,482 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 09:56:33,482 INFO: Done: Read Database Files
+2016-09-08 09:56:33,482 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 09:56:33,485 INFO: Done: Determine validation split
+2016-09-08 09:56:33,485 INFO: Start: Determine 5 folds
+2016-09-08 09:56:33,488 INFO: Info: Length of Learning Sets: 169
+2016-09-08 09:56:33,489 INFO: Info: Length of Testing Sets: 42
+2016-09-08 09:56:33,489 INFO: Info: Length of Validation Set: 89
+2016-09-08 09:56:33,489 INFO: Done: Determine folds
+2016-09-08 09:56:33,489 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 09:56:33,489 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 09:56:33,489 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:33,495 INFO: Info: Length of Learning Sets: 169
+2016-09-08 09:56:33,495 INFO: Info: Length of Testing Sets: 42
+2016-09-08 09:56:33,495 INFO: Info: Length of Validation Set: 89
+2016-09-08 09:56:33,495 INFO: Done: Determine folds
+2016-09-08 09:56:33,496 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 09:56:33,496 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 09:56:33,496 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:33,544 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:33,545 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:33,550 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:33,550 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:33,596 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:33,596 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:33,600 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:33,601 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:33,646 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:33,646 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:33,650 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:33,650 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 09:56:33,698 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:33,698 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 09:56:33,698 INFO: Start: Classification
+2016-09-08 09:56:33,699 INFO: Start: Fold number 1
+2016-09-08 09:56:33,702 DEBUG: Done: Random search for SGD
+2016-09-08 09:56:33,760 INFO: Start: Classification
+2016-09-08 09:56:33,767 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 09:56:33,767 INFO: Start: Classification
+2016-09-08 09:56:33,767 INFO: Start: Fold number 1
+2016-09-08 09:56:33,790 INFO: Done: Fold number 1
+2016-09-08 09:56:33,790 INFO: Start: Fold number 2
+2016-09-08 09:56:33,794 INFO: Start: Classification
+2016-09-08 09:56:33,825 INFO: Done: Fold number 1
+2016-09-08 09:56:33,825 INFO: Start: Fold number 2
+2016-09-08 09:56:33,835 INFO: Start: Classification
+2016-09-08 09:56:33,851 INFO: Start: Classification
+2016-09-08 09:56:33,864 INFO: Done: Fold number 2
+2016-09-08 09:56:33,865 INFO: Start: Fold number 3
+2016-09-08 09:56:33,882 INFO: Done: Fold number 2
+2016-09-08 09:56:33,882 INFO: Start: Fold number 3
+2016-09-08 09:56:33,908 INFO: Start: Classification
+2016-09-08 09:56:33,909 INFO: Start: Classification
+2016-09-08 09:56:33,938 INFO: Done: Fold number 3
+2016-09-08 09:56:33,938 INFO: Start: Fold number 4
+2016-09-08 09:56:33,938 INFO: Done: Fold number 3
+2016-09-08 09:56:33,939 INFO: Start: Fold number 4
+2016-09-08 09:56:33,965 INFO: Start: Classification
+2016-09-08 09:56:33,984 INFO: Start: Classification
+2016-09-08 09:56:33,997 INFO: Done: Fold number 4
+2016-09-08 09:56:33,997 INFO: Start: Fold number 5
+2016-09-08 09:56:34,014 INFO: Done: Fold number 4
+2016-09-08 09:56:34,014 INFO: Start: Fold number 5
+2016-09-08 09:56:34,024 INFO: Start: Classification
+2016-09-08 09:56:34,054 INFO: Done: Fold number 5
+2016-09-08 09:56:34,054 INFO: Done: Classification
+2016-09-08 09:56:34,054 INFO: Info: Time for Classification: 0[s]
+2016-09-08 09:56:34,055 INFO: Start: Result Analysis for Fusion
+2016-09-08 09:56:34,059 INFO: Start: Classification
+2016-09-08 09:56:34,089 INFO: Done: Fold number 5
+2016-09-08 09:56:34,089 INFO: Done: Classification
+2016-09-08 09:56:34,089 INFO: Info: Time for Classification: 0[s]
+2016-09-08 09:56:34,089 INFO: Start: Result Analysis for Fusion
+2016-09-08 09:56:34,221 INFO: Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 63.4319526627
+ -On Test : 47.619047619
+ -On Validation : 44.2696629213
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with SVM for linear
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : elasticnet
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 09:56:34,222 INFO: Done: Result Analysis
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095627Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095627Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..03f454c1
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095627Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View0 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.377777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 10, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.377777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.622222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.377777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.249628898234
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.325581395349
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.341463414634
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.37481333997
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.622222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095627Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095627Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..11212171
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095627Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.377777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.377777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.348837209302
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.348837209302
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.622222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.377777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.245415911539
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.365853658537
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.376804380289
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.622222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095627Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095627Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..717561a9
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095627Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with KNN
+
+accuracy_score on train : 0.609523809524
+accuracy_score on test : 0.422222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 42
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.609523809524
+ - Score on test : 0.422222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.467532467532
+ - Score on test : 0.212121212121
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.467532467532
+ - Score on test : 0.212121212121
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.390476190476
+ - Score on test : 0.577777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.609523809524
+ - Score on test : 0.422222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.237135686833
+ - Score on test : -0.218615245335
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.692307692308
+ - Score on test : 0.28
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.352941176471
+ - Score on test : 0.170731707317
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.602396514161
+ - Score on test : 0.401692384271
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.390476190476
+ - Score on test : 0.577777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..db639d87
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View1 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 10, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.390243902439
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.390243902439
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.119960179194
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.390243902439
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.390243902439
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.440019910403
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..63f60667
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with DecisionTree
+
+accuracy_score on train : 0.957142857143
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.957142857143
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.957746478873
+ - Score on test : 0.444444444444
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.957746478873
+ - Score on test : 0.444444444444
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0428571428571
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.957142857143
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.917792101918
+ - Score on test : -0.104031856645
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.918918918919
+ - Score on test : 0.408163265306
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.487804878049
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.958333333333
+ - Score on test : 0.447984071677
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0428571428571
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..450f0ea1
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with KNN
+
+accuracy_score on train : 0.561904761905
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 42
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.561904761905
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.559139784946
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.559139784946
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.438095238095
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.561904761905
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.133359904768
+ - Score on test : 0.104395047556
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.5390625
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.676470588235
+ - Score on test : 0.634146341463
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.565087145969
+ - Score on test : 0.551767048283
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.438095238095
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..3d2d8158
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with RandomForest
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 19, max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.423529411765
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.423529411765
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0912478416452
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.409090909091
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.439024390244
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.454206072673
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..511f2fee
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SGD
+
+accuracy_score on train : 0.485714285714
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : l1
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..2bda3cf3
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SVMLinear
+
+accuracy_score on train : 0.52380952381
+accuracy_score on test : 0.477777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.477777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.532710280374
+ - Score on test : 0.459770114943
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.532710280374
+ - Score on test : 0.459770114943
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.522222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.477777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0496545019224
+ - Score on test : -0.0426484477255
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.508928571429
+ - Score on test : 0.434782608696
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.558823529412
+ - Score on test : 0.487804878049
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.524782135076
+ - Score on test : 0.478596316575
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.522222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..59cdb6c6
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.475
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.475
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0555284586866
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.487179487179
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.463414634146
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.52762568442
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..a96b05b6
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095628Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.422222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.409090909091
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.409090909091
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.152357995542
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.382978723404
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.439024390244
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.423593827775
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..46f9acd1
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with RandomForest
+
+accuracy_score on train : 0.995238095238
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 19, max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.995073891626
+ - Score on test : 0.516853932584
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.995073891626
+ - Score on test : 0.516853932584
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.990510833227
+ - Score on test : 0.0506833064614
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.479166666667
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.990196078431
+ - Score on test : 0.560975609756
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.995098039216
+ - Score on test : 0.525385764062
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..c2daea4e
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SGD
+
+accuracy_score on train : 0.485714285714
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : l1
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..65a1d806
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SVMLinear
+
+accuracy_score on train : 0.514285714286
+accuracy_score on test : 0.577777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.577777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.547619047619
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.547619047619
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.422222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.577777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0294117647059
+ - Score on test : 0.152357995542
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.53488372093
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.529411764706
+ - Score on test : 0.560975609756
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.514705882353
+ - Score on test : 0.576406172225
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.422222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..ffa02970
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.394366197183
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.394366197183
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0157759322964
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.466666666667
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.341463414634
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.507466401195
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..664dd67d
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095629Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 19)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0193709711057
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.44
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.268292682927
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.491289198606
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..1026306a
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View2 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 10, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.375
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.375
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.124563839757
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.384615384615
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.365853658537
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.438028870085
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..e47d02bf
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.433333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.385542168675
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.385542168675
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.140124435511
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.380952380952
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.390243902439
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.429815828771
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..15b07a9c
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with KNN
+
+accuracy_score on train : 0.542857142857
+accuracy_score on test : 0.588888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 42
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.542857142857
+ - Score on test : 0.588888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.323943661972
+ - Score on test : 0.327272727273
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.323943661972
+ - Score on test : 0.327272727273
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.457142857143
+ - Score on test : 0.411111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.542857142857
+ - Score on test : 0.588888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0866552427925
+ - Score on test : 0.161417724438
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.575
+ - Score on test : 0.642857142857
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.225490196078
+ - Score on test : 0.219512195122
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.534041394336
+ - Score on test : 0.558735689398
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.457142857143
+ - Score on test : 0.411111111111
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..70517c8c
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with RandomForest
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.588888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 19, max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.55421686747
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.55421686747
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.411111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.172919516163
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.547619047619
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.560975609756
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.586610253858
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.411111111111
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..fd86ceca
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SGD
+
+accuracy_score on train : 0.485714285714
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : l1
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..ea0b1413
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095630Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SVMLinear
+
+accuracy_score on train : 0.533333333333
+accuracy_score on test : 0.588888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.588888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.514851485149
+ - Score on test : 0.543209876543
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.514851485149
+ - Score on test : 0.543209876543
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.411111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.588888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0654069940168
+ - Score on test : 0.169618786115
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.52
+ - Score on test : 0.55
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.509803921569
+ - Score on test : 0.536585365854
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.532679738562
+ - Score on test : 0.584619213539
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.411111111111
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..7ea3a02f
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View3 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 10, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511627906977
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511627906977
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.066931612238
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.488888888889
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.536585365854
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533598805376
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..a3cc2947
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with DecisionTree
+
+accuracy_score on train : 0.985714285714
+accuracy_score on test : 0.522222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.985714285714
+ - Score on test : 0.522222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.985507246377
+ - Score on test : 0.516853932584
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.985507246377
+ - Score on test : 0.516853932584
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0142857142857
+ - Score on test : 0.477777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.985714285714
+ - Score on test : 0.522222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.971825315808
+ - Score on test : 0.0506833064614
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.971428571429
+ - Score on test : 0.479166666667
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.560975609756
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.986111111111
+ - Score on test : 0.525385764062
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0142857142857
+ - Score on test : 0.477777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..889e2b6c
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with KNN
+
+accuracy_score on train : 0.533333333333
+accuracy_score on test : 0.588888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 42
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.588888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.505050505051
+ - Score on test : 0.543209876543
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.505050505051
+ - Score on test : 0.543209876543
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.411111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.588888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0644812208979
+ - Score on test : 0.169618786115
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.520833333333
+ - Score on test : 0.55
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.490196078431
+ - Score on test : 0.536585365854
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.532135076253
+ - Score on test : 0.584619213539
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.466666666667
+ - Score on test : 0.411111111111
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..df0c84da
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with RandomForest
+
+accuracy_score on train : 0.995238095238
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 19, max_depth : 10
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.99512195122
+ - Score on test : 0.488372093023
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.99512195122
+ - Score on test : 0.488372093023
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.990515975943
+ - Score on test : 0.0223105374127
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.990291262136
+ - Score on test : 0.466666666667
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.512195121951
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.99537037037
+ - Score on test : 0.511199601792
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..58bf957c
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588235294118
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588235294118
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0350036509618
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.448717948718
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.853658536585
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.488053758089
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..b1712044
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095631Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 20)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.453333333333
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.453333333333
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0695369227879
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.414634146341
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533847685416
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095632Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095632Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..ac66b07e
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095632Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with SGD
+
+accuracy_score on train : 0.485714285714
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : log, penalty : l1
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.653846153846
+ - Score on test : 0.625954198473
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.455555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 1.0
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095632Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095632Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..c4a246c9
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095632Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with SVMLinear
+
+accuracy_score on train : 0.552380952381
+accuracy_score on test : 0.566666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 8627
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.552380952381
+ - Score on test : 0.566666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.520408163265
+ - Score on test : 0.506329113924
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.520408163265
+ - Score on test : 0.506329113924
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.447619047619
+ - Score on test : 0.433333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.552380952381
+ - Score on test : 0.566666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.10237359911
+ - Score on test : 0.121459622637
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.542553191489
+ - Score on test : 0.526315789474
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.5
+ - Score on test : 0.487804878049
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.550925925926
+ - Score on test : 0.560228969637
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.447619047619
+ - Score on test : 0.433333333333
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095633Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095633Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..5ec16784
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095633Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,32 @@
+ Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 64.9704142012
+ -On Test : 42.380952381
+ -On Validation : 48.7640449438
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Bayesian Inference using a weight for each view : 0.241839908393, 0.362121620258, 0.0533308084229, 0.342707662926
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : elasticnet
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095633Results-Fusion-LateFusion-MajorityVoting-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095633Results-Fusion-LateFusion-MajorityVoting-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..f9c3ded1
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095633Results-Fusion-LateFusion-MajorityVoting-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,32 @@
+ Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 62.2485207101
+ -On Test : 47.619047619
+ -On Validation : 52.1348314607
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Majority Voting
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : elasticnet
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095634Results-Fusion-LateFusion-SVMForLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-095634Results-Fusion-LateFusion-SVMForLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..457213b0
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095634Results-Fusion-LateFusion-SVMForLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,32 @@
+ Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 63.4319526627
+ -On Test : 47.619047619
+ -On Validation : 44.2696629213
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with SVM for linear
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : elasticnet
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095845-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log b/Code/MonoMutliViewClassifiers/Results/20160908-095845-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
new file mode 100644
index 00000000..d434781c
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095845-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
@@ -0,0 +1,32 @@
+2016-09-08 09:58:45,489 DEBUG: Start: Creating 2 temporary datasets for multiprocessing
+2016-09-08 09:58:45,489 WARNING: WARNING : /!\ This may use a lot of HDD storage space : 0.00010759375 Gbytes /!\
+2016-09-08 09:58:50,503 DEBUG: Start: Creating datasets for multiprocessing
+2016-09-08 09:58:50,507 INFO: Start: Finding all available mono- & multiview algorithms
+2016-09-08 09:58:50,558 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:58:50,558 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 09:58:50,559 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 09:58:50,559 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 09:58:50,559 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:58:50,559 DEBUG: Start: Determine Train/Test split
+2016-09-08 09:58:50,559 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:58:50,559 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 09:58:50,559 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:58:50,559 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 09:58:50,560 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:58:50,560 DEBUG: Done: Determine Train/Test split
+2016-09-08 09:58:50,560 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:58:50,560 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 09:58:50,594 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:58:50,595 DEBUG: Start: Training
+2016-09-08 09:58:50,596 DEBUG: Info: Time for Training: 0.0384030342102[s]
+2016-09-08 09:58:50,596 DEBUG: Done: Training
+2016-09-08 09:58:50,596 DEBUG: Start: Predicting
+2016-09-08 09:58:50,599 DEBUG: Done: Predicting
+2016-09-08 09:58:50,599 DEBUG: Start: Getting Results
+2016-09-08 09:58:50,609 DEBUG: Done: RandomSearch best settings
+2016-09-08 09:58:50,609 DEBUG: Start: Training
+2016-09-08 09:58:50,613 DEBUG: Info: Time for Training: 0.0557579994202[s]
+2016-09-08 09:58:50,614 DEBUG: Done: Training
+2016-09-08 09:58:50,614 DEBUG: Start: Predicting
+2016-09-08 09:58:50,616 DEBUG: Done: Predicting
+2016-09-08 09:58:50,617 DEBUG: Start: Getting Results
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-095958-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log b/Code/MonoMutliViewClassifiers/Results/20160908-095958-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
new file mode 100644
index 00000000..9a77052c
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-095958-CMultiV-Benchmark-Methyl_MiRNA__RNASeq_Clinic-Fake-LOG.log
@@ -0,0 +1,2842 @@
+2016-09-08 09:59:58,949 DEBUG: Start: Creating 2 temporary datasets for multiprocessing
+2016-09-08 09:59:58,950 WARNING: WARNING : /!\ This may use a lot of HDD storage space : 0.000152125 Gbytes /!\
+2016-09-08 10:00:03,964 DEBUG: Start: Creating datasets for multiprocessing
+2016-09-08 10:00:03,968 INFO: Start: Finding all available mono- & multiview algorithms
+2016-09-08 10:00:04,015 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:04,015 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:04,015 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 10:00:04,015 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 10:00:04,016 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:04,016 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:04,016 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:04,016 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:04,017 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:04,017 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:04,017 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:04,017 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:04,017 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:04,017 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:04,051 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:04,052 DEBUG: Start: Training
+2016-09-08 10:00:04,053 DEBUG: Info: Time for Training: 0.0387499332428[s]
+2016-09-08 10:00:04,054 DEBUG: Done: Training
+2016-09-08 10:00:04,054 DEBUG: Start: Predicting
+2016-09-08 10:00:04,056 DEBUG: Done: Predicting
+2016-09-08 10:00:04,056 DEBUG: Start: Getting Results
+2016-09-08 10:00:04,067 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:04,067 DEBUG: Start: Training
+2016-09-08 10:00:04,071 DEBUG: Info: Time for Training: 0.0559167861938[s]
+2016-09-08 10:00:04,071 DEBUG: Done: Training
+2016-09-08 10:00:04,071 DEBUG: Start: Predicting
+2016-09-08 10:00:04,073 DEBUG: Done: Predicting
+2016-09-08 10:00:04,074 DEBUG: Start: Getting Results
+2016-09-08 10:00:04,106 DEBUG: Done: Getting Results
+2016-09-08 10:00:04,106 INFO: Classification on Fake database for View0 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.56862745098
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.56862745098
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.00503027272866
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.557692307692
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.58
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5025
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:04,106 INFO: Done: Result Analysis
+2016-09-08 10:00:04,108 DEBUG: Done: Getting Results
+2016-09-08 10:00:04,108 INFO: Classification on Fake database for View0 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 9, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.576923076923
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.576923076923
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -2.5337258102e-17
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.555555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.6
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:04,109 INFO: Done: Result Analysis
+2016-09-08 10:00:04,267 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:04,268 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 10:00:04,268 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:04,268 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:04,268 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 10:00:04,268 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:04,269 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:04,269 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:04,269 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:04,269 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:04,269 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:04,269 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:04,269 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:04,270 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:04,300 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:04,301 DEBUG: Start: Training
+2016-09-08 10:00:04,301 DEBUG: Info: Time for Training: 0.0347349643707[s]
+2016-09-08 10:00:04,301 DEBUG: Done: Training
+2016-09-08 10:00:04,301 DEBUG: Start: Predicting
+2016-09-08 10:00:04,307 DEBUG: Done: Predicting
+2016-09-08 10:00:04,307 DEBUG: Start: Getting Results
+2016-09-08 10:00:04,347 DEBUG: Done: Getting Results
+2016-09-08 10:00:04,347 INFO: Classification on Fake database for View0 with KNN
+
+accuracy_score on train : 0.580952380952
+accuracy_score on test : 0.6
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 24
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.580952380952
+ - Score on test : 0.6
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.661538461538
+ - Score on test : 0.678571428571
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.661538461538
+ - Score on test : 0.678571428571
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.419047619048
+ - Score on test : 0.4
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.580952380952
+ - Score on test : 0.6
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.130162282504
+ - Score on test : 0.171735516296
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.601398601399
+ - Score on test : 0.612903225806
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.735042735043
+ - Score on test : 0.76
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.561069754618
+ - Score on test : 0.58
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.419047619048
+ - Score on test : 0.4
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:04,347 INFO: Done: Result Analysis
+2016-09-08 10:00:04,669 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:04,669 DEBUG: Start: Training
+2016-09-08 10:00:04,730 DEBUG: Info: Time for Training: 0.462595939636[s]
+2016-09-08 10:00:04,730 DEBUG: Done: Training
+2016-09-08 10:00:04,730 DEBUG: Start: Predicting
+2016-09-08 10:00:04,737 DEBUG: Done: Predicting
+2016-09-08 10:00:04,737 DEBUG: Start: Getting Results
+2016-09-08 10:00:04,771 DEBUG: Done: Getting Results
+2016-09-08 10:00:04,771 INFO: Classification on Fake database for View0 with RandomForest
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 24, max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.52427184466
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.52427184466
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.111088444626
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.509433962264
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.54
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.445
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:04,771 INFO: Done: Result Analysis
+2016-09-08 10:00:04,916 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:04,916 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 10:00:04,917 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:04,917 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:04,917 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 10:00:04,917 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:04,918 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:04,918 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:04,918 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:04,918 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:04,919 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:04,919 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:04,919 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:04,919 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:04,964 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:04,964 DEBUG: Start: Training
+2016-09-08 10:00:04,965 DEBUG: Info: Time for Training: 0.049379825592[s]
+2016-09-08 10:00:04,965 DEBUG: Done: Training
+2016-09-08 10:00:04,965 DEBUG: Start: Predicting
+2016-09-08 10:00:04,971 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:04,971 DEBUG: Start: Training
+2016-09-08 10:00:04,979 DEBUG: Done: Predicting
+2016-09-08 10:00:04,980 DEBUG: Start: Getting Results
+2016-09-08 10:00:04,997 DEBUG: Info: Time for Training: 0.0806729793549[s]
+2016-09-08 10:00:04,997 DEBUG: Done: Training
+2016-09-08 10:00:04,997 DEBUG: Start: Predicting
+2016-09-08 10:00:05,000 DEBUG: Done: Predicting
+2016-09-08 10:00:05,000 DEBUG: Start: Getting Results
+2016-09-08 10:00:05,005 DEBUG: Done: Getting Results
+2016-09-08 10:00:05,005 INFO: Classification on Fake database for View0 with SGD
+
+accuracy_score on train : 0.57619047619
+accuracy_score on test : 0.644444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.57619047619
+ - Score on test : 0.644444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.661596958175
+ - Score on test : 0.724137931034
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.661596958175
+ - Score on test : 0.724137931034
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.42380952381
+ - Score on test : 0.355555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.57619047619
+ - Score on test : 0.644444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.117819078215
+ - Score on test : 0.269679944985
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.595890410959
+ - Score on test : 0.636363636364
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.74358974359
+ - Score on test : 0.84
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.55459057072
+ - Score on test : 0.62
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.42380952381
+ - Score on test : 0.355555555556
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:05,005 INFO: Done: Result Analysis
+2016-09-08 10:00:05,029 DEBUG: Done: Getting Results
+2016-09-08 10:00:05,029 INFO: Classification on Fake database for View0 with SVMLinear
+
+accuracy_score on train : 0.485714285714
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.571428571429
+ - Score on test : 0.609523809524
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.571428571429
+ - Score on test : 0.609523809524
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.0643090141189
+ - Score on test : 0.0662541348869
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.581818181818
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.615384615385
+ - Score on test : 0.64
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.468982630273
+ - Score on test : 0.5325
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:05,030 INFO: Done: Result Analysis
+2016-09-08 10:00:05,163 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:05,164 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMPoly
+2016-09-08 10:00:05,164 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:05,164 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:05,164 DEBUG: ### Classification - Database:Fake Feature:View0 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMRBF
+2016-09-08 10:00:05,164 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:05,164 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:05,165 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:05,165 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:05,165 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:05,165 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:05,165 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:05,165 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:05,165 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:05,212 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:05,213 DEBUG: Start: Training
+2016-09-08 10:00:05,218 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:05,219 DEBUG: Start: Training
+2016-09-08 10:00:05,230 DEBUG: Info: Time for Training: 0.0661790370941[s]
+2016-09-08 10:00:05,230 DEBUG: Done: Training
+2016-09-08 10:00:05,230 DEBUG: Start: Predicting
+2016-09-08 10:00:05,235 DEBUG: Done: Predicting
+2016-09-08 10:00:05,236 DEBUG: Start: Getting Results
+2016-09-08 10:00:05,239 DEBUG: Info: Time for Training: 0.0759570598602[s]
+2016-09-08 10:00:05,239 DEBUG: Done: Training
+2016-09-08 10:00:05,239 DEBUG: Start: Predicting
+2016-09-08 10:00:05,243 DEBUG: Done: Predicting
+2016-09-08 10:00:05,243 DEBUG: Start: Getting Results
+2016-09-08 10:00:05,275 DEBUG: Done: Getting Results
+2016-09-08 10:00:05,275 INFO: Classification on Fake database for View0 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.6
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.6
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.714285714286
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.714285714286
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.4
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.6
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.171377655346
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.592105263158
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.9
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5625
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.4
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:05,275 INFO: Done: Result Analysis
+2016-09-08 10:00:05,283 DEBUG: Done: Getting Results
+2016-09-08 10:00:05,283 INFO: Classification on Fake database for View0 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0973655073258
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.617647058824
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.42
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5475
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:05,283 INFO: Done: Result Analysis
+2016-09-08 10:00:05,410 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:05,410 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:05,411 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 10:00:05,411 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 10:00:05,411 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:05,411 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:05,411 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 10:00:05,411 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 10:00:05,411 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 10:00:05,411 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 10:00:05,412 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:05,412 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:05,412 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:05,412 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:05,447 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:05,447 DEBUG: Start: Training
+2016-09-08 10:00:05,450 DEBUG: Info: Time for Training: 0.0400369167328[s]
+2016-09-08 10:00:05,450 DEBUG: Done: Training
+2016-09-08 10:00:05,450 DEBUG: Start: Predicting
+2016-09-08 10:00:05,452 DEBUG: Done: Predicting
+2016-09-08 10:00:05,453 DEBUG: Start: Getting Results
+2016-09-08 10:00:05,462 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:05,462 DEBUG: Start: Training
+2016-09-08 10:00:05,467 DEBUG: Info: Time for Training: 0.0573270320892[s]
+2016-09-08 10:00:05,467 DEBUG: Done: Training
+2016-09-08 10:00:05,467 DEBUG: Start: Predicting
+2016-09-08 10:00:05,471 DEBUG: Done: Predicting
+2016-09-08 10:00:05,471 DEBUG: Start: Getting Results
+2016-09-08 10:00:05,499 DEBUG: Done: Getting Results
+2016-09-08 10:00:05,499 INFO: Classification on Fake database for View1 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.637168141593
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.637168141593
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0487950036474
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.571428571429
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.72
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5225
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:05,499 INFO: Done: Result Analysis
+2016-09-08 10:00:05,516 DEBUG: Done: Getting Results
+2016-09-08 10:00:05,516 INFO: Classification on Fake database for View1 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.555555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 9, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.555555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.655172413793
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.655172413793
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.444444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.555555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0674199862463
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.575757575758
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.76
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.53
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.444444444444
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:05,517 INFO: Done: Result Analysis
+2016-09-08 10:00:05,656 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:05,656 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 10:00:05,656 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:05,656 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:05,656 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 10:00:05,657 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:05,657 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 10:00:05,657 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 10:00:05,657 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 10:00:05,657 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:05,657 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 10:00:05,657 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:05,657 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:05,657 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:05,688 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:05,688 DEBUG: Start: Training
+2016-09-08 10:00:05,689 DEBUG: Info: Time for Training: 0.0336298942566[s]
+2016-09-08 10:00:05,689 DEBUG: Done: Training
+2016-09-08 10:00:05,689 DEBUG: Start: Predicting
+2016-09-08 10:00:05,695 DEBUG: Done: Predicting
+2016-09-08 10:00:05,695 DEBUG: Start: Getting Results
+2016-09-08 10:00:05,735 DEBUG: Done: Getting Results
+2016-09-08 10:00:05,735 INFO: Classification on Fake database for View1 with KNN
+
+accuracy_score on train : 0.566666666667
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 24
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.566666666667
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.659176029963
+ - Score on test : 0.542056074766
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.659176029963
+ - Score on test : 0.542056074766
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.433333333333
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.566666666667
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0939782359481
+ - Score on test : -0.123737644978
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.586666666667
+ - Score on test : 0.508771929825
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.752136752137
+ - Score on test : 0.58
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.542735042735
+ - Score on test : 0.44
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.433333333333
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:05,735 INFO: Done: Result Analysis
+2016-09-08 10:00:06,049 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:06,050 DEBUG: Start: Training
+2016-09-08 10:00:06,110 DEBUG: Info: Time for Training: 0.454261064529[s]
+2016-09-08 10:00:06,110 DEBUG: Done: Training
+2016-09-08 10:00:06,110 DEBUG: Start: Predicting
+2016-09-08 10:00:06,117 DEBUG: Done: Predicting
+2016-09-08 10:00:06,117 DEBUG: Start: Getting Results
+2016-09-08 10:00:06,151 DEBUG: Done: Getting Results
+2016-09-08 10:00:06,151 INFO: Classification on Fake database for View1 with RandomForest
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.566666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 24, max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.566666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.621359223301
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.621359223301
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.433333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.566666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.116137919381
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.603773584906
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.64
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5575
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.433333333333
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:06,151 INFO: Done: Result Analysis
+2016-09-08 10:00:06,304 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:06,304 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 10:00:06,304 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:06,304 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:06,305 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 10:00:06,305 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:06,305 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 10:00:06,305 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 10:00:06,305 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:06,305 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:06,305 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 10:00:06,306 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 10:00:06,306 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:06,306 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:06,348 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:06,349 DEBUG: Start: Training
+2016-09-08 10:00:06,349 DEBUG: Info: Time for Training: 0.0459690093994[s]
+2016-09-08 10:00:06,349 DEBUG: Done: Training
+2016-09-08 10:00:06,350 DEBUG: Start: Predicting
+2016-09-08 10:00:06,356 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:06,356 DEBUG: Start: Training
+2016-09-08 10:00:06,379 DEBUG: Done: Predicting
+2016-09-08 10:00:06,379 DEBUG: Start: Getting Results
+2016-09-08 10:00:06,381 DEBUG: Info: Time for Training: 0.0768840312958[s]
+2016-09-08 10:00:06,381 DEBUG: Done: Training
+2016-09-08 10:00:06,381 DEBUG: Start: Predicting
+2016-09-08 10:00:06,387 DEBUG: Done: Predicting
+2016-09-08 10:00:06,387 DEBUG: Start: Getting Results
+2016-09-08 10:00:06,406 DEBUG: Done: Getting Results
+2016-09-08 10:00:06,406 INFO: Classification on Fake database for View1 with SGD
+
+accuracy_score on train : 0.566666666667
+accuracy_score on test : 0.555555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.566666666667
+ - Score on test : 0.555555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.640316205534
+ - Score on test : 0.666666666667
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.640316205534
+ - Score on test : 0.666666666667
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.433333333333
+ - Score on test : 0.444444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.566666666667
+ - Score on test : 0.555555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.104925880155
+ - Score on test : 0.0597614304667
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.595588235294
+ - Score on test : 0.571428571429
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.692307692308
+ - Score on test : 0.8
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.550454921423
+ - Score on test : 0.525
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.433333333333
+ - Score on test : 0.444444444444
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:06,407 INFO: Done: Result Analysis
+2016-09-08 10:00:06,420 DEBUG: Done: Getting Results
+2016-09-08 10:00:06,420 INFO: Classification on Fake database for View1 with SVMLinear
+
+accuracy_score on train : 0.490476190476
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.490476190476
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.566801619433
+ - Score on test : 0.576923076923
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.566801619433
+ - Score on test : 0.576923076923
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.509523809524
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.490476190476
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.0479423260647
+ - Score on test : -3.54721613428e-17
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.538461538462
+ - Score on test : 0.555555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.598290598291
+ - Score on test : 0.6
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.476564653984
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.509523809524
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:06,420 INFO: Done: Result Analysis
+2016-09-08 10:00:06,547 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:06,547 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:06,547 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMPoly
+2016-09-08 10:00:06,548 DEBUG: ### Classification - Database:Fake Feature:View1 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMRBF
+2016-09-08 10:00:06,548 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:06,548 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:06,548 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 10:00:06,548 DEBUG: Info: Shape X_train:(210, 15), Length of y_train:210
+2016-09-08 10:00:06,549 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 10:00:06,549 DEBUG: Info: Shape X_test:(90, 15), Length of y_test:90
+2016-09-08 10:00:06,549 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:06,549 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:06,549 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:06,549 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:06,595 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:06,595 DEBUG: Start: Training
+2016-09-08 10:00:06,601 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:06,601 DEBUG: Start: Training
+2016-09-08 10:00:06,614 DEBUG: Info: Time for Training: 0.0678429603577[s]
+2016-09-08 10:00:06,614 DEBUG: Done: Training
+2016-09-08 10:00:06,615 DEBUG: Start: Predicting
+2016-09-08 10:00:06,620 DEBUG: Info: Time for Training: 0.0734059810638[s]
+2016-09-08 10:00:06,620 DEBUG: Done: Training
+2016-09-08 10:00:06,620 DEBUG: Start: Predicting
+2016-09-08 10:00:06,621 DEBUG: Done: Predicting
+2016-09-08 10:00:06,621 DEBUG: Start: Getting Results
+2016-09-08 10:00:06,624 DEBUG: Done: Predicting
+2016-09-08 10:00:06,624 DEBUG: Start: Getting Results
+2016-09-08 10:00:06,657 DEBUG: Done: Getting Results
+2016-09-08 10:00:06,657 DEBUG: Done: Getting Results
+2016-09-08 10:00:06,657 INFO: Classification on Fake database for View1 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.5
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.64
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.64
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.5
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.1
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.8
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4625
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.5
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:06,657 INFO: Classification on Fake database for View1 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.422222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0714285714286
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0714285714286
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.119522860933
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.04
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.47
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:06,657 INFO: Done: Result Analysis
+2016-09-08 10:00:06,657 INFO: Done: Result Analysis
+2016-09-08 10:00:06,793 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:06,793 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 10:00:06,793 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:06,794 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:06,794 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 10:00:06,794 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:06,794 DEBUG: Info: Shape X_train:(210, 18), Length of y_train:210
+2016-09-08 10:00:06,794 DEBUG: Info: Shape X_test:(90, 18), Length of y_test:90
+2016-09-08 10:00:06,794 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:06,794 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:06,795 DEBUG: Info: Shape X_train:(210, 18), Length of y_train:210
+2016-09-08 10:00:06,795 DEBUG: Info: Shape X_test:(90, 18), Length of y_test:90
+2016-09-08 10:00:06,795 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:06,795 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:06,834 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:06,834 DEBUG: Start: Training
+2016-09-08 10:00:06,837 DEBUG: Info: Time for Training: 0.0438461303711[s]
+2016-09-08 10:00:06,837 DEBUG: Done: Training
+2016-09-08 10:00:06,837 DEBUG: Start: Predicting
+2016-09-08 10:00:06,839 DEBUG: Done: Predicting
+2016-09-08 10:00:06,839 DEBUG: Start: Getting Results
+2016-09-08 10:00:06,847 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:06,847 DEBUG: Start: Training
+2016-09-08 10:00:06,852 DEBUG: Info: Time for Training: 0.0599958896637[s]
+2016-09-08 10:00:06,852 DEBUG: Done: Training
+2016-09-08 10:00:06,852 DEBUG: Start: Predicting
+2016-09-08 10:00:06,855 DEBUG: Done: Predicting
+2016-09-08 10:00:06,855 DEBUG: Start: Getting Results
+2016-09-08 10:00:06,885 DEBUG: Done: Getting Results
+2016-09-08 10:00:06,885 INFO: Classification on Fake database for View2 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.433333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.43956043956
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.43956043956
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.124719695673
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.487804878049
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4375
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:06,885 INFO: Done: Result Analysis
+2016-09-08 10:00:06,896 DEBUG: Done: Getting Results
+2016-09-08 10:00:06,896 INFO: Classification on Fake database for View2 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.433333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 9, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.43956043956
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.43956043956
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.124719695673
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.487804878049
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4375
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:06,897 INFO: Done: Result Analysis
+2016-09-08 10:00:07,034 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:07,034 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:07,034 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 10:00:07,034 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 10:00:07,035 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:07,035 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:07,035 DEBUG: Info: Shape X_train:(210, 18), Length of y_train:210
+2016-09-08 10:00:07,035 DEBUG: Info: Shape X_train:(210, 18), Length of y_train:210
+2016-09-08 10:00:07,035 DEBUG: Info: Shape X_test:(90, 18), Length of y_test:90
+2016-09-08 10:00:07,035 DEBUG: Info: Shape X_test:(90, 18), Length of y_test:90
+2016-09-08 10:00:07,035 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:07,035 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:07,036 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:07,036 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:07,067 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:07,067 DEBUG: Start: Training
+2016-09-08 10:00:07,067 DEBUG: Info: Time for Training: 0.0337820053101[s]
+2016-09-08 10:00:07,067 DEBUG: Done: Training
+2016-09-08 10:00:07,068 DEBUG: Start: Predicting
+2016-09-08 10:00:07,074 DEBUG: Done: Predicting
+2016-09-08 10:00:07,074 DEBUG: Start: Getting Results
+2016-09-08 10:00:07,115 DEBUG: Done: Getting Results
+2016-09-08 10:00:07,115 INFO: Classification on Fake database for View2 with KNN
+
+accuracy_score on train : 0.547619047619
+accuracy_score on test : 0.466666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 24
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.547619047619
+ - Score on test : 0.466666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.649446494465
+ - Score on test : 0.586206896552
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.649446494465
+ - Score on test : 0.586206896552
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.452380952381
+ - Score on test : 0.533333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.547619047619
+ - Score on test : 0.466666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0476928413215
+ - Score on test : -0.134839972493
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.571428571429
+ - Score on test : 0.515151515152
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.752136752137
+ - Score on test : 0.68
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.521229666391
+ - Score on test : 0.44
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.452380952381
+ - Score on test : 0.533333333333
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:07,115 INFO: Done: Result Analysis
+2016-09-08 10:00:07,444 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:07,444 DEBUG: Start: Training
+2016-09-08 10:00:07,507 DEBUG: Info: Time for Training: 0.473404169083[s]
+2016-09-08 10:00:07,507 DEBUG: Done: Training
+2016-09-08 10:00:07,507 DEBUG: Start: Predicting
+2016-09-08 10:00:07,514 DEBUG: Done: Predicting
+2016-09-08 10:00:07,514 DEBUG: Start: Getting Results
+2016-09-08 10:00:07,544 DEBUG: Done: Getting Results
+2016-09-08 10:00:07,544 INFO: Classification on Fake database for View2 with RandomForest
+
+accuracy_score on train : 0.995238095238
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 24, max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.995708154506
+ - Score on test : 0.468085106383
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.995708154506
+ - Score on test : 0.468085106383
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.990406794809
+ - Score on test : -0.109345881217
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.991452991453
+ - Score on test : 0.44
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.995726495726
+ - Score on test : 0.445
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:07,544 INFO: Done: Result Analysis
+2016-09-08 10:00:07,685 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:07,685 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:07,685 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 10:00:07,685 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 10:00:07,685 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:07,686 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:07,686 DEBUG: Info: Shape X_train:(210, 18), Length of y_train:210
+2016-09-08 10:00:07,686 DEBUG: Info: Shape X_train:(210, 18), Length of y_train:210
+2016-09-08 10:00:07,686 DEBUG: Info: Shape X_test:(90, 18), Length of y_test:90
+2016-09-08 10:00:07,686 DEBUG: Info: Shape X_test:(90, 18), Length of y_test:90
+2016-09-08 10:00:07,686 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:07,686 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:07,686 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:07,687 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:07,730 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:07,730 DEBUG: Start: Training
+2016-09-08 10:00:07,731 DEBUG: Info: Time for Training: 0.0463371276855[s]
+2016-09-08 10:00:07,731 DEBUG: Done: Training
+2016-09-08 10:00:07,731 DEBUG: Start: Predicting
+2016-09-08 10:00:07,737 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:07,737 DEBUG: Start: Training
+2016-09-08 10:00:07,744 DEBUG: Done: Predicting
+2016-09-08 10:00:07,744 DEBUG: Start: Getting Results
+2016-09-08 10:00:07,758 DEBUG: Info: Time for Training: 0.0734429359436[s]
+2016-09-08 10:00:07,758 DEBUG: Done: Training
+2016-09-08 10:00:07,758 DEBUG: Start: Predicting
+2016-09-08 10:00:07,762 DEBUG: Done: Predicting
+2016-09-08 10:00:07,762 DEBUG: Start: Getting Results
+2016-09-08 10:00:07,767 DEBUG: Done: Getting Results
+2016-09-08 10:00:07,768 INFO: Classification on Fake database for View2 with SGD
+
+accuracy_score on train : 0.619047619048
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.619047619048
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.701492537313
+ - Score on test : 0.592592592593
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.701492537313
+ - Score on test : 0.592592592593
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.380952380952
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.619047619048
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.210547659218
+ - Score on test : -0.0103806849817
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.622516556291
+ - Score on test : 0.551724137931
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.803418803419
+ - Score on test : 0.64
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.595257788806
+ - Score on test : 0.495
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.380952380952
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:07,768 INFO: Done: Result Analysis
+2016-09-08 10:00:07,797 DEBUG: Done: Getting Results
+2016-09-08 10:00:07,797 INFO: Classification on Fake database for View2 with SVMLinear
+
+accuracy_score on train : 0.47619047619
+accuracy_score on test : 0.555555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.555555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.521739130435
+ - Score on test : 0.565217391304
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.521739130435
+ - Score on test : 0.565217391304
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.444444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.555555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.0568633060564
+ - Score on test : 0.119522860933
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.530973451327
+ - Score on test : 0.619047619048
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.512820512821
+ - Score on test : 0.52
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.471464019851
+ - Score on test : 0.56
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.444444444444
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:07,797 INFO: Done: Result Analysis
+2016-09-08 10:00:07,935 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:07,935 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMPoly
+2016-09-08 10:00:07,935 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:07,935 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:07,935 DEBUG: ### Classification - Database:Fake Feature:View2 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMRBF
+2016-09-08 10:00:07,935 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:07,936 DEBUG: Info: Shape X_train:(210, 18), Length of y_train:210
+2016-09-08 10:00:07,936 DEBUG: Info: Shape X_test:(90, 18), Length of y_test:90
+2016-09-08 10:00:07,936 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:07,936 DEBUG: Info: Shape X_train:(210, 18), Length of y_train:210
+2016-09-08 10:00:07,936 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:07,936 DEBUG: Info: Shape X_test:(90, 18), Length of y_test:90
+2016-09-08 10:00:07,936 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:07,937 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:07,984 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:07,985 DEBUG: Start: Training
+2016-09-08 10:00:07,990 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:07,990 DEBUG: Start: Training
+2016-09-08 10:00:08,003 DEBUG: Info: Time for Training: 0.0686159133911[s]
+2016-09-08 10:00:08,003 DEBUG: Done: Training
+2016-09-08 10:00:08,003 DEBUG: Start: Predicting
+2016-09-08 10:00:08,007 DEBUG: Info: Time for Training: 0.0732269287109[s]
+2016-09-08 10:00:08,007 DEBUG: Done: Training
+2016-09-08 10:00:08,008 DEBUG: Start: Predicting
+2016-09-08 10:00:08,009 DEBUG: Done: Predicting
+2016-09-08 10:00:08,009 DEBUG: Start: Getting Results
+2016-09-08 10:00:08,012 DEBUG: Done: Predicting
+2016-09-08 10:00:08,012 DEBUG: Start: Getting Results
+2016-09-08 10:00:08,043 DEBUG: Done: Getting Results
+2016-09-08 10:00:08,043 INFO: Classification on Fake database for View2 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.107142857143
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.107142857143
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0298807152334
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.06
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4925
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:08,044 INFO: Done: Result Analysis
+2016-09-08 10:00:08,044 DEBUG: Done: Getting Results
+2016-09-08 10:00:08,044 INFO: Classification on Fake database for View2 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.687022900763
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.687022900763
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 4.13755692208e-17
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.555555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.9
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:08,044 INFO: Done: Result Analysis
+2016-09-08 10:00:08,183 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:08,183 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:08,183 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : Adaboost
+2016-09-08 10:00:08,183 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:08,183 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : DecisionTree
+2016-09-08 10:00:08,183 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:08,184 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:08,184 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:08,184 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:08,184 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:08,184 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:08,184 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:08,185 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:08,185 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:08,221 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:08,221 DEBUG: Start: Training
+2016-09-08 10:00:08,223 DEBUG: Info: Time for Training: 0.0409498214722[s]
+2016-09-08 10:00:08,223 DEBUG: Done: Training
+2016-09-08 10:00:08,223 DEBUG: Start: Predicting
+2016-09-08 10:00:08,226 DEBUG: Done: Predicting
+2016-09-08 10:00:08,226 DEBUG: Start: Getting Results
+2016-09-08 10:00:08,235 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:08,235 DEBUG: Start: Training
+2016-09-08 10:00:08,239 DEBUG: Info: Time for Training: 0.0573840141296[s]
+2016-09-08 10:00:08,240 DEBUG: Done: Training
+2016-09-08 10:00:08,240 DEBUG: Start: Predicting
+2016-09-08 10:00:08,242 DEBUG: Done: Predicting
+2016-09-08 10:00:08,243 DEBUG: Start: Getting Results
+2016-09-08 10:00:08,267 DEBUG: Done: Getting Results
+2016-09-08 10:00:08,268 INFO: Classification on Fake database for View3 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.588888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.626262626263
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.626262626263
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.411111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.169618786115
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.632653061224
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.62
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.585
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.411111111111
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:08,268 INFO: Done: Result Analysis
+2016-09-08 10:00:08,280 DEBUG: Done: Getting Results
+2016-09-08 10:00:08,280 INFO: Classification on Fake database for View3 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.577777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 9, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.577777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.62
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.62
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.422222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.577777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.145
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.62
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.62
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5725
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.422222222222
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:08,281 INFO: Done: Result Analysis
+2016-09-08 10:00:08,439 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:08,439 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : KNN
+2016-09-08 10:00:08,439 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:08,439 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:08,439 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : RandomForest
+2016-09-08 10:00:08,440 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:08,440 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:08,440 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:08,440 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:08,441 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:08,441 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:08,441 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:08,441 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:08,441 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:08,489 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:08,489 DEBUG: Start: Training
+2016-09-08 10:00:08,490 DEBUG: Info: Time for Training: 0.0522999763489[s]
+2016-09-08 10:00:08,490 DEBUG: Done: Training
+2016-09-08 10:00:08,490 DEBUG: Start: Predicting
+2016-09-08 10:00:08,497 DEBUG: Done: Predicting
+2016-09-08 10:00:08,497 DEBUG: Start: Getting Results
+2016-09-08 10:00:08,532 DEBUG: Done: Getting Results
+2016-09-08 10:00:08,532 INFO: Classification on Fake database for View3 with KNN
+
+accuracy_score on train : 0.6
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 24
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.688888888889
+ - Score on test : 0.637168141593
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.688888888889
+ - Score on test : 0.637168141593
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.4
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.167225897665
+ - Score on test : 0.0487950036474
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.607843137255
+ - Score on test : 0.571428571429
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.794871794872
+ - Score on test : 0.72
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.574855252275
+ - Score on test : 0.5225
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.4
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:08,532 INFO: Done: Result Analysis
+2016-09-08 10:00:08,857 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:08,857 DEBUG: Start: Training
+2016-09-08 10:00:08,918 DEBUG: Info: Time for Training: 0.479932069778[s]
+2016-09-08 10:00:08,918 DEBUG: Done: Training
+2016-09-08 10:00:08,918 DEBUG: Start: Predicting
+2016-09-08 10:00:08,925 DEBUG: Done: Predicting
+2016-09-08 10:00:08,925 DEBUG: Start: Getting Results
+2016-09-08 10:00:08,961 DEBUG: Done: Getting Results
+2016-09-08 10:00:08,961 INFO: Classification on Fake database for View3 with RandomForest
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 24, max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.117218854031
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.509090909091
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.56
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4425
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:08,961 INFO: Done: Result Analysis
+2016-09-08 10:00:09,084 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:09,084 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SGD
+2016-09-08 10:00:09,084 DEBUG: ### Main Programm for Classification MonoView
+2016-09-08 10:00:09,084 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:09,085 DEBUG: ### Classification - Database:Fake Feature:View3 train_size:0.7, CrossValidation k-folds:5, cores:1, algorithm : SVMLinear
+2016-09-08 10:00:09,085 DEBUG: Start: Determine Train/Test split
+2016-09-08 10:00:09,085 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:09,086 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:09,086 DEBUG: Info: Shape X_train:(210, 12), Length of y_train:210
+2016-09-08 10:00:09,086 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:09,086 DEBUG: Info: Shape X_test:(90, 12), Length of y_test:90
+2016-09-08 10:00:09,086 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:09,086 DEBUG: Done: Determine Train/Test split
+2016-09-08 10:00:09,086 DEBUG: Start: RandomSearch best settings with 1 iterations
+2016-09-08 10:00:09,129 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:09,129 DEBUG: Start: Training
+2016-09-08 10:00:09,130 DEBUG: Info: Time for Training: 0.0473730564117[s]
+2016-09-08 10:00:09,130 DEBUG: Done: Training
+2016-09-08 10:00:09,130 DEBUG: Start: Predicting
+2016-09-08 10:00:09,136 DEBUG: Done: RandomSearch best settings
+2016-09-08 10:00:09,136 DEBUG: Start: Training
+2016-09-08 10:00:09,148 DEBUG: Done: Predicting
+2016-09-08 10:00:09,148 DEBUG: Start: Getting Results
+2016-09-08 10:00:09,155 DEBUG: Info: Time for Training: 0.0714659690857[s]
+2016-09-08 10:00:09,155 DEBUG: Done: Training
+2016-09-08 10:00:09,155 DEBUG: Start: Predicting
+2016-09-08 10:00:09,158 DEBUG: Done: Predicting
+2016-09-08 10:00:09,158 DEBUG: Start: Getting Results
+2016-09-08 10:00:09,171 DEBUG: Done: Getting Results
+2016-09-08 10:00:09,171 INFO: Classification on Fake database for View3 with SGD
+
+accuracy_score on train : 0.642857142857
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.642857142857
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.701195219124
+ - Score on test : 0.596153846154
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.701195219124
+ - Score on test : 0.596153846154
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.357142857143
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.642857142857
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.266179454365
+ - Score on test : 0.0456435464588
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.65671641791
+ - Score on test : 0.574074074074
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.752136752137
+ - Score on test : 0.62
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.628756548111
+ - Score on test : 0.5225
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.357142857143
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:09,171 INFO: Done: Result Analysis
+2016-09-08 10:00:09,189 DEBUG: Done: Getting Results
+2016-09-08 10:00:09,190 INFO: Classification on Fake database for View3 with SVMLinear
+
+accuracy_score on train : 0.47619047619
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.541666666667
+ - Score on test : 0.576923076923
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.541666666667
+ - Score on test : 0.576923076923
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.068670723144
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.528455284553
+ - Score on test : 0.555555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.555555555556
+ - Score on test : 0.6
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.465949820789
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
+2016-09-08 10:00:09,190 INFO: Done: Result Analysis
+2016-09-08 10:00:09,488 INFO: ### Main Programm for Multiview Classification
+2016-09-08 10:00:09,488 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 10:00:09,489 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 10:00:09,490 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 10:00:09,491 INFO: Info: Shape of View2 :(300, 18)
+2016-09-08 10:00:09,492 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 10:00:09,493 INFO: Done: Read Database Files
+2016-09-08 10:00:09,493 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 10:00:09,496 INFO: ### Main Programm for Multiview Classification
+2016-09-08 10:00:09,497 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 10:00:09,498 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 10:00:09,498 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 10:00:09,499 INFO: Info: Shape of View2 :(300, 18)
+2016-09-08 10:00:09,500 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 10:00:09,500 INFO: Done: Read Database Files
+2016-09-08 10:00:09,500 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 10:00:09,502 INFO: Done: Determine validation split
+2016-09-08 10:00:09,502 INFO: Start: Determine 5 folds
+2016-09-08 10:00:09,507 INFO: Done: Determine validation split
+2016-09-08 10:00:09,508 INFO: Start: Determine 5 folds
+2016-09-08 10:00:09,515 INFO: Info: Length of Learning Sets: 170
+2016-09-08 10:00:09,515 INFO: Info: Length of Testing Sets: 41
+2016-09-08 10:00:09,516 INFO: Info: Length of Validation Set: 89
+2016-09-08 10:00:09,516 INFO: Done: Determine folds
+2016-09-08 10:00:09,516 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 10:00:09,516 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:09,516 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:09,519 INFO: Info: Length of Learning Sets: 170
+2016-09-08 10:00:09,519 INFO: Info: Length of Testing Sets: 41
+2016-09-08 10:00:09,519 INFO: Info: Length of Validation Set: 89
+2016-09-08 10:00:09,519 INFO: Done: Determine folds
+2016-09-08 10:00:09,519 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 10:00:09,520 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:09,520 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:09,608 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:09,608 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:09,610 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:09,610 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:09,693 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:09,693 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:09,696 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:09,696 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:09,780 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:09,780 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:09,783 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:09,783 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:09,866 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:09,869 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:09,946 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:09,946 INFO: Start: Classification
+2016-09-08 10:00:09,947 INFO: Start: Fold number 1
+2016-09-08 10:00:09,974 INFO: Start: Classification
+2016-09-08 10:00:09,986 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:09,986 INFO: Start: Classification
+2016-09-08 10:00:09,986 INFO: Start: Fold number 1
+2016-09-08 10:00:10,000 INFO: Done: Fold number 1
+2016-09-08 10:00:10,000 INFO: Start: Fold number 2
+2016-09-08 10:00:10,013 INFO: Start: Classification
+2016-09-08 10:00:10,026 INFO: Start: Classification
+2016-09-08 10:00:10,051 INFO: Done: Fold number 2
+2016-09-08 10:00:10,052 INFO: Start: Fold number 3
+2016-09-08 10:00:10,078 INFO: Start: Classification
+2016-09-08 10:00:10,083 INFO: Done: Fold number 1
+2016-09-08 10:00:10,083 INFO: Start: Fold number 2
+2016-09-08 10:00:10,104 INFO: Done: Fold number 3
+2016-09-08 10:00:10,104 INFO: Start: Fold number 4
+2016-09-08 10:00:10,109 INFO: Start: Classification
+2016-09-08 10:00:10,130 INFO: Start: Classification
+2016-09-08 10:00:10,156 INFO: Done: Fold number 4
+2016-09-08 10:00:10,156 INFO: Start: Fold number 5
+2016-09-08 10:00:10,179 INFO: Done: Fold number 2
+2016-09-08 10:00:10,179 INFO: Start: Fold number 3
+2016-09-08 10:00:10,182 INFO: Start: Classification
+2016-09-08 10:00:10,206 INFO: Start: Classification
+2016-09-08 10:00:10,208 INFO: Done: Fold number 5
+2016-09-08 10:00:10,208 INFO: Done: Classification
+2016-09-08 10:00:10,208 INFO: Info: Time for Classification: 0[s]
+2016-09-08 10:00:10,208 INFO: Start: Result Analysis for Fusion
+2016-09-08 10:00:10,276 INFO: Done: Fold number 3
+2016-09-08 10:00:10,276 INFO: Start: Fold number 4
+2016-09-08 10:00:10,304 INFO: Start: Classification
+2016-09-08 10:00:10,339 INFO: Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 59.6470588235
+ -On Test : 50.7317073171
+ -On Validation : 47.191011236
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Bayesian Inference using a weight for each view : 0.395042964582, 0.135468886361, 0.187401197987, 0.282086951071
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - SGDClassifier with loss : modified_huber, penalty : l2
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 10:00:10,339 INFO: Done: Result Analysis
+2016-09-08 10:00:10,374 INFO: Done: Fold number 4
+2016-09-08 10:00:10,374 INFO: Start: Fold number 5
+2016-09-08 10:00:10,399 INFO: Start: Classification
+2016-09-08 10:00:10,465 INFO: Done: Fold number 5
+2016-09-08 10:00:10,465 INFO: Done: Classification
+2016-09-08 10:00:10,466 INFO: Info: Time for Classification: 0[s]
+2016-09-08 10:00:10,466 INFO: Start: Result Analysis for Fusion
+2016-09-08 10:00:10,588 INFO: Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 55.2941176471
+ -On Test : 56.0975609756
+ -On Validation : 56.1797752809
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Majority Voting
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - SGDClassifier with loss : modified_huber, penalty : l2
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:03 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 10:00:10,588 INFO: Done: Result Analysis
+2016-09-08 10:00:10,737 INFO: ### Main Programm for Multiview Classification
+2016-09-08 10:00:10,738 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 10:00:10,738 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 10:00:10,739 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 10:00:10,740 INFO: Info: Shape of View2 :(300, 18)
+2016-09-08 10:00:10,740 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 10:00:10,741 INFO: Done: Read Database Files
+2016-09-08 10:00:10,741 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 10:00:10,744 INFO: ### Main Programm for Multiview Classification
+2016-09-08 10:00:10,745 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 10:00:10,745 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 10:00:10,746 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 10:00:10,746 INFO: Info: Shape of View2 :(300, 18)
+2016-09-08 10:00:10,747 INFO: Done: Determine validation split
+2016-09-08 10:00:10,747 INFO: Start: Determine 5 folds
+2016-09-08 10:00:10,747 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 10:00:10,747 INFO: Done: Read Database Files
+2016-09-08 10:00:10,747 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 10:00:10,752 INFO: Done: Determine validation split
+2016-09-08 10:00:10,752 INFO: Start: Determine 5 folds
+2016-09-08 10:00:10,754 INFO: Info: Length of Learning Sets: 170
+2016-09-08 10:00:10,754 INFO: Info: Length of Testing Sets: 41
+2016-09-08 10:00:10,754 INFO: Info: Length of Validation Set: 89
+2016-09-08 10:00:10,755 INFO: Done: Determine folds
+2016-09-08 10:00:10,755 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 10:00:10,755 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:10,755 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:10,761 INFO: Info: Length of Learning Sets: 170
+2016-09-08 10:00:10,761 INFO: Info: Length of Testing Sets: 41
+2016-09-08 10:00:10,761 INFO: Info: Length of Validation Set: 89
+2016-09-08 10:00:10,761 INFO: Done: Determine folds
+2016-09-08 10:00:10,761 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 10:00:10,762 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:10,762 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:10,811 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:10,811 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:10,816 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:10,816 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:10,862 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:10,862 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:10,867 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:10,867 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:10,912 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:10,913 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:10,918 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:10,918 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:10,962 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:10,962 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:10,962 INFO: Start: Classification
+2016-09-08 10:00:10,963 INFO: Start: Fold number 1
+2016-09-08 10:00:10,968 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:11,027 INFO: Start: Classification
+2016-09-08 10:00:11,048 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:11,048 INFO: Start: Classification
+2016-09-08 10:00:11,048 INFO: Start: Fold number 1
+2016-09-08 10:00:11,057 INFO: Done: Fold number 1
+2016-09-08 10:00:11,057 INFO: Start: Fold number 2
+2016-09-08 10:00:11,074 INFO: Start: Classification
+2016-09-08 10:00:11,103 INFO: Start: Classification
+2016-09-08 10:00:11,104 INFO: Done: Fold number 1
+2016-09-08 10:00:11,105 INFO: Start: Fold number 2
+2016-09-08 10:00:11,131 INFO: Start: Classification
+2016-09-08 10:00:11,133 INFO: Done: Fold number 2
+2016-09-08 10:00:11,133 INFO: Start: Fold number 3
+2016-09-08 10:00:11,162 INFO: Done: Fold number 2
+2016-09-08 10:00:11,162 INFO: Start: Fold number 3
+2016-09-08 10:00:11,180 INFO: Start: Classification
+2016-09-08 10:00:11,189 INFO: Start: Classification
+2016-09-08 10:00:11,210 INFO: Done: Fold number 3
+2016-09-08 10:00:11,210 INFO: Start: Fold number 4
+2016-09-08 10:00:11,220 INFO: Done: Fold number 3
+2016-09-08 10:00:11,220 INFO: Start: Fold number 4
+2016-09-08 10:00:11,247 INFO: Start: Classification
+2016-09-08 10:00:11,255 INFO: Start: Classification
+2016-09-08 10:00:11,277 INFO: Done: Fold number 4
+2016-09-08 10:00:11,277 INFO: Start: Fold number 5
+2016-09-08 10:00:11,285 INFO: Done: Fold number 4
+2016-09-08 10:00:11,286 INFO: Start: Fold number 5
+2016-09-08 10:00:11,304 INFO: Start: Classification
+2016-09-08 10:00:11,331 INFO: Start: Classification
+2016-09-08 10:00:11,335 INFO: Done: Fold number 5
+2016-09-08 10:00:11,335 INFO: Done: Classification
+2016-09-08 10:00:11,335 INFO: Info: Time for Classification: 0[s]
+2016-09-08 10:00:11,335 INFO: Start: Result Analysis for Fusion
+2016-09-08 10:00:11,361 INFO: Done: Fold number 5
+2016-09-08 10:00:11,362 INFO: Done: Classification
+2016-09-08 10:00:11,362 INFO: Info: Time for Classification: 0[s]
+2016-09-08 10:00:11,362 INFO: Start: Result Analysis for Fusion
+2016-09-08 10:00:11,472 INFO: Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 25.6470588235
+ -On Test : 23.4146341463
+ -On Validation : 27.4157303371
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Weighted linear using a weight for each view : 1.0, 0.342921905986, 0.474381813597, 0.714066510131
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - SGDClassifier with loss : modified_huber, penalty : l2
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 10:00:11,473 INFO: Done: Result Analysis
+2016-09-08 10:00:11,495 INFO: Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 60.4705882353
+ -On Test : 47.8048780488
+ -On Validation : 53.2584269663
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with SVM for linear
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - SGDClassifier with loss : modified_huber, penalty : l2
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 10:00:11,495 INFO: Done: Result Analysis
+2016-09-08 10:00:11,576 INFO: ### Main Programm for Multiview Classification
+2016-09-08 10:00:11,576 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 10:00:11,577 INFO: ### Main Programm for Multiview Classification
+2016-09-08 10:00:11,577 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 10:00:11,578 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 10:00:11,578 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 10:00:11,578 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 10:00:11,578 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 10:00:11,579 INFO: Info: Shape of View2 :(300, 18)
+2016-09-08 10:00:11,579 INFO: Info: Shape of View2 :(300, 18)
+2016-09-08 10:00:11,580 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 10:00:11,580 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 10:00:11,580 INFO: Done: Read Database Files
+2016-09-08 10:00:11,580 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 10:00:11,580 INFO: Done: Read Database Files
+2016-09-08 10:00:11,580 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 10:00:11,586 INFO: Done: Determine validation split
+2016-09-08 10:00:11,586 INFO: Done: Determine validation split
+2016-09-08 10:00:11,586 INFO: Start: Determine 5 folds
+2016-09-08 10:00:11,586 INFO: Start: Determine 5 folds
+2016-09-08 10:00:11,596 INFO: Info: Length of Learning Sets: 170
+2016-09-08 10:00:11,596 INFO: Info: Length of Testing Sets: 41
+2016-09-08 10:00:11,596 INFO: Info: Length of Validation Set: 89
+2016-09-08 10:00:11,596 INFO: Done: Determine folds
+2016-09-08 10:00:11,596 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 10:00:11,596 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:11,597 DEBUG: Start: Random search for Adaboost with 1 iterations
+2016-09-08 10:00:11,597 INFO: Info: Length of Learning Sets: 170
+2016-09-08 10:00:11,597 INFO: Info: Length of Testing Sets: 41
+2016-09-08 10:00:11,598 INFO: Info: Length of Validation Set: 89
+2016-09-08 10:00:11,598 INFO: Done: Determine folds
+2016-09-08 10:00:11,598 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 10:00:11,598 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:11,598 DEBUG: Start: Random search for DecisionTree with 1 iterations
+2016-09-08 10:00:11,664 DEBUG: Done: Random search for DecisionTree
+2016-09-08 10:00:11,752 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:11,752 INFO: Start: Classification
+2016-09-08 10:00:11,752 INFO: Start: Fold number 1
+2016-09-08 10:00:11,788 INFO: Start: Classification
+2016-09-08 10:00:11,830 INFO: Done: Fold number 1
+2016-09-08 10:00:11,831 INFO: Start: Fold number 2
+2016-09-08 10:00:11,864 INFO: Start: Classification
+2016-09-08 10:00:11,867 DEBUG: Done: Random search for Adaboost
+2016-09-08 10:00:11,906 INFO: Done: Fold number 2
+2016-09-08 10:00:11,906 INFO: Start: Fold number 3
+2016-09-08 10:00:11,940 INFO: Start: Classification
+2016-09-08 10:00:11,944 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:11,944 INFO: Start: Classification
+2016-09-08 10:00:11,944 INFO: Start: Fold number 1
+2016-09-08 10:00:11,980 INFO: Done: Fold number 3
+2016-09-08 10:00:11,980 INFO: Start: Fold number 4
+2016-09-08 10:00:11,984 INFO: Start: Classification
+2016-09-08 10:00:12,015 INFO: Start: Classification
+2016-09-08 10:00:12,026 INFO: Done: Fold number 1
+2016-09-08 10:00:12,026 INFO: Start: Fold number 2
+2016-09-08 10:00:12,056 INFO: Done: Fold number 4
+2016-09-08 10:00:12,057 INFO: Start: Fold number 5
+2016-09-08 10:00:12,066 INFO: Start: Classification
+2016-09-08 10:00:12,091 INFO: Start: Classification
+2016-09-08 10:00:12,108 INFO: Done: Fold number 2
+2016-09-08 10:00:12,108 INFO: Start: Fold number 3
+2016-09-08 10:00:12,133 INFO: Done: Fold number 5
+2016-09-08 10:00:12,133 INFO: Done: Classification
+2016-09-08 10:00:12,133 INFO: Info: Time for Classification: 0[s]
+2016-09-08 10:00:12,133 INFO: Start: Result Analysis for Fusion
+2016-09-08 10:00:12,147 INFO: Start: Classification
+2016-09-08 10:00:12,192 INFO: Done: Fold number 3
+2016-09-08 10:00:12,192 INFO: Start: Fold number 4
+2016-09-08 10:00:12,232 INFO: Start: Classification
+2016-09-08 10:00:12,263 INFO: Done: Fold number 4
+2016-09-08 10:00:12,263 INFO: Start: Fold number 5
+2016-09-08 10:00:12,307 INFO: Start: Classification
+2016-09-08 10:00:12,350 INFO: Done: Fold number 5
+2016-09-08 10:00:12,351 INFO: Done: Classification
+2016-09-08 10:00:12,351 INFO: Info: Time for Classification: 0[s]
+2016-09-08 10:00:12,351 INFO: Start: Result Analysis for Fusion
+2016-09-08 10:00:12,358 INFO: Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 97.4117647059
+ -On Test : 47.3170731707
+ -On Validation : 50.7865168539
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 0.564923899429, 0.171414234739, 1.0, 0.282773686486 with monoview classifier :
+ - Decision Tree with max_depth : 8
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:01 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 10:00:12,358 INFO: Done: Result Analysis
+2016-09-08 10:00:12,486 INFO: Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 100.0
+ -On Test : 54.6341463415
+ -On Validation : 49.2134831461
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 0.444263234099, 1.0, 0.292116326168, 0.822047817174 with monoview classifier :
+ - Adaboost with num_esimators : 8, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 10:00:12,486 INFO: Done: Result Analysis
+2016-09-08 10:00:12,629 INFO: ### Main Programm for Multiview Classification
+2016-09-08 10:00:12,629 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 10:00:12,629 INFO: ### Main Programm for Multiview Classification
+2016-09-08 10:00:12,630 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 10:00:12,630 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 10:00:12,630 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 10:00:12,630 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 10:00:12,631 INFO: Info: Shape of View2 :(300, 18)
+2016-09-08 10:00:12,631 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 10:00:12,631 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 10:00:12,631 INFO: Done: Read Database Files
+2016-09-08 10:00:12,631 INFO: Info: Shape of View2 :(300, 18)
+2016-09-08 10:00:12,631 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 10:00:12,632 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 10:00:12,632 INFO: Done: Read Database Files
+2016-09-08 10:00:12,632 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 10:00:12,636 INFO: Done: Determine validation split
+2016-09-08 10:00:12,636 INFO: Start: Determine 5 folds
+2016-09-08 10:00:12,637 INFO: Done: Determine validation split
+2016-09-08 10:00:12,637 INFO: Start: Determine 5 folds
+2016-09-08 10:00:12,643 INFO: Info: Length of Learning Sets: 170
+2016-09-08 10:00:12,643 INFO: Info: Length of Testing Sets: 41
+2016-09-08 10:00:12,643 INFO: Info: Length of Validation Set: 89
+2016-09-08 10:00:12,643 INFO: Done: Determine folds
+2016-09-08 10:00:12,643 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 10:00:12,643 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:12,643 DEBUG: Start: Random search for KNN with 1 iterations
+2016-09-08 10:00:12,644 INFO: Info: Length of Learning Sets: 170
+2016-09-08 10:00:12,644 INFO: Info: Length of Testing Sets: 41
+2016-09-08 10:00:12,644 INFO: Info: Length of Validation Set: 89
+2016-09-08 10:00:12,644 INFO: Done: Determine folds
+2016-09-08 10:00:12,644 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 10:00:12,644 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:12,644 DEBUG: Start: Random search for RandomForest with 1 iterations
+2016-09-08 10:00:12,692 DEBUG: Done: Random search for KNN
+2016-09-08 10:00:12,706 DEBUG: Done: Random search for RandomForest
+2016-09-08 10:00:12,736 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:12,736 INFO: Start: Classification
+2016-09-08 10:00:12,736 INFO: Start: Fold number 1
+2016-09-08 10:00:12,747 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:12,747 INFO: Start: Classification
+2016-09-08 10:00:12,747 INFO: Start: Fold number 1
+2016-09-08 10:00:12,754 INFO: Start: Classification
+2016-09-08 10:00:12,768 INFO: Start: Classification
+2016-09-08 10:00:12,786 INFO: Done: Fold number 1
+2016-09-08 10:00:12,786 INFO: Start: Fold number 2
+2016-09-08 10:00:12,794 INFO: Done: Fold number 1
+2016-09-08 10:00:12,794 INFO: Start: Fold number 2
+2016-09-08 10:00:12,803 INFO: Start: Classification
+2016-09-08 10:00:12,814 INFO: Start: Classification
+2016-09-08 10:00:12,836 INFO: Done: Fold number 2
+2016-09-08 10:00:12,836 INFO: Start: Fold number 3
+2016-09-08 10:00:12,839 INFO: Done: Fold number 2
+2016-09-08 10:00:12,839 INFO: Start: Fold number 3
+2016-09-08 10:00:12,853 INFO: Start: Classification
+2016-09-08 10:00:12,859 INFO: Start: Classification
+2016-09-08 10:00:12,884 INFO: Done: Fold number 3
+2016-09-08 10:00:12,884 INFO: Start: Fold number 4
+2016-09-08 10:00:12,886 INFO: Done: Fold number 3
+2016-09-08 10:00:12,886 INFO: Start: Fold number 4
+2016-09-08 10:00:12,903 INFO: Start: Classification
+2016-09-08 10:00:12,903 INFO: Start: Classification
+2016-09-08 10:00:12,928 INFO: Done: Fold number 4
+2016-09-08 10:00:12,928 INFO: Start: Fold number 5
+2016-09-08 10:00:12,935 INFO: Done: Fold number 4
+2016-09-08 10:00:12,935 INFO: Start: Fold number 5
+2016-09-08 10:00:12,948 INFO: Start: Classification
+2016-09-08 10:00:12,952 INFO: Start: Classification
+2016-09-08 10:00:12,974 INFO: Done: Fold number 5
+2016-09-08 10:00:12,974 INFO: Done: Classification
+2016-09-08 10:00:12,974 INFO: Info: Time for Classification: 0[s]
+2016-09-08 10:00:12,974 INFO: Start: Result Analysis for Fusion
+2016-09-08 10:00:12,985 INFO: Done: Fold number 5
+2016-09-08 10:00:12,985 INFO: Done: Classification
+2016-09-08 10:00:12,985 INFO: Info: Time for Classification: 0[s]
+2016-09-08 10:00:12,985 INFO: Start: Result Analysis for Fusion
+2016-09-08 10:00:13,124 INFO: Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 81.0588235294
+ -On Test : 43.4146341463
+ -On Validation : 48.9887640449
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 0.073909136797, 0.326197494021, 1.0, 0.0290483308675 with monoview classifier :
+ - Random Forest with num_esimators : 1, max_depth : 8
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:01 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 10:00:13,124 INFO: Done: Result Analysis
+2016-09-08 10:00:13,128 INFO: Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 60.4705882353
+ -On Test : 54.6341463415
+ -On Validation : 51.9101123596
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 1.0, 0.567673336435, 0.401953729602, 0.0761117950819 with monoview classifier :
+ - K nearest Neighbors with n_neighbors: 40
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:01 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 10:00:13,128 INFO: Done: Result Analysis
+2016-09-08 10:00:13,279 INFO: ### Main Programm for Multiview Classification
+2016-09-08 10:00:13,279 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 10:00:13,279 INFO: ### Main Programm for Multiview Classification
+2016-09-08 10:00:13,280 INFO: ### Classification - Database : Fake ; Views : Methyl, MiRNA_, RNASeq, Clinic ; Algorithm : Fusion ; Cores : 1
+2016-09-08 10:00:13,280 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 10:00:13,280 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 10:00:13,280 INFO: Info: Shape of View0 :(300, 12)
+2016-09-08 10:00:13,281 INFO: Info: Shape of View2 :(300, 18)
+2016-09-08 10:00:13,281 INFO: Info: Shape of View1 :(300, 15)
+2016-09-08 10:00:13,281 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 10:00:13,281 INFO: Info: Shape of View2 :(300, 18)
+2016-09-08 10:00:13,282 INFO: Done: Read Database Files
+2016-09-08 10:00:13,282 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 10:00:13,282 INFO: Info: Shape of View3 :(300, 12)
+2016-09-08 10:00:13,282 INFO: Done: Read Database Files
+2016-09-08 10:00:13,282 INFO: Start: Determine validation split for ratio 0.7
+2016-09-08 10:00:13,287 INFO: Done: Determine validation split
+2016-09-08 10:00:13,287 INFO: Start: Determine 5 folds
+2016-09-08 10:00:13,287 INFO: Done: Determine validation split
+2016-09-08 10:00:13,287 INFO: Start: Determine 5 folds
+2016-09-08 10:00:13,294 INFO: Info: Length of Learning Sets: 170
+2016-09-08 10:00:13,294 INFO: Info: Length of Testing Sets: 41
+2016-09-08 10:00:13,294 INFO: Info: Length of Validation Set: 89
+2016-09-08 10:00:13,294 INFO: Done: Determine folds
+2016-09-08 10:00:13,294 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 10:00:13,294 INFO: Info: Length of Learning Sets: 170
+2016-09-08 10:00:13,294 INFO: Info: Length of Testing Sets: 41
+2016-09-08 10:00:13,294 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:13,294 INFO: Info: Length of Validation Set: 89
+2016-09-08 10:00:13,294 DEBUG: Start: Random search for SGD with 1 iterations
+2016-09-08 10:00:13,294 INFO: Done: Determine folds
+2016-09-08 10:00:13,295 INFO: Start: Learning with Fusion and 5 folds
+2016-09-08 10:00:13,295 INFO: Start: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:13,295 DEBUG: Start: Random search for SVMLinear with 1 iterations
+2016-09-08 10:00:13,348 DEBUG: Done: Random search for SVMLinear
+2016-09-08 10:00:13,351 DEBUG: Done: Random search for SGD
+2016-09-08 10:00:13,416 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:13,416 INFO: Start: Classification
+2016-09-08 10:00:13,416 INFO: Start: Fold number 1
+2016-09-08 10:00:13,430 INFO: Done: Randomsearching best settings for monoview classifiers
+2016-09-08 10:00:13,430 INFO: Start: Classification
+2016-09-08 10:00:13,430 INFO: Start: Fold number 1
+2016-09-08 10:00:13,456 INFO: Start: Classification
+2016-09-08 10:00:13,456 INFO: Start: Classification
+2016-09-08 10:00:13,485 INFO: Done: Fold number 1
+2016-09-08 10:00:13,485 INFO: Start: Fold number 2
+2016-09-08 10:00:13,492 INFO: Done: Fold number 1
+2016-09-08 10:00:13,492 INFO: Start: Fold number 2
+2016-09-08 10:00:13,518 INFO: Start: Classification
+2016-09-08 10:00:13,526 INFO: Start: Classification
+2016-09-08 10:00:13,555 INFO: Done: Fold number 2
+2016-09-08 10:00:13,555 INFO: Start: Fold number 3
+2016-09-08 10:00:13,556 INFO: Done: Fold number 2
+2016-09-08 10:00:13,556 INFO: Start: Fold number 3
+2016-09-08 10:00:13,581 INFO: Start: Classification
+2016-09-08 10:00:13,598 INFO: Start: Classification
+2016-09-08 10:00:13,617 INFO: Done: Fold number 3
+2016-09-08 10:00:13,617 INFO: Start: Fold number 4
+2016-09-08 10:00:13,627 INFO: Done: Fold number 3
+2016-09-08 10:00:13,627 INFO: Start: Fold number 4
+2016-09-08 10:00:13,644 INFO: Start: Classification
+2016-09-08 10:00:13,668 INFO: Start: Classification
+2016-09-08 10:00:13,682 INFO: Done: Fold number 4
+2016-09-08 10:00:13,682 INFO: Start: Fold number 5
+2016-09-08 10:00:13,698 INFO: Done: Fold number 4
+2016-09-08 10:00:13,698 INFO: Start: Fold number 5
+2016-09-08 10:00:13,709 INFO: Start: Classification
+2016-09-08 10:00:13,739 INFO: Start: Classification
+2016-09-08 10:00:13,747 INFO: Done: Fold number 5
+2016-09-08 10:00:13,747 INFO: Done: Classification
+2016-09-08 10:00:13,747 INFO: Info: Time for Classification: 0[s]
+2016-09-08 10:00:13,747 INFO: Start: Result Analysis for Fusion
+2016-09-08 10:00:13,769 INFO: Done: Fold number 5
+2016-09-08 10:00:13,769 INFO: Done: Classification
+2016-09-08 10:00:13,770 INFO: Info: Time for Classification: 0[s]
+2016-09-08 10:00:13,770 INFO: Start: Result Analysis for Fusion
+2016-09-08 10:00:13,916 INFO: Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 55.2941176471
+ -On Test : 56.0975609756
+ -On Validation : 56.1797752809
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 1.0, 0.728775264645, 0.482876097673, 0.365130635662 with monoview classifier :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:01 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 10:00:13,916 INFO: Done: Result Analysis
+2016-09-08 10:00:13,962 INFO: Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 57.7647058824
+ -On Test : 52.1951219512
+ -On Validation : 49.2134831461
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 0.073909136797, 0.326197494021, 1.0, 0.0290483308675 with monoview classifier :
+ - SVM Linear with C : 3073
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:01 0:00:00
+ So a total classification time of 0:00:00.
+
+
+2016-09-08 10:00:13,962 INFO: Done: Result Analysis
+2016-09-08 10:00:14,116 DEBUG: Start: Deleting 2 temporary datasets for multiprocessing
+2016-09-08 10:00:14,116 DEBUG: Start: Deleting datasets for multiprocessing
+2016-09-08 10:00:46,421 INFO: Extraction time : 5.03609514236s, Monoview time : 1473343204.39s, Multiview Time : 9.72813415527s
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..c10750d4
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View0 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 9, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.576923076923
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.576923076923
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -2.5337258102e-17
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.555555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.6
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..ba0382db
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.56862745098
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.56862745098
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.00503027272866
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.557692307692
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.58
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5025
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..fc54b504
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with KNN
+
+accuracy_score on train : 0.580952380952
+accuracy_score on test : 0.6
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 24
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.580952380952
+ - Score on test : 0.6
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.661538461538
+ - Score on test : 0.678571428571
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.661538461538
+ - Score on test : 0.678571428571
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.419047619048
+ - Score on test : 0.4
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.580952380952
+ - Score on test : 0.6
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.130162282504
+ - Score on test : 0.171735516296
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.601398601399
+ - Score on test : 0.612903225806
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.735042735043
+ - Score on test : 0.76
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.561069754618
+ - Score on test : 0.58
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.419047619048
+ - Score on test : 0.4
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..b24a64e6
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100004Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with RandomForest
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 24, max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.52427184466
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.52427184466
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.111088444626
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.509433962264
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.54
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.445
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..9d76693a
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View1 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.555555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 9, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.555555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.655172413793
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.655172413793
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.444444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.555555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0674199862463
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.575757575758
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.76
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.53
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.444444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..867521e7
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.637168141593
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.637168141593
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0487950036474
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.571428571429
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.72
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5225
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..589edf90
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with KNN
+
+accuracy_score on train : 0.566666666667
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 24
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.566666666667
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.659176029963
+ - Score on test : 0.542056074766
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.659176029963
+ - Score on test : 0.542056074766
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.433333333333
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.566666666667
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0939782359481
+ - Score on test : -0.123737644978
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.586666666667
+ - Score on test : 0.508771929825
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.752136752137
+ - Score on test : 0.58
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.542735042735
+ - Score on test : 0.44
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.433333333333
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..1881529c
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SGD
+
+accuracy_score on train : 0.57619047619
+accuracy_score on test : 0.644444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.57619047619
+ - Score on test : 0.644444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.661596958175
+ - Score on test : 0.724137931034
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.661596958175
+ - Score on test : 0.724137931034
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.42380952381
+ - Score on test : 0.355555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.57619047619
+ - Score on test : 0.644444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.117819078215
+ - Score on test : 0.269679944985
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.595890410959
+ - Score on test : 0.636363636364
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.74358974359
+ - Score on test : 0.84
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.55459057072
+ - Score on test : 0.62
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.42380952381
+ - Score on test : 0.355555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..cbbd1a0d
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SVMLinear
+
+accuracy_score on train : 0.485714285714
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.571428571429
+ - Score on test : 0.609523809524
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.571428571429
+ - Score on test : 0.609523809524
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.485714285714
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.0643090141189
+ - Score on test : 0.0662541348869
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.533333333333
+ - Score on test : 0.581818181818
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.615384615385
+ - Score on test : 0.64
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.468982630273
+ - Score on test : 0.5325
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.514285714286
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..23cf02f7
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0973655073258
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.617647058824
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.42
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5475
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..d276635c
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100005Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View0 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.6
+
+Database configuration :
+ - Database name : Fake
+ - View name : View0 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.6
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.714285714286
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.714285714286
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.4
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.6
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.171377655346
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.592105263158
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.9
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5625
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.4
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..caa7c968
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View2 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.433333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 9, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.43956043956
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.43956043956
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.124719695673
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.487804878049
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4375
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..836977b7
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.433333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.43956043956
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.43956043956
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.433333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.124719695673
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.487804878049
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4375
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.566666666667
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..4dbb4c25
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with RandomForest
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.566666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 24, max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.566666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.621359223301
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.621359223301
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.433333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.566666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.116137919381
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.603773584906
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.64
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5575
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.433333333333
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..d66ec8a4
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SGD
+
+accuracy_score on train : 0.566666666667
+accuracy_score on test : 0.555555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.566666666667
+ - Score on test : 0.555555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.640316205534
+ - Score on test : 0.666666666667
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.640316205534
+ - Score on test : 0.666666666667
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.433333333333
+ - Score on test : 0.444444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.566666666667
+ - Score on test : 0.555555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.104925880155
+ - Score on test : 0.0597614304667
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.595588235294
+ - Score on test : 0.571428571429
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.692307692308
+ - Score on test : 0.8
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.550454921423
+ - Score on test : 0.525
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.433333333333
+ - Score on test : 0.444444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..3b75a933
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SVMLinear
+
+accuracy_score on train : 0.490476190476
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.490476190476
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.566801619433
+ - Score on test : 0.576923076923
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.566801619433
+ - Score on test : 0.576923076923
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.509523809524
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.490476190476
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.0479423260647
+ - Score on test : -3.54721613428e-17
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.538461538462
+ - Score on test : 0.555555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.598290598291
+ - Score on test : 0.6
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.476564653984
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.509523809524
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..d128db52
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.422222222222
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0714285714286
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.0714285714286
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.422222222222
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.119522860933
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.333333333333
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.04
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.47
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.577777777778
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..d2a21462
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100006Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View1 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.5
+
+Database configuration :
+ - Database name : Fake
+ - View name : View1 View shape : (300, 15)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.64
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.64
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.5
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.1
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.8
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4625
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.5
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..d9a3f5a3
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with KNN
+
+accuracy_score on train : 0.547619047619
+accuracy_score on test : 0.466666666667
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 24
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.547619047619
+ - Score on test : 0.466666666667
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.649446494465
+ - Score on test : 0.586206896552
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.649446494465
+ - Score on test : 0.586206896552
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.452380952381
+ - Score on test : 0.533333333333
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.547619047619
+ - Score on test : 0.466666666667
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.0476928413215
+ - Score on test : -0.134839972493
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.571428571429
+ - Score on test : 0.515151515152
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.752136752137
+ - Score on test : 0.68
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.521229666391
+ - Score on test : 0.44
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.452380952381
+ - Score on test : 0.533333333333
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..8e7a8c2d
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with RandomForest
+
+accuracy_score on train : 0.995238095238
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 24, max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.995708154506
+ - Score on test : 0.468085106383
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.995708154506
+ - Score on test : 0.468085106383
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.995238095238
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.990406794809
+ - Score on test : -0.109345881217
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.991452991453
+ - Score on test : 0.44
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.995726495726
+ - Score on test : 0.445
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0047619047619
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..9ee2ef1d
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SGD
+
+accuracy_score on train : 0.619047619048
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.619047619048
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.701492537313
+ - Score on test : 0.592592592593
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.701492537313
+ - Score on test : 0.592592592593
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.380952380952
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.619047619048
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.210547659218
+ - Score on test : -0.0103806849817
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.622516556291
+ - Score on test : 0.551724137931
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.803418803419
+ - Score on test : 0.64
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.595257788806
+ - Score on test : 0.495
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.380952380952
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..d16950a5
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100007Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SVMLinear
+
+accuracy_score on train : 0.47619047619
+accuracy_score on test : 0.555555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.555555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.521739130435
+ - Score on test : 0.565217391304
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.521739130435
+ - Score on test : 0.565217391304
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.444444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.555555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.0568633060564
+ - Score on test : 0.119522860933
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.530973451327
+ - Score on test : 0.619047619048
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.512820512821
+ - Score on test : 0.52
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.471464019851
+ - Score on test : 0.56
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.444444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..1fadae0e
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-Adaboost-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,57 @@
+Classification on Fake database for View3 with Adaboost
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.577777777778
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Adaboost with num_esimators : 9, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.577777777778
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.62
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.62
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.422222222222
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.577777777778
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.145
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.62
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.62
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5725
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.422222222222
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..ade21df1
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-DecisionTree-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with DecisionTree
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.588888888889
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Decision Tree with max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588888888889
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.626262626263
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.626262626263
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.411111111111
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.588888888889
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.169618786115
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.632653061224
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.62
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.585
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.411111111111
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-KNN-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-KNN-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..ce39d233
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-KNN-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with KNN
+
+accuracy_score on train : 0.6
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - K nearest Neighbors with n_neighbors: 24
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.688888888889
+ - Score on test : 0.637168141593
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.688888888889
+ - Score on test : 0.637168141593
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.4
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.6
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.167225897665
+ - Score on test : 0.0487950036474
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.607843137255
+ - Score on test : 0.571428571429
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.794871794872
+ - Score on test : 0.72
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.574855252275
+ - Score on test : 0.5225
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.4
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..a6d23dae
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-RandomForest-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with RandomForest
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.455555555556
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - Random Forest with num_esimators : 24, max_depth : 25
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.533333333333
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.455555555556
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.117218854031
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.509090909091
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.56
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4425
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.544444444444
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..53f3a855
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-SVMPoly-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SVMPoly
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.444444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.107142857143
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.107142857143
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.444444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : -0.0298807152334
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.06
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.4925
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.555555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..bf98d86d
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100008Results-SVMRBF-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View2 with SVMRBF
+
+accuracy_score on train : 1.0
+accuracy_score on test : 0.544444444444
+
+Database configuration :
+ - Database name : Fake
+ - View name : View2 View shape : (300, 18)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.687022900763
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.687022900763
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.544444444444
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 4.13755692208e-17
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.555555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.9
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 1.0
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.0
+ - Score on test : 0.455555555556
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100009Results-SGD-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100009Results-SGD-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..04d9aee0
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100009Results-SGD-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with SGD
+
+accuracy_score on train : 0.642857142857
+accuracy_score on test : 0.533333333333
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SGDClassifier with loss : modified_huber, penalty : l2
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.642857142857
+ - Score on test : 0.533333333333
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.701195219124
+ - Score on test : 0.596153846154
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.701195219124
+ - Score on test : 0.596153846154
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.357142857143
+ - Score on test : 0.466666666667
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.642857142857
+ - Score on test : 0.533333333333
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : 0.266179454365
+ - Score on test : 0.0456435464588
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.65671641791
+ - Score on test : 0.574074074074
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.752136752137
+ - Score on test : 0.62
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.628756548111
+ - Score on test : 0.5225
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.357142857143
+ - Score on test : 0.466666666667
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100009Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100009Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..d52376ec
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100009Results-SVMLinear-Non-Oui-learnRate0.7-Fake.txt
@@ -0,0 +1,54 @@
+Classification on Fake database for View3 with SVMLinear
+
+accuracy_score on train : 0.47619047619
+accuracy_score on test : 0.511111111111
+
+Database configuration :
+ - Database name : Fake
+ - View name : View3 View shape : (300, 12)
+ - Learning Rate : 0.7
+ - Labels used : Non, Oui
+ - Number of cross validation folds : 5
+
+Classifier configuration :
+ - SVM Linear with C : 7704
+ - Executed on 1 core(s)
+ - Got configuration using randomized search with 1 iterations
+
+
+ For Accuracy score using None as sample_weights (higher is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.511111111111
+ For F1 score using None as sample_weights, None as labels, 1 as pos_label, micro as average (higher is better) :
+ - Score on train : 0.541666666667
+ - Score on test : 0.576923076923
+ For F-beta score using None as sample_weights, None as labels, 1 as pos_label, micro as average, 1.0 as beta (higher is better) :
+ - Score on train : 0.541666666667
+ - Score on test : 0.576923076923
+ For Hamming loss using None as classes (lower is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.488888888889
+ For Jaccard similarity score using None as sample_weights (higher is better) :
+ - Score on train : 0.47619047619
+ - Score on test : 0.511111111111
+ For Log loss using None as sample_weights, 1e-15 as eps (lower is better) :
+ - Score on train : nan
+ - Score on test : nan
+ For Matthews correlation coefficient (higher is better) :
+ - Score on train : -0.068670723144
+ - Score on test : 0.0
+ For Precision score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.528455284553
+ - Score on test : 0.555555555556
+ For Recall score using None as sample_weights, None as labels, 1 as pos_label, binary as average (higher is better) :
+ - Score on train : 0.555555555556
+ - Score on test : 0.6
+ For ROC AUC score using None as sample_weights, micro as average (higher is better) :
+ - Score on train : 0.465949820789
+ - Score on test : 0.5
+ For Zero one loss using None as sample_weights (lower is better) :
+ - Score on train : 0.52380952381
+ - Score on test : 0.488888888889
+
+
+ Classification took 0:00:00
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100010Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100010Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..31c59525
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100010Results-Fusion-LateFusion-BayesianInference-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,32 @@
+ Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 59.6470588235
+ -On Test : 50.7317073171
+ -On Validation : 47.191011236
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Bayesian Inference using a weight for each view : 0.395042964582, 0.135468886361, 0.187401197987, 0.282086951071
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - SGDClassifier with loss : modified_huber, penalty : l2
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100010Results-Fusion-LateFusion-MajorityVoting-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100010Results-Fusion-LateFusion-MajorityVoting-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..4d7b96cd
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100010Results-Fusion-LateFusion-MajorityVoting-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,32 @@
+ Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 55.2941176471
+ -On Test : 56.0975609756
+ -On Validation : 56.1797752809
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Majority Voting
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - SGDClassifier with loss : modified_huber, penalty : l2
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:03 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100011Results-Fusion-LateFusion-SVMForLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100011Results-Fusion-LateFusion-SVMForLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..92e2e7eb
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100011Results-Fusion-LateFusion-SVMForLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,32 @@
+ Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 60.4705882353
+ -On Test : 47.8048780488
+ -On Validation : 53.2584269663
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with SVM for linear
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - SGDClassifier with loss : modified_huber, penalty : l2
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100011Results-Fusion-LateFusion-WeightedLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100011Results-Fusion-LateFusion-WeightedLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..90357518
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100011Results-Fusion-LateFusion-WeightedLinear-SGD-SGD-SGD-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,32 @@
+ Result for Multiview classification with LateFusion
+
+Average accuracy :
+ -On Train : 25.6470588235
+ -On Test : 23.4146341463
+ -On Validation : 27.4157303371
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : LateFusion with Weighted linear using a weight for each view : 1.0, 0.342921905986, 0.474381813597, 0.714066510131
+ -With monoview classifiers :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+ - SGDClassifier with loss : log, penalty : l2
+ - SGDClassifier with loss : log, penalty : elasticnet
+ - SGDClassifier with loss : modified_huber, penalty : l2
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100012Results-Fusion-EarlyFusion-WeightedLinear-Adaboost-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100012Results-Fusion-EarlyFusion-WeightedLinear-Adaboost-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..3ebeedf2
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100012Results-Fusion-EarlyFusion-WeightedLinear-Adaboost-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,31 @@
+ Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 100.0
+ -On Test : 54.6341463415
+ -On Validation : 49.2134831461
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 0.444263234099, 1.0, 0.292116326168, 0.822047817174 with monoview classifier :
+ - Adaboost with num_esimators : 8, base_estimators : DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
+ max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
+ min_samples_split=2, min_weight_fraction_leaf=0.0,
+ presort=False, random_state=None, splitter='best')
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:02 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100012Results-Fusion-EarlyFusion-WeightedLinear-DecisionTree-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100012Results-Fusion-EarlyFusion-WeightedLinear-DecisionTree-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..007add07
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100012Results-Fusion-EarlyFusion-WeightedLinear-DecisionTree-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,28 @@
+ Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 97.4117647059
+ -On Test : 47.3170731707
+ -On Validation : 50.7865168539
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 0.564923899429, 0.171414234739, 1.0, 0.282773686486 with monoview classifier :
+ - Decision Tree with max_depth : 8
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:01 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-KNN-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-KNN-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..d10e5809
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-KNN-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,28 @@
+ Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 60.4705882353
+ -On Test : 54.6341463415
+ -On Validation : 51.9101123596
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 1.0, 0.567673336435, 0.401953729602, 0.0761117950819 with monoview classifier :
+ - K nearest Neighbors with n_neighbors: 40
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:01 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-RandomForest-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-RandomForest-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..3109c44c
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-RandomForest-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,28 @@
+ Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 81.0588235294
+ -On Test : 43.4146341463
+ -On Validation : 48.9887640449
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 0.073909136797, 0.326197494021, 1.0, 0.0290483308675 with monoview classifier :
+ - Random Forest with num_esimators : 1, max_depth : 8
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:01 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..e63a7f81
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-SGD-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,28 @@
+ Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 55.2941176471
+ -On Test : 56.0975609756
+ -On Validation : 56.1797752809
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 1.0, 0.728775264645, 0.482876097673, 0.365130635662 with monoview classifier :
+ - SGDClassifier with loss : modified_huber, penalty : l1
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:01 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-SVMLinear-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt b/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-SVMLinear-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
new file mode 100644
index 00000000..6c39250e
--- /dev/null
+++ b/Code/MonoMutliViewClassifiers/Results/20160908-100013Results-Fusion-EarlyFusion-WeightedLinear-SVMLinear-Methyl-MiRNA_-RNASeq-Clinic-MiRNA_-RNASeq-Clinic-Methyl-learnRate0.7-Fake.txt
@@ -0,0 +1,28 @@
+ Result for Multiview classification with EarlyFusion
+
+Average accuracy :
+ -On Train : 57.7647058824
+ -On Test : 52.1951219512
+ -On Validation : 49.2134831461
+
+Dataset info :
+ -Database name : Fake
+ -Labels : Methyl, MiRNA_, RNASeq, Clinic
+ -Views : Methyl, MiRNA_, RNASeq, Clinic
+ -5 folds
+
+Classification configuration :
+ -Algorithm used : EarlyFusion with weighted concatenation, using weights : 0.073909136797, 0.326197494021, 1.0, 0.0290483308675 with monoview classifier :
+ - SVM Linear with C : 3073
+
+Computation time on 1 cores :
+ Database extraction time : 0:00:00
+ Learn Prediction
+ Fold 1 0:00:00 0:00:00
+ Fold 2 0:00:00 0:00:00
+ Fold 3 0:00:00 0:00:00
+ Fold 4 0:00:00 0:00:00
+ Fold 5 0:00:00 0:00:00
+ Total 0:00:01 0:00:00
+ So a total classification time of 0:00:00.
+
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-accuracy_score-20160908-100014.png b/Code/MonoMutliViewClassifiers/Results/Fake-accuracy_score-20160908-100014.png
new file mode 100644
index 0000000000000000000000000000000000000000..7f3edfe4fbd6b2ae487dcdc9dba912286b8d8b90
GIT binary patch
literal 164514
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@vh+~cmHfB!Sr-{n4`G<(4U4YsBZ>vannHtl%s
z)KuN%J<B^QEG$fGhFD(atex63c29dWX;M@5qkT(u<UbKx)FGwC@%(%H*&4}oy)zFq
zzW&@hufM(j)tut@wfBqPTNXb{d~fOE@;`yeN)Rt#B&gzVGv^Bzynv;Fkcuz-Y72z%
zx<inGkcx};GaCHxy2FKmpo-A|K?}iQ9UxtI?%WAj>NRx|U-Jo#MT-|Jo;LdS=4SAv
zg?r2#9UUh;4ga70puRfZ)zx)j&CgF2pPqE?%K858?u1my$H)7x|F$`{>-?jb-@aYl
z-OW0uBX*Un3_M@`_gCqOO+9sge@TAb^S?~lt*4>6nfcxQ{qdI;{#pHER=rnIjM&kL
z&rkpJ*ZqELZjyUTB=yvkMxE0y?(8h~Y!7*q66xmQaYB0kyZxoPaW^9DtG;MNZOiE_
zdV0!nTI!Yc@$w88mix<}*wnLS%NBE4J)}(Yvax=$8zTC?NcqgM5Zt8WJS{b5PsPS1
zhZVKVJSQo526?tGRJ5~;v)yO+|4;GU+z?NLi4!O0TUh-v|82hS{4q7pNr6II-Iv4j
zwPt?)@bGZNwj4>femP!m@6+K{*Z=dsXZdh{|M^2gw%$sd|GM?}9oU?HUO-m%@3D11
z;}?9HC;982<m*~pt({jRK0mELxVmTZ>+9>4b#!>Hua9^C|L?D$tZeVQySw+dX?V*2
zf3`E``i<HzF9dIG&2CqA?_1#BFW1r6ckIEzX3^V71;WMs?U|nJ4oIHcpK)=K>x5KE
zCk~y64Gfdj{q<f>=;%_lwA{JGIY7lzDDB*w&V|nHhpt}Ty5z9pukar)m(QOtcW$iG
z^}68Bl=!-zs&C%BG03>EAl&ZyhQz}c7Q6F@tc$tHG4XG8>AO3UzOzgmTe(ENtfu_u
zJa_Kgi_6RTpPilE?r;BBWU5xE*2@Y1w${|v7JhpZIYl@6TW|dC6_zVio}d0dN!GgT
z!OhL-Ki=(re_?I(_DOv0|CUZU_G_VYd%^d2u{FQnZvXLS^Ldk3Ny*8ERbMhf)<k^t
zZSz8S%%$qr|HsScbaueOy#+^(xWw!(;|&Z9EGR2;tEsV>XI~$8DN#_gd-rbZJ9qDT
zTk*`bv9<m9=B9DY$D`t^vRoJUyDjya`rzr)&`XJX%*6HMT!Mmxc9p(nD=z*VZa2TV
znR(BiJqd}4i7hYw?aj%_dGPcptF-j&Nqk3Nv<Rpc-CeOl<H@sUN&o)*R4w}ZpNpHD
zyP~r4;K73rK|U>iTwl9S=SAqTlV@j}Gd9>KIJO2!y*AIk*P`NSbzeR`JsqU@$dM<$
zt)568V?(J)CQj6i*uXGJCGkK5<BO}S#f^-NHq`yCI{NMB&!01_%k`L;m=f~y`L(sR
zL)J!#GPCg<czSwz_tkCw^X(?2N@iweMqR(Xx7s`<^4O1$k4;ZCH#H?BB{ki-6VoGa
zFL&?Wy$u^SIP9<c%fP@dZ+B#hX0U*i6jyk7_>9@J51%~AIoGPx$;+$j(ciiD^>TlI
zeQn;o+ge9Q=fRsdJ!xlWCBD0}lc9l~Uv9;FXU}#%S%uR^eX`ceZn!;tb#=9bMS;Sq
zu(e#;+S(RYR*U@RT1nVc7#JBFZ@slXZm-nBg$oNxN?MjKRlRff?#0dN{xY^zA&X=E
z{P>cRlLMFg$xhLWl`1PM%eb~i^4hxC)urcNUtjM$E%nRm>-?a2+Maj!!J9Wc!otFD
zZf<tJt7mL1yx6_ptyju4AvKk?y1IHx#zm&v+w=85*_Fn6PhYS=;l!qI@tjAGA3uEm
zzPz8G--az)T%MkqdU2Vr^qR=cZj0y6o-Ms9WaXmLHQ*vjv+UiS&Ib<?Zrr+c=-fHJ
zx3{++-&y>;<XF+iN3JdH?S~H@WW09m+K2DokFVeVZ&jgPt>>hcb+Nk-9Y4;l9lq|$
z>$?G!KRzge%7gs;{D`QiLkABs=HA-k7!))q>~_=Rr%z5!uK4|Sd*Cu3Nsvz+9UUzS
z9yFZGe)9C`!{hSxE|b-K6VlV$FD><6T=)0a4BP5$j-Cm}`(zJy2r55#{CIJl``$f!
zKAcpa|KMOVd(_+F;$p+%XFetw7Z~{X_%vd7ncTU1S5QoB+2?;Hp8o#F)#ukRfgBPY
zz1U}_(T8u}-0ttIEqr^+v^V?jhr|3Jr#yW2jE$R{8x&cor>EW6mOJ}g@#=fa_y7MV
zt?b?h3aiA_)Yhu6uM`y(9q*P4tNXP~pDwPWtNZZf%g&pd)3fKUez4io)6=nAOc#_S
zqobp@WL|d5<`IAT=jUfo$)FX!j;FY|c#3|!+}^6Mhg!MCd93<R{rUM>@wAbcZq$-M
zIdO6J$Z3hWxxIJp#PnLl$HzxRMn1f`IbG^0JHMQZiwlcZ$O?wy;^L5XF_O(}yocW2
z-oAC+YLjQhMMVO#vb_BK{1Fim3%sUkNf@W`6crUIoHlZDauRu;dUsdphp%5<UtU`J
z@WqP`IoqlS*VabAs=8{kCH=e{hoZviO~3pPe*X9IxcrNYi`##FK5+6RC$E&rffEyz
zCr+OpUeW%~`Re@G-DSF4=I(oJYGoBA`}_1X{rJ9LUtb?Sb&BiUxpN&oJxAW&-Y)w4
z#)WL=wzHzY>bAXDWO82W@yr!-?Ca$c6B9w{ed|_JCT3>tzc$f3i&UGMn?dm(5f!z_
ztygM>MWIqrQPGx1(^NQjm%Y7IvHe)TeE*CY5+N&tSSP8hJU;E!`P1KL&6v?q_V(7o
zn4Lu%Hf(5EzFghz@0Z||)YQzQ%Vw>Xv#o0BxBJEM?%g|$&{b28-C9}r_*g-4@!>~D
zyLn$Nf3!}0UHtyOcXxL$2I=3j#bvQu?}pUVVtdzBzP_eAW5$dHj?HXcxwp3Eaz{>^
zIBV7_z3%RAXBQV18yg!?zOuHqW?^AT`1$E+)&2FCb_p}|$=P<9<=$FxT|hT_n@)-E
z&cwrPU*6r7zPc*3dFxiwHEY*i+>q#eW|paU_MR2@7!_IW+_`h*z3V~K-b)c;P6_Ys
z?98~c!!Rc&Cm}bt_gJrV^1C}bt?Unn7T?`l{oSD8fy0g+I}RK=#I!Z*s#8qNoO`vb
z5@u>&=i2i~s<W<~7h6(d(jxHcUsdI~oh2`Yl$4bNR|cuhm_2)O($TJtuC7B%y{B(E
z7g=yFc4HFjpFe*Rl9Ly2y%v&m;?~d7+VaYohV!gHC<Rvk`0((<r%yrk?H|8>J=(%4
z+-0-P;`^@h_i-gJE-<cJw+>WBwsMJHSmG(XcH^q|yFNVKxNg?|UteA_E4KXloq6#4
zx()Bww5_Y<`Yq>;RFEG{j=IDsfM|I9)d%IoWxlfm)<&6@Ivw4TdD)=;Urou&ORlSH
z^YZlW)&0(Wb7Ld(RPAuL^>KR>va`Fhudhoy+{Vkn!_(5<-hMDw)w4;(lkMobEO|M(
zK2SR#_x84m=X1*+JbA*xU{U=|XWy?^+9vt;WZvH1?mp8fb;7i1ZN1XwNw2T1y|Jg#
zIBILw(!z7P(c2beUtf3P<VnZbX1NzOr~BJfd|*)bp9d=c4Kgk$+_-&vF{pvj-R&F{
zB;@4mY<jNn@iE?<+uL}1rA(dv{`$(jx81t@-Gao!Z54lh7=jul9UUAtwZBBd*T)^*
zlzQ4A=Z3))&0x2?`~2tIMeHikJT+Cj{lkZXDca$D=6QDxoSSR?@a@~RepgPNJ?pwU
zZ0&~h^Kv2U<7DM)J}_?Dym@2ZU8|DU*Lc<a=Utg8Q}ptZ>W^Q)7Da8%s`!4l{Nt08
z!Z&W+Vq&;->C%NgmBmYzE>$!z5Xil~?dbjb|Gj5tn=kgAZ8pQc-tO1;_xTr$uee^{
z{bBJOPD9vQfTQB^3T9?vp{qh1x98mjm9n?D=RXFu;I`+@bxT@)sanNT$Sn6(OG^vO
zmh9_%&FuVcSy@`!a&9&$yZ0%WnuaE`ANl<J{9@0^Y9~&ea{B%4ZQ$;*+?bt3taGi)
z-EMEo<*kcv6_}vHd3l+yvxf(V-One&D(dRul`&yqVzbP0yNaKmTNt?5?Zus)#-RE<
z?X1+6tgBqb&(9rgU}WCXXI=BdK+Shn%QD~DNe3DjJ-odS?<#$LVUa8M9E(Dy$Lu2W
z?Cbl!y}kW-`~AA+?c2?(zP@7R=H`BLXQ%MtHr~Svo!bTE<=0=Y)r;7`AZ?c8@cG%<
zi<?rtpFDs5_{GJ=peEOb+}ma{HWdO(y{Ct5@9*k5v?_FU!0xhK7gyJVmo5oy&%1kQ
zU+wP+GiIzX-52-m$w^_8+*_cybv->z_u|H6cMipZzrRXz?(7hZ-Br>!d$u&ggMWX2
z|M+m2|Ka=h{b6gPK;_ep+TUiNU@UukEAio>)~HVVNh*rw=Hj~1+g#Gp)D9gwG-2}O
z=Be7@N=iyhot>RCY^%-q<n4O4<=#GY=Z;MF^>s%-JUsmH$&)3;a=xCP2hH!-G*8ow
ze$>owcVMaa^be=?_pg{7|M&0T?l;eKZ*Nnyv5`4H-`>5QPxisfmz~n)c@L(?*BzXu
z8@(a>y55f;KVE!1@~?l@`pJ_fnH<~ns-0n;O=S}^JKuuH&1npAD*dw7WjtqRn_s_i
zv-;zsqZR-EeostHZ0wV@K6Le}sJMRIkwvcE8!|7efx>O7R_LV{$+3@D7C%4t<LmYK
zhfkljCLV4B`R?P#j~2zxd=`E;tp1jhb88EytaX`7K!5<BoK45o)!~n?tPHj&e8h6*
z%$bDz{Qeg&GISz0v1DduzDjXrc=i2hzx}_4_3QOhBHfPn$v%AduCJY6{?VnS-ZPBT
z`PBU8aA<3<R{CwKsmZCPruO0U=ir>=6BVJa)}NfL{`m8G`}XE$=3n35az{r;fBl`3
zp1#~7eQ)Q^MH|jfJG4h;^Tv6c44_mBYP8R_D!szlv^sn}D7|hhdg`@y<L&kF_D7B$
zJ$Uu1sGy+WhV9$ky}Y=N^++~9d6JTIf1m6ooyBo`t2+An+)7GJ?%cU^VY$EjSIefR
zCWbvTuBV@w!6+{;-_qK;@-=tg%^5Q!jvP61;NnHWx3{;qPo6C7H`l6lW$<!PNn}y*
zfMLzrwWhzc)YaJ)6%|jMIpgyB+S<hIZ0_>%^4{N|Mpc)n_Jmopx};3AL~i;Yjr9k$
z>wBfm+uGaNm6VkW|NpC96Sr3?F){JR#$@(c=J|0iN@HVUE^JEm2Dvo-+#JWVvrJ82
zy}z@wS=PF2LEvIHsqcm<Cj_pn3gtdK+uXgCOSItqJ=;IOUax;~celA-%#MZ`GiE5g
zk39K)|Np*ey3tDJ=Hd?@KK$_E!+}m=bpa8PB|n-a7Q6R{_5be@)mGBh=017yq=aD-
zOP`G8BEz^vix+RK`&%`~s+0@VmEF77mSM$zPL2Nm<@amFwZqrBJUunlFyR1$$E238
zudgScn4oxLf4zO(ub1j;ljUqG80zcmLDiP`biImiZ$J&+?z+Ff4jwtevbXxX-X?z@
z$;oYJ<PRP^Sk*gu`p%s@6|JnKc9*?9^zQC%K~d4A^Dc+}x2gGI5Va+v5!7A-CAnTH
z(}H(*EOnx{@o;i-dU$zV`tguCbiV&wD^csRHxBK5vI0Uvi$1q2#HGCeSBIJ>B+kn+
z^vPH@U0WOd_+T?TsOf#^@ZpJb=k{K?5_06okq4{S@6-BH;rzbz_O{%N`}=I)ym@nB
zW3qe5nh3$~@9!VKxjEf1{hUmXthHD};_E}xS6*XN_nYJ3<iuoE`f5qt{gD45Qq4yr
ze>0rApN!OTTQP$LQAr9)p51=GPFuxOXtJ7b&~($B8v!$B%;-2hT|axPylvH%2`Zi~
zt*xDN=E(H!nlndc;>3x8Yqr(?`XabVr~CEw_1Uq-*Vn~5O;QmQ7G4}ECnBPv;we=6
z`kLtX_xG<`y?c1L{n5R>)lpB)^Y4l1>FI&mT~bdaB_$7CyB0QM_U!Jx)!$#)_&q%_
zQQ2vd%EhJL;%mzuAL|v~q|@!%EtYw8Z_c$fkxtW64YRN5tljnIP0q(JFN43<pPy~+
z?=eZ`&!0a>7Q6SG+<Nx>dAD`>yA}U`&(7Z`I7y}R+uPgSd-m9r{=B=pymj{M*%MMD
zWh@FDV(Z@CGF9}PG$A#z=IhmPtK{5!dv+Qa8VY7#TXRw4{Haqyc6N4$PMz{vvV6IC
z<@r_FU*FyiPp=IKm@pwVa`Bmq7Xx?f+LiUC{nY96H_o2*-LZRj_LQSXk8*lWYMD86
z=8c`j%iZq2xVX4g=XBDkDVkDG6%`dhj?cem)B7p+_O_M3we0NnU8t`8`78NYkDwFB
z#eKEail;Z-*pfMUSMMv^_jh-1KemyXolj(vO6S35_UtL~yGlH7+`P%j&CT6gxY(*+
z=XBD`OG~AWuei5xp>uoIlzwS*KaWW&Zaor;pFV%S`t;||pNs1M|8ts_y0P%F+unDk
zy1KrPWwg4*^~ENsbe^27zWVg0O`BSDPA@8ae9Y?n((IW1IhU9DI!#jf`0==W_SL7)
zo^>7XmtXz=H>eZvIO6HU!|jX0)<zw=croy`Y;f;%zqwYKXOgSGzZ0FL!pY9gesM=(
z^2ZMkolEad)ed)A8MM^p@2{_>=R!Z+{PW{+zf`HTd7j856;6G9{oYS6USxngySIA#
zE*)dz;2XDZbE~VX7rwh=+50X1+#JDc*RCycY-Wr4zOsM&y((`DYwPSOJ9q5p5Yvs~
z2o4T5EPE4CTIuA}G(pAFXNG}eY}vy@tbwaSG#@^Fs+xCy-`c`?PoAVCCM79ZmA_jP
zxGwvQe(bIgk4Y*`O-(L&dFyuBXlr{{R9ACHPIE0N*l^77;>C+jlT;GZ)78(-v0NN@
zeRI0M;^|EhyUTJXUJv{E<8lAiV=GTJv-6k8ecrVH|G(%Nvu1T!mA-nhM*m#J)vtar
zJBwUr%$&)Yo}Rw8e2;s-+^g(8ueS2e)&BA`Cs0USe7Py8Ga}OSa`Sn+%PXv_zN|1X
zHWudN<CB`d*?XD}D4BM2aDWC!dXtlql3H|5Cp|keQ|jp?mCU`1^^Y(3VmV{Z932%;
zAx1_<sp4({rz6LYb9+uY;x1piByioV)lplsR5xwjEc*Wc@Avz~H|ca+7C+P2ruicD
zns9vm->t`X3JD9hs(3znyZ!#P*SEC8*MU-1;9|GTtG@GWB2R46NjpDpZD8HgQ=)6P
z?cBLj$;2dNidLxCon58gi~X+4EZFjHP1xF5=f3AZJ2UfDwVs9E)JK9&9V=F7D4yPA
zQSxGfTV>+w#HAJCYa$d?JcW3r&8}2@yLt2GqQt{(p!8St)T=i+<RhPqML@F7@@31o
zf`fwtH>df|y<R_4F?rLD&+V5iG<()n2DyHf{8Tg_G$!CNNo7^|`gNsxo|9U(Zry58
z`Duw`p~SATy1DmbTMX_MpFepru>XJP>M+sD*x2l1=l5HSpPzG@miqCye0_#&@CTc=
zHQZB=?OJzUUNkm&%Z}{%hxQ#8LKJm@A5W;xW$;Jz7{2UJ0kxBM-~IaXGW*Y;KO;6I
zG`ijX^QY#_Ok?)2urN>?;LMpbCa=z(IrHGfi;RNX;fkI@YCba-Z1mpI)!W;9tnZqZ
zo}OMuN5_Gk#m@^KALA{pjERu}^$Hc8+Y}TO9G(|y@k*IE9B$*CIAKD=moFuym34J?
zV)}7B($dl;@9)K~uNH7RaOjZJ>N}S%1to_+jNF{&I7#KqY;*tQ>%k9P?JcaWSN{h!
zkS3%`-mm>GoAUGjzpAA<H#dQL+${nTI|>$FGo3qk?p13Jv65F;G~e9Z%>MA<!>HYd
zZr!@2q^8E^Ki}@?dHersuG@;Y&zw2)oGg2(ZL+Fu)t7+x4y%m{9yo9)7QDEiSUNK+
zywcy_pGU?bU~%p1Yilnqa^*hURDbfx$;pbRjqHBEF@Ey=x%RfxXU`t}^z?LMa&mM2
zzMpQ3&mBI@e7K$8-OrD2nqKUx(i{hehHHA$Kx0=cSFSv^mrL=(VSf7sPOV&^cCg8>
zh^@)i3_9`qV%Ap|mzG}rIS16Oi;j*~QB%vB6VK5YwAAaR&GdDJYhA8O7@3-0y^*^&
zWMz=l<A|fjj<Nmy_0>5oO^r|9Zq4UE#%X6R%s9@(#Ps0ZyFPY)xr9$oPHxz^G4T4%
z-Mc|!PRsr0hrM4FJ7M{9bvAyvHG$U_I<teiYSZ;%58c~a&As>fj~^8_H9rI{Uc9&>
zZ0#(!*j_19gM<SNGWK;c&(F=({$jJMrKRP;ySuwBYJZtDh+9v&x35-OP*8A1`1*NO
z<|PcEwvdYFr5j8C9ha{M^-v6xkMT^=kB@tN=itGEFK%p91~td`|Npo9M0Lp7_sf<o
zdsPH#DatHMInp5*Wo^wbVc?KG=e76s-Kpv6%dc-V&%fsq7bm9`vLYbEy7u_$Nl#Bt
zSJv0(KitN9x$1awa&lr)(x+3`>!$8>dbxS&j<}~YMRM%Z&Peob`t|ko;_&rx6(1fj
zURxi(Uhn_E-|rLC(%L|^=-Kf2+OMKAGBRK0DSrixT6s)r`T6;I_8DCU0ZB<td3pJx
zuYG5m@lKmIt?Rj7{63o&0S|BQ%i7Z(ty8~O^;);)=hNv@scWOQIz2r#^{ZTaVq)Tk
z&6^K@dU|^6v6`A1n=@z5Y`GSt|NaNxo*z0ARwWwq?CaMVwo5+xe!u>BE4TQS-KOFu
zB`*RhDk@&s_=Vdr7}WeI;7~NN6YkFb_~_^a70!(tH%gtqcj*$i4N~I<%6ewGvyMfq
zi`#4U=kH(8aCS<1`fFL|z~oCevU?x>`uqKU;lDqXCb_plUf+FrX(=}o6H~#zKb3E8
zZ})$F<NN)3`O;TcF8+=>8fm@%+<QH(V-@dao8=z*`uh6CmBH#Iudn&8f4%R_h3e3w
zt6#@nE|sgj)_N@H&Q||K)P_=pPj{XZqP%eV<>BRZXsUMjg>AXfy-#+`v#oygxZmC_
zCPoHSDEP%#m%o$Qv}x0W=g*gawZFdq%!F<0R|PJ1>ni>I{r&Op_v`zoOc7bKe7Ul^
zx_hj;r%>L#J)K@twHO)r<ZL)RCtX<PE4_D}b;=0=(4cF#xc;%{^XvH-Zfr{B&bzat
z5j1OX>eQ+e#U*cU2*%fZWNqV-Y|6d8ZDHwa(75PzuX$(AojW$uI6Yur%}=Gt@pATc
zJ*TJZFAiGjwIXWks<2uQ4-SS0KR!N=DlL6|?dq?M3=E*20fU0JHn*XnVbs@`FJB5c
zJ$Q3-bL+9N7|?(rzx|&EDbp;_;6=v0J(jafGMS>IqnpoNUf{^Q)+jtYoWUV2ZP~6j
zM>>TW8q|Dey|D3jaB$c-`9_0yr`_M*-;X!3a)U-(c%)1`(szG;eqPzyTAGoOal`iQ
z*H`g#avp5q6fUvzj{TmMmBp2wp59x%x8NbuyZih3_4V~@{(ik4b(}*nAv1I3_szBc
z{#ZUcH@Exh>TqRKQ_;xCNGZ>6=K1$R{_pPX<+Un#(QtOQ`QhWoL1iCk^k)6~{DquT
zSWWZq$%tx)x#Z;NfJV;B-rhQR|GvDPot@OlNm?scuAE_0Y4q*g-EPo;#LLUeUs+w9
z^TDXPx_ZaXotaa2@7VF+*4FG5@%#6M#UAYv{rKl+@tvK;?%F>s3=9IE?`2_SO*}u(
z)}rpujwERY4^L0V507lGn#$?N>|l7{`f11Z?b{z!mT+=%I>yAvOqw()V0D<TimK|$
z$!FHb?d^JbdHLh_`~SPWytH&<@pHe3=;+0TkB>!de0yuFclxBvsw%5bpFR~lJj8ls
zb-2G_pRl^0!?e`7$pPV$=60!gR`q{g1RAlqU;p3Ms`OP$M+XOJ0RG><e=CBPcHMiv
zqx`*G!=id0$NL{wxtON^{QW!oYUsKc$#v`2?Wp_vOFQ;==rgXR=f#{QAJ1HIWqo{n
zx>8a=fWV{2j|>0&DE#v7uC)I=n}aKZmj|qivGkd57rT0|0MoN)&)ok0@%Hp=oH<kS
z+M3A4o9)!q*~{PGb4^QIc5HWQVq#;|)-2JgywF8yZf<T93-_F=I&}QF`}6*ZJ9h0_
z^}KTtXtX%{`nrf61&Tt#!dG8!PCnkJXlg17s<Aqk*Z=#eo|K$Can78cEn7@%DnGfz
zE;l*;`tgm8$qWr?XJ=(zJ-Ml;p#jvVc3u7M-{0S$=-ZZew@W*GU53hneO@-Kvi5Z{
zn{*aeets5JdUm#XduM0ox%7~&S)ps?O_)rcpI&rr)2}|y<n^Xq-d|;!o106owYRh+
z{QvhC6pP2wdsRGJ>+WAzx+DAf^`CcH4bBz&dwLrF*tJWdXgw%L{QCMD)Zzt&{K10<
zKYai0ezZ%}^jzkPT^A(cQr{-OsCGpvE?Se3S20YScxJx6{3I1cEiJFbdwgaZy|}QD
zx$fsvaTOJn1;x+LfoFCY8m|3+vA$a|H$L>>-2L29`|E6XmAqu~_V(VAb5lr8P7XBH
zkP><9++6F8>F4Eas=uwdVOakDo~(TRA44&nhy{KQ;a^{#-kqksGG?a{pS)eqix(N7
zfyCF>*S8BWty{P5$CJtapy9&i<kP24F)<vKEf0OVs#t8vmt@9ODyQDw-k$vX+gq#K
z9+N_ztUGqpH2D}$MMXuz$w{g+OfrR%l9Lm&vbsPcOt-dVc3JoDlbOFxCGRS~&XcE4
zSDp^3UGXJPbE<UGpC2D1HYTwqB_(YsldrSvdt~Ds`<-i#hmLN=`c>)GA0N5)$lJ#m
z#?{Wxy}mAXW8z`9ii!#a9UY#hr>D2?+-b>>@axM<sboHeYilB#JtwOr9_<qC=<90}
zU=kA(12wm<tPFnm<VnbjuQ@q61s@(b_DGxaNt@>#$>0B%O_Al)G~I4R=QdFPIq3a@
zxsxU}UAPeN<mppI6BCiSR;5jA*XpK39_tiVpD<y<0#W$|dp2)+wMYMbK+Fa`bMx@k
zelPz9zV%sC_0H?v-QCM~EY5Z8m$%p35+{B&@0q8kCukG`l$}=wsa8}~DVdmvOjh?l
z_U`WPiwhi?=U5iAy}iBty2p#4z5c<={X+M&sd%~`n>KYSD?2;;+>=SJz4o#1_r0nV
zsrlZ0X+@y&o7>y@h1LCzoVWkqlX`lZBS&M_)m4dib`(bKe*S9FFU8g-`;rCuXIAa_
z+8H_D(p!`9ukRVrW4{!ol5K>i9y+G@p}uz3%$b~uEbs2^jeb%4+H0HMy6W%m6!rDj
zpLlIs_a{P`aqo(sLJd}m(evehR>aPCWUZgFM5FfCmxE2L+@OI=zp~!$?#nyt_Evq>
zk}}O|S+homg^g`d>FaA7Hg9h3?BrY*ySwejkBYg)d+auC+N9taH1Yk})5lG6ZU}(p
z&L1D^6%-W(`EJInS&t4jv(GS0cH8*4@~73R&->0CIl_{9dfL&uyUVw};;MFQsQbKh
zAEXiwvORw2UZ!G;V|I!vsGffJUaz5W-fqKv&n2tYzu)tj&n*95Pv+%iiJ-J+UvJkU
zka1xF<G#P&qCq8HL*i?v<jSdA`wjO6BaQiA{GW)D=LAzyQWO*w84q;3WW{<$Pf|(z
z_vhy;mXgpzO?JCYr7npzSe^Xv^Yinl(p{4rz8I#Rk(e=iHfYrL!>3P|R_rc)E%xor
z&BcLX2G3@hW{XwUadUHjd3l-LIPJ`V{QZC1q)f9CZg0!|@cFaz+gn?|_HB;Znia9L
zNcGd_&xN0!c!FjZHm99E)GlAgk)56W<?Ze33;u<up1!xU*ggI4+uPesZ;39M;;=mH
z_uudLA2;*cY5ZEo6?kJaTZw(X=Oj=wiAUZ}Mp9Dp#`b*qu(eUGrrFmNOie}8&&@GB
z^=_Bes<~JH|9Y)I_p8^_wt}LfLn{Io8|2-wICAXRD&cgls;TKK^{;LO1?9E1(cy1C
zGaR_M*d3JFK%?LL|NUC+_GyCv(_}T@OIFA3+>uE>-gorI#^l1!&wN3>h{D1`&=QMv
z@%#Jk?k*Rvj1?Cb2d!z~7SlO!b8|YVl)kw+J^9a%j{;6B%H`%7Br?sjtL=*2U6%RQ
zKu%hE^*rHt^QGUPpPOqvL1pEM=b7p0?4FYfUR}}L`%KF@WJLhu)m5Q~=h;?+My2oW
zE(fi}IM6-!xc5}8R$1$^6~e*s_guq7e;;n=FMX%CRzEsA`p*7(`JX?3MtQzCCQ<+E
z)7P&@kM&AVoISgHv3q~g?QOX;OtZy6gY)X@>R<UTc!h8tT=itj^`#Hygzl{>U0ap>
z<>u-$qQ`vB)m=?r6m-La<=^|d(En?~*UR<ESSGbtYs{KESGGl<>TOWm1iQa$s>Hu~
zhSdwtcXZ9Xw1jh2*xIgMY4b-954UgFv<W<bzbz+nOYZHk#c#J{UY;;>X6KF_7Hj3p
zBDZFVK6>=1OSb*hOp&kmM7AUxWC9JR8X6i(7^n5P#d>*hrJb1(_@*MR@9n?8zfYV#
z9sGYqpI2O*oRN{ymEt3>7o4AA@+|6c=!$vCiSM^udcI-d=ZL~<=hpw;-Mvxbm#x3J
z^LtT-TibHGx8>e`baJw~Ma2gNP-c;@|05`CRdV3t<KqwCzU6iJU%GIkMD|-}q$+8>
z-*5GINMnH~5(*0oK{Hd$Y`h=tRlk4vCwN;<<eM8Co%d$1+P>ZV&D*zyudZkwJ;E#M
ze2XdI{ez#+=htUlm9?wc5pgnmx_&%p1;Ca`QY`{Ec9*XYtG2hd=TO{G`Z{dydc%qj
z2@D7JRDRx&aZw307xMS}eRGSj2d+tFd#k=0WL?o%6S0xWi6iI621bU2)YR6ftyvG(
z@Beq`<YaYj+y1RvO>Jy!3O+ycjoDWdx!TUsQj+1q0!QY($)7)eW@ecCH*LkCd0!X1
z_ZK`o)aul)AH7ZI(4j*cvaV`@I&Ghxp0=p{^+o%5=!E`$euf7J8kwzL_g>^@08QZ^
zIC_-z@^b&<z0&4eUabyY&8DrbJ;$a}h+p3B%BpbN)4#sH7Pn@*8sY2dX_!%-5vv!w
zi-qCEg@w&wmp&Y9X1{9vUTbB<My0ARFB*>=ajB@PO1i(V_QaVpCK_$8uC7jgabe+)
zx7+VCIM}u|h!;0CH#diUvSfI3YwPI+ulID-{{Hq-=l;%O^#<|Ib*+JCLw8Nu+yknZ
z`sHj7&9N;0@Zccx*L5$ZO`8TPRf2+qCQY8K=s9WEx`Z5tILmFI^#Jzv@}N#-*xZfB
z<QYmgEfZLDp)4&e4Wz!L#AM(9f7Kj{Uw$2I;u6(b5VNz$qW<5Wz(=7$>*H)W6ifC+
zXJ%$vJ&$&lEM8~O_Q+0nYVz^Emv?e2pP!pMLB-RS&wILF?<~{oM`valv;9@*(>dMs
zcS+UzDX;$i`2$Mio72y~s<o}1YhBJaNoA$|bFR-;*MyG>ii)-__n)8i_0?5Sf5phi
z=)&r7{k19Cp*^eQ{j@T!uZvy(#hGK(`N&xNu1WLfuP=TRyRSxal8WZB#omGM+w@lb
z47$E&clGzYCr_X5{g%!mVyD(^TraX*ziW}yb+5nqJ*88<3a_2Zf3&;XP~!2fwtLx*
z)22=1;Nm)TWo7V3&=jM(y1U`DL)Ti5C9T=Yj~Mk4+-rrhLR0eKp;m51PoZaLW;Xx)
z{QUKw&;NeESGKp8=N8vv`Jgm2>%;`b6X(tyTj1C{Ve;g~h3D?viTRp0w`~h+!?9jz
zXO2czZn2ClzaRJ88x%h~lXQ3S?Ag+KaeG!wWw6h?V=>n=HZU-7!`7`w=U5h(sM)=^
z_4NGZ%fbs6F1)cNQ~24rx!l#&)u8_8dx?Ho>t)6pBSec2#(rtzm*-PtxmW+cc5QOp
zy|WwR_t%{`fByK2z{L~h&tI>1{=|s`*W>GXJttk*o*%#Wan6MWj7-eTA5ZJ=2er(s
zZqKo+l`4OKPxn&{XpzjfZ^!=q{S6ve1&=nl^~tQ9x@6Ae$%~CSP0h{2_fB3tb?Vf6
z-xu+RhljJUvOWY&cUhOObGy4O_x6M-Q&Oh9j);nS^m_e%x3V%bP#bR2<1=T@fFjhU
z=0`yG_baET>nA@uGZVDr;hNw2HUmS$gBubL7refv%Oh>Z<3Hc-YF6>{bFzDd6z|@-
z!;qm~wsiUO*LVIJD=Rxc?`OBE`ohsKZ{N0ZrKZ<Zt<V>y!NI{3=gnJZoaRu>vvcRp
zhyVWmj=CPRC1awM;Y;5g6(5zrBbC!8OlYvJ{<a|N>MASYC)}@YZ`XhG_N}0>aP#4I
z{_LyVieGM7#(8>paI^^g_;x#g>!dTzPEH?=%hxA7KGs`MQsOe#s??<K?}KLkgsiNt
ziOTMe9v$tDdVcQg*-)PY`Wi+?LQWi@S%DL0&xTG<Pfblc)WYd@JMi|!i-HHbRo+gQ
zwJ2~Xv|;#l-umn;Q)f3fwskQ(KXFYITbF)*o`I?9(KV5qx73|^^!dEKxfj!N!{=R(
zjIJ3o#_jRef8SL7<b)uowEOn$8)*5!m8bHxUj*mbR=4e|{jH>}?fp82U(N<pZkwKx
zk(Ct{{(pLkCbQ?Hl6~b221QRiI21wSQeX8Rv!<q}KYnnq+4bIHJ$62shR#mTS*F>`
z!mE?lt9L0I83|2NNql)}X~eD)O%+e4kdP^1)=STW*6Ha)ZFw;@DdW}_%~heR+ia`9
zfdWOUbaUF-OEVX|fA)+`u_esrc)z@RPR^Qhm1{OwdV21!`>W7$;Kjworq=>Mok7rG
zgy*CS`|IoXo=@kfJ)Tndtbfrl&%z(Se=m;Ongwd2)cyOJ-n*;x^|i$N`)XH&t(9V8
zVv75@`n{+DY%KtIM5gn--mwb{o!NKn+?n|JSZ~DEtk8|?vR~|dcXxOA^Yoji-_KHf
z?UZbI?N&Q{v0+C?++4Jkmhs!Ouj|F^C}1poeNDH-{m8$+zmp#w>5SNv!kLtmq;T5k
zSg&-ub30$+<z>DfK79f$8vu=3ZrNf2nz9UD?&q44qQW3?Wn1uazZFqiwZhiLblU&_
zBfM|lJ`ZniXD25nP<>MMHLLl3@skr1L96L%YH9@J<oJw@jo;kgFQ0yXp6l^G*^QZ(
z)q216_4P$;Ok&+t^0Mi{gM=-)x5Y|dT{(ETogY+v-q}&;oZfVCf}-<=<l}rxmM>5K
z@!_F?x%qYLWAp2NaejVw*4e><!N$fWV406(%)T1Q*=D&-t*xwfe?B;u-u`~Cn*aB=
zw}<`h|F*0OUA-uHxt~V(I+?t?yIP+-N%`{rzI^iWKGqLO>2KFYZ&y-O1O<re?y|QN
z=FaWintlDzySux8yxDyI!j{b7=3m7}yF@v7d5>1V-`hUZIQ`J|>*C+OecMs^m<=>z
zY@B`$R8?w(uZx-Z95fkxull_$Xe|P0*+FY7D`=74^Yil;=iS|9QTl4iuD6rb{RIRB
z82tVHK}+HC_kI-vwE^GW-v0Q`&f*tWRtm2QT^;tswENb>AE}$u&$sR0Zx0%_im(4G
z3JRa8+ToyO1)!cECnsmr?iz9T`F6Di$;Wv9d^|31^*T8@d1LwexIZ5b^IMd>5NK*{
zF8uy3c1`SVv3_~`V{dM5{&+1qe{T>^^06M!V1+^cJsZ#x07XT`6%iYiE?vG{`0<e|
zD6a0;eCAyhzCP|nrIcwFOMQL)pHHXtLH&0J2Zn#YUhC)F-6eYO-o1jt!iyR8pP%_&
zSsl*5HT$~TT&vOtuU>Vv^UEiFes=c9>-GB$l8$sJ3Ab*`zuy<Q*lnTbWVH{UJ~d6A
zEDRc>YiVJbF=Ix;l@)=nw#nE1P!tjt1})G4EmS;rj?cYM=HS1-zd_TSYhrhA`!P48
z0koFuc*fmbr67l{iQg|bZQ8VmJr#u$k6T+<B;4Iq3R<)B=g%JjDXFemrrA!DRQ~*Y
zJ|8r0_wN4w{x@&lBpnr(k>QD)HgVp(zE@XQFRuCd>D8_a7Xn<|-IbM<nFR#}qmGBI
z4&&_>*LVB>?=NTuW=rN}wz#;s6KBu5Mny?|dv_N!4Yy?3GBGLVloS<EH{-|=7tq8#
zXj(fjPY;x<P4ezYJU>6*{L~L_Uf!d(wq}1kXZ?Ob?C!D+TecjD&fnV#ns=Y9?(bGq
zWW>bG{P5j7zU=I5P-i%LdtU3}#ma1aGApi|9y)yZ<LC4C%7%u5&FuVjPiK^_3|h(s
zT6d?v|Bq1V>uavi6+&-sZ&x-p7A}2#Ep$#YPvV-LPVxHZZy&2tJJ2o97O^Em5Hw_3
zUtfP`S1EV)wKa_bOrM{fZQi<d>#p4U`)Ui{+%N>qKYsY|!Qu6_wShZ}QbAn@&|;~1
zw$&Hb$J>KsUnM&^J8!J|ngtqA{rdWP`^=e=vrMzw4jgcpq8BT*Z{NNfyUX?O)qanK
ztQ%$lg~!`lTLp!Lnm}U`UtU}Ul^eIVX0w-<m)q3+k+{A-{y1offP_RxeEr|63;xyo
z_@D?Hgb~w?I&kcm+xq0V<5h<OrfP*c6%-gunluSi6W!XH4a!eZZ$TMD)q9$Pk`j}k
zpkP5^;lY=emrtBAqhnp{?pHojOhF4`F02aGZfS2{T>Sjphc91_fQB&U%mJ<70d;?*
z-YP3A8>XHT>5(vGI(hOW$aQ*gdpgd}HdnT>iAlFvxNzYNqf{<XrUtF4J$8)k+qZ8L
zRwXNvVr;9vfEEs1TNm3s%QRa_M~7#UO5))*-W_FcrFNCS2d!b;e`&9_VTzBGRlP><
zWWTvq3&Yk%9qqHUvy%hO4Q$W5dtqg;dPQ|LDC>K8cr?tND?3du_SdPui;`a4`srI+
zUKyH}mKL$QOgCzKUhh2H>ZE&nDnESweE9Nm|B16^b<MRd&-(l0#%Z3t*B>5kfBfw1
z><{0+x6hs}?KM@ab+LQDlBK2OyLazimEW0AnwZG*^IigKLr=0%L21$dE$Qdyb^6=?
z4cW0{2Zy(}_ruq(wYTNpk9$(+=;-J)No8)m*Ho>qY)a}%5b*2%#ns{Zil;aIc-SuA
zm2-Pls5WSpdP8FKE**V+|1<M!qksJR#U(8*otT@eyJydyBMTgxk32m+-L%hq$=hCO
zbC>V$?zS#oym-T=O+vlW=3>%jIRd-O-U@Bf>Hhfmc=i^4E-oQ8HMQ1b^78Wfudc3E
zU$b_t>&~L5E)^9!ENXvk>FDbd+oaQdcXxTV?BrRqv=%K|<g(OjYRk@@J2m3>?cw0!
z65<xuyHeS^XOB(bx)@8v)0;eeeRWOdO_#MQ@!*j(a{2M&$BOs6v#zcJ&HaPg?N<Gf
z8<Sc=I=_AUcIeWjppcb8u3z5Wjh3;mi&=bkbNcxsphX{9*VpN;S+k~P?b@{&*VfF8
z*ju&rn&tY~-D)Y3Vt;>q)i$|zykEXMfB)Ywlbjm?H*VbE(AL%tT<RqXTDP#V;GxsR
zxpUWk->V<DC*sPgQ16I{hz>4Mt&W4u?A^b=zt6V4e&<dMC^=qS7i$eFs5wE=@#Klh
zER#&7XXoeZ7Zn$qo_qc5nHp#vc%YcLxOz&Y*vF3_t&%6EMz*xHWK5lJUmw@f-rjAL
zdI~gva&b#$@W<Ed_jj!fUd|Oc&DF`NDen8KUH@)uOfJ2quBOHnIjvRaw33lg&}utv
zZSR_YKc62ueH!dAqtsI!*VaaN%UYLZYz>vt*V^^VJ@w|M)J3k{VuvnX44g50cDL75
zt<D1n90aAMwe#-mSa^MJT3TAyLg#j_^78V;%uG!iTic`I@wKY+Y$_L(zGdf^>sY`4
zUsOw5TbI{VEzlZ`hmRg9H8nSv?pwZVj%{^V&7Y6Q7X>bMJ9P4-XGBB<M|pYq#jV-l
zg%1ueuKgChEl1FImWklDZQB<4%rsi$JKHSj{k^?i?>!R#hTf35vfN)Dw3cCA{Qh-%
zx3^|bpP=G-<j9eZDN{s1YYRcE7IJcPU1yu+9=W*Kee1d48!@GSf0Y{M+%N#GhtSd0
zZJj%J?uxj*yE=M$M5N90bhg~@y0pNNS@HBH3A3CTZk2g?>o#oLCZ?vQ2FizB$LHJC
zMtymEJAB8^onXJbc%cDGAZ)x+DrN8Pth^YuQhvT|wc4>>X?0M1)vW`qVF9h{nWWNL
zey`GfacyGlQj_CPpFZu>-~T75qN1WBXsH(`WVMBWQ^(ue+d+%0I%k<?b5&PYgLBi~
zy+_;S>ohK1y2SN%e^XIWQOoAdn?HR1e0i1jxeDDkcGGpE)m~j+zkZ&&va<5gx3{;u
zu8rF2GSetE?&mGm^^4EPEPS8dt+(sg62p0(2WOm{Yps6h(4m&*=4Or9U0XPKcyzwJ
zU$ZUerjk|33xzpz=eF+LxpPIp!ln;jzltUw?-PA~e*X20+4JV<RegP>dTP49zK^dj
zC;_Rdxy9E1{FDk>dKtJaCo(Z9X;JaNoBQkczqqz`_KJv&iww-o#r^#J7RBwYdNkSJ
z?&2(cuIf0g&(F>ZZ_<&rv6m>eU3mVM@ATBu(>NoiwSpE~+STq#+Re<)*Ky%Oz{3X*
z6hN_;kg(v!j>5%`*(VPjJGL?TxXbNrxvgv0uHCS8tLWOOtwNfbnq7}Sy}7v=)aE;M
z^JZj3baZzcuXNYZZgKHj{+E~gi<@R$5fBp-bDEa=@ZGz(j6GV#&&~+;N|_2R^`0&U
z!o1REBE`?nT)Y{Uc~`mR-Fbc0qmq-`)|h^gRNp0H=Fg>gq?KFTB_(A^L1CfbQm?5(
zdU|@G92B#o;NXK|(W4i(et!MuUDBH8>pnf7Uk}O-U0R{5IEsslK_T<-`E$^ejp;4T
zv;J*&Uf<f9?RtKmZR_;u(>H9~C|Fijwy5mwt)w$E43(6Xo$sETP`dC^g#Mdq=fuA$
zJ*d5ODNhdO?aLLE7S&G$Z5IG7B|R}w8MN17#|{e_s}hdgWpA}g+FO<^QTg-rdc0I>
z{r|t_pdRy<{QGj!=6N-D7s5AYy)60qDiky}Z(sl_inU%Ayx;|G<^i>Bil3ibn00lP
zsx04M_c!<UN*_FU5VW)F#>QlCt2zJIyuH1Bap~)861G()YJPJfE<JpqYGx(|+Lr~|
zYE%6D+4Ywf7rTS@JMFFdx}pC6Kl7^GU*(xMHYje|yt(k%8A*>xA(tK^jYta$3QA6e
zbX|^?zqp{dCT_3P<z>EyPfS#1WY}B%-ED2u)(<b2&j*bmbscYOYs;Fd8^2HHK==Qf
zlVRPT6-#_(8nH5bILIzPr9dUc$BARf^5utb-i%yqqp8W6eQgbB_2tYOzb{gE_ti>^
zYK2_T*j@f!4z!QXV^T}`y~^b+O2&6iOjI^3e;3muYc0mf$+`Zil%%BOhV9$iSHArJ
zcWPB!oSfaS7s@u(-+1O)m)GfDU;4j|SK16TVGLTzKKVS-s9{IPi+Um93!NSR4qsav
z%^n;a%p+mo5Sx~l*Z1%5@5iV0_a8Ys+dOb%lIz~{+iQLnfhISTkN2%tj)By<N=izu
zpvgYaj*f0|eI-3TK07<Rj*bqEmm5xW6crVL+T0HwBve#aAHH%$B>mi+gWulXPRz^e
zySX`idP#@N|H~k^g2wE8XPbd4Q_$KQP#b>c%$X7<83IyfIT4o>U!A>kN9Oc2-NWbR
zT7P_UQaB<iO6sqa{r^A4$NFTuL2a_DS3wIEkI%EM2G6vvkDqTp>C^w6ppmR!UtVV1
z-j?gxj=TWC#pO$s0pr|`7xth@Z&1U3>(;Gqm5-10Uj6z@Z9#fU3TV&Ji;IhoXaAJn
z3X8rDuHvVsL_u5NK(lwC#*cjcpN&hLm6VN*jSoLK*bEv=cW&oXw6>N`Jw45Jd*0m-
zH`C`Y%)7fwRaWUQyXT}YZsqcR9v+~jv0XXOpFL|^v0{a}z{G!`<)ZWE^_`t<4q8A8
z+Bb1_mg&cP)$bSP-`}SyJMSP96O({|z=vDs-oJj`ec*t@o4dQkzrVZ7%&=qk?&LEw
z41avN?4OvI_wUv^-~V-YcbDtG6o9)L%!t$W<WTgo;!sl3ng?pB*8Kc*V_)rVx1TpR
zr-M2Z;FU_{Uk-t~XrPHP&~$9r+NiyK1xV@T-{oK5-gbjZqnqn0KR@&E^Q!~(OppfY
zK)Gao3~2jC;78laPcF~-q{YO<URBkujo8Ta^wd=6ZZX{+F?ocJi~lEq+RC6=E_)w4
zSYr;FycYd8x;%-mp`)Yg{H04m=jYj8)~f&YW#z6o`SA5|u3lbTpz*dyy<gisjf{*Y
z%$UJpZf?GJy(7{%ISMoX++=nCg15I!x8&WGN<BSI_hmsx#|!%w(C+d7iK1E|2i8V!
z-*PJd{yts?P!IC8&FSg-?JAxxZf;&4_f}X~_~X0X?_bGlAY6~in%a?idfLM9^>M1Q
zY=VM++aW3J%<<#wpf$&jkM}3$=C0NA_w;O3@%-@d<HgrD+TrV3+S}Qs%=6ZSSDTxg
zGwAPY2w5L@_rZ?NjuRDbeKMUdFE5{7BJtnrjdUs&H2cuT`Y9Xpu_CVH{{oNg!-_Oz
ze!ENlcEg626}*v$+jRHbJlpQ_`?cY7*_~Wmmgs{9VE?wey0|2~y0Q|qQv{TI865ol
z_#Qoa^x*mP_AXIvCWd!+b~dkBqf=2;b?C?um&Y>dese$*O@?`QEcUL?&dlUwSP{3^
z>eco2`Ac>yDlK}nVe{t4F>4xX7x!R6!4}{8jlT6_L%t7h*q^##juo{g|JO*qj}?jZ
z{e{~UY!NEQA$akB^83EfB{qi*c<yiJ6bib1BWEcKw{Faaj}|#9dzUY0P1wCWVe_Kf
z6%2B1+Z5-nYvo`rJD7KQ52wn*$tnvrPmT%yd-lVpFXr}tVwp-BY|DOsd;9L*-rI-U
z`G0?S=p4R2?(NIV%lFp)-Zpvi<oow+D?ThpKR@s5v$M1L`1${TkYB!hd9K;)cXxMx
z-+G=MexL-1p(nv;bzolgzdx1za<;F&eA&`3Z(sKL+1a>#H8(+pd;R8{IaU@HKThYL
zKYzaZ<0DshclX%cWpA_R@q)C&af}1VUF9z?E$!>?x3;s3+h=KM`SY;&MUVki-{0Mx
zZo>~(3}W0+zHd|a=f}r&{R|2F_tgL2r|v(m<p00F>tc3pdR@%$?|a^z9UET@>*?HH
zb2II%S@yQb&1YxjUd!2>Hv9bM^H7#4lH~K7>8Q#;lFvTB*_<{T#6mXXbLBUvX`jP?
z@iY8ed-mtgpFbfksr$QY@nX<!imPj*x0ltToF!Vn=s&}Q`&Ku;GJ<@7gkyM^N|3l9
zrWT_Wh(f~74Jd{&FgU0>phgBm0td!Xr7Y-2mGWR1Je2|c3{*vQgBJ)bU`BEZ0|SEr
zhQT2ierUrm*bChc2L#X!4&X%hg9L`bqk#jDjM2b>2gPX0fd|ECwt@#m!)TcU4~x+P
z86Fg)wG})lMyqmoP>i;7;6c$a#2bMtbA|51)&hV$HQHJRg#rW<)0L>%{TkHdZ>WFw
z=FOV7WxHP+@0)RYx_)^@#g5m;5M#jPzjAO-U_<)3bLW0NY=2$*>&xkN{y&rU{eJhm
z?%z*!L8N}nfp9fY&!WM0^W8jkJNvck-v64T|6sXY?XQh*%d|mKU?UkA7=E0Bn7Vyk
z`1Z0|7ML&t1H*qs_T6?!d=Rst+Y!BEF&f>VfPr9QqI<OG2nnmvZZ#|%K=epRIe$*w
z``dCXR4+lM?(#9SW53vCr*5&>p>d3H<<hA^0R<OZAGom`Ws71tI#)q-qn1{O7w459
z>B=H1p~_n|y1MmRxb&8EahHlW#om~>rOVxG;jxViip9V0ZVXx+S6XFs^0UtVnTPjm
zp6M*MUxtB!VG>40(*T!rpwNb46+w(a5e!`(O31|}Naq5Kp_B<O7^NacrLNG4F-YTt
zp-Tv3%%~MZmkP!x4Ht$kPYkb$VCWhRAW&q&@n`_Sg95}DO+lbgfaB3D1`i4b28IS|
zmO;Pn%`{HmRQ>(kn&|C%hYugVxvMmrPu}j&^!4^NKMJ<x-kx?^Z@13$m?F=-T`!mI
z`FzgWHiie;H4HjoOeGC=<?r`?f3|db+^KVOtv{dAUY}A>V6gpuU3H&~<)`J>{rvo%
zZM&U!dR6G^P3h<7y}7&FeEYqs?0tW~-Tu4*R9_%WjL2boEyr-+{`a5H=RbdNu(|SK
ztN5nu>+4ibo||i3e3;k#$whbhv+DC}Ha*ySyifLYGr!%8cDX7IVPWCt*+vL+7#J8f
zbW}1~ImlOkzguo>VKIYUt|H-I&evC0cmDtP`}51?^V7=8$_{47*M7bF=iBZ4%4ajv
zC#l%~{StisI}?gI-Ln~F7xdSDy&Asr-LBW0($3D>d~SQrO{4$6oa}zRSR7OT_p4>e
zi-2`IpUsM?`FM2aqb}`FUoQJEzy0=Gi8+c%8!ULQ*)lZje}AM?SW;5b@_9{4ipt$Q
z^W**U@gHuj-~Z1_JAB=l+V6L#-`!oFez=Xd^8McLpY9Z&e|kN>{_N-T_V-V}L^1Gy
zl8OWSi)8!%e~QD_$JL(udEvr^Kd-qhYk!sOx|?_G`0>vtl>1dY-|hK)4zxnE^5@g(
zpN|OpKUvhR_v&l`ictxHLJOF`Y~<G8W3d0vr_+|t=lZ4p`)a?dEH6**_V#@H*EKmg
zI`VZt68HW2box%wY2E+t5*QxHye+d14ZUi+c)3)s+pM!`ca0hTO}L+oF!_f*qm_fa
zw4~(8kB^U^x3n*O<T5Gc?X9ical6aj-jcDcG69{Y5cxbjwls9t-8{c}Hb0lo-=BSb
zT};)>rRj5fdwWxJa^9>z!`_g({%&4+$(E^p>FeHU+M1e}%$Yee^P=*GjGwlkEA_xu
z{<_=9%wF{1K;!0fesirtFH14}nhT1&+&eoA<?H_x`pvhSYnpxS%>4RqH`660Bu*Ub
zl@{Lvn#!}R`jU~Bo?iTR>-BT<&!0P&mXM$j9#{EvejVuS;~BoQ&HgTa&%kgxGBi}R
zY>wBZRn>m|KFcrPoVaQgOaFmIPrplm9l*fA@S=SGcZY-e`+g|RHqT#|Dai2Gr-ARn
z@prpkuLC9g-{0PzKFn`FN5!)Ena{WP_vf#T-kx@MSE=Wu_xpb9E%%#y>etuTn~R>F
zQaNe+{m$g=_v@_J@BJ1vulCzb70>Or&pvsQqPPD~QGEi#fy%31kLK@UxN`ozA<S|H
z2967iziv#^jV}6rxBU6X<MQXf->;wl_4W1i|Ns74mc5BkQ&)d}|ND*P{-?d>_fDAK
zuQC3=WViLZ9m==2<({5rTm9)Uzx|VA()nk8zu!M!*}X62{=V9s51P1N{fa_Z!oa}b
z;LGxYq4wQb^ZRFl{cWeNT)A?NO{I~vS<Z=t&h15?&zhg#pPrDQpdGfx;`uFpyB`Yv
zc0W`2<ZNbKkFU2~ym)ct>$TfA)&BnW`KKs~xecyP4SW}#hpmm8`tjq(p8kIQAM;M0
zJh^#Z$3OeShY!!3G2_IMBQE;tsCl&Z(VgQDQH2;b=wM8;jkYII!a86?H@HC+4LmsZ
zUdr1Z92$DpxN6nKj3qa7uGxadg%}!Ck@^V-CSA$fZfteSYq@dw_bKzFq@>QBIkSZW
zJg?kPkJMRcP+hrdmC$^D)y%85%iWh<e)+~DG!)tg_$LZwfUKUjBW#jyX+Ma`(6DdA
zqIc+X<~n>xs=>-e`&N)(fRUqJ2UtjeX`;FgD$S*cbtVtyXKuf}a@DGLlD1bfOfKb^
zy`Be2h2HZJ-QNZMTW`PZ>DzYc<(aFtOP9B`wHX^5>pFo~W;DnNBYN^*Hm+LbRbw}G
zN$B@Eax?vwZ&nTsg%-mLjw5x9y`8jAF5Be}b~8h5p6gw3c7t%iWP}WoYOn~y=!gL%
z9H8XrkP0*)AQVwUDxUB{|FrAwyMCderRQI)bXz<zZFA&zM8D>r8gx)+4*T0O>&1)L
zmRJ>+`oCPcaN)x<XMDO5OLu-vfo73&%{Y@i$aM&Hs}Ti0NTT8X){#``A5B2X=hIe~
z?Vh`8)vI|IjeFgc&!%mDC&}<(ee|pEACA<@FibOs#sVmy7#w(Sy)AQdkA7M5?A5$W
z#?H=%XU?1{ww`gr5}o$yibr;Q45w#8BLl2{0b6M3)Ph_s&(-fNZ4Ku7rMs_MCA1Et
z{4Z4bY!u~TYgJ~yl4E4}bN|j^#)hStqa_kJ7~urLdbZ*JhH`twpzHne$K%&|`*mlu
zf85|1%$_OPu|d~IWRaer?5jx=5?owL&hkxdw~~-;SrXl@7p3bVaQDq5c78`ejl0u&
zJAOGteQXm*nQimr{fFxRf40uJ|K)Yx{GXpI8rbcvt@o8B+8fKK&C_FG2-%zqslwdC
zFPmsC-C~=(V%Ocgs=aZyjT2s3-e+L&5kLPQ;`oFTNCnhTf5pUCOzf8=PuT5wMj><0
z#e{`Tb7j1s^jw;u;pL;B@(|@cW{_m}q2Ei>lr6&RQhxQh2|DQp788QH6d0nO)G#v`
z#M=Ca)K?7`!E=2K4F6p1PbS?~ZdmyMRX)(<@;8XN2-2+?Ipu-Gv5e_puKvTU+A)`R
zOu}f<uOOxxg#-}DB~Xl|qlB?I63f85D*A9emVtMSl}Zkn1MirNH8BUhMgs^MS753^
z<z%Mfo{O-x06Dk8>GN7J_RPU>VD0lNnQPPMYl1cZgG`Uiknp{nlDKgG!Gx`EHJz`%
zJd>K5dQ<w@0@rh(VXT7JJLTHHK27HWX=%uY%-#quo)UClWBZgP_rJ|ij69c6ps-XV
ze_FE`C<mfhvd$Ge<KnZRZqm_h?hL^Pe}aZ>@@%g^-mveF54g#>;hGP`-5@KVSb~>`
z9?)nahlUn}8Z8AN;Q%GE6q72@>f^z+j9F?+r)*2-3Eh6%cm4J3YEYtNVDQmd4@&b4
z2cAIsHa?BZGB<6wa6Vzft#4BnzAAaPY15`RzKLK93|QjwL5zl%3gF^z2Gi0hztT1=
zRr$N^InT)=wq|C{r4`PQ@j;%(>(U^#309DTdYKov+5ibLG;DnKl?}x~U*+RKi_nWu
zitwH(m`>3F^~4gEK+FUi#=sz<xpa!ue0|lI+ilZ5rWs4fcxZxi-~kUv)`coFSoF(N
z?6w>z{{^QmdkdnWGGMBQ4N@C|IS^vB9)g4elpL*xpaB7<hGt7fWoB+Q*!eJG%hJqQ
zQ-W^IGYq+#XTCRX{aZ-}h8|ATtPs31bC!<I7h{Pv+iX);Sk2wJW{nQ0Z@5DbwZ>W&
zq`CCib8pXIx#uM(J>_9z5Ap)#z=BwmY|Y@a6H+lU9PpTtiRu~#28P9$YrjUDO|aMk
z(U>dX>D#V^)F=&}7fpP<G;_~OtjgOyJ8pgX;rY+2nHd-giq-z^I%O)#Fgfdz{9)n#
z#|#Yh&mldI$>0&@*9$Nc)BOwGC-;G>A@g*pb*p2784Ws@Jv6lWXu-$up&rr$NdQ;%
z39?gyUUi>9Nn$$}ichKq)k}Hjp2UamT*j1O<ohqV;!&Xt!-M~o|3D*m2fzbr2X?(u
zkIbn)((!38BLl+@%XO<65^O4Y*coQ%&HE3k4h;UK-I4<ZF%mwILCiWFRd9WXq>aq(
zz*T5-7G{#fx@DO`UYXU$0!nw^{Zh4eTRH>7fg6yT8m7i)1NLgNVYUj2t7ar%uO`hs
z!Oc~eaR#EWYO-g?%x$31gUNts11Z$J%)o$cuySPevX0$b>OK9_uh;9-e}8*BbN1}h
z@9yp{esyJK{og(O_J0hFjg7<q-rP}`T=)C!_Gq+K01~F4_Su7HHvj*8{`qF}`JxXG
z4!*guQTcek{Q1fLb~7(8_fJ1R&-VYvV)L9E6F_sM-|rNkpY^!>PT_F@ad6iM6fI!9
z*sFoh;Ml&O&t}(rI;jqt=LO9|s#Lz)`Ml_U?f0i!ug9I99$)u!{r8VYg#A+r3kz=q
zgOWX1Gl*y~GywJC|5eYg`<0oNp8olgw|=bUw#>`R_WXF%{qxo8^`AbUw~xR6H)c<T
zVg28)*Egi0&O|0VfnD(T+wD8m@Aux^Q~7z;<K1O%cYXT!|H-GPrz^i)bl;qMdfJ(@
zXP>@YKL6bJ`}Ou)_JVAN;{zG9K^4^hy`P_-Pp_-{x9aid&!2bJ{46>**Sh@d`MI-a
zpXS!zGvT;gwNCW5oRc$+(~G{mxCokVPCq~I?6<eK+bzMfRB!_&9GOZQ48I+huTQzW
z%r{*2eTh}LU7apya(Z9w?{$Cvu3SFv)Z>2pdG2zRD)0Av_PbaA|L<3M#1JXSq#hGS
zs{<0dL8~~P&##Xwtuc^@`T3*w#_sZbxw;<@=UA0y#eM?^<%M~e85U#$1A~tU$c)+Z
z=bztM{Cu5N-M>FSRZh+=zgKzqd*$`m@~6As@7ulZwwz6cLG<>#*y5c3|Nh?GU;m%?
z|8B7UHS@9Oa*$-gtGO11O6q=dB8uM}YUS2l%b0M7^8(|s8=#dWzrMT#Mb~We{C!1#
zUa#MOu8miEQ}Oe2()-SX4jQ|?EqC|2+xx!XtB#C`+4Ha-oTM5aYAwC;qejzn|65Dv
zO>+)DaPZQERrSm6+5dGqxH<j&vxDsNIhleCk9|OqKCklG%ss!~?f&_ong7$P)$7$f
z^<sBTd3?M-{rkJSH}}<6PkJ&vzV2izxA>;y<9#`Ib{L-gzwhUU+i%zH+<)HwzfJnN
zIVZK(?<vaOF97lqL)()1N9t9;U2p~lh67)P7clp1jNM(9dVgOnXc0=?->=tU8O7iJ
z@08@@eX%?5O6TvH*l+hs!~Wlo$5Zb!ZB9Qw&*sAc=E@ff+c%ZIzBb3QSPit6=5G1@
zxz6o;TfeG;BModJh|m>Uz}&O5-~OLP{=T1S)22=P^!xq(=l_1cKYwzv`sVWY_q4a)
z+>q#;mX>y{=HBM>cC#m|`#<Z}-*@8GtE^|wpMU;zTL1al?e|V?%e|fVbvmlqJq(Oi
z2WISkyX|(-lM@qVEQ_AZ+HP6)=Eki19rIM$`Q^_&Jlx)H3mNJIxdntJl#Tz_34>Tj
zcv<7<pc+zeP_OYb=_YD*x27E<FUL$SHe~3rM`<1#e4DlG<RK^f=7U+cgWFbJo_YGz
zsZAdQB|Og^WiXILsV)!P&|Z4wK_N=MTI8OfVkypiAO*FZA-rUM%Eq^X48iAiN-!L|
zN$zk_+HKSZO%ImxsYe9GKMWh(E}KL~yht~Q$gMsVP-;~i85t?IkeT66FKWVzSUe@@
z@n@9YKd4{+&kdzL!4TsN?fLI$9pL8G2m3d-H)bi{lybY+`_jQ8Y)y#9*Uvvb{_#7M
zc~squOa15J(*~Ezuc$_6KV_9?=VNuv9o>!%&uIY|jk?jm84VoF&M58ns)z3XhFqBa
ziMhRP>$O|e$6{sskNYjZd=I>h?Vm8Lp#qAW2YTCbU)Ss_*<JhA_USsl_Um@`>y<!f
zb3AZIDQ?R*UYqsf&*EKgY@hqByPNlZ?N)HPeV`vQ&<Qe%fq~)Oo1ndKZ9z@mhWZDo
z?@{Y_1_m3<5k$=C9gH0tLvW8Oazym!-QIRBs`~tn)sH{kcv*4_I;_mVU=8o39=LyF
z+uF}RFTMS?_4}0FRx)wF|Lp04EiITg2VSZCI~JAw=yU(8P2cBO?=0KBcl$N?Oq`7+
zyo&mxJpEPfdqHTF6ol(nqqdnC7#<jcsv)QX2!%OqGJ0+bBxD#E7)ApJ9u!zk+<A5V
z9;i?Bp#J8zwOg;<Gk*7~!luk>?zef24F4_P7lO3zv%bFrL^q_Xfks>&Jj}U$?Ptx)
zvfsC=PsPget*@<%`+I}=K>s6K(2+j}%AZS%gOq=G11@B2=4`$8=fdZ}*l+WS)vxDm
z|9&m1?iJ$$_m6U*!IuZSKlgHjR9BRN3pTkMORH{IvoL&!-g6vO0R4DZ^B7bjG0eMs
z8thPzS{SYvJ%|Vv6bz&77kE&RS4FS-we>s9hzGxKq2-2y!arYrKQ$Me6d5XVz-bkv
z`oVV0%)q+&kKp-&^>-k1@(stqxdx<|q3(24w$e?MD&X`d_dkECpZb9kI|GA_6}%$&
zP`@iAzk0Tb<|Eizfc^&gV|yVkNRS_`7r-G3Ax6T+Uj_!c=5c7f01DrKOLA{VWxut3
zysqzf^76|s<L#g4fW$!<mRvuWV75g6Yi%hr11Vx)U~qtSuNu@hU7K~_7jj$lUueo(
zn1K!OHj)2JP;2y&qa}Eroq>U&B5gFyLqiipjiz}}D1b5M%sqL5gGloa%5!gDi^_g4
zSzc-*XFb=i`aIYo1_p))p0L*Uk7<}m9^Cl?EB(g-%NqAD;cWLad~k=G_Dt{U?R&~#
zy&!AcD{f-U9rt6-9b?SQVQJ!ln_)16LG)<n02B&fOykbM2l49f?>Ck1Wh?koJ3F;Y
z&_u-F%he;eMWiDjIyyk)$^!wuuWM|t2Dq7;uy8d#ys;=!!Rf&jfe@2W7Z-1D=Pv?T
zzKR^vSmr%-68K%{_dMe6oa@<p-o5``9Dm>b!C6oP8tjYFUJfi6K=f!90EGe=56yFh
zHheiZ-~K*moAkEa+qX8QdhafO|L*Vi`~UmTN5;nH9&Y2c{c^!MJi#06M;MVH$#H>k
z+MRoQtE>Nhy<Yw2<8kYf7Xi}dd2bro<z77QxBs{O{Et7M&sTpwYkqrA<!8}5A~3CB
z`p0tN1<X1d&)fZ8^Z0oG_WJ+-zP-PHf3m;bO?LU33v0LEyH$MN_Iv*P&D*wJySKM`
z_s3(>>mO_bYlRU9?B_DbCUoxoe9k)e&W?>&uU_rm>^s}+>k(o9FDKRKmwbA1(%uGi
ziz;Xn`rco!R)-gb!t{da1Wu42ZcLA_yD3|K=i;@s(fTvr-`e{6(fj?+-`w2%_V)Jm
z;_)>X-#!Pch7k=6vI#Ti+STrwI(6#lXWH7@u{#PD1~2#f`|kJpJ)gXyx8=NixqSY<
zAZ<wJ0jAA6<?;Q!3=H-6b{0RswI%a%>gVkBd%rz;zyIm$_50slSm-QkU$<xV`hCB;
z-g3b7fN33mb5KZ~oo)UdG+}P`|K;-edjI}KU%Pf~*ZY0HtA0FeUw@+xtQ1BZC@N&O
zIv^As8Ts<c%HZi|{pZ`oUOj7m|Ih08wLc!V@BMzSdagy`qOV`SuF{LyaY29opG!N7
zpGU>Vzi*Syd$H^Fy5D#I*FT$?z6*3I)y%gyH!ruX{`P0)c}TYjV#@=6i?TNn$NOY=
zr<6TAGjo5YG{ZD-e7wE0b92AluN9lq&u=SzeXaYmzy04WN0Tm|n`>SFb?^Iqzt<g2
zx~SZ5Q*^RsV+1IY^7jAz#wTZUBiP^e>+b*cA08Zhx9|76|NopJ7D31#m+Rg-f%b<l
zs(!cgdHyYqhEz2N_K2i@yI&cgo!<F-KDwQ^`<)Z|{QUg)CnhSty|;IF?(J=%U;lo;
zU;gaO%(6E(E{2B3Uj6(1{{2p2bv^6+($cNB^LDSD9#^%}`u(2I`hUeBHbKb;@6|!(
z?=E}$YU6Ra*RA4lFWTknGLHAj%32mJ`TF%MpS)eo$DOsmzm<M@adF?@Z@2SyKApBL
z|NgyiZ*S{c=jZ0Got?L9CA)mhhxLC@R{%VacWU6<@Z?_A>$P!pKcC*K`~9}=&qwfH
z_j|S9@4nmn{a*KZ9kFh+oEsn7({;tV#k!A9jR6nyKpn@x@Pi$ce|BcC+qsOHov-A<
zfyVna&ptdnJpE3`zi801jsH)x;EF+v1CxF}eqDeZgP^0-_M?nRgVYVdA>`3!87Shw
zn7pR=Xqy!rcnl1qr=-IIf?@Osc|=e!jAko%U{I_3KU(I%f^@V81q+GMG6x<K45MWZ
zA}mJB9C%oau9JcX#h{pk{h<Ht-80wIRs0V=xX-TPRAk~-OBNH9Z4xjv(9IBS)XfTR
zEKy17n6Z?*dhx%8NS8~CT)U@m>8wocjuUeXyr^{R$iXnpCn}PXZZAVB%<S8g=QSU{
zkT$P)UG~=xd*kQ5|I1$U1Kw%FGQfng@(2_(SV9G(s>R&eNz7^^V#dQqodb#kFdmI8
za4>+0hM|{sdhe}?fvp8d7){pTXao_X$r=<25Ih8v^=MLtL>-76P0FB9fZ)-j3<(D?
ziMi4mYyCB&qPx4>_UDtyxwp2gT)l4Bs<*ede?Q1BAM;@+XaeN-`~CZ8&YXE|ef<3|
zUrMaY-@TdaZ}*dX8|17Eutf|E3}H%)RtH+DpG<VWwLL!`H1~E?JU%BYYgP68z2BP@
ze_oHTzbhIZbMeld82!Cpf~vp2d;8<#<GZETV?on6^%uXv3<A>!yo|Qq;b!>oy!PME
z=X-xXn{E65&u7pC&Z@h+%gbM{-Tn<UJNEIo{Qu+W>FMdS=gzfFH#0ZC-fMpE#=hF$
zyPnUh)_eU9Y!r+*aOyEjNdxD%Yti|prlwbu`)#+GMDH%k-Mo2o?XQ>1Yk$ApF8+1j
z*Vos}-)_BL_UXw<@4Z?uy<pmak>v%0@SD^6``<j9ou7BOjraMP?YXzNmHc(`n`?EI
z-~P{qhlks%pUq7F^=kF{UBBP$)<3-utP@5YIAsR$m9CDCiLGtzy_%}3U7OR-m%X{M
zk$d0ch3#^$?v~$Qn{{@UsqMcXk8OXy**v`_9HtvgCp;}?vO2)>`|I`i=-p*+D?gXM
zzNQ<yf5Ok7KkwE5{~K5NbSh|y=+UF3{eQpRR=qC@)&(OXe$Hv&GdKu}%9+OL=Vs5h
ztF3zZt2O7|p30Zs5A)mKxwbaC`pZRk>yj52mPVt_bk5*lDrw*}v$eguG5Pqp+4?#<
zA*Fx6UXQ=>d)=N-r{3*;zwg=e=hnr~&g{31{TmO8E6^<9oSW-nci-BYecko1KFk#$
zy8hn5W_Ig}4-YIigErRA+{T!2iSq)Z8tCxiUmp(h|Ni-W{_PEkhcErveBLhm>Z;J(
zo1304y8rXE{{E70Z*Ka{wJJTx@V8YwF5~sJwc>xFr+0x&W?+c1`u`4m2J@oZdAoCG
znlU9zS{wI{mEp%{xrzskb^rf<2TfNkz4_=-5<8zv#_w-$K?#2qXiD#JJOB6N^7T4*
zzyJMyfByG<lhysdeY>4+Zftz{Sg*AHf8@mz3=9m~UBVzYZ_B-1_2D3U^{<!9t?T|&
znBOf4X6KW60h+$MzrX(FzUA|(R)xpcZq48KbJ@(9Ggp<pyK|G*{LY29+wb2iy&ijg
zqO!YH!2<_wZf;qtl8l{poDhFN$p|-4z<<A$z5eT+;`3jBy<Y$Qaliex%Foa4RX(2!
zI^BC|b=cadtFNxEK3|zvR<_OjUd3Y2eBP%gCqc)OgVF<N>iKb>^}ko}B}ov&!$2D_
zTcS6o`F{TV`Rw`g|BqLHdw;+FT<43>;^N}7XV1pI`wCGBB^x+5{W`QA%7IZI{yU&<
zZ^Jt3KHB(%g%`H*!O_qe4IKssB5Q1TP=OhvZDDXQfQiwzFgO^%1eUgNXz*#2vn4*<
zx32n<0Xik&ovGgHUTJePW8=+tvKbf{{=~x<Rf7yW&|*>bC8PfLZQZ$ce@_>!FN$0n
zT^`!b|KGWVkAYzW56ak_fui3W3&TgBudj}tRz3Ih6ZyGzf4}?9u>kM$i(rHAg8&&k
z!(w|#^z>>_mG_SwTup;S5jX;Mw>U_G_QQVvQ{MlJ-Mi{PL!UkOK`+HFjXWpkNL|4o
z1)<j2fypYV0=(k?8+K=`eOK5%tLVigCC4o{MG89?XmCtlF-=2hy{>D*exH}S_w0CZ
zJ^%h0oxcYj8}2(-Isda&{ej7#eN!M$V9V>^@PSA|$k9bCkZ@pNU>NFmb%H#CrEr3+
z<OWHDF^$(2gYAG4nE7b*@?>bxFffb;4m>DEFHeRC#b|*H4~o$O86Ff^n(d=iIXrYQ
z`!u70Ga5Lf?HqU-7+p9A4~o$iGCU|~uyF25SM37WS^%g$qlGgxAQ%{i?FQEk56;c8
zy!`NR`|XX%?&fz2oU6aRdHHtx{ePE>L5F*uK7IOb_4~cKx3{g`{chLlW_JEE&_S(<
zpiv-r;4nPM+Va#(pW(p$&!9<&XS4ISZQ69{++6GE=;+rUkIU!R*6wYWt9rqIUe>N=
z$NT;N_x=6-z5M&#^6y8*<G)<;)-V0@<D=gki;HWw-}|Ls$BHnRfq|jGRA2$K&IW$_
zKO3&c*Y6dNuh}?t>eN-BTQ5QLN_?_bS3t9f?djp+;nhDLwx6GE`|HKxw|94MpB`Vg
zQ`x=m&*I&PaTSo!;q$ZCe_>*X*#(*l(T(0#^5Mb3vp27;jgF3s18oX?KRbWl&%>Ml
z%gztC{d7Y4Zq4Vjph>|0C(tJBuKG6cZ8!jOx9#^km%qKeeSY@)dwZ)t|BC<kxZl3)
z*O!-|-BPEw!M9+8EN9qY!SaHEJ104L@zSMBxu1D^d;k6S`~6&-%1`>Xp#56+>wd3Y
zKELi)(OR@EasrH22bjQ9U%N_QvwnWPZg<}2Uq`FH-z~Q;dg9@4`!%Hc`@6k4)~H+Z
zx}8CeT(|$<FVF#?+|NKaxIX*Z{qbh{e9$JslK+3dmw$P2@$@cqS8j`W$;z;!#M|2&
z<hG`t$Bwy$Zogmmd%oS{*X#G^-QQPxx8$-fXhUD_?QOANeusyJ?fQ63`uuEJi-HBr
z?0hj_z{iV${S4ZLRoy3ReGNQ2`1iwM{_qTG1~Jf9y2iJ+wyysA^{d}}ySv}s-Zp<O
zU-QB7dQ7qJ?y|SP_CMeM``zwuZ*O0}xj8*LKK}i-+j+me-^a(szHMZe+p**>eAOTW
z1H%rRf7kh0K?j-2)qFUpy+x3r`^_!wy$lS~-<?#S|K`oj&3iwc(w@E9IQ`s~ZQHKR
zv#q|hG1)zIx!>GZpU>OBzq7M=_V>SEF8kYlyOErmlk??Tbbjgcx#j;}|3*tb;`I*f
z5ed7?-{<}R_jm7yL)@V0VbG4ity{P5`}JydT<zDZXMfMD|MxSl`t4TGrMT~QJnmZs
zI`9>AEAX`G(|<pi{C`9FakD~JMiJNdc@8f8B@WCYj;<mbe03PNY-kn8@!{O^;0b5v
zfufY?j^a!I-F^ihxEixNZvFh<w{PE;lb8ShvlbSzV7lSIcLU#tvwQdK`SRt<mDjJc
z<>lq?-oIbIGp4Gd;>R5szV^Q3kEa*s=jY4vwV!)l{QUFJ)7y9NwuT)k05*hy;g17T
zNkjg-XU~>hetG3($*;H1e*XM<y8A`w`}gnbe_w~Hf=~_l&we}y4b4Kh5Yis=tW}I#
zeGU*YuGIrS<P2gi1D131MvWN_n-|a^fKj9A1{M;SeW=l}84Vlsr5K}SF)U4tRxq%T
zU>GeZU_mijh{8f*w4i{6#ArbQ3yIN!0v-~h1qCc9Mhgm9NQ@Q~u#gxnDBvMMg@WS8
z(R+V)XT@%3l&Qbp?)=U9)K?V?*Wiwnjt64CXH6|SoWHQ|m?CJp)urX)i$xI%j(xd&
zizZ$Y(BsQ9t=OWd)KPcBaQ@S(bIo&>&*S(~@p(^Nf&TUHzaLiLtv@gubTs_vJPSOw
zXfV$LHG6b!1sV{;cy0ymLoj1BTY-ZCOpN5Sh8k4Me}8*>ujcdFviJAyKJK>%?{=#H
z_vgP&`Ri+I`{eEKb?fiD0Xin~)G04<{kR$iY1A1Aer-mp1Cv0Dv*l~Q1iJUhynNhm
zpI2JC6*S|ue&4TG`sZW!*X`xE`?28b*RS8+-MyW(vBCk}kkwb;#xXS1zXKi3xcR)@
z>%;u^Z*FW%4h0?k_k3RUI?(Kx{{BCo{Lk<EaEKc;X#<+7DSm#g^yjCi>|0^yaD(HM
z;lqR?&}odn|9n0l9UJ@h>-G5ibKc(AxcGWp_1e?Z^~)b0>$SK2eMH!QOZN43>>Je}
zx}f9+6_yta-fv!AT@BjR_V&)s&+~pZGP9e_NA>ofSf-K&)w0je&R)BAZQGga*RJiV
z{+{>x_3PUkP<OIzSOYfidVGEE@jlt;XZ?1+UOX#?S_YvS_Io$*Z8#!V{bnO*&zJ7!
z`*pu_KU+d1q2z)4TX)^%X83S^?b@|l_wC!4TKD<c*;VuEe!cwt>u>V$zOPq;{qGuE
z*Ze4G=a=8N{yy@&<pcY3^K5V5+?@V?CTLFS_7+}-(|#ZuL6cdn+~U7LTiA9MKY#Y;
z)KqO<vF>kgZ<ojKuYYu;6Etu1`xh_N4Pffut@_;oA7<z8%l!ZE@9iyu45xEacZ)MT
zm|y*LYWS@iH(oqBIeGTx+uQTYe|>ogI%V?R-QBBqmA($UzCQl_xw+Q2x1w%V+`w`N
z<P<&`iwmpQ@4FS9zxV3*`}OyY&)Zynd3pKoce@`6@cx0V1$b{&`s&KF>f`<L@6XIM
z22XX}+?-zg?_Tx$tr0rA%HBqmzrXkP%uM6hT_r15fo2FB|D)`<V@Rmx1RbNQKELLY
z_4_@Sm(Q=e)o=gr#=X7OzaMq$Ta~=H@XWgV=%T4pr|PEPul;^kto!IQ>;HY%#JgM3
zW`X|k=dKlGjL_=0`Q-6_|NlDkygM(Z$Jf0)HC21>mrLH?_keB@H8V4NxAX6wSN-<?
zUV!GH>!hWn`9Gm-Fl1ohN4v3^VRXqoIH^I1VY}J^;yoBSS|h_kV)P^~L`X1<p2P(Y
zjM0<0;6Z`q%qf(;Y9NK9DF+k^U_6>~z`+0_MpF(b6u_9gi?l|w6*%xf1ku^*!2TP%
ze`{!SGu1zcFY(*cvX-sriR;IT2|O21OeopPq$+TQFDq)%)P@29bEDvF%Zx)8H~ARG
z2N;M53Yp#yFv)Q=?-uVAwe50L+Oq3G^sx>rE5^^i7r*{9?P&V7TXWLee%73O$p5}}
z-r@3n?bUmY%lCapUW@0Eguc+gp%rbZ83ThS5A04$kk3GPg#qX~KoARt6*@7riL#+D
z`cW}N*S6pgTF-%@K?Orwh{OWa4kp8dBN*Dam_fIn!kh!5Ct+v{NW}215Qa7_4Bw6h
z(r6%|CBV^?gpnjhv)gEy1S)os@Myt}kt9ZIx6vj5QVszzN83s0Nn*4yiO~ifGA(YC
z>aAP1{(M)yfA+fA-OFNkms!5qaQIXH|8M#7FYdg0^{PkGSZ%IVsn_psZ;P)4x<Bny
zpZ8;eFlzJ4cPgWmgYoy?{2Jx(*wWB_-?pxQ`fBxhztGUoHa^)|N4v$%E8=2fV?msq
z#n03J{P?)@&!^L$U#(uhtp5MM$lYbR%1cpC`I{xgT+)#C=Hqes^KZA`pLbesx6bs~
zvdD8bpU>#T>@c{yyZk(>c+7<dJIn7?rccv}oD`k6Q&m{q?@VO++^Ozzl`6a6?aJQw
z|L=SAOW_O${@=|_WzRTN66|As6qVq;>~DBi<gzasarg_S(xWAp4gO*(HN0!$V-Gcz
znc=?&+Y5%XH}va1c87$9rha*G@$2@jd3UWAyY-%$r0V@C{{Pqb*5{xD2ybSu-&=Hu
zQ~k<)(C)1{MW-}(zTfxz)Aap+o;si9J7C`>KTQ<FUC5T9xR6YL@G|^SmR!JWlB^xR
z&gc9*+spfEf4|Lpe|>%Y-@mT&Djs#p6rE7CzH@JV{Qf<Ezuk`9oOagUOb1j7!tsSC
zU<0Jh^L(D4n_IqPZ}IbUD_5^R-Nq~ZZ(Z?ZlL|e!QV?T9v5^CN#<8rdtV_E}U(4p@
zUtZ?>_iz3Aou#Fvyz{^p%!8DH@tZlTPVq4uxW7L4_O{CJcgxFn{GD5VZ{_~~?=827
zt`6g!_xqm3-<#?4|3)h_zuEHdfAOPcPpQv8KOR*nmU{U<YWkD>`hV9UQG58*OLz05
zQk!QlskB`ONdlKQEc;)xW_Hpp&1JLO-u^j%d{<^faaGLAWi#@+UM@@Y{r@upl3I9g
z|D4}ndU?aMFFP(lO`G-a^G1-W8F^CMKHJN`UY2<FW#Lk&S*CxVCqvSdiSGN<l8H_X
z|H9V3diCnnDL%#n_tP&daJ;!8(HS(~`8F?pOGY3YpUjNk@Aumum#cpBd*1EM>F2+^
zxoOOA^Wi|*_WLE5eI;$HO6FC)S}9ZUpz(e6yE&G{MZaDy|DU`MWh0}V$>#L)=Q5Yi
z4J+eem?anv3gus4UQTwGuQkcv_cIN2LTvr-OG~{kuL@oL<>lq&2aD@J&%Xbr04%mH
zcK4SzH#dK{bFi5`{o9+HH_PwWO797>0>=ZCc)DWc%9FpozBaD-@L<zoh6`tQFj+Ym
zfBW&c|M`Z)e5d{EK24re{cfk{q+7RceR+4+y87MD^t#`-@2h#nRlQsq5+1(Xy<hHT
z>GjyjD&=<y-TiF8Ub$2Ge6HokBf^taK=<%feS0%g(YY<<+#JiNHGxoDA(TTV&jrR=
zJJ;7d)!zC2UUl&~%jZkn`{ia@7N^yH-+e#z;v!eeM;*$ORMO`Zx}}|+HTCQ3>*@1r
zzj;o|xxG!-U9K_(v`uhM`Mt`QH#R0O^P4+MJg!3V^mP66|9-!Ze>NR?j+udB%7RsI
z7#RNCzf<*k?amK}xQ(m7z4`O=eEqqD?DBJdetv$v|NP`7p{v7grcRIDW}QDhw(O)c
zzwMOI=k4vU#}xa568HM}{by#Gp8g>NaX*xd(g??>JUus^{$Ga@l?)6Fx{Vm)GvHyJ
z1ve|6&n@4ScX!vCsI6MBudO|8{eDkynF`c=hKy;TTL90@HrEGjT)i1MYmRR8wv?-@
zLP1IHX5g$P^8bGvul#m1o%{X&zwhhkgSfpjI2JrzxpL*n4-XF)|9-oDx-2V0SrjbA
zGBE7f|LWB%pP5Fgpjf-MCUWxsf1mb(d|&_nZ}BP3<xl1mpF1g6{U$K!(x)p|t~?3f
z|0@(!cI4dHplE7pnt6L$?yi!Tlk94LJ?W1BlXPoqc6iyDOINR6y;=@Ri<=&sNJekZ
zJ6n9-cKhM|bLDKSQm)6A>srTUf=-NG6SK3ZJ<jgyO8?aLd%tN}$4w55j-K6L^F%rI
zct#NDFxH$qJ2w8i@B94R+{?>+XKzZr*b`g-_v=ifRIh7mB7@7OsAZm=Wm@^`<?`Z3
zo$AwMS<ATc_kImqwR-jCrQXvwEoL|ykei$P?A+Yh>GNyNWUb52c&g8xQv3aGdHZ8A
z-KZ&`s)yhHPr>8%95u7tTT`CTueWQLDe|}($gtpO^wzA<yd4kQa&B$WWM=0(bAA86
zuQ_*jnTp3%BtAPcbMmWKuVkuTEc|(pzixsvzwMScJC@$uQ(0`5e{au9UzWYFwE%a&
zPriEfYUPK6?7^|IbNAK$UY37<pQ_pt%bS~0y+JEl-t7DRF4aA==-S%o=^!%;4lv%U
ze!zTlM`1GP^x-crE-K6aec^t(FL)QYwyj?sw)WC8-`ORvujzuaq4H9#_}JLkTU#<G
z&;R#jxukVj&dtJEQ*@)ZEy=yT?dM7Vx=H!9ucK3sXBL&+Or3sao~`xacK-VNzw`J1
z{l+72XA`|WFZW4`?{QEFr<|O$=hG=|Nt=p-zwc**^4IP+mx|Uc{_*X0{{OSjw;Z`&
zDs7$@<JKn=`D5?pE>Ufx<YPTPbFH>coNOu^y)EbDv$L}|-_F~;bk(X=Z!CO|<?Vhu
zO*44elQYKWb*#A<-b{%)r(Mp#kdbz6ef)e-s+r`i=Q&+3w&)<M_>)zu*PY@uzcXR=
zx?Ni0F$IpGl;y3z*97FP&2@i&ZBjPh^?Ln&ySuwePj5&(Y?OIv3CK5}pPxVf=H_PO
z%u7q=6ddAwd2Ma<y4~+~ZCY%$Yi;!Qv}b2#N?Mg<Se3t<vuf3<U-EY4@9tPSxAB}j
zYknV;gQm!C6#->7$@DoB`DCq@gs+d2v?xgEvwpXON5;ZnZ`IdR$L;@pta&Vb{{-lw
z)v_yYTXSx1`ttt1eeCYCvlkXR8)scv@#pmZKi+P=Qd1S3+m>WsU-$En_`V5Cy{Au;
z-Fh+i_BLHm0X}`-m!)s^e!sVJ)he&s+j4_LL#OWje$V>2e0@#c-mllhem*NKEiKjC
z_v6u*S68*)-rnxtFK1hH!I6Ebd%s-f{e87|KTrBU`+fg^-M>H2?WfCb6#?CHdaPG^
z`eA;1o4dQq{g?aAy|lObyG-4WhnBC`Z2ojYxqpi6Mo-XHyqnA3-rAIG5(#Ql`Puz^
zvMJfb)BgX@^Trt$7J%7*9`aw_Rr(sl2DS9Q-K%~NVi!L@2lC_TzKbfLy!Z0v=JcC}
zvzD;S*BB%p>(R7!TYO_rW$~|XZ)XcCyFGEY{}p)7{{NqvN5b<@xQfS4`TsNWfwXzv
znM1AI-d<6lc+uWl_0=mhH1yk@;`241XWu{bdj0-=hYLSHKc7F5d0YJdU)N`v<wm{R
z^?Kc&pU-B$uRgOW^>oyk$FFQb)rgw^yg9-Cwx;+0JTw1%`~JUgwf(cr^W(a!?c(-U
zmAduG%mf7mC`6x~nfZC&@w;WWb9Fy4e-YD<n<HtQ_GI7hciMkk-#<M)J^jv(!rnP+
zVzzGGI@2^e?BCb;|EA$Fg{}{Ob9Ia9W=*^w{P$yj{h20K?oCNYyACCT>X<(d*zGfp
zgglMhnicx%>+9(&gO@*>SN-l}hoCYjG5XB0Ff>j(b0V=_cG~&+f1e|_<wUaaNK6P_
z9X3^V=f&K+yG)ah_xZN-$!_|7uX=g;`+GkR%m14&RXaRw|KD$?GndbuR`~eX)6Mh$
z=78GSZ$I2BNdJCHd;ODB+Uw7N0<-@A_xknwYkz%t2~J*iwZBrnytt_Q$@W|;xA-&f
z_+LSG|9_rO|McYK&(rb$CT+i82g>UHyUX5QTIk&VX8-?xGtKkkZU#!<Ju}m|_`^YV
zP&In;#6;!Im7kyO`SofwsGhyF*uB5znelwj<$iOcp8Vbq3ifsTe!cRUXH&WR`ccqf
z+<kVxUVM3b+dO@4Y1qHd_Ww5@nc{o6_WRxG%zPFKpxmk0E;A|h^fc9<+3ldrTl{|S
z_i1xB$bjl<yYD;Ci~h6xbVB*^_Wb*AwqB2Wd3Sd?D7rT(n|FQJ`}g5i_WG%^OHZy`
zwd$1J?>Ccg-MY1Dv5EI=v)rtS_xtyQeE0I!*6cppZ#Q~mEI0l8-D>~$rT@*`?RTTD
z{6Bqrd;a{pWw+ll|NnX8xLsJ;lb|~Vhk1GH4E`3Mx1FAOd6{X_qGgF+UtI;Yympnp
zpLcC-^z!86eVKQ6m43The!oZ7`da%>^`Fn{|2?<)_v3NuafXJu)B5)^GBl{Yx_$p&
z*|waUla|k`(%M_~Rm&#t>Z(vsS$WR(`<*+r-|zO$*brlWuOj)J-S0O%(q=l3kM(-*
zulu|0H{&1a{5=zwdQX4$>-GBcKR!PGJh8t<WwCp|o?+qRpO@$Vn{u$3{ki?W$M&1<
z*ZodC(7^aLT(R!`t0VpP|0+PmO7{A_W}vFds^mpL*&DadPbT|=`d6UVIH+6k<@NRa
z_PS|$v9or+-)H^#+1b;J`|W1=*S-o)J^t?k=tvIBXETy7t&QFuQ}gj?>)ty>r*&W6
z-(N3R^<p89gu#M0H+mm^y&ivlf}-=LnxCJ3J^b+7cG<J@^XF%;+o`ty&r|)+AN%X~
zyt&bv^!L|SNrME3xQd6Zpd#>a8}IFfvr|t`dwR)R|E%uzJCoeyYroX4XWD7JYURq4
z;roAGwfS&>8PrhVv-|Pj%iG)KyYoPexR;lgr@y$caOdMb>r2~mZ*NLA@8Xp<t9g)o
zzv6K(zagjf=F->Kw%#bb|3B^awp`tB&K*B~uZ`Vp#x16!VeK~g$>E?b+mA<tXBsBE
zE%TorS2l(JuIludNmo~gKTo&+9qDKBuqEft4nzB27yFA&s!o4$QholJJ3EV`&t&ga
z>bLzC0V)IE?0&z`^79$v&zHRQQ*Uj_-1+<6?&9xv%b$a?;7vjA;OOYtkNd3kxW)C>
z$S-}n@wgnQZ);ri<iy*)+IKsjN1b`B<q2xZfbz@9HeTsZ{{O%DSH51m-Kg}{l{sa%
zGH06Q-YV-~eRj6__7%?`Z_U2`?1D4@+1>B=%?358BR3|wf)3ueQ}MVL91tsmm;XxM
zo_qV+B0Gci+qRh<ZsR@O#LE3jK3LYO<b-H=%*6Hee_!90-JN!Jmd|XnwMSztvp+vO
z3(B^i&KRG+Qf{1hsHNun?)zt#cuu~wDs=U)<mg-M%dT9#ntEo2;m()KX1~h64Qkrm
zExrEq#p3>Z?`}-h4u5utTmMW8r?8ZD+Tz(JnL*!fWv{pSb|V>dNjNC&fhzC@X1)`f
z&)Y@+H@>hn`}(r@{dGSd^4HIZ&fmNB$(7#M$E5Sme0h1f_?Tq+lIrj8c0QYxZIpDR
z<IS$u>p%^XeSe<nFJHDy&Hnez^F^n1w?FAn?#nO?537CHDqi$rVf(YG;c=dmVya#)
z-T7|U>rdCB^HU!k>9qXupm}rd?QLh~SQ>x7UtbUE4J?h`o~ODzPsV$i&Pl`LGLvn;
z-B6abE<3ZtbMmKGtJgofTYmrSsj1qZ-{#j_o0^*Ld_J$b=#r=U(~ZaFPA9g@hLyc>
z`*^{bKlRCpiJ)?)>ifI7k(<+&E?cG+y*<zO_O{&Ow_C3-TeeJXbK2QcKR!O*49bot
zCMc#J&lAz#_ag~Z>`#xY(mWYIe{uefhi!YlUW@*D@B6;#%=|V6APYYplLi%cX-B(6
zUtU`3eRAdL!vBB2KR+Vuf97Gk{Je*U+n+z`)?c@Oee&@>P&t;j@8>ffX|pwZCaBJ|
zudh?{nK1!WZl}+yOso3xVxkJTijXu;TT=V`8`vWIe;@m2+SOM1Sw5Wt>tlKQ{d+ju
zAkhg_4$Z0gbn@pBb-Tc_IciVeY(9T(OXg*xsxL3V?abqvcOM<?{yh8spJo5{%U3*T
z-1Fm6x3$dn%*)F_O(}M{iiG52*+%R3e!B%KD8O;|<EZ|#C6oPD?O*TQ&L?S>6H)iE
zJO0U=&FA$DQy=eq(8Rs%_q^RFKow=t(^GC9S8VqF`E)w-@-p9>hEi8;zu%dB+27vQ
z)YKHzFk|DDn)2=K?dNCB@1MEsZ$J0t<>k+>MdzQrv$MGP&&T7_Ww)DvdRZW4-g-M#
zK-J~(KH1ZKEDYA7plPm*MPj;9Q#>cDnOfNSPm0@H_4H2hc~D}P(u}-Z@N{bUGwt}F
zUU|FUZu`FXf3p1V2#`sR&1_Fs$N$X&-K!yH?C}3w`M$}Zrar&zmjE_?xtNMOO|0BS
zuU0O9w&(M?(`U`^-|65y{dMm98ui#+B`1~pZ8qK2fBdgJ`B=}%)akL)7@66gfE2E;
z`?}iA@8%Csl<lkio%Zlh>-*nrXC2vPr+{qy^ZESwKzG@xoWg1;Cnu?@s^r!@pIaUm
zwmxnybVMNMVIipP`f~aFd7$p4aoU-TBP~xqCTbo98QCshXA!*I?`(&l^1bhu-)3iL
z7k@r${v6aHYvB|&N<B42Xp-5!yt}(<7nt9ey#F854|dzKbi=woKlp3je0qA?{)mc+
zdbha#zXQj&ZP8Zv`{%j+{{zSEem<EjpCmL(Sbo}}`&sw)RDz<|tw&;_%FWvEca4jm
zoslWM5-4e$<^vkK`1$$y_80M&=Gs&i@malCpcA=C<?XGl-ji(pez|P<^U37mFBjd@
z-`&}1`EJK!FTcn>?e%+%xW)C(9O)E(ZGYgwr_=i9UtC<gIq7IuO!eEXy6;RsR_pD0
zv1rf7W73g33KBt$qqDQkpLc1mJF#?n+$>Px-N-I?VqW#T$g(p*p!QVm?QLg2Jw5&U
zxS(<RxiddLKK?IX{asG1_}72_KR@S9nq;PG8J3j0h{N;BlqBzsW}It#=S<sL6mjiR
z-JGIV&2y6G7R9XjeCuw%b6}LHR{N=EGx#Dry;@ad@9nq$GwXf&ww=q%_TQgdJ>&Z0
zUAxxJt-QbP_0IR%_s(vf`Fr2}7k77?FIu!HrQ6fw?5@(+0-~a=JBy#6iVaRa-gors
z>hO(qf2-~Z?p(+ld_ze|X+!dHz8)!4ud=*r>*M+T{ry|o+LFG#xw%KVsPN?_)taAA
zr)S*Uq}s53{@VW^4)aSGr}f-noAdVe_Tx7;CKtZApcogp^X9f(X}jNVjBh?;y>{)|
zhwtByw{Qw?$hm2BbBA5+F9mCB>FRH9F3w<mVR}DWO-=34p+iiMkM$lt)XIHvnXmMp
zf4|>v`o7Y8y57S2|NkPk<w%<4-#cTx>6A|FE|Iy`<;RY8i(gz3sC;IoG5f=Z4_{ne
zEglpcoH}1sKWYm{?5>i7t3p?sJkvX(9k!-n^Je37^X>T^1vXTD%{nvJTAZ1U$DyQT
zOHNEcfWWSjmrY+^U(Y_n^yO%`_~KQoxHvgEH*DB&poLS|p#ERYmb|-CnVFfJ{3PV%
zK_Q_NyDKEw?B>tSN4v!jA3e&tapOh}9i1uB4SWoHtG{16v3og_gO3kSNlD3s88bTC
zc%@It&bBJmiiwRa{P`($P0UWA;AK9Id-vLgt%+DD$bCUrSoq?W%-|b0ZY;>Zzc1tV
zw%oOOIvh=I|7;g7UE0dVE485Z_csZ<8jH_&eCAqB4R*R}RsC(vn&%u%4bANQj~*Os
z<~qJD`#Rt2Yiom3ZMJSKeC*aEVaPPwEY~S9F>&qVva&LZ@^>=rDK&q7-~S(0_2<k?
zV-8ME$E+-^GiT2V%E+u)l=5e;O{I{!|GX)-_qJwFzoW))+ST1%`0GpNmlqeEr+(Z~
z_2q>i6EpM0O{v~F_xH)x{{FVsRL#sxOjymw!NGwc@9wUp8>Iy-EiD)B*(1X(u6G0!
zi7Nt?Ti=KJ&$D?rWrBbcN9Fd5OeIbniY)?8SEjfqIhK}|?mZS39-e*2<;t8nbE^D*
z{rd5^|Kn->{eKR3UOC<=tZq>KEoW)>dBy{mFALwV`OF)(K5p%zlvj$Hnw;9<>r(XW
z)+c6Vb*<m`i>vtgxzIqPeU~m>+EDlRmsL6Uwab?e?<jn1kbI0sRQ2)u>+$tR-`w0h
zRnLySp^=$A>Drpei0yfEkLfrpKO1y|PtK+za&ubZr6rzc46UrJW|(9O$=Osi%(X7h
zI>Yp(jaT~6ty@ycZapiCb8>RlxaBZ?x}PN`arI8`I=xv}7)5iR90<Dq`TM?tva)5p
zvJy;8OfP07t%ziZlAl#_J*2_RJMh`!e!ErQZ!B80sNSHns`A4F#$9D^qh9~KxY+&h
zojWpic6J42Wo{uMBJCxw9{&3J`p3K7@1N9tzj5P+f~BS8zJ2>XeEmB0u5HNWH~06;
zH#RnI+CTlxn>P=hK5aePEv~Gh!ctjTX;JXtK>RDG_uVsQNchaP63xrYV_;xrX4Z+?
z!l9?9Ct;Q&F=y`F!e?hBBO)RS{8m+o>&G3rvNHJTyEEo#XCy2vEDqehE$!#$XHoiU
zikt7LwHx#A+kwh}yob-#=hrl`a*HLrytK69&kw_I@9+1s@k$l=oMg|PacEoV>o6Wk
zBbMrKZzkHB*ZryRnP($e{QTU}#qRwkMGsG0Uhe-?ZT)o}m;C$tYS(TI3k%z19h*Jr
z%o(4Z=l@rIf5*$fwST^(MS+5te%zW(IeX?>m-9_l^KEKwW@bouc&N3Yq~ypP%i<?y
zo-gn2Hb2%Q*?f7q|L3k%MVgwLGfcCmtRHs@O%w$>>jVL{AuV>7d3H#R13to>aU
z7a02PSg-U9`}%!v-si~6%b%HNyZc)DNh>QW4i1hBEAF2)G&G!HQK<Cm%S+}5Z`Jtw
z`ub+rR&R?@pW?NYgNNtJi~aVOFJIo6c2?@y$7g3}XFsVHV|a6SxA^C0XIF3iAye^N
zw!p!GVVZt?-&F1JQ*!#TyQVk?UA?`daPgb{$w^5feHX8=zKE~?yY<cf$l2x@mzciH
zG)_-C)WRv?D){W#vl|-{nQLllo*d(7VyLaHm5`Du@;Vvs=f{_JcGgjwyo`($f%D}z
zySTb4s;IDddU_fd8y}vg8*NbbCZhM(nMb#_W_NUSFnsuStFyQFX#W1cYUazH&3bil
zG5evzhb@;pNq&88?TR&Pj@;awo|u`rvY==7Z0U3JY`LYSrE_j?TYK%8^{hql`|G5>
z#>y(T2rSCl!Z23=oIy>m?ys+36Sr6D@9*#K)AeF!Jic`4Qp#hK&Ye3g>wdpA?~yiN
zcW&dxjT;Tj&BGnFz6Qj_#l6?x#KX%A3Z;6BiB%V`UOl=w{roG_Z7Wu+ILCVPJ-4#5
za!P9I)$E+Kv}JC-F1q^q(|0fKH*#}x)6m!d-!8n8|CUbc+n=AGf317Jal?iSD|Rn0
zdwq>}ecawdb1aKr$wYr{U8R<JcbDm|(${UEAU(Iyd%E7yL#^DQ6TE7-WMB8&#^5<K
z`}(?vr>1Iac`T9p^7ZS*rQYJ8p2fM1$NS}vPgHgfnc!t>l6i^c?yl0qpo&;#clLF?
zn=0bI0fB*yWp8gCJbHBLxs5AVuG~@fb{1FAO7>eit-8j>!fT_pHud)U&Q0FDY16B}
z+pq6lSNZu_#g7jQ4<*<B{^pvKqr=7{!Jw|L&ced7!eVY!#ph?ehxV`M<>4uKbw#sB
z%9QKz@qYKZI=iUtd1n<B?Qh<^$z@&{y&-||*7p4V!pFxBUcS6J?(c`%&p$pUx0Zh_
zD=&ACiIK6fwY|99U*5&dt;pkecw*whL)KEIudZ-T*NbghzFhszojV^c``Z_K91jl*
z69aV|U;jMXE&lj0zx|OGPGL~-Fu(raOlPZo8HYu-_4M>a&E|OZ;zh#oKG`214)cFp
zU;mf;=g*%%9=6L{s6IJ-<Aww)E9<7?w{G3axWCVqhleMtS65Fj?8lyED<cDPQc^-*
z&sexnQA<lJM7DGGojWl*U4?RQZ)0U>ojtSc<t5i-vr^W3b>F|-zi&BX#teprL+2;o
z-j=)Cus)pe!0Pbz7j_gT-+Vml{UVXC^QP%WKRVhiu66oYbY7m`t*zPW)iK4srSI<S
zycS_?ZT;rfR`1Y@SNs;c^#(*mowAuXb!zJ}-`T4SCjP4U`Dy8;qu+o2{0U;c**I~c
z;Fc|0LIitv|EjycveU@OsKPx!n~jZa)4k~8?TN1rZZ*xlCDJc%pC-4z?(eQ+wQN7`
zD=8}r3JEnmd6F_?_Uz=(&(2Di=gDl@YMP&U{?E_PhV}ny81kRb2jz2R_r51{ylm%K
zm-Fr0x9`l+=cc!|X16Okw<%azMJ0<bkhiIrP|o7Sq4;F)vP#{l;M_Bz{K&1X*$-d6
z>Uwu~_u-2d1;2g!25KuwndNkR`c!07_eUapU5sN=lG2&8XHB22TWPw?e}3PB1qvad
zp$}KD-{;gXXZu9WXn);bsql3%2bcNIE_iW4G3UmH#^k80uP!g=2eruJ<KwqvTx_y@
z_wn&@4u1aj$&)8@UH<s}<?{JSS679;xU`hp?&lNXXFKBS|B5CiCVu$*IXKa(&aF?T
zb8GhXMWL(1B<$<<9I{T@SM`<a_V)bayGmc1q_Gz>6qJ;>R8&~B@yT)p2M0gfq3%B~
z;cy%8rrmckm~QE`o;`Pt&${f*ffa#^7c5_XT;}_$tJ*FuE(@Z!=V|#IpWfWeyzl?N
z>M7HvImO4vzl;bJF@5KEZEw|Ar<$6Yy~naHE#qTI$j;`@&CSiZw`b?Mji;ySUS7fa
z;@h`xCr+PUeLd-B_4jv~SC~rJ+1c;xtrp)~^>tNoPD#lYE}@nD(b3T_Uc9)Heev(6
z)YB$ej8?hR4yEPh@+K!guDUz7;O3^(hz$viTtOeNZ%+6B^XK#VGrftRvZAGhrJ|xj
z!Nerw=*ugI+vV#zyr=73jk?3mz$;~Ppplt9Atj~d!Gi}?xdk8W49(1rU0&`lDhJxg
z3Tl@9`1$kT)vKcO>;LWSy8Q9#uF~vhF5l11wSIi4mHWeo4-MVj+->~w>mHTVL`Fm?
z*xJTE+&E1)TFK5%?%ut75+)e}Y<w~+9+lKcN=ly8o$)t+v3tMU<z>ExH9rczyuBU%
zc%9}ggVwc$kB=2~ul*NYP+;KW>-+KP^!P_NH>XP&rF3*%{+OJc+&pE9$j!%UzOxMK
z^_MSQs=3Gb*Y9<{v(0wY|KIm!V`C$ul9G~$-llUWPX_+_`RVsE&&g^<<y)^@yVf>s
z+O$Kyou^Knno`&HYhUKIHInmeDwV3&EMDAP_xIOHu|@y4|M^qXdrM#ks6_knV&a>P
z>(=QV>z7|&&={4Mm$%oPzfQj9!$EcpJ-unR>mo(gEM6R(of8>3^H|P?wH>o(OMiQF
zb8*4q^?UZ%xVX3^Tv*^JGwI{=XV2P7Utc?T@+2oS8_xvmvR_{^*F<mUtNs0Ls_pb?
z)7ZGVxkZ<&ymAw^j;oD~jJ#U4ZqFW><9)Kum6et@wzi^qixzRR@yqqBjozO0=t$?*
zchBa|n9(6?U8bO+(GhG_mnAk&T~+nqp+in($BTVqD%N>KM$SBxw|M2ddwaVR54T;-
zUeny%>{c7@3Tkj(U9`;$L_2lN%DTLaHz+uGW8z^p8S65h+2;Avb{ji2v+-WoS)8sD
zw@1R!(ecNFW`2uhp?g6s%hc4=h&>e>bHq>c+x>9Z=CJ>n-=<%`e*O5q|9|iLeZRWW
zW2Q#!F4J8Sq-po-g>ucWm&;#VT-<)>EO*`Cui-CVyvVpScfz4VhbGLM$0si@za{Ic
z*TbJXtG;R#6&EMw=l5^eU~q3@Xwu6|OHZ6UdGO22%ZAn8a!TIZ*m$jSXYFsZdwVLI
z6`k8a?XEq_tIy0b&AzZbKfdI}1x8SDl>O?*$Hx~gUAnZwwRTG+*X{lP|K?XzR2(>U
zimS1)@yzwJ_x4s#oIihkU_4vh&!^KjY~6Zvwt4=mm<Bl!k(TpzzkOU!UTF@|I{NeT
z^N$}MI?tFnQ&ToOH<vd)K3-Jy@%e)X8F!bxJp|HX`qN>unSMb*!GTv-R|m$##5`Y;
z;(PnX!Gi}G)6dOutgEY=EBu$2hsPw#Xhw50^S3uQov%+}+7ih%ySbT}Pu{L))heyt
zoy=jiJkn-7@iiY=A3b{X;L)Q+1wQS3vIQR>xmHwFJv!Dat>t&(egh-(hPuC1YvT9I
zwY9Zv?c;80I6K??@Rchf-qUn0uIMd$^X5&#rzf6g=30k8{K&}6_TbIU&7hpt)Z838
zr%yjUJzd7Kh~@Nj{qTxAhYm4`>%|;sU}P2$6kHg%e)hiF-;X{#JRGq#YwDr<$J^T4
zI{NyKZAd&^@aIQiua&v!b&+i4nT^csN?KZ6&FuVXapmu|ZyB_nJ$8&O{oI^`XJ#6U
z%E{Z;+4S`EeE9i%{^LhSyS4m|pI_oRx!~`wuU5xxYk!GMoH%iYQEC@g&`NQ3cJ`gU
zETttS26cZbT9f~Op8x;A!Gn&W7k6ylv}w|9oufBy%&27lA#I+QafQj<+S)p1Urpq<
z8wU<F{QOx^RJ7^P(cJf|<!q}I3=IRnMa0L?-&q(J6C;z8n;R<HYpt!Vy>q|nY_r@`
zdy+q&oo#OVYSypKsi&tMym(R2w))$V4T*;pIG7eKT2%1vj%Ci>U80LLjDBDEo%i@y
z?~B{p_1XAjIJmjFZytJd=8Vss{q^!`X=$5!|HkjH>s_-(=h<&5MV1*hl}19s!l|>(
zLPJ6hoIJ^?si`U8DtPSJv5wx}t1G^*mhzsa<5*H+l9QA3;Ne3?M}ZBQm(|upZe|M%
z41956A@j4dvyWRZJ2l6yR!UJ(aYxNhBOM)`4Y{|?dL)h8#OD3?EG;$V;^MlnCerw3
z@z0+>Z|tkJK6U!^!`H97*TwEG@>vme^ytxyTU#>s9+Q%mUc6+<6M4TS|K{1%c3rs=
zGG)pXjW?%eZR^xjY!UcW?<!!L8O8(ZU~(wF->_<xmWYVRiFZs1Nl8wV_cGel|C5<G
zaiWK>@6pG{`%|AUPdz<t!{*J08yJ~Q@(S%3Y-)Z8cu&(g`0?@az=(*5*E=?DG_0wu
zHO#+fGh_DbVviHyrKP5zu43}>K1Eek)_!?=x5`RODYG1n>bF0B{!Bd5At+ToH+D~j
zpnJbuYFuz#UEPbz%lY5W&?^7`uePP7<-zm$_0x7AcHwn)b_R8rK0iO-zI3T-d&{3a
z6(60pMS4|L?K*Te=+B=&CPka4tPWqVWMLt(apT4nt5!{#{XxG=NkxeB&fU8kYkn5p
zxP80W$LqvyP+wTxZ_a@&nU|la$!Qe*|5tlwcRByxUtfa*t@afa7Z<+1ru*g9RqkGC
z^L530)O2NPe|}P(XH&^kT>Lqz{N{y{>3Xq;*6;t<wSND<UFVMeym|BHj_U7vHnz5*
zQ~K85-kuMx=)Qh!oj7sgrHyB`)1_c*0gfI$s-dHEWrj7QtE+3`{e86&TeC!?wqz_U
z$%%@RS{Jj^NqDO0g(de7n-&!nftoNC)z#N6UzXk9SL@;JeRx&q>X0dY>*rdRgZe`r
zK0YD4G~OQTmHzPM%aO;&`vXHmmmX^Q<Kpg~{O!$6P)BLb+_^I!$L*`(tgo+MvUI88
z`*(l#dHVUeWn^ePJ2R8n-QE4!j#aC)eCFH9W@cs<ajV=<w=R2gKs>&t@yU~vrS;kW
z|NVXsGJUeTzsa*%R#jg#_WgLo{pZtZ{WHA53=cj&KE8=J*yQP*oI5)NjnmFJR8?77
zmAyG3BQ7n?EiW&>r{-r+@;TnXcRxQrulV=J^46Bj#U(M0j*Q##?sAovmw$P8H`?{(
zk6YVvrPsyoZqtq4rXd?16vSj~Y}_MnAD3)qU|avs=G~p0&7H#PTC(52ybP}S^YQo$
zgT$s|cN9%*ZDlPjElcms{q^$latZr78@E0gkXJ>QJ_gN->?nIHRqR;T`~3X;!)MO$
zfClY$mA(#{;`jH?jzZ?k%l+MRa@O2A)>!-d+tKg$>-n>@v-@8DsQURy)hzc`%Ze2m
zp!|K{_SwBQwzh_qpHd_wBntdaoPT+FIjDCVv%8E}RaKSCeD0Mid=-z6@#fsw5m=V@
zZ_f&U0hT*Ei`#>(>TYe%?*~;H+baLx+gmLtA<-dgUA7?m`nnI_zqhYltJ^1Qeauo*
zUR6~!Vp9rdpPX$MJHH$QL)6x+)`y4NlOG;x<uYGc6Yr@a#L>iHZEf8nXS*xzet71k
z-mokd7M2I!-rn9(^pvY%`}@e)T_uiwetZlL;o;)x=jH_dvV8d4MQLKf{e86(mPILZ
zlfS>e-+ytjd-j{(S7w{%e>f^0|KPZM{gmo{A=kjXd40>~$%ESD_1$6%guxwJrxVrh
z4mPuI6%)#Sw5ZtWpMJ-pjyG@KL|qTLy)9R9qDRH?$9-nrfopc`khs1+e*M>78@Fy<
zTO242DNCOG4U3KK71xggxrbNUEX3*?C=LAjvhr9?mE(!~fuW(Tj~*qxc>UTrJUsm6
zjYp4?Y$`vwEPki+J3Ql3o96nsy-sd!Y*E|uc!h<9mnLuCym{i(sY?x|=LvrDU%h6H
zi>D{2lzCoEy0}uym9>i&F`b`hdzf9mhQZd>_Fmx*Z7r=sd#k?(#K!iPy}fmH=SIzo
zF~|F44}W-g_~OpubdRM$IrsKRD!cc!XmtH}Iz9fvLTC0LKYoCQPWCKb6;o4VV`F2J
zkdVMoU0v<s=62}nRngScR8UcDRr-nr)ZMzfdwO}u)XUeeyH`}~$YDOW(7FB5zrVjX
z9o?Lmm>97+jkl<{xbj#Cx2UM-igoL*-Prd%{P`q~rUetZQ_r3~YnXV5MJHkd1H*>Y
z(_%g|jaUs04L5Av+S=aE?&ISlAS!y)a%Gl>iVzDM+oJUI^Gf@C{rryI+gok=sg#+a
z_}Q6*udc2Jb-KR1yv#mt-aJqZ;N$BH8jltc6HEI2?d^+ud#&HEXc2HaVciLf(NBB^
z=H~4oT2ud)yt^~ATxIK~`u}x1cI~=W+0N<o@6FfO*Gv6euDZ;eIn!k3T!BSG&z?Oi
zC@gH;yxF)^hV|R~`~2eK;xlH>{MhGoPw`6rjTMgtoI)CZ`QBaec*6c>D?aH`8K(}d
zfa5ErOJzQl2OLja+~>>@s9IfJZIW?;fs>O{Lrbe^<x0&(ix)q9_pWcw92pBMtE8u=
zrb^gWnY>@2b$xq&{FA3oLB+GEsA$piXNOw3L2VR1IU5dtfB$=dq34bqVfp;*?BO0s
z<ABgmR$*b`ny**GLF3#E3BSL+oncj~b?Ve93-za~w`>t%Wo6B{xTy7*p2Pm)=jY=8
zna|o0Id9%PIZ)o-n0%axVb9*ZA3r_yK63OZBg3J?hc}kI40`hX`RAUMMq3IU|8C8_
zE%x`<*Ta3X)&UU_9cgE0oxHc&C9q}nYVBQRZ$VSlANoKI<UNzORI)3yfV;6*&R)JO
z%*n}VQSg9)#j#=HM8P?8<~(@xh-qa=mz-@?#+kVuB9f+AA}o##GiT1c<5ZiSoqg}(
zj>%q23rb5{H*YqcGiOdhLc#&-Nl}I-CM|pS?tNqW_{ozNHQ!ku`i{o7^T}S=l<K|n
z^-AyQdV7*rvYMNl-!#3tyFCBJ>(`(AmY8L17TFfK*zIJTxvX{B6Iu7QS4!r{*Z-Ml
z)yH(D@WzVA8v^$yF77+*CfnXCc56f6@xUH%>}?1H#T8f>9E)bJEV=^0(P;L{A_uDT
zc%Yt*jf}egyp(&gS5KejZf55{_T=Q`&^bP~M~)l;jgOo-b;>C)Q1D+3zp<mhziUn>
z%kQ3@Z7wJ!#igsOn~}YLZd80=Amf9#i?)F}3EE+6E}UR}0qU+Va_vsY$mm$KNQq&B
zZb3;=(V-=tlMV9k+4ROV<fW&#zrDTv@a4<G`~Q66o@Za*=h)14vM)U~bz$Y_XEMT{
zM5U#>A3R8i*;&N8NaN9)o0|*D%iSFv8UOtGV~~DMrlPX)W8X@lSvzL@d2e81GDTNU
zUtb?IQ1tBFTy5)n8xozTOq=$pYkAT3yt|KNAI_aPeLB0lyE{X^xe-G{`1&};ircwu
z{PKNEy{BISkHtU9Ut|p}B0up}{`#W%=<#DgdHMd97M3N;mMz+~ORB1>3N&+cZl3LF
zYbEi>$jFZFZf7Sarbmw-Pn<ZB(NW;SmdxOrELJN+xT>qG?*)dwd)#mDmXxIA<?X$2
z=~C9{=xC3nK{uBe1P2G-6WkfKEk{yFNC?#A-&66CNvM-$u66mex$-MRx~Azyf9hLV
z^!xk!>9PK%@fi|QQio2S^el_3`u0Zi_ovv&J9h3=w6v5=O-;RU?ONO1xpUvlDk>`j
z^`<M`pFHc<-{;`u#PsgYPUp!1|Cczo^PM<zX3f`oPaZvL%DcPk@6)-f@4H_q6oICh
zU%b+#GVmm!;r_R+7nWY&sU&f6-(ndgRgko`IOh7gSWu?lntff%#xDDs4rq8tQ&UsR
z@7VoWrrDrbiy1R!EJ!~;&%nqi$Rh9ky}ep~$L4o-a!%8URJuLG!QY>Mwt4=s8HULW
z4AI;3j$V(i*Nr~2%yX7WX46#da8QR=z*Ue}+U&@?ySojGo_H`gxVW&Sotd#Pu-hp+
zW>*PkTwGkm$49I#fkz%3Z2tK9y#49E@>f?lV|SMwZDeM*SoTC&O^ppS$+g^X?t_O9
z8?UYoKmE>)he1wG&cMLnz{cd`7V4_6jvPPEuBoYcV^b=(-+a5?_xu0LX=-Y2^6l97
z^O-bg1Z7A0d%5RJT<*@8JzH5rgX4bPZ(W81H*QFP%B?dqjTsrV!`2+wlzRHZpP$9^
z3^^5BCX|cmI;evSkSDTVe|$`yV^b-Vn3xD^QnENscx$xg<)_b|Q-v4!&9zdUtrHd*
zdD2=+JTx>EG~Sxy6yfB=#Kpy>z`<nq=Y#W(9Xk}1l$y$Y)~#B-dg82ETIGFNWmj{r
zuah-0GO|#A^8DuJ^i7|I<mLOPOc4nQ3v=@K=hu(l_e8e8`_w5fP)DjPPA_Ih!=gn>
z98C><vet)=9%Y?vp8rgCvh=K$RW~N9`wNJRt6S?|UmxGD(RJbab@%u8_C9>{sHy(%
z>-as%t60G$#*@I~fqlPvi>?%ALDIv~6_2m*f0cf^;_(THz|$3vueiy&TSAH&`BxUF
z0*_C02Me4EJifBmiZA-{v0hL+%V&;7;KPp{9UNz7nR+XWD{RfY%oY|FW>Ndgq@<*z
z;&`C8pP%20dwX}kIk#eO^>??$ZoQz1+Eb^zKpo_hlht?B{x*BQWYzV>?)+a~U+32j
zU&q35<JK+E{8T%?JR8H0U%!-8RatM|ylInMG<o*y?jJuYKm*=#a&iJJj0^!GAuYML
zw=D#X`tM{6oNrgF(4_<lqxAFh4qmwulE?UKlBzdo^7qM;Cm(oMDVcUB{qLHU?Kk<(
zzFKMd`agzpwpA<)px*79??t7hraHR17x&lKzqzroIo)Sb+n+yw0wN<dZ?mW<C@?%f
zH}`NGuQaILvNCx2p<~C`E?&GiXR?qJhvIv+s0Kgqh|CFVC1qu2vp`ilJGq-TZ)V)t
zVJIUjo4WhK?j1Wm^qssrS=~S7xrUw|-~Rvqtha30a$&JMf6ShWiRCt1L1Xr{zrQ6O
z?GiQ7eB+;`mOaP5UT$~!`(>X$|Nr~(xcsK<S7&A#pE!4}ZQZ(cZtp&<^GHoq{r2vz
z_w^}ECY)12lMNPSZzT5SImj;Gx8m`YUaP(&a9cpbUA7%u9L(9i;{Fx+(mA_8^$WOs
zcnYd{Kvm3VvC=ue7WW04gJT_1RLuFGn3K~ZX`GgDu!)tcUq5b-ME12cj)jFAyC#3U
zz9LY0P3&&5$!fljWL@93w6-eR*vLpqN@m>H0J;*r(ck{BNL5vp01M;NrAu$@EMESm
z@5QW?e}8`7*jsJBY4hfVYuEP1?k-FG^W)=&O`Dh)?(8gP_nxkIwETYUaZAlW^<F8{
zL#skp8>F5R5fKwx6uCLAi2K6!{QG??gO@K_v!<sw=;{Oym9J9an;RJ!dTZtD|Nb()
zbm`KCC7!}J-%CDtd;jTj|M_nHa<(5Hw#yg!tgu?7k#u&Jse!rq@ePTG8TQ!n|NZ@a
zz3H_>hnU>^WCBZFwhBs1cRRQ9CI0>O737JcqM`@y-s#<ba_G(-Q0?mS{M_81Y^p5+
zPWJ*~b4wG-9ZpZvoj8Af|1#g%hi=}K3|c7?v{K~m?(+5D+poOee0O*GX|+$FK5Va)
z>7>~op1gR$VQXu9&v2)vw)Wwr-qTZ_YiMe6u8-S0>29Et*3_ggFD~v$E((l_>gpEP
zKXuNxsK_X8e_byqyWhMSSyp%E?Ac29(3Q8h=b!dfsrm4Lk%x!p!g7E4n<|Iq*;Z%0
zIrrn~)2AL@UX$j|_nxlz@agI48Mn8sePe2zcgNzM;m!q~D^8`Rrk<QTzxw;TlkYUt
zrh3hsyzpN7mBJ~I%zt#neNgM850*MkEUp8kiBo7PCa}+{&*qgyDNNI2sHWN5x0~nP
z-`Bfki;0AU#0gn#P0hx+b7j}8StB4Rc~Vo+J})ot1!zX^(4h+VO7$bhk3U{MzpiQ8
zG%?WVjk&q`y@@+C^!42f3k_$PW~;rf-Ch3v*v91J3zjZzb!=u!Jk-KDC-~FUDN|Y|
ztNVi*^$hp)SY#~<6so?yI%+9t@8;$<!@k}w?cAJ|1&qI%Sh+!CGf$pAE%aL@_4Mh}
z(!S1~9v2S}j-cS+#KgqLH*a!8Rg_=7d2w;EgkchkUhFOwc6N4#39<gyu3ZC-n=<T)
zT~YV*Q>u(r2}fOBosIJ9si4AmZ<T0NRMdv8TU`&g@m9Jkfzm`IB26^7C^fn$HO`(r
z`;LofY;5eki&vUllp3c^6Kms>?Rt56`Qr5R^DbPw_Dt4W*TTvQRK#7qdUeCbjT2{E
zWMpNXvX(2iva%9z6)Y<&+r(KMv{FP(O>NKO!q8&h%IfOH@%!s0crAT#Ypb@e3d@5x
zZ+cdTuV1ui5!1D6*NU!(tPWdSar|+Y+QLmgfB#mtvy-c=tjxHyr1Q<69Xoa`sQ&&=
z>hC;PaA^*18Gxc2*75`w7_UHWP;m6a+Y_M3?XmK^3o9%j?a{s>PfyQ+(o)yg*VY;)
zALF?>R}VD1oOjpi$+KrlW@ci0tG_>+6Y@3h&JIR>ef^f!*2Etl9`1Q8@aY_=mza>C
z0O~#jilolwojP@@qX5f~-@hNX%hxqbn<n;r$tv@T4+&46J$rO&s`gf~1>&Nj3yYth
zD=02L{O|AYO82LFT3TF+ii#dyUQIJ+N;Wk&8|K}yFv+;kP;R0Zx3{V__x3hLGcz&J
z7~F<L<~MKO28M*RFthU=IDMLX+O%nVl2^5?U#|~Z7xM0o<;~(Qvl51Tc}AC)cnZtd
z*UfPcapF*H+4DSu(F)ROe&6utPt8u*dzUX=TCjF)@4LIZPpc_eSXv%DaiXI<MDJLi
zY<EiwOG;YWp#ujT%Gia(#l<ZwEHb|EO*5T*sHV2|<4N`T4q8(e<=)=5CwV0=Gc)s)
zY11AZ=C_{`>#e7!mvMca?E8$E$mr<D=jK{pxO};J@#4jA_E=b1Eec%hw&yV@>Um|Y
zMC|PBCU`B)xV((_eMDBH+QLm&=SbVz+k=)UfL80=*uCkGWT_0SRIh_X6sY?L?l|lR
z_5YA#6%z68hTxoxqPWz$`kRiL@2r+Nb7VN07#_U6>!_=%yRq_fT17=gf!_)D@9*vg
z1_U&?_sbo;a6up~Ep4mVF|MYD)#2-lyiVL-?A|XRF5dp<PYsW(l}PTbEsmw7rd{3L
zi5VFyCUSRXhlGSEn3{_I{P`0!MR$3bZ>9UAyo-xmBlc7nHZ?UFWM9*Xh=^cd0IgfO
zx;i}ha2s#Ljsit7y_gf0D_<>Lx)d}Qb9Yy1^Zxzz%Y0|IO_(6?;?*l98ygu_RaFl^
zzqYAUMc=Qu^QZFR&+_}V?HiMiXT3R8%y8oL>E_j|wT+C8FK)|?PDxLH4C$1#YjlA|
zcR^D$rrFm%^sN#CIXNIe0Mrwy?%T>>YhogDzy81NzaNkJ<pQrV<;FR1D7O45Mx>7g
z;`(t99v$uO=<h$iG5L7G_jj=#DncP4As_mVg~r9nJ$m$L!h{J8KYmpF`S<%hsL8)~
zukDf`O($pPO81bRPoAXQY}wG#!XhFnx-fKgSW$W4hK(B^%1)mB>Q&Z~B}-1sUA)|X
z{vy|Iu}z;Jzj?!BZEbxoFm&C51rBApM~@#@R#jzfQUFa{Zu<P_@#DkR%T8VW^RBnQ
z|9C66IH)~4WA^ORvBBWJ=Vb0#EvL$Ud`P@m>FMw9-pt0E^4{0<`O{{8y9cttx&g-n
zd#wC&L4C{n8t$^7!~rfSz^z2HR~B2rT~bg_;wY><2(|~Q2DKX7d#(D4z}=Eyd(-RT
zX=!Q<p!Hra?(N;3<G4$$sH|+=_5bxXHG8-&tq>0sG0eWE0~(*4I(4c5i{rKz8<#9$
zNlQxurGm6GGY(p7iO)96J=Da?9S{=2!mz10I3R#QT3UKd#73sZ#>P3ptKxQ-y#-Z&
zZ*Fh*fB3PXfgxs3g<xc4q?X?@xk-~J8>XI`5;Z&O#?70Fx3}eP*uMSwl%Dk`PI$Dm
zw18G3J$v?SQ|t3vw{GoOTxgzkMPrUtDVL$4At-zK`1(E-i#k8gRvOfbsH(DhzGT(K
z4T;V<x3~Ge`~Ld%_4S|;ogNuWA<!(t^YXX1T2D?^fBg0Jb(=*+?z6=~gAV_75Y0k0
zYisF`A3uV+n>95yMn*;q49AWg)6md(FvqXfruLV}|DWgUH)LJa0yTr06c(&n)m5(Z
zF7MtR&Dj$`ISG`{PMqk7v;P0|++6F9&d!5vywadV#?jPp>Xg^LjXSh;b&pO|cHfY6
zlnXT3%wY0wmXNF9{{R1W-$}W<XOGQ{88aT7oUFd*aiRO<08wo{y<@H1;wh7#t&7{+
zb?THCXmOURYHPX8I#7S0ROaZ4$B=F$C@Fv%2NEDLQ1cNY1!_{FNIkwH4^r_M(%J+`
zas1rBvFNE63p;!AxjB|EuCJH3`}ZSxr)z)mu^vazx*5H5_cy2WAM2Clwzs#hsHjMI
zbfmNBdD@K)iJ%ebMT-_$sE6)t<CRXjyQ_4DP35LTk3k*H>+$t#H*z~=KY8**L0Osk
z>eZ{D^&Oxt*1d^4ENXvk$$7Z5wUt%ZCj7vWBP^Gf`5ta!<rca3vikHi-5JK|d|qB&
z7V4qA$;rt&5gQi7&7KdM%2iZU+|=u2!VAsVn^$ZEHSAjiKJneyl-ix6<e!(P=Mva5
zbEf2yAkDOMb2wLqbotG-`q+2!YBM|k6E&N=JB!&FK#flxDHD#Ml~anH{+&8~8dO9s
z_n)t1Z!hoa>MGzWc=YJeJ&Oy!|N08*_<DYm^78U>%FNVM5#roc_V$#uocYX|GdE>x
z>FM#^ym?c=Rq*UA)8@^ajo(+?2@MN-^z`&}P)8Xw)N<)kP{$&V$xjZ<Yst#UIAJMS
z?>oz+aqU{&uC6Z7sMwu5F;AX6dGPD&>phDL9c7p2T`7F!2FlImIpD?~q_jWxe?c86
z_d=vVBT7@CBMMgM{x9gmlq&oD%r_-9^<>@oKQ~`oTx_{S>6Mm}64PS${$rn>o(9h}
zRZQ25E%@~%lkemYZf@?wpv88F+xZu7*dQRR?l;9cFF(Kk!-oRDmp`)Z?lRSj*>NDI
zq3+=!R?uYf(Um`{zrGR$E%snxVM%y%V`IkcZMwI%<({?{3-9ae1C8?D+Lqhh(ZSIp
zY0MTC6}2aM<=pV~aSL6$#m+o7wRI1Uh>liPQ(G3tec}9EYxeByY|$k_{>%O6AN%t1
za$<V=@(;CpYJY#L`0+upJq0ud`@0b_20Ozjm21t~wW*VXmjr2^Idi7sc#yQ1nAnfU
z{q_o7O1HLTGOrBjS{c0DNo(q%W5?RcZPqC%E2mC2S{Jjk$vpqw0>@^y4coW72LuQ#
z3DTT1XHLcOCu#5Q?Cj|7KD;&i`iEy{rC+>y1sXJ-VOMLlBuEpqPLG+H`JQ3ux%>Cy
z%i382MG`YJIn&eAL92R$R*Hm$h3!!;5|)+K-Mwtm<jEg@ea+6u%v@Og{oRj8-TDes
zy-dpv3Hv&w?ymj4?adufYx?2gb^%vG&;qXzt)u4mYZh;u?7tG4C;6nmN+Z|)B#to}
z8w)csGJ5#=rRfC;vp6b?Er{P!A;<tKes>-(T`9TVQ_ikt#h3rl@$vHK=i7%TDt(<e
zabn|w1q#m!larHMyZ@Rvf|eKRMzev2hyQ-PzG1@#1_sbf&g*My4>vNigVraX(+pi7
zxY%t+)mN=QfB#mx2TGqjd6EG%>cPU!u54iu@v_2E;KP%X!l5p~+OpPVM_ReXvvNxU
zAKU-`+3%Kn&LroC!I@d6+{^vvw@sfeUL2E>qT)B#s&&H#1JPx{`dca)L6fWJg<PuC
zL0vfxMVGg>)!%rI9XqxsdBs}K$!aInY_8TUbiOyqL&d<rz+t{!ZOZc#2M;pxN}D~A
z_0^S-mOedq_B`9_MUKsEdy)&UZ_N(BX*tnrsnkww^KKWV#(n$jKwbXl$1h$Ktg5Qo
zv$$~i(xt4~+1Wd<^Z7c}dMiz2U|6$eP0I6QH*ZQ#n>KCE<d2ZS6>u#}Npl>uyfG<B
z$;sJSajI8hO3IRgIck5_P4iF@U||FeGhVzn(Kb!cRS;agc(rO?ZQi-l60`snv`~D*
z27$A)Or1+gOzzyh%g7+C?sw$p=jVmb&&i(i3|;TqEjGg}S8Ctych;@X)1IA~`QzpC
z`4c8jK5VYRK6UC;4i1h34-dC1axj&YlrS*l-`mru(FN*JeS3G8J2&_2?)U}k*Xx&*
zmV$1Q{?xZf?9bo7Q~&)7eR80Y`G0`a*R93R{e0$F2(Aua-?o0ezK)KLfUs~gpRARF
ziVBN$`MV<ro7oL>ZW!DP3|+Kmj|?9lA86!gncv*5^Y;H`%*@O(E-YZw($bnRZ(iTu
z-`|rTAM4$)X_He>kWfi!Y31=}i>klB1FaXCXIm|@FZ}D<+n_<Zj{g4VbEbfna+|}K
za^ExbpKs?{S7!$r30e`Te6O%$mba&;<Mnm1sgs{|?3ty1k#ptx)6?}ASATzZ;nF40
z(8mRpkZq5T_aDA_Q}XOA)5o%|YXgrf*0X{}TFsxlUjP}@2lbxrPuSlD?pQ&mU=F*1
zi{%sXuAs`4@2B;O#~RC*FK>Up@3)`wd#gX`hK7a=4RwEiF)}P#y!iE3>*Z;C)Mgqc
zv(^3i=&quscId(daGd%0@Z7m`r{LKcNl@Jb8rGbq7kkQj)u~=dW47n#=euWRX=!O|
zKNb6WcULJlA0HnF56_Wfz0#HLPt`0fCDr}s9cgCgXV`Q1!J*r?rTO^y=1l%r{QqAq
zkBo%?XaaV6d>yB^w|A@b(g1svdb9d}H7#vzPD&FOY}zDbWo5Nu#R>)n(2N<kxZaaF
z0b4=S@%8ofbL{KmzR9gyySDe#DKCcn|MMnzEw!llpb)h!=cKV#I4mPBVtoM~U~So>
z>^H}vacA-KN7vRyGc;^YKY!@%U0GIERtbXy1~Hw8hJ(%Q#eOHRcM7WuNK1GB`BTHf
z&b~N!xgV%T)QjEKB4=B*AoKFFJ<3JlQBhpBwzj{7p8JCm#jIIffBw{1SXo`le)|9P
z>C?_NH8!6<e}4G*ar3pc(V#67OP4O)RwNP#TMGahw%gnHq3n2~tgP%Tg>UL6oKydZ
zf-6u^J({%`)Ug7wL>Biszv}+w`xiX5Hs=<&K@93-9bNHw!mmZJ`g1v?)CE<t^JdPJ
zOglfXH}mo`@MN8;s%k-Dp<`K@*^(elC1vH0ACJpFetLTPj*^!`pyhr$c3AYjIo&U3
z3tB(EWy_Wipf!<~m-%w=@VI~$aLC*71P2Gl?5mk+R-ja*BE-q!7_jSRp904w*DddN
zOPl8{D1LtKtDJrDGoLk)o1e-1EV*Z7WK{6wMIdNU3fgx1^XJcnjmhr!F75!WyzUfM
zFZlf}7qq~Hjg9Tajg87|yizK=Pj6qg_$)VvV#|bjzS>`I(BaMpS5^jp`1sNB@v&ae
z(vm;l?Sj<Q)C^2bkDi-rZK?L;_0!YSL7nyo2b)2Q)c*W<+<)TqX=VmcZ_U6!;Pv(O
z&*w~<KV^ytDCzb}o3|}os0dn<&EVkZ$OsxO*|Ec7AEV{%Et$em+j2PF-Q9WQY$P%>
zGa2s9n=hstm2iHZ?Hu7xAKz}j5882~?A8NXJW}xdoGinEZgKq!yGpZjZfs~QcB)$!
zzaO+_O+re_DL!6)<Hn5)_x7c^^++_fw6L7x{ApSEh$SZ{=fWaa?vj_6SUWpA8Sc%K
zuCA{B^Xv8cIl`YlAD6FJ(9qzRYhCWPIqj@~ygdJdw>xKA7OMpX2V1H?X$E(Ez^y0L
z$(Jnn2pXif4H=3BP1bCM%;dp(>)?Xo?P>k}NA}hJ4hRiBYTb3~<A)Cu_J)aA*8c;|
zdWX#L0IjN5GBgytU-w%VG<Y2w8w(mHK6>;hsDJ$E@nh4XkCqIeO+Ml4<63v`wyyi}
zkiBD3$KBoKk8f;D{_y#;b5hcxWBPXWUtS27y}Q%d$}OJs@KEcGt=ZzBY4PKavTkk3
z1eNv6{O9ZaesBLDv`eSlXKG=2`SD(9^H(zJT}sFLWLHnDH{VnDSL*h*+`~t^#V;;&
zW(T$NkN3%fOnP>9_VSC}=NS*2J<Gc~eEqSLlhr}<aKX#{63@;u-SXqlex1loEZg($
zI(c|-fW}VF+x_MNEvPDd%%*DxnsNCz9nrOJaP1ZY_4hkFJGtx|%8QDeyu7&DQ(h@r
zSV(w!dV&VM<?L!S%s;MlY-aoL`SamUVRZ|&C+dcVg0;WC9PE`gH>mmXA!_oWd3Lp3
zy3yMTd`?`SXIm{GBEnK$UY>Jz*Vb!4CweXY@$tC4rP>o^9UY#;#6(aNO-Wh#={fJo
zYQ7I%zwS;x-dE^z!oR4<NJdt+@a-+rA3uIvsXA*@^~EE3y(Xwj{rg*P$?I#pzrVe8
zULCgf!<(DNH~mhlsi}4J_8vXfD{Z+Pnn+Nmd%-or(G~ZvfQRTo=>psk0F9`EhT$bj
zLBsVZN#`kOZDvSl=)&yl>p;sH`eZDd=GXmNd97cqtFQ0a<Kz7^kAMF3NkCY5@gbL2
zuKxb~pP!v|&dSpA^7al43v2uGr36%5gBmA~3$HG6<$iN-uk_KQM=QR(5R|j4>3H-g
z>CcD5{23P)vA(Z}`TIKlf78;Xs%kzn8dSZfC7hh33R=$tYKB*Se)h5NIB5UfhO)P}
ztm;i#*R9jLbNBAVdGpT61P2B-E_7~BIzP{LhCyNz*X5P$v9YnB{R?s2UpWJUf|``w
z`xI<!WC8;N_dH&~duvaFfD^~h^b6prT+oOr<I9&XL5&Co2Z5HT<Fn24`~Li?2|XSp
z4O&?n5FpUTBgvGT`!?$M+BIt?OrE^>S3;J8g@uHC?H9qkdwV)TdsuuOz!m7pcR7nY
z4;?!6;iUTf2Ol0DmM}{3So`?fw{Kqi8LHxQZ*SvW?ACke)Ku+@i{1O9j_)pc*|fX-
zeUZnp_<{n1Tif&dZ*R{}{`%_b)^#iY{r&y;(o*j^mp-~q4!F7R@3&}^ygL%*@9rFI
zWM<FWo5#i{qp^GPv}FqsldYij7?8=<!;l_WDXfnL9hrkfxCW#-08SmCDH)LBor214
z3aYBC=K1%InBT8y7F2dSaQ?jiyYw3y689t*Eq+nE$1N>QP0BoP%^{N~vC14wQQLAl
zudR)C_V(^Bmw9*S@L@qIDK33|{UgVYDe3F;S5{Vb^!B!H-)`>Y><lWA?-_<J3ta4G
zQSw6Iy+qc_?f2`N=gpJ*_4Rf8{rdlVuYC+(A9wKfZE5@ee~h1<nc2KHdV7(_$@u5z
z=7QGP-ZQ*%Y@)KeLBRtD5fPCSw)H<hrA9<X9=v~F-Z<?{!}jgwF|o0MVPVHKS5~cD
zvEsnx<^B`r&yRoI4jLY*_kZiZn-em;n&s~A&%ZuyZ<5^kbLZM7PMpXkymET_`FRVS
z+xgBsUZk;T&z_jp&MWRkMMl%~<ImObZq2(ZRasdnGihaePY(|ZE309@w6yf%4I2Vl
zJFgsWX6FaZTR;1FtQWM%(gmb7C`f3UZgiVluaxGWPs@B~n|ZyL`C#Ym@9!QFA;B=K
z<yZRi^Yf4Isr-ClPi1lI{$L#)oewWAD)XKE0h#0g*Wr{z<&7H=_XMw;y0^D_WBL2I
zn~yJC2zYaA>*{Me9z9B0vSi7D%a?<ve!OyOZS?jH+1K?_Qd1YMSh3>TGrlH;j5o56
zyuG|Ys}7ewcM}#rlXq{A<h^_MK+B_^%riGNZC$-un~hhh#do%u=AAFEYrp*ZnjI1v
z`mt}}G#y>t!he4%ckJAG@a|n%LqkK*ZVHA4D^_sC#l?B}`5o&L)t>Tg{&&#cb3q9S
z4t{=q3v27oeTVP<`};dED2Pc|Sa|1iW+tY9fPjYl{eQ*2efwrn`AMbh{k`4|8w}3O
zx1S#zwGXti8|0rG8<}_R+`0AM@~jK*H9(8j-Y<l=@0fpmd)vLY`un5T>-VoK)v>pi
z7Zeoy@afZ|2|l(FQBjY6eSLlA@$++Yosaj)hR*P))!23VSpDg<XIuB}+t+nz#e6m2
zSsHV96u-WvyCvhIQ)}my=9McoK?AbSK2Dh;GGpe<l?D@kt;kj{_uaQFLr5z+G<52v
z>#mNDj8Y~U3l6!wg4EF9>;+$ILq_2n6B}FU9-w`GzWwyOzF`6^B4T2T7A<nh>rvpi
zaQ*u6A0HoY%($q;r}^{t?s9!l-Nwc%b>P$~uSD@Q-L&fauI}#1FD@(uHCjPix|VoO
zj!G8E&05O2Y4c{o+*>BkJ~lG5YrQ$|VjLL}@nHM?y2-ju{e69IpP!utO-+M_2L%NM
zK_&3}88L5fZe~|gQv)qg+PW1qd%bY^a&>bz0Tvmnl8#`ft6sjoN1xBH*ZUrml%!;2
zWMq(eNu{N&jfnx&vf8u9M#i=(Bw2ic|6D6k(6*TdM&=J!!{amGq(^~<M(kY=Su;TL
z=aM|{>3T>1{{DV(b-4bU8ylIM6cntiq`Jj)o7S$?UA1bJ$+vC?1_|Rdo^AQ}`zEXV
zpPDDk!WbGF%E8Nf6to_fQ&_FQ=S2VF#marM*2_NJSRKB8L-qH(9Xoccu$cM_)Wiqv
z`M9U}@Y>qwj*gB43mls*R34u`ew;meTaKfjpWoVK&;<Ot*xe7FKVSYUA?v`wgN(=f
z<-;r1tXacj|K|hqlAx7c!7JNmd9LUx<5@Se<=4mK^2Hv<;<xAB6_Au%`5_`SRFqH7
zrXy}|)k=%0RST$5J}<93b^0`D2RUfjEod-Twtco{@UjQj)<*9reJuuBEb2Sk?4;cF
zKX>+23QyOMKQ>J_+NA7qw`;f9!szXJpkb(>;9x;%>D3?Hg=_zQy>4J=c<}1#@Q;s<
za@*AW*l_K9Gdq99@h69l9ASC+^5vPwFJHdg`Yz_rzROq6a=bcy=Z?(t^Yhy$P80+c
z*r09b#>T?!e6p8*9DU9J8aAFZNodBbS&KGo5CCn`s;Q}2EAI=MtuA|e>!hu?s3@zW
zfI-m{kDbric_bRnobd@g7Od^wCv$LyVKQ`6g7{=L-=H7PpmzU$PZelaO?X}We!X40
zc6Bu=ocQapG|14_c5b=Nx>c)IxzyL!2MVxk3|$?zNP%O~(xpo?5)u@+niTq^OuNcm
z^7P{NXuNvyqGNu|r_PE82N(kdSPK9C`ub>H?Cv9ebFDh7s;ZK_ytv-axbx@Zarvax
zVQXECjg1X8G(4tws64u{G5P3$0}g@y{{CAwY!LYT`E%v*ke!PbDP25v%<a#EW`58>
zLAOw+%a?E8#A0J(T{~TrZr!}u30_At88kx|=<e<=W0cZS@#8}x$nM9-dLP}}TkRSh
z9UT}R9=@mSt<?J&F?aS<2Ai0eh*W=hp|~z$qtg@*m861#4Lb@RI$gYSCB($cOl<R}
zO%=zVJUY@TyvRjKu(_$}NJ|S#pa9Fq3k#i-a&p$(*k4~C7#$tm)7$%0cCs{h?G2W)
z$Ly8)De!~}WIPtNK>%B~0c{k%+E(|s>f(tLpr8O*nw*s65-4(Xx&Qnw-`QrO<!^2r
zv{Vc<-?eMkqh-FcD~<<v^GchE96o%w@_2xE@Nz%Vty{Jn*_wU5D>XHB)ARWKb-L@K
zxBFeWc1>)#|NL`?3$r+z6hNUB7Z>;S*T-+)p2<e0dU<<4t$TN8r}DPk+hI9ZR!scy
z`MmvgtGKABQ`Sa-%xj~z3LQRl=*hg-_xJB#v3RlazN)WY?|#m;F7NvF>({ED<zYO$
zyhnATw|(ey1Wl-JX9*N>z1RH!TJ3)g4+v=J>EQ_p4_{pS`<v8m=B-K-Cr-4e`m*BA
zPf5EPi#>byR=Pia_2%Yg(AJGjn>Ia}mw$Vk?za5<eC6fkekZRu$HmD#J2$uc@$vr0
zN4v!tKpT%in-R3b*Il`h{pRZG@Q9s7OW%N|Lf+om3R+}rn0`(MyeRX8Z%T@an*Y3>
z-{0ReSM2WIuF+*+Z0zjf!eV1%16q*v{eJ!ND=UKq#l_XX@7cWB*ew5E&$+qQ#a_qm
zzq`8|H02Fi^tVXkR9SugogIc|d3QPj7rPbuosb8O{eTu~CW1!_5Iw$Af%`!#Cz8O^
zW$-2;bkYnu$pUU?fR}{6y|tD5@$vrl{rl~0Y-|kj?pV0EyPvK*&m(UqbM)v@i{fWI
z&zJm(*-^j<I_qF>osNzUs3m4$X<6uZ%zu5{UeH=ORqtsZ`WBVt<m7-h_$XUg%qSPx
z`uWjO?uyFFhmVeSgXWrN&Xi<$@bGZEhPHO|<jKOI)pN&srHlPmNeOkboSkj{-~0c5
zNlD572})lTCwgSvmED)d*}rJ_F>dhO)6^8@SEnyu7Cw6PC}`9|MTqm$r%wr)nVjO{
z;x4YPCwu4G*W2;QTD5?h)Ly5<9UK@|ty)#^-~i*jKv1#rT?n?wu0?=Xp-X99++Hp7
zhbIpnWEARbDL2`w*roL8(<jinD>2<D2T;3KWzjLv8oD`ibjp1#t*o4)qi2_!Y;~9%
zAX@$L5v!82a^d@Xwl{Zv{Pd}5;X=jt87+G@LuRx7go5Wj7E6@MIQ@GMS_x;x_j5H!
z4m2}j(emd$q^<WUJn(qnnPbP;WUWdLd<5^H0WUMwb%@`X#CquP;g2saDxdQVUB74%
z6C)#|Mb#G#m%x_BM#hHid))<CK-<E8e|vlR#PtiU+~Ni~Hw<KKt3+yleR(MBzV^?T
z%l@FwrC!VqhT`Jldxcm0N=r>aeYoJ|eh&{evoqYwd-dS$TV8v6``%ZULY*wXzr8(t
zVxn@Td!Tjk^K+p)F2u~daN$C|M(;0gFR!2-fnMw5_FAY1uf1RQoA=$jccAq(GBPrt
z@xYYS)Q3kpg+F}yG)emQ+Gz8VH#Y*4#S`pneh7dLX@D%}O~}hz_u>6Yw_d424|h-|
z{ha|@^^o=AxO_be!_D?jrv0y-<R1w;aVWaX4LlBN6rA|o_KO$9xaWSQ5TtE&NolE|
zoLnDhKS)f2oS<Oi%HZXXzP`RbXY#6hprtq^FN4m^Fl64GcGl_jwY7{4J9qAk*jr_K
zZCz~l&(F`5Ra9DvgRV;3R2YCpsJ_38EqQgt^Wh;=M}ZHg_4gNeoj8AHrt!zy`THM!
zdwUzyVmNc=jL5v%S67D@dwE=8)pbz+9}OCd=HUU=0*YNqU%q@{U`S0(6<}ff_wOHQ
zU${xu;$@&Ub{7}9g4WT^oGA$^JM{Pe3CcUOv-tUgmoGbQtG{Ku`KmtALxF?IB`_uL
zn*s-umbP~2oF33fu|2$ZdL`g&dlF<+edYDO9gs0~)|WpvZ{6DJq6DhLK?~gUVs~Bn
zna|?r5EV6x>(a;4kB?j#CcHfr`+0}ntWDkDKRrFI$kCKj4qB&m9jvaPU<22skH&?M
zTsXiR1)Y^9f@Vca|4BOvY$$ylCc5OY_Rs$t%b#B~y!&7Nczn4~<OBuL=m{=crbT&m
zntDu$NLneB(sXTK$i<^#O^ZTT9oe^a>D11MEKR4$i>`%)UJa^t$+_t<VXDgK-^%uf
zO^VaiUS6+Jd-m00`STffPFlV{H}mPqJLjLzv*Bd;@a4;uUAZSV|K5M9LTJ^V-R19@
z7*>U>TvU2{Li+dmsT&KwBtJd@LifQWg#Gx%v3-U;y~_RQXtA{PaRakH8wB!u7_usa
z6VzQ_<~Mg$G2<`LfjYIn%Z?m7)+HO#AZ3~bTC5{&mUE%9=D~qRi=rnSd3SasK00}%
zxVYH3qBO~Kl7O&q@}kZ&?A8}H9PgKZ{NP~otnZ@b<>gy)Z;SQy^(C<z8|pde?>chC
z1+-S@)~%>78ct{DSPIXt|7QuBF|PS^QoW$Gl$GJg(W8kE54A?@D$z_kGow+`IE`c8
zl`mg(*QjOut4lpGJ-#lpDYK)aBhEIa!Oz9T#U-T;G@!`v;lqaukT7~x_5B^M=OoaE
z!HCGn%slB$si(z+eblF|n|$btt=aj1jkkjK@jUS?-W9qwN|dXW>H7M3_f8?zfUQ}f
zi}xk;cXu0KY<cv-RJDJ-dSz?vJ)30CeqL#Jd$T^9ee$Ot|K11+xqZu?d^A<<?_DhY
z`xq!NvB^M!8Cixa{lkNUpq&rr=2$l0xf8RN^@X@zjKk)%vj!C(5_BRrxqMlnmY$y8
z?%FMucx6SPRsZ^!okGHDJ{wM~K0Mhb`M$T#%dR8(v&{45Kw|)B&iL%vp>p`%Jvm25
z#~D_os}8*M>E^!Bt){5R7`iINF(qY5+GY{&(8X@NTXJp+Nt@?gskAXL5IEj1zx~8n
zhkw3n!<02OJEg@11O+F0ZZPWrfin}@+uN^+3r{OK)MvOY@9wJa+f=)IdRQ24+_;f(
zcUg`9d^^?;e@>rI->!T2?d|Pf?`=yF6cl8bw}08ZyJ`<!U0uyE&))2Op74gWvr-<D
zT7*=+GVZFG^(p4aROZN3zL5rz5O$8t-5cg@8w;OcppxXr6332BJdQw`b1aLWEr{Hl
zwjzAJ+^*8sY@U-gBpzm~`F^+j#<pB(t?+d{4<003Oy&ZuvsQNRJE7-bU-X0{CML$m
zMs%jNcWgvnPvz%liLb7#1RWr4kak7_bifuv!|Cbz$v;0m1yuwhT&!yT^K>eLE_ZZv
zI2>-{b?pz-`B*jSCunnB*xIO*a`{(RiT=O$^}mp?@XkU;K|#TpJnNyUaM`M`wO#-I
z{#I5{VCa=H6|(KS8M(jCw(9%4-b+ipyX9KDX14RoFY=jbwCK2j^>n>hr?<DZy7oIB
zJ+parhJYv=D1q^bvi^3HlWy;7>UC~C3d+6Ct_MM3uy9er<AB7Cg*?fR0|GaI0_;V-
zs-dA^@N&PS{`P-cu3QOWXlQO`zE}O;_RMT^eo?Iu0h@&qo72u7S`)e1pz2G8&kO^{
z%?HnXeSLjn#m6Mjx*g-RGaEWse-#!MGBmupx;p!=*^`@pI~f*4ZOsBr;(dE_Gx))b
zsI_jOMFj8eSa#nFQB_l8Gc+{x@btX6^Te(D_u~(QJZlYisP7ARFpqO`Vgg0NiWM5&
zHTTZUx0j!!^6;|1eXEKm=$M>?_a~}w&aeG8lXID}l2X;z0!AxAK|#TZGqbL(kpvAL
zcuZ=E+M1<kU?A}K_xJYQyLZ31c&5o|VZ+|NwxHNv8q|4iuJvJ1xe<{D+SCH7cK-bR
z`|!;hohq5l$@%&G_V)G~Q@u*w-U=;FmG)j9pz-0`?R@8zA)upZR)nma^kU)}x7XL!
z8YUcI0PP6#^YdGD+)&$wGc<00-Cu)*0}Lgvu5^a8{SY_ntAnIZveW9WB}-JEJbilb
z=1obiR;Mo(PEVgadGPo9{dTXVO)8$V&aas>M`p#<ERCsNYvT9cQ>yY<7~n8T1+-@I
z*fF=_+Y|2Gi4pcu59<_CT@au#VcN7dAyuyhE}cSb^3tA@Cd{3iyNL6w`^!s9Hzpip
z>X9<_dj3&VI}B7id3bvpe@uCFcTc78`~Cmz_~h+)9KMV0Q}x``aea#7w0#qPxE?%s
zaE5g`c%3Atu-bvES4AEEea`&&=qPA+CFsPEna1f|vR8N_ejQ`oWp|wSVKtwiVBp0<
zXoN|2cXm2vWN3hPh;@tWJ55qC$-gJl*w_d<hb?>kUbQNhL{O(-s#mLR^*7LAY)?;3
zb)IimyC6jC;;z!{i;p=&mwJgFIez@`ty@yERwWHVD_zddvklyo;(2lL%+`IizmvYd
zyL;l)DW{o6sTX#a=W9&$+LC)a>`R7|?<^C}hYufibayvTohrI#@7{$WTA*PN3k!=5
zIsX-1qS{KDnw+X$QyiB2%>~)Fx4Qhs&6}Naz83RZw9cP9$LBxau66Qc;Xi->3JM4`
zgsqM0lslaR&QIVnC?8CMvKN?<535$86)L=PeSuUkO+0?g(9g|{ZB^*%wv&_9KXXm5
z0&PmK{{HUh+1cid4C~gd0}b>^ndj+L7+nSx2`Zk44m2_=dQN(_O|hAc*XUqLlJ9IY
z-bpHn*VaS^Xo$?Z-F9Z4?QNFJGpB!hd;9R+yRxsZt-V}Xb7F$xj>^w!ixw^Nv6)%1
zZ{I#pJ)CxS7OTF#{uJ$Szvq9muC7Xbbn?vk%gg->9~@w;sH!?;=QmABU7fwLvGK;9
zN@Eqzrrus&2GH`efYnz)d-Xvx*m=KL^I|^aTo#Uwj$V7a&1Sc~prD{ApZEe{P#zT(
zPCqvX6y=8wA1?g;Eq97WAd{?hSxeALmwq|hg#3K{Di=l232C{v%~phH$ygLHR9055
z2wN+~#Ka^ZAka|t^;M_b#V1#?O!;Ii7^Zr)zP-I&+0;~Ysn=A{nKYn?+L-L#ePe6P
z{4ZZhK&|qCl_5XAUXPzRdv>>0=&Fo)=AiDg?IHvBKAA?ZrH8iV-kvaL4rt}&+SS`5
z9!<6Q^y!m;q$KB5uU1*>vIid@9|xT%vHSf#?xjJU-`?Ji{vs+|A+#!wU*7J>wYAX;
zgI0dHoxk64ZP?<fudf2MK#L|E?(Qme?awf~VX<ptAy?Al7svNq?C%X00F}ypc{wtV
zH-ORxSmGF(1Sq*6OB}Bd)ebw-BWVmOb}ufT(faxM`RFIl1tx07?5z@=YgO8`f4@Cw
zvB#>=)l3YaHTtQirzM`Arh8+5y?xfTHJTMcm$f4|si^tQIiVf;-`mZN?atl1hJ}w@
zKy9Q&#|@*^{pVfT8Q8Ua`SJ%R&#;^8Y0PP90qv$fzR2vhqLR|D_(x17N=iyfi;`Y!
zzh8H`=H<LelbV8-dM!*pKM&OScIj6O2?`PdW#J7Q3|!pZohPYWSsm_QtU5hC{#(Q(
z(BVAi=h;SuKd5-S^*ZQe5Ed4e1+Lv<i`+%@EG;D;K71IkGNhxgkB#BV%3$};dkRZS
zMQs*J?A*EY#`b*q5G~QNx3^k*dU&SjMvK+{`T|;PbZbkda+QnXrp=o-W?$D^5u)|x
z_I7^%c{Yx%T%s4&$J>K!$h^F4k-JEj`odRY^75b~Oj@2N2TQ`%0<^Y1ys|QQf(j?E
zl!-$^g2Jz_ui3@L#V;z);x+5b%bC-3!{XOQP%M=sKYnri*u~!7WSMWhHfDZ~IWm85
zSbPFU?U&@oFOD5E<db%nlU}X>E9vjvu=v$0XDbCgvmonA=<N7Xu2v>qX){nV-(UAv
z=Tq^E`oyQFrbg_kFw~3Rr&A@ed2{AvHPH0jjoszzUj)WkrKdk<dar%+=1mW8Z{~mx
zUVD~$Pj8z$S5`<!$j5qxWI<u!!6zpt8<xF^xVU)6TrN?qglA`F-qC37Io8YlZ}-mP
z=b&R5cJAD{$X!uMNo(2;hPj~T*a``6FRw!%9v<FU{M^rD(vf<VYR8-$oe(Wi&@|e4
z`~MCL10KA*ynNAdA+PJA7I*I4SrDT2@#pjT-E!x3K*MLB_kbp?RXm+mhpjF6@gecz
zV$P{EXLib3mnrDz@cjP%-rdiS4^(>HxDj!2G3V0Pr#$53<Uq?B3JNy7_}KE;bH%RM
z-DSSTOE;dLuJ61sV1e&!Gtk172M3#7`_s+9LCXs2gMfM;FOGro2e^yzt+x&uE1)cb
zh!qJ?rb3AoE~}a!25$Xwy`P?*PQI}rv7os4^3IKYOJf*~H8eOtE024n%}sO{hiF~g
zU7kNhGuZ7*#Zfl#btgA3ISx8y+4a^9B^{kNsy@m0($3B4jIaC23Mwk5PM!Lq@XV<b
z6O}=;#4fI`opMKYYX1Fv{^IIt@mE(@t5=C^28F$}_pdcdN=j9duppmt^4z&&=k5RV
zO!aE*=-^06PhVX0^b}~_te9SmMwQLx!l$Q1SA=M-2+;zaa1a(2CRQJGzWdSR$A(!~
zH0Ft@fhHzr7^QN_&li94^l9S%e}6$6u$7dQe(d;j`tI&>!?ZIJcIhP#JXd@Ijq!li
zPVFvx`zV>&tZySI85cg;m=6gsNE^7auQu5RIkm!C%=3~TOZ4|HmItM0cXN=6IW=6Z
zPM_0bxm~YjZFRM?Q}>(G;I;J7G~MV4GiGo^M@NGeRd_8Gs;jHpuyLcH?V`xXhfFJL
zay+Jk_JDzEpw(9;tV%Rig|1#!tXMT&FP6ne9dtvJLDCV9kTns4huit5-_=;^*v!VX
z%-FWosj*kuTuDKJf#Ji0gUlgoqeKM-1wmV#9=rsVO+WH~M7p}Te7PUdE!O}_&mBCV
zg+C!7BA{a8&5cITdg_A*8UOzJ+8ngf<@dL@-CIt-Tm9_b-f9kR?q;v0hvMu1vTlv)
zJ=QDzcy|6i$NhDGUHa3-{N`G*PW5X2@S)(&?sEUnM~xWE-`%-rQ~&SZ@B9^4vnr~p
zoIo4OeOEj_-k<H~2HJ@*cdqQ8zkhZA6;?hwGt+q1^($+mw+Ae8;RKCte2F;p(wcK>
z!;vE{Ik&cOYE9)*_n*hYu;=Tw=%(dD&ArJoW_^j^{>mqC{6He-<neuma^PNG9=OH$
z7gokR0Y^)+gfu8lAQ6`fn#Fw~cqXV@Oc%7a1+?<r$SCOZ%zeqn`7Erg9_{^p&)LC&
zp{AzBrQgeCeFJD0*}p#z+vT%lC##%HGG}IF(AU>zIAH((PqTA7pQuIN$$s7m|NqaQ
zIyH6U|Nlj7JQ59p%5I=l{&#kOg4(B#`$8uu$j?NSlx(@Ccjel(YcH;>6rSRxx~u#>
zpS891MP;t(vu1Uzjo$9GH0a@piOMI=o&_ycX=-X(5TX^hI!yPXGS~MvT+)e&iJ*f*
z7(iKnhH19guP-l~jZ#l>%nO(^Wr|47%}uOYQ@Pyx<y_<9<g%`<>3r}YL1U`dl{JyU
zUpk!T*w@QxP2~b*<Fm8P6+MM&YHC20{_1djaLX-l#f%veXR}{jTI$WvFikf)>C_ZW
z(Agi8Cr^IBdGvwjieI*Me<W^i%LS!|gU##{XV2y~H#hg0YbDy)*tjBg_qG>;zFob^
z5|Eexx7y(`VRL++As<8nHHvJGgQ@}0KnOhUK7p23Rk3Vd7NGIq^=t0<`1q9c^yKU7
zVmY|Eoij2t_Wl1?9kMcrb$i}jAzQV;jgzKKX)#Ve2O6+Far(4&!5wgyD9P2ur9<vu
z&f3V$#}@tH=j(d7m%F2*!$U>SK^;^p8wJbB$#wMhvQGG)`msmSSm)pAN8-8n_DE_?
z<pPz)Wo2e@)o)EfW6O<=jiBQhUVLo1T-w_E>+9>sr}g){fQD_u)@oI`BpMkTgKC8p
zAzGkmuZmAkIJH7nG#Dlyb66R2=<;Py;De^S5)%_SxVaDi{QP`j*lN((#yzsuVxTpu
zOTDJL^lMz{4!8RCxZi$3*y_OLezIrg*-CpY6<W7$-6D69HuZ(4sy{v9EPH>CcdA$G
z-s<m4+S=Uf_kNRV<CShZaKK?p&ds1N9ZnlSLr~yaw^kWm9)YUZZ@r1&>US5o#DX`d
zMUEUZ>;acs=HOwdx|}(Oc9*}G6A~5<+??h+MJv?ni$&V;YuCi~R()-nJ69Iu)%yQ+
zclK6?e~EB8dTg?~KWI32MTpkg*5~KNn(UH0xi8e#*1Gm5Y-{6_)v99AYTHrh=ve*z
zo$0TA)Ai%)IwuPV3hw=-vNdY0m@NyaWh*EevOO=Bg^dkVeC6fkEjn&!&DF~E?b|od
z$skP3%nx6`=FZN3w~>{>&dzR@c23CZFy6nvzqbdibou-1t80InnAdc@-ZN)>rszZp
z*;ao8H5S_WWD`<TRjW)Eig2+q9JqT|mXVP$Kx?X4sj7UfRoR;rJ1+%J)e1EUZ_2u|
zV&aR7Ex*5euJBqqNqynJ{Rf-blYf7E3tIm3=FOW6YopCUJ=%A7Za%VK4=#2f-4ZYf
zs#BkAEG$XBk2X>QsWCv!9|>@+AO|Iv7l2loc}`Y)2pXelIB~+`$B!SN%{Q`EB@P7z
z2KQ>e#~uvsD*f>xaYcw$&h2fy{Bkx8d-v{rX1lWZ`ME{MjXBxb*%ym{wypfc;y>SR
z>kRGFW_fpRy!d_W_;F=L#e+$5v&BJOG|)NCUtV4Y9qRn!*DuhPkre?8nVg)Q3jY7A
zT@$^1T|ocy)f#GQZ07m*SQvKf+O^27SE@-}sd!O<258nBw3>>c;mVbeEqQmPK+Ef9
znPxBhT>k3X+U!$;Cw(+UxI8AYIG=tv?{0f|hq{uImK8K-X|;X&^a-?L5;U4=W@fhN
zxZtDX^7Th{zu(sl9)mgh#=_EaVfp)e0a{Z*Rn&{ZGk(+cVg)25Iza2lQ%+7=blgz-
z{JJ%Xo#CGhm*m{s1ZpWv@lvg+soAmm19yecDx2)=>>odVIIIi-71)oTPn~$fB1fhc
z)Ce;F1R_BV%}+NhT95BLc^ou!1BnhescB>8X9rI5HZbyI-M^pdU*6ml){WZYaJ)~}
zu=tsei>vFw<Hy+<9z1`}uC1;8=FZOG4@;JnKRYA2B1EgDz5VgGx3>c{L_mAxrg*7V
zeS4Ex7~Wa`|L=G1zfr$HH@aOidA79l^|jWzoIV-LPm`7z#^>ebfwt#>7D|Cu`ky;@
zZq|3{tx>((a&Iq6Jlqzst7PSiz*bNL-tOOz$4udJ>tc7Cflh4b-se?SR%TZA=0@Y?
z<^GQ!9&SHz`t)ThJx`&q^>MlxR+p=`b^LHWFUEcPp;8i4!{6WE#ebFS{H$&7=y<XJ
z0jw*cp$Hz6y!hsd?=3m|x*pHTYKeb-e5`ofYwpsYT;xB`X5$OtegC?b`_Bi><!0R2
zpm=JErgD`G=uD$l&`EvQuZxRnhl$wsolH$nKYZ<4*cXYTeM{%JNXg6hdrj5qlv{iw
z5!CWed@KSPM(Yh0$&oShOWc^xll*u?VOJAqB>eC(O)fJ&>E#=4ShQ^{ykP+uU`u=~
zu{!heGL6_>CVX->5ebeO3}@zAi?0q}?-mm?=Ygj$=->;jsa&9nu;iuCl`PX)X1QGl
z4mf;yeVzZ@xpRx$RkXIfdGlsN$;%+nq?4qiB*?6?x3^gB?d=&rhgpCQS~+t3IQP6O
zUzC)UFD~^K2PISIc0Sj+R;3IKpi{F!=jY4I_jhz~?D>4ox=G!1?~WZ7Tk`MAfliWW
zZf3r8=~BQlA4!{<9|BohrTqN-G$J=GIa=c<n!50BhoExYA(dzSkilFHu8W|P2|*(_
z1^Swml9H0337)+B`*f>B6u->9FnPiR25oI^8H<7gEyAMmpq##ayZOIApZzZ`o-wtZ
zU;a@uzukdWZgH1>rIvldRYJnTiOI>JcE`-T1xcV`mUr*ofo6wa1h!l#zf@FIWR!Jf
zMWe8~-;9DqkD6ft4eEdKNiWy9VUaUuQNsNf$B%&`2UH-nLn9{;Tyr2I$MD+E&(9ye
zf3IJ?C+TRHhmViRLzkqhYa)dY9z0m_>x*Vnb2F&%4cfXXVO^#pKL7vzo*terudZ@0
zT)1$N`@*DUPOV%Xo}P>hpfWl2^t7W>wZl!0U%q^K;>3xHSvCtn9R#b=R}T)ga?dbK
zW&@2OzJK2@X`BWUSrNP2EbZJJ%_<*7HNQC>PoAWJ<_kfgAGP+_wYAX`r%h|yS^WIa
z!GnzK{Bk0;%TD%47%sZ-KXTEI9Trzshl5TsIKC=$^@g&yQ8{;aiGoV6Yipz1=hyw>
z6ciL(bX-MAX;Ju;tuGis?Xr#)87iJawoQ?bJN-ZXxbfonad&e&y<ID>W<7cGMC3-~
zj87jc7lRHmPD)OmICG|EmB{8J$1e7-*RHI|dGc}N#N)@^%+31hYVN%Njg{{+?7<;(
z3`1tyBvo%ETie)g6+S*Zpw@=4pUSlx8<Q7?Xgz%S5@b>6rW8*XS69$h??vv0+~x1@
z>0Wvtx-#f#y-nxO&tJYA`S|#_>2}ci%=P>KNv&JA?!@WShZnha>wMb^Dy2Y~r?0P%
zwa?PZD(S<6gEP!>XEmHW(%sc{Xog`j=!7PliVqA9|I&Bv-D|tdXJ!*<82-<Xk3W7s
zpU>*=_3X*fUhaDpk9k8@1TaQ#&vWe-)7=0Xw}u=5x#+mbN>EYotK6+$?yr!VB4|h%
zIzky}cvSyJXB^)=ljYL#;#ypG`71PTSh)PJuCbqX{CHbe(|Ktvoo~DsPapiATv?N|
zLgUAtg@=+J3+$DFDCl|k_H8e(v{}NRA0Ju!jvhar{Pxz?51&5^8_bkYR8*X0U;p)L
zI0p|;OLuqofzC6*udl5wd~}49N7~Hii^ieQwNYC=-f!QzbEkfy)MvA_GZHQB?aJ2H
z(%ZIe18sS%si^^N(_(M{tznI8o_6HeF*bgAyD7H+UR+eZapT5}0;SKO^N-5Q%fSQs
zDxQZxr`;cq-j>q|IwbE(#i7*nbkGW{j?PX;FE6jg{pDVhTGsFT<#nOtQNiP;CeUQs
z+2>OY|Jx~g3W104L<PZ=prEKT=oJ2n4+{6HUh7_5JVRAlTG}N08c*t}DT20KqRuv%
ze&%+1AtE*RKywXWKywWr|3=8kOM^qv06bT-V#SX-o&J7aQP%n9Ard(<hi_Pfgg`^i
zu>4&NXf)V&wwWvF2pCTx(1HHU?0gAdUtJAYeRYOma@z~TRt_#Mr+@%~TU#=l8JXD@
zl)t}MP*5OXJ1r8_M+TjYnS0BmN5)bpbaj}h?IeTjYilk>HLMF;y)oye5$I4tP|I~~
z)K&%t&~VK%-`N3+-FSN>joq&7aH_1XK79Ljbn)%8XL&)VX3ekv$EmHYePw;T{I+e|
znAAm%-@YvkI$3mk-d)hS;cJsYhp$dj^?va9v2uphM$j;bb@@962Cpd^jas3rKuhc1
z@B6LC@Zi(a(;GH#7Peeu(9SRK_Ws`9!vFtjZ@$}nh4saq9S-Kv(a}GC{!~;@U?_cc
zMbMT{Q1GI*chKkfr{H{k=H7#Y&4x)wI83sy`8@wPS=}FWnl|V%1|J(qQS->iNDh8}
z_vL<b12!hPUVJ=b?w&n1cXpL>Pt^+DbVHwMWx=LRn*^k!y4J<+UKF&{3p8)xKi}@?
z$H&J%UW?BEsB*gA)8GI2_4xW;$7Z&JXV3b6v2fa0_@chGSGm6yI)yax__346_bvRd
z3Tk%niL!zUVRt!cb$RLbf78JYmk^PhIZb*oI~ocfAA9)VU~?4r4bZ9NPft&ee#5lX
zy8NBP(jY|>6Or`u^I9R(GHsyv3tsNGVbdld+eHR^e0-qOh9|50Gca7cc8&F3yQ=4<
zYS-uCSEt9<b%Kt8I^HMSym|BHYa3fySU{~i=XSoMOFSpD_<B5hacgTfXrX&hP|$;?
zPnX`@0Sa=^2=|;hb3ljaf;y8QmMjD94hJnrvnYKf!jJ&kAz@!{*Ty5+v}cb^&HumO
zIe2)soY)_|_vf?O9-f|{BLKhVJxlGJ8?!o0S7Rz@3pDeI`zI6>6dX27{GaS^cko!R
z^u!4h6pDN%Th;%wadLJR6ccNU-k!HG@o-y!)>P1-PfSdVOTW8|%NMVQu-1&j!hnRw
z$9g$9I4)G$*x1N0GBTbxd)D-0%Co0uW*UQbR|yFV8<xBXsHmt=Fg6x8&%4twd$zRK
zG#$+<7b9akJ3CM=`2Fo|shoYq2L;eZBxZKL85Kq!FI~C>+EsPDU;gmHgN*Oqz0(L?
zHRZ*|mQyEAG)$i^4(fJIRCe!@JN~Any?wEJzns`^X>(Ct>EjkTGFm)HV{R)p+%P|u
z{5T*HT*HchY7Wq>;xR)x>2|JWP~U60f|;KqC^lEGUVY9rOH)%5)X4`e@mcKF%ha8&
zd$YTH+oMO10`}EZetCOa9CSg5^tnB!?$!UVUAwyO^v{34-}@T$R<4ZOYjvzwy4~OI
zr_1w?(EB_(y1R`(rYtM}^yH+{-+9ZIKmT7b>CwY;bFD$eppueO!Ru?f3_rWmKvl?s
z1q$7<3R2S2-S_MN%Yr&mYuD-;85@H}(?A`Ou&^-DZjw(=PwN&H@0g_O{Rp%<XGh^<
zm;R)(9fgf`pwT|BrH4Q@^rT5mpjG!PLl%|4zo!wtZqAF39UUEAw%O1I(Z%}m@9$!7
z+`io{=R9M%|NNv23miH4`P-w`wyAi6+S4{RHVeX5gXXGy=2!?$R`(aPUFA8)u6Eaj
z{g-zXKAvvS`O~`Og#f6NS#4uzD7gRcx7nQPLZC}XKoe_=7B8MSefsjBJEu++1#JOX
zut1^Y#RbO)EssDA67#$}2CtqldtcdKUk@AfNk~xGvv;p+ze>pIX}X|;7|y;{Raa*}
z-Y@TdxQ$o$)9FWxk{)j;j5~77kncCB#)l3l<;?ki?$U3zgvWoR!LffAoQr>LEZnlO
z@Sn9ApY-$lH!O}Nf(E=N9zUkJB5<)AXlIS->?M14Y;@jP^z_1(%;1B<vzAwVef1C&
zprBl;?B16Enhe~S#2U6Hf{~w}AGG=Ka67+yE0?HCf0oee>+8jBn{Imf`MHIKO?&fk
z%^DpQb@kZ=N`<q`^W&C$kN3X2<mAz#tl%TWY<9;f+3#mCH#gt0b7yAW?c2AL|Ni<~
zBk%N2^up!KmtFf4r-6<(0mb^wn>Rtn_yhz9fTl!xrOgkWI>q(x-@k}0853U^wt|+B
zO`k44O)s{q_V+i(r9p{@S~x*1z-jvNeTvR)9dZ*pI#xtHhGbAB<E_Qd{Xo5@;_9=r
zOgp-|v<miLxf0^y>Kge)d^u=de41|bhK!3!KYsiG?G~Svtm-|@WxieQhUDXX-Ignt
zdrnqs{dLK0lFE}OPxc(?JTrUW@mIIDW)~C`7(6sd(v8}}F~9DY=9)EYF06~S2DSW_
zdQW$Yijq1v*Sa0F$-emcxri+pg2(z~wX0$jtx8|DfVRUP=@4AxZfFe}Da**v*p_p%
z>Few3pv#^Z85uz%?t81gy7Z?PUA%bF!^`W^ow^?%6!+}iD<~<+DK9VIIJxsUDEGQc
zOCPUzBb^Jbd_Uc=xCI(@%;#$FUEJFX8YMOZ4^>v?$mD_sEG=3OAG>%Arq95v&#bz-
zIwd6~BTxF)jmCMWPn|l{Cu<F=UH<<5e)!ZWE?Micmfl`oP?5BL-!CrEif+)*z{SOr
z9OliN$HB?jIDfvplv&P-(l=*j8iQtyK?g)-SY7Vw=(w=!@0XXsKC{huL33>r6rBTB
zhv_mLSn56f!`<@x3v+I6nqi#Y*AaM@Pki2KZ-4*xy?bp%xLRKXw#+uqmjjJp=H1=3
zu<q|KP!)G)#{r9L*REyU-DL_oegF0K^^g1Q{~g#{{oSSC)x{;`jpwWMXfN<U&cw){
zpHAz4JSrZ~z+hx#l#ravoSpsFc8Q9o)5@TwpoIXSvEzf%`Fj+TLLT0^bLYa=>~Nj<
zeKOzQ-*4Z%*?7^SMJDQPtt~AH=jK>OsZZE@$}Hzb!UwyVGiQSKb)B1I$?Q2vC+qlA
zUTL!oxy8=yd<*^NTCIrKnAG@t>9S>@6E$C4TFPDa_EzdEL*I9gj&_6kub?iX?`*S$
zQCqWE-wBJ0w}ZAUU0E6Y<M;dhfxF9c87Fsv)}et`BY@6W>kw3a@b2BZ&!_DC{QQ`f
z8S`6OT7tUcPR`DtqZpNqjfKCyzJ9!ckr_0rdTOe6x7<Y)5iVA<ygMs)K5AQcUfugB
zG@jk%e!Izm3x&fsEPf)T56Eh;WbkPAoEoI`0U4kGO^ija4qH26(xj&IcE3R_L&x{`
z_JU4ys;I1d`FC&J-l~}yPM;TrtrnD&?1XMK>6f<$ohWGX_xqc!=ilGmb^ibFub{Yi
z`-~Y92ZLuHTkPHs%4u(IZf1v#_#8Tao*%TJcJboH4>*s4t`Xa_ckjemv%138Mm_v`
zJ)WHbG*=4RU3PO*YT<_mj@>ajR)vpTTwGlrzPPwpBXZM{Ya6$0F{!AmJb3-O_~&P5
zg-sT|?2)sTnxvBW^3u`(4G{_3sx9DEC#R?Dn;$HB_I&;Re}}%jybQWT4zwC`dVF1D
ze?LFyY?`Da96i$Je7U!_2-+?am~Ec#mXH8$BZJ2K!otF$j;ne)RaER)0G`pfFm2|{
z&bij*pdoXRA-%o4yUO49H8g+@NffJ)6BHB-eE5Ou1!!%WOIp^cDVm^}poTw_=Yxh`
z&YtvNqHAX-*DGZ@$u@403+IxhOJ^1+Z3GQHSL;|?OM`Z4hR4^oR)2rDF!%Ph8J5M%
zUbY!COG-*csaM$6{n>HA{)D}CX5Nz%6FK<!%)WLwfi6^9>OK9~ySuvs*Tq=Q{SK;+
zL1Ri+)<g<tUtb5h%gEPeX+{3NpK1&b=GXsg^jbP;@BF26G?sU7-D>*h&z}d+pSN$>
zVv=)zpX}@F>yIDl6b2pTy(RlPUo#soXu3KlCVn`uK~&v8&;GV%C6(6R^cxH{j<
z!}~O4%=*kg?aDqIv%W&`z>0^wncu?=psMHzc;vU|@Ue?xLPAaV_EsmKn4rk;Dc)XD
zQIUg_bK+lF?^|CUxeBZKI8;<v2nh)V>?}$Jwf~vf`L5V3j|<sZl*%J(CBn?kCt|Sj
z<=ws2;&E|tI|?7OWnEv_8@4uzkwGthU(ZbA^hfRTbq6LYyX&MiFB8AIK3*QQQ3Z5P
zdq)Sy9E(CGhkw66zPPy9F!PeijvYHV<^}c0*Zp7&Ugo2@;fD+ZXejsl{d)P&&(3b{
zV0~f#_lvLy7ps_l98arL<NUf`Cm)2K*DYnNDk(A9vv+Uc${^Jrzkg@v-U-=PQ>mh=
zns{|psMt=1+Ux6LB`gXQKxfnc`%`&mSLx~lwLG@#<5KVJaJaqMSM>0qLmP^p``Og~
z64|$JUj%50*q0Xzi<{Myl$5ljU?Z7qpFVwZ=})*86BASL^;PK2$DnDv_V#v8btC(m
zH*bQD#D8{vem^LY#O^NR;O5@EqQ0Uo?aGQk3DYbQ@UXL@q9W+Drw1#KSXX_~`1R$b
za<$WWW6(LEmzVR`{eEjM?3)(X)ZDE5i+k-MP}|pUo=s=*^K*`C!xoply|ttMza1N&
zOowLhGSEEn+UV_KwrZT<R%Eh-w7NXBfSGeB@$m$^H`0f}vHl4b*P1eBd@m1!#`wXC
zL7fdy12xxomdU}b+1CsH{wh^bQCR?TI~Ug>>-T$<t4ua;E_)lb=l8qapzym_`CPX7
z{NihCqaXi%zu){~Nm7(g%Y4{c0MIb=$B!Rx?5#H6Rq}FCsg9BoQ|+%Wp!xN!VqH;_
zPEFNLetBsrXr*0dW~PUq-!$8KGiG!g@0SNPR31Hk{Po_l=b&K+^LrJ{pxV~o|M;)3
zuebJX&%b{!>3+7|?>ELfcJBt=;j|)t|GpQ6XSmGuG*$#H_44rbZJj<{Tue8r#jf_(
zf}ES1799u89jn5JA3pr}m<&4PIBILwtofkS3c5kAtjr9wHm{<pifc~5n!3Ng5^ruw
z1x<3zo-N(*+<M->ACLP%b2M`-i&^|M{L0GA!q&xfvT}<(xVN|Z!?$nSPE4+Ra%V@O
z^B0b^$H#i5C2T4-1b)xGu|aWL-rZl5)Q$Y7m55GTw5#YTmy@&e!l0F)V>>=QJq=oo
z$jr{?^7vRUBg1mPxrZhwIvW%{@c^9(@!^R6`Fne-P2<<4r=&PcQUOilrJtLlSrG3z
z$sq9%OK`u23}~tzl&NjL^_s!5_B_z~3ee(2NM!<QbwKKq=ioUC9?(K$(2A*y<i`^2
zy}=W<ZZ*xix~es5YgXcg1&*MN@0-)ky7Z@(f%5vQ5Y5H!-#>e{?59ul)wj2|gQ^96
zP<FH`f7jD*_lqO@`Z`gAnU$ViUQS6#N_XzwEsgtn`%*=9b@InYM>8%ia&3Hm4z!0{
zNQfyvKi~24#GO`^pHx6MFx<F(TUl9o@qt2daq;fh1NFbZ<$^XzcAqbOaEz7Jw&DYW
znVH#+f`?2^O-%wKB1^vio1~(ssCdxjvY?>g-YD2&0140?nR$11G`@I|!Ej))d;f(!
zmBpZAYq?sP6crUgHT12m+3IBhj-b_ZkB|2+cI_4eRsSlUhn9Fw234gqW=Q<_@#Dc|
ze|u5eWuB?2shR7P1m)%V^Yim_Zfyaby1dBUSi7*Wu%o;C@~)!u_v`=nwsMOrSzAkk
z20PBrvt{+mu<Dnyb((3E+Ouo@;>F5xwpCvysV{n@rlP{KaN$DGW}w9E?C!j~yAnS>
zItrTRU9)D*mUp+8cnX7Vg8*Imv>?;hd1;X2(xA-0IbUC0wR)f3sjkPIBjbF-f)%v1
z^nOP2;|ujik7;)FE|v$aY6h**I1FxIeu;;!iUQ^6U;*%as+k$zU;T(vqPx2n)&2bi
zS{Jjc{QbJmKi=Kl{qdr^yrP=gu_Kc^r_Y<$*CncbN^X6~N})@aFZ)_dth~9m+8ngq
zr(0Z~i9tzO8Fc=~lP4)9udZ+&Ja}-^`PJb!H>I9_@b+zQ-rZdX&z|L7zyF^V188Y+
zM{lp|*H>3TBS8m)yC%+@*|}wliG{UwcHOiYGdfCNUsJTUmfl<S)#-2>FRPzM-`1`F
zo?3&(F0Z61uAc;2Lh$bH?nTE9yzlH-pip05e|A~Ei;K&bB6#KnoyXB5Vdzv`{rFh#
zj_U7vee(8w=J#ua-`?JSe2!(Y&bK3S*4Ea4e!X4~8ot?3`Z^4Be7L42r<|PJk2jmo
z8>F0=z@&b5?<r6T!OAVBps2`bXJ-dG3p;9SmTHyG<}aYY(beS*3=CxWR9^f2+c(f;
z=7R?h8bFs)ot~!q;_B+@4?N@d-MJI9_<v&DB+ydQy-zyN+}@ac9CVx)XglJ8WJOOQ
z(7_NHMunjB0K(QrfhwR6-@ltzOp2JS<{S6&cxU)JP<zfETsIfqFu!#J)E5B7Zf|e0
z1So<*m3ARGf?E$CgGoRm7gUc!bWEH+X;RaM4F*S!90Bcs&)ORGdWVYVk8ij0S$)<0
za&mMoUAmOgzkKP^htJN=R-1F8=E~Y=@x;VL3CkjtoSd93eW1IG5)%_wL~mcW;N_89
zyUX>fzP;&G^PL4Azp<^}_AKJ(r>B7nomgwW-z^v0$#D1TRnheG^NxOcdRkCWu<`VC
z{p>nBP%BN&R%)sDbTONy5{KJ(L8tbDu0dq@`Ck9*Y;*UV932MG0m-1v*jvmVZWK8?
z+x+;p+}j3ucXluxH!?B;UH`Nt^RnB4lt;Ren^<hCzJONV>wL0xmCuU_xUkH3woAW*
zi%W{3%Gdq>Q(GZJcYTl>bsPEZelRdxSQ)GiYCK+8=*;k`{OVlOY_Um`Cb9T=K63&u
z;RUT1ahrQa*;B~L$;roH=FgQuOSwQpBc7Ah7*G74q-|j#0oo_Jd$%>HOSol=iHv<+
z%!eiV^PLugrv5%2lg^je^M0y!xPYW&CwLifS{&%;&2_Q6A3ZraIbikG2`Zk&mriZA
z_nwq8vHxtZv^nT#<SHJmv>O(n@z}>3^0#a(>^TgYdR%xY={{&A7u5DT23qal4jTID
zhKvI7NrU>47CAD1L4&mS_Esy~+RFCz^=X8!i)sArF)3wY_|Gs65e{Bn*Z=?imdgEq
zGT9##fOq!S-#;?Bb9?G(G0>P0=&rjL7Z;npcb={ve{5Cg>Vj`?B3s(q7ni@k*Q9Q0
z>+kP><M!>x+wa#o7Zn+SmM5%Oq4DF#4+aL%h9A@HYY}gru`Y@J`sylZw2XzFotYtQ
zZB(ma^05ck<Lh1j{`z`xW3u}c{dl?G-`|Vdtb94wqLAtBt*y=L*Xu*qmxAs~zIaiP
zTTJIbue3R6tPm6pi`-2u{r&w_)YL%77=act2CR+R$~3#eb5hIw`v0*PS{{K8H3x0e
z<(EJ9_xJaQZ{Dn_)IWFPgu~vduNPJXDuYg#{IWuAbKYI6AHRPezIZY4i-wDf%X*tQ
zM(D~sjp%JUj~+i}WSBW~CTOU#sj122_}aB=AyZA8Cr+N+T>Si;qM@On?`*Ty$&)9)
znAj4y`s$C@>-T@S9$zoHXZ_N7SD2s7UjRz`XW!o4UA{Q?_O=fnJ}@wRd3BW=v{Te{
z-pRk8PV0lxbkDB!8^ae=T&?+bGu@*48)ymOEYs{ZDbuWk|Ns6Ll$Rf0<l0^E=m@6^
zXaPzv$Gj~u7Bgqg^zilujk&%EY)Jyu$Dd`Sj~jgRb%c!`v>rZ|cwdA~`ne@&*Z{PO
z60#$MtG)N|F-;z`bH!kl;2Prbi|;4Z=Pw9a>IFJ=EMR|K?Zw9&;zB};D(k1Ja6UfX
zfBhFv{j-OM+dX`JT^$@6R=S&TgVujmRat?``-#f#S@+_vWNm%Mb${B9A2JN*=G*s!
zrjHuleZLD@y=`cC@k;W{y`V5NF%d~jOcdK`VXvvld39Cj<vaJbW{XE{&1x-sdyA0)
zbjE^Z@iUHDerrHy4}E`kSHd)F$}`*YKR-S)fX18N+}nFwNqj!@PwAy0>tZCQYKM#2
zcHIP>5(FC4es_0w_B?aYiCi%;GN2=^e*CELnQs^SVahVonjZx{vesg;yUSXGR=QkY
z7n_)ztX!o7nz)0^rw9s)GV4ZfJJKbp9k9DB7qpNyGBOf$J>Rn*Q?<h%JbI*5;Pmm@
zn#ktN%gZv$9{2V1v_N{ApmR$>+cTKicm!;gW<GiPv{P>3je@eWYc)4P3$b3j$T&0G
z+`rgHU7g+1(sI!;V@<pKp3UX&<3KlW*Z%%?b<ceb5iU@_?(}qh_w{jmLD#>vw6=22
z`|?!UrlMeBz567Un%{4?gJz#fzP*VAwdt;bFG+WwYgH;BE8Dv<`S_zRFE2ARfZE8<
z&dijsDp~O$^JoHS!%b!1{Lo{G_cI=UK4y_K=Q+4Z|0VgpM0@XN8T-}XV&r*m;SG!P
zpymQ-s@;%J`nhFYm?UWI>Advg4TWEJm%Wt|(}_56^!fkwPOV%OpU;{zGHl$qv7oR}
z^TSMCPa&_VTCLmf*GVsS?-w&%7FqHC?|0ChPr=LmGVjffjg7sy#8WsTI{MwqZ{NOs
zt1_3`Rrr|g)Ku;CL!D=?uZ`ZmAZR6MtcqJ)&tZ~EMO9UooOg#&>ZuGfwG-#g9ea4V
z9n^C@TNoW3y=3|FZYlpAe6m)cmIJ7PRQUB(C}>;8;ls@H=FJPx5Lt9wSk1~R>I+9&
zx3sv(mg47rprurQKA#8O6(l1o3tDZeG1cpAnmDMHus?BUy)vkqrljSz@7F8sk~cR5
z-|zh{*YGEH_xxJV8M9}1>qc)|5WL(^$z3Gt@v&Y|1z7d%4QG6OJZP6j@tT^SpE52k
zVs&zM)_t}_&gh=?`#sI7-qQ|TyeQbtC+id!Cs+0D%}UFE=k5PzyglVJW!9`!mH%~P
zcbPCK=<50w?@2!1Csu4aiJ6^G<ku^uX(gtUKqIHQx3?Vy&$)ble*So$tn~%R!aC3i
z<Dlu7kB^Uork+46U&7bNH7z%@1uYYm(c=2XE6NJa_I02f4%&zXnkfa%0>K;d6332#
zw;q9J>8t;Kz5emX$K;F2GkX91{k^#U|33zX{QP{-Xy4o0+r@3B{@k=}8~AvPJ(a~5
z7ta9QD)kVw{-%Xfm`ldn$LGkct=XWPr5GpAY=<rzT)1$dMcEsPD_N#{_UzdJDrtZI
zJb3eF<d+U7ll*%!+F@%Pn%Q^-1O*$<obf4ne=oN9&#SAe#p<VKdrktK@oJKJ$>obi
zh)=;|rrf)`N}ado-JLLTV&mJ}+ntvNJp_#hfKHv(3SG6J{{KG?4vq~wT7SB@xac#(
zrbL-dv#%X_dV2cD^Y;H2_{=l{Ej^Ywec}XY#m0pViOz-0T%dFIO5WZQ1&s*2yT5;Z
zX%IgH=<bWt({zPRWM^)!{QL}bH}sD$m;FI&BtQk)yLayxK9wil+f%tY?RkU}!-}A#
zT%d~L$@^2W3!Pa1{QZ7^*6P1^b`~E`@;let+be3@6gk^Coe#8w%C`F3f~2Ee5@tCP
zptB^ZzP?h_(&Ad`HI<10G-s|GwdH{M{hH)LSlc~B<c+iz7r31M3(B$i&`n~X$UF~P
zmJQ0;hCRKYc|cHPzA#TeCj&aPm64G#YJND2j7>$r7ml>0si&ubmUdc|ykKCM#oG?L
zRv5g*^IXlDna1p(wMm=P&OUhmp5JqlfT(Ee;dcJyr>CZ#ID7W!nVH6}{h2{GZ{EDI
zHCr5XoKgOLyA@ZnKp6yd57(8I!Jr;N<emHC|8no`sRYfk>?(W9#Q-{{M9L(C0dyQV
z=mPQ&=d9m%$OP`t4qvCBrpBhJsTr{PDr;YK7W1mBSvmLiNLGJ)a}c(x2Go(9Z&$0c
ztB@ftW`Xy~NvaD&v=)YFeSC0`xuw0`d1(-MAL)()MbJ1AXsOQo`}1=>TwFq2pgTuH
ze5PmwIz2yW&Bw<#OMkNN)v4OyppAhyA3r@k-My%26Q{b+>!Y#Fy^5YfW$*6%oV3g^
zAGEh)WAgD2A09g2xPALDXup<@zCQo{f4^2Ajfs48a<V$eQ}^nA=Yoc?9R6`m-SzJy
zs6AW%@8|Msk5e^4)7~dec(AatGBW)7_7=3^8Z_!&Sy>servh{_B&)yYvj^wx{~x)r
zF*$I1UM$0bFE1}|Og_#BE<-LEF<4kyCW4k!SeLI`5!eduZG*eowUC}TpJX?9=R+NM
z0^l)t46f(!F~wwXv+!a+c$xq*U{`p<;@96_uh$opmATEeD!s7KnH@Id`F)}ar=p@_
zlbXrg!|nXcC+g4bsQ~XbzUu1kuB@r)S^WFq;r0*TzPY8OsMOTdu=u6Ly}Gip88m<N
z=ElYuHkC#Ve~uny0G<1{CT3^Q=E^Qr&^-<tYJZn4S-KQ7v<aH-2Mvl$(GKUkzCIpw
z!h>snh8QTeR)?>D^nU+;x0{<%L939@g2sB!%(s`%-~V^p0nVd43m>zA#-<)0?|&Ur
z!S|%zFY*!7mn~aNKx^BN_sKTTohus?8_W3Q|6I^{@u#QjAD?Gi9k8n;^WfyJ!@b;J
zii?U4tq5Ffkaa}^G|!%xm>94!1bWt9-<&xz7nOws1x3B#>Ey|?XGxEb^;(tx2+^9#
zy3b^*O6sX82b<aXQ~KlgR0xV{hk=$U&9$w*wn8?3^QKJ`CQL~9xce~Eg`Lei_wL>6
z8oM#|a2xN94T;Uqypt8`(;tG|`sRk<RPAuK3H679Gcq(l#{=@nT7_KMaR}65@961q
zDJwI}$;|~V2Lv50ae28v`-FO@W0#hCv-)dZ>y<Va5ENYaHS+4t;`DB-j|>b#LPA^o
zc-BO1)nYhs^ytz9wXrcV6Xwm!+jR2`FK7VHU0Qm1!431D;7LJ=W5-T{RzUxD1NRR>
zW3`{a3B<6ccXB^?y*oGofyVbhtJ&Lo7vBfnk6nLnZ}s+bzavgDeJOi;%Mr0_F}e>t
zg9@4je>mltYo6hXrK{ujgO8hd@+2i@Z<T0eW#xwt9~{7oj?;>y&2kz*ry~CQnO;#@
z*(rB?&CQ!P7e;PQW37Al;zh^4+TUC=PS}7}L4(eWz8+uCs}I@c_QfMD`PP<9i@HA+
zpqAUk#qNjCo#SJeFn4aRsCL+c&FAe7gECCUMWut2XUUoCY3$ju#l)uS3kT@z&ZxE9
ze$;PPP*VD(4<FwFo&5v47~;5mJ?JbW)2u5D3@&bNNw>G<M(iw71zqar?(TkYau?|G
z*wWY69v<em*C}{&YN~d`?lN6A9tnj6Bg3TR<gaq)Pn|mS>gwu`SHt5OH_VYe^YqBk
zqYu0F_Z<MOTAwkaW3F}iBH!6&9)5nup3krE19d5TrA&ovpLuUDeH{i$ymE4KtbM+7
zECREqe|PVfOZ@!otXO4`|KDF<1NYa}o_$;N^c1KzSh;fLhE1EAnwy&sygc&z$z*>4
zAtBHTh_&;zMYww8?d9U@|88Ay(#L;onDfGbj6D0_o7V|f>->D;1+M#Zb7UTG%m?iq
zX$P$X05|=?L%6qYSR6}!3|SiQZV#?gAOpLgKIQRam3@$e@jp-6yX?aQM}~&p-rj4u
ziw=Pf!M?CL-5=ER2bG;aKRw;r2g(_@x94x4p<Q49<6%2!{~@UDeXLg+G%ES;-#;t!
z^_x_{`z$J|s<OcQk9ALOOg;`e91FBx`HMzc`s-_JB`k|nK<Cx3oqzk*EzqT|JIdZl
zZOgftG?Dwl&cepRxIM3a?ks-3AZ+!+moGc}?f>0aWWEm+#p^}d-aCP(VHUBnvOWZr
zsh5^|Pn<HP1+<R!%gf6iK0Ze_rJe>2BCxQscFG0M0PVt3R%QnEYTw-4tmr9p=+Gg9
zk{1CcSywnxPfv3NZHY2$J$>$+n}-L7jg8HRkH_T~m%Y7ZQSo7cYyHJPpjJfSVmHu&
zg5A5V<!q}!*LE;C{QUH^@XL$9wXvV#Q`67QalE}Pw|7_m>aevRzTdCk|D>~P`li&=
zQGYmXL2IWMxpsq^aG)8Bl`B_*?iKD7R==>jJYOej%ZW$(IDGv5k2kaPoBU@y@c4ND
z*1B&G4l*xUx|DNXhzvM(!9_l36yTq<8K1N}Xg@PJa*riG&PWEKKjt|yW_^0#b@^@J
zOn>nhXj<oI{tb&S`MI~ZUEQ<nN|vdVX;w?x*;$!&df(+Qc7rbWFit;rLe9SWo6a)-
z`FV#rk3?-s;RH?1f;z5YYoj>$_}W&l*1okZxBKhs>(Ou8LP5ha-D0|+Q^MEYF8Xh4
zo!1Gv?eWPIl`5XiQ|8R+*;V@blwAGiv*r`$%*i>_dFD7M`U@Yq_{=b11RbN_-rj!h
zzs|*GcK!`nSGBfeUS@mu?j5Ld0j&;6KE?woS1w+>_~XN2e(+ZC5YVni@1WIJvo1Od
zfTo5g*6Hc#y|}yE+{wwQMDG8K#r>c$yE}WUuOFE_v){V>UBaa$o;P+Dt6#c&nUMjs
z^#9^w_I>|;WrwT`a{bWq2($y_>Z(xCT}JQj?rtx8dn@tTnVDj>rk&}3{`>*mHwf83
z30kNa7#KK9TLW}a@WY1>cN9JCdf*vv2f8IAcDGnF8}Fq*Z(d$req(pJe$@87-s^GI
zzMnsTeSJOoNQdBwbLYeiR~6{T^{QxUa$1+Y*>Gd^#62s@-rfSONG*GFW8vqD^Yd&$
z2b{(1Dmi&%a_7PT4X!x}3&K{H&MW!w=K0Q@JC{kF&)EPvA>agPkK;b*oWD7E^e^!Z
zsB`uNv|Rv{06<&Dq`~7q2H-(`$lgdu9$$Fq)VXtRpjq>y;_(TOj&v?MZph8m3OZc}
zbQ&{*g0eERaoU*!A08h5`0Mq0@g4hBJjE)HCbhygf;l|@7`i$Pv^?X)nKLFIQ=Ta*
zD>L8Tp5N}Z)F~xJrKqULB;4)&wY9U)J-@U%<Nv?E3=Hw{@!);O`&DP!R-1i$bF(@5
zc;CTOr$Bo^mio=L`taeyfp>Rzm&$$r{Q2<L*VhX_K5`ZISBty4Dik!C*CT5k_C+Jj
zd1+AQz3TaPwOw4IS_|^;?*px<xV+5Q6|#0~qnIrNC`AZLmi_-%du3Iq_qU3-x3-#w
zKiLqXr>A#gN1<|2adF}Icd<{NK3(WFRZAmqQOk>qEug)Cr>1IyZjwE6{P^M9x20#B
z<u*;9KK;eTGoTKqpo|PpdV2bu{q_3~e0+6vHR#?TCN<-|MyaP16crs`r-L@6_siLG
z-7z;b6zuEkTPAgO&7aTb?LU0_1nTmE#&AHB96O{utE#L(bHoQH&x*^*(K*&DtzLcS
z`gQT&-`*NObV)ip!_fH)$5AHG04-=}{x5h)_gErquH_hLrxSEjE2xAA?`z)z?y7_4
zVIX^%A+tEFrWqF&1bm;a!U@_l;63Y@&COf4KuZfZY~3nq+Z9>4t>Ufg>hSf~D&xJQ
z8tT5h2$Zp_i72jqer|3@Z?A3vXe~`kYwN<ey;W*+&g}uMZ1P$v<h4}D)6?_Dmdwll
zH<sUb44m70`}lh16%7kI8hCXQ6zxqHZM@#Vxnjk}>8z(02TpN!=vDnTDWS*k+lq}Y
zArU4T8x^&>W;ESMt_>0KHtFhc642pz{`YYBq_gi1G41;PC~p4DGc9*ZpUvWFT)*MD
zU4Yiq83u_=pmo~2N?%JIJ-X@tz6p0E^mVR>HnZ`9*71NkX@}eS+b2(+e2n|z?(+9~
z33DSr=gaOWd<?3sK$HHZudlH(fbK>0p04LwQeq;eAE#5XRHCk~4z&Gn|9*RZy&wN;
zYHI_x<wSmYeVu>bzI{JlEbjktzpbO=h3-RE$TYvI!`oY1K^vQY{QjL?Q+It`Y(Zh+
z#m`!YCrq8%YE}9w0kl}jJWs~Q*Y_c)@S7F@x{7&K=;{w=&F??>_xCp_g<o46{WDDt
zbSH9RX6DMTKc`F)S^QJA=JB!Kjn&`t=KAfqzqi`_&Ye47Hk|t4Gs}e2%*;%yT=}Ou
zXcp=2uFwls8)al<KGkkMcXM-kVt)Sm<E}{`dr$95e4KIoSm5zv7kPiXiAuYh=g7Rh
zVX^9l1#9yCC;h#P`+65koAqg#_2u2LxV5n`WMd)Mv12FYrQK!0YD05m?rtc&a`V<L
zr%5Uojd|`}Sm?Yl^RgOftp#W(-qwAGw0T~~yo3#)gT*Y1pD|RFKCE?dVNp_2GTFB+
z@9r+p#uB^dk~-DZ)hsM53JMAgp!0SzGFIGTWIyIKEj1-QJ^ODI=peKyTA`;j_LqHs
zch~y;{o{SIt3S<A@tlw<IY~uPUETfu<rZ!(F3^qDAKq@ipLBg)tk(INGiHFwZw?+F
zku82Yaxn|^baZ&;*L?EaS3e)L0p7eB+RvZL@bBM0P|s{v$;+mV$;VgC`LHwRrV;2?
z-lJWjP2pXMnVFs9`f&&D+==-j(hTZ!fI8cGd3h0AvqJC9uKcw7cgNbbYxg~qoTBDC
zOF>J^>+$Soar<gIK|?;Nr>8MZdpUpodVSDwo}jZh&de~3ivNDM{Jx@{ogC=kq{mi=
z5AL3raeaG!yiV*c5!38zE)EV1r>5z0Gn_bc1~irk8vWQBzu?k+&|G8G)~wEX3(LWA
z_3DPjuEhH*k{-Wk>s>4>y}Y7lW8n?+pUIC`B!h*zz%f{sGv`s_;|+!XdQs!_)uTs`
zT>LczLH&8q#p-o`e}T65W?fsu$<58Z_4?OWSG^Bd{aqcnxa|ceTQ(@6nr4ZlM7mvF
z75edR`Tdo(aUPReHl?0^_BXaEF1BRuq)ANC(a}40>`1t_Cep3?MrcBULQ+yv!Ou^r
zz2|rD+_^A#xgTiJ-n{9Z;=;npRZWhw?d$EBn3+LGQh<6}2Uf4YK5yQ<6;WGPJt%$j
z;Q>=AGdtgvUollxR(vuR4WKm*aeJ#ieEM|hv5}I}qVj%~)0=dvpgZ<*zP-6Q!~R6$
zl`z;^fO@-4n>UBb>4&ZoS>`h{Y0LgC3=I>N-5)(WJKLh*LBk78wu48GsJy>lYO8x=
zMjgXn|BDwdg0Ady>yznZWM%{H&`V5A+^~H+=*Zy@r}g(gxUkSU<Nm(AFIMKy)j9p*
z&Q9Z`q@)Wwi_?EV)(URewCT`fb^n5ghgd<EZCY7Lflki)_V#xAl;wfZk&%f9n^-@5
z{|>tB;mzB(pw&wi6%`B&&(6+nZ{-$$_FHXNd1zRe*sjvoZHL?W51%=s^L~1L{lA~;
zar<gG%gf8(+}k^QIsgCDJByzi)c>miEr8XJ+aqA>&SBP9mLmhsk@+DT3rh|kyV%zo
zY;x?L#hclGz*)EC@Ug(7$1d_pyIY(2UEEN3!{TS+V`$0&Clfx=tM>cNvXgVf*9RV4
z7r(#n)Ku-yPQ|h+>gtQLuCD6n>^%8<R?eEN>+5)1oj`X$WYyGtdvh~DYwC`wudC)w
z7o6$?I@R=LsjPKb&1r8QcNZ5HCnu*3g^%5C+`ReJw(ijpPSDZonwpxG;?K6{-WL1)
z?d|1?4}72#MS5VFQGs9H&c(-vC-43~-UnAX=gZfAnRtr-V$a2ki`_wEm7rbZb#--7
z{;&S+|Nq;b@%5Mdb8{?PtNxyz4qoK9XQ^ph{^w_BL2Ib1s;chs&r6MT+gbE<L)O(*
zHU2)e*KMl5@gyJbJNoPE>xr{xul_Vg=QQXhgbj&@H>8{tTKsom&F^n-6LWKWSFF(3
zYW{Uk%}*iUStgB(7b|~zcUQY=m4S8nJC~A@EvGWC#O^9_+@5#0=Us0CXp0tThU@RI
zQc!cR_V+i}^Yd&O89*IWP?xj*f87+VP%f@kCi_1hnjai}w4u->865n5wTruYgAL65
z4&Jb+2j$w@#j?`wqSEf=p!l5A1TJ)cN`p&WNa?%_tWl(=ck%3=9v)D(>6f=}TejU(
z`t(7*|0PdO2+obWzR<aS`<^2PENpCIuf9T7zU61~?&Y2|d2--VFVU&ajy+RbTUkL%
zWc}^`hCKfK`r2COgan06n>Kyf)5CMJnVrAu%X1kSnR_3Ev^uN4yl4dN{JI`rA6mI5
zZg16&y1!PS>UEj#Y$Yx5C6A!B+i7QJC}!vi3I?7$2Hju2;>hK%dR)hfg1$F0vp;zG
za^>ah`S$gFpj9r<&&|!RoSJz0%o$L83keHPoIRUcTwENqaPQWws4pgpptH4JyvT^z
zS0h>f_pA7twQC=~desFw?CIo5&o4F$E6jy1g*rJgfjV1nZf@RlT*dRyBG>K@pPqVy
zE?WdmZhZdi91tL|DrBWnfv%($s50|=xFP?_#=<Shk0-3VVev(61Grvm2bYYp((NTj
zk1aHB>;=V%MUG4<xRm|r?dyAVhG8;jfT}mXI9~osf=+zDr?s%~<UP*zC5dO|n}gQI
zfl}0zDN8;EuzODW@aJc-<7*!F_YMEHYlW^#xUj%6VnagXvFGZ3b2@xyn<-jaMxH<Y
z<^1K#!jn`I-{0G7U}}1G<wRA_L;wE%{<^_$&Gq<p?$Z(b#U`(sWtx5H_;L1w2M<>E
ztE#9hD1ChmwBmhL=;}{$?=LOo2KBNwr=Rbd;pO5I^5`REmGdH@CnqK<cXV|H?Ue4^
zzJ2?}ISy;jzPh@)^jG7S`Sa(?UF%5C%mf|uA@ak!Tit&iXhy)I=t)Q5zk+`+FE0m;
zcip*r_u|@U^NYnix1OG!4w`JQ{{HUZ)vKbQeTh4Zp1PbDYAaU`EPZ#!a!u4$F7v!Q
z4oAC0FRqWb2Omb0&Ut;Qx44Rmih_-e%-dUA5BEx&f0+OO4?Ae{&E@6(pu<i;^8-&$
zPZzhnssPImB0aUi7NC?5D$LH_u-KJ+AJj%UdQ4LSG(-hzovgZHF>7OC$#GB-2Z|>H
z@N&YCjfGoYUtKK@I`jO%0f#Nw*ZD-XLN5HUO8$SZ^yMYhsqdfv|6c!Jy<+0O$cPAs
zNh+Xmd#+Zdd-v{vw^2m0J^y^({<!)5n&viMY0w>@QUB-vdep7|WzU%pANXF>OIwv_
z)ctx1x(|18-QQnY=VNyiFs_Z>?$$473p!BHk^AfN+}qnGsBpIP%eT#(8F}wG>(8gt
z<G*b1TT}mE)@xcSXf-CNf%E_0-@x^8whZg7J{*^?cX@kj>%-^I+XEN7b<SF2ZnI-S
z!nA4ABKFl-w(-l)`+j4NWwAl|yO<+Kk1mYeT~^tzAH9tSbhz7Ob$=HhRV5{@j}?#u
zxB@vpJUYq^T9a>G_NGDS^oETa85x!=UFtYV<;$C!!Ve!lbo+XG!|m<)pi=?G#KaaY
zmzeYH?Ci&fTDd_(ip%}xn(R|EH5Hv}ReES;@bV1>51o4C?c>gC^E%($l)ACxWl+tp
zm&+F|=h&WfluIXi8_&m&A2)2?e7d^k{5;zimzVQz+PwL*pHX>PnVXYS)2Y`zzG-P{
zplUn&`Z~$4cRkL{v+WLB8@2MTY}Uah)*o*+pJ&k%UY~Td>%;f&;gy@gN05Jedpr5h
zkB<>M3KkwHZEJ?+N_X=&(xEw^@y0!eK(QWd@U1ruoHciW>o5^M>F1)L8W2=mnk0i-
zwV;Yl6r5saMS?Foh<_bh-h21lTx-L+KNX<EZ=QYxEjzoo$Q85{az-LkN=k}?krAk;
zvT@_a4coSXc5*EY&;YNYn0K(Cpupkxx3?Q}Z<}2V=7}pSGfPTNzPP8dc&+#=>2CXf
zKbX(XGClnGc>l%a{`2>AU(k=)(eU>6_Qg)ET%cL3tSc)ND>Nl1fp);0on`vt?e_Zt
zD}z+0J_n5)Y|Fi!bY(^042!}=3tE32Zsz6+TN`Bx3j3$&QJ@>pK`VBbEM2<tk8SPY
zHeL=6jtAh*g{vy~6t0N}XIqu7((#;RQ~1c`C+Ozgesy*A)05SFC#iZ)TJAqzuVCT7
znKNdbNK8yzlrFL4%a@X!m7kw&+PQP*p7Qr`Tc5wbvr~Eh_j}cwX3m_sC-E@bUw#vX
zx3{)VZf<IFId8xrU;k(0ot44rQ;%=jyg8Mfo&DyeOF?{`oD=n9b|}>U{dygw&!+56
zgroP#318ma4AzU^w`WiF_dH8u<6yh$Z)@)CC``V2?3i2K$49L%DxE-1nQfLERH<WW
z897bGv#+a5Xv?V&8ww%C@{2Z5jR=~O0ySaKVj6VB;g;mbpvq4Y)RF;pO;&-5@f){q
zpT1xFeeMfMHcc%pFEdlqsdMMfefsnB^V8Pl@1~T$yQ6u2zI}XIS=lsSU*D%MUSwP}
zZrxG;f8U;zlS1I&Q1L9fx+?T(;p1Z`)&1rO*!o&%Yis}f{eHi=?coP0X=$hU`1n2@
zYUOtIH;mYxe}CHVudmgkqoPhtQaL$E<>a(!(~AE8`}=gZd4AWt^bLJ-wpyT|S(MHZ
zxVNhG=j{A_7k~X}VF>gwv(g@Tes{{H?TYm5B+`gBfjs(F9U_U4^CG2gy?38{Yj
z<>lq4R;90AR4WMzUbH^!^M&;Tc&swSU};dNqI27dxtHEPc+dcvPCR+?<c&R*n@`=f
zyjS|^zx~~LSEg!*^Re^GwJcw*UiI}A=#FL3-5?ATX3Xg5xBn+`^5jX-5tjXOwk+#K
zvrkS^1?^6dGRbII=-htj%$bV+vua*mQUxt^d%E#(J3r{sT2N^-LD89k0kp^9=H_(J
z)fhT)dm@g6G*6f~u`zmk-ouZNk4x>B+nRqr?ts=`>(W;ufBycxxHUVR;lS_r`};x5
za1I}47T1q!nLT^<gVskUHi2%$ntD90J|{0vFKLov5~#<L0qcn_FSuc`egmkE7U`*7
zj2zLehmTdZg1b5iIWlL#-BL)yR#V2TFAdZKf4O}AgZJ<CtGW*UeAKP~;otA~kEh4i
zIo{lq`dRM%y}j0;<JCYJ4s_e;m6ekZOicpqwRd!M<ly2u^!4?1K`}A5r9quby{A7~
zy?!5PnWl@s$g#V3WtaQS6|z12AR;QtX<F)3>o=3M)Ya8NJGu4a_Z<Q4CS?G1TP}Y0
za|CsFXBwwVJ-t46$`p}36(5~mf7XxN<KX4hB_}>rhLe*Mw3oT})#o(OaW)@5IDpRm
z*;82zIv-CzZqI=m8<Vfb?M^>0SM%W@J5!jDpx|EV2uKQ01?_PGoe{M5{Pv8COwrqN
zE<RQ=D!F#;T1RJR<Mip`phHD-Z*Mzz@uFZ{TpVay{GvsR9z1-gShcLcxt*`Ivy=1B
zpFf~uEwZkzTKTsrV3Nul+v>0jPJcapeL?GxP9?YV$u_BYzPP!0`KiaCE0$AIme@U)
z?74C!1T-~#dwV|URIrBde4{BUo=@+`+kaoTyZXBxXu59daS(Z8Q_q$yCXTClj^Eo`
zUHJds-#z`CH*Hez6jD-B`tbYx{?&WJCaLsDoBQ1tZUt>Z1hsJYLHj16((3g&bN*}u
z@62WeH*`T=+pgZp_GW(nZdibpAT+`HGbiKc+tn64IUxvI9;)o#*D`tX<Xeu$44~P6
z#@9!z%HPR=F1afD_%j={+yBBsXT#E0A&jSayrZI|E`hiGALQ;~TobcXXx_Ye5gQU1
z-TGuWrKP1WPUdl2AGcRPQt~9TK376oTASBYt%W5oFIC=O-C>e>Yl|jmv)Q}5yB9k)
zvuT~5YhN!18Y9}Ac9vzWan7-df`jeyb)aTm;<q<9L8mLsnKK8x%c=PJIj!~Gy}d_U
zxy20%AGtVscXo7m*~LK)iVa}`T{N$!$G6z6_tK9)6P4W`ym+zVdFZ2$;=(^SZ`yRI
zk(nK|%<#+0%k0mdJ<|wXB?791wqyoh{LIs|cCD^f*qRQ|k&5$_VwQSM4Y`-V$*}*=
zCvF{GUC_}!Q;&O3*8`n6`?`4ELC~E|s7)mSThA4sbBD{@Pn|t0YIt&i##Aqjsa{);
z@Bja=dh79?kG-cEq}`>#(eN`FHs}D08S`5k3qKtPj}Adbl0rez2ok#32aCK_pwWuQ
zPuAz&-d6cvPFQ&Hw>^gO3-a^w`rP~FGHd@`T<mUOZhrl-(qYhY9F3`7E$!{fhK7Rc
z)~%DUtuhheVx2R0uIu^BtGPtAR(w6%Ev|2ndP>A+rV(pcSXfs5`UxtWD_5@kH78Sm
zjaQ1r-rgRx%0St@&*khaQ&YJJP+7nop?(k4c`knDBV$)10a~0_@PGl-f%x#y`Oo+L
z|3PchPF>Gg^z`&}(D9mid3m5E39qiKWM=U2@i{V4**#!gjHOQWHlGh(Mk@RE?fdZc
zYp7+<%lkGqHWTK~UHd%M#l_{l7(7Nn_Z)0aI}18n6SUa#*4Aw2Nh&I8YDp(2se<lM
znPXY(a{kKhjmgK8Zf(i5+8Z`WC1!u!UtN78p5^}Y!+u&=SV%ax@qi|jHzXb9nlWR>
zioM4q{43ZScI>dYD9qz_d71CV!pCkbEG!3Z-I4<JLqU7LPpZ#9aK`8BarWu@@n*No
zh2<;?7#<(%J>0~~?c#4JvB!E!nt9$G0o#Qx36C?59lO}myIA^LFJ!3i6}WxPb!^|o
zzFtt_YYuLXgNFJxf;z3Bx>r`(-55M92#wPG!)?5a)FpKI`T0RZSaYpPK}QOP%(E_g
zBQZ@kn$6$e-|_XA_wVlR=HTaduc)v9ZJPt#6DVQ8z}3nGI$-HJ=i|3;&oY;lTv-=u
z4c-@MQs-~}j9DMF%$nc+k3d;j8R*n}Cuir+^EPkZeE9C}@{Ltrv*H^3w4_Y4T0koU
zEi5E1Uc6ZOKi<;PGV#fYiJ;w8bLPxB(x=k=<^B8UO*)|3Y}>YNS@r!2N=l0kO-_lN
z<_cmeDJ}Z*^vRQiA0Hmx*pex%;@Q;M$=MKIt~xPQ5)}HszP|n}XU+z?#;3U0d280y
zl7Gg#%iq^^ck{G&c6J_<U&A!3{z2B7{U4M<pP!%azB%n|LUM95=vb~RD}zs*I(6vc
zV)u^++2vR4xpwp@tDKx%#O|`S3${M8u&_w@_U7h?@8893k1B|K`^~ri-i7@ep-mxB
zYo`P}ZnN-F!hKLY^?}#wKpMC0UCrS5u{Hzm**DLT(OM;Kp0^-$b(n{zr{m{mXTiOU
z15>rbK`UP^EG!<pxVU&l<mP2J7FH!?WpNc37lS62xmuat-rlbN;ZSyTbhPc-#gh{5
z?kcs4U1MMKqri5Jp^mI|*^y>;{(?6*3{z554?+$&X=!g~X8<`J)cUw6b1p;zbb7F5
zvD$5kTmSz#y!uhOSj*B<GIVvAtB;S*z3Z}|Jxo?|&%u+fAxtx7%~DcPVR?MK-#sKm
z1T@&gup)3V+pdzAP2ca=$A54#RP&j^(CVaE)pqdV%6FiOsrkZ%0MI5s(9NT9fA?SA
znjQY*$BzS7u7rGW`U~1rk(8V)C?nIeWQod_oSUGN(F3ZT{bOQeK*ito{CG$2qo2Nh
z1)Yg~#Qf`@`aRYnqT=9WoR%YVcVqs)W8lFtQR()sX7CV<v02|c=#UI(IKcVnK~UEN
zlp)G<=IjTLu`OJ*Ds;6NXkYL8eZROaUc7i?SE+VGczkhFQxoVWkHZHKI)3o_J26!f
zbYpEwii(o5a_KMQJsbM}y#(+0IG7-7UB+|p;K2=Bwj8;<-2dvl@{*Dxd#k^*=m>-Q
zL00>}{rLDeztHpKA@1`lEh^@RDJd;7Z!d=&7q>|0<dGwwEgm(&{G#4fRaSfU>;WzE
zjfjp0U37b3wR!Ttuh-)<?(MMzE#xkGdWtj7t4+zyPL7e05j3iKVxscHCr_4qJR9#j
z%S3QPACG53Lc+p0eNUljda=KzT?_C$bZp_Hr2C+B=n<YHqorlWCn_!tK7@Q%(&K=@
zjfE?AKr3a?1<j!Qsa{@QK5^c>zB_kfrao8oJoM}9Yu2^O&W7pd<~aSI8M!%aZ>wsX
z@5+#8zxSwk8kn26FJ7#C=gysgRUw+Ty2{RB`)VrB%(WJGbaVu5r`o%B?<v^}&(F>6
zetLSkvZ|`<hoHX(hK8C~UaNW<-D1|CG-(oOdBc(=DmHb0BHk*2ZW|C4Rn3@NC;II{
z(_;62skhJ1?*GUKnu^I6(}x6`mLupS3(zHJ&(6+fh?^U5cV)1;NzRRcHwKJ9mdRBK
zgPMq-BPqP6>mBV7RQ^;aIcx6RUeFd20|NojB+;j*r&;w?oj;zB=gG3ljhvRc_+P5R
z-?K-KuuM{US+i=>#`=333jZBL3A?)+K?AeU;F7rn8{m`C(gSB-_4@63cbj(aw$8h^
z2h;>vvV8gBYuCgwGc!+|JlQyRuI!pMYbH#YqEe+5*!f}CRK~BnPyYK{=s5{g%w%3(
zCi-g8$w}{ietv#qW3u}`_Bhaa7fshXKYu(f4?1F|u&^*oe1U!KFA-j8vm>A;`H2%A
z7lXep(zrj_R95fvy4$--wQFi?6+MOK%$*Bba^Ab%y6Ve{dDA-&Hgk9BfpYSykU+~H
zO`ro4`e1{#4Cm+Dx6hw1Z<c?LCvw{7x&t$2&*t`=^x*O1=F->KKn<p*>96?jUvbWN
z+M0Fs!g7E4wdJchd3cU&%f0>K`TY7<m6DRHKo^#N*`?^*w&$s8TVr|qrE`Z4F-=kd
z9rYHVA@bqdw`ZOIrNEuT6+3R2hlqe{qqpEmstj-tgU`JO4gbLUh3#G4y`cW%$@u+s
ze+yn*P;_y32W1F8K0eU#8=z%&pmUXvc8P+xudb|Au6h-1o^!*%V^WK0_O%07u816N
z<GuXy{LGm%51u>6Cu?2ia=cIW{wFW+h8o9awuOO<-4-pE*kYW1F5$+8#0?uaHtyeV
zpLKm5FSwO(YO40ci4z-Dy{CZ=(bEoFb3lLppQfqW;fKzj_y6!|`}=QiZ-egaT^GNf
zFFQNirt%XDXlYDUl~qb)+uF6dp!)!Sf6KiX{Pi8^uE+Lv_C0&|8Wuco`11a~JZO3M
z&reT52fVAOsey8Hue7<C?NlC*xmKkKsj00iR%nE*jSBrD^RS}8@nULvy0V#>*xA|U
z*Q+Lg?j?AMh`!|GeMdptsouZuZ)jlHv15nBB$b%mWxS`S=^kDcx*F6=Q1zbHF>jSQ
zC~@xHYpbKH>*~Ky=**ovGTmajP5bxnKlVI)T}<c4$HyPv+?-w&=N4l0;a$M3RJ>y;
z382niK;g#xj;?-4U+#_c*&7xiF*!1e9)U-1G$lYKGq|jIaTZkBzqq&<w1xk{#l`L$
zHg9$YRVl4k4!7}wc8)Asw1`E&_BUwSN?2GJG-12cYpT=PS*D-gMa-Q)XO7I0Wy>Dj
z+?+ncJYP=Df8Lt*t-rqS>W__$1ufcYWM*HKc6QdHbjdjn54S(=xBqvbk(vF<yveDO
zadB}g;`UmB4(YmcCkC{@1k_wCe>bOL>o3!U0}OBO@0Sk@3|tYtJ?~zl_}ZwghbF0d
zgRZuav8fQy)6-kDoNHtLeLK)}==Qw3ObvVX_gh(7CW6k4`tn6&&jg;{)>c-~r2g7m
zpCz7QVPc@Ikf1{tH=nl?wgnxLH}?p17~PA(+S<CJx;oqTY|VuQjvak{#}2pif8BGY
z;K`FGpe-IAUS5YDAMd|<&qdu+2s{igE4hk|R|>R#95l`Hqh`6^T+nFagGWcZVbQe9
z)6Wld+1-K=Ezmhtpz}-r{{G(Xw9o;xG~&E4cwT}}RP1-#iXY&nd&aSS7kQ=Ixw?Cu
zLqI14fCp_~w1IaGDOP>f(be5p^Ro!FFi$^zpUX_6RM6_|xV=@3450giIEB>|Y;9vd
z1RehN>8W>*gdx+$jT<Y)`}bw9i{0I}VS@o^M*?Vzk&0)=)m5T3wY3+w=f{Vvi3t4S
z(wvZ;-L1d>kJ0_ZL1|}ZG=grmII#VGUH8k&%OAhIy!_W3&6c@yW!-wET0u7jJ#G{S
zjZ$Z2X_dXdr(3boV&~4CpkX+WMR)GR?AWnmLF(yg2FAw1w!ZnVuB=>q`Jw!O6;Gjc
zF*`p^6O&w*c6JtM&}4J^c`@5oF9~*b_A~QrXSa)kjtNyg7W^JO8lxIfR%RBpEobG|
zpV!t#OMlhZ0d14Mx3?O!%p>aky+h_-C#a#$EicNuyNjVgJA7Tj%}uEtot+1}M73Gg
zt4wU;l?L5fl6F>V#;jRMH#Q`){*&~a1lm(&yGHo^!DjZ#^7dD^x9h*>Tk5*hYpQ^V
zNXvo+3NicZWD^q;1GJ__>?+aR_v@9m&ny$qFD{8UEPjGc=-QC)Ar9_^fu;j{YJ&~H
zHBEcTL2x(C96W%+3RYMMQg{e-IKaC*JDC|kSFCN#x;kOPgbC%0zm|GWPsq#DD@y7F
z^@JOl+4pT0pU(_h)&M$@=FBWp?&bdT-6A3+Ko<u5`2Aa1Lj!bgDd@)W@9*v=CMGIY
ztuwH+wDj=tx$^7J)z#r2KRrFYr~mBPv%Sy$Z@gZ9mz5zqJKJMY%l?1AwBLimG8weC
z=$Ryou(0r!tgBq03+!xNXNc)Wt%z-?dv-=LW>*Pk>FaB*d#k=O?0L0+b@+PFKGTBY
zVqwG39r^oyvT?OC-Q87sm|ea`p{g&yX2*hps;{qFPn_@o_shOa`v99I0bO47`}_Oj
zpnYm~`}6PHRa8~Is+{@|bY;cm<^G_x)u5RK(21eyft(NDzwc+~mrMBf=jV<6_4`j1
zFZG&w=*&#xt^exXk13j&iK(fnfzC-@xl%JJIhp&9s()fVXUL?;=xETv2B3|$r|vGi
zwm$y+Zs$zUd4XTPl%%AjI7~}jTz8o3z%fk@P}8c`c~`>YC;h#_6`*EjJ{M%4#RNTY
zq>9K%KhMtr4ReFm@Gs#u^LtoPQIYWc++5HC{f6*zg@3PBumAAlV=`!6^5<t~C2T4-
zJeaE5ynOlci#7H6mzHqOGRbTL?I70E<MUc7G;!j@8=KSlL8sL$cIO8*s865v{t~kH
z^{uVi`+mOzpI-wiXJ1}g%E$m3oci_k^~R#7USHncHh=#Ww4l1XyL-jXs;5t$w16(3
zs`y&FJL~Ey4-XFq&;;n7T?=kR=pFmN9dz#*JD<#fudlCz4zbJ5&c3oPRyr;&&aK?A
zDkEdXspGrL-X3~)cekLd?AmXps#aD~T&+x>pPjw@+@%?0;f-6j7J+t8-`QcfDttX(
zaB%R{>mHL@)<$pVidtb0iek)8|DFE~S72)aO#ksb|NH&E_=diYjulTPr{ub?6A}d7
zGh@&%XB+g>LRFRZ@2{`T-QC>(e&7GUsO;@62GEh;plzq110}ZQ-JSLQuxoO1US8jW
z2MIObZl*6<9>Dqa!$W5on+k*XEZ?O}vmPw&w`-a^ckY8!7uC!5@A;<An2~X%yqzg-
z?w|D`TA+K^jvR5>v1=D-N9e+U1E9?;HhYsEi|~Ov9nN2#fk(FD67P$EZu)8NMTk5`
zh=BH&tNYDyxV|nn5Om@vXg>Q`&%tkRZzpDDfzE+Ty16M8e7e<2Cl`13<co`3Eoy(6
zT)KRD;Y-~omX?-G(<JA;d6NT@ySgg$#{PPHA0MBPcVBXKf`WrVn{ejXR0=(N_6&4S
z2g8GRcXwBOdn0N0;{h|M8FlU)-}!mA&HMM;Ta~@xke8P~c>4ani;LYKAL$gfsQjeD
zknrovOVChS8^1iL6OeOb10!fy_F=m`i~iO5PoAXkNEk5K|Npc3*n0g*DhKc0m3{c|
z;fC$o#Ww`(aqE>@SpEGSXvwgNoqg^t6VSmh>F4KN{cQA6D}3FW%Zk>Zy%O`pB>Q4_
zmw|RV+}KsR`dTwL=)Q`)ySq4}G^TZSdfwZg{Yz#NXmQZSLQs3P1KM9Qawsb+%d+R0
zoGJ;rM*7@b>#K6?4Zps=mVT<go8iF4i-C{z^*TyY)6?4-nb|t#Ilgc3p04-s`~CWM
zr-cHxt{V4bUtOK82fD9YPOi^5{T!%vWoF}Pa9U{aYVz`%pgq)}j{1e!M?j<0hmT!s
zsSU2kk<sEa<J;?*GbbE$9<VRy0N`T_A0<4#FgxW<Z}8r#(vbCWw(paRi;LGpZ|8e`
zZLRQ*QwE>|SN{I`>iqZDSHpw@44@fSu2!Z^I-v6%R|GHTtNQXnv1*xP#m7gi-`?D0
zUK-T7V}}I;Xa)U|KA|O`^HDuK4s6T4y`ld9zdeV8Zf(!!*Voto^769!`$P7{#l?$v
z-KhHX<Rqw4oM&I(XOwyhwBve5@pC>WXJ=4C0!`6>d~|eC`m3|2r|Um_`?eR<*uAj8
zQNkoc0JJklTU#5{a23~!Ik3!kwgBV|LM1!9xVP`F9eeQV>gu0zMk)FE{j0;*zbc&g
z5H!~UT19lMN0NhsBVhLr83wEJcRcm=^*;0M?q=va#BWaXZ3I`bffpe?HWwGRjBjsl
zy8c>tV@>4ddxxYBZ!dcrr4zG5K;3VS!L7-sJj=OSnUat7ID)P!+*4J2N51|~<Eg3I
zi%VW!YPufiDJ~-eI{ZcI>B^mZtfy!N2M5oXJ$teDbiDu#k&OHMY8&t0&dtsJy2Vch
zJcaBL{zkg$Ht0aw>o+W3-7s%GeoQfTW8sV3WY8IF;6+uSYzSH+u>I@|>Gn_8w`2x`
zmUVzCE;;);9(HziP}@&VP7ZV%Pt>*?&@mkeA08ZBw46)vv=N`I70c3~PSA<3FJHa{
zO);LIXA3$=oS&b6s`VP7iK{ML2;h;kk+A>sfw_%OcGcHXX|o*Aa#}$tsjMmOOHDE^
zFo3F@{QZB~yuH1rJ~uKpzPQX+Iwd{*@uQ>NO=6Q2H*MH(;Lp#`f+8YIKK@koo|bTG
zie|;HFDvJPX7DE(K9Gf+`_FUX&CSiO{u+UxBe7CbTW@X6PCn4USWr|HWUU$w8J@r3
zWTX<kEywZty4cV6ZhU@mQTfWMP;Ns*!w(-m2<+)wk@E2F!Yz~0#x{<9NQ2DBg93Ar
zc{iwi?=Jg$*@qhzOSH}SF3vs*9!2Q`Rd1kPaQln1v#iVYR6GxD$-JD9l+?7d__^4R
zbQRA-J(9*>Hk{i4s_Wxxzl!?!`X;7*d-eA5&6_tF8bFI8?%$UO?Pa(a+feuCN1?`4
zuRlK?_k(V8m^o8&&z?OGUcc^scX#(;(6T)jEkz?^<HW?o#4YTiIk&g*>PBxn^ZijV
z!;kaz|C&v+uPG=g9n#Qum~WiU_v`!n{_ppy`TzesUk}>E%ixfdqy##m{QJAuoV&Y1
zKX`qN+f&iF|KBg}ojZ4Cowu~G;D}I}*4@qR<m3dp38R-?yrrc@;%Q@(i;K$=`8|-!
zS~|S;a0;tE`TM&|RNG`<TmGwse@<-DsbUK34B1=tb<b{R-}!d2Pu~Uf%h_J~k$&&%
zZs)yeXUeM=nYZ^kA3eBFQOn8<w8X1Q_=ZJ@OpeT=Mc|GSXsrrpWJ*zM*Uio8&XZI?
z3tyIcPrvq3Ks0$T!`(}lgqC_wX9Hc(2in58qx^l`z0Xs%LJ##yo4cI7ynCi`x{{5J
zjHf4PG3DCm?Z<i~jW6u4uV4H!!51{>4eC(ssSr#{OIs1V-0$9f=`9mgIK$V)T)gab
zxaip#Nzh%Pg@uKn8Ul2K6F)yc=mhGzx;oJMtKZ+=x}LuRKDZIwpWZsxy8IZw{htrh
z#3h%3PJ8<P?(Phm%1yTxYJzrEtO{LyVX3#c<Le{0HzYEH4$1ic_kDeo^v_s(0Y726
zn1Bt>&(BXj-X{yK&aU$5Pf+0m-JP+Z)WyX`RT@6NQ}_Gr_L_Q+w4VJctO+6eSyYvb
zRQ6a;DXV#0^bp)<5fJQzjOJN?>n+QXQBpFz0b1b-SySTdqH=8ie)-H@!CHHR*2me#
z>?+ZGpKNY!o^x-H<i36TDt>-ao#LgsDtx_O!NR)QpHHV3l$IX7v$Gg<SjjBY?5=q!
z0#REs7(FL_(zB}nYq-+e!vnORNh^F^52#dqe5|+f{LPy;6;)MPSBI}Ro5g)W-mZp2
zU0r={-0K%FI@<Z=_dRuOTV4G8+>1LqjX|rRqPOQUGGtv@!RYSpe(>~>Uk}^mKfGK%
z|IuN7dl%3lY~}A_Ky!1Tes4yG#;VZOZ1(o{7mZsV9Ay2uyY{!4RoR=4*VosB?o|U_
ztn~BK(~0xu@kLHc%+6k2_Pjz#N$HX-Ec6)VY^zxE^Ydlw>tr_RI8R!#C)h6j|8B$m
z8<)HFN-a_s5R_EiXBobmQ&<hOtSRHliis~Y*?K{fJbZ!^CBVxvSd;II^z=HrsIY-1
z=|M}|Sd$+M2u@u1`sQZ!X}ZyEt=!^^d}bPf)*0FTd?I|~#tq0VcT!hnJN@TcwI1u0
z?w*%e02=K7JL8{O>M0S>{vl3I&J$<OxOjMUocb(lT^6!a<8SQrsZ(2xQcu13a?2?7
z6zI02{K|<Bi%UvOes!Pw54yY#G|-Zil=R`lLub&)qHWcehW2*$WqxzJmif+p^z-xc
zMd@6Jo4L2lHpvu{v#aTdum39wIv&5dnR#38?KaTyDJLhXg3kKmle5vNQWF#m>^utV
zmp60@t3SH4vlw)1z{N$N`KgWd|LZ{IWVg8fv5Sk{1!ZM*tCkgjMh=Rebe!Ukv@Utk
zuqpL4SDahhvnMAf8<?B3Gk`h)lT`lvdcEGm+xzm5UvYb@UKYzq&T#D(d-><q{kq?8
zb@dEwY94PY>lV{J^yp~!!&k4k;^X6aWGp6>`(0=Nt@7o2*;MP?3MpM>rI#nXk-obT
z)UA`z(g7D7;1RROFZy~x-3!psA6@F&+T79Gat?leejaq>{9;>^ltV3?GYk@)?j4Wa
zUFI4SBcr6OoS2oxm7kx#WA|?Em=*CqV{7VueoA$5aRHq^RZv=b^uj{tz;!W}w(Ay8
zdhp}pW6&Urj*iZRsZ*DJtJ#`$6?Cx!<LM)nA0M?I`!DuC?Tok}^MSe6<)G!Opcyz#
zP0btoYOQZ=&2De!mruI4r&7YE!r;!GJ1*z1?9RTv4s_KiLqpI~FUE?mmaGh-+F?gd
zOjHI9GqA9+aox_~s3>UM)y&TSX#fAe;LS7c{c?;9DUofht*oF^yg+^JH#auk*jv5*
z!BS8uF<E85UEehD0WLgYQ?)`33LZG<L~Y>!?VH=a-QCBB2h^~AaCJ7{sVSPxA3hWu
z^gbH7uf`H|f|I)cya)5^&u-kd&8?uo;8>5Oa)GR*kg)J%r@f%Fc%D4jv(z+1=tHra
z^*vcHkn0t7ba+5PJXJef!BYry*kgQrJm_o`&=KXf7Zo;uR@5uTeyA1|Wwp=W0xr@u
zC4Re^=g3@Q-5(wp_~EmgH7NQ(J-(8|$KXm!%xiuW$XJ*0i0j2Le0X(e>oVWj&uU}#
z)l?oicI?x+>n)<%Vc;=_{{Hs4b7Sv4-d+CQ?f$;n&w5oX4C(3VDk>@~_MDpmYQU`y
zUk}==0@@qBCT6D)Xc^OD_kL)5?hvSt;<HyfexJ>=b91{FELgC|&935uf{l$014Hri
zbD(p0CQh29RI##d#*7&blT_x$X`kM7v2OjYnx96XNPY7r$0Yk2&&G`#!3&7@WZv0f
z2<l6$iQew_A?WYwkd>gbia<vsGB_ZuGGk~6T^;st^Le|=FDEpY3-aq-ICtri(CO*=
z$3HwgJaO(^-s0k7P(5y2{f&iTP2^@aVRb*3s;XU(I2L{nn@|VsC$9VZive__0mJ&b
zgP&(DU#`B)Z?0C#Y(>yaUsF@lg;k;2ENpC`J3E*e{=BdMe;9POkcdbN=*F=N3mluK
zPg1m~`LW>zXUHM&F>5T%M|V4ChVL%R1&w`dPCI+(<>lpqVq$Ib^?wBa{rktk#nm)@
zx;W@O_r2BS5fKp`^R#(D>l$P(iT-ZuY63TjtU(KY%~>I<P(g#*Z^1PX*D=sSNAN1t
zMG22zy!-I*@Q1Ho&;E{B8S>~*D>vx2p~Y^!pdEjpo%hydZv=Ks;yJi3cK3rvj}{dL
z{sgUpez|=9p(|HJq|I_b<9LFiqOF;imnm9UNOX(qi|vT$vH$-^7<6a)+1cg~-@NI`
zzP=8$4T~WmI~zR9qN&O0Jxxb&Pso2z0~T~4qlSjZ+nsCH=(M!7fUb~Yn$`(AN#mlh
zSBvLlwS%WladC2T8km~4Ha9n)`h4%+y^f9!fh~S(K(n8Jetxc$H_yK(lYMQCW51m3
zgxRyZK~n=|Z*MV)cYS`}%ndrA@y(kYhK9LwW%=aodiMYOby|a8kAXp5UH#79YH<e8
z)DURZHzy}&rTBvQokgtAo;_1i7ZMblnz4u33e<-W<b3exQB&gKw!~XoGQr1}9KL^F
z-Z=dn3j?Tuq8+}@B`a&yiJ6CX?A&?q*fBQH3YV2DSDq@iw6p|O50@@o0xeA8j`DE%
zlK1HDLN51dsYi|;bzB*uWMm`+T3tPLs%X`h7mV`q@}M2b^H!9D$JIJIjwFD3@9v_%
zmnA@(5v}0)T1^S*_Kp(<5m8Y|N4rEp2R1M)aPOA`A2sslM<K&{zNbH*&CV})f6sQJ
z@z-V5-`}-X?NtHoHhdl(l^h`>D+^leerA@b_WO-9W=K?2R)Vf4{_*Lw{%5)GA3q*E
zIawWa*M(qk>!*(&5B~f6yYR<{M9=^(A0MAq`OkSKnL>*eEduR9Jm~%P{fmo>!P_98
zK4oonVr+E+%}gwa*;(}C+3fs+$H#b&96v7oR<_e~GbqXb`tovyMWIqqa4=}6(5L@b
zZf(sr%)4VTm3e>9(OX-yL4z@%0~&p18i5Wrvaz-O`01%PL&M6InxF+fC)MY3#I35o
zySx1O&(F_8`SgA~e}4AMOVGi2iBs+`XGr++;-W?2BNo4THk=Qx*7t)}ME>~j5Oi2X
z8?Q8|(Jo*2!|_9qlG36{CtbcUfbPXo(u(-~?X94&@Z|5H^+cel4;FUz$Dr-gpac5f
zz0)gL7!kfM#_|5X+N<|2Fz@;Gu=xJI+TL&MYg}CNFTdXH{1=q3Pfk_`tvUv+nE&_h
z--@WMTD!{M_pOcI{^;f9<%^a}v3O2;@a|pT*6iz#{{8)ZV`DP=tu2|LY3GXS>h5{!
zEZ{s0ZYzQ#c^^2EJ$S%<#}LperelgqMm(Usz)?|B4dLaR`?|Y>EiI1Sx+V4U<;z9S
zUf!K&TV3$sfg@<o{`2$mufLQ}o;Yh3m%6(8)Z?Jeq35Je?`Hgpnr)T~x~i!5oUz33
zZ*M^h*rm*JI6Nm^nO9y`c1*thk7B~i3ebE5$heo6R5e7n7(k2040CQ6fDR9>{`ThK
z(dYj^JUH0Ahr6>k($A0Y)HL1IUw?vbnGRVQR27qA;npM3Xq<iy)G1(S03C$$=H_Nl
z-3{8`I>)Z|mWI9^dxNrj-+}x0<)><eUiz_hhg+{yWjTYn+hleBV@EoLKmPey%y3{!
z=H&$e8lc)@ZS;1~eaaDgDmFft3aV+R&wRlM9w-ml@bU3+&@DOV=i9r_G)gt7{+1K7
zr$W#;?F_?*SH1S9r|XOF37Yfi>FLMM&d!dSzrXUc+Nr79%lA8mECNNAw0WLOP>>L)
zhaEXBbe{RL;Cr5%4;(lEu61={cYV=aYZ&7@%fxZAnlEV8^3>hVZ*OiszT!RK(v#id
z`Ww>E%V|vYI&$<VBZF4xDwVP+3gFzkV#N*fCEVa;EW45)?>PjH&#o?T0|~U~%-Zan
zHe{%E#SIIP!grvd)2-Rp58b^hySwbIlbajcuF}`jzW@39`g-rH>Pk>^2Xuh^&6|!3
z0}>82Fs_K%x#>kD+rprwUZCNRQ^~kiV}aJ`$;ilTvCHo%&-}L>v`(|LvlDcY0b*Z-
zN&Y<<HMKqd53*05JPAs?Nl8hc-rdMqBW0e~Q~Ued!Ta~)-|n0<M+P*Fq8qhEV8a=M
zox64&x_UMA3lC^2@E_><y;-K&&uViL6B{Q?5NK&>;kXStzDRH4lluQhCV?A8UZBN$
zGiJ>?1lofkvJf<kw_$@pOG^vLLt5u^@9qL^0BG&+=fAc#T0KKia@B_q1)x<<`tkc(
zdV6_KP1j%lP0Di;XtFv%R+39tSlDCIl5flOb5%T@{QS;E$AucDq^B!eSxK!9TYKo=
z-`|NzNl9Cl&pN%S$GM%)ab?J(<@4*Ds;aEktX+F?bGrYJU%w6=KHQw|^n)D~Au^!T
ziC%W~2A6<_#|ul2@B1kY8aD5B-j(!NL>4qWE^~Jyc=ml!0(g(dF6+uqDtq?qnJ{e{
zTjaEh%l+j+0|k}mudfd0KRe6RIU{4mfvLYrpPUfXnCb;;RDd>{Se3kBke8SL^78WW
z75m%2zr4);{QUgmCnu|ewgz>J>mNFMmUn*5C(doTx0ijo1)AEjvI4EX64??q2h^|F
z`~BYGXJ==FvUhcLHF$_v>Cv~hx0xA0i@7HnpFE(duD;l7s+QJ#>tkA4T3mN`m$&cV
zZx1@?9JG`C^fX=2lJkNBgGY}Zflh4YxBnCHC8YWD=kxZ-p!tX0<?CN)R$X5gYYp0P
zw7cwW(C?@@lP5Q;`OaG4HC5}z_Wb!TR<bD?8w-nxiT%0BD=2tT`Vh3+vf_xhr>A2(
zpKQU?Q=*_V&`MujVPpWEhxhOAZ&0ItqOyBJdb)arrsS+yrrC>Pb{5^(mMi`0+FI=@
zK1mI3Zf=iBE$d=;J1q=2aQpV{75;qJuG+un6BQM0eSUsE$X7e6zps0dSyf7KV8$pR
z2Ogs)IiMj@(CCI1ml+=@jxj|nG&MCl`up2^dwH!&UQGC25fvq6mUpLvPuA+d*|WY6
zoD4zt2$#Q))0pZ78a>{*b0?@1EyBeL+Eizhda7gIig1#aXyx45AqYBBvWb-&)b6sd
zwtoEJU~@rP*|9m6#h{HJE-o$$!q>+wTFzDc^;M{fsw#LjG(T6Mh6q!bq}V;i*ia7-
zj$?hY-90@#CpPhTPGVpP3k!?bn8eD)E2UDg@E>R=320*o=)&V&rP(uP&U|XSJ^Q*I
z=v*64PEOFS!ua~Xss$@0Y<4V2NIy5{V2`A+fVg;j`uTYe4>U4^wg?|?=LhW~0kzPb
zgF8ApRun+Dg-m3;wIwrn;=el&4mRKaFliEKqW;If-|q!wWqV=c3XOWPyAqz9m{^l6
zk(rX3+RDl;cHsW~_%9+x36heM9X&mu>kD&obU;~hcX_^s2-l9?ySwM52UL`=*nf78
zC1`VrhnH8A&gqQ1yG%hX-~ILVH*VePny1bqz5K%si;##n(wD$%UO-Eyu58Tjg3cPp
zZUpV*0qt*-m0q3!QkVlC7QDAb-G3fvKL)6K0y_Dj`diK!&@OkKz1{u&?ga$~lO|09
zUGD=r4g$PMFdLLn1OyuL_x}}}H*a3kv@X;1b22p_kBU!F;k2~01WjuC`SGcE9s=#C
z$-QNAQMeT}v%|(O*Yo2?MX&fg<`cj3)816Dmy}9MN`emWMVc-yetu3Pe&3!KnN?FK
zPHc?ZTcv1bX7+w#*40&@-CG+rY&fvMu^F^P?#Aug&@)U{1T1Via1^wQ^{tSQ5U6Ew
zYN|G9QK__fUWny~MYX@b6_k{;1g#X=Go_<rMam;q&@v?#7dDT}vv<Y)zwqHc=l@@Y
z41bog1}c`mxgiMZnf>|s8MFXH$<k6XdRtCo(8?p7!s-D_y+lDPL%3R*d}o`9+WJe}
zll7Y0*~u9b8~gC_V`h1I`75CNR#lo098;|N4Ov8U7Bs{S8s&ERb?_MI@UM(xpsnD6
z$B!vq;s;L@FHf+vv;?hDeR#MX)H?)?p72VWxqvp~%38IU<=z4v_qZsX>+_$V#h|?A
zwNwbyknQZ`3|k+UdqsR*;K50gCV_U%P3=yt{{F7ls`ORIJhd~&<?BHqUi0(m^o;B4
z=3eVgij9c@ZL<Q^3y`%c=C``r<3SO<x9ThC=A+*8_Eldvrt8PMy}q{g>mHw;^LD>^
zKtn9*^J|*Q-rjn6tXDc>d!Fp8>+AcUJV{|V@a5%Y(5a!I3!y(meXJ;GOndk4UB#Cd
zf<i(<6K2i?-B&r4S^wFYna!X(iZwMoAuY~M=+Y+11=q`6D|B^rd7ayM9Dja#DhRo)
z9&(^OXfc|yGPAUK9%wC<ev)2bXX(E`l_l@)NP17xahz{g>vDdf(6e7(UxQ8x2wLfq
zl%xcop4Zv?=<dQT*2T|wq|EcyeB60@y1ufK64Up0cbiwQ)&}hoFM4|FW#vMN9GOMi
z`)i$#9zB-$_z7r(Vy*KM`5f?qF==)C9MI-OrN0S}0}3}5URk<yDQI&w=;R~NLa~`M
zXO^>{nKMV`%8EedW_JE#dn!M>_+MRp=S~dhs9qZz8SAn)4q;(pcE4UIYlv`x_J^gO
zo+fI0aRF#9;l;(ppkcj>@mJh$MMgy>eR^_ohH3V+7n*FU+S=S(v#x@+MSQrKKEHEb
za)FPp@5ai{X&NG2z321q?h@r{J(R)sy{N407`uE8=(6EG$FHr6<+iuC2Mq)m8XCHN
zEdS8-;X%`%sk+f(pP!utHE^N5jUvWhyGmb!)*Y=`qjM0vI9|>8A~U#Q;t|^`Wg22P
z&$ikOw0HW!0miA;o+ddr1ol>cZ(F`xT}(f&hgaI{MfECyckkXA7#f1QMTu!?)4m@*
z^v7dTi*q~Q%S73!Dxf4>P+$P6Xg8&vK6LS-;Id`QwAN2l;Y>e2Pjt%!o=Eua0LI8^
ziJ;{RlkOpn@>Z6wsQ>wP`+d+bIq1}nbLaHle*_(KlYf6-#m7gk_mWRf({*+N?SQ)n
zSp@&WH{m`gmTrKzTtkLN^O>YU%hV1ZJIN0^PhojNjtqEcKPE?}bbkFmOTD-~9e;m+
zUtIY3SV2L-iRyD#u87qB`f~8z-s;|GOkaNdsL+_|<>KO^U}`F=8@=twp32V`*2nKJ
z-<RI?_~K&sg7Wh7)_V@z*pho&?Cq_s&a=&OFD&zwUc5hftJ$_~+uZ7BOjnyWZQ7rC
zQ~I0U$^QKFvv{jq&Gfr_tHtNn|J!*gdEUHv3=JETkAHgf`TzRZ-DN-JVg!VRlSA0W
z|ID5l`EUBszdxVPx5;Vm=vW~Et!Dx`K?iHFu(Pk;v+}vAu&^-boZ8FF{lz!<@I+3V
zID7W&?}d4J>yG_5`~T0_<^Q&#r(U2%>v!(R=;`U%?483^^7U0H?nVE*gO~e#d>0V)
z=GInjJv}|G{Ckx@KdIXN{SpjXGIO|%H{;e8%|(kA8RXtFVPR)a{`lx9lX&;RV}ale
zy|vDcQYpJ(YXMxr!qDwyR%U#AIYEsO(C*;AGH{Fk%ErPMz6s!kg`c)3ALnCXVR`Vl
z-`*`NYt^mKpp_>c9v%PMIWKL?jgE+jSl~TfPr{-g;hv()_Wb+D-rnAB`fsM1@2nSv
z3m+Oidw&}w2s)+AbCQCmP)uy>#cjE__taO+xT+1BDB<RA-oJl;V64HKZcw#iWF++O
z-@ir6C0eY@->s-Q>+9p=Qd6_%*6T}`E^R1#8x^uXE_VLsmQ&}>wN0Hm^;GhD`*k5J
zCv|wTb+U^;S)Y1(8fZARsj2A-=>8rj4-bx8+w=7kBn1U8?rww@Zc`aH={)}Q^mNqx
z{Ut9a1^)e{t*57VzrVA@H2<Cr=<YR82Xc0m$LihX??JOe4<A0XD1OER8k9&lzyPZJ
zckb+*r!MlIZ|U8o-qS&IUQ>^Q#%`ue5%HO8CF<P9!^i--SPyhiHz>ir18p4vT{-nd
zZ9~3CICzTS7O2C#FYq{cyEUlo4%+?I2iggL?tk)ozr~AeF28;FzMV<r2%~7hfsTgY
z0<Uf^4z^P(9CMqPI~gx7=@mNL5cpr9x1p%X&G&Zau}TIjzKx=y>C9Y#4v#u3WcoW2
zo~+O?Vi9F=eD(K1cIhfcO|F%@7ktat4PXAME+X5Ud!_D`Qrpmtk1wn~(C7Rr>3Cp#
zV4&cx($`^+D=RB4wY0Rh%<$L)YKEw(u~mP6SNpP*tCeYz%FDNRgZ~HTcBjtT^yW<t
zXgP+br>BRPmy?$l7wF!mUTJfuNh+W{NzUzjp?piezrP=^ZyyiJz5o9H{y2UAAJ)su
ze4VH3#jcWN`1<LS&;&o7`uchn78cO{1JKQ*IXOA2_9|EHulvig<nlh<=xqrfA00il
zl<(oghaCL;>x<?(Eo^9PWCV4<6qZ_m)|PvEc77@>EHrF*?tHbr?jLJ#aPZnx;m&UE
zE88<JD(%?4`|#=0-j&mTfGQhnYiZDu)V<Z;1%!l@EK~&r10Nq{ECCI)EOI+=`?mD!
zYipZ(dwD?zt3Blp^7irqoj(Fv$Wd2U*Ay&dYUk?e`r-5E$Fr+mECt;V3hJ3IcJDuS
zsFfQu1o2e=0yh`es=qU~<=)ORUSzPxI^^u9&!0ha3{#)`&9PwgoMZqRPkP?YCmZ#8
zcHJzkGMPo;{eRo89PJA>E}JuJ<KruRf7@0hZg@Ol*NwugV_?x+8y^dp@|4L0iCg#m
zdh_PZglW^l9{)UV|G(#Ye0^+p=aH_S9ue7v7cXspYW4r+(M8>!lhqg*K-URRnIfX1
zuC8opDcR0154sA6kzsArR;R?og(r46few@Vd4F^I`7q1LDxT}7TkY7nld)poidDN@
zeSdx1In$z0sp{)1(6Cv2d^~7ldqHVw=uWpuDqAuxGUf02$YxdgN=0L(#N}nahqq*2
zUS(rn_U4AxdCy5p%)3)|>~N?(ckY};$qRwBb8}Y8IMjcvy$KnAd~``oNoi5l0|v+d
zrt*is-|vG)KR{zJpzB-uWUZMPii(N?;^O)iI=4UC{eGYDoS->x-sGgDr?37~@b6G7
z_mAKA|MzX$WVGl1zuzCeeG{88q2%i9{C%C?)Ac(09IgBo20S=9S^dWD^7Xg!^{!5j
zpYrKlfGKDn+1~2!A@i(jf0_9B`d-{$UqAJEZ*Om6PR^RM6;{o%&!65X^bmeyzC;fa
z7d^7e%ifr8O+K#Ziyk9a`efTp4ni`|eRuiVmIn_KK$oNZ`0$Wn9{=j8Q>QB0*vK63
zlRbQ_SDJPCm3iW_{jZK4I>cn2f6t|zPu9i#qGVcHnuKMM3h2z0Idf!GR8$hq&N2m+
zH*$708dmcJ3JVJtDZg0LD{ZbNzVyQ9`gCgx3x<li@_c@N{u{S$arrHkZfb6Jb-xf9
z6BA&r?AGJp=EervlhM<|6A~77=-fHJW_JFz#>U1M6)r9=y;AIuB@j}Lpc`aBdqZ<_
zbo%6MyTF|x@bRp2wo-9%aaB8gf3%*r|1Sf&#Hyyoh5>dO)8*y<pc~9VP2Sz*?~ncX
z_?T5)H5POjd_`4N($7y%LDQO`i$AP{UM|?M!Qi4`iP(F-P-Ay@cNcf}$D7aFIiH@U
z3mU(jV_Plue$Qt<9^TM;mGZZ@Oe3PBxxKW+tk0d^_;`ZajeL*THx{PJ$5%>P`@Ox9
zpLM*?c~-)4#nO$Buk^?+PkUprHTn2TS!=$`CfW8YNBb7<J8-}uW@i!W`~CmzZf(hA
zX87>+t7~1IotBoCfPg^2+t{$Lft8h(=jK>8gU)F#eSK}w;}<=1=EyvG_UzETdva%I
znF`CgtAkG5@bvUNwR`^kU8UTheus4a9?+35NiQxeT%^qPG3g|0=+}$x@|}GPHvf=X
zlJ)Y^(nZQIboBIASbI)-@ZtrBySw|vz>bcNSt6bb12kOP6+oqn(%C6fr-J&cpem|Q
z*1GM|rJ#!wTV7mQDa^#oJT*End`(2-g$n^7>p{ymZ|CptJ>D-5+V@cqbjegVdYemX
z>e5f|{XRcCt2p^&$hwItoUX2}N{<9z+DJ=FgNFLK#dHGf%u8MbfW{YFTU)jAFWlWz
zY5eTm+|}mw^YvnPwSZRd`_48iC@46vv-o*HP*4+SUDJaDjat`l-Ms0jH$D0CGT)|4
zujI<+Jcr~1m#@b`C6LV7jradZL&AE+KXAFU*s^R+JtSWUn9f<UMCHxR&F)Y6W`OR6
zZR3?zvzm1dbXSs9>8q9<J1kB-ExK6P(%swZT2NqMWMstP@U!yd>C=Zh1eFEE#Mtul
z^ABoneGE#FMMXxFCQX_!YgQNNV1cl(u!6$Ez<-h!1qwaAy{_)6SyPORj6l~wtXZQY
zA}038{&=N|=b?{}kFzelth;mP&WzjJa;H8maJjm(?r&9Z{rZOIpr&-kig!1TfSb}%
zlC4gl3%L`1e|rn+=gQgDaBy>T@BPOZ>FCI)qpLf$pI_Fh1$4PdSy>rF!^g+RSMOQb
z_o9_kSj}OQ%0)wu<7a1^^Z)zz@5TN7`(J2SwU@WAioCzCw(!#vPZt*#1#N9^KR>@2
z=J|0`&2`n))Ijr5c6N46lV0(a%~=HrR;1!3??(PAjHF$9xG&hYOy&}cHQ&l^+2!v*
zo!M8fw5;0BJ+?hF&${A+!m)mN{`B<pAHRMjU0mdPYV)_Zw-*;bKiARIb7eMT2|qu-
zgrwxb<Hy-ohp%tjyxI8uE^g2m#{?Bl(4C+@YKKouRL=e@Q7fmSr>%YX-{0S$CAo_h
zDTRcEt(xOKsfAbCjKfR)T%WA9LFuay2?+_%At?st=HjxR>4kw^T6%gbZl0ZOZkT#X
zWXX~xS8n90cwYKFKUzRgFtdvp(v|N$va|R(r~~}x%Vqx^<?rQGJi%Qj&=lRtlb-AE
z&q+v31Z|*aWcc^vF+XUd!tDHgf%C#cLKZAq<P>6aDKRiGaFKF=@`j?PUVk3T|94m)
zx7VQZQwpfe->`9`pscrgOKU6W_9W0T7N6b)Oj1ew_vdHmy1U!+=imDqbm8bx)^>jR
zx|gQ!-o4vV@^aENp_gjlaviC7skAJcb8F-MJu;Bg4XuZ#gUc3ZNmK|biC%sF@}*_}
ze*0s+((J;*!WRom=Iz^Gw_iX`t}pR$o1&s3<IkTzwU}QpJb3eFO?dOB+TY(mcdTzH
ze(nca#-*pHS5R8o+TG2)tMs*+)jR`LRn-Y9o|bohJTeTOI(KgG!^7>Ms|-Q?8PG`@
zyGpY~L`5AJ1}w<Ez0JVXR8%&&<HCgi&{=z+7@RtF>I)02{_dc8j~_KnpKX}T2Aaov
zyZ!#5vuAtf%Y$xZ=z+$Am5#PHH)wa-x3{-JJ99v12%SIA59%3Lzu()=DXa!sj9cRK
z5On=DXssovfsmA>q@}GLYUUrmw@Ng2SBc<^2^~_KUteFZeLv#o)$n-G8RDQ}z$Ygs
zgI4~Oy}i}hr@`}{&vjPP@j!lSK0#9zctBq{-skMX+X*hSmvENJeBJn1AkZ1q<O~ZF
zQ}dt4V{B~PBW=$2@83Vrol@;C*#{2pdk&f#ovIyvts*Zqwe`-O7+p1?*N0lULBklJ
zBK*md6cu&#<lEbFH8eFFmo8O}iHQN7NDDfE?ZJUY10y3L*+}h4lP1Oen(<FpLxZET
zvJ%uz?U%Dn$jt1tt^Ri4=1s}_wclkyBd9-qR9rM{-BJ9U@7cMzrymxZe*F5|Qctg9
z=aVNX(AhQt+18GZ6`qqs{=5Y3BodtH2kPeE+?;-KUu`w$N?cIA13FzBbnD5BdwZ=x
z=XHL3e4N`)>)zkr-$5s@%&{zHJ9g|C=zwn~W@bi))YMea_-svW?Z&LDS_eHn#cgYT
z2>kzX+`iz)hs39MJ$IG8?b?`pJn7q;n;BPEO?}X^#2eHTs{LK|=XL!5LvyXm6H-!I
z0vEd-Jb#`)E-r4*WTuHyHwr-kJ}YVe!d*$n6<5iBo4qUXxT5dI#{sb$9}8UNxAwcc
z;qioJHwss*yHS|+{r>;I_dx^P|GuuTR|I8ntCEKG>-GQq`D2i9fZ^iD61UV;)qn5*
z|KpdnDgj*#<Z@haRqXCE(9y5Y&dzTC^QR^vB0|B=POfOD48w+mgG``${@h&arpaBO
z-`q6*bN>Gy{z;Q3Pn<NV>B*CnJA13e&(1P!Uc6Y@Z?2W9)uMBrzP?9S1}_&75mB+~
zy0$g{z8vV-7tmash=>Si&b_0%`|yW{hZz~<Yd$c3`urJmblgGDt@$4w9IW{LcDtaQ
zoSs$Jx!v{u?X1e)toZadA|7=9;nP!7XIK_5d!b=<^42Y>g9i_S4&8BaS5#8Unq<-7
z2b!E)vY3a5=fc`(bI{t4<YPUJ3l}c@)RX^aWn5sOppTDFLQc+_ns+BBtAkGb+Ewzh
zX<P1XE+6+@FW%kVT~J(n`0Q-+i>t%+L4AFO3G?Rl{r`Laf9u+{x_<NRdi!Lpx%|9#
zxh)J(Ff<gjE_-v}-rnlKhzJg2W8;eI>ci*H^DlPm6_TCkk-qWq6<KS(tE|6yud-Y7
zO-#FyZ*sWLx%6P4^VfrY&PycAWX^7Q91y$VaX{^c$5+;E+9Xt1SO|);q~zqln3x{W
zYQj@fG(UX(+PZb?))yUzo;-P?U~Vq{?c2AEi;G%cSRC@5V<GtR<x7kDe>PoRT_J22
z-rwEbzOVLo(wiF_J3w8BP<2ol1v;?p+uPfP&(27COlnC#Kd-ZIX|a-$l7N)ds_FBk
zgM))Xr#ON7Z<Upnv&{4RY^%Q|+}Tmc(9kPw{^<YT{r}q+EmAt@x%K^(mBBMiGKIdq
zz1<GFgt%|<<x{6mgDObS3g2hXo-KOJar7vw{`dI*U*j!mei%%eJXvw_NtffG*eQa?
z4rt?)taX`!swyk!GLIHcVbBrSJ9h6@*4FOMf1_B%`seRo(19#(?(GF#oDyaUy3(<x
zrUrCPpNqRYx0gq+V`Zf!sDTSQp!~<j#|8!l4z8}PFCtv5x@Fr}ByPNaVfCRt=OuRE
zq!+av?{i+yWz9G7*NwssDLHGty;^T9w*G$HZ!aJq&~SHmIdjFnjH7q&%Es4xWCbmN
zvY7kr$gyKe78Vkcl9CLdLkUhiEqe0wY2uL%LD1mm_U+prOu03E-aI~ab@dxJZX7s%
zoLx~-5!B7;>FL>!c$iH?gzL|@+xg(iEcErMQ>Q+>UcX;SQ<D?atM>H`<>NKazQ)tc
z#@n=dwYHLy5{vp(+g~;f_drvFKYxO5oo4_o8wIrjZf;6tXxLf&9CSYWj{5)mPRxi3
zyt{w;rOTHK-`+9>)f?;gev6vg80k4lKv;P3+77FQOO~+Q-Bk)2f_!#vuC`U*xrdLM
zrr+M4FAvImAt524Rq-z_E%n~o{30$cj_H!1prC18+tzsSK6V!+*b1Ptv&}cw{w{lS
zV<Yoyvs|ZkKG_EkA2Nald?vk^;q>S8{QoQ;{`g8xQqh#Z4m$OPSF&4bVe;`l&;cQ#
z_pUHA%$qmw$DhyVLFcD3o?NjJG$9N+Mg|o1hK7O+38|^7W+D^&z+C~py<Bh1zi4fE
zEO3?g_u13X0gUxb)_j3?H#`Q_;(NK?Sb!Ali3ti40<B`St^T%P!2$-*7{nCKU{Hy<
zHhTM^)2F%PYrjs7yA$~3!NFz;`#PIBbLWC~MY?v2X`a8eJ-`3lTx(?`qac0u3)SD=
zbS_z<!otP|+PKfv%A_5(hJgXp**iPSw92$bPFi}kjD>yuKbuphPcID6xUeqP8noQz
z>Q&Ko>(+rLIwnq>_+rPB<|jp#d@>dbWE|#Om1=>`9|WyR*t7|>6KRG`<)#NyZWVre
zb2IDz-771D)t@|ls;IBO{?tsnf7Yk3ToK`FWl~d9TeSE^%PTSQ8M9{}K6<pZn|qaE
z;vtr&_2=i=MnCnLq@p3h<uPf=bZ*Cvj*d9id(bPn1TD+o$!yEN5867SsIJZ)78ds7
zb^L!WeSQ5sU#~@H+}pGBMMqR(LIQ*5B+#kk64KI#4;)x<t^Xmv;7Y4y%a(yw%Y69x
ze13TKzO1WSpxFxzP0fo%Mwe2#TA9@S<{apgwce0_-%dnSbYbf0X%gmnGN77$XUw{5
z-&K`<nS(nNFG3UcgDN6{y-{z>{~zmf21Q$Dmu&lst4YUynwQB`iQXvm2!3OsU;gz~
zC}=hsblzlHnVF8R?!(uwx$Eoec_a)Rp5Br)P6J(p^7H4<rb}7p7dSS9Hs`gpusnJG
z{P3YeOdmgfoN)Rn!@T=zD-XBvo;Y_-Y);6ULx-I1>?mZOI(6!Xty^1LTU%dvM16ns
z+kJc9-6@Bkty{P5#ogW8AEfkl+udjU`~80X@%8)vffj#)2JZdm*&IAG(^ybgn0cm8
z8>mJ;JIgfV?yjvbRxEJ_4Hbb*{`m3ZqQxBPxw)~=T|s-{-)8^l6jr~oEAPjLhrDxI
zIyzQlK7x&SghWPmPFD8^<yCMW#I}khI5-%zkH5rZ?T*sdVhjtiudmbU&;I<VYLR$c
z&Xa#nr^kb;qoT05I8b|Y;hsG*`~QBMy`W`@_qlnt-LlqY590s-5`TApKfklHbB~lM
z*JO47w&~NS$L-xYX~n_~k2gFH_`C5wxD8;cQ~TbW!J2Qc)EkSC@HZANyxp?xvh8ua
zWiqR@%jVqTl`vqKt{3aHIqfXy>KV{B3JKG!kY47W*5&V7=FgYc($?NOC*-$}j}NG6
zerAs4=39(k&dxS}eA(aLH8XSNgC)1b<>dN4K0dzKf4<$-d7y=BhK7cxc3Ya4?k;~1
zIt|~d?2U$%*WzX8nP0ff^6>L>b8ui-vu2G!@-dzpH*SPfyML+s`-{`V-NnUa$$n^!
zaOK3*Y15R<%)~$wI5|0MURb#Fo&w#gd9V8Y!ub7lplyIvUtTaWctGy01)YZu8ZsAF
z_Y;{j#f6KP_vpE~))S{r1r2G5i;MsG`Sao4@AsT<Z_9N(uAH^$Mq!7^;X2T0sNyBN
zZ_-L<H-ZP@I=1x7wtE!6u~?#4Ci8XY?%kjTc6N4l8CO?@uDw2e%9IBOo7t;2Dl9>?
zio)MA{Ayz57Lb+gwJv|h;kT-mjg1XdW!Kc!uC~3uHCw!<w${?4=Q(!}s4@HR@9)=7
z@2-A+X6E8=TR{WIGmX=Klrk^au|q;lP0dt~`J#IH`+K!7cdB@T4zxIP_UzUv9_4?2
zzFxd*cfB?!#~;}r3~JFt9fOQzDrJ4);^Hd!{q3!k`JA|2C7jo;U90+exN=o&NQlV3
zKcBpxJbR{9-?%V91JoD>9SHF1%E~6;Nf~TxY%i{^7KdDZ%?>&aYGQ|nKe)Y^?;-of
z!bOG4nh%s^uN>@ic3A|LC<IA-(E_!B@i#JFXGuH6Z_kqj%{;36&&#l!`EDnu)dm?N
zc>0N{Ht0HIR;}DL+xmYtPEJmsW7{rW3i|Ws^Z5y<pPo2<+S$Q@fr*(JG|+m{aO=4P
z2Nv9V`09U3R#q3NyRN9H2-;>UHmP%a<>$1mcIKCt`CfLCx_js->nhOUR-ThU=VhHp
zG3t@A+;pvfq6+8ne);Q8R!T~XmbF7WOIKd_&b1PK`SPWQukYG#ca9!q-CO+~v`>7?
zoF1v}t}bwO4bPyUl6~RAg%47eaD(pbGrw1{_||67!tL+x?w&Y#(s6y<-VdOIZ%WNs
zm6S@s4Y>OOxi<<sJVeT5R`Hj~tm3ui6YM+$Y3XfEJiaho(biVh&(9BZszQH1KWJA?
z{yiHBNy)^+ZM*>*B0t`4zyBre;K7x_%O}j3!NCx*B}4F7zkK{#rJ11N641)5=jY}Y
zetQ$CyZnmn_xJbRkN3$=J<a{4SMBf<qnT?MC%xEq<w{6JMa2T=c0SO(Goa&qFM-yN
z9=vr+3bd$pPRMW2mO{`<z-w!xK^M^_=I8S>oH%jffWQ6U7SP?Z_wUP_=iLF7`2jI8
zJv(+-?3KB;y#DbcrqFfk)=g011g(iRF$u9-clPDw<y$B8b#$zF`4Cd}37S^L?kWM5
zrW+FuHf5ckt{2<&_4Re_`&%4cLd5O=d|(b+8`U~xipZAy`*A=29BgI>^)HwE&)1s2
zdFxi!tgKb1N?lxLB^_5>)OG}t1i_t2MWw(Sg&ivtH$J{{_Tpl9&_Yen`sWoZIIiyX
zjf#KoQS<baD5wHgRCIj$`O&*~eWuyh7L>og$8<UK`lF-W8!J90F`R$j^=s4i%lrTR
zdVOP4s`q5MXTj6=-DjM8<?+LZjZIBVOO`ELv}1?Fv}x0{ytzSht}k9>q@<>D`mL(H
zU-OxF(c;Au=gjHZmV0~EoTpEpg3gPr|9$&DXvaEe=k$XEji7^PPEJ;5RaJ{UaFo@>
z#YIIZJO#WJH*oRy2M3#{|6|%4ySwbf*|S%ZlrDuX_nUj^#p55$m4C|~9ALb0^XAH$
z`72kfIN&Z{%QDla?ZgQW3oENfA08h5@oM#Y(0K#(e;&&-2@3}XgT|$ymF+~0Hx^6y
z%49ByK-1c*1aNn7g}#~^8)&pnMn(qIu3i(pop0a1eE}LG9lgD--{0MR`1Y-?)iMJ<
zKE96re)q&gMbHWCr%rj@xOMB$p+in3CTqF5xDG9!U&qzz#OUqqy(WIYoUoct0BD9_
z#;jS3DnCDK3VNk>?{{BT@wYdTI+2@L)YQ~8G&NTi-P>85erI>Nzk|_7P$U25=Jaq$
zJNAZeZ*M<d+;4XXbpD2j2n#niH|Uhy`v1T0v#N+LUbBYh_xJbVdJ|W!SrcM8U4>KH
zEJt99-<&^xYNkw^_UKrzbm+daLx&H84oY6`KOc1My+cHV1n5RA*KV=G!h`?yO-)6Y
z`^|L<2$=9f12i5k1RW1waq;zyjmqcd+s8i!-I?>{llZcbsk?Vut9S<4g=vUr^=B_y
zFa6==&eh@TlYV`9sdZjeMFmvqgEspv^P9`{;HR`1=wKaX_r4czXIFKA8Z?Tf8}5U;
z*&U$F9>fkQHalDrk1Li!ip?wAOI`-?$k|AEdU|T;=p5Nq`ufB6{eO9jcFOGk|Id2P
zoH-XjXAm2<a`5vX|MBth#pV9;GiJ|DzOcYi3v}{`qmK`dle06c>J>d<Vc{7wW-u^-
z4$$G|=AJQY7MI`B-#R)v1)rb!mb|#&SR%6a^}W5jqt@T9SMwCQbosKh#>96<CN)1h
zPTk#IesPg2x9-x5x|Nlc8oIh`KknJGMWnK_^3?IUR;8<qTJDCVrl%)^7Al`P<8peM
zF6g?$EqQmPTwPrQG(<9PZ(Dn>ZvL}JO}{J)AF((&J6nRf*Gm-n7J!dv4P5;E?b}|^
z*)o?e3&+L9X{B%62<mknIWyCkb*XafqzMxieA=;Q4UeOvqlTs?Xn7at77B&~TeGi&
zmY9Jin?S2%1*evH)YaL6F1G)4r&Cy6!Bgm1uk`Xye?V6+l)sP5J*K=!tw*-~%E3Bk
zQ278V5I{B463sFhC81W3L?1{Z@cz}+;Tua{2AxPTddiSeS!u~|;Mg%X&|Zd3si#4w
z>P<9k1(mCB-o6DLXq$CjKYm}&(QfhAXBmFYFMWF}w4}ui)QH}>bLWQb+d=1@xg5W^
zOVPP4MA8A&2Ur)kw@c2pN+bUG<;#}~|Nbfk9dve}fl+A@*YhV&T4v0UU}0kmv((nq
zbPNd*0gaU_%&h3^>x<Z$CAw$t-jBatuU|bUc4rZ2gIrjoK+)S<rX}z0MBX-R<>2B1
zU5zqn(xeNE-T6Ta?9b1$EhsBH2D;4=w3f%tF0RB!amNnO(i0bGYg5p)s#{FgsiwvT
zbO_(StpfZ3u(bexe{0t#R{i{x8ndH-ac}kaV~>t@vo2SO{qSsd{wkY!#_4=Ly}c7>
z&FXq~cDDBX|F7f!clq1>WXa$6Qw=nQA*k$@VXgI2KwDcIl$oFIyu951@Rchfe}8`u
zue^8ThQzUB$8PnwyZB02^Q~<D+h%eUQeaQ8f;98Njfs`bvh5~E`xe^;2M0g>{~xrn
zDspq$iIXP-=S4?Gg6_^<^yuZ5rY5Gn|8DK9_^1@NKCXAm784Os(NM`dlT|op&YanF
zsZ&&1y8FR{gp`yN28KtE9w|&eJ#qT<c0pw~1sxrpd-v`&1)J^3y}fOvja|V520l5P
zj>Yc%pmT?{(%t*zTGy}FpQaPJ=xm2o^2J521?A=Kpgk<LwTw3JkKVj_6SP_pbXM_%
z2?7T-kAkAf#>VEt`gr>tJ9i$ucTbK1w2xqpU9A*o@b>%tdj1DL0}4Um-7l|iwCUQB
z<HsLQ_P1;7?&jv=;$mQc^y5I|XO}KtHmv@Z1G;LmAn5JmM@&jeN<t?cN*KU1MvH!B
z-Q8sx6db&<;Gxr$>C=<X&$9)cS8?j}X+a^OCeU8J+*?}&Wha+h`1bbp!}sske_A$A
z9CVk;`}grrr*|x=mywkPt#ownmt(B>cY5~b^z$G;pR!ipQvjK7>+bM$@f84#e1m78
zAuT$!8{h$NaO}V**XG$)KYDd_^{L~`Y&-}0?f-Rjb#YCZHZAFRpKQh3t=C!9uB;1Q
z?gyIjeE9GoL&M(c?^^Qzf1aOXS^VMa_4vj4_xCjkcTb!#qvK#R`{N4>ok0^{n>KAq
z$j<Ken``y(+S+IXW8=%Wcbm%FR0x2M#{2#4E$BGfR;PtF+4uL^T9v=+IdQ_Hk@F}g
zC+ETR`L$uGKV%qeY;8g3u;|3>2yig^IA`wM!WS15WA;{sS~l2Kf6MvvHoyMxWOaYg
zIaqu5TK{QaWCm>u0Zo?Oym_;utIH`QL}b(E&4!>Wvvw3X{@j^)Z;vIYAYbY|oy%{n
ztg5Q&i)(A889*oIOi<zEm$wU<w|mEq2Uk`GFM7neHS4O@l&MoeT@TPIRM4`!+FvE0
zwpIQAf1r)$_w@8YXDzlJw}uvllR?MV>cs7tQQp76N>fiS>}JLP`JkEZprA!ZU6yo%
zu2svppiuJuo-F9VuJU&>DxQb_{QSH+W_SL5yAw}~7&SXrtV}w-a97fP&`hYnL=Q+8
z4%9VK66%y~f7Jz@4J~|pEb;29P|$t!7uQ4@*L=MiUh#ZxIcO!6$E21=kCH(9xl4T3
zdU|*S?9=m{)Uvnwd(!)Rd#}d*{`Go&^4C{aZ}luU1|5iyo!x!qN{CJEFA>n$>>Cmo
zpA=cv{rwsan()23DRogY7wB{k#3TslmXlLEH*YpJ%ekSTHYWkJy7%|Dx7jw^H*5f%
zfwFam$MzlxLncW{NsID#GDb#50g;iM*4Eabx{!_SS1tch(30G@x3(@yelbTccGrV*
zbFCQ|l$Di1>q=IxTnQRoU{J8N-Fxe(@2>|(A2opvEdKHFv4@uz6T_Zwx3WR&NI<=u
zr%iLkySYKresQ9(+Gz5m$&;J!+=;ny`}ShjZm~s=C-hanUb`K%2I26<iyKcpyFO!v
z1n3C4t9h%{{$ARi9}hYbL{L!h#HmwFlP3#<#=IMu*;mC(pD}|YI5_ynj~^UfUM{|p
zps6}&F51-qjs$Q|QYjX)zy=guEAsE{shnY+Kkw7W8yk~BxnXbhcPF*UiDzaQf({m#
z5wN?dsR^{Z8MM0m(j_6#)e0?~!r<B7Wy_XTSzlpi$jr<HU5N_1^ZU>tCx!!?)6X+7
zIJfaQIyf*mIXOLe`BKwpnZR`Y_+zK0YG>PQ-?YgoFK?Zg@Jl{xYik!**Ti36UK*I1
zhFWUt>A8i3h~(tvvM#;MJ4pp}ZgO8=-=f6<$_mp@gRZ4%X=`I*0PPljdV2cfhlkr&
ztXbodlA@yKKTpSEsYOi8f~<3MEVJUPzrDH1=Hukza^;IBSF4kv735Nyz}lk(M@N@r
zgAQHV8Pg|ip0^<Rc;ANY+u0dX($XHiySsbC=FNv8n+|j>GzA4;YJ-L+zDX-7W${2J
zFFHC_7$$)7!f{2V++C%w#dLIZR`Hw?0;O@C_<b_QX=fUo7CL->c6MXw>#!d`e=;(F
zdNv0RI82!`1=J~jdu!|AKR-Vk=HIhH9Xe`Y<rY)0vWlv_o>VI&EZht_69Ke=zg@m=
zMUCwF6DJ%(LPXx(+1VVsyDT*F*8+dgoiUIJ=|#IHipIysGp^i{eXK`vf(j>SMNwlT
zW7?S+fv=ByfTvb76zAss{QLd>$JgukAG&>88nnt_vbw)P@iU(zM~*nCO-_7sV`IeT
zG~TG~dAe3wFBzDbo2_E?Jtr0I<Pj7Uyvhr2wt}XD_w3yZ+RHdm*&Q?$thN7xly#X-
zijibeax!RbMo3gt7q7J0gBKSU!#l2^BZZgw&*u{s7Cy+?+2Ikt5i}!|-_hYQ9n303
zVo8O$y0RJ>8GZQiG5O28yV7ZCX^WI6@)ebofX+b;TNA;^@Z$b{`(5SlLGu9&414zO
z1r5BUq^5TEXdXGzDLirByuQ!R&o5rF!XuU8@4da%FK%zw2W<%eox>Q|YEkt?qp7*M
z@aL!0sn36ZdD#p)#0qo``V^lvv(599PEFDD@bp|+_Ce;t{KSCl>}&}M2?b+gVK+Co
z4coT0sd(!DmGGPdI)8X+%aZOLI~J79s`)?RWD4&D(3soH$MAk<GaGNy%$brxLPD$V
z?vN1_Y~+<T`_TT`#l_{yiVcqi1O)?wK|M+r7hgeZKEa6*?tL-`&&{<?%*f!VudhGx
zv<P(Q-Tb;=nnguL3=GGP9h+fYt_K<_KbUzGwPmt!)25)OG2lyJxxCc<GBPx_<=ySN
zU;kgWt*s4ofL*(M9f!5GHG@N1ni}Xh?FSDM4tj3YC*1c>NKRI^S{1N8|9)7cN^)+l
zuEoR%(6S#dFD{TvKn;>RclO+R9rs68d6i#bp`nkD&#Ri{ua`A|%R!In5?y=_pphb%
zka)}@0<@p>s=PJmRw7f^Hx{6f5!v`yK(Mp;%?-mIS!*#jH#gAYV$j(-rLV(4owN1(
z|5?@4)C2?uHa<SypZxODQqUz*%lzl-S#7(fs;2hn?e_a^J9k>j$jTP}`%`)1X%VQe
zc4nqAXc5YRMrPOJBA_w##>U1|){Fh-T8SFX<S{ffoNzLQgNNtHj>5+*%S9HapPvVs
zyG=+?aB^~55TG%oysNyt{P-->>@RgcWGd`*R=szAUO#QloSp{{5<t5iKxJ6*zdw~N
zEiItwx1~#$f=-=RgtQ798W>pE*gz-EElM`qaeI6I{x620!?4T>8RmlOiVi8;;NV~p
zaq;UF^QKO1Eqi+_(@@Y<?RdZZ@oBozpsVW+9dgnT;hI`pd-s!{i_0T$mcgERUgiJ%
z^z_B$<@|ngty;};Z-H0RIyf-6^++^2xASSfmxu}sWK>sIUlYGSPM`gPv$Jy|;rcc)
zB_-r(Dd-HN88($h3<^q0OrS#xTwPl`Dh^p%Sb%0@TU)_9JhZg66SK3qxw*M7UTgs!
zhq3SHGien_?-g`x{_NS(pFVv8UH{}W(}<OsjYmK>`1P%Ax!v1xZ+G=Ayj=JDt+|Sd
z3TQqNdT{P!b^i$yCo)=FTW`s@=v3me*4x*&wY{C)s^mpO`Tbh)ix)3~m!mvB*vuZW
zziw|F&w|UROW)tyd(HaLe|67E6Xwmk=g<jSA7uuslNUdK_^|QCi;Oe#Y<Hi!xwrZ|
zsNdHkYaQlbbg2}yUUPbU9jCUoHmHG6`}>=yY-dM@N2hGN$-z2j7nfbog?I?omn_gi
zu!9E=W?Wvz%kThnx6QF$Y0$>)sSj10ot=OD{0UmXuxJt2)M?Y&j&_SL4qY9lp`*jX
z0J<TI!64;?01FF?f{F^uym|AKl3%U)A0x0x|Ip#XpjrGckQ3-7Ofn{%`Z-lQTtHYD
zv`^NN^XSg9w^E?<eB<K!9Glr5-rAb2p|8*Wp(esiQIU~f-tNe=v$I*%ukLGTU;rI)
z1v(ntM@?APefgB>(?Ju$hK7a#8X^-^IOolq2dW4^{JAe${QTU}CRT11^{e}Sety2#
zy<g75*VnbM&~VYBMIq<f`Q_IcO<C8!W5<J?7#+|B>F4J$G<^9|0y-;^kB_fvCr?X9
z$BR(JNSvUcU_nvQp#_f34<0{e_M8MdDjU?=kv7W#Rh$tKGhWPC(!B5gzv>fDi)1W|
zSlry)7J*92m7pP{4fh2EC$57o0Yk9%O7Y9tG)$d3_0z_sOH~<G*nEG!`O>AJwW*g?
z+uGVPZf;U#Sl~O`%)rP9)GqmS=h`)~@bz(`qWvXT7P)pO<mdO>)&2^p1|7Ab6SpTq
zpZ!8}Qxj-{=gO53P?!DtJn>^alFfH_mveimht0RE-BAC(?$1;G`h#0CFJD;dJw1#4
z;@&-bSe6KDo0y3F{{H^>tE;OYK77c?&d&aHW@jg7O-+q}wDjuf%r8Jg?UPi!6Oxje
zCQX{8^&C{i@2&pMq9WYi%^i|^dz<gmkB!Xipl!=CwpAjF-Fkx{Q_Qus8&ggS<+`aT
zDP;xmxUfT(_^nz$&$b#gdkfli;Nig`!o?c4CIY<SJpcYa(8)bHIXN!JRb)dVB04&S
z)j#>#y0|Qv3|SK9;<Ds5m}P;)T7Pc-`=+1s%a1I1{^spl(BXj(em-9jzCI4L#qrah
z4-XH&xUjH!Ma2~lQ4x^?H*Q3f@F>>(d@2r_nhgsJyIObu<*lvS@9ykWR+w2Ktmbpz
z=jZ33+j7s$vy~QB^J&<=-F(m9y`UZLPyfGK44QCNP+-`cc6QaKEes4*-{19~Ipf24
z@`$lX&Ck82@9*thZC?K4pMQN^3~2MDh6vZwoAbrRU#y-mL7?W_&GgW=^Na^BUls-p
zr5tMIW>ryEQp%F5U<WU+R>~5Rk&zLQm+!}%iOX1W7_<}Z%a@Xih8-OpSx5SuOOJxG
zb}yqf-&Ijig=ESG>FBtuKlgtB|Gq6-Oc)#j0|glrl$DutZ*2+O`3|&w`us9&w|=?a
zwb9#?US3*iU}ACv)B%0iF2AVy`#Xk)GiQ8sVt0iUcwJ%z4Fe`6E&B8kbWg|QW4&6}
z|9(6!e`9O5_^)qoS063e1==d8FWYwZ^y$mDRgIwwaese*zqtPYKht^AQc{a{?1<>@
zENP!SSvV;vNkBp(;^~?tOIQK}10~FIW;CQc`deA(SXWm!^)qOJ#`$@+Op{)=y}rJF
zaqaJKrt_jBA|Cwu`Z~%7RLO2BfYm%(H*GQkO?=w_|6^=qZ2a-XMdd9yH-)}^`vzL-
z^6>TR)!T1RTUnNUeO>GF<?1rBvJYRs*0$mk6r3mo8esg}*3nTS31Z2%BUmr4a&mGy
zf=&)92E}dBT&IN>Zd)&DZ)s65Fc2`B$-@9z<aZ(kbnmBw+GIrogMjt#JpLplHd?*A
zxA%5~XNkX)6O)*J91p_;70&AK?~dNvTfKVkx3AaZL3wMdq<{LJkH@4f%HBk5y`MeL
zwz_S8-7ik(HXgwVK6@S>Ztw0}uzAheweeOQvnNers;;iqRl6kHEvDPFd$;wTJ$t6y
z{qgDP=@aM99qSU+E_i=$uh#mnznZ$a<IbHs#}^nFIK!^i%E#9?^jueWx1gvfYjkw9
z<I9eY4k>%&^|hCdEcKoany!3sZEZAYSn}>J(=%tzfLg7fg>;itZrr-{=s+VgXqp!^
z760q&>-MH5rYBFH95{1^=i0Svr{Z_)SMU_li`k)|p(rT$QW-Qw1L|&E3VmY{A`fZ~
zEm?h|aE0BC!j8D!7cX8|)t|YtGFV!{^RbwqVB>}j1|cCK9es;L+1S{!^pz_%?s#x>
zb2{%FFLTgIGpeep0U9EpqwarweGQtjpPH@W*|c({<}CAkJ&mOm?fmj>)2EB4ot@PR
zI#}fFSzi0UUxamZbp-_l8;=}uIdb&q!Mk^3OF}LwE?l_q$GhF{1?1)Vt*xyiA|f6f
z=@bS{<)oyjfKKXB^`54nq2W;yqWI|1BZJ~+J}IfGD{b<Vlbg@ZHh0#W&h4c(ZSP*&
zWBu~|pv`>t_VQw4Vjcbc;dOR@{($f9j@eb>SrB9hIynk7wOaiA9Owv*sotQzx`3!?
zt9ALigzM{KL*q_&baZ&w$~dSifv%Nxd-?J4aZuyFsJK{ANQkMvz8*AiSy}h|oGfS=
z$dT*u^`M1Oj}EnRgH|RTII^Vs&fU9Le=RL?a%vL0Bp@ib5j;yRAUIJk>G;B5NyinH
zlwyzcIe!I>9PUz4Qes-TaAB2k%Gsl=uXaK^e0Kt;&Fk*!I`rn|W>9u{x`+vMhVNm1
z`#%iz_4Nliw<bS1F%f;?E2OT|U2<7BH8oYjIE@EXYJv_Y0v+ktz{ngB5YQ04Jr8sO
zlSRpkfT>Geez`0RcyMQD@re^B98yzN-@JKaQ1Kx_LPDaWPmM=h{K~r*7Z-Ez@f~}5
zdV1)*_m`LRgBn^ra<)+cpxauH^}{9@HP*)MmD-$s{#d85dfYDEA5TtB2Hi&kn)ULx
z`{`262x=Oc9O!d)fp$a$1tD$mUF-Mkkx4%{$MOHazZZ9vW?w8UnYE91f$(0femUDi
z8<US0JU+(zbi<nE%a_O1o-ZsdZB_B~@bG8=Eov*w^_y?EwzXuJ`@#SPD=Vq$Z*Kx6
zH`RT=TMoLI<HgqnrlI}a+*itff6E0OI>B&ZYj!wjIX-Ba+?5~jcJb2f_v@r5sXTmf
zadB2GH^cEh+3Xh)px(sSLs;DV{@>r<pkY49c&zL3i<vSG%V&WWr>_oQ?-ms$)z#G%
z5E;3$NY7Kq$k>>5sj#}LDywbvH<#UIZ&%ssYiJzUntdH~xX;rRm)_f;({razZ9R0z
zDa8EMlh?1c6{c3i#DF?8i{PD_C7}Hu4?mx`4}TrCGp6tT{{Q<Lg#(j8izc$KuM7Qs
zI*0*WIET2nEa|^d_#!lMKPZJAf-L+J6nrUECQ}s(TK*;W{<7<mokxzi?D_lcHuSEB
zbMx)_cgFNxx)cOj$;rpZCt*>r;KdB59XoeEJT70qrclC6PY*PQ7V|2g_sW%!IaZ}y
zj*gCt7H1qi)XM$v*)z8E^z<!RSG`JP=9Yeb<_l_ZYieqm?kn@2v}8N;i%BXEoB8by
zfKG0<>hjxF``ZkZhVVDmCwFwL2!xOHd$F>zf?5Po*P|jM7cN+^0OWhnVw0brpC`Y)
zwG}k^_R;E}(}a$WEv>Tcue!k%hM+ayRdG-y`%<Y)W|e-KjMCc)DxM`QiI*;2y0Y)v
zySux2XS7JIzHlMn#;sdQrlz9)^X*!fE>#uNiD1|n(+3)e2HhdGEobJ78BSNW-C49|
z4Uf@GAMZ@5>B8!M3MM8Y`D_=a>qIhnPD)5fU|?rw-?3|#*8hm;=<dGd#-Jn3w`?(~
z`Tcf#L2+?2=+FWWr^3R<U+ZFbvzeQlgGRnDEO6XW_EzfD>C=o1Z*OmRcXDC^9andD
zwmG+-my6343q%s#w8=<9QgUVK+Jy@h=h@ZXI?%boFlti@C#WUX(7>=`*RDhN@5`T_
zrVH8^3fffYF{$P0>FM2lo-Qs`E%?IZ!gK2d)>c-lY#Y`GXnd)Pn7?W|YVYC0`=c7@
z198_td*p83ym{)lq@*Nh9HZ#2eEpwB-`Qplw_cCCoMv+=aOTXJ9)5nuK$nM1n$%SK
z`kLnMxaoSaA#9g^e|f2Fwa(z=$&;XxMLfPn(W=Yu!6T-xtgNgD&z#{|xpL)%lPMdv
zYzeWHH%{XLo%gOG3)<3l9JUN(OWps!<y+0l?(eA#=FVJU*wxi_X!rYl-JlCS?Cs?l
zKqtVRcv=M7xd_^<RryH;v<m#7XJ?1Ue8_qQP#Ygq7AJtq;-iqI3Rga$%q=P^DJ#3W
zFK|0|;evo}^fnfTEt!|u+}zwwoIM*l@Aj=*pqYb3k23F0(~aIx@iEC`5{u^~(8Bo-
zA3kVZ*A(HBkdOe~yTcSTY2C|fYo$S_Rh*ox&Rnr?fr6?kD`+jGpWm^4wZB1|Y&|Bm
znC0F&aP%lEJHMRBoT%T3&Z;qJ&l%{L88N*W4sC7ir~6m`Ta$f#-HzhteGMs~@{}1q
zaK;605qYe=UKnhC^~txlw>h}Dm>58dy%++bqPQ3g%*>8GIXM}$jzA}JlS_n~lF}u6
za67=<#Rc9D=<o>N2ws*eV7dmrlPK<IxzBx{xmKYiELl&W&2~`3X>ZlnL;GrfKY0F}
zodI;HTAXeL=&&gww%BRD++>z}3v_xEXyA@v!Ja)bpuwq6Pfvr^>dIIaxfD1VGBGiM
zc3Xg&{zfx>N@N~_LgV~ATjy>u-7K5)r%yLeoH$VoG$m`Q3$L*|XYYC$nsI%dEa-qC
zP`&BAI&3ZI0K+2R#KeUi87?kMmft8`vF`?GctafISI~G6ymro#*tl^c2OnP;-`QhF
zk2>m2SJv0(2aQKXL`dw}yO(vjN|p?s2Kl`E3(H?#TG|wx)!*FAEF&Ysz;N{F(GMR!
zG^|~__Cd%MiP+s`yeChd1g#GX3IbIUijz-*k}Qv`RY-}A;;%0+oB#g){#d{MC-*Yn
z*=>5UyF#ox-aUP)sxY@ACMICB`MnBe&<?yck(*b|0o~FAYE-rHNGd5v3JL~ZR?rmT
zYJDL9s=-`bT$Df~T%akub91d3!8e92^_~t|!gcDD7pSNP-RxCVwCTYTkos5Pnq$$j
z4p2k8W0n$V8|V862b({9`v%%?1KQE&+ARjU=DujB%z@AQ%Z+A&4gzeNEM&^}^y$-z
zA0HHNZOi2boriLJTduQ@4^N7b<ej^BL47e$qp2WBC>J)k9to;$&d;;WKH#zobm0SN
z5zv(Kb$*_nj&*f*AY;<g(|7FH0m>B3?EGz=ot-as9FmZbxKg3!DI~(hs^WQR_WIec
zu58({p#J|q&^`B{<LxgBwu07P@7c4*Ap4q*&ny$pyu7?0FPF~;tqJSs-~ipQqNm6A
z?%lgZi-iOQO}(J0MoDRJ>4O7|ps9rC=jLWyTO$dY@lHJ4ws6A+0j^f2XV0F2%$+l5
zj*Gjhl9Eyo_itX%(qW_##l2OC!Pp7&=ks%Ob5CXb($T>I+G%_9=1ovAf%JgR`~xl5
z)^LK}P#YN;dFuLm`^n(7TjEpvcE_37#K_i4shAlWf|hz$eS5<xE-wD`Lgo6ny)N#T
zHP!v*1iaq$@Nm0%fzaIpM_EgSMMYb0ZcYas6mTk)l>s!cAYb=`@!!9HO~N2w#=(90
zYx1H+N-An<PHK}69z6;=dGD0G7dZd8y)g%M+eAQl0WxYFVy~vA7O}HPHSOG-$hQo?
zo}Hcj@#XUQi?(bDDF|A$OcB;{_4t!+UH0a{m6gGX2?-7Fz(+Lix%C><I(wRul<~<_
zVe&~Sh0b?|1_l8;y|;FEbGPxya%E>{U%cqiURdaO*S6{l2Pj4NN}EGx%_^#@7J)W1
zE(V2hR@)+G0njk6py10%pgo>*%kLe$yxbpj5+dkunCt7~#bvuet@h+M<}T(x!!E$q
z0=T$bLGjPBWy>`5^wxc}(bndEdu!|EBqgP+RZh;%7uUzzgNA~_!on6k=2)(O_{ppj
z=g+%)d2xX@dCZy9<2&1I;hHr(bFIt6Bt7H}5*+5fSMm1^kBpQ|F_HxBs>sUf64Q-3
zaOR9piO$?9lO{FIv#nkfySwbe$B!$E;sOF1vahc@c=V{N188L)yy5J!q<o%TZ5J~;
zA87FZ*|TR7)@3?YrLR~RK#NBB?f*2q-}jpjbdm_@5`rzDJi0X*)Vf2-qivv-T-Zk%
zm9nxxGdeqqpBMd@la-p6*Jqe~EaA)yLxzS=pNi&Km-|^xkrNbb1l@;|aghnMf9k?Q
zXVC5wi_*i=mPINmo`)tXyDLmSX;Ad!M3lYTBo!I^x)|=4M;<?7`nnU+Mr>KXK7Z@;
z!otE2U%wvRoPK`GoF34^VCYt8LBW?(cbC5hov}7^=F9*M5e5cfVPP4I0?=#&NXK03
za!{{hP266o$H)7{=gjEn=y>rIR5*96&;<9Ez`k9P=<4Ef;N(fpW;WiY{{H@=fVWRh
zPQI}rky(U`_0XY1F2_|CsV&IAzwgA!lY+9&>Y(}NNh()gCaZWlRaI3nt6s`=b8{;w
zDgsY<o|(zaU{UaZVVZ7qTT2UzikjN1qYPD^o}4P4L1mA``(Ik>=>^>HUcYeGo*lDo
z1O){%-GZ)s%kl<Afs4zPmYN?A+iz^km40@1HoLjG`JFwLpd*t&M-s)w$;rsbY$$md
zwCCru+2B$}aAhl~O$shim6VjSx<HNbd!S)f35kxD7M7`vD&^(nYa%zZ?XCVUHlxqu
z`_iRLSJu7-H7)A?R_)!h`pwGV<)HO!Z*Fhr2aQ3<y017nSv_1*#;*RK4XC7&v#mlO
z8kI0eU;y3VB3Rg}t*?K){{Q!SWlc>^P}Sq<>FDUlD8j|s)7uNWhDt?Uy}Qq|_dxei
z*7S388dW^2zV7|;?d|Oo=gzT#T9-;XIy}m5Ju4vXyrtgLmDJVQ&GYVDDDzQLTBO#<
z`~ng#OTyQzU29nNB_rp~j=-NWK0Z94jVozqB#s<AcIdzXhXf}jrC<MV?Ed^<)#=^;
z|F1u9DX?h)=k7L@O)^p{jEg*+%%+{WbGR(Jl__b$h6rKl5Bo%aZ53<e3KL|L6=Q!D
zz`E+>1kH&}Iz|h1)Sho}UE_Dsg-MC$kt|QkQccd|AAbIQxZdY7L({39=RD{2&-_zp
zcfB-i-sR4ZmnH9CXMOPPLme{%!z`tHg$xW1!AGq59#~(!dey4x%ZhbzdspS%-L=xW
zop0IXhK2_P7I{C#l5TICefGlR7Z(>x+y4IZ`Fv<x+&a73Um9v^%P#Wno|d|D!-fmt
zopqq?#ivf43UYL8Y~z!?m5_UTTkfedXRgfu_eI_I&xgZpT(z(N{QO+B`|fqNbKc(G
zq2b}`x3`H33NC!|BxUK+rJB0BzMY+&Syxw0eVMX<Oa6Vk+AkN~tN#6b?z>##;6Ya2
zv$M_pKR-MB`(Azg&275vhZj!O4u7?B`MghovJ4Eq-rScN89?AiP-^N@HXex!4{q+a
z^Pg)q_5TWX1_l<Hd-+h`GB9LxRUBu0x8~>P=h<IgT<q%a51(z8du4z9f40}{{PJOm
zi3^{do148t;6pv=81uOgrt`^I6x?+@e&U2jXlUrlRjXEAytS6^leuZ}vojZs&)Zzi
z_z^RyjbDD<ojWmS=h^PQ$+KX4_I1BY<;@!|Uc4w}nssGs<L4hgex&`bF53O?*Y*9N
z!su)o!`x=>yu33r3}4;cygcW2SX$b$WxlhQZP~Jgty<@FP(;KGxrzsju5NBpTC5BT
z9}FA#K>o`Jd-eLYsEo`VkpJ4-+h=<)F);iHtk}=Uz~C$R-hzQ)f#xGw_8pt!s$Qz@
zjL|!K{CIph=$O#m&(6+1&R|s_JXy`xXzqjQesir-trQbLEzGyKx9@*g)y^kd^5le|
zyx7dClP53!@}&e6D^^ywO8A&q*v0R}#Kg>b^yra_r>Uu_lu=5@uF}_OJGdAcmUS|g
zfE?zq`Sa81@vkl{biQsEzoWo$Qb=In!j6s(x8L$L9~|dzWn^IZBe3T_14F~Ij&d0W
zh6^Ge`<Q1Gzq@0}%E~(P97BWJ+UoD`qBf`X&Z~N*+1l1-7O{He%8Rp1vu9mh@S;mp
z+ecl2p|IfK+Uidy)qT|&7%nV{1f5c-46>ZzgJ}EV!n?r<xwrGa{E0vR>h<f|sq734
z1-H=y=EqA=y1KQudi#?1c@FZnRa<_2d3ibGKIl-_fPe+(=32i#(8z4Jj^)CYId-+b
zmc5>qs%c>nk$Y>)$H0mIHFR{YB=_4cJ2%%l`_vT8qMb35_F3nopPgm;>(%P@Aprpk
z;{QAnZ}UF8dd-@Ul$0f1U0qWqPE52qzJBkgQ`(>#A>JR`v97C&Yi-=#sQ8+Xt*chA
z{yIOoXj*FK?{9D0UNJCm<lKQpH0ZQ3D@F!}2kJ+E^Fos?B$5yK=U-nJJIg$O-jeri
z-S_JM*Y5rQ@Avh)w^xVj>&EZ9Grf{w)`}G?R=k$e`aIvs+1WJXg2LIE#_pb;o^~3>
z@5T53XayZs{r8#q{)>NpewJQy^!V}Yr>CY$878$XwEBOzcG8YmnV1U!b#?pHd}pb&
zA6_VDTV-;(*`9%6$K)N1vfv;`5Do`+*8JS`@8|jYQ`>S&-`ohS|8ZDe>h7xS$Z1Z_
z&Z06hIV*%5f;VSf)mj^|(MjEJ&V|SQ_V*r4dtdtc+RE(f>t<OLF6xuBUG?Wr&DASc
zR;*az!OYHQ67w#4x!>GNox<uWp5O15&tJ4?5s&!K>8DP4-K~DV_twT__sudY^9+-Z
z>Atruc+l|e-QCl?FCKk=X1_B=ueH5B`}MW8udb||{8EO2VU|pu13SXKV3t6ElarH(
zkdTt6Ro$N*RwXYMT(}T$IFw=5uFdJ^S8dxC=H4$CdV5>0^qRBt?c*~uGj|m|?YdX<
z+4t|e^8La4>;8VZ<gK6i{M_8OuCpCoT}dxw%(tYRoOJtEe&jV-Ek}jluU4-&DSqbD
zcAk-8hqKHwX0WYD#Dn8I-tYS@VaNVJSUYUZg<yZ%tDu79*7p4M@&7(euljt}T-8(7
zs^r3Cf4h~JE(OJ>OBKJmqUk%|F1E0+@YRiti@UnJRXsyPLuVN#xBdIJeZQpM7ygG2
zA4cu1+WP3xBcJ6G55HFBzkYsds`j$U58JE0zgxS0|G!%$Yzz#(V&)6b9mG*FzxLbA
zY5MW&Ku3xlYUSQl^);)x^z^2ZH#ZEOOBrT$ty-mZ_1d+21$(z`3kwYmy>933=4SS*
z`bx;u>C?4sZDZrshlAILR_@#rw|>d{w$J5nZ!PT>*MHSt|7Y>Tp!>J?*YBS+Y0|n{
zK0dx{OFSp@h|PRjV&$vOvgBD^!NK~dJrx^|^~<lHsO)a`<2g42!ygj~%xJq%_Ws`5
z#KUbXeP^3hy;#`(<)r$24P|BLty{O=+Fic>(W6IK*2mjlp2;w)p<S-Z<McG$%ZvN%
zR>keDGL5jV`LO}y!GC{$$5)5N#jQIx*ZQ~B<&Nj`>*Ll&Z@;#$_V<$#tE(H6kF&j2
zcJI3~|NozK=h8G)b@kIvi!vV_>6~Sd*aRy0tT-7Pnz^N<Y^zEZr-SCGyu7-8eR;Wf
z#*7(m?a~p`mL59f6tBv}aA8RVqKrb0`*tadf(5HqtpZhau{(=gWv$Du^vPOJnK*Ib
z-{0S}e|&g&>h$T$A08g|UCzW&0NQF`l5#>Ic2|k#%a<=f#m<t&?)|HF?1(78TROe$
z?X9IPEi6~BUDMLk^i+21xzNPQ%`^Re<->;$XW3S7`*;8U?|Q51Z)>bdUKG5|->9-S
zYOB|I+wXJ!eeAE7(EGag&!3v7PoJ(_vBKl)*RN6r2@Ps~b5;~SKDILV_O@l8YgW1U
z%Wcwmy=`A|<TShge?D7>JlQY9#|}C)ZN-We@?Ulre|mD#I)sJ6;qo!w7f9X&GnsBJ
zbZ$4vzh`r|_WRvc>()(ExqAJ&_oPXaCQX?<d9h{jGlK@c2kzb;9v9N**Dhn_7R&hk
z?X8xk=0ugFM~-M%TSx2f`OuV<l%!Hy9{q9o{JJco>&roPpqN<M;jgP!X>HB9d8ys?
zpR%!W@XVPrSFKugX;<m%Df8#AzjG(X_V=63Qf4_b=2bl6{QKv*eRx2?gqK&W^)xkC
zUKIGKKEGzsrcFkF-=y0I=j5zWdHMOg{q>2;?jqvi%UfDlgjXKh`~6-uC?Zbl?_V=L
zu4-kZe2jwUa=*Doa~T*MHXp*`*(ev67BStZC2!v3+}yVI!GnaopU+u?lFgF$d3XQb
z|Nl4s@8|jdO=7qhe8a1%cHP>Nx!8BMndvUZz5DjX@!S1a@NVz-xY{2N+m{9Z1&#c#
zyW0~N7`X7mhk{;7W4Fl2NH1@1<GIg`XPe~)g@sMy;^HzXd2xX)`}Vfn;Iy=5|Gq4@
zfBCRo-Yg{J-hTNQ(7sJpR#wy9&D;zO4eu>|&`Uvv1N{$+c7_B7Dtd0x@wTo0cBPG1
zdfnRmo10v}-zn~2X~U2q7FY3*HTUKw*Yh@?drqA`ty*htvAg<v9<Q{SPiksv)x%bC
zp73A&6DA0>wzX+lSVU~gJ-taM_s)*MW;WiS|Ns7mhJ~eBT~vQ|X6EAbd6mm9e%PtP
zD{mLGbLUP_;%qef4?1Q6RIJJMyNim7R((7w4r*i`m#g*xxna}h&7na-NmiGi`^~qj
zy*z*Y{(n(duU=hd%*enIp^ME&pflz{!5+0Cp)qPp#zINsw2V_zG+$j@+`i;}-ptqy
z35^fE7#cxoYg%gN(^FH6EM!idJNNJ2`-o{vx8JKe&0hL1^~s5eRlnbE|N3V0`K+T|
zqLY>!m#>eRbY)j*Hpplxn~Dtwoj&Wu?pgxc;-s(dU;XXP#KR9Se0X@+wESHRsL5Mo
zA#-a(Vl(K7EY09$8UO$NT{ijs4rTYg6}7*=na8}pu&}vL#`4i&rT=A%o4G+JG}-=m
z&>Xe9Y;D!oSE*K))fX*VloEOE`#Wx4-m427n@!Ts$*8KT{#?Mr(6H>_rrg_RvXC|}
zIGaHT`zhC7Up?9_esx>!?d)cc_j|w3<KpIiT4H5d@gbpC%G7JFb-7s#m%;@XSJ#sd
z3trsVn4EQU(^Fkuo2Y3^C#(DaT5;h&Xo^t2?#Dt<mApE9{i^Ek@1*Q%b{sl<*mt?)
z=EBErPoF-`{QT_fs<mrF|Nr|tb?Vfmpp$fBcbD~kTOYO6>+&++%Tu+(d9M5ltEt%&
zwJk?;`|Y(CE?i*CHZ?W%^7Wm1{q@y{hue8YXO%B*=H9evlay>s!Fk*7Cf&{4OWyyp
zjNF*i>Nm$?At=E0rh88UH6-!36!;h%5)v3NnkAFJozh<aqJ01Fx%>Wpi@vPMa3Q7A
zM(*gbV{zpRq9&c2YrXu_r=q1xmi*Xp#-{!7!WS<xY(E|m2K8cca^CoUm$xWz&<<aB
z<<-^IwILaPiHQs4s^1uvzPl3{yv!%lz-3R`S*hBuSHrb5G%o1ZedIp8bl>rVtmfZu
zWv|bCduwaa?z>sHx8*i(UA0PU>C&Z{udb{Fb!WbwHNU?iet%uj&X`*}i<d7<Vqjq6
zX2vKrXKe|Ot8^`XelE1OcJE6OhKx;f{FdLV{T`c|mKImOcfkUOnKNge{gnUl-QC@w
zxV<b{2Py-8oz1UXy#N2-_q_9tA3y$j>-D(H9fHa{Q)eDM$Z9SwEW8-ByxutN%#L@z
z9v$u8nsd`=u1#goBvA3Z_usGAyDB~|(#Mst7#LV4UAh$X_SRPK^mB6p{rvi3^rq{@
z?_1N=#Z~(LUTk7w;xggdcfa4cuUWl%^5vIb0(<KdfBbm{>KZ*f-2VE?%3!O)M=dHZ
z_x*ks91=3+q0#2DcXukI_gi;%c6#~v>?wAvTefPI*Ve6D&12TDT^kx2dUfmhi4!O8
zs`|Q0{}Ka3h7e|ZfPrBLYux&9(B`zn#DzJxr=>=M5^Id!bd}5#6BK7z7B5RXJ1cd^
z6?4D2R;6#t5<OR~STW)F<IFAZ|NQ(MwKZ#MQc_aQ%=9yVetypXZ9OeD^V}TE@&#%I
zF0QVozZZV42S@1zXa3Ban^LR3Ty(#>I($7_c00fPwNFn^U)^8-Kl}Wt)2FZQEKZM4
zXJQc8p!558-wY;5ZiJH!44|Z#@$SyfRqNNA&t+0L@b}yH{a0VF-@i`Pds@bc35s3a
z-IpN^07cKLUoV$`J*hq)RAjVy*CyZFQweJ8>zv;8((d-Qrv(;Uik^Dee!UWGx61hV
z!-6~C%5_d>ZTmmZs`S+q(7}bE7`k8cxtEKZd+NM->sGDO+WYI(YEZg%a%y^c#=5VW
zJMaAcf8We`C5>FB>%|6DRsGu9>;TH|j~*r6ExjIlYiss&At9lV=;+l;mZ<bf7&>u_
z=@`U-^4SA6aCZ;xH3kL-#^)CnI&a_e{maYC<r`QWiYLvVzkbdfnWxX5y?S$VbMLkH
z`~TOijo*LIVWwpAv7W&5^K4UZZ!<DBHqE_dvUKTE(;LZ=(+(Xv^yL6EzlM>~rGS<B
zv3skomN*^I(ANi5l6&IT|N8!Z{ijbwm3!kngMNQ|yEXf|UhJNVK+vX0-s$%$_4j_c
zlv}^tl7E4^ipq=4=j|>xv2t&z{arS7$`p@DNl8gl=FVL!9#`RLXlOWT$%6+8wZC32
zS1V>@;IQDqYzSNM+kUz5{oan>`rC5ve~M$+G4s?Zudi=!e{XxO8?`0C*SD9y`%G7N
zcW_M19F>*Jmbp2%@dR$qyUP>)bNa4bR=M~0#m4R`37l_N>+}4_T>Op8eMb+nZr8W6
ziqZ~SV=$MI!C~?d1}o&iWnf@vXxLo!HS01b!>olXR%pmt7CmWuE!Xd^H~n<G>%Ye*
z)#sbceK5VLsmY}5O@wajt|^RPUf<Z9-k)}U-dex8RxcrOu=~9osIX!?b>`6nCI*HC
zDa<m5>D&^}$v)}~8Er<!##>WP3W1s&cXyXhSBada`f_)(Ar}|dmshLT&+;)@wP=yk
z>hSf~#N%rgzIv5)bKBj7yPI@!@9(=CFjsO~>Pq*1xmBxH8O?n(9ZOTKv6)-y^tp4>
zQX`{w7A=+GYu~ha^ZxJF(^6lq-G1+rBWOH_AJcUV4BH<Z6_1~C{BdAb)~c%S?{rUZ
z`tmydf7J7Hb1!!atDBU(2sk^(@^Z;C!Jj{W&N9iIB*WKU_2tDvv)o%V{60x<PCI+4
zN75J+NJozyn|1D^Howh>2D?8WoS!~>W)`)2{rc;mhU1heDGSc%@abjbyuP-!$U<h-
z`t{QfKfG{lZS;Csh9c$r+xZw6^3H7f|JgzlEt(h@7-FX9-Ue0R*Vf0c@9N@;-CGrU
zcX#>q9fglgDnF%I%J5z8blZW}J>CDw{{LtDU$5i;uTpmJ%lPo%;HyhZyPcezq~2`Q
z@%EmsXBv`mZklfNm(TP6gBndz_H}zMUB0|E@2(Z7uf2ZHr!G*JXwf1iUOAf^C9BRq
zef}J@KjGHqbbfYm1_p-t$rx250|SG-mxo8ky^6=Ye_w^~H=6sXJnv}$)9Fni@$v7Q
zrT%YDJ1YfhJnt%bIVtD%zOwAn*Vop5eKtEk>(P<UHtw?zz-dSbTP&G_?m=0)e7Uxz
zWn}sN+U+l8_D`KLV@2ZOw#<Kjel80ZXaKdEK=(el_sd<qx;p&o-s*BtgYe<Qhs!Sa
zJbcg;9UK(}I*01znVH6?PM(~2`spRm(wo4*h41d}*4EKEQ=-Jczz7|8LWzV1=>iLx
zO*-Cu?aqaTg<js?yT1vGil$nf&#(D%(H#_WW;r(&ELoy**^)y*uHSv*#*JCm*WE3>
zejceY!1M3i>#tddS~#_Ibf)Cq-lXI0>gsyx#EA<}Pfr&W6<s>hI6dpyn#g6rj0_we
zn8gPJ!<_>kA0K~OwmUQ?MyLPy;!T@2WgqUlc<~}H+oi{kANxN4b>;=;XsVmv^34Z#
zrABJ$=zIxPVrsbj^2+Y_`&OShbLRCraS;&>W8=*??|<q&R`>h%{a0VF$6ueM>J91>
z9zA+A^LU@^sS_tAsM!Afa{1Sj$^KjF|JNN}%D}*~Obm0}fq~&q==F86SGQ(|gPJ>&
zmVADG{`BLIE0!#A$=e<+ZI%NX_R%>V<l@p26cqI3AiKQ8x_zJdWGoa;Z<4a@@97B%
z4V}7b)hemAvHA7I8*^`)?frO68gy%gUd)aKukWhglxbhH|9#xqUAuO<u}d;c0`<kP
zRtJ&{48F|RlF)VyB_$_NKej_qS;aGMeR%ZtysL{`ySIS$0^i+rwP0cX9IMh(pc+C)
z=gN-4$DkhD$H(9?tW#&sOv$}{Ye(T?P~LZ!uf0;T?ED<7QZIG?d3(O?T(rnZu7CN(
zeV?D7&%U}Uw5zl8W9q#4hYy;hK|^-;_toa_xVOla`|6b|KQ?eMG%Ran#Hj8V8g2)~
z#p!Lot-Jm9+DVgyWUb45{FVp*{q;3CD{IwDn;$b-xy3XL4FgqGRadQBckR?vZPU_M
zA*m@TFHY<4ztX_Sd}V8P_~n^)pTFJC&%U>(a+8ktv{X>$m}OsIx43p&?&*gG8Bb45
zWz#zQ_(9X`?yjy&6P4ZbcD(yo@uX;HO$4Z;eF&qLU|=}F8?&>>b?MTjpx*QCx6_V4
zzIbzU`qgc@(W>g|pz%sCPtU-lq(x3nPCn12ihq51IeT67w51OoBy7#Re9YbT-{LiE
ze7MDQCR~0Q(k*ts_frL^x}B~UJ7xCl)ves(TH4yDQ<k0Yku-L*t^PJ8_cmyNe@o`&
zDbuE1OXyFH<l^SO%*=1I;KT_J=cQ?d1qaWjrln<_oTMscoYu3e{Jq}G-S?$ELBmt<
ziiCwhVF7ex8zmzbFh6|w@Ke>^uHN2IFRv~!y_gkKrigrfbMtb^toY8Zu3ct-DvcK|
zTqtFdF#*)ET(U$(e#%U7DXCQp7ASav(r(n&tflMs|NC{TYPsLsl0QERgDdUC#l@HJ
z*kR!r<m=np#v{2X@9r+ib)W2IVhW1&_x)I8BiA1k9DH?md4A-yrSboNUAHQKH^*;|
z#lnTo?OD&x%!G6~`7UGhx)>P#ty;IvZ(6FRii*p^g$ud3xr1L{TkD(tbME$gRo=C~
zz64fO?3h>gD^oXaPeix4ewd$M-=V{Yr%sr#;Cg(0>|{0HNyi^wJkZDtI(>HLxo@2}
zZbVF-IyLt9oCy;al;5unzhC!zZB};n)cNz*&zK?6-1^Ms=ab1i^Y1f&M&?(CtqlnY
zSrWQBOw-6HNN>8gxPDwnPR^QtKaSgHot~y!WHlG!^l7=bx4q;*31~2<J|s3)xBs{@
zBuO{3^MiZ?n&r*PS``!&G-cMTRV^(nmNI9*&pU8EuG%;I`nsvN--dxlM?*tHL3203
z%l)o?K5xH1f8S5HzrVgtKK=C4xw+Q7qQB2U`x&7jAuB>xhuzv!xmm9AiC}9>%ZW`o
zSFc=oF}M8Q#V02x`!1IX3=CX&b#?gbZvA}$rKMZ{6<;|CYg1URT)DF9!$J0~H9w0y
zgNlkaIXOFTt^HkA`}^&7DXWqdTH4y7adCM&L>L%MT(OqPO6#w$?zjK9<6ywAna1fN
zVq(jV9C2B?Y*`klQZla9Q&V$0Z})pm+L;-JcfZ#2CeFv~7yWfBEZlgn{(r6IT)$o!
z%OK}A9>cjQE-0hqD|~00UB4S16Z7V=(PxVt3pU=|oDLcrJ$drvuHWx=`#uLvTwqJ_
zACz-$ZSmw5*Sm6WZ*^+qv{$cR`>Owp$;em%YR5%xPKz!7`+fiay>Yc)LqS7GQ&2|n
zei&U&2NluNPhWju_T#l>-Jcy@-Q82CPJP;J^uJ|=tP5-{z@ws_B64!;)<$n%6};SU
zS@EB^V*4Ej9u}O~q+=<=cl78{O<mo$xBNpwro6OaV3;Msb^$ZB=S{r+`s%@E_Rydp
zrR}$M`;UW;r#-nXmz9-uC8%e+`|dL1+Pnt`8m)?+bd<fjvl2e|YGh<|Wpld!+nbx+
zCxHgXbMNhmoL~QMXXhR3b1zF?-7UW#nwGXq<>j57#a&%pm$v2JHp#fKfUWxTr%zL+
zPQ9wbugAg3c~Lrl&%*e>ufmrF|6yVmzjFtzwl%uBP51OB5n0*02@1A$cK1s37#JAW
zw!Q=>byT9h^xvP#op;}5Ge2Ltbm^+qt0(8)?&|0WC@T82wek3oBQ9IBuAVB{BnTQs
zo}lP_Wx2on(&fufKP~c{gw$J#+EubrW#zVQVb*1DF1)z7*jMd-;Qz|_CAqg(tzDZt
z&H0)6<=y4^wST`}UuOKrt*Gdeu6)dcj}<1Vr>3NtHr(5q9S%Br!r$g&%aZs1?5b_%
zW!KL)&$+SS&!3veX-hjgIF>G1@}imF&LD=D!66|DOKa`{8|Yl_m%AAsy?Bw)D`mRs
zAZTh9G#|jp$@%Ne=JQ(;4l?E5-xsT@syb=Oj2RNC>FKXq#p42ee0o$s^IP-leyuzi
z^P}@<w|MrSA0MSGi<V59G|A_=#PNfy+tmrw#)=FKjosMlNomko4^>sWE?v4LA}gC~
zb$q?6yL<N0F41Mi500-Ze_cD<EO*MJNsA!!$!IMgpUTReck;I1$=mMb<pr99u$=4n
z_4RfCl`B^+`^><=5rH+EGcaF0;Q#zUBl9Mm)fYb_PuYI`wzzUv(bFz3Z*N4x1<m#3
z-rnZr=XY(2W-!PtM~=9(wzSMR$BLt7`oJ6#7N%un6a;A$8q9qheDmhbO*-D%;p?Ux
zei%?z_U(J!@l85=zg~;BTk)AczV7EzK3OXj&s_x%n^aaVTI3`sD9HOw*1qn}^W0_N
zW(*TkL`B7pJ#p)kl9Q)SnzRU1)vBtx+E#xvnajrDF!?aHx}HDf_O_QS%G>hpYPBC;
z`0H1dr3_#0-CbX+^H=5NnMa<VY3yG7>`dkd9dq;T7wv9un|=4c*$zWKy&W5O?Xt3*
z>(|=SqG4hZl9-s7b$8d+mpTj#vs6y!t^4nfF+|Mpz<tG<HCOh2zqeY}y3Ay^^o7FW
z?Cb0HzJ2dA%j6~BlpotKFZaJ+a(9ysD?9sY-`Qq%T1KZI7MNJ|JaA(d`SZH6ws!CO
zPd%&Gt($iI@x<G2r`>*g4ODuBhc7=j*IL`uG*nYl)63U4)XAwyhOhl)3<Cobmfk4?
zgFOTDiv#_|dmCTB=0qD3J;TGNx5GAWeYkx6pTg#aUyRewY3S(qbar-n`TAb{^YgPW
zXmDnN1jc+41H%u-tnBR2fPe*{NhL^`=#-hc5;Um-GDTh8U2nSgbp7}+SJ&2E<?q*R
z*kEwE^Mms0u(g-EM72vE9pSY7_v0~mP6jlw8@=5xc6Zs;Bb~yfUtR=0eg1s)vSn_r
zuCAa7pNB<1K;e`5@KEcm-R1e4cPq*<G|b1^i`t&>|KDHVU*Dd}A11Cd^3WYL^s_d0
zcUa!`Xwd454Pl|7OSfz>@ttcGdfxv39?*hwQ2x=I?rmNE&Lo7V{?XT}(hm<Dr%su2
z;%(XK#~)wZ*;%|PH`>wB@zwS9^Y7$sf9b=(z%=PFW(%0XLBYe%@7npgZ^nE7d^-K>
zQMbO&^B+@p7C(QbU;nckG{<(ho&WXy_uf35oEL9wOx{}f*sZzsgFBHkornDA*w@EJ
zZ_BxuU;jIrSH>dX;lqbs{{Gjw_4h1z^e9PHP3;w^GW_=D=3;JfJ%buPh6DW<4q<g@
z#rwVAr%a!|e0qFcr2gJ7lh}A97IX@$XWiLRcwKfuuHUE6pFs;A?%au)Yg@hT;;+Bo
z@2~&*`nt46v;FE-tAcWK-|}A1&dv@E4K00JoRYF+UEJPR-6lU4mc6~@IVtCMSV_qi
zw_YhwNP`wk*xAKROO@1PVOa1I%SahRL-d51Ggs<HZ+r3O<z-O4k#jpNFK?Zavhvp#
zi~F<w{`v|kqF(waYiVm=-JXA6dfoPni%zDdrgl0`3KcIFwr|O~X*6}}RMRM|bD2hh
zbt>xW?x10RP`g!F-A_Yb-+%wFtLv}qF3$%|MgQn5WJVufVqiFsn{j{N-evyt*S);F
z{Pm5E$*0br508tR2O97O&8452VR-7)si3H+SuaE8ccS-4S{ydy+%y6WCW2bJRaL*X
z-k*pxJvmJ;R_o>N+ZW2;+*o*VvHNVFHb?Ma7ibFYAm$Vr1A~2lherow<$%uZZK;vd
z%<}H6aBOB<S^xjv^}RQDYJ&P5^8Y@t%UTpXxV5?duE(CLuUVoZA{md4bT0e!V7ZWx
z(3hL(^EIulqt*TAU72N?y(R6e6lkRT=FOYGzFhX7I$?r>Cl?>zwdM2cR<Ux6NvvzL
zU$th<l*=!#oSSRyyPSdHf(rJTTLuQEqf5P~Z>jrR1)2sqKhL(vLIyPAylK;>FCPx`
zgSu{q+jv3a&hK_UmwS7E|NW9rvf<(3%O@(kXPuvC`|9rQ?^_Q(EPj6O<&jQdP}|ik
z|DMkB%b8Z94#FXkkt?g;?+v#udlTU1*7j0{fq^LwwzLVQ>C%|+_*gG!YVz6H*`d+V
ztN;D|oqckWDrkt~*4FIn3GZhZCWpkvuFbr>OmfxNwP9<cK-0U~*VkSB_4RdVaPZ=8
zaeXZ_voO#arY9#SKP|BENe7Ku?_kARtu_TNcGI-7iUQ3VZ`!m;L|VG~^55Fu->$ZB
z3fF|B&r6M*WmCCH&3|5w6>FWAwRJSEi8TfWh9Bamx8>e0VL|Z^h|{qD_TK94Z2WRL
zR)_P?%(IPt`SK;GX1-f~Ki7(#Q9(<~i?7}Jc%N+W>1n#6qN1v&H|713J-w;q(-Tj5
zQKf*Z*RHKvu)yJP8*lJ(zqvlo85jgUU@P$t<Q8KcCE|Aw-d6v=PE}QP<~at21t+n#
zw5*<;pI?9b{ze_|;%8@eGMoN;{^R50qTP43^z^13e;gPYIWq?|3DMQpmuE0RPF_CW
zO58#CQGvyiqMas%k6e6b7&zYDRcbt!g~4Gm)=qq>g-qY=e|@QutJbgI&usb+G*9uV
z!Uoc(56jG4sTaRb=kz8KLBWMnrij#jILN-t_+h)3w>M}|e6D4&o28{?(axA%H9t3L
zX=z>ATV3AT+B(y(W&TM>o(3Hg9v{D+k(mvYU8KzO=G@wrn{CC<(9m!kOGAU9t_WoS
z=3biZoc`CJtM-B>wYj*tQ*Uq6IUN)jIMK++sO0CTR99Em%x7n2&N9uO_A=zh%2lhh
z)<$pl`}y<dt?l{qL4(veHw-}IPQQMhuV1%dfx_iZ1_qWTx9z*QK}i4wFPOP<_3F#Z
zd}o6)^Gv^w*-xK71<lEVMpHn;USD2Zw5s^9;MdpJ%hTso9xIXibLP&@;;+;9|8YG%
zUH|&S!|h++f6r-aX~}qVV<Tup=%CY&-QV8c&i?h~<);dpRV!9p=+@u2;?t)h+iy3L
zcRin14VosHG)d_4Owf`+Y+avy?g0T4j`hiE_a9HTI+_m}Z;|VF?-tX&q}*?_h)>pP
zMfmzS@FX0lBOJWU=i<4!)};>*vC7(11b9!=F`Ua|KN&tfvMTv_A7pw&*1GJBgCtWR
z?t)KCTibXp2ZO_bj6}@xo8iFy$Z1REY^zqRT6L<V>pllR|McsxLvwQ01O)|cDR}6#
zbjgwx>F4JyyDXr9rDj>Mv*hI@(3tg}JvN}e8DG2e;dcJ(puj{e(w6zmT=e(%_t}1I
z3<?Sc4d4}tC{b3xopyHCQqY9^n;RRudV5XhCdb6a&Yk1;d~0<3;X{W&^XHc%ITQi|
z1FedloZ!7~E7u>RH=Vy*Km%0B@7ZGm>Jo0<y7krl{rf=&w?Su?dB62Z8oOP+dUcjr
z?yQAT3=B-zX9yDR@2kzazHaWL$B#j?qNOh{xhg6u@_vh$wsfiYbSbSbYd5E#KlS({
zsKN8LEc@!J&{eBf2R}bIcj~NJtENm5S-NbQmZG8~U;E(_y*~kIY0E%vFibwSqWb&0
zN&9}MdrS&jAGa2CWZkb<tJQ=bE(cZppo!z}cZyG)I`!+Gvm<DeIj6ANj}?3j4F}S1
zZp)qBhZ00!&WG~tMlQMFUVd%B<N7^u>+Syic+BSf5;U_K5ivtZSQzA@pP!%4KGz}-
z$_6JUDsN3cFZcD`-Dpr}O-M+n<lP<1xfX>^&h30xpPilkw8YAH`JwY~?(L0kX6H8p
z&m|qjmZ9Hu_|7(iw?XC39q+xlZSB_V>!8*LC{I9#<a?#f{U)pX?_1g|&%nU&;WD<;
zkimWy;h_LVmIXgQKfe!}rMxu9viO|?F9U<GJhpM)9l6iX&!2w#?LM=DxTvUAyLMUK
z+_tu(gF{taU0YYzH#0NS%f}~Vb=X=T^~3y_6~rOvTxd{j?O)jyj0_82Vw?GRAO<@9
zA%D-uHa=OaCEVhAFRGFy&!#@O__D+c(w_UWHSzP7Eha~gA3wcG=Wy!>cfNM#X{je4
z7Jzn59DMH!9UNikz}DxD4vL5Xt)0@;)AM`z@+D}7%gER`_4YPU`j)e;dU4TR{_6X>
z@79-B+D)82do{{J+ap+qGS*d3VEi!u)vH&a8BI`<uKo4Ja4s{}xk3hp1G=Dg;+0LQ
z-czScS+Q$Zlq_Oxng0GiLCkDC7Z$m8PnkM3)k>5@0u<uM9|wARc7l4^-rl7@Kc%9M
zI?Uy?PrALWskwP;$;%+n6vMJ&28N7DSe7(0FfchrM$SCeFR#D+@=7t?D33{d;?}FI
z^q#JF>g?I8hg!LP)qeG!I^|_K*YE9}otI0v{=~Srw7B(1EDVpY4Xyt6=Hk!K&$lKX
zX5*DGaJYK)>aAU+t6#eOkUYKV%3^o^(9qDCevAwYPG(^%0u=;W+S;@<G(0YqJ8xba
zwe`~V`1;!1y}`@<Knpxq+U!pTb(mQ?K7A_Mc{gw8-Mpz&rhwMJ6j{v$b$5b-gMFVL
z1l^qOZJc)I!i|l|qSDgYR_qK7YVBC#8FbJHXliG^u#nJ~ce~%e>QtY1Vf+2M)qnof
z96fSGLWkwg{i)jFAyHAQCQTCBc{i`pMsBWcby)80ZJ|X)n?ObBlqn*rYHC_4Do0B6
z{#@Bt`}@keSZmN)T*xG#_u~8Fr#EdWc^Tx~%D}*4cKR8XImd?gTPr>$=|*q!5fv2$
zEuS~bzqiI+uF^$OQE`)wx2dUV)$_UKpy|iUE02YSg}u60{r)Osr9q+<d!34kic8%3
z@QoWcf+h!wiZ%rW1%Za>E@yHm@U=g#{vI)H>91c^@>dubE_}gO;(uTk6&HW~_xt_n
zmtS5vF;Uqx<%Gax&$@-%wuP~>vVs=hS(Uy@v0|?~^045<%aT?3_xFMN`d(gLLBYYI
zpvgI21_p-z_SkA$&=?|f(axBx+uPoLe`i~VJgB(|)>3m|Sb=?H!Cb<_-@{|a(&%-J
zpz;fAS-^%^RpSL-5wv232B>&wX5-D;V6Lz49~lX1hnY{znsWHzgwszi9qAM{O+3U>
z`uf`05+SCR>#wgKm#@E*pz-(2Ok>cne^Sz-px|KB`hPW`Mg+rIuHy`t1E_Zn)ZhD^
zetTP1cJ}P26MmlE^Zi~mXmwg#-OtpoFD^Q-T)FbsVflXxil3jG>DN3z`{pLlmWBnA
z#%U`yYzX-Oz5f65{ePb7zq-7<A2du69#?s^MCs3!ZMnC<fUaEuRe(`jG8C6zzWIWk
zf#Ht<55^h?28IXjC(oR@GEFzS<ky!>-Pm0r+j6zd&BG^7oCsRwvbFASRqW29qa|v8
zCR~3#_4wn9i(I?EoKWsx;oQzAWtuhR+q=7~7c5ZVl`uF^qVy*qF>&F)-~0bZPn|jy
z)CB?UBmphodVIV;+{2>-v@~{S@$*^dSQr!%wi=)>)B-JWShleC_qSPgwYxx_(B$KN
zn)debm6erMZ#EtWjaM5cAJfp*_Rh@ATo#;o;^*h*py^fc@blVBmx8Wdy?Sz6uB(fS
zhNWdBsFv{d4o*s16ty)g)k?B1<6sjjsNV4O>|C{a_12=NUZ5cnNlD3HpHAzWCLCZW
zeS7O_i5dd~Bep?IhCff7oSa0Yq*gt6kN_T8-ctD3ZSUW2x54ufWpAUtzPft4M6G5`
z?C!EjDz~?Z%F3<{T<jJrZPDM~KRq?Fja!i8)TvXT5m?K)ep@p>-tCxk{q<B8P(i+P
z=gz1d1q(NA+T@c4T0DfUx3Z%XRBE^L$xc#<McP-v_PbBs{@rJ@`r?<DRM*DukE^V#
zytO&KUxu%}jbDBpXej1kyZp4n4==RwN}Civ^YNW&<of&jd-J(G@~2Op3`821WoOhf
zF$r;Wbey!Lql05>)>W_g`oCYde)XGc_0e3Cp+O$UVnc=p{W5&+i=}7&FP;6p{@3--
zzkXH4KmFMYy3<l$-+#7wepqhqTF}y+HEVQw<?a97>b?Fy@9L^hP$O<#%+90*Vh#(u
zeSNPs^V_X>dV0F|q)C$}i%LnYdV72O>)ZMJuU=T_92yz9^3$gx@NBjk<|=*$h8>Mp
zSBKB`<KO@t;Z#zxWnT3=%hc3VO*6A^%YOg<_I5R-E!Mbb)25(_6DMkEX$66M);~4|
zE_MSg>H;l02Tc}=$JYe*+kEO!Qc_BZoR*c9_2r!P`x)RQi*3k+p>E3E-R0RI9voa|
zEbu@}Tf6lA-tSq*`($|*Jl=+_NMvAO(ZN>8F-RO|u*!ROpb<w&$G|Xa9%vf>!T;>{
zeU7hJ{kGt%KfgCKXP1dYj_j(G4^jqAN}^FBQrxVrQ^ayO!*@QCa@?ZVB(g+y$z7{Z
z0Zt)dnKhG?QdVA=AhgE0ollZyR*s(H(j6+-o>=Tr^8NkmTkp|1cb-)~;CVj(e&hKG
zil_DK!A(>MaqINS$?Dht`UZ+v7Ct(%KY%%h_4oJp=TDsQm~}R7Qc7W=VfD8+CyyL)
z;ghl0kXBYzWtG48>onF9h9B)ZD5cH@J^9)%7kBO7*l_Odn>#y=4<A1K^8NeuR;|7(
zbWU5}n?7yYrcIlI0tFfF?9U2C8H2tM7Zx6V{cnWO)3We&F_EA5)&Bkl+EjRRZ*{q=
zD+7ay*ahSwb_e_E)2DY9Jak$YyF09uD>v=`zrU4#J{~WAb!Fur&<3{W3=ALCxlvYJ
z{z;xYcdljCmyBi0m#_9)couZfV5W(bW$CLBsb05v)$ewK?#PXdiCJUC%aGvxdId@s
ztl?Xzh^thuo0yo`D!+wiO=g3Tj*iZg)B5|*+_(|Z*4Fmv-R}3#j*7>hk<Q;UF+9H3
zbne`_q02XUo;iR1`Kzm|Jts+<=c#z6rKexMdv|YIUS3|_;oA%k>Vl@EMuwrR@^$zv
zB`tmW<KyGTmX<U3?c2AiI3wBq@0Z|X$Br3US<Sk6^Cl>8*YEun6}2{OUj4tHt3Iy?
zSR3XYD3X2d)TTX;-(34Vb?VgKQ_Ky&yQERWP5plT|Jtgms!vZQ`==!&DD2(4_vNcs
zQO3a{uIJ|2Mh7asU9@_&wsqN?6W`w6{vV|zCog|KeSYn<^m&zP^Xvar&Z~ITxypFu
zfe#-Fu5vPLNJZT!)KDF?`szEY$7V_Y&aL17Z`S&KzqA%FUOaQo9G|ser@i&}P6=B*
zH9W3Tb!(LF{hH6d_v-)uwfXbm@Xn&AURO^tFnl*fjj{u6((>}>U%bfJ_xIav9bMh0
zH`C|)uD*Ke!GnaVs;YN0{(rgb4_aXH9MmLRAjXjJ`UPsNG2E!?ld+uSE?24Ye((3V
zsI_6ge*OCQ{7<mI?Nm_HvH2AP!!|v%eKOMTE-m$zl#p0q#mvxf`^qYm9`J&{zCJ!r
zE-Z9@`SPWwySw|VufJsZ@0|K%$#CG=mB3O+hJuoB-~Rde*|O|S#IN7KjV&x@6hA+=
z^k&X7ozp%2{mU<AJo)hOaA<na#>wjb>weE(q*3(fNN4>*Him}%!B~<6Xfk12?(J!(
zr|Uoe_4W15t=ZvvaeHPov-79b)!F_2_V)Bl<Mc~eTUYrlb=n%0d-uMG>%^&3r$P+e
z{BQp)sH4Et12JP`V@VkqpS^MZ?(XiBo;*7{+jG*rd-r&Fd7plHc{x;V6X%+B>(>3=
zSi{G#;Uj7;FYqsWb7SJUbLUh%%gf8<Djqcc`E**p{%_6qcXwybp1oSD-#4SO(o$S6
z=ET<Q>#O`286KFSWncB$+S-{jXa0Qs_vP~W=T4mPsQdr-yN<4IYEF($zum8l*47*|
z<lKtQ2=_jjlRth`Oq)J^vWk4&k3_xLT~pq@duQ|Ig7eH-vre(g*8~)*&h`ux$uyCQ
zjEGoa#mdldTO>7dTBtiX44_0oJxKNS`1-k3d*@A$ud~$O^TFw=XO2;Fa<XOJp9(c~
z^~=|<hnMm(Fw}2C84WqG>+grd{FQGu9{=>9ng3pCSzexAaBy(u)+p%!x80!Ax<B15
zzyI{OeEpdN2OO%Zt1n-@x;1T?M%NtM>TQdh7#h}|WI`!pUWcu}Zfs;UDQ)vimB^Tw
zGxKb#jSLMZGPCoonJFtP3rhK?PI-y0%n8~W^>&@HYv7N)j0`stWYLP!x|nCO1q=*~
zA)YRdA$j|SH|m_$(bbI<d-i|Zu3b^3ObiVFkKX<7D*z1u7!}>bS^{H3=}8f&b7@*2
z=Qy|XEnU7`T~=0h<@ML)HVh0oYx-89Y&6U8|NQy$&Z@6jlb#&wmG+!;^XAQx^78dF
zXV0E}`-7R;{?E_PKfkdt`Q`if=N~*sI5*dNdfMihn{<rr?B=;Go_M&OKYT7H!-l7r
zadjasYim^3qKM+KX-{R-x6fO@W=&3rTyDbqdwXwg%Z=8H-#6#=_4Vo3*TwFv_?W~e
zXEWpH&!2B@Z`V&hH^+1J)m2ua3<=(775!^78=II?rrf-=G&Rt~;;XM!R#yKuKP&nC
r?5v7setv#iTU*huFPWf{N%{@{LBEhc{_E_vfI`UA)z4*}Q$iB}+-X^g
literal 0
HcmV?d00001
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-f1_score-20160908-100017.png b/Code/MonoMutliViewClassifiers/Results/Fake-f1_score-20160908-100017.png
new file mode 100644
index 0000000000000000000000000000000000000000..d93e30b1e9ae77cdba769d66ce4ef25942806136
GIT binary patch
literal 167745
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@vh+~dbfzScARzcbrKZKAJJlZT4a8<jH839NxF
zx5}GdC9PfRHI=QF<7#`5SE=W%D6g&8Zhen(*3ETI?p~m%)UBFgyWhU#*>pqWlXp%|
z`1Y}Ke_Y(tJH_v9%PpVRoG&>iqqJy$A(NFLUcmT(r9=rY_$95rKp3wXf((8R>Uhl<
zbqIR!jD`puLgeph7dJPjX{jozs#D7XJG|aJIM_TPRdRFMS*^E=Y|H}#11F?Pw)4qq
zT`Y`it9CtR93C$qBf}F}x9|Vy34gDhJ{Xf5l9Qv85_!!0eogYSNiTmb-?rS)(D3}<
zTb(^$zg~}bo|Zbts?<w6c3NsnTbop^Oz}1IrO)dou8ZH#7dg!^=Z3*%`P-*Yb6;H*
zYW%zK|H-;vFV#<M>iPTo`}DHFe}O!`+FqOE#E!;1UNHUO)6>&0u8lSiSrx*$N$2p*
zn>)93hrEhAV&OW!{?m=40kQjwpYyfxNHX#B^G8HQ9XfP~>HGWp={cS*Fra#j^979U
zqAwUZt@}^#5AM$Gd3O)h|NAWe<=tIr)2u5Et*xvnk;ksC4)^}Z#lfKB*`(sRG?qvA
z6{q+noyDoAr?GuLxrxW$|GapF(V|P?vr4y_sMoGgpLl9hk7n?)7iSmG`(sq`;emL}
zu6q08z2W+g{_6BvZAd>a=QGQMGxzp3*PoxBDxNlq+Mf5<>9oVL-^-6$>YuVVJhpiH
z<;Cv(2D!IPO5WZQ^_^v+`SD}iwDRATvCq4Alppo|Qgd<ggWaXC+uVAk5)ZX->c5%u
zpRMiQ#!IV`kN(X#b2{kzRiCx$tgNgrZf(^rdvl|)ql3f6)m2i)ey@+$>%TwM_it}I
zWtMV6U`^Cku7d{;&akVsTC`}<f}oZEE?#$nhs%GyX-i`n;AyXFql%|fNQg*_fYt3k
zfBu-%+n2r)S>`{VFLK($w{LmX)zwo{Qudr!G>P%z#fvknO119Xz3aVO!%D^T(8<Z_
z8}sg3eR+3x_m*zwFZ~8-XC%J7zP>)BuIAzV53R+XlQvX*OzM#`<&u+=TN))+RjCuZ
zOJufrew)`)r?0QBPMkL{?v|^PR@nD<cQ0;A^$uATvT{qelm1SByPquO@9r3$W;yZf
z>}+K_JGrN)r<*&U{I~PY-MfPF^8D`Z$1mx1d3JS6dMnSX`F^+j;&OlaHL<(JYJY#L
zefa#pd1rrr``Wd+E9dN9QNGyZxZ~1;SE`EM-ZDLM{P^Qu^Lq!<=hvn^3%dAUsJ7JB
z++4i++Z)H-Wp6*c-F`nSHyJra9Ys!23twJdE<SsC=H+D;H9rib%yKxat*u*HTBe-h
z+O_2L*|WTPd3j4?dG^}a+D@D^r|0{<YW};s%iEW#+PA3{m6f$^-dwzLPW1i$-aQ#t
zSBD>edV2cDd)4n>)+o+<Q908nmFwA=naxpKvlKNoIq%)Ow=`B|QPR!Zw-4XDw{J_g
zqyEmOCZ;tJ8=3a)+m~@~Pi1HS@}QLuUcb(6oAh^cWK`5Xk?TK|N?%@L_4D(K*p?%y
zzCe8OmV0|29g|vW$@j~AXX$G(hJr~3qTcbb{(gRLj*gA@zPE2wh1Y9Sr^MW1Re+_7
zMfJ;0P1RO5Fc2s!D^s<*cDSA2u=-ohmG$xReSLie1qBXYUtPVpJwJYqWwD!jeN2qZ
zuP-l~wL(`pEDc&%^z;-5KmYMxUtgDgS{J>YZ*BDUw#k!)b8>SpE^uUaad%f%S9e!m
zKYhCRs?gPK?EG>Ghgvv4eEa4$(<s#-`<jmLygz?xbfUNM=tggAS-e>J)HL00P^Nf!
zX=#^Q(W>)H{X;@TQX;R-yiot+L!yg|%Ynm(nYE^JP1Oo@Iz3Hy>nV1Ii4!MINR{;T
z^qjTj_4W16(^7e)&3LY_k9WVnuQqU@6YGr|Hx^`GUUp+!?(BP;?(DCZ&)@&o%*Mth
zAvwAE*4FIghlg5sl)atxtir3Jq9WnRiHSR^zG_X=iA?%Z=ft5Czfb1uEYs$_du`vm
zd2?Y+q_Ix?zL@v5(^DlEE?l^y{JmUU{om4%bup4!Q@Osry6WuX({u3in>#y&Wv$Cx
zTDe3`RzLEaXCpat=1jNgrk0kV^4KXLKtL;W6-#z@_Kw}VlMgg7cJ%jO-+lhs+1Y|(
zV#_p_@7`_Q)ZE+~cUQ;UT)bOc-|g|S-iL4A^lVB!edzXW>Gk`5X?=TlclFfr$H#gl
zOfm$ruC3v;wzj@;^X5X&$!ZasQabNdudJKDE`EQXzx`j4(%08odwY5J?A>cv{w~IM
z-`CgI7gv6Mwqf(;=Gn8QkM&44tNYJ;A>;oyXVT=!h8Y(WcI@1F@Y*#o-&rOHXPIXA
z?26m^<x7drTr1JiS63R>uGO70XU>IfxzTU#?Tx-zctuD^Na3^*8?V%osq<#c;E0^2
zc-p8>#&Xftw|C3$x9Xg>D0t8i_G@kQc7v)f89#pf041B6pPxWQo8MfkrNwd1rE&~m
zYol7-dZj?t=H=x{*i;xynmkz$R6m*h*<W~Wu64WLT&smKJBu`;x9K!BHy6ISVYt@j
z-o1OXzB$+0L{3XgOk8+!@}x;ko|DxUhOLd-uz9od&Z4IQtHX48WUWLxJ3HCV=j(V*
zy0E)E|HsdtiDze-{`h)5zW3hue}8|2%DSwpt5~I_r7f(j7dyA}S-rPmkg=%{*rbzu
zZB3-xU1`(etv~nw`=x!XSDM}4-hRi99S4pbW81fH-wcyXAtNKBl26(zFMAz5a%4gJ
z`FS5cegp-RjI6Anh)7H5>M+rr@qT`M_v-)GhO7?ry=-@GmMQnnoja>O|Nr@Xen(GF
z%kt&wYu2s}+?eFbBVoY6$;s(9ee06k<iJ_x`F*#xX3tJNdX1T#@4?sW@$Pqbl|Fp&
zf+IRQ8k9pfr=4{wE8FH*x3sX|?%=_L8#ZhR_!IN(-Q8|JS*rs_kFsh_<uc8_cI3*+
z;KKj^YUl2`zApCg>-GElq)f98T)QTwr>B>3VFBa4s@J-k*Ga73QYW%4_qLg@&8s(W
zdgAt0J^b|abk%3Ox<3-d&(F2)-*5ls&6|Y${QiaphBdLfujO1{)W7S#x2Na94T*;X
zHYT~=xOr32z(8RCpHJKj3fkJ-@ArJ>+p}kn$;VUt_J0->ueos};>4z&{Cz*&(r<%O
zMA@5&AHRNO%?tnh?Ci&f?ebYqjn(djUfL(N)Z|s$r0<#c_Eb(ty_w)MYt9@VZ*Omt
z>}x*Sv7Yw>EZFv!ycGKN<t4MZxp_oHM8>b$;8zWrhP!sYI`Ho9?!w2%c)z^7y!=GX
zv11Qgf4@jSdi3bR+TY&_3JMw)FIK*_HM{-s@qTehYfa1TvnClf7?yg>KlI)y@mbH-
zclY=AUtH|I*lViRhK(B?@9rw?mMNZVQOIOl{q0Imq>ZiZ$7i$il`JhIm)~jUlWh`k
z64qaJ+wALSZ!fP)T{FMNuAX$m!IsU_$LGi-RqqQM5}j|{x}{`d5;FPtty@x{tP9E;
z8v7W0e$R2Z8y3DcN)!}DSyvAH`T4omE`4p()`Z;L-Yr{9_TIjldudbZX_HK^+kwtk
z&cBY-)YO!)tFh1uTLX&zAHRRUew%z{%9e0NMa5a=4u5T~Ci8wx7j?aws%qG6rKhE#
zabS*R@q^c|xu<%u`uqF)%rrWh5VNHJl2xY9?}ba|*?3P&WnpK}zPmpCwomYJ*TTZW
z7gtsa$Hc^JndcoirLW&dvU<t#<;l0UWUh$cZ+B{%F1Nb6Iw<$Ny0Wt3&yS6Mb;UO2
z4>Ij7^Y7W1<lYkD<Kx?~eY^Wyt5So!I~I5LR&T%YcWT_~jT^U3+W2sD>D}A6rQ_n_
zCa7>48X8)?pKEnCASd%wy433M^={o_x(WH)7jry<tp&)>|4{4?tD=;C-9NZAy#oeb
z?BwR>KfW>fxPX8_gP^k8flHT!%=7OZ`S<tt#a*S@KYstt{<JP;r;xIHU(3>^s=G>F
zHc6RgDX6NlF87;zD1ClyTio8N%uoBi->dHE>vL=65;aITz;NT{&BWi|-d4Qd`+Y<9
zb-g#Ywt8o?=6Oz<FnMzGg$n^omM>Sfv6129<C_&4`1#YP3p<O`-`v{Dy*2CVp$10g
z1wkt})c>#Rku+vg_n+sIld~r9dd!s;bI(a7+uq;U$UN7&ylwGf<y|E&naaz{mn>bX
zXlExkzxJDC+L;-FPyS_fc6Mf5TO(OhQ)5u^Az{hVr4N6<-+z4d`h8ut)!!EQ&NiF1
z=jP3u9Gsj7XBwwpSP`hqBV!>jbLPw$#_4=~@^(3&mh6=@PE$}*WBdQ}e7!-*ivSBt
zOVQou4>U4wOgk%8QB{?6q(g9m3a9<wFT!qpGM&oqeJ^57EtQp-8yg!pY}@9xK5p-X
zxpRBJzP_G(V?*MG4I3`ZOtC3`=5uC_rLdl!-itdsjbmbC3;+G8)QQ-@aC>_`C<c0d
z9c*=O=S%$e=O+gzr{no~wu$NK?cUS%5)ZfW-q=%V+$U$-_3P{F>`(Roem<}GeAYa0
zWsqvg%S)_JPfvIE^5Qx--@bpw42eBouSFl7SA1fEV#Mw;-B;Jw_bWQLfr{ArzhA}c
zem)fkRjG-IiL>?uFZXM0ZDozxlEGMBUY?ScmUMq#t%P}=45%{s%(wdf@=js(M-L7*
zcXV_(R8&})<=^Ycyu3_NU7h{usi}vrtPBSAJhtTBmD*kY{@A6Z-hlxD4NJYJznWrh
zYb(ph$fyy%PNt1lx~->&XHE2WK4vza1M&5LTRVl-#j4MGdU|GDUdB6V(xeNkLbdmN
zI;CCl<%Qt3yt`d|vQ`g1pSM5$;o;$KTffA8`}P%-mml9(`+Li!tMRX<sc=?*f9INz
zupsUBzS`fQwnsw)gYT{N`~P))dwW}1S(*9a!-p>}E@lr34&GS!*o}piHSzJW-WL}Z
zHlMStyY}bjXT#J}A{N%x$uBM}EGQ@d6?1|T5*+UC?#-nJdU|}HpPjwDWu>R5=Z}Z&
z@}TN@j%~G=Y1S16h8}r)Icf8}BL|z=1tldp_4W0AD;t)_AK>TUIIuPQ`h|6|)}RP+
z;)vN_Cp+6bACwYIe$VjYVDy~y;p1_6WfK#T$!flrcK-jBl9r~VpuixmALnv;neWBD
z)#Xc;Elaw)t2E>OKHF*f@qL2IZZm4~89s0OsU5!V$gy7Oi_3haw`5=EV`XKvsQqQ~
z@Av)xNyqzSEeap8oSLS)`sDg0e%hu*Pdu)y4(HFkwZ(C%*VKad_iX?C`Fvi&Btt+*
zNXVf0na|$eU*Fx8UhX&736#Q8Q(Jv!n<;8(aV__se{7lW>@A<(-Pp)%TlK{uE>2EK
zNhx4&Rq35QmBRM_ekgCtz1_yl&UfJa`SmA?W-ZRG34C^TcDw!mKf;WRjG#n4&!)0T
z*}YFeON)!0U+%~}+v+W^R!`b-T;S`+DK^tZwZlMdLQs2Recav$uU>UAv-2g~+f#XC
zSE+WNj3pC0J3GUHx3{-nT;eHgQ}aUr)b2Y!&-UY!lfp5(%XshCewPI`v5KCan)&pf
z=34m!m$xN@^2WYe>s{sV`zA~f07aCvS<Zn*X7++FF9O&8nlp1|CrI47oUd2P^w5Wg
zhe2s{u66mM`v3oS6g+g=IN9CXNp`Y@g~fvU|NlI^y${ba&AzbEnO(-VN@V^1e^y3D
zMgoF@jd$+Etcl#rR{Q(g(Tj`SOV#XOXaDw}Yt{PULqSSP%7W6@*FY(5)22-Y4-c_|
z^7;Gy|My+{=X!MavTf^sO>w&$@X3x>%7o+cGT+1I_iLIBlaIZSd3`&7f2#nKb35PF
zB{OfC$Ly<-JUiRm{p>7L!-5A6Hg$g@g6~hc#u%JbQhbf^Yq7QrzpZzs%)0Xno!bTE
z<ocSLn7+KY$b5BG=;8eRf7>QZ5CDxP^fb@=F0o*T)shy=<h66=$ZW~IEjDxJ%oo?!
z%NG?DZAd)K)+24s$H~cQC46!JuUFc8J|2?}SQ+x-(o$|48=HccmsD$hKAnDJQ!2OL
z9E(P+&{YRcp5zP+4E*uy_4<iZrnIbBp>b9vSYKbiqPkjHON)zJT(3pNQ^LM(Pg?cE
zeQ}vN3;Ozx_sMq0*ZpLjYgOvB+;8rdIt@++CT3<qY3Xj;>TeQzPi@znFZ|@$GbI}v
znUg0^zPPbbSw~kFlv#ad8nNEId2@zcZPmu-y*)igwq#!3kakw8N6OSIy*ejHXU*ER
z7x&lK`_8&l7SdV${oTUU)6+bBd|XzCtrd`v=y>uZ1ylfLTwgc$-eaxI^=*8zT}4k%
zC0<_UTk-X3xas-uNh)X48QP9HdL@Z{Eo4{_zrXIs)9LXaPHC?{aPT0b{r^A4&(6>9
z-(CLx(P{ntI^X7Ltet#pn|xecoZD65+C_^NO_(vGW5x^#P<5}ic=iA6to^lLUId<*
zY0SPhYAYy(O`J8W%P94fNTgWsFNdYc{YQ?tu&}c~KGrLpac74isKRJ!Vp362Nw~Pk
zwc_>K?GIkQT)EZXbH4S5E$=z__>TSj{5%lU*p|1GNj){?;8g8!0b${0IoqlQPOV(7
za?U5WYISb)HZqg3ud@*n7T%a~QR&CepAWBw$Fnl5{k38}->hFVk2SG!gGN_eTwD}P
zOhPX9TMEJYtQYrBL3CKBx2bqKO-mIN6<zvST}^G-iQ4Ao=2o54k4{b1?mGALcK&`&
z&q*%*a<*Uc&Yw7O;m_Ygt=xxBo$}hTV@Jo29~E==Y|p!U>CfLA8<U+TsXTo8R5d6l
z$mHeEpFfq9l$=g%(s_1n?&_`kr%#_gAvJPK{{6U=)YO+U|C{;k1SY9;7Ct`K+0?}3
zTjl83C}CH#V?t_V&b>W1SG@lA>66gCd-tlgySln^Mov3=u$kR7^X~3)@l872_v?Q9
zs{h|x{e8<nSxHIFlt{7b>*KF4QB_mRn)m+A&COdsy}z?F*kh84Rq3lGQ|+>^=_q<m
zk}ybU2>W$*wz+F7muQR5>7*AI7P`f*|Mh2W)K(!Uj*STinG`)I&9Eq36lUi+sinQW
zJ?z%2tE*d8JQsORR*O2Xs;%v9l6lGH#3r3<Ya$mH%S28)`g;BTbzj%$#q3bf(baXm
zyQ_5Tr}wwF`+H1MX=-XZ^7r@mt=o<sJI3WX=|~HwaL=x5yUX8qwe!orS~B0hKJLcN
zo1J~K)>%u<^X^2f2+^82Yu2jG=Qp1Zn}6nvkK*Y~8Q0d#y!SRUGc)S{zN)XQ?$tQA
z@d$3x>7K0apS9H8&5g@*Qp@)3+dcgJt}RJVN$L3X^mO;8)YDwy;o%>j&#%wg_Vme<
z4y)2v98<ki-`(50y42?D=9jm(uMewAN?KG<Rwj1s+O<cwwr0=z!pzRc;W_EZnVH60
zKW)#v>=qFb(NX&P+RHoq_V)IP+1aZ@zxSF}d`M6{y=h0m!zQ)0@%!rzUA-D=l6A#n
zOWxh6$@AvT)6>z>aoJt=)+DpCvhvXJ<L)<Z+~_#m&Yvx7ZD|>~WB2avQ&Y9O=gg7u
z-L=oE{_CsI#MD&PJ9qAExn)*bdFA^?gRgrhrAF3#K5HIzJ8VsaqKc=`Vz=H)Uf0X>
zw(3T2d$D%86UW5avsZt&4OdcAbMu&_vdn+JUW>q@;^*g_rloF7JuNmjTgoJ3!nJ+t
z_y5~9LB$hP21LD_t{*Sf*VpH?G$?ax<FY%_#oK;*dU{435BU9R_4*bS&!m5Ue$Fyk
zT6#;Mwzg5=*X@QocVYy^#MDkr(NzBT>$U#c+=B-XI!#gu+??h+apugGp6Ab<6Vr{}
zCbCJV`~AM(eqg`PnKP$l_3G6-Dn2f{w(;MO$NY)u>FQGEc`-SW-nY!OKIX_T4S8s`
zdV{2K8b{=`t+zB)3;hG9*iC<ZeLZ(}cJ{*;FEoUNgtqj7s%}NkNfnQK%}p}Br|E#A
zTh)8oi#gWX+TJ#mpN_035=&cQ8y;le^5g$D=V_@QKcBbH&W+wvv2lWm=a$^tVcM~G
zkLyNkaL~53wvH}&alsK3m&MP|iAIM7uQ+X0^u%NBm;C*I!#pOb%$Yma_4>M4*Rry0
zX}2F9Zf{lbTvYx2UDWR*M~-krPIJx4S)-<_uI?^;cwOx7u;+iye^Weqbhp>->x)2D
z*)O}+_IB>bX-DPj|18|xZ#7Nx&O5EQ(p<+MfNH(SQ#oEe>$dQTEOqS`bDEag{CDCd
zi<tOYZ4C{9tE<C7nRu>sdDheL@3((Fnl5h0rm>Dsa#5W)m%ViH(WqBOTl4NlX&>|P
z_ZPRbvvZo3x^{<&qN3vz&0x15zkX#M{qAJ5S6xg@%<64_)t>keNuJ((-(Fr7PodCN
zA)1@cT9&_?GeO1k%gf8h6XqTA`ef<&{M_8FzxGd=BJ%Lb6O~g_wbeg;`qX9n{p@V>
z*4Eb6j9Xh)p4+x#hlQf&q!(9LPY>HQsVs!!@W#C=o=PezF50<AIs~1jrOy5S{>#hD
zprY@@rkrVZzi-y9-tkGRH?rl&{~aqpWyD|Cu&`+>;`Z*^uw{!#`MWz8quUNmx#Ago
zo8S5C5)Id*s;ZLWYh!i>1zP$@%4^D2uXuc;^7FHoZ_3}_vt3(pGUj}2$MWQy$Z4g=
zTAVmOzPPBoHa(}WaN5R=+b(TfxNq0G_5TAehr9d!^>Lo0l9-;JUSi{j7@d}Wa%moe
zKb)_BZ%yRpl7AArPpw`VqBZqiiMzY|+56LVquc)csW~&lka=s?)k`O%cNV3dy}$p@
zCvT5QE#L3g$7fGfik$ZG<8gWCNh&oTkBV2F|M~H_{NZEA+_Zf;8bRY<Q?)`5)&Kt;
zzgD#A%Ifb-2Udly?%5Ib^vd(g<@4vvo!e{YcXd^$VeT!HwOhWuy?yxdWnp#yc~`vp
zdwW40jb~?OE}r`C-MhZ+_v@lJCr#Hp)+5QRudfdp;O^|~bba>s)#~*Mo<fTjFWx$@
zySJD3+1c6biY@ojGqbZ-S6<87ntk0ZAwl8M<Hr-HPF?C5zo)`b#q-ef`SpC&)zxbs
z^T^pq)Ya9w+28*3^z`dBSGX9yzP|3Bk)iSJ{r&zwe`?m|PMbE(YV}XXW46(rlN4GE
zc0}FWtbIi)YHs118yf|j5}u!%TXo(r`4~^gnux&3&tAOf(2L#m;N#=t5|%|vu5~qs
zg@wJiyqv$Ns7OFwetoeGH#fJ7yL<N1(6v#b$;bO#^YYf+6Mf5VUH{L9Pu8jhRAYy)
zkBho3BO?Q9dD~QeVv#n>(fDNXtEIKokz--xSDA`krz$ftG!7j)RPg8sr%l}-2?kK#
zS42bvRBcZ#zr8ING=>Ul_AXeUur@h-O@!cNb^l{;Z*Sk)xBmR9(A5*>&+j)(K9;dH
zmq9>QcJ24tKyEIsOObbrK|RkcTdu5pe(b{acM(xhuWHYGg9^L}sgm#a{nq2+;^KLB
z`s~@Gt3p>N<ma!yZ1?lWkAycjHl8?n@}T+sn#G&fZ~T7jPVT<;_V#;IpDHOUKYZ|D
zLFoG_*D{xW*~&O=+B6B%ERj#2K7H9Y`<2;(4_=c&jg>n)ixpcAgvZw|_3ZEMJ^J_e
zcR^9n)>)?6S+dLh=2}S@Cb68GW7*s-t}hmSZPJ!r{YeY2W*+aAPTvq~s`gH^Z_@Km
zZ@1r9GB+1bKGt(FN>Ya5-{<-N58S&KH`(2nW8wBWW@cs^wrw-pHRotxkUbYSH}_%f
z^?MdgHOso9@#Dvjg!}tycN9KmV^Gl5<y{@N)@ibuuR-A>m$iRDj@wiDIUpdQ;p*z}
z*)O|FZr-{D3XZ7EzrVk?FI}o?WMuT=r271ft3MYkP^hS^eE8<(=A&}er>E)esQYWR
ztL$x;UG1+IIrZE4122oepSGm->T;7;ZI`}ho|vF0;Pj%W)Nj6B?~fl9CGYM;UVb-i
zNq#|b@!=jx<1;~NOAUAJeC-evB(!GDnyxqfQ;t0R1?paeuZwZa$k4d8J%9aHP%-1W
zuH^5cV+_AuO;~wGH2dsaYw@tKuvzuimX?XXzPuE0dhmMv{%cG0qqp%?R#rxA$(R^c
z!_T0os0eDhZ_Bya<lZl*xku=)52!RewEO+O)the>CcgTluBs{-I&D&oA82A}?Z5R-
ztz4iHV<Tf@P*XvyI<LIEyrs1@^Val3Nl8fxo<eOrl8dJ1d0A)m?Ac?pCT_3Pw{PEm
zJZR?MvduK>3I{VA&xPIdSJrM5T6RR|z~%3$|Ni`p`U@HsXXBA*Xli1bV^w<Ug^@(C
z`q`h7O)I@F<^TTq^WoO(amK%5mVImVIwl7i{q2*t=c});_nBuCnQot+o<7%blI6VL
zcXyYACdWXNnew$?CY~#cj*gz2zNY_D;WWdI-#*JpzY3mo-sE1zV_uVt3kTk$!bi0h
z)$5(Uq{jej;|lJrIPce2JMYz%mCW|`_G=<HvvqcMf_&Z7)O2Bqr|??+^UMc2h1D4t
zWUWdxzU@dqH;3`V7w#|TR|PI+TNSdhDf{}mhX<S4qvBOUSB9(zUqA1h9VaKJhqrh0
z`t|y0=jW~69LvEdEiJuwa_-s00}YHnUM`;xn$!65@-n-kq9O+mPs{GzyB9tF@$=`)
zzlV0Tx3l-j+pqiiy_ucA;Onc<imIwte-HiN9Pbpm%4en#Xz1zJ_xJsp!OIff-rCCc
zd7fo4+a{gGzO&7&Zr|FH$;{2oefG278n<4l4VyP#_Wb_g0|Ud7<;xFWyC%j^@aIQi
zL}X;*-Cd<sr$Iw(yUX7z+1lP+q5mWA_BP(r)Af(Pyu2LLE7`Nh=B%0LqzSWTahaQ&
zGx*PcyTo&Hz;Zv?FK=&)gN6(e5)@8N*N=Zw$#CG_Jvl)^K~UHH&!0aR7Q6Fr$-2sQ
zcDDI-YfUv>UEa^n&maHx_IBadSD|Y=RVS%DytX#F>ip#$g~@YGzAoA3)+_ZgCwTvC
z^Za{PZa#bYvU64F>Q_tH+1ZnyotarRKRxkypDZ&2Xvpc=nVD9%gM)$;S`1d&tx})-
z{_bw^#qRyb-tYh4H)V=QOKa;wuc=xQ8xj~nW$K3y1#j-|7N4Y&>FW?aUDwbsF#o1r
z?5-u6(Sf-$t1cxbBrG^*=I`%cQBm>W*Voro->-gOqob?)@Y%DrFJHbWt&5AEZI=7s
z-MhXQFEZxX)k?`)m$@V)DE#^JN8$9d|GbYuvsgbqJdD^`q-yv7Pw}3g&t_MB{`>R!
z{1c~6IRyj=%$YN%WLtY%+oQw$_E&z(Nml2dx%=$-)2E3)KRx~N@Avz{hlf~G($cbg
zH|fWKi^{w^I~rfS$ar&mJ3nY%O+JL7D~~y9d*0f~Vj?0-F0-xvJ!y0L`B!V1IXO8Q
z8h-q!*lVx0IPB84kFKXqojSD0wR=P1V>cBQl?Ml#*=KPsIDao#wXol?r&iDPsH>l!
z--qwtk3T%zUik5mD`*ZQc2~*4>i2uwCn~#xhK4x!`P~x|6kc6fxp+qpxWK$z{&tg&
zvW5mn`1-h`GmX<9Jbc)=V~53)=g*xdsqB59;^)W5V6$C<kD;cvwp4A>sZBiQ=H{SI
z+gstgcklN8x;WwS@qXt?DvKW_n>v5Y^Sl*a>$NyfqjvtT(${S6?(U#j^otiS&a#NK
zl{7Ij3YxrKrPldy8!vBM`y`{;LW^hb=DV}IeEp4z2v3=H{l8={i?e%9YH4U-h}l)L
z^2l?uQl5kre444}B2HhrB%~X??TRNqA0HdT-rBE?%<Nyb8Ea~4o;ZKr-N}jR&)>hI
zQ=R8eI>P2V+f4V<jaTwZJ$-#mSLrOP^Ly~(#ftKx%!l7kNlctL@y6b2^Q7ctQ~MKB
zXV325ntdJAeR<v<I%UgZub4d*f{~Gt8FzPWz1O+*;K74c^(_~!*hO<LHS|vWl~k*G
z-otaQ$@g@QWg4FQ@2-h7c71NNl|RJjTflbF^Z!106ng!-^Z3ytP_=SxZS?evJxiZN
z_4aO^|NTaQe6aoH2`VdZn9YU_ws-vdUciJ{SY;c&NhkULzrQm~v&HIuJY)wAeK>L4
zxP3eM#013|*5&Kc4*9vcu`x)PzO*tn7G?-o8Kk=Rwsz>M7HRW51!ZOD*WB0Fty@?1
z`Tp*5{sWiwqt4ATJ^i5a>{hQkn|GDIZd)6@{n6uo`(xMR>wC}J|Ce#%Fv+_EntgJ;
zy)C!bs&AjZDzm@3j>x}9KmPvy&gfw5`75&R($p8Xx9f}P#dLs1uMf3wvh8P>J98#y
zdU|?9)T_Fb+{DDjPft%jes_1b)$OibVGh6B#opcB-Tvp#AEo(gRXi(xd`R3FFZch+
zWPgLYKNX-!z}VeoAHIBPS-VzO#q*HA{oj_)&(AAcTSrf>|MTPHihzYo({!WTRK2G?
znCx%I_~Fax_n@Nxo_?@>_T62jGtBel!q&(2f<~RZqHL?b9cg0aHhEu~mZmn#B(v%D
z_4SJ*H>XJ$rF1;ImzI(O8dHf%)%Ll6YVoV;$Sd2@!<RAh?6-d<%5(MWb%D~_JA13m
z%iiBxYu>Nosdn|aR_Lk)ZoN_#6(1I)sg`(70uA==*tP4>sZ(6l-``#JaVRe+xbSPz
z)?GRFe?BxHEM9Sc>7o_y9Ro`*TwwXK=w7X=y+Klbe!sA~--Bj;y93Y8&fb`PU5`UC
zU|&sTkBp@ds5^A8DpF{3+Sx;|uC6vLe&#cG>Zz+enfDw2zc=PG{&sK1?z8Xj?lw2e
zyTc(bFTdy4tJNzaHZDpF-QCJ9{_2W#^6M=@*Vn~5UtR|4fOdwhjZ(C+k?HH}+puAS
zLsF7bQgSlyHpXA~Tx)Yb?5+N;&|<KoYDH9G=>eJC$K4aAPj8<vLEy;IqYLZ){sP6T
zR>+D4Gc%+_MVFTPPd#FL%;4KjjkV_U=FRKq?sg6d5h;6fqj7%SFHR>8&;<UaC7u$-
zX+0NHb^0#-T9}p-zi8e0!otFi?(WOG`&ZVsZRA;dFE=wY^2xSC_6f-ylYT^;4Ui6+
z^zCcp(opj$`~0=0a_z1DeoQ>RrZIMRnWBwNjIrbvr&g{g;niN3%x!j`+Ojg$Ox4Z2
zTz138jRz;I`*)pLtipF)-Pl-olFCdIu}Z;YhTz{1(`OoA(~94>=bpUOW%2mc_d8j+
z#UyOz8Gc-~(Mw2LB($6%L#;x}TJZ9f^PFD4{8pE~zQ)VP$M@si?)L`e?_xYAwdh7~
z12qVR)qF0@da`DVZ0MpL8`~EC&dZvg>vhxTWw(rsOv$AwHp;4{m*&h@oUuyf`>Gwg
zzUn}R?|OQ8JSHvq(Jtow>yB^d(s@h2L`^+%>wI=jhKHx!<$zyt@J7eQ{qjg_9xoO@
zfAOND-~OM3eElE8b#Z&Un%Vi2j&_Ou_;T4FG@1}u>HT-<`{?a?2d`h>ej}L)H1z#-
zUC6XKbJk4t_q{*;8~5|q*VaZ)j6Y;DP3Lr#`ZK0B^{?Q0lBZL{Km7QZJjbGtDSCU}
z(M_qRK||EW>E}dtPFfT6O8>*XoyG3&%bZ_&=|*f|$i21Y;1bWt1urfr?yZ!Om7O?k
z8mJ!#n(NIyeg3?AR@SO}`ZC&}sc^-Xi`vg6C(WPVKhrpUQP5H^i{fWJ=foTP<!o1#
z?{8#gPkL~maYy}sJJ4JdD51pH{ZzFodC|}<u7Bw0(WNIoM@2^`AM25vVVKO8cXt<P
zLQ7FijSVz(4_ZUf%+Alm5VkI6W#rMUUteBE9k;0aV<Dy+71FfYeBQ$E&%eFB&A{V-
zB{(=AT!2)4$@nbB=O5nn`_Jd|g5u)swZFeD%(}Yj!>3P7A4-<)u&w^4U}-5?|L>>z
zu9BCFuI5=-SvgHo$+@>ja;{aW(N3P$*P!N9>9*Oc`NWnNJv{}g*TdGubpH5J0jiO`
zr|TVE6S-NT<-%^ID9;_cc0HO~e(xZ=d`-iP7a4o)*9GpVy?#94_qrC#+kY-E_fLL&
ztQRypQ}^#@`r1xcCyq0-&HdBmL3vcZ{*U3M%a;X(g%=witbcoJYe#3N;g0unt;++J
zdWo(zsm<N6i*Js7y<F+*Yo;sbWU1y#$G3oHUi9?%4!7}Mo*7a8`&+JytLw`*$vJnD
zc~sB4#;VokcI~SQ-kjzOYQKVJeahd-e0y`V8B|uj-G0Aq?p)b6KH01iOJ2jJbt@!q
zPhauhy6(>pCH3fk(V~6*y`eFCvirVmHF?#x^8Muriq0E~o_ZZQb__J=4oWtAtG|Pa
z=(RUCtJF3xtX{X}%(5ddo~>hEw{G2znxC8Q-MAAYBO{~GQt>WXF!(q_+q~tPXGF7?
zE?efru`t-I_T$!H@4vslAO2;r`Z6ugoPaxf!~Cb1lrb$^IbV22_b+$-eSbcAzqz+p
z`t9xQ?m0O+DxQZP9BkhDY1XAaDev0aqhFV{PF-@|Y-x^Hl320PHosY~jaw#Zc<x`j
zMb>yJe~8t$f})}(0jEHpWWHrbg3cSI&PmN#^LNj&wzerxjCqT{^}~ldzPwiupWh0v
zWlz+A7Dz30Zhv&3k$J=B&4-uy&NjIXn&o7;v9Gpz<MEH*zq2#QSQI#<-=3-+Uhw&u
zZ$)*rv~A(eu(eSIMMZ}`K0YqGRw2h@XVKGw=jUYi9yi)zv~X5$FK<(GGia!I&-Z)P
zCr+L;d^JxaF+aaQ>*^{{>(|4}>(b4-A0HAo&siS2It<j==##N*lCS?0m@ijfUoRpe
z@?!3Sx(^Q=pFDp)y+ZYlm~NDUt*z|Gj~`X7{IasNKr>AO0t<{eA6;DR4q8&vedqqc
zgN(9PB?r1hwFM+4JGX2xX%_y>TUcK1zQ6A8hT`XbA?xF0K}$p~UB1j{Q~O=j)9L%W
zyQSYQhlkIbzGR8Y-uGAk{XMMr_zr9>z;DJs^?yxW?uyNLZCeu-5h1~l0GdK9c`@PH
z{a3lq&(A;p{eC_FgO@2^(@(3l1pK)(@9F#Z{E94~dE>dco}QjN3Lm?5_N`ww&mzrd
zci8T-+#V@YuH9vCnHX~J?6|0tT5)ZO=j4E$MX5S5I|RV3|G3R*zBg{&dUR)J@vNx{
z+_$&q%QGwpT<oSc{otJ3e@{<OX9RWIqJ&Es9vtZuo;B5)S96u0cIneoq6`K%*hEYd
z9qu1#JKWB%Y;PaG`rNG5d?IOm+dfwAtodoA;_0+K?{3L9$;<1+M88WMzVUofUhtQx
zn#RV$>F4LQdM&+VebIYb>W|;QAA>UXtE;OOTMVNA>U;jZQ2v&cm33BGaP42vnlzo$
z=hvRs$bDs%-WPG<#<#08cB}^HnqUV9hO8?q8hvM*fqH{%>dmvNZ4$g@`gUGC8_O<b
zlEJ|6<MVm@vqd(wSH6bF%c!&%{8;SgH8YzhK~J@FD`<4&o_OuYtya^*E=^yR?55aq
z@NL_xqn|r?ujs|?;b8di`LnUs{+;&f2CgY7DlGyXy}hnkSz4fKxQ$mj>(#U<&)XLl
zU0D^%y=~hzi|TJWayAtUHrM|D_t&a$p=R!y)>hUQfv#I;CLPgv78WwsWa(dxRr6*%
za_#B9;`5SuYM<?u+{@?YT6;%CrC#~_WTA6=m+WlGph<<(CPmzylkDs~FMYNzJRAM5
zwqTqK&qecAA35R@v%Ab!-BwqZ_vX!;8@6t}x@7OyYtb7vY&h`d=H{<;C%1pday{I}
z+bqB&U-x6-wXP6WR@NC7g-R^~6>qm*@6lV{+R6$Vy4wHm7kBcp9#9ou^6AdL+S@Pm
z<;}CNfrc?avx-|UB_}0)@skPgSG!#9#}M`XWDFa>T+g3BH9m8#Lbd-M>y`fTWU~L6
zZJRFcsr;OfnAiwfQhaw^-L&B4epi1PeRzDlA2g-!F{$O@;r8h(cpe|`Zx>)vcI&yY
zMkp*IEKJOAjz!>`!kF0D#O&<u%gg;AUtH`y>&u=!Ha)V|VeemMw5jp02w$xI?&h*(
z%N~8dUw_@R{=)-CIlCGTZ*T7@n!#)g51u|<`u+5u^mB6@OG>_QN3Yegx0ipv@AtZE
zEYq^DuS@*+=;($`n+_dlWbVGRzwq&~jH|0e>;8OnpKG<`+wb@LLG5L=sro7^EDRfR
zZW`U$Umu^%RF#pT!NtX8^8NKq&KI$}%Ub*U`KRf{W)&EL1|7d{Q*8bE{=WRQY12UK
z5YMT+(F|TTBll5LcQ<#7K$ZH&*c}ConwpwcFJF~CzbR_m+}vy$e@CBFT3Y(dJX`6=
z$jBL%#mmlBXQrmMGBUG00IklmtKD^Nn|AoRgpZGoY6LIqId`hqYsTiY-#>j~S`d9b
zI4B6TuyF1luUA`w+D>gMe(ndF3TFE*?3D2B&CL@hPFz@$nx3Bg>dMLqDx9EdYYD%s
zm5868AIPSA@*#pw5?j6IPulkJ0cgQ|<Z`=x9BsF*t`1+H^=rkUDMxIN27ZcR<CEdg
z*4EaE+~i{H==S#S_xs2H{{9YHD;W_P$;eRm_iOlG;h8*F>w`7d%D29~y`BH|w%p5J
z!SV4K85%Y=HVh1+S|JA-7?}%RUD2%h@vvP(L*s(wwX3VcC(f7=kyGjYIo4Q3Nr@>g
zE)KM4=Gwa0)th5aX3aacZT-=&mmOYS>7BI4-?@zklo(C^mN&EUf>xHTwRtATKO+h>
zQfK*^;lq~w;!Y2Ke0=Qo)Z8^8L7}Fm1~e-B=Eg?n?Au+U+7l*BNSO9{MmA4^*3yk(
zh0FZrcFmb1b9VpbOP4-8Y?pVMq;l447Xv6PBch^`{`~m3qvYkJbA?64#ieThckkH2
z&~R@?;NHLQ?(RNu?%cJTY3pt{%!l-=egDMC6xaJDbRDv<+F0|m2sB4-WE7-6|58~9
zr?<DaZ}tB-UavrFuU=hU{dF39z_mEh@AqCTHc2y7S1r9X<=f&FRY_gqhI&DeIyB?T
z3PC0&rh;#8B3<0wU+07$XL%O3ucq?L+uP!x^+0OAvzB~zmhP9cy(BFzzU)gBsPp>#
z#sz`m+GU9O1%39@$b)Nti(TE^vi5yh6IYq@>B-3r+qbhb^hg*oF)}i`%00fbv-rim
zz1FkLa=UJA&0bve^wf^(?|Nprw_5h>vDx$c-R@a?wq{>Hwkh@WhilRK2k+mPkKJA7
z+AC!WTC8&9=+T20FA7$Ff5*zOCFiCPXsp{^zP6?6>#K$7=jUleZ`0Y9f4|TE-w$Tc
zZ2J<=$s)0!i5bvZD$p|T=xsTmA=Nu~?@pXFsmXh~-oq0Um1h{I_XTPf_DUMF#n=Be
zy;t+u_sz}C>~eB)pdz(T-oCG+gCpneu2Aj&H#R00zP_f*!p3&!^l5I;pz+Jg%QxoV
zx2veGUYvh_U)Q>$5+FAn>y_SE_BIMMd;n_RxVf=iTOZ$VmV4{L^7(a_B7dF{*|%?B
z#ow>jH|E?l+I#!=*Vpa7v&|C!{`$Hidb?g+?blF`NiDt7=1PW!g0;WD>3;m$-qx0M
zZ%^e6t5PjcjngM<edzXWX?}UTBVS)%FZ}Sp5j6g0|Nl?%#N!iHIFpa}9R&?%@2{&Z
zd3#IL($ezA{(5^*3sgvG(dX7Dd3SdmJa>*yH)_iTA0yDZ`$vx+UD%Qtye0ScwiCto
zc9nAf`}c1}{C+!79mdbk4_eF(Y7@@2E(a|*JUe|lJHK2{zuhm6$H#gP@2mYCu-J_^
zW>*Pk^!7Yg&~gC37;R2xZ56YO3k>Rha~vKY>%F+I7QDvs@2{^X&YU^oE?>)%pZ`9o
ze{a>-td`bR&<OD1M@PFa?x`%cu(W*m?Cfld`hPZ{2~!#CG9FQ_kbsyxadB~zj0+6U
z&&|C&Gv(f<RPP(NZYim%vaVaV4m1XPZQrzM(|&wBE`M>MGkeLaE1Zmsj2}LKZeF`q
z7c|bcV}}K3ozTgXCj(Z7u$>NA8)bTCmMQn;Wxk*xD9~;P3oEOn@9*w<`1`vbZsYxU
zJAc3CzHRBPEiDeyQbEHn`~QBEJ~dUFoneMqu2k9kd%flND%o|Tx3#QauMb+W_xYJ`
z&aEw+Vq#(y&*zqJ=~HcKQ1RTbMd#=LxUQa_Ba2+SdE$~wN=*3V?Rr4-WuWzo9v&R;
z?(OaV`uh6ghlkrEc9m$Z3R@es$Y{puv-!8SXfiP~e|+3;uVi2#;OOYMqxd-=D1k?9
z%>r!*i26D8O6F3~l9BcM|4G?ae{(rM&o*#pQR<(6zu({3S*%|5{ax+`-U%w4TeGjb
z-Q87sadWyqXe{{hGGEZVkyZJ-9!6%ij89h9){ooe>l{FvMi#kpgGN>J?(UkP!fBp&
z=fK9~;}fP$Yg@Bsjne5=OL9Z}mxX+KCu>>6q8+}j1w5pq$e^I8=$PF!Z=w7S4IL#V
zCeTg{&_p1pOY`sFza4ddtw5{8&ds%ceJ5D8(7$ks&Gc2FtCKD+a+R>HGLbUPYPq+!
zda+Y0mqo<~g+5v9HmlNC8NOeBe!HE&G3h853oGlv<Hy0v3a4s^Z%92YwjxAp&);vi
z-KKBW@Otf@C@3iS;@Vni(74vCtE(TMnQ44uV>0`x>H7Uky{BhA{rlyzf8ozhsWl%C
zvj6yYJ6}*lgvH$4{Lk0x@g4pB$5#d~2Q4Bx`$W;%r}Fxlw>S4)J#~uf_4W1c6%`hs
zfp<~uum!H&ViljBaO%bEX!!g4d$zBKZr{#Z*DtM*R;`@R#w*n#X`BWc<#C9Mn|JTz
zf`-cD%*&?ToFZ{Irj((=%JA*m?e~wJn`^zb?!}=wDxQZxqaNXLm8`M5N*w#;Y#%&+
z-2D0Z`Q-ESY+u~isJt!ze%zyt9XpRPEDMs#7F`;&)a%5#b8dU9zFt`BE&k-mlZ3-<
zygO=to4NH$wJuno;CpYDY4)Sl>-T{c7zJ+6i!FI^fpOoyeJ9SIbqxv<;*+=I2@emC
z*-_xQ**_ve0#q2~-QBe?`FI~_>GjoBp{Dj8f?{HA!OQ(X14y8~C0n<eN}1(!oSSPs
zTi5JD`t^0O1w}<hzuFz=9e>WU476`xng9I0o14=QpE||$_xJbfCl_y#4b3_?$MVMR
za(yw~sFoc&ELd1sAFkj3@6fK&*B4d>tLNO>;;Fq~^X=5CH(N3;DlJ*IY*EtDE{1t^
z`xgGY^CHqKSu9yXYPy}bC#<RZ3e;4c@~v@MkL|wS??Bsv5^inDys;s%`I)=FkdP2)
z4HKx4oi}fu+tlkfp7YtfRsa9vF+XTC$?xy)LD6?=ie~fb@byX8*TsSstwn9m%Ppv1
zdOa&=&0m}2ZCU5<siW3qoQ^Io|Fdr1yqWar$;m}UPfr~>cFfHr|6a_SdwXxMsP&&~
zrD|3BN<}MdjmDcdZ(N$$c#k|f+U;6b_peyb6f)K`Rm^izOKWTEqCcB-r2hy@OGm#k
z%)7TobD8gKwWg*fm!)1)TfCME$;rtr3SRD)1e#a=Zdvzd$BUbrmlqTl3tzi-?a<x3
zv3ow9(oQ<u#%oo%|Np=0i>pGlA3k`Xkdu?+vbXB%kvlt!LCZ7z;`H_P1J_1vO*;MO
zZu$MrZMnC(#KpxEb8~f9g{)MH+M1=hXz}8sXJ?yt-;IBJVxsaQ-`Qr1a&B%qbn#-K
zi;GJKXu*^VVjWfG_4V=kzrMfMuc@tV-Me>hK}m_o*Vos@FE95OU%7H+)bZY)9uYAy
zu}8nYzMi$^$PpLC)0-sBa%SAy#KO-0y7t@5nKP5_>?j1ee?^E^;O?^AjRg;#3O_yZ
z1g*2OuiF!NeU)AP>uYPj=IyWkzOJCCNNAG|x4*yt-b%aQZ;UT)$qWwMmJ<oWpmm-f
zZ>G<Gc~<-MCJtWStGj*g{|&S*deZUY^78(I@^W!dKwZ5W`s4TSZqLbTotKyUOP8+w
z`SWMe!$Yl$^6u_BbnRML$f^)e9!Vn?6;;)jw%@x%wOziyyW85|->(t9ZB0R8p<u6+
zsSvlAjsU;BozAx!NlD41Z*OiY>FD@`tPFAm`C(^Ks-TdN(!T%ys^|Xs`0?YS?Ca|e
zojvOdTBN1sJF8>;zF(&vSO;DCd+GbSRY#8;d6CPm;whx4s0iA-z$0biv18{>P_rB4
zA5g1c?qeB?0*4cubkfewTDtk|!^7=K@9yjbtt2~i?_S)ETerHhuCD4lH`lsbf8P(M
zl+;ww>i;}5EeaP+NR7O*K0ZD@x}pNK81BpK>*pW*D}R4aG<dn6C@7LrPfrv5_U+rD
z>(|4-yt?YWCT?%kYvXN;-aRhAU#l)<nx&GHlLK0eBw<sr!Nbo_?CYzm!cR|4y?iSA
z%3h&E1=8EIu4+Ae|6V^QH@8*i^sH?Pc6M<-b1VW)a&Lv~*tLsms+a1Xy?b5X-`jh1
zWAgEmzQ>OqDXj`!o%ZE<`>XPlV?B~p+d-@AF3;zYvx!KrPD@)h!zi`u!`H8(T2sBI
zXovf?w6}v+c)oaI`t=@1;yg2ZTie(kDO0bC>S}IjY3abdRiz*Q{eItlykGwHoaoHC
zW=8_<+LpbU!NJWfeD2)2LkACn+BsgJWq=QCgTC`yT3ROk`tov7)YdGgr9qtX^75b!
zbrUB~Ui|&f_4V<fRRV(h_U!{@VGAoOP=mAkU^9F7+1cje(P65&kJabbD5XS-#n*nF
zdhxsa-+z+77OTkZs{Fi6!lGcoilC)k8@6s01%(nQfmBvjTK%1<3EBSRG%fY$`PA?4
z?kd^X#8_Bcb5HeB&APHeahcCdB_m_wt)J%FR0j3PSO)$0`I8frA+xi!LGo?<@_L{~
z&EnIMGZvQnc>Wb|+FgHhTkdQQ4i3<^z(p}Tix!2ik9%}!sdv@+`LkzhPt%LlVq#`)
zojiGRz{-$CSyxvr%DufU>EolLO1iphZ)}?NX`QI(WRa`iUUZ-3`MTDL1GFc{Fzbp&
z;MyotP&sgFy1stYmJG#3ix>CWEuS^%+g6RGfuI5S)~(ss{Z4GsS+jPntCyG8#OH?F
z@-_6>%(sF@`n+B_6z(d0tp+M@+}zsEnJq1>2(0~ba<aPX?{9Bgo12>p3JL_?-rg>L
zyk8zPB`dZ`r@Q$1xv4MiWO*H9IMydQf9d<!0I6)rMS7S2{{DXS#l^*@AD!n~l^$6>
zzb>m_|NZ*^u{^R?Ar+OCoKwA2V`5@l{{H%Ubawte&2R7Tub*meZy)b7+syaJj~^XI
zsi#28&OAIi(ta;??>};4qH=3{d;5k>n}jy$bT4#n&yrodWaGijLPA2Ib$f?eINk1R
zn-<sl1%$}NPg$}=B{4G-v=%gWcbVx7e^2YEkV>Abz1HRLIvyTw=ME1KPt4BN{`2?m
zQS<vX$=mFrJC+;PIyf|J*uMSxk;qriqptilHcJyc^x?UrlgQn2yVFywRxbH#ux#Fo
z;5!k=<~&wP)&MWs;!t#nikbyV^D9DEPus9@qu|q1Q-%Ni`v*#-k3K#=KC9+g)w`_7
z$jGE~b1WAn9&Q7d#0L*LURfI*?lZ%{@y_1r@X6<89_u70=Ppflt}WfWB4Wvk-zn?P
zo4|)&UewQ4X=$3ztg5uAeoo!rUk{JV*B|-u@i8d(96562!IP7dEeakuOw_*c_t)$7
z92^`C>(}eI@yqi?M@Q$}-zN*&p|GRy@rHtjhr}yHq2oJW{5Kap^#U#Sj@X#Q>eeF>
zc<boGdcnwPf-*8awZFejEerg&RnDe@!Q9;Z$M4^dPfS!^8Y{za;OFP(51&78KX3P&
zCx6dJw@mT&IHS9}%Rx&D3ZI^u8WcP8mn#=1=fQ=}?GxtDkH6(wxpGg>d#S&>_pFfk
zdt+lV2M^DYL#^C~d3Sa^FOzcytpXPpZ$ER!=f;g2dp>-=Y=8Jjr!c6ObmaK)!>3QL
z-qP(1buozga%rOXZUz^ZlwFh6{U7~)zu#AMOp#UF2FuTOk`Z|{nzty*gS^J1Rt
zJ3U>$UBwgB)j8HH-7cu?_TadDz02!sYXyacKPTxmKttCnwy0>6UsO<#P}=!<yxQ8@
zE-o%poK|+k@vU6B^2F)Wm%UD(KYzT1Qy8>?=iS}i(}PZy$Xb<fh-!x&xv<dLd$-0H
zA*-S%9BRI^j&L6Qa_3|0;`**jeHWv*<#fjFtxCMNr?TSHlas}k#~&Z>2hH+KmJ=3k
zPCnkJXk#;H^7;6r?fLhQeR_J@u<T8QpPf2<0gIB7mg*n-=PoY)lkER|VAj#q-5O@G
zVcWK2A08eCEvUP*tCaiQyLVOJYd<_-4ABymk(J$gNjq#!M@vh~^Qb(iIlrERb|DlM
z7hl{_m~3Hbsc2{@2<p~7KK}psy}vDGj{gf~>T9P@nd~a!wmHD0-RRH;)@(sXkHvg{
zcivbU=6KY~WChP5rnTNn3|<5Xd^XA!QV|gn=@9>2{37U@=PKvy_M8nu%5_<Oe`V|D
zA3Hz4F6?J<-S^yn_KKhHet-S_t+gib!^^(3+uL$qzIl`Lt@A_w*L&6PQ(s?OyYuro
z>&-PkKmGZ1TL0&h$^M{aUdxs*S9f-HK5JKa?81c$dv>+ArWO@#x~aaw;m6)%HHPy4
zdhBd$=3KmZvF88Z?=RoI+xNi!|B)judAnXN`||z!^3|)gFJHcFS@6KY?)RI`F{M{S
zCFSJyJ$Uc=T0&kPv<3L{m&^X<zeN~8pn=u9f$zeheZO9<UK6=lO;%Pm-R9oy+t#1I
zMm5wOmn~2E{_d`%jLey3zOy%_oSani<)Zt|&FTI1;8Sk7Pbl}>Oxn0{<DUQjep?nj
z@vyS8Dtf(kds;?@#`pX6^_$NxW;K=SHIeG={#F-X|F`tpo134f&-;DJTmS4w)B5we
z+wV-eoxk69e%-Ikx_>{PtDIaFx_VRU>1j6q|9sy0X4C0eHHsH}#6NHT5)<|FvuM=a
znjgl$K0Q6Xx%Bll%illO?|e3khll6M<9_>d|Nj0i{`2EwNm<#mkH_WDckAz)5xP3;
z?9FQ9|6jj;UAlh#`kUz>|1vP>Wb|HM?ms{8n;^rS`K7O~E#17?`1iNB){j3nv-3Y|
zlg>MF;=~Eb`?7!c&$TMmI&bsY$IZ>H=+Ti*m6MBHyFVS1&QB>QC^(nT&cMLX!2NLT
z_Isz2`)$81Kc8(PHFMs)eH`M9e~f?ButIEWXkESbCObpHzdkwJs&ns~wp4t4G;{s+
zEnByyetmUy=kIsBjm^xa-Q8XO{9g6@vllJ|*!_6WY`I$!q+4%^yL_#Qy8paCm*pRM
zH0(eATpJ|Jz`&pr(><$}f#Lc3y?bqs_siSA{+N8c?`+LpPztO3`}O+gyXE&&Pfk+x
zoYX6Ao_4s6xAN7><wfUhzb{$)_RfF*lUJ^Ue0z6y_EhcgbHC)EW`Ze`;};jZ8{65<
z+x>2rw)b?s+;5f)TLc)b9Jr&m<wVx~`FMP@oPEiQfJskoWv^em@7r1P`)AsCrPCgL
zw!c$;zqaz-&gVvUcJp4Z-~VsU`n$W!^V!(g{`H?mJ`#C{MA_S0Q`_aLR@_WyxZuR{
zf<ZUu@2{^n_t)3g{eHW>q@?7G&A*?|=P$pQk@EM~*Q?k4{QRChIXOAqwhkN#U%r%l
z-KrhF&gawo{S77M<@29^Wr*Q8Z}&SVuKMlPwE2emH<z6=E8Vtov+vy8S2@Ayv#oBQ
zIcJ9|a0R4h^Jagz3a|i3&Dl3^z*^t}U{j2(e?tW<w>Pu%rzIpLEMsPD*zX0(JZ5=!
zW;}fO@Xd{l%CpUKy(WPMA#Uz0PXG1mSJB<l>#Cl0zg{kvu`E)Fjg8&;WRmwJmF#P4
zPVTGyUG(F_!<fpaQ#~gIFZX+TxBULur_<x-U0od>et-Mky|$j0?%tg{Z{EC}e^i-1
zsIS}ch->~)Q51iH-9(l*u!m0CcXxIshWe=tvI|<je*5;UkzMWtxBi|9Cr_R%DJ@NX
zes1p1hwbu4R#sM@_ne(={`~Fs`{#cAs0dpVVfgvRVSf8L_wL=};p1DjcdzaHJ)iyf
zWGp6x$5p1Pg@7^(IDvr)F+N5shi++U>C@A6qc>$=UngT%V_|-;BH8ZGhr@TuZs!`G
z&oq(B%+9ucT*`0vBVpaXU#~z*KqTel&aL17Z`RiA>uD(|D*iSfj~xA%3N{i>d~RTn
zU2rtE>gCd#`)aE};|aCrUc7iAd0+4^|KGoVU%r1o|MX|LY7nDAtmx!v{r!K6Hup0u
z*eYXHqG4V3=EP)wyP2t{r<wkiX<*I2yQ}o9UE;k>;Ix38JZ8?Vg(fj@RDcqY@7&z9
z^!Zk|kp;kNZr)suo-VK4Oe^~ajf!Hkzw8XpR~P>J^78UoJEn$fpPo*SfA(y4{yFjZ
znu+t~%}bll400|MANYTvo}pmhEl@cC6@pTqn;FoLDOX`Cfl9(CE=DUD6H0rspr2DN
zf}v{?2e{ma>Htw17`jvh7a+Tnfq@|aLzjn=18Rz3SRjC|Yk~{<+3F68=(-d-F}&)8
zp-TwEtF0KiMgs^GnQ%Pf0%(f<k*Bb=0Ps*?U}zXkO-P}^Fq++vLxW+oJVFVM(E=MK
zI7VwUl;9Yx@==0gv`vH(9HWg!l;9X`RigyQXtx6;I7a(rD8Vtn9oL8}Z$SOshW+_T
zNlL-N!DsD~&*{YOGSLoOlkp8ajt6xucOSUh8Fl8!5tnQ0-k#f-{6FiPW^vlbN2))c
z&2Cmg>Y_Jv`+&Q#x@lQitByS1J*mX}_Z-UtgX4X?DOp)wU^%F%1rs?zeewmVrRpy;
zzX?J`LDZk-EvCOg3}pO_9iuml7JmQJ-v5hzq9tz7XK$?YE+uk<WVfk7@5NLHm7E05
zsLrMYMGh`C>5T##?;Vq0Q18ICar?<dyVo&p-0VHk$sodGSEAO}j?P1jf+l?jCq&=*
z&UQ%ZZiR7W`lk8(KA+FcG4?NCrO!U_Ju4ONt;iz~G9kW~m*n2QWxQ<J{rBkx5?AIi
zGL+xh`;W)p<~ZX61!3gDiI58>zG30*Gkw-wnP+6W_g>Jk#}g}f8>&w^R<x<ld(2QU
z0URT+P}j=1y{#qtwrAVc=ROBDCZAlnC09F!`N6!R_x6W{&lfUS+&~#Z3FV!<=BgYc
z!yU8p1q=`FU0G`jGYCpI+*BBf!ysZ={2&iB+?ut_^Y*r_={}+R@1IXFSYZpwJRlhc
zh6YJ>u+JViWY1Dtz51|^T6mWK%vEvunvXwvv>-0pJ8)kJ93KS>w&q4Z`utYq@U7xy
zDN{~93AwdR6f6TV@56RT$WC~&|Krc7w@7&-AawgTh#CZ$HacvE2n+@WhtXj(<lw+Q
z5_I6s?y9d@_i8?$1&v^PdwW~f{i!%N*ZO<^b=#j$CciA(UH>yOCT0&e$_xlYL*(Xw
zY6gb?^TXpRRp-}!i!?JgFMe`jVoq-E)0^q@&;I=U{PT~;{r5lZD!*5$zJBkwTfXW0
z|9*>(tN;7e=JOfj%ky}V-NtZ6fzj%K4CwHlqHk|*g0|t@ymQBA(w;w`PFH@p=>GYb
zbpDfW{e3&0ZuPhQdS%|`xpU{LoIG~ySP2^<^MMRBUK<T^*1hHP>t?mKw$8qnvTw(Z
z8R7A@rtx(@Q|o>_Y`?wh{<(90)22`Ve5d&Q-Ipsty5RVLjKBisGaI|b^`A|2mpl3C
z(<k5OuV245-*<ogw%p=(cXooN^(;$XT#&uX3D*Q-oM8vKe|OE#qOh>AZ*$hKS@Y!A
z*Vj8sUS8Vw{_9Eg`A=?b&Axf##*WFt$P-Bn4VFp{>@$)<i^Rml#lO$_UbR>H{`>34
z<?H9L%T*}&+yDI{dmFiwXJ9xZ4zkI*<VC>0ACLQOpHDvd<k<J$AJ3ZKe{!gmyYl7I
z>6hMCnSk5`#|Ip@f+OqRsZ(BhvAecB|MThTY0pXQ@-+qV-*4W$>AC#!$&-`S^I!ir
zH#aZ-|M&a-lCnofI_FpvKHByUIeZW7-@beI?7MgG&OTT7^XYW2Y=#--OeGDLWnW%g
zoMT^axBuU->}k`d=g*1XQJ^^2Pu;y=?(X&4vhwoJ7o7Q1Yis{*`v)@p{H<HJa$`{p
zp8GXiU*ylP*XxVl+}P;V%`hYV?k#49AK&9D9=87Z`F#G*2hIF>b7J>anMOxPgOVtp
zyxklX&>=R)a{a|`Z*8^xzN6w}lH1}yGc&VyxANeA2Qd=NDw(Yg$VA7-gJ)H@-><W_
z|NAAlPsVc6+O=zIzTYjkEPi&T_x|3m*P?%ZIL!a~?e_a=1`>Bl`rp2NTVgeLj!osK
zyz{8hkk-Q>n{cl7%SHFf?{~{L@7+6he*Hhoe%o&mcK`o;w)uEO*u3uY%aTiP%f81{
z|NZrKj%~Hs@jltphxzSm%+rzm&cI;o(ZFZ${N3*N`{vlyS}pgVzwc@OxjB}_m!&WM
zUw--Jli%<6&wpkE@(CO#^u4K-)q`^(4E9Oj<{5+oCL2a)1;F6|BSze;0L<f{nSRWf
zfJrF}5siq3zZtXCa&KRoXBhgo&c6BJf^R%v-47U$+K$HSGiR+?$7eh<W~FWFs;a$9
zdyXp$LgwKDdJ(B_MrH2pX+LVLPj2`&M^iG@$a3noTvo{BoP#N1PA;L32hvmoSyXWT
z)ipT~0|_6<8J$!^3JwMu4nZb?lR`uDn#@^Sa-*w{g?#<}mxrzSmNAn34YlCt2)TsR
zeF%kgA2^UFY@aoNlEQ*X+j6~Y_RUR+s6IEP$7tppuiM)YanHcOFoPMyZFtq@c`d6S
z$r=Wa(Y7seaEwmkp@ar;lX!@-tzlW_rER%yC4;ZN|86Y7lXV_$+K*^Z0%TxdSg>kY
z=B8a%XHtrmew(uL)z@i8a{Vrl@`{0h;eZdU1PsO7T{HHD4r`q0NSw6wmNMKPzAbrg
zQQCbB3=C)32n}N}FffdclflCf#6TP889o67Ppk=LroNN6<z}Csv8rzW{DTPr)odV-
zgYf|$aOumyP`?sqB@9yNz;a>Xf>PL80B|Zkpt}X{I0JN{%Aduk>6T#!_b!w{CXn$4
z(vUF;5F3g|=RTkT0ij0cJ|N)$CFwl(ajyQx?)d_iuMhV>o}UvgyM3dmb!gIy2MbHA
z6fz^c1*$$gaQqO&rE9uj;esz=8jVS-RwzU`E%5yx!_{=eURz05*Y?RYC;p?;<Z|*4
z2k`&$m?XAeRpikxlaTM_m355?ivz#ke1GoE>(ZJsxo^hDpId)UgZdLjSwSlm7@vUw
zGX!2>E-0I%a~;<F&DpywGstVD?c(sm4-FPyTmfx~GcYu?!j_#iuwFLtJ@(l1R@vfj
zQ{s5pv}c}OrUV;*Z_rf%4?{9AG_VGHy?pfftIFhC#Z^YWx7RJ50yBYu;f52;r4bR6
zRaS3xhq>6meHvt}6DGjGz>ts*EqxGTSe8q;Lu){|B8N#SJ0X3HhRQ1@zFwMJ)4ya{
z$fTJ_U7ZK25*_^K6oP1m5Bs4(Vz+2nrjeZgrESt%mw(AJh&Y*J_LVgj)PZ4r(!&ih
zxM4MPfnJTv(kbt{cfR&i+xq-V%B*d%-kL|J7lVuwn_vv-9j|kPxah-1-$`q($${h;
z<~P73VZj74m4PAQde$tprBiMhSDDK28B6toS_%n%P-j7uFx;3rYuU*P8_(N$SLR(>
zeK0|F^UaVJK86FPP$xl^ZP1<?wChKW?a3wI=FIcCye(UEDaf21YOoN8s4Ls)Iq52>
zp^)Gnu?l0De6AzJ?GUvf63dXLED_C!5+X|M3#cAoU|=9BdNIdXN4A5~p{X4dTMRF}
zFPmsCy)y6O>W2k0E@p&4D|2q7p7;T$tXXQ0KdR*J4y^WC&(=KkOj<CsLmiExOlxV$
z$DdV`Jl|T{&RmvzJ;)0hUmH}BB3EYzG(CYbte(zQSb+j|4X7o1j+mJj$SfaB4=Cqh
z4kM9S$RP?JsPPMwp(PcR&w#CUf367HeBKak;yXFW>#gKoDZX~eUbn4~9T6KC=B#FB
zU~rIy=B^uTzL!&M<}JxJ&+>nHHDSY~n>nve7lCc4Q95^(k%3`>95mbHGzWQoSKWzR
zKtAfmp>#D;;QCpFgXRF=sv(>|quBTIk|{yeZtL3)FN|jcZ=Yz$MGEj4$r#Skasm%4
zHq1ksaC;V^xwQNI^~pY2=U<*Q$=y9Is0-AcW?*2bLb5G_1F6U^&RYp7WWj!f5M{)4
zFh)xTNMON8%pS(z3!!P*;CaX!UWnwD=(afUEz(T=0Vc@&BKP9VSv|)mZ+YwXR&%cu
zPngkcUsrI40OH>R(;yvN?!{9s9es{mjk+S&JUN!&%(9_D%`+?;d7x&7wKqohV1qHJ
zqJx+ZC9#ZJ5tHi&T`@#k2hFISt`~c1WAgD$_5c5^S+nNJyWQ{4%`{G5_w%1|`ne~d
z%~fa3@6S13^UV0?tML7^;{U!1x79;*4?%%lrp0J=V9xJz<@+Yj|NAB#w4tr;V|RQ?
zWu+x(H(Olg)2aM>zh7Ayyz~9O-$j4FUVr}M<Kv$n`|IaazuT#vzwhTWGaYb&1TqYa
z%Vs?VO~m~8_i6h6Cr_uxpYyN#G+D;B%EYti$%%<~Dxc4-{PD2;^KtusA6I?f_wktY
z&wJnZO@Cki|F>o3rzd5;XznxE-@s>ZyzcMo`1Hz3%lm)dmFvgve%L1c>4G!=Q~&y3
z!RO}LR$r~I|9Lw8+1~H>PJ{Nas8s%byS@58xakLW6Nq?|1DbgHwtfF!-S}UZrf({L
ze@}azyj97IPxse9`@a8w?Y=)x^`C!vdHLrd@qH6!=k3y*|NGAKPe+9PQ;Lf>U%v}7
z1C9@z+Y(dFz#xDB=jZ2}^Y8Eb9(#X#emrPO^WB}DtMC2(zW=}N{9jj=e|pf&|Ln%b
zWYEsUy3e!kKUuka-l^U1_sy37`@+4}4=v=tQ<~M!=av^8<~85*{#Sy*jz8a5@2vQk
z1Ty*2k<LF4*zG+g)jXEIe`5c?uj~K(d2WAxalhRx|N38-|MH-jwqz+d9`g2lJoe|g
z{r}4QU$^Dz|Nq<k&UX^KT*ZT~*X{iB=d9oFnG7;2dIw~0B+Q31*y|W&6Z+oX-md@r
z+}!H>Uq3%TukM+*|L?ce_o{!t-Tr**^|;fy+wYbg{TiLW*L3#m**gm!9%}#hf3bW2
zv(5AWz7f3+ns7VZ&L4le24*OT-gdxSfA5s(aaAw7vj6}4zF&JSW5PYo3yjZh9BgL)
z+;0CzQCvUn%)PzU`tkoi&;LKiw))$X2M3$O_kLfu``xMR^?RpnPCx&w&-&etn!j&u
zZoauW-QNy$H{Xl@|6lso&$@c`s{a?1M$C_tf7kiBK$|^xzFxOmOP48Op6*pSh6BgH
zpUtl`{{Q!VJ!o%e{Jyf6mzLW6ezO_0KXG&Y|9>hc?f-r3Ka;i@bWYXu`0sD?>#b+c
zo?ZEDX1ZSd?K^kQtPEaWbXs?N#Q~7F;J6|7gg$6S*twnWY4rVHVRDsECjR+6|Nj~B
z{XdR^%&&ahYhLu~%F5I0e?R1}pYeQtz1{l#|Ek;;2TpqOI{tsvyS?A<$=KJ~<nR3&
zw(rx_^-s3%|C<ZShc<t|T;BO^*Xyjkx^UY-j0HlVEL{DtRs7SB$NlNGwYK7VF((?C
z*^7RCd0F!|JAU_{S+>>RQZh4N)_(u@u6+OL<bK;})8p$b&)a^FIrg|PuIA%Wn-2$=
zZ~qhnnFq%WvQD6B#&!Gu{hDJ@sHE;UXUD5-zqwYWNA(x|-#>Ng)HyblM(Y0a-V`gr
z_3Vzo(ttfM4W%czHv@YEc7p&?!<4~6-%B&LX5YM&plUz=Wtq3PP6+}_A8<l3%yza)
z<XT%MP@6M*Lr68;Ay9@jmK821VU0tunltU#y3Q-0y+E*%1MRq)+`Fei8(JWB4g8_l
zyUq#MA(bmg5d*^qK_7U>@=FSRn_()E>)@Tn1VK}5O=AXzXb*T@zTqg=&MVj>+|V&V
z1_p)=N3q8hNXh{mYhWFFXTsu&fq~({EKoKCi^GWnL$kL*wQ3$Qpu=DtizOq00%|I}
z;s1cy#CP(?ib>n<uCQGi-h9w2ZSzXltXjf!NJ9<Og=5#i(Gz4~cvA%J05LG^P($h-
zFgUEI-hj?%j~^6oaO{9N<VCd*@&q^a8(c494xDXxt@F!x`Ey@TM_*9qm!#h#8Bl{E
zVLPZeJs^fzCd;caGce>VzWd?K%SvI;<ZJovhdk<qeW0Z%8=^sN_5|)JLA&@TqI5j@
zCowWGY`gf#zPRch3j+hgv-^+cKU6ta2=aazKd4)fvl7-Tj_{ag2^wE3vrD%C$)DK|
zYO;V>2z)~lQGP&0F((g3hoYcC1Et6eA;?fv!bcqS0@&~xB~Xd6ARO1g1XvLR!?RhS
zit$A#u7L@NvKiSR!xCmADny7l!vS_Wk8VOT4#f6^@=T0TU64#eKV*eEh<#vNCiX@Q
z0|P@bB7+~;rirWUH7JKBY|wEm&Br3`3uOMQ@P6Z2TDpVJu)>PvaHB_WkT>(9?v7?X
zHk}X`mzdt>TaN8r&IcbodoXE5qf$q7?3)XY0WBii1q3g$=Y+~laOzBF|1Dh?-(>o4
z_1nwO^=kJjIPd#@XY%>85C6(AFfi!8P@kDy4a$`a3=ALGALoLH1wh_`;sgs&wuW*b
z6qc?ysK9_oLP;#+zN6dLp<x52=o>&MU2cQQXt2#-;)dL+RbH{zbI)glY`^Wh{(5#b
z8-odQ0~gdv2wlBOYxCy6JZ#dr{+S`mjc0!SYAR^Oa2vUW3u<Mr4!d63c|Ls7m)r9$
zPuR-C)*gI)D}!u9t~b2V2)6Tp=@oyY>)$vS9@tCeV>HVT6EjgU1lHb7^4S7!PlLSO
zkQN#`b=SJv^DeH)+deyP{dLepoJ1w4lmkhFaYOE!RjbaN`(`YWv&D94;M{X5*REd&
ztsN<t3M~=9$`}}KN5o!NwTt(>lwa-Ve9cHg#xM3d$fO-!AQGyGfuTX#$^K-_ZDj_A
z21WCG7^AvvSb9Jx`auREAC1w(k|YXS3jmU1V89&X9FogSk`_TH1t7j+xb74hy7Kj|
zx01cD%67l}T9pf0=d;Za)JB1-U|=x#v})C<H#zpr2i<N5OI>~GlU7^n3)+`~mVbKo
z>{{ntvv1Op``_lYtw}Yon6qmgX#Ju?GD@5tFuMfK6*t6?a^zPBc7_Ifv{H5YO03!O
zz<X#3y<?dTqddf!316<3#y<KyRpsxt=O!t-%?BS|DScaifPrB@bkOv{tdA_vL70ZO
z%jT!71MLfmafhaYb&~!EKrKPAVGS46AoCLo80R%0s)xlHdr-rUfq{XC;I^vav)l%=
zfj+>6lc(A(q){#dAEe|2E#Mg#7z|pF6Q65n=*+oq(+zH9RC_J9ntO81`t_ZlZFCF`
zx+u!97di|K3EW6I<AB&-mEv5;(Eg5h$8IAz2Aqx#6riPNth2+TtpspjK?xeR5{^Qe
z1P{)KU{+61+Zh;cfEPC;ya)-Mdh=!-TXXNW<tD2x&ph+%*DTnu0!VGcLU6Ptytsl<
z>gYns4v;DahJ*}oQ6-UtNGTAB2I*rJXe|^51_?fBaRgBVA~6@iXdow4kP-&Wp3dkg
z1K@yx5u*VF3kfhinu5T=03(KT7HgPT{_)XK(1yU7^X8p<@+1XxG+*#?zrT-v->dz8
zx2L~9|L4t($?l+&3SVyk^^akp!oVP5CY;O9@Zc3_&gJKe#r>Oh?3gig=1d)Z{pT0m
z<<GvnyuA3sgM<5P-`}_q5m*2B>z%^mveW0@FFLKui#Ea9HkCm(p{4fYQSqM-n)!?V
z{P?J&r>EvQuj<vxJEhlSLEG;>y<9&3-(y?QOwpOMXH9KI5$<4MV31%0_0u2h|NY@G
zzp<g=#OL#>^FHT1KR37X+s*XPH`C`o{r!Ib|M2fS3m!Uw4wGD#2AT{(7@-WB#5uI@
z&!^L%x!0Rpv#+N<|NZ^_{hGh;V|JBjg3cN&dw*~4$&)8R7jXRi^?JSZZPb}lp6#96
z*cm?DpKD#N7aSZMeQx=(WkoM9Ed|ZZ>EE}uw49kfuTqWQ_DcZBpsQD}f~K!NfBtM)
z{LE+B^5wJVAht1soW-NaXmx<&_tWX|n~I;G(|tbIFa7h^{hKyyn9$nVdiK72^_z`0
ze?A<pe9*`aI(hWT+wJ%FeQO4d6M}Sual=A22X=`>^ZPZ$b$`EJ*L~i6FyZr8Z9{we
z`M=-qw_olzcbD3428M=*L7}0qcI8#OE#7rEuWE1HZKS;^2`QWx7~O7Mxe{`2p6%|Z
zf9~uo_M8-*zxQj``^ww7+n=spzwcN0bv-@3wDa?9r_YtOD$!`?lil@bKQ{w|$!hF9
zII!aw4)8ub(kX0N_~=M#`t$Si^D}uF7W*~u865id_V)D4%l)4pYUKvS!?T~y=hx5M
zxN+l~+uPrFz5jXE{C>*&dwc)Cy0!gYm3DD)arhr|28M>$>({*&n!jG<<#yZUirJDp
ze9PBmBU)kw&ObNni`W!D^8rm9P7`A^IK}dULHSLm`n(gf^Y_gJ?WWb=_akZ2lSfCp
zBje)EH8Qgs+1k!k`T4M2zUbedpJ&dTNjcsp>-kT9e#!2;r{8`5cw9ccwA568&xb=_
z|0*yr94Niw|Hv^2;x`a^V7~AI=AI3Ie}7L;OjLC5lR4RM{|}ZucE8_u`qHIK&q~+t
z`Q&x4`u*OT-*30izRy(g;laT>#pi87>j*ZbpP#p8-MX~QOwH~0>#F-?EH7PiM@_X+
zDh})th41(OuZyewdKI*|;raafb9c+{&z-F9pH^2__j%UFjT?LV`{TduQ=eZ0nua{1
zKEGyCZ*Q-UukX{J&*z^9%@yyh{vP+fA0_QD@Gvr39q8Eoa@p*nH#auQSeL!gUmqD2
zwd;-a#mP@zTwH8f^(Eu-XOKtXxIxh9-}&iqE`(8_Jle#Cgam{f9Vvu_1C$)Z?a+V6
z@5!zXn|Q2HqK=c%G=fc9vCQk1?vd;bAGpGTGP0~i*R)P~B&%_oBd%#1S5l&KQuTp6
zuZam;&&nsxzFS&;eqM`>zvbbYKR<p=hh;4-M2Q6TzccE1AOnMgDst}tq$&a2K>)E}
zcm+lSp9jO>si2t!m<ABt0Pc@~STMW*dA=PiXn<jG2u6RS4Z~oRQ)fWt9Kgu(0r2Tq
zkUR)WU>H0aIG}I=<I%tY2Lp&8FXbdxUxp3tH(bu%8nspD^s@9dSKqzMtFEq|4c;LE
zn%vosNT~l$WNm$QYwO>>{{6XCr=sTC@4x)~{Cv=WGsqPOW+K)b|C^W^sb=?o?XCM?
z=9vDx^6}$(-P7>(*XLN^Iq`%3+wlE4RnUnfhX0LgeGx;2AVV1#9;6@~01;sz&%dL^
z2sHQ@7)FZ`cu<TMBk-UY%~tTB7_FV*LD7KObh&Zw3skz{|K+T$S&`Fx&qu7jd-v|Q
zZ{O;ES(n4A6<DLJ!8mzqRO#DWb;pn2H?vJ$dv5;ym!F^e+lxl+mWCR%0M@EHAh}8B
zG|RR9p}%L(+pIR<%I@FR)W|xmO=ad#l@73GQiE~k{$Ht=mHjl}7N+04whTT21yx^Q
z1ak&dfPrDOZ3qvF(S|cTC`Nk~@StFzep_kB`)RLH*8(t%cE8{OKH4{h2gPXN3=fLo
zQaJnVeSd%d_Xh`?_2T#4Id{&_JnznntE<E9YtKD=m>3-$eRo%BHm^2p00`{;hRY5O
zd<CauWn{iQIXOA+{=U1Hm;2wockkV^v$OYBetwoe|Kq>EzvtOjUu)$SzlOHu$l@i-
z3x?%4c9*}e`uNDz-Q8VQR<`u}ySs7w>+Vj~4&PP(|KEMP=lAwj%gV@<yu7s3bRBrZ
zEZAZY;b+BYbwKmmr>Cd4ZQpKfWAo?Zn>#y;@9r#KzCHi`x2LD4@3(pU^YioCKR-4e
z@0VX+tOe2p#|2y*7a09E^2^(me0_CQFK*9|_UG5v$N&HM?|jYQUt8Px<-fhSs9bN4
z)KGa){_WlTtFL$QKKSu_`SxWKS@eotDG2r{P7-L!JLlNMYsV12bs3Aa6h8~QOsoj^
zk&`D6x=PKiVc@;!7&QA)!vlGiXgwA~?mhXN<-fl+jk{le{X65Hp9~BQ46+F`@9wSM
zK6UC;@n_oF+P1a7wpf?H`}6ek{hH6d`TPHtrJtKq8LN#tWbXaMKEH~QA?|K7JAc*d
zwcF!nyuY#W@y)N(f4*Ek->Uv!P5An_+}qo7*XP2IZ2<c|q0)j;Hlg$Fot>NA`{ni;
z)c^SKaPw>Z;$L50f=1@k=huF_^$pfI1nXd!)-8O2aoUYjr@YGF-Kk8h`~L3kD$rQJ
zeJv=a@9rpEoPB-W){PqjuU=m6U;XKcC%>FcMso7vySvM`XJ22p|Ia`1_?nBm-|zc<
z=gpB$;kg!tk3#E^LYAQ+yx{4nsq12Pe!7!WT>P0gm-)aZ;RVb(8=2Ypz8vPaFZuuP
z@4d?BbJIV|*Z<jgH0fd^GyA_UJ8y5#-yWf3Rrcma@#mvS7uWCqcdK2#?#8cQRm=V6
z{yP1B{rdHw>5c#2?U94-fcEdr%&hr$cU?W$%zpoZ8-tE9qtyW+>$*P`_v?P=itEL^
zIIX{b&8v@(kH_vRS?S!)_x0cJ_u-}Q@9i}+H^03-KR$YU-rE-!7su`{d)xYbu1)18
ze!CwFil3kRdeL3}@8bW+mN78wsbnf?Q2lmNeg2o9&*ztadvg;sZTIc%?dwaur{B79
z<He(+-RIwdPBz_D^RsCGpHJS^-{0kymTtXz^{V*2@?T$GetUEC^78q0zx@B9ZkGI@
zujs%YQFOoddo1YY!Ta_9Ye5Hv{{H^{{jaaDW$kKy+_ddJx=1&A+n=|)#kyU)k3K40
zhdS5yr<?Nv<Fq^9-rkOmj?T`_eY^B~%$|ymJB2UCKYKpE{$Kn$R4a96?ziU?holM^
z+3=rxbO;m{7^B^DSV%C8cF*BKfu(ysI$jD3ozcL7g#-h`=$sThEJi2n;6X7un+Xq!
z(Wzc|P>jxl!-HaUlnN0PqoY*tuoxYsf(ONL8Kr`I2+SCr7X}9dh#2j7f<gg|(K?<V
z*sIIm&q}|^R`BDxRJ1ayU`WSQ9womZuhv^y7M%g?u^}2kE=?ZC_`Y)gWj5+Kc<|ss
zHqlkC?(Ft#j)8>&;_X&94<1uWTC&JYt9E+#hiO_1mu{{6V6m+I^S_F7zxjWFjwi)z
ztYRLnhdGmixhocP%^WfPMA)<}*!Lh})H$F~fMAKy(18R5=$d-iv^-p7z(Ysv-m6zx
z{<dF3Zg0<j|7!L6yz}#HYkxd!e{BaEy8V8Dncu|P`u3MECC0|aZ*Om354!Rw{)QCX
z10cqY4we@T!tXA+%jXsrg2#+6dFz{+nqIB_es_DG$G@}Y_e+k7hMU;i-#@Lt|IR|^
zcB{%yDdqQT%ir(+|8GC)o^FN>6MbUeu`=u^h_CtR3Obfcf6oUec7C}vuMRXa-z~eH
z3%d8J_R~rA|3BW`xf4@dT%3OP+4JYSe?FTX9TW2gG%&toH|hYobieQgMztHa^Y`Dq
zawVkS{@;&VIj^s+J$v@-*PH3{zk=4eU;n*q`SRWWe!Y&4jNEx+HR>3$utNi%!NGmM
zUaijC`}Nwk+}mZ>YQDd_n|=Ly@vAE<>;8N^-Y08)ZS#4%+t=gk@7jL9Q|$Q-b+*K8
z+se~>85qR#Dl2!+oH?`jnX$3)T+8BR!s>o&e)qM@*X{UzuX_C|-RNy!jtKjIxl?>T
z_Dd}4WKZvT&KC^AZ?@mB%YJ=r?ejD1cfDG*_4Vt>h=>=>{B|#{hR5f=zqfbox^>@<
z%h$(X*PT;Uwd?Y7|M|wCYo4yJTc3WsPd0nMeC3mgWp8g?P42h7c5$)0{=G$@ScT&Q
zE&>afeKyRTIn!^BMd7)c%F3Oqr1STD+;gw|>D2JD|9`)4->~7r%gf9Ee=GU=zx>04
zgX?xao3%OZ_xJbt|Ns4c{&hdxC<X?Gm>tUQeI-v$Ox&Di|NqbD)LU!~p6U+lGZL)J
z-@RGfZ})0?d|l@4ZMoT>&)fgs<2&1IYw`1QpX;83W*24}r(2c2y0VM$SGWGY8|z|s
zpZjf(Z1#?dfA1U)>hJ%v>3079zec$%2UKp?>=b8saLD$@gXX_KpU>a>>6CW%=Brn)
zPMbFE*5-8o+uQTkzxw@t|N9#olmC9b9-saF?}x+u&-dh~rY<eNSGoM=&713XzuV>g
zA0;jr4zxXDDQV!`R{i~*T-A$(^D3Xs^qXgMQ+NBFOP4MM9q*Ta|KZ``?C-XJzg*t?
z?N)Z}@3-5}o;w$|HUIv;yj?Gsz1#7)FK@@gwmy0LdzUT+oj!e9*0$<PQLPY?XB=;s
z_94~+6i9MjU{t&Fdj0-;pU>Ohm(JgF(ck{>l|EVPs_%EpcfVe@``WvkTQY-Zo9ElT
z-nnz<PSA~UV&dY_k&!QNWv>UN3|Xs^71r<fe7^q=a&HjKt^{UK^zP7&-nM1Kh6{%d
z9kRby44RYjb6G!Y{`~y9x_?3Iktd577<?w2eSIG_hcFzdZzN(pH)8QC)OIZ63B;^K
zB4WY=^Be}uHCm(2fkp!Z1C~+X(a;$U9c;^>M{^cDU0_)xJ{mfsp@Vhx>}Z_@PZ(GR
z21i3@G;|n7TZ8aKz;Ix+`2`P*0c)Iou>baMnd|9I{0Dv*Dn(ifxJpb82nd@k;3@Eu
zwcIVY$>Wql6i;2l%@o~RJBkH2ZwPJV6ZH^yyDapGfMcM*wh396xhE#iR@q=~TxF)t
z{Q1X^l(atczjdeom(IKXcfb9CgWyqu(Ix{trbio8h@fEL8LbrIp)uNIfCmMG!RQbP
zJTOL^4Dg^BK1~MU_h)7rzrDYI|Jm8*<!`rM-&Xwm+`YQrZ|(PfKWF_OG$9dNe)sCJ
zUg_O`zug9{2v_%?w}&Shb<jV2(bw#~3=H+>FZ<iyot?k$=AAn+(c5w|6B8GL#@m-J
zT?#tF=kvYW`|InM`_0WdKhO4V;c;2e*-@aO(xXR@f(G@M`OemRj52`Dz_5;msicAP
z+rxJGZ@*rz|9*&D-^AQJ{A#ej?bW;G_wO2?x4B&XesB4`-Jd^yzFYtQ@9H$ru}{0p
z-o8329{=V*BlG_k?+~#DIt_Sg`rRmfh66{dANQI^?XRo-{q1e^%-kCr7T&yh^IrY`
zzx)1vyZ!mz-}gWEylP~Zd(kGH_u{g@{a<&qS%!6>OLsWS-rU&uZqMg)%a$(>KU@Ch
z#>P*7*8li;T;96&SBd$(ipQ$A1yO9DAp`Qxwmp09oH=vG^7G7@GynZ~-0wHX;^Xvt
z=JxjY^Y{O~ChTuhxH1fO1OY_5S_gw{Let+rpU>ys*zj=9&#U3_dq4eg+WY(6Zdr?h
z1;^#<_r&fli`^uPGIri@QV}%Te?6wycmKa%uPr~v*ZoX=`m^=No6YB|zFc&_y{j}^
zfB&CPs&~;{`TBYlBZJ<(GiQ9%{pMJt@7uE{=IUAV`+t_d|M6^g{;j>$<=5luYrDI<
zbMNf<*i>Jim$&Zqy4`tKbKc+E`}Xec?@jlS9dh7)@s}4D`{ZnQWqmu$Z@=cE8G{dK
zOAE{GZMo6j-rjTVYInVS`Eu${cKMnMSFVKI-j@4&|M&g>|NSm|fA8+i&FRrmQLmQG
z&im!P-`?K-K4{V>5M|n_AoI_9elF1DQ11PGwY_Fc36s`Fzh-6FQPFSvEh7E=ythlI
z$3@Kq%>uQywwArSbMx8R*{eY_WAp3(Re~%!wR3*mua)g`RV$u8eR{9z_1e7MZ?~P^
zhce~CP>}kO6*Lu*e7p~|QK9&}?e+5ewb!TVMn^?Nym-BS|GN_tm9?MGtNnHpbgd0|
z5^LwvX{+Ydd^&0O>&4=<^mNeHi{t(B@s{?sws)2LZHjLGM?GL-!#3~)-_`K=w?CiH
zf4}v5-0LeVgLCih+IsZp(RaJw@0)5I92~qhdVAj0z5aGTm#kd5l26|5&cnm);kLWK
zUW*1D%?n90VDf{$iUa$Mg7DbVP<DQ~HxCXrKesJ@a$;g=yvzDupHA!le|Z(G4n{O^
zZhm(ja`-7sh=Jil{%8jY9vTDIK?1vAwEqGQ1~7qnYRG8lfCC0hjD`+47{J76?+yV*
zdv}Piz|y-@V0Cy2TMK}(oN6>3A;NA%r=!pE-`?E_Jq_9*{oPXLlFzAyPgN{j1zS8?
zIdU&viD~}e<@|+x#}q-+tu8JXZ!DUj;MkkX8#wWjfUaPkYK4h~pyP~_hWDRV`FG^+
z6?|dY{{3@f`p$R1kJsAPAD9lk`~VizXlp#NuWch@_=@^xXh2<vx!QB|*g|N~FpO^3
zfQJOb=ynZwSYRnU;b#!S6pdypSV)Yf9C%2Ko)v}&iqVZe@UR#?D-0eKG&m~^YBseB
z<gI&dB911hx2XSDlbxMCd+#yb;`e*MZ_B^G?`#}oc)h_M(U5A;ee~z&XWJhSoMU$u
zRc;R7nOgSl&efg8_q)J19WgL$(?HZ9IfB{Q*~0VZuadj<rZlfHe|OQ-__b@-!nQ=9
zD7EAd?a%oJT@L+6KI+yR@I*P(&miiC6h=n~bJxv4Z|A@9ZC%{nTcEY-_x4ub-kKfW
z&L{ioalie)`Oo!YcU{?-e7x#Wr~0nn?{<R*lP~+*@8y+-gfhsBARG<4&ti7<x0~sp
zYv8Smo_M_9^V#q8>C?7fuLOgpD(WlW-Pu{Z_v10?wd>YxtN;H`tovy0EeVibIKHuJ
znt3%N!@r%NmGR&2*Y7vKU$c3!dw*EzlM@r=>V7<ot9aOI_y5mld)wbPlKa0t?zi8T
zetw?apAU!6&9N-reGT;xnr#~93z&0~<!e4Tf*kVy&u8h)vespwO$(*Z&dk({+3{g{
z`ukn4*L{0)v)K9?>ZHLoPDZN(X5YSEj|c57*;4)eo%Azyez`jpsJB*pDCfMuxNT#%
zxc;_Hn~E;iq^2%?eSQ7*UAuO1Mk9~nGceo+g^={`uh-*mZ%jV!`+2T)d7cgGdi5W>
zSza*QzA?A_-c8VHPM80jnyM{*9@UtC>z<yCV`!+)OHEyR_3G8x&&2iP*1X#H``zxP
z_wB2`WPHC<e4cmn;dcJ=A0Hk@|B8hNE&~I@zk*+1Ui!_qt3CYY`TY8OOL7@*yaU_V
z$jtuh$z=auPp8M<+FSko*q=8yH|vUZ^T}8gc<=vzEjs_}3FZDfm-3Mf`*8i=?bfFF
z+OMJgcE4Vz<+2<o+qUH<H^YbXpxp#(*RTKnZuk4VGoXakDXeZ)@*<%6`@6NTE-m$*
zYhAuB`}(@vYpamWV>n>;fUTq<7c|Un`}vIV-Y=KDL3<oP6H{|73KzZK|9{`(<Nf)2
zKr=<4O$?yfgMGEX&7Q5_`z@;b=%W06KbO6}zP|j^laqG8-)vqLSNHSj?SJ(sb~Kz-
zbzr~o47B$KG|AvM*Xk;0d&0lJzkk12++X$Q<8kwQkvd|!y1I8uzJYeCY>dd+^Lc(o
z?ZybSx$Fo3FPt@1Vz_-uw*1aT&~}GbZgJ4TOrZIalj`&LJe>RZc>nf&`|1wAeI5!r
zZt42E*xfHd0@i2;KW%VDGaBovOhowv^$@iRRE*B=Ko>?(|3RtIb_z5gMsG@h2LuDd
z;BTjlW-C~94bZ7H|IXgqdn_&Xeyz;^EhbSBzH`Kq8IQ7W4Yn~{<g&OkEm3(x<}x)s
zBY#2DEHTs5$L5_`(J8e^&EV`6_0JKD9{AYIesiG4fYtw?1grZMA^rzjI%5uA>}tK|
zU-x()@4xlcMsN3v?}_7I|Ed3eU67vT-e9nI8&ojj9r+Gjuo?!>NqxJZ^VSV_zuv2U
zpIT6`;hpim(7Si<T7J3U{MruIwrbeh0^O|EFzw5|>i18p?^_!kJ{<kp?rHSZo0gjY
ze;l_Gw1Sw*z>w?&y<5e>TS`Vo=VN94B<0t3&!ac#9X|X#wV)sXD$T%fU<Pcv_=QJ(
zK1QqGDZ|W2=)Vy69ks>5z|g~w;j7_%LmVtDpfr{U#AwnF$%~I+$pz|91_p;gcb~1`
z0$5gnI&u(Sp9FOwaYevr3W5d~m>SJu;9!6fqbUd)5KwA>@6;YGgP`#Mrii{N*TzQm
zBWx`ISSO4ay$}!<5@33?Mgs=}j2OL`8Ws{@n&|8XRt+OYvluKS!1QPq0|x_)82Bu9
z;nB9-+tcp<d1gM-sx(W@ch(ePe;dR4pQq#hEl!v2b<^AZW|K_G1;>}KUY+8v`_Q~5
za`Ut3eW;TK66;xBFzCKJ#I1kk(o*l@e?Ol;|8_gy-`(B)+4=eN#p5a#zARq6c=1g8
z`a00mK}_k@(4AkeMSni2KL5#<%YLV=-|sPYyN=quc-+Y#yPy>`@*KIZrcz8lZqCte
z@#mAg^-jkB|8?DGzMXBim~PguH_H7slR{UAJ^lCl{rUX*-?w85kBa`hegEGyPGPkt
zyI!x8UVNUR;r~77Qh9^Eo6Bb9u0kbdZT2_49kSUMjVS)MGHrI&HZ&shoZZ!&;In2h
z;_1S62>0@wTBx~f4EsEpN*ctz9k>5yC@U+w^UEdg@_pOh@B5wh@K9^y)~ry_6v?S{
z`PwfRWokYgwETR=xP0HWyLaanpR-i&xBpkM@5iI={I6vU`!xS;ScBo-RX3Me{>F5#
z>1~tr`55k9nKt{`8zlFhH49~VarVZtS-A*rGaNAYY~Z_aD6abL)-PYbE?vF)wfFk-
z^K7f1A78yDa<kgzw6nLKe!aOlJ^l5ywUPVl{+d_oz)~-mHh9N*fiddFGT+&kE??e!
z`n9dCt)#5%*<-!Z<*#q5_|8Y2h5P0M3LP^OlPR^|@0L%$Zf$K{URP5-PgYho_ZO<c
z8`58`_|3pjcK=AH@Mq8-f=|CbeE4v#|NXhmxw*N%^Z%C5*_U^B*ZOLs19GqH?+efO
zG@AClUtT5B%<cc$MwR&gfA2$L>g?6c{kf}ppPG4Q|J}0*64k|z|Np%Km45s4{qb#?
z>!#MlLDR<0kN@j(AkqKq+n?{rw@t2l*{_F2^_?H}_S>L_RR8<EF?ZJOzqNKhpG@ZA
z<Ey*O9{TG+GykTXn-O`FOUldBKRr1a|5`HM9F%1KuZAX)w3?sad-r)NGQ@}9e(~Z(
z#$9)Y4b^pD7R#qTKGs|LxYvB&mtUu*Y8$7Yn`86y$>g6O`|JNqJ^$_N*QM*%>-*b&
zy)r#+|MPj(MK705fA;ly{P{q4*{@U2>qT$Vc|N!Np801_aKu1~4{Kk(e}Ddb{lCw<
z&ND1%{lWKwK{w~wnVFUEc0T`fGkyNj)vL3gzg``_-Y+^jI_=z?n_q73|Nr;>?mhde
zzP|FAWujSITRZjqxw+QnfB*iqe6!*3th(hTP_x0*D?<~LDZJ8VDevy=ES=Bf(EU*s
zlpwtI_kxR(?RU$f>wcb&SMvlFG>iM~tR}1bpZk2?e!j}j7mNEZWtd#LeS0>iu$qcz
z*qVrm#pi9!`)xjXoU?kpM&;y#2MND^{W8kGw?`*>+nRa)Twohv#EM=9*#$@czDc(~
zo!oCbEqmQgwY_`yg6=Q>bV_@D%F|O*Eq^|lJXu9Nwj@xl;z481jSY(Ja#b0VK-Z~T
zKAjT$>Dlc3XW{#Qh3?wDyZHIs@@Id)-#>p^fB&4r{Pug!`6FhxK{l>%bid2a@Zo;t
zhlA|JZ?|4wwtv6<{JLM6eYW3j*!=x++4}KkmCWpH@9OH`)8}R9=bztv-flLiu-f^!
z&)UeuWXjFW>CYS4<pk!VlynE;PL-oyyR6`O>EHkV0w7zF@HaN>V}A=$dHDI$6A~1%
zudh3M;DAG0d;4oUPMF51OQ1XK)#p_xt>6Ez>hAI$Yh`8S$lYbRW_foazH2_dq`Upj
zq|(>dLhJsl-G1+s?)E!IZQ_h?YTMe{HYFTv(uv=<=Up&ELjP4WD=Vw0?}7{r2g0*W
zq#`$^faB}y>+8?||NFFe?ONS-`MQd8me1$J6rVNy`L29_^y8&pC8eZJ&Hw-BIjAU+
zHqSeA;X;6#-<%nm!OK#fotgRbA%Fc0&&g_6Yt!Dkxx1I=UA}fL?7QXTW8dE1{`~EB
z{`*f`FGCW?mD;%6e?QOHKihge?sn?*$9>j%?D91Qcc1r4-`<vc+V1z8;O~-;Pks1M
zV3vDp%jeh2mM>SIJ9lpBd{=JJNoSi<PEJ}AzklDm;A2ZcF77qIcOo)<Zs>Q-4emd#
z@BcT|ZSh3S;AK~8xh^z;l4-kqoyF^GYrV_M%g@>Uej`(MBXRei9aFW#(>^{r`t$Pq
ze<t7Dw{@JIZT|dj`TetNA~(OXV`cbO1&RRB$$)2Po2Q?fW4ZG|6ZfXt-``@Y-)@cE
zmJ=z}>*i<iu;ot8=d+d%TZCWPZ8wYFmUD8NZuGt{zfZa?o|rzbQmxlb`M7+2O`rY0
zA5!{DruOvoJlTBS?)1Ok@8iE~K0bHgfP+-8Tc5=vj{5Hh>QgQ+^ZohbaX%=O-q$?0
zE}b8|8(iNWzkTc0rJFZrW?o*F`svBZ<dV?8Ztm`vZ{D1F|L?o<oqs-^er=Z?BPl6)
z@<^v}@$KC0PhYKGzwY;(!sUDS+W!6fH*!P5!SK48pP!yaZb)$4mVe*w*z{ic+2;A@
zR)wzq^zpcS`nx+jt^e;m*(Ym#>E6EYHS$N-MsKfsoBr)s{p+%)Q^TJ<>egTPXYb|J
z>-WvF|MQT4=jU_Q$A4`4n4FTL0`hd-@3+(Y`ucXAmo)!&JAc1U<R+ErF-4wtmoprY
z%Y6THsx<?{mKmT@<=L5;J3k(iHcmY?MJH;DhWB*6v!Ebe>ODQ};v(0XMyXz)<MC?#
z|Gs~|jaT}WUFDg(rPpI;n&n2-{klB=S(|j8M}2+$yt-d6zkL7xyiGdq#LV=0pm2Hm
zegFU3yUY7_zP-Ku`M%%pPXGD&`SRt<ll%Jm=GOnXbNTY*%FoZ9-m89p_QVN~yUVX7
zB_t?-N)kSs4+qZ7FjOvncIKpi-KWWCW*Vy-r=2;$$SyO1TYrzi`+dLj?k?|JDIQ;A
zxO{F|)H1)hvwnVlp8oJq>(8V5brV~;#nbNXsRT8*{A|BoSrfN+*Sp~3cR&Go|NeaA
za~8_&GDRL%R#rxZkB*d-lsuW>%y;tT^7->X34Z;b(~sR2Pkg<8znyW~8ISPr@T%(S
z;xmTFmu%l|9vd5L`RRmm@!itvPcQr1ul;=`%I5o>;+>yPX%}DeR8Rf&<)!6|1<gja
zzrM^Vx#YR?QP=;(_xlzv+V$;Qqdl`n-~_FW0c#vZ1VuTynj6^OI35vdX02Xt*d-pg
z!PQkqg1dt^+GK^H(jq0nDQS#6Vj(Q1N<m9BluGOBe;DPfosrz}bMH*ss(tgf#%LeD
zS-$r9Jk#`NGiUDoKC^Yk42f%kqPJ$7=TDe9^Q2YVA*<3?B5u7>N3GhNtjgX<#Kgoz
z91rl2Hp^+4HB0KX1Q+NyM*}mnG+AfGxfX>?&FuUj=G%LFrQ_><s=k)sdU>dodxl-D
z)oY2OkKf)#M?^;-K7E>7+C1;brKR49X=!Zn@$r9Z^*@BKk5ja=niUwd?a<-F7ngdA
zuUN5Sfor$e4D)=sdwVK_^J83GSoFm=96fd{>HWRE9Q^#pcbC6k(&y>r_2_JA=<)>%
z82<hH_v72`e8c>EHg|RuI=|Xc{QTU<cV8`(m6<22`@7Azt2M~EVIX5$74mAw<Kz9G
zi<tNR_)*c)*7oRneErioFKRzO^F1@qHu~Jj8>`l=Ir8vu`@^?ydv&9?75rOQ@by(_
zT-~y&Z*L?QEm~CY`&;fg!|(6z9{%<9_0t($bANw-fB4ujw%uiK56v`AfAI7vtG&Jb
zj~_o2OiV<!ZQE8*P~Z?0Bs6EvoPz)VYOhUvx^CGrHskbjE&KM__4M{8CMGr>@0V9L
zH5Gk(d;9V7`?c*iH>W>dy?)=JA0HpTE<JocHZD$%iJAG~>(|}c*VlFamy?m{sr&ou
z;HgtwmzViIewsh$;>C*+b~P3<GBOX|zwckQN^4L3f4RrUdYvyX^If=peZSvatA}@X
z7Oz=+>h8g2_QcFgPGMnTpLsTt`S<s^*45d)dGqGN#$@*|udZ^pwYBZ}^LP7#1q{|@
zZyNUR-|wP-Z-2f0ukY{qv$M0$%rfOZKi@umMv&p3U$57{xU<u^r>Ez_=5&7*RaM3x
z6@1lSUNmk_KX2rBqHXV9+ZHFq=l0dr)e+Iri&IZe+puASLq&zf>k~zR<)7P|nwYKy
ziu84LaryZ81Vl!jv^u4}a>tGt)8`+5{p0uV#lEx6B#crx)coh^{M!={5y7FWs~fj>
zdUjTplehQki~nbt=by7O60ZLCX5vo6zmwJdH<Z7Rvs4S>k(892VU{c9<LkR{*)ld}
zX66+uS1!!Gy={hNv0Cmk{ssB>_j&mFrO7r6IC1>Uxwy@|MZk$eu|;ErYq!|KUAv^p
z-`{hct`}=@{O<mG`E~2oMeM0C^qX&|d%Pv5wWTHD+#Jh-;^M<^Zf;IYPFDWNT9cWn
zDI_esvHE-7nfdnet5&T7*?#!Qr{IVPj_~mCJ3EWn-`?KdK6&!wA9_bh%hmn-{Eki0
z4Bk-u+%INV3Foh0zt$w5_Kk{?l982F6zY8N@FAnL^z5qV>V}4b%l+pc+gbel!|(U|
z7gv9Ow<h`j>!hS4gMtSR5|WaMUte9F^Ze<Bh0X;fB`zr`Ds$${i8wy3+dThX!i5En
zJ1Rdft9ZC!OSYDh5|g8&<Bp1tN?*Qw0jYTNCdb0k^5M~L@q&_)mf5qT_ZCl{GNq;T
z^|gl=7CQg<`~CjXd#s;|L*nB4HYOhjEe5=B;X=dGrK)Szu2nsE_Tk}nK^d8zgU#%Z
zpPZb0;lhOk*=W6@q9Q5VZCkc{iT81`OOK3<+!K4}`h;7zqVDB6x%}IC=8TVvtLw(T
zg%dJ1i{xo)YI5-Mx)u}|yw>=?Yiss(C1qvi-{0OI?hsV|@an2|&Yc~C+1J;(Mny^a
z&9OK*d);wWJw3j~ZoN*ox8)j^z6yEr>=~#iu&DiI;y2%}cm2L!U8OE*TH4x%B`*S8
z+}*pym%e=UD(UmHvomZeHyyd5?mzFtvt3LL*Vo4{4qqR4;^fK3ZQIOFojSE4`?_Au
z_q*jcc9*X|Qu_7V+vvExa_MPli^|{MTd`tA!_J+SdH47Aa*OLJsHm{0`_F4xxNu=b
zPHwL5db2aD*Q{xoJzILwqD4opPuaK6Zd=aHCQe~BkDl5uF9g56yL)=Jb^6}g-(qED
zWjo5>&--y_O~gi~)6;aD=g*gCVQQ?<xo_qp*y#c)Bfq`Bum3N4x!>Fmm;LP**8l$}
zlpGu!ys_x1*P4ipPWKF-o;!b@UpIQ2OH7Om4==A_>M4<&ySqf^T9+SdX6HY0zcDQ>
z?a;AfY|>^q4iOO&kFR_Z6%uNC@F2lwmI>#wWy?6YxSFO<7oRe9s$uanpNfi#1$*|$
zfI@tsb9+L1`tjM;tM^rWWZGN(-7PLojv?XhuF@Ybm(LFf3uBX)myd{wTC{DO7(2h*
zk^KFC+oHGU9XxTOqcH2Ihlj_31C7iJSFh$~W@i5J^QWS{y}YQXsE4ob(M7J^0daAC
z#_8u0o}8H2(cRs=cCGH~8%2VWlAR|fs~<jeh)GOL%%bLp!Ku@y1A~K^d3kx?+}SDo
z^yyQO;Is4d`@g-toqS<|<C^5tN9Wi7<CK<`e)8-Y(~logd(+R$O_@41@#m+fFK%ts
zK6U!Eppa10=JfNAzP-Jjad(&L<10CTzTM6*C@*&h75;g5EY`&BjjB0w-~dDJtt|%|
znb{vadv;7uMOjc#Fk)j8>%IN;{VRi)FG@b%$It*OkWEZPX3d%vv9HE*o^5s8g9iyc
za<)>-{pL39-fjK($^U(#+F=PFA03r2%@R3t=1j!#K#k&OXAa)mTWy$o%jCt27aRHx
z$JEr=tc%~TS6B1zPvxJV&*y(VCMque_{2oz7q_;qwt1}CGuOI2>FcYjprUEtzhBus
zGL}I#KJoGLd3kw1o=%T9NIxgjrup=FyL{b*A7{?0YH4w;T)DEy<4b1M-(RLzu3n8i
zK4G<S`ndy_FM~qOz{senyPMm@)b!)KyVgsVFITp(kVs5Sv?zSU(#9)&%u3JL(b2J>
zu<+omt=XVtAR!^Kq0fawv85&~gV9Q{1ym4ny?S+Z^@q=&C-3|r!?3I5Wz*4a@x$lO
z`}>^~aZX53IMyTC{P=jkx9z<>mBl-D>^N}rC~NZZKG%c<g?zCE`jMMh{O8-brlhFE
z#Ku}4cXf4rcsqap(eL-``<dDKP8cdidr#AGe0^=Lps=vAq2%}V%lzl}$=Cl8^z-xk
z@$dKh!k?c~EtgN(FRC4O;MOgvix)2j)o*xtZLM@nOw5Lomq8ZR*2zb^L_It_5+;QF
z+xP!pbxKOggYEb04o^^Ywm9zU;sOc_@9BE385t{Ngf}_QURn^nF^N?#c2`U6?y`fY
zPkX<5_igIbsTKtf7{v5qIzZ9*`r2BaNvGydoEW&cE`i<7k0Jlfjq^wU{QN9!`|a7;
z+5eM-K52IL_ve3!*msxl<&BNWy>hdsP5Y*=rZ`{dmQL%R?dRrNx6d?AKXm#uH^YL(
zi<_I-`48Q^DS3Ih|M3P!W&uILgRebz{rmUt#kIB4LPA0pwqyn~I8;?xx%Eo5{`>p;
z@sUnp39Ax~$5V1x*w~b;tfcJh>>ly*nC0K=$-KPm;kUQ9Z|p2qe{WSN8y_D(W!f~5
z5<fq`ir?RKK}AmK>uZY2%FNHt&v)+@(~UTua_IPRb}1<-a1Bs+<X|(qVg0|FFE1~%
z2L=W{I;v8$Irp}ii>oUr_Xu5|GJU!@sEB)ed;8|T6Fj*y4(Y0>uq<4-P{O`$&yPDf
z_xH)JTet4UhD7FRda<Xhl!Q4sIY9|FYHJqjgU98s+xg{>E%BVJV)o$8g@w#}_U!ra
z`Mmw+u2Vh*1qS>6evAJ2jP=>GXA;(BI?Md#c9p)q)_MHv+uP!ik&zZ9F9h<%7F_?E
zH*>}ej^N;6P@80R*xIIv69xbMc+CItcZib{6C002L+R^liQnJd)loiu_SV+yi(9k9
zj~qX~IP>zdh;2ENWp8dYuHW|ylr<i`pA^16j@R4UJLle>ndaq+_jVL2zj^z%@a-*A
z4i=`Io10iqPuD+wppm)o=_%2VJ9ZX7KXmDm(CzK{&(AWI)YsQvxpL*fudlBSOihno
zSqUzFw`5*s%goGt<R>96&K@2fz9x3}H1pYS{><IK-(E&WMnG7&`OqP!PSzI;7nb|W
z$KA6PWmvR$@xoQBx{e%iS+R1Zr_5~ge7Rp=U$@UT&riC%%y))yI^UYLYd01?c8k+-
z@b~cnwFGr^bRN8T(XlP}_O;i?m>L_V&sU!^b?U_>p28(BE-)^3?|)`v{`uM2<S7CB
z^y2sFyt8C#WKj2;bD&dLeMw*L{e8CEa&N1hui#34er~RWaT-tA+gq)N4jrmGzIM$T
zQ2Ukb<PFeSF{yI<OI`~7`SWMOtXW*b!on5R)u%Njs|5uGJ32Z9?ClC3G#pXmFYW5?
z1{KnAd#g?w%LVJl?>lm&Q~2VlQ0+IjxAXV)^?f~d<j9ePS65bk`10jQGdq99ZpMjo
z=gMknX>G{5s<kF+E0^zVv#G!0zW(}}?Z(Ne*fPOiTGv4xT)wzCYHDgO+_r67U~+bL
zcBQ$XskQa)i<9?(%0Ez}@_&)i(ZYX!Ds^Iag*<yy%urBT3NAi$qqm*VoSEd|<#lM8
z?`#Y4`PU6iOpd&{xp`yF&mv3JWNlqt-rL*r^9!~o@bdD4QWCeg-jraYZ=lS%)O-4=
zm>NC?=Qf^$lT^Jo<lZ*Br{l2vY|su+&&7M1&cPl@V~gV}R;@}p)+1T*?~moT_xI1w
zW_^*Bm1SUVetd>uvXqRpu<+q-Ux$CI@)`s0-hCl;XgQxot}?q`uWkK&?&|95TQ?e;
zmoHb34VHN&)?mgq|J^LE3u&60YJNVQ-YXX!67oe~El}tDe0%rr@9w_-TYIR5)4<TM
zarSKKH*enxii#dpn47et`nz7(nh3>@w~`YR8=pK$*|B@~;k$QZYrY5Uv#k1}q2@P7
z<KLc?)YMkTX10U(@5|TK)txwd_UOmQ$N#U^`?9m6ukYBN%Fhp;JYiwDaOu*aS65d*
zeDI(laIxFLd-vp~>%}&$T&ekZ$tQ7n`Tok!&phwU%)hk6bHm1s2Ok`4PE1d4=N8xd
zkQJ0SSJ}NU;m?ncLfrQ4ywae4+M3wiV(a7f9=f>L9h55DG;c284c_tg?rw2qx1IwF
zo!gJp&o)ZsN;^BN_37#9kDs2Nz9+_F(){`QhLwBs6stfxBzjGajfL;OoaJw1Y^=KP
z|Le=k`58R^)~219p!nhY_vz7Q*Ve`D?UFQ3J8<k68v`gM-MDot>E@<Xq1j77h1X;?
zU#FB5mDMYXrcavGr0PAbWB11=Cns;L{G8@9$0Bgi=a(;E9z1=T`}eoE$)cg}-re2Z
zK2<xs%RYVg&Yg)bFD?DL&pRwMv~~G%_4RSH7cX9HSo^Ew%iG)H2afy7<>cmWEO{B!
z>8ByWWmx#gC9eLTkH5crLW08ckNW$5G);dW$siym#wIU6zpDFuWB-1}>Z+=wzrViT
z*pfN<$H!Y+vn5rg?w@O2-u2(w$|~xW#6CTT_$?U|f9&6BmjB=~)0d;&;>oYBtQ6>U
zF)%cA3<waobLWoAF%A|clk96ew{G3)3EDJ$?%ZBg?`Z{cIum0QU~2)cU%U3~>i6R@
zixw?<@ceoEk|in<($dN2=h=Sv^y$&na<TGvcN{%DI2!t|`}z3r)cyZk-f38RJ!E~{
z-VMpe`PejX-q>BPziRbrP{q0>`?}vN33YY#n0+;pVq#((e0=M+f8>k*^8Wt(@cmZ>
zoj4Rfxp80M1UCc%1DM%(4ouUHHb^+Y5D^ts)aUK(E!_WDSXfy2&%fXAXV_F0H76%0
zB_$*!DYb`mEnKu{(M9`|%<SyNn>Kxl_gfNi<?7Xs&(6+v>($lL$|`XD_S`8vT-<-Y
zUG9||XU_P<`MRuKv0}oG#r-<FcI{fRV#SZ?!kT=ybXub`Gcy<8ulDivtt|b1Mb5VB
z!QbECBevy4HYdNX3wS!&Ecey|_kKBx@^>-K$=BD#c89JGJE=JJQO5m!dn*_x>6E{_
zb8v0+_9qiO3_)Q#ZQ8UM_Vsnm$>---HU}^FJE=G|>B7Z}j{S1B8|wc4VmmHpQQ%;6
zvXy_;s#O>E)mB?rSeRItnVO20zq>QhS?j37?4<>#&zy02eQj-GV&cUIH<tU)H~Y2u
z`to<(`uh%ai|a3uD=sN<@$und<CEdAwzjUQsybykH)+M1HB)~5jPmy87T1e8@Z;lS
zP?P=1)29o4XPfZ|ZJIoFs%q(E^Z599Pys(#-M?-1>g>h89zK6|b#-{q`$uozyy>}d
zBVxy{U5oPX?*sMSnoDv-#l*b!E)JZo7dv6X1cvbNa8NJq%gf6=mo|R=@-kQ_V#9)a
z_y7L=dvRm3yU$!J(PlQ@LpL|4OD;+7HuHJ-?Z?N*RkJx(ty-mIVj?1IU3R4Y-)H$J
zPoF;g@bGYt(58jUmxFrcACpBzML~{=ii-MrOiWzd`>*x=E4muju3lYR?h_p?9U2<?
zsqcu7pI_e*rOs`+x0xEQob}Pw)vesTQv1Wl?aTN7dzO%pz`zi+-#_p6Hr;%?aK;0_
zzrSC&a;0Wn%=hRiTkc(66{@|b_IFs`&4|+{Pdfho_V#H1>vb#F#qPc)ot>K63Ti59
z&pMQOYm4ToQ>QHY?Q4ID{QC8)$Y+Vgy}i}y#UE?q;^aWAx;3j;bEl@JR=Omw+ql2{
z)5XWf`y<^0G@_!S9^H#B-=6sD;MbS0Uq8OOI(*LY_xJXm-u<58|EotwyFYyX>|9i2
z<m2PBq569ssJ773`V)O?GpN56vs386@t^96iHQ>Cc`}bfx*oo|y1Jme{CP}G-16Gr
z-y{r^Sk}etJan7&g}UFI1ldN=K*E}j>z4|F#t{TQb>7%jstu~}=h;>tx^_+M+O=yL
zS67K%xpE~SFt9OvecZ!qYok4Ud|Em?IrHDmib_A%*eTn|*&RDa9)^6IL0lG5jP
ze))pe*L2_9+RAPJ|BrD~Q<KE9sq6RE{!aS+?JcNVb9$Pt<?+2$U%5adHFM|AmASm}
z`&sk*37?;x-LPfLkqwE5EsoE%F6U!pWc={q!-Qn3vSYo{?Q5gAFDiX~ZH7^5*A?re
zef9t4K%KyCxwk7eH(N4*3f$v;vJ#d>Dm=WrmdE$j{grZbbbPe?&IiWaX@}09I>iNP
z7}}Vam{=U&TmN59QBm>5#l`J1mp7&+CpXWp`^A}>nwoKK&CD|!l_qwSmv8#_YV~>n
zaq;UbHrCv_!pN|z^fjBPsOXz}dv_n)`1;z~$5)w3va_?FJbPxAweihlb^nU340n$m
zW9yf*Jro{ad-cH$?eKLc6em7<ac!-1NNA|^))#emca`pmYVe!Aw7}ThynWuhxW(`M
zcI4f)`tj@6DMit0(4MTDo6{}L+g@H=%)TyuKcBd`c+QOtj^|#AI3Mqmoj74aKz^Y-
zgGuHkmgD{M?d#U*?b*9mdh5Z1&t3fe`G5ZW8PpG&`n+)cdV702J18pO@B8g{?&XcF
z%gcD5yL?|4yZh0xUg?6u!p7!iX19Jh-RC7aGiS|GvbBwUwJ~gMl%k#<Uo$)Zu?q{G
z4O31CST0ZY4i67cI`}5ucZLDuuV23;Y^zLUWMwPMeJ{3Y-Z3#XRTYc=J9YbZb5P&D
z_?ge1%Fk@dZaou<t;%$CbS6xiq*S+N@#4cjcg>kLP3`Ns7xO_gL^jpmeEvjudvhx)
zDh7#1rl+T${!{l8G>xxZ815}9DypHa?R|I3iamQ`o|UhdKU+*U>cQ97*B>2UwQALi
z`}_A-DE^9n`t<3?EawOM`+hL#$L|xd4+{@JK1DNliC)0zlP5F3JUckQ`Ptdoi+AjZ
z__HG~aKoxqS$j7=efo6I&4g$vb#-+as}he_Zt**J?&RR)Ja}QDv!qJ$`I9F(Z*R+O
zo;z2TjZa3SP{+tf2*h8!c=3<?%*;#!Q`4!%UW+n*-1sPU`plU%_wH+HX$i>5fyM%N
z?AqmZ*QJ%ejbFZRZ}s=2UteB+efMncj2RslE(DyJYdt;Cs_d26JatvogIBJE)EqCi
z)3cerY|oyUtnCk1yZ6f_URe>?E0vv`e0cT!RUC>f0!r~$!eAAeo12@5udi!BfWV={
zhd~2&oz}{rG!VPHtabl>`)B9oc0W5i+t^3DeslVHx5`S(KY#xo-5p_;e=lZ_!~S=E
zo6gQMJ=|~qujA(C^vylm;nCakS_3qWOpmYY%-{EuZEw}rNxLc!?ks-3VAZNqyR8*j
zSy&WoZDsTF@-pu3+Ir=4@$YZBPo6vhb!-_K8P_PEK6-0w_Qbh!ds(@~5?)?f`U14&
z^Yf<<51m88!jg`32uAEK(|vuSNLWIG!`<Dz<kc0<ckkZKxqfA)ar%NaYtF28t=$sI
zwH?%b*3;87Fg8AXq*K^(zIkF|;)&CzA7AZnG)_O~vOVu^KxE|22TWgf7C(P<JAePw
zV56f7B3z(8(VmKrOvjELGdezN_H0l))9>Vs%^Np@Mn^zeR-9z7xwQw>8jIeR<5*Z&
z*gSdC&utr<dwY37{pme>_OPk{%FfLEm}NAhx0jbs*2?Aj6p<~FT;|f!(sOJog-lIN
z_v~a2OYV^}1&viZ=j7<f$jB_|dwFH0@T13%AHI6kRsH?lNlV3QW_G?K-`?KdSo^yy
zBRl)LwVnV6s9=_ml1e%|%XH7JjN_+Hae;<v_SNjX@))H0>FMd9u|7}_#!@!=+qZ8P
zrLRP;t&i9Lx?|-^&AdB18XK9}l~hz(!p}>)ySsy&Guu3W+OMiLYuEN_hp$VxvLeu;
z_!-aobG~;?k8YiKW`d%#fT(Ee!^7>xapm*1ZyB`CZfyk*931Ty_qMf5Jtgwu)vHIl
z-|us-so68<@<!w2V?1~ER&PI8`19vaP!0X;%uMC>kglW0j=3c%JBEga`ph(PeRbo0
z-EUqqGqX=!$L7qOIrB)GW>r<yobrbK<?rRzi&;cPMm~IYcJ`y=QBhHI?(?gwt9!@Z
z`L^@b)z#uc!oo-UXPagp+gTWwlcTe%^tIahj59N5&h)IAcIEo@=X;Vr|NZ^FveftQ
z-Cd=x6SA|r@9nKlzOo`vfP<x@tLxC!)!`e<-^X>hD4nzWvh()NVs#l=Sx|X2W7e!L
zak2EYv`05LryH1=iRHif|L`!oP3^BKpKE&sm_XzFot>SJd}ps(wJIS!y?x3Qkq#H7
z7cXBbs;RYwzYj0HwkEP!JAB=NLx-63^z;NcSZ-|17H48+78Dh2^_y#T@c8leQlFij
zJv}Y+=ga5a+rt?g9L&Pbo_uME=avtD^0TtD0|NpY#B`%N{!g1ey}kDLw}p!qF}-{D
z?!~>m)`wd@g~r72)YkrW>%DsUva_e>$^COYK0bZ^95hX$s;U~a+vvWTp=yhO)4%l`
zE;X}6ok3aM>4f^4Wy{!DSy><LW{{AOxR8?1uypBCP|O4c2Y-BZRr}-5%&V(J*Q{9s
z8bQCOdyc(9Tt6=1>?~7ILg3=&el2_b^5y2;yRB<#Y7&x?4k;)`Z{4~TG<<gG@ZpJ*
zCN+hxj{~_gD=X{K^S<_W_G3Mghj+i$v9pug|K}6;bJM2}A2#l*{k^GAv;6!#ThK7?
zxp}tQh3%bIw{G16wHw0L#dMavy=CZe;@s`+`A26jU9x<+_g$T%hYvSTpS|?XzFO&f
z_wIFcb~^g{_8w`epXkA&s;UYa^!oej>xOOH(q>GV;O`t1By?`RegDtT&%J$YCOo^j
zIlbc36V6}X-|H_g$$9$Z$%BK<>_1+uUcX@F%9{@=>~v*nzrT}>+h4~kEIhfY{N{t*
zEiEi_tjqbj#dNa@3hTnc#N=$NSi-}@Ete+0et5WjN8w|(J9qCcT)kSmIH$1Ckc*qU
zvRHk=iWM3%mPIVH&GX$(Pt#59^Y!*Vyf%7!#-dFkHC3|fCeNMQJHP&)WHUQ|Ucsfe
z6P4X3Oq<qrcDDIxP1)$*-`^j<vNCw$j2RlmfuK#(4_>|M0)^(XWo~_(H+L32<(j4!
z+qGbU!j0Rvi~Fj-zmq-IC)>Sci^;j&*7bRlCQsg&c$iHmdK=HSZQJHN&dSQ#kZ_P`
z$<n2sIuriPX>Dsuy0s<K!_RNp&&c2X_Wv4Iuhx#+Uw3wPHt62DgIh8$e|Wuqe^K5H
zCWiHKdxi369GYIdx%j!CPRtI0moHy}CbFLIm@z|Q$IhJ(@9r+&V`=WP?b4;7DbuDM
zI&s3|*^Z_rrZ;zYi=R7p?#1Qh{c|pD6qS+bu`Yj?aDJYx(ebHMrX09&Ln3&Y&%?89
z%dW4Bb#`-OTjoDsuQ;Zz&JHxN;WO82s(CqwufM;0Sy@?g`SNq;&x5L2gS<NyJ+jte
zelKs_+FNb@?#|A`I~Df(WoByj^!7e{`m{Co_O_Fnb06(2e=jGd6VWhZhD2vCv#hM_
z$IJfq2k+dOlW4W=-rnl=*xhA{T3TG^=h-rUC@j_w4-W@r;i#yn9^p;Gl9HVV4mg13
zp+H&3eD0HM_C4kA<;vdO(X=zKkH4ZWz%gOs#Df~L*0NS52e#j@)4sRIUPp&VSl!Ph
zBST|X`FqeT(4y$=c^v%w>2s#^PMRdNCUP?yD9O*WujgX`jkmk?%k_q?4)eUb<Wup|
zB}-Tu9T>E=wS8t7EDYQq{_&-ocBzf6?Z*!fo$u@_<vwuyyN<WFcS?FXGsBguR|{WW
zQk{8UxXy3Nlqm&IP6+l$o3A^#(Y;^pXbY!s#c#XN$jDC6IOvUy$wKb~l_q*5&Etzd
z&#%}b@accI*aBg2v)k!J`n#W>pMMn-`doO?Qt`jIi<01`O`BfD2It=1);ejD(Cdmb
z7t=H^fkxop-QE3lp84HfrP&36(%{~%;*-x|(b3)8^Y1&w#>!@8Wf>ixHf@@cz5RUi
z*>M7&{I6WOvS7y!iL<jzn|JNnb!Owyqem<L{xV(vPUrXi2bbG4-{0SV{PFSri_3ha
zB_t$H$jqKPwRO4w{7-3zjh+7GUcGu%LsPSH*|N0e*bae98$eUEm7m$p&NgpvYh!zD
zaYj^B^x?_L>MPc+b^ZPAt@NE6Q$B=OR9JulbzSUkCk>IL@9*w{dLu4Mf^~nthJ%^{
zd3kveTeC!8uP7217iSk27thGdJb3Gtl(>GJ%l^8*psAPH=J|`fr|WIlw8<$VLgMv`
zqU&oSjo;kZ=)8yV`H6|jAK%<G{`lx-Ljwb7*jZh@J=Lc*AT+cUG->y3@BcErP6vet
zPn{w`v&D0*MEC96$IxI~{S7n)+R@kNwmt9egGY~;n3<VfTwM+QwB)_Kyk=MwDph@d
zclW`KCr?sZT3bJUs$^z3Jx%xUG~MV8MNhpz<1L`k<n8(LJiNT1>Rv=lEb0Ef+7~xB
ztG`~+BH(mFy%QFtpTGlT0U9FzU*FoQ{n~@;>5GetUtC`w-&{UJ;mLcunjaS)xP;i9
zI&)^p$u}(mI}HpCLGAH3Z{Mzb>{0mTMWBU+#eo|)W|WG2;#^pFxYvqL(M4{>eUlz5
zzMtwV9v3X`bLN=H{>p-Pai8-)&Q}(9Ry-DPdUEpCEh*nwCI`R1z8)A7!s6`g9J8~C
z_1w90C(fN~Tf0`*EcaFmr?A?FKCSY;zP=M@&$<Q$39VYSO6A<yUTJfKk{1DUEDD*{
zty{Nd@u|6ujf^!lH5&>ZI$gPP<-mah44c!>AKO*>nt=h-?b=iMIUp|XoP}m|YHF&6
zhK9rGX}XoW8Elo6AMgKn|3l$s8_<;4t*zW~ad8X{p!wFjyUROzds!LY+}Owrnjnpf
zlRG`5$XQz4B<}XM+>86`>s#8|7H!xdpc}PCV1Ib0i_(|Z*ZJ@6E_V+I5P*iSXKN_~
zB+Galj){#e{QIj^#=cI5sgYsVu3Z~8Z*FdGW^Qp(tor)u=xpnW9>#TlDmYk}B&4Oi
zb*`A3o2Se6S}qLe04+hdcTcXYtn9+2OG&bx3p28_58t{K^=Hn;&6}J1`uJW)oGE>E
zg>!Ax)=4|&>FDZ49uMO1^YeR@y~=;SUB<OFlCM3un$5f)n$`WO`1pBQ@$++Q9&1e5
z)mQxHhT$uVpn&5K-DKOPze?v_Dcliw{Gl6n?vB9Y6Z?Mo9tKApC_2r-aaORn?{KeG
zU&)n1DUgm*8JG@P_ieJ)WeQ44O`qSb0F8xwczD<_`<jlWdN9w$ix)X~d5>OR?jINu
z(z5^lVIKv7KZ{!@&ENI=`}^d>ZM*?tVQpQfj<5V08XC%Ar<XO`w%W`r@6L(StS`3b
z-97Z`>gt7S*Y+-2q{JYgU$ABK=EFUb#t$ApK75+>MOawajqUmJF|n~9U$5W4Xv-E6
z=XO3(`TAd9H23{@#NEbuv#YbSar<`jyt}(tCwjD;p00oR=1oafR@M(6J{;JTdfFi4
zg2FY!r%nCcC;xNi=H`BU^r@?h>&UTVNk2b5eFUogG_<voMg8B&*;E{`I;5^_ZZ5uU
z+cpNfyc7n8_xJa+f7o~%G+mi}ece*l7obdK?@|sOe}5u8Y5x5F9Xl+J96kE**Vose
z9#L+tu8D~WX#OH*U(L)?7qxkIwOu!EM8xc`lPxSPtoZZ8kcEly%h#_*g<rHdDXv+&
zHqw3S?)CfsNp*I1YG`XWZ`x!8>env}(3mHZmXUG7N-6mDwY7)8zP>IfFW(O;RXsg9
zV|SN{&X->p&=IyaYGa>fxqH8yXuN-^eFiAyoIB@N6Ib>9o$kMnbN%PcnKNO|oSsjg
zidL*xap2S`uNvQ*w{JVg$ImZyNn7SSyY2P$^~%c1&1wt(`7ZaHJ7MO`$oG3s9z4is
zTlM9~`to)EWI!p!iVvJV?nBZCg!A}>+ut^6q$JV~=S=K{Y5)}s(A2f5^!+{AbLY<8
z*j2jv%45(x!PV8_6DLhldY<xzm5nXw<)x(t1_loA@9hOOmP%tHB4*5)yfHl?p}{o!
zT8FvXg$oxByt}*GF!PcM!-0Eyt2bs`RQi}?W_R)8#e>UyXB*W1D(P@hTCsBF!v_bO
zLFGGxf{F?Yx47PutBWpJadL7>m}Cgt+gHmy(WB+z;r7RGZf<_`ICfWw<M(%W3;+Bm
zY}3368uCBT$P8LGwPVMQgwxY>AMF-oZs_jj-m+zjfSlYp3(Y{4yu3UQPtSw%Y^wz%
zB|GQW{o>Tr)O_UI0h&OaV_PleKhGv{&J+zPVPWAjbFIbg|9oI(aPar%x3jYYEq`H1
zczmokVtbyfm$!H1F_jhpC%eck40A!##Vr&3udEJVFCZw`*wDaWQ}u;|snKE2X@mPu
zpFZtWcZl6l;Aj)MX4kG+r6y`wSy=_o&&hsl+3@=M`o#+tFfcVT$Xb`RG&eIlIXOif
zPg%8Xo7l>gD}|n~$P2&w?d|QyA0Hp@5#IFq*;(n2m7U$)&R$+zt5&aGxNu=(`TKht
z`;NPmmYU|>+oNfxZ=QF@Auv#og^AIs{2dQFJNuh^duNyWq-6-LDp?=D-z_I+&5u2I
z_Ew84P2@N`%hY+kUG0Mh4;uded2YWZS&Ic+ka#TWQ<nZJeRIX*EAF!HX0I$R1s>0o
zd1byS@c2X*u)wCk<172E`f{!mE?L}n+2TrJ%HlrdPOw1A;=W+{QklG2vu1Jd@ErN_
z^72wSeooGVlT^Jcb~2niae^Z)Ev=)cr)AYDt=AS@N6($(v#tIna$j;Qs5rc}MRU=j
zMFFv~yy4;Dd+Pp5@ypw#%nA8d_4O5KhB*21GGB&<yt}&&-nk>A?mv%(VaM*>%BrfY
zk&%%)$wreWPj23^!{Wt@7oh2QrbY&afRK=u2M-cJBm2{(1-`z$4f3~n-kk%p&GQp7
zGBh?a)SjJX3R;6xR%Uj4K~d0ljc@w{%g=s1dAObb<Jar)pcx#72Fv1S9r4q%v$HR*
zi?!yFFko1?aG_4J5bKkN4;x>-%KE6LFmK+x9aUeonwpvdqNBSjKR-Ko=nzx*x|qZ{
zQ$WL_CKs7XAa#wMV86V*n12W;8pFcGOiWD^v$M7DvEDy;u(8zVS=|0QT|4)U8#n%V
z+;6{N&6=LLy;X{KcJoSYz)cd+eAMG(y(XG(@?WWC$LucSW#^Y$^7*s<zdxV-Kbn@l
zyri0vn(7!EJ9oPE9`E4T*xn5r40bJBvcPl29WQThK{+|U^U?vwGj+hVy|OI0T1f#{
z9H4?hK5&1g4O9wTI3P<M$B_EG|I3#zpi2G6uU}ra@7}-fKXAZ7L|pu|rDV15Y_p@+
z)<zp9ALF?eDB|bfzyO+`KHe|y?CZ<>{QUgm=J#trD_uBPm_Q3y{{Q>?$a>M|lc%O?
z7k+r)2=auhD=Ryn%z-JI!3k+;Yz!w(oH%f6Yxc&Zqg=;4JC#6#;-G~Amc`E&K<fDk
z5e@tD@7tZ3ZO;Gn>C>Lcr`jh?3R-;ZYHk8U!}j-&<?U)5qN1cqN=lBbH$HIu{L_gO
zC%(A4THLDa%?X2re>z;0SlHMO9XZ0X*sYi8!$%t)34;aqB7%d1=UA0`-4hgb1I;V_
z`<V_}2#}SP1!@It-n_YDGPkg>u#1b!g6!+-a+*Oy-}5!18vLLg@dcr)!%mz&-Mnv~
z-J7>>6-BrdMYt}4M%C&)|5{pCd{|JSbbhkBKWHUHC#V0mZQH=B$R^MH^r=WiMWy3>
zU{H|Iz5Vt2`xdtZXdG$b6plEavS`g3o{t|tJ}RC(XHE~lyxoH0=jS$T-!491URYT8
zTHw=H4-dBs33JZ3ujkX%)&27JcDPOFhVu9K_S}`+zi1JYr>Ezm&yy!iXefVw540Ze
z(epD;PEL+Ip3<bY@YJ_2FM~Tje|~aO_@nGm(7MHx73U>OWp1u`e8NrE-RhP39WV=2
zTijgn*ke)MWrJ51pmL!PTxo0qHBi7M#H1CEO?tou!V+-m0+kgzc;##)_~q?fqN1d>
zY}umH2kJ1MI>nWimIfM}Slsf)!qReK`1&{w4vqxbr;`Q5#oI40_jitrlyq+6X`DP+
z__c>mNJt2%2Lfu>ec#v2&aY%+BXjE1DbTu+Wqxx{S*S*PdU|$rbR5{6ex9KwhQli5
zgh0*LtKmJ9H!fbix_hd2c+$s5M}x!{{QmVz$-+Wn=gyrylTW$3y1F(e>&5Niu(!8g
zvTWI*D_2A!BO{AE+(d5b@Bh<en0!n@QIXNi%#1-{-@G$t&tBY9S<E0WzUuy-N@4r|
ze~fKxY$DvkG_GE~x})~D8EDPI+Gz6?D_3rWtSj0CUsp7rK~+^%LsRqM$&;Q*i@J90
zvU;7t<>=|j3G#$xkqW4Ldv9;Gv#V=ssZJ|sFl)*bkt^4(9XfQ#De2LIg$os5SDab7
zYL%0U(7{uuylfKvG(-*^IM7gPvh3Bml?R*I7uWy)C&1MT8bI<@VM)l(@4vl0fAOkS
zT+g086S^J(+8T8{xl3(fk+gN0&Z9?<Cd{7A4eCk%EG#H+I6u#}^6xxXa1`DFwJ*Wl
z1#tTT)ErQj{W`l19LJy(0B>J{I4{8w4k|>z`oK-m98XWr7uVOz-`bMd+{!K9^}b~0
zym@`Ox3?*(tFs##8os!^od5BXPv!6L+44x4a4<45g60EWTeQ@CTD5vLX#N@0g;1L4
zvFBz$Wu+wx6C-Fa<ZwH`b7bVq!l0khb~P47MMVX#udS`(zR=y(bzy5ZcrNh8#l>qD
z8;OgGg4Q6bsHz^kaYN$Xy?ZlkDvf5DWFE4T5`KSwzk5M}K~hrEgz3}U7c5YSh>l*o
zVg<+Xe);1I9Gfq!i?zOH`1H`-yRt`*9^Fy(b=8mjOJ*euc6mmN7cXu$PCvJy!;3?)
zWx{zG*n*BH!V{)XSKoNJIx0#kBqZd*=5+s$E-cp8)-PVY+SGTdW%_jSb@BWA&Ybbd
z$jt0~@9^ls0|sen>A3d^k>;9b?%tI>+{W7+py6_RTW;j>Ac?4`C=G3G=i_~{N3Tz6
zZf3r<J^#FwRPeKB&rX~;(a_e$mXn)%^!d?i*Tj5ho2AP3uiTZL_2k6Fg5u)l0F9Q3
z69r#Ka5bteELv@CE+;29!!%p$*O!-vZ|~mpM;4r)!L7kxyzr=nbRF{1yAGhJ&4X0)
z2H?g4SRXjE^X{(sX_R(mM&p||IUFoZ4D#>!Zmo;8esgcHw4R<`kMO38o74S8L_{7u
zJw5%xwQFq~Hx}+~-N@9)us#2N+LQ@<r|ZWnnVE@IR#t-M*?M|<KsD#1M@bpk*`JFP
z3+Jv{rL|<)G9`U|{%zZ~-Cj6n8Eh@Uh3nVTWjl9XT^)Y-{(br4=jV=2QuR*A%Hm=G
ztylrA1Y58`0kryNb=caZIU)ZpUAhDsyp^-9N_cZ);|%+HyFY*aELgX$Pu99@!IC8`
zCr_R<Fg8w>ojP;BzD@kbB-TB9_EhZtAj42pTzqkTynRYq+M?Xs+fJN1b?E8o=?~w$
z;hE^s;y2eS@yCaU96UTJvY~oCJv|2H?_zY~_r?4%U&s1F+AQaQzy049`~QC?yN0wn
z%oYbV693B~YK9kYZ*TAD?{|-hkvVku@W&Syl{GXqLCd8|O_miE7Yj;DcY|8@dU|~I
ze?GE@goGsI=JGBK=-`z$+t8;`e)8nWN1Tb**T=gD1`0-P&(kdwXXWPRzGgUc<=VBb
zUS3^CEKi+3?|yok?$PJR@7<FN3kzGb_*AT;W8;sgE=UWKg^981%L_$2{k*)qHOZ%9
z?`G%6#K?eV3@%*?nlWRBM@;Zs>+&?&$(*xVPQ86{a`L0kljhCqQ}dnGaewx!bKaky
zosB#m!U0Yk;3nUdd{8q`7Tj>y0ckSc0k<JRi3n6(xXXfAc~=Uh+QBL4E4V0uwJ_)G
zdaZ42EX;6Wp)>oJH#dX#D9r7D^Y*Ru*Z=l<dVYMFBHbP;hd`^Ail6(1goisT2y}?s
zPJ@g&{`>bYVn>1E>lHqriQ;|x_GxHoF)@7Hsi~pS(AvssmUpM4Q&`=|PqY5*?d|UO
z_th3YIU%_6xUH=%sAIO=fBq@UnModge#hom7Qf2PN=!{{eefV5B0AdG>)5rU-Qo|Q
zKW~5XBxS~o86D#DR<BsGq3_t8A0HnVK0L(g;_iO<#0ieJwl*Q|wbS)tyH1?&Sh9S%
zv7eTFR#p}VAK$c!+P@zjGH=Vj-&gqf*ufh&BK~}5X6H+|wkGn&hlkAFE6!Ye#tQ13
z?uQTJed;`U>XcJVj7(B;vY@zl`|*BxW`-|cz61mW9I%-C=*0Q+$3g3l&(1biR#s+a
zYGg1qHC>ZzSpNTC?Z=ju8#f~M)ch3MwQJXxJ3qU7dU#yi-IX;oIQr#mn;aAzN=r>&
zN1T~Db?U<_D}!(BC{zZGdNb_VzsyAmyxg$!<gT4NcN!QN9C&?wedO`vKDC8j;W05i
z(&l*`>SyontChZb_3DNV8yvj6xL#NIfFl~zMVQzNE>6A%9-jyqhFG$=?s5e<c_>4A
zm#-H0fmknBJoa#xUH%bFfnpz;N+$f5o^6)fw0*nzG~MVn(1Os{>-SHK_+pWHNhKvM
z?Nd?VzlF~2pq(ZB{QRI!-mfn&g`THfSrMqAtLqvPBJz02r{&9*wdLO4mUwMVWKjS6
zdwZq3#dIINZMtA}^X5%Z|2-=^`{F`p_L4U@CYGwGDJd%-<v#E0>zny-rwAJx8>nok
zsjXdl?`8G*dA6WMm0n(666#a=ZEbCT{Q6~<^?7pc?QI9opZDJr$Z`JyEZU^BA%my$
zLBoO_>YtuGdE%fV1gdnL77BEW>$e4HxJ=iJjX0k2>gVU@Lc;TmjEoo<tgNg+t(F!i
z#m6mgLPJ6pELgzs^XJbKr%yWv1`4_;33hdNN4h7!JKWCi;o%`*-#%&5q=2w6HdR&C
zlK1!KmfEBl85<wH9+H!zvuV>N1)<Ihi(I*H+`hfJ?|4jUsVQhYe0%<V(6CEtYN|k|
zi-{-Soyh@Pw{DeGPxg0rXTQ6v6l4(>H}}NJlbheX$+@$)dU~me8n`0&I}D1Qzo0RK
zo1k_8s6IdUe^K3K3-IugyVWbuFyRUKK+`|*(mBT#_JNv%m*Bbj&b#~j`<MIA?}|_V
zmv^XzlP5^f6|@|mQ&=tG@2{^KIy!60?_9bhG;!iYo=F?U1q2!r54Syha&oeUjt;2j
zsM;4D9i4o<PqydM#;ePGrSI%0Y%XT})hlg&VOMFk<?^KWe}8|MFw2p!v9$%w5^T%8
z4JxSDBpaq?XLo}}eRFSb15L;;@th2rD7Kn*sPg|m+o)|hCoA`?d;Xzy=T6H-ix*38
zW%&E*>S_aX^Xbl7M@1whJ6XBKK*KGsepj^f$$ofrl$-4&xUy$PRQ8}X=`&`}?p9yU
z(dr~2ExoyKsezBL@5kr!>p@Mk6DK&F77BcRb{13{x3;pruJDQ7QxRyR`S{w}=oM?$
zxJ*{_O~}pd-C6wHNkin&xpRG`K55hR<NI#hhyYDdOr1J4AUxdt{k^>#6Am(Qv^s%C
zjH9BW)+C?0dt+nr(Q*%gPM3`9>tx@&eY>&dXAwuM(~OxjH};)4GgUkM$n}t-A|tz+
z9}KCfsbAjQ6u!L7w>d!L$=eonP*MKyaQmZTVR7+xas4<46`_TtudfMkwStzNS6cs^
z0&cW}M;gJg4{zjwTK~M@wmeEB55xhD4@kg@eeiH)smx6yW8;S}Uv@rul5);9i>a|e
zocqG#$B!8qYJY#5T5)H>u8%dJ9v$VL`G5ax)9kiOmx3(Sf@J#T?T_8rS!~(=`sGW{
z*f+=7=gpf38gJp@;n|RJQEA4kSxgL|Z3wxyw>|vv@o~h?BGt!JK3(6E84Q{-Og`S1
zD(jl4qOQ)&(ACxT;O$%9{QUfxk6D=*LEY;946dcc&(G~BeC)QjSMSxIZ@2UJ+?tbl
zWkq1brW8&kWo5&R3kv57#r5Nkv~r6J2nZ+~FX?JE(^mk^uf{S7?wt(k-L(iT`fzVg
zC9|!q?KMM@Ydw<2M}+6Ss=J^luc@i&=<Us2`}>>dd}V2AX>jX*nZTDXUsTTdzQ4B@
zv|jYu#u=~g?cM!j4o9m~+`Cg}T|GTHL6a$K*RK8X=f<sDPR`EFr6$inJ>tAPy^nVm
zdaeMO%gAu%%$Xz4kKMZ`_x9G-<T*XI;9eIvsKH%$aD0Jl*O!oiedKl>D2ncYva{^+
z#4C_NWU$h_D}^c21_=zHZCi<l**IFAUc7qcC40R6dX}oHDhCVGl<Cu*LqkLV%;@$|
z0o5G7zP&QRT5O<skXa_2|Ni~c(9v<}7Sk<wdP>y7+M1aGw2LA8`Z`5r<>tbmpV>Dz
zse*Q|h-!y<*qV2X>mPf0dHKY-bI+P-FkiiT^~0AhM@~*wR}|n_uxb?-!-_R)T0B$^
z%`i*`Eie@o{dZUY!ri;FuU@^fD0?IET7xU`&5eyl@%2kB>;C-MKgF%^?fw1opsfYd
zbfX`<d&d_X9PHxmzBqWf--pki5C8l7yYSHw&K@b#uF{a5pdC!Ty}WXEH64|opFQ0D
zeqVEIE9)$i%qCDHbNTYeFD@<yZ7n!+=FEgCQ&>t%ORsI537U%8Rr<Qkxt-6mc70Jv
ziHol<@1sYLB-BAO?smS2kw2fhI=fGwK3!NBYi*KyYf7oiq6a}iK^OK`mw#MhskHK)
zdx?|O>t|<YgG`(<b!w!0poIzN)Y~(S(?Q)cG2N&QeTy!vcs$`h8z>XypRjj?#gCNR
z-?l&7!38jEYNlW@xRiae-xaLrlYhYRiN4Ox%-UgV9z2b0|F36dCB<-Ie|<f}fvMWz
zQeS5Uo6qwHZShDx-lu42D0u7Et&EF{SQjl`{P4+>7VqhLi7zfJ{PD0|enZ*YsB3{w
z^DZs%+)?&cDkwNOFg8|q<BInOo7q82qmOh7Z!CW9cP((Hr=Opjiwg^A((}P%Ht}Y5
z{<hv;-p46#Y^uNUfV%377b~Zon**BR_q?mo`b+WWZcx7)G@B3<<WyQ}8WI{B7#hmT
z@Zsy%qpLz!OQ=s-e|>#?@|znQca*)I^}{yC)s^+?)vFA4b@K$cT0sjBqPAuoHPQ;+
zQppIK?tH%pJe&{Ov7-c90svZSeXyCGp#d?4AYoCUP*YoLSo5RcnC4BZ`hPZ%z8-si
zetyZzORS(hpH5CpRbOAR*4EZu6P&57t=-(##`d@4vw3J}C}=t$E)KLF`sL0~_Mis2
zxOn@XJvKXb?gXt|U9obdV`QYHiK*$!%9eg>zSXN%U1Hg|f1&4!C;J`2*-Xk!cDWsR
zyaY53QgWrxBROz?rVMy+4boZ$P1Att(Ip#KJT~Dgozn&$R0U;L-o<^&CvV)4@Sd)B
z^v}=Fk?xA~Crp|oWMN^UpsmgAv`_$4MqQ7u?=63SPf<}3G~DlylcS^m`_t*^`iaTO
z%&DoVHJ{I#gBGKx`OWFLbt?+A?x(G-ZAay2wcH0TDjJ%ajtT-N?&P?GTG1Elz^la9
z#qKt%`t#^$x1fZ?4}G<u98hr#8vRiBpSNJ!HZfVNl7{wncB}GtXRM@*4Gj$~>i^k*
z^3<hEK^d8u3yYthldvjT@k8%^jXSKv^XpqLsOQr%!T&%jxA=o+&)9r@eSiG;@nHRL
z4@n7$0~am`{Qmwvea3{f<?rtuJb9Aya63O}j;>GEy6w)L7>0&jyR1N7czb)hvENBQ
zFE6e(K3OhbU*C-E?8o2l*RwN-h=?RSIWe)Lw>MRK!p7L$WeY=Bhi%xp_2`F(hbK;(
z#`fUx&&->fRQY7Bj#wy4gNF2de0>em&Paf^sY*&pGBki%NxrkqIJmfy=1iEoyZrs3
zvuAlh+2q<9$)uzthMJmlJ(9+3*Vo6V&zUgy^YindEql7r+gg?`RTUBzW~{L>zjp1K
zMfp3K$1QI_``cz%m+S2+d)p<Z8>OJ9$9Ld(@#cz;NlTV3Gx9sZ2JU@>8&0St_ncqg
zk{diw25vz?`${{&$pX|K18V}65a2T0toWG^XdMcu>AzS*MqFI{W3lV3?Ca|e9zE*X
z*D2DzZJU{pu<*yj{Pv(8ctCjg@vYg{17c!&LRW_=>gn}O?>^7Cz<0J8XuxXD+_{B6
zJ|uRyD9PAV2t0iF@WY1>4oOK$@5SfuulXqiTDGz(bTw!%f{aB0gQcbAnq))M`hPW`
zFyt1~5%~Z8{{OSH&HGDzb{3YE9ot*|T}nn>sPn<or$<kp=LHSD78Dpfdi?m}%3$@1
z>S|>Z6A^YknTGy;{`KPXnHwfg76x_OJ32T(vvG%7xjA@vmK=RvzcKBslugA4hPt}C
z51&3A+J3)|+uq*(&hGMlvH76o4*%yP#?=}?;{oT+@pX1~2JLUyzIiifmZUkQ>)`F%
z(w?54pxyG_;`%CTcBYw^Smfm7K#BKo%NrFnwMC$n<>l|?-1_BW^MfMl>g>L~xp~+?
zF}j^k_RyW3#Sh=S>DgQT{hGDC(?WsceX_|jCiH?93$U;x9Bg9UQSounk;;n~FE;Mp
zZGGtQVM(<VbxTXhZQHi(D1Od&=gys1w&`*EYEItH1`WDZ|M;L-_2osQvU}fx(%082
zK0oWNSf0wv%naH|^!(i1p5RT6)Ea#Q9Y2tjl?AGYSlHMeU0E4yQTwZ8Z+%V4(^H~*
zs=ju8uE@*NTeNub(-|HcGcqy`96!#!a^*_Uuv2BF<)zD)AHIIg&CAPs?c<CrP!5u_
z>3H-g3DmXJkK5x=SZK&6Z`U(TH+oaw@hhMu^jos8^93*WJ37lWdqdh;DW91}thu+h
zwf6V(zpglwb9)<a^!B{m5AyLVR<8!l^S*rfa!&H9RjUk&o_NSum2d<v_nVq*brdu(
z^Yim_^Q?t-j9y+|1+T7Xf@b*x0|VDQ*5J9drvWsdQhotGpThX^<x9|3F9rt%fh*Sk
zj*7=C=<EC6+bH5zQDFgE%POes=HTkO^j@K{v2jXz`f2+aOdq~|I|f>=3Yz1-yv$cf
zSb$+c{r`WDtZ#n^bZ}s3<CSiktnLq5dioXA1v&kP@kKFcsnf^D$3at2FRrc*-}`vl
zv}qMzUI;d)ys50NUhLe?SMlS6;<lWdLGNctfm&5ULJ~`pyVVvJ{eIXkzhLFc&Ym6~
z8T-0D_dbKR`aH7E{KyL~3&104;I1=b<h0}pDI;;4dL@n7G&MDM)c?2J_y1otsI-!k
zlN0(6KDI*5_|m=OuT#>}oPvXc`!Y`~cT*4m%}ZolUd9V*jT}$RJKiS?+Stg(E7dY%
zhQyO+&y>u~#SIM&C2T4T%yMotELZ@VhhLU?dD)Mj&*w)T5AfLk|DQEzu6%!e{hyD=
z<-hjrum3LxTIzjsbNa@dn?`T$?w;=G^$k=CitER1=v!#uH`l6F(YbBGf&~tb-kay&
zYneGy5;UCK$}OJs;laTd*VoIRI(=GFHB=`wH1x#z^X_qRaeM1Qd*yznzpB6O3!YKo
z2(*xrlB)Rs&-VGpHEVQUyn1!YaAH#B=V!cDrLT@u#;6D_T(rokuT#XmsL1Hr`uOud
zWk74yi;9aSRf2gy^%<;tv2eqNfWA(V!=Im@2km$|_juN<SsI#}6O)yWPMiWh17Kn1
z<z+$jdkl??CRILfI3HP6WyQqA#Bf37%KqJDZ>4H#YCaqlkN2qcH8eFndV0FPq)IYm
zP88f2r>ygol#~?V9-xt!n8?A+Eo^^pLn1Suj730xOkts6P*Bi=SFg0rS8zQ&*vt;v
zzzbTYuxQbus@c{YEKK+ADehacgvI{<pUr2A4<BdUyu1AUu?Gj6L2EF){@lHALE!JN
zuZJ%zbl#YKU2o;=y4pUwnjfH}Os*M<1nn++Tk!UlsfDHG!J9WFFJ8R3Vapa41`$!w
z#0v`?LE~e`dZkmp%|8#?^{M7JheKRk96aK1_|C<}?twu;pjA+v`>U&}7A;u70IF-(
ztX(T8DA)*^s8LX0&<<ahGG*G@Q>VOgZfsy&xNzZ#lP6bxw+n5LTMX)7*SCp5SFwHK
z1fAs&5g{R_8x`_CA}&tO$;k<{9E9zph%?BM-`~ZadmO$#&h`1Zxld<!6ngAFeJuXz
zlP3!zH>VYOEv_gjDM|6WQ~BWmW7M`B&Eqaz2QOR@sQ>p<{rSf!Q$!@BrB549e3X%)
zUTzm3Y{EG;+Sj-D%yU;qN5)wunM%i9x|*rg4gU4@^>M2vCrw>l(fht(3Id?X%FxhI
zp=1^&##yG>ZJNQ$6288=$`iCnTuh8jUtb@z5<e|1EoisF^`vd*@BUAIzi;uZUH|R-
z_UAdUhy=cN5e$fSpS$*GCl_D9#a#<L3To~y4*OfSqBOC)^s3f6tJPbDT<(Mx25fy7
zmAm%RuE0XYMJp7X8-M>kJb&ZQNwZm^K65_%YH_?+D$nBi-RemnLf$<uPEJm~xY(V4
z$+BgOA~q&zL~cr%_x#1}E2pGl_Ew3?*M6D!=%e3UtCw%nH~Hn|<yjOwXebk`%E{3=
zHC?}dTkh>ghg!KK_SIOj@kl6C`78t#K~pq?+15sFby^#>6?BpZJ3IT_=N^+<R;<u)
z6rOec<>loI!&aB>EBo`K5Ony5a~sdWFE1}MGT2sq0W~|!a&9DS<-XwFC({Yq0e}8H
z|KWE2?YHVLD=8^eg@!C*S5N|h$A=CbD){@W)FkhYgm(D478TEq-d@*?42@UU)^^XC
zBeVLis{#XP;g@#Unge~Z)?4Byt8iLcTF$Vmwc3_@yRDI#ooi0O95vrrpoJY({Y#fG
zPyYJqYR1h?OJ^?MBvV&c7qPEq=RIo`&?@26)Aif;@892W^2n=OTeYX@L^fq#U-#4!
zblwzbuEDnYo5}wKG0?XA+2;Azs&$l=nX|90X`DWN`po5<c=Yw0u5M5M(A^zyduz6O
zg3(7Qvz(6D-DNLrr%j&RT>ARj!otVL(&n8q+EB=o{8$5o?t@7P`|*q8`waVf7x!Qw
zdFkU8W_?CTD09=MO$Bdm7=q5lIC=8qqT_;TM>+&S&C_#ptw9SUb>j9!{Qhxt{{DZz
zxcC421@cSM*4c5O6?2J)+d!+HL1&5l{r&y*-{fA<K?g>uryg8c84NniqF37d(;rU{
z4*}a{0;#8_IL5@xdGv9|jvY4TdUbarU#GDwTNSjFtM1>=^eI}QT)DTlIBrfm3mPAA
zadnOS`>2?~qT+*soNZN0(bH28|NZ@KQTa)QPu6P6^Zu<KUS3XDSA~}D+gANO&tnp3
z-NxMYzkmLGcxtNlGnw;?K)w6;{dG4sCbNTfa49;sz4+_w;^M-pA}lB<C>Xe~;Mp0;
zouRA4HmP`8)$iG}=gE#878f6LPMthinVpsO<Rq1odU|@BR6IAex3|A}@<hdZlFIjY
zccZ^_90DDPv~Ba|$=2oXbllzCPEArd`S9VxPpd*#Ke@Fv`!pXP->3Kc|LaxxB!X7i
z?B22C#JY9sKDEo&X{-*>`f30FXaAk;`SCXo9&{`#E}lGj(j=Gu%rZ?)&7!$hrB8%Z
zy-vjLDw!CnHTBNMWOuL&y_QarHpx&}zI17)TyV$XcK*|4Wo1R%^X@+R`uh6mNh&8n
zo3`tJJY?UQcX!vOy?gimxt+fsq;&tkU*2V9Wz+80evhquc4p=#ucecY_si@1&opw?
z3tu-UW>-n3rJY^eml;ku_xHtytqcJ>Q{Jv7Vw#F)Usu<p@9*#HZ_m9Qwr%UysUUWh
zPvQ-WQ&40MV?adA+cp+X!G>UI6q-6E#O37lrfY?Ig{=$$xv2ivOZCWUsXy=St^OpP
zzejO>%+8<>Eh(9A-oAZ$v|GGe?y!=mZdAxT`}%z^40SG@n5dj8EiDbY>#fMmt?k?E
znKNg8+Ee*CB|18~^2&-pCUp~i&q+_%c%@FrT9p{Q^grGw>)M}V=0DHo;?LrThgfgk
zy&GFrQZi+G&do{Be@s^Qcj@;LJ8<-<>%U*G*O%_Qwk<dM=DBlze*XT~fBq`JU#l*z
z9d>5U<4BS8^z_P;lT;TSS5Q)_%Jtl&b9#~ZL2z=K_;S+Z$)FY4Po6zn6ty)gY&Y{(
zJJ8`)ZM@PY=ll~A6s*eLXjGXj{Pyl{cjDnTMLWB==da(rdl#`WiM6JthQ&8cQb<_X
zFz=2<&b>X7D_5>$Xh=HRwJ>^n-VD?1X;=3hzjXOBXcgw$YOiUjA#0;V8yg!Xtjlz|
zM77nbToOSi7l1~?e|>$;Fz@{%-P1-fv9X|$-Yxm}<36-JnqylnrtIE#<X|&<>Ari5
zT)At0zujK(`|WmCU$uL$uC6w$`jW9^*)peTsc+xCKiVyR{7@_R#oguk2Zg(i9}7Ho
z>|%fK;+|UM0wr1E_b~&rzPcQlR8(~MhDF=P!Y`mQ2^!xT(Oa`bK?hPSSfH>a|GwPc
z-{0MHa@Kq+Rx>aV;Fq^MGS9Y}#b4{(L}m94$;bKLzCM2TEbm;aQm4<)&a(Qe`8__?
zdvRZFHRwoyMeZ9dN?%=Rj9Po_$H&L6{YiyE!NH&@8X4Ov5k5Y?g3?k}hC4e7nI$D9
zGw$uNOiD@$*i%t>aPq8nucb~uKRx~Y^?&utOH0EoCO!>V8B+O<?|%|!|GwSFyeGB1
zd6TpGjN7!+*RP9%9JMj|_=2F76K2fd;OFPxl5<mNclrBkmG72#P6lmw>K51MniaNY
z!UTaQPo5|k83ldOaB*>2ud3&u4ytREHZg6|d3<GMu$8z?WmT2a(x6Vcvq>j5^&C0k
z0!kuIty~*6ZWOc?irjGLPRtyOLZ|1pSC@DS-?(+FOYW@F2c?j|LBYYGHdoBPn#k%r
ztCANC>FMbg7Ym9;<;WbqVLl}uL|OdWSlIEe7R<yh^7qx1mCfe&YlLT;=O6p~`+MNF
zoXEMXFO1XA9r^R~bK&c2x(6rEy1zO7ynv8U6R)(H!?aWjOH0Ozd$yBQ6crR0vahe(
zdg}UxiOTK*0s;-Z(q^D0)1u=WHD;UT9$FE&7_{>sWMz=+7Yi|Ub93>F7cYWFMumig
z7;NreS(tph@5Rl{%R@{1yp|riwKZE%Mn<Pfq}w>}j>TT?v%E9yYJX|ZI`--Br_=gX
z=3be1c5Hlb^33Z4jm#fDemuDQ{XTAgfB!c(H?x2I`0>WRT5GG47Yjb$Y2%e%ly-Jj
z*lvd3$9knf2N}&W&+h|u7QCivRsFYn`r?H~f|ZieqC@@M7dks;+*~sOwickHqeEwc
z+hRtBxAv#@SLE>g7n~0gl9X=m=;(+ue<KZQG01K#?C4mrVbk{Q$N&8NY*_IjVK4WE
z>H6_~6P4YSjE#doEO};L`3ba6Kk>_pi$8um?hjlUq{?vM?d|P`>E~oXOF<{A`5wBm
zGMLprt1fm|$-$-G(+fU6a=o%HHv0V`Q_o2oN?(UL3U__J|NoyjXwllw&(9w|e-1h)
zW$*K}b8{@4)Kt6=vcCA@pPHV&IRE}W(4<C6WLtAHGlPP%GV>%AMGXy(>}zW_uIin2
zZCz~lg$n_orq{Z4>p-hv+xTQxeV$YM``f|m*TwJG|KEFc-~SLTQ5DZ7ozq>jZ9Tv#
z-PqsF#pO%Y1Evyia^?Q=NdBmikx@c=ditfl9g|cP)zy#lT<#3to)^0!L~D*!Dc81b
z+g60HpLg;7L>12ZKOfsAmkGaqad9!jg1b|HA5BhPlPdlmbe_y4mCSN+(C+1)x_%W;
z&}lf5%Y@TEJUBQ(h4X&hZ`}|rQ8s?LoG;ZXo`)_i^*(DbH$vTS4g*6)Rn;pSvu8&?
z$EWY%2)+6C_I5@FJv}|E{@%)uf38bPA2)zBTE6unw_fVrNI!;FMvyuPO8(kd*n?aG
zB|m=R-^wNW;i9|z!_VjKukU84Ju}1b#-2*!b+NnE$^sZyg{|e%*VnK4|Mz=U|M!=d
z*+HW@S67FhwV7G*?%g}L_kKE_LXRFlK5H`ZX#%^{^jWjI{{H@+Z69u9V{>6usP+_%
zK&LkeX~$S!uuh*crRCC6@59%wg?-U*YHe$K1UmDeUB0fP-~OLOUS1wULrV+GnVH7y
z++sSQ1&ao$r$i1;o;81A>s6Mw_t*E#w5#1ExlB<>sp@Y5qZO#NGLdyx(Nivl1yNhG
zpaBwlex9wOr_i;v(d^RF(r=TK7cE{43d>)5T*f7NaetV%ZvA64LHz8?@SR1eD?+qD
zyD?n5L>!-<n(F(Dwc5$4X{MS;`+LpQ8hg#t?_WP-&9*QH7bB;BRIcfne;ib^|Ckqa
z?E4fWvp#4jW0T2|0fj%Z%&GbR{{BwBzpoZ_%v@1XQHj`s|39D4&$zS0@YnbEp#68<
za#!EHdHdF|{9O!>w3*NQkNNxmiX|WG*?4OA;mJn9_TFn=_8qA=Pd>)e(%K3-qp3cA
z66in{PGPkNpU>NiTg<I2WUM-PXK%H*o}M1)47#$-BH5u^vqC{fS7cvbceUC^MTNz^
zUvBHEvkw2J>zv+E{$9>p57Z6VoRBL33em^~SyxxR{F8KOmfj7+qiwv>Ja*gCs=vQu
zWw>$k=1ZGp&*#}zvpsmKZy#^7t;{_Cp2?3JvyL7)!cg&ZUe(7L4c^oB7%M9C;%w9s
zZf;7Qpu*|eC33OSCr2h3ni^4>M!z=ZqoqbjWBtYPV`$Cv$@YnfiJ+hY72D_LT02it
z0VT;F?{>f6Q25v_WKD$NWOaWr+hqb%wL%XqbZ!?BUm$N)!ZB4V)aY|a%F8vSi90nx
ztE|r3|Ch<Vz3nLIXuxaH`HT#DF*_PuyTuYOE%6Lk86shxH|K%pS!Fdfwy&?Ri`%*_
zJo4MquKe{iU6cHKF&`^FKRf&L`?~+rr%XB0%iYn@aU!RJ9a>U^?kr0E^6D!0!Gi}g
zZfsciqEP4DtE;QQtGD#yV!mjEoB*w7KX>ljqT?GZK&NY+on`9U@7Q{#dv}JwQ+7~B
z<`ZT4?ItPR&ehcG{PQTNtK!Uh5Y)_A*p%=%pbngO0~|Mi8j~;XPnt5N1>_r0g>$%_
zpOL}O&+o;>#q1zo7Ck-1IWM4RW$^N(S65a_*wt7Z>ycc1H{sc-soJ1(P{s7)dNhNV
zMI2@N+tR|q;4oDyv_ww&^P`_G44|!)RbO8v9`BQ_>^r%sr%%@U(VLr_!}hN9s;RMg
z^!V|_Ns|_pPb^JHSkSOihx>iQKcV*xdAoL(zh9Jew5y}Hck8L^p!1OxJcaCjJ`whq
z)DpQlP4cgt=cErWm(QP-2&#at^NTM4HxDCM9P5>Sd_BItRmF2f;9@o>C#MUm!}TjF
zDmvuODy<07vaqlKEzAvAef7nKh0Hm*xvu@Gf}k14dwZ*u4GaWQPfruI?K@gnP|&b{
zzx|agQ>)TfOZIN=-5R_yq~iPC@`Yim1w}+!xJ0!&<W44S$+!qUlhDC|!E3snZk0^;
zq3(dGtgNgH%irJo@cHxOxs3n75drQAl3SvR+}T_GeZuV7-J4QRgBv*RE8e`x`SSWY
zzf>>VB$dqiwAA!;=V_@cu4b)?+j~o^%42De<0O@ol#~PK&iVbmF=Ngg8Dk&yu!%~p
zpoZ48X>CfbT?;%WD!HBSRq;G=>XgytmT8MCK0caZTW!|HE4}Rdk4HzlKi*8Auc)hg
z_RQqY^1r`ILDsSJ%dsr@&v$>4O61Y%Qxe(n9)HRwtNS0@l6e_4S_~TB1eLn;_Ro8E
zc6R&E&(D)DE%D^w<rTGF!MfpFFZY+fGUjdbEkT{b<E$@SKtK$%I~lZdetVuQs2}V(
z>B16E;g*&b1p@<t{5>DrUI@0{+*4_6BE<_@sJ>>64yXgm$jBJ5`fA3-MXfJBwiFc>
zIwmD4<>cmqwgIfTnpN`lmS|sJ-y-+T9P%|E7(pw%&YbbFu(n>DetsTE-_=!9UtDaF
zvM$qEv}h6NtQu))>5A%V=e1#rtG~Z1C@K=Nofq)*^z`F<tG@><@eus+^QYt5u*IOg
zircq~+s-Q3!x1`j?_OKbnukkEy+P>)lu7UH+4*9l4x6;QBm{x79*iyRE(vbNBiE^L
zb|PxS{_>LL%MV|@D*E_X?_*g#-XCwb-`@Z_j&*;XEW?9m&)PsaXm0sEL7SOB*Tn6W
znxwMOf4<!W70=%{X6&o|JuA^_BWMiJbCN;ntB@5TT5pq+_x<_gZS0dCd2351Ge18+
z=*-Ud9~qh19{l?Hx}&$(^mEFipTB-Ry0FlBhE=K7o;`a4R)uKpJ-<3|aobGw%{J%f
z*&g0k`}@Jmmn$pgt#K_YGjnos+EDkm%3~5}B`w2&%gg;0PaE0&c)<MU!(skAU%2n=
zcyM%?x@))C)ykYR-Oq&u1q1&<tJpxr!e3u9U0hrgw6wU)^Y6J#RC2wrueN%{)vP`L
z|NSl~C=jq+B#@bz30ebZBE|dd?d|qEcVc$z+67t{e(>PI6~W8<UI?D`o0bYX?@g+g
z4b<X3+|D1kCc+S80w{*>@7o*tCMxd)=-}PV%W4@WQh&Z&_6MD-+TGp#tu%OlUF}6>
zuHqLL6f;buK*zbBJb7}%_U+eqR(G4;>jZ6BtN#A3)ot;?X}Zy%!|2r2)k|Jq<IUPC
zm3wQ;##h#AppFA*yad#eUwrYw^ZE5{I;U3zE#<nBW!lu-9JsqI_o8wX52)WZXAh{O
zmd}&?_{q^@hCRKD<)x3Cypc}Lfk=P`mXIVsNdZ+N_UEUkpwpRn<n3a<XoxB5>7CQ6
z=M$WHc&Ybv(4kug4mk8k7&1-O4rgPyv!_y+TU^hjq{O7`{k`5-S66e-yYfdyRu+_-
zKl)w$uWV~8D<>!S<IU#tA3h$J@0L5BG}ofg>Ajogym|AQ)HloA*`ZMX?%v++=<Rut
zSJSLrTwMOELHk--EuaCUxB7R3gMtFqL>PkdS@yLxg0`~)KnG6mDt!&wzV-Nczw;!O
zD=UNDtJSBA?|-vV&40e#(LP!0l6MC_9+S?0(9Cb=P*7kn%Pd!`%H`pt$&&>|MOk~@
zK<9QcGh|&|wY2u`j-5L})y<qaGN5&%QoU@qx8*ulRatpW)9D0F@v*amPHbM}E~2EZ
z%?&!d#clDyb+NlYe0do>MLV3&(b18EkMCIZ`@QN_E(<FJSJicPc6RjifKDOyn`gu6
zIVoU$oGqx3(a-?Z=t8!OjwU>Qas1fH?%rexaJIEK>r2d$`Fq1+S>k;Sc+5c}57HaI
z46ZgmB|Vln2C7jn_V*^=`0(&B=x{(#T2s5b^=Ikwpp^mp>uOhA&0=9?jeL53Vg2Fl
z_v=9WkRBdt<p%Y!LHiIv6LZDS{Vp!vQ<Qpo+S$)LCrzE&x@C(AL*@G;(R(TiZ`{89
z_}$&z&t$JKg{%tUe0;3;@QI1apg#GjsoL!qE(GLFaZ-DHjP?H=P(fVzDdowNCmnLF
z9UUtI9znVti=5uv+glBqHrkeVm&<d~kN%YU;<vX<Gfbph+}s|m-~X@4Yw4lQ>E~Vg
zRj2H;F4(bqxAWSt$KCq-1Z?NI?x_2_>szU?xH!A#qzij0i)Cyo0={H8rKY5S_Vac0
z^c;D2clX4(b3vQKVs@ALe#vlpx!X8sYt~gzU-#r>^=>(Ti@26m_n)4gzO`IxcfmuZ
z5G~QDZ8@D2CJ20ae?R_9g;+Ca1a-2w^l<}lEm;R{B7-{@_a%-&;sso&!sF%GMx=}b
zju-Xy&FuV1KR!Iv2wuj+#w*2AUS7Ue`gO!<Sp#*S84aN0qhDQJeQR3a>Z_m?KXc~J
zb?pz&D0n!_DBH^1(b19h)(s^iqfeqf$v2&xoj0bRmjg|Inwgn_dg0FPd`F+2o-QaY
ztz9M34VqzEQ2qTKxF`zLkuul&k-p|-x~QPw#nlI(HCwAsSeRJdpO5YtCQ?U^904s6
z5!DWJ2?!7X9mG;)(_Q%Sk!yyDRECKZ=)gNOGqbSz!1MQ2)zp%1Y)IUr;dAik=jVoX
ze=6q9-+%J#*`x37?%r7N(CNsLBOmts0c{>hKGGprbN0o-?trO(zunIN@u*uLbaLc8
z=?#TGkb<VC7F5<i`*UXJyx&M)28WtPGAOZwiX!m9^=BdJ<0aq#KXn5%(7}`Z*k*aq
z$}Rub<}X~Kb2_ZDu20sQt=Fyj#fuCTRn>(V7Z<&_u~GR-mg%3re-qQw)vH{(kF{o>
zs>t)0pL=^-;;SnwC!|U;v-7pAUcLHW>kC=yG7*Eh5$=652PY^x2kfh<<dL(9C|o?H
z>gy}c8R!0lXo-S4*AE^fFdS%R=MUIflzQaI5zt&{({fOO^kDwO^IA$ui|UVsePIAK
z8eCFh^78bOl9Lx+%-E26TFj>IkA$C}ALtP2sI_jh&2qW6oPPKE*}1vapdF2Fix0lv
z|DP{%+Q)O&?;p(0-{%+*FyX~VokJ%lt1rBm0UBhoE`OI%ztQKw+UV_D*3Y;9_k($p
z&f&|Kg|oIseaUc=wXF)NHgqZ~G6EfiDIt;Z_4(7*%gg<<?+2Ub-Eo+x<oe+GbM-2n
zhdi+@UZB(TL7l~3w`O5=KL!RVlMIClEkjU2@>t^dv5Wnn!M$V&X?Ji+p7Z>M`Lbk)
z1Skg}OIV;wTwfKs+ND2X;w-b=u4TTnL0hb<zrVZs&*%Q8RBo>+8jW(cRSFgs5_WcW
zi`-QgU3a*?E_UnxzYp8xU&%~XIhke7%*ddxug`EGzWy)h5W6Rqd1s%qRs8!uf9A~0
zt^fafRegWg3mV?>oo#k!M?*(P$C*CRzz%5S=Eldz$4ko=Zri%Gb^d($D_N$yN?tNm
zS65$D=KB8Op)+XSP^y=$oln-u&yUZ>#>OD=5X*|ISyxsBI)CXnw0Fm0x0DnWz4(1R
z3>h~!se+E$ZD?Syu(sx&7cgha6cHD9cjv_yAAERt7<6L6*H>2!D?g>IxSAERJ}&l4
zhtrXxM;#Ym1fBZ5qwcSjif2=QKR?I~<?s2_)zvR5bBW5!udnr=YhN$NaA8fPagV&c
zTw`OSM(nOF4>*rLa9z>1blI|`$H#gvWSHF8UvFPjRP^B8yFO5FM^RC6MdapXF9gqa
z^(M=JXKm_0m9xxYSYFt3WS=1~L;_SfBTF1ZmpJw7+gt4_mhNRiD<8am%^e>fpOTuI
zczatesP=JjVF_Cs#VRf?4!Q*5%M6#+Q+unw7ySB?3F^r0+_|%|kDZN;YlhdF88aj<
zDo3nIJv}Y*>;3I36Lu6b3JMB#9)T7uVymLIW`Pz1Hay?2GtVfs>+1haKi*$kAJ5<G
z)_iw&xw5u4cmAG_Y;62;JrgDfnB?9H`BHJ{<?h37cXyS7&J|^0XJ1_O^wc7E5jACH
zX3#-lZi^4jv#o|zpvrDN4N+^`mM>raLa-GS<VwoQpd)v8?65eosi%!sI_b#?@GecQ
zkQEA5E(`zFEngg8|5tRA&f>7OQ9nMN)?XO5`r)%@pb_&5!Bv}<`_BiR3kVARoyF=#
z#>SwA0O%F~4o*(T&1q*{`ZZWU{Z&Yv3+mFtXE;73-Iq8HZ8o_hMyJgD;=m&!@DXrO
zEwSIa{GEcPCg;`F;qDugj=J<G7j}v1cD=j1`|!Pca*~pgH}+PW=iT3@Tcxwe>G8|U
z%Oy-Q1WcrQ&mH<K&g~e#;TY?Sef#z;a^Dca%+4ob%OvV_XNSW2xz^>g{@mdf*V}Ul
zw1Y9Oev;1VO)nHXKtN;tt*zP0Dk>}o4<0NiFBiA%I~uq$q@bX{VY*(dfRGSVe0=<k
zTSfi43?Dvzym&7W)U4lI^|dK#Ehs8n`_lxw#P$1ndU!0XtQKWoUk7TtUSB7hlau4p
zuQtVNDHB6QMFl8NXKlT;>fMuMkKf<kZY{SeDlEKsk8@Sx;kHHY!td(!okCY%-NW(q
z|JV2TK{xCidwje<F+aZ_G_J8W473I&?EmMkUQpoz>Y9KXI3Nb3M*Y@X2u{~%(+huZ
zSR6y0WBLTTz)ixsOh+$v7YhUE<kp&+8qi4yWp8gKetL59#kIAwA7~!6s`#K_BE<{Z
z+{4Z<ci`Yb$KNxrEOchS_;_aP<jIpycK-w|j7UE}FY@f%)ccjsWhc*{J!3}4?(+9h
zXLtVGy)pTC(z!X7GfXmtW|?M#5BH7O$n^BoROgBci+A_;_ls(WJ$YTTukX?0$DqSO
z7#e2JmR=RMR;xm3lZw_<F3_QJ%l+muFo3qSc8lqP&UG=#yA$#L`;~REx92ENY7JT$
zGC_s&*tElYEBM|E_`A4-6vQ<6fhv{|j;GI_J$iO__KJXoOmE)2ap_k+!f*elA@A<4
zg%uwkff{T}y{EgKpJ%%;Y&Gb_>5Gpe=Jd&0E2*fk#O^L@UA%bli$a}a-PYL=kLT9(
zXhv>Q*;W3YZ)+5<yuAE7tv}|Vj^o<3x-~U53&K`|=Jx;XF%pz+?@i_abr9X)ks>Lr
z{{M#gdDQTSO!<B4@BJ(Tjyag><0bb0ekg<1^epq8y{Pv0H_*oUoE)8+ni>Ys)ia<~
z!q?VDg9gc$`_FH4TkIGTA_6+~Y^qml+1p#7u5I@9bz$Yxf7Jc`_4N1NEm>Drg`4!I
zW?o$6y6^nih0g797fq&}zI#^|bT<KLEBOC^wNrGX!+uvPpEioxn$`O2>+9r$O{|OD
zMU$?ti~aGw{{QUf=MI}@Upr!czb5%=x##&)rw&cijs9>ufB(aai``G0J$uzs&r@ic
zUaVGz)#s{>9Y5a3>4=3Lay`Pru)F;Ix$oa2K0oIZ6ufAE5L)K7Ubwrv{NbZVi|($R
zT>>i2-`v;;+Ln5+>b360$20C;Uhcp4SJV1>(3x?dmFcgpujdC%<UEe(IdjHmP5gd2
z(Dt+VeS2OMp3&3R=63BC6SZ|)nEY0Jp_-c7BBxfaMaMNtKs~j>8y2hw_XQq1miSnN
zMY_Fray)qKJ7-Q)0%)FXLm^jF@8M%7_09SUb7ai?Aj4-jES6Qh-}@aj2lnRve*5!H
z0Sq(Da-~40hPAY?9GpDMy{5*-M2c5QSsBzrII*ec`@L#@MMXspE-t5=n^Il-Jwh^W
z-o6bAMhTM)flHS!2kxmT1TD||_wOG=Lo2tql8z2fXJ==Vy6OJC)!#u^L4Z;z8=p)^
z)YdFU2GBv`qS|2!hK7QMhK3opx2=8Pc~)Ohkr5PWQ?<h%JbBWxWs8Z0we{nRi`^%r
zN-p)D-nMx0;;Vn=Xq|BSt?1mgr^!=C9x{3x2wTjtsOe!`(5Xw8FN0QN-Puza{6)h_
zV%LJ_@9ys2uyNzTeYL;OSOh-&_~0OOMRhf39&VBQMvZ<s+e4t0hoD8bi`)edU0}8K
z^z_`YdGp~$X7)4Y0g8q1@7Y#VRDkMxu)OQ(lP6EEh}x>vCu^N{tdol$GzGyYy<Fi2
zs4f79JSf;}lO?3vdxHhQ#T7W@K~V*&91b7T<bdco9#U9X$ic%CViUKorcy;!b!MT`
z##Q0#`%X?)e|&Ru`V5;&BfYpi9r1NPS(V-Uo;>>efBL+6eedq>R#sAS0*$JIdXSo$
znhXr??(S1`B89~D<F3fne|o}s>GEaQUiFZS42`U-t6J^<{}B#e=Hr-<puoh;4C<hR
zyt^WDvzn8$vunTRk@WesZBL%0$k^3Lgs+Qf)Hw}W%XjJ0C4<~sCKi^KiU0roU3A=J
zwxV;}li&TOULGC}bFE52qm??5n^-{i0JQN+g9@)T5gVCio8>zB`1HIm?Cj`xVVbI4
z#Q>g7(vt9;<kFvTvEt!mqj}PYE9$;HuDs|!Ej1-Q{rSzv8S@^$cH2K^j!ew%GG0kZ
z$wlrPJ#u6Y|JWCFtax$Hb2rKJy`X;9k6n;S=VY1t;ioF{rhL4k@pvbwJ1Y@y{tH|J
z^*sLVC3(KrXr6Sc4M?cO(#q=5$;s+n#~(j_464d!6e?|W>yzQ!8pZ4H?|*S|gpRwr
z`;lYE7CE=`Epp$;u|5C3-i7ZwckK9cdUAxFzrR0dWykLw$;bPC{Cd6q;j?F;MdfGa
zT3^q)Uk$ocXiMhhfJH8yHpfA&TF@-Vqa&S6YQp+vW@5^2Jr0}G&VG1skeT6p{WNO}
zi-bQvKJF-Z$OJl$Ouqh4;D;qCp8xh09*oZ4+gkMWRN~<_-i%vYG(kg>si&tYnwf=t
znUS`&;^U*5`tu(i9*#e#;^N}6-X1o{vE&DL*`n}f@v|?Fe|BO$c%4_2MY{dP{p078
zQ*F#c1ZwUE)NRb~h~ur3(|){jVbg=xZJ)Y(oxfy#_#7d5o_FS<+qb3f*Z;S5>zAAR
zJR&JcX_|gKUwwT&<K#|3Ik|Oz-_JBo2UQnSwL*m~CZ=XxT*L}mRPWf#)+y(@<J44b
z@fV-X)YYGZx}k185{)ZXXr!d3g8Ez>+}zFm{rsTCjtrrzLM~SFM+sY7TiaB9@%Z=y
zRO6?oryuLoaj&YfvazvY01e+yP~q&Cx4$Nre{GGV-QO?4fsZ+-Po3JjHhQ~~ot>Pf
zre@{8dzzj?Y3Jr>W>^*OD0GaIulup^+w-ZK|Lqh#g}{UAq5@z_P*BuqsrU3_|Nj2I
zxWJM5;^GJuYin!J5--pUg!@9L4n&AO1@+_2_(VnQ`=@@q6X5uv)cNN@$n3*Wq+r|t
znmP<{{0Ip+&=H9lmzHqetA20G!ouP(Nd>fJ9dr)arKR4Ar;V2R%v7rKQB?Dp(ZDIJ
zwjlNNv=?`Gn^%2%!wKpFBuBQia*H3jeqCHx-S5bSh0cLHi&8Htb8gPLX*8Gh#U`EP
zhlg5sRDIO~9a$q~n#I5X+Mohj;FWcCm4snZ%ZkF*Pv5?^ZQs8A+s56ytwBXZ@N&O{
z$Bwa;zP{#qagi&lpGM#I?dG7JQ|IPdKb~8D@1kYduP>RPwf1&)c1_EKPhY(%x;^hM
z6N89m5R0Cko<-dsi(RF!*%&~n^Ud40u6-J34mPucW^nH8uaDpOdrc{$mAT%9^%)lz
zefa(zbnrpe)m5rhGD=E|u1{0>9RC#5#O%<C`~UAR=v-8AE9RrHx?jS{Nvfcksxvl{
zqGmH^&g|&wYMMV^{?v4R{VJL6$+Ks7OPl8{aBAfW``ztuYCh<4D;Jjq!OQ(t1T1WN
zQK)ljbNcy$FE0X3GA=ZTNB-+q_n-IR_4@s8_xII4eD_YTN@n2=i!b?!k2R9-LuZGk
zY%H9YeE-7!PEaQmI)@Z^>{w-Auk(L3aKS6eBCWn2R3<KV>pk@EVffw(*jj+Uze~k7
zY|XnX)h(vG=@zTk_Po1IZi^jVTv*P{v1DdvXD@koM{;lV_qO@-<-rYKjh@Mqg*R>9
z{PD}nV1|aZYjfwFPxPF`bMNBMQq$UBC7@+}?tL<jH#eo0_TAlEEv_52<-mbPX2Y^K
z5st!>RCm?<Gy-*zr%Vy4sI1I1*8>GVpR85OrKR4W9c3%x_U?M%c{cyXhQuFVug4dD
zdg94&;7F&iVfHm0&>=!QckTq8T<GNFwC2<Mu>Adh&4Pl0Hk7;!YMxygnXG<&MIdw5
zR;kJA{%jv=l$#$sNO+s{2Q=ZFeSO{0ySvL>`!d4{3ky3sIvi3`R6zUoe|>%JyfzH9
z)f<%QZRG?7FJ`wwJJwu`Q@vV2H;h?WM7;mFVuc0^JG-*F`tdW9Bd1+n?w|bs-(S$3
zA_p3o1J_2Gf^HLnoc7)hYHA9eJoMwokAy=loEevw_1=37+7AL+KVSR%+ssO%kC!f8
zDtLR#6m)LN$&;LNa&j7BYi7LI*y82y-#&f1IA~e<Lg)4_x#N#qTwNdj{eFM@t-Cu`
zCV+=30_rv(My$behqBV`pPE5^2z7n%*yt&Jv%Z%%ET+hVM~*5t7JjlSe#Ud>&YdrM
zLEfI82cMpvK5_Q!?p2|ypGDeapZ&KlLt9aiG4<4xgY5D(4HG5^9OX@qOaJ@p>*bxV
zw}UR=o|!0hI%uhvDCjt5`T9Q_?>z>cM%cv4Jz>Ixgl8wuyg$+@%=*jD-~W7l<)lNP
zQ|dXmxt)D{c=GP-V0`d%(ak<t>!d?1oMF2izTDcH{p0EM_zPRJ!$owXL?k68LHm)-
z^6qd*OH2Rw{X6;MBG<5;mU9*_Rt9a33|#EiDR=Zy!DFVwe6m(7y>89C(q;;(s;s(E
zTN<L)f*SmRt3os{J{A-d6s_6@UFf=~{@u5?x4{z@Z3gG(**f3fR|^`;j-00GDRgUV
zc6-*<RgTkAL6d~@Yrjbz>y=io3fT;r&iVA$_WhpE=d@=W`6O#mz`)GT7h*GS%9NJ*
z_5W`62zPGJzOLsp+l=>kzr1^1-nwtE&CJX|M-qa{zOuKsIOhb&xVyW@?5(=Gq?><D
z;QF||0gGHXzr47}tf;8?;oCPc+erbS!@#es4Bq;F`kOa7pha6>UtiyTDqc)nM7q8A
zb9s);<qi3ewPO;;j$J%@?C0|}d-EC0&izk%JfjUXM*;0@>zSRiKYlFn@gIG&zD)3t
z$drwRpR#UjP^|m$ko~QiX8rve3qw{0RlMK(oy9+6CTKqW<>lqczrMT#U7!T2bwQVl
ze0+3tMc7)YUteA}A8ck{9J8}%k-KU4)z#tMatD)C)zy`aje|c{q@}4%nmqZe#Y79=
zStgnnp0D4UcPV6LkSb^q9Ycfockd_X^$*;=EBo%<yIaTk`1m6BR+-wjfB3`q!hfEP
zplzEgXil&0=TmWLl{v#8kty%qp3be=*AE>##@5)_IK#Sp-3!CkkDop@O`k3fI@Kq3
zcNu7G>C6m63D7w|x=}5R%xoQU6G6l0k0Hb7O59sZUx($~-4*(~;^wB*j^5t0pZB!$
z%PX0gU0YROXjS?u#Kqk``Q4qJA3lC`+*|c^%W)Z5SwR7T2Hogw5ocX(d!<ZIUDwZ5
z@pLLH`=&kT#3o6r@ag*TZIdTYmRv5F{qD}rA5SLxCnP5~Ut1f!*l(_tM%*3?Q1<=y
zCK9ys3v}}Bot?#oMNd2~KIQ_QdU1DmdGd(~il828JHI?=+vlRii#Jw%%>vC396Wds
zG_W$)s??=Fy$p1A&fe<pTl(c~t61{$^WWUvEpBIL$D}UY-<xb@)~5%`$L70W-Te~K
zn!@`}_@&*&!NbC_IpCEiH!OC6WB*fo@8WKlzQP=tSUx^J4}bsbc4pf)GVh%-b7rS*
z^fm=0C8piw??Ky7Z*9-#x3;zhttp&gS*&(#O=NT4-Cdn>Q&~QJ`QlPhVe#kh-@yHK
zwR4j}4ZlA>KVRHYnCy6YX1I?}&$-9x=jSCpI?@T+&;wf62(P%`@B7WC>OIXRB4S2I
zpe~>IJniaFPdH^{WEKRibm>>R(<5noVRv~xsAegBeNEK1&-LLk)@2*FZgmCii~jvB
z7qm<Vw8;A1ot?^6I!a25oct%n=V-cuMgd&JK=<5&j;Ll}c=__>hRvIs*RFjh7c@y_
zVZ_EH&?<nBXU*?FSiAk6km0HV(5c{8Rtk&hMz#F@{(f=J%}pJ>y;tKT#N_1qHf%7M
z%Y7m)9ke*?;`5Z06wo3T&~hCW&rPdjr|<v&ullW}Rlx($v{&n=r>CD+-aFjRU-;~d
zWXYQwg15Kj8h@XWR{rje<(2jE^6&S4mjjI~hlgLcIq&J=;jlh#Z^5T0o}i6Bpdri#
z&!bl5?_`*mm@aHcbmoyX0&S<OdjBSPS4k%0<;b=-Z*oAhX@Y`+pu4svPMp}dtMoPK
zB1sNDKDVP?qOScJVp>zVK+AgW6*}KPubzGMn4v5v8MsS=hK!DzfK$SGr1Sxq-A0yp
z3`sZ$iP*EV&E37cxIoQM=oCEYQo=oZ_VCoje}8xPtjWUEiK&v+-`}~qxUg)?x!H8(
zN{C6$jey(r`tK_0o}ZKb^6Dx#Cnsk|f4{iR)=JP=Kj>_sK3Qwf9s}^`&!4}4LF;Nk
zOT#|2B!QOT-n(}XwCxMDUJ<k=lcC_{B~{R_OjYk`NB;f&y|!rM3sCp$#*GM2_pGn4
z&+7Q4OP4@rn8e4&pP6Cke4*u;am|kck4Y`8++q$(gFuH0x$SqKq@okG<pj^=$a(kc
z|I30_A2u?xPnbEg)3*8>XrJE6lP5vf!h&wjo2DDxB^TWB_4Reo_#m&83Fy@CoSdAJ
zK5xi|i_4LGc`*yLQ3hZ^2O{ak?gEYY?c2AnGS1z_#bt{99%d`hQmToqQucK=$NJ^@
zAN)M(uN}VbO57ipT|&ab7dIq2AARiFCE^$rHA_-mXm$SmeO<>lZQ8V<<YmyAIhMlZ
z@9sFR4qGcAC6%@Bp^igU)vj}_aVuA@to-Nr@2G3Bb35PBCnqPLwOu3tx|{Ihqobgs
zkEdvbdc7}R6|%BPzW$Hk)z#t0KRrDST6k&fuX*ow{(fGDAFtQ%UvM!)WPZA?_^Fr4
z+1cFn_4Pk~|5n!3<poX3zq-2m<IVK>iFbAsX58In`s>@<?gIxLZrr@tDL0)Z;qi<<
zP*DO|?wl+I9!@c8shw<}BNGem;irNsDNr9_f@02`KZ%cDB!R|XG?Kv;l(vnHjBWL|
zBMpqq3^w)uTiV-|ZERvbR<Fst+`V7gIE@E%8S?jcv7nV)&h31z^X+Q4tY5i*b;L#`
z(2$8;?JtfQSN`PP-^Z)3uMb+(X_|e_<@2+%j11y>F%B6S8laNOxt%ZaESqmVXmuti
zS;g0W6-`P?0&U}9IB(zI&M)7$G5PqSpru|-%SDpU&N7v-udA7N^f?1)9O%pI>-@%P
zXEt=PzL;&63z}fvQ~7y8(8>*&m(>=R+it(c`T}&l%l7T&S|KYM4jgcp+dKQz6wT)9
z@9z>%PErlq$xwTHTQ2A@woRKigN_@LHqU!f*|+if)z>}J;xDQ;u1rcvQQ4Mvw=4bp
zJkS!<)#2-p{eHiHeR;E*l9G~^1guBPQdC^*+MjSyD|A(h_jEl?Is39V601U2ryc9m
z@ed0Vo2C=l6uCL=;kmiiplDK3R$lu`eqKDN#ni?t&Bg%QbX-wkv8&{zQiaw>(C*TP
z28N^DRdE`zyG)pvm_Row&dxMCZB+RwW%a+-u)3p1k3KxoDQr>wO(!MN?d&Ym!vFtj
zzr4K6{`h#mdrFE*)RqjzDj%T^P;2tIh1t1c@Py0d4TYcDd!5@hfY$Iy90zqS7Wecf
zOPTro+faBy0GvJ^->`rTiuxQrcJb<pKxNR>Y52OBgLikAU))ui?K8uGG57X1QQKKZ
zBlp!<g3gJstNpbg_x3iocy~}gVO8krGbVE*KzD*BB`JZH2KC8Wzmn<h>~wT+U^vz*
zy?k@Pm06%f1KK}r+ji8`+uOOQXw##QOO~iCS+;Cep;DocurROPvgybA<@>katKtUL
zub_1%RbR8_J_aohxpjV)zx`hkIXStA{dKmluC3JuEez}B{<JD!A(Nb44TrwI{+YSf
z;*5-p8j+ipyx0g@6YUKjf?l$0*`tSt+Y3rduhzZ&_VzaD7?e$$HeFck&R<bg#Wg2j
z&4L9ApsN8I8ygGC%h^8^9ltDJ_k(fb#EGC?i53ejA|oTg*Ns<y%K;r)bMM~0uu8-J
zNvp%xcgY=00wwmpzrUNm-1+tO_2X^4(s3VMrk$Mi?odzw=x}xy7ZwvK-barg2QKrG
z1WgqA&$p|1KDV5KLEV2ID7%5q5I=JCDCfK%S8whtUjA+R>z6NIPEg^zc<~}=BlEoH
zUXxl3laI})c6kUMP6ZEJ=a+0O^f?S#g$bH%Hb9zlh=t|yJx4$zdCBmxZE@-2COLEV
z<mBcCE_UO+vLcYV_V>5e{rl~u%=2`rbh?Ybzl#;o4m<PY`R?7jv+I}beFxf{adENx
z^T--L22hj9UB0&E>FMd*GtO+fv%8$%)6?_AhYuI3ujgk!e*3n!^7Av$Ued}qYwNN%
zpsT<4?A^=i>ptz(kxpSy<qtZ5_sf?rHpjI?SEX#_{*ixgPiN%jw8D=&<v`Oypt+56
z=lDRI7eVcEPGL2PntdvsJF360o4HI`NvUcte8H1J#fJn?s2}f_XJ-IaV4wrs&(1bq
z7_<^}u@LBRgwog7lGsI4E-mr2sQRJ->b`<{jgwS*WUa+CH8nf>``i2b`9TXHFDB0l
zO-oz$O;4z^vlFyqdROV|2Tz}>R+)59nlJ&h;(4z1cTk&PhH*L{DBY|M*DrZ{EA&Cj
zv(G<1CR<or&;D{pNY(4X$H&LlS14)a96Ed$v==mZxgThh>BXI$#?Q{qX1BMuzj5Qn
z3!CkMi`_s2`rVAoY#g($fyS^wGiKMP>BX-4zVlkeL!$%74BL7^OE)aO_3D}N{SAgL
zYyxFt(84BgDewGWL>k(0e0;;A61?*CMbhI7`wvFFyAdl;`uf_@J(Zs?EcF)OdwhHT
z{l0#?UmPDleoUL^vj=p{Ma|DoUB|UURy3&l&zn)Gbb3?m@3J0gbH3;2<}x$9fi!46
z{QN*e2x|WG*8JF2HCH!ghrqpi_dx!+bNBAYXS4H}7(n*|WnW*n&}*tz#Eyc64>XUS
zIB^1W{OqY|x~u<21qBI(t%+z{vqq=n{XJRGdR>c!7TdP9O@Du9U#)fg?AASg_bQ*u
z-q}|h{Y65oQ(F9qsD#9dyI*=i8CVxy+=5C-Md!8*`Sr28#kS|)KX!4k`^Rs$^Ff!!
zb8vHSzQtYr=IvY19T}h_Zw|NdN`oe&tG~Zn7_~L)$Cu0gh6x86Y{bv*JqOw+e{*v>
zX!Q@MXHimOGRr()uS%!;%SCs2MO|IqjT<*I%zOXq-P^al%l+pcI(d>)+APPRq{L)b
z`Fp*JOX2$J>c^kd&zP>lxpU{v^%Y8|%buJN1Rb$d@#RI}ykbR9AvNDwDj7zFp#6l;
z&dyFgIZ2g+hsUI9V#H#%-niGFk62%y(FQ7~LA?Q!H`1}-n)u04P?yoLuNIVB!TD4M
zRRT1X4%Pvx%RzOwhPS7uV@iq&WW6s_<g`*yGia)IIM*z{IiRzNbaj0{RzyWft&88E
z2O7nEduuCb#(AN0`=N8^{GQ(c?VOR6?7X!#n|qeunz`2Hpy|?#D=P#+$B^jn{}WWb
z#%HFHM)*3JeZSvXua0SW_v~34=yLCii(ET8I}f&Ui*JdSH%j3E-QD%*XgBw~pdQC&
zwugUyeg<uJY<NCjACxP%W?yFj--0mDwz|aZ;YKl#;IUq5!>lVSY>tEGL8`uHZOOSA
zbRgx?+4=VJ@Av<=lQPfCnL1yyt>AIfo@;BP)vH*Pl$2I0p8Wq?UmM(?NGX(&k=ao3
zG3n29`~Qp#pnJ%TjfL6yWEeiwgx_5my!_F<z12+1RlFAltyJ(7k}}CixOCKJl8T~@
z%^jY}k#geV;-Ep1<l}v;AO1{_nXK;b784_5V`KB+`SbQITTDQs=^vJ?pXasI>G!v{
zAFoB{OV++S+AY4Z{C(V$Cr@T18lC?1;2<;TS`Kx;ISo3eC#ZN<Up&?Qf11ikt@CHE
zt`2|r@S$QAk5&p~Jm>NTXmK5Q?AXFTN%sTlz=ik4qoDN;?vm2&pb_t%5FRA<4}(@4
z&a<rs%?fA)E@JVTsx|ew<s_BJr?LA&wM3Palt2?3dym`y`;iP<v-<u0ee=&Lk6hi|
zA2;*cIqa?aYEbi|;O+AZt=!@pQceoZu`Ff_3=9PAX?oy!_Wb3`!hC#uphFHO&Y9Cw
z^z@XXnVFcKogG6%=H+FHH#en*?XF~e8NSp@lt;!w05mkm0GdPr-TewW?i19{sr~&8
zv@Wdd{XN}^pwHH2ZzQ6&=kdnJ$AbpkEG#5GKRfH(DWqyp{VfMnRJ-@fxi+)$y7Xt2
z&6_t5Gz8ZxZT{hybpC;>S542W#Z6LqI6b~j&}5;-zJ2>ZXJ8*}W(T!$rhukJBj?PU
z*JoAwYC+=Rwi`PN7rzKRn|8EIl!J%IrBg`NrQgZL<;$(dvKKl*<GWmqlT^Kx3=IVt
zCQO{z=-keic<**5hs4wt4vbi<{0ndg9!<V>dUagN{D{%^5EBo-SrP$zYQX=$xJ7
z@Av=D`?B*|RUrR|KTN$vPfuma=ilEa3)<toHR~z^!`<EG$Dhxy*UPfme0y^`|F<_c
zlP?wf?qxpu`q^cF`=g+%+Ad~X*io1a+Uf}EvbVRhgGwFHsZ?reZeM0NeOUDL&q;VG
zsa++q5IjH#s;&EK!Nopk{1?<lyJ7zG;IYb1P~Ha>_25+npuE4K@KbXysM@!HuiB{n
z^YJ)n_7Zek$*$7ZU2^U_K71&6`+T*Er-W_QmUHJnh=W$ww)4v?Sy<e-qa4)&I=;X1
z6ANhZ<AsIJTj%R<(#d}RA-A{tJfni19$$R@UsHy^^LIZzJ>5MhXwuH(n<~=J&jWQS
zLCx8s!hd_Kzdv~OYE|u?+}ma*`S)bjMsH_h`11C)cw%B=(=y@JnU|M=cD{j@zyCcW
zYg=W)02*kzy*+>XsiV&ieC`d>3R~0BC92&eck~fxOLpn&YcDP>?FO%lY;S2{IWx~z
zy0f!$hDqk62byQIKRh@H8cwn*eZ{ghsuy(U*tv6lUm`#=O|Y$tS}dT0299=%FHSo<
z3v?zFXkE;|-|w^g<M&huf`*DM7FK{Rr#aFoymfcsdw4D9_V?FU&;jmW-rbG<Fy-0A
z*|W8)TAV;554YmK+1C6J0JTVaB#pNm-@JMA#JO{Ivurj$dVS2qy8PXd35w1i4zkN<
z*yo36iGrp@UAx5=R)2p7no3tvR%Z48_3G>U`}X(mD|-rst&91|wQQqL`nfrdB_$>~
zxw(Q85}?Uu&>?>y-_`woYtG<sv`bV_N~#OAYkyuC52%?wXZnxLr$CiO&D|Mo(3tN_
zd?S5%Lt)&b^IDfT6qbA}O_nk{=M5fFXakonm7VshL9P0u*LyQ>ShU6NtC8HCe*W2`
z&;P^M#aQn7`|UPE1E}r}TIy9<m*zdGCFy9_!@K48kA8S~*tI89@YmPZ?Gq*l%(1Bq
z`hD}wvuAB?y;29SU8~aHUS3dOu;b!|tE<C7gSf_iDLX+U#=UOM9UUBhem<W+L4|YP
zym^a`3mv+7Gjg|~V_29NpPWrc;p1bO{o=Y&BA~HF(|HANZ*2uFxdxql13DaG=gys=
z5ltIg+l8PpC-pNQA0Kz^PuK{WMT_2^*Xp+TAm}p2v$M??yL1YHR-9hR+FG`mTS-aj
zS9!$y`yG(nKXImUI%v%XXs1oX^WA0pf2bz<`SC4Uy!hes=juf+3qeaG7dp3tsyooR
zY#R~}Z#fR?CW2M~Dk&Yx(tD+Nd28-%vCq%XyLSqy7Cbn>2-^6XeSO`n$Mt`|PCvKq
zj0?ZK-Icn3V)}713=^hJTV{K2Uv2g3ozf@w)&BleTP~QrOZp_}K(Vm3Q4e2UUe3@E
zxj8NI^fcWU_x4)PnKK8}DoaUE2hE*;1~<H>>-E07yPJF7tv}%Q{R)K}<{<((bEboN
zJ;|W;THyUfjvET&z{{fz`#@y^co!1u!DEJR&YItM$;w*w!cfO;ecWD9&A`yGeY-iR
zCO6By#WC+x(al@87I{uq%eb_p^F^SJ+v{s<K?i0foS9)**{7<in)vh6(-#*OHaDEq
z0Ual`Xz^lD3s%{^&tY0>MP+5;(JoQYgc^8Vg@(&yHD6HWdu4SvzoDTasKqy3FLuju
z{n%Y8U(0t+Q{n8DGId()*6Y&m)XHM6cj4;J;`EYtcO+lFe0c-1^#n8)02*@C)6)ap
zP0-Zbyf!b<4rR5k!`D|=LFW$t`FcIRpscKI_wL=_BC4vaKu7%j`ue(CI$%TO=Cp;u
z%l&R_$rOHffB*X8Kz;_3tScPc;(8(`vXPr4jnf`HI@%2$2~JOM2i;#ICnv`+@BN`Y
zb$_egp4;fc@Ziy-rXxpO7|xeJ)eB!I^Y6!F{<nAQ^6u_RH5Gpz2U>c~A*QRN!y~F4
zcBD_%8obn2%7nww(Q!raa=xVGWY8W7@FH8#)drxm=)%gO4R~kPgZn_S1}fKkdXr^-
zAG0vy15JH%HGy-m0VrdGMuI~Ga%8kP%=!{RHxL^pu{1R|m)6AzZm9oXcTqWFO4`|3
zpasAg*VoB1WSGmWir;THXYO29|8&bkhYo>k1x*<@Ha1RB;oP`!qeaCBg?)d&ML&7+
zM8U))<jah-sZ*zdu9Z^+jUbo3ZPGcNaetrfp+kp0{CqzD@#22FO}qB%|5-0-oVFl#
zciD?8D}@;nj&umF2wyM9pa9ty4O;qgLa=pr#YZK0YxA?r_G@fYQYBwsUw<5J<WNvR
zAmM5+bHQV#S{Yf{g<-1~hOGvzXK`_LbzFQAbekBcBb9Y+4S2QstE=6)9xg5+4zTXJ
zhlpm7%lo6&etv$p;?<&8cZ=(T4yfunetL>#^OGkj#(pZ-?w9kLwW@gD*j4&kd)Bc{
zQ}yHJK#QRlyZ1kM@PNVE+WPIrJ9lD0y9UCF(>p<nC69Cng2tH*OI`#poY!A*<$M2o
z&<QW4ucn;)xk*endfSnEd#eo-53w*DV3)4}<yX*5_0F9;XPD>9)zsFq`g=}$aAjpM
zsFcpSzK)jxw44q!xSDvlEmJ>=?L+;WyX65Q-~S)~cwKH$!=jD`-kb=7X)89WnHdOj
zf0H_p@#a%#Kyv3^*W`{s!NtdfE-GZbVGVS26&CgOSrfQXU5rH}#AV5w_xyEnn;!Cs
zUHL6@@3rA%$@gV*EB)Et&%5)s&Thljt*)S%>*{Ygfs467OP_leA2}A-UJE9BowGI;
zUP-*4(hm`Zk`U3yXrhz%GPCm?xOYzuGzzIczlKR&U46#PnVRP&s&FzgGB&B1%u#ml
zV>t0==Fjhs=j^fiA1f{@+Ir(g#M{S5j<|rf4%yhq<mKftsT=Eoi~tpOg34|WPV4Vy
znNV45$Y7FtOT>G+-c`MMNnCdS{}hAPU4drwK<fu9J|=<o{v7QVKmPUgb<p((7nP+z
zt9V`9-5<ZXxp~9JjgDKhu5LL#&$gPazP`TZ!$Ec?b&==K&d&bvX7hQ_VBuWzdCW84
z2QRB&{<S&%{DpO~)}R?VF)=ZX_<c4FXYSv;zBao3{r>-Q3l}cb2wKwd!1E~R_>9e4
zw;tV)c-SE4h5@Kp0gWbs&ReSdlma@$Ei*H7k-LhL(y8eckn!O_yNUDW^*wlyFju>#
zs<JZm=cOxCM6|<r`sHjdRsT6}|KH{0BvoFEi4o7w%?;lA=ykWazJRcB@~72@nJ(;X
z+PQS;QqQ+HHl>}FS`)e1?e|i{2|G7^06BM8Y4#MoSSg2Rtp1?wDz~;~8x}lp2z<<C
zT=gXbH1Mjb%G$~$dg#l`%b-0CAh$U@W0h=dY;0OC^7`4NcJpJfwE$;lb8vG9?+M?U
zd;8iFJsSqlm61nV8~ghD7#cREo=&seo^x}PhnJVpjhthUS;)@b$<}XX`{c-!-mtJt
zew>o@c*Ws;C*`EwK@vH0P$iC`OWcg!Q?c>edGLu6eJk%Y+}o7u?J=q4$&(Zjorr+n
z5%S=<+Dn%&^I9w|yjX6$V&&@4)ncI4&f?<jFJ5GT_E6ruDY?{Zs*vrhgKHx<vw@1%
zb+NlatIRJxmN4b!<~GT?qH+4OYqyx|`nbI;J}EMwW!Ipd=e<3Zpjq24aeciimBpYH
z?K0M7JfOY#pbK0R6B!vmw_Z(B^)@Jb69Eb}(2%3e%7=vyo9<M9dm}l|rm{)hf1bm%
z)XD$PG<9^mDE+_&-W$BA2DHlW-Me?7ONH00T?;-I0W^XI%Hd1Br-N=R)QH-$;(_PU
zg7Wg?r>1Hf*8KROb9`Og-Y!w?um%3}?U>YrK}TNSl&k;vh!r%G3#tqle9~EqYv0}3
z*=$+-?7@YF&Y(GzvNtyxpPikptf$8ZI?Uqv{Q5p{i~aN3+j}aFZ*9$HPfvfYa~w2u
z8u9e+$;s-VZkq3>Mf0MzW-Sa`8+GgW(Qa{f7Z(;GA)$n{G`8&Q?8eKT-$4fgDkv~W
zN=kM;H<jXb>yzoM{QQh_)|n3}k!@~^FWS|8O^+4-HsjOLsX24rY%H8|!{XJ({C@|J
z1-AE2wlzCv4@wUApY(vsjsD)x{APVtV1@q<9y=*1t)8AEqiWVyl{2S)L*bRg$0_gk
z=O&*5P3|*jL~K~_$S^PubTGhN>vGUGF?MTf>l-(3YW9IP(BIgWJNx9DKejbL3jX~0
zd>*u4;nmgE?Ee1#U*6mde*P$Q*^?(HCo?p(@k(pSJ%4ib=dvd+E-sd^ud{LMl~Sz|
zS-iROa~hAVmB?cE{xF;P6#<H%&inOsv4@xW&i47lR-zZP;N1RlTl@NdHYt&Ahue5T
zlUI}Det@Gmv&gO$)Gh3AnQf9O1ZrV}Zof1$6H7lg=ip4^^ba2%I_t#kkpRt>F7ce~
z(yw{u&CSgp|NJbzvMyG7bK2P^6;Dt>!Nw=kv8(hoXxck?xu2-*vI0#_O%4u@hRvIe
z-TLKt#l^*CtV&KS*`Kkm<fRbkWUgLmbI^`!&}F@sE?r_^C@U)it&b61{bc`XP)lP=
z#zm*AJLPM?2%ei~`+J)Dsra0n9G`zp^FS>lZZRFub`#L8Zz?J(pi6l`ix<AXy9+ue
zee!Q515Hg%P&xFEoxy*;U8v3X7Z;Uns=xVsSn_B?;iluDSY3Q%UtrSXJ#uDz((dAB
ze&24GTP8nVarjtZ(qoN{g>n4S?Y)b+rPZr*=F9=r93a6dH!Rk-_d5T-y2zFL?S9S3
zX@T4GVokEHc>Lb8?|;X?+)qzVf-da(B4=OzPG*_U%%lUIN20c52)?_!yZ!F&^2JeG
zvu0S8YJtv6104#hp>ZNbd`;G!9fqJC;nVfwwd7v^et)$vI3+uqJ32c0VzR{29Xl-c
ze7{#+)el++R9INZHs?eIs4xe0OjiUh25tAVu(p2v=e&q*)fbM_({!CbKRX+^G07D)
z0}eW>Z%gK70a@AJ6)QA&<n3g>efze^T~$fx)OMA~X{i^T!Dl7}emgZyw;Qx1RYAew
zd0~8fJm{>V@9*v!e@Hn78Vm#_Hc-A?vP6ZUVd+v;tI}63py6zvnMO_OBI>HDtf!~x
zHt*kW4_YrjO*a~JQN7yU*+;ZNTR%Uaw+F3K@tg!2;O^+)c+1BXyv*m|v0mxIudhN6
zPTp6`$}M)JOH}*9_Wby_#Vc2?ys<f*f0kKpmyoJg#(aJ*u0s<PohMA1q?8o$@ZVl(
z&zu~cZTa`}HtnAHXLfftcT7yohT7j{bB|k>zw0?YUH|c?r>EKG`SA3*O@7M6967Bt
zuH?h3pI^R|IQOQTfO0WtGup*oaI>Jlcd<0MXgB`WYX#naxeJ>03rmtgF<x{GoK)nc
z-ObJVgrwbV&G?>%d3kYhiR<-P7C%e4v!ig)aYHVtUbcDj=7C#<4}N}r4qA#0DwVZD
zSEX3SPg0qDXJf?Ti=bK7dGqF3_3KA(<5}$1>r_;<sZrgS@BDoG<J)p?gElXI_)xH9
z>C(({xAzwoHlLfnwEW_}+TRQe@7}%ZI&N86x=(YaX||Y?vvc8>7lAWo&g_&sz9M9O
zob0)C=Wgt+-hS?}oSYnJ`wZwBIA(vfd5ae-gJz8cmEAhzj%Kv9v}D9r2L}f~eDI(l
zZf_OnNL*ei69MoFG3%ubFBriEfkyhrj~`crt(|r6v7VmZEm=#S(3_i51!ZJ<zI-VG
z&1*<XN`i*A&YV5#+OOv0<psK{nybFP9&|+Sx^?S7%Z_K6W~)`1EG~R<LeOWfmFTx`
z-#YsH&ll~9*;xdduxL2Rvp!;DQb%WJpiO#SUZ3Awt5nPH4-dD4YLSI*##+<$Vx2ap
zodu0hx%EmtytOquvP{|2%j?jp(A6ydSrwo)ee>tfzxVjvyLUHsm#=437s|f1C3BJc
z32|@?ryM<YQtr1~XYXP@@Xj|OY4!9s(xo>nA~%9_Kd4qe23m%E1XOst%bNLxfeUj`
zslTCc)2i6rW$VsOSK&-QKd;vNvcz(yRxZ$@BaM(16J7-NoLW8m`oFjB@^u#~*J<8u
z`1gAK{zoS!D&IP8UG@gFr*G4o=@TY2e0_Z#G}6L0=iH8n$jF1IPlN8Q?da_V9ZCX<
zYs2JY32$y}ToJW(mFFFu-}j|Y`hGlCv=!9ye|vlT;<&w45(WtjbLPw`xz}-TW3oHr
z<xbO*7XhHcJ$6^gK~U!3niUE@-W_y=(}oQOIuRQjK1@jhEyZ|!ZEbUZKfk!%kNSJ}
z?rFsAFaWJw&Ck!T`SbDkpL%B(moL-cwflmir>Ac0ELN|nsVR}Wzq43<&fK}YHd6~L
z{{688&BudWdSykRfw6J(<jIp?Y;39e_=pv>)c|z93%{HVXh#g_GT83Qk`pIRG)$d3
z_1@!+8#k(bR;{_as}ywDRjBs8_qVokm%h4Ucp&6h`kftx8#ZnXeB<^h|LyJVpt_vZ
zSAAM@v-39b*PwatZ{NPL&GFEQ+pz{5eSTq}=9sw`hy-mIodSwuP)mNYsI<E*IA6+|
zfle$_HS;@n!{TQ0<CLS|Yzu1s_fDR=cCD_8r;u&i#n;!@%Y()@5)Zd6OgPxI=(ym!
zXJ=<GayN)#=aV_mBWcW#a<5{4=4G{<TU$JzgO2EPb#Q1<JZ>EI?b|mA!z32a3Te=N
zOcoXvr<vH7IZaDlvTWI_+O?HGKdGKMd)D{U*4@$D^KRMq%UA{#`b<(ev5CiX(u8^Q
z@?KnQ`TY6w;lIDXf4p0MKk@mwxn0Rpy=;$<^)|0xzkb2XBaaTTMy`$C&NtVp^whWS
zno3GaRmSjk_JhZdn;#x-UmUx;Ov18gNmA>1*KRRI8ylH!aeXnHr4nIbVHH0=sp{zH
zxb!EPfJP46`Q;b+&9#cyRkHG1(!4ii@*B5qHN8^dwlr>U6$dZx)yj)8QBhK6IX4=P
z^-6QkIP+o8-o2npu0U1&;dcJ()%U*NukTMj-k13G)m64R=PC-!h5mw0tZryv2w4%p
z2wE2Z@K7rwgQuq_=uXtIbulxaa)<mnes;DwsP?&-EFlBRdFW9W*RN^D_gk$xXU>`%
z7OyrGLNeT!WJo>yd_OpcUP%NMy`WZ<sHCK3RZ9)1T?ZO1&APIpvF`7$g`iW`wrn|5
z6nA}HEUQm?#naQ%#ci7|N*Sl|fX;=FoCcap2A!`HS*NGs>GbeW>(>3=0ndD|Z``<X
z!`7{>n>QOT^PQcxsXO-PuV0{jt<&}6uT}2xn`;F+4f)ym`S}k{9^vNa7q@K+oNZmM
zS5sTNvHpJ@=ynl@XRk|NUt0^Z;Na!X!>!z#eto&@|5eW0#|O012Q(%hvO0|S-Me>e
zb9y>DUffkaxk;y6t_fVU7Ma!lDgjN!uUxsZ>-pKUXF*-+$$u{~F@S1|=<RvnO&ac?
z`o!&b`qtH~voEn<_%9|V#>UUj&m(6evA6nr+v?TYpk-Or)zzRDCFt6DJ{gOKXJ==3
z%Y9utIaM<E_BPjw3X5CYa=G>O^{=dn6n5<rIS5*U{qPX$n&|C(iHV6nemw36&DKng
z>D}cqQR&0?@1W`4M~@$aw()gzaO~K*lab-snVHR%pP!{x3*Oxgy0Hj!f(@UnRSOd<
zSH}K7yUX9pUAlDX!K+tYvAfF(zdrmAI$IPpmVb7(`QxXjr!P7#*aTkK2`YsVWwGDA
z8C8!r<b&E^;8HjcOkV8oooo);-c)wO0+P=m<dpFLb-CA$U&)JGJSTR4o$OMtsgHV}
zX@T}@`^+@r;OD=-Pi^+9Q&Y7MU%o7CoPO>~WzDZIFF}|6TwNW`Ya<!>ujIi2#?a?m
zv#!3<^-r<^O#pzdg^S$GR#sMa>$(42t5!Z)D+M#Nu<GQx%gcO0p)!~Iy?~%#;5m5y
z6A~A1|L~yzw79|H8P|N!YT-xDCc!0teiVXkECekwo}lRbW!;s(_p0A>&N%lW?aYjc
zt3O}9bjcw5+M4Yqy&r$STs|K(dv@fA%UkyIn{*auTwD~ft0Z%q_OgB1aeFEnCn~!q
zU0oG=;>3vnnaQb=X=!OM?(er3(~HU2B!9|0|DMdXYu7k<dCwLF`bR}cfjS88?(T1H
zZg&5&;t=Ry^u)x(uB$6<Z_RG!leL<0r!@g|ImD%<-k>duBKmPMpd)ps>%}rKfZFv>
zPEOvKf8TD#?Af4Tv;X&F@q^BziH~0#12ukE90#?FpY-%jHZ}uwdtN~n?rto+0&5YS
zl$3rhk5m}H0=Jn!t>@2QUV`u7>6f=}TX%YiZ)#$Dy>-ox4XZv!ZOQmJP2G@h-@bi2
zt>P!Cu&}V~S(^DGRzO&|`O;EvZ828E&}q}Afi4R^(8ydW7r(PewWhWf)X`w}cRTjv
z;o<hmU)6kkeEAhZr~0kR-}UU+Ve#kJ>-AmFSBI_!U4fkps!Zee+c`NqgN{s+G)_x6
zHAS;&8K|{;9~zZ{Pph-a0}ZB5-Sz$b{r+ofqgPv*tE#es7IyW?THpH=a!glKlk?%j
zhaG)=Zf<UDbLP%{`0gEFc6Ro~#hf3%->+BJ(czh{AAfAJx<BY9K5=pJExEVF{QUeD
z9T)D}J#j)*U|?WDaq;19as4glJtwvN{QMlWI_>fC{`Rd~P1|@Rne6TDr|88-J=l`6
z29(t2+)2Ejaun1S0S!gH@J#>}eMRlPpsLN@jBn-9V++k2L7mQ%;6@7Qh>)Az{r$&3
zJUqNH^|aXB^*h&#RT)gZo_xuF@x=`BzX6A*)aQk*jcN^D9ro~8ue6nT=>!$f{nky(
zjOFey{*?!9D4lOt`{4ci^`C#-*qFSr>}}MMBS$1Ej1Fht-DRrcd1#((bwXO&vQ-mR
zJrC`x{mo-AH)4HUd-3Uz_-@aYPOV&^I~d;F+`RR?tE=n7!~FK3NgmM3zqg-3Qx<o3
zmlu9}6Dhb@NKo);^&ZB#pps8R-m>P0fs?bd=<bPI^6%eE30rV2{pP0BRdy5Pj8Zxn
zmkFLfb&Biu_Wbi7y}Q%T&jTGWX;JfIgJ+$^{5f-aJSVFiyn0ns)~ZCnwl5HL;Up*@
z|Nj2|@X@2Je}8>-zPQNMwO^H|TsaW5Bo)*&0bTnAod>ZheWg;R18PLJuUMh6CVsyh
zXtDa)+2$XAKA->i)KqOyH|fMgWzfCkBHCd-Uskv^BKifs@4&T`SB}hG@Q}b4crJjn
zJUYQjZIRj^JHdU(7uUCDhl3Wt?%THyIxMs9vrTaQ`&}h3Cq4T6XYcoW!Zs5hMn*+B
zO;V|-r~n-q{r2|u_MJO-zS!7v4z#ZV)V$i7b=B$eGT*QNX3sLsp4O;tYzK<OzrVg7
z-j;hCG}Z??@}Tg|p;qo69}e?h+*zEyCU$q&g_gF<TQY+^Cbc-X^DT5}WV&_S^5@g(
z@u0Z;|5w&)TB=U;HXhKuk)Xx=YokmVX3GBfeBK_kOCL1n(#9vNm6g)`@DQuz=1rTN
z5)u^HcqA6o<{j&i1g)x8QdYjWCerxr=Wa3GLq|G=KfbwXj2_{j1_@{pF6g4<O*)5<
z9b;nv9ew3F2{gU4CVv0DCHr`G7eD8F^Y(3GW~OG9$l}Wz5}jjq6fj0_&vTt^mRmAU
zSYE#0Ece!f?f2^r@2UK3Q1vB)**{YT)c0y=VBnFl2>7CLNH=be1jrd1laD8)r!TLq
z`~L1OXd)>nIC!h}%<xqqoPmLXU7vk?gMx&<y}#d|eSO``FL^4U+1kl!zMJ0gJ$?Va
zUw_{Zrw1vIrfLK-+1c53b?ess{TdFMwq5Mre{4_XXBNM78*tO)3uuS{Tt4zis|$l$
zIOlGd@7f4D7Z);i@B~T10!_kwyOL|yf#b*B->=)fEbn-qENB`u@9wUp75kEoc7d)P
z1f3?FX21yAu@2fbr=r5b&M()pb*t&F(${SM{{B05?dp;{p8+~nuJZG<8+$4@zX<G!
z%gWLM%^<e%O2670cs~R*c$;xy0i&FKUC+C_yR-A1_7^;40u9zZI@<mCNT;wy{JuR8
zJWtN}@%wl3&reT5OTfIQ>8!LU`~R;NG&BubpnGFuGOKTfMa&L`^wiVSj=s3KSag17
z?WdFK7DZ1ugoK1d_Ag%_w^vHpt>*#n3l|rcN>%WQcoQ$qwkTYr<2lKu>`lbagU#%>
zo+l?IJt=&A?Bpbslb|yWEfzk^G?A*jyQ_53aRaZ;&d#F4ZM>=6+}xGt=h;T~{r~&@
ze$m%gSD!Mma-CQmzTWIlgWHnG&1swF&!7Lou;-Ba{2Hb0nU~!@#$;u!dh_6cLUd&0
zNk>P=Pp#bIPxANubkhr1&|p*a#KUp&B*T}NmUhRii7>3ZzAm;XC}>j6w>OdCv$T7A
zd;ffT>V5Gs=hBNAPqt=X*P7Se**Q_wbCR>OGplcE4Qgx$#BBh@@ROce(0GA8XzWi$
z)r{{cD>Mb5MD&H(3HkZ@_5c5V2YGPe!iAe=&YT&uGDsD4vh}AvS?edV)@3J(pP!qm
z9lA<o_RN_l6B82`9T$0Yu$leSp;qpvZM@Q;v&U0UO_}K4E2TQ$s?_UC#vxJ7AeVm+
z+vQ#Q6H6vdnv}xM&R%(MPvs(a!>ICicP3VUd!q>oib*P<fDQ`_D_S47_eu2jyiU3E
z8M5|uG5?;;&UfioblF+-^hy5yzhUnS>+9=x#_TL&o72$~`TE*gu)Qx|zTBj9`qSUv
z-$7Bbv-I_~$a8aTDmTR}^%8aN_i%Cfa!y0x7h45*Kk%tY4-bxC-`>tnotnqa&JG&W
z1+9JZxBt83#@xrT>i_@0`Zgu>;v!ejbSY@7N%r-1peat!CJly;zP@AX^J|)B%#g^r
zwS{x8b-9?$+6d5TV!O-U25e6A{qp)cKP%Uack541*NZ*0z_D56ysT9T$Ht8tXIK;}
z{rdKnn_)%ZVzzVhY`bl%za<=OVpVc8<pQ1l_4fAmk3T*p&t30+cDA{=!PJMK1B*U<
z{Mgvu&d#u)?Cq_H4GD~Q?%V+%-n%l`{X@&66PtL9jg5~Mua}FCi0F_wsj;zeQxa&T
z2r_{Ls(sZ!W&E5u8}m!R=NSdI!>VPN1Zd3Y1$1oj*hyKlzPx+)?%mjyD_v7l<I<m0
zl6H1h>#eQXkEh4iIX*npy7hedn;U|lo31V|^93!i*phkK?ZK2J&?a!uRY#vcAO8CK
z`o_GwR-mK96ciXhi%!71x?B=tVq-tv&fniDclbp_WTfM?)T4a6mppm$q@`EdTuE1#
z_xroM%nVaBgO5F_R#yjgZm+Bi_We|<Ze}K?AHVNP^`EDwr-M%7d*JfZJtRb=PsTDS
z$lhF7%?H$%mom+20Uf&X|KDFwDel%MGxO=4ySvLDH}l&G7^n&gUfkWt>hI#>;xdK*
z&i;D&UMbT{)q4ULyWQB3*vzP|l$@TM+xy`I=vc4C(cAMtF)kx3`|#bnz9&yoTH4wU
zojvROWyYbekP{_AH^r@AuYYQq?(C=BPM(trzP*Wb6qfR<sj-<eXO75u(2li9Dhs`*
z>vcW1|MfyS=kBhn6CO+U{`gS=8qtj2mg87eWz}$|n@80%=+Doq8_VzB-CZ8Ix2p7L
z@zvGg?K-DH_okXm{RkRXl(VT=Q2Xc4&ti{BExxnO9`@V+3z(zrDdg5GmHI-kHTiKs
z-p0bBW1tcqQk<vs_fEF`#`~028al*p1sdr0`vx9n02K>GkVf<2V<+Rjzq?!b<3r+>
z%*$-e?EGz$CkIb!O=DOPx3`LEnegj7JBw!+r}sU2_Bk9>gVp{01=?!Fq-Lzg$;s*A
z<8$Qla{tO^!v<CFX$wkUU;FU=`|$?{n-i0hm8(=1U)-7<o^yBCRPMMZ3mh7mG$J>t
zaEa-xs9mpgX=&ZxUmP494#)ds12?Dn9^Lr)`FUjp1qRU2p2^%o<D;$IQQLArd(uF|
zvY^{+=ggV&;qUkRi*s*p>-r3;IJm|2KtoYYYM{3Ae`s4d(C)#D7ab=~c<{(tg*^Xw
zxSjv-#fujY1a}_SSKAc6#6$4S{r&Qws~x_-yPKGp$XHwqI;l+nw2akuULa^Two^zo
zU~QD?#l;-qn^HWFvQA_8a9V%=fm5fr-tYgv@6pdDR_;X!2b<bt&S!wSQM=3DHmzT;
z4_c-4=xBGhoac(39-h6sol{d%IwVf60A&Id6_wMU?f-mmp7z}5<Dt}s-o^aj5&Ab9
z^C2S%Q^4_((hoX`3^a5Poyh?=;Xva;{h%Hxio_<+y`gXCA3l6|vyAyu=`XrEIv-wK
zRNi|Ww0(`6o157$#RfEyHDQ7PsOfm|;>Ci(!h;(U4?lSMveRp-R;S$g1zqC$^Ookv
z?W^eo-D!KMg;OJFiO012+A5w-H8pz_kDGAS{`vwsjO@ayP;F2@UQ{dO!p;Q8x3{*k
z`l#RAS^V6f^i>Gx_%}~aPtbu;ckbK~5EpO%|Mz`8XtVeu)7csZ1_JBWty>YioG)ri
zMx$2fDh7r{ix-2^n}}|dNVk}-kd3OOaDIM%MRm2dSn@A@b93`0%a%!17%3?&D(B9J
zoL_&6{nxj*-I<q{f#&Z)W6)1eO;z+10&V6ic<2NwhmF(D2-q$=*ehcxG+E6zsC1o*
z=Z?C+zoO@zu$W_6?DnzZ+nbv&Zg1BI-S~I3Tiki^#T3iqBH<P64JS@`TvV3m1s%=;
z+L~gR#Ik1XTF?yb9GglZ(6RrGOsD$!_2T#CY!U~pNReOc*4wmy|Na+&J#6Lem)<@D
z4aI>5aCdD4m82^ULv!KDE>II2G=Tf}2B@M%3=bVWcCi=KO$Ckpfm-L_XnwV!aMSjx
zuUQwBC3MZr%~@DjK-b%Wmi9cl(J8DBx<PhJ-rcARC2i&3-^GIB6tqeMbYz>myZe`S
zccnoi`JgjDKelAv-)Ad+BXDKp<}?P-(a<kz{LP=T>if;J>71q;edyddzPZ-rZUqG!
zzRj3BR~B@PW$Ni^AK6NRD*pfdUij{gC1{miVq)U0`fxu#KhSxIYCba<)Ya8DI!_Ax
z_5SxXozoq?y{&84=1#k>+|kjY@f~GW26Qz<!U2XgvAe}4sW>ja$Z+D$RF`R~pjCvc
z!`5E1%jYtY;stGh-IRKI)j#XqWpAsxg(dlW-4=gt4t4m>zHZsCR&h<xDP^GTV7<M(
zpz*W&b-#H*GY%ggAOCoeU0&l{X<1p@?Ag*`Ya$dgqChK$4QhXt{P^*sL++@?lW(={
z>&?H!gNN&WZ7kH#hmG2Ov4S;wL4_bBN?w$107cx3<Hr{6NdQfyE!?xK^0OLfa_h#8
z2$P%}0#{dsGBbeoLaO`EYiVv~?vuCg1D$Owd&S|*nKKEAiH&7%ZymgRS@`U1^Yb5%
zWk*LxGyA&#Ja}rVcIe$T_6Y|Vn0=CCqPAwWw)4wBI?^c&8lskwkr5CSWHdK7XE^ZX
z<z>)9_nBuN`Rp{T{?^C$;6H3FK#tE`tEss>fA`x5g#FnW*wxwTIMXOqKu&I5?OjDB
zrA2!l7wLiOG?$+ZGiORRH8p|y8!c^ZkIv1tW@z~I^fYMrbw%v%Z4Wq)f^M3#v9)#W
zPb}H7s`}lM<;#^VEF=~#T)3n5w^_rP`e->hxeuQ{HO-tk^8qI>=#Vnd%A>UN^Ljxi
zB@{kBCSjcBGmX1SNm&_m$-JCx700X)o&5a#oZH)a#lQZsf5+##z8jS6LGw;kZ)QVg
zl{GdNz9<C`$AE@vV6)JmmgrtSP~!yBMJ@aXp0#$a4BeRII>)-457cfrbm-8A!pCk5
zGuK<z)zyKHOndm?fkK7X;fbk|Cr_Tdv8z;jTi)GOuik$+X7_7*BQtxK+`){w7KKck
z)6cg}ohmwM^5o4j<s~IY{{H^X>Z5k-#l^*;^Q%8SIl0}!^WP!q^Dj#a=7%XMEi!Mn
zh8&F@xNphD3;`LLGu>4$wyLP99lCp0cDdi&rmb5|wL(|1D11&j1KMc;TC%)7U%pFB
zSF0k(NbGo@?BNbUWzdDV2b<XspFHXL{Am2wS677%WF>{;<L}4J)%O%)Vq&^?$z;m>
z4TUdCH|B%V<PtII_D@~C&g;8-ohuI>Q`~yPVoG?9OjT@-%qea&zjL4wHr?oL56;Xq
z_VDp>adT^Xv_r)+Vr$ma1usuToS9*$e7!#X)|SltM4`uGLPC??7J5!fNK9mOcXz+C
zGMN3@vuA9xdU_%^CLJ{>e&z#OP;X}^_wC!aF4+s|=jL=CIN)&P*fFkoR}4&~d_faO
zCsV}tfNoG~YHBKYe2mwo?vKT3-y@S$6irM*E|j!Qz1_;)CvTs($=>|`QSiF#dph?Z
zM}kf12X%p~zr8uQHhMcl%DRBN%Y3D;tP1shlfd+0kzAE<8^3%XX!{i-Bcp^##)NOD
zFI>42vL<Gy(7t{9B&<p_n3$Pa{k@Jox*yN;Dk?W}TI%F~Mic%myqKZjIq6mCRNueP
z+d!)q`1b07TQ%)hk{+)BkN919o%9%#mpybr>lna^N)Oz{QLo;fe;+jLoOgE@tF*K<
zC^D~I69ctc{QcYK&Xw&F(QJ}7&+Cwzsu5pt^_0W4yD9(w?osgso!GR*b8=DX<&?VV
zlO{F2y}dns_k*MS_J0&ItP1UZJ`rBBY?+dgk<n@17oY=~LRX7rU0>I`HhO!P+*O57
zpXRN}E}U6@_gJs=!?$mFJtqaM3{n-*kBfO;dAwiV{6k7o!NaCKpsjQ-FD(`2jt7m|
z-unn&vZAWW>fFY2(BJ+qOXRez@&;)sDGrlVK+83so|+0;l<~lmw_W_}h1mhyaw1FK
z--~^pXS#3SK2U4*-QC^k4^EzlSR1+7?P_K1?{BrICrhxu<6Am^=~7h{&!+Zvb{kt;
z(A_obeynGfR@XLz1*dx_xPg)WM*8jzi!ZxwSWFQIwHN#9z^e#Kk{`oDdDHdH>HeTw
zR1*^uSA?t-f)rwnpnXW7(G1Y_yMltCYQ976>)O}%_uH#@9{Tk3bYfas+rPiRSO2PJ
z<q~O_J69G|7KW{j+WS=VsHAZk59q*y@AvEDzi7C<{eHjR{r|tepqqf@<>f=x#Yi#;
z$jbJrdQW@s^78VC9R-R>Nl6<(+eAK{)(7qSYvYkrs`#}1J!oU*)m5VF;`f6_K0&uR
zAMFx#PD)ZriELZDR(H*sH3iSl$zEJ61-kAJbeht)x3?c(_O}NuND`2c=tw%+b@2Xu
zdC&&EvNsao4T&K}N};Pl949Kd3P?$H8Ks`;kaM@ti<wZqa^*@;(I{n>v!Yy)SxHGL
zsNWn?fIMXeU2L?-wHq}1C8+Fn;O0%qNh+XWyofCsg46V3x#HvFbz*h|d|AO({QFz(
zjoY^mpE~9BMPo{TWJE;5zdt`gXCPMAoSdWz8fJ;xQ<3=KWXC5^G~U0w+<#-~>#&xV
zmIn_GHgDLr&24+$-3KpUa)yV8Uwkad3z`p>sfv9gz34i4A>m}>Z@qbt@&qno)&~<Y
zKY#8V-{Cgi!)qcpgW8TaZr)V1v5BcxF8%-Sub{AS^Mwlmpmh$SS|JT?iw{oK4o}F-
z1J!#O<!jFQRaIF%di?m~qodrQ`JBhc`^^t*Y5TsaKQ<=j!P~dJpsk&vS|I|q(=JLH
zBryE@^;#cv;@fG%$Z4P+73jpNr>CZZwuFGTA1+w}x~0zVz?QbFyUX)I2bM2fxDYhO
zTz0S<biv)jL#?1I`jnKE9=v&@Qx&2Jy|?P&x3{+$7W}Qfa`GgncGwz+*Vopv`g<HZ
zcIlGP{o3zy@0qDxdiwM8^A!;rl|Z+yfyT?eSh%>jyjOvhTl_a}-dtGw`&(7G@%zim
z`41gBBp@!H{@`Q}=zu8Dq3Y7+d7wRjk$Q_Jt8fM{^AR+Wm0Uf`H2cuSi-MqYWh?ji
z&Nc&W@dowEnf=|S*cX&*l!B6I;$b#WOkG(StP#7*r0VM{R)2s0E9>Lqzf?GZdTYlP
z-buPIu-6VeEOYmU`Kt|u8ryGJxUBC7&;Of)#ZT#)@m-vqo|@Wv;D7_@+?~wKOpTBg
z0-%xPb+Nmd7{b;>G#Vx!Q!q3P{IKMhuC6X`GaK)rgU#$)&HMLduZ!K?R{HuH=yb0g
zMNhd@Je?-1`GVp{&bDfSOQ+BxcN5S}I-rf5n__iRPfgM6=<jD|sQG@k9CQTSq{)+c
zEtd(Dm6d_Y=zYIlY0u@30}XI|{P^+4*6isIJdd6{apFLyusY}n9q2N^UTJf;MkZF5
z{xpNoRUv^}e;nWMIjKcEeBGX<oju{rY`hot)mHn=w~PIvG3C64g+;=zFE3;EG<0;l
z&^4S}1-`H9)N#-~T007p_Z|mzn<oD|^ytgW%P+32mHzkdcmCep+dnLlyL9yUadyx!
z#O|`UpnDZSTXPsdm-XpHZQ*$M@L|NBij5C6J(v9Z``dYvicb7K8OZEZeP6x%B$YK$
zTTd}u?gX96`}SRcZPk|t?*gi(=tK$;8o~hg)B@r*<a_XfR$qZ;gG-V@E9}5ExG7kA
z#bIa*pYJKFbo-Tr$4~rr7Crs&{eC?&1DA+K!=}{JN?KZ8)y%(^dQVSCOjIm7QUe<9
z2JLFRe{=SEM$pm*&}y7zzO%u*^X~2{1+5o+`1moiy}kX8-MbH;KFuv_UDmR6>CzX4
zt)Bk=?j<E#?mY(GDH;_u>)XcG*4C4Mq^q~S)?<i>j&`1;VpI9arTPzO+T+H?WY^ww
z5fdq1PzzVhcUFg->kQC9!cNA&-|yESU+O(QU~5(=Xgb&-?SJgvDpAv{E1*O7Tza(b
zfG)B2_xCS(ae-03=0oF)!j?yeSa)8AcJskS;9gbu><MUD<-XeApq06EkAHu6xBJ@K
zXz2>A#}6Mr1}*vqjj^AdW!l`^+xudo#(dBvTZh~ELHF>yxxL-L@XVb%GQrFJuKs@C
z=X3aAGyB4e851T>WHdH5ma(ZYIIdq=^jkHcE-g2=cVF#q&^6dycR@4mNAE8D;^E-|
zx`}h1T`gDSG~ZuMq7A*1g+Z-?-)&bC9)ku)szFO0^NWsw+x!!xz{_Zgz)e%oS`1M2
z7u4K4**Y&T4|HYYGT+&33dQW8BjBa_<?TUpY<0h0s@HtGnclSgjC|Dgyj-LA@4vpf
z>I~YWmw(U3#m!AgMTI4LdmiXS^1vk?f}pJuadC0r<8N0TtgNVb@caFK_pMo1FYK?c
z7tx6jVEFLqsW<4<F7IhNj{S1BTb|FiC}aX18+Xi9LtR}Rbia_pv)^T)*1xD|t6uCb
zh7)@h-U!J%_J93i_x_~+|Nep&QGxuNot+J;H{ZQ`r&exURZy_u(Z_RhtwAeVT3TCE
zD}6b+xto_SSATY9X7UNa-eZ$gy%VytyWM)F7UtdEr4hbP=FFKhBA^>jd!@~}W?d-Q
zQQ-IvbTEN)8xQD!41<af2_Y*29G|CKY|XwdW*`f?w?h5ouW2!=;PKT&Ioqlw6*AJ&
z-Scd#58b>e`TzI*|Df~A89;k(_x=A@4Z46q+C1+{-Hwbb9UUFecEXyEN5vPpFRanh
z)8i8q6uc#R=k#>_{(k#^5@ls&P3p?0=KtGk9a2)V#q&KMYs$Jm@<KvQpi@Jvtfchx
z^gev~(z1NHx>o2al`5O&q{mPAq}$`zf499jn+%$nG}@S7)Zgp8zPZ==%QNt_@5~z(
zJC7e*c>Ulp#j0Y^T3*mGc83o$w{nRd>K4}r?X%3exrsF`E$zdH4+j>xb_Z<92)wwM
zOHfR#?dRv`k0DL+mUZ4IE?>UP>XTLz6dVkagRU#SkYUm_cb~6oO^wa1ZMof-m-`<+
zbciYS^fXomP(13#?E&vd*s#Ii#?6}#k9LcLHZHFYTMOEvUh!#r{*4WZpjFF$^X+&U
zKm{@A?3RQB44|`dzP`E&+Rxr^|4*YL=x}Fer{nv3dqGRq=C0SDqyn07e0_a=``*2K
z8#s?v|Nr~_;>Kk6GqX&+pMUh6td{uw-Cc|7Z)+OWh1Z9y3|b|2b7%Scd5vmDa-eN*
zpu=8zrOjW(?nrohYwL>(3!4{k9=()da?AepFUd)%l9N<6f=+Dv)B)`*Nh(@f@79rT
zJGrUn^Yin`$NOX>=dm|PnP$y+GCh{z!HX9wK6i5~ZGH3R4d|Gmi^&(PA6#1M{o`@J
z{ezb;HLFAx?ywGd<|+;v$oTd3^~c}u_aDA^Q4q9RWcl*tp6hMS9y=*(#<!R68}D9E
z@FI4zKD{@y?|_=436C$#K632jkz<LEUmQAi(iWu5jBl^!vU?VwLy&hCJ>Al;tE01_
z=&9G5n4LinLXLsAYTewd4jN6kx3@a^<)x*dRHJhml)*vk#m>#O?v}f(0lFf7clmoa
z4-XC{Wo1SNRqtsc)>9Nzy{0&Xgov2s-|MOU{Vh}6JM-Qi%R6`PUff$<{<gPXOiWCz
zbo19AA0HP!I>NbR$&v*D3!OmQNkA1A3p@MaGiP{gtG^v-V&!(}&os!)%mnS&sr&!8
z9F(zYe|>R0JIfSQPJr62;(9R$AlDP}@bmM_SeNOXes^uzgI8Bq-_$co$<Oa!9ll<w
zK<P1P1I|TdiM5)+%Rt+EBJ=Fn8@A=%K6Lyz`($;0vzyWvrt8Pgd;EwMH0E7?2QsOB
zg2Q*dovpuom+x$|x4J&be?TpW%FoXpURfEewmZmj<@1*>J0Biye|(tVo@GL1;T_O9
z_(4m(Kugb>mM{L3_wCKi8CIpMJlD-SeRts$ECV2W?_Rrh&EazAVQ}=VJi2e;_TJvZ
z$0}QUCyV}8`+ma$)bG7#X2vJ|Tolw~opUGo@r0-xnX219I}0_czrMcSzH_G~Xf6|U
z3Irb?Uq?p=Xn;TO?ylBjz0!y8-<O|X`)%fnz}5+=lI(mk4jvvHpc|2o9C3+=js{&o
z^x@mLw%N01C$)zv1#$859Rnq7(D6K=bM&gg7mOwxU|?ZqpZz3B(=_{9%g&vaeR8&3
z+S=MjH!fMCQuF1ayN9pu(WBkstiB${PF%VqRQ&v0>-_oi&pqZA*E`a}DLi4$oSX+I
zL06H96tIK08z?E8)cz{DsQg6Rf4-gTL?u^HiTCB*U1>i*zsRtYQ&l(@yY&j0C`wM|
zl{PzY_^@+z;`zny{Q(=3TwB`P51&2j`=P|;CwF=KCI4xuD(dRVudl7Wv8#0Ts{P4a
z;>{Zii`qe(f$}@<>43&e=B&A4zVkSE$iO9E3_PC~mIDjOMdsPh&di*k!Z}&Zx5;hs
z!80?Bi~m?pQb{~DMU!pDxgDU5nV`{?GiS~OEO2=C^fCB?S1wVl1ILfE->>=Hd-85W
z-KQs>pyuoI`Sor-K0I6^8Vu#-<rUS{i<6J{ZP>6uz*gz0FzCGEEn7@(wsL{;#j#%L
z^y<%+3^o6LJ_j||&2n$0Ofp|^eug3Q-m0%oUte7XEnNUj)-yD`c#*-v%KGr#-QA$A
z-w!m8R{#8@3fjui)6=7KTt-HQ#Ybh@=FP^S0j-P+3Uj%|Sy)+TK51%ladAnJfVMC?
zKJ7J3K9=!+PsPWixz9f=k~`I>b9#}x!l~(}rfM(0E1UJ{$;qy}3qjS<=l6SF?{?ms
zbZWQl#o32J1^+(9Q`Vr6l&KQFVe!T4hJ{NdxYOjE&jhMFq}w&#FY}+z=Q+us?oS11
zAIw!Htz}iryQWSR<r353U;u4sTIkeT@c&=!+mDk}y+H?}FFIzt19bb_-(O!r<0vVS
z$J*uVIy8fqEeKy9r*`?^u8@^MtWv#fpc7;onOFmsdWpV$&-=>*+&q@ZaC-dd_xt_H
zpjLQK&yj9%{SEd1>vrtisi>#N2byo1KVKevvV~7Gs0;-)973OO%e^gT|L@0R&`5Xb
z>ubEb%ibRP@$vCyomoMf(|mPecZs~cwN=<;ZUyMvqdz}Ce|$c_{#EXi@>)lW*c}Cq
z=Rl`+*8VO79VO7&*%>LOKS71l{?CWz1ur`~IzE}h`bqsVwpAv#`A_<M^bTTB`>LuT
zIMMLoyMSLG4?VpDUV^2lB-9KVL~ytL20AZUNy!j=5Z)E=q@$ve(Bu8@-FKCFE%mv&
zD)jJD@9A6mUtd|-JiqQ2=e>LPJiNV~Jv=y0P1RN}a60_!)#~-2J)AR*(+{0K%?<8G
zP6`B_Vxi)B>0ZgdSB9ygqN1$f;o(!XLb*Vt>MYajEyv%yc_Sb#-JN=R+RQV&FA56_
z3yO+@O4lu3to-QFqkErRj;+qUy)EPRHeFDW3|bV)5U{VN(!$D$Yo5;<Q0c(T&gXJ^
zn(oE5(dMAzzz(<bgUTV$JyqLsB6%c@T)xb3DtOrR=I+j7_O(%4K{J7gxw*Zdg+CD+
zlRSKUT69it*t+%XreYgGLBW;Br6ETbd}?&>mjm@NK__UWM7F7T-U_vg|9f+a{u@ou
zN$Y|g9X>+(=dR|TnPCVz$Le1F|JsX-B}~EH3m2Cp*c|?3V>3R%i4x%T{+7v)pY-%P
zySN-%=RI8yG_n9XLei;~3v{6(XuoGpPL6`7(4<L|e6rjhfd<b@K?nS`UF78BJNM1-
zZ}OoQPS8o>ixw@KFl9>1f&~gkKZdQ1(#-R!ziwOqPo|YiG^jLhp;POGIdlF@Q#Y#X
z>+4gizx;E*Zo~!#(6I>>6&8;kJpv6Ymb|+onU|M0!=g~>)%ErLQ>KVqOy)Y=%Kb&!
zJWuA)qemZJuiw8Y>*}h4f`S9j&d$EL#8Vh_EYs=f`tB|+E#R}dKk34f8Gnzgwb=7>
zb3v&AG@t7=RV(rSzFJTR9&`%j<Kz9xIyydIW*kygRekv3;o&a+$mlH@jfYyfx##ut
zoPBwDc_L`XSjDd|nkt@$*6;t<)zZQ;_j&o-TURGMo;Y!)ef_>y#r<-&zr@rH?e-Kz
z?gw4Jcd&`Ips=uU`*w5C%Aa?07BGX>XY;K*xNqT|q{lD7r2=Rur7A}zsJYj9CwSf4
zVtMe?>em|<OW35_i@JM1SIx7p?}MI*`u5gV<D0I|pz~rtC6s)1MTLTqkq~Id`^=e=
zpoIkC;o*(KQekE0^W*o`NP=#Y{QLX+!$*&rKr4kaE-qr5)Ay-)vbulLxjB{_wrn}_
z`T6<HGWyZmbmVL*6cUUI<M!38{QUoD{mf6kM;Jg|OVGiZptD4il9NG8>`bz+@e~#o
zf_CNF{eEK%x@qjo47T#Ow@g8st{4*X^7s@!r*koQP0?sP*vt;Pop0a1eTULa*kX1l
ztOo7*e_#LqFsS%)@0Vj_NQrD)x>OZ(gp+pox`ZbuCPKRZogE#Y)IICA%IJcQ-V>Bu
z3pzdcvcLV&KR-VU%FFXtS68>Rw=WJ|9mZg!Zv`5-xVAoCzaprRiJ2L+)eqF#`Tx)K
z_^n$~o72x9`|$8EtDpNZm&F&KysGh>G-2Mnf76yN{L^4>{Hw5B<1aCz8Q>9158i#@
zfpH(6yV-+Ec+ld9D~XRMNY$)gwCBNjQ1SE^v=$#U*Q03qBhIz*;C$(?pp!F&)%_kE
zYUO4y%8ywczklDi!i`Bs3qCw>d{^TOS}qPcy)yZD-$BrQk$*tj8yCCtzxC~B0FCgv
zxVmbdGgbv%0=Oylbis=YiZ(Sr1VDYcW;R~X@EWKQc=#|g=)?-!Wd}vI!+4C-&$Y~-
zKY!aqWhJEt&z`X{fEKASF*Ad%&#DMId?CYRf{N$Wott!Kzp1|Z^z`(LYa)%8EL*n7
zv6&4t_;~2>;jQ-OpfjOBo0~z01kJnh!E2gM=gG<Hpj)pP8V<E`gQnD(+4)!)Ks7;p
z&BxYNu6*}gV|F;$Yinz>u(2f_Xkhg4^=)l!Wd&8?pk5`zH2rwcfqhEgAte_Vm!HDr
zuxVH!A)$c9ZoCW*6O~*UQtA$V_IiD7Eoif^;%3Qa(D||F&-44vGHG1DUVl~idOilw
z>O4US2@ZREd(a-++FxG;Z8RmDo!j|3<r+WDoNb;Dny>-ItycKD9?&s0x3*+j6hGs+
zwl=zbe*Hg5J3G4%pFcP6-fg{S&z=h#lieetqPpb5CBTK_60zTHpCGHX?Lm7eKwIHJ
z4arm7plAmzI)#>#SsNj9fS`pq_wL=hbzD(V5p>=)$d>Q->*eq6Dm~mIX$;zs)fha<
z@CIZviKzM1<x7_)J~+^5U~GK&)z#IY6Iff?+LA6U@dRB0Dy9>mP>^H@+9oHa8};DY
z+Gx;_I4F@W_n*(i06hsr+B`4e;i1+hb<;h^dZm+3Pt*PI`Sa<bH$Oi=2i<A`x>Vjr
z?HKs__zC);)4D(>REC6zoH=vm!Gi}2EI_AFfHrnqC`r1yB9Qs{`T5uF@@{NU1jW+1
zxz@_c%FNo~>s+3mn#$^@ajsrmZ%55fqoCkmM$pzoP=PSdrZQ;~w>U$?<jKPC?(OAf
zFfccFhm0aD-OKp*)KqOybIwvpP%v=cG4QlbN5?0|^z`&E@9)b`R`X?I09CVgc6KwY
zO0^h3tCK;a?vEZncJ0&jnQK)FI*^x{o$tVzGd_hnwzjgM>cPp0>EDmX{Eosxf_rE0
zunu{5VpGqF6CN!sEeWr$t*!X;!w@w4a&E5m;nSzN-@SXc$lb&O9Hrp;t_ZY7Y2QiE
zJ?I`hW`2;Rtd_}-1q3D8wY9Z%;`T`V{r#Pt0aW#X?o>QES)DOO@6_kF+wVX6_xHEb
zag!N+vewT)MaYKa<9*vrdJ79nN{%dWYzEyb@wWKk!-t@uDbNzotKspP^S^)kbm-;f
z<%LgAi3%>}diwNfYwhoE4=*fq1`XWG$jFH7uIZOH=L1cYR(xFaz?1j=kB^T*J6`YH
zz5DRxOHO}(e^8a?+AVezbaCNq^ZZ9QHYTg>RyKSYwkE>RXP%8@^6@^<V8ENVZ$<wv
z1NFE97rSYS{V@{N4qJ0zlBzf8el@37E>N8YI$aXHwKOd)4Ri_yXd!S#(BaoNHY%T+
zZ@)fb$AkO!=Aa8@!5d|3xft4brQ3p+`#t>f@-l<b|N0-le<vSkU<8e=zq-2m;oG;p
zkoz7$IeD@h^lrE*n?bvkZERwG?+9NX2U@lB=H_P5+3p~ZtXsE^NnPaisj1p8E-rST
z#$DBLhJSwbmluhf<TnTj?)6<?*8c1Bd3(?er9Cp1LZErJ{(gSYaVwz1#UCH*_3-l(
zvt1Q9L4|YOx^)p7lUU_!DjMG2-VQpN!l|IZ;MVqh{VE$p@L;KcVCO+lN3l=nw_19R
z47lM4S&IyA;iSlbmK}kvOP;wq(%sEXORR6>wry@nNsCr|<jMQ~?ruj%$AMOE@q&MU
zDntLz?E3Me!ot#0bDnj<0|ph(OYdg<It7|xur7ZmQDn0iv`^y4&!3=i!U-yxr$2g4
z)q1#o|34vvnH8WT%--GIUHI~nYDHBQ69Z_k^}oNrl`SnLcbC6^cJ}%IPahsSzwJG;
z43x-Qxy7$l+vw@>fhJk!oTvb;1ls@qpEZ}L77Ihh#YL>==Gk_G_J_~T-v`=|?DOea
zF@r_T4}+STnt)9yo^#iOE=s)qjv=oLwAXQC@^K|qRaORr%u6a2RaKxnT&2zPT+Yw4
zjkV!0gslYt?Gip13|gTc&+5YO0G{@@l(wxhIdu5UEyK<&R@UtaF0_^7nZXC{-v
z=R@-k9B?=o+!eeg!tl<nQt$U4qqpaQ&M$0}?)WtI_V#?xX{<X6AG68X*YQM76Fu&m
zIko)K+3VNM!=HOkYH4U_0PO-<6~12X)z#JQm7kw!mbKs7TfN=$J>SyPr>E<0tp1({
zTHs`4B*Xyn)kbH|L&r|afo8R9owLAO%2ymecJc@~FN0>fk;Fh-7{RmOAhFfq>*d1M
zL@<VjhrhYAQyA2PZs(KTa(sRK{=A^~PeDt0@9r*7Oiu@IFn@PfdMW6vfoXxD6=k5s
zaTV{T$JaGZohk}yJRkkc$}Q${u!)t|a^6J`Kfku-=H`2km+kQWydSg@7_@>jfB)Y$
z#K8r;(q=7ghijSQL8ED)l2J}>-QA5hL$0ok76;vM+u!d$E&1ikmp3*fGE13esU#RZ
ze)8xMleoC}#bl1-t=yZ!7do+mMnr$#xO7R#(b18Ei%ZB%7_{QhWzzrOovPr*(Nk$o
zPEOEn#I0Mmz6flQGDu(m)jtasD1eTrD$IF&toOzB_40f6>;a8hISNnO7`4C77PRnb
z%NCOxH*PG5*q9UvI?Ka6?~Z_htR#1@8?)!6O)+1V_N#b$`1{wN4t~nNa^*@6ZtlaE
zmU@G>%4C>GO^&@9Gc6S~Wvi&D2wK%CBrFW-wdlp}I&k~8bY5QG9*&3cH!Nm?CVk&X
z2X*&OE(eW`7hXxe|EC$gE}`=Hv7hXqjl`h6HQ?d#?%u`sUS3`fn$2rzVL7o0v}XJ9
z^ZE7H<kp9+m69^aXn61-p)pwM+QY-`f<i(~p#4=RC#!?<2B<3ETU|c6j{p6=z1E;B
zMnD6kw{A&+`o*B@eO3mm=iJ*9S@>>-VX}ajSX;NaKG&?UIlsQXUR?F{)sL6U=L<j@
zmo6?Y8Tm?i_x4yaJUB5?S?RcnvN&{WPF<N#Xhw#HRoNR3d3kxzKn!UA1n3ya2M-!<
zZcbM=G7@_D@L|TyO-o+{_MV%l>~2v0E(W|eNrUbBnn+{N{v+%1cV|9D&6zi^uj=co
zg(WX9-Pm2e{zYJ~Q&5nQj;`*{o4kU87o`tDdwLr8yL)@VXQw|sB?_uELsx|`GJp<1
zIoQk&T7UQOa69NG(25`<Gf}M&hl`6`H&%X53t1Z#`o$t;iH@$WqNfn(z`~a=JHNfX
zJ^Rb4gIRy8%U4{u5U^y)ANlHXIkD26-}(RiO$~Is!y02CXkhB{wu75PEm?2IaRHND
zfwexKr#5_PG;#dc@!B#hN-vX9_NdRnT5gdbhcBL$G4cY9PYPYd0v!cX>gs<KTM6Gb
zcyOorb6xE8>zVt$m#=$WyJJe_;WN+od4mRxLHAgdn5+feSD~b={PDE@{s-^w?lv$o
zI<z8iu|eu75m000>?~7Z*@-0*)_j>wf7`Ac?OQBaHYfc?;R?GOg&x9hESBh%$(-Hr
z*yeDb^VfrY&a)DZE0%72eC6!k>hGYA=e4!bk9*DU1;p*I|8J+Hr1asKbpC?){dG*j
zU4da?ZO-j{ibh64pfNsISJpds?<!6|{qg($|FXWb%|vAbSA*`KVPs|lEj-<@ef#m7
zo6`ehVtRs?`z@^h|4-}tty{O8)Fvl>es;F$QkSrxU?acX4~ErYYn!G|7thJb5s;SV
zmX?+VjdCrYUw7!-T<eD~Uus&dG5}4ZrKPEHadEA>qv4`Ao!et+bOqC{RUbYSfF`^7
z<?ULW7B;AOGB6k$8-s3L`0(+g;GBTppo3F;dU!x9Y0sTIXJBL$wC?Tg?fjsb>7pW|
zGiT0#?qh27Jo?}m>sHW7p8){^pc90Hf|}y%|B4#T<k`7%=ZCLfTleqZUvybSNl9sy
zG#_MD!OI2n>wbAIe(pQhYHQ<U6FF5?RZ!D_Pu{NQ_4W1447<wSc7gUgKRYw?Pl80~
z$unnoK>h@6KG0Zl7_{i|#fuEkCB~qJ%f&^kd-m*6n11@<vuA2n^ZXvZ45$Z<l74%8
zd*aNQoUKlb>FMbe)z!(DmUx1WiF#3SXv5<xvetZ8MSt_I?3Q(}ePdCdbbMvcUpM17
z79rt~SpK^4@t;oF<woH64v5|Oc*3q5g)0`?R(;{Pc=00WnsUGScD+Zt#g#QQJW6!d
zdV6^}Wn^d=85@IE37?s5&Y!>U=dx3_A3uHsHLm}CU0<L0<iy0LNnN5sLQVC59?MTq
z;q;$x*E(^cAZU`ya}sDfy8iw@K_xDVn>K9%twmK)RSmVQ;B)wCdb!+&aqlM3a=Q}~
zm3NfAmD1AEO32RUE-x?Nl6BRq#AI#Nj}MAAwzi<NIG%1jH`n^{g@w)rhK7y({rsS5
zm*V2$GxKbv>+0$<E-&jnaO6?J<EB@t>gtEjp5>LbDglj0D=8_3nC$`0jIUX<MnF<h
z(?U~FF!1paM#y-uY{=F2UGx55`mkQ~-_KHpn#)Zq`asK|7@64;j&_MIS{$HU`2Ah%
zpFf|^gKmee|Np%nG`0$wG<Z^EDI+WEdR(||xpQb*LPEnl+v-ENZ%g01cW=YCZDO*X
z>Kh&l?5%iXzJ#-E&Z>=%Lyq+YOaA7aShnHu1hpH5t3X_9ztlGtF1H|=ZYAjEzm3Ju
z{f-<xs;I8c?mbPXvALO<i<`Uf%?(4)*86GGrY%b53XY2EVrJ(9ja9Vs$u>1MGMeSx
zS#iBNJ7hQLek51dl{}}bDk~ROe}A`VF{g3T5e^kq)x?*VmKKzjt}WBJcI{f&>60b?
zk&%+1HIj|Y?62N__)zTW=?OZx@7C7r@TXOEb#_6)!4KcOS@Sd{3AC#?zV@r=y}IAI
zpaZD1wYj6W<uvZyYYXnFMC>R~1l@E6x|_8i>f??=$E$bl+?g<cen04JB2m$UhYmTV
z9`2qnLBPeuMZwrOxFASLY0<GxX3*9i7Z<A+KUZ>`zq`L){_-+k=hb0r4XVH8e0gz^
znPI}LSzVy3t{)z52VFrl->%l>h-%gry|_Ib<>loyf4^RzVUXDL!s5ya(3BhWX4<MM
zD^RDap@HGz#w}gTokR6iRaw{X|5r6N8+81~&SLev`}=z5*;YT=`~9Bt>1n!K=LGPS
z$t)7@|J(MeTee+xx!N0xsT=PLWU^cHT@|<Hv-b17QK*%CT=5cLnanEvvN@+fCy`uS
z?Ed)7Ok)FMW9PuYiJw@`Ecc%eI@b`?{hFp5t!A|<EHorUK~0VA_V)ba^K7dFVq$vC
z@7D+y?UVr>9sl{+Sy%TfnyIO&pee*(-`=kN?pzyU8yp-A>hE7%<hp3_iz$yDfsgBA
zWMrHHy6eTl>iC5V0{{Pg->*3R^y--V8<W|e6z#m1^DZ?xx%uDU-^tI<%{`Sp+dRK*
z{d#@SNXd*D5_^A0?lHTwV?o;4+2+SLrJjE9{(b+RJvK9D&tA>5Aphnj*7<e6G`qUH
zS=CjQl(OdZxUegLriT}u+Ew;;)u)P&kB%Ccn;&1l|KF;jNuX7=d-m)xD0<>i^Yv;t
z2RHZSvJk~PckU!4Bs45`?>}_ngvZa*hh}+9YDqrcm#HXgs>a91$HB`Bx{=}Hp335g
z$jE~iE(AQ4^PB|g2{>|kP6x$%Yin!8j}M9>T&zAmJ}&N;b}jXuz9{|tJWvnTzx`MD
zks~fXvrITWJv}q-@7w$7*T28NL8BR<)e@DtZ*Oh&@be4X`9Ae%U$AkROcuu*^N{#A
z7H=#}6G5flva&Z8R|IYpuGn{@@J3<Qp}t^AYrnTQ3Rfs@cpOl>@o~tvqvG)oK0Q5c
zQT0V5uKsUnL_~zfbsk<`(EfQDs}hfVwhNOdO%jll?3`;|uB5Ne-^|W`Y*Xs#59h4k
z@A*=@%<j|Y&kvtHTXtuU!~GpQb{x2RRTQ)~5VUFg-;r0Zw&dOpdvE@ERoBXun(>pf
z0&d@&xOC~#slOhaegisH?NPUW$U4x1cm{*?b25DM|JScux6U*#MnG72ak#YjpQ#fA
z&n6dc&%665&DzDq<?8`RxwXhG;ru*X4qo2Sp8@BK+1S`VeED+ZP%Ag9im>y-fCY;d
zIsM$RXwjlm>(9o|cm5I%n!J5;b2Dgc>c*{GMc<27UA?+G9CRr4+uPffZEa;i<MV4G
zH!Dm(4cZi9HSgM7+v;h{okNrF@2lOgb!+I)4}O)EmUe$WI7>)Lfo|{Y>+1szZ|(c@
z$s4qedG-2zLNg+G%49;pp`8zERjj&ExaxRcu=Tgury#)%D)mA(J`U-ZU0w#tV~+!z
z6OJqTZg_kp=lnd|8Mf7CpffP`?Ahb>di}m%TA-mbc^?6Baq$^5W`NGi1RWzdb+$li
zdb+Z;_3l&8|GdqwzntWBcj@`{w{PCO8L_hnw185@^To~0>M=1fQ|fojylT8}-#$=-
z`p=&~U$PP+WarJB*U{J42Cj3hK%1Dg?iXLae0k!ODIqWS{r>(w`SY{06;G#zZ;|w0
zv1yahjF~f6##H~iap_W!i^|+1z1&%56(15@TwM>|zrX)dRAHgvp~Hs_OI`#pf~Fbc
z_+%hsa9J!OT&zLC!K-8U7d`EY+xt^gUOxVDvQnvT^fsPz=gwIaJYcZD;(Qgfgne87
z{l2%iw=1ivvWA6)fz}Z`DYE?a^|iXyyZ{^7RaKxXA$lZ@L)L+=qPVxW8nnL*wA6(G
z)R_AD`FY`s3yOPxKQKDb_c<II__1#+t|lK}DF;gE`C7@x7q%VfbAFWs7WsOkFzYxd
z6Y!a`l*t5%Tlf9q;^w}%HhO#3_0y+L1;oXzJL>Ytw(gHaU|?WJU*EcqcCAi~o|C?O
z`*LOfs@&w6(<95u%s_X+wY0E+&d1W!1WiRTgI0`qOlt9)Yn6Cng5s&hFZ*hLzj}Io
zb@}^ypv_VLzHQ&1`0LBd7nhcLPi0>4_*k#-1V0^ldHEl|ekJ|*@DMbrx@PU#)i#2A
zK}Wh>%Dm5S{|9un+S6rx-qUmrPEz&Oy1P6;160)TN}F+bXr7y_?jH~nv!*5{B!uO`
z&491<arNh}TnWj(>GJ3p>#OKJ6^3oR(rty0k7@dM?k{;Mv}yBZ(5+ISlNKBu9h*R1
zbkjI^gxT2GY)CxJ77-l{8vh9Tr?hp)4hd<qoCC{zXFquRR@Xu`@NsZN1V?^;e%*@p
ztS_gu*Dr|NoCaF04>}ihp>w;|eTVbs&#(VvnR|QN)ijsH3agN>pFVv8?Ma@ReY{V$
zS;bSrzHZN{uZqrXSAH#=KV8(CFYs{ke#KHqo~U|bu{C+WVwK^ILJ#B^EbNHmfyPu$
zZf@bbJ3F(k*Z=(*zUSMm>?j|Vu!x8mFF1Oq?aN*FIsCl&E>H?$cyMvCyN8#TQ&N(W
zkg#y!hX;<J9y`N@O{v}@A|f3<+AY(kPye+4`I(uEH>r6}ipziX;MFUx2RGe9Lvybz
z$&a7SDXg|2{rtQD4Uq|_pMs9`c=+hiqN08k&y0I}EJ4L&$*U`#0YQeKE9YKbULL;7
zuI$YXuj?wFmuB~->?myfHD}Ho(D}WfMJ<*M|Ni{mv~{Z~pNz!;-`O1<9j_Xpm4EL6
z^ZPZ;Yu4z1nwFqre~<UcGBRw>zwZ_qDcQy&*|dKDzo-JQ!cCh&r$4X#bo%G#=jR{C
z|NkZK<?a3P-R}2?4j*<-aJm!<x+7jMZjXi)+e?d9r^e&`^2%0LQE&ODzd9|w6qJpo
zO`Eo(_<7%{t&`RL4_&z;Qv3T`=+1jfJcUg%FS*SASi)xQcNW|mGGC%sHs=*2O3L1t
zZ%qalQJ{7*s5G-Jn{#X9<12l#?Is7oc`EQeX!-@T?o--~=Wshe`-hx}wOh7`fD-LQ
zWp~hKIBvg{w&$(ouJ-QSX}M|BrV9(5*)Il`w9T9;2^zkdsO<je+uPe6-Q9=F@7K12
z#t08KvoCtgDJU$gY}It`*T3KIr%ErquzCLGw{PDv+F0McefBJ`nVDHr@XNLX2OKU6
zmWY|_t(YyS?51FAD+}6uUR7lUX-RiCGP55#aKNF&MoDRrTQ4lo9ae{}1>Ikr`2OBr
z&~O)MH8uliAv0(ytnl%%mrwH!ov;1%ayjU-vZUl>MuzhD_gZJqmIlrJi|IxsTwfOp
z8h*F2wPjUTjoqAhm~F@I-N{#1h0d_6wYs%6Tir_N<pS4kvCh5)n?czCbcLLtVB^ir
z>5E;v#Xw`<=jK>8Z@*tB?dG;>|0Hi;-`1&9r!H8MwDIwk9#GKMp%hnj!PaFmmsqU%
zR(8uSuYweAvY^5Z-h2J}^Y?Gi;cTEP0(5x}Lqm+7dt98{sne$)zJ4A3RCD#O6>HY;
zEccu1bbnth_`37Ll4EagZ=X1MGBfD%*W6nnB{FjhUS3jFQBl$Gx8Gm)*J_qoZrAnr
zdfDRV=Z;QLbartUdGu3FJmhA(e4U0>)45046IMMvJ-xec!R8%>j(0sLvADatTUc3j
z^??q>51J^#)#_Bj0cuStUGmAy)C4V5&b__u;faaL8k(AdvYs8Fv()e3kKd{N>ebcN
zpi|Jir|T_@-kt}F3ecJHOO~h{^z^*GCF3HKsHo_vdTY=^%!LaVp0b^!vT(zO02dpj
zxuE^9GmX=e4mPo#$_6z&TDipo0s<C%V!W#xy)EJ0ot;&m-@klxv>SBdSJd`A-s<Y=
zIkweeM~@x_w>-bUUthF-?ONRwBT2LTdpa6x-z6TeY=gu>NIf{LFUtHrJ0F}kEL^@G
z?+dmqlQ|3SM}qUfmq#ipDxeghrJk_w^Eqn?tCAHjGOR#n`+?@Tlai7YCZBXUE|~ZJ
z-d@nP0aaC23>y3OcJACMVVJ}srW?h=&(D8QbL->n_v=6#0fdBvCd`@B13H1@(j}pD
z=gyt7|NHy9`(!m=7kAaHDVHu^1})(`bH+zRMC8Hx$2OBx9=^D^xarc%X>;btY{|X7
z?b5RXm(ZP6U$eIUU)PX6TS!n)F!1iiPVn%asS#Hz6KEsQw%pqrs=w!f&Xs%i>{-=c
z?oEIG)PS0P^70l144~2^CpVXoVcxuXTJo!utInN1%{@t_v(M2g@7|tD&^o~T`)Xa?
zFIs|%7Ct^ci@HA+PR`B~XU^<A*vy`MZ%^e^yDc*E^8CTU!9H^=0t15X9t2mq&;giW
zTW}e3h4;7bRY=Gpl{$Ig&LMmlW-jC)LYLzgDs2wGnfdqkchJc?etv!vPCo^$pDtQk
z`}-T{ZkR)d4t+^uxO?_2@3CXYW>^#|fzEPLS6836iyJf<JVAvM)LmS-P|>YVCh~Rh
zm&yq{wrmjr?FZUf{5&8cqNA&eYig<Iqz##u)f`_Q>Fnt_vL*8}sK$MFcQ@$9mqp4i
zb@HYx>XH@@(bv}I4qoo(8Wa??^{(3_mA(J>vI+`LTxJ2;YIMZ|l*Vpv%RPMF{(p~k
z`8$V6Dxevb`8A(7+4$wwT$lF)^((%<zRt+-{r!FSq9UWPH4zJA^!4@KD=T-ds919N
z(BZ?b?hD)!&dxFgt$e?*Io%(0u<ZMNzxCFvUF&-M5+`UgO9LbGg}v3~PhSR1Qc3*x
z=jYUSclTCrzqeQO#hW)h&FuWwD$Z|6JY4Yck*luiC0}rIR`lI)A6A?jgNpO}kTM5c
zoP!!oXCX}_V|bb4Ui<FdyAK~f9{lm~abi-El2zZi%ipiRe-65BY@u_zlAa!4Wo4xn
z^9zOtPo69ZZ{Ebm#|J9pKux=DaedJ0T0K3zg0eEuRuGrt!pnB-keH;R*)Bcbe%Yx_
zn>QQQ{3u9CNdc9Zpb{6f@8-}UCk+uU&;dZpmMvS9%mpeP>}r2KxUkT9!<H=~vhL3d
z7f(swQRsL!?cAKs;^*fc&j0^MJtj8x=T}7~rK|*KyXI2j%$YMm?cZ&=x7)saDJgk(
zNAljidlD7}3TnQySoHPvEi5fN`!w&&&ff>x#=R)@^t6utes@>b)>G#$hp&rqoURwk
zqNcLw*qc{ZSD)e!tNZzMI;g`xXU-hZ=%UXY3qjD*CD}lUd3>(3l8y)RTk{F-^?(QT
zihkMljyM%?Y6rFduN?1lcF`BI?)znAYz(?-e#Xq1iGO~41cmO0hledyqImhf*%rUN
zq`D?@^Rio|-rn9%o;=AgoEY)^{QTpf8zo;|(Ns}W1KlzLI?Sc8&`?K5=fRsdJ&Mk4
zplv*Ve}8Y^xN+l)6HyZ<ObB?K{43bOfuX3lc;bW!4dL;%qGDoVpbIKM`_#W)kAM98
z{eJhHoHZ|IINjM(DO~*g+|v&`XZ`r~m&aUhMPyQv5)(5s=-$6hNSQuK<j-41P(d=$
zuc)Z#&`jfW@HUAV28^I&850x306GQu#l5}OWp8h>`uqDI^gOz|`nw)z2<z1qO_R(^
zEZX7gTK4a^XIQXhi^yE-^0pYg<F~eEgR0Rl4-PVe`qdT{9~OKnnY1o;chZ|18)q1&
z^F?jT(X>!}IjQ*hxy0MsazWPt7kqx^D<LhNd}T!-Xrb|r!p9Ypm?lcyC<F!Ytfc)5
zcO@NHTqXZ)_O8U^ioP2kgU0#<uJT*^-QDnb!m=BME7sj8%=&)+|KIzd?U{8ypNc<u
z@??Q?JKu!UPd|M7=C;4?ugmevlA@xbKlcCsZC~=@0wZ`h*L_9V+gqTF20ESn)2B}f
zd3k*|ZbY0&F=9B-#L6uoDA+jLJfF)?>)hq#{vYlCf3^p0iVO-80yRTlU(*F00R!qg
z7Cvfu(P5=-X(_4hH^;%jq2Yx_)b)L})u2_K5xYt>KYjjuabIoqkt0VEetdYy(D40U
zHGgGg<&FLI`yVX1WnS>Wp-0YE%6poQpsee2(9PMh)@30->(;FI@$uP^c2)}1?ko|R
zn*!OBb7r1xbcu+P(xT}??2z?dB~uz38F!VwZZplk2D<*VY2w6*MZNNGRz@WzD*E{N
zTv*~M{B-N_e)-3*uC9J@X({)uZMoV8vM(1!Z_fiQ-;Ruo1a&j3zP;gO@bLCN{Quwk
z|A&qpV^jB^=W@JH78IY012hEW<@-;Z@NjW=U%X%eXsY<bhYz6ZAwZ`qTPaOEmvnrk
zb(zd6?r+ko_{(IJ&ThD$(I(ses!6u}RkLinhw&SWS&7FN?n*em@K?g|m9eg_te`zh
zrLV(4_k_8+x`J+SSmrmEYiA6fwzl>~!PcF%zs-t@ia>X7K07<RyHEKJXc_FZX>C)c
zh=_=Zt>Rg5e`hf}A0MBDb(zkgLx)`4uX2J;b2~X%ePixzvpH6!T$5BDzP!AAQS!?<
z7cK;_u(Q8@di~gyD<Yud(!adC3>xqU-HUL2T`cJ2UIx$xiR1Nuuh)axBLzWktqUKq
zsQJ(90bS~QVS(eK$1k>Q+GHeSUnc`vxHsD@*X6iim$dkmH}d~~u!GKrIC8{ALQ1Nu
z4|HtkrH2fV+d=z4lWI!J%AkvaKx?H>pXLV5rEf?)JYnX{ll<QVOc~_m<v|w}KR-8D
z!Z@wx)UAhy+d+du6_u5WN=i-vPFXysPMs?F@gXti#s)_Be!14hM#fX8PrDvhx)k}w
z!bM-~H?OHknT*ocjrT!=v=&zaZWMNaGS8Ps8y^QaCmvsU7qr&v_3Q4r*5ynU+b*8k
zka+mR&Gh*X*KWTjG{>(Rw7c!V0f!~amoqa!8aWeY&+Zmfc1yUp$o0dA4+3+7eqXwD
z$)MsxLPT_Q@}nc299&$7_EdgO$jRyPoo(j0FyO)W`}OUhiN+OC;ZadtmzVo1D=IRA
zHoyA$h4Jy4=iU-wX5(q-?&fxKc4k$-YWvHk;U4Jj#Oi9$o^S?G*Yd>EqBSu)g&08d
zVmWtriI%^=Cn_1Nz3Nw`rmimU%9SfYs}<uapHB5+-aJV~QA^7!TCmiqu+R{c_!}A+
z&djwAFOivhxR*O?TlM!m&<dodPoIL?@w-Z120c~ywWIJc%MxWJrK~?aS^J^qd4pE_
z%%3k0x|TKfwwa5YThixeXJ1@c$b9F{9R*Jz6;C1A;11BT(F2?LQ#~dvsfn4rGI;sE
z6A@Q9WG#zWil3cX`DLLT189B6^7(aLXJ?ypd${!;oviK;>NA4&<=ENDF(hPWYMO~m
z>;n&F@R_oFlg{FJW8qSIxDGndX8{`6>v+{ByF3j%@&O*yyP~702s-EM=(^b5ph0NR
zHiB1IRvMU@9RporQ~3DU!_)fvuXGE$et&<T-{0Tg!qU=FZ+h~_M@LU>{r2|u;^OD$
zKtr3S8NbNcR)LQH{`c=62Nze9)4~I<uC8We0PV&szhApN{P6SY@9#qS<}6>bWWky>
zJY20zZ*OgFzRQ^|0$U5PdbM^;Ow5BvkC@!u-6f=@yZgMYJk%zGR!g2@`~q4@b#+x}
z#fJxsT3TA5DOAniWgLDhWz)~iS^4StGQYW2ist6xJ9qA!dhN@{=Q_c`!5Si5GiJ=_
z=vySb>edd>*%Jk2WzUYWhJN_;Dd^w#IhMsC*Hk>4!1G>JI~6$u1p}QQa6-n}dr#cl
zoDRz5pd%eYt3j47RsHwx`~KuRI|?g4pEU;!4qg=8dg#CbhDj<9KR!O5acK!B4-ZdP
zEnj`7N2sBx>CrAx?GG=P&kx(Vuk3A9&BvqS8hU!yii|F$LK@Z1DJd$T%hL`WasqW(
z9v|;NK1DNFVe-i<zxKJf)F*-a6;e#Uc{96Y+gBuRy#J?Dwq1(Jnh(kcO-;f0%hN#P
zUf0$}gRbvQNlypu%qiL_V`pdg;`;jer}i4BpK}Qb5&87#6U)-8^B9@g4xBl|Q&?Dd
z;`Hg}ojWa)l9LrDpJcGHUR!y2neT~n=fviOtZ8auirHPpD=I3wVdKU|&|!EUQQ!ak
zcHf?Ncgo>skPC69KS=5AwwvGZ@3?&ZgD)>HgD#A{yv+CGkB`Y`W|?va1_m0Km>jvW
zF&T8$?!wU3VT%?|;`{kxaX)Bp<&k5@y84vnOr07!*Ia3Wif4ZO;eJ``W!GvCxAWH@
z^aNe4=m%|>WwmH&X%+nWQ3%SjyUX7nJKWBnn3dJ#-Y?hLw@mc<`gnE*&{daD3v=h)
z_y2O|v+U0L-*3%9gB7W3*R0`jZs&82jFbfJO#uy~gI0!5oH!BOGWh;3RzgxT@yd$8
z8AhpGpvw%x<=3fH1%k%ESNyw?532e*;&f`?n=@GRnevp$tkMR}e}Lvb+NId6`L2pu
z`@Q}3^>ur<xc;Kd%gZW$zuj(F`YNPH%5>GO#y@XwZ$EtdwzR0IXq4ZoS~WGbh|Oud
zX=i7JK4thdO*i_(N%i>)mMn282znd6DTUL<*7oA=^7mTT_2c*TtXQG(H1nMP?zz_G
zhmIa)m9;JtkzE>i`8i{Wk}qiI|MlzQ)22;B9|{x{6cl`^51nH*EmBogy|KGoUrAXR
zv`*+^VTaVzxz^>N<$j=&?$4h;A6~6q&%|))(xnZBkKI5g9)OO{Zs8PWQCFSV)Z7eC
zP-$sS3j;vS#e4Vef#&i+wY!zvMelBKtqU3gl2Lk_ykGH>40zC?-Q)L-!VZ(;;4VVo
zeb5O#j~_R83af+K%Ukco$Heqhe}DJ#D4Qban94stKO5%X+oQ#PL0l)Ip`(N2&YsHP
zf}pp?1_lSNt&K*Sys>2O{Fu``1vD3)e}7+9W!2Z`^Xu1r+Y35Kb!G7KAK%#=0s{qo
ze0)~j<#CyRXIJU!W2K&xF06?(2A${S-C1(H{@>pfufF7ihiHG~cXf1hc$|jz!CZRd
z>gw$B?(7JB%eP!yKdxo!)Twd*isogB%gOcW@B6`IX=!=N+(3kjRYwQB2g_%+nQwuU
z(AfhA7;LM*wQS#RzGv^=#N1q6D<Q#`oMkeXM1J$GY?f{BaDlWbCs^Gm?C=l)Nm%oN
zB%}@zY;Eki#dg6w=SIVM`~Nci^7hw?jP8Oizb$!nh11Z`@YGrEFP^dNE524nn5n9=
zIyyRnIwPK*oS=P1CsK@_JbQNN`gQSt|NenT8D>PKCnN+sE%+KgbJna!z2^5E0s;is
zc%_!Kraa2Mxyg0y`m<kNUfw#vZF|9Erch<~z7`cvi;@=tpxK?GCnuujD|-s{$=R-I
zEpc&i(U*rNvB1UVxwlM~EM2N-X}R-MDQJ!5tE=3g?H1D}2POx`#r1(MOo!!A(Z0Su
z10y4$IXxwgUS3>r^?$!=T@MNl2F>Gw_Al60e>+nBe(&;YnOrU|ufQ$2{R?kxcq}kc
z<Bdg#{2Pl9=`tB5p;kzfFY9ohGq0kqE-&biudQ26LHCF)SfBtJ9X)pJ*o`fj!XjL(
zpiIB_=7R@EI)%X-!9hzc=gpfJnx|6y|6eVrc%N%ser%?3`j$CC-|y_L76-MB^Wqld
zn@Fmeo0!xvdX_{N6&c;Ra|bjO3EH}%q~w%(xoM$u`=L{(xF$}V*fcro{<E{QH`e{F
zirHT$3+mjwdGm&W;pNMhpe@dz%@;p@{CIF{Yj#IZk4s>nU{X@jm!gRI|Bm!>hwR+3
z!(o!jk)uZsg60Evn5p~EyW(U8YJBrU8{aD~zP_}S8+2qHE4Nt4&V4mMi*oMl2>iK_
zS835M&~?wCgJV@xRYChPPQCv9{rz#!D$pk<g`b*&&InOgUwy~jWr=2)j8fG^Xc9zY
zy?XZH;bBn0bZ)M7`=LWlAzuwMYi%d~`1JHN=r*;Om^r7er{36*_~YH~_ZL=&>o>mK
zqOGFBqNu3IFmG;G)aBzZ<E!7A{`qj2U;nGY{9RxEvXlh%&z>#)>GNmMwVjI=DMds?
ztjLKH5E5$Y=-^06OXKoeRSQ}}0=gYWSoq?$+~}!W@7#&mv17*r(6yir4h*0r$p8NS
zK78&R-|>EV@hLM(7|r!Sv#k?%xT=8)IYHB^@9*xe{>b~K?CmW@b#?ddPLJ@p7KKiW
zpMMnp^eY!O7iSk77uUyc|3{#$t&M}5yLs_qWl&36fBzq$g$oyg21{7f)D}%=1!c;=
zZ6-(ioLv@ecnr#|9>H%cTvWI~60+?kNBb7<Td_i8&*yX2pt&T_$<2v}*-kty(h%VS
zbujMkE^lvdZ+|i4(2d)-mCek=SXo(Nt2C06nTv~yFJ9cDr=Y+98r6XoBZZIMDk>{i
z-cj}x^6~WrwJ97mONGzxTYL*tMS-sJ=<MX|>h9KFTmJ5jWcj;0f)jl9e0_aA`P>}K
zscq*O7u5d#20CpPlmb{-SPtB|BXfDV|MC6*zUni29@Ws*Jvz^}ddln*At50v)_8*t
z+T-+6_lt{@^YZcn-D~JoUp`GI6142krt%XD=!POO-KZAO?D)q=NAK)-@Za0d?^vg>
zx`2Ryf)$sbVBlidQjn}KR%LHGrc9ZVb^ZK2+tt(aX9T4lZsToM@jP{$tJUdgVd<Ar
z_L{0^r>1JpFidVcwROi13(%bv++sQhwq#yru=#!97;HZ7ZvelbsZN<p5Idx`11>U4
zAzg29kr~7eZuYp>o}R9M{6Hf!Xn3Nji3!wMk+1o{m|`ReTAIxxXCrZUSE;aUaEGe*
zG|(}=d#k^@%{I$5NI1YS_3P>B`pQ~bTn7&xY!b?v-r33N<Kx4?5E&V1U~b;Na^=bg
zA-m4sxg!JWt6o^x4C-O;tuEghxBdTQ6;BUu?`p@+lIarz&njze&%5jN`Ptd6Q{1*c
zdG>74k|j%SeVsH(=*hEZTJq(uuB^Ny@a?pgwY4<pBnLM)Hqa??pzTtjtHU&ObXuGi
zI^5ot`}Nyz6LY;4^Fi0GT3F0r2DLh+9zi;Ef~HlV>ssFJeh<1Hy72L_m22MK-3_|0
zbcSj6v;`$gydOP!6e2f$+B78v1%{(XkAm6&RbO5(GJtk?f;J@WsVrU-wbjcd<dR}#
zW#x-YOS?~PO+Mb|I7y{P-ahW>uL+9I0<yAe&sMm65lTL;Si0dpXp{pvs3FxBG!Cwm
zKRqQ1I&Pw^t?d-!iA|e~7#g;2HU0DF&xWF>UOscJLQ{Mc#q{HNtgWrTyt}*m)K~B6
zdWtG4F8OR1{s&)Q7whVtAp%-RGG~qq=x~zE%gYu$&bYh4v000E!SW?b9-Nx0UGep5
z_|)}}Gcz-HRDIQY^Y$(15(L4(R%x3GgGGxLJ$U~<K6CAk9TE>8J_OZf4JnT-t*nyX
z-r5S<%$~h|@3Kv0KR>0eiQev)+C1UPm5`EmcOq{awt~)M%*)dg5)uM6bPgRl#I(EY
zZPVn*!u$UH$_8Cb(9zo~DjUp^7vtdK;-XZ@06rzVLuxN*RhOBW*yH2<?)UfAPR*YY
zx2uHn`T6<o>*Mwc2ni`!sJ?76zgOY>6tw%WPtA9hf~BS8*;%H+aiF6C`arw<LF3|m
zGL}t(%5E9fS}z5>y}j@3EOvi->*Qp0Q0sMH?eA4F`InY(&N9hdM08xFXJxJW^Z)*?
z(rnP^(DwZMVe6u!qLj3?y+dr~PMbe}{q_2Cy_g*hptV4Eb{1>s=&Ui>q3$VUWMss$
zR5%-HUO_=kjSaFw4`ps4e$U$I?W=6=ZO@ng_WpkV;dXw|xS3XVJHI?={B2X}=`E6h
z>7Z&9)VJGF_*h~3X-1pZM?s4U_EwpKP99jWK;fX~(TLq;x}a)vxxf65UAsVs^f7?i
z{h&h#b)&X`<}#Td+zcqp$<YCw;O2I1){PqxHGe)H2Mzt!)!8vPEDShs<OmCBqBAN=
z3Ump=-{0T4{Z`f9+0oF^(cxkwAPb^9I#%oh4FW%Tk^)-kpPHHq8nP^Vd#iQRCL_>}
z+%GRLXWZSj^~H=O&D(Nsv&qZLPv!q=lb)5uB`-hUD_?2Szrqqwn}$Wsu7=~m&DrLl
z2IY#t#Z%PPZKltf1=>R`XxRBe^$2LOCwKxH+#FfL37%)>6YM+$k^rv)U9sN1Uv5Xy
z)2>g2`|JLGcwhft`svfB8k(A*E70RApNckeZhd{EQy8>Z2UPHa&fX2P`*+@ce*Hg7
z&`C<{?Cb|Sk9PF;gNnJr2L~8IZM~T@XM(ooF87;T@b_2gjF~fEzRf)Q`}_O$<;&G?
zZO`v_?G|%f7@%<-#0Kr3(b4fqa4H1tGp_#j#_RBNh6nH7@!8wkgU)DjF!~6cY>wGk
z<Z9VqmwrwLba5eQ0}G#w#e(h24}X7sogcJc|IAF|iF4<I&W~+rZ&$XqmNrg5cjV{i
z=TqZnr=6Vzx<EZ*U(L=3S8fHy#PsCd-NncdwIzembJB+g2brJl+PvA=Z;pkc*1Ul1
z>+4)IGc|vGdC6>UZhmHlA+vGX8PICOU*Fz#tNYJ;@%9*KJO7tQA6X#F468IjCw?m`
zD%#jKy;`zjg-7b~-}`sf{x<9C?%q11qvYZu*KSamUh@8)?6+^<EULfhsCXXw^YgRz
z-QCsS^G>7~F=}?cNIlx;TzV8dH>#*K5i*DiS}Ne8A_VTXf#yfuYeD_)TU)a~p0EEW
z>^s}+DCoF%&{XT%=<RJPo*G(Ohd{?tSS`DD<mge&_~|O1P9-HKixw|lz32PZ>v4y7
zmA>90>7NeT33u!m+sTtBLAR)ZdI$*znNFk_&9SSMdiU;K#Ll9nFJ?G_t|kX{MPp)Q
zK7IPMq2goG)KYbIb<kEQAB%&avrWIfy&b+gFE6ieb@=)$!-;v4hDj`!E?)+n<G*D2
z^2Li5F>Twn4KyFY!}H}g&r!YDT?v1GeO;9NVvb(yt_RP~&SqdpPEH1;nUg0^f`=Rx
zbamIB>Ye@N;OAa$&{Ds}?)^%Nii`{&PHC@Ccy?yyk4N45Q>5S6+z02W6$=ZXC19Ku
zXkCGyA0Ozbi#?Ua7YjX(@BR5~_K#<?^B=r;5s~@)`id1Apo6AE--Y@9I(qORBk1Bc
z$nsaiiVq2(R`}oF-@|w6+u6x2TefV5Md6|aOI*GffhwGh;5nrZ5AhA)HMQVqS;7rj
z$^lwm{q^i@bN<iI&Ia4bS(oWNdi+>WR+iV<*?G^`YtaS8#lkZJb~7<CfqKuNLgLUN
zCTa6L&>{`cT<^gvS3>gJe=$6`v$L3klhg6^G~K{}00xGNUtcsC5-u!o{P6XwYe0a&
zox68kkBL0GwA4FdbDHng*VCp=J8|;l#U!P>iP_oRpoP&h44IcLTc(xm>gvkD&)?qL
z+q<A-m*XTA3oENb7cT~uh-9&(7)gR=svkT^U;s61He_AZ0?m?&ii&b@b040f8O*X=
zq+MEk#jih~&tKj5{me{beFIKG!HcK;gEU0AE-HfVWa#L4MMSaec^x$8Vl<QI`np)>
z<9)J;>FMkYpdC?bqql?3x_NxOA9U&(Xu0U6aPS&ta~GE@5*r|s8G?by2SC}O&)MZx
z38)a6Jv&@#it2*W*ViJpW{IYqo5R`a)CkJf$K~rmomqy2&(F?+TK|QG8y_sWb$wl|
z^_lth@}Hlbb&iXZJ9GA|ptLmiOdmD|&<ZOhC8a6L#a>Tdu|fm1_7K#e`u%?Y`Wjh(
ze}DIi3X8mZdpbegs#{+i=f~`=5}i47riO-wL#VQL(asnLt+%r*i`7&-54G`1gXT|X
z8mC|TB?FmR)m?H~xBkyZcF_7|etv#XmDewCe{4<UW&u%AR%d5t(C+H{wcll<wq~hX
zX}x4%W^T5+tM56fs8|wtwRzy;?e+ibK({-bJjn?<&hF9C?$CQ5q^!$yczAh1V<QJW
zJ;kR^nUZjMnXg674+HQjj~BPLYJ*mJNE)XdIC8|Lz)4976t+t=zey`8T}pjp0q$18
zS&PJ1@7W{s^5sj=ykynaSFFay#uq1guv=PL9XflKcXjxBHt@~!cXyW`Ul+TZfdO<&
zT){&oBV%LNV<Jh1S~x+c27oTL<K_-!yYT+bPG)v?c90K2=h83c0-Z6;!o~(lvRc=x
zzrX7h)eZwK^=q2c3A#ObW$<z(P0f|34i-Dqw>hp|vj!BHJv}@U($a@do#L9La`lId
z=cEa9=dNAavZQ-Qq2pVVpZ^jwGJY^k5)c&J`v*P}a<74rIUy~rZO4usTIDf(yu3%3
z`Of}vx>89=DJ$egVMj;Di_{~aIS3bh<uVy1rH!D=h(IG<Cr)tK+1X7vnF3nGX7}@n
zFsM(@0Gb^Ft%~-Zt|vMtY!2v*>$|&3L6;P9af8MP7jDvnHBZznEF|pz{ZIxq=OrX1
zL6<?l-~ZnZyt+VAQZiy+jV0(<P4%n$wrnv0wfC=Gy9S!O2i0}?_iQAjrIRl&^9|4t
z`SJJreeht+ssQu6I{`O6j-5K?RiL!dtw*A9$r2UN!2P;)>oP7c^PT$L_P@DX$kauP
zlxEDBapmWd*V7pxJ<Zr86)OgCS2M6Sc2@~!_O&%D%kEyfBxGr68RY}oss>u};o{=*
z#VF}G=-}Gvg4TS36D>ejJm1)uoS2itBP=Wo8nOg=3AFa>dR#THu)3d1WhLlvmaeC#
zr!UUFz7EtsdT}F4TwcEa;$nBu(t(1K5*IHot`s9lP(SU}70nyBZ!fO@{|_{^Eh55F
zUtj<9<ciD7e47_8R9v)ZQ9?!rM}2)gsBK^1Wmxs)MPo|~%a7l`l{GXtxLTbmgZ_YK
zWA2vUfBE-=<%gVzko)cD{s*JX*Y^5&d2uy0HG$^fCQT9o-RCpmWXg%NXIs~=*9RTd
zRPrL=qG9|F&=FTZW^{CPc+7?;mw78!YIb#Xt%^N==8VhkvbS4ibVyBJ?B4&VUB1o%
zvgu?&fJVr*ucgz=m6U|~L7nM3XBU@Upv6m|{x+NyQolNEtrO_*r$<LPx8&WG0$n;<
zQ(J48bc933qQIdtDWkH|5_Clu=uD@l3{?dM201x7pcOFc{__qTI>f{+rqke~b{M*g
zYpQm5SD$9f#*KwbufNm`UIyCf%g}J)LO{veTcS^&K2>_enVz5Df8$03XnD-7t=TJ9
ztZ3-%<ptfS=q~*3Sg$l_r{|+bj|$%3vjweVy?Rx2=gyrG+j1nA`OWRB`}?c2Z)Iuj
z?QO2Nx8=GXzmN&qFZt-vqY0BIGsnlrgAT&_`1rVozkmDMwYs2lPOKJPQ&op;xHw?_
zeou2p2glQ>-{0OAzQ1P+8rIQgyRb6t?(XvSUtNCepQOT>nVG4tAqc85dcmDU7ndt9
zcJAB>${C=Ep)F<4&&lT8+XLE-D>|X4<nF7ht3MtUk3Vqfk`OaHUrTdy^9v6b7Z<NL
z7E3t6rB*431<JLTpsYo0g+D)~vaqo&Dtp~2t&ugLxS|F+9~W-c<Clai9clAoUs
zYB`34ECh`YO_(6CCFiCPD=RBQ19($78?O{ge0)3$E9=3#cVkn0=6=1->-6R5Bvo(F
z!R+_;R)bQsgh4{Xsb5b|PZtywZGG?{!IAT*r>}48>ebq(PMrd^<v^zZtXaczU~}Tl
z9Xl*Qb!haq9KksuziVo1LGv&_e*OflhA)ws8x$7CmY<&wx~6?$fWsse(Ak0K&hZ`C
zJYO4h=@~1x7>D1g+Rx9=A78zGUl(Lo1?Uve)Y=~(9%?zi{M8{XZeyHrVSyL(3r$T;
z&>@m>wO>QOfHzT0o7T2EeEp$&_u}-;nL%qqG@w%ui`?{0OhiDd*&7&{4GJH*cuZ;m
zrSTshA43Nk#dM=otkhmE$lv!9)U5)o9@@BZ;|tK?oLb;jOXe;vOJ0Ln7Dz1K$M^PD
zZ`iUW#BSS$4GauZv;Xf53kq7aHD}k66DK%yqqZ<GfO5jIW5-UMJQ=v|_Kh2$?((8X
z6Z@j}R2YI<XOJ0#*j+6XCJ5}6ap33R0G*pXY4YU6jEoh3?tQ)!oxitru5~$=mwMRy
zdwVygpO*tI20#4e<>iY@y{BujUp(F`t*$UP;^4u9po06_+GuujbMqUwZ);!o@$mt9
z_RZbh;ri?s&d;%IPCY&C;E^LNM~@zzdJS~Zt9AK14i7asbG?AArLV)L9{>IA?csla
ze}n3(9w}3=)VCiV9tN$w+LklZOj$@!aBm0?blZf|s`b!0!?(A#ItK&@h;Xrnt&i&k
z*>Lb6Bj{vu&~)#NCCyx1Tn34USn5`^cXX5pK{n=fbd<<~Sh657C~L*TKhHI1)Y}S9
zp0{!HX6LFZtA_OW#q(^dlfJ*Zd+KX5JO3i*cD_ZA0+pxEpWhEUD6&uSNdEr6Z1(o{
z5m8ZLKWmp~UthPQ^7FEWlt-17m5QpWte^@1IhMr_o<3#e=jX4es7Uzp<KwCSSKTL0
zoCw<4Hh+HnQeSR{1>x)CPMkO)Fu})0dGW0C*Y=dYo_24}hri+fcNQLedV2c80F5cx
z|92KP?&IR(I`rn|W^La2%niGDTZ2YX3LZK!LYBnaKu$F4h~olX)!N(Z>gdP_I)0(6
zi|fXX8wc*(i77F;ln7cK5EV7+g@lWX%hjag3wI^$S5#VbtU<Q@RTn5cq?n=eRBfL@
zGjn%#7Be&)I^@LQP*r6WwLNcbQG8g~v}>DRf;QMaI4)m*<kQpBi76>9pm_#ReY>mt
zJs-Gj`RVCt*5xX(1&@w!9yxwoTi)H>{qe1>*;C)`uKy2O!_3Ie&aS)cvaJ7nyS0T9
zX6EMM`Q|e_J39qs9n(SUOlp6BTU&Pb#0d^pSJx<?CDx##d<kAHRQxM``Qnxm8qH
zfNr=_m|5|EXQ5+UT-?&HaeJ#0udj<`n)DKs6BpI~{&scU?AfzHD@(wY?w2Cyx(7ki
ztffnrf*0ic{TiN<lJel;;dano+&6FDfKH4*@w8~~-Q1a3+w1;Tfy#)B7X^!U#+1k?
zDJiLfW?_Ew3JSh70<o<55Ujw%oLpQ^0Ra<EncCa$_xi3W!nM~{(N;r)<KMr31|}vf
z3_i2Xc-z|AI=Z@=7A{o$^Y`!9S1ym9ON*^|d~I#CzCq`^&hBo|VLuEGlT=*X-IcAZ
zcAcsQ4UmHdr)GaFIre(}{yt^*zL1}LpS`@i95h8>m~laY@#GO{yP6#@IIK>eI<@MU
z<BcUtRBqh7nQ1ujT?EqV{M{dydQYD)cW&?1)!~oN&9$By_xdZVx!#JIYuD<6c2^`H
z<C!sQ)~Yq4qN1RCNzKg6nl1?n3YykUa#|SB!RH8Swzw?m>=xI5^mhCGV_#oiUl^cq
zVO6O1jF~eZUR>-B8lr?87{0IeH)yc`VxcGd*O!;sfByUlI#VBXI9_V%(wf76En)kT
zIy*e%H$D!i-Edz(aN@co@bVi)C8gM-kPWg|43w0VUj3Pqd3o9129@6Ej0_FXAoHhB
zMHd6NfYw{TJ<BmKKjy=iWoNQZ!PWx2yevM)%iN~!kHpcVM*}oOHf-2%0CfEL)2B;8
z>*@_mO<gyqon=`n^8UfWW(o5=nLmI27*u{r*|BTaqv!MM+ge*$LDvt;%lFTiA;BYU
z=2H@KN%7#pgFk+~UJvTIL`O%@m_7UPjg83##l_AM5fW)<W;CXro~Edv;7}3*I*;2R
z`<hNlTH30Z?c25;o2DDBF!>~ls_^M^=lJH$n+NJMA=Yy}y$+h=1r3>ij@MHc1r0M#
zR`Ydwes1o^f4|>rn-_YZ_JgW)m6eo~zQX$2QcK<Y<qjS^$Y^P430gbR-_LJV{%%do
z{>sm4b-!M!gIcSy)@7iv7tqGA#!gRhUTHI*wdPYFKYFxfLR&{ihiv<+{=aP<9VLR0
zeRzU`FO|R>@MM%OsV-c&kb{r!+HA$_yqE>^USD5-_|Ba@mpV6n@u{e=0FA4)^UG_Q
zYcZhi{k3-Mli~E71UmOeLP{#>$%%<u?c67+$k<keaK9|^&dk)jSM^%=&$rw8pmVT(
zetr%bv3>IV`Qu+-UrU%~iSWr-1Y`y))h-IqDERg!5`FxF$HiT^O<MfQyAKZ!gD#s~
z>ODPV-S>BQr9sDs%rH!5QB?*lqk*?FFYPLQ4chf3V_ml9*xjandHX)l@}al4wt_ZX
zY!#mXYLqg+0adrC?eTZo+S-R#1}_KQY7X8gD>HXlKJyC~-lq=_w}b9bTNk@~nas4(
z^78Ae-&^YG=}l1KEG#Sp?RB<WclP9D^{o^9zH5kZxwyE17j8RWd%x#1A7~HfUb!vH
zRuw*G`g(UqAv1i6Gb}8u33LOSX&t=jkoo1sMbLs`e)+K1aSRqkPfm3Axw^Qxgy>^)
zFK7*<Rq3mi88akKq!?W+ERkZru+j>YympnoE_ipxQbbH_(V|68sj-t(Qc_Ylywv@I
zf`qERya3(V5xR5U{Q3P?u7p@vTW4EJ20kwP`YJRfEp5?)1q`9RRwthpF|IuF7(C#n
z(lzk~1GqeJnFTsv19Vi_)^}4+rhvwH;tG_q&YU`RYQn5pQBP+tWiSA3+gjPt0nX~q
ziTgnr{7|1WZ!4(2DdDu{1Fa8RB;NhJL@-m&&Q5Nzdp~IE1$1-Klqn)7QjDfdneyPu
z%HR##w}Z~YcRen0=;~Eb(DuyLvTePcosBVi&zJFqf^L9>%{O(0fyQ&!ty@=6ROEDe
zny%~di;<C$ku$7HwI)rPw5s;)G!@T$_6w?>hpON2ZU26++P_3(Zpq_gylWyhG8GmU
z?kImR2bwx~^{VU6ofyzPi=Z{w`$20pRg{#nrofX{P+gs!RmqD5*Y<+OfX<(<KiIj#
zaMg+x2mbv044Tyy5f=}ymcK8cqNJ3Yczoe6P;ILed!*0#E2Q@V%6*`<5Z0ijT#hq}
zpPyS<`+jZo_P7M0tTj!|&56m$%}<`BfTq~Q#Kb@YCMiaepb?Go^71t?JA+Dm6tiyM
zS+r$~NLyQ5l-K1QGS+202M->sGH%$HbJNIU5(_gkGw4+PqeoqT9zS);tHfrmVevB`
z(3K+p|2(&U`07=cS?;ZlJ{1vjy@2?vEUlQ>SkT%-MrJkzQ&Z8@)KrFsZ*Ola>*?|F
z%h?>5rW?%y*};kkg3L_Kp5ET8yRM%&!Qns8rV<ncQQLAP!`8>~#>dBl_G%tK&JH@3
z>Gid>pg{4M)DpTnth3M4#igo6w*6H%j^gL-h3CQ-WMyTq${h&T5UH|V;~#2W{!Yfp
z$qBl@is46b@)XBrwu9HNi#s|xf{v4x49*7anS1jl=jr1wUrIoG;CH?M_xCsGN(j&>
zdhRi0*{KsJHXb?R0-8+#-PN=qv3b+$(wCQ9Qx*1>zrVNWG1uf7Gdd0&aH#oqGkwwG
z7c6-(3-&cMFwB@aQ_<2=vaPLc!-fq3k@c_FZr@P++|Ti4M@NU0J$zBa*W>c_E4C(=
zhlNcOyA+TtA}7~Zey@^U+APN*E>4bNLH+-K6Hcap4m1airvLd-xaa4y*-ev$1Si^o
zQb+<ge?Tih7nfaKkOd1bjvAYryN88|S(Us{u<8;34eKZeD5s~Sw20|OF)&1J&*M!_
zPJZ&_iN^KZoScHEr~W6uzt_B2=l#F_`ggG$Dvpy2u1s*5xYUtZ!d0l~(S-CU%Mfi5
z5oVT)QYNp0TmM~9V)X15bdzO~U%{^x;L8;p#N{=G^J&7S)0#<NHGLEm4lNMlX>nHO
z%-&I7Z;&>NO(5jkt-E{TjejP8-&Ow1_MDKO?EdRpZ->k~zxU%YY0yolI;SV4MxHu<
zKD@53Zu9e;+tUs|ys*f%n<wPZ{gT($eDCfmy}YCFvC3Tg1qU8~T(M_QOy2hB)nRLc
z0s|-NoDND!SrQZ+{Pmpmdx>@5_I`VNdv)#aZ_AATu(6BB>^nQ#Jp0#|m#;u4?ClT#
zyIVSMhvWSEe>)qE7#NzEnO`t4FfcHM#l_A0^y$;S&z63#jvbY;tBD9+?l)CsYvyIQ
zNg?6k>YiMjoELW#KK}CQwEpX#&*z(8<6y|Byz%%!dqO=k!-w!Ug&&+Z9A{+sq5aL`
zhvJRL4B^+O$Jeb~?B0LsX_4ta$?QxupBV{OjEv`=7Oh;h%4<?e<g}`9Z&rq`4$FLV
zW8<VHTeGikTfr>n)+@Dio^AE1ZMmtbsV_GkmkX|{s+ydxb2_M^Vn^QYw`Q*H?$TPV
z_T4=_S2iRbHp#hR;5q5~>rhY6&S&T5uGWp-wqnVWBLxd3L6><YCN3;0E`C~K<@;RX
z_(9g`>lZF`eE9I8c<lOh>%v}NTU#5!!r)Ml$RNwWz~JEUXi4552~Yu5|MzwLq$Oo<
zZ@s*gz5eR*`E|FR%$zk#N;s3DL9EM`uTJBeIRiue5jl2yk!l%+2K%J`X8A5#zJk&<
zaeJfu?f;fMzL1ldxzfnkI5akP?fidVmd~;*UiNP1bGgG)9TFtWa%SAC`RpqyBC;ZM
zb=WMM%1vs1b5_XNR(V*}JLfw(Ha_&a@9E(Y;N;Y#vU1zDFwl+>U-P>uJGdHGY}yo*
zw>>&<d-T(%PjBt7-#^E1IcT5$mMtciE8V`ly6O#bd+G1D+g~qimkY|tdBe(n@%_Hv
zdCaBH3JVS%y<2uWx9b1j?^9>bzMZpn;X=pL)AhrPiZ+3hLUZcvZMjxVpya?HT=(zu
z{MWOx*Ik_d?~A(Ur4B*mFQ9WKqPFGCJU7>R`I|R6uI}!q-<C=1u`)31uz8cuz~Eqz
z)X&Vo&?Hzb^WgaRbJp))%&UGE=;hT__igk1mph-&yZr0x>!~wmYQFq4-+KAwl~-4X
zOY5;RHD7;yb!G7KEBk7zBd4i)R{egvJv1gpXZhuoj?HYDM>+&w-P*ePVbBb-%1=*D
z*OmSL_V(7M)NUy$sdY&c|AUSs*V59G%3t@b!p5rX&5T>y^Vd(ABC>SZGA&cnP)|=!
zE?!>Kx!FC3AMSWDD>ZUcZuGR&tux-AZH;;JpeZ_kZ)j#_<}CC4c`sd*udRz+z5D&X
z=$$)vN*Sm17#SIDsrgw{`tDBT=JfN|mif*OiHcg~*vvN5kCj0|!LWf36jB)*udRt(
zywrR8EC2dmlW%RwTzq$TdG>(@##Jj<PRzaC)zx+B*4FH+`|Im3uVi3gnBMxAmw|!9
z?M)#xy#D<7_4W1gvbVP~A0O)ldBCdl)s+;6+HY@eR=wSNz2wCO#luS-3TD_=Z%aEj
zXJ!7rpT|nN1VckZqc){<+Wq}<`Plyb|L3MgMs3fVyU^<Xt}7otv~F4A_~^ogfXcmb
zM~@%ZHZ|Q^_+n4``FYDO|2cL4-?#0jtKRMZ_j>=jqR#pU51O<$m%I$J{rP0FRqd~m
z$BC?yuB?l--uvs-YAO4=JrA827?{K%MFhj2*^|}%vo0_5EwY;H<?9<75)$&behM1{
z1BVNG^tW^J@?JfyzkiLpeC?Me<`?Vt|Jx;3|EKWk)vJ<vtWAgC+}v!Me5^;z*yGRp
zuC6YV#6v8WGJIcOTyzc$3>2?fw`R?m<Ed#i^WQgIez}KB_22P_1tvR}TA7-HqN}U3
z({L`E{jr0r;qSh@ybMauTl4SR&9yG~ySuym`h|tgqJn~nR=f-i4cAVUfFg;3;h&0<
zlGFYlNA*j-y@}L~-4&w0@5iEV@9t(>aWgPHs7|hjCR_#vfu0+W8SH%`B4%V|XY23!
z_j39CRnF~vb~;P~YtqilSZG)KYsHc!F0s2x4Cf}tcuT7Nx9gL&R_i~my#2QB_S<WZ
zc8jmxw=XVscUi8{gn2V&R2(%wsa$dO`t{Q<OSDW(LJ|`bx%m0RcbC2ON&l(Ze|+(e
z9~Gr9E;ufB@6X#-_vc4pXjqt*sp(Y*Sq6s2enznS9lDFZy@^~Kx!LXa_xIr;AyYuP
zQ`^caYSNdl*W+Jb4UfONr}Fcc^Y#CN@9r))kKtxu_;B~eeFlbxgd=k73=AyF-z*MX
zHLm!Opc}o-$KUQ}%I2;0|31%;+EcL+WR$c9vp|mB|3AgPGmTmw7S}9au|k7a-Y({F
zJO6Z*%Dr*5KOVOCI==*EgNuvZMdjqyEm@+nbm>w}d;9wZU$1`OJpZrHwA7VLmbmyW
z54Qh(^ZdTg#?w+W@9rwKTVdSa%&iyi=GF%4#-ygE#un_|vLz%kGBPV8<3ph&1H-{a
zm?u9S6_3xju)q;iu;tvIrqbHhmUVWPDHkVaU|85Rko#0sRWlDZu}WDMEqR#4z|i20
z9&zE<-`v~`%57g?U-t(EsZ7Z24T;Th)o)F2Zd*IkIDOVR76F#3@9);?@BeeDq%Ho%
z#l`J9r*|znA2DsIZS}X9rAq&=?JCXw`u=|W-{0S_KRG#B)ie9rnu~KRi?<X$cFVoB
zWu+_6g8IK-uW!;>UFiSkZT1{c&GP>C`wK^Fs%P6UF#M>~`Mvw!Hdau=Q|JI~w9McC
zcU#@(+4nV+m7Ur7WCH5y_TAc=z5LayEL9bi6$=(PFthWS%;jQWD2T*}wC&l~_5S|4
zzW>^>Ug_C9D!fuA9{)ev|6e>if8Wgn*$4m2-rcFZd4Au=W75A4%m2Helt1<FgJyn{
zv@;TGqqcgTJb7|iagUUFUd-l$5Bu$YdF(EKf6c${lkm~w$Gs<gdvkN~-s<mKii(b%
zot;&$*KYTDBK7=h)z;+Wd{d`SKmE4s^y7~&etdkqDK}bCQSsI7?d$L4ZGY**(vZ)u
zcVkm(x6bLT!2R9)@^)*S+xa{vUAlbPwD_6N-!IGUbHCl`6jl!j2v`6*XX*F1x1USZ
z7#JMkQ7t4ayg2c2+e=WLB7I+5Pw(1`i;GQbeiW>Y+Z)B#emFsqf#JZ^M6_(VFE}`O
zaqaJKFYoLu-t}_X>?<pS)h~NGI22gOOt0nMn0s3{?M2~}6BEzgyS+KRUrSs2>T-Yi
zqeqXL?oPbENk>#%{I}M{{56rA-EQ8z8MQH~_1&J&=hU*_@BKb+)22;dj@$nWEWcYi
zeWBBRtHMVuck;>~AE<P7ZGH9nb?WVHO3KPpCrw)P<x9!Z<;%4-H9d20Z84ntW;*B=
zL4La*4#CU)Oy?%Cu#20RW?$1eJInO7_5XdFa-;d$ox8<!FCFH$f3w(%fuYG;`!XXa
zX)ye_G*Q|8%KrNQYVT`*|2oJn|D^sEBLf3tJ6a796Z`Y$Pf&`l`ub|=iWM4PUteE;
z^4Gf9-61hCYb1@+B(zxm+@GZC?W6u<>D$}e;|nerT3JP1y?S-kx^;Qm%62yYIjE+u
z@9%H((Pi_)Voxcnk`+b8#iq5tzK9t&+*|0(?)jWOF*!NeH0emkvBuAFd#kqIcz<&0
zuiN+kEt51(+cJZ(gimkBmcYesE7Q-<+mss}85vpiX5;ZG^XA=qB6)g~h@9NI+j+Zv
zFJ8RZ=EcasQNy!<8RWsJDQ#_RTXS!3J6U~yUtdRu!9*4Yh7Zjf_A@dt9PF^=gH(eJ
zt6%SYK5z2rr$OuE_Ui5U*I)m~d2`y?BnH_XEu6w?GyFbyxAV)J%@r{C_U`WLK3VIy
zlD)yp{ci0pU(ertW|m3jBqJlEDf8y7yKy7pvL%OrOiV#0Cnu+uhsOk!tJkh&eRyyX
zlu~%Y85soTNI0;AT(-pmbPGh;yE`|3{CaY7@}woJR%yAqxtUe}`*u73d!#f2!-4My
z|FJ>JO$G)9iH*k@&sf&|+2Q2m<de?e5b*lm-rdvmVpp}x*F_{ICi-5>%Ff<e^74|H
zsm88?hfbF{IUHnS3VzB}y->W&$-uy3dU{*#?GhG{-3<F46<Fw1aIML`efHk}Z+qL?
z*y5iuGBCs#elv$!1qq%HkAFXC=HHTeS<Ul#zJt7F(UM<ZUS58)Q&`<E<7k&Cs8O^n
z|NgtjUJM7Hb?fij@nlzOWY+C%YZonAR1@;VzN@>t^nUI4mD$(V&9W$56r(qN$>;XB
zI<dP#Kuv$pzUKIUpQg8YpS3P}(y?gq;?St5RcFrlT(+#s{r2YOEW>2B>g1S!(9o&V
zbRrk|+y4zQH8uTp-q7;&rY(7Qt(;347+B2mpuwr(Jx#}OE&~I@hs8-~Io5t(ue5pA
zwKb8G&hd-?eX3u75o9g5UG-_*?HLD~SofV_7Fd#$l%!X&;!HgkH}~ZOjm%T0PhbAz
zNs9cGncq*x{|kD*=X2k@x?h=3pFcN`e0_EGbTQqiC5eaIBv*a5zoXu%ee@u!uc)YK
z=AjnOA`6*U7Z<yC+x%c=Xjt7TeF2iwz~K%iSmqd~pL_9o{r+jWw_n}ax%uCRc6*cE
zq1QL*w6?ac%)Py>O^cCb_R((f?1zV1ttvh&c(?!mKeg>O`tkc>KwYpOA0LC78ls}2
zpoaO<rAws@5*i*B-M6awv4Ky{M#FR0!!~IVVd3N*C-%!&7P(xHuitxZef)hT_D*&G
zc{MlB=iT2I8@(;(AzR7Ey+8f+rh5wt3TkO;22R(D^?A;~AW*V{5!4w0I~Gbf9N^^T
z4b8|{q4M%TBlD{(D<>a1bciRMk)!N*pKNe!?A&i}Z!iD$_O^NC>GS8qtEzULn`gT^
zJia#6IQ?A6{e87x?-ZZUJlw|H)^)a{vorC9jJRq3y*=7h_cpCr9n$3R?dS9P*{7yx
z^2}#uD41&D1I{5(tHIO({=&n&<_0x<2h_#%Vpg=v*X_9ZVW&#zn;U`qe_dVw<<;u-
zUX!d!UoB~utMU*P72S8v1hmk->d(jHQzuMVaBi;k>NRV8CWXYtu01(f{q_6$|GOVL
z{TC1vT&U_jO+!)fU`dx?-1_fbb?4^UW?M<tttfwg@7Jf(`o8H53<6uQg~#tFll`|O
z9AtWXXJ;^IA^*<e=d;#CPh0x;_jl=4%mO;AR<8~X4==y?b=NMd(C~2ceSLj>dEb6(
zM1+QgX(=l^$E^?l`|E3PYU<KGaqE|SKKv6j-M%t-`Ild>*Gubt-J5%Ro2I4Z&X1+H
zx8<599%5;BO|zWqcbSuM<x=^W5A)+{KDzcw8oM2C=g<H2oST8+j|H?~0f!fa5V&BL
zduxfJbDM^imRI?m!gjk~FO*Z$(pIfo=NG*#C(y~M>DRZn*;c|10y`e}S)0`VtGQcz
z-gej1Y0<ORyuG#6n_EmLV1M0Tsr#$ftO>ckF1B`V=8-EagRicOwa&e}E7Wg!@LcQi
zyiImBKMMZ-JYR1Xk{;&e)fJ;R{aC;J`i;rQUoD%RXEe8k;lM#w-(DHZO*g9p0|P<L
z_W5?TBI4rL-xM&P-V_oO^JcXR14C06Qr{2a0Wi65JtH&Qie0;+qPOQ=y}3F4>dxZy
zwekDoX3m^>Yg_K@Ha^)^hYmUM%3571(Q07${(b-dSWs{E<>lp5Cr(tHep=P@*7p4Q
zr%s(JIcs`7<MFXxFCU+f*x0#~CQmlaxnUqGA|j!;|Cf@I66gk;zx)4x|6lUvhGFTe
zD=R;iZ&cBZ+Y{k$`*jNFL`O-zuX`6QQW6ytTeW3N2rn=1tNZ)+gS=Y(esB2O+uP0O
zJ`c97`Z6IkGW?6==}lYG&(B*O@?^gZA3MAFpV>2J%y|Fxu4T!K3!z#}3<^66nXSP7
zLl6xO+lrt2ot<UseLb#vZB|y6iYG5G@1!M9o}~EBGV!detmIk1{NtdIu<+ND>hnR3
zw%6Cz23J<@RMFJa^Ru+Hta>&xT|``5{pFwBqw@8CHlB=`pOujjP*L&2_4?}7tFP`V
z&6XGY*}rCuPHJlE%3ZsnKwa;^z==i0#b2LH_Rl&oK~c&)Z_c}Yzw=sKT4wm|eKl$F
z<k`G}^<OT!gHBGa`!spJhMis9q%G;^<=)=i9nQ(g>E+{NGBNAU?fm^~4;^y)`>uTd
z<>K?U*B9~YO;~ccoqx6;1H%H>hiu?J1j4Hf42-%)MnT2T&xQK=_2t|S11*$)HakBH
zG!Ap_{;uDz<Nrs+*Z<x6Fo=O8PEt}5)QO#Cnmy}o!@Ua^7TnI?9}6niKnEsYURjs;
z|KHzU^Tpwzp_)ocPK(`ogUZUbUAlbP_xaB=vrMz6%$>VdR6Fd&IqUa1o4(zvey^#m
z?F~AUv-EmwxullK`}_QQH+Ge-c5-rxx^s{fRQ1X%1GgWL9sHoZU}wy#RjVecL{0+@
z4`p3l725kc`}(@8rPpKAwfGsLTGHoLx`70Q{cRSWI_2g0oITwfk^?iozq<>H9iH%C
z{TD6-Kudb?NI>S-S68Jh3KoF+;CFYI&-VM$xo3}!?Z+d+XWP!JX1=(v@YLC}SHHZx
z%sb_0f1j-NtB=R!ryqYD7#cctUhTKY(6F#q`+mQ>TzWlr`J6d2Q>Ra#eeTOn{e3?k
zO|p-#`?)kLE6XRHi9ujP)J*VT0kW4G<dbe}NUZvN);u&IU_sd0sLW4KPJ*iHsxL1T
zU;feE%*x8zrp?H*XwDp&$Z1PmyTwjEEYMI_e{OA`961ftp^?AxbNa)>?XP>y?_HSe
zZ@03QTik2XyZ!&`JcD+Zz5N1;(F+S4*|^VI*Z$fPwk~Gnp+io&_x42cwL3ev^Ih$c
zG%mRwTYmCkLB`cpp|gxqyFkNGxwp5?^xO9eOJnQL?W25p6_0z(OMbuIo_%vuDyXdT
zN&n^I<I|&a`q#PVhYlSwDR|)U^yyPgOUs+=sSFG(>_`nCB+u8x$E^=v?l(8+_qVsw
z>=Qv}c#4XPpMF`Abzy;{lwnfKuCljTJ4757bar-5JpAy&zrVk)?katKTB>4;j(0ns
z?5Dtm|1E2OZ2=|0x3{<ZKR-7&`1`xNrX?=|TwPpd_!*~teRWk!N9W4!_xo1w+GPdm
z4BotXQ_484$ExJTg*QKsc8kB>cwFxC&CTh&SAK=9kK21?S84XnyLqjxt)`Ky*RBnX
zikh`2ZhhI?Td6B9?CF+`nJ{<m-8T=KUa#A|&Q&HxVebFpO$85~WNj(}zTdCkAEP&2
z1vIJ&%G2BP?wZv7sQ|gl)zx*?+O?sXnJd|NBocPWFf<%Ez<^QmEHJD7mUDKFWiaRh
zt(PJU98q%p?jJvX6qi{sZOP-~{i`=^3R<~xrJbJf`G*A>W@cfJkM#zZm2G?U__6-a
zKi}To-kNbyNjGxS5%<<-BI4q&_x*kc+6`h__~?k5^AYdqdRIXkI6;|k`u;yl9|qlj
z{GiFZ`eCd1mYkbLJMZRg&A-3zWK?PC)=QT!e|^x*pY`g>%3rTmufMWAKYnM7Uha(z
z2LlWl7#dq4{dA;wWN?Hw7Tctxq<oe$I9w>Qnp^dH?e-~Cr<NZ4Dyki(p{>2z^`G9o
zEt!+qc%@RT4(IRvey_Uf*URN!`|JNKKKXlZ)z?eh`g<0D8gyF5-Ob#3x_Wwk{&qi?
zsQJ&UIrvpPz9#VV^YhmiI=8EMZcaOU$y<N#lHlcjKaGSL8XB&`#&?h%<)E-~#fl5Z
zdZkOhya)sp-g?u$)6dNTW!hck@7I0!P;j}^?tAQa<!j(UnO`f8?Kh~Y%LL_#3k#h~
ze|$&;MeC%J!@TAiYHG&{W=2Yz<?LAW-Y+O<(xgd~*2PVjzjEEWu-MqUuGe3`dKD5I
zd-sQxl~vU9b8|ntN+Ei=$Zle2IQ`&jm1)_V2v9=bmK!;3=|boBQ%{RLCxMP0(hOdf
zacfIvn|JNw4-XIbZs+z63JslVBj>;Qx!)X%g-5%^we|GQO|Lxm<oWaXkLfz6gW}@u
zg|6U~F*G#Pt$Xq3eqq7ErFRRD%g(Z|-v=6KzFTx!*Y{f4+gnRnxy4q*@2~599~u_6
zD*O7nedkyh6cQr8mCG8kG9=%-@DH{Y0L8fs42(IDegHITISTgweVhOFlDB^5y*-su
zHWeF$goL)#{jEw(OY@o}SNTM+7F1Df%boo&=ssuzRodBEs;4*U{hX6~yU0Q&YD>mM
zxw;>T@>gd*F0fel!+2Wi)*Jhm^U2$-5s#~I1U10I<7<~bdX$u!k^*XQoVWkKXVd1*
zQ)kS`u=>2}@q;Gq�}7ixmPV_SOCl2@6}6y>6$Qw0T}gQqrPVuU<`=GiOcW;kK0v
z791$BWMF7)#MTX%Yh51qZF79h$D^S-j29+}h>B)jTH*;R>^CMKpSAXW&F8aGJByY!
z8W|HeA@Ox>@$+*t{Wv71PMvz{#EA*lUx)6m`x_D&sk#2Tw&$xG8yAC)Lk?c<_wwuY
zc=MR5ueRUs6o>zrInAbF-i#S5{Ox|au(Gm(260cFKCS9mSXg-K<jIT1=WQ16*kR!r
z1gfDw9+#hehLu6#fdORX87aOL9^5HBE_=W7@w@FgxA(nCXM7OUCu6xNI)CriMX%RJ
zZ4JuJUCZBn#tYk|!m0gNu3yi-yQ_59$79l0m;1|KwyaBkb!BDN^>uT%<=xd<etG4&
zxz^^9@^&>l{{4AwFTLusE}!0xqKz9jM(rqA_>zZ#p-BijLX6}jrgPvS35JZuq@<)R
z<?ruxudB9^+Zm$=Y6P{*Rh=kliU&<8y|}pe>nZK^1`TzLv(59beR+BL>QZlUS?jVj
zH-GV(-&t_p{{J0^nUOLv3=9lD$>5n9BwH994$L%2Y<kJUpc@btHtpHj*~>xW6xH9~
zO;S0%NoB6RMDo!t(W-wxpZlswg@%SMRrQ|s;<CSesIPBt&h5NSd6Cnut&L7!agOKo
zrYnox`9s6QXZwBh=H=z(;^*K0qN=oXYt;6<w}+MfA2`T*_UV%+CpPKmMs4xnYj?J^
zw7maQ^7N)Jx3bs&T)@ZB@Zc~;(aykdAhqJ#&Ge@qE2d1Fw(Q>C>eHKa{ysC`fAQnv
z<E0-SINq&%J{MH;zVuPX7zST9`OmQ}nU_r}Kc)1_*+zZ*_;FeBpHsQp?=Ayfc)xS!
z&a>B~q@+Mo6sqd#(i)($bC$NI=ETDf1Du_kW%$~?yu76N8FtQiAH~kVAfA5nf8`tz
z<gkOV^-gTd1&s=8hp!6>4V?;_+<A9*_v?Gr@2@iR+bFajPPDqnG5z$?jt-8gQ>Lu&
zo~{RS258*wb$<Qt*`S7kV>8>!W77E{85tR%nYv5b>-QwBxG-mH_VriqcE1nH%UgG>
zM{;pb507sAzL>ez<=5Wa+`KjOvf9*X(?Avevf$cvD^_?+R`<X5?CfmI9SjT%KV&dd
z6a&K#M<-|Jub>IYi|+EKb03xKJr7_yz3Iw@3lEy5{v*v}Y{|Kuw`c3F*xhASU$2In
z*8QnC+?rNUz{tR0(1}@zF*J0~u&dn#8b_KmX;Jq2z1K?m?t6K8U7DciJZ1j;d@EMQ
z7kK6w&Pwp<?XVFQ6}`2ia4~4-zUO4MlTV9Yo|$R9YSpTs@9*x4%E{$f2{JS^9Kn`C
zTrFhyBB!agA70qf!m@Pva`S&jjvSeB?z1%Lo@`LSg{}?*HK<DXm|BiM4y>u!V^#8^
z;NVx}mO=CW&sBS+tjpGPb$6%U-llUpC=)#YSo-XY<k2HXGEPm=oMo0f>tzT70~40a
z%D^BF+61@rZr;?XQ%^qr2x>9+9`4(?aicHWrRuM*QmwA1yY<Q3e6!cK`Wt8tvi8@P
zz?hghbNtdLm%@6HEDXypuiSpG$~!VLQamPpV^Zs;O`D?r=-$tGw|)QLwQ*H1RnN{g
z_itwB4|8&Ay0$)k{h2d9o|lySZ5Dw>rf+Y{HICt8a7f5XMQ<T7Ffbg5FGZRK_f+?r
zGvWB-z{<*<ck;G}t&Li`XpvInw52Cbcr0DE?A6@zdxkN!Uvuy8i=CEgT5XR!9J=s%
zbQfq1i~jyUo66qZSvgtV|CQ5s&uvE(U%%fKzIorieK#H18dN|7O4us|#GE-K|G>!U
znnp%Jhue5BZ%90>;u*I-Tvb(dmUa2MZ8<j=O`0ThxOE?Bt?p$`#>G2!M0~$jy<SL2
z2sBI&Do!FJBRAznuMS@y)-PvUa^Cj)jB{UR9&YD<ePN+<@A}oNRz3MxG0V36(GgBi
zm$<O7aNn8F+A=W(h3<Va7uRmTS9S4g*xIO-+qPY6cV%E;5of~~_+nsK=a8DZ^iJOP
zJ9*nroj$#_{(qh2T)(exZ--}QW-j~uAf1bgYs!=<OFn%nx_aeG#>GXhRUZzrPn|h)
z<$1f`KA;_D+w<=Fr2jf2oxf*c<mR-Kn{*<lE&cPS1~e>JeQsN>r3{~L)Rq$tODjP`
zu!e?)w|1AmcfD>a*B_%doxhubfkO{EFboSZFdcK`=H~R!z`%u{J{9e}n^$QgCu?2i
z^Y-@ka4#=#hvdqY5LH!GO%szVCF=}96}IYi-P527QB+j)>0+h-pqqq5MMO@#ELj!0
z`txF&xb@+aN*?!`Ynhve7e6}_SXQ>}q|baw)2t~~-`;56-ZpjW)TPJes(oI*eCa!H
zqmK8(hYxqX-F90<RyKFV6&=t>_nI|2po9wQ%6@-$S9R|Hdmfi2sd{foI?84H|IcSN
zVMYdy46J@}adBzc6Sw}+<Hu8H&01wy{7l2tG}N~Go5|c~;YmqJQtkHosyaG8%<Oz2
zadGn|O`cpEkQNsaF~iBpNyT&G#EDs#m-X)Z^Xc@luX?e&UL0s-UiPU*Pf^j4laq7O
zl3TZ;c;##&%<q;=eyH{T@Ilt;-`;FKf9ml^4P9N|z182RrAGcbn_sv1@$vrG4-Pi(
z`h3pXH1(9o<(Ui&EIREk!J&;x)Q85$>!02vA|<tI!v=%a_V(4WyUUhs{&Nnr(c7-}
zmxhv(Q@_op4$y$t-XD*;L8I-UJ!ms#te75G<teP@GvWB-iw%s-Uk<X%&p7w3^T&^h
zxA*q${#crnv<NiaSNr*_`Kr~cg98I6K6><sM{L&T3(ow8HFbiZB$9h;OJHW^N-_Po
zH7{Od?2OTyYgOv?@#Dv;zhAF!EqfaU8gc`>9eW>=p}`(B#eV$p#M^JD-F|zmPu4ml
zK7ReW*xg#Xy1pw{uJrQu4o*s1B-1yo+W!Hli;;SI+R3+Npp`Mc*H*1wJ$2r^b?ovr
z0l~}tu7cX0`)YrmdRhb-DXo2eR6PF5pP!#WZ3eU4TQBaG-@mF~_mR7`t?kq%ovYWb
zy*g`t{|Ym|O@h_cj#aC)bR##p%&+^kGAk?V%lyTDkjc-sS7$uEy)VDret#V+x0uJI
zpr9ZTF|lQ(udltFoxktm-12)XmEHSRY}$0GK$C%i!wqYiQd@t0HNX9z4JQMBVa&aj
zEIWVn=+T!a)#qP%a&of%j(=|jzF~HhF6U2~I`yS~{m<?>e#_hV<<}i-W}oe6v}nZ&
z4^R{yei+a%XDcEqT6*yLsZ*zFV$$T;#ZAm>f0d-Bq-dzBx`GD8Udk{qG)ZBrl<g19
zGR-zgKPLk^+-6$p%7qILmP|U|+S;1=>&weoX1TXmuh;+oegE~(=ku>$kFVGD1Wh{6
zt9qsR_jUaLPpQk!=iJ{Ht2cf1&D;;-MGp=zPMtbc)7ttrd+NWVPm4f9N~)@=uP!a^
zekrs6`Xzq70t=Z<I^KNk&Y<BhfB*bHouJhK><kV8i5QJT28IVlm3!mf-q`5;^y$;0
z-FH7#*jUy5*^zTQ%)_JO*SELY+i&MuU4G8SBe7s__4lm9ZM>i{4aoTG%$YM^-Q2v~
zEdQR4C#Z>bul9TF+nbw@ySxj1USjq2T68{WBx_R1pC5%sj~sci_xrue2O61Y+eAl1
zta$V0jaX%YV@Ae`xVoRIw!dC1UKad^iCsMARwFa}ld|2RVPR_h$3ZJaPJ_FGH*VZe
zV}7}}>Z{RQZUzU3Z0t24=+u?G?Yj#f>{+zP>Fd|8n{uNkPMqlF>6s~0;p62MG}|oK
zM_t;m{$CBKoB&nPZf<R$k%`Rv`)akcwJ)1qk69cZSLq5`(6#*Q>+9K1PE1srynfaH
zJ^Gin<zBsdb?XVm&)zTZ?%oc%LgBJxowBOx(@p$(A1Z8SSrjI9OF6v1ws!We($~uh
zA0P9y`v3dp<Bul)>f*L$P3`LHN{O7Nq^t}o_{#599xpIuU}(hN*m`kcVe^vD%ttnE
z+$d$3<T6>hO!u@=%nNzKW2>H^2`;;TKawZ!{2&Zk!2xO>Jv`j5ZE1P4q_0pWrXW>G
zSs664%qwl?GwI3Ks?eaIMLUb1XPus=tEH)F7{kHf@E{3WLQzulowcN=hX*vdYi4$>
zq%Xd^xA*FyR&L+)1O2ftuKixILSyN&Wvl$>+jVt!Prm#z2h@4!>h7+c+QASU8L0_b
z{qgBj(cAm`<NcNggU)h~ikkJ(hJk@e3|qz#Kj>ik;qlFVwYzmrXML+HDcJ&=w}_3s
zoAcJ`{Nhxr>Thebw6sFv;`FxP*6lwIy5VPK?eA}1o}L$vbP9vQdC3yc5{X&oSQ!)+
z7-Dn^85lm;g65zuUc9KKs~eh@w(O<M{8J}SPE3si^~PoR+KY;czza2AZoMA&*>P_D
zk2jmoZz+E6=XvSmWOY@~(9qDXo}QdfcN&@5Ywo3;dU&|qS6!jO)y3t+>#tgNc5y3L
zuAF6@-WL=ce06iW|K&^u1{PUtO^<!*x3~GKO9Tc5DYYM7*w)5oDZ@8)%9NVtzE^eM
zs=eN`$L8tNr>2$q=H}aP7H`YlzN6l3hXtSBjvc>#RawsUYi(=O($VpG`0yd9Px?}a
zfuU(q>h>%3(0O#^I_(D|sNef~{r<Su*VpG4nlE^KX_{_y+0pqk4H6H9YJAMcY(Q+5
z;d9@7m_x73;o$c7<|ZaTw9fCCHA||}MsDZbyq$ORK&8jmuU|p)t(PucnlfwFsx4bg
zRMpf@JuH}kC*%zp`2HA(OYPV<VZ#OkUKxvk%F0SFKfiB|GbKUEbWhxRyFVWet2w`P
z@0Sa$sMs-S(j-t9@z0+caD}acH5}V_?Xp@MvC+x7jR!Jg_@lL}i!1lejzIT*xvNV&
zCqF6LS@P_RWN2vU%Ifd$xcK?a=W^I@s`!|s8?z&TonP+C-|zSJLDMp;R;{}9>FMdK
zYopD3<?Z8se|rn6q_eWKLG!?j%xn^R?fauPr}aKNGjp+S^tLTKq#rRd{4m6p$_ga6
z<=z&%vR(hbK-~K9<l}vzg@qe)Zcj^%geJRlb1WCnm?7ai)5!JmGGF7lT=t(1aqDN?
z+>~0h`)=0#eYKOfzIv6lbouhv2ifJXTv-|X^=f$h%KZELigw1_+K|}1FzJWz`s=G@
zt;<&I0k3<N>vuoiFF!r^HfUwg{e87h%Xa&MhS?`znK@u!U~&X4LHsm%{)_VczvqHh
z-(R+@OFh;j`RjH3|5dEqVj0)h#s2#KTgchj*|h3Q#@e{Ow-OZpTs+ju{q@6PesgKN
z=}SOE|Ka<8O$F^>^bA_=H}}g0Xa1Fo79F}i^MkOu-<%7#wq}35eg9t=GaFBUi%W}<
zk<phk#^+b8S>xmB>G|vL`}*}~XPdu%a&j_gn)L(o79&~YWD8*naDWHG#l&8L96GQ1
zo#of}_v0TQ@4pTjGd;+7YZ~Z~4$!*Ryu5XNvewsf{yv+Xf9=#%ZQdyd=ZA)euU@zA
z-J;i}rKO;iA2qVFvY<h!pGv%SE1cW;CaK)sCMqqxT2R?d!`3$T<;$0^uCAW0bJ_@0
zCVqH;IZ4FOaC*YjsY^k<_-_4u7qr*!QM$ct>g?I8U%be;TYTOYG(HBNvc24)?B4g{
zT6F&27gejn)`mn!zdo$Q(q#Q^hcjs8_TAmxv)5vs(VWR)Z<KjSW$)i_w?T95d~!A`
z4jpm=RhO^s?lwRCoPpub3C#Il28IV*C2wv7_S^s40a{ZCDsNp~T|vYBwcqb9@95y@
zl`{3ZdGn^1zrXq1SH>7!5dn^8=jX3K*v!7#f4<$R6DKnM^u4*g-9I%ob=R|5*<Vg+
zulKO3m;UwZ>ub}ZCmxee8e}{?)VfTVfg!^Xt81#cczHu3B4&WjYrMTJHF8?m`na`?
z%<QY;_t%N<xoIf@TFJ~`|D$<Z{{4GD?rk?0(vRHaq8+y8!jF%SeV-omS5;GcHQC=T
z(9f@rPu6P5Qt#<mFE1^%DtR%XsHo`6$K&$ahK7NYu58PVuKn}zxR!>7K@4ww$&(X;
zmUI0;qw^(P3=ED3H|5?olSN<fz`!7&;WyuI?NsgXRU0-0%r?&lEiAvV(0S_Ixoda7
z+XZS#tqxmzX^LiW$=%ZHnYXv)E}Oi5*RNkyyz+K2v(58CTUn*q+xzA1*EO^AzdC3A
z9yF<<z5H^fm8gS&Rne1<b^HHSLFa^*6*Dk!RIJ5ZL%_hm(sXro`05QC0^aZYz3$bk
zS69}@+k<*p$;WyE+xcW?*;r>?(YSi$%8QN1<%~mKM?-rD({!Vkf!w}rTNr4*sHSGm
zr%#{09AM@@0V;k$D{2ZPB_PXCAejhC?%+{&>j}uoSp#ZmrlzNB+u8k_bpC$T>$RX!
zlKxj`HtTrv+k9w{t9Zb8S@T1%rKRO29q(>2-ARWZ2Kf1%E3Z4YNoVi3TiJFim>C!j
zY}dKHE%&k@)Nmx~U*6?qzEUO`6JGM{H$-nTvoy?@Az>-Q2TGx9qqm2FC(3p`N!K}j
zX`yp_O-P4BXn6Q?QSGpd6B866ZCnNhCOK@4g&j$J?atFuK~sQ=ijFT|zU;L(G&EfH
znSo_vE_k)V%@Q^S2FGqjjJaNh2JRE*&+mT(THv^6&z{u*kL&qlEEKliUb|_NQKgOC
z+k1PXx8<JRq;vGxF*8Yz_g7a>e;LEzc;sQhiKj)Ge|~%f1z6s$mui<i85meZvDHg@
z2Obv0fM+F~oezhu_*joJJfo$h1*(%!hiB$;+J^)NE(Dz~@Z#cPP{%SxZ#t-=ShY&4
z^!>fqhYuev6MmT9)zuXe5wYUZr65xilNI&<|4G@`?RmHNd)(Ii`}a!Z7#J9#D`b(P
zgn@zK&x<{A>%F|ZOv>NI<lfx0)Rq7F<3oGm)*tJWUH#}$(#>tUr#FEXbDufmGuN`%
z&Ct*g)WTopJ3Gxvv~Cq*Zhl+d-BlAN2=Gc8xja7Bd--np{k0P&2wd)DU|?CIZQsR>
zYAXW+!-Ce8>(^hOWt#ovr270Bejl@^PMuoyxYzv4gJyovGD~ImzAJsQ)}Wa+&?GZx
z+y%6zc>lkz>!UU#G=k=9>i4G`o0x<wcJIIT>gsA<u|xMkD{Vl9osC@os#UALyxDwy
z)uv5B-|v>sU$^_6)zc?WR_xhxr$mi`fw3K1^uHGn5?XX|vHR)AA7}V|lukcCZ|d>K
z7w_yW{@NY?$7!xr=_TFmcNQ(5Ul$c$`*kX44wzTk?8TFllW%QIZhv-mcDj{h-7?Vl
zteS67Ufw#Z@^^P270<uFzj>!93P77@xwp4X&Aq)z$9r}7`fCRonXj&ow|{$Y@9h#L
z1_s8(Q?ZUeq(@Gx`toAot5;c<HS3g>l$_$$hkyL|(aYEO>Kw~rP+M!BZS^ca=LU<S
zCmnfvzh3KJw>|5s*Ve6D?R1<LfM$S6n$~7xP*A{}JYirckX+_Fd)dj!>e*jjT<q%a
zH=mmvQ(L=tj$iuYwTI!&PL>HXW=OofyZig1*K+;tdecw0yK;zt#_SRk7v8J=9((ob
z)s^x4>p+_cK;05PSu2yuvMVbBSFK!mF}dG1ZG{*^!-2!tMu1aq>?&Oi+ISMTw<`0(
z0!PqHjHr~<Ezs&pP<14s^<{1H@xGIfKc0A7cKU5u_Qyv@SFK+ketli+)M?X}UAYnh
zT8nLH7|7RtxJ2&{`b@~V|B{oIsCrKWEgOVPg&gwll`wSLxN&3EtCh>A%$@spZhO-m
zc-hFnz)>?T_x84z92n`Fp}ySG`3j_$&u;qf`0KB)4)fdR7)`1B@*=Rcy&beJHZwEx
z)cNz~b2;sU;^WspJlvlB`Ptc5cXw|Gb=*Kz-H(rtLDl`cJ)iyd{(iT+$ZGDg;D_m;
z<x-B#Y%|X>FeqeTYiBmBPC7fw6x89^mUHvcqV~^)h1+sL>kvQ<kyWc!mAt!S2`V~3
zW2<r%4;oKf{Q%X5_IlWgtPjnE2L^;47*3&-oXiXkA26q&7#JAB-yG=_F4}#!m-)G<
zsOYNo>!;`5?&|3Y@$%}rbonx9plQhx&{nErB}RV^e0h0!>coi)r%Vxvt$w?8S+RhE
z4Bv6l`eU1POifH;TBR5mn&h!n0n=ZC#uz}GD&|_3zj|_V@~#UJZr+j=C028xZM)kR
zIrHYtTNk&t>f|P!!>u3Ok?M?vC%>zysT~8AnG9H`AyPH<^sepwes6V43rlKB3TOoQ
z)TvXGa&JfNt=bC8rPc3tx*MmTGnxBJc<0WYr%s#*sH)nPl$`AQT)_c!YE0ht=+xBI
zPZc(x)k@&@zqri_h9CZ4zkUVHYv%3w==SyH<>MuM3=ED~2L?_T9G5L$QTqCtmcD+t
zuWv7CbN1KQ*R_p}gF)+ce|>+yerNG>Eo<xBC0YUoese4o`;RaF1RgdH4GDR1W~T8b
z9dFQxh_CNe>-T$-t%U22Y|Gu6dpm6Xo=;t%DeB9X3=Ax)u(8mF|M&0xJsMUkUL*5=
zPO;a*3P<O=1;W#^R+u*PG)XfZ{h+RxcaGEd*qT(iqte3LB#!6xoEBpaWV*@wxk>f3
zo7gos;eR(+Roy~7GG#4x-e8SXiCA|;s%2uT=fWwUV_t0T`IysT^X)qG`tTyXbMI^X
zKkdulFrWV!yfJ`*fnf!^y5Ag+@bGZ0sa{f2Qj=5`FJA09>DskxIX5;aMsLs4H7YzL
zAt&dzH0b2}y6?Le1<!aeYxeBVQ`gt1+W$Q1U-aX{L(nO?H@D}<i|Iy9`TYF+^YHz@
zLN9ju7%UCa%+1ZUtp1jBQInzIbe0CnjLHHzpSf11y}iAj|14+CwW%yRH^=hxzvuf^
zER+}+ct3l(IEEOfojGygLO@`pu;1D+ZL3DBkKb<Rrza#RFf%h-7CrIsn`<@IYw0BY
znupvkU%b$;>gRmXZvQ9IEbq>Yt=ZR??cKZgg$%=vrxK8r;Lu{^kMynEw~HSg>HL2G
z{Cs=+-DPi2J?^)kcY3=1^6lHrzuzhLZ)`RA7`v-PGk@RDv_2WjNsWz-JbZl5<p2M0
zU*<o5-qCLH^uNEpMs7;+6w`~D0lI{!c;<q86_0zjY}u0X?#|B0eKnO)(b4OFR%=f6
zy1B2m+Od@(;J%lsy*ez=K~5=%J#YWNCa&UP>l~X(qsi+2=l=cuy}9b^D-%=Gr6F2R
z_kO>3T6_JTN%{4^Z@VrR%d4ocD8E}8&L?LxW2$zz*xbV`m#$oya`EEDE!(%JpPZx`
zxu>FVnoi`T^Y#BeyDkrOKlSue>G>&MOM7~Id!2b1?o{!hOvn6l{`>du&E4hsT2sB`
z>V7<26R~m8izS?iDJd%U|9_tU{GgdX?O2bb>vMy~DW{)?XiYsc+gx8(Ru<%KD=RCb
z;%8?TU1nhTA<m54)@$f5cynXpnR&L>mzVqRe|K}?!i8VHe_tN8w$J(Ik)kgzF4lbP
zj@Pkjwkr7d=O+&zUm7Gbe?FG~Kcib*|JmjF|GtDafBE_O`TywcG0Y4f{+~w~CVQY9
zqBZr+t*zR3@80#CRQ&v0>a#O5EejqvfW}v@-kdjYUdZaJJ-xl66QfoX?VNLSbNchy
z_y43_TN^$7eBHOruIhp6Ztm`%m)rk+xhnA2{r~^I*E|xQf8tOp_vMQhCxWi=najyg
z5dG2E0Te|rEdTKE_kUNjw)XV&+?l5Qx&QO6?Db36uGO7wp6?eO9c^W0_32T!{<Awf
zi(Qu+9`v1MqS-B`d+J!P^yc*Q^FXKXoYt@V*nOw`e(le{@9XEw|Nn8^Ro%!@)}laR
zb=X=jZ*OlYDXE~9A?qp`8U9P61SmtES9y7P-OtnU&(_!f&EA%Oe_qtuX}r>APu}f*
ze{Pm(_NMCZ?_ze9tbF04w&3E$i=Z&Qy)8F#Z&m5L9gq7;%F3Sc*Z**ql9t|_adFWi
z;h7EJ-rStLzV7R4NjW*c@bK_;F*_&a*F2Vf`RbKdaB%Ru-S79=e7{rdn$F~K7cIv&
zL?2eS|9R5p=ab2mpH8Y5zq+#W%eQaKmM>S2|NrZ{aqg`xHosmhUKzGJa#u;_#g!sY
z=9b?(dEkHpG!KC`P4BGun3T0OYS!%8n=3v((uv(=;yqpO?4ed}<H}D@7EPYnur252
zq*iY6XD22qTh{-pDSLBc;`^HC){#4lQvK%J&2{Y-dulxYr_aTi3<29w6ZDVz>sPK!
zSsA=M?bH;_l~=Pgr+U47{rdE2{rz)Txy7Db4Ua#&_xru*61B%`mM&HG3|f8FDEr!)
zlCrXW_7?N4%k#XJ1|4j@(k!g*mvVZV?#d9Y%#0t;UGhpwOgt~$x;2Ye+AQVuwY4k5
zR=cJ#Iovfu>FxcHSnfan+{eeqC##6-#du5t<><3#&xX&HmXebCzOD1w-SYcq-`(AP
z`SRt-huis=$LKv@*e-Xf_`L0OcezTHr$v^(zr8(u+24Nd*Vosdzqq*ARo(d9zTbD>
zKl6_N6*NsRc2?x(G|{=vb7xtVW=Tm)PgXg5_Uue}nQ5GM=0m;_!=09(wPCA8QF`A7
zf>TdF&CW~tcmMVt`#1IT`+IwP!|%0RyncQ9ym|B9+~04ntgKx5ppiXjZP?|jSHJ%2
zy)OUdlDGcTPW5>wmU>U;TEY4%*4^D*OebOjXbZ9DBvA49>dMNWU)R^qJw09j`RVw7
zMQ!cvpTFJC7mwj$_<E8Typ<cCcM_kUo9n86rS;sob7y9mYWv%M4Ow+H>(=et_TT>O
zsr<Yt@9wU`Rg2?z`1zlMl5~FE=h<swc5ZqhqqgDPxpR9y9OAD0_wzX@eb{_HV+=~z
zvu4i@)|&e1UiJH@Q^Vslt%Mm~O+#H>wL`O=PxjQOr>DEmEjY)^&;NYg?sumSHna0y
z*qMl>*i&Ix5zU6;YKMnB7k*kC?~^_K=H_PO+FxH@&y$ss@~W?|Uv>4B#T3Q^YnLxX
z(ZKNP^fKSsc|WX|25FwR`~9YVA=?gFowz*~yUX5!a`2=lcXk%fv@A~Jld+hPdU{%H
zX<0#m!Rzbm%^lbq{!d^;sT$3nxZD4_$XkD$VeadhX1P&i@9xaBEPf_3_Yh0S>Z|K2
z?Tw5kZQQuAsf*#kwNO12tqs45o}QX2T_@T3Dbc-OZtttVQ#6A=t<A61HcmUEv4Vr4
z;Rs5B+AzD|<D;W{{{4Dg`Fid4F29B6K#rdO`_A)Cm7kyed8%KpX~oXaP;ZEm-XGXs
zyKw_l$EFn&Y<MB^>P+_fz0<aB+m>^0k7aId?#mZ1PIT+<1D%Z_I+u;1AUYeh>TmcJ
zsx|e}wQJKhr=J&_>ooV}yLW!&<>lw*+0LH-_f7iCw{Oq3@k)RC`@Y_u-|k0(T>YPq
zHE*-yy_1uZFRt_vz?av|7<NpZlC?Ez?F*D{!>jQ8{CrTm0F?W{?SfY~Rt7J>bo=(~
zdGqFhvg_q#zNZ)W+s(?_I%}!-bg{Yaji;U#c`dyZdOmCGEz|RMKWcJva`t>;crfh|
z>L6v_De3$@6Q@m^c4n@%`RVEU{@K~tvu4d&XBDh9byMx{Z%te)#eIE!XIhnJE%TZA
z>0if=_3QQZ_x~vZWvTG^TGQ|Ms`D?-6iEQ*6NUr1hfy=oohd~-YwjB7DL-4h=l8qa
zH}_VTS5;Mk+FeslKehRC!Fgra>dGe*-GlU|Z_dBJ&*tx!%RjFyx0|}yy<coD4?}^s
zF-p`i9E**QkFTn#+EoAlUr$fZlSXzqkF8O@;o;#?QBmtG|D$Gph8?vgBB-Opcj~OH
zt&Ov<t+DxfC3t1n>dgH7|2IB=es=csuF}`XR`M}C`1TYvh!XC|T9s&=p02NN#mvya
zuPKgVpu=D5f(H&^Yon%4n>NkF#AHd(%9zhh{6=={3^Qg(b)hU-U$F1(&CTllw%;P2
zotZg#-MV#eZfsP(d-v|jt648!zxIxfj=r`gGPp#I_4by`%e?i=L$sdWOrQT({|W=c
zhd{5bQES7X``@6&)7RJke!oAz#B*}dlM@r?*w@>Y->XcAHnE<4d3iZ<OGe<f+}qQ#
zwnmj`v1&~}ZT@F&(8?(rH*Wmz#LK`S|Mb}Z>ugZ7z?6K!qa&RqrKL-QRxVk%P|?%K
z%4(KMW^OJhL2oL3eN9PtCd0azokfTB9~Uz;d`w4~FFOEEC0NUMNITfaL0muX%<J|0
z=WV}Nwfcn!1A`rUcD{7)-aKJ-zdir!{{8uRb8B|EUi`i}6DLmm^6lHRdDZVUH%#bU
zwsE6j_VsmVA3R97sL8-k(}7m{EZw}>xVE+yR98=WGBbVN$%W4Cm+st|WBqQ2^54II
ze;(wo3n)+(_FNg_6&)RYZk}y)2^Rx{e9)?^Sz8w=gM$G|?AZF{`}g$s_x7#~(W?CM
zuzhpV(XK_4XCzcrS8pzSd`!l!#^UYUx313_7(VE;p_He0HY6YKOa1od=1jZVU!~{y
zczKuZ-*104t5oLH3i12D?|uJt`~E*O(C+cgH9tRX*|u%j%9Sry87~deyuCeNe}w?U
zgKsIQVavNZL<<xiyLRuMtn&Qa+|y@f8W%q}(5Mr=?aivqwzjq_!&Xa5OKU4l<y;k`
z7ysR7Wyq&;W(I?E=t=Nj%@4mLQER77oG6%__%AnnU5us`BSXXg!(Z#wPzoIehKAcs
zsA0>%z~G76Y-wnc!PX2k*oSVd-CVm`tK<Fh{*z*M6exNYeR^`z#N0f-G%q6~<Ie3F
zKS1re<8swH#m~-ohKGlPT2AlYy}OdN^~=|<pvG$UwKbrs^1-%X%y?R%|Fp<*Y0%46
z>06`T&PtcBu`@F>i>tiS`1}2S`^jp)rzR@97ybM5^G@aSxt0|l62jKS%)GqZKmFn&
z*PGjNqgP$cy10^oVY{d~N>8icaM`;%ktIx}?~Zf|-`tey4enz8vn-a9mGzypW!tv2
m!)?4bca^SYv|>15@moIDN0~E_<<@6V;_-C#b6Mw<&;$TK`k==E
literal 0
HcmV?d00001
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-fbeta_score-20160908-100019.png b/Code/MonoMutliViewClassifiers/Results/Fake-fbeta_score-20160908-100019.png
new file mode 100644
index 0000000000000000000000000000000000000000..f19e280a9410df100c58eecd2686897cf2d2e2e3
GIT binary patch
literal 169262
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@u0ZM$osNgc!gcT8UI6C4GO#8n*ZV$%AyPVh}<
z*D;Y^HMK00&MwuBYTHz@gt)Wb#CEc}hU6UdO6u?8m0p;sv*qXCiFf{5<nzDlbFTSZ
zXMcXOdSY2wSy_2nS=#1eXO}Pheh%tNcmczl20s_P;Qs@b61+wzF&*H1f!ByphhPNH
zXw;ww3Dra7*L*=yQP#+58<UQ9O*+T5w{4brK40WB?ciVKKjJgqv+>DrL{2MweQmAM
z($D(~)_T-0s}ifIu3j9p)JyHe#Jrlkzxf8C(xQ@*oRQNCUtCZWe(H1k^{sjPx{B2o
zEvk;aJz>$VqNiM5)Af39Zcfi`k^U?*JylXSYKunEytwanE`?tg`<T}K$e%Q44o`M=
zw$BWMg-bSnin6TuppX)I?8(W=riZ*Y#fiCu*LmK4e7xT<=?KS<A3qKpI>eNgmgeE(
zqw_Ln>WWFPxc8qsUm9C#tFF#2tnTM>bya9$W+tbxv2o7*eX{2H_gZvLOPFK?a6XyV
z0R<~k_U`-d-U;P(ypZ3dBmSdbQGS!>q>vuVr|t{?pH=a!dTVzme5!inw2QmT^N(7r
z>Q|U;miw!#*nR!(M|tnPW~q3pS-U%5);xJqd$O8u(01-_G2Nh^#lJ4h7WU;yUsd!~
z>(zYC*A4s3a&NT=D!VPnyu7TSprAqL^o#rZ|7)K;{9h?}>dEj>y?Arg!0?VQrQhGh
z*8F@r{l(4A>Z?LlG8r2ipV-v%`uck5xoIIGB2uPVEY{Z67FJeDCMF^mFJ4qTQ~L3z
zdEa&We?O9U?ArCHncwaLhxxKxqg4B+rFr7r+V$%n?ctvN;^(U4f=^FRKVJQQZ+rf}
zpKRst@71av|C1jU^uG1W%san!U5^gd^0Jk*tuop7_gnOjpFbaNK5uvUNT+b%ww#+u
zC!W^#PtvhopFQ(x==JpT^LjOdmmN5Kn0c{#|1pr7y;Y@O?bg5kDIf?1qUxU~onwG<
z1Si_5csiw|sI&+~-Tw3UueXBxm;B8|PrYnve{ET^d7;N7m7E(J80G8#7)qJtL|nS5
zSf%ST-%j@NvEJtP_T$?2-(G)sxKYJ(hDoN-y{gx`H*Va}$Wu4kx-xjVlA)pCwr$&1
z1T19Ii`^A+DN;%6%7=%CFE00&uc)k?S`yZ=WsXgy(BtF%?K-DFeEitBc(L-O%a?oo
z@~^B2{PApd{)3k<JIn7?vPVWnM(i%rwJLwtlfVD3m~%UyY2v$;2JZcGNA>srY0A93
z?BJzKn@+rp-BTfW?b<c96E|P$nwf1|vN>VPp<|q?hJ6yYRVHFO5e=Hb%U=9p)c$q*
z^{==Ufs5UCRD4v5iH-HP(q8Wp_{y`S#AH?I>bBh5+h$sXf5~68dY!ww`{8rv_<nzT
z+dOmTOe-68b#`(6xR&PT!>iAz!9wt2cBAkGSW<nl|JaX@kG-w9TZ3jP`2UyH3Rw|w
zDe}U}>(|AvuZumrB5-lZx+QL3_Am39X`~Un%%@Z4cWK6J?eKLy_Wyn`UtaEie2Ql9
zmTmj_DwovH-&y>8ky9(zhp%6c9&Bb8l#+@91>%&=n~mqpo$GBS?b0P>lF@Luo&T}@
z|DXIhxw(Q;QduSS|8Hze28Cb1QZG>z6_o?`?#UgvKiU8FwYA-Wi`^CmFZcU@+5Xsv
zRlnWu*M65hbLPy4Yti{LRran5T|G->?)AC-{r;Zm2QylyZk+UD@pSEQzO~WYkG;CO
z+A#Z?&W)Ql_kObZvt485cc<2=+}_@&|IhrzFS2%?in{vZ$jxbLXL$cgzg+eD<jIo-
zg@qSq)bKGpd-m*qaOnhCUe>VRxy0B3R&s_2En2)-P(*|!Iy&0I+Iq2jzub?<{q`b{
z?W(`=Twdnu?BKwVlbf5Ep5CtJJ1gPst*ufYm6Vh&EOO=kn)P;*j`OtC88c_DR2NK1
zOG~=8CNksZCRH0-+rV8VnLBpxUYvb>okiWB9gfdGe0b>GBW22Ub#-|A+O@iK=FAD$
zTUF}f;-a9b>8bti-rnkqJB!n&Xa=)Qn>Ovkr%z7X^X_h_|6kWz;l!a6wS|LM+N@>n
zT-lu5+>09$opqwNczje2h@5tDkt?@N#RrD`{eR80LRK&o7Z<OI*m&qcc7(*$jZ=7J
zECe>`JifLzTI%8L?fLGfr|AantEr5LiaK=oF!R~j=Eo1Ua+^Lf&A%tJY0b}5UmhH6
zo{%azS>6BG&f@16HYU4USXv%Dc8m?Aa%1vwk<Uf{|JAy<xGeCQX|!S6Ha7<chOjje
z3n$J~WMXE%xHUUm#<GYddRxxL>iuih=zy|mU0vOVjT;-Ao0(^s<#zE(n`Io`TlrZn
zCGyw;$L501&wRhUyDOcSm$zZlCZ}dLUIAIzwVy4rudQ*+$k3QGXHG(DYU?c1>_?~d
z_q&9JO}kgQx9Y3bu|C;uHeRU%ckjxA!s^?%W4qt)>)u`dUhAE(sA%hg1qwTM?>>C$
z6jxkaT*mcvve(wfufJ|M-=?xjGkDnozqwYRLU!+7TdnYQJ@@ujKRz?lSgLTketh4D
z4+TGd{W^5(mJ}Z!9|s@bvGex-*UTvU{OoLET3XwjIWj);Y$T^@hqq0gD!M9sec$}L
zU!Jo07Z<sH`24wf>sC`6TU$X%$(2*X{#6(M{FGYq`WmmEp5BJ7TU|XoIFgc*zF5Ui
z-Ch13R1i0;U$3vDtNZZPtFCpiyB|F{Ihk$g;!Wl6<4$Z^^Ho`~u(0rz*@vgqH&%!1
zpV+kKYFO;P8cAk$zLx3J#X*(jrqt7m;`i6>D0<p;t+4cJCBqE!e7UTvt5~(QwL?|}
zFdlB_cTY=G+p~9X;L0G?xzCFp9AIo|YdduBo*W+^--|0NCtu?_zey+gXqTvf(}CN!
zqwijO?*IK*uXM%px#gg28xb9S_~=pAy1KfG|9`(voHlLQ=O4c&sc?b}-dXh2ApM+-
zin{viz3>12{%)9a!{En{A1mfNCMG6Y)c)EMc4x&3jjumn73YTdTzz)@=+TFB%kMd^
zjoSL)!2^cu?CdKmgV{letXo`v%OmNa<-8N;&g})2tg_Z+E!(%7g97H!qo!+Xqm#eC
zyUY4+_RN``{B}PWM72U1rcM>jy1J^Bm0RpZPyM4KoGtC`i(_^cX~ga_*|TTQhkMoU
zAKu$rUG;qXiri$!S*F=+@$vVSmNPR%Z_hg#oxis=>*}h5*RF|y>V^3Ic49ga3vS#u
z*m8fd%T+dss`zW`<NKHS&OUVUBB&t$@cHxMFE1~P&M)5o_nY*uFE5$p<>f({=k8tE
zudl8iJ~2^w;_TV0zkk*2S@>0X|B4kFSJp<0U%PfqBX}7P8^2r+JHMR9F<)=*!#fHe
z2W(FB1%>Lxi-K#Twi^AoncVT`{NC5s*DKrD$gEqpZo~HN?zgw)7XJHF$>8AS#dWXp
zx$G4Ec)75!u#6iU6dyf$wB=Ip*V9wgzQ*mVk!)t;4Z6SHDD@Pm(GaD5<kjW-rb}vd
zJv^`QI-k1y`~80Y$Y~pskMkYfQup_3_=!zD^K7fLTBJYaoVcIv=i%XSyifM(<i?Qm
zwaKp<3~RqUTF3nK^z`t4@9wOJhgv77aL%v)x3lV#B|}AJW#Wwui4`9ou};&CUKSqp
z{oUQePfku2l#y9er&d`}u>h0|D?ToIWcRCY_m_|P66@{j{z%L=%XONp<{PlDrgHAb
zPoF-0xEdb6Fzf27SB1ZBY)qawckWuz@aq*fZhTy>c$}^0^=frh)x?8MtUu1z|6|V1
z&Yt`D=btIR-rT%-bB2Ar-K(ps+0)b0Z``<X;P`R(k8|A;K_;FxzrVn(S8BtiO-;*}
ztK0qik!(}<C&F;wzQ^kF^73D|hV6|Hm}=;-zmO#%V)r#kvCFWv0F(Fc-&g%T50o7)
zUJT6sl=A-G-j7dC3OE0Lyxf1jTSUZ+U$&FBZ#Qq_m2Ug}{eAY)v-Wn;dnye7{P_ba
zjy9#9ess6|zH3_Avbf_W&n%PA{AN-0df(cx|MdMSn!y1(i&7(^q80@$^^&l!+jFj5
zu5HW0$!fk%OTDHlcnVF^k6))JzUnvEf&;t$9G9<OQ2+nmihzYpzbu&9cmi^aKY#Bu
z%e&Lz)++@nclGr2UR++@@A%lu`Sp^0Z`=2MeUiFx;lfwd%d5mc7R`>7d2h|VDgC@$
z$%_k&ph9%Z7MG`|rW&T5kw{5N$vA4dEPnFz>FuuFVu}_P5w?CSgO+l&@klmhUtg#B
zF8Iptb(`|;T5ZX>DFiB|Hf?I^@8|#Z?QM7PazD{s`GtL-du!Qc1O*q?rKzf_W=`Gx
z=kes}Gk5iS!>Z0NyB>1E`>bE=T{#+kXPYHnUl;r0-d<}bXXnCiZz6MUZQ(2|EVQWl
zqOmGu<)Xg%6DKxaxDYVMx}2}{^|hl94mMAmKE2(x`rCs1`}=kjJZ$>Ke8K!)h4bHo
z8K0k>y||~cxYX+2y?YD|-QxO>y7l)tY)(6SVP&wog{9@gYipx#?5njddwZ*Ou66k$
z-`QrZ^Nw#$KYw9~r|_K}h0JTCx4TW(i&bbjaCWx&#@gRyUtU~vuJvJ<VNs~G%x5N(
zwY4><h@LlZo`;{`v5Sk{KYl)Mzc}^uv{yUw_x)76wkDEUUtga`(uie}O5*8hx)N3;
z8htXBO;feQv!1G(nu<0yHg4Fw**PLYA|*0xy-&^wQynhPNeZ5m+-~sO|7rMsubThq
zsj1G>^<p2qdezm=FAr*wo}R9M{P+9)@elrKadL9bFid8fWs=#X=-l=I<ewdd%28Xh
zS~sVk&zdsRy<bkzz(8Po{(U!)w|5jKe{ETEZEf^x8@I%?b8|Z9T9+rixv}xZrKR21
z*q`d3K6lP-wpnh$iwlZZRs=H3*L+}{XII<RD{a0ge0`in`8%0qesfoCjSmVEk}}KT
zh>wr|^8UX3%9Sf4w&%(2Dt+Bn`}<qwS{2ib3ko{%`()<Lo5#V=-@bUUa-Y0?-^a(t
zmCek=3=Ivt<O}xae13NJ$HR7c0V%1j1q&3WXoYe;KR^Gtzy05qxz^>N>P#bi-5jfb
z>GNybUS3`f>JGlRx>{UDMyBBXJzEtOm4wH~dZQ-Ko3bVMw%GAL+2H%(#l^*Ub{4a<
z^T{||Ugj$(Ah4j%y5vQ`m36VwXJ?r@?<{)y;raafN7Li$4uZ;Y?eKL8mzH=+Wv+f#
z49dW-*Y98C+|IXQ!-fOLdZj<U+x`B~p+ij1&&@r2YO40dmBH#;vaWL7-kyK_$;ruy
z$;r(Z7rSRa{r>Cg>x?@)Kw0~WaM1O&(e2;f-cCL{%k;&?#qJBA*ZlgDxh3;5+sl_P
zGj4CwJ#^^Mgh`W{)<$nvvapbd-k#^WyX-BOuloK869hmZ@caAw>k*yS|J|Se{{G(m
z|G&Ri>yIBjx-e*|m(<%U@9ypv6cYnAB1+!f0W~6y&9yGyQ29B{#ob+5Pmk~4zkgEK
zBUak+%36tZi|IDCx3k}?{T>T47v$>o`~P*#nIkhrE7U7nUXi8j&5g#~+uIg8xATGO
z=fa1FSY6!RA3r%c8I*^rzTP=;!XxMACf3f*&L1BR^FMs?f`j2z{r&y*@?T$HKR#LA
z|H49N_Llbc$3H(m-%<FOEo^O6>%+tChfkh7xgdMZkz2Q<f|vUpUEtXK;pg-DuT2-~
zXlimgIy&yC|8EzyC8Kd)?e9n5-rl~kA(45};>8;)Kc|(vxZs#9?>XtqKC_0*+kYgD
z(;j?!dOG9M5>BhqS1r%a&wqSkqH;%1&yj=8>>Km%+w~eHc+53($;#5Q`}IPZg_U)o
z?`*Sz;^M=5tG{nZKF$X!(d_?znf$2zMPy`T#?@7#Mn*;#mix=6q^2fbUgit(RpHZ9
zqH8(Ndr#Lpy8Hb;Zf|ezl9!iQ=gph9qw1^HG@ZyMS?jU~M>>UD*PY7f+V(M2(mYS*
z%$YL+5)vHz{QM~?DGFw0V)AuA6#eGebgo#TQ5xg?+jf`7q?8Y}fw95n=H_2sU+3Sp
zZQG5l+2VG;-x$BSyIZ{a`@7biKkxrP{dN2OI_Jf1y$Yv|c9pzjl9!iHNlSawZ~yPW
zp;qpXPp8Kpx^?T8%JuUXel7fT*8IMLni|{Qs;^GJzr7Wdm+wzKJ?-IxgUuF&k62=2
zVy+bC-`&-kc6Ju1NaNt-bo~A8?Z@l!^@-2V%>^}J>wY|B=aI9yq4Iq3lViQo8CO;a
zW?fsea-PrL%Fk&nZEcTUTwDxNCnF<sVRw1{l4Z-1Kxz2GLgsZbI~N6pm)PnrTD<t;
z=5+s*)YOHsyUSkO-mZV?^5w#JcP!7$GUa~1_xn7zKTW@OAKS8i*A$n#21{&sB@7t4
z#r2PMiE3ZiS)9Ih%QXFXKF>)4f`SYAjKAG1`0^sK=IhmP4o=R4pfY^Yq(yao(oyU^
zFBeZQku|u|$jr|0=dVpo<nM294O35v965F@>CutS)@7wHE-0RvV=26F;X+X1vUaWR
zy12bvpnBu?x3{2L;?<Rvi~I6V>{zYvf7-`gucXpaQxz>Nb{wdv{q@DMrpD&h_I&>8
z>gqqAPV3LGELM}Vt!h#Ao+eT?XHkzmujRIlwO<95-4yKX<YcYOT#on2a?2iH^{w`1
z10(Z>vbRy7mM1eC52zJ6Y4T)HOxRX`%h+>S<BYp}ZOh?y{>AC%=M|Kc9GPcZZBYI$
z=E(8m%64{f$$Jt`{K$NAV&aWmrP_RQHXV)3?5j>seO1FH?apv)tMw$6#KUd8H}+O<
z-?jhWCzoRj7AP<{`1tU&@klPZUV3Y1vHGFIhZz|jK76<$VxyAZT&vbrZt<kw-`;lg
z_q!kM5;gs#=qcpZFSqs|<B@H-w;vs7Wd8B-xP0N;Tc&SrZ(o1mvDD`|hF@x%^mhH?
zv90=Y;M?2Vfjf&*dF1V6Kw}fzawO}1zcoKv!jtLj?Cd;o;>5<C#m^7jzb}7xS84F_
z$@~2@Jv}@eR)?+qa6P_$q4#vX6_K0O^kR3lgsu)tyuB^=#{PQyS65drFRcT0$U%jR
zUhJ*~m7kx166m$H(d|c$xXiJw784T_YmL)(ezipLZM)r97f%-#7AI$CK}ku@{QP`S
zXOqF?m*cX!`;ikoC#xl1TH;wySm?OiZ|;M4@A{4$aXB;3R(f~Y+d~_ZkDJuh9J^5G
zTUKUfRraQ%_V>4gr%!YL{q?nZ?_S$UlO}B_eI3@)(vtDFV20*9>kr@ieb+>6WXj9S
z<KX6Qo;`bZ)t%VARi(W~%a`mp_S3bJ{m(J!`~%02vll-*)2QMpVOgZoBG5W*_oEk&
zg<zv3d&^j0%!}E6lT;K>Z|dmjx$-Oh=clJt%Qx5jEGmuK|L0Tpv28y;Kj-$G<gz+!
zt;r#F9tnk%NU_c7=dW?pe|*%Maeduf17l<1=jY}Iw;w-xl+$z4ktLp!MLtiMIaBlB
zpU?hlKkP1l-}UL~>F!yk*{@3VtjpdAOj7CexBKam9bHzot>V*@&R_3stG{u0P69R7
zj_$4gF4DhtQ`OfjMbAkq;`i^X`1NI_)t{G_moKXO`^#xs>c+IQQoVmeua`VH(5Pf?
z9<E*Mygt!U#ZzeE!i8P8+4y8MQX<97^Y4YUUtJyU9}yMRHD!v(+8_G&+n=4C%^f+-
z^iat6;AyEFla6xr=5~wgi%nALOg!9{*}^Yn;&Eb=&aqzU<%08O%+T<fuBV$4c`ec|
zZkg4;=={B^Edrpfs=y|lZdPuw6^~U^RXIH;xp;VV9NQOP`*rFB70;4aS3Do@v#I*x
zQBhsZ9Xajj#^mE$E=^30^qFbos;nC-`Rc~T#cn?~rJin4@l>+0iP=-}(JA@%63@vk
zI;WHV{rOonH@m24(}`23E^+mDb_%AYr6s+%uu$ruo}S*J%a?;~>i@-L%P+P1w&{M|
zZ(ol|Du)go64}0d`SR>PwSRw=uC=&%^X8(|)6*7(tPE1Jw2VxS{`~B0tBU8M#KUb$
z#>T<QbAy(8ajL7UgSx@JRx{_#(~F6XZQZ?l_c7bk_4#&xzXbO_o?}(&6%i4^k)EFZ
z@yEyH(jT9mo^I7St)!*pB|B~MWaXOL+SaL4r&`qf*x+XM{oP$*IXSsSH9tRfeP3wc
zJKIcDOiWDb`K=v=$${(RY#%;*ruOUm`}KVG<?rT9Q1RUJ_uK7P8@6mQdHCXm#+|!&
zk1q9|ZgR=4{@<PrTepgSeRcIRNBFAG?fmkfXpu6_%6Ot`Z5?frdn?3al1fcYjmf1z
zTWK8~og<CR>?YfKrOo|LY|=?PJ1g|X#!yi2HPk<Jo?Y##h%{b7NlDF=NHOneI)asz
zm50us_n$F)cJ`LVtBR%U>-HSmmwRiA;3l2!%*)F%TjZ_Fd}hp^%^e;d{_%Qzedf~S
z6I%^aXV*VI#(VSwr?47F<g}x|zP`Si*mf;5cFH_f{kT0BD#BK!q@{J;+M3NRE-t?I
z_o}S)*=D(`0+(O9bg5<i`t=i1BNxlX?JRNyHBv&>MuonPl$Dm&K6B=b%lCJ8xzA<?
z-ga}|^QXsXO3-etBmbu_jIaM2Dx2o9f4M^2z3Iuv`#3!(wQS$Mz2e7*g;qA^=HVsp
z?nJJ(tNnCR9h3`_kMpffejUvgzwF99?!<_{0*~HrbDpFE8faT<Wl{9RV{KU^hvF>L
zY_&6I&TP4K>ck0wfB*g+x^*k+@vaxARxkWy|2-~m{W71KN-Ca0=gysrs%@UC9nR%B
z>Bw>U`Za><vdsDAY*z4jdwL3f`}S>7$;(So=Uo(A!shC)*`J;9J8HtD71C|fmS<gE
z#p&(s4H^*<{P*Z6_ro`DbWTmvU0pc0M>hE6CY`!JAKfQExjDmb*TT{RA|biIw`O1G
zx%Gbi{(nM~R5+`vtB=0b)YNpEq!PF-Cvxwl>Mt)QCjIpE@e$d!Z5yZoEA_CgXLrd@
z^WN*N0-(k{$m^A#(~iDf_0j3?udk-_1pVjRiB8oH7kl>X*`tHa>{7oqdfR(7Z@0<a
zzOiqYiYI8mwyXA8Q$=-k_LrN+Mn)|<r$O1F>tk?m@K>+!sp{tD=7qn%<@V+#CMG&f
zOEoNg6;e9G@Ui;R^mC^xFPQcT9NLk-Ud8j!nKM3b?(W`x;B$FVkx=TXDVhd-rzWfW
zw`|_L*}&Xf+`Uic;tjLnXFiIalQM2^TYGJ%=Oh)aur(U*?(AI5cmC{IQBdaCq|@Ef
z!m_t7|3&e!3*R|+-C|n$@9TN{|2it3LXM7(Qtxd)eV314H@$7!!d3hHU0hl&J-smV
z{;R92wf8NL-e0%3DrV07RrW6)JWx0{-+ukZwfXn=fr2FQFxyd^C+Qw@O|C}7$M3o)
zEq463Uu;rxa;u7`l7&UY<Gn2cPA;yln%}~C-(K&LHuv+Gq_V5@^|H`!n>TGTnRk5I
zuJ=xV{_nnU;DAGKd4Lng#Oc%3-`(H8{@-np#}dxRe!AAO>$H6P?Cu&atJ`O%2d_F_
zFZ+<1-T?z~!jskgul-X0&(-iN>*glaTif&33z~t(!+!lzGBXp~o`0Y1!*?xn`~QE8
zUtM3{52^-~>sAIWHAp_j^W^E%#ILWeR>|K!cg`<)X~fh|PfvpegQn}n9-3=i{>AV7
zrAtBDXYSmQF*7rJwO?E(g28jrhp*S;7w6pE)O9>8a#x9_iszv(FE1yirY_~%zG>5;
z9!X<`mIMCwf0s;k1KE;&O=s=Yb={Apq)y$r6H_?Vbm{K}-US5)pqY~14UWxh2k+dG
z+5hj?YAYRUYw7Ik>sp(eneG1nDenDI`s&KX2*z6y!s>pYfoC=Uc|FJb<;5k+UtU@|
zAyx8z&F9`@wS}dnM}K^LTzc<xm#B8u)4jg4%|3kkbjczdJRqr~qq8C9q|n-_Rr`KC
z;<m81e*AoX{k7M3PEFNbzT;NV>aeu|tHX5P+}!M*J-fBF_0g-8wmZ>FtymcN`1qvi
zfB*QAan#V<{P>2%!xJV?UcB+v_AV7qP>1==n>QwxIQjV8+}zmId}b^NRF{>J0X0*X
zELrm4-QC??m7o&OE#mI3(u?ck?UyWHo_u<mF6+GPk`j}3@%#H89&XQGdn968PGpay
zG28d|_rq<b9|Dbo?A*E2qT+)B!-JEP)h#MNsYGqh>wR{1wz8R7m~8p~e}5;acqY4U
zS+PPRB`r<K$Vlkws?f_GyVK6jk}yi)I5)?#*?YR4=nVd=Srwr1vty;^=H|z@WM1aF
zv)zBbos@PW(*f)Edzckl!fxvK2smxbiHwX~Sn~1`+tN@0&q)T^*L0pddzSR&#YNU*
zd#k_eB_$<2c=~jysJVfG0I2nwm8E5te{ap!_4}?LyOO(aU1+uapAXI)iXyjJYhQ0s
z^qQ)*^y8Y4jhi<gUf|d~VcN8|mKK(ywaa~HFT1$S(#mSp?FWBWU#tKB_xp*HClB7)
zS-f@L)rAWezPPlMyX?)4Mo=oa@MqSd+#1m-w?Y{t43k<Mzkh#P*KhY_ufF#*okkVU
zACJ2AA3S@ujBk3XWPJT!Qx(sknrT{3H*2H@bQ*qTX885}J-@xZeeZ@7Cp;`HEE2xH
zx_aW=IW`6rHMK_<7CLiqb36CT*_u4MefxIur6ryf|NdB-<=zVUGWp`c+qb3X*Zo@Q
zcB6rjnSmiPGIEAx@v>vv_SODAbmxvt`uTafCU2jfp8ojb<Kq%mB`Y4iI^tCt7hb<z
z<L&B6kb;?!nN2}kn>+j3nu{Fw_tjcox^(Hov)TEp)&~d9<Nf#VU&ZgY+q>taC;xh}
z-dWbb#m$Y4;cjlPmW{1#?D{V;v9Y43{pVVhg64H(ED9KQ?%XML+sE)7(?8qCrB}JG
zu&&*u<0+JOZqCZW`)k&$xv)Oo{>js)51*Wz%qq87<FUVUUv5r(>?D<%UoV$``1DEZ
zgAJFmr%;Q4Rd{=8QIV0x+J3uV9HLqw7dYmdW{atK9=f#D`)cA*%etVTDP_x}x94Tt
z-BsH7a=LD`SihXDQ&?Eo!pfW5a-}a_x&-RdnPgsaNxpqtzMdyPKmW*)BN<oOJtr9y
zK60t3s9140CDP5srN!~Fmh(L0hQjy4U$*AlH1e3#vVPw$uf;si-rMgxGsEmkfP24O
z=z68QyUX)?b8V}>I205Z=*92r`SGJ-Z7nDzU0D+utekUVf@0NuW#?B*Rv!E1n)>Sd
zT-KTP^>!+rhxqOPEch75^kcXFyZ7(ce_eNGLY;41oSc|m3`cf$woc5BfYooJBO(qQ
zJ?d(>cF~>k2mkLI>c{PgNM<d6@V;o_`Bxu~TAnixjdzhhdiA&}Y&A^P-5JwM*kI*p
z$CuC>$7izh%elnF%yFBsef##RMO|K(m-%k}HZ@i9;K74C>i$}tn`6oB@9(doqM~4K
zE<Q;G)X|9gy~6I+-inWl9G@3HIU#svwmJXte);2v+xboH{!LZkEPsFR>Mx03sb^=I
zHn+F4FY}+@7rfjLG=9Rt#nrTb|Nd+46V?6ZG^luH+}@VEu+qBt8Ba<iXxL4pKQk?@
z%{cvBM(*ct-`ZBMUL96Z80%d7_4RfB#csV$XJ?s$rvFW{ukkoKI(Aj+dhD(Gy5-QB
zvu6XB`A9BVx^(4XP$;LLpSRGlnXOA+nw_0pyY9j&{qXSc9$9O#`L*99_x<_g?K9sl
z*6`kBb^n65w@gD;1TcoK3b}ae-Xd3ShJZcO|NZ;dB`j`hYg_o|N8#7|=jYivCnYJ}
zxpN0J6SMY*6UP+2*jo##cV}JIa&dKicxPv^hqw3T6`%F}Z@s;~ULG`We`QUiux<4>
z7wAypjoY_hm#&#*nhokFf@a);f`oRJz3qDNAmPgT`1p^9zuw-SpZx2~%Z}dOqidtL
ze|U4#_^Vmy-q1xMWg(Mqy}Gt`^;X}n3;)fvE`RXy<;sm~^X~5Idb+Ce^Rtewu0u18
z)3?-VDDF=_-p9x=Y0@N-*N?BR4p(eBaI{<e;<{Mtxi2*`FD_zLQdZtr|G%!})fLbv
z@rko%T|rZn8<Si?<HpnV<K4DqUA-b~67p1_VOP#v+v+gG{P1-#j33IQ1NT;y&ixtS
zYsJIGb?KIvgak)%@!kK?E-&L&zH|In6*ogKcGm;YGKC8Zoi|p0&jSrKIyyQ=$yd$x
znr)VQVVSS=kt0VEzQ4O`^?vTEeeEqR8g&!yE^_5w6Sb8q{oI^`v-9_@+~|8hJNcE_
z|Cg7S&#*4n+m?5?OFMksgO87ozv7hBzi#dPddot+m>mr>jnf}}czAe6`Fpu}_Vw%T
zEnCfNU~caI_*n1OL!py@e%^j?m6d?F`0^hg{~vDWpE!GVw|4kC1qB6%bi3|bX8XKW
zu3QNk%m9sKzrMac+h<+<&skEJ-fQ+Kes}$Pf8oM~Q6E=_tZd>E)p`J$qx<v2@Xeby
z7gmSsgVK5I?lRYk3JcJ%@qz^kA*(`8F0grZc*3uRN}iLF>~Gw=C-?8)KZ}wV0(x<K
zIPC51zZxqmD?4wrv#<FP@b`>{o>#5VRpTvLS64-ycZr+^O0;{`+E@KL-e&W@<ZF5N
zrF~kOox2h<Dqr2-Z-1;`zJJ9EjXnSW{eJaf#R?6NNlOg>X`R}<F!6Ak+R4p^wO_6;
z<eReP#fuD`s4X1J{pLD(d2tmL6<xWl;_2k&)m61<=E`HS2lglL;bW-(_fx&$kh;70
zQvRqbAD8btuIClM*Rh$6bzZX_$a_1B)8E|LDg5u>KTyTt;lUwgnzh7mVo1DK>Y3xm
z*+IkhUS3XVX=-oYzU?mkvt)_J+djMNk*18ss;aIZ+rvIt*Zwk5@eF#yJagvEg_)O^
zMeHn6JvYa4aj3kH;X0!ymWz{4{AO`pac{C_uVMVZiR=FGWIFd2{`!*1aO!W!gZKZA
zPgHg<cy>mzS3Y2Z%E}YpPfW1NT(z+-aOSVtbjLn<dp>S%?ltlI;|i<8!o)xWQCqf{
zd^J8aq3-Nb@97gJPHa4Iz~QL8RA^Gy?|)xj2G6mtmrFf8?dmT_ZD*0|7Wb#r3f78*
z%TI@ueJ@H6BbESuSuZFq-hOhjdUlIx_BEf^heKlJD^}Uv3SKL>{8xgFqN3yTQ_Ci)
zyxc0a^3*il=nIS8`6D7D7nZ)h_TlT-*4|#;l*nU^%<Q1KfISr-7hNcM^X5&#qa&O?
zb1Vcw<H`5-Rx7qNtX{3%#wXjQzwd{W?L{M7TUkFpzpC1T*%K!+rl+SL^_-QKmR3+&
zdUUaS|CVhpe?8b}v2LNFTb~T4xw(1G|G(cOHY6}UJ3E{G!TTc6+Ki+9`co~ethCx@
z&z_xKb7hT|^{!J9fp&Ufl9oj(VtO$hKR-WDzOf;(t1#r}g{`;dX~kr+9%(vfs;}?=
zw>&CJszspU%ZrI&dr$jk8ttAmQQ1A|-kwU0_<c6Fwq~>Q^YedgKYe<dZt!}A6-MRn
zVt)Mkm2`7cDyTuY%zr*#ad9zd&=}M%sj02ywwbr;obNmvNon)EBR4iCE4DPuoh!@6
zBhip~dD%+!LeTsWuat>{n;V;xlhcK5xzQFD76;Cp;qmnJ?C9#c6qz3%_m-<+SDohC
zfR(qFMKzk)*WT8P4f$I5_*k#iV~<HK>i+XYX7o)uaKPcljT<Y}r@z0yUw*0ARHuRh
z1Ff(%9EvR8-rw&(HC6lZhlhtj!)<r&-ZlNSEc@ujKU}Ay9ZLhIr5+7E(6Ik}^vXA@
z)r6!rS<Rh3U0g^=NI+7u^X~5Q<kQo11)L6CzAU`ht@qG}hljuVdB<-~JL}}&z;LWb
za`ETmZaul;JUh*n<$NwKDgsT!w6w5*#y9s?e+NatFXhiCPI&ZIrF+aZyYlhz@r#>M
zy}$NrmAt(r`t94d38|9l=jR>WmU~;|HbZ!L_))WfmFHHiyZh$m=F(@*^M6HN+4eE?
z<cSjwe}8=~{QS(<B<F?zXom8;{iVy74a?uf^k!#y>|busc1OJS)!DbVw@;imkI&lL
z+9cxw!^e*we|$QvzcKT&8mKUJ;s{wC#w)DucO`1>rHHm`{eO7gvL8QkL_tl>t#JOM
zH-{Ndo%amAy*PVndU0{_(exLmLvmyPiAHfRUcEnhO5OCJsP((@B!cJJ*w|dyl<NKF
z_ICfj%*Oq4wuk1~RtpFSG~C*nz521()0+!k&yt=6Yv8r4@_X@$f7PMVuV3TM^6%O7
z$XJ4U{TX+6neN%MCm}bN*K^W_)YD=rYHC?A$-%w58|sf&$Tn2zO#bhlJw@ZMN6)Hz
zV%OMpU;PNapDey~{kr#0P8?bjzhBNc?aYB!S671uJr!AWbae&g<oZBs7khNMf&(OX
zm%bJ=GBQfY&yQd8SY6dMv;51>bF1V7FQ;GHxAMN`i|A#cJeB7d+V=Y!w7jyNd8z-*
zi(T*9wk<sN%zM%jruP#C7TtI^abM}BkmSFMjK2Op*YxM-^Z6&vp4I&ldvmh7|AQw_
zQVRATn^C6|@a1>jo5Ii9=L+{}{#N>>fzn6qKw1wLpZw@Z=M0O&q=g^lY$_H=)cyZg
z%kcmI$9=EvE4%mU6gbUL1eNNSmU=(FvNCu@)YetUwmo^0B4btJ@qWvx>H7Wh^?wBI
z|NT(bi`&z2<3>cy_q*jYY$}af1YTVYmywm7IBQmyxPF|773bZ92N_qcTzTT`*{i>H
zn3<c4YieqC$*+7pD<$Vuwua}VW2*vxzMOUC^RwCckItIkcS%cA>yxwX(v9AhaB`9=
zXaYkocGr?(r&Wd_*WJP;FN@}NTw3a#{OZa|34;U%&<u>vT&qy+zE`_epZaq8-QC^G
z1<y;Ys%2(kD){uobMa-y2KRnB&@zG#pFbbIxY#{0H+SvE+OMy!M*a4f)FP<tmT;s)
z(8H7M&Fu-WwE&)=DTQn6V!OY-zW(@7E4M}cznX=s<*Y3%9=u+^|Je2T`rg;q*FS!6
zusLE+g(0XF1)4U}(&AzO^~05Qb$L%u*S{W>So8MQ)`)#Il@rg!$N$<EyUW7D!eNpM
zXmzQqb(u-#y)$Re3d+dz?5+L|8nWr=?R9;8tT!<;b7h=r#r=J?92^`69v|;F4YNN#
zfBTUmE>~8Co_<mDWPS6!d-tSngH}5{pI`rKYf@@p=;|<DP-87FPVU@X>-O5;-#{Mz
z@nUg*LUwj{M+e7bx%GZ?tv~@bO+UVGsrPiPx{&``w^@U?{Jgy_*V)O5iH%okiD~4+
ze}8{>^z?+-?6WJq6#$y;`~3VosLq)%L7+Dmv<?tdHhlN?^lTJxdM&v!Bt7*1+?g{o
zzqnK$Fv)$q`orUX`&Hq>vY?^GZI6%lC%?P1GwSz?+wV1d48K49_xJaQj~_33d9S=@
zl68dxwDzp5%nUT~0V>)KHnG0AzFz*$-Md?F*(XZ`+lTPHWj{aLoL|1?gX6@{e|81>
z9@ts^eciqDa}WL6y(}Z%dr_W5^gK}MJ!6IhsC~P7{k}u1LRW)^1-?FxcdaygvFlme
zvzs&Qe$_|IZrHZ1t-YOn(&Wh>9~@*}%egIleH<&pTEi8S?%av-nPtNH^wiYDpa!bi
zH#ys?kV5<5-rfInAAkKbS-<=AYKeL#*Vn6G|87oc)r{R`qUJNBfm2uwG^_w>LxBP{
zbamLnXJ=<yRD4))FVnW-0|Tg~&K0heeAKiqC@E*Rvgf3@>p#!i|8Lp3b7$4j)Y?x$
zbCTN+z4$%H@L6q>B3G6FvXa`KT<6}C(*+hCs8;a|+IUyF_BFi2)hg@F(Kuy_$lgcN
zx7MG$-(Ne`r|`}rx##;&l^-~I5vl7Wds1~SBdjB}DBSnu;U|0c*c>^2ocTw!lP&|O
z%-*B}s(-4M$KJ@=d3{~1^VwOZTkX=sog_-;OuxD!koj;M@8NrUs~JJ-qeAn!d3ag`
zn0A-H*E5;h(7^EI=~K<Ri24r?9G^UUCbcE0$ME_F1wTK(9ksu=g;ju(;5^&t2m8K#
z`v%IqV)}7Cjm+#yrlwaHaI*Yb5x3WB&6+h6X3SWz<IvfMhueKWO?(KNxo>D-SQEL~
zt?<+KwQF^2YHJI>zl)98UFMrzos*-(Ad>l2URqlE%BoQA=jZ2N&vrfE6tllhwz9G^
z<L<7l*N#6be|P8L*Vos%@7%w7RrKzz(!;m5W`kBi#_TTR-T(jJZpX?MAuENHl#~R-
z#o42yqkB1*uFAf#x4L}o-$#!g#ocUQyxf0&m`*r5pG<>_=c{er;-S$AuZq@R+LY?e
zaA1~c_J`l^_pkoX)*z-ErJ$$BXJ}{$8upp3`FYtcwpHJ3KwX-be;B!)U+y;ArE?mT
zbzfXuys_$Q7KftAt@PkoR;5~N)~qo|Jj8OeXwv^%Po6%_%<b>(ZB_AH5xsrg#Y%(J
z+5eBr*E>v7+4J$3bkyxfj~;Q|-M_#pcSZK~bq8<WjLiO2nOJ%9<jKG}37~a*3>Q{x
zZftC1NVxPXvuoSN9UzZRQhAvZ&K(>8se!N7Yd?K?Yist7;^%xdH8mpYt0N*J6buXm
zCQh6PS{T?O;HuUBQ!?7VMWE~NgEMD*Ky!K1rcGNBxR|Zszy9Q9uMY3c3pqbGc6XVm
zrEc)H^{Rp9J-YsPcbB*C-D?}RHi}h|WznKV35kh~cD27Uju?NfI55LT`m+1~{58z0
z<aY!}egFIEv_8XvtL(v(CQWMk@}&ecV3GakNqqg^*2~NN#dp*P9*+f0=+2)n-y*Q1
z<mDvC-;$3)d+occWfC>``T4)Ryv$zx?TzEpQ&R=y<@>j6G1>b)Tr1f;@6Lg@x3@oh
z`*v;JI_ctjty4EPZ4*!5{rP%){lj;6cYpZ&`LcGMg9Ag0Kv!;7Ufw#Zepg9r5x4u#
zeFE>Ri!95#yGtrJpl;Q_<ho;97XIqf|E#@YKG&cB)$<?iao1wKdh*c<_hSa2dX|Na
zO-WamS6n~tiuOLkzf$h*?kZ|(ul_JLJxa*U?Y*@%`|-hMc8l_Na{@E>tSbDsx`I7M
zrZxti`>qSBFA#=~5?}m3=f;f)7kBsU7Tt&q44{11EvEb6<x5V6g5qN5{dIpq6_(Fj
ztI$HHlV4w7pEza8l7G=#C!Jawy<MdL?c2A#tHal4)hbvNK62S>@59o-Ew1<A;o<hE
zhpS3Hub*dC^P_-6@xw{=`3jbnk=gVABsR10HVH62KGu79bNcx!56{oDJq&8|dJ3`e
z%dIK5>)qMLnt5Y`V&2_dt)MkNE&el&Sk3eAUFll?`myU(uLAx0IWZw(Vq%~*I+reA
z-WsN6U;a)eY+X#|rsT8pY^5tJD<#bH<~;i5*vzJ=ug|~Oz5m*dcbb}-GmKKXR6Mml
zX`KNr(2v_w(b&<!0a|;O>+kP>e5P?am#_QQps%Nex6iYw1TAvP@Rd4u>QvAin;CQG
zu8m9Fu%UYPlqoIJ=6M;d%a<*CbhKN1!=_D_PTfEKH1qsC+lWmmo{h&1m-h7VtPS<?
zpJ&r~b#?gRix&ewGT-~NtL!aTe0)5pJz}MPN7lYh=KOqnbFF&as4WcwOqZAYvooya
zeDU(-%OC%KzgIkMG|N1H-Nt+u7Zw>=S;NdrDk>@}8B5n@UwU#HG;XQLvhU9)@07H(
zRfjik+VtUO`h3aKI4`cO*Z%YE))wZ7F8wC?V|UHTO=~{yT)4jI>8Xd4{p}9!t^RIM
z{w`+iNjEt;IZ)Gb(xgeC0h!)hb-y{FvgE;=H!&HOS{<6VYx48+k9z7~UmqWC-~UN_
zji30^z2CombIZzFb?wPpRqtsl)GJ>Z<=wGJNlndslK$$-%Bb8A?D93B72Q2DmO*>H
za_es1yxBE5?vwGB+@7wkCdi(Z#+PF3vERR+nQ1)3u6Eb8zotv>FXpd(-@Pi{r1Vut
zuPD#wPoF?Z#et)7`~A9T*}6A343C<HO!W``YR$7&{^#15ok6eNtJVDGboBJ_e0h6Y
zTue-i;orZBvnEUs$ho&i64c}JdHwx<{qe=_{ak1BJ*Sz*vhheTR99Dn#{3E|btr0E
z&)QV0+qo+-r*hMlEiUKh*@DXSGc%3ZJ3BjH+}Nlb6B}##Xl9j7g3r9(my4yN*?qpo
z=%4ue`+MQfPpNDF9jku7clkT^r~eyQELoxgiqH*Pwj4Ro$jt3~|L$GcYuBz>l)jpB
zY{|1Zb7XoX44n#H!-M;F|KojJ%JAynyN{2L^WHiyus-Wg=Bj<WHU<R+iPXD1|M>WL
z#iu8npkcUGA)0$H2{|R)+fyl(>cG($xY*5+W8ud&MrnVZJbJ{W*mBM&EI`ua>E`dL
zoSd8|&YlhZAK;p}tMoNndV2br$jxl(eseC|FiSrt1L`$`Ru#5#iSnH5-uI>UoWw7?
zg8_nqf&xwtKA*Qg-Yu?w<>AVeD?$CAt@A98ZCU8&=Qly+<brhffB*r|=8hjfDspaZ
z@l3vbtXCRT(q&y;1zMc>-sEel$6S+Te>K*uHEUaWzg#Tk$%%;qP6;O_DDEhKKkwSN
z<^J=tu4p^|Hr=F?{NlpGieFze?^VCI?JeZ}@coDX{j1k`O_Ppra43FwxBGq8SLYUi
zR=*DYbA|s_*P#_u6DvK_8{mTup|9`kG`?5ym={zTt%%ua1e(UUySx1G)vKcSYroHR
zy8~L7UH|7JJ1B`v)eZ-(eM>zx#j&W!2-G8(tnQz5c9!WY{<zhltJ(PZ`Panm22D+Z
z7P_c-I{p9m_u<QzofDPaAN~D)zkUCH`$LBgfhrPZ_r3>@j&?(59~NG>1dYahd2tc6
z9B)<FTCVc)a?o<X+uL%RXU>!at&Qosy{k04N8Vm8c)6czuaxP9wbAAkRaM{yb$>r-
zux(?>%OD1a`F6D%a&Mb~b`5RKx(eDyq2MV58oFDuL<O|lU~lzzvlms;RlM9rSywdP
z+}z9_yQ{=;ecav$Z{GAQcJEix)Z{!n+x+^kjIX`s_Zrr&)n#I4zAA4iXICS^$;p{<
zVF6>*)~wVEJ6|M2M@P@hGzJaJnq*#LIeGFVXjL3&QOnxs?M~CW|J_~ynq;}Ku(`_g
z@bq3OQ?A`*Zx3zDz5QYS|3B=qRwV~6FZbV=c$m$m>I=vGx?h^JOfrL(*tod3JoxhR
zGN|Z!`1*DCw%pr?PM_vpxpF0FwH}|WRf}UY+r!`Q_v;(X1uX(Ee}50Oi1W|izZaMJ
zN`v|+YHDm@VPPM>f4?3P`|{@IbPhf~x2LD3f|e+RtcegjKi}Tn$A<^B254RE?nO~s
zvsmRm-`QCVTDl9`(<5b?wV>wbr;0Bx1h?hh1}$6ck+lw!Eq`%gVZ^o^$wP+^gZjOn
zo}PXTDjDY4R$thh?!P8>_co8~f$_ex&5lk|^#+YMv9Pi#T3SlJzP`R)fT>$tzisW>
zwQe<vEywOZd-m+co=W3eTeI8yWUUu@PFDNy{d@b?t)_YR_w}~4uz>Q~_jh-jmo8m;
z@FzD1N5kaF!g6*s9M#p;COJ0(_WGJi{(X43J>$ZH#%oyz&z(DWV@IL#uJZSN2M#!Z
z=JK{?U2RhF+)?}6tWVau?aGx9(1x-L*<a3CzkhICzTRbR)YdC+-}K2^KX~z?<I~gA
z+Sm3^UmuznwJoPJa&y|lx7+W#MMOxvdGiJ&pLn<}@#(3lpiW>@bMwR3uesIL)nj&-
z@miO?X;`{c6|{(PZL;?ymg3^S|EKq^`_m_B%x3@RLvvN=#_76ITR09LJSbtD#`Epn
z-R@ssUxRk!fSh~g%$W^2H;vYw>}rdX4&M56u5~#ml0JeK3>q2=GBPsmsQj!3TD!M0
zSbc3(c*NX)UoQLeTJ`?{SqMtHj*gBmZf;fwEv)_Y#1pjr2DCn`jaORayLR|G8BmRU
zYissm@9BCcPMtcm%y)Ld|9`bS(q=x%Mjl(Uu5KuK8N?%JBLT`NyUX4NY|RQyNlynk
z&!Xms!JWHzK`Tq={xsQ=8&a!~?{V|?w%plOuBlg_G%a@TU!|VAd)F?|rl;0rm-pA#
zpP6OK4O&i_l$;#6)JrsGZ<VNZ`8$`0h#BB&DOke!o%iEoy`bgkAf;Qgue()LSmfm7
zY{<T@H^;tSPEk=&!Zd4&)xR?{jRmEpyC+N#0PW_yc1;YlxOiRc?gx(^HI?71bbnv-
z?0b=|$(Fh&*Z0*{mqzM^uan`Ex9d@M?^_VG)N6)W?ku-ES67FF7ITB<{S52>)qwh;
zeSLkPHnNbgFld{FjCC1LUS6KnXD*5GYhAOuySc;G$MwqDRw<a6h`hbMy?y?Cc_U-v
zi8E$&SeL(haBFLJ)$(+o->a6WymAXXb-96&`NL&@`@}mt3SSxa3kCPF_nh5qSX+|(
zx?$n@ub>rz^KY-Zy6Je2B(t@(HN$}kiq0m#-X<UKJK80xy`ko3QE&FW9fip?e?A_c
zVVutQ=g%JjIk~<yYjoB`Z|4IwTfW`SfB5uiXhxli=b;WkWzdoV(D)u`ygw{Vj8Dd*
zVapbimbSJm-%mzQcf7uD5XasSwKZ#D)YhyU`|J1biji=-Zx>P6V;^s~ZRM|5$97eJ
z*JEO03RvzZ`{U=&gO@K0&zw2)#?E4OIh%?Ge)~Tc7RWE=1kZ-qSABiO%FfOXN@35>
z&2?^O<2AYEn|#cF;lhOzQYArt$lw2$O<i4`;lT6x^?VB+6tX1jN`HU)+nbxro|7)@
ztuEiYZenjQ?=-#Gu6efAiy}9ty|}oTeb1gf1+T7Xf)>((Hk>YU?f$a+f$M_v;H4pL
zuP!g=2Q4;~wJuvw_V(6`TU)g^ZQi`G@Ua^x!>`_-;3J)toZRfzEA{Zh!^0Jy&zc8r
z%?h0{bLPVA>+4p;?%sB8kE^RIXdyAE9SfSvdUbX6<4a4uZ*0qzmXVR!kaU!5@%h~f
zZC5;#Z}lH~)oIxExOTaoZq$|oJ(9)-d3P*ARtB-kT9q{P_w$3=tFz7XA3ZqO%)!YS
zxc|KIvUuadM=pPUy<UG~V>0`yu(e%&bFB`ZJIA*@@2-=N4^P_pd22Vvhlzl;;yrr&
zcw^C1FOYe$yUSW<&z7Dvc`_(TA8ck%KGeeb>W8cBaS5Yy`kmzmmc2t-q&SU5Q1EYf
z^~Xo862@sg8u9z~Y}m9(s8`BV$k5QR>TUI>C!QBKCcA?c4<%-2YybK4=g6O*pI!6v
z@(iEP0$1uM3?`{?8XIp`S`J#%2wLUX)g^TC;zdvid+6G=Fbhk|PC47Ej@9Aowcbsi
zJ6Ct#?|0UMA|fg>va+p9mo8lqv2jtx)m2kx*w^p#@b$ggQ4g|nRjBsE7cVr<oH^5?
za~c#Vuigd*1}Z5iINZ2(i_6^HTu@9*t?vKda?l1i(eUZr;`&{n#V#fp7aVr%-VIuu
z{qXT)<*ILQH2Y+&m+d&eE_S!e?{9BgySuwLY}q0b7Z<mv`ujW3%GanualIG~DU%F^
zoSdAN-rio&qR5CH1q+jQZPMu$(~T0D5f54cS@!0JB1qMmHEUW{uU`G)_V)EVN?%Wt
zuqapnTA>MA5qUgzPsPR;_xA4o@b#;xnVH$4qeoq@tc?yoGtV~Krt*`E^4(`=XJ=2{
zykm!j;^|E@Y$`V;#qHU<*LA7a)Gdc5Po8}AKqE6~vEYVn+r$_d8Izu#nws?ZSg+G0
z6~p{{Hha&7mj3zo_qTT5{(^^18#ZhJt(08mJ3A{Ev{DpQ2(1WS-UrePT2PjGd0Eok
zU8PZllP66AEq=VPz_IIi&@MYIP}~$hKexzdrV(h>*`k=8MT-I#yCofJ;e7Pz>FKJu
zuQ#WkKO!Dqqqr($r4q=u)2C0Du&dbtiXE%6va)S6OtYuGxUjGp6m_8F^6uTcMTL)#
zJ!+S)6S#TvW~<!$b91d9eLin5e(>Nykoku$T?(qGs_N>KweGU5{+4mnzU<A6jGLR5
z7L=8Vef#!JNkzpa=l;IfbV<z@Rhm;nMVFR=wyAndQc+S;I<nMzy36*wyP$Po8#Znf
zR8&;#df)VEd$~SnF&n6#2=?~Ije=!mWs9<|u3F^YFPHT7)m7Ija}hBywUkJ)xz^>^
zZiTIlGF3di38dlN-~4-fG~4*)^;U(g1&yAxG&eV|2wdFu;{N{qH}=);cDvKG?(v<S
z#h`Xy%hIJwKYaKgaJZdceCEuVht8ezV_{**IHLO^igV%a-r2_KeJdh2F9W5jO*-82
z^74u;0_uKq1f1LXL_sS8j~;c6h>q^o3SHH4u$jI4^YioBOD0a6rgrAc8IjlP^;Q{e
zN;xTX^et$m>?R%1n${m5A8*~JuCCs_(7Bx}KR+L|<nZCMXKK63-|P9!vso#6{YG~3
zDzpEfKt5}JUqn<ZMBv)BYm3U>-b(uR=BARmy8G)JpoNqrSMR=fk#TWHVRB-AzW$s!
zbB_GqSpI)w*!5QV<MH3UV&1)NG7<e5`YHQ5M@Cmq%o*NXpKPta7fesZyDHAkVfxs9
z_NM;z3%!e`olW%9JTl2N*^Kje)|M>G_FL<ZvR&Sg8naD|)6co-`}cmkJL_5AcTaCP
z-FrOw^Zdg*t@GpNRG)ipFz?>#b-Pymc_hAnMPA8^zlrDP*`{7x<eK{C#>UhW6BM7?
zzOVG(`F`K;RsH|l?f)#Sc@;cg>+!K(ZRa)~&F6E9{briwMn&!@cqsV(`v14tk0+^m
zdu3;5|Gas=?%TBQmS6s?{#(A~`;l2|qqk4nS^Rw3=kxaaOUlZoNgAh3X_u>dvEse^
z@#4G1CLkjpAMbzvdH(6-e%mm;-ETG-<=ohC>E6A#Wqxy`rs>DWeS3Sm{Kj9<@*umv
zFa4)$1}~fP@NoO|bLY-|dRM-Gw@%!i9e;kFudh4(yk_&Q;x+pB<(JC*`&aZLYRlrq
zi+dyt7oC}JzrUosT>k6F_}Z^mH`V<7WR!fY$Ef7Rg-aJN2CDhY2w1o8*Q-wtn)#<)
zkE?z=BmM2`;<pjkRrbbK%e}p|W_$J<`+pz%pFW$Nua|thPd7I=H}%PhiK*Y-+<bbF
zUB2dYf2Bu!TzvIq`TNqfwRU?W!^6Wfb8~f{&n=Hze?6hLGT-8w>5q@|epalz`1_M>
zfzA8ZOaJ`-oR`0T?f;*)rKfebfBE(A&)xTR+t19g+zbk&#KUb<PwVgBlXGLkLjQED
zf(H(fJBw0h8l`%@eDOkKv0JZ}`Td&DoIme`e%}A3^6!NFy3ezhZr!>y=gy9g9r3T<
zes+5M^^1$`_WtJ^y)6r`zdHVD{`#l?e;l_zb+`O}tlfu3{x5sV`{itR#nk<L>i#z;
zy7+}p{jbaOPhH>t@2gSerzfD`Kh`H3Jxwn*>f5`!)mPTPe*Jv;*6i!w_MG3gZJXT2
z(znG&6xAQ?{eG5D&L-mC&vWI|US3|l|LI!3o10R-f4*?Hk8<mg2)uRc)+tu;n1H<9
zZ?|nKetu5*-R;}+e@0ivuCLU7Z(RHHcgwwV!N2d_*k512^Y^>mr;l_BSKrHizw7n7
zPsgP5WxoF2w0`}<rBgl~;?|#%y?*buIo0oW+OGF){})qzJOB2!+^5TC=V>i=@7HT)
z=hp+#=66eiZ*I%IE%^QI+tN1?*W>fcZ0=94t^BL;^u~R4)8o7HEHBpIzd1Yp@2l{q
zkLCYYNE)a4WM*e;E4%e*h{x9yMsCZAto(K}oqzZHk1^L}ED9FX{Jwo(?|t?C-={7t
zboNe9Pk;I9l@_<So{s*W4^HR*`dyj-d$#Sb7mGpZA@#?HhfDYF-3vOM<W9xo-lspG
z&ws!3eCH3D%hS*Q{Qveo<Mg2a)%Wg|SzWxogMop8p<q|0=F)!qT}%y^PwlDv{OQNz
z{`8ZRRA-uG28FGUo0~qbQf;<*{=2WsXV`wfQ(XD~_x<_n)~!1;-`-wUR`%yf|GG(E
zUtfRz?RNh8Q&YA5AHHW|U|=}MQ+}^9{oT&z^K$O&Ff4v{=H>gx1`d0^T=JH*udB)1
z`E;7imkZ8+Yv(X#|Ni!N=Z8bw#`*X5fO>5E`zNbZKI&BeG_k)%McORq#MJP(oA-}D
z<T0-O^<~S}txvD-|5sWs|8xq-ps1**Pmj9wzkLrpr;+}sxVQ1COYGw6_~-U-@9s7i
zR`)xzCUWzq#qxh&OtIg0e!j}d{`x<U&&;(p&%VCy?4HWczkXYQ0)XKFgOUTg#DRI0
z&t}F{y<Gb9*7beURK2IEcz%0(d-}@Y<<I_nK7U@n{^#je*YzScC}dw-<5^x_e$MXq
zn|Zg>&(E8C|KGRmH}_V5_q4ZXU|{&O{?^Xobhloq(i^$^|Nnh&oPBK#kED@G{m;|!
zMin0()LF?g_cH9wFME4ys-UvllBG+RKHqjdu3Gnce0{B1-klkxudh8#mj4}LKkvhT
z-RNyPv(59*P1BA3^;=_3;<q<9Cl{ZyRPVR{SFvvAvswS_&S@$;*nd5D<+;@I<&$fB
z-__1tyz~FR-<vZoF3P#NNmV?)=A&mN&wTrrXH}=iOxnKpZEoeSm&<?u)_{85c*TBx
zh65jeKjg2U;n>Xfbo2bbIp=e8b8~0f*Vnz<^ZDGKKc7xZ8mFBJ++X(o-d;(gloN>`
zD<}2HSQ_2lmTSH8IU55*!~as_v@<7`cuqDdeRXBe-?#bazrDTv`N?GeWm6`-uX%3$
z@1y-3m-|1CnSc8GzTSRw`uTG!0vBJpdw1^qe_xhY{(L(9^FsdG7h5{dPfj`7CHl9P
z<y^qwHr~_!{{H^`TVf8Q&2@{pbKYc^yniiocJ20iv%=#lRqx)ttNzxo=HHTKyLVd`
zKR<W2-Tu$Re|DfF+8G!O7&tF5vTeBk=b8D-SFgO%)1N19KR?HE^YiQ3jKAL8+`KvO
z?k=5(4GP}V^?cpk-OX}tO!)fx`fqk41_p)?@liVp60fa~pD+LC0sGC}<@s&=^7HuX
zJ~V?eCa8A!XD7!T;O%`n(f;D^l;1zk*UvjU+g$#0-Qjlr^KZA`ulvM*1+@3)<omks
zyK`=B(X9Xf`@V6;g#{(0rKuku9bJAmvN8C5$i8WEXC3NlTN}@rTK!$Pb*pLlox<au
zwLIr@v)uY*X6n~G<o;XB1CFJHhAhpcQ~uepFdR?6wIx&1vM9wY_g2Y`x6#}4&Q8$`
z-jsE9)!{m;U$bRxDh#^C_0O#eU0qf8>%;=b=A!$x-%}4Zv8w-l12SsPzI}h5>Oa?x
z|9Q&refdFF@h3;c<84^gnSR`V@KqF~f`NfSf+OnpZw3aL{nz8`ZF6&T-S60?oR}~#
zetl+c?%5-q!o^oZ!$E5oBe&<pf)b%l)D{hYn~z64t&Kq@EZ?tR_p#fu;K2dI|HAG}
zUwW^HgM=9v7!njDuH0v5c<^KE_U-BS_tm=J`FFnlA1GEpMMcf)==-O>y}f<;;>C$7
zJKybkU3645{K>Z4d8e<2$IrcXZSntluYcdR?|-^-`Mgs*3LjTNLkDX3uj8-R@1G}Y
zUH0UZ_WCnBpU=B}|2Sg;gWv*Yo`l72y{F>;|GKW6cYkMb`lOUEFD_nPzxV&Y-^E8o
z!@nGP-X2r^cI(eO&+VqmT9>69YT<PMdu#c;DlPLn1&8Yki=Z}uDZf^Cxk{D!f1arS
z{w=}4qrg<s!1!iSx8A8|XJ>zYwR-)s&6_tr|F(R7ot3Vx?#>sBx>v>T&c41*#-iXs
z$L;U$@6T8Hd42!C(7(3|A0Jcw`JH{j$;s;S&tEcH2u_=5?_LaB3!oD@X{vVkx9^62
z-rH7g_MMyiDknI7w$<$`H<z6=+q>BxRiG54=KULl3a|i3&1LJ~U@dR~u$nLD?4SaD
zd9San-TAOhy2?s`p<*@53kK#JrPpJpi)x2GX=Il>acQadWR?6qAKgH8fw%r%ljLJP
zo|8(-%b!mTk2|@<b8^wO$aGcDUAuN|%DlYn&Aq+W?<<a5Pf}s$mphZ(Z#!+Fb9>sO
zBb`@|=jP}8Px6^(V|jVGzx~Ypt_*z--)uhrEh;7v<}0X+UgZ#SGbuq)-j49snVH7L
zf4^RT{(1iY8c^x$Iaw|B>#M7kFPBdL^x-i7_dD<VtlypZzVG|qH#asazpuK!yDD$@
z$79mQ#m~-wN{hE|-&TIP=>GZ7=kw23$N$apUx9k>!W>Ib@ZFhZnq71~w*2Wtce#`A
z?(Y74@B2P;f4iS4X=i6$EuKGZ+O#d(w#j`fo&V#AdeObg=czwGJ&oL$<O(X<x%KxL
ztPWdyD&6k$%;3Mb!3hpd_%VahTHc2T2X}tIS6%#m@At6xpFbStm;WYwk$<Lfy5F-i
zGmDM-+2I;M3?7B_+Lzw(zk=%JnHm~XpP!ps`Jj=#==Iv|X;)SR{;id1Fuu1X^YX9X
z9Lsefi3=VL!RfQ_-CTao3|Ro20L#B&q{z~3FXz@G#|u<bRr-9emUCwAm+Bb`_C$GU
zF5S=1c;LXNJH_XpPV&|}x%s@^?3b69fB#+xaxM)2;Qz(X&=;OvFAo!e(hZlJ8PM;)
zP+=;8%EBlq43SA3=vQK7V2F4qIiLm}!vaNg5rs|+>)S9yMjZr;2r%6+8baW3fDxl<
z2o@3$dNh|o!U0B(mP4?RfY75QH6$Eh<Y-+63ke84TH8ay0ZKNEHb0;t0ii~lACPc>
zk)zEISV%zV(dGvv9AM;V^8*$V5Spy!$G`r)zso1CjyYiQ@6CoCvr`YI>0CQt;x?Ue
z;)X`m3{|eCRt1e2IY*q1R7ux2{A1KSa!;-M-7dBx=k#2;4kjqRY+HLpS&d7-V?iNL
z+nq=I%mtE6KBj#-mtrqJ<Jnxx^m*?>;`ta<1Q#$v+z2BBIMKVgSYlHMUDpH`^cy4{
zREg;LdSU1iVzh#}1WHdOqI10J=QWTw8g5@NjrG!8o9^SY|Ni*|gA7}cDAb&U`(VEw
z=y|zIZ}sZKJ;$d<`Olnj^ytzzZ+l&k@3t(T3AQoKM|0`1=eIrE);{++pz-))=ae88
zY|5?~oQ!%c2(<)6-Epp3i#7_tU?7X47o=>^1^uLyeP2NigW`t2t6uM#5)^fQ#*DiC
z^A9FmsA6NdQ~3RtvCT&r_J+Sc$WeE};d*IgtZbUizAIIyj_By=rRL|W#4$gZw@H59
z!_Max3~$nr$5R^EyfjT?Zu=SK*rqeNN%s3MnW7ZK{9s<ud;7z}=L;Eb+(!v5U*5@U
zw#qRw+%Y>}!0_PSm26w66Jb=tO9eV6HZ6=K>WSi9kgGzFy$cdxz-)4_coxkMl4`iN
zYn`{|(yu+8ufG45<Y8Nz4ibf6gQpOq-(<&LPc1E-@$pB{Yfa&;J9bRjyLTc7Vi>Do
zKP0;)#A`3T@}tK3<c6<vI3-hU>?Q_vfm1WYIGC~qmH)lxuSfMmL_uW3vZ0x1$ty3Y
z7KM=50R<ow54v1U?*K}>_w@91(4NR=4-Pg*Mn#>vxY)h;*_oO3d)}Q?pYOB&`tQ@{
z4;?xb8-Y6V?K2xxg#Y-z=hG?epKmsw-?Ve*Oy_pK)a-2S^LD>;&dsx(eO$i&&$8=#
zKcBO%e7p7fI_uwWx8MKt>-GBQGt=kI{E`EW00@=9#d(1-?M8Tf?bOT5{h#mse(&_N
zXK9n3Je?kYZgIceEc1I6%JDTHkNU2!eYJ9Vp2h8(H$5li<mC9I89)qxk_J~n+2X_d
z+Fvi1&zwJh|2yAj+}zxiU$2ILemXt=S-X7Qj<vtvzIl^US!sFR_WPZ=^B~iQQ0)w7
z7#OV%@L1RXtC6dGGEqlgKfZk5zI}CXe@BOUot$Z${s}Y_aG;U7yhI(Q1xy=Av%Fw1
ze)H&PcVuMb&WAOrsjA`Y<Ic8ni|74}n_u(Eb6w2NNxi+j)|SXM4+FytMW&Jl$#1{k
z?@v!meAxE+=+UFu_wTRjxBq9sZ}Y)nUfr*k*4x0P4%iwHF+&%mrR>3h#y=mA%bU;X
zKmIuT{{1e{k-^W;%{}d{zjsR9`NfPNrEvUhH8{4uhlPa|Jv`JZeNI1a&kU8y4+q)v
zU)ot)ThE+5`}D`h$MawRH#avg{{Q!Te0kZM8yjV;%ie5zhg2ss9N52o_wLzu@7{fV
zuI}g4>2BE!GfKhE`SIc59NTKM{r`StPn$k{{oMK1<$A@%#g;WcKIq;}FE2OexBU`u
z?fUin*Z=R=|NpyY?b^H7OyTZhU|_ftS^w4P;QIaltlax#GPiIvL|)6bWoW2>-zpw=
zVt)O<nf!J?9^AV5^z`)2TenVK?A{Mbubz`Y`+lmct9KSXJ;nPSw0+iXaiE!**}GeL
z$c8f{SXDAx9pH(Mk3Zk7zi-C&`*qg#f4>Ct$y!ZWyLK&T%ZFv@t1DaY@BMl$`satk
z{GZ=$zn^9x5mOG@4t3`2*{44~J}$4eLow4J6%^<17Wdno+Wmgt?6+^<{`vFyeC3;s
z$3OjiKL2^A`n(<AX7Aj&^GnrU>2-UnzGnH&x0|c%-uL8TyZpY{n^9t@K~u$neMaH;
zyXEnI^K52LR`<X6#eBKn++FW_U;H;VH=q7~|Npv4pHb{@kSu!qx&Xx(28J8cM~gV*
zP{LA;j|LD*0I7UNYW?2nTK780E7LZ4(XYRCY|W0ZCBbSB*r_2JY|G-18jmizkjA4E
zqy;?-+-3*sVF+G7CFt?zw<?FP6|1F8`S`=dOB344S|EvNk{LL+d0vCHY<8r7jY2K$
z7#I?)h?%w<Y&{&(TP$4ZyI;fB0)PT=fK#sN{VE0qh68oipgpt@%pMxU4pvZvHn{Ct
zcly;UgU272UJF*sDlF8ju2vRA?iPY-RR#tJ<)u@k=I5(RZkuPUxVY!IdXN`VYGGhF
zz#{<arka@hY`Rv(0tx~sb^z7sP&Skr3jH&Bx8$Hf1Ep4s7IV;$08^6?#av13^dPU-
zlEPQte>axki8>FK2N6G_LCKkcfnmYQb+0$=vN}^yv-0bd&ZwA}Q}^z9w7?s{KBmy(
z>p}=($l(O~ki&rxVNh~rU|<MNnvt^hD+kC55N@bldmWUwKx{a^?1<by2MIfjrXNr+
zz;FY##-2zonL$pVYiX=9GaoW!G9xbb`qC+vs*bsQ{r#7Rt@#>wxgE$o3=GSfAOi(I
zyzvh;C_obR12r#AQ@i`%F&ro87!IONXXt<$=6+Zud#yXf1`t^w{$<40$RPjIJl_Ab
z@BPiWwWjWm#lKmvjgEgc=bJTij?NPc)n(SRrnDZ_nbIp_Xd0BVd`XIc*TiKK^=4UK
z#yci;=%ksSayr4Z`*tU*e6M|Fc2M#&=VO0!?e?!cSuSzse9b${?;j)T-u*0zPybmt
z|1)?gD9Aqy3=CMtew~RZe0ZUS9@G>D1_sPwG!r5!oeSVv9%0IecaUe=ZaHXh=<Hv$
zD#+_)mD_4a^ZPnHzb}Ii3oi2s4VC0`U-{ZO);}|Jz4`Qy6@l=&X+sYz1`JZYG<|FK
zO-Q-&b<Q-MW$U&toq|~G7U2dd6c`w0L@ieN919;<OlUe&0x5c+E@EI{XqZY&-Gn81
zOuD%a(kt*;gw0zSoyK}#TmFedlGXwHkkHV!!-21U1zZn~y88NTs!iM%)>x1eG@tZv
zgVZ)WhBg`hI4_;@ta~T7r(5j#%#%s4s-nF#_ss#RF=(Ar2<{XY*g!nlP@g*`Wgle7
z|AV~6W6*X5h6fQ4Nsyr+9JUtIi8BPy)GS@K%1EX!=z9CEd6!nj<?B8ExQIiRp+OiC
zuppxnLbaBfeEjJ&De!u6)TSA`?o9)a>0&6GDy=&6J*c6(hQl}(qt}x<noU4~3CEZN
zwS%u9nei5>UAJZFs#Q~hcFnuE3Njt@6|%B_Sqr451$nGtC1!#bSqL6)+n@u>$P5e&
zK1+kVgy-w4NS4|zSM6T;I#+Wkv`-u%hLl8?-O)H%b6pu^GDCtA6*DrDQ^1BZ(6yZJ
zg%u+QvI0Xxy)<LbXM}<~qc5u1z|ILiuoKkVEP>Tx>W&yC<i+Vv!AgJl&sojPz~E30
z^-_V*l%QGqCv}m7_QxU_u-gBf#ia}k3@`ei5$3llaMI6pkhal*mV$Ml{($;ys3d5w
z!=cd7sX<=Xjiau<|NhqqvfXA53nGFVIKwc?H)wP_oQ66GWV7&^DVL5sM=9E%hGamd
zIzfsU60~|Iohi2kmu3tz3Py_%aHt>%x~5SqwI5Q1LL5ak2PJQN4X)r$uf$ryfNcX$
zs4y@ztPI4J<iN@pPWyqIem=dpN*J)RhE#QMUt!q=L<s|yU{E{fa~)h@LAYQtLK4I8
zL!tB@_zKr&&;7dJy0^FIpKs%pHZnJ#p1p3T+V5{~tsnmW{`U5C-RNyk?i8Otdoz9h
z+|}#%S>^BhnbzG6P72^~2Q`$YdNuGFJbbs~ai7iiJH<Qye!Kno5Vw9xS(%ynodRdO
zKOYY7-&_9u-QAu4e!VWfmAM?ewd%6J{oL2<cI(}*`Fz$BZK7|D$>vyoh6ne5Kbh<g
z+8_I5X8OF7wcqbfR{<Fg+D!%CHN-AoQ*ftx|G!_a?-ZZ61#MT^T>SjpWK+oaG0b@p
z2mdfx9bl<`y>`2iwe{@X@Av(Fv2|<q^=IpLzdPkFUpwXR@9*;8?}^9P7}o#!=q^|P
z=cCF={r!I~{fdJb0j3jDg%>dUY&dWK-)4GjS>!pJ&u5a?<=@-$^Tqvs@Z{ms>GAXS
zR)2r?s9XPBWcu8xpU>Od_uGDpm^N)%)LmY%88Bjv57dM2cE8`0cXyY4Z2b1T*lE+I
zeR{k7zTEeF`ulz;EuT~51=<;zbAO+0cwA-by}I9TZ9X0mwk&$$F|X#+Nwejsc|dyt
zgKR>RtX+*o_VsmtFMo|&U;gF&@!}5;4(jOYrXKH;1#Q@ztOD9NT=(nca-08uK3D#D
z*j{{0GJT6Nr1pV1FJfZaE;)t+`^$g5T>kueeEr|cUw5tR|Mz$OJKssS^LD?T@j7~Y
z9_W0_&o|TO>pl*G=>yXVLO)nb8aTJ*-Q895`|bAnUH|Tu-&gg#wm!c8PWAQm@$>cf
z|1lDeExBlTU4PGqLpr*;PY*OQ*Z=<ie)s!*bBfPd9*+T?dbKU@Zk5t!<b)Q%wtoM=
zs<`^UUz6AU{qy;}>{`ZzOPm)N)ovW?mHzzi_xtA$4mMkUK4aV;_y5P^{>^D;XMy&K
z@A#f~Yl~)l-Oto-@9)p|*4z2y#n->Tzo(y_WxDf06ZgMw|LuRj**tUp{Qv&%k*#a^
z|E&J+f(Ogz*Uj>sZC1L4qrubc@>d3ie|u-=@3Y+h|6g_4+gqhyZsqU)JI%KG+ml(@
z>rS@uN>5U`U;n@M*yF-J8Ox$CrQ7dSWrO1NlDEF>-fdg9Ou4(e{P~{G=RP+e+r_}J
zdP2Md`-}w8E?nL1cP6#VRcV0kr_kH`<<gs*o7Lm%|CW}$zgPREl;7@0LR{t3si3O}
zC3)C9CrRh;F^t}pb28Z9b}DFQGCa04^j_ujxivo?w%^>E9qwoQ^~$<?V&J%e5f=m*
ztq!zQgQlooEbdQBOjKm&lQ}UpJZ>f^0pH4AZ~JSOY4)|0w6tgb-}n7~x4ZJmM0apb
z1Wk??Se(gTzjqoaC8X?Qg_#Ma6IulpF#GJd>}RcOUH0ZgpR9G??^$<um&<?de(^s)
zFHg_9{N0&zbFFXBfe%d{&<exS!aA@?06LNhHh1lcRa%E1YLwQlc&)ki)z@c6a{67M
zHE0bhQC9Ut1$t#Z`rN9rc-`|YDTbwcb(e~OyLkqp$hCvRX*bVjyX8O;aDa2hOQiNQ
z*e(WbEStYh<{(!&Gk8Knmrl9#wI>WRMz#*T9LFIY*_J<RvG&{;7#c#o!Sx@+vIF<A
z_S`U(*&BEn-G>b5E>NX&!wcT22K5UTV|H3WK50l*0aw=`c0^ieXsU(G(slf$wo60z
z-itZ**cCQ8<0A-;5s<P2M%vgqtsp6eWzfMv(8#zc@^FDgBAq>t9H(HXQLRk{>pOr=
z1rZLI!|y~j@(_bL4BD}wp_)reY!`?At+Q`FxBxnt%D_;9Sd3S{aMdcF_QhAeE?l>K
z%c|?MPgm^GfX<~dL_imlfwriN;~vdHQdZyu&rKjdter(%hJyAkKw2PpbbkdT9H1n9
z_g8ot-3G1eoFRs#Tw7yx`QMqBmBI`R3^Uj+*R@TyI1Va0BXmJIV*}5sRi_Fpykg~F
zRe7zh+Pkyoc(<Jo8v}zyXV_um<<EUVozzQf+l=QNu>^Hq4`hKhyEdc-cxBqT#CaIK
zs`B#|3%-6k$m^q{5d*^kPm{mr=gc!_WMF7GY5q6eqO%y(G-<dB&MT+0V1sHts^{l`
z0!n*6r0Jq|f3!;g3J)YqRLKE~LI#Ep^>6O_m%ra^2wMx#5nB5A_{aXo6Sg~UIa+Gy
zxn1m1f#RWM27w*7T(+$6b!rk6yl58v<;fy3H*Uqu>x+8Bn1x)dZ$CNY8o=VUJ5gy7
z-xASy4##DayZ`9c#XtGDv3^<lxxK%t4(dFsK5zSZ=j(^HkYQM`d$CLoKvt@PWg!HX
z?Ic;-K<%{yz3Ve)O$qun@8Zgb1v4&YT=@<e^MYt=$Oey-T3t2q6%#v_dHd?V<t14L
zGftm6wFzluECa)gEKqs0AQ-e-KwnkzyX|u2)0wwx;bUG<(^i6)q+B~;aWd&XWXua9
z!SI9IxE5nL)d)IZ235nrz(BQS@}5Swzr&5q)APN&WXh%QJ$}6HhkM)>?*q3+7#I$O
z!e)aR7&fHMT6Xf#A&cDIx4uvD<7F$3jEoe64Er${ltPjL$iOu-gS>jrPoLEDd*0=V
zPq)0?hgi|>BMYy&8EhrgBi~d*7fgJxPx~bY(u{-;q@c9lKr&=T^9Y)Q9oP*LSSG0_
z-P{M6O##Ip2p1%0%u-uAWnX$pmW523iPTqHW(F%|c*75*gyF#~Q{Tz0t%bMBw!YV#
zE5-9{)22;2PV5ib&@%OdSyO|uYW7V@x$}KapU(2!@8H=YOl4M5khJze|Lhlxd7_gj
z?SGK{SW1c^kc2$bexqa|hwZbLd1@|wFF99=uU)d&t@b=<U=1=N2J$5c?`Xst&<qXP
zh^9D19kzhRRHoT8S?3#QaCb%leM>XU(=G;GjG;wOfvt(}<RGv6##W{>e8y6}zveMA
zFx)wSC`Uo-*sf&HQsd@+yyb1y{a`Coi8HCGsga;r(-JqN{vQK_&t9xWE^2R*;Q(*S
zoRp341q+;!a$wa0W`+a*(MsCsnOLp;5D#@-O!&M8XkBIS7qmbl-plA+wV(U6%iDej
zd404`U}*Rct~D7L9_;$aQUgjt3=9p@XQ8!TgfpnFWME)eC+&X#UOY6s1lNrW3=5dy
z#xpQ5T+Ubqs-+=jKuI4qL`4D>!kpG8YIh9OM^Hl;7#J|ee23&-H7rFjhF8f9Ak>1!
zz!S5WVPIfTn}C>NVpx!cH9avfFvK8F(g$EIWI)LTxrp9z2%3r*7#ObI@wtyWhRMJ%
zg9n<p5OGTL<uC}Vu&q-;tF;&yhGqo=UBiIzD^VF^*4t{3jz1HZWd?b@tae-8b~w>(
zao~OU8W9Eth6j*Q3*qINvvhQNE^k|1>;Ljfg2D8uQ&VAsJ|Hs~gu#8d14lGLyU#RF
z?s#u08|ioZowueda&dUz2)H;iIC#uc>^FFf4y>7hfx*0YCR%HRfx&>7X&<6|I`kKF
zgTiSvuYf`Uj>#+|$;&IFDF`0!)a>fgyKxx&{!lCT&-3;FCa;a&o(7$==oD7}_pSE*
z-tTc~X=&?zMDDMvt^4=$xhdMjrOzx-hp8ZUUhTJ=pi2&J?ys-kmV0{|XzSR=<MQWE
zPFCNXeSO{jn)ka(UxVjU*6n_`>&>5SxAR^X7$OHBgTYFc7YxB~PV4VK(=J~(<8V8F
z`u~4_Jtu)q%Kd()*dIIx^zCMPeRcnFxoVy6?(SHB)VY{t2SC;9kMDNBUMxOy?%cCh
z@wgo&+Y%4Afu{a`{`q|V^I?AbKZ}3Qv9GrSO=pE0gNF6sj%d(SbYP#66kq!_^xeMS
z??6*&n?B20m&H{5T_3Zj!jRwoPk~wPttmTq?zH*&Wb)5vv-7QPgBHWVO<?fZ1`3W3
z@8{Z9n|=QLIegCf^XH#GI@)bn{Orv9edT$1dgpDw$AES{f(|fU?l<?;!^7>HtG~aS
zV^?bxy*=-35onDK!aRdUaF|?=uRq(yE4|J_o`-FE+<)WhZ*NY{v#r+q`|pUb|C5XE
z@@Jj-ZKs&uuQ7hV=kvL*^2h^13=BRdj8+Fkc7MGV{rPtO{@B8M+ukm{zWx~K48;e{
z{LhYb3SUo^XJ9ah#M&|fJEmc!Dkx|^fBp>eiRkn6^YeTs-KqQiHoW${^}8L)@%4Yd
z+V3j+|L^b3J(ZtR)2qL~J9}?$_4;3+V~g+NY)*m9z7x_XYdtObcwcN;*}FSC=Urnk
zcnk7$&hKw;Eh|5zoSSbyzgOBk&g%c8Zhg?yanAjHe^<T#3EDe&dYbP47q>wB47<C#
z!~dEyFf?op_geY!XV9d=`^8q9=4`t=9lR_MWDx@c!;Y1IE{b!_v#YiGe!srnznfu3
z8dFJw=C>=s{!iC#zX#r7I6c13(i60QQ^vN+1T=YfZEf^q75jfblF!Yxo}PPqTk79m
zUp@cX+ez}ZPrv(qvcKKQmBGtDUGmmn`<9)Nf#KQ(i%xb=q=Z%P)4*qNwCv4|iJ(c-
z1C7i-UoM}&Dfjj^kOiQrQ_#HW%U$8|wWgr`hx>lN+wFayX-D?;b$80|*Mg3f+*JAb
z*&M4<E%!c|lXJ`O&17ch`|@=n)K3tqL5}kR<FY&K@--7cXC8Zdd;feoJ-+Du-tW(T
ze0&T#MR{rVwYAaHXU?2?`rh|1m;Imr`1ttem&^W}ckP<>^XJb!KOS{g{{4D=bL#17
zTmMNw426;hSU^*pJEQY<s<!jVo?7VK{_o2yW%s_AZ@n)(i#|L!C}UHx;dLccHH11K
zGV|weZwMPs?vSM2_#nLtO}MAPjKNgx{*nJ()*&6v#2WZTi)%wu@9Zew&GU5ht2g;b
z*UOm71W6a9S=lePYqwwd<p-$zY#^fYm%!-1Vje&;Y796jFfcHTh7BwvM$-)}Brv;V
zqhUi?*!-;e1~cHn|JP-^OJ$DVG?shy_3PHtPm8`mn?McrPVm0=pJ}(>Ub}sJ>+iqU
zZwAY~dipe4UjDrj^o-*Nn((@*;eL_K@kgKMU;X;VlK<1azyB6Lwtx*r9S8<@*1;D4
zzqIvN-8a~>o`1~o=THW;K?9=qk;jX`nlMj*N`RRSmIo1-wF&C@DFXw;s4<{`0^`xJ
z0S5yE1H)*#frSLgdFt?5=kKt!03bs~^A{)-z<5~ZuV=4s!Up31ExG;nTA@t(`HB_S
zuV2@jetP-)Kaedi3=HtX-v4pg?yuj<-q!su{Whh&s`BTx<Hvt5cgo%m>*&Gf?`$SM
zwh)W>zh+(f`N|33-+h;tJ^pd!iCg*Luw-CpfDfAazl^H2uRaog3MTbnX00W7@ENKU
zOx3fGHod_C!N4%ugn|YH!)TWc780X<EqF+b_9tLLF<MZ-LV|7u#gF#Azsqm#iet9;
zx9_acQ4Xmt^`%NnG@ZCyR;<<4;L0lCXs^09FH2*wloV6zfr6ZiIs%FXSsYrkw3HSt
zU8-2cv2~dMi#OBxBE^os7R!s*<ehtM8u$JC@15)4%YS&r%wRx7CkgX96nLc!3y%Zv
z3LPebC9Po0$73!|aE5m(q2^#|FT(qiP$dkY!-Blu|M~gZ_Wz&Hxwp5i)s5b^rTY83
zd-ebS{{J!O>eZ`eIX5mi^V^oNZi6l~gle7E$RL|=^6lN-+povh?>#PGzsI?qZ)@S>
zV{#P_8twl5cwGOx=e+&@J?8goHlLks9)Hjm)+_-V&`@v1Xmvp7_nXb<t?K?%{Qmwv
z|Np<gwm+XtuKjS3{chFkwV*2q|9`X0&dvr|BAvhIBUc{k%*LO~oEI3U-LQVY=kl>$
z>FC(ly%x8(WCr`&d~^Ywyr}L!@6Tc5J~`W4;qkRsSFhh!r5X+zTm;(>CZ;to$R>2w
z{(L(9ZsBp++`GHJPWrhncDLTYf7R#a+1}n)`@8DnQSrNVpf%HA4Pb)f0^_usFE1~T
zj*Q%yvv1R;ORe1ER;915yx;f#l=k{9si&ubPH)uSssvUIBR060{kzM}@ZtGf>+*HJ
zv&~}7_J6yTt^e;|^uB+;Uh~OXUHSO<`0ih?R<FO&2h#(l4}2<MwmKkmdrxJt{r^9o
zQ$NqI`}OkC`~9i8xodyF+r7SBzV1iYTlf+nupS+8^99U08>dd4>NnS_^yZ&0FE5AQ
zt@(U*|F3)P@^v?=-|xNNDXbn9AHV+9p;qp{pHAz8T=n(q*SsAM+d#8n_y7J+pI5o;
z_4@t)Cf%H8TYYPD`uX`kL94*Q=7WfTEy>6GO5fbr=$)2+ZqCoy+ZYpWg5%@dT<hO2
z7WZ3Kf6Iy9p10TH|Ch`D(K=#p@9g{>e*gEo-S4Ax#B4vEP@aB9yxUdXf8LvKxAWgW
zIM{6a^-A#m-~ZY9<=(v8{r=y3d*lSyVE^{Ip2(j^-TJ$p&#V5otd}7IG*6=X?Zx8$
zZ@047e?2Ch|K-i*^I@g`{`~BdvAp!|?(W;$a-%~*vl;2<=42l4lZ`FC8hW?>|KGV5
zg^xCU4hs+8{dU{!s+UWr@A`bs`v0YTlmyD~ua2ptL3La9^>uR9Z#KqNJZ!D|@vyz@
z&5er_mEEJ_<KKUHcvyV??d|#T?)`FaZ|CoSJ1sgd^Y^#6x%c<|-Sqj|wQIXxE}LET
z;UN3}Q;4IcKq1HQPm$#XgZI0&+wZ-4Iz9f~+wJ$?9ha|vvu^jhS9i<rzr9!ee(#Sn
zNgFc`xAE3jTua)Ru`wd%WGRaC8tM%gtqx4u{cKh?=*CudKA9h9)A{7>YEJgP*#C5P
z{=T2_>tH<wu$>G#Gwt{Bi9^^hvf)2BElU=dH4vJIh+YF|Ujjrmlw1Jsn?MDIO|c8}
z4}=~K97s4YFo5eMI0wua4IFSVfCx~94WbcvG;rWyF&a4Vph&>l)PqZd8KWr&91I|0
zH06Lo0gOje4mcP<1hG9RkXi&D%~tTR7|mAjpcu_o@SqsYR`8%;AbZpXVFZXZTIPU4
z0gMN<%sICI#_sCtHmA)R4)4EqLrSw_fzz54fx<~aT35mjdbU`-SmZQONyx>hY(@MF
z`3a6Ze0+RnD*|+_tbQ1BbagfFu()!P&rD2ES#)dQ%iS?8+e0{Y*Pd-YZfHB_`|;v?
z^#}TqPb~p^7fWU$W<ZgMu}jPiVwj7_h*?WA>Kt%Hfe5lAYuU{@J><0jAj6;-bA`od
z#6g1w>-v+?(4k4_%&1tsdNpVWH~0R&y{p&n+htq*?aRY<`E|eV9G9=Z!_04U;mw<z
z%a<>oJ#%JD{{4M+f4^L=Ps~QR1$0J<vJmLtDtGzXEk}<Y<&&|v;H|&+%9Sf2-|v>+
z-=+A|{C>@4(eRjyfBw|y@BdTO&L{io$;rugYro&!`~TnX|Civ4@4%)Wa5F01DbDcV
zQ0>Q~;-LF|_I^0TEo)P;VHGnwU&-y<?O&fv_WyQLeg2=vn~RH!&z?Oy*L3#$`R||2
z&d)0>+*tj7@ApaXP>23=Z2Uk6gyrx5TNWG~Z2RxW<Lu3Aqqm!xn_o|#Uwf_mer<W&
z``Pp6z5DfgeST`{)1>vNw@mqfZkb~F{c834U0<(7-`<vcJM#10-R0|J<Ik@QUjFOj
zae3>qHxZzFv_NN#eZNzDUiBvGknN2d%k;i8F~sb6`t)g9TH3jp=g*ued3I)|-yDmL
z@2utOemn$?9<SP#bMun0zs<$s^S0#|%TZ@N%<R-bXXxFp`@ME;^!9ni`(LeEeQn+P
z^u)x4{B}PUgvZxz-CO;A+pb-=<m>+w;?Vu_<x9W$cD3jJe7|2GzkA<2S?jVjf9sx1
zbicJVI~;W2o_oLC-imI>A*JBxU|?Vnc5L7?IGC1}W>xs;h~?*}PoJ*J+w<|*=c@Zt
z!{cuL{eJ)cp+io~{pbI?efjGD`v;rZLBreUX1%??fB)a#-{)Wdk8E7Q!#)|yOB0pd
z&&>iIL^nNCnn7(Y==8m}cXn>>xBImszV7Ez(3I9$(6otJ?yW25=31ZsJr{ISRr<L(
zFR!c&e$Dnmf8UR!-DPjB-v5U=5=1|E^m8{e>;6BVPUr3a`|b1=L59gWpP$AtG;n`^
z(9Hks`TY8Cr?l6vIU5!p9vu~xb$*^LDAliezyJTf<l}u`ugBM~z5D$zzx|xg`=(Bv
z3OWcbEj@kryIrsK{-RFQFi3X^gAUJocXxO7i-qk~&t|4uRenm@ey7OW+uK{#zHZOq
zcK-EuLAxWqgJwD2ZohA4Z5@4eU+r(u?82_ceb&1kwn>Ag(7e69b@lbjzr473`l~0%
z6L5S0bSl`40?@&I=k5R3<nQ_D2D$^wy6nvh&~(GP-S47yr(a&?n|p81&o$4VJ$qL5
z`K)<#OiWH{>eB4>d$;Ya{$BRt!a~qFi1ojbH=QytH1Ilrj-3Q0w?l`VxVgFiSDb%%
zxc$79;NGmdx_v)?{`B69x&qa}(QJJ^>O39;!+-F7GH?fj7?=~Bm<PgP&ZQ#nat4{g
zfMx!Gn2|9eW<^Gw0}fy?F&bImU;q=Cd*??(2OKb9Vl;HX!2l+(^i)U79dO8ih|$mi
zg#rW{jMiC@fB>CDin$_SG;~HohXM1Rumhv5L3p|#B6J%5Z!9<0jha@=aI9bO<f%rD
zLo-^MHr;CRX!6kCVVouG62x{f=>zi_wd{+>=626$UCULn!l5a{e63O&M_1E^){xn8
z9Wu978u!k;xY<&2#_{9o#>IPHevkgQ{_~!9|Nk=b>5VqV;qk#Rnm7?*K}6yl?Z_d5
zYc%a3g~e#vK?;n~F$qLqjP|+_VKI_=-9CGa)6Z?G|NqY{|K6Rg*W+%Vn`>SD`|bAs
zU+#f+3cPufQ+~HJT-rPjwC+6r{=V9|HkF@@a!~JviRrwy{wov1A6tL>za^mSc8ZIO
zb8l{1+S=L*8e^X}ZQ8Ey_o~lVgElS9wJKd@Tm7x%xNP~CqvG);FD@(;6Bh>!<j*$C
z-PMCKXwAT|Lx=-3;0s!Y|9buYd))eaF5I~j6Y6jKH3T$$aNg##&-=aK?^V7(cm90&
z|G(eY&$9jTp!w~st*gc3Yc?{o^Zi-88@5dp62al~O0)MeFo?hJHNThf_t)3Ax3}k~
zf{vI<OHZ%<|M&avZ@2T$SAXCC`12}uxrznSc{>*R+yDI{k2bTgV-xrqmyOBCLCfK1
z&zl!#dVgc`@l&7oKLRaI|MK$k-HOM(({mvAph2u=U`Qwed*{=qB4cCY=V#K>(tbVe
zw+D^y$5-9|^QUJ2-*3_WHXn~HjS_@u0n;-Sm`WNrzkNP$zdiAATk*5-_}Z_hK68J4
zxBGqBg9D9n^?yEsZgx3YhP(-YfkCYuG{PTSeAe{uuh;9JpQ-=(bo$ii;*U0;w|jlj
zT|W2qwY7Wyd^$b71l^Tu;$O2e?5Hp{HU_Q!pY!w6r=n2v`!%2E?|VEue_!VJcXwm!
z|9;ig)7w_~_!#%UzdLvC1nq+e-3*!vDSv;DyAEaGzW)5h#qQQsUtX-b$#4H>gWGKe
zgO@BX7=&|fZ_Cxy)h+$?<>j*F%fp|^*L-jc4i3(}z3uJ)d;kCaet&y!b$R;vdAXUH
zD`)5Jda3{S-=9A<pot#Wx5!gX2bO-^Z>RC&<8k@zwZFfa-r{KR+?KaioZ-PE+iy3L
z=h{|pn;ut{nOgSj%uF#cv0FQf(`TFKuLI47)&BeW{O`Zt@3o(UE*O%lda-cY^y#2`
zmv+6~c3bcFKXB;7hyzoPii1*PpRDz*&FTK2gTU_BevggbmXn#7xN!acf4h|3`_{~<
z{&q9H`svhg(C(C7Pp3t%s`_+N9kj<|*4(*oe|&r_YhPFM^v{<sCH*#^PNe>~hZzs1
z58MJz>Vc+}p3kq}cRj9pZSZoxt);K8iHVDYE`ka>=i}?UHSg}O(C>CXpG;o1Y?)Qf
zkAil7`M9rdu0`jIB40tnz;Iwc=!&I7puHTRxx8j}{(0ZeOjLFcs}<b)>a_m;Kg+{W
zvxnN5UH10K6Gxy!F!nbhovjLX=Fn+Ja5e1Sjj<MBv}*;9MKCeiwE_nNm>4?A8thyU
zF`AS?p#Z_7Nf{CjAaXP*gF*p{M|w}M;s1v6<LjcX<uV-KfBxZwv>-lR^@EyS3NBhM
z8QsgCNwtJaEwVqbv}eUiRi&<DVn<mxvvRUKx~8;cbQWkITzs&T<B(6^Prd8aPBpK4
z9nM?sna^)?y7a#NyVpON_x*teGKj)54K=!t5fm^WJQ_HlPypl6_5I*r01;SLxpIK+
zi3G{P@My|`g#^QB%7F*PXv%>H#puouL{MN3<&JKffrrj$;J|}If{5i)qbUa-T+~WA
zS(Td+i`4%W{QL9s+O=zD)xFWr?p43fy}z$^_FguKrS*uDZyBPG{QUg9`oqEYT}4kn
zrL8YI{pQZj)y2>Ei9#<#%n3xq<_)E5*RHAA*@xP0x%v7I)BUoir}jrhN5gJbL{VBK
zw@U8j8&!yfKkT<`xrx5oc!TK>XpU@n8@sn^D`?CgGy<J{eI4kCpyTrOf9%i4?kZUc
zT4sJk*uUia-SX{Qwp>|0zphH!3>wN1uQP1ZVzfG7_WjM~^WVPR&M$v*Vj^fEI%qWb
z)yn0+9(C*g`*de#@$;(3z2;G|vAO^M{nZugzP$zY28<1%y7}Lj82%K4?rsO&1pt~1
zaqpK~`|89*W!pa=4udvTfX1BbtG;bKF8BJle0|ROdA7Ab9=6Z5EPhtD7Ij`FCos=}
z{l+o79}k*A4*B=<xp^9B9s17a^Io5sX&k$w;GzHdd!^T7-`?E(ylf38)GH7wN0_Ok
zA@|Me_50s7vdd+Be|OjX48NSsj*lqk5-~h@FSLL;Cs|xSE+;kh>9U`vPI+BlAD>@Z
zS}ME^bsTt`HYkL?y<We6Tk`R~+0U%Y-`%M|9)@RN_)yMyfpObL>-T#$->>`qcG=IV
z+TmvNP)C^m#GanLmx1B`ol~d0R<B-depWwjPsG*Q?{~|+_t$@Uaq->G=kuh~+WF<*
zeRz0y`<LAi-$2Me55K&;JlC%FSKCd{X<44P88+Mn+X%W);iUTfFQ@hQgAU~C{dse9
zdbEz1tVO|tX?6cWM+Z%Gm)p7YKExOZ`C$Fu?cA*Uf4y2QSNr9n?=6mow>g=c#Tg#V
zum1INd31dI`@7}$@6G@vEMav&&_va@cXy+&F7=*nRsJsK`nuTLYeG>^8OlAt`-0*2
zjf2hX)z4<8gU(9&^{`!j*Z+UNtqUKy+^_#%d%R!%e#QG68<XeSRBn2|@Atae-`{f2
z#8<!FD%S0Kzvi>=_4V=ZpPZar`|W0WC}?hG`(Ko;77Prty&L#8oZb8VUiIEjr?f${
zY4huTt^E7@`}d3P@?U>E?$6(|IYK8YDr(ouH>=n0yOp%@M#Xdci@%aKqU|g^@PFa#
zY!`-YQ?1|aSPVLqj9Xl<<macSptHOt``c9>wm#l3pI=-1x9#@%)ph^>eqR^6yX-PZ
zpzI&&7MX-@G^4Se^ob~+Ai>W-tpXKebLQywUT6r9o(=>L2!_#)BO)wl)N%ZG_TJx?
zh}d_9GXKw5Ea2TNqs+Ocb#8~!k)sM%l$0jrgmx<#ah+P=>+&T%c#CM3Agk`;oVI@v
z0U_IcBfGse9_Vn&69_+}^TC1Rp%2^K-9OF5H$FdJddaeQ+4bz7(sDKD*q^I&<nu8w
z1Yl%&ESG4GszF3Jwo69I3m;FlwpwVV7qLp&y>H3=_x!)5o?rd)rNk`nj>Q}J7S#{@
zu+!-hRAeoSRHnz*xr&MT@%`3%esx#r<e%U7^LN6Bxgx}1wS!yG{`>2H)R>(VJ-qK+
zWswFqxAmp>-&tS4{G!7R8&6h#*QFBORts<RM2H@1hdB+Vnjs8x|1##its*cZ;o3&k
zz=MK;fnnH$kLK$0pD@+}KzurE{0Q+5oE-HRJSZ3#7)J9oa%haE4dl=mO&iFeF`71z
zLt`{;Acw|i+CUDC(X@da8l!0gIW$Jo26AW&(X?@(!@BfU2xyIcOwGrmGv~}Xb8T((
z=ZEd`|KijA=U7bq{eHi_cw9x|vSrJP{(imw{K3KI=Rc1jdz|5bm#PE1L?LL)0_dLY
zJEhlSE8p#WZe(aU@$K#H&p)5He{W+h!LzCM_qRRYZe>?~ILQ7Pdd2U~ce`GH`uqL9
z{^hsOemBJAhN&(Md<KX3WGp6JkFU4gUH10Wy4c-C_iMjDUEFVXN_Be7q~mhcYd*i3
zXIs4~|Ng!`e?FbAeAKD_=>RkTlgIt`=VqB^f4UOvuX|aY;lcar(i`Ft2Xii`%{IHe
z<>s=pX1UukH~Y@c-F0(0oP7%}J-ZgchD)O<{q$-zni0GVbG(^K8U(*Ro1LGQl%!-`
z{w}6wTiM%NcdFm-y}3O<zV6S*<IiqxzgML#9$ONaxAW<=qv@9~U*7q4+wD*1tlvNR
ze!t#+eL4Gsn2+;Qq3%O=$K5v=&cBs&`K%pbrGg8}HzIo$?$WE_@k_72PR+`CwdJ|7
zv2nM3zGcOSgl#!Di;jJsIdkS5n@XemwcqdV+^YkL6ezjj5$6R)w;TTUf2Z(Do6Y%H
zbGVIHl84Q*?9Giy=hR->piZ%^@dJg5nZ5n|t=ZS-eXO~=tF+rb{?yHb2^T8Gpe917
zh`Hd=muc^sxb;qej@3H$xwW<R=zRUBZ*JU(cz)CV@fYWIzPWFwGKQ`FzgPJG)D+A6
z{qB>`=w6=xb-qga|9{(kXXoC^xtwe9`^K_d%k7?SufLyyMD_Nm|LwLxWxww4&%K;G
zrEWbW!b_rmzE8dlP8D~<{{OyVcGvACZf!4r%h=c1{H^;R6Tjl+i;IhA&W=8pJL%=i
zmuuqp|66nJM>Qyt{)cUaB(liJe|r||YqC7Z>E&f>KDa@j@xY}!6_0x@%icun`}u74
z<$3S#?lw2SQ{a5B_WRvCHJ{JcS8luhdg=AoPxpSmXZ`kPxBk8vbFIsty<Wfn+|=;6
zpVQNyKYO+*`FLOPXGKV$K}d`IwDk1i=X1;XeoHa*2;2wd9kcv<bNuaos({Y8TDEMN
z*!=hR_uD5YC*RytS^WGaXxC5A^WWd!pMUZsrD|{7=QrDOZyQ-#&-T{eyXEujOUSuV
zqVMO=pE7ne7Pq(MN`DJwkTBfGD4WnCYf+#Oy*=-&@p+rc?ecXNo<*;&tc)qW8XCF3
zuGa4No6RaG&)ff>BdqS1a(S6=<mNQrNl$vs@12k>zXQH%{91Ir@1!rk|9+|3d#B{G
z@66e=rO&maPRg~pHSifc0-d|H=kK@Ml`j^yZ_2#9Y|ocV-akK`*56$I{$5P+SyRtR
z)$ewy?=F9T4s=_6;p1Z}C*|w^Ow3-t*X(}X?_AJz_CEgp&s)XgPVn3RnV`S#htl-e
zvYQ6>sOisuMfmVO28R0c+UxgBQlDRAw0ZMp@Ga$EuZBPW`~7}=&-uwIIXOCyA3t6`
zS6W{FJm@xacllZq&_P<yo`bT`<h#4eyU!zs9m50pQ|9npD<9&&y|dO@m7OpD!?;02
zbfu7MmuXkiA|=K|fq;W@E;@#0Z(<i4PFt<fVQ8i!5hzgYf8j_+N0&>$ELH=vkS?j0
zUg9f1|2{nZbDIJCiNAYi+E(nFzcoht@XhkI&*zz@Kbtvo?{~!(0VfU=f}z3bursO<
znhH3VgHhK(9m4>)G?K|o4Ppy~!4j8JYJPlRT)A>(#h)LBLBYWvA0B4EHW90RnUhYP
zI#uxTk*iI`hlWy-oxzcjoyYs-m2GY3mWu4$Qu;c~rt(wE_aB#+`)@3L9VV%!)FSXu
zQ&;!skxt>lZ*L;61#&31Oz@xPp)}DWqFn*vP>=9{fQGr&<&W;{EUx(WM)F_OeOD#H
zT_rD@3LhU!e0gc<g-e%`W=xrT=~7V4?lRtwA3u8d`@3gmYF@c=Wx@LO{Kdt^JaRS?
zXJ?zI%TBiJbU8FvdZNb>tG+ucR;@bJEw2B{rrfIh9gnN4>$Q(FPM$jD<mBWu_w%LI
z;rd%LFSnK2><o;H<4a9Vy=M62R6D=?gozUm+UDQdmdhO)8hUM`hw!uK&)Y%HySX`i
z&EgYF)6dU)`0#LhL1}5KZ0iJnCr?jKE-tPG>(`&R;!<3~sim)fe5P^whbJe6U%Yyi
zbY_NO254Vmp?Th&1N`=X8dis|KV_F9JaPW~{wY&LzP!BLUMk|mq3H5K&c3ea@9*!*
z_V)74Y`ll2Xa)y_hPIZzzV`6R$;lcT8V>vG{(kuT{r=+k{dH>|8wH1iv@BY*C~Ces
zHy2mI&rhi$A|eM49bys_6XOw{v~0<yO+rVH9=&koN{X!OyCut(En2XE;qI=|#rNer
z7N?}7C|Fxd&$TXh>lV|EIG(7drM2qbW2K24t5&TtFfed<eQj;(lrGy&7pBnA&^Pz?
zN*6yrmn!SNE+j0>$=8?n_V)balT^JUj!(4a;^ML>e8i&WH%H^^kDHs*4GSN+goK8k
zw3zwl#QF2?B_$@CHgA6T=FOS2<}25&YinvMc(?e+zrVlh|Lhlh6tn&3=jX}4zP#Ks
zf9|`xyW0;OaCmcjyZ^D1Pux>eRlB;n7OY#xr>d%Yt?)_Pu3c7T@9uQYG)~{t2THaz
zlUgp{;RNTC%%n?~E+ypU@#W{|zj*!n@$UEg4zG*dy`lbp-J4rmx$oD0m;Lhf>&DE>
zYG2;nmCnq}T%&w?&iwiEJUl!P9zA06_xGP;QOI=g;6ad2Y;0`}tG;ANNJu<5E?=J_
z8~SY3s#OI~P6+ZyoAKn{-qt#4lF;|3#kaTR8kW2Wkg=<gm^yXpn#D#FXU*!$yu8fO
z-JSjJ?(*Xc9GeZ2j&SfunQ+|QUEaQJo7pnIxm{DHh+GRy)iN^^`}XZy#`SfwZM@QL
zlE!HX4-d7@Fid7^<CE<wdwVPKKm%h(XJ;bF^3|&gA06TBkuv3KYikP#3Tm1)OKQrL
zDG3=F9TSz^AN~0FxarTw9SasPNSoz2e1CWM;-*yZl6Q9`)6&vj+}UXywJnEJSXg*X
z{C>I0%E~p1jXwT<zd!lkpPw7HZEM@O(eTTcF9|t0JlWaVXJ(u8KYaLbjq<6j<?rt)
zT3XI5<=Of5vcG-en;RR~B%fFsyxi~L$&;O>JUh2keokAlV#S6&#pz{lZ?QT%J6|(=
za%rY<x<SqjgKLIQCe5EOZ}<OCF-Y|3>FI{m-*T=QrYu^qf<sJ9tf0L7_%z+<4M|72
zO5WZQm6MbE@jLE;q@*MVH+S-sDQg!jP$+qSPu9!JE934iQ!(ABmh$)au1bo_$mpD4
z%@Gt7v?zGM(A3lv5EG+Q>XVbRCSl!bshvA_e)#n1P<VW8t82H|!*6eI2OW>yQxRCO
z{<x>7=M1}At2Jxa8WuhAm}65J^lHcD<^J47%zIa?&|qO>dvra%{^{Howa?GVo|$hS
zf9&K9P#)fxe0)RI*Q_@;Ha34RZ<RLB<M?EJ_4IUoK`E)O>hJG9_Emm)A-M1VziP>4
zNzXq%KE7egmLvOWe-}JF#JXem?!%Wa3uj+n=bDh9ux8Dgg!J_G8#f{>EG!;;e0+S3
z^68k+P|;`S=5ou*%1TH{9lCNw<otYlcPA$%tFkv8>-YbY`uzO-aq;+?#*>rPufJ@Y
zzw6DLoF6}a95{TK**yQ=lYj5tzwc*cW;<}_j?Ct?vqDeu=OiX3N|<Jeym|BH!PBR$
zU0qyz>i^3LtNXcpes*@@;>FE+vAZ5TI@-Nv@u@o#mEA9FPWP9PluZ2f<)wy}mXn_!
zUrtWWg`LIeU*6spud1qQ`t#S^++4i++ndJe)5F)s)x5Z%$RlGRASNa@!#rOuZg165
zgQYb;zFv>NxHj5cLPBDJ|9rcS-d@%ZA7#G1yDPo_&nNE3Ejc%C-Ez_q`}}Y7)~&6r
zt*p1UWHJW_2eYuUZtT+$HZ`w5arSJgtm``sP0fQRPH;SZ`gF}=6VIPNe>VNGi93Ay
zH22$ETMvJDc-XM^SIN82hi-4rU$}0a-iq&^rs+mI#m4Tv_&;iE)=?`X;osliuP;yj
zC9WU$;6Nj@k&lY}q)C$uvajh#NJ~4ry0Y%twJRVn(DC=Tw}$2KVs4$0cliJBub{a2
zaVs{(7J*ME7v<(ds=JB7_iH}$YH4eKd~lGt<o&(5<#!$*?|=B_O;76SX%GMW{A}cN
zBFw>oK};utL0nw?%zS(KY15`{-PfS6qvPV^!}I6QpA8islQguoldr9b<Pko7?)LV4
zkoMo--!D!+-d9ji@Zg<OOmX?69Xl+}%rIoG{{HUh)z#q(7cV|+we5_Gn%bdz_vC~+
zS@QDoHf-6lrnoLCDXHM!pURj$6@vT!|Ff?8`s%3FxBYrHHZsm_JdKTwjAl7E4phhW
z$=PyMS68>Rv>Z5iu(32}X2th+vY^t$y8K-Mcl*-V;DZMbe)#(J=v3|S1#8!ywc6&h
zWa-j_2M;o?kKf<6cdu<sOw6k}vv1sp$hozJ)4gBr===Tu^}gy&n7`=Kr68Xf28`47
zVnIbu)wegC+}zz!&!64cnEc`U_v0H94;Q?<W4U7G%8h-x!Y^OG?3Ig-i1?werZ|7o
zl`A0!_1<NBl$LHyFjrLizxT<Ll$N%(O?`^fGd7FVef;>5gNLVO|9<<|8vm{G^Yc|y
zRUbY$*eqdNWnyGxv?2AhSVeWUvZ0}1`nfrRKGz=$OG<WbOg_G-_V>3Lmc?pD#>RyY
z4lvHKua|p%em*F_9JEq0e){yOgkciPp+kpuxMoI0McvqzE4|Ereq8pOZgG8<;#fw9
zurRS--`;kA`BIXRk+ERO5|-cJ-X6XlU*F5j&Ua<kx~{G+makQF=FI7-`}=F*nl(IX
zYHB;m-^=O6@9Sx3V3=cF&R11cb?3&bS6Pm^Gs5HI_{7D<TiV)+u21Rf<12e}qfs+>
z*%hhZZ*CgPSQI!Il%Lbm(rW7M<(0FoIx=^*Y4){*r>CZV`0}O2L*>yiuH3^Soi0r`
zH>W?ou+aI=eNekczW$FOGdtfJQ!_<H#@E-@9-d{Iogy3j%*NLC;xb=p7dJO2e}8`C
zv@-|J&9w&QKv1jeH=l{6rR20}({AjkH13nPKWDKuhn0op!2SF3mzViAZ`^2DQ(OD+
z-8(*4SJyLht;O^5@-%dHj~;AhFZ}W%@WzcB9M8_JS|7jPZGYY033KQ2GThjbDO~sG
zqdTa!d3$T?i<_I(SFK)M_~eA(pKrJGcT|7Z<Kf|vSU#=y#fuCcNh6l1sHh89ueL5<
zu3l7B6c85H*3!aK^ZBef$d*=aaf7ro5-x6Thfba9D$SY6!O3~>%gf7&Sy^1c!ND@t
zWjsrlE?u!|6)25;dv~|{(xo7fV7Iuw+wneGP*r<vW9p;x_WxU!E>$%$HfF4;>AknV
z-rmd0YeUvmtuHSwGA~`al!Jrgfd2kJP1WDuImXA&FU&Hl`~B8@$F5z6Zrzd+R`)y7
z#w)!edDpI8pt_e&-i}9HT)a$Cl9P|`*euiR5C8sFpP6GRJlDFMjlrh=pG;$8W5&%*
zs$pxRTBqyBAG&{E{_(Ni!~XVvS;E7^kDdHqn|*D~!A+^B4a(j`l)Sw)wNz&3ri6n`
zG8P34o72uVEnBAc+Tx6>tLwvSYoqTx_MWcy@Vx#1HO6}O_VVg}a~%5RY*Qrt^WNOu
zEiP@AbKuU-V#A6L2|bd=ZPv>cFJ=}O7yt9;^ZAGk35<uQZ2Ek+{QlKnXU?jdn22z4
zavFJDF-c8Lbqo!iTFNtXSHVLjHQ!k+mo5cKNJtzwd6H8%dYemOp`n~z4M%-_y^MXG
zO!~Pw2Tx2?jy#@v?D}<aKR>?@-@YBYv$J^N>eZ*Mgh1t>=R(#OkS6(wmD1*U2QFXU
zeDCOUh6{VE%XOl+@ywey&&W$nzNV(epzcq_9J|`6S0BUHMjbqPlGD%6Z-zl4Q%y|`
z%Vvh!pP!z3czQZ|cyP>_JGb(9Yg^l+)$8{i+J3*T`*1t|X#>UR)6@0a_wBPgbog+#
z@3FtDL5aUzzOJFUnR(yeZ_zQk%Y2V%rskiWWx8R*28W1<8CT?U&YU^(;K`E~QSGn;
z7cUBCUt8l?Qex7)WYhPz+wUuBYI5%X`%SuyU;do6o`r?PWHsMIU833o5)vARTi#qq
z)BJO7O=R=x@byXe_th4ZmrvidySB2@l26{QXQ}t}q_eY3Z|p2qZ(gz~Jt5)33i%t2
z{lW*Nt-l3ttoZoIt$%Ov^K<)Ww3w&{1_t)ZX>YMs04;31m@F(T{Qs!R63vBYgHG6&
zetZPZR`1@uV_@+0^_8(KV(IJan_*jR#>Okv^58*&qyMF^pFTCsoGH0z@#2enDvKEo
z9B$_~EPE3Hs#-zO(;=uVu{`DQ@#E}_fmwTDYXK4y6C-w)>27a4xGncKs8+kPyPUuJ
z`#aGX^>q&)K5RU6$f>2Z6;zhHy1L%jn9OdLd#h#15|x-;C7f%cx2MTY?%bMv9n@|w
ze|P7hm^;X2-QxOfTeq4zIXmw>s^YXc`?_9BTU*lARiRtgX_l9lgKXGc{yt51qU0@u
z)_4a81}0`^!^%%7@9uzl1Lw}20~Io1Ya$L>DG6V^cyWexx!$d9x!eyPm%l#VCwq8H
z=H;y112<O&tMAyo`|+Ebo7XHddi?%<|N4Eux^C||aO4P!u$s?-Gc%1rjq<#h|Ns7i
zn$L^f`?=B>tIockW@u<=U}kpg%gf6f>;6`O+T#88{~p|1zG(4c!;A|GpgO9qu1-h!
zbkFwf=2c%_G_F{oVUmAOMmv1nk$JY&AC8L0D<~>9{?@BJ+{OzkxVGiqR-3U~Aphnj
z)@|Fi?Wp{$=AtABDyl<Qhb5kvptz&%ua$Y;!$Ykg#bxjB>CRw%5f>K+>OroJ-ky+?
z(=*dJJ?ZYQQc%GmBrLqsPeM|XGd(@MqPm(pZSvgxpFe$Snmbqa(BZ=$zrDR3#eISC
zz^z+R6UzNr8#Zh((9qUaR#Ris($d=6ryI3}gPD!zz+CI{4W+NcbRsq|h>3~a*p%9>
zAhzK6ks}W7?(EB!E!(htyZi5NZ(o-rPxMeZabCEqt1IK$8cD0tS1pB)kA0js+qGNF
z&`Trw`nuT1Rec^Rhh`e57d$&7xiZ<h>`h1P?y{3c^X}Z(U9NwuU%tQg_qT^{Z*MQ{
zn>~B><72(jJd-wlJj`!@rTWjStE)eJ`QqZ_#MIN%18VR}swV4OSV$Z^c<|2S!|nXn
zZ#`M)R##`|<m7Z=dwzW6vE)~0XPeKkD%HBREw{Uwo&V6id;8AK`0$|sRC0py-DGut
zmfegKdwY3LojSFl?r#;S?{Rjv`Sf3LQ>RWns-dXZB5-NTMWzx^FHXSe$&{uhrd6v~
zOPg-nwJWMXIPmhNOH#Hkvp+mI2x?#cf9mq-@uj8S5gU_S_jaFWJaF@-<o&wex@B)}
zC@xO<q-bU)7QH?1X>3iLv%fz-sM)+Kbal#<p0!7gxV*WyclW`&O;@j6F{u4jq7%C-
z#O>sb-4!2|!q!9tzJFBAAYoTyF-<?dFLrksXBwkb?zBVi&&)KA*jHou?99x=)^3rJ
zlEu%?99$i~zTm|L#e+Hy;emmTot>P=`sMFGxbfjbfnyHSr*Kp5o~(Cn*98<y9WtdY
zKV-i7`8(vsty`Cl@!6>P&T_df(m#uJL9gPH-OHG^M0(ZQ{r~gXt^e%l)4#<hpO_xL
zK5k+7`nb}6cB!XCBqSvd9z6<5p&Y!tsT2I{Y$`r5WM5me^6RbStgNmbJ1js|+10C4
zcUP~tFvq4+D0sQwQ#<{cvu7v2xUlfUr%z4Gm#c$XMZdnhtiRG~CkiS$wqyv($jC4-
zyn6NO#)d@ZH*ek;l)Z_#aqHHjS65dXn3<)`3Hi2Y(V`6*7Z*j9KbviqE2X2WYnXGx
z;Kq#`4?aCT-85@T^y4F)!ZU0ti`KTzS9b4fX>VuWvv=>ri4z+qtNSmC+?>V}yvb2|
z*$3-_2Mliga=nY)`-|#l8z!?oJ3G5QbamLnv$M^cVk{<2o*bP0sp_oL7r(hyS0!(6
z%?^L(cim~yoH;SCf7@qgXERLr_4~|+hld|NeX6=SXU*Lmh0Mjz&NMDvs>+b?_t)1A
zn>HOfHB~!1cT!SrZg1x0Wr`{)EukSZyZif(e|ma)XP!;%uacbG+jxVQ`>nnDbIaDP
z58u7(Yi8%))TLG2FK2sbSLy2==Wpui>48$y-1n2FPMvC)c}c}_uUUI*YvQ*zH(%V}
zZ{N^A+a@A1GVy4a=vJ$R5jw}NtPE!T`}6a|!|fkFetc;A?`HaZ&QG@741MzUeOt4y
zUyH2atNFuQacPO?kAJ`4gT}qyZQQ=yym`r{?d9*|-t9kp=+Kfr!B<RQ^7s90`<=h<
ztaQs3hT5B(QbBE46(P=^o}LG<UvrC#PmfA=Q4);WlEKK!%j>3j)7#to@TaGzEBmuE
zGB{rSPPSXPa3LtO=H%$`@bYe~|6jLb_ipZ2*4@9qzgJdJU^s9*TiwP+X8-?x)oTq+
zuZP^<SGzI&yd0b6O;DFvOIy3}?Jd)i7Z)5~NwBlCgT~U9EnD{C`}g&mKlTOi$XEmf
z?7u4L#G$y!jr#&*WMyJ7Xeg>r*4iNBg2I<KHz$|JBqb@C`+4;A^n3sfB>ejFlDChS
zpTB+L#ECpXC)+n|+T`|s!qSBc8$W&eRBt)4CNMPg=<f3OQl@75`s)v}-ki^+tE;<Y
z$r6*SoT8#l3)B`(n>zLCuEqYfTefTo2n+kBuRckBOC;C+Lx&Ez?f)(zEzSMv-O9by
z-;e$N{(fW8(^G86ul-q|rSkUHR_FKk_7;A8bd>FQRdsdp-(O#iJXGzi%HEvNby#)&
z@9*!0-`~Ybs!Zb7joRXHex5C;DrY+$x1)g3{_mH`JV7VfeSLkuyt^w6+W63%%r9?u
z#<xhYsjG{t<joDiva&MXK3@-y1Al*iPo3ap2Wmo0nml>o`t|(5!I#;NFI%$2<k#l#
z;O{rn=Rf@V`g&0R&D*z?p}n%+US2idSt^f9J}um{C+5}j?9$TGn0+;plhyr?^+*~|
zm^-((?CmW>j}v}bS*x!2-m|f>xv(-=-Dkd??74I2dSA8ApViaDv$FhSSxJeDiwnz~
zxpOb>udk2US=8!iwe8-%TJ5iWZg+Q=gGSfp%$@u2!Gng+&(9ls91rvI;+m!t8T9;p
zTwEMz^e64yoX&;L?T@C%*CkHq)4gTTdjIqD^RIK1R;*dmbKrmjXrSo-&-3*lCnX>6
zGxR#qwr!hPQE~Ck<6d4~FRrW<zH;^I>z=dc&rknVzHnt^z?!8?L!ZxRYXenfDYBh2
zzkK-;)va=Cdp<uykh$^Oo12#>n3b~H{rmRi`hA&_(o#l;SKm**y}e!h%yTV<ivRy?
zqqgOov|aa8*DLCM=Iw2|U0q!%(|Wgl`BGBy=ElV8m}1|rFD@=V7g1bXEMr#_5q9y3
z-{)s%1A~GNRokelvRYYL8TqK#cXfBaj;)zLcW&>aM@jECPMansA}X3H*t_%Czk8Z4
z=jYp}%Q~)Gv3hm!-tEuw4qs`0ed*#wM>jXN_aE8$<v8A1AK1UE=qZ<tt*xNAIJ>g4
z@{gZC6Mubq84x6N@6x=|*Vhv7?kZ)lJ7;fM_s2rbZ_WvesWm$aAG5{8##V~Yzy9LJ
zMrBYb_xk#J?lQ(-GmX<D+(ARxcA1B=S3=s)CW6-G?~XJuGGAEkFCP&ZdGOF7CeYYn
zR~Of*Q>P|OoY=U#{JoNz8k?J&Thq?$tX@^`X`nGcP<!Lg&(9aP=iiSKo@rn6qhWXX
zdr+IzqWYUoO>M2@vZ-tT{r#Q%{oUPy(o)yiX1Nu|Q&UnB&d;;muyNzWM5}N6{(SNV
z6@j+Z-;SJ^s9bqGc29-i?d|#PvuDrdxxCT1@R7@#J3EDc{rWY-FuCoDb<)22|8ng7
za!1z1?q=ECY{>vB`p(a@l`u}@`SRsU#qreC)PvWrPv3pIR{)d=&YV3fC?U~ta<aO!
zuWxVpo!{Tz3knD{+}m4y+CVmX+O%n)bIt;Tf||s1qpnzoDNW>f=XWi><|C_;va+;k
zn8$1@hK89lC8tc8^5FUN>kn@D&Nk!BV%*i*%4%e6EWI`2+tF_Erl^Lz%*;;EKzq0T
zzKnu5UteEOo#0V7W9Cf9$jF_6-S5nEZ>g+ceX%8y%U)PmI3qjT{MEab*=D&-?d|P6
zK^w2HkGKEx>9qbH>BFELzCG`5)8xs*X8HGYKzXwG`MHk1zIB^-@H5OZ&2GEA+~3*T
zn|pQm`n)S_?DK_kb90|OdE#OF?d$b;XLon@yu3UKg9L_s|9)jlE>B(^ySr?U@ZIV!
zFB)%e&p&+fBxhM!nS^=XoSw@YQ*&~9+WF<ZY_Dz0jdpQ!OS-Wk5i}Ih#xJk;xFjbt
zGxKVc!SC?kWj>94eSF7yrP-^is}IHoZ%O3ZKTS9KT2#*0@YUh#+vd%adv<PaclrB!
ziC<n^H1a#%w{oTCqsNbT9-lR9)}HmJJ3Bjr-uL`lX>4F{;PiC;oyT9jdd0!PF=5vU
zD_z~S_ufypH=Q+W*4B4fE0-)`admZFIa_Gzv}xCV%f4E^tn~G@6Q@o+lGE1KPJVEp
z@s87%{in{I6T8xOV1Dg4$$NV$58H-?h92#aG+v??;O+09|K-`i`AuPKqZIA!=U2yU
z)`*CV+<ETCrAt8vb2jMqHa9c($=Pa^E?$4;j1LP7OTv*3L7qt)pFeoe5WBnV;IU(D
z&TTv^OLbIKSaz4aZQ8rn_WSlDM_eSNrB7R^PBeFVQ_*{MYxZ@kdTniO=YRl#Q>RWn
zc=JZ5R9I9IG@QvNW6^MPbNcn2v&(&ac$k=(Hx@i}a(j7WWn_h%v@~~ea`L;r=T0#d
zdcK*NE3f1!hn$~hd-%r2WNFiDmo5bb><<N1XD-`TtQ7(`HkFq1@bFBSFo7XHKAwe@
z_2BvQ>#xlf1SJAF+o}VnPjhpN>$$8BTPv|_>fWE9pD*6BMI<gR?vCEHwNYCiiM_af
z$8(!&x7d$|?eYfo|7xZcre-}qH&>wh=#M|2&wqS6J$_OC{e3~^`a3E<DovR>m9<=b
z$=lo8AA=@~3JV+e?b~<dbMgCowo8^TKYZvA)9vl~>9Ub(poY}6X>Fha;AofVi)(A6
z=YIb5<z?`c>C=<Hytw$`+qX2?$h4Z8nuPrPe!bXT2d-Y7`h6Ct!!IH#%DQz$znS+#
z(Dg*1PJis~vZGg423O8EKi)6zURJhkK^@N=>vFv_XU+t~#oc?r^re+s9Ml(|6lnBQ
zL9Dy*^E2N)b$_MW+S<PMnHm~4u3o*mXVS*>%*@Wi?fi@P?Aa4InZIRAC8z}k>MZ^F
z^M_4cl{+_?-P_wcW^a|~&6_uQ{l0{Uhl^iHG4S^Gma(mxvQASIG`Kfy+BA#ucQUJ1
ztzs!=Uvo^tx=bhS?5x&~4vrf)Z+gmJUg|CG;_7<v=1s|dIonBvPT$&iB%AK;E(euu
z7cN{_Q5>TpbnyIn{;H~~8#@XYFEG1hXm0LaP+$<YHcIvDj|qy-1#fSe_DC2qtqxy5
zt<Y*)PHyhU%l`Hcf4|>9z3R@58xq^|?;o3>=qw;0ps?b3@7}$(=jK|s=ic7tS!;Xk
z!i580Utb6Hy<>J1I0igl_H5Rp+a75@K0M^$<vqG0aB;=@-TtDvGY*}<az!M3ecaJa
zsi&97%{NSD+p=ZLhp*S;m9@0Ij=j7w(>R?^&ZgqRgB^3`$i(a{V&xXonc%4PGbuAO
zGF#a(H8u6j3`6HvH}2Q{=AAZe+NQ2!psktNxziS{U3<2g{fB$M9A{SJ;+;D!-`&}H
z*fuOY{Q2KH3q3u*SC6*&hu+^;D<~{{*f#ItBG&iEDg^}v4UCN^hnhUwRrWUO_2wmg
zeSGg_XUp5y>8!|p_1-M^7K^sF_LtY!`IC?LwR)&HWn^gN-PzH|%+BYaH1Wf?h5mQ%
z?X6DC&+mVDxc%^r8#AIKK%<<Xp{)xSCfvU9|8P6Mho|Sm+IZy_hR@H=I{WzWY|jjK
zb!E-T$q|s3=kIi3%FWGfX>aF#^>@{=W4+Rae}9$Em^JIr$&;K)6FGi=d)wUK&+p{y
zd~vC__?p<=(@K42a&mGuE?=(x?#@o;<mBWZzkes++LF2D!=L<Bt5;8)J-hqb+UVl?
z)920|JJ`$~7#7AB9v=SX)z$7qr<<qFpKtH$^ILo@D?5Aff&~xa{Z#%J6%|dGFrlHT
ziD_kQWX9|npnUy5+(k(7Y!`ScP;m+8>Q$?p^78b`#TjB_V`shLU9e$;K=`^CM<*vH
zBO{|7pD%CAjh-=kcJhe{icQgT_!-v6?+1J3;UU&NwZFHWE6mN!-LY#|(%V~G4UCME
zCQMlS>Q&Yp%VIW1N5_u-es?!Fwo|80Em*YZkZt*$J9j{1VFzQ=0|Ntp{CqyYa=oUx
zx%rp(_ve@T%&h+TN!7;I_Ty>&{a1D!cH!ma<?WHPm3n<`t#dn{tb|I+@)avOZtFaK
zc(^^t+`F*2Soler=J$7Z55Ky)T2M}|Z`G<*QNsUJg*Zh-L>|0&(eZx&e>u?f?qs1$
zCP$7Pdj#qh@2MzU+sS@uPt8vu{kS~`4m2{SPU&0w<x7c8<tG+Uy&JVH=jMY7MO_(P
zJw3OuFtMJVo>zBLonI_kytwe=BUjJ>EwA1=e_!9Do72yO%HG8#IkvUGM7HPOZ(F@u
zd&`zBuViP>pWnYd|323<KZk`27lLL<x8>e$16{*rZDwdFSpNRr(#}&s94||ExJ5-t
zottOdop`v-)Z*p0Bb~w?K0Zgb<=#%2(g*T&;<Ga|J32d8mIvNi?B4(2&6}Q{9v;wq
zv4NuX_4V<`yF|4gynf9c9UXnI@aWN_GYk@$goK4F-@p5_va`GU@UyeCHx@nhiinK-
z*tdGsszZ}hy(i3=5s}^aWVw!kfxzapvraKFF?;84{r}@JzlF86vbMIj!SyTW?f>^g
zZccj$n&`W0z{&th2fV>8MR}l+=B3`#A3Z$W{^HtN>GwN6d??tlW5<FWJ0c98w_RDk
zVS_+xYpa2Q!HV*jygWTV84Ct?clU_s=+hdq(f|Ja+fo1D?%VtO@$YvuH8Dv@NhKZY
zk!-qo;LEeKvpu}L4!ya#`L*oy$&;H8HnS%`J2SIsr}K-$?fes`O}qBs?#kk#B7@{(
zJU(+Q1clXnCInh-`}5~d!T*1?_gH_La&dDfW@K=bmzTe}wbk40<&*P^-TODBoD^zl
zZ@+%a;=;Xqa`yjzDEs*MNGwZUy<>;O?{9CNGcq*d_SJAcc>FBx+_`h0nYt@iuS%+?
zsH>>3*xA{ET+7A9wIt6<^9tXO7Z;V^+}%Ch+Ppsgin>tegeg;wXvkX6wJHV8q8`n?
zSO4cnq0d|^(Z<Hc7gtw{tNF}eFg7-3VP!S+JLTr+$Y_>#r(=HoKgsoRdzlzsynda0
zXGdYg{<^(ae6{RDxwyClI$aFR&5uvf43_#@J#|9fmZ0QIOFS!nebIb(Z!h<Q$JJry
z=h;r2HjRxTAT$&-3HJK$ybr;P7A$BGR`*MIbflBF&$jZD$}*psN;kf*{Pd~l%q&yx
z<$iNleU($4=#h2yvf!(qpgjMt9zK@D@$<;us;{fgIVCCTS*bty-{hj?n3a_^H+xm>
z?{5JC0SU7GmbY|Vcm4TOV^i^A!MV@J&YW3u&@~s*XrJI8U0P}iT6M5$6_=>!)T-lR
zVq!|_>h1=!;{-n4U$JVHQ(c`MsCyn7dbR5Kv**u2$t$3I+F$jSEs3Xoe}Dh+&(Gp5
z+1L4Y?b`LV&)3)2)yu0Z!OTYa$^Ed%$j+uFrY$))HyzY-;mC||b!EM`x4J!SZIq+0
zZ*Qs0vrnHseRy<~J0v_DG*QT#m*dr<t)ap3_*k!VznratSog!{&)YkN)t!_kKDZuV
z?>b#C_Q9h^O<!MM-`uBFJaOX0f}*0PUAwGwbaV=yo)YDeFko1^bm@-b=X|@$-}8a`
zQ}%UpN<(I5UtGlc?aj@@xd$xM&PeR3`8g@tW_RuHvL8QwDA?N0P4(Fs5E$6_>Q&ak
zZ+q*lrn{&JaTYCHGjXC|+POKL{QUe32mby2y)oe+6KKr&%o!d(KfeoCuexSrXgprB
zY2kte4J(6}FN)t^$J^K2-F^7u<KwJ9_b@h0)ecWO-X|NeJx})6_xJqi>FF{y6#}5T
zeQ&k-y?wQyk;Fy*^X=9w29@Z(La<d#OE?XTjG7{Jp8fm!;$m~D%Fd!sPds@f3>F-;
z_7V70E^k+pQJ}O+KviA+a!Q#~hYx53?c6!OZQHh8DO_Sv`AOx?n>Ps=87Hi`GM!f3
z|FF2vnPVdBD|6n(ea`=+uN3|WJg(Ssf~j;)Ti|iU|Gcj({;YT`;FNOm&>^O?vrG@K
zjov<C`gC?%TiclZb+UbZeIDN4%~Pj}Zp*vdr5U_zL!Vahw{PE0oH^r?lcS@hrIj^z
z_U-NY$wxW_EsCG<%$Ykk(tWCBY;5eB*xh2@)Ad|KLq$tUOAYJ))#TjT!pTtZ;en%0
z)E17VOPBUc-V_=X)O6=g%$Cf{ZX38SOrA99-^c%M9kZXVT)8q4GHb!k09u1`^ytx!
zjt&NfH#ax4-@AA3#JO{6lEG;ikDHEV-`{7;#wXKp;DE!P+TUVpqqjf1w^~JrlZ{8B
zA#QIKs2f)r;>4l2#4{*KwgIvh?2<uxditGRrQFN?=eK#NG)<c(mXni{ke<%IF`{Q*
z?QgDUekzxI=GjOpP2^~6YuhUJYW9p78~TpTiO@OLz{s4Coy{#RExls(>dk#B;U*>~
z35kgZZPRmdau%#ydD2R(ICfWw<Lzy^*|Gk%)!$NNz4a_CEDEkq*}By<YD>mJt4Vhj
zoDKTnJI`ij^}UkU*Lq83b_QK8^qXttD(lV#j*btD>kju@@!7w!_>-}a*Z!5orNI4}
z5~VVA;MjZUF54~-<4o+c@;kiZ@rT8IFdZu%U&%i|&z6Ia@7Z4KR~HsK8)jY6I5XQE
zw8Y3cB0_?RnR()*Nlkn9*!=k`m!>rF#r`Obn^$b>{z%L=&u?3_NNLIxJHNH-SFB+8
zP#Ado&(F^rQ%{RI>N)JM{;p@1bAy4Gm-orjr;H5S4_rKUj14qad~0hq>rRHdckalr
z^UJkt-fUd=_iMO_m{`)04#7Jgr%Vy4`F1m%M|hK{oLt}4)!~od-Q7LGLuE(VTPYb?
z*@?4fbDNu+uZh_y<lN4eDjTfUvSY@d{R<Z^JgBRuudVIu;=&TPHtMKscwnHTrzhv?
z3Zw5&P6}TWoYiyYj88;lB;$`A6B!vmOFs@A&oj=uV^L9EeHlE`{$#&PIdo;<63&w+
zPdcWgs3<8b7rwrxtD>T^VAn3GtgNgJ+qNCsnteUOJw-`Xl~qtsa7XEDF(qYXP`TFO
zqV(d$ivr;nN0JP6baW!zr|vx1%nq8>P*qh82nlJKIaBgTlA*b#kH3F^smn6ZBvkbF
zJVh-nE>~CAfPetdbmxxG%3|FYx8+7(GfaK=<mBW#Uqe1Ox3#sg<>ch-_<U)7y#2f5
z<%)#`1r9MWGG5-^3zsZmDK0L4H*3?@t*w21e6KssfNFv5d3T+Hf`ojX{?68m-KAh@
zx$|80<hgTYtG>Vc+h4x!pGe^GiG7eX1J3kF$)W!jC=LBVOC=u`_XUGe7@F{v_2KK|
z3Q9_joSSRCR4#sBjU}i#{o_Z4q<ZrC<Hy;x!`3vcTc`Ky>uYvhUEP(B`{eEQ9;du{
z`RY~D<72&dj<IBAWqtVk`S6y^%M1+cd@={j@7EmGO%oRK_4UoUyGwL)`uR2&rN*u<
zu09#drcPmXCI%)ZrVS-8gB*3a)(XnX_AYd8U$kNchfpWWVz=Hy`uqPJl6`+~FK8J^
z>*eMC#y%(AA|fO}J*RhfcY_8atjpd!c<08$;OFNT5FYLx5Fqe)iOaklJ9a48*~$I>
z{@&fgg99|Df8_Y_;@JYVzu#{E@pO7TsNy;1*}2Ei$mr0aR_>2?%kMKXY}vYXW7*p%
z(9ACbXekD$$ZBnE)ky}I&|>fsy7SbD6AlFh2HW!Q_obho=cpo7xSNMNwyey|oblDC
zr>F0vY&><!>)OQ`puw%bzrXL~Oa#SWUY?$dk|1bdrnR*-3k%DJzLO!PrKUncLRoVc
z&x$Pt&0;-2Ki}Bz#JSz&?{|C_l9cTH@uLE|0`ch4qiY@;21Z79f)=<ufBNn1?GvX@
zH+!f!ZO^+4D!uIO?XMZmT<E#tQfg|dqLNaRwLZU`O@oV)W4D-YLT)avwYBx1=l1^-
zWrOtsjz4slU2gWu;_Ko%P%<bDJib!CROaQ1$0mGVXa5R3zOvWK@9&DoSNg5|Vy_gw
za+h_tdS%h;EW5n!N?{fx>3m(>7c5>XQ>Poft);)8KkfWH-LDl64h+-u<MmFkda$vv
zy|}ei+sVmk!J0K^tomX$ZrtcN->!Ct_2Q`L=*5+vpK<W=x~8V8&Y3%R;?$|F%l+pY
z`Ds<x{{D9KKqK?U($`_&VKW~epMrOHEEyVBuhxF_`0>P9vrZYQ8NYn_vZJS`W!W;d
zIdkSH2z4?rR904g`2PL)fktN5os5D1|NT{*=uz<dTkf9f@1V6STg4XS-`OG9*x2ad
z?VT(g;+7?L^q;Wl^*Ix4YJZ6|v-2ODZJy7-z%8cpAa45V)vGTqbY=&wWNd6~)JYby
zeDdsB+o@AtdBPJsC#yX?)+_zt>sQy(QqWpGmf+yvnEiEg3xh!QOy(lkf&vr4^YiVW
ztF3Zzb5k-k6$ORT)TyG|x%bVTEBkuJnbg$O!si-FN=)^CKC+95ieB8FAMfJoy0K4P
zTuV!<;L#DzoSU0k)ms1ho=xeUZJz(=#6;zix_`&#*Z(^i8yvnq&NVAbD<m|Ob?4#T
zCR3+QwW#}J5gQzIK_#TFwY8Oli)+zy-W88c#K0B(#6EBt@D*N7$OrDvw0UL0ySPtT
z7F?ISg4Zf`i~25CTq%@t14sEEa2h!G|I)Q<$1W}Pe)#aA;@2J1r;FFr)J&K^U;lB+
z8`J!IGN7T~IhMr{?h~y+3uQs`(SLpxuUN6-!KJ0%KR%t-U$|@;+eD9+Nt1+RtV%j|
zEAN`HCVD%cd!LMBR+iS3DN_o5d`JW>4vXDg#>$|gI%VSuXV_W*)q}ThOJ`qOlQ?I}
ziOJ8-&Q89)Ef=&v1k{AOwl?~DR6`wdqvBLsQ<Kx;V^?z$7#udde=KiT<B*i3WMXQ%
z^Sb1N$Im}am>}@w?QQY7*5zq40?Jf`I6>n~DJd-*laDj~sE}jhl?q8;vvH$g-LIGG
zk?vEZA3l5t8i_7@e~(vGR1~y=?Bd0Vx1St3af0LE!GkX@E@r>IphdvRL)aBIgOtex
znkRnqCg;VA7YD9g6HD4Ck+e~w_ScupFVnBg-=yr`S0G#&x2K}<+1c6GXMIRXO=UGT
zHN9pyQ&U&hwWP$Pye}y^`QyL8)$jU*k~T^NFY`&1o!mKTl8}q5YvFS>Jv}~<r$CuL
zJNxupd1YngYk{e+US3|lRZVDL)mN@puU>&B^~^gr#P6?bx+}SV%^IGK8#mth+1c0U
zR#<3wYkU5A+w^7r^UqnS37c?kt<%)h+<NYOx48Ze>#okDN%u|$%r^p+4B!glQs912
zQ2}XttduXEb8E$YlOAy4-~moEbAAPa3lm7eaM=K?6Dd{Q-;j9t!<U!ADr#z=6^z$5
zHZ?KLm_2)O_Vsl;ik@;UZh2#2VX+|p{=OUgYOP;u_&TMesGOT`&+qE$$|G+l!^g+B
zM%gehEUfL%pPDUscW1q>1tpt+009wEQNyGo9B1ZOPA>G?mXw?<C?nG|T|b`b#}0v#
zA0Hn6c+{;gp`PsS?ad8ZPzD;#(sTI!;X}jz{q{!2#**q&dpB*`#C9AshBa^AJP!|#
zhK(CRy8%)s^qklX>gPQ^-Vd5^($UprY}h@|$H(Wws!(kPdGS^EcNVj!pP$z{d$#oH
z6GclmZ4&za?r!s<MM`JRoB<7!fEO2CN`d#%W-+j`vTA5(95{Gz;WZag&?@_jPnw#V
zm_U9=J0qbJxrycPudmIMCJDWcC^~rR6xYX(A6Kkf*S2zH=GxBYs;a6rj}4cvS;N!m
z!c<&boOftWgihPKb$YKee6Gd>A8zA4e4vq8QLOvo>Tvy89vq-l_x;^n&^k~bAD^t)
z;9tLft$A$dIyvB{?+gRRi4!NDICBP6c$U|_dGiJ|VdJ<z9Z~~;;~5m=?MQ9RU%u#V
zOh|*XuLN99Ae4er%EpZwL9++9wr004^`2f-zN_ZP2gS0tw_3k^DQRhMKYZ)ftiqt1
z)n8r+f>vw3y}cdOjb8Iu;L?-Ou&|_8S5|_05-LKR+iwPBW@@@9399+bXh=TZ=NK3`
zu`uYSv}u;erOTHKzrVX{#eL!Pr%x9ayYqwA89zBWdCg)YaVaS-e}DfY$BrGka6w>o
z_<GQinu}{9jjvst0h*2b^Y<@kpb50P_}8yPhYm4SR#sZn{xSi%g-_OML!YMbx^?SL
zoIiiOSK55Xe$U$%7=P?I*|Th!nqJI~14>$;{<mG>7KXXt&cp;Y1#9cw*ZAIdc6J5?
z1v!E0w@wZ-Gc(Wz4%w-kpoK-dO1V#-JQ)xk{`{RoQhGYOx3{<B`-Dhi%`;c8iYmMJ
zwM6K+{r>hg^7tg_SFc`aXlgn>KR0)0_Q`YS_++iiQe=BIg@uJxR8<{)eR;#e!tPXV
z+_cH*^Ru&&$CFn*n<ZtO#uF10qafCun2>P5YFf+!&lP{N&h^foE&c55Z1(Kz?1T5F
zK79`^#=%_*wC16Q``=}Wm>r9UkQ$#CUSmMokC!)OUtgDaZjL3WTj-&}^x@;X1+rEp
z4fE&A&zUnvLOo@%|9ra>XU`s;ZJxhi;X+1d=fhUq$*xL*@9yqCuAx|+e{YYYiwn!9
z&6^F=&Pae(QSaI%_4DV?3l}a3JaKv?B`PZF;o;#>R%W(l&6)+ECBj0*(q=gg)2EAz
z>BV$BJw5&KjT;gSA6{M6esg0Z^S*uiBKFtWURxi3-eTn&RW-Fk$Bwaqrp{Y9g*Q}u
zOsc4=ataL<t^W4L(b19d(W6Hfwq}Q43!M4$_o2_G+1C!-y&JoM`#ht9v9T~S8;?U#
zk<qQ~`TbX}gn(8G^!4>k@KAYiX(_i`uN14iy!^Gm)I$djFmQ|O9a$B+ddL2cx(@gE
zR2qXCmw$dfpRcp%6zi=$pibt`?-#&5kQM=_Sql~|QgU&1RWvdZa&&YAZT1ln5eWzk
zJZL2qJagvEj*gB4YooUdNJ@6v|NFrVTHCo{Lqmklv1eyzN4ihhxnqY#p3@Czue`SQ
zZ&Z1pfvIV#?BtoRUS%CQe*C(XyQQUN#^q(a<#jo^xrups=d4zpdHU>G(e<E|6qQGh
zA1exVUf5lp|8CEY9XmGkX%?HV2Q6dSQTyABi<>(!B_-tbtXJ38O23}r18O@wKR5UB
zxzmT+`9WFc-QJbY_H4<z+Ewba(*fKZC<T@Ef0xx=DO>_i8NJSb+vH2<>;m^BK#j>u
zAVr`~>YQT>LH$xt3-Sk~cmXvq{my=!I%f_K18A=O*O!-vbv?wDqN8uS{r%tH(=)|U
z>Zj5~j}0|Hi{9MbEk1SXRDn*HJByA(1{)8ZKF#etT`yI3YG>{5ZwC(_X0EKPWH>N)
z_MJO1GiJ?7Iz3HyhE=K7<0+f2Z%lUo^8UWOy5F1$RW+BEcy@GkIeB??^-Mn5zGH`l
zPQ-=<=az{*d-m+Z_wVhkt*nbva$<KDvCf+}ucN!WdE!LD?H^)1Jv&QHo~ilI>p4AL
zUs*?ohmDQx!sW}Ww_d0^+9e8F&U?6>Us8Q4sA2Hq_wVafwSPZ6WG;JuueVcJ{m_LA
z6Mp}Gc(~m#|DH|Fj}MKmA<r^CGdXc6KDm!*DkKF32MbC{c6M}dxVX7J`uX`e14C|Z
z?vrQFjQrH?i;9Xq+|J*hczau}hnH8AhYBb$zm7O#TlZ(i><I#bf{o_+_Z+;vyXRTg
zPn<HPWy1!8AHRM*y16-Bpwnf=nl&l1-8&~u68iJyvj2@usoe8ytJxTu_AgTr;{5mH
zaevh0Qe$J|g{xP0uUVsW?c<Eao+~areg6FMx3{<NEZJH8{oTS%n}n7vTh`IvpDx?4
z32y#_dI4X-!xNxLg?0--!xJ{3Q3`M$qV7uJt3}YJ1E^2x_ZZwY1@$ICeNORG8K-~w
zId^x7g39JoQ?(5X9ysvG+3dKs=s0M7lci<kgznG%a<*LM<>fne?gXv1-JE`YU1{F2
zKG|;2!q2ugP(MLSOY6qgZ1HDjXRCkRF@L`NzMs#e59)EOoj7e;+w=4D7w_67HP@=t
z>G`?2k?u)KDk?3}6?r*1KHTS*UbuSo=%b_E;HIqK{omi;A3rr!J1`*NfW^w3jO^^g
zhYv3foIM}3jcVS!d3W3tot$Tjg9`iqdRc2A!=@&TzrVkKuJ&ok^5xD-6AxUtAds|C
z;`B7#<_I0P@9*wL9#467b#?ewH5*k`RYnFAQ&UhorQ>MQG0vNyN#DFYJ<z1i+_}Ab
z_Skr+2t9fJd~@HiJMH}P0<yAaZQGNQlLLc-m{?g^LDNE|HffV4Pu`iWrKH5Pa^=bi
z9x54kcbVqo=0+Y*UI*Fo2HMb)n5gLG<)tvuBV&@x5A}sv85stC$L1|trgrAcnF-UU
zw{OqCuVia0o0*we@!<jE>kOZO<CzlJI|u)}fB8NJOM^Ouph$xc6nx$f>LEh4frlGF
zeTw%VA0G$JqQ#~E%R4nilP5^9QdB^oK{I&SgWvD>AHTgl|Fz8fo14|0oSY<7lJkFm
zdn;jCqyn0o+@60w>D!x|Tl=CTB0x(zdM<6ex-QoG&c52&<&3}H-rl}&{d)b!A#e89
z|CdvC?>n-@bMk|C@A|&Iy}h{h_qR34hN-Ekt=8r57S#U!23iTfCG+xv6)R3yO}kV1
z|DWxxEt!X__bhwP(c0O`dFap~sjUoukM&9$7#dD=)cPqRB-EtpJ?+4qJ29_*S1k9N
z`{CEuY_^l&?V8N+zCI_Yui@k4v*V;@(ng84wzf6NCwY^TlR+i^1P>Jh0|QWLy~wp2
zR0C&aowAY(4qq4ZP%ZV&-fHouPoIKTu<GdOY$$l>)NwTF#*G^r`c9r%6}lRfdqG=d
z_Ur*o7{9o_UVfTRB-6%-o_~LTJIBV(E%li>+aQstyq%@frHN103e=`s9k#Y9LdWg;
zy4XnflxM%bzP@8BDlXp6FK_1%7${i#>&wA4k((97x>>CscB(D>RQ>CVW_ccHFzeUX
zY!4No7q4GC>xezRoxfl7&68koI~_7iWDcp^AskXi8}%(MB`2%-I>p4uyjL=v=%LcV
z`XVqekfGt<-{04(?o62V(dpB#udl2A*Kg0b$kf`}3R=!I&%VB|m0SFi-1TeMrtP}n
z&jDJ>?>pPfF+5xxv>&Obx0jJYKYkx*jZVR@FPUqixAzr#-ORqX#}c$_l2cf1L!XlQ
zqeqXx9sh{ERi<I<<6_@eO!R13vqmS<WwQ3&U8RTL-roK?rzG(4_WO0hSDyJKAMZQ*
z>FH@fA)%&)&h4N2b{9S60_|{ldwct7gSj;e&vJv}zJ9ug)B7cmjDBKo`TKj0(b2O@
zd3KtnpOeWu6nvK7>WMNdE9;8Ys~6Y*|98i7)0QnQU0qzSGm0Feqjz81`SSXD`B|pf
z$E?JP_f~y<bgnZ(N9@VEJ2fIAA{Q39az{i)7Ct|I>J(R2R@R!uhRav1;1Cv`9CcoH
zR?Dx6O-)P;3$m}TyR&oS)~&AXe6kYi$^GEI7P!F;?!?36s;}fqzLXoNp2Zj$Ub46k
z)DeR#1vUJ>N}FT|Bqb$nsQjGPaWp9-Gt*O6z2$lqD=TY<i_(;7)0`qBXI7taSDNUc
zBD8STDz7%pr=W^(neS{ieSLlC@cOZ@udhFR@q&W^w8}s4-k#1SOH__|rmpv$Z5FYo
z!tmOfNae40Km%yc&(C*{ijum$fF~p@Ea}n`Ptei`7bU?dQ>QXAJbn6ff`^KPeVt98
zygi?)>chMG7p`6vUA1bJMd>S%*BV8Mhgvwl?)&Fe3|iK!+55+;<b^=m`FXvv)@28-
zUKKrd>=*|(w=-x$=;g~!=XSn_XJ#6M)?2(@VFa2{_xAP%4eNA^=^nZsU(XvH9Bh((
zjYm{ewBpAHMZbAAoqMalFUr2YuA{fNb=4}Z*Ef8=yu8ewmX>Bw^<~AC?^@N>)ghsw
zibh70Fh+F@EiElioIB^%&L?|ePi677!j3uJ{r&Fi<M!_GEMBs0mi$G|%r&4A$$!3G
zKu8E^D>A5EC9W6Kuy(C()b_lyR$VcR`<(xAg2wvqPx#LU9)I}}csx_$tMn&-NZaX;
zIk+`-xZesiyg#A73tZMd+3zU3ye=y%D`In6uflt)Kjn#ui3|;m%<N1I>*Dv{TXB8P
ztdCBcN?r!du`1;<G&H<$;ex~KYik9?#MnT~U-wptD!cU@D8FCJo}Zt8Eig6j)|O1r
z&Hy1Hp@7K9$n3!TlhyqbGBZ0@1}{%~e{b)a#YV#7;_VL}B<!jB%5~s4uU;FkG@G}#
z_py^VDt~@bZR3~ctFEp-GuK*N)~aN}u0XD@&Y#Lbz3pdbXM<+OPMz}7(AHkOXb}^`
zgNF|rzrMb1?57bO85s$h=FYpf=j7gYZB0#3L*u~l^TJ6RCDPB$0ZpDnx}|oR>4TOS
z{)<KQwZPN=TeC#x*;FzyASMvH6`k8a`$QMJ^(M`kwAOpNo}!J7%*~rOLFK}(^7nn9
zCb+x%;{5yjE?m5rC_53<C|a>{<;8xB`ryF8#+DYAl=Sq&r%rXv)Bdk)Y%C1wAfG$e
z*4@nw>cp;E1sb7Rka~LB7n?)JW!tAtotoKn<NgJekWc>LS`svswz3<XIiUk;mm;p@
zOSOaJ?usiYhk}%V#^*D2z|E-TiQq;OG<vV3Wn^@SYKJ9!d~|fp;t6U?7A#;WD=YKx
z^=*yNIW|>0+@Rt^f{3`dvXzz8-s<meE-oz!zdy}3&ritA<aBj)t@-(M`i<@R@}TY3
zpoJTd-Fl#T(A)<uS%Coo4IV11$~VhS^f;os=<gNVsxKV2RbMi`{75}L?cnj_&*Obm
z?t=<s(2$3I+#ZM0Qd6taS1jh{<|Ux{DU-BAhYuINyrc@sQmw76pi%bid3Qm3z2E8G
zcXEfej^uuQ>jgEFS|+GH`1JI2L1Cfe>1nzf%ic!)DV5iZjg5Wr^5w$|3!Qm{H-*N;
z@UXM9_ehy??c28xl;uI&+Za}@S_Nvom%YDt)<V_#<HwJnm4s2-ayWT;dH?+T{hp!W
z&YhSZNn<uaLBSkmqiy;3?Y89J77Ggt11+2r5*B8xv9Zs+wdLT&#qN^oDWFa9%^Now
zf_8%(?G{(o)Z}CU&DxZ`y#<;VEOaW9v#9{>Y0b#USm4?%#=+0e{^6sgaowMaJG)A|
z3!TdJVt0W?cei9-X0xsS2HNe~(Et3{p+ijK`f(|9Cd{?}|3?_Key(56_QI~xY!^2-
zrXLk~({!Uj`v8w|-dq4~27_8iXmc=rvEZT`G?@MalHuiHrNGK=NV0)W078m^{C9VD
zg4Up{TD1x^#_H$icc<8O)@<|qLnlvqwsk&fZ);;qN=o{0xBNb6;{j-O!P(j7paU1a
zzP_$(WE3=^`#j@<*xhBIO`S5bvW0JM7<#A(fwo0CIyx2<7d!j-^gIxszrXS`TRWfZ
zp<iELZ>;-U1={KlIw&UDaBIcKB%QcD65i8v9{&6N{=b-R)Df#?XDqC&9$j4Q&f7QH
zL#3d+T>Q!NHhy_K(EiK7z(7#XIc$Ag?|}mjAcL~6uM_?9sF<Okpx{8CthIoQOwWlE
z9-u|yc6N4Ke*Dn~t*%h_pLgK$W#M=4-u-yBdi{f!FFW1)<t{!d26dbM3nLn3H#Q_P
zgH~t>3oC!+u8@|NK63oHv4@&G$i5plB3M{iK}*!Ps@a)lU*pNk%iB@%Qs{8Yn<Gb#
zEU5qguj0!K!DGGB;pssUetvx4-rqlOpcoC>0eq;H`{9ch9iUCImi9>-C6@cmO`0*G
z_wDWN$-lq7jo6gJxh`gB(Ca-JSy_j!UKMq8bmS4<BrGn@uC1+oXMerCo}OOmJmdU(
zdj#K@f=1gwtBOFw5uL*73)ZjiFMofp&|3HPt5-@kHZs-U-=)r(#7nJa*!$1t?cGB|
zMXSEP0*zIG`g|7k|7zyeJC*$XRhp8L@<HzWnKLdC5i@v%Pl}tGnu2ENIXO8&<4u{F
znxI{i{QUgjJ<Z2MW}D@L&VP9F{Q2Xvv(5ka@3rplT9x<5;@?hYC50VJcPMaWt$Z5Q
z_M2&zg5J)?6AvcM%3fwS)%)Gbolh6<csfhFdC9X$yPwRP6*(*D-HIKGNgYbvI^Vyy
z+b@5XxX;+Z^8Ur2d(M5F!~U+~-1C{thplH;>w}sS?fmjdXJ?se#O~VirZT8k(wGgj
zrvLVKeNY$t<Ye{5{`2iVeED+Z#>V8-^OMuw-Pt+AIKA(t{kB6FFADD4x38nGPs~nD
zS($mRb@{PZS65%$o*&P>ZZltBU*C@(kNb;D7uhj-dU}G=4rrH-ZS}Vk^O8*~J~AmO
zEfQ~5Umz?fC@8p>1+-OhYj!w8!y*mKzUf+_pt0C#^HNPg)4Tn4zc^&A%UbsCt?hdp
zx+>)0*Vor|?ay$57P;l``N;O~$7B98b1W}E;N@Tdwf6qb&CR(O9$(v9_V(7p+xh!l
zkN3$I%dC&yzV2i^!`@ZX^kTc--Q5jZC{^)%Zh4W+`pC^{da=7y5@*&dcJFsv>NOQ~
zy26=xw${hLhn$|KTlnWkq37!-k7frPb?cE}6c-l<ZIc%i6tvt2s>>JepFC}C;^P^|
zjtM3|?%0@r<c393j*OvMpM>;ri*LP^P_}zduQF6gVNdeo8OI^Y3n9uc?<#xSb$Pk}
z<9_>p2bRyT>slAPdy)5aJ+^u#X6DrMQ;yv@|MB^{xV>EB;^N%v7EbS7q@fYKjOWhX
zyNT)P>eYQEpP!ut&HsXmM9{wA!otFi?(V~l%<KXJ0u7m$mnHuD^K(;rRL|zk#!AY{
zspmI%fff!-o-7=-C8M$U`MIYS^CnGdYG`1{xw(lI)a#q1>aDV7%KNq3?;Scj+dTFB
z1}V_VAG6JJCrp@-@Zl$@-U?k6;#g2%06JWxp@9L^+FQAD<)mp*(|dY&Ksoc{$B&l(
z1Ox>G|2_G0Jx>V)Hd*=k`FVJH3d-#-dn?r?s-1Sw_1e?(_WzH(UcX<@X5A{SOP4R}
z?l@5e+IALS_jBoo>=SqI$`%$D3Qdb_KRsRl@#20vAvyiHJr;5{6$uAjuYtDa&9D77
z^TUqrZth8wCh6=rQ3c9~pjvIt+_}B~J}rycS)}$}=7UyuU*ECt_*&M6e5b$hpd$Ci
z#^k_NA)1TVYl>=x9C&+syQ<FQ{@!FMX>eri1IH&cf*#*6f3^|I2FEQ}$uYye-eft5
za%g<|SQk8Kc*7Z%`u5h=h}~st|2+nU{?k)aE#<y{c<4OGu2!n9u5Q|#^w4wj?fa){
zhbyV6v2}KKTI#)9pwV^qo}!(mCg;S76V>KRN82QVE}C(3aA4S$cQ@-prMbB|D3o(=
zZ#%lkwYw+o%j?i7)26kpS)+5)c+I5g)5ZB@tytvc<v{~d?ecXFXJ?r*GIVx!X58In
z3TlB%8mG;8Ge7(;=*W+Gw$+P5SBGWX*|G7B<)zm4c2Hfd>NUmSM@>eChLDgDsI75j
zZM3*`*_#8aLRWvd8Xli`XGh_rYp1?`c^T|8+l*H`Yz=68Y0;lKRekFNU0hs#9u~gP
z+0oI_5yy0Pw)yc}TeA&oeteKQ{^;@JjX5`sw&dN7I%M=3baKe%^z&T(@9*!I4_zI$
z^?}ms#5a1<_2tjc$%<%&oN&rs<9~6HtM9(T=YM{F1{F=L;*sp;=H_>Hm3mkF`SSAe
zhYue%fONg{dbjP5?NRfEU8$+5Gym)Yjbk@5v4YaThC&}ub}T${!yJ|!-FteIWqu#C
z0cA}{^uc5J*v7&$Q036vn|XGY>15l3t8A*ic+{Imx(0rDaF97AB}Kx<El@;6D})2o
z^*_=nth#1O{@Ytye>`aB4_M&97_u_xXa;w;Ut0B5S6A1C#m~=yj=SO#)oNMf+WoAe
zXJdEN&8F<@>mEMtw-=Mkzr3vXVx8LUkcCdHGBy<f^+Hu4AtGK=wOXg?Mn8IVv^!#3
zj^wW|FO{p8g{%%=@75`#dSOkZamea0-nh89f}$d$ik?Lp9X&l$wp`eBZjL4M+OX^o
zJB8K#K&?U0ge0gV$pG4-_2|)~4TX>0X4^8>o|vEr+I#xv?_a}=3ktLUn(KnfVprvA
z22fcnIMY1!l*pYOh0I@HT|L|-s=YviYtf=b28EAYuB-@Tj*N^n``zup@Z#!fanPPt
zS?jVF_RBT6Hf`EukbBDnv?r+c_qVA#0_Oet`a1dYGGDj;rAwA1TwN8Kacj%U*6>LF
z`ucjE=xt|S$O?fnK<epf3v+L86PkAN>OyCBP;=+{`uOvOIsgCtjo4YFx~t@6($B=O
z1GjHW&o<9DtI{zw6$Nd|pRDGqv*(nRO}+4{joNJX^}?^J-|tmVoLN))>dL`)cX#*7
zoj!F6)T9brA7{(GeiL7g%w<Tq{H<34kzXZ_?=$R2l*^E^*wC!6Fh}MyL^(9AOtyac
z@+D}xAG9W~rG@2Y@e)a!3ImW2K0iOdIOpc3h%Fft|2=+Q52}s8=PB%|*mySXOVXnw
zohyQu^MUGG<MeY64m2{m{lBs3;o<hhE}cT)RWUz4Cg0gpX?%SCjT;d+jhAW!E&^4D
zt;ZKHUR-=<=a10z)#A!0)_!_=8gz1pM%Wq&P?6onD-GIM+tJgr<>%z{j1N9MJPaDH
zo;_Py&ZeRvc)8!h6BCs!|J~>UEoNC0aq&Sh=#-sB8XTOQhClY~-*3MzZg1Af%CJ<>
z&h@LS#X<Wn0vEe2tpESd?Z3d0^ygn;YXJlW1MOD2fWVg^i|TJ{Zmo$l4h<A(w)dT7
z61aHr;?(n#wY0UpdHMLlL|p?<Pt#qk)wQUqvU26Rb?a6w(#ZP$?ry686wo;?tD2je
zZ>@{9HdRt`3KenX<>m$r+pPp0aky&o<jGaPzGU7sUb?gN^|YvMIgwWnA9nuxVsU>+
zuiN6f4+q(^&d;+ARaaNv>eR}WRa3L)%}lZBGiIy+jX~+g?AUN?Uu|{h;)^R785y%S
zr=11qy0$Jh+Sku-nr(2`V)y=4e0+Ra$NOZj=I{R-7AoQzyCI<ww83GkTd&lr#fumJ
zdcA)Csd<`5<?H_}6w?fHseL}T{EDP;+6t*&H(A@NEmnz#SgxKu>#G~LXNQ!quyXY>
zk=xtz!%d}ne_eE!U+La27b@x+sI07fm6@Gyg>Lk=khgE&g4ieKY4S?L%A5Ng$hFAt
zV<yl925%cc(jYXkLM4;qA|hr)t%)!Mc~Gj??eD{O`H;}itG~a$U%h_sw^_TAj&hyk
zK6%T+%4$`&nC>Lo!&;&`5dm|}^XI*h49h$*L2=dGxpS@3&&imYnuh-Wxn+w<>AO2S
zSMA-q*Q(@2Kqt4Zcc94DvbVRgUSC^V{8e2+!Qop<cjc!iod@T4i|enNH*emm&6_vx
zN<BSI=J<S@N~LO}$i_{nr&q<-ew}*odDOO?l~xuOD>OAV+2;R$Haq`{Q!7_w(Y#R2
zpd}r<Dn2INGzQfPkzK1+t$H*00l0?H_%0+Q1UgSHB|Uv{&{8k6YSye|&@@i3w7Hax
zy`!Te2M5OlTVK$U>cj^J8ap~W4S(!ezFd8pemq}%e7xuBHO?_HGH$(6t!HPOKmPdm
zI75R|E7!v0<9#zMi<h0P0~b5b&dmJvUNbZ_aAT4y3oC2llM@p)LRL(8(|HMWz63Kn
z-;rKva|WB;UE5c!`taeyflaBWLCXzJazC{!e<#z%BiVGgonN|UU*Y3pKYqPl|M6OM
zzGsx${Z*l>K}V3;)cuiIwd&RSfA1bWYGUOUTTuP|-6Zi-;Fg^Ph(w9(%s0}PZ&(~d
zj($+8NS2a5ZUQcG;LVC{MNhpzV`B#o9?ZD9O0??xyWSNmH2%K!2?!97v#aUYTm9WD
zPV0QX{l5-S@w>lHD`Z83S?;X`fs5THO+OjDKF)Sa)>W>_>i*MgkG=|7A152NR&23*
zKZpl%^V;a`$2KM(fAHi93wWh9sM|VgR+n3^RO0n@u?2;N6Zc#(GLho-nyNK*`TzaX
z_2cUryVtb4Ek0RT{^R-b4-&hx_bk#lapugH6K0#@>gwu1BYdDi#a_4O9Xl*4Dk~Re
zUS4)%b9(>5<m0{4?Vv8_t`g5nQ9GTSok7daIyyLR27{7>rw!v=P<x@{1lx*LUGa54
zk3Qh_zjyE6g$$ET%OiP1Lj}df+uyv&nW7gfRaREENqwRyXb;cH$?ClOmcP2bp1-=f
z`sU>|O!r%|?mRx;zp?szUd+xS*Z+66<lU8W?Gl-2+xuea(PM_awa%3wsyA6iy8Xrd
z<HrnpdvS=YtNQw?;_uh%8!JDjfzCxx^`2&8!B~5&M-sHrA@BY^-O80uQ&UnDOiV<i
z>ATttu!jW&N<GTEx{cAwl8V+UWGj@y_=Deke0BGjA+>>}Ha4BjB6N>Q8se?<c;v
zu<*yn<MM&~YASCQukkA@Gc(J%(J<G#T*=H#?7-%3D;5@(1>V#3%&uBW^|FC>@OXH1
zywMCxzp^6G&ELd4_12b5{fyqPzh5q&-xH^?G;VLzr0J2@4mPtteEqt+{9Yw!sW#{|
z4$zo$?eDTJd3SF;*jW1NisRK)p}F5!-pn@7U*z1*mvLo<;IHrR`#(KBE&cbsW_o%$
z=W9@W)IsCp1lP+FD~1dI7ytR(fA*pMBVj?oiKfYq1q1~zu5PP!c5!i8uVlt2D7bfx
zjI69-{ym#7udknf!TI9!G~L4!6rCqbo2FK|@@cQUy<G4zpM#*qNGH|jAGmv0mZ1Q2
z{M|fTY0x6(9fgk#GB2r|^wwQp`}^CDnx95`vAbH#@7G*@(V5+~DB<<BwUfk7eV+gS
z4?Ae<a4Wa?gZJ<G`T6-5pFjKN=4Mr0mF$DU7hcXkb>@r<XzP95->Ma>xYX6v862{*
zv_xD%os(;8B9nu~v!b@=$*TFy>Bzpm4m5)eTIJfn$jl?Rx&D70Xj}HzS69t`|6P7D
zV}S-&NT_Js8^=JAl(e*{3Q3Tc8=?Kw$c4}UYfPIpi;JDTJtkH#JWwPhH8nC}ZjEWy
zl?J!P2le;=VXCgKzOp9r@|*jCBCPxWew)pD?PTej8-@%Q;-~)pdHmUpQ=xnI|M}#t
z(Y0v*t`F1W>oUK+*XU}xxY#{9VXn>JUtgOSX@H8Fg%>j}tdF<fT<;zzq7%942-E8)
zR+XPr7!KUNefvRj@jUx~p~uV@cHP}s%+3(7Ehn<M|7_*IAK{YV!UWX9sYR|)j&00G
zYu<vCfO5le)YkA5-<Ow`e*Ab`{_*GY_U2Vgzdk%X49W>H`|D!g1#oJGt?5wnot5zQ
z)m69t?=LPgyZ6Z)+?st|XOEAazrX+Ha`i9~RzpKWv8WW=8;#FEE8N-nWG?Jq2PzXH
zH>YXD?AUN8QS6xTh0pqSc5+9%#oPDp-TOu}$aju~V0_I-R=Zy>lxsenR9_LWkcmOT
z%uH-^`uSsjettGgJjCKN!@%)V&}rk+BvZ%#_rst0%r-mAlnqL@w(w*dySGY|Az)>Y
zDl|M|r|ZQo(BQhZKAzv&+WPPDXE`@E9AtX^#OT{HgW&ULKi4nVHZ`8@lW#F-$d^y5
zmkqSYvyq84U|r14n7>W7W@gu%xSu}!K1E{x{3D-!m42S1Yhw;+OV-$mJ$}6r6pr_U
zlm5&TN`4G$O<qqn+$Yz)vGB+bTh(LlH4*JeWG$7KcbDhCxxZf?H2NMEHtiti3((1X
zudc3czqhwK`QDz&P0OR^EMBbq?99yOMrL*?+kaoL$0z^z@X)NXyh7;o+w4x=yAyxB
zU*<o*PcwL#f~l!!y}jz;lP5WokM$gUKEGbCaBk{HmM?#HmcN%fHBGm>_V>4!`qPqD
zgW|A_R~mH6kXwIyTic@>8<Wi{4JZ6xx=QQa{r%^;#RUWfC%SGh0~gF|0+xDB<*74F
z^v=I=vbR^-eAb^E)85|R&d>1R!GnYkhPIO@PGo$rKEBTG|BY*Rca@%ga(r9P^>wif
z|9;J@`e(>ET|b`f!}a3Nf0CJ|>BVxn27)?C&HbId$$X&NPx%;mz3fkEr>1DG2wyL^
zDtvuk+1p!=fg)?-_DX@KF+oE{MyaO~{`~m3DcuWnG>fu(ABVq#ebEz+J9qEu?&(@H
zckR50dD54c`yYQkzrJspZgkRz2L~%2_nI>>i0j84In>H+n0Ln_!$hh_%GB#q&}q=3
zhpelsRI879cYdE-^X%K(+Zk6@O#D!>*sb@+{n-Edc6Rf`^%Rtpl)4|vLVCb!LUtBC
zy|6agyrrdOf!|!KP0u6dhOQ1<=sjHzRKeP|#u<5fdTInM>3Aa<_WV#Q_ll^ktKLX{
znN(RP&bw$&0%$yG;hzLh3qr&GhQ*ZdH`1SPSWJ-zjVAFuWtVRM)CC%OX#dm<>b@+j
z_pYh20iA_f^Zjl)s5)i<P1%9Q<i5PT{P5W`waSGupi`5UcuoeLvBD#77gOIjb9MOo
zq<43AMr_Fdt@le1R)2B)*fA!CQ`7bHKWwx-FYnL7ASWlcB671@*_#^^AJ15|ii3mW
zz|P|5IlmTZ85$aPbapx>B`vx*c};UulggS+dV83E#aFO@xw9LT=B8*iuUMfm`_HbK
zmc?o!t_PRTuj6tJG$?-Nvl&#X)qJ~|E*9bL;_~IyL(UhV{)J1}s<^#Xp#7~2HMmxV
ztZce)A)w^-HBeV~)AC5xUN>fSb#>6jx2UyZYooWffr^gEu!VJhf4#W3*BW$I>!uXX
zo5gGTCQlZ=wJn!>ZCJNi?yVQ^bCO@1Nb%mQd@h@@HHw9ueR0XlOPkaqdyn->FRuRn
zj)RBC<>RBHspmIp)d;VOC@3%hZDp&kufHexpq|2E1iycG_t(qcym?b2a+8XQRPP(h
zpwzUqMd9n?F1#!W5OMu)tZi&8ylR!x>Z_n*(abJ7OZBpKEdu3cK0dx*{bx^}I<@J5
z)lM!E4TfH~<|j{5L^J{zSh++De&5mPYWnh}gj;uuoSvTE4AX2eHa?k*FFzK!c7uj)
zRMgd@D`wW1=iPBwAGf#Q$A?6QWA8t#)#&oA@t>LeT3zV>-5(zx8<xHb;gK|AIo!_g
z-pVD)VDr0bmUX$_v$M0?3m+d#d~~F<s6C1?dVfLV#`%w*eK2kB=+O9I!DIy*DVQkQ
z-P!3_QDJdyeSH7t=jWXRMXs!mmtVMWAqN-Nq3rd0)v6bn%r?(&^ILwnPu6<Eym@^|
zN4pda3<RRqiuFpHPqX!3wJG(qlAa#lw{PDn-tYas;A$3V4}gWW_33$OqM#wsx3{+|
z>+15lc8NHGO7g2&pe1rQFE5d@EK*TYRu+_&=C-!B{_*37!|JPxf|vUhl$K7l^<NdV
z)a&8DzrQsC7BKwz`*-2htc&|<t1YaoPR&!3z2Bns?8S?Yo*o_%{Wuv=M}w2oaj{!(
z%K1%Fpxo65D$-GE&m?fm9cdH^UbVu8m>^?De(#nnSpuCDeI%>r`{V2N_>INS{Xl~$
z3;_$BSXo$D9=zRtf7+fiMPX~BSX~1_%V;&a7X805XP#|!RKnaC(2n{=8Z%5Xg-oP+
z|0Nfz`OnK~EWNhWwOb5y@bIUnr+ekzUtZ1++90%Ig$B3&<n!mx^Mh*PC7zQnEb$Z;
z(GENF;_<4Gl}Qg%uc<35GynenzJ2@l?H?*PiO!rk6Ljpr_WO0*u7M98JYZk|ZIcZN
zb-lhW7BpuV_l0{;!NJen^F(waE`S>u^Ex^@KD9wxKYLZq&9Q9$@Sy;-YVO+FXi(@z
zZOvj`8`k~(e!aY(pWh~RuZeT!^nlisEWe!i|KHye=gzgYx3fDrISB{}HNCpJ`t-bv
z!d0u1{{Q=X;bqB<J(b3w{)|&A*TcWx@3)7oc3mB|Hs{f*r^`Uw%0UNemsrWx{dmZp
zlA5|O=jNtg>t{!8%{n<x<LpFb_XU?<Zpgf>rlO*9;Nr!L58ml+t5ENI^Csub?d|+l
zbNQmT<s5u`y#L{=S6zLw)=sOhE^_S_Gpjw$vXArXjwMS}a_;O9w3^G;&L`WnYL!O(
zKASC3x=v0`AD+$5KQ%AI6x>rQN_srw*gnJF-pRt?c2!}{oI8o2A{i_J>O>$*Jnq<7
zh%BN09W;=~DXf-oVS(eO<q@qfUS!PvW9gE@IbA=#ZU27zrluy)Eb|oYa6X2D*VlAG
zXY_$i=$vO;9k8<~^`y7%`I|Q-mEC$C%w6^0-OGz>&z?P?tPN@)ZF(NDcCxy^)ZT!u
z?c29MNxjxAu6JT~_4jw6L#fS5H_9q0EvgsxcTfk7x>s?^T9tVG_x^t5hzn@wQr4>E
z0O+h&|H-fZ{rwGE&8wuO1ls<h(FKa6*YBTv`ZL{j+mn}<m*3c!+<s8jBCh(aY02AL
zqKb-&85b5bzUjQAs-mJ`WF%xYmrvbq4g*8T>M-B`rNIlGSWj|4J#p&Pp?7z8FTDJ6
zL+)*}B}<kp$hf!&RLpvKaLh8x)v8`3^77?N(22PvR<fW@|8oENht8hmJ$UdSXoctQ
z_xrS~7lqUauPOx1V{~*lxVW(R&9!264Gh?v=G)TNret9u@$TKbP3lp+psw?rIX5hp
zfoEQhZ3GSbN*q6SQWiAOr><_+mkG|)g*l)Bz+)Q=i`qdI=E+XzFn_X)^zki@&1?@3
zwQ_?_Tq!EO{w#d1+hWJHQCk;W%@UN6$(d~5{*O1l{;w(Mw482n{ZsRjN<l>)=!D(p
z=jLu&zNbLdd)k?gyC%(>*Z1T}3WMeQBd;GlVsdwPzq7mi{3hqM4ZC++gGMS8o!d^#
zODY8&=TP{_B~GKYs8?L?$Ma==bGtr1J`URE{Y^wkY0-2cSiE(DYLCCaz8=1|HhQ53
z*Z+xc^4G=h=bP)--qFGF=i_nt3mGOSPMnxv>#dbs{s45=Z`kUi;_)?#)$>Ak6h3bI
z_gc-$N~&uSXk@^m=EsINnL$gJEdwpt1+9UeXInjC=1kCT>zMs@vENKq_S}_R8MM?3
zR7m{z_&D|a<i30-(|4z)YX7qC1s(7t)yw8P+YGb`yXyNp-RgN)6X0nc)Qpn=_p3o6
zYV)l(GY1kYpg9wGtQdl4SCC_6&K%I`sE*BS3qix79}e?BeEBl-%OR_6MeJt`laGPU
z<J(d8cGkYsEm69=N?tZ8xptkH_x;j?&g`UZU+%E5vp;`*NK8;rP(Pu!bhbsI66mM}
zW%s@V=g#?klUZ$)aDV}{)g&-55R?J+_x)f3El~aX>T0V0#;iRB2kn!+?N@`k5G?Z=
z{6KAxFOxj|{f~dYU(Y|+uRV5mnWC+&Z0e~gpsplnvt9MPtDtG^5-ZsfE7^51JDIGl
zt!LK<pTB?f=uyxxRZZ}W1E52QtG;B|+1F2=JGa-i`dh-mCRR`ra{l!Hh0o8)^2piD
zh&Oio;JYGe|G!__`+hv)&bhs<_dM?ni=E&>3gu(_K=Vq_X{cjAxqqvD2PJSsP(lU~
z>k}V8kpmY@ps7YsN}rPssy6DStph_sLuc32fd*yf`nB^)n}IfFvT}>LI5;qDiP8nN
zj@a4RZwjxK@{bXIT<m-dG;lvz&9`aQsu#Dn>)Y7a^vvs!6A(~HoErlg%K!})1TFPi
z7{9;n5ckq6Ya)XWS)IO|VFKD|@8smfz)=71r~0X>+Mpm?7`ZuZ()CFGxE&AXKRmAm
zDu|B7ePaL>L`p{b*4EO2fq|gXe^V;AoNX28jAIsdc4tTd{d3o;cdMVhySuxiqocuZ
z`QewBmoHqUb+7Js?w{}b|GO3xY<N={_VCKe;0rHHI(mAJ+}&ONb$^7~gKuwd|5`sE
zbo|Y#RflfhmX2B*_RVBvpRDz=dSfRiCngzLSwRtzl+Wi+7pI?_bFtq4?w(3vRxXi-
z{rmU7iM%wkN?42W<HwJnqOinD)^DB-C&P-^-P@jo7Ht5P7|C+rxm*cwU_*+M^BeMu
z`aw<b;}&M1sb0t!-sKw>=Qk9hODvqK9e!$F!c-}fj0QGdDFq!Jp5NczUjFZMe^V+q
zm$+Wfxw+QLDk?1d_U+rWT<D_q0_S$VU;qDJbeETu2^Kk;rq9O2;5*BNkpYzDEh;`F
z^gZ78=MKa9fB%;+U3&A)|N4pV?(PPyjLf*Wh*dwv!NtWz>^O8PZq1EOVRfE$PPzH{
zpsAOPtx;R@@5}Y|^=(r30!>Il>p{@|uCOpMPz{rIMj~TtRLII8*KaN_=iN_KR#IXL
zUl+s3V3K=F1hncjAwi)_L{q79p-pFJCunBB#7eeL&bI5#o1Bn!F_Mpu_k*hPr>CZ-
z`cF}^vXZiz%lG>F`s2OQ<_k2qYHDji?J>}qy}Ndunx_%!<J0r6`qiOUZiWU>xAe=4
ziyT~BP9Gl~Rn?!;obP1%_T%H@pfkcttYkswbgfyVQ&Cm*2(<DdBST|V*jlaXMXuo4
zyBWui8TNr1Zic<RphC#R>|Fc}^PPu}fl3`2P;V17)@lLHC;Ji63X8pn^Yd&|{WoMu
z^|IB~)qVK<*}1C93UmNXM+ZksdwcTJQ&Tmfx9Q~F+oM^ncG3IkzrVjho2DjBnlxeV
z+_{e{0s<zqgciNMwblC@%j&HqFN0?Pd!KtsK5j=tM@L7>BX}1lXsH+I7~qEV{W|ju
z5}VHc-}K`>=s4;ZC03xb7GA!5S@Cx3b<p5XOIzC_$7Z%o&pp%M@JX9yT{*BN^D?L*
zRrK`K$$1*SSy@`!^6qlY^=sc-{r%C)%gYOjiw{3I*u3y+*2A}Nb*mSNfLi}9E-Xq)
zN&>R7yrH3i%l%|Q&HcN(N}XR`TAJ!V<<<Lgt6x8#&tJGoYgOp#Hqe24tFJC{YUSFb
z?seFFVHapM&F$^^?S9J-pPOq9TIhd0u9{cA?uR1i{G|<v&NqdZf;+3=K>zL51Fct;
zj~zSNSqsWHkc?pn3U<h<2vG4~39F8efD5)y??73;zu*1osi}c00u(`mqX(N<FRlz$
zx3IDTZRM^0_U7PR>++QIN>!PlHE|#plvvF@*!ldtKTGX7F@J~epFdBwJ(%_N?d|Yy
zELEHz53yRly|dH!djH;vkB_)xoLpSKyb2Bp4NdI_b<~v>&AC_e8QhjoQDK=kZ{DWo
z5wg%8X8wIS&=IJgKR55SUB8i)Vc))ezpQgADk>I4Z_m4swRJ_{;<h)LVW2Z~SFT)H
zP*w(7n7ZI<*2jC*?+=119+Q<OQoIbHlim~+6)$9MH7iw@502WJwRHdGz?+*=zm_+x
z3SQp#CiBwY_p<}GM(N&f`Sl+($`6{!xVYH8prpiQciCG|Z)jI(_U!+Vp=)rb1JwA0
z%n*S_mB3>H82u7ZHH<o`S-H9Nby$y#r4VQ|h5^(--nVa`hlj_3>i2uwKR!MVItpe|
z_^Hw#9}-`bSb=ungNpMxbLM<m@3}U5`!w70N-?pq#kEHFFE96>IB{a4arrdRrvBo;
zH+Jl>05x*b=FQ$OZCRuOS}$Dq_}Ie4!)>4w2|hhN{qWhdwhbE$Ktt)Lr|X};{Q0L=
zS7+xz(7X$Ss8)!>(JoO{eWmP07c&f!kMV$({V{y_@X*;L?~a6a*cykuRbPAl%>|7K
zPZB=qm1!cS(Zy7}{IG33&wBxX7ndpZ(4oH<s#E69?Ty}^x3J{prGkQj3AXNCTeGh(
zN<Q8P9&b7N3e?++-Br>Uw%T=b+S!!z8?6`_8A03O+xcW4ym_Nj-FLO3E}b`e&*Xkf
z*KRS_<$iM)T+Mp;`t|A6T>p9Rw`is1=kv$M$7gJfDtUKjrv3V&&fdev3|o6q$FSz?
zNxpA$7`hk)9#s<3>hHl-1G30>(7i4tFD@|hN|`vU4qFSFV+S2pcm29J!-Z|R(Kl}1
zOazUAPmj7c(>Q&><(HrxYth^D92Z}Fu=o4D=CIYE<?1=_^giyb`g-c~_e-ayYR6xY
zdVOg};bR+nbN4=(O2_Oq)0Zz-2hA9ZYKJ{I*vzgGxoOG2uWq5Cpp_(Bv#uWc^Ye46
z|J0=K@9zFMU;l6N<8y~YSBD*~|NlFF_CD__P#KtWvnjs*uc)V|=ZSOY%q-Sva81*R
zRLY#2YHQ#5<Ndt(Iy#3YcW^R%dvkO0^Zm)E*IT=|xcp~<wP88$?k?v~Jw5Ge{L0xp
zwsn6bK&y*DQv%1N^H0o6F7%&oxAmoY&0k?jNlDNQd)C!et>9K(vgxHump;7Re*e(<
z^ZZM_rcSaw{^-)>%Yhpb9B&%OS#A5Lc4fy7iz#}sQQvx|^MR^nK52D(@Ny3`zq$>D
zH!LcTf~NNmA3MnpD&*UHC(Gx^nEAzlYl{tqkfF20$4{>9e!q`fTwGknqCnv|=RyX9
z(pMp%-N73-Zk#kd%FV}zr^HHDNl6K`ENsQ9uJZe};-EneK0ddTlT=gvRjM*At*ny%
z{rUOh!(sl3lO{2Vi;IKWQ@OXdu`+-<b-~Mg9AjeUJXtzzd;Wbp&>T<6%S)hk)~e9e
zYz!9l|7<`@DR%6z0BwNMjovn8&y`O}$;lTNxpIS!KU}wNorj;F+e9VT2~(!9goXz0
zsVKCtw!VGl{K`LbGVbrM|1ZAb$ghuwSY2FPRJz@uO|4V%ao%1!s;aEs({v85jozN(
zKk?8N>8f{kce7htTfe!#|9(?<oE#{l*VNQ}IIX|`#Jr@?Ns}ghILI#l;QRgh>9($1
z!TB#bmsQ%HfvpAT?{9BzX6BQ#$=K<r-}(Fdd(ibc?)`F8!D^%YJUl@88MI)ITd%5e
z1E|58GY2w?dBfu8!DES!pRoTvW?}}8DA1q@G@^bU1a+p7A}adgMNl(9NKQX=mB^#V
zk9Bu=tUEPTJNeI#k0(x?IPl}+<HDDhR6*;!B#crx{O$hNYieqOHa8wRd^pvA;q;!_
zv!y|clNrvPJEsw~MME!k*An}GPfiLiS+eBBEcL5LI)ww*Mw$Nk_xn9)ReV!ZlYodw
z3#YIe$mi}?SA`lDK61HfycDz=8Z=S;<wYPUCRVKiow(xR=XdPN%3#pY0y8_`iFuiZ
ze}8{J|5-j-L|VH0)z#IDqqpaQHfDepCHG33Cmrn)jo4RXx$pNoYtSic-+Yvml&V~B
zo|XeO)LdMCF4pLJ!x`3_UnBImI9Y1G{No>cB$ltzGBP$Uj)|Nx@8R{{!pO)-P@^Fz
zI5^dRqgRg1<sY@G$DX_OobQ#GFa7w2#j=mDkAd2uzmM6}#dm((DfqZp`Pg%iQ0AXq
zhJBzeuVMfF@T8i&BR}qReB24@U!1skQ__E)ji6kAXXnA}^?TC}x)$+*E?8MBcJJQ3
zP0J&6)6>&kTwNEIzP<+PJz1B(d-D4IRNd%r@o`Ci_w3yZTG9OXI3pt?Xx%Vqd@ChA
zJ^9=mOS9j5%b%T*1fA;E$}N7ba81F(Loe>`Hb2%UtDQKrCNMBi!luGN$}Fb?w3z$A
z=J`+k{QM+rt4#Fb_H-m3ZhQFq{r>5DrmQ)6Uq9x<G3opRXV3CVo9DSSv+){~zl+g{
z-6aC*(4|LRS>)RN=}$QuuhbW&X##?Rdw)TPCNFw-?N3mzGW@a3^6`&70d*f<w|#2v
zb^h`mG-ESg`V@cN-GI1_`5kdQ`{cSm?p*li!FArJqSEazjy`z3QDVOIDPDPbdC-Ky
z;WpmWg*tkAe5a@BI^W)wtEw|uSx3j`|NitdGa4^k2-vZEw|7j+Tq*Osp2x@gA0Oto
zpJMB}tLW*er?0=7X=}e`U9&N-nVsJ)B}D~VbotCQV%@iI9|sQ)3&Rxs_<IkkFHEzr
zuu#y{^sM*;s{9KIKug;|#fZMXKKKY05!Zu@-TS{Bmp04kIB)mc=bFvSOP4Q$PHQ=G
z<cNZyq2clRa;>f=N#it+D0P1Qm<gBN<!hJxubeu&etv*RD|q<sDPk;0R6kCJolnN$
z?X9h##KgzP2bxF$wdkw4_O>7gSr@1=*Z!${{qdxlJPrFFrOuTHK_#m5&!g9q4eiXQ
z$p6{35HweD{Mf=jk02q}yE1tBqPoAoD!$(>7nG3Ta1Gp$eqIhV(d9i&r*YM)83u_>
zZ)OI8wiF~E>v6oi%=hBn>hhA8msr=WTem4avXzxv?7;c+ptD7fHZU>=tc$U{IeAIs
zu9B4pIbW<=m2|L)6|@UwSLy3Et<Y5r40<s;8os{1zBuV<mxN8lhBZ5be*XAz;P`R(
z{~MPtR|icf$JhO2Eh{Tq5xAI*OH4<jaG{Nzo!t!cd^ylYlkNBGZa=sIx>GLyp3RS6
zzr3Q<r?<DW=iT4O%K#eS1kIcYtNSfTKHkUB&@HZi=;Fn|XD*qbK?~4bX9t_v553!b
zRro^XL#D@EVmck$a&IfCsIXjJ6*}3ry`$sB)TJx_gj<69zN@eAF3<n+{=WRzS67Xz
z{yaH38B|Ds_Rw<cFP`oj6(yylto-o(`~IM%UMJ@zmu}j;8FX^)6usD6Y4w60m6NAU
zYy0q_0MtZU>OFm$?eSG9DJc(bY)oDeyW8x3%1`@wHkD25_x<9st^U@seEIS>mO&c}
zU)(=*OfdO=KpnU+PRf~+e#87reiCTh1~jh(Zakhd&XM_L4qlitMLuWFoVx#i%Xwt2
zMA-Rc3@jSgR(^gKv7=z&*?9{}et*k-QDW87-VVBKrJ$(DX?NLM(7ioBe*ZoUYWTWj
z#>B=>oH?^|x&M47hBt5D7VqKH?n?U9cW(Wv%*)FXpPrfuUjMKu#j_c70<ZJqW4)ji
z<2^E#L6@91xq%K)ZD!-0Fk=R2n)!u(4CoS28OtJ;qut`iHzps44vXeLIM4{1CMtY&
zMU&ycjg85M#m~UI$w2#$b{45RIXmZm+Q0T*)oWc9HMOLZlT_98pQU!sjalj?nz1#i
zN8VoUz-DgAmX?+m{>T15ne4wI@2=II-R1tze7d{(`rIliEI`%$=V!iGR)um$tra_X
z@F3_qAKQLVj2;q(O!37rA=YSId^~aDL=H|)$FQ(zt<xi?Lznu24syM}uQqUHkm{0U
z%O2g@nhhGG+q`-6o6eNfn%Y{>fec$RE*^UEk(r$@;nS0oH}==>Z=HT}`kXmEudlBM
zEo&+$Ep44XU7Sl)OQm{Rh^D4y#-$~kc7HxN^GFyte3Mx%EGgOf{eJ!ZwDre)e;z(|
zQr3*`DJ!Us_45Pwv8IH-nSCeuaX=h+ChN%&P(=$``f}11q!83<^7G4?GY52<Dwn91
zgsrEpp`jos9?Hthw8GZRc>E+X`rG%(ptD{A7rAhjyuBs5aN)v3+~@Y3s`~mWwcvXG
z#HrfhQ3<`Jn(_N=Kqq?m+x<N9;$!6IG|-y!j^5s_AB;|0SAI&__ix_z?cewBdGZu=
zMii(V++Fte(AnAMj5gMpW(o=n$;Wy&-V}COAHTnEe%&w7n6<;fCRWguJ&nxlNtc)T
zZrHpTR0xAk=bpXCV$SBx#>;$Xw=HyT2Mx(qJY>4uCu7Mp*RQ=-+FZ%dP_S3pye(`s
z=m^VzH4%n4KZC~ks=jSv7XZy(U9<-+H@2{}JULI%*UgQs>f4*n6DK@Ytm1MF{BW=O
z{lcK7UIC$^z0&5#Is}ysvaV>{4AuqR;du7*{mS2Ox5pn4dR_kEf#a9Ax5F!J?Cj*)
z`D8aeQ2JT+{vN0Zd~~E!_{6z$*Xr+`JIBW>ZFXdaVKT^A&lrvV&6|za#qOTA+Fbs|
zqP)Ai7J{nBJ3Eb?oSh#&eym(QDFmc`iRa`m_w{GaoM}<^Mk4F#s?^E*b<XLV@ku{_
zf5T$uVbBPn@-a|kCU^9HK7X_7K10r&|3^Xb4_dtn>25pc%&G6|J$&qEJZR$LF?dbd
z<0m1@{bbj~?hdP;IAwqQjfD{#lR#y)s{R(gtE<D0Z^^t2TF48^bj8ol9bM$wy&>bG
zQpl<hPTQ(44*To=K6v&_t$LN~ny9T_-&j^poiL$c%NCP|AGd5VQBhHeD41yT_4W1h
z*I%z+8@J@--Mg}&fpdljKmQ8-{LBqX{L7aw|Cg+;uD&K}Yu9?`iZb>u>i+Xi%uAf=
z)+f^miuRW;Uur~bP&n2j*&Mw+4|GQYDB1%81fHFlsa(Cx#CMj7<772o(9!6iMSNCs
z`3|@9AD^J;4BGDf<>h7fZ!VxQbSY^6V^dJ{_PnFl)<%Do*M~G5APezbTwQN|(f3pL
zoz=oCZI*CujwR@Lv9q&GzaF16cdnp>M2Bwlwi{<=SG~HncJ}i4TN+(WXU?1v-*IBs
z%&K*uk>Bv}aPD;zv(L@3{PE?oe`0!i`?IsN7gv3K1=@vIRAdC&Y7aWzy!7?88OG^+
zZ9I}n)$2t5{rh)gb2|U8@9*`iyRKSRebG2{`0&QW!)$A!wsO6D_YPEsWMpWp3SX~R
zJ@4pTi$bRF@9$r)pEG3&XkkCJ>n=3?<nd!CZO!@=&HUbN%;y1jXgW3)@@y>ZNxuJt
zSNgbswEFiO7Hu~yo`H+?Ht=-Tr?%eYj^4@DIWo>Up!LmdbLPyMFlo}F|2OWm%D&Lg
z%*+IxSOIcR`gyq<H*YQsT^$D6Irik_WW(fRJZmC1v&mYQO|hM-^6A?*(20PcGq<9)
zW=YCe7eC_x%^6pHedQUI9=W^ht<et)Wo72%<9)6{K|;U2yljS7*7^H>vblDP9i5^X
zoZ_?9%I0Ito0F5(LC4CvEuLuWy6ffT<%_GozXRQXm33u>Vs&5W!&dI1<M-~#f%4*9
z>+*uHuR=j9tans@U-u@`#l=P6*0r|IQxjatZqmBE%=hs0_&QDo4^Pj==4R$MZ+X`%
zF4f=yt-%Mako*7lef>vJ-*bl6+~v#FZ*9qJ1|3%q=^CpnTD0g(J`XoH_u(m;!94dI
zzG+48t=f9?_>yJIl3rd~3L5bfaoxC5TW@{b-l+dFvNjb0S678PuMApRWb^Lf;dYDa
zZ#tmE6?1Q!d7t011GG3iY;6=MgKez)TUAj}@ub2hCr1a=d;u-e-hRK%`Rb}rRh_A?
z|NQ(6nj)KPReE86eSJk`rR3ht{vRJ5Rb8{0Z|2OIH}+PWgRcGh`~AMMsi~-G))j~E
z@9u*3)f=UrIx#Op5K<XkzF&Cw#(DMVqtNuxCjlChn`{k^@beoG=>xJL`J}8_UnQtf
z09u#|Ngv>GrpHhCq>l$IcIyRI#pmsQ^FU|d4N6`Fm}Fi$^5p*OD=R0ribaWshHlKi
zZwDG6Jv~hqwAbO)m6eO%?|)uy13JAF<j)&7B90t6;t`h%I)eYu9LwSj$;bKNbK;=g
zq=(yhogW@*Rn?#J_|DGa4<A1s1RaL6B2anHzhAEz8bI5Aj?34(TwLS|x`=bOO=QWD
z4#AGDu0t0WyFYyMCZ|Bh(o)iQmPzCM`SQ#B=j&xId<r^8uxnAmzdt`OWSB^pWK6iZ
zf3XIam|jdqW9hZ$UtV68Fwc|Wle6jAvc&{+=nZ5*%;EpPzo1JXO>%FAeDl!+4a<TC
zVawj$`tadH!`!)Z4;H!x3P?(7X3qWkpp}~kG@17L+FH<T#_n=`85x-i`)aE}x1*jv
zuYdeHsG51o`yMi}l(H0bnajn+?#vb6o-G&E4tsI`k4xL5M~?!Q`^i51$i&K}U}<@?
zsr$*Ro12$^h^VTvnx+#8YSTY>cXv1FKnpd$IT<?(!xU6ik3Qgy>zB7b_mTh8`THj3
z2?rQ@<n8ZW5?%`0EEy9Mv!V8P8F(E)@~P?i{h;IAr)q~E16?3l{Vj)kJ$O?W69Z^2
z;lj(3L&tBPl78B=ar<`n+uL$4Zp)2UQCCm?{OoMR)+|xC9*IWKu7JwV&p<cUH8nLo
zc<?}>TF>(Uw&az<^;<0;T<U<Em45Fw6rM?bJV7&O&Yr}_65uxH5m4QA%uqy3tW7U=
z7w9@)hIzIBTUuKcb##1wl;^x$BwlY`^8>uZ;NIS9&>lC?vBGk;RWJ50`?t<#rV(h^
zr0UBH#l)3QL5m-KXPJN&AO>vB3N^{P!odJ)FoKRc2VI#tQQ1A`8Ix~)_+mF+&~>Wu
zbw5=>XQDkm-p^d|t;#0jf&yqz^xeC6lfqAJOgk&pBWG)M{N!_n2ag^##qF&EUDjh(
z$n*=ecfZ%Id1vu+r^Oc^?0&z`xcYi=v@PS`Bb~w@K7Mq3d1)zVa;f0qG9gv32cQ}C
zJrx^$=QZrhy=?}%F%)#<RA1k*v$M^MZI0c!esy(^xSqk6Ka08q1qE;HD%CbJGJ5d*
zIrs*%zu)hhS2e0BDJh+jhs{U|oj7-Hn(e_=J9qDX{ORfGLytkXZY=ehs<Y$7uO-Wu
zCx3i&6m-ScyL)@PpPikptfX{k*}sQBcY@kX4-PakFzD;+x3sn{to{9MQuxX8FE0XF
z*x0!4U-%sJ@zGIGJ?Grc7nw1$RMNg~kMDmc?e(A|`#(ML1clhDRg1E&t^yri1G@e2
z;$nBuTo8Ea&SVwP+K6L@{k@-gpd}0_mM3U}$E2TaES#4J>SGkO_f9s?kuhoo&y?Ai
zfw~%oW}uY8b9HUBc=)=QgI8CF7rwt|3%XY^`B)EV|9YzbW-CyC`*@%1#l`OYTXJq*
zdUHMS@v&aeq5RxyCucu7F%h)8@!Q+mf&u~w1)%kY96UTnRs=5Q@e|pqntE!=LC~n?
z`3+VlPoDJf@DPye@9#hU_;|nW4v%>|c34c7zZ?(Bjpp|%nAQE}9GI-`zai_YR`X-s
zs4W|AUY`Xj@Z#d)etf%~AGp|!_h#`LF8!DZ!JwtFprPr^ODx6D&VW{XcZun0Rf`D<
zUexXc_p${A_p->@*MY9*Idu52^Z%XJ<?j+cK04~*@9+Nn++5JCOyR<qg9i_S4!8m3
zrk5`{AFS7&w=Q-!XcBvdQEJzbR?rbgk6*9fe{4<U=7R6<Vt@SjapTGCN|$x9yVa_j
zu7Y~MRo~yuU48u8s!(oe^Sqja-D@W6-fdOg59;lH_)zeo#0s?O+NDzn)SBp*v;FYx
zc0MzM-(0I!yV_p~pj+Sj`ljvqarEZS;^qIQzt+^$3=m-jtvs1&oL*!T7AV3aZ+GXC
z@X}<^Dn#%eIZzv;s2voE&-Fpw3dCkeXK>SU#_?l6xj~(YKG=R&P!pv5hK1$L+qV~c
zP1RZvw3G|f#NL*Bdr{ops!i#Ub3vzF1uS&hS+@t&CQQGzI`8|tyAozO5q*=-GcG87
zeGRmM7_@JY^Yoh2e}8`$l$Yn%*VkWM{&$-xs0VLdt|w)ZG2wA``td$l4sPz|{{H?Y
zr73GcJ011+{}F=hG(A~(=kDFRY5ouPm%bKDJ2&U#<nz4`TDgmUeLiph@WF$I`}O~2
zK`Ulw7$*DJ#RZChW;2|?i{W+QQwyNUIMC^I;FT^mRbM#1zP^5ZZS?j97c&IJ#M<ue
zE(aa0Th#7lly}EM#=49LG@uV!K%&6~YSkV&;&SB3kptJSi_fq7wernOv8mIhE!*Gi
z5)&g+Q&Y2{?r)Vz<|UVJCaZ;{rMqw3h-kL{4!ZhyhHbUkrOTHuu8lSa-KO`*>2&3n
z7lK_Pnv+%^7t@Q8=$EstI@tXpRai`{?Zbxx&`ngJhBIhXV`uSm&^5wkWo2yrYooX8
z{rf!sKd7*sbS<jQZ+Wxda^oL&CaHS&*j*F5zk_E(;hDt8pq^oWZE{Di^M4U(&=g%J
zI44_z+m;eZk1yCCJ$4ejYUa3&8K`gh8C=qT$=@*5y6m}ouav1l`Ma1c`S<U=_z1d=
z=yAWjn~zUV>-3YLv%{xog?d%&DS3IR;?t8(R`JN`pzZxvRs@2^z8Mnk@2dqhzMY(y
zK${Zl{!~1?esy)u!6sHv>AJh@E$B>w>+$un3<W<wrGn1Le|mcQ@g`PomGx6VZK0DV
zPl9JPia|5@`)VvffwnSO{mQCP??+CRZ{GUO-&g$n++3SjohPB6zTM7$d~UAwrt}Ea
zxE%`17c5Zt>w3SVqvOR<*c7dP<6`&zMfLyx{p!EIHoD!q{2geJrQ-G4?V#P|J~NGu
zrrp2s_{ED3`MMvB;1$PtcR2k0{Xtuvr)q^BN}pfbW>@>`NyX(mt8>oHv7BL=Ee0BO
zkB^Vfxv_z<SITsf?P;yrKOc{SM)gBNL>kh=YrlW|c<}Oaf6$mRXvi3}EAPt6$xoK*
z$AyK3t^1!C7budFp1%Kq>$SJX<?D~E-~X>`$&w{9=UW$PfUX5wlKKgBaBHuW>7hqQ
zyFs<lH{Ybv*Vk&7&R4&;Q>`34%gO^<{RE2Q$>uqr#W~>aLH?O!P~8k_?+Hk&=ijif
z1otD(fVZd{9szeK70vwaZ74h<BrGf_DA+h-h6Lzb+0fAD$6bpOj&_Mox^}Yo@2^r7
zb#?B3b#-;n&97oHDYl^bRTmc*P<c~OP+(v&ZQ{hnjt-7JKcCH>bnWEU;^%%PFD@{a
zzP@%8G=fw4Ddq1*AyqHXVDJ5!&%M6$8sZi@vCgrr76TprxGr`#sA~WF{P*|w{f^CS
z2ag_g{p4i{8VHHmQNXy|Z!Xh^H(!_5{rv?RCuc~wwkGn%?(+2qT`O{2|Ni<4x&W9*
z*2?7g#wk-oKwT~0*=AEW`0T6v{0y}8(0y;!*PKtLM@2wM;_K_{r{_7ixTF}1e69bV
z+6q|*4_Z_#rW@75Z})?N;lca&{adz}fG(FfuzB?>zgZ@n-{0S#zGKpwR=35Ci!@fm
z?k-z*@62Kiu0w|o>1;UjYl?2Pm~%Vd(GwGu8Et;6UjOm&v7oFhufD$ikKezQEiEOF
z_sLG)^X2H}3=`0nuX`1bc{lg(EqN*Q?d|RMHEVRZbvEmPrfNXFmC5S<PNAV1U5n~3
zpZfeCw4&F}{QA1s=IPU?gBFk{g2#G_+QAWR4O;xh_f+(E+o!HxP%i*dTz70N)L0K%
zRSqt^C6d6+{VlfD-$0v>Dn32o1T9KQI@<NLqGyqYS>^QnUbp5C9|}rdUpxEaqrcrx
zmepZv4>hy%>+JE_$182NAp82d6_K0O*m$Lu)XVOw_^2eNAJ?-v{k)Qqkx=Zel8Jk+
zeA=^j@53igTAbVY6crU2^YZdKy1JUyuh(Ztcy(oE#IBN+XXExX^k~QLv-$PyZTH8=
z$C(*Gh8%2We+=5n-YaDa+L<>+Bao^3+Z&L9pnFlDot=I7{CR#wMMcoM!8<#P19uc8
zo|$FJeSKZ*VbFNt?y}sQ!Mf*e-<JOP@gwNeCD1}fP%msp$Mi)SKVB}MucABU`1$kv
zD_5?xsQF<4+B`c+)%#U^cW_Wpz}~9TD=UN9XPf0tvb~xFnxk8=KtV(=CIY-nFI*1V
zwErRmnqmSUj0Q5M=n2QM9?8Y_dHMPMQ>KVSeqQ62mZk<84*2n-V$bh)yEWqW?0DmO
zX~in=i4R|1UQUzGUY-Anao%3X!)MR>{s&#{d=a$GdsPT0!-bW>>NWp<KHu~#^3J`z
z)f>y--;1#|+g`q);%d#eo9UqbW{H(7Xxm7asCLr%dA6W+!gDN(3;z5lgv>T+{#f>O
zkEgG%Yf+Jr*EAi?>aGxQwEqD$%6_Y<gL;56hTtrI!@Tk!xFUxa@ku$LX5EIuPffj_
z#X%}T1;?|Eg+9NZO!g1hRgwwXZ~$HqVR@;wwe@9uyr?T^!xv9ooBi}DQ(D^j<&{)a
zj$9I6>y(h7Fwds4DR8k{;(-RnU)RM$L%){)*miXCc}4{*E2;R}uc8c(*Y95HHPxx6
zX3x^}NYI7oiZ(Vff`Wo(l|}#l{{H^(;lqXhD{gPg1#MuPWuDK+0P2>2?(WH)8^bGQ
za^TzB+n}>8|7O42ka(DZVcxuXH}=);_MKP5XR|xNYo<|Zz%n1no55?&9qAOlxTmss
zOaA@1|E0pRvb{HMM1T@bVPPStJbf~C+ST>(_Mo*gxwp1})(p%x%LVs+&{}(-SuEFX
zv4vSzSAlxypc(6bzu&*^kKa|o`R?62A@Nh&OI`-`$XbWho4x~`pL+eeI439PiqO?!
zpq)GK?(X)E%apu%^X4Y?Jtkh$bXNXPy??l!zwpr!PM`U9vGq2_#=<ja&fN4YQe=N#
zQTp?9b3xnsca^<eRloOQhRKSUokpNTdi~~FCEnPO*wN83Vb7PNukY?IpZC9Skw(PE
zq@&ys$#X%YyS&n72kzaIb98iE5w=#!Z;nNyqH`PQjvrQrDVo7-!s>o5_xIJRuAkZr
zY3BWjoNE0>+WF6}ld_<NRG^V0pXB>b_@tlfgQRj~(4;_R2&z<HCa8VCCUSGdr=S0e
zi;E9O=kH}@0F}>o?%pl_b0$oLwUtZskoEgL&5q4%Cud}W4$^78a3NrhRjJqiTQLir
zSV0F+eEYWTcUiT%y82{ssa=RuLtZ~SJNv@R5)OX;<L~$X=W`8w09x}jO~kcJ<fr|&
zcQ#hbe*b^`<F%TTi<66xYf|^tve4+<POk|8zbCn@jP+`Y+V?HiG}I;NO3*4#9Yu{y
zucTbTZ12D$_o9?In^ZR4yD$G!a_?E6G@&!;NpbzfRedw7=YF=cHT-<$%-@=IS;<YH
z3c#|6<^S*d|3i*<i)yz$d6E+NnDhEVXLiuFX=i2{cl7qUmX(>!nKS3YmdxN8GiG$i
z`Ola!L*k;cgic<}gxl+4cMC{Kb%CxUJl-b@+9CovNl0H`|7x1Ji;K&bG>P~5M?kAm
zU0P3s$JerkhlhW8b5q#i+`7B^`&G`II^`4*Az@YaMx)4OVN-LnVbK$hlGoRGL05^I
zW=(lD19bS^mW;*;69g9TT+v?g{o`@@<e#6Of-K^bwQ70uCa2`}HQ&-dmzH{W#m?-U
zXH&VT>hIPqTUZ!u>i@-*-nn}9YQ{Uaq6Y^WYwpJ$neoo;n(T?Uu(be1kB)GH25(-z
ze96F2UtbTp@71>IOT*NuqM)4{XU_P5TEfb1Jq^9Ryr3R?Mb_Ws$4`2Dommg=TiBHF
zc+a6@C#9v`t-tk_<;ZApnDL3SNIw@f^SgJ$;?~B(Ey<4q95)oMP`F`HxjJsI)jZp3
zwJM(Gi~H;AL33yfpiA9ALxr`!zcnp4igE1{as2%3EGSQ3TrAN8I{F9HPTEoUxJb78
z#|Oo0Ya*Nd=2~&iIAZ|X0-czc2&yqIE_PQuZ4|XVuXk(q^+SgbGnbW>EpiuG1e)^N
zn8f<(`uhG8Cp?xcTec|s`npw*H*VbMRzE%4a}sE$1*pybMI*$c;4#xu&{&4|bUhDG
z&x4?2wxp!GdZo=D{eHjS{pY8rASYK;RY~1FRHLM{XnP|!WcrA!G3)B8ho`1$gBBEn
zb_$%Ds=c~z>5?T18X6qDQYHfC3ljeQ`&Uq2?p{%0AtWp;D*lzhVX~U9fQX1nhLuqY
z=%mG~tHVKCBSmzhM7qWG-KJ`VGCX;6Xiw?uu&d`bx-bOntEmL7ymC0V?#{Pw-z>`C
z&3Tn)U;h4{>8$SJ{JXnUt5}-N>i^YD(GKSm6chxlZv>s@Q}_4R!o0h?I{NxRCyp>M
z^vl^gb&KhO?uA>tyFfDGamL|e3!4(|gCZy{5frD3Wq-R_gJZCrtEu-hm$Z6*j?7zd
zM1o>4L?CC*p0o4q<>%M`v$V0b6@4Gh0y^*H3kTcM)YH>I<KtE(FBlkB@wS83$ObL-
z;+%J`;LLn`dEKZj4x7`?URdrg?=h+6#fuEk#DsSEI+w68v9$B^bgO*!dU<;v_P77r
zGGT%Ms1GzDRdU_Bbu;Yi?Uwn?<%*AwU;MlF;eJrljZfAJya)Ni&*$?O*Zuv)(D3F>
zPD^Vm_$(I7MFpS>ID4hdKm7QZd}7m_*E=?vEzmg)8lVA92LAq*%iyroYwClC4;%08
zt(Go*%y4IigDf{UcSU98!PBR?`{is8P1B7AWoXb4H>hKfb#)bMem-c<cYdyii%W<@
z3}h@Y#AC+HnJf2J96xo+>uc(!jk~J8YJoQI^&Zd7&7C-5!h++SM}B=@cW~DP70%sd
zZ>zj7OKjVediv3ei;F$Hyg+MX1Gi)ZUfl@V?Q(zr{fu`y6X(tAJ8%DAM!x0)qg$U0
zr^53luTuGa;j2P8)6dNb{PW*PEcezH$B+;a$cZqwx9k7;`!_Kw3$$ogCwd#`ytbz0
zD$WJZ&Pal$=HKuCZ^w{utVi<3&SG`9Ua6(KG9(#ta&kcXRdgaYI9yqAXk(#C@?(vS
zg(Zjg1tvXy(bns{3q;jUHaF`Nl6E)Gkx@14%e!H*L>o+1LKPo_D4x9i@9*!2&z<Aj
zntdI#eDcAI7aYOC!AC78sVFKaI9zD?Rs7_HAcLj7@&CFtXHS2=Ukci9*xw&+>*wXw
zw0X1fqD6}yJbI*5V01WWcUkVAU$57L?vnoZegA*P6Ol1I3~Qsd9y&EuJ9PGPiDuAv
zj&<3a1D~It2Muttu(B>pKR-_+c9+Sz`2Bq=gO_*7T~q)~^={m_5p-ngnzd^KH>det
z-T3_c{KNO}%gfh%Xgt7qbZ6yfHM_rGf@Q4BeBK@^R(M`}N<w^ref>Wf&_>IPi`^6R
z^7_1{YB8SpIoDQ2h2?(TZ(SuNrG(5(&5EGH9fgkfKp~iQMFVsQWBvcX=Af;r7cK;V
zZe%x3JL8a+w(NyqXGaH@svczDj+V-%O`8N{WY(0m`|InkkBOfpH5s(E?c!p0ss8_8
zug7adZ(Ad$E(Dr8uzLIB*Q2A{M~)tq{QGVL!<BalaeFEX7w<|w&2RswLB8&X<JYBz
z6E<)D@cH?9P%pFS=_$q&J0EDOsIW+z=N-AQ(Al+D`wXaGA}ZRtWs8Z3b{G$6^Yzhg
zanR%sgQa*1XxwmK(3;ui`ASAcK_BC;t_)URyz2u4!=p!!M8w&wEG!rpv_e))czuUU
zR7=6qGBSU&q?B1-8Ym_B{o9aVw4t!%@Ue@1y_1`J7fXNhy?4XHD`(E1#K%t(K<Q_(
zth72iDB;Z6v$1f>4U3<LkDWYt>>{tUdcLEh<0||2H#fV#wLG?oVQ=j2vI#1jD_5@6
zh}yE^)kd{VI?j_+Qc_c27J40ClxetP<LdDBa-bTnrG@3lv13Zs*3y1{eiiTces}3#
zR&M|212brMDQMWH^!2qx#|<-{J$sgMZB695=ibwFIziXb%{XBI>QASip9ea&{Nk?C
zY|uKxFCJ{kzrMT#&B*Ti_bdCyj~@r_+>v3JFl|~J=qS-gM>=O1CbLb`i`A+K`uq48
z>(B3heinmPEBnv4Yt=dJ_J1a;py0*V512|ob5)C+6f`wC^YZdQhjFf1vnF6`Rw#o*
zNQlU`{QG@VwZlP&!Ggv$9(W!FE$jxJrd9RjMa=PaaeKQ!dyft@FfyqLKfbm$x>BzG
z<0IC6zu#Hce7zdZ(38$y?ECJ{PVl_egM-bW{lK7cZ?oK63W|!1#m~<j1&vX-^-6Wh
zeO`NeTduTK`8ytU_2n_g)qH0yx$*QbXyeze($#@+S3rk}Tv;9N|8+;n%S#=7eaAqD
z)n;XJX=`gYUhe#UR6JfmL4o1s&6{1%eSLfk%HBli#O;Z=kn&6Yw2_aGPe_0KzsS3-
zw#RA;Rl#+Fs#)K=8|Lf5DdD6vsJ`zjdn5f8loDj_ZY+#T1f_(@=4R)#VfDw98y35g
zL5&4)O8B2Eom}?efg^*%#YL{7{hgnZA0BFbac!;iz54&PH*VcJbnRML;h**U{~hX+
zweER#?*3x;{$tnHMqgYPYYkdcJa68-7nhg!-#WXx=j6%B>WmD&v&}+nu04DD^VpLY
z7Z=a4sWdv)E3IB7(!4qMwi#%8;PLVPaGUrw5r#d|=6u)J#X3hs%m~zTcz%p^*U#^<
z=l}ot?0;fY&obZHNq>HPbldw89K}W#>$pJEKZ2cRxwlN_SQfK2Ha2$j_aDExIlb`P
zn@F3Q9|De!j-X3Wmif+BtMW+{(}`%9G6lSY_Vcr|%_^RtJr8YsvY=yG4&J&YWt@Ia
z#CBOhW@aV_2S>x?$-<x`R-?9NJ$!Jm+3m0E=cV4$FRTbu&bhgXHFQ<TLC`|&nKL;V
zHf-H`G=Kl!Wj9p+$9_95U%w#t_BN}zzc0GWKfJTEIKOhyp`*8M-Fl(_;^(v3`5Q`J
z27x9lj`zzSpRDfx;mJv18T&e!y;WZiU0Ukh`>y-IlP4)QRbM>5$}`whfAjfxXR&+#
zhd)1y4^Hkn3~tPUO8sxWLekH_g4W-@+EDoE*uIN>y^E#6bwX$F=c*ePIWna;EGm;9
zXB-D*ZuidK#Yc`++UCgoTE8v#_NsrrCpY!D^-6(u5v_V|`q%wSK4_yp=v1bUKYo6G
z4l0an{Zy`fdU_f(Z2;ObVVZsI$eEeOpj9@Y2C1}Jj=?S7)w9g=`^0pk6l`r{KSo@x
z*YB5BmX?;japOjZ++hV(6_p2nzu&)JvBz(&m4}DNg~u*!k3sQok|}hoSGrxzch-TE
zCq3WRAA50eu{&rg3^ekh6}sv{{r}(cLBYX>+1GSHMT?pm+hX_rwz+fXz6b;r-MXIB
zQX{_zfE(>owsVPUEeKy9$HBo7P<`k6b@AKVau4sV{{F>g=EEJ;-}Th|=k<X0m|0p%
zG6d|YC<JZn1g!}>HC<o7!m04mrAwe`i66gzKmPakH)ujU?fkslE9H|bP98qYT>tm0
zcv4c5f~U}%w{HbyW!LU%KGY*=47x)vW^YyKhb8&(7Z<sLrnPuvECRm9xVf>_{ri~?
zIvFVS)RaKm{fUR!dL#^)GBY!k+(h5qFIVpD?>~NSu66IXJeB`ptHX3bHKKL-yO8QV
z(cAOD$Fs!mTl4(n5d%ZRlckM~I;XSrttx)jgoRDpcg$D<oL^^cEWDC@AJi&1ek`yb
z6tfrmY8Oj`D}k@DOnwF26xfms%Ib?HrQL18iK9G6=G6KvTTDPhJfIQ3C7zRA`jZ8G
ze0)H|zsGu|nHhqDf(){+>3~Y+tE<D$m+n*XbgMj`BrGh<!p?s9^5x*SA46A%flev(
z@b$g=Ii*ceRh8Ac?2SW4hQ^{rizdvRxpJ3r)pWhsEB|!%c7J<!mz$xWxHuS+{ZsDk
zsRZqc1l8kNSz1*x&7g*bg{5WU`FXZk{nZr}4}N`p{p0oe{a<WmR`Buhfy;^>N#!b$
zW<e>bRaI}#o;cC4cdzZQZ*RHt^Yd$dJZxWdTv<t}YPpD@E#z#y%;_^`bj&i%&a#PH
z9j1F#*0LwGl}i+KEbp2%I(K%L^Mg(bh~H;(=FAzFel?${D5<b@F`V`F^`J)lxpU`0
zJEo(y=jm3NG#5TOA$Vqvr7-BwY9F67rF)W&c7awzG@SghK4fK3M|XFyO?p~do4?&p
zmFqkC<?UQfPE!49I?Hiq$x9(nkLS&s9MBek>+51qmzqy{@+4(V^me}wOMaEVzNY)*
z=g&-=ch8=+#n=6G?HBGe&Az5{QCWlw9LGC1f^s#a83&5K&R$UK-#ll|9dNb=MgHMq
z7keO)56b#}c{$K3eOKb+Ct>^R{?^RZ_Y^ue*ZTXkWrjXSyF?FzHlidQ?dp^}x?oSt
zo^Sd0YroIERot7&_$z<^-!^6Uz7=xsZ*Aq?o_F_D={?YNUFK!AD{G^}`!7q1A)4SH
zKYj#-kdw1Bs8a-*1~$#QV$gMT)BjkHydLh;rJ>vNVnO{>&`OdCip~#SyjW4DSap3}
zEUS<DwG$JSLC1cSyuT+4x(>Nl%9Mctv=Gk0fk8=Gd1J}Tpo76(pj$;i6a2@Iw@Zuv
zvCq%X2c_5AUtb!xZ#TF5_aph=enlmvD(@W(b3x<AD+EA;Eueete*E~c!uH=~fBS<c
zPkNpYmTa3cMFey-m#~`8fgOd96SA_n+}+(TCUbs$bd-Bd%uXTD!YSxs*`Qkq#Xql@
zICm~DH#c|h@yCxJ_dfIf;npja`2F2otG5;VtH0-g&Y9v5mYnA~S?%DhTTzAPlj@7h
z%a2dfjb`yxpSE{z?L6_<bF9nx%F4>B=6LAD?N|fOmY`VMl?cwVh*$$P;{Eb+WbSSN
zHN<u$KF&A>YPV+`2Nm+_=HLds7g)Mz^Tv&hDxQmu8&ov2@g6$XD-F8)Rzx={<cr0j
zyL&2wzi_Z+|Nr+F)WvI<)A}9M@#f|ZuFmU~G8GUISaAL$&$PL7WkIXG43m$6au^36
z-?^;^8#hi!m6Vi}l#0*3bop{(T3Xta^>=NnzlHp*d~;)CSMnqk$7!h^lR!65)b^{*
znLl6t-TnRjppKXQ-!GFN&FJjpRP&w15+5J$c)9avFLx0)C+9)+`8AWCzYhivtrReV
z53vYTeDL^j^ToyPi;JJ1ldvvZlhl6x>FMdpT3TF=j*d;sMGhZ2#PsszO9OLraoetg
zplM7wyP6KrPQ|CErmpI){Iu(LM{jTMzGKE3z0&4xE-o#%x}O;t8*i-qoMw`LFXlkX
zujg;y_BuARDQakNEOzg|R&j6p{krbt<9&&Le|@c*bFSb+p31DR@9s)7GBSe3^FU!C
zr0T`MFlq8+K@pLbt=ZR~{bHIL2kL&T3R$UC#j`gV6d@;jL9OUsNMGyh4U6^1C8XQ2
z#T=+|H9J?ov9JhI<Q@UlyXxDW+xa@>76yP8f0w<x(`i-u3Up8b$OT>E`tx4zk+ZGh
znBn(dD|D4g6-%>e;vp7Lb7+&!;+mhIKvUzze`7o*wFs$tt*D#6V2<ncj~_p7*toHA
z@?_z(v$ImS%#Qu}>z9(27T0wB_^|3diHF->+}Nl*O($~E^OHxqySjvIn;fIJWC+&O
z)`C_L-Pu<w?Qrh(*43-E!PTD?sKb=^_xJbf6*`)loWH-lJ^c6gcTl%%$IhKE3yqYN
z7M1s_oZh5U#Q|zeD_zR__U0z&BpV|mBa!p7XU<GKHAU0y_fl2{P<63A@9v>}wZC2Z
zlRy<pNd2|a?Fq@h7=GOcExCU9un}|~XZ-#;&|W?d4~{o)-hdVpf;yEq_Sf6r+LEbU
zb!EHXwA7MUS2zO$13?>2_Uzdcusts}A}Z?9&(F_y6g*@CopK>5+1YRZPh$U{Pu+p<
z+;THBL4`Ny&T~UU!LqWlj=sLO?rv^|golS(Blc7j&J(}5cXd!u(1oSm;-JYS*DjI3
z+Mng`@7boLr5(C?Q*w9t`)BVC|1bRarxJ99_w8-D&Q(>rUKF+@fKmXs46a=aj!$=E
zGrxlp)sHvie*)*#7j57Im{%Gs0cwp^CPKRFpqvcquCso9e?85&C-<XNX8GS=rF*{L
ztB%Q72RgxTihjIYU|`^?>nX{hYokmns;WT81ZDM~pJyw*aN)uoRbN-lQ&-lS^X>ip
z^_MH(-rin+da^{{h7AUw`AtywDknEL^!$9QQm)utC5|;Ud$JPiR)?(xZ8BPMx1znH
zqhrfsSRY75QIRn)FmOllbH0W-vUc|Wek31l&p7tt$H&JKW;qg|6-<K4ZW(u0{{H*@
zzPQ2Me`jYJtH(c2PfJU>x2G~cQ|j>d$Nl!8En=RYo~!uhrAC5wWo;~addjBUr}p}u
zijPd7J7{*5zMe35?ph1A(?&kNzJ?Va5<rL0X4p^3zr2ih&6+g=f`SuYFPeAejE_m)
z9SJ@@KG6Dd*M6-tpfOrW$(1*HcNITB_u|sh?u)S;Wgj28f{N(t>*L*DURru_cX>Xj
z)?g_3_9hb4nXmr-u65>2NgG?+kAJ`4=bjfKW7by%>IH-PK3?ET^cJ+QQwyy@t-);|
zYqP$xoH^k)EZ{}%i#~8P_Vq5Foqm4a!*6eISN!>5cqLXXS4Z0V&+UhY+e@w1=ic6y
zUnz9>!Ryzv*MC;^baHSw5Iw8y9&2G?p+@++IZ43+$)S5H3R&3Ll3rX`nAN{NcDER4
z!JDV&#m^}z9&&ay5exRG=jZ=#Q(t&!MfCPO(B4o`uc2aJ+Sys40ejHdd1}716qJ;h
zK<h;2SQdkJYdT&Q5)>58gN|ysw9Z>s9%wLa?ym1|Z?lJohtECd>+S74->w#Pf#G(W
zsfpfxer_QlB1y@~psGw=T^)4S*r`)qUoxEjd_Hdv+R*>>^z@HkUIs@*MlK9n8wJW}
zGP1I+{pup`-JEuHb#^v(cXP+>saRO$H%SGwM{nlLnV@#qnl)=cC!_rM`Ey~+&LXDe
zs?JA2$@~fbZ#8pp<MWcJbo)IPP#~+<->}#T9=w{c?uNw|HE<ON8f)n7T`VcBp5NKo
z3EGRaE&u+yZ>Ha$y73?TROK^k=8PFD%>G_zHT-{PP4srY*Von_?v*yblJ`o%Q|QvA
zODw+W78UGY!a+wMFfy|pxPL$X?Z-}Gb<lRPj_&TupHqH4fAxyXbJB;;=j{()xe~J6
zZJG*a_4jvI50@nEt&u&apIob}w)E6gZP1Q7ZZVwzTXA9GX3)`OM>+%}b`~vt_4C|Z
zYtTLJph4UYa9_g~HcaFK+K$rE!EyAi$DO-(d(+sne8bj8ExpWsN!hLE!eNs~kr5FI
z&(F<`+P|gZ-yciR@I2^T)2Hp9SFT(+!z@>7&fK{dmwJm|d@Ql$H00X7@9*!suZ`LY
zIxK98PGr!Rh(jOpRJ@*_pAWjY4ZJNyGnfr@1h)G88l@_ohgRk9dS=X!0PP(H9WQ!z
zw)w}K>GL0+nyT&L>kFRX&%I>=S_SfD1zTh9VmWD0zfbnJT0OW^pbE|(cQ@ukh7`9X
zKYqdwR&fN}i?9Yqp(;3Y`~jC@Ca*6pW(VC593LOQCGW1(Qt#<u)$=y)FOS_-;`y=e
z-@o7Qx#xNO?-JMN^PKeH;X_7$fBzl3cOO1;#^*}}+jCGS4m5&uWpz0J+NiCUe&lD}
z+f!LJ@63k}d@t66){cUP3qcde%l%}JZsZo%TabEs8fcioEbop+hST57tE)s+JP#dg
zW)EEAA$T=8x9;!Pa9bbsYxVW*lTsyDhpj#I_4Reo)|M-4B846N*z@l061}=A^e|{I
zLD3VBK;_rG=6V;-9XiC+*w`pxl+y8Pr)BZ81kjx$B`*Y`w&$&_s{8rrDd-gYdG_^s
zNg+x~i=6toVN(ZRzLbDwL9EN)wdkDQux%R~1L(x0Nh%AgzrVY&C3A9Mtz_BrbF!dC
z+!Y@mEpj)s@SSaTw3S<2Ku)f&Pu6;st-7J1psaP-k(tKnpj$h8<n80m2TQdHsd|A1
zbe!AyL~XkY9334&I~V(8t=XcZqpyAjUFx|$ZtsMN6Bph(xhL!Ds*cXiz&YtTlO|6F
z)!{L_%g(NN?^g8gj^&n&i%Qq;F8uTN@5iI!@f>q}_86s}0&UAG+z1+vXfw;b1v;TG
zVo$}!121{lr9q9#G*F8&A2IUR1MXPZf+HW&5(Q<`gW$e}EV$bU)&Xjw{ycmv@cgAq
zLUwj`Qtx+VzbSirtM%jK<DkK@uIH;mR)Q{_1Fcd>ViSIFb8|WeKfilMh6bOE1%tM>
zHfT<5-n@AQWo2Tv^A2v<zTJJcSuW`0qKk_q_Vo1dfG$+<oo#k?N5K7vKYzd92W|8H
z_~T>pmseN4w{rYF)XIHhU#+#*biH0-b-x8cOTC)ZRh=Kbf8T#~bvS5H0W?bc=*HjQ
z-!HBT)dsbpgw_2-Ocwqtc+B(`bad~>$H%qpF2B04khxFBvPs>4o<^O2{Qf%IV?C0G
zSwSb`v8sX=-Uv=SINPdpm5%2mo5DvfKMyvuuX_IY(W57xlhsa6QaO2fxxcu@!hbVo
z%s8Q_sJQ63frqE3XVK+lzNy8<#Xq0VuRmA%XMX*^iP_iJ>56Lxxy0?S+xw5*L;<wH
z|L>naF8zrDRwXYK%HP}w{21fr)|Qi>uOA%|aYEWGXM%pr4u$%!SHp`YD!D${n0%aT
z))XGk@9*wD4O;4Ta(DUrX_F^Uep>we+)2>lrnPI=KK=5g<l<w_)TAV({5v}WKgPtw
z%+c|jBqJ!On4xv}@G(%+RZ`mB{Ef6Kc+$w-*bFob`1OXxtc{>C;=m;E<ev$6kO(x6
z08$L9K>7A^mX(!#+J3)IyNah-L{Lz1_N-Z_LRW`P71xbYd4FrG_r0yz)AwXtRN9$!
zb=9VoD_6=$N@`a5D9YJXDCkFT^U1rlWu=biq?mm*m6dmP6n<J6yxgT<ZO+oAOaI(0
zzuzf$_<@SL`sr`qzI}RhwA-~mX~VlaJC(n`yzIVh!-ff}o|9BPC+X_wJlR+K`_%Tl
zyF#|}4qDay+41LUczmavb4Qn`_Nn;#zgv$z{`c=+(a|o^uNH!mM&aS%J2NjYD+&vn
zrgM5z&HsP3H}BkuDJv~KTl((H%gaw+U0waU8nkJp+)eNzH{^V5kKGq81n|gM7+lx8
z`|aB|&<<Mxaq)Kf`agk%<$dLI|NP&5J2+3(dzwp0iAhXsENG!@&h2fy@7}#*Xt;4B
z0<^TMu&@wxW83z;yDa|N*Fa}m?<`IS&8RoC@j6XZI`%vJ(^Bv0201qjjux}?%emCl
z*np0rY6M+v_Ug*Y=Hln)9zLI654wZiwI@qpo^5s8?d|!XO=(&2{h&s1g4SQq&X1a!
z8c-3-up)lH9q5ox=nW~n(q<wy3oSP3fa<%CcTOLF_UxIGn~?{2pa2}t`vQ|d1wClg
zA2R_w;RjC#fFyEckW&VzYOu}E&j(#bY-eW&D%?IlJL~-S*Vm7)*Y98C(kZm+`R=l}
zU7$`~=;|;~&l5C9Uf^YTYML&$y}kX9pFbb|`uZBQI5s0ggNcdh!_(>UpzHD$xr-dT
zc~dg|+#EsMwu2itY-rFq-DUk|(xk<UmAB>GY&vts2Q)|no>pD_UN-mJ`}_Sfjnk!`
zzV@rBvAJ~lvZ<WEzrTA;%^o>*Et{mIB+!LEi+}B$X_U$p6B7fvx&d^C&hKw;ovW&>
zj`hjTetpNb`rCtMememJRYAdvyBk^kK|_Zj9H7O7XJ?sSuGkZ~Iqk-t%FS}>O3vx2
zsjVwkXzbXz6EuGXIzLTDM&`k@XKh!mgt)l495{N^^~;Pyyiz6{YHDhrt?M<lwSfzr
zT4Uk`ye732KR?GgE1+ITSoq<K7b`0A{{Q<sK?QU=L%7ZVi|+D@Ha0QyA4~QeIpPAk
zS?BileD|<0v4%O_JgS~Se||pQSbq2J?()FhWw}R-w`N~&(~J=bfvpA5ISpFZxnL#F
z@$>fod)WEqR>&=1vczGM3TSq<-~L~~9Bog~xa#uvg00Dq1L{E2`_Lf=P!j0vooxP%
zSCmEC9nuU2jUt<Y)&W#P76EJl4;YplK6Wx1dX{C$n;U|M+xgoUFHT<9o5rx9@bNLG
zWx}9&Fwj=jq>n$nRlTMhSm4-fQ2Hu_akAtzb^m#w*_QM3Y#%cvGiZmcX;{5l8?@TA
z=0`z9bac1e$pp~I_rr$|?|g9TR&woHkaKerczS7Xm&aUC(^o-(A$E6}>)l<YqR0RJ
z`Rorm%<(Y4y@<)&MB`(<;9KiJD>p&C(5+dbGP1HC-)_GTI+L>NGw9qRZgIVYM@KrF
z)Kry}wEn<{hd}$Q7CN^Z6g~0SdYoV0j)$F{-PT`KZvTuEvzIPa{r2{Dd!MW|=)h0|
zbMy9@GbKT0srk<8kUOt%<Hn5zJ~NG0L~dU8BCtg}dfS>uOx_HjQzsJ>6C2rhr8MU0
zM{UvQ64PCE{v*$^4T*<0RDaL=@$1*3(%08O*Q&gj*mCOJxoZ{WE8e`x5mc6(a^XTi
zOIzEss(-uR?>qf<j$s^Vaj*$^hJUg-Xj~sMtqX~o`x(c;!$J9=f*CZ^>jfU>`*aLc
zK~FXZM<8U7=+m`Tq1spHFJ82$NY?xr>#t|eo>hE#G4a^remUEwojZ5RsT;|F4qnd4
z&;U(|-nbEQWmPEmVz=I=<;&GUM?6*8?A40hRkCg$=y0|vn!yICr$i#6qMrTQ>oiG4
zMNREhu}`xBXdjG(A=BI2+mC;EcsOupQR-G{u`BE2;}4WPnrmM#XPkcS$iZfI&<T~G
zg;+<AvT|~A{`m9xJZKm0(QLE8gaidpLwG}?GiVy&>gsTIh9k$0J^JwQutwx2m1+9%
zdKF$qD);W)`|#~sSkAF8@p^iCCr+HW@HxfB#pS&itToQU#wXJexj79qYXcfc+?sV&
z!BZ$HIT^H;y`{Akbd~#}<5zZXOg^4;YfGlpTy0OGb@BWEO;b1GNk2a?)Fy620wc%_
z(Aqf-4NzX*dCu^d>^;T@7Zy4%ayO6wZF&LC>KY~=J8<e07wF95latjyo>ZT|z(erq
zarWu@@n*NWIlsTX4LZg3;QjmYUo_a7%iDwAKRY{nk-LV-4U1Qxf%?ZU+MuHcpypQ<
zsAFml9>E8X%!7v&;1Zyk`3my*QU2@e>&0!G4i*&_IyyKoSe3o$5Yvs)=$mU%$aH$T
ze*5axs~5cd^8Vf3-JqE)P`uu+|1ZnO$M@p;dU+dL+lw0#oi9G-eEja+Io`68E4xaw
z84fJ<o_=NDa_P@);_CkMTy~eeO~}sf&bzxy(ZV94^vtzuV&(7e9R=M3&oEa6v{2;p
z^Yh6En^-$~dP4s0E-EQG^5NlO!_-qE7FJeWvXgi&)!*Nq66sb`W0RAUQ}kEP(Z$8(
zr~1iFI^A+jpwZcmPt&GOZB=w`OL%;&cY+G1nwlCz(K|1t(?+1+FMWM&<vepXH8r)2
z8ygh0LRKvJeE;U&>hIBWP87_TF=NHw1kr&1jjK1-J#_T~t<43kMUIG$UhFs53baiy
zC@2WD2D9eFLH4fVxpU@#HWis>U*nh+CIh;@bDpg<r1IkUS$qHCYu>-&ur{z32W)(`
zO7@L3q~-%HqS*!R`MfCIP<RDA{s&q^1s=yK{rt>#OU6Z}j~_o~+}fg<b!`nN!;Ye-
zT%cp@s;jF(Q+QLg!^Nyu%$qT5)}cFhK+6@{mV>uGE-rnzwYRr--m=Aq65ih0YNdNk
z-YBI*ZkeGDC>uc+B7#n}y?0OU;>C*vg@ud^XXe>T+yDEq_+rkvDe~N6ItR|oG`@N4
z!k^#FPmj%)UJ5#s2R42LIyFbjBJa5qq*4Q27k{{oSHix|MoCGj;Q2XO@RFJfpk~SX
z`1lVkNj@_S80XEKx9GTm#ht6R^^oNcJslk!km14oy8Qh7p!GIau7rGO`4zZ6&KA@-
z2RWiw+8lH@tj`Ps#p|rLpkrNITUkNJRAvNi+_QJ@#^mFCaaTV7uPE23iUqePUTrKa
zIliy56*NQ9CnVh-$Nt;R7}^ho&O<Lga%|ysNPk04+Pxe$G85n!x-y6r)EAx}U)Oo!
zga>HS)!|%r-~9RVpam!g@7;_0Fy)u>X(P~0^Kx>1A3hY!{l_Q%?c#o3S*wsQ9Bi+T
zbP9vE0O{!HOqexm*6SV3&CKua@7GT-0^OXs{_{?C|9LgtlSTAmD*V<rf6r7^QmQJh
zU<WT7P|}*><KrVBBXg#^>cv(SRn>!M&+;z!o7*&Xs_3e)wOk6%lg=#npT7un1;_4k
zeb9>EiXbDA<9)J+XBZ|Yq^Gw(JluZx;>EzXN8@{?&BY94C57VS?}Mjgn3$OET`~!o
zv7zuq>Bf9eqFbVE#wRKw-5w_{-OkknUgHzsxDg}`UYd7nZ^cKZ+uQR&^V$=qOaUz^
zJX+{E33Q%<<K>A9XBemZ?fZXjP2}c#hg8~hO-xMAKc1v=@Xj3>K0ZEBt~zt(%oh_$
z$xT5^y%OKu*$FyzFDXgs&6_tO<qq?$%k`L;nFZzL^(%t@f+iiW|D2>E`L<2mJnznd
zHeTt1$H#bW>i$?<S4#4nBmnALSp7Zq{ut}=etGj-^Jo8mBn#>;-_wB=%r2m_LO>VS
zZO^;QG-0!I>G3{UP!ihM%z2=@>V+?8*ax(Tf`x@8;l_r<Rr=1xMn)UT-bVfS^(*Pg
ziHRIMJR&xll3n%nhAZ;6r$$ce{dL-*>gbUpER$4T?peKQ<NrGwKq=?K>!kajrEwnN
zIWl)Qf;zNccHOWD5y+9bBnnDKGOA{Ld-cE_ANBn0`S;s4Z#K@myNfkDI~x?8$Bwc2
z&$Dq13lq!9%}vbA?36ao>yVqeBB0{tDTjBvPyYK|={YGOH@7$Q^0KGd7gG|aPn*^@
z*Sh@K&WA_K@7JnlSQT28yl4P*T&+qpt}}hPawP;b(DC*4b@z&j9WMgEE>d`Z@|D^2
z%Imo|H?iKkcW;6UXXxrM*O!-;UY%F|=SQKfzZ#plp2iMPR@M&p+X!0IASfy$4!NyS
zlqoYa6V$q_`}5KL#HKaB8Vs$ir6;KzJbjuw`}#W9i;G-Y{a4xVS<!y41v&vP^*-$J
z>(|}6x3@jKx3{`#UJuVze)~TQE>|+M^VOW5EWvh9)@$>lqutJvR4OVeptq6U`54b@
z2AYMcihUyuDino4W7*JtA}mBz!J`9j!4=wz(v9FmS^4_%a(+<T{KN^5khM{w-@bhV
ztz2=JuWbQM?PzFlT)cR3Mcm$9F9PrHI@rwaJV^y~*3YtK%Oq?nHu%-A_n4@(Ve3}c
z-{0O|+*kX1yUkJy&@5d8BlCp?j?5PqOKbtvWX<gSZCkgR*3{Gltc@~daLCEg30o7<
zn0|g<;>}H|9o^l|0RaM_VWBk<8<~{ddIW5K-Ub~xu_gb$-1YVG?Ng_U&a<!Y3tH->
zsHw@hN$2pfV{Bq#VmpeT_q_=G`tHTW#RY|hjk|YS|N8#Ee_!oyB?AM2rCw8;_V2e(
zN=^oyy=0Pg#pBD06o*ye>-oIBy<J>f7S#OwwCK2CpR~9LXuh9M#-d@F@9eBQCqQRV
zmK+BUCb+n?9=NeFd1KAbq8~qgB%GOH2-<tE;tASU2-@N>RXhC9_3PrNr|AmYuDS;*
zcgxDkHf-1+V9O<%^z7L)&?e)Wnwl$e@f(v^L5ont_2XVt8ZA21Sl)i=4S~UxgvU>g
z9b0()=sv}&+8mj)par7&SCSuJc%AfEV6PooTz1^EiH?p2EtUh_Zn@aKAJiIHu|ngj
z)2oBc?8<t2pf#&a>b1YM!q@Q#3k!oz`b|qqTM@H!)2qI#l_yV~a!N{4irZ7s*vc)Q
z^y$gTsu^Mb<GvNHjoSL)?c3gee}6A7dU|TnaU%=oHlBm`>;L!G{{HsVO6|1KojZ2|
zHYT~QiQO%B^XAPTFBbPtm@}v6^YioEGs5=&`uZAl;HHw25|e4xm4Ms|&^c|OHI$$m
z`btVn=FFMn(yw(yfBzrQUI);SJ;Q=uwO1})6wJQ1rg8P^)eksNUI3j&2-@a!%uFpv
zT~!slW@m}#<PS&1<2&TqJ33y>Jpzj@&>iM??%p+hmu8o6fWgJhO-WJF@%&`TzBOxf
zKwH;ArQze_{l&2^>YhSrXJ#m7SQ&+szP{Gl+{|3}^QrjO<JM(wI`;qnCoQfYcja@6
zODpqxzNNEw?6AnWw?}f}!iAvqXP|-WeYL+2UA`>rJIh4Sc3uFeHE1y<{*Cma>yU*y
zw%>a5Zdgo-&yj(PfEy}c5%cr#p-c`VW8=Uz5r&{m$L{@d3=N>gYKK}lJ-obxY*r?o
zK6B>ChQz}K4-PP1eRQ$>?AGk-pfgQDXJ4M0sy#u4Q#Wc$!}jgwRo~zB8l|4<kh=)#
z=zw<eSLRJKN<PM;qNc{g06I1aG}W?l<;q_&!5pA;B4a7^`T6<q-4Bm0aBK#hTX1)G
zIrqGfId9(N%&{nBy1p*fxeT%xe@|txh-Q$>myD|5y;Y@i&Hn!|_ncJl^wiYtCKDh2
z0v$sA?p@!_&FS58tz43j#@g)J;-CY@RF4I}2eoBfS|i-t*k+mMulrbWdYW$UFYfNk
z%l#LppP%>R`TTm5dwW~OzfQ2Sv$F%$DOTn0dNw8>U*y&+#n7M~zAoYCr>7lVT}}Z3
z6CP-KF2N{)uI*R$6uP!HdU^ZHBh^1XEPVAYU~l#JXLlExfEH-~`Sa(&^XKiaudfFk
z84Nmzkb~m@s3GDxS*=qpPy*cV3K4iCeTh{Xv<mw!sJ(bU<2Y!=_Tve9;58bc$w4`3
zcj$`kl7q)i&hHY{el)-SA0vZ^W)O?0R)~X-Pfr%(uchA86Y}!(ijFuf^q8ph;{N{s
z*1LbmFo4dA1)cD7ZA~O-2a=PM(}vR5VW0((=g;%!<>h_&^vUV^x>(Rjg%=-lO`bZn
z^~Q~e-s9`z_I8~)<8w8+xVU)nPxEh|*6n6UNKIw+ob=(#%iyaYr|Cw6E=*i>%ox<`
z0i9+XwIxHbN+fZXY4)^i#$WIE|L^mjuD8&wR|>S>tYOZ--Bn+;Kx0*HywY6~p*z;^
z|0e}n;&*8&x808i%oiVX9PQ=)wA{U4j)R~7IcUyt(e@VDC_1CLxj85UEq3b-s{S)Q
zz7CW*=Pfsqv9q%S&03tBYYkfY2_7Ek<l>Z<mj^A|11-D1x3^mK_?a_j42qxm^!|T$
z!UEI^RZ~+taqe8(%9WaYG8PNIde8e)#~CssGBOf$Ft~(8!GcHc0$yKR`}poc6VMhr
z&{2zTZW^E1lygOV4MUDhE~tqBi?um_KuaD$OXr+f4<1vD1udjIcG4cUEE3$7V3k&{
z2c7nieO(W<bIIYHYzOFODbV%?P@(nlxctYL%ja{=+f-0cT53A$`}bqL(u)fp9|Ns0
z11*jPb@toalh4ny-LPeg%l5px51u|{H8(fExcJrF_I7sA;TNFE3()a(7Z<rQGQ52G
zGGcq4EU1#Zx3_xrIs3v#ETFQkcXfDQUms{aTf?01Z$CXft*oZTc6WC<`-II4ZbXPZ
z{(t@AVt4TL!2UYf^Yd(*K@HW=)okYG=8L0y<YZ*lRQ$Q@Zx33^($Uj%=IbmWNl8wB
ze}A2r9Rc%|rFulQ!wwuf#&&j=sq<pDUQoF_W7aIKa}!lKqqpS<g2&OD{zw`mFn~_0
z`1bZT=#C^%9dPS>!K>@*^%Ja=lolQGpJbZ5(+iw+4}n%NezdT&lLIZ=nLJq-wDcZy
zr7DAfv~+j={=Z`8`S*@Y(~S<1*OQViE-nTg;Td1^vGqmZiV0pG9u6fXTe8?empgzq
z4z#UZyY|7!4zA_(_hq%r%&x6?&&T@Y%^!IwsV?8yW}w@Nw`N@hjbqr@+6HdT3cdLF
zrKq%e{SAvRRyWLD^1%~flbdTN*XPJo$>zu`G6%1kJ9!Wk+kAWZ%=j+OE`EMac8*mk
zmz<m&==x7kg?4eVJLq<F15?x1_I7qqwLMAIyGt&#<HQLM(6ng!`FXBEK|)tzo#suQ
zs+wSQc=E)FjVDfcfM%^hv(ufOosazP9|N6|HP@>2(96rqL2K8!M70<gK<7w^>&Jlx
zB^^>yRC022KR!Cj{o}`v1+~AwefacA$mZv5^Q<cxAQvt7pU=hsDu)04`zK+P!m(-d
zX7DjL)zy!Gzuzxzv-01Oqenr9##<CU>9}=W+;b9W+m7#SGte=~2U;GPW?W#1-CcHc
zPvz$;a`Vk{rM|tn2^w~OS!o11Oxbp>+0C8h@8``^Gm^3Y`$ZVE_&(?6CfCQuSV8AO
zPS=ZN@zt2t+1dH({HwaQl*l#}&m0*grA17TmVZYF&xEyWbJy`7PKi7=zy4om?C!Fs
zRdNikuB=R+5?{vH0J@J<U$3JiH9Nbz?(eTox#oL})AeEx$=Ck@O&DHW%yD$L^V67;
zjhUC#Kr@@53%WpuysVG62W{y2dhRlK`TB*|3HL9|J_1^;p7?mh;e99V&A>6Y*E461
zOpc6MpH&VhKVNvA@c6>)lsCP>8<Si^)<gt;y>aJ`O!oD4M{jM-X7x*z0ImDBtNpdW
zZ>|++j0Cjw&)*-kxHxuq*}|%?uU=eRJNtzpuTxc(6)2o8TnLb{D&YWM|F+SYGiaHQ
z<dGvs5^itHy|KG|eb(kFX1TXOyQ%k9eGSt6V{C42zUt_;$?E>cI)&9iOV*Q)b|v20
zk_oD?1Y~4*f`fxWmri<5*Aul}b`P}v<nCQrkdHwJurM;SEy%mOYr~c;M?OD4U-<A4
zE9l(#g9i_SZq3}7e7xxH-CGhdd#g;(`?kG#^9FQ8ldWG0=#Fj$(AuHoV>~^Q#%k9e
z6*GXQ^lNHr3~GOsERJp1SM@b(Ex2k8Jou3hG}q<g!j|#v%}v%{0Xf&!MCK<-9p0XH
zRtj`6@N&PoMz`jk@+_Y>Zyu;xjoOyOsqp;K4p7VH{oe0#pu;#SthC;MR#JmU<=5@p
zV?AZk%9WaD&Yr!vvpBt?s%nw%Y_q8Qw{vrHzL?Cl0LR{hbvMkvY};6P!$KdlLhAk#
zdFl3&qsJC*@9jN&tg^Frvb41NfABUIzP-7}?pRFO4q6<1<_ypNzu%<g?CW@{tE*ky
z-47o<%DO%8uG8mdXF+E;`rH2v`Le?4#HOCVzrQP+n23Oup#}vBty!}MbYNmdb@kz+
zM_misLzRNK`1p=3pI_GnI;f|ajrUT;y<cBn8>XBPU}0yMewwBUYRb)=DcL7y%f-#j
zeRSiKCn+^wF1mxx!9Ch7&g$#YwxZ(WBhb>PKY#vQk&EA!Be~3HX491`A-4W*E-o&|
z8p<KtNsJser=J(Ibz1o8%}wKosHjCzTeCn3O-5F>`0XUf2)%lSlab17^Zd5<_V!nY
z=DGLFE%chI)zQ_})ZN|v;AIDw_&r%K<H%{CQ~5r8C}?SKfBmJr=V6k8ncu$+g&yH=
zq!*cYgBMbmfAjsfu@KY;hKrc_!9}v)-Pt)oh4b<<-{#Iv&S&T5uKxPoV^WKxaoUSS
ztHVVvFR9l2d^+90)YNsNlI8UN^pq3^22e9!US1xw$H8qo!`~+-CxdP(xwbZ1P+YuS
z$+ZiV*zeuD_u|%8?K5Z3y7qgtx)c=|b&2ceZIKoQO^%(NZGOJ^qa{Plx0~q^d#g+j
z9Xixg#Q1BDW$}gW`SDlQ#Y)ew{U*68bTu18M{n;@&=AA-cd?)n=fjjoOP4Qy{PObh
z6X(vID?M}XUfcnfBuh)n#KUd85@tCwZuN4T<=jY^BF!ZvC^)eWy1GzMv`SdbC*ZH8
zhK9#m%RMXFKPjEw^g^(MYiXCL_NsS$rnSFHj^14;XIr)8+xtDQ%iF6?&UpXLC7%yG
z9M!hs0eC|6g>S-RP~jmUDg){P^X=t?))h^&ZL7^xJP$oNIT^GeY_3_L;WgG5Vq#(%
zQCl<^4&1sW1zKDC_xJbE<EN+TcF#7??~?L=pLT9er|)dDhsS!QC!|X1MsGXPBWVl@
zfW<EpN<n=|P*-YCg&=54<=0nNL-(6!D0vF4i`ltoIVbOFP!mkjIPJlOh0YZpAF+OW
zdz)QcTwFy(CE-YiAZYw%wpp%A|4Q-tKOfoI_~q7I-U+H;zTdC^KTX}p$F}<0k#~1@
z8&-aL5;J=lXf6`8m+$$xxvakGpk%)><)qM`uh-+Hq<_ZV7x0tKi&+pG6(v>n?oKD@
zH~~#f&FjxtC#gK#{eGXYiL9Vt;KO6EZqkX1i`_r}nQ%s8zY1$YNPLr!prjBet;X$`
zV-Ftib8$)90NS(mq7Ss_s=dR52i)Jh3tkH(AlUiw{&(fla<8Q_p#20(y{CutOPl3%
z$k+c7ym#;3i8E(hGBPx@!q#XMIQ^YvUvHOnbyX|qoR!n3xk00=wv!w|r*x@!2I*SW
z|C~|O-Pzf=d9(4o>i4#wV%7f7hi34G+((ZeZ_K)?wK%e2-h>GZ?(Xh$&y^MwI5;^S
zik^3(p!C%hPEdH+|Nql`dwV`JgI4G&7It>_gOfYI{{4PG`Nf5W8Q0gzf=<%eS^PZd
z%ZrN!#>UPC1qPsX1cJ(L9df}Oc`*~VTbI8BRo9@UTWi*=`S9mw@f594E>BO-38|81
zW@bCz$$;h=cfnWTJ-E2oy`a4O_{quYil>cKJcHhT`uXYnv6@8xrCw8A`W;+Src@NJ
zOG6z7F#&fqV8NPk9Nb)WQDFlm(!Mfq|Ix)I<;AY@_kB-KPfz~%=qRZ90y?r2bcDpU
zYu6^IaGpGQ(yi3}k#YJt&>cmfao>Xn4_4YO3kMZpQl?o7YHDmJPoBK7A+h;U#qV!#
zMY}KEFV)o4)CgNM!|%D6b{Nmfl`Hcrl@33D@F3w!_qqSMFE1_4xWCU9wBCQhgod5P
z&lg2+&nqY_Ja}bg@Wmyb!b_Ge?UW0a$ctHUbBX8V2@@tX+^_r1YnpWhw00kK--noP
zRKm?osh|R4(c;Cf{hlr^AsL0R<-(vt`sdi!gKmfb#rLYPwOxCwzc2Edsui)TL=$u<
z#fcLh7n8X_N4Oqt=hwDN$-TWz*K3M~Vug{B$#VbsZ98{bGCa7sIemf(C#VVm?YjQ<
z2Xw+&v5k>|_cWc0KkqDd@85USlZRhF=336lNva@|k@k|7`vrhD(3$bQY^rtsc@#9=
z23kdE{jK-i4T~k*W_(Y@!BLO~j)Gmu;9lR9_?$V{Cr_HxbauA6vaT-gT<dbPTfWX}
zJ~J9Ph1FKbf%Z3CSm?~b&)>dsrRJTxcOSlaqf_AY_f+=BpHELu7Zej~`~Cg>;;^+*
z5+)e}ppy!Yzg%HpQTa&)bpF7jqut7?s;bvNa*1j^IM~e2q$aFxYa9FafA@c*XRb#W
zKAgAzpKx)Jt3|~J1yBxv+)XUS$;lb9qd*bVt^+M!|1zVh{Ov8%9vMp^hJ>^<HihTu
zTnwkCXf{7Q+^%e3Ah2)WzC&pyEO&M&Y=7}019U1z#?4Kta<)}03=>i%L1zR{(F`tl
zdP=lM)>>?L`Fk-NO;8b`a#DZ$VpZ@e;pWhFF_xf}Q{K~b93dmk0-~a=-`?J4KC$z~
zf{2Ytpw&|kJdbkn@ErN_^76+&Ka2nTzAmG!tqtl0EOze~vyhb(5*D5e9xvatX%lF?
zT;fBzn=xnzGyD2FMHLm6+2;A6`(zb7g`&1(FoJdfzq>1)dTNTG?IOnn(7q?d*bjTV
zxSH(EXMqbJP}bp<ZZA3bT}zAO-<=Hb4C-Q8&|XNHORV=-uTc0=ym&Y0xP~L0!l0$b
z4RczveP@{j+UkX_65*4vIA9$w+|<;xq2^~1Xw&_+ZQE8oFMofp7t~J^vt@F)x++vq
zSa`9;`589#|71X`(+)PXfBf*!88kL2U-v^%&bF%M!GnZ~ii!nUS63}Meq}deL_XNG
z2(-o|CWe8b`1v{4gal9wvih%*S5s4)pyIi_I5l$bVUbU;wE$+fzOOnxU4L=u>uaDU
zO1per2QxdLf|i!o*W$}70+m4%ViCK`);{q3x<2RTrWtm%R>yiInHe+!7qKugF&UJ+
z2w*sHYN|G9-PnsQClBuKkQUEKOH6D$aKHg{9*3l)q=C8l@ol-cK@BN}1Fx>GHY|MP
zqN1wGId4iw$BF`2<DaWh-G3gaG0ni>?d{EA8UJC=lUJ|0Rt7KUnt4_L)PAk2s{@TO
zfL2NDF3V*&5MTed^}qoK&??f9l|d2)2@MZCPYOUbs)wAo1KG{cUEY3aP1M#b(6LTw
zXJ@s7>LnEwmgwzyt^NJ{pwXFU&)D?!^-JE~5<S{2E^fQd06Z@aY8!z@vD0AVo?DV1
zgI1t|`toPN_52p_awo-D$SC$M>xvHwd-m=P?RR!|2DP|bT3Qx3HnY9Bxmg`_C-7YB
za;`a(cn<p8|7B5ES3kPw)0s0qpkuq2En5b<$7+^IW>ZH8htF&?UeNs5rKR4iemckY
zR)4>+EjRkku2OE$H6L5EuYY)R)0hEtMgtQwbK&D-ygJd_d_FAsb$w4|anAjHvUPQJ
zJNuR{S(0$LjW^@+vfhT1M`qYmZh9fe)e72aa_N$gp`jtDAG&w%-bXuj@3ua4=n#vq
zde~g6(htw)*RPT@&%GrA8X4W5cXz_vxxHJnuY=m1OzI-f_e+b%?5hFo@?c<yj*bQ`
zfcKwoXL_oao8iF4i-P6v@3At>m^pJ{&CgGub%weQ`-`4(fm(Kbpw09vVEu(w&~8XJ
zez~5^%gY!UKou@%T>IIXnG6k*#%Z7fsyuvrL@bvX@JgGtY~5=5?frdz&{p$}Yu4z1
z2IKwb*&LLw|D%}Uq_n79_&wiL`%OBJK}8`iuWLnx1*nPd?d@Ii8hjCLL2<FL?V@`d
z3qKt@rl=&;+&kGmM@ID<=m-lXCBqvQpoNG@;4H3W#3Lpq2D%FM!NF!mhP%5;L0kU{
zK0Wbdu$=v==I__*JL>=MJ7M^BS@!jHKds^?sl2(h^|h{Va)gYG3}{i-nOUaZUt>Z-
zL_qfimc9x(Gv7Y`>z?V;#r@{n^=gN&>yQZ5(AU=ojbMRRZ|y94nvkEre#hzWOFSnF
z2nsfKi|cdE3;7SKlFHuR0?iW6n>X*nmoG;)rJfGhl;R0?Lgi<*K3VIuE#)d|U%jSk
zwZ6Q(Jo(X)P7fcSmbr81KDvKpmT9&@-W`jhZSlvF&dxH8*qFqcl#~QIP+P{XMq=H%
zbtlf8VPTjtYnGCZ4$u6WPo1EAoqc`XkI(1rMWx06{C=MH>&r_HZf@gK-!&N|OtVBl
z=MY|A?$3PU=YLR7Nzu7Y!P;8-_4W1b+qav8uEaSw8MLh2Pi+yq0=UqA3)*`L8uxz;
z8lk>_A3W*2r}FcLoSQ}#*4Er}0@i4UuUk<5{@zZ#7mP)AHSg~3-hQ#}fS1b`v%Pz)
zuYj`k<>mg#Z*FYdQTy8rG-I=`rV^AtqqpTaW@W8<5y;!5;#p8uc5Ieu_J;=tncv*m
zDJ)<6MX;&4`Qf{FdQ~=x;9*k%!OnxnPRg7034u?$5S%Ch?m=pRmNPvT5R?S1o_%m~
z^8e)b_Z}DR`)%K_f1m7<Daq{ZK3XX)zJ8iohmEo|kF7gmwm5V1ogJp_L3x(<w&&&?
zzOm|Viks!rEsG``>8<Ot@4R5Ud`gRw?7I8%b?e?nEnn@u?)=o(Uu$e^-o@TOzy0{*
z((emiht}Sof4-LCyx(R&KfkbB7RSz<;bCQEUGyk3rl!V5NLaY=-5tw0w$))v?RP2Z
z>+|Q{-WIxRTmAn!k4Z}`48QLD_xHE5wRQC5k6Vu2+gmLtBEsVC?(Q)uB=PRGYhs`?
zl37)R*T?U#18rJv<rY_%e3F47c)8!v<MQ=A$NS}#?d;|qeqKLm^5n%5D%Vm|Q&Tgp
ztO%U?dgsoa1|}v~5|rM83gsosmmfZHf`h@J;DN&&yILvGzRpRi-UY9&XwH?fV{d3?
z=Lbz|g@uJpt<%lBzHaU#mV#Ij8JV8_|Np+%(9>gMI5X3j-DoBc=>E86zOz64`~Cj$
z>h=4C=1l77Sn<zDKo&Hy)zOg!+GVYxqOxGe4hc6mHx6#@!#_Vi7Zeg=dT_JZUORl9
z$ef@#YQD1`+}fHQx-Ncq8E>z&`L!5@RpFomAYQ!4NJ&jqw6~Wp+8L7>JH4!O`Kj8E
zN5!}9il3xX^ZBf~zGm;Ys?TT5KR%nC|7iaIKg%z@4EXr*qgAa{Na{Sh+O8izDvlgE
zq5#^)n~<8SYBojTjm6dE<BFvl?@!RWQ5bT#Z?RR`ob(&{S;zXEUnLz^4BhZ}MVqX9
z=^Kml8y;Wjk!`<nw9k1}!tubnv-9_Lg3hA3dsh~;1pRP3|HpT`-)mi4AG32&@cXB^
zx3++;&PvG3<D2QzW|(|zLF(ygi;^>0wY9bH?5mA_dF$cf_Qa&5rgwLDYscnaSimS{
zlCj`qMHFb&=7ud>))d8x`)B^!44OYPHWmi0vPnx*J9YXr==}0~d#j!O`=7Jefu||+
z?t+?UUBa_VuS)0dY1~`=UCF>;!=b3iNJ-GF(wCQ)-5reHK6&tfft{WGqG8M9W2{#}
zn*n=!dmnAxxY2OYqD2CtqN+N=f`S)UyG;83Rec(G_%$RSw6^iruU`hn#=^3$D?k_I
z9&Y0W9p^m5FnP)~&`KeG`#%D8b#)Qj^X4vSS+dqF?@kBknzAihM0{tPxlUH|)w-kX
zDYR+RCYB}2xeJ#sXZM_>W%DIe)N@imSlG8o!B_cJRaHUftcR_QYOVeK&C%cAKfT;^
z`st^j{ai^&Nub#Z5fPCCXU^~_yY+zPLmxhTc(7gIUyJN>$ugNB_TRiKyJX#K-&oWq
z91oQJeOCTPp@-}nizQlRGG8}7{?iDKy!wRWilrMKPgr%MFr@s^5l&F;`~Cg>_87h6
zCnhR`R-<ZNvo3wr61TSswAYU*IP2QMW_Ceg;bz_FZJ=hdghheEpFe*<tN-TK@ylBl
zsen%E5?1#EIqdoQ`R<^@TkloBPdq(M*X#Sa8HUWDd+>gKe$Kj7^!Uk>oO7+qkL~~e
zH~-1grw0!mV(RSd>{5Kh$jrvTz$a^^Vx*S26Vwq5T^;6CUtV%`UF_}$PoIKXIG`h5
z)~#Fj<LUJHgv`v&jt&kLb#-M$@VR`87H7?MZs$w<_~_`3z17=aXh=PO^{OlF?5xD&
zeX^qa#HLT3`tYpzeV5f?Yd4g?kGmMS)hRJiv8T89=VoaorA1bU7$M74R(%JJBsVg%
zD=8~8>qc*LY3Gw=V3;{`Ca4USk&!9*@W64#?AhFYUbl`NJH`guk~>W|`ohL!_lt!d
z-jdSN&XZJl<n3gPX7aq>^SRIOz08_b_VYpK#psEMi!Tmc9R|AL_C<zN>7O5kM~)l;
z9c6ZOu621rLPEnr=k}yGH#UN1p$@n4y1J|Af-+vhe#Ov@k5{yVqqs`&jl~kaGMOMz
z>%OWRh4T`RFBCu6=lm++I7rczb9Z-_Pn<QY3v{l-g9D9SuR$APN=i)F_+&aj8zX%*
z+&n!wL6<$um?3fG`0>Si_Q=eeH*dnp6wq1ki76>6R*T%`+E$D0t@`Q&y5wf5xA+{J
zN+DNQSBt7I8dcxktSnhScdo3BjSXmpiDTx`&c425pu%;j_jJ(w`?hV{K$Y;?wYs2F
z-#?$X2c60N;p0a^+0Yr@)Aba!wYh)({5dsGL}~I#mL-?;Y#3uBLC5>}&FyOEmv_>e
z?mS6_p<(4p@FC_ue*fn7TT%J^+}y)cwZlQ{kS(mO4<9(-uyI@RaX!%CYG!7pfvM@y
zW_ErSHPL2i@hdvEwz7(filDo$Cae2@xShZM;Nio}J9qBn;NWlw2$+y`Swu-mX_YJ=
zWKl@w!uj?8BG>jyo9D&Is;>m!MFX1mJwMMDGzh`4Aa-{dXg{Bt@2n&2hgSrF8mYTV
zG?|#0UELLRzkPV<eB|g+MKv`xc0QSgnKLD8YHJlIpM3D{ou1Xau!k=L>On(&$9knF
zPMylSGlnlcJ^jbepNU^yT+Fz)XXlHGLmM7nk+bHzDhA27rQm$Kvg5Ct?Hh}bXh^=j
z3eLC7mC9tkZg?D!yAhmkSFE$G`od9ISP1Iw_sLp=?ka3)Y3b-&TDWrM%8rf>hp;fQ
zTU)c+L1SKPx8DoerEX~{8NAHr;QoJK^?4+XTmphNf?}w@{txpcm4$28@UXG5X=rOV
zt9Wwo^B<pMS?uC2^61so)u03CgMx##Wo_6O{Fw97YF<O!#l!9V8_VCvfm*>&pFZ8N
zd2{pf<?6FcGL@`mx!KnI5U{hevnY7b@F)tjA*K3zo`kgY;rsXHkN3$ox3;o^hDZ(^
za4^Zf=97>F+Ae$b(xpoe-o5LarW<|e?p@i77cY8A$MHxQFkHKKt)sJ3a1N+{RQHGh
zyz_aY*s3=R*FCp4`IFsRUnk2@pXnIl4cZy7K5j2)N6^K<74ty5GC_qsD0|ue|H&V<
zHLLaFVs~e?$)H{AB{qo_Rw1rcRaFHA1r77(%m4ZFCm}gm*=kZ)!g0l_pEvSBMdsAx
z<10I4mn(gfRyqqQFGKodmn)Uc>AF$aVbUzye&t|a@a9dMj6kaqJUu;6oIH8(&(F^f
zU%cpOYGMLi9QF72_x7n%r@okRNJLy*+0IVR(9jTc*y5KjUp7>I&6+D0vv^i&YO11{
zSy*Powd>c#WvxmCWPN9VDmhbAQEoAvhSjUHr#f#eD=U-oTUP7k<po-O@a5gz==ApX
z`QE<1pvxXFEOPDky8iy|?sm{MPd9Hy9zJ;l)H&Vv>y<WWZ)`zn>CvmJ!#C#LwJLde
ziM9OQ9Y%&TbFIZe-RGX39+u^z{nFwg=kDH>{r>K*b5xWR7dLleX6DK*4?(?%MT-|t
zoH|w20yH4;_XxCz)cx`&q~$qi<2tBz^PH?U!zh)@s`M2L!;XrNN@43_IzdZ-t*oT(
z?kW`)oWA0oRrNO=(5}+2*W;6)oS3-iae!^{(^I0LZMTMoh9}OPIkL#L+o1TF&&7=<
zUCW(Ab!}~B^Y?soTbd18BmC^_?84XAbS*3_9vtSkcX@oQ*K|$*Pnpc3>HUA(;zX?Z
zto=%F6lx{ySG>eiCQ}vo#^Q~|)kIM2wR;%fD170%@o`AW|9`c6{(ie{QTNBf$JaM7
zB4ULF<K{JMc;4RHdU!|SW6-|oi-D%A_Uw`2<m9}uqfi+%q_$|0(w?u^q9>e80j(R8
zGR;!4S`?<Ksd@0?Vt3H>UvuSOEnYQq#ta1u3yIIq&I-%At`-p$U0D13+YHNMHPDp~
zR(;nlUcY`ERN0+K+2nQIJogsMOrK@Ov#W33y0s|%{Ja}`DmOp6b!%(3pnyO_+}<ih
zMMX#TeeCNw&GlBqEq3b#IgEvsRZ(A`UrbEQi}?j;3#WK|P2-|PN(VhVJ33yeGhbu`
zuL@qVsO;@6&Aoiw+@M@m_xr8+(#a|^va%0fzwQPN!mM7u&nYEk$+E><58u7xv$eGa
zUCYA8#?~b-7Un)l<<0&5@yst**cFzPxVX5mfVT6y^-6(Oga7*V%j>(xq?XIe{kgq7
zZoT>U_qT?I#(~4_{EE|0C+6hnSWP;n8?k`_bhwCpy`6viuWn`cKG4Pl4`1KbojZ3v
z`gLxuwPDs34V&6uA%(d|yF@*_y@PkX4?Wr!Y+EL?iu;ZEmqj-UZxpUN+!rkP+xP5^
z!WDWO9$)BAI-YoZC7-pQ>l+Kx<l_r>9q4n`?~+}<NPqtyA<#nBeYL+ofNt8mbSY@#
zvi0lxCn~#xZUnV5ZkRV~Ru^bv=e<3Wm6esC+ZRCNeW3CDsqc;TAKlwqT~J;go)fnq
zJ0>RP!K+tYpk-C{|NmLlCzXbR7RY>_T^V}p$dQ)!o>y1Ad~@Q_qeon|A41C>AL9kh
z@OWKs<B?=y0PS;ZKmULJ>ebm>r9ra^FRmP8txrt|_#1KO>}>O$H~9oXTcaQ)SD-Cu
zbDoQfi-zr$&vWL@lLO5smcNT(Jb7fo>8Bd{`r&)@^!3+&DgJ!DU-8%K_xu0Lfo|YD
z+{T-jo__r9>6LEN^<tfTe0V_Z$}?wtEG#S%K0P@(;bh8&ty@K9{U7_yvpIQr;i?VE
z$N6sDys2rsCpapq3p8f^>({T2o}QM;lZ8PW3@wYFfi^_P*M6OP;7HPj#~R>}tpl|o
z0+00to0iR)wefz)kv`|rMp;lPx41`kc@{VVR(8m?zhbiHTiGnTyz2J0+{2(f4HX{}
zo;-aT8u9+dM&(6|7MaNV2#AY|OGry6-`J4&<3TgO$ZUbs^mJuw>)n_7D?gt#H=Pks
z{qocAva&L>X*!Wio|6<jg=A!89z1%q=*Qu+YvyrsaDbM{3P?z-2xdOK3UruyOpFY;
z%Du?7|Np<;m#*JAbH-=MvSndA-h-~K*j=U@SN+!1_n7diB}-VAEnDVwect|Un>Gmv
zdTJLwZhH0g?QQXm8#i)rajn`A78263Vuc3i7BUCWVGQBS?4Z@Q9UZS2cgFN}i|dE&
ztb2Hfb?&dH;YCG7Ti17nY%O@`WMOR$>N)a%4VapDXGbGw!_4Djy&nGl?OV5+f`$QS
z`n1W}R(15Li}<&%y4A`p4jOM?n(gW730h#1c79$j_-N=|B`=#mU3$>*C*L0!9q9WU
z{>CCi{6@Y<=o^dB<l`%)to_d3$k$4Or1e!vV3Dgg3bT&&1q)j9U1f!|{9bW!ab4I~
z`&;X}x0hEyRMe`2E{|;M{zz=xxUr+Vd-XTFoiTi#lS;mQxw3y%X7bGN$g(oCy8nO6
zmn>PLpsLEca^=b&pmjEf`RyGhsem>j|NZ?voM%b-`+KqK_VJ*l4cl^We|R=KKj}~l
zXU6Sqxl5TB#KpxiUFv-L{(XN#0|RKU@nkjMrruuPrRs~yUtjZeusZwu<8gUGIk|N=
zu7Ivkn_*vH*ZTWOktL|U%etz?sCl&V*B8yMt}c=F+}zxZHqxv9eg68~$H&KHny*S;
z%z|ATHW+|*)}KD@UFh{^XYq5;xLfM!X`rQu9Gskjkj^u-84zd-S_>JvI_%)FV{G&5
zeyx1OzS7mz6?Ej)wKb8<_V)G%H9KF;Z)#%t@$=`$g>tK|Wv}1c*2XKHbYnx}4C`_|
zHXexuKUjb5t^Tg{cgC}`v$KsB8Q93K%Brla%(%U6?WL`Me}8wLq|zf{==8Gc|G&T4
zH7}lr9_@1u`Hmi29dVHMxZl+qg{zMB1sj8^re@jpkfVKzt*ouB=UA1lI`tJaTeE)u
zzg=v?ouZPGnpRGGmuAm?{pafEUOi9(VyO7?LNF*e7<4`o=&VrC9dpml&Sqo)oz7BM
zx9`Lbrysw5Y5l8yb!DYj_9T^;UzYK$Teps3UT#R}O*h|N-*!q`7OBX{$S6!dtvLDQ
zhnwm1L1)dsl=GYfI$v$i$79kNcXw@FumrqUL0HXaMM3S44-ZAxc}`klEPb-zG1Jwr
zudnle{P+<xOq#^-_viIgX=&*r$B!3ZR#Q@1Bz^!=`7f$^Fgt%A==KxC<YPRb1zc;R
zwlXn*24+=NRbSlSZx7m_eo*u1$#du2%F4D~;(zWx->$d*@9TICJ-uV>@-+<k`T32U
zp3%HA76R$#=ZVTTZ<!OLcl`13enD~Z<)02O-Sw$EXdYjvDWS0eP$2~B41JRh619d0
z{<qn)Ha?zUb)yg^OMx;FsDJ}?l2*K%>~H5-P+$NWpv<_Sz;M3pYFBr+Vg0`v(4Zt}
z%JadLS)cbj4tyIC5%J*F)zuj{H!Xdk5q0>=6%o*q+X;%!1+TB^s;H`hCUg&9T<rew
z!9nJWA6r0ow#YhW|NU^7zpFRs#m(<GV|SG>et1)oUtV5*<JK)MzooKG&CRav7ozU$
zSWpHU{5^BV2h_isIdi6lzJB}Mxw2K?-|^bo+FtzF(b4hB6xvO>%IrJK<lw<(_Kmf_
z%RpzxU0)y1&H!rAfI268_UtJsGJp7d-;YP!pld!lJ3AQ~tjphlPK^Z};W%@qBxoDx
z+1ciYj~{n02)bmpI&3XyZPzrt*e*_CwFR!-VvCd~ip?_5pZ9_zs(ZO}=-HDeIWJzk
z2x{1!Idi7q-=9hu`#KrWaupt)DfKGlA0N3!L`QRbX^C0;eFcv(m@m;Po3m=;<B(q2
z<!NusO+n*GkTC{Oo&Z-WkRhXkea@?rjt9mD1PGj)Z{N>v_XBj8AuGd)6r(3kpDx_8
zMTC)&aq7HHtGYoA-Y+i#L1&bJ7Wc}!XM>WNrKRPD?c3WYPMr9{A_{aGpogbt;GDX;
zzrRW)BqbmAn%_I{<>h72>BScXTPyaRWDWgtQhk0$--4|_<d)=IT;#e)IYT!uCZKwf
z%E6N-IsN?n7A*#?kquJW8KWmI+XQY)T?vkf>5;WA15F>?*j=ta&!$qzYLdX(=<RNx
zPGtC%)YH=xO-w|dpPTFa``g=(pzAp<E_V0u^%b2nWlQhOnUbeYpBDXJCS{hxQCnNP
zv|7c}$<eW~qrxTX{IO$flhu3=y}7wr^!l&w@B59@&nej3$G>E}Tl)GM=<+73&+lKp
zxw-kp)z#v&%yPRx7q&h*IaxzX>kz2jxjEf`Y4zJTZ$KydZq2^V<+ZvNJPx2(y5YXS
zUJGy}tmyyyj31OY%48Oa9|zUxGLYdPP<`(F<<pWSOA<h1GwKQZ{{Q<eVUW=9A|vYY
zxw+OEcXycz2?;%T_)yWRuK=`}wxGbk$k>?C;bY~=vuBS!IM{5Mf6u0(x|-W>r6fDQ
z+>wdO?h__W0-Y)j8XpS_3o9rq3;Xl(=4N#%lMDqbt-!rgX3hldHiC{-*2_Mhr~*0{
zNqCCi?k7*4EU5haOw_DhdDWSv-qTn8DQC60Jp~j6S^d5}AbQ2TiICwhvz!|ZYooV6
zI@rv<VZ(+CFXbnIZfKu2ZCcm$j~_pRhNRxSdBeb9XJ_Zde^t=-`Rmu*o|9aTE9jah
zALIG)`#0!zzD0{OWI;uXySuxLMFHq=yA!8QIo;n^YnXhjhl^iVU0wa~ks~aN-Fk(l
zgj8>M3~B|vf{ed_(skAwi>-(2f-ONKZPt7%yTI)tP_->vHs=(g)Y<y{(IX~taq)|W
zTjb6gRHr>ZHy6~1*<bfpVe&}<F|lP4#^&ar!x{u6C080Vzj*iVoq>tTkrjc9Hxxbf
z`ttgE|MGWCpmm8Vo`>Gu-Mw)A`hG>{wktmjciDKv#KiP~_M==`8LXk9;ZRw*^U^LA
z&xp-wy$ebnf!5Le`SJ0><;%|Pe6pbNl8Y0!h?#o@9_!^^Rrd8&Xpgix-^!IML(8N+
zCzbqrF6QFm@(Ny|7Jho-3F?yV|MQ6(bdj*<B!jdw5}@ho7q_>s_p_gqkeJx``ucii
z22j^;%N7%zxIGaY<D#OvE?o)={OHl`>gw9r=kWEwr>CbsUJZ{wc<>-2=nNxJnJ+CZ
zeR1QKLwhPeUsxTk54snq&}xc`=M2;Au-5ABd3RS8?-wa4D?7F>cK52i$IqVSO+P>H
zYJk$)BjB_P9oGc4La!ztUn%+97gFYc#x=oZPCuy3fs9>4%AAnrFJFSrumYVFdF<G+
zMUOLVW9$Fd<^B8fQ^FvDVbY{Y6Q)mJZqmTV@b}l(%PSot-QC?m%OgN%3g6tE{_xEk
z9&vGT3v27ewZFeDddwLd62js+N#t<v`S@Vhn>TNQ789(C*~w&VYz!)KL6>_vIx;>f
zvYcg}&nGM_e9^F#gO}HJd){5p-sOnM$j-jSUv~taGQP88K@}+XuMA%P;e7o+;dSfQ
z{rMvxD0tNnTGVHP=J!C+AZ?c8kd~%)YfC1mHS^`&UFpT{{cY>l>;L-tTHR_{LH^#a
zVxUFM$9knfH?cf@`qazXKYm96WA5#3qBACRyxQzNT~AYP%^c%&zGvs=cGvy=mH6hy
zM$l9iXmz^PA_E)Qt}93T7E6`MC{@h_w_TiHCF~EBwdNDt>jQ3&f`*A#^vSk&#Hp3Z
zTun_)1(^UEaO)6M23;oO*vwYwv4u<KP4%-oJBuUs)l^P>9TpaL;^fJT2}&D56MpUd
z@{e9zTx?PFgadR+2<Xb|6)QNVO`8Tfv+V!BzYpKM>6vF+edxl4fRdD64^PjP-%S4|
zK07n>#M!g1US3>QWp6mVy}dzO761PFdiZ*LeJ|+#qR!6FMaf*Cd0(ITc5@Fu*Lw8(
zJ2-6J`(!{>`@e77_jmR=xww4sn)Kw)OGZIKLBWY(udc6`?~}LZD=sbuE!F^?IvxXB
z9{@Toakg`JDr_x4JD)7*JklROesK6{-J5G&4mxZPbi0ycGaG0hQBzYB1H;jyM>8%j
z<4rM=3|kYSXrY<8n4Mql!Rqz<4y}vbEwX&_mh9_%huis&gVyitC`>-c={Xy;_84>y
z73dlyY4f}T7cK}mxAV2mpD({>&z_1&OcS|o6owoJ&9&@bcq{3+VwK?=^R0(L{Npgb
z1rmSd&H8_z<=4dTm)rmEmv&K6(S=Q^-X~IwKnnrf`{for&g}j4sp!x5{r_E0Ptyet
z?)C-fMr}E;CUP_A94y4}`-cx77{D83FJ8O|8lHZz<k6I=Qy<p<dtMJZ3j%Zr^ofbe
zJ1Re`_4M>SfZT`E*|(zf(xpoUFD@vanPVATBGPMYZhjoJB9xU|?7_Xg)duF~?oLij
zY`jt|44|`TCQhH;4x0V<TUEKY`unll`TKi+etzEFx9ID;J3E`h)<$X8+FlDicI+7F
z>>f4$c{)~IVVkyXb1Nt?09}=0#Ra~wjv2DrHp<K2pC7c@7gX4svwnX7G%9?Iy;>_g
zAb=q`IoTxRf<xikkB^Uot|_>+Ef;jhAh(bEtrySE&V~+&J%r2wF*vxnvHkmA|6hFD
zwr!xxbfUIqsaj}eO7D#6d-5a&G()DR$M^H+Pta<C?c2>k6CWin0xk-6ZV|Kgd%N**
zK<<Y77rGOUD+clZ?yb5}xWWuH=(ORnz{+-6chEqt^c#yWN;e9#!s6okT3T2@5eBMR
z6B8A!%HQ=AK0fBCHu>PKTTvx0iFtQ-wa%F%bK~~y#es|67Cq)LFM8sUl9HleYb(pj
z%Id}Z0<`gR@nYpRe)&Goimkw{hd^gD|M-vyDl^>s<yuudHMF&bWxZd!xVR{on1ra?
zo2#j*MeHn61udGIG)c%L=Y~M^ww!|<g31gG_J2Mw|NHlS|KbG;914QYT9>>KIMyTC
zyf%9KBLDeziymieois@ZR9Eh;{_eIp?X1gj!7gd>koWTcf3SlF6O`Ti9OC2SOF-+_
z!}*|n=`B~j->>hVF+&1$1x4lOXCJ<PJvzfM8Fb{wnl(ChH=IM*|NQ+cC@$W9cD6Za
zn7}I=G(of?aPfoJue)Eo$Z+IbX{Vv7d2pU>HRvc|&_GpHRh5RWuBdFcNA||Y0()cL
zn1_VlDC`J1Ug!Mf)5gaEv5ChOgJiAwE}lN#=Umz<yF3jv_2J;aV3vQ6=fO=k?Yz9a
zAGh!SYb(E3>0V%U_U67?>!#-BiJ;S_Jv=-b+S}QSii<%f?46ly&VTRTy{6!-I5#)8
zU*FzxOG`_Gw(}_}D$X!WX5-=I1szX(;%O0Rf0mh<*`mc+F@=SOpkeqaQ$#?0Y+YSn
zLzA486wnmf!J|i61qB70CTGdV$~nBhvQqfZpFaXpQd|rfx3}r07)gQ#K^Q<ow%69j
z_gk00>*!f2IJI{Fl!+5TYau|(04v^Zy{^S`#%of`jT;fZu2;BRU0p$o1wl(<UtV6`
z-M6@ON1@}_ZFzUQSh>X(Y}q0rtmflzdt0uytjqULpM)m#fu@~}SNs$MFH8_pG%yfo
zY;4?7^;HYhs+uuF0<>jNH+oyk?%mcZo=qyAi;}rMem-x{T=6ZSO~te8x~Zgj-ksAu
zu3s<Q+goi|`sxZ7|5t{F<;&GUeU3G;yTcreR_SA#Qx=&x4Lq#Dca`;<^eXN*7A~L`
z6lBm3H1bi{k<~7{yb3%D0v_}W(N|Sv1<jjJ(~T~8f6o@Q-r@1F-sXi16+!3GR#aAk
z4x+FsT=e4HT<eFAA2-+i{pF}OSy4yFXJcAkULWYRcq5}Ab@mIODa<KTL_njbDk>~R
zJ7rE!(`9DZv2!P=*LHd3!_RMTZ`Wo!clq+=z@Q+eoiU(ew+~#sDypZa2in3qd9pAM
zFR$xyRoy2KA2!NbmuawFINmScztnp=s12&2ukW6cqH?THR@-7}nv8wjo=fj%gAORZ
zb0_A>vu9xumyf>R?BnC3039Oj3R{u$xGC-Itb;di&Xg7pIduJc_{aOf%l$&5CaZ83
z?Ub3M^72WWf{TkwX`?!1a_XwGy8pZ*ZM@POGB2xvx;|lHVW4TchfkljZogN>4LYev
zHc<J?moEyQLZJIQ*?6TK{QcJ->wm~ExY7ue>-SU`?)&km+v|GxnutcwsHv-~tCXMH
zEg!w<$^ZZT?da@0cx`QTU_bzav9U3zv6OtgueH6s-79{2#|wV&JbyrJ!hXfljgJMc
z>VBJTzu|E}END6e%rBdR#1DCYsFfSEf(tY}`Q}YdL{yZM+T?@x@5|d(eF@lAerbs(
z=whL`xOoe<%(}cfTpzUfMpKisva)i+h7Ar$NlG?0HVih_Yb(#rGCgtboY<U@HGlrp
zz$TftZf$LCZGGV(_5IIl_ut>%iXMKZr>FPg&d$vbQoeTU&2OlCd&?BGitygOdj>{E
zpzCH0D?g<iId;q`K3*PF5trYu1s#yy(dQNQ<g&m0(Wj@UPn<DB!>X&`+O=z2?{zp#
zQkh%Je}8}dey{JmQYJ4{)fJVLs!R)^M<UB<>FXbFWM<z`_qQtN?k-V&dApX*PEI-7
zDiy0)ZlLQO87{1gwO)GNw6f0rV)6O%Cw3Jd6hP}3wuA)*HG#IGELp;$?l(tZ%7iT^
zKR!MVnoy6g|0`Pl?oMN4BV!w%Y}dx*<A+Y4_FgWxPNgamG$8)s=*Ih?IX{8DF}v>N
zGnC1!l7`F-y6B5r^I7v<<t>w0rCT;<*4GyonbXhDYn?bz5VVvG)X;Zs=UZE(Q2+Q?
zFKB&xW#!Jc$yxI@ZZrgKyE-{pJ>05cU*26SQ2QQq3etlmv&`%N)qplkWnW)6b=`dX
zdby1oH+Ef~6JI*pJio2Gn;TRyT6yhVcAEKx%PUZej){pWAvG1epzheQWtW66?k;_;
zrXUMyYrTVaD?s;Xf>z{#X215;?tWq6^7YiSv$GAWzGQ$Fr!_V<f)3baP*7H8ULC&v
z80cWX%*$#$GL}IFK|-1)CL*9cQ(<9ZPl_z(%$@u2`SbRRi`^Gjetx#-vEbfKHwrth
z9IgY6C@5aC`6jLO6*52CVbU+#?okV!LEX7?Cny~*cI$O|e5^Nn&;AuFILhDOyV}X?
z6tyLz5ws)pSdZjXz6GF@V&P4oS<9C%Z~yxGy0hBk&|Uj7FRPtMG2#<?e3MPny<g7t
z`@6fPpT4}xyu55>&HIm!j~9M<5%_N}V?aa%M{@FGEpz6Js^<Ck)|ACgQUO)CXJ?sS
z4p4gg@%euFsdNA7PCu>aDfHhL)GW=EfYzET?(HsrFIV^f?{}?o3)|{%I&0RhE&bH~
zIb`#S6&j#PhZ84H2L54k)|-C#(j_79X*vgge0<ERu5$6qmoE<<JYawv5q9v{F}D&G
zrAwf70(#%1gIKNk1UnCb+mN93I|36m-dHTrE0Y09Ty34G><(Jz@bcwL4GoO|DTn>F
zzs+Q1Wep*BS$FlVDm3L?us&)l7wCHW$H)6k=lJ}-v$L2TG!WwC)Rgp@DK_XfV^*x(
zG+%#zcMlJaNs}jkd~#Cw&$rw8A3l6=$jj4XVqy{y5ouv$X6xu%Sy)w7HI*;?|J2S-
zPSBc!2@?cBD{`1m9*N$bH`i<aY))ad429mZhsRh?fo51dCxQA;FJ8Y+J~2Vjw5~_R
z^Tzi4`D~X21qJt3SwOBOa`}4i$H&JLCr)hKvSo|c^|^EBf_6>)`SG}4%FpeqYi6dV
z-y91_$Mx3MY<6{ZbqNUx4nMbBphgw0X~vM3Cag+Ip`b~qg#8O=ZFme0I8ZZgh1wen
z7ZomRzP%h}GOIYP`L4G1^zeLndt2Ph%na1Ka&mG4wXP+kq(CbVC!Bt2QTV9kTuuR~
zrL3Z^&dhM=(4hy99|ym5Gy4Ai{_$nLvo9?3m6oxui#e>h_557xa?p*DN1w6oa+{l2
zR9pLZ`UIEVOP4M^c=xU>w2EG|c=1#-T~J4M&Dyns!otcHE1#{6-7R*%{=Y3~Wf*8o
z?c29+3=L<_`26{FS|8L_`1AK~;m=R0pc|GqY!Kk&<g~I}<6r;a80)E+m>305p-Gb_
zB_t#)sED0>xSc;6l!-5{ZihCuL*8%Ay)6dXgZJj<X6@McEg6Dg>*Ll|WHfiIFavG4
z1+B+kxpJj}xp{cZeaO{It;_xAYpuI^>z0zPuJ21bB_&W5a`E($K4+Ij8y*XwvVyHa
z?LW}n7_Y8qiin6T*mQhJ=~tIWpP!#s*3jVa^z`(aFK%vb4!X4wROBBhnI#H2poZbR
zpX=Ipg}*@e?ArhP@mSmT%yO+*d&apTkKeuPtN#8@QCF9@wY7D_mMtN-wkX)x$XvX5
z@x-Z9LUTesgD&cXUd?rOwt0Be>9c2BySuqT$KivnC@6n_&-MH~+r<3*er9$)4lkcu
z4bq_9^b<YqC`|?pO?AB5ySw~-*l+GHpbI<H)!myrJ)&i;N<7x~Kjwc@db>~7Iw3uM
z`IpjVTegVIuldCJ<?B~LNl8w1b@ey5wsM0m<92aj0Zr65c6Po91r3Zst6Fd-<tmd2
z5{KsARggM&g`Sz280eBK&_t49^09=gt3oH7Oqp={Dd;Fq&|PHt`S}+OTVGyU$}J=;
zJaPW~e$blsJ$q!fZQBMq3`5rUF{sga-u}N#(N39Z)22o2tun2tt)2RABKRDsj2jyk
zE|_wwGyQ&`FK7jBE4TQe8#g3eU0p@5-QJQ3+T6qKp>_|{yk8l-JWRrlouRn6xaQMI
zb<hgiv~zPfxw*N0W*9L3|8;#oi;C#t9Xlj$Z_5qNQ3{TWTen5eQ|Q{7NM((=7L}Ei
z6`!7P>c#JidHDVuXyL@8M@`H9=RdlgzyBy`m}qmle@km?;p3+NpmSnCE4!YZnF$`L
zz3MFk*%-K}YJKSHFb{wK^+ljvbyh#QgIAq6dzN>Sie}vDr$tMzhhDrY`{CtG=oxli
z*C$Py1iG0VbQ09#<NfR(-Zb{YX5)Sb@C#nm1r>|Gc~^GJws*KBg4a7v*ma|@!$Sll
zVa>O)Th_g_TTIvK{k^>tCrxVl^QQ)MDX)C}A43}(n}WBuOhLuK+uPg4WrI6@etv%V
z_;Gg7;d`6Y&Vq)$mVO1LXEQUgg$oxp31v;&xY4kux0jJ2e0^MNYb&ddj}Oc8OLd^b
zRI0veMQzK`wCXxm`r?A)((iBWC#!HuN=oW$PW)zMu%gc8>9e!5Gp?+d*mfyn`kgy5
zHkF^2ocannEYRFM{Nt|D*VjbbHpGYC#6M8AZgc$dorMRxZ|<+RcXD>N1Qn-C)S%-~
zfqS37ecStf-)}z9^6O8Zf}(EktF=~ARtB}I9AA3OR#8>e+^eUjckIke<G_%R7SG9Q
z3xk*YF*J0G>nFXvwKe0)3c+c5v06%6nG^TyvDuP)JM87He}8`~dJ4JqNGvSbTmSzb
z=#1$U8>On&jgKd2-N^Tdg%+(Vn;>gTK}7{<DJn=})$W3aOk%oGEVZ?@M;TH)JvkW;
z96QF=*w_dfk^$X*WVB2mF)<Nz5bpJLvD&fr<?mz;9X?!|#_;$2t*zPWR!)0C(>70@
zJUMXho}8PT+oH!AG4t(ewRjdRU%veDp;qn}H#RPQRBNNG%nX`opRN~sVX-^EU|{R(
z+uQY%l9L5RL_!kRu2{hl7#Ii|GjB+F1lme@v`h5Ew{OQ@uiw9JOWD6am1|;l24yx+
z=oZ%pZQGsIrwO{{XX5PH-BYHBl)SkiIBnXr8=F$OLFci6&V2y&z=ec`U5|@2L5ml7
z^48bU;Q^iNZJ5NetNi`CAFVHU7C$fe^(C|9-5tq?4<9xKPcj3Y&~WK>=H+Dz9h=!a
zyuF<dxABTzzhC=3w&vT-bkMN)w|95D4>q%BTWMtq5|~qS`NEY9O7{2BlRZj)2uV*$
zTJ+=p{Vkcnpc$8IYoohLwY9Zl_Ev?4*sLvkf6sRAzum>p&Pal`?JxJ6>*VO@*m}?w
zd{&95<I5wr2zR~r)x5sGKD=sg@^L=UqIOX2aABeI)N9|~++?2V)7Hu@o@KP?8V5Ib
z^X%Eud-m)Bt@E~dee~wdn-SY`B=hd?>zyz`;GpJFP^on1?%j)Pqs@2h+I8sOJvs1Y
z?4UgWX=!Ocp3Tl@u#wjC^YLlv@9#fxLTd7i86BW&_s*R=x1;>M9D{@2^usr9NNi3!
z>*VIf20CUII)Zg)2WSbm%Ozo15Z%%7!qqhM5=&-gCTMQi%gYNieh3=0R8>_4-PpM?
z`S^t`nZXwgJ-KslY+(HN@1Ga{SDW;tB&PcM|6KcBRPH{0@}%X(iww|F9S1hY-vdpz
zIk)qL&YAP!&e3l1#N1q6B{jjlP4Kxk86}}sS@3kus-)wJN`YVr(15tiRnTrsalM#;
zJ?}0qX8-s1ef{DsTSP!-bNTr2fEG$La+<!ru+VvieZAeY^Yi%`I=Z`q_x$@jKlAdk
z#Dh(&1tldSb0T`4JV^l!I)hH<ySvMD)22<JV~nn?jeh*=>uUp3)2lZx&nka+hf`i&
ze#Y$C$@lhDPB{Iv%e1(-cuVGGwuuubG6{DH3kfx81}_T%RTKXH{-A^W-`&~CG^z9Y
z`gr>z$B%>ZTo>b)mBGs&J?^(Z2ATqvmtVhm`Qh)N-psi<2SGa>=g#e2u|mVe)m72j
zS{gKT{_^s2(fPC6c%>hGd3iZvOUA?pS7w0<pl@$)Gc%kya|YBIwy9VUQC?PdY@u_z
z%TeL1qg|pJdU|f4!$RJ@>jNEd|L903=!(+s@9u)m?Vo!W9G!7?^FU>wi;K(p7Pnq0
zMH`zr%iROkiinA6y{-5k4%#Ol7&wtlc%s=X^L)9gudiD9WUUr>PuH`k{G_7dd1y`K
zX01EBOJ9doR8(+yc)G0D0`<<o^V58Sok#kdw;lygekv+WyivGf8)S}pm9$|J3uqv}
z{@>^Mpq}d-%i<6Bs^2fnyu56J3TJC;E9ky&m*ZDvELoy*^!Fqc&yMbH=a`t7rQi4c
z`}I0vXVFr%$C<qsE(F{FH@0{|Q@%@=s-~Tv$IH*p59$)nn>R0FQ%dKH8BS;B+siYv
z@i+tp34QwX2{aeA<=*;u`!$i9-Fz$#>c#G2DK7r3bzN6Sr{Lu!RbI7AdZ2Su($duY
z=Gk<fIpZ^B`t-x+&hhQ7{@ylkUf%qLH@4+Q*ZlwceNl48+-<qHA06wJW?*o3b_T5}
zfgZO8>e(&6)H}Q6;OAa$(0!)0zrTSlxMKKlD|>z7r6ry}KAqMVm40J$9~=iO))hcH
z+#PY6paA#t<9qY=?Zp*=$`=bgPVfDCEgF<-A3S*ylKA}kjT;f5jSf@ah57C}dhwzl
zJD-e$iwn!9O`AX)!_UkxWCq>6vrFI7QWA8uuxZwm1xsAMXo1SOjrT$8-#a{{ArnTR
z)dDU{cp*^&S}uR}><mL@<FqpYd*tkDEGA8!EGRC{URztc=kq!1g7R|l83CK|wxq1A
zudp+K3crd93n}xwo<DzT7#t!aB^eg@&$k0DM)vUFu(7puJtp!9bL!+RXkWvM6&j$s
zpw!gVys}$cTS12ztX;cyLCG!0Nh%hWmf)qVBCFUzOR<xW^R=|KF)@J7HN!SOWpQVR
z!_6(3mqYe_|MBs$z9FZe;KkMclTJS^x~K?l$#%qD`S$j<po~n<nKM2N4o*%?Ha0dB
zX3qvy9H6}Y;oCQ{Ig_@W?UgnM%{zk{m7%M{Hf-O{&Hy^T%sl^I%iOuLpo8hNv$H|#
z5<S8}1LGU-3kU|*9)Ki#7niS$pta7{e1e&mzP`Smn3x!t7%&ZV)LYWaOG{^%WC}eg
zvXnB*>6l;li?gn-j-g>|_H`u<4GvdV*QUu?aou9NpnKFn(TX}~#IQO2yjw}hmPc2T
zVuhroyFmj4zO&6h2cU_(e>`*M%#N<EL%q`G8!|61<C<;vViIB{`ih(sSGCEU9!n!Z
z%b8R>K?{h!eEDLKd1;B1z1t)eP|jd}x#jfM?CS+@ZWw|Nz&LS&qhH?s*pri!1*N6A
zYinyk%l+@yewPKWfY!=nw6)zEbyweWQc|%b@>=u2z1xeQ`&Cp|FOJ_|2b$hJbm-8O
zx`(DUKMFt{+~42cHcg&nR`ux#C+OB^+v;x*etmt-&`|dF7U+)j85V^~J-xlG>MBY~
zu}4AudC-krxu6XKpz>b{#;V%s<?TIj=FCpe85qUS&l#ASipq9wnJ{^>@SVGNL1+0g
zIDCJ1_u@ilc2NDq09r-`T7jUg?VaMI=+-CG+0(<bWchN?gg_?4-*0bk7eEfE6$GtX
zS|tFwOQE2^;M`p6<t2Nwudj>PQ(@S~E3Kw6GXiuG@s7gB6K2hddilU|f%V}9*REZ=
zaQQN5@qR)^21j;ww#TH9x5qsufezf{RaMD7(#xH-?A&#Ja4)x|qvOTZ<B(-WN~^wC
zeSO6m92~5osv5fMagmD)%e6I;hvm-+3knAAJ=Evy;^MMisZ2&mNvTS7<6{BA&aKto
z^K$O&5M*Ox`|$mHdwV-OXbCT<rvo}Slffk80t4tq#wJ#7mgS<)&&)IiO^JXu^))py
zO_@Gjd#(4R7VYqL9A4^v85tU&vF4cFWxQ-`Y#n`l$K2&>S*)$C84gU<4&RV*QHh0}
zo!f6!rKF_fi`(1vq4(pqw6r7~>yZS_<<BzBR+xUe@X--Y(9Ml~T36oh|G#d_#Gb8N
zw?1%5;+3<JSh;c~=qS~g*w~9}A~$=zul|?cv%;vgwbj7PY~5GS>+6~FVjNstTy7n4
zC}98(+b<F?eRs!FCw||aQ=sP7lP6Cy3_t@&7rT>>D=H~13Kz5noh-N)v_QS%$j#m5
z`fdF3e9q3!ptYEPe|-g2BL<0wSoZw;^%^uz;pOcOI^GI&LDSn?TMr-U6m~s+ZO4-*
zDWG*lphE)Y%$YM`-aI~jetys`9iTxkP?LCbx<6=ko0HQqAYj6ylq(+}A9s$Am*2Q?
z<Av+j-2(yy+<GJwEtX2mwJLS;^5SZ0Y7!6<V%izA&O-Cv*|WU&YroGu$3LI>e4A@&
z?TbI>L9@aS9whvEn_n+1+xlwemoFtPEiIr;X`l_R`TPH}@$>UPdG<_6L4m>1(Gk?{
zelbJ;?)&}!<KAY2!o?Rl(kOVfT1`z&Lq}&#k*&5iw{Fyy3kgcA{6R;NgAT)pjEp>S
z{(O6kUU<~?tFiYwJ3MSa{p;Vnf`XaGAQmX_V62PX(Ys1CK^M+AxATE2;vZiw`-4_!
zgVyHT*~JwmWn^Y*{`&T|`|9fO*H0L#GBPxBa&sq6o7T46fBvCMmxMN_pKoh#X9rzD
z0y+~ca+6Dmk0K8*ul64Qepzd=<l}v;44{)QV|SNn=<13J`tQ(--KAh?DERZ|&mA>C
zjX-<bva`9lxw$W1YysUNwXx!35@^NQySuwPdV5<}uhuRqF5X!1(5Xk-oX@uEi-2tK
zW6<59&(6;7?pt^jG~~5piOQ2FPeAvgeEasT;?EC5BV%Jw#R9rPw{JyZW@ctVdAa-P
zX}TZ({eG`(WfcXUK-pdXKI!YLt5${$epf-w#9sA7|EH>Wo;Y!$0<_+|BQ6)-KRFNC
ztue!@G^=&%?d|!=Z*Ogtu&de8kh0|MG~MVn(1b%+SlElZyUjt@A-O9lDFuNBGB(^7
z5S+LTvO)}rb+z~N^Yh9U781U*%~%;~J{}eS@vvRqpzKY=(uXR{%*>#zGw<%~T(pR*
z^wky3miBhgv2Z8OpJ!*7GIc5=!>=zdn;RM!K-U~zz8sw5v-azCUZ;|yps|I=kDJ%U
z?p_qRIqk*O)zdHi0`0PtmhQfAA;6LI=+26dN-?pqfk8n{aeJ#CK04YR#Wk@SwiZA`
zQ<L#SPK24JCMUm~&4FE|uUXWu?rCUX0L`~HHa1?keqCJFef5+nQx2Rz&%bfw#tEmN
zPEg^TH*X%OcKq<>ch}3y%agyox!E*1>)x8k&7hrPOO`HOxM71pU|^uv>t;6IAStiw
zu6K4km}yu0D@4M<-{1duE4MgEVacm2oD35tPHY679_T$?&uXV6hoE3!>_f<ka>1+B
zf`Wpe5(v~54P5NzI7tOGSIW*Oa{y8T8Rp-!0d+cRKc6-K@ZrOOcXxLuW@Kns@d*k}
z6ap<{0;hj#5DT3Cp{&5Wpk>Qz)~pd(udA!e=<xE^{Oh0tKQ`vvI&$CuLt0uI1E|_Q
zbm4-4rKM$8X>@dS%#H%b5SvRu*m~ea47JbB%rr1Hb&ZOW`ttRwXngg&>gRLIH&lL3
zb9{N^)vc}Cpt9QhevL5N#HHVw3l{=FXCP^ZuLDg^?kah?D8ksx>=<aVRPFDwxiSv+
zb$=|x^kO)Ylaob6MMEP%H>2g<->0iEvjWuW`Stbn)VTLIHZoh6zdJI|wi<L$!_uv`
z)!!V{CMP~T)H<uj1GGxyBBCP)>ON^|YJ!efaB^}|n0^{mY3ju65a{dc1Fa9p$;oj!
zuA)0-{(R7WgHH?Pl$0)cffn0+lU7o?R0d*!>LnO!(XP+WgAM*yDXG~e=jZo>+E?f8
z-1+$UZtN;uom6{$U2Mk9O-ol)g!qHjv++uq2*^5jAn!1~n|XbmY~Gz6iV8C;_U+r}
z;qMPRw%V}tRmhKDzYg8LEq(9aJqg34mPhrafj&Mwpz(GIiHO9@ObjpX>@;2%vr|c7
zW(6DD)%j~HKR@%GYx(f^`hR;05B~i8Tygqo(d_zrI~>AWTUruMP0<u>JI@F@#<;Pu
zafWsIx(3h<0qfZiog&<2lt=g1cXy>FB_$Un3kV8^cFMMAb^mSa=y=5p>H>knV--K7
z&(rbh9H=q%>WU_VgQFuOgMzWKFz7bxUGHCAT`hHfnQj}ebQ`Dz*e#~p)Y!-fI(Vnw
z?iYuwRS5&QvDq!AD>P@)mV*nO+b7JKv!+5;T)h4Cbp3GfW&qHk{W7w$rZfDir%at1
zYRxly_UzT0XP;3~Q2{LheRpSP^Sisd!*}K-Bs3g4<ix9XNv`(yH`kmTou;NHtu>;e
zqKaBtT+D1d0uy}p*yqPgm_9u`ac}YSb2m1nb~mKldU$E6w}H9&`l7ps4lzyFi@lVf
z1gd(uVRJZf+Io7&etmuY@pk@x&^2P9OU%!lIg^l|-@pBSowU(RpY-zRWwUDk|NZ{q
z%a@kPlZ8`^X1=g+adF`S&C7t3P#TB@3bIR3)}mdYp7ewX0!y<S8yiL6O+Nk9s@kc_
z!-J!#scFIb_52K=v*|&j%a8^s3oGl(E1gHqo9hG|Jv-YxK1t~9<SA2HK71%(Xu#2Z
zG{0BDT>bss+ArC@k;prxKeF*ksaQ2#+q7-lx-tPXQ&Z5f)KWf6Y(bM4kP|~(&F#wH
z$$-vK%(-cFXJ75^L)ClNJpgU1-n`j4Bt%5bZw`mBu<+8YhYmTpxVj#^b}cLbbhza&
zf8-9xmBMdtB0(G0K>IF13+YTUnSz6ZL96RnSy?BjaBkbS?Z(DrcB}GtI#zm_3-j*o
z0v*b|qx7|ykFRfHZtmJ2t-p&WsXYAh@^X`qkl;kUB+%B_I%gM`TV1m4aV+5SO}k76
zw1d{ARN2aE*EM<Lx<5arPgqjd-O+JiPvz%;s3<L~F1HsiU#{FE3F@w%I&~_pNbBu~
zA0I(wiz8&_ZFTtiw)N}RU$UK~a`4Cz7SJsGl%PGayUPxqKFtlf7R@+~Cnh%b<7xf<
z2QFO_5)>5l@bhzXa$>r3=Z=fJs;-cfR2OLAud}lgv~{wzl@)ZfM|pX<i<=wh7}<y&
z1&V3s=4e{20!`C^t_j?<Y15Q-w{P4?xVx+L!-o$7Q+#x)tE)lBg}l79^u+1Yp#5G#
z!os5S`R(oPLASPp*457m>A7(u0(2)1X!pIleC?7OM-+{Xg+aGg7CvS(%e@uyaBojX
zM@PtESett~=u9GacXv>$K}Ch--@kvLqf?Up9_y6`-7C2<;UE*}9`5D-^W7G^^|Gj`
z<vw}#Y}qCKsgoy7GMUiU(a|B>9w!5?Qj{S(@myS%^nzAHZG0>+(X6wh!yzMM#W|kH
z;>S!^K{MuJVq&6xQ<kPLTC~WZ^i_yW&5wYMfsCMIIY9FOt^4=yf6y`ubf%!kq?Wt8
z%R%i-=Qf^|ACpx)LHDAXOz_(+A};=TZuvdX;&{;B%gf9C7rXb%fd=nDGhqvz+m-C>
z_8nU0vdcwp`r{`jCxcEztE{wq^XAQk-R1c&UcT(?Q{yq$TXA!qZ8hjd>*D9<G-Kc2
z+Nuqj9ZEdh#_8qe;u7*7x(cA<)zYcj;YqKqth}+mzJBX&R(Xp8hGusDV_l-!A8w}4
z&(u=@&3;SWDD3Fyco7Pk?fO#x=5BStm8W<A|G%C-Jy=MEGu^p^)v3A7S;Xl?r}Mkr
zQysQCF&a8Bto7`@rSzq{i=|aeAg@GV&%!$^91JymJT)~0)jSTQOi$i;=@82y#~BQ)
zhj&hFF@5u%|M(vtX91UQw|wXI&-}Boy0+|@rJsl1(eI^<E4ptyW@z|cyffz3zS`YY
zUtTOcaKPcRW!&0*ybGA^r)Y<-%XoaO*Q(}6!PN~pMMXt>f6bgcVS>WxO;hI2U(d!X
z6|(oA9xE%W+=|b3dE2A4!`57wWtzQ;H?m*C5Hy9p`g-%V9fo{*J4#hmRY5n2sl43x
z`(1EG#)^kZ3=B2$%r6)i7#M0U9cW}ujhtrp>&4>es<26Bd3P$dZ)RX%c*jvK!@v+A
zzVSFC14F4`wG6|Dy7Y5%0zEuBK7IN$Wy+KktK+K;8~Sd&xxL+=TU_tTy}i|?FE6Ra
z?yuW>YgcNdRne1<g;vFL{FW;zDP39Q+AR%Qt`O(y>e|)a{kcH$!EHWSt0jxw`(GVu
z<=%C1MX;AwSEJTviyaIM3^OhrC;>T+p+^4ykK^`VUdR9cHEo`+m)E7}{Jo{qyC0m6
z(VO1Y)s^>S`qD{Pw&%w)hcYz$>agXj(|D85z;Lex%qm2%8g_SA?`n9T|N7cmDT{&y
zP0h_$SBLA@{(8CG%gZaMvT`TrO3o7}JiflUdAVenU}tA%)Xt*RwTCxUR#tj>dOi$j
zm%gzvx!vyP6Jg(ZHaAPU+<oR+g@VpR=<N;NoOagddBxh~<9(W@rlEezH($GdcUtPz
z+l(crH<{$!vFMdHKUdNfuBEAY5j6ks=T8mj1dvlFPX;C>E%NgA2Hk+ZblEa3Ev-`}
zY77i^os3}5+r9kr^K;hiZEtmLZ!hzeo@-zKPfz@yc<lbVSpEHfHi_v*EdkNjp8w!>
zWN28v;rPM1N%hPOAKcy)7A(K<n1NxBV71I0&2JVB=@HXXtq#uETmAjsr_Ia#=I-iN
z{SbP2nQ!p%KH06w$N6G+m-()Z-hOS0X7H3LQ<luNF4wZOj4Xb3#&B-tk#gC*z`#Jo
z-FM$Dl)C@v<8k@yTU#=}rZLoBTNAlS$J=bS@5G4{y*xZt{Nm!}HJ$t1^wOnETgu<Z
zot<s&-`Uy8#m8qhH${Y9{LZdLi<DH=)J{Du(zLRQa&>hr+8Hxx$u!+)EqnX;>H6{4
ztl#fR-XX%kaQ_H{6)5)ShXe*LY~z)_cWE=Pl*xsy+1K9{3D$sm;$Q6lf42AX_YZe+
zYC6^<x!AJ!nTCdjN4J>nq}0e+*5&J7`Y<@y9+G1(@A}Kja6oz^C~W$X!e(CJ{CtP^
zS65%x<$tjI?z<}6HT}}JcbBhU=0AU3+Syqz54Cbn`uD#%Fexc%%Dj2&&Yba4Rac*V
z=F5yplZ5746fSyIT3EPoj$eB3bG^7dE0%gs*V55BGr96Zkb9rZ#KR8*9330y_$?RH
zkBixQJ^TK?+O3UW*2V6gb<XtI!-5w_#pADV>+eahI;vezaB%Hxo61eI%yL)BT9=*3
z+rGN=^|h<l*!ktw*#G}|zU>tQ!-ra)1<VW#3?Cxr*Z=#eJNHKIn;VAwR}P5l#_x*(
zUBde4Xg6rk!87RmJlm;LrYzZ*d|b=SEG&9k&c*uw-|MCISQ)OUzbPzGzj2>|VUK9F
z%pJ~e77PseN9EYdn{4?CzHiOC>UF$NHu(0oT;JsqpqBJy&JTs4Ft`1FN7<8$i!11G
z8*k~iH#b*(?US{Bb)b=X*(aNKcgycz{qpj1YUDJX)0cWAjZKn|^+=uHc{lH7j+t)U
zo*NFTdwkpZWUnlAX781=jk<K5UBqIppQxDFsfPs_Z*Ofqb?)4>)JTx&F)?#MN2(vb
zI`8_P%3{;}dv{9Ou0MFt6umw7wwdo-tI*tATUP%1zAAtB`+dJlK0WbdPGw-Y!V3$R
znKNgeI&<dFx#t!urMGHoYF>PDa<ZytueA9zm8sLGdry)w&02DCvHR<@=J&6xiQL>{
z%Ea(W{+q=PVQ^v5Wy|-DrCNreVS7@4v-Lqa_8q(Z=G(2^oPJ)*#%9l}^AWYiWp5%t
zA@cCyLoGeMX)2M^mg>ds0(n8oG;4}V=HWKpudf=~6A!no^q#I)wEM1?r{~4Z=j~Rv
zw6tWMkC?W!p@G5n$Ae}rPENxRu6!{OktL4JY?&7pI8IWTetPMhJ27YHT8H1>o*$l<
zx9*{n@uka`r%s)^w5NyX=G(H%md6SU4z69jW=)8LgTva_OP4Oqy0Kv)dp85aif9Q3
zb_NE92a_#UO53-H=|;V{|Nq~1m6e&7mt|dBGqX?5HtH>CW_^YSGsBf&aJc|V0?=}S
zfg%40D2v$g6_l@u-tMQr??=+r3psId^CnH26cQD+YW|-m>Q!H_hJU@0+%LI~rRMMg
z$L25hs^4dRdvi1E!h%LMzd0*DK0dy>`1!d>`}Qp?|Muo)o3^dGkx|gZi4!L+*|f=s
zSHi$S*1F6jhBZDUBt)hCuwwh+g@+C~$yye<l<kfM4gA;C?0IRUysPZ(s{Q}IuCIEr
zu>H%GVE>i1zrUHwxYU2S=+1j(=JA89TdO}DWZzo&*ex|B<x0frHEXV{3SBKCES$W6
zhoNED!J^%F^DYa5N)3h?A2!eb>+}6iasR(B%k4cUwed(Us{iv?K5Ao9>$>>;>#kf0
zX>Dma@vuNbkClO8hbbr#IK&>2V`pHv;`*krLH-`Qe9eO6a@9T?H*Wm((!YMy^|)%^
z+2;9SK|zz2tp9)K=G(Hh(c8}zXg-jR(VMOpzi-X6v$Icc((%0X`~Cj)bLPn0d|USQ
z{r!07HlD!UWp8<=AKKC>tbXs)=G|p)FMWG^J2Wz~QoMW5@vYg{x1^t+w`%t4xqiz*
zW3|uD&ek?F3o9%v?CS0get&Q8)926At*%SVJ{$IWR%&F??z@|GR^O|+f5#)2UHr?7
zi_RZEew<}rzwf1svRTfJ1@7{-A(E1kQkF$agoK5+W?j|Vns+zKIQ`s}YipyYPM^N~
z-{0S}{a6_es2eu$fr4tq_G|0o*FQZy{k4DnugOy8d25*2`BvoL-?yvaVbh(w?M=<i
zTN4kneSLZPc!?GR!vWpIdS(WOS4yDLV}V{$Kl7gtixw}wx+OFC>GS8W@9Zqjy1FWK
zE8~}$#_3rnC#hN$K5BUwv><PWW%07O+OMItU$2HQ3+~a-(*s=?TJq(^#Z~w3-%pF2
zW|n&^WyQJ8d1f{>%3m`l+&F*UUvIj%prBw^clT;3tM`|dcE2=P52}0aUn>6pHU59;
zbniXP?BaLkJv}`=`%nw#uA--2R})z$UD=Wuy!Y?7+fv49JrA827;3~JjU0xW(@VXl
zZz+8pcJpo7(W6H-Ei87tviD+UVECc*&76S&>=}s94$S@d`Sa!3`TJI;&#Qda#{2?w
zK+wGEca~G9PnXtXebol?9JmIY@Z<KT&6`cj-bCEYF)Mv{C-UIIgXT5s7A!b$I5n+i
z{(HvVck9Hx_Vk}kTV3W|8WS_;(c{OWQc_t~ym39v+<Et>YKLzreC#G`R}*o4eSG+G
zzqwQ9%vl3!0%kHW{Mf>_3{>bdFnmyJY;64X^L+if?Ca|?e|~y8%RGM`pR84i6*mLJ
zgX(0oD7hn9Utd3U>eQ>d>b|@P+?sLmP_rw;t5u*Skk#McojQ9qbhcTp&vS|J__mY#
z`$6~WzAQQQu;9eQf{d4!mabZ{B4Bsf+f}?v++AJoe)IjbVz-u-R?7C<PoF<mudlCX
zWno#7d3o8g&3h(Yei`E8(h{{LW8uTY?bjph>;LTmZ5tOCPhY^tz;ORKqz+$jZ)e%t
zS)gR5?B1tgVG&{f`{sEOAt5EtU!P9vfBkklKl|UGpTDl}|F_g{u9f6ERtAP2dFVNE
zclv<_Mo{)u^O+Hl{5Jmouj$kDVpq-o`zD?36vGu$b^m!+mUvE<usdGP#m9H;!NF$J
ziVq2%lTJUqbpPMC?W-1oQsk>QH#c)}a0I-+w^vkNe!Zk|n#8(&zw3Too_}hS&eLbl
zPUUTXz1;rq%ksKon{;w-Z8^zY`V3U?di(fXIW<*#>ZD0UhrjOGW3zP0k`<daT{?_Z
z12Mds8ob<ZCFo>|q9+}9^0up-Jb&IFv^Zk1Tkn)flNL=@_g_{1{$A9Mf`x5-vROMM
z7#JQr1J%Y2yE<(77#P4kf%5BTW*T2z?l14^?w<YQ!^6<#EKn6bN!9yF+3v5eR<ECR
zjwOJ-<n=Y*<^J={<~|e!^|DWI%6n}*E%oJtgU#hDPwY0$xe-wN>r3E#yIPaNM=qY1
zetmsynto2^>GS8=udl8Bn#Az;wEq4nsga@8kMiRlXUoJCyx#XyZq-@y?I)QT8r~l-
zs=uBe4JsQLUQPJ;`1tF;-|t_~um2sbs;2hp#>V7XhRJQ9w#ubTL9T9YS>N8=e06>O
z{FfmN3=PqT{;@$yPzDBYak}I8xA*tg-~aQ>{M7mL>&+%y*<WA(_x=BW>)-AFU)NmP
z@cs7g^7p#-zu)bC|BAo<hx6V&q2DI^+g&^{QF&|G+o+>Qj?6e`nDynwMN_tR`@dg;
zWi1LE?Eii27Zns#^t7t@umIG5IB~+m)zvlg>8Yt|MZKV&)ZXgtT-@AG3oM?LSe5?!
zQ@QhQo@v$<58LW*Qw~2gn9C{u;p{=y+uQS}r$&B#m0sxS+37dOLebO9!{fs0_4~k8
zp6R^Z6(1L+ou9Y%@^b&zA08f_caDW&fnNfHEGS?C*0;2^WnEa{_-p_F-}_g6FDfcB
zsrgaBD`yk&`r6vbXVZ)$I2afTs?no&Uh%_2tgy^}yifM(s!;9Ao(=vRZsu&S;of-r
z?K*Ske$aC8kM|BXvxkO+ECHRfr=zpx81L?BshaBQ$AdfLlK=kt>gDTu_0`qYUq2k?
z50C!+VsSqxg@FR5>d8cR9?`06N4v$J7FeueJNNy~&Ba|^Ts!aPv9hvinwf=ha&mfk
zc!09N)g6V&mrurJ9`BR=^<=WYN#&=M%bIQl1&*bcm-}D;^78Wj&)=usemm`K+T}+_
zyT5+9>|ectkD+1L(#DsdKwx07d3k20@vF<r{kMMKSNZqJWdBe0Ul|w}<{w5+1-sME
z%viY4xqVgk^>ti)d|@ReC0oD#{rz2AUETfiGGF5mj*9)Mr>D*I`{1>^?Cq|H3z9uN
zI=sBSL!+XilHZ20|9m~`%o!is|9?K4ww+hiw6u(rl$4xhRhqR|(jouiqShtr*%NPX
z&tI?T+!n$+r~K`$t@rBY-&xmh|1aY5GT+ta%r9hO3W^W6@di)Vi+xhId+MY~i_+)U
zg2LkJyp1~EjEsy`9}cpM3JE2x0ChfK1y|h4HETj9tNE_l`~B?e0|y+0JsB7n%3J>O
zLbEFaIPVse@BMZwn~R@6{QA1s{2l+!*Z&K?yxc#XL3T&y#^mF({62W8s;Vv%t^uub
zxw0wsbkz0etyxQ*+xaRtoLKYaONpwQnwFxX<J;TY&F3=9A3VrvE-op#^27-b&!EW2
znV<tO`ed!8)-f?G$V-AI!1ti-0JnCR=U;v8JzdXpQdf7ksEA0&<DczvRVR{j85kJu
zv;USx>AN48^ZEJt)q#uMmKifF@Oyn_<>YDl@#~h)uZ#Nk@88vHr%s*PQuFgum8r(A
zjEhQ_IX^gp3Wj-AuQV@nGB8}poOb(d+3Y@W#2*OGF}uy{-&nf)uIau1&-R`=<>mjB
zk%8fk**CO`l>a>_H(y&Dty){l{OiI(=c{|Gze}Bu-BS^`I(&WD?y|RAvajp$hcm6n
z_M2-}db#xUrYlQ4g<09zt5=+;e)8nWi;u_U!*`dxHL3ek(c0eb{p;6;xuC|%larI9
z_Ev4J``8^Xp=bL3%uHi0PR>9`v(@K$#a3ty{ie6j`RLK3QQLAr4dGSX;(9Oak3Z2l
zeQBBRY@Vx(3=eMaV1(vqo#<_6N|+cJ4)BBei;&_N62Bh~pFV#clpj=UZDYPn-~Y$8
z{^#lVydQ6v`E3@oa*J0P@jJ+hN=a26c24~_dH??XzrMa+e&&qN(IZDH7M$4=|L2kT
zuLsTiUmkVqXC3R2ym}4P&^_8Mo_%3~W814e{NFtvl@%5^mfpO1Q_8w*O^(@YtMYd-
z`uzVG7#`$3VgnBZfWsY1*gb!Bbv3B!d|I~q>aNo4zYqEAR}`*Zmm2x$`}gq4YQ8+7
zOe?ZMwWDjd*vlUuA6Gr<R9|)X)84GBTA*dB$;WywK0Mq$b?)4?n>HCeefo4|{{4Mz
zr)^g+S>kfMUw*pE-SYdjppJaZlh|`}EEiY5-y1&LJb&Hv<|D%DetVv#m%qKW^zH5K
z#mu{Y?EC5e@Zm!)9-ffAymhy>WF}j&Gc;JWOJ87wIu=I#kg>P7|M~N$=cGPa>t$hU
zqfXwxf4@MqVb{AmJBzjS^{+oX+<tXW<>#zy&{`fRr>1qWyO(XhUl+Z8->+4m;|xI!
z@aSzhh9Nm_85tVR&sSXi^Ye55>&nxc-UV^i+&np1-8A!(O51rxh8^BH&~_8da!~)s
z?@sysTAumLA38vx@^bn7b%r&1p1RT7uIShQ^aiyUCoKtE8})MK@_Co$*;d=k&Ghl~
z>;$#?T;1GOmA<~FrJ*rFW$LtPS&xo%{`!6Yf8LG@)+}snSvNPOcJ=g_%uQ-J{dCvb
z_1V|g&Gc&%e|2r`Y`^(-xmL^!4OZP)!edYE?{Aq854GOfUA|r~cGnV6Qz3f0j<<WC
zjA01-f^{0Yx}lYom1|!=efm^OS9fidtdLO9<L7~~pladB5tp4Ydamy7t5>Y>(3|dk
z>H6WHKY#w*Rr7Pxy~^jZhnLO+Enzu&<VeWgyh}?ukM+rBZ#bc|`);1qLG`QOo4Nm8
z-c$M6r09tUubj<}Tl4i97(N_^)@?{(*5H48SLtdtKA9B{9wdByb=4bmeh;W$7#Ft=
zv?tHVD9E<@o5@_x1$?0CS}~mnaF>bS=7Yml(6Kz(4-d6=_4Tc*TEAk2$J<+5KbI^M
zoUHC2c6pia*5u=SH{X_R&AYqn)~^Q#o4-D{|9>-JZsf*|8@c%Tug@?{Hp#l8QTpb_
z#S)<!26pif^O6@Aq~5c#vuo?=`Q6=J9v%@9(R-Lz=X8*tU*B>eMuru^I@@o*HIqe8
zcntT$@9(P(jfw&duDrOlH9PC>uB~SI_tq>~qVo36&ft?LPo6q;DyXPv)5{PByLa#F
z|L+EsxZ2_CGz<*`A3l6IY02Ss{?!W>IDop7pFV#U6%}3j=~L0sBS$hWEO4A<TfOb!
zr``Gn1_8m#{jUE1UH{+z`MJ5ltHai=suT0RbZM#g*F)U;;7<9&p!28CoeK*KoA&9`
zr;y0Vm3FniGS18}lrl_enPr}zXLWutW_zysW{w%3-j8V)E?jv3b#L*bBb~cLSQs4c
z9^-w16jfkm&8>TTt4(Wvm6&E<^AXpJnV=FH7Unf62|j?uc7gHE#uY0x-rnBszd8N<
zwPn7uLn0zHJh`~JgQKEm#Z|pjZEbD!{Pk<wqw{vZ&!nt#4-E^`QczfM?dzpWL8du3
zE;PH|Q&v@V)zs9~($&4XDs=UfxpUX{^ziu3FmPmM=ezRa;^MC_7Wc0LRWrfwcg>hF
zL(2IGDA|DStOE_?c6D@2P?5E%2x#Y%4N6H_vS`sFpCwY?|NVZit*!07|M%VZUv6cu
zzxukFTV>^vB}YId@>ec%@ZcBNk5J-6rlX@HXq4~LrAtrBc3)lM$$w%YFKjJ<@ZRtD
zs-;Y`rYu>XfA{a%{JO>Z`~O@j&}6t03mJ~Q_Ur5G>^lu{k&!Fg<*Gcs->Y74mUkz^
z>Z-PkWzmvXX<r^aN@8VW%et{4(aYC2)XAyorA>e2{<^(E!NFUrzGm6}`EdB^HM?Ig
zl$S19@}j@~&tkdCCxXtc&uV`^Xp*%qTM@X}?d!V-ObiSUD$OoqB*_BxLx&HC#>D7&
zZqo6N-Boh&*4FIR*UWQnEZCNNd)6uDhN_24r^j7t<CXsM=ks|`9=~+Gd2{skysHNq
znM)rWVBGuVl6RZ--uC(P=l}Wp_v#W);hlH$BBw0{-6<ZwzpksV?^+`>yN`O6OIq5p
zdG-H(N*#VaY08{AYd}#o*XpXn%<maDH!TH~ZkBWXM8(BlPYsU?3=EtoSO2GQYwqo^
z%*;$J9UYUoFAG6q#V@bFyu7^h;UU(`GZ`3utbuh)p>YAC9{BM{nRvY4`+Xj$&CJFt
zmGS6Er<8r&9#DdQ`8ql+{rtS#9YPKIUf$l5QzN7HRBX&Kn|<lhrG1}`r=@0|oTMtZ
z;xlLs>$TnQ_pRm>R?E1!$aT^Z^?4OekRJW_d)2S*@85sW>GQgnor_GfuW4v&d*9xc
zJNax{a8c2wWxlhQxyx0$n9cUhzP|4263@w?7Q@>+J1>`fiY<R}L2+x&%}v+7hOLcy
zd10ZmoX)4bt+Fv6K;4do?Q)m8M76&hVCJ83?n}po3jvYSzRo@W^Y`!7@%!seojDWY
z<I}@_ih*H;G_C?>`st^ao}Qi#s=ih^F8O}HKHk#Oa?|a%AP0j+p32_dlGI~;knQB`
zoVxjD$&(X;ra3o0Ok<PNJ$<QDSluS%MJ>ovz0&5dK0G|UtM2bEtI}6Xo;*omWn-J=
zXPkC-SLvx!r!KY2*RA;UsmRscUE9<&RN1{Rq+3ik%VvMc%OKm|Z#M5LdpoN!>inx)
zTUSe&<!H1YR;;i8pOu}On%dRh4|3wazrT4!XNBKB2s&5Jlur+IUff=b9S*;Koj<wA
zwY%ick3!pzM})cf`KPOhii>AoT^0K3!op_I;5z808Efn4)YQ~dr%wmp-&e~!otfc*
zG-T)z6#p<Bu>9;C%V1EQ4cabsS(70k-Eyv<tBcE>f(22N&ds-9zi5%t(W6Hzcbu`A
zeRkQmx3{yuytoL;V=gX7eCOZanmt`iKW<Ix>1mZKF3g!TN5=NwkH=Zp*UdfFFCU-V
zQStNBQ>)5POF+BYK<%nFZ`=N6?!0$jug72S64icEU~vW9hFH3EDX2F$+23yE$;s-k
zyY=@4oS$baDkry2H+q|d78}EX?FNwXFPOs_7#J4#&9*FF21-e%PI-Zy4jSc)*%_p%
zsc9Y)zqe{@P*BjTr{^E7jo!Yh{{O#a#(S=TrfbFHYXblOd2YXY@BOXW;d}r6dM#y=
zF=3(6W{VvUo*g=L$RzO)i|-tZk8Q6%KRbK5iIuzL(GgD1OJ81I{(4M0|HY@Lr{|qv
zVK|U(Y5;DEBDo0EZt?#1=H}u*e`@C1R)@WO`4Ut+UR@m?8WXd|Z?2W5g2I84MaOHe
z|LqVJ72S0Et=y`QdOY**#}pN9nlyQGXi(6i$H)7<C%xPK-mbN+O-j!=`}8#3?O*p^
z-d&#m_1)dy?^r8mUb+-Cb^7${yW-;F)?K=EY1MT_MMY2|RKLW)utFF!ju{wsu<A|s
z23>3F=ht^9Z@bQEQ1yA}@L^R?W;UJ+pv;$gO62g;d4WMeL8ZGlfKt=xmnGLK-htL^
z?J8M$=+GgXndxVGB#rZa8&6BsG&cUMcjZUlg$oy|>`VUTf;ww^tG-@pV&(pFBf0-&
zBfH#+ZQJVq*XhRW2)KChV(5EOQPGvLyUReG@&oCS@7`M_aiInq14GS?Gc%1%b8nf1
zhK0@YV|?&9uI^{*-jBzmL8GOh8veuykKB8EB0W7lCoPHp`zrj`m&^WJi=X=)UOLaP
z_E(ATe7o3bsdv9vZojQN`|Pr#-QurbE}#D`V6LUv?6=$OlOx0S{<Q@K@b&om*q=Xt
z{(97{KV|ad#Yc{~fEtO{)<l9*bx6pRmuGhOHFM{kzyJSVIj@9)L-@KF(45j$M}>BN
z`7lSv#&<iP%RPPmTw6=a>*>>{U7ej57dSSXRDa7k{FH&=2U{L^d>`3+4~oCNyIXzw
z{5-4DS9;SJR`_q)ym{)pdFy(5c;;G{uRHeZ@Av!bO|!2_Xc&VI?Ra%*Y4@GH?Lk37
zU*2p!ucfHC@D?c06%-u!?S3q9a&qFCT6OK~>+8PiKYECopZoHz`t8>1dB2UnRx;RX
zX?gwr_V)6do13?0URDzo6Z4t`S}#3q+Op|!Ri257iIbM7`ObQ=`MjO+Om2pT^NEli
zERug3&cD36`g-}j9lv?E->yA<p6S5ZIhMt4wpCwNl<swGX4BHv{+uu|a^l2^T|GTh
zRHjaynt7ms@zsruiyvye4+;!i=sVl&rMvyFiMz_*=UE+p?K96N(s#Dm)jnD4l<l{#
z?katq^}3mz|JwZjf6|>x=N&!Bx_y1^?{86CGA6#{VPJTr!iL#fnFAh<U<lxEZEJgV
zVWIQZb=GtJTHD*JH=L-p`FbUIned*V#csWzQ6JD&2c8A@4{Xc5ZBqIwWNYSSx98{P
zuHIO8zxMmfCnqPfojUUf)DlRLV#aK-ox8Cy*;k!mMSD<CkV*Z&8eVBLpSf10lT;$7
zslI&OY#6paZf)e|w3$98t9I;&I6Y1G^2NpOpqhB+-FI29r=@0IUgq2O>dXcm@443H
zVVRjLUy7^;wJaMN8ltXydwXBqkm$@WR>{t%w?b1_*LPZK=Ep}zH{Hzf^7j6H4m2&L
z>OHMu0ccdG9WvvL6fd9wy$`3f*PnP<qGe|ncXwCm<kZMtZ}aO{e|~=cHK<?t<6%3f
z({*{KTS|I*_M00UH{Hy6b!X@1rsif}^~zq&;AP-ufL+ZFB_$=F=M_`g<!b_@&GSOs
z+}wJ%o;u~VHfpPvp`jr-h?-^<6&I&&z8Ml3sX6=XvO9O~tYUV^`W*Y3fnh<}wBPpq
zlbKK)2jU#y-FY`}ZNx^W>}zWR3kx@b=63w%T4f&T5R@{{o0DTU`=yKWp~HtoB_vkd
zxf8QB^YXEhzVM%4*VnHF4Gw|Yp#T5<{kmBGuSZ>79e6A#fA8063!RFIpG^6><IS5K
z-#He6x3}d!21WFPLdc{f$bks_pzp`epD#hvkH+V1lC6%uzH@3J%e2&$n>JlyHocb)
z8q_yPYyzzU+<rT@G`sZjGGFk}_?a1oZQN%cfDBF$V#Y{83=CUmSe32<ttyh1UY&M!
z*35GsqxM#RzjmOJ*);hW&t=UIj^XQKE*|TZF8%Q#5wvn(u2m_hyk=r%_FXP{_#o@{
zwDa?9Pn|!1{pRL$P%-l1LqY7`s?eiHkG{IHaxxPWlaD$R!-L7#DuNZQXVWI9MsB*9
z)78@x;^gFXH9R9@#Y>y@A5W^!&v<fTV$|-kwMj`yKF<%hTY%dED_pz9%wrHU1<xNE
zRaj3yy)<yKo2I(Dd*1fwX{nm}`u?7tp1Z2Pu5xmA2Bk3HnMOxJ(@(H<5r|-AU|?v7
zlCduH;cIthWo0e0nrl_?z~Sl!(DlWud6$&Gy>+!@-EkgSt1ZW>+4<!{0s}$C#JUX|
z3~s*t2FgK@QPmHOWxHdw!`Fp)d7a|D9=<+q?UX4~s_IXhXI1@tIvrF`XZ-u~Q_3Kr
zK}lJ8Yvt!ORaI5bNp)XW$G^PnZ-4dNTx;IxObicZOU(e!s-d`#;X|0LRSBrWV^Z}c
z!}AhoY_`NIG$KNy{qVxA+1ItKtwEmF(C{cMECh`d@r2*6-Cg!}Qfj2>J$_Ekz|72*
zUf$l>Ywo`I`Rmc*e!EMcsj0oy-(Ou?>b>h??WC`TCw}dIcXiE*6)OrSFe-T7ym=F}
zFv88P?c7}J@Z`V$e!ssy%QTy33L`^+IcB?ufuW$gsj0~%<AMUOl!?crCq+A_%$~h^
zXYuo_-{0PzI(ybM=7l6=1k=sWuMe~-_{0g1UKz`vZgKrEFR!jUdD}tP$)B5R{d(hZ
zIpeu64MD4o3Lm*#ef{WBlI7fUQs5Ck@9BD>5fL-gKkwmU7r*ijG<JM(vHRNByiz6s
zk&!czXR}emZwD`ErHF-0k%f$wj?R^d%I=_YeRI11(c{NwpKG2z)3$nB)%SO64;^xf
z-BIA!Ev|nJ)bd-hM5XrM&*!f$FYmW1d68gsIr(1g_gF~1esYt}*%^k;#%X6(e4GOx
z<K_*Sb^IW!xww?nD(7~-tGnKnSc%HXy*sGH!0<{8vzB0B$SQn$%k=Hd&F-zOtwk0x
zpww6XZq6+8{B@xF=;iI>3JVKg-QB(Y&!0a&&!viAU0FGMUG%i2YQD2HEG%v~yWV?z
zpph9ggz%<px0K0`swu~x7I{vp`?6SGQ(4)$_}Q7jtgKZheflNMa%Su*d8xGh_Sz{^
zL_n>5FAt9u-+EFbxi~m3H1pf7m@q-Wd1+c<!NIdjmn;FNRkNHKR;900UcP=W?FkwH
zg;ymk3<s7&XMa(`IiUN%0SC~ql8cLmo}M4b_L!JCyGmXrS)E<o($*HnTYs+yeR$KR
zzP{cx>x#!D5fPCk$9kn-e|dR1^mXp7Ef+T?ANP4$8IzK-L`hj$)iX6U6_kCf%HCw`
zIQ6@r;NaQ4pH68PS<UV0?+5MJOo^OU_xtw!SATwf1}#*RtNW4YJImxGcs11NH1J{|
z6xT8whz<=2Ik8FS=g*%f@86GSWMs^`wPoc?o%NejP70O2zZVOdGrhXLZfWJ`XPNi*
zRD!ZZLc)SYixz!3CY_)0=ElY%tGTakZ(k2u(RKNzoS>lKLS}ZpkiC6fU6)Qx)&6=l
zJbvY#Jux?L-sIxuHjc<R7wm6)^h2dCs96u1DBrWkMmKg>h@zq*s8Rm(^mI`{!G)kx
z%cRY6Cfv<4pUcV6aDLOByzRG3SWuk~DzwZ&6YO*Rmdo(9%kZ_Ay}!4%tBY%E_I1CH
zA3uVo{%dOXELyZEW%Jeh)lBjAe@j8N9ACTh+1cjnw}nMTt!imuvHkgE@+_OmO`x;A
zzP`B`{P5w!Tbok57bcybX`Vk1G#vNnQIcuioe2559}DaLeV%{%{CWRrsVmp4@d5SJ
zkM&BYTV3sV^e9O;dYg}XzueVUZt*Yk7yH4R6`lS4*PZ!om$Y(=dreA8PJa6S{d!Pi
zYxVklmk#sWuQ5(Pw_?SL69t-}`4DXN!wy%y>E89fZ{J_VyL7&7br>TfBPcsOdi)q%
zH_en27ZY0s>g_)|(rF&^KaJz}kxt=BOI}`H{<_!v-i4>9r`yhaY0AaL1s--U+Z_vP
z$2BlA`>0D!oI7{z#^mFt(l)OwetwRNk8j_@V$e!RJ>&jn?yOm8bs{6f0>5O8mL~(l
z1HLu!`{RnAow@k!?d{aaX<FLazUq~8_V3@n%x~^0&EREs3jTiI|9@}V*;z~V_x}l+
zw58-_(B2P+xPN`$|NretpZ=R$v!@?Ad^r0KTfH)9{gk6)V^DCgZNRfw^k&EP)$iHG
zZ{(OoPE(zIcG-y&9;zxTA+@b-ZL`iXGc54KY!@>yJP_L%qxbgS-e^SeQvYwyoxJU!
z)lBnjt4}>Fm~rmQj(xSiL2Xn}+{;xwXw1s~{r!D-P|zgMCXC$M+dL<!`OaFxZ~rHN
zonOvmV)b=Iw|3H!&(F_mo0x>i*M6D!>+9?Aw>Q_U(OJ4|*|pQn+<*T3`SNUb{;Qek
z^9<)c5(OpuK3QwE_QMOCnwTu-`hg~6!Syw0q0UvdOS{Y7W?6|dFwDOOUAc*p=o_~0
zs`$7_hR^-#fuHkit3v_<6}R7ByI_IB(PPKLcx}GDyBpmrZEiL<=SUMPw@JbQ22d96
z?Cb;&N66aMM6j~5?s`72`pdQGe9uXzPM-$V!o0FpS5iL3ex3i_b=TcIP%rkh;^)~f
zVPo%yvyU7*cJI?cR=?%JkB|4S4`+UXTocFtuPL*d8)`rQ`nuTFZ{FlYPFo6c&(WhV
zoB8bwVt5%E@}cu>C_Y&rrW>_o!k4cMg}=YOHBC7&A<O(t)U?zc7pz@eT{G|Rs|6M4
zX1TYP96IFW859vQ<I<%|UoLs;YwGCuOae`B)qcB~u2%d|_1W3k%O@(kXMK2Zu&cAv
zaBi{;Xg$k<1>kD9nT>an%FY<Qr_Y{cy}Pp$v^=<|xR_U*iQ&O+Y*}rEYgN@QAz|UE
z6DBP9_V)Jdb04$b-rjzFk!!b4`ho7dFRuN5@F3yn(W5J?zrW++=AL{vZ~eBs$Z17I
zMK)78<by--tjuCys1d{3@=RDD_2c22TU))SrCzPDS5a|Ux^yXMu3}@^;^%?(pe3c%
z-`)f!CN7lWYoCL%zUlGt{_vQXIaS}^>Dt@dU*5^U@WTXK1-q}^IQ^W4ii!(p5w4e)
z(cH&@nVFfJbiBL8^{1Up3yzAqRSsILp&PmB2y^MZho8^eU%$7vTGey9UhE{$xP!Ka
z#)@0T$NOYISIpJ~H)0+fW@2W3TC`I{P;lXn9TsP28oPsPY48Fg28LHMSe>E1{dTU^
z!Hzq3Vs7S`g@%QlO53byZvNdmf7QBt^T_nHG%aJ}&9|y0B_&Pg74N?L_1%2lEYOOz
z)hkv^xSKZ}GEOThAh2MW@9bIUm>3rLZMyUI>wS#5JqCt%2WA?lm%QKmJ?rzcvtQq_
zmE5`0C90kG+c^1n-(GIjdvC9-3^tG5uHy~5ptqo4LwnbmO*eB)`IJ|@ZD`8Bw|>o<
zFCp^^L8JedUrssvaKhn-7vA079U2(85OnJdXisEeA*jj?37G=w9>p*))L`kDGBDg{
zW`1#C?#_z`zV`k=8w)-2;6c;v$3;88Y~TNP?X7@cH#et)ymoJIwYHsIoN?M215nlH
zk1g*!sMgTezy9j#YSV%T4$$t{jm_!(pFV#s{q`nu>GI{;Ha0Qg>*GQT3pavBK^qzv
zE_Z%V@}91DmGm*n!_jLIrTgo<ydN1D{!GA@d3LZ`m%m$cdAt67P9pmvdrpAXaf@n)
zop@NVqVn^ztJl1|y+L_TeSS^QWOe^*;_)>L=h;?k+1SK@r!9H%9~JG~QvE#-viSAH
z%Mwsir)c-xtSc)fR(*S;*?u_DN|=FReu^=+VL<Mr<m9i9<^M;3rbtS@ya>E(8JBu%
zOXjcF@&8wWj#>Ht@9(c~wVic!by9XUJFcybPTwGK4>XEi_3P#GY@YevL8qtbemx!k
zFDQTi-)$-@Lsy4Yy;`|^OZs^^|MWxNF?%WkrOk3KoYvpJ26SPGfk8lLXJ^&RrPD(K
z0v6ocTm2eT4Q|W5z07;Mo?#6i!vWch1Z=G`@jd_l{RRzJzpwjl4O$ohYJVT=kz6dO
z>~^Q1VVm8_bLYaUs&*L}8I`=dvs3Ez_xttxudRtpUchs2&6X`8PoF;Bx^DXP>8rPF
z+48E?!=qze{Qh^HCKU_CbfY{b-O1a23$oBdLs8L@lamuP+^uukD29W<;qF1qDKQ3y
z?Fy=@t{|VS3|<bZJ5IhW(^gh?R#a51db9EPmb9}{vAfI8mMjwlZEWb5v&{lsYuR|}
z)G3<?mUz%<P`VKt9N76}R&2yN0_oEt?&<G;9klB6@$r7ps0hgK#^-Go=iS`}4k!K|
z%-LTChCF9bblfRE|8nQ^d6y?DyMrdu)~wM1jdyeL@LbuDczDXJS)f+l<&|>67#)%y
zO|0Bv8K7aXdwX{a2@9{@=guc@x2CCy>2C3P+p5=Vx2x3FO8<IxcD8BBi-5@|4L~Vj
znJ@#x3Ula+2b3!9LG`E4pFv9(Ku05NzpZ<E)0VuuR$pIV_rG}YqWPYiJM}=zndSd|
zV1IjS>*`l~^Yc{Vw&lzObtw#!kIgvM4BCltX<zN{DbuDc6IS=j`1$E+)V`XXese4q
zZrNf2s_?qHx+bZZW?picU;Axl8fZ31>fVbpGmSUhehX^2ycA(zc*S!1ZP{*LcNC|A
zIX}8UJ7LbwG6e<hw%pq(n{Q5;GiS|}D<QU@PAG4>nFAVU0JU<q<=)PEes1ov$?tb{
zb#Z|fWPwgK107t?)_#7z{d!OwJ#3f1)-GSC0h$gMb&xH2c1H4U_4~cI_Ec`3G-;C0
za|VV7pRxDjSzljU8yprk&F;?!=c&`DYg<`GeSUua`iY6kpu#EZJfE}~Xx{b0=JR&h
zE3R#Zb`n4>chLA$WaLcHLg9`Mj?}cYtUEgjH{HxxW(=Afyu*a8(#bnGLDBijzS?R~
zdlNL644xu+e{pfUTd&m9g;t++PG8zl_!zXk<g(_6AUyRV0|Ud4wx?yg?=DjY2PX=#
z=kB$&(O37^*I$;5O9tIq<Kq*Ole1=)X?B_wyB+9cYO~qC?tL<Whue5XrKGe@Z_4{6
zd3saHqa&RBqKCq#PM@Cr_0?6-mKx~#4~F^B^;0O;Fyzg~K32p~dgI(&Yf)k0WXM_x
zY~zs9GYpfD<<=kDq?4MKcCS_Hees(chL$pXq9P)og7iQmGk9UN_uJds*PBhaw>3Nb
z@=k_V0<+I9`|zQlSJD`?4KC<-pRBJsBSXM)tV1Bo&|!U07vQ~9?|0Dpzd3%(AqxpX
zr6g!fY+9<O27H*tC;bpNsPF&t=TEEZZ)+}Hz6_dRS{=R~G*k;3WOHz6c<E9x^Ua%_
z)Ku`G*3_v}kxD~QwXy6o1H*?(tmB33&r!x<zE)Ytn?Ebs30fEN^vRPGZ_7?^(s}yy
zsivl;C#b&6$XEf&0Gh$eX85&E*FwzBL#Lxb5#-h{x7J<0Hl$a|)MzdTLxcaWzl%Y8
ztxzM1;nmEpE-p~b`TN^j<GGKnc6D`q0Zo;jRG%M`lCq?YPj=Pa-Q}y(&(Ev+_w%{$
z^Mj{-W}Ere|9u?~x`XTO{r&Ox_oZJxf8PIaJOA}vrLTF!4&C0Gb2I3??e{rz{FZlh
zcYi&ly?(`t6(0Te|90Hkmb-e(786l1v03L>7!Ewg7CRqgK|P*_hucrTEScr^QR@1-
z*vXe)Ub(Zg`0MBS|6|rhZM_6qj0KvBi?8|E`fSc=69xw12c9mDA;<dV*Xu@advR&0
z_pQCv+n=4EpKm1@r)F&({qp6@QzuRYyuP+Jd(Hj&|9?Td)f$a{D1jC#{r<h$bFvyF
zQGqi3{<^;+va)NL+4*Mpf#&K=u+G)J)j1vX{M_8osHiNfquDHMY@m%!N=i<Jg@v<>
z)B7GhdUR!}xA^7E4_GT3&{d0TBR9K6Mn>M+mODGgZ1$wdlR-0BXl2~T$H%k5WgH{J
z2Tp8B=MLyFFO-pYiSWQc#oc$~N?#W^I5f;M%gwUlwo@@N32En(T~&JbWr>!J&7Ee~
z527Hy5-8yQ$5)q&N0-+ADEw1=PO~-1NZKk@YewFsQbDyN>~5Kz9!XaW)m2XIdUUSD
zJo<u;aQ-yQyG=9MlBPY>GcfexnRbSyq%`M9PwoUejV_hXO)~_;%Z%F{<&w^5Y@PG}
z=r?oc=Tj_yzizy)Z7Kfz`g_lN;<^u?74LKJlQ}6{ekU+Mm*I*$GjhARq5navc$|l~
zxA(I%GbbPI7GJ(~tEsQA@A5gCQ@tYh*VQ_<J_c?3IdkDc02@2Iv4zD9cllZqWo6}^
zFBWxQx_NVEE4TQv&6|xsKRfHaGe*y9I_HYz%hf@P)Qdi!HGe+IThH@T|Nez4H+K{!
z&#QX1(&obfW>+;MN8R{+Hpc1a&cv4Aotm}v*TQ%%qw;rm*2L^An)8Zb!M~|lTcg&#
z;6Tb-4V~{6_pI<<8g%T~v11F<9!bi|o;|I<zvh(2-(K^3CoG@Onf&wf^W~d28)siz
zqiHpnGbJTO#e2Hm*>$nIKONPtGX!m6G0wlYN5-zk0<;FP=x*ut)Z5!~SB7Z0E;l;(
z=FU#zZgG7*D`tjs5o{<^1vN_ZYQNoF6T92&y#4<_k+$caH($-#YV+}k@XbxB-rwHe
zpFdgM|JfvOy^~#{+C{f>x7RMwuVY|%P=6X_(4?V1x1_{GfA5zdHa0dR3yT>G7cK-j
zW^0sgZ*T9;M_t-R78VgDY60!n)<hQHny)$4Yv=cS)%J~23>KdyQC9I3-0G9Foptcw
z!E*NJ)!*KnJaNJ!Yirc3*|RTSyf|^)x^*R`rK$h^{G4f1S#<HF4}<-mhy0r}E-or5
zDR~k+|5wOG%PXBlJ8QsJNJ>lpX31iBa3&pPPXB{o?)`nX_J3dcZ!Uj-PsX}T=YQU`
z!fiZq+EcwIEeTtl`s~ci_kCw~@7iUQes0bbucb}gGdoT_E%I6#bn0nQ+WC34r{16K
zku>f)$IPIB8l3VcudR*VoOHD7%sgA`ZZX|cZM@Q#E?=G;wRYORefzd--I{uHQ|ix)
z{dFNFuXaRi%?cIMjheD<-MTY#EH}T9d3EH&hXOWs_RIJ0&tJH3;hWpr^|wapE)9Bl
zziuMqp6e%0c+9JQw{y$3ZO=BH*3-6PXE^79X8pmb;c+uPC#$6<Bq)G##?R;T=gV4`
zrJS6kYFY5WK};uNLh0*kOQY6`&E+b6{NmzbNhzsQ2M#!}v9oVZKR@r!-}m+YD?_}B
zi;KndVrGD5zg^Rf8n0w+^_gj;`uh6%^X2<K&s|i^@SrC|52ca6Kn~>EyLa!d4AIKW
z$ncod)7Piw85JG9IqT}GHL<(5ojAhz_`$*El_6R`|Guw}FX0l7DK0MF_vfkp^G0^L
z6YFAk7kzng(dP3R<H!vOj(swglR&!zT-A*ZPVrj0W$V_b7Zy6ZE@wC(xq2Z=0&b`>
zD1CLs#LP_X=kbiPPft!({{4FW{@<TpUS2k~v55(}*Al$?YM0*vzdgTRt(KILIrHE_
z0vj9Kr(4<Umj<nT(xtu5BRxI+Vx^CR{f~qEo2tIPx>IyoH#0w99~8b8XyNNvU0wa{
z?d|XHeph~emU?-a@6NB+qCcOrexLIB+1Z^x9(8l;v~<2d(kXm%bGknwEA09CZ1zmE
z+$bw6tD@g;x2Hcm)H>6?zHZj6SzYH+o2nkRieI{PX_95}vy_jIj%McO*4}^by)xv~
zudlDUwOAT{g{}H&rHNc#@PEDF%>VRZyZpI-e}5ZSetME~dz-HL-ICy0vt|WpP5t!k
zcK-8^$K}uGZoeB=lJ$^J&SnO;-VO!pvNtCtsd{&vOJvH-$~yJpMaHe$w>K9&JXBIr
zlJf9S>(4{t`vOX&N|(gw)xVe-v~tSEjT;MBFg6(XGa^U!f%=vE_uKp1|1Hs)>NQO-
zc2@Sfoy%S<;e7bx<KxO#E0-7j{dzt9*O!;B&kY)<oPHXjHTBF~YxB8t=SJ=*NVKxH
zHcmd)v*<Dd!w+@T@|yp{qi+4QYilBBn&sYVpC>CP=T~1}zv}8Miz&W3yUX97o4)VM
z(nZEAm_aEUQD{$(tI~uP+J2Ht&d)Y~uY9+Nm*K$wd8n>tUlF2pb4zA$RaMm_m3Dsl
zb3KyAn`(c5i>dv3b@`mPZ{PZEjXHbdMugzXR;}r$XPRb*?fcl9pYrt7)Sq{r+l7}1
zl_r78xcz@VX)gX^ey>9L`J7_EXXoe7KX>ljn#j$|UidIHZ0=gmh&&tpgW>(&@9V=>
zKmGCXar)B}f9xwiom9Vk?b@{8@Aup1=H|Y9^X80lzs;n>?fl|%kFl6%URt6Pu|Z*V
z`1*6#)<%EczW=Z8{y$Iki*Ke*e+t?MQ}=1|e37{)Shj-PUHx`zW@e_Rv$M0-)KkCX
z7!K4QM=O+<E?=$=+By08`u=~WudlE7UmJFMRp{!XhppmiH#dRGB5%Jr7J(&d!WUk=
z$Y^V8+mv^A*PW8fzLxLzeBM;^^OMd0Kc6#ma?Uida(DTqFx}c!n!WGS)b&pu9Bh91
z?%lbQlhr?eU0-i|_wHR#f=ZnpJMH(o-RocYFsz8?bp>rdg{Rtrv>#uV+t0OrzsI=z
zUS)b*_1mpE_x4!s-Mjbat?T=y6`!{?H@{y~yy|M!u3fvj{FW-X_sgAy<W*38Vq5(U
zROxMv(mi|j?8_G~Ji^1nckS9`RR8af&pex*FH+PNu*=sNe13lZ{DA`wpyGp9+U!a6
z{a<0zbRs7)v-71KY-0WSCfz=|M2+E!E=s~<`1gF)tXW2-udaYfIdF-qSzB9M`DWws
zqMuKvKkrnZcVg-ExTq4f$7_}@RrL&7ebuP=*%_VqeShvA{5i+6I7n+Mm);U^3CM5v
zBSCAbmz2~$!->+evc8kHY}=N0byaBO?y}rfSF<M0WC+;KgR-pTUo*&c@9*vPoRoaL
zPt_At=RSM(EchHRKYxGqZI{p2qVrQvPt$$*_ARKs57L`ne3;k#$-dw3PWPJMn^ClL
zPWrq`wetJ5<$3%6etUCo@9q~V$8K)l|M#s<)E14{*w~qt#c3BUudG}dynNZljfS3=
z?%bJka<cmKuh--2zdygc-2Z#N5kn2n(x|mz+E&PkH$h2j`sw$(C;t4O|G94c|9U$!
zGqbo#VYm4B_^Rsa&AGR?$=KJ~gvXYKf?{p=?)!T`{))H#^<weP$9>jCkB)RQWi?h^
zzj<@!Y5n~+pdIUzRb*vlXIhnJfvT}RpU+wEe7Ea$(T4{IL1i=RbS8(|B4(6=hW*Bl
z!sLsbrHMa3Jq3B=-LBW`LRMehvVHsi<DZM4pF4YMs`l}feN}}Y9vqCRc-Z>$ZGQc1
zRqtsca}Tp@10~--9}ZW(SlDh<`RU1>;`6pUUoM*s@_x|DDckSYS@+xjtGEb?kvk~u
zg9FDm6+b_x6Srr_3!YbZ4mPtFA7m9zIo>DB_F~SqfB*j3{QYuyWr$Yfu9D1kJD<&3
zG?`&R9%>tgq1D*oxqaowqvD_zo6l^sx6bGJ`1zOb-*104t5oI`!-F%I1CZOQ3=CgW
z&(1Pk{ufm0R=?l-U3dlKIW}2YS=<Gdtd!KLx7+XMHSjU~S4B<Fey98E|2)3@uZPh}
z{@I=4^JkCsN*h;yd$TBbMnl%tTfgtg+t=A7CnvLtG9H+@ItI-lPoJEey!@|`(9^wT
z@9))~`mGtf?8)r=f6|uu&yNcbWMJq-DOMTe4};nzwcl>;`E*L#b$LL#m6g?}pXclC
zzTdB}|M%y)z4%;ah6DDf0rVk0J16Ii?)E#A7A{=4D0qdjzunK2Teof%{r~%Y`P#L*
zbLY;jd@|9!=*NeLpqk=b7FuZ%u-|KG5J>%t3t;WGwze-{zC5|mx&2dj{2!&+=K1GV
zg|7az_kFGY_4xYQyuDwq)qGtY@0*;Qd~v0Z06U+|iF<piC#xLqll7kT=Kg;BvuDpP
zpCc_NC->cq!D8|hj3zq6tLx9s&fZ-0_0^kOTeaW5ee3!>;5bqtc5{Dy{W;t3cka}D
zKD#n(^~+bUw5<A>rk;K}#cOHsysKGTzuW%4{yaH3`SDbChIA3sh3g+S?)h+tJ2Nx$
z<Q&W5O%)#>ZP~VM*~*nKrx-5{(tLe=z5a>`RTr;ZnX)o?dD^Kdn(zBMe*gOQ=|*z@
z(@&@M&kOt8O!U^@yXA!s*M`E!#})}QJXrG(b$5{6w4$AV7N*~EJHuZ2dhPa2si&uX
z`SvaC`np)n>8E!-Y?BUJ8&>?d*L+!w-t(F1^G@C^zd!eU%`@Yhd#lSYo@8K1H$hEc
z33tAJ{knAfcJtfYa!-GJe7yK-X!z2owaa$zw$|0veQ*8$#p3>Feb(<zbPB6;tzc!a
zs5TKn9lV}XJ54`+-b~~4XX|#q^V%BaTV4IT-o_r$PhvP1m*;>|gB-hiZm#v_ijR*L
z88a|c^cP(OjgZ0Xmn-|<-roNFR`z;dZ*OlYDXE~9A@{yF)u-0*F&G${qT23IdwW-D
zcG#MTi8nW=FW<e}TG}kf!{6UOYirc6U%xJ0yEZNL^fb}Ao(C~HD-3oXE5lY_?Skxg
zgId0zF1GUN)R`ukpw3UxlM@r?)c^Z=b7QhQQq>c=Jui0E)vSvvMOMV<&Ht9}1@7$G
zHA*os*qwO!e?2eMEHL%&=)T(Dm+s!3>$P-JTU(pT$rmp&CN0^z)pT{(+Ecf-W_SCf
zFj-W7dXl-n=R70BvH55j^7NIJ!Iy8`n4yxHmv`>T$;qF8y<Wfn_ve?Fm#0@$>{wx=
zwqWAKi8jCAY_5DdHN4A@k>P<Y4@#BvBLdVe%)h^{{Qmjb=K8bEa!*;m-!u8~@&0sp
zGdE=ss9gZh!3+!){HSTfZran+)0eMbudl4E>^Z6W-A;Au@^?PP#l`2W-|zYI{rmIZ
z_y5-&oa&>pG)OZyH`lV{MZiT(28KQEm;wCY%%%JH=P#dMXEoJJ71ZxFy&e->A|!kU
zJxek$eDFtYvCr8i9$#a)IqmGJEt!|?zP$PHq2Sl=-@$9cjxX$~`gr$!ojGXU<kNEd
zznb0R`hMBj*|TQN^0N%qn!2g(@2@5<Muu~K=q7qCo#Z>)4Ai#r1Qk$cW*92p-kyK{
zYIuC@shjui-3wWLwWqgNbmA$NP`&B)Uwl@Ee5z(<FgPdGg|Y^0!M{D<{f<Pfo%Z;6
zzclyfiF0i#H@#qCVEEU||9_SOI3Xa2b6lvdU|?WSF+|NDT$`{p3K@FVw=II4763JE
zg+JcnPi^1Y=<R7oyF_Q&R+sJCy?b-w;kGYdzAOn_y>$J0{oLH#$Za{17iTgsq|Xgn
z8@5^$Wn+~?t>*O8np3@&+pNBt^}hPs`t!$+9XqDoZ&mPgYIxeEC7zNJ5+^1qyBGcY
z`8@r2pKRo&6i+@GiwUgUVkvibm97k1?Yf+aVNNJog`9aC+zz<1v-bD5rw7^PeU=7!
zIv=)A^IN=lvFD^~*RHLJ+Nza(eVwTTJA*{}e|AmhdwDr4ru+i=*wfX|Wt~$(699P3
B!esye
literal 0
HcmV?d00001
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-hamming_loss-20160908-100022.png b/Code/MonoMutliViewClassifiers/Results/Fake-hamming_loss-20160908-100022.png
new file mode 100644
index 0000000000000000000000000000000000000000..249481bd7ea44e8ce5f98b7f5cfeb41cc7404d1e
GIT binary patch
literal 164153
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@vh+~Yq(zW<l6pJ&`W({OgJ#Oa>Y6W>hB(x#}M
zZuOBAooK3+y84T1JWo`I)2l8smnkaV>oV2^o|IBm;z`UoE0HqO@bkaFfuDc={83}K
zIbznUsyq4HUzf$+d;i_?d1>79J@=pQc=gqi;R8Dt`VbE+)Fx>-u*2A>^q)qi5>ycw
zuR#T;arFxr(8il!niM*58FxS)ryD#L;WBR2OOSvam{>Z|7`Zv^<hI<s|Ns52l<g9}
zz3u9r%FlcF9_u&PC}{i6Hk+FJx!+^GdDWMUpTB;+y0J02Z`<K^{?prXzrMR`&9D6X
zb8Bns%9@{_w%6>pt^PJ8_qJ8hlM}l4zsFzw`1ttK=g*f1E_Qobs!^}``uh6mxwoaP
z%hm+{?p@<wf6VxN@ScLwe}5`@Wh??7K74p;y8iq<d-iO}zP@e`pSJ(eqeo9}%dP$S
zbb9@(!u0d={!XvSpKf#h>+10JSzlgU?CR*4(BIz=(opj9(*Ik}4I#nEz;L4a&uvi{
zN5Okr?&;H~wND!+CMN#>amecQrj*FAxc0`JKced|&oE3*xxFpt_O&lBFW>DusWW9!
zz~^tjwC~ARzI}0V@hp?fNpjV13|rgUo|RfuzAL+{Tz_ou^w@>Z=f|?duL{w${dOa{
z>g(0;xpj9K-bGHEs%}4F;^ary{x945IqliW3k#jU{(8NBb=uikRqu8_H>vuP(c02-
zr%mI(-KS6Yey+Z^dET>MOFSo=<lV7oZEMSVabcm9ZPk`lAuAu<c(%UE4(5di^G{o^
zXNK_@>g)gWx(do#mxU~L>kZkIa&iwJYvhg1>HUBH{P|?Xvt8%(r5T3FUp^e>U!8EU
zDerfq{p}kYlc&y_wQ8Yr`?FGwdd}=?Yfiov$crdD|7cG|7{9Dl$mM0emv<CCw)w}v
zUT2<uP9}Cwh2i?c1s4}MGQYjK+1<5U?Ck4+e<J3_{?qj1*PWWGoqckW>UImQKa(qF
zy*@o%Kit8gA#82b(=U(X!`H`Moo8DuA|mo7y^Ry*>I344Vyj3=LBT;#P>_p*<HYNL
z39TI+98>jTt=1ndSe<mV%c}I%lw<w!@3-BT_^j^U^1tl)xw)73RDLe`ez$ye$jYEf
z*>mwu6%{)U9X|Zosz-X#U8zap**+&Hsb1Zb>V0;$x&QO?^Z#G&|6d-ot0dFa#pTb-
z<7eOP`|$B&po>cjm$=>^b=N7|^U~(Y*w@XG*K*osbN1`w<Nd2WCMx+IeLm^Q+qY{$
z?$HQ*be>BP=6VMqR`@Xb1GA_-6&vO1ek6vji;4XA@875I-^1_jDmBf$WwM>s4w?sQ
zer$-V|63ZmI?Q+9zI|N${MWtp_db#M{_(i{YR6_ake*H<Rg;7R46*xaZl>06%Uxah
z`5DOXRo~yOoiIV*=kMRzT3TMx=6O?8V)s-8I=AzMMnuf0si_IsTUDwXv*SW){O0uY
z({gWD{r~%Y?ybXz4u$NisXShHYO1!nyu5tqst`~8{eLzczvDC4>S|%#Qt#>48W@>N
z-rcc0{x9#^&f@1LH9rbMR|dK6+qX|EX2*tGTQV14T^+t#*1q~%j;pKd%8HMVK7IWf
zdUI3i)n&fYx)B==WZwCHzka=5>@E!(n;1JgJFU1qJ6>H`xmeM;O~cmK_V$iz>*Mur
zZ!;}>6S4j8yL0xsy1wi8ewzhSa;TLXlo~++vG@DE*F|<Sum6cEEG*oV8y#QwbE%kK
z%nCMMsTBzao3w(KbnGg5x#;on{@uN)r>E&=U0pSmiJ4hcL}bY{-RP{#%Y6NQpVmCR
z2^4r!bs~c%tNVYe@G1A3W3f<uUWL=chYz&^7BqB;>#w_UBO>?yzPqV!wtjzkYist^
zHIc^df8O5Se*NCw>br7}FD>=1dbxDEh@_-ueSJME3(Jba$H#tsILu!xvs`6u^mf0$
zzrF@<&AKWgBBEk%Z+~?~pmXx^zN=HU!()!c?<jD5e5^OPSISgGL}bZ<0}i2UA_C`H
zmtX6XwJxf;^W;fNuY{qKY1Wm1gH5cWGBRtTwq|Ai`0#L7$;+T=x0fwl`ts}b`0(9j
zZ)ILPOjL5cvMJSjZN$byZ_O;{vhTFrpTGZa*j%g9pp%nSLl-zOPSuSL>$m+jLr7RS
z_L!Vii3iAOOTDH(dH#I4l55urP!aRz<MF9;=FC~V2b2k>>&0GT=C_%!_~Xo?D*w8V
zN5wbgMk~Abm1M<l&zqZbd)oBr)B9wtpI!O>pqc;Fwp>*e6^pI^zg+fzb#wFbQ`2-;
zGqG}MsHnKa?k>B!ul9G$qti9hR8&+lZf(i@HUIxl`JX?3?p(wB?#>&jDRX;zc=rB!
zwR+d%KI<p1U#~VwJ@sPc@_C;k=G4BqVQBmF$>dc53!6X*cS}a#(IZDPUSC`5_xRA^
z!?LeIk(qjXoAU8VGOwEq-4YWM`~JN?Z)#~7dAOZF{OYPuQ2p`XLBieI?{~ZU`^!7u
z-ujw$v`aMW+M1b7&CRi0>el7&)^LmKJ*l$2xvzG2QgU+WA{Wk|KYnQF==k{Cd~ETX
zWAV_)?DH&n%OV%!v@-!`XPG{I{d)C;2?DmiUM#jMe;3o&_w&c&{?prXb)&bP$^HNA
z?CjLr+b++!xxapY8?W@Ts;{p=IiW8?zV=Jt^xxLnGq1m`%FN7^GS8c%6}Co0US58x
zetev=dtXRa)~efoRn*k7-rU&O)z??HMs?xBg|BXHUH$FN&BrEXXJ!~`#qZmrbNbSn
z$jvg}k8XW$9cjD0{@>5^()agbmwHbxlUeTGFZb)`^ZBvI?!DN2WA2@EC+Dn_x16hf
zJ^R|4nU8O!uFJo^zh5HRr1n?I)%Ef5jEsz+g5>Y7uco!XO18g0GV}I)o64Ymn@=5H
z)Ae-o^Yf>F5AY9L7qfC(?(J0(8<ReL{1|w&OZ4lT&F8gLRgb3T<juc(>3#OiFE1~P
z%F3>N@F3ym&z~!UmU_Lqy?s5OjKzbp*|Yb)n`!s!h4R*ni%zaxB87i!A1-W{yR<F$
z_NKev%JwbSiQN^V8?_~1Wzf<mj~_3-a3R1n_f|;$zMso3?|A*ZYJJ>Zne%H}T3Dw4
ze)r+w;Z3>Gd#k^fb?TeH&%b`|sc!VP6|uX^`kKBgyZ5EcwuY6rAMPJVuJQiI9B${I
zK7IOhDYKjv7cK-WU9u$O>?~6$lZ*-5^6sv>xjEgsce{@FwA7a`m(RcU>+9>%^S0kt
zl)k<ewX0;MTaU!TD_259wL&}&xAR}G{eE}3_4_@+A3uJqdfaP1W#Ytz=JzTNtF~=U
zKd+^w<<;2OSoLCI`;;kDmi+wue6{avvtPenufMuJ-hQrab=dbi#r>BqT{5ZvS5x}#
zPGo%j->t8%uYWIe|EtdFps1)>QQPy@9y#K&HTQPdy?ggS6$K~_X@{@dArk-X{r&jM
z%l*SMGFHgdehGYfetx|7biJ$3&dx6V`YQD4`T75seVR9E(xPL%(%J9t?OheVex6m?
zn-#|C=Q0j9v4Tp$W&ZQm?W_H5b<F<zonk5bx;>|+>#t{*uL*E;boBD^xiU>RdP~7W
zC-;SSLFF_XuhfZcxuq{II6i#%(5n31oVtHM)A#;-HoNL!tN4@W&&z{1?mk`EFK7GZ
zVY~b)w_d4N7Z<nJ)Yg{%`B9jAXGfrR__~m8G2Kmfm#0R8f@(|7O(T$LzO&7)Zogl*
zy5H`X$L_MXm&)(gF0c9d$#UDzPp9>-?kderO-a!(GYflqdir&cJJQb1T3Pw|S>EF_
zee>tfpI85{^6R_1(aLT;7tYKy-h5Y0QPD9lFwm;-QOhjz{B`YeRUZ5QeCoFQ_aj+1
zeqT(tm~PPRZMm`M%5QE;joOsbd23tl>f`eDG4}s{ECw}3)<$oCbzHu_<kzHJFR!jy
zrrFEpT9>aXdwc8E<>mcGMn+qTo_g7Sx#0Zk<8gW0e+dV^s`<=VFu(4XXRow**za#|
zOMiY!t^Im6ysNwW@~^M2w`N_{T7GA1-rcDCHJ^K>%=6altNnfI_U&l*ez~i+wq}<;
zpIfeFWMt%SnRRQ+%DSIV#jmamcK`ePd$^lh+qbv3mum(ud-3tOeE7{xskV9Zr%YLL
zu$f(3OUr9*)Yj>iw`alD0t9VLIyz;>j1{S;r>)Gry{+o`-10eH`-+VDi;C;s@BKax
zlth01__4ydolh%xS<kok_t%%-uMIyvP4_Y=@GmX(_Wre(VNc%OUAqb%Hh}`gZ?4tL
zPft%<mAshn?A+YdjLd8+0v0;me3o~0Rp_K8FJ8RJIUYCr{hWJ~eP@{j{`>QDYt`4R
zUTO1l8~d}lUBcJLt$lZQxAnh0d3UWq1sbR<-X^LY28u~glg{@0oyA?E+OJ+*TpYC}
zV<ITzOJ84G8MZd6@8itkx(5duZ|x{td~0j=^0K$Lc8a*|F1Eh5Ae&dtCPLaQ=K?do
z&4LFH64u7-3<_T6bMaWO^wz@1Zp**c|NizCl(Nswvt4~{ZM3$TSy=kHITs%t?FN-c
zN4v#A8F11PMd!ARkB^Q<?XTNg_3h2e6Y<Y}9yxmS<z;{StLtKSn`B&2U}b0bp7eOX
z>dO-om3O^fx4Y!Y2|?4$OD_L^UElxZcK-gCo6p+?&o;~baxFT4rT=_8y`R5+Jnr9`
zbd>9ORdKCia!AM&6-_(4doOQJo_gNyx6fRw(n%_%udaALJvH_6w%prap3TnBdU<In
z$djk0YCjigPmPqaDp|4b$0P3JzYpKqn*H_L?flmV8kzfk+iKfZeYwyhY5e8i@At3g
zRlh5IIo~vUn$GDUP-&RkEv9=ZI)Crdw6n7`wY0o`etv%a-QC?^&so2JvH85+<!fuB
zi@$`vIa9pj-rw){*Dv*+zAEWxmy|(5Lr`$AY4J0k+W&vQ=Y9YDbb9=&r_<xZHm9Av
zvNBlx=kMRy|Ns5{^<=XDmXeo2wST`}Ulq8xZOMJ^<-tKgCaI@HuC5C8{(i4|eX{-a
zbDHJba&9i#{eEBc{=eU5Ta~<6uqt$Q*86*VXIYo8o2C=F=<4e5)qZoW^qx<joxV|h
z=gi4FBkhZf{O`QHx_UY&kL}oD0qXaqpPx7B$(Fv-*VlYMKR*vj^H;a$$45?E>Tmxy
z<nQnA*Tds$ms%D-+wsO+Q`3`I+APGup&=<bIrVl~-@Yc>v@;UDlE!YXT_S<Mzr79J
zQ&IT#)>iMyYQC4A&#zyXzwf8pzkmPwKJKh7TfTJZ%GljyQCqX7f?6l*Vs~p97zA)~
za)Qd(Stgl_xJ0!qj+SVz+x_Ktzwe&^|9)$Qt(gI853GqWJYKxjYpRyt_c_+vU)w%i
zyZzp!<bK;_lT^J|fpS;WmKA<;t(L~_F3Y^OCbH_!$K$fU_tdSsUw*$9)LeaXa&l_q
zv^E||rDUIN-|zPB+Ybucs*gv-uP*Tv{`&H=d-}OKJ74avhE-k-^&0Tb+630qn|g9@
ztLf>Tdt2|;FPGcY+}xXc``L$why8BL*;HJ3Yghf{MPklvv)ShPWm)fUZeG4o=X6VZ
z`|Kk}T-<-(+??)vagnR<!6sJUkB^R?^|$}~<b}7duW9J&FjG4_yJufsUd~H?e}Dh}
z;NNpBi+fTdmlZrbq^72JEM{lX(Tm#?53?mlPJ4M{<KoL^o72u3ZOfevsw}s*x3)^&
z-sb!J+uO5GPfwS9yWDTC(ZPcUmjx_zdiLt-YQ5k4ANN_G*;)Kt=51zX=CgCw?@Q*?
z`$bMmon@N+?8>$E@%G7)(<=XbJU;gpsQn@=B9c;5Q!{5>=tLz~pP5Ffa~_@l@_PM#
ztAF1w``hQ{+%`KsO}ALG{M(zGGDmmk-L*=NoF-|U)^q#ch7AVGKl^)n8g9#-{p;)N
z-LmtiOnLGpz5HiKcenAh)R_wwC~U6&p0|8oyIj?Y8{2Y0wSs%Jn_Jt;h>eRj=H6Zt
zv-48spB_nLneSJBeSN*z{-J$e{_Sm*-|v?Df>cFrUiR_ZH#6(<cO^YDO|z$M)H&TF
zV|gj_cG%h|$=ln`f;wea{+%_yFOi?0AG{?a@bm5b{X5^N$M362dwXlE-)$awyE`|w
z<*ND3d2wZ)rM$ZDtS49Mo}LoDyv$en@zbYIMY6;AWUZcTtG%)!@YuH8%?SsY+;4xs
zU!SjY+Gyj(jd|NozO=o%B2YQ`_O_V@iA~=3*YE%L%4Gj+v)rtl+htP4Pfv*!zqw&J
zJ@@=v>-1IO>+`xqG#{Cm7g>Sof#2WW8vp$K++0vl&@X$w;juN5n~zmgR$8w0yu8fU
zcw6r5%*)GmzWM&>Xm{T8P1cHvifR@XH*({hoSHW3oc{9a>gkoX+rK}VTYfL|)6>(>
zx7;($x^m*m%HZQ7+F@r(-ru`>abNLsKTu3QndmN)d-CK-kbV*UxI1s|?!NwV#_sa>
zX8->ETjn>{%J1#W^OG(u_1<kWeN*w~><Q{K4MnxX&iwgwTHmjB<Hn80w&i~Q^ZC5>
zt#xsGv$R51B-GT_o^9imo^woHO>NeN3jx8aLNq7On)NE<d`z~@T3_4hZzaFioGZB=
zTP~@uufM!9>&$!06``xAef<2{c)8!)qAls`%;VzXo^|W*JMrlcx2RT%*A$J3PiOdu
z>%|zfa*LbYyLa!|>h=4IURD2mI=weFa#`u?YkJSqBByDFubX38^<~9kTU*<^cPgLH
z1w~8h>1i^u`-`5QI(Gc{aTRrS>#gxSi;jxu#oTCVX_@imONsmMkB^VfUFW>)$Bzn7
zynf<)^wRQ0UhS_3&HO#7k!o66r!sZD{rt>CwL%QG<?gom>^I*oS1)GA1EKTlVt4oK
z-@iZe_O`XbyO-~r7rQ5PRR}0W|NQ*idaHiKh65kx6|cQx*KK?9?3_Ipzbdb;oFrQQ
zUg4O8asEA<<j83&qqncyS@Chv;=hlMb}!4jyDRVWjGyZ+Zcg`K{#(~N``Q}AX{j?`
zyvSHydR-zp?fkr4ozq7CwqK_NSLe;Ud+g6YyTr(8JHOwnj(zv{%9W7fXJ;gj&(FVF
zYX0p1{$|sh8yDu-*WX*IudIA{jz!_2kLmvJ-)?_xyVP&46(}@b-Z75-t(V*LduLwH
z>(A<wms`%d{eAnHojJF+RsMdv{q8(r1}HeN_01l=2KX3rJ%94?zS7_G3m+fTR8>9t
z*6iWKhk3Wz`D8Sbd&1Vmyu6eiInAwCYUzXt0`AcP0TV#AjQ4cCmG%Gsb#-(Ue0h3$
zx<9|&j|D-&!CTYM%T53L^XJc(Pp8M1WmUge*bW+q*_?hp>(!N&e(`_1`})EnB4+IS
z{ciUf;i9?M<EnjGxkL*7?2Oo$)YaJ;=;hT__v@v)d-b#H!R|d03mY03+;?x^zCEt$
z<<c10%X7DEF{%A<ke!Qz<3hLoz86=*7do+mMjcnKTnQdN`31@#-%hW-UZ-h2xxc^P
zJ31iXg0I`Vd8v^`$1469CHw9BG$-@I0>@QRTUP}~-``i8+H>*Q+1awWpe_KPjKzXy
zXJ@YtT^*+Pc>Ui0MW;9E_|CBieEIUFlvPQ_wB&wSYf!?PsvCVRHRo^}@71N=;;O2u
znHLwi>fJ7TdCApxwpnS`>+9?1pWdmas`|2--!9<puF|hxF8f>eo}X{OAJk^;>ESs$
z+g#uMdHLJxaqCSpE-3UD-@E%)<>{MwxAxWUHp{)W<irUN+uv_C>-}xz7C-lG^}L^-
zpNFpuS{ieUnThGj?(%$9b@lAi({wGnZpWUnwA^3+|M&e}RbN*v^O^Z*%Qw&c^$T}6
zxAR49%b8jC`>nbAZo^}5_tn<c&b_AOf9cYtl21=g%GCOrU+%p#8Pwyes@ipJeZ0OW
zsQn4*hE3CrUX^)yS=8pV-sCs0uC7jvoObzocl!BxYm1+s)6~=Ro2ngNW|ekzRVb*9
z@b<<==j!k8N?&c(@&5mN|NqsSQcpko@#oIYso4`!Bc*IAHazzJHdD=Sj>hRtU+z`E
zx4Z>vayGN`XB}u@)Qexi&&hdl^Le|~!s>n&wZ8w--rU;i4H`*GN=`2Q|M$D~S5`K*
ztTQtVch&sdWcTxl@bujGd%wqR&ADlG`fqzn%Zo2BFMIj=o;91M>OD=v(lT<cb$Qt1
zW4&{K&8vE)+1lEwX=fMb-Y*As-(vUvu#Aiqi_dP${rc+a>D0HUz53;Br_7qQ3X;QP
zcZHlhdGgh@wX<`6|Np;QOx1f@$?vbvK+UVGt3r!+zk7P+%uM6d$Z2skA6=JM8(3IG
zD7*JfF+7$!dy#ARs)U10dT&7^MW3IY-CFiGYU%Rj_X~V3y+42Q%zBUVcXw{CeE;wF
z`|y&IEub`>duPYR)Z265rOD&4>i2uUr$kOW)-SIgA0O|&d;R+LYCba*l6&q|K9`;T
z_S5t8>pO+jt?uUEtbDumdP?N9dsVM>mw)&1e06W{?yRe;mh#*EIIz;z{QNu6NY2k^
zvp;?Qe0g^MzL!PspP!!Y59;;rUO#*1yGbUww@f0ZEtND*v#327`|Iz%6DL2vDciTa
zqPqI@>C>lE=j<+jIlI*Oeg4+0tCy7fZHi7OGeOG^hW|GADiQNZKdMixiqN#NiE;0f
zDa`cu^15_dfB%~E_Wxtp`Q=Kq=55jOKHeu=ynDY@>8l-EQpGy1t&6?ARDbi0H@}ih
zJVC{W=8;Xg(W+ikE*$L^4_y~yx&8O)Ov9cp)r?)clYSeep7NM9Y4T**+?lO!0|Nu~
z9!s0$Xym`2{rkAN{ogN>_2Txdc<~~Gm7RU}7xVmkG3V|7?<sq8<6*|@TU%Fy$8Fa}
zh4R~cXn42lwVr9#6_3WoM!(y3KOQvCvMODbl#~Q&af1h?y1IgXetMd(^=u6b3(Jdn
z)$cB*&#zq;wKYrA%q$Gl(Q0Pnozt~rQ*z|A+rLlUH9d8vcXxJ5<TNSsyfuG+e}Dch
zL?&u$*3z)GQJ@5;9kwQ5wps3-zSBL6JtwQ>anAyEiFX!1&pO^G3rb(X@qXt^PfyeJ
z^7o&f8YyL*)^ply=Fvs(>h2tz+byo2b!v(xs6h<shkky3-kM8g{ru0NtHVOqMr{R+
zS*WV0XsD^VUA%a4RrL0Cx0C$J&2n$4c<R}UOo#^cr{n5=rsm$*;Mm#O3CcH%-~ZZC
z3~q_ce7-U7uGRMJ^DBdwPnkDwUG490nnp%JvQ{M*iqG3F|M&NIHfUJx?yjwi7A=bD
z`n~DX>-GD+PQ@~Q?Y%Sk>}>P!n3y?X>*LmbdwV<k?ygcVfB*1qG2M`LF_yKTPOATU
zxqN=e&Z1Oz!_v>s&dUBibLMRM{o3c><nC_IpTFe(`-@tkt1P}=T^+7}{Q0w!YonTt
z?p8jZtCtHJ>J47jBP1jQ8rEiIV|z6_f8RtERTY&Tw(tM`{(f3wv2FFYiWui2<<AwG
znwok2<*%-29{;#*`ed7Qv4nY+#mC<A+r?!6{`Pj0j`!JFro}HmfBJN3Zuz~Hmc`F9
zj`zvx9sOe&`+L)+z18KtGL}J`)6ZXf+;9IbW4>+mHl5Q!{c^T3+h$squS+{WZ|z*`
zaxF{Cn=j{Ts@rosJlQ8}opO8I?dKQ2+8Y(EeR_I&_OCB5Z*9w+eQu8B;??2nt$yj8
zzBJP~z3A&>;p?~e)$Uf=x!3K|`{Ey~*YCU3Cu=>Y&Oy=qe3E~Wv3h>m-yKtp)<2Fd
zzx(u3`SsZHlc!Igez{jCI3i+3mzeIX)ycWHws`*h^z?EQEBBpm%a<*C1uEYB{L0q+
z-&tAq{_gH@O-;?L8ygm$=3iD(q`mI<(Qfgr)!*}4TUtOv$Cg&>mjAue_kGH`*xj#Y
zrq2rmmC-wk)9;pEkL~K}I`#GI>6No9>sQC`|CiedpVImBIRLT$Ag_DM6p^cIqr=<z
z<-`8|`g(P-JHM!2%#DvvKY|8CPEFO$+g|!z^x>I9Z`S;}bm>yjmi1?HH@(`uEkfJ+
z9oOFVy{~UMZ8@|4=x*&ln{scz4OcE!F8&WHM{m!+S@-Qtr2FkDn!zCpomkJ#u?!Yg
z^SSWj<Kw4q->%)3d;8VY@VLNME>V@gaVa|rAG_`SaEKe!4K^u%7bBSrN>{ydwzr;Y
zuh@R7iIv+V@em7WfV{A<uutE<{M8lD$!fkqA0Hhp-XdRq{p4lSQ?I;dnFnu~p84oV
zXW#m=?Rj@^y`3SwbK0f%tRe5tnQl(_ajW>Oj?=wOsol5N*QCFDe@njq!;@E6SAzzn
zLA`1z)2tQ6&(DGSpNl=T_4LkVp1Zwm?bht;pmE`-9R&;9c%{{ndzhG*t}J%v-}~i~
zci#R-)oVAWpFg!pXSu%I^J~j|XUoLD%)7X#H7O}cL_$L2_O`Eg%kO8NoTTbk_`F2!
z$+JI3>klvSoNRL}Gjf_<%nk)lt>|rQK$h>=VX-!1qtpDlUn_eIK?6tgDxXR6N*E~I
z{(Mg7%ARdE?5xd;{LON11h8_8m55AVAGbFO)JiBR*#eq4O6~#W(k@Z$tix@*ptjEC
zIsd+1kGHLp{Sh^D=gu&{ZspCztFI}X{QOH$NNAC=d!L4?s%v9oV_$XB!$Yld-%H=x
z7H&4`7nhe`|KmqR|MBAOVoy}gPuGi`v_wYq?fn<G)SuSOJ@1u~u_9_q#=_9mVU~3=
z55K&;9JRA(sgkmC=-#T*<sY5fcrIR9863JQM00EAWw(V37xsOgV_CfHw)~5eE2m5m
z0VS-r{B{+meqUJ`Y?^XHKvXX#LN|I_$jwcuPoF<mKfUS8%jNU4uCI%gyT89kczSAN
zWSnyHncUrOmUAbYZ?3!JHS_w#yZt<sm6a<qE-tdF{k6sWe(##Z{r`TgzI6FAX#T1{
z+30$oQ!CfgUpMDg`WFAbv-jrfy2Z!$UVB^PFKLw0(Iu+A4Agv@WtKZ@ncrNkm*3?j
zW>^$1y3O=wcA@e6{Ozx9a=@y-e?O5{MQlHMJAeP%A4RWEOjMrx3)E=S3|{smFr`xa
z^Xf<H{_{d2B4z}~yScU1{rws~U4Pdzx3s{&ox<vOzNxFJS@lk?(+`leC|JP8Cj%ZC
zetfJKG-I_j;ULrBACLQQ?XBLv*kZY3GaG2=`_iRLTXJukffB^!Wxm1J*TshJsVH2o
zFTOkZ_BNGDoe%ca-`1QKpUEwvu^@1<TjrG&fmUU2X6*a(2~-$*7e7CD_2J?6t#yBY
z$)u<~XJTef?YVezvijX`)mi6zLCM^`Uv8FZ_OyG|?`^lcW||l27Hb#ZR&;JliTpE1
z*n67J#c8_Hpmyi<r2WF`ej1=rkdN_|Peu2BI;Cw@@nONW_3`T^jniI$roz0uy3)?i
zoBPzTxw$#Dr|?%&W}fZ;Kc7MM(6zPE%hh~mS$yr4w~zClrc-!RZTV+~<<F;A%AT8R
zJw5kg?K04m^uIqpPn|e%;oMwn&>*hwY%||xcK&Jm_wTRz`fBRaZ;p<Rr{>%5U)-Uq
zp7&(lmv7&~N=mkX#_#6ZR0d^VTNAk0trs+f;WbrjWy#A+prIxuWo6L%gz2U#8X6wc
zQZuiwi(Lg8@l2jt7k@jiHF_r-Nbgjw(4x%qXEM{?8J(|wd1-0Z^>uf3E&JD`$d$jk
zva;&aN%i7Ab5kQNPkmm$|DP6UR_3ei>WIAOx2DgPv#rvwvx@`OE8Y70R_rW({t7hy
z5^rx``)kWG-`UG%nP$Iwy?+0+`Sa%o|KC&jIZvx^!2$(URaH$}+q+9S?#9-E5^UNT
z3D8Wab=jMOpM@>!_y7B~?9om$y=0$h*H3I(bGxj!$O=-4Y}(cL^5sjb;%7aN|9*%v
z-_({GH`_S<+>?x&y!m%$wmvccd}puV_D4Im|F&Hky*&@q<Ty9idinbO|Dr%e%Dvj}
zv7j7T{r%nEm+~`r+3CGJcJF@P)y?pk@;{$%A~*BWtqLAA=$sBZ-X|OT>)P7r@6Xx4
zhzm+eYI@$<QMlOqzWM!{$*c9(?+)Hsl=}1M&&=oN=7MG_y#LQK%~m=2c)CQlnC`0T
z_j|+T>wYW*wS}13`Chck*A+-k*N?X|&AAa!SXc;Zll2(pahI;29$E9_wEq4bU;h62
ze7;ZrewC1v)GEE$T^UbLO<fhSagkZxofS`>Jjv;wEgc!FoP0)C`$6@;pU<DZe!V(y
zvD?nSPEWTMrlh3o__987v)i=Pm1S>lnaeo;{q;5V_BOMe8wH1dpZN0my#47-I(N(O
z*Xq?;&iwrJ^z`ucaeKGq-L?Ap`}gw~b)afiCG+X2sXP13FE=u?hwLawoc^d-^Y@No
zWByH6`_Fv-@#(aFvF!fb+g&|9S1v4cHqF0hBbmIV;^QNk+~~z_ysBzy&wjk#Z(ilU
zE#sooBv8Zc?}x+uefHi#pdLcrU8|$VkDuP8v)u0G_d62Fc^c;151(D<_^#_JzpT}g
z_`092puu~kE7F$l&m0Q#j~70-%Ko$59?|TBUqSskS?e+%)9h<!F8(-i!b39o&bj@d
z@sA$!&EHa&Cm-+Q;^Db+XJ>J0&&4-4H&4}%w<~>l>1gJigU#$yCr(^AO*eX%$b5O*
zst|U5xjic_vaYXN+tb6d{ruvs+1Gb%nQK|>mVSO-=;LF(v0dluf4?;cPr%Q9^G>?l
z=sJ^scFMEe$KLL7o4IM$<n76FcRNm;@JLNb+0mQ)_t#f1fB*fd@h9?bY*;vH^5m`Q
z=jX}vo`1V}x7SoHE<V0%>tc7?{9`!y_QCV#%U@kx{rbtt$+vbEKj(e>_<WT=Cl61^
zY_nXG<YPQv-`ouL^z_{RN3u-&{(V>>%wV$+u>kFkSYl#g9`}i|H#Zi3e0==>^}5>i
z)!*M49edF#9#^0x;P2~uwfMYk`Q_i|r|Zw(RrYpO@$+*#YbyU8Xk@N>yY>1M`}(@l
z*VoP##+0*O&CJZ~(^pOxyITACtU0K-I(_2|(~{TS@9(S(TH3|L%)B+_q|oy9#c}&;
zBAMCwN+j!_osrzm`r-Nc`PW;y#X$ode|~;WufB7qqpK^Zl}mI>+1n`4T7Z@L$9g1h
zZO^~2Yw34#k}7C4K-<tTFnF0y;Y{I$3m0bH+_Y3kNXVq}Q_Avvpalb<A^3-fTJMSl
zJq_8Ibo9#B?C{*XyFx*|o7;;XHM8?;DJm-7uC1K)nVnzm%7(<lG3WFZ6&>68WQ%V4
z2L(-97qfHH;@_ZDpLJ))#(lrvS@+7@-+R1oQ@6FI=E<ja)!*-ye?2N5zoX}To?J@Z
zK^ybu-=9qO2hEOws_cJ%f5&d~^!6^+a=5#%cK2=h89VIS-k9Xx3XznQytSvYxbN8g
z7q&O|R2EAn%Upl)i|Nbe^z*Oo|Npl==XTiTWxjK_y}i16dQ)?=Y1$cy+?$(@s;VXX
ztlQ@>FM4|suhFrLS65bA6+P()zHNNoMmf2s>ifI58U3A|ptj$aW77FAKA*QQ-@V^=
zwwdMKZr3i6iH65A|6f1#=hwR3|Ex-1t?-<z2Aa7_J2&TL*>Cx}ACAlY=b!uMvVL>w
zX|bitm+!8*dv7wRsA=UEzxL<n=dW+K-?#eeJI^MvoliFC^fcYjT_rDLj!z1<v$Lyu
z(8yl$=7u3ic6Zs^pxtF}L$+iDE-y?>Oq>)`Kjq<}R_<4~x4-xOzrtsI+}@O)iyeZ>
zbFOV#vP1>cI@Nof_3_bB(AtLF+uJPvZa8^$b+~E41BdPLNA*HhOwc*~sp9?)VNubg
zpjr)7!#|nqKj#-{jZCk!`KqF)r@H$3&V95i)-o^t<aVup&9jreukP;N-eV|bSF=Me
zcGr`P{Ut9aJ^p!Px&Qp=qBV-nZ6_oa@2mZ-WoUSD>HkMZyZt_EZ9kuPd)w9h_4ToP
zDgr@EOM-%f=l;5U=~B_3uV3#-SrjbjF|7J>(LHuv<FOez+>i2~S9dLE`ZihJ-|N&(
z>!Q3nr@ouR^Opaf&sK2Ghx1qVR+oduzna;2FU>N|4p|wb`u6_*`1!TpW+o*ke|^|4
zfA7*`$>hA3|MIRIzT5NJ@9XR9{`vd=Zd(<)dfAN|5ulO5)6;Z=3ko)PP1RDpy>I7z
z0Xh4+J!UyK7F>_7kDYCv51RHW`Sm5U_Rq)TpaH0R6_0tRYKQw>dVka()V+<^xCpfD
zsOae_(41&jfB*G+d#go-g%_Wis_i`q)X!ZTx!DcWL9eLT@#pVfP;aRA-_Pfu)knX+
zzMh_&bMM|g&;kR{eDzh(%-P-Y`Rn5LuKMw#qP4AURmjR9zsI0qy%Q%qKnsIRv#*8B
zG)e{aLu<d?Ot-51w1kaUYRcoJ+jBPQc)#ECx$ocC_4O;A+xfbBdqY8)Jo~!d+NiBw
zxwp4neLlZ_-s;y+Uf!$xb~F9!wdj1yeWxn-zP!9#+sZ2Hyxs3LpjHZ~bLHMAbMa6s
z_tU3Om(Da!-!-Q`@BL*^fY|^4v)Qd*ZmnhUGYu=NDA2IT$H&J(qpG0%|M~g(a*?R2
zqVu-jS0o+n0xekFntff*)y?hIhlhuw_SNjXwLSm6(ev_mcUJbvTCa-RTLoIn6S68q
zbFN)&6sR3{b#?gH{r`XOx9qBacV{Q4rvqA6;cxfT1++rc(CzoPx0hFiuHI7qK5nXR
z^tH#|n%ViUotmmGDk{2^U9Q5x(b4hNuF}=}e!bGZTmS#>uOE;5=N?Np=l}KX?d;c|
zSI6w!1ZqQqCeyC23I)y6iU<lW+_J?)*0RV&+AJsF<D;WrANSjPO?q}_=3+_XG>|Vv
zwL$_GI<=NOIKZeIz0JqY&Q8jvqM)xxTv~c{cwD8ccKEt8g@qq_?@XRJaiUhpiV2`u
zz5@pwuC9;2e{p(bPu;64npancpa01E!3UJ*54Cb%-I(kSYE*!RH@9Y8O^KXV_w%VZ
zs9g8*^15`iTfA7LKJV@;Qw=RGFVGlQGr!%61q&3`#_SBTE`JxYx9Y1&$%}yF7Ww)4
zx=~v^a&K)3++Fte%8tThP!g)EtNZnIdi<8u(_*q#Og@W`!PWwlcyxAle){-vqKawu
zHJ@#{**7*M{`&X(edvk+MbAqeg32m?=e_O}R)00oT`n*uXAKh*lZcGW8qjLDNhbOC
zY_?`xbOJ5<iK~8VYMODu;o!l8R#jhCl)b&R^zQER*R%8Y1#V0_DpU9@WpCupqNR}b
zSn-s_O|0Cn_I|&2nVH{a!R~jvyuaVC-w&Ey&Aq+tWw-u5(3&2T+FxJhsQyv=^5UX1
zC>6Ky%j=!q1j^vk4OP9S1Ux@C_v=M>dC)ol&^&%nP>_hcJZKp5>Z;J!ZTqk3c*gE3
zx#%umy9Bh*q3Y`^&}e;B)GSb8_Ur3w(1f|)W8Kr24m2{GCLUq|WhFyHLoZ)n&{~VB
zbLOl`J3DKq$SE<MhyY$GlM8LU(pT0-o4dNWoH%{j+tAQ(RovcP$8Ug!U&7W#y*$V+
zAL8TFvnpieqP^AMvrbM@<>KPH^!xq(`oquXPQ7#Hq;#bHrrGM|i@c}nf!30MrV~L+
zG(pqiI;Sr^I@&#T!h{9q=31{Vetyn;uJp_A@?U2dBsR72%dZ1<3vzF715F9Ha*LPz
z_>j0Zet(?rER&1%|31rm?yN8KzVzba;;ogR(?H2lP*5=I{=U6TOiZAq2uF_}&%U(8
zGw=E7vsF(fx^F3b>~?mhvHMi5&>$b59#CiU@$vrbv$IS=i&orvrJhRE|NT{BeLwi!
z?)P>-fB#;cc(|?4={v8qS;pyUx}c>&@AmzE7d@{(`s+W?Q54|9_rXL)hCgd#cNQJB
z`Tb_|vXGTQ$F5($Zjy1~z>(v}pJ&`&8@+v2+1pz)Crl7{{QiA@*0nX6pcFHC-n_cm
ziy@{QxZjx?c?`B(`q=5yr)BJFZmg_5KhG94t2{*`@X(Lnzi00%eLd^@z3THSDk>7U
zxB0%mw|DNb?{98iep}aL2%77@u`T!7`uO*k%(JiQfMz~ztG5O3&b_^?^7AvfWWD%(
zdv5Pr<~w`WoXyLVQ?|}ulQhpLwQJ|&KI@+T{(eqgUQ=c^9)suS<{C3HGO8IFU3&ZP
z&c~8IO-;?T8ygbUl#~wr`0-<gQ!CfZYipxtgT@egy}iASh1LB`a&K=leR^uD@xFcg
zmQ{Rwv@CG3+q1RX?-_yGXd6F%{J5<A{XNj=ENG$=<PojVRWlAYv(Hv`?|WjAmfQoH
zqXkVZYX&T608J!Hn&r&cS@Lp{x83=9w%NyerPHIfWF&e`*UPP`sqtAEwA5#F+SxPi
z^0iYI*QAun+T86vCb7BlbK2!qq1wU{5*bX)%)YC`)}C4BJNwLJf4j__+n~AVGZ%NJ
z$^E}ue!uj#eeyA$<lEae=H3R)OE3NZ<KyFH_5c5=>FAsh(FiyIo~eCv<6_R;T~|}r
zEdOmXdHHWuUEQ;LJ|2?>%}KJbvrEg%%LlKEu`K?6w|w^XxazYis;W<4#PrMAX6-6{
zod$C2pFe+mzP`G8c8TZYGgnuK$M)5Jc@b!wbc91#RyNmbnocIjGc%1+eRh|<J#%WR
zc5%rbA5TwDP-rjnnyLj#MIu@uCtTdzW=&LfpXEJW&+^#L*|(2LY_9oPba_RfGRUi3
zqFO1pwqz!o<=l8+Hs5kCyLnNa{htrbFR!ki&dJSfY-eY;%wwX`GPho-XB&^p8E0Q#
zSK4!XPvz#9_xJB#8M=C!X3&xj(Dd(Atx%)dUtbJ&m%l$3`c6q%**7C&#mN&V3bM{;
z<vn>e?~I7Fbau{dGtgQ*@A#*uruOFEPW$oUq1<-+njae^4H6nUJ30*Z?c1lOp>g6)
z;c?kz)!*Nxy}Y#4FL`s-w3O#**A@JYl0nO)D!*P0KPy{)C$Xls*7xP5rDucvZBx(9
zw|`%@`|@)C*$)r5&z3UHn$g6{J*%OCL0C{Q@!kIab)ZSx>GjJ#A7q!GapHu><LA%Q
zb8eUIysz#*FK1QQ+N_$I8qkst8=E^T{~v1QeztUaoKflPYo?5hjK|KOKR-o3{@#}S
z`}g*IK4<;x(b4X{jW^etACs6oabn`BDVoVy*VoN`9Fq#FEkWxxG~@Q{cpUlhh_L^R
zBS&1OZ;XunT>APNXz9X@jmgEb&Mq!38*^`ilF7@;inZR;^=5)5(~Lo32+9LFH#emn
zXkb*+)I9li)?-aM|JT7$QL`k?^X9A!SlIOO<441X4<DvIIWbYq)b#4xS@Y)2%Toh+
zBXo5dDAAmpr0Ux*XM1L%vb)W*mj@b|mpQldEz7vL2vjn>+?6(Uf9>yYGvD3aJv(Tr
z*UUdZKZ9uyzxMaHojrRmrhojJm*V#<?XQ8_@5)D>VejW2llc5>cK)oYudil;!WD!;
zrHT3dn$K<Drp{fz@7F1t9}k+<OiZqTGk|{F9Z<SUpI3P-=k~U<nK^m$?#{e)`SMxm
z{5^?MCK(A#OiVrd_wNVAIj9+HS@57C`Oey1@2<}>&!3lhYs*SbK0Y&0Sk(Od^z31~
zycuYer03%nySwYYPmwfEo6#q0J&Q|J3mnZ#u3a;3ZOxwTIazHcx451~?^l!Swtwd;
zt+sjk?C;yOYfcPM@ZtVRqi6m<WH=ZeY<qcWX}6ee6lj$isC@+*5i`rbx2E*<wUvdB
zkI8KZ4eo>HdpbHeKrI|lGvLqX^II!ECh<y{cuZFJ|0jGNI#1T10%|Bv)eaAvt{3~|
zAiMmNQi~4?T3TMw+j2mY+%>hepRHsbEUWqPupP9r7-a2?88i0qvHv#!wU~W;dhC8Y
zU@m=mNp<~Uq@#eI2(Z3j_+Y-R@^c!feY1Ygr>-_0NhQx+MNhj{g|A;Hr0SLN_*k#p
z_P5v9&j+=!K*Mz!8YeE^+madl_Rh}WlP6DZx2=PC{=xpMCnu|eh7u#EJ<Zr%@o^C-
zTYyFxxy5t>a&mIy+&a9c>uH*rUVZuBe(I9Q&1oyk-`@kJ>}k5u)7&pIZVy}R)?4!P
zQ|j9r8<p2PAG8Opx0|9LZ<l*(i{^S~WQRAE$FVao>?q_G*PF6^`}SYo-oDPz4p`9e
z>&wf<g34|$Zfs2E;^i&f{r2bQ=T9F$e*8(_zpbSu<Nm(d?WTD!_uieN84Mam0WD2d
z^`3U6Q&@dV)z>W0NJ#GOZA*Xr(SLAaqH<SHPY9@=w=u~zc5hXvb=jK>$9knhcN8T0
z&N9(l@63`nbNl_eXwZt(q@+b&({yHDfA~QD(UDH!uFlSjd%xeCeSIOsMle|f+9vly
z`uDrt??nU!73=Hkmw)^9^|kdcThRsPxwk?<fwjNx@0TmV{wL3$_y7O%eEpV+k4gWI
zdV;kxJTS|?xoIh=5%=Rqg{rFR$=kQ11qB5`Q{$kn#r21dL7hUXpym*$A@cg#+RIb5
z!$pLI7TMMQda?8Qyx@w8inw-;J4RPmhlhWCb@j6q&!59BEiD;WRs>ecLh5_4O%K>2
zj!8_u?#RH9=L6c$ASATt$B&BT-)yVDt%%y1HOnx$?eg`D>p{am2b<ZmkM&4;d3#S*
zsjRMk4H~%JU-vh!`VH75G~&VfcKrp+2kzfk>ODPVfdk|8GI@D<_x<YIa#uUGa%Ej!
z)+<->fKgN<z~S@r^VcW)+pU~1L7?=-g@@aY@}e09=Kh<d;lSRo-!MKt9@NTN`uEe*
z(|vXR$NJ^hXI@^G`TyVFPoF<e1~1z@JKOxau)od1Z*Om(-j=)l_B_jCH_(FSh=_=3
z$H9i75Dxctl)RiIBqVfYS82AWZj=cq_x$MvO>osGgHp`L$H!xD2@4CWdM@>v`f118
z+4=icK07<xy6e0#Xic=g{ogG@LPDS&INNWpi`f};cUS4|&J#!p8EV~!^cmLW>vomB
zopn8tf#IJU*h3pZdqeK-Dg||9|NQ+c`*yZj?xfVnRiUe=9nbZjXS4Flmy+q<wrnx+
zymWPSxNV-an3&qj@B14-m7BSQEyIH_38Rz_HUD{Yt|$IcohW_&L~r_&W5z{~C3k-8
zxl`emXQON$scb)wHZprb=_Go4UZ0f!14B_4QwhTl>DO0QPFC}swPgFfDsRwAB^6Cm
z)6mUnXM+y6@rp`GX?cQ{dj|ytg=|c6t*or{oTQ|rBqA@r{>hURQLPY<NuXu<p!Ma9
zjEtboBgY^A`t{3e(z_jx`L3>u{arRsi9tcy(a~|uQMn29^{ra=%u)pgh9@H6@-%FJ
zT`j0TD`i)+!*8C=O3=jFwKb7eH9t0hhM6SHb8Z-bHdcChcm&+slq#FcZ~te*tLy96
z*Zuu<^7{4g&(F?Y?vu6ta)?{sg6k?~YGGhFP|weGf$>3p-nluJQkF$aKr6eSJW08_
zCNdbb?Jgu_N^(zX<fh!)nY%$N=Z|)YUiQ}CyTo&{+RHmTi&w?$+>~}^#zJ?w$|vXT
zu;!@`;tq^f41dmowj+S%Ra-cPZTe<f7B9Oje$jYq&dng*=xuxEKE&p>hW&!;ckI})
zV-Ft_!-wyaX3SUtitc{9Un?MGBg29Ey;7!GPf9uJBhiy1I4$~KJJFAkP^ltQ==ztP
z;elHuv|Rfaw=MtvI;+xG8Mn9Pu8Q4V7S|46q6^KK3=9pg1O78I><BCaRXA`_WX6x|
zVX`OspZxE#oW~&y4vqz_9DYao=FXcF#Q*f-<(EOn?cMl1;}})09XAL*Xtn|B`_VH4
zp#i}#dT<9UBt{SJfQ7{9!5y%W7;*=9jGlZ6kGj!R3=fLY>JAnZqtzWOBu1+{SV)W(
z6tIvOt?u9<F<MZ-f?~uL6lbn)M($KM*q86WZ{7F!P0#XOF?zA<uWvSHU|{&?&4zpw
zS%u*D-+RA*kM2Ldesl1=S8v}&&z~=^R>Hv0AdGU9{R3B-;~RheNiVgwe(q^kWm8uo
z(+)bv{s9ZBahBU({k{oWjQFQ{-yFnt6G+?~xPK6_U>zdlkcxh0S^~y_`5`D)fb<=s
zvN0ypmb1au0)Wg1;lbfDkV`;#)HR?`0Ap%LKG;wO28KZ##C4m?|F5f@mdns~z9nf5
z%N&`cgGXPf1nIOanykUW*R&u(`iSEZ%Wivz{|$VP-d$SIyHO!8Pu7Y<jQypWpH|Xp
zg^mR)j$X>&xzDNd)7HOPx5fLJH^rR)eCPevRI8ofk;McK#PMK|09nBTKXD5pz`(<Z
zSYrkenu=J_2@z;eM9<C(gccwdN(>AP1{em1U>s-IhGDQ5dX_&RfNpRAC%PXbFbvkh
z@PjkD!49hEexPFDL=-$fKmYyJ@c7*O`)cnN9+#E1Dp>)Vfjs|SuJ+5tY160w|CFDa
z`jjmP^=6SfS>NuwVP*L7f6s?Q+_hgWy65KQZL9zPZ`-zQp!Mz6rLRKx?f-nZU-$i(
zbpDr1-ukg-zrS9O2kp(Se$=V{@8wo-G(%#EfuSLK0)uQqBWR`ET#Ld*+wWDaK701;
zs(JPQe#%umXpF0TI@Rvylga!4e%p9l?zZXed-v95B_}_gA1MJd0Zi{$s(b$pE5nX5
z`MMv8)!*Lie53Yx>eQ)mH6M@K{rz$ov|D(!Rep8#?yFa?&Z~O0^7URVus#^Efq~@(
z1NWOVGmSxm_-og#i!+OlkKh00j~8e!#ax@pP0Q!k?b=)YJ?^?Ks{4;BIIu?~JU=%#
zJ2yA?dQEQb+HP_EvTtv0YTLbT=C^xssFgc6Cnx5-D5^GAC6KoLf4@a*YisX*w*7wH
z@1@VfU;X`l|NXk%?_Pa8F26tTH;NX9Zr29B4F|rxyL(%{{?Eqjf4|@FkFTmz-S_L&
zYQOn*cZ<*4UjMYI9(8E{L;lw1Y5EKYwnj%szkYLb^X_NQ&&^%^>fP@5`xX^%+rB+I
zD(cmViOS($f6tyh8?=>f`dL1CyE_jLx37OC0}C7wz3%S0bAHy=*3-|{{rmZR_7+}-
zZa<K7_+%_DtPEZbTFn*}8@t!UzV=s%x3{;fMZtrvb2o3^e0i_>eQs^--&J-0-)_JE
zZehFJu2uOU17Uc_zJITr4uTdYH?#BKThhxAk#gF+nvr4MUE}jMm*?02yJ`J?PjP11
zzdt{>ZQEv5@*?2(x3{Zb{eHjy{b~LEZw|F`?>=Wy{LCl5=A)~$w6u8+is=jwu03HZ
zX<*&9Z{NMm=k0F4Ucdhyzx|&J|Nj2Ied`uzli<r68<VHstA4xnde!&4<-dQuUcdYK
zylOq`$3H$k*45Q5eR5)=^j`P@j9^z6bPFzE*4Y7CDrSDaX7l6Y{h-4wzCLK?|Mu~?
z{Pz>e{V`SPnVBn}K7AT{KW<OOMqzcok`E6Kf<j$-ry1A`7*W721TyP(-tM)F-TTYF
zytuf(_BqH&cRT*YdwYA={(igt|C1`1axi^>>1M609+-(B{(B9&A_n0&5Novj1%(0_
zk5*3LU;q=NH8(gIK*VUX1{4ZlJlf_12Lp(pVw(?S90HFP$ndZjEs)_s!7y4N!^2{<
zK!yj!Xn_n5iqQfY9uzbkp@7>0W{lQW;9vj|!>qRY!C(DdSgG{y@xnh_Z%><jQ$9;O
zEc2y6E_dQ4X{C}E4-{VrIZovE3@G7t>R7WvK||%me^r5`wLB9Sy?AhTfpY{)lzHT*
z3Bs#eg@q#gCY^o%>7Q<gef`y2@5+zW+VstzssDRc<NL(Kc{Plnz++(0!00GX!WeTL
zRRakt2ss))kZ^#IqiF*Y4iIuQZ9u{SLJps_@$25o;N_c2Ute1jxmgXgfx3-XdQ<uP
zd;4qu-rHNfx$yC^n9{4EJ0Epv7yW*_{rO>j`<Np~A%OrT9o7piVE(eRU9L(af6qrZ
zv;2E=w%@DLc6N5&`TO1O&H4BD?cY<DmZnyIw=`UD=aWe}x3}r8-}A}q-JZ|q{(Lyh
z@4W$K1e)Q6sk1LXL&C#-|9-uGb8oNp`hCB$w&mQMqyjoeB5&{4Yc@ZhO#b<(TmM|;
z+lPnSKi^31fBNyb{Q2zld$)y5h8F%1w>8K;<9xwT`(|;!-Kh%~0zeZUKR1hNhdr6-
zE_ZTzeBI2QJ9iex{r+}4|M_|Q|7W=M_e@av`Sp6dc&$Ff04RCkHVep@+xh#?o;ANe
zCv<h#+`@fze}DbFe*Wp^^LD3ox8Ip$Tm9`xn{?iZr_<x-Wv|<*cHaJf&91xe7QI8-
zcf-KIP<1)rGBZQOj>Yc%X(c6J)_lHr@nXsDyE2wVPv%^&`+m24=Zi(%pFSMsPk()F
zZRGAU&;iJg_xyO&ZCU%PB(Cb^(xY=wCu+VZFj_gtTUUNc30o6Uc<twh4<G)#eqQwG
zNN36JyL<k8I$imwQ+<-k_j}d(pdtM|KcCI6d^R(^=w|A4-E##{4??H~>bz#Q3=OTj
zzg+VE{QLd>`K9+>mOP99Uw>Wg<TBsc=Pc&Wn|JQyWcANy&F}x|_C^irx(A@3&M7G|
zaqp9{eEsLe#l@bJuC5NB|M}L{)#1-CEOg%a@7L?|7W?1rdVT3_S@EAAANT+H9lb5*
z<kaxE%40Xbd?{JBeEI)#H4wKz$bYQ6%if+^7rXnM#qX!n<E5gQ9rg<^VE(eP^!2r;
zpU>N$?-W+wly!C0&(G`k{nBD)W{%vRch_?L+*z|uEp%=-GB=+toxi8>Urk<~9y2rZ
z&TqG}|9^VF|KG3IGv~~)S$`g434}cG^JhH2h)ux*hh@u_Nky?Z*h}YBF)(nK->?1t
zwBP>UiEnRjKR@p`*J`S)by>>cHr~k1X}*)59G9;@^X5&C-+VjU|NGeGDirSKnZF06
z?8xo6&z?Esvu@w7tp5oRE1={7qbJ~?`upqa&j0^@PY|tRg{=kn{N=L$^X2pFPWhVO
zog!;p_T<CE!!u{joLPTA*xz>Q_j}d)_v`=H9y@kylFIix#r|e_cV^_?-uCpy#^jxE
zx8449Qhk2P{e87J_tjSG?fda)nVlHaN(gm9fYHife)a#q-#_0eKA-yh++54LKNZ*3
z#m)vL-ahMhGwRPDIN-p>&VGK^x6A(aXE&d>n|*h8`SZKw_s{<LQ2{y*Gw0TpOig>}
z=0%9H3>TEycHPa}{!)<P%XDUTzLcyit>53@pMUZs<#I7p2?GPewBG;!`iyVRf8z94
z_Iaa9-D)m|=idJr4>-;JYY~G`24+oD#h5nr#F)hu8C3%gEC?|gK9F#LkfUh>5)Ke@
z*rtt13ztDpCqLk{HEQja+i#bp>#UkMabizzuc<9;9Y{l}6LigmLwwfOC`tMG9?L&R
zUk(<#`r*T=Gw0+)7Q$3+P=S>)UzV2bj{W%aoQkmT`A8M^%P(zal<n4qFVslzg!Ls~
z6bpN*&6a~#hT<&;VQzv1J_7^81!<VEa3K{zjMXHgYT%*6z%We0r)`!T)KeR#M6C_G
z^|tJ?vDnoUCp?ZFJNEBm={{+wtOGQGGU!OJ4by)7Somd0U3S%}MN)EcGjHB({;#p+
z+g+$qhECX8r3klMZ_8M(Sx@#cu}z;S<Fov8!mYR8?7P;~!Vc<kP=ck{X-hj*Cj0ik
z2!vZ1agJ>^%yBTI9r7_2IZbeZISsA|Bk7K+frSl-b{LA`BbfzXd~#twdP<!&@1Rl9
z!u#RxG(rAjXt<{aOI8eGORi?6*3>A?J(ut69~pA^u(q*vb%4R?NfCVCr&e=;)i2l%
zUntkWnz{Y9=*f3JMi;-#aV;{Kd#*Wi`|YI2X-8V?<999xD`%*h3rpb)7XFaZRb1jb
z^n%y35};-|L?Mja>xhv?g)kb2uA^#T;l;q<K%ekAP=8~0vw-I7<Nc52ud6P1-Ez3%
z#*&rITX<Y<h^cV}PVe9=_4F`MQreZ)e#%+4htKKKT4(XKVk#YZWha~47jR6;JMHFT
zJ0Yw_k>#cu|4-{b`|ImF?Y%EAPfz>ym5JZZ+PJQa@AH{6=Wert{N|wqPnRGr0|Nu*
zbOM&L3S<4H0=$TY8pF_lu^iN4Qp&d1pj!XKeiPrxL0;F5qprUHZY;sGYaSzm`P|PI
zAgz<nRfD@W2cp0^CgF{V@8s6jM7PCP*Dc?&>iX={r%r9+|HfbtI_EgZs2L^q9)r79
z*Q~(FH+lJ#Ao~lOr=;BYI%k?ry2-8SL0$Y`aVyW6k+Si%Aj1LsM>e2Af&)uF%ZY=W
zvBB(Yi7kkMgd098pa&LF-o{Kgm@~;L7(?%v%V06vq?oI6F$Wzn=O?i=6yT)|%)4|=
z7egR`&X&Pb!?D=QCYno2Y!`?At+Q`FxZt%UG|)<X;N@lg!pvDZIy}ZwYs+kxhVH!=
z6Bahj6}DJAdk(y?{^z8*^w@K6&$ig}nJ0_f7T0Png|(6yu33OnG|2Fn$%&JWu5$-5
zL95_br|m*-h8(CMrWrzBwxw(IsBDhqhx!vlEeppM*ygS95M*Fr$Z)-E5*Z<pW)k(b
z%4>Di-kodK=yZeDnK!IN$*@s@UMoNT44Ra9y*O&qoQoOpUYg)sm!Jg?a|Q;6hH1Q$
zb;@i(g-S!V!R4<YS0LkK&B%6xWEw^@FDMw`c(inb2L&j%(lz@ar)01zhD-5(GUqyM
z$N}uHhL4v`e7!Vd&u4`0zkfc#;6)W1!+{92e#G?5S!&$ehkM*s$NFc6t~Z}Pb!w`h
z6~lq~sKL~5dP-1M%|4Vy1A{EX1Ao-<g#)2HkdmRH{-O`6YZw?9B>2IF3D|K^ViH<m
z#;`+j)-q4crLQH|zWV-Kl7}t!Ji`vH{-X>AKT&Kta3mYk-4B%wrrC%wA1FaB=!Mr$
z32HvRRORrx=UY-N7hl{rCCH`!K*XmA9)`=PZG4}JkV<4tp<Fj(!laSbzEQi=$}Rrs
z)#~+Wudl70IeYf$b91eWA06r3zxN(!;%4T|ncDx>#P7G;|L4=`{b&<x66T;<>A^A3
znXx~gO!nVY|NkFoQqH|!?(E}!`+1Yq{nM_mi><G`3z}s)YkvPsZ28^Nn;$`&7mlLN
z{T<jLw1C-X18DL^zV=HXpS<0izrVk$d(NwTHuFyLdE3gTQ^P;~d_MpG+gzJ(H<BY`
zVsffccjOo_f~x-m_TN7qmrpM%Gt=Mm;n31#X|tRYpU>OR*WdR;$^PGu$EJ7B{rvp=
z^Ktq5EvE3>3Bl=dh5%DZ1LwD|*W;hR+x`CBv0iC?>wU?``@G}-Ym4j0ojJ^JKgV~r
zS!!OMp1<AClzo4{-M;n>R2_nKgNetvpoaXP;`H<L&i?uHNA&pf=g*5jJ~}$bviRAm
z>vLz%K3#m?cDlP<rOIrx+*2!qmlyr`@DMaJ2|7;x+S=&bXftv>ii}nVSbo3Vet%Qq
z;Wq8Q?^S!f<M+?9t^SsBexB|0fB%jM`#-tpE`QdU-*yUUs`UN7-|x=K^MD-#BYI3h
zhV1@&EgCcv7hhOoA{G1V*Vh|+tIOqTJ{+85QTS-t8*mx2z}olnk|~$I_Jn=?{g;QW
zd0jfp3?EUD8MEilKR?qreVs+!w>LLcPQKlKzwYk#%Hy)-PiE)u+qvxYyZig?XPf8m
zdvgOc;amRx-s^wmpw0-xj>=ifP98dBu=rxu_28(hug|8Yrbf1aIu;BJ2WFMOxv^2k
zy6nxS<mcz+zRuufnC#cUXK-*^{(VpadiLk%=bJkUA1{3zU-vWh+S=&pZ*Omp|DFq)
z;k>yi^|Wd1x4Gr_PCk0{sPsQ%3~bBlDM61vqhx(pF|wxe|7&rsd3Lo{-|yGgyLU6p
zNC8Lsm0<s;Z@1q+SN(qP^y%?+mYziq54FnJR+(6rzdLhnZS-Un`@dg;!57Bd-j@3J
z*H_Pf?+>^Ct^2>}_U|v3{fl2+S-I!SCGY?5%)tr5!Mn}#kNYB6=*3urLhts*WcP1x
zZcb)q=X>&ee*L*^xwnhHytoLOxV9{Ma$@P}z29zS|9sHQ|LO1d`|-bY4L}o?wcqbf
z2h9b}HqSo?N-s}NOa$FaYFY5WA^g4&%mOfd0hCx;et$U3|M}PJ_34?Jn*0C#%6_-^
z`#l-^I-A|)@As9=EPZ_~H7)Jgrq{NAzgz}Q+1dSmvw6+Bb!l~VcKZ8%B;Bic+?#WA
z)6@I^P&XYl7%Dih&nVb_r^uU6)@q7#J74TqBlkX;oo~z+sh>R9%wGKA!NG0M!I2Gi
z42Td;dG=l(93CJZ1Rsb(X?lVLNBfGPP=I3x)7z+R>swbbDs%=P8+acGr15|VmWol(
zih<#d0-8GQrB{B`XrA2g+EO?2T*emtrQqo;bY-&)d^X+q%E7>paE6xE;Z<<kB_RrR
z)MMT6s&~>13=Pu8Z`ZHhvy3Sr%J;XWO`#k+!w=*0|3TiJAqHwv?BK*KRDSNNoAG8J
zBLl+@!|aEpQ?G|G_$=O9z~>Jd6!|y*c|AzCk1!}q?yxMK^2_-NN-44KHTy}Z)qf#Y
zTlxNnTCESYS`BRV$~I52-ExM@?tq5J&5ym-VwmA`?jZw1b~n_HeKXfVr;|Wdg0X=d
ztP}!sK?Ds)9GZV0{|;LVFa)}{s0~jB1_m<Q=abGL1|&cs%&_YcX6_M&P2z!7FdUe5
z#l%-ktWB~vZ1=oNtK#zYw6#wwl`t@@Lmj+pFkLwXTg4IsPEZiDKxFnEgOf?ul^GZk
zbk2+pmVrV9j%hfEI@+Cthcali26L1dC4fM~>Gc;ZUbFW-o_{1`{X(S^3y(|-ULwKg
z;?)v#;jC|fNQp*>RYurizNkQU_JynqFI`-^mCeiX#S?`U7AreCx?3zdYL~1%B)%lz
z)@F{sy!-WA|NS~Y|LoJ9r}xG^p8Vv~&WH1MKmK$M)UI?ez5ET?Z9n3{&CG8-3tyG(
ze)+X37qoh+K^vtAkkItKoKm-M{=o+|w}abOU7mUN)vGQJSq6rNiI9=`83OAd?MH??
zTJy~rUM~e@&8I4Vw>{@M>BZJ;tGU$TJ?O-SAV{Grd;oexZbS6b&uj~1|Eh53_JhKy
z6KWg-ig64K3<pvm9ZDaOaA--MH}yQYftjE@JFgnqLm>8I)K2B-00+isAb}JK3Pdbh
z$%eof;;c+?YB&&;HA`*jlx^ueq1$i!uD_mL&E{kC9F$@r>hJX*zV&GaxGnr33Y;Pj
zv|TjuefIpfB+t3+wy7(u=H6VhZrzV&%Z!PiK?gFdv44L&F}KnO+@db91vNSt5)NxD
zy<$Hl+V4_+^|=XaQVecP4(hU>)+}auACz8yeXf(aHto0wI3TYpgQsN77Sv5@-R909
zeDEh|@#wYr-yd(-X0r^eWXGkF+o0?T=0FJvUa(D29+(=PIROU)j2KB%ODBCG38dj7
zxC@edUSd_=_StdkuYcp2QE|?kfnoB|*Y=Qrk%)yPoCmXJEj#(A#=iOB&uz<jLYEuQ
zzIs(OkYUS-pKJ^Xn=1Z7i_*oukSU><V9lk+7*2cs$~`YRX(|s}b&!`Ji$nLEd<F)!
z?(5*@Is=2jEpU!uIN<wbvd$J;rWqV)cDr8AMV=c0xhTN|r8)r#4d1Cd6=M|t&j^9l
zuP<TsYlG?bi}Mc)pMT6?a1s)jpb%kTV9?E&rS|#rUmmvSx91s|%srPA79M^in;}PI
z@&}oD6>{tio@(HN1gbp4QFCcqHYC29pz*bial^u#KhHlL`E0@9V+QJ5K@~GNtp4RG
zc1w<t;m>`Wc4h|Y%fqF>$y)XnTre{jXo3f>-%2`PeOq?<_19bTAmX6%c)toH<QhsZ
zV3zb9pm{h*I31e;ttziMf+js7feXtFh^2i!n$VzKvl>#SLv%AR95D6WZVTf;>4uA=
z!z|FC08><3s)5po1{*!-X7$c)L8OL;Xz*+ha>)&L^o<Wlr9kqU%vop7e>awxlV5!*
zpwwz}WNfS;WFhN;2}mm-jz!=~pD4=AT9DFba^5azRsq`!CVJSQDH+TI6QfHwz`+0`
zM$j6UNhz?h6y$jW9az<c)HP&aNN9%i#Xw3JHYl3<PX76`j;;A~uD|3ezjU+JtF=MH
zH4F?4*IJ-uDX4453m&dP=@UX51rfrK)(Y4>vmJ=^dLUxPXx9!LDlh_b!#>@|>yzI<
zI@(?NxYr!Cx$w-nbD$~3pMO4||Ns7WWK7JNFJDUL)%|*@xP}GhW-xuMkwG@$%-g%W
z&E;!8IL1{xY?ZMp(J(ePuKaXT{qxuB@&6y+{_*ek`_C8M<x@XDJL?<+Sz-#-%)r3V
zW5sB7Kmv3FSJ9szAK%>HZx7mu<gLGV3TP@3G<_6T|MzQsjkUM8_s!kq`R{f<pQpGE
zym%011cTdL2HAw3+D|9dXU?1nnxcA|44U}s*55ZHf8S5F<$iN_z03toGl6E8?p43v
zo9KsXz_A990iY8FD_<;Z-;{cKns(p&J3Bvrx}N{!&d%bS+w<e^RlU{?w}-Z?p*FL;
zV0a8VnsDaq*}Gr;xN|2)FLu|I%gg=me|Ubs_WRv4=gvKw8XhNk%>}9+LM8N^*<#Dk
zQ2+i=EBDPUnU_P4ThBfBbbb8!^Y;JeIJfgX{qgbf&cEMow{HWTk_*uTA|>RRN*WBe
zRepZ<2Xv>GtUM3f^!;_V-rnAoe?A`ne8%`ZPp&*eK`}<w-l6zB8Dszi|Ih~o`0UxU
zPrtmpe7#lOvokYQPS$?ETYh%_?@y=oKi^EB|MW<wuw~_^lu1u6E%pBS`~Cjnhlg6{
z*i;&o->)qP?E;nl_b)uY*0lU?>2=ZLW$*9Jy}P^o|Lon&48qH?)N!^<%BO$AkA;*d
zKi(&MdSmkObrzu07^huhFnGuEf+0EQc%SUgSF6_-y}Pp$G&lC?WB&fXX2HS1H#a69
zH?4oS{eIo)D_271)qcCF-RJM?`}E4n;K~mN!Bb+OU6ba2{<8DSojG*q(AxWg3^M|j
zPLZ<KQ-8VLHr*r4NaBsBrt1fe9vwtTB;1L8-PC0N=Yun7m+3SyMuT%8XS~_@eBNo$
zj6A>nAA|LKzeP=Y^5|%{WziFlvbVRUu8rQV=2`du@Ao;j)n>Q1=bz8res`Msyb2|C
zzd1WzeG?NG|9pU%{|RW0^Dw{to^{_@8PuZfJL_LDU9dw~&A=eAfVpSmT<h{@KcCM(
zKRbWlO#6R7ltJcARCX`=^yH+BUCobA-{0Qet`C~yU%&s~thn{lb8l};y}d0r{O-L=
zmx4eOjy7Mf1i!8X&5b~!7DP4(Dmt)B6wBBDDZE$te6EhZK6t0Ba=*<afBU~C{kGq3
zJbgcN)~r)szI^e`&(6xy3JwlFJck>k7mj-j7_AP>*!{TAy6C}yMj4BO2fOYU|M>7w
zdtFDJEog;8lppGl#<4SJ_1jU+U^w7{RGUDI9!c#(q!t~-^TW4e46W`V-UN}bS*1Vi
zwbt8mwHOv?RJCd-WnIry-hSqA#T${OrGK-ZOnRp4@UVvGxle)k4v;1Yo(eiM9KwW<
z4Tgx$8AK#N@&dg32N98A#yEF))EG$6FpP!`G$0s8(+w;nM)MRbBp9ez-fVrvmIPZ1
z05>1R7!7VvD1b2)gBxrfj2O@$4z0Dd207$M@%GzmA6uL|S25%C(@U>kzrG3En*oyj
zFAJ`vY-Zkmd+qk^t-t?Xzp2Up`O~Mh{r%;_NcGnNbz@MCcVMz*U-IXl=U-Koonzip
zzW@IV3qG&`AhSRNpHO9&cZJ<Q-v<>0Q4i!lJ;k`|_a7e{@}(Xiby~=#fdm+mAtR|^
zHkepo1ab+O2_+0hje&;5XxKmlf?+h>z(Zm*Pr-s>w4i{6#ArbQ3yIN!0v-~h1qCc9
zMhgm9NR0S`;z0hlclS)sZ{mIMVZG@#H!h_W0@{);bCyiu+8SCQw2*Jtihv~@EE9WV
zUy1)>PZ4NtZf@q)3hD0StK(@}^hiOEuXIy$uj>&H*W8d_dg2dtL!G>{KR+n+;eY=3
z<DBpEA0S)xLBXAXF*FIf8cOZnt5;e6wqHYTZ_j`KYW4cO^Yd(Le>`k|Z3o)y^!)%c
zzlpW=?Jr+SjE#-o-rm06-~R8H_#09n1L62a2g?fv;dd9^<#P)QH!`#HeYxbVZ)$3K
zwf6hn?Rg&m&YIsZIVu`%VsC%{wEq4(3!U4oDnF%w2G-y2|Nn14(xfuT$PE*HV&Abc
z>?i=;qLaV(Ync9?4^Hg-a%)~4Xk@-yc01Sh=ab2xiI4w3-rTtpQ(Rn}e)ie(=evJC
zn;jh!^9D56v1B*uP_1;o@C8P-8@KcK-@S4rq~HGEk6SsfudO|M_UzZ2>GQwdEx$ka
z`tN1Sm+$`f>veQw<jxzb!RzTjt^s3V2hgq|(B(#;qaC;9-Y&aV^Zni3?CaM-+jHvv
zd_3MKYkduLr_c5H`n$H@?-YA}L!E6g+qUxbUIqs7yvoX*GiS~$er9ZJJlC>#nXtOw
zn%{lx@^#=Fd{*g3Z~JmY*#FC&;`6azVo^r?8hX!jzF-i3v;BTu_UmhFpPyO3>(#2Q
zuU|(-M7#jq?F70#>;1jGYuBy&c3i$b2D|Q@s;XU=m;28*{{Q#;{p;)2ryuW=&E79x
z`D9|*+gn$Y`)#jXT<orY55Bz!?0fK_w$Fx{GiUnEu_!!OQ(3ulm301|k9+QwKb;z0
z_W$qq?He{+czJpG|8FH<|CfJwaB$tuXR|h^{r>(w|Np<g&%f>m8v`X`b||~|l{`5y
zadVpe|39BoZ?QFasyndHNU$z{2RZ}u)%5tf%-h>?vp<9GVe*}Awzc^AxzBaa*YE##
zYo>9!Rq3lMyBL3U>+ib(I&twgbdeau@EsNZ-Z>o9-~VUR?fm_JjdEEIsNAmEDbDcV
zknN8L&3}JBpTGChDedgdSFc{3Hf`Fi&FTKPx96`1-`{j&WAfjx*W<Il|NU^7|M{N$
z)YPTr_bQj)ym@oo?svPq|D(hO!-2L(EF}$`+p536ldF2M5VVufZ=TIf-R*ZSUAh!>
zykGwPhlhu=zk{|yfwo?OE>1do?p)Z`{QLXzcD-EoZpY)kyd4kQ`sD3F^BSj5pO&?)
z`chPjy6dVylJf$i+8xj}QJ>G--<QtcbJ5@a@0C7TYtZdbyI-%{eeK=NEt$cy&GYSE
z@7%d_=e?TGXT`+Dqa!0<-pXE|`~Kcu&^>C_@ArJZ{||NJUIMeg0%o5by3yOVY}jz&
z(4j;2_ds(UoBdqY&ze6!zpn0I(0bH)Kc5L_U*AW~6$}UJ8xeEjkQl%`g5&_kav{u>
z`UW^h(;=pUNFJnlbr7F{0dpw><~acvD}zU!0|`73IT~4@P=Mmmv;z$YhS8jb2nhy;
z(Q*e78n8J|gve;<Ai`oabP!=NTB9SvVzj-32#e9?7a}Z1n_q~qU>I$FAp&EFc5FWK
z+7x453ox4L5pg@LGX1~f_wH`Vi2TMVVeh7*&Ax~uS%~XYmar11(%uK>R`?2dO1g9(
z<TseT##OppFG*~h)`f*koQv*m>5@>=;5sB0lv|}(lrx#-TbkSXXDJDC^7GG}`MB(U
z{?GmAKJWVfo!tUyjofJC3Xz6J8&`<17;Ri3!eZEzv%>Gs%rt&`fB*iov(3xjZoR&(
z`1!eeb-&-*@BMzx`aNhuBDVbQ)nmQVyZ?T>eS3R;yt@CqJv`B<gZ|-*zGm-bV5mQT
z+28)|?EHN<@7#%r-j<V@n79x$-oA9{QqX$x&-ZTcudiS3H#h72Jlng4$7O3j9u)@-
zn;t!S6f~&6%y+ilW0V1G28MMk;FG-`w#$F}^?LpHL)`i%=H}s7gZ*u<-Yvg>*Z926
z<?8o)%kS;}{Q2|U`u~4dr}5kUNZ4KW_SI4G_%{a{ng73dhln-Mx~8e=ccb(f4jiq1
z+-n}SzpnQ8x3|$Vb8l=|c=P7Xd-ebSf=-0{eDCl3AA4Rkvdg__lg@i_+28)JJK8M6
zx*U+h%HG`A2->l*Z29u=v*mAYZ2a_R{g02w<*jRfm6+eFc&vIGb(6&m8IZ1Rd-mKp
zbLNcY=b1BS{`>K`-*1k^$LaUX?d|X9@Be#E*x#mbWf<x<7_|-t*@ULQe?Fhjy|Llp
zoS#?2<M)30<FxnpyWO%D1q+VL*YAnlT^74Z7G><b;iMvHwEuccu`lS3Bg@aAv)7*f
zZ2j?O^ZBYT7u|2~D$Um4|L2qHU36EzzFx)1pm*=g86S1OITq>r_Uwtd3cBQJ`THNw
zX6N79TU~xVzP`4*yF2&Jj*m_C^?7;gUa#AocQxnzy}fVm?*86%AK4)X?iYV~aj{R%
zc30N7!~FJZE}Aj;fcE9E+}@TO?d|P7*RFQg%a<>w{$!W0xp3u5$n9;pzxRLN|Nr0b
zviJAy-rSrX9ToLz+3dVu-uvzC?eBvoeF9OYoeDDltmo$fO%CPW-&fmf#*{E=ZS-qa
zh8-3Cw%;Ps&(C|ibb4IWOwcS)Yin!SyE`|Zot?cJG&458{$C}?qEkEP*Zo@AE?2eU
z>C>n8s$Q?n+x>Ri>3t|u9t;JkA6Y?D5y{8<zP-75x%j;8_450**Qe=5M@2-uc)foA
zyAu<YwV#9bki=C!oeG}B+WB<as(Ce^PTKu?u{bR~-Ma2i#qoamcuRX*+q=sBHbpo8
zqi%ZNunj!HcQriz?a$})-*3Gh_xj4p;M}{rwjMot^xf|F`=%NP2M4c>-kx`LufN^T
zB`a61<de6%^YCzcxGm^(Kvvi}%#c+7L0<)Q<Xd=bX(&6t+?xjno1fbjKRGcmG~Q+X
zuTQ7-|G&HnQ3xd)I5)pL4?0o>$_G;)@<%5YzySdwhE=N)<RJ(iZS+CH0Yr{A`aq!o
z!J~~nNH~DVVbkaXc?N+;Cl(N4F<J~F!eX=-M1;j?F^C9@(P9u07Ne~}NLc(&eE%<Y
z>$=+vef!@ZR{X8_v`T2sB25<~mxAtP&!l9IDE?xOIn^;MO6gEWNubUIh2v)I7d<jL
z#M!q?+1wHkbg_Rj<9w0rbH{VR{w!5{D&zEbOn?3R?}xqb>>r#3uZ~I}X5A9Ti8PqU
z`Y2*-LK4E*goJde4#anu$Hlb~u^J2OB2b8dFj9hul~&G>L)Ktg7#J`Q^B4^rc<77<
z4m>CrMpF(vEHLN!MgwOwa6qf_;h_L#j26h?U;q(R44jCn?fLiLoi)Fo^Zngj+kZbE
z%i2_I`276*|MSJ$^X|U-@$vEAACJ00n+?{kSyS@y(NXpdh9D=v@rMmU3z&6wE_Uz#
zcF|qF^vQ{dcK?1n4hs*j{`qwJ?^mnW|NC_3>+9>kA2jnv#mDErzqeOctebrcx*<__
z-?1|Mc)su7uh*a}Gwl9+INT>|9d>o1vU}CLozJTt_nLzTMZdh^*57l1-~P{qb+Nmx
z%HPFI*N?9Y$VQ#?;MX)?z^t<ov~>RJ)vKUmq|V+1Ef{~h_4=-wpGD?*cYa*n>~HhY
zWp~-zDuHa&1>N3G4SXAptc%-w3$&Ht++6GTGvzG`5<XkPy$oU;xUcHK9+708e=jFD
zH}`Z+ZtmLM<?pxc+qaK58a}|@_Q#9^Wi7yIFOb=Ff4^P_O;4o$d$G7b&ko#(0+|WM
zKX$XcVDNsk@wnXU@AvEP8~uN~{l3|JRR8^nU445m1H=D2w{Atfe*HT7nR))bHLqSS
zpTBSYefzRE5&pJcuh?!r+|FPA<HN(>zhc1#Ly3Qn-`w0h*S7lGyqo^^f4BJFX4vos
zWMj_#eYLSW3Kq_<|F?6lb$Q;o^)WjyC2h>OzpwWD*Wc=Xb6)&>K7apu&`HQplNcBt
ztpB^6n|1%sXS2V(zrWvCnsLLKux-_h4F7h9$5k%v?d|oOXS36CckS=8<^J>EJvi9>
z_TJvztD?8(mHz$p_1&GFn`6<on0O!H1$q8JBlF&0uU7B<dM|KIPnpU)VBCL-SN
z`@JrBxnJ(S@;^U5o||KNdHemk+w*Lz&7QyC`#rAv=%VcF>q@`By9<(9>OFl`)$h04
z<$s`UTG%$7K{nweXy?q{&*!Xbf4y7|I{oYI-QC;u_x)Jp+|HM~Z*zoBRAl7MqHlN0
z@8@oe$l3S#eMarZ2()JIgZ~$<NeMPA{d7XP|I5GM@5>(_>#h6wbo#oOotM1z_m-Tu
z2F<4>CqJHd`}}IqToTB`Pq%N}_)+0MYKr?XVYEF8OH){SZKHuR8aSifJXjiFFknHQ
zM`U0a4V=-yX&4<nfhU5|p(S`w@DMrf_8|Vv-O345S{uziq_>DB8m?y4v=lj|5a{A0
z64<nQ0Sk+1t5kk(kyuhnub}A^agih1T3SsDG?dg<d~~|#$~@z0fk(u}(1?zXNZ}8B
z9adfz`|K~B+pc4ly{Yit!JmIu{W$#YyYBqTuDq&c&nrP!cEDYz(23zhRW|ezPQ?&o
zZ14!iFrNyBwkZ<m1BeqawFxn!pN}*NLt8)+#z-HgHZLCZ(+NE=wPE_!6GNK@hHpm$
zX*7_aw=uyoj>Bk58qIF7!~mfkM$07h@_w}79<AL_$Ici=n*gKjB-9~Sh6R|d!qLVg
zwib7S_4c~IzhY`W9?iVBr&7u!V}diErON(aSJ&^murvGmy0Z%$n=dW#oNSVF!@ymp
z&;@iWguW%}SbspU<O1fL=jW_muj!FAR!g5(nU=Tj=d&woqs{kLe?NC;XYuyRd(Y0!
zzP!8qz0YhjUFUYbv!&N#r<dQWRFB<VcD74YdzB{Q1|Cq=7cg030dvmrdG-H(-YLId
zyYttp)x}@0hNmBBV4P{19Tv4MXJ)tFu8i5w?LHh}o@t&R_io?scQI8jms&obQ*4xe
zZqAjJ!Rp~Lg|4QxtPFqd|6TNg!E{F6sms2VyEOgHpT1mXb9c(}*`G=_=l(+B2hW2j
zx@q<oEDz(u6y?mW!!#s#Ufwoed#It(3_q%k9N2I4{rxn3zt7!WrN#vh4y?NU>gww0
z|Nj0?zqhCI=VST*5#R2x%hwp}e!s7}&-&etRkx+g^X5$Uv(oIh`<3zU&vX0wl{XoG
zRDV3Y=~D^18>TFuoqO3I%_Cq%XScmv4)qwA5A$u>?Jp>NEWT$raDOtR)q%2{kB^RK
zUS8%aWtOw!=-atgrK@)BpCcYup~x;%a3E}Z`Kv3Mp!*1>>Bs;3&Wn0Wz?BNN7Yw&I
zUR@o&JoECh=)3o}WM0m>x5sjI*xFyS&-rdTTMVB@0Y!1cdNt;fhPM%^sj087uHJt2
zt@Yb2!B_v*pWZp!JpbOaogg)Ed>}md?jmM}58GGA@2|7_`{nZ5y#G%o`>%TUKl<F-
z6)SE$+d04Y@^rn}U)SB(ew_OC|9q#v%F1)kkK3#4+&=4Hy!PZjU(f%CM19)ru9xoS
zPeaqqPk#Hl;}Rr{ZijuI-(Lz2q_f*<zs~P3-JE;-@?$SZQpt%vTW@y_s`A^_db?|9
zx8?fxYs1oz>HnV*P?fjCLG0VxY;D&;BJS+AtACy+LsSNDu9<eRU4-ew^;I|aRDOQ8
z$eH28_LmnIyN9ifnmRqcuCn`f`uTZt-`(B)eB*Js(-+<4|L%OgE%UNk?yW5+ANSku
zJNmZ#US&EPpUjNuaaEeX-)_JEd|vhYz2Bep7@zy`y9Q-vNloT5zqzw6``hn*A;FO2
zUc+Q{plpqEJ749qndzS%w#zR|Jlqz#{rr4;dr?u*mlqZuHalPYZs+rDyK4Xa`I&iP
zf#a<$nZe)g%(Jaddv#@H=G9eK&FnR0;W5I%(2x`o7WVAx^?3jD^K85Om=2U3Q-@_*
znW7VlKX0C|o5roTL&0-X-QQnZvajpye!DHY?(^*XDxRPtoz}$eHd`CL-EXc{=_D1<
z?J$0}U$5AFIKXWA@5kfGD)0CG&bzfGb8_6?s;Bp=-|If>MxA5fN^aoWFxUF$lgXb?
zDEB}4^ZC60>uYO`D?dH?^KJY7vu|#0zP!|Xy2{C$>GS7m1}}T^^?LmIdDZV`s({Xx
z;<Np7Vb7;i+B-iS;=a72@Nti{xnBOBk8WamF*Ejlzqk8@K5E+5Z~!O2`r`Ap-=Azc
zt#|s$%HYq-?f+`Ny}kW>kEHRcW6wQ<0s|+?mfc9~{#<q=vEAn9lgW~1IT3j~pH2%2
z3tJYv+;65)YS%~9NyjTeb{MxCsGQ{c|636$ph3(lY#4PscnGE8?J@QFHIt@lho_yK
zq#C)iDAn%glgW#eVOi}!*~`oR_GiDmy!`o+x4x+C(qlI_Bsx#iiJTO=I!sh{soSn^
zx3V{vyu7sO`~T<l|I*j({dOzMhb7=QC~mi0_B&ns{cd=P2*Zz4@FdH?FhBq8t*tvh
z9+NKq|Mz?P&reT(zSqC6t);c;`@QPtOD6lB`uTkR{MholTMsNbx^m5$Gnf7C=Yq<R
z)nRMBK-vBJ`uS;RXDxMZ=ll7teE)1VUMUgT%>}c~^VhvvwrJ6!7Z#?+j`d1^ezkgi
z-q-TwrLV883|{Vc@gvvgYti|sA0Hi!{`zTceyujB^t|{ntLN+M>*>d3%XO^WdOw|1
zpP%ye)z#4Y{8?tXv*woFTKOU(=lHRH`T5fMdkjxc*Vni5>fKWF^AqTv8Bjv&?qiDQ
zl&}2~cx_$m?6kA9L}giT@U4yCZ+Cf_@99fRy+NsCPQf8gPzDG)es-R%b$EPj>Ab2}
zD_`;NoExz@%{Q+4?N*tB1B|Zjj15uwCnu@ye7o)TrnIxOO5WeIwf}LDe^cS(V=-kn
zQ+Iy9SG~FH?Jb#-3ywcu`q$5D=CfMyVn=J__Pp3@YooUx{XQ8~;|lxROx&7%eOdDH
zzLz&PCO2~4oR@QBgQ9%hkHoT@snZuNzG9&rzV6Jet=XH;+x@P1->47rapmu~+b{1b
zef{UL{lDakg<R(4@9yN@iw_K(IJfMUrf$@h6M4JehWW1S+Ftqj*_$nw{dT@wHruG;
z!-GYSuV_e{<#_!4_4V`S`G0l(f71USR5C{@y<N8K#Fdr7#kVq-*S`Dv{cd@@pY_`<
zId^t!oHhBXO!l=kC-+o-{`Bp3{_^zm^FsIMZ_2#9?9B$}w?Ac$f{r3wZ@1j+-@4lq
z6rC@vkKe!PzO`=D7LCbjzNdB+K3-)Rd3Iys;kGr=+x4v9?<szDZEbYP9I52zbIZ^5
zn%|qj$jl}p%gV5CQr3Cxat4MQ=l1;j_4?(7h0bohQd85;&U(72Tkq5i!{nmdx!Y6E
z%rM;fVo~>{HIbWp<ZP|(|NFN6^RL(I#btNi>Xo;*(~a8VG2gD%DCtOt&s-~0<Fqp%
zUl}JI>5wVEQ<!;ikt^u%!$ph3cK1q~r+s>I^5xy#<)Fl~tMql)-w!)8FE4v}b#?f=
zU9Z>W+}N=2#fsL5okgkV?0%cwoze_j3-HDy>xxG1?QOo_-`y=fV|aW?_4jw6)Bg7T
z`?~)5n$71<Wv|~GR&ph4Yr?^%lDD@^&(1dYe}8Z9<^A>l|9oh-_xb<t@8#9u>rL|S
z*|f{oRXjUCKfdHj*7nTH%Rp|v|NGweO~>V`m*m~uwK9Hx-K%SBXWM?ep?qAfItO%#
zR@BdDA8&2VE`B;Sd|B@8ZJ9SVBt~t|oBQ|seS1&=d$^5v^ZR|jpLJ=kJ2C&?m*tBV
zi#?i|KJO$bYIYVs-;#6F$aj{B=jmy>mv<IFpHqC!a;9;*-$lXfE#L3g+iQod(Xevs
z{d$0z|H%<ye^4&_@_GJ$8{4WcAn}r`q2Wv8_ExzbUor7mkK|<AZ#NddkTAWpCG+y7
z-R18WC13G)e7xU(wpnghU!bz>$0Nd$CK&-24OboARr>nU#^mE)-rhC`?V4=km7bPg
z_j&ftKc7y2wqMV>uj=coGqX%rFIaN4>cc_y%iD5qgIbiJI^>-7`#pR9|N9*+Yo2_p
zC(1J6_xAeV+kIvjD1tVmf>xTGw@o|P#Jcra;n$hv_iN3S-TTh0Tt08s=X2Kj`+uIz
zxBI^1<>lqqcRhccdV1Q@`2BS+@9Zq@v;B7CPWAh}^Q-UZ*M01cs$|@|v-o-1r6rz~
zUoN_z{<rA+p;m6=loJ!O{KD3N%A8YEG=HA-ubcFG{r-J#esgV3KfiA3{oud<zVAPO
zW~TAxjEjpl9S2o1pu8T{yRvI@%E?J3udZl5KGu8sFu(nreYL;Sj&um_{Bp_LIP=mH
zP@QS{X2ao4pfvLOny&XW9ZjpEt+#g+CbRL&&2j6MO6|A(=CQl%?Wf)M|LS#%>z|9O
zemnKDzrC$<8_&su?DBJr&)XEQzTOsJn!o>V8R#U&n7W@&e|}wGA6xqSNT+b|kB9Bc
zo!j{&EeaCW*7O%&TNC;7-uHde5A#{;fP!fL|3A-b{(L-c`F6|YOA8#EL5Ui)<9C_=
z{J4@US>~0Wo@~j#Z&&?pXZo+Nucw#3zV>u(`906+da;*wmA;m#c+i-6X^H3Bn*ZPL
zmft^n*8KjQiOTMIA9wvYXZ`-nM0dHFeX`ci<`kbhS^xKXz37ZhX%$~Cx`PU_C9d6K
zmJb@3L0(s>fBE6|{eNY0l}{!%35z|x;LLy4{{LtD>3@q~ENlmriZ^S&-@UvpcDK!s
z2hFbT>%`{Q{y4n*{l4guDN@Vx?(Vu-eBO3*-QQn}7UxXAwk9%Id%yhuGbbi0U*1#s
zS*G^O#h2ID$6x)<4O(GRcCYez)Ytq<P!9Qg&bt1gef;lR*Sq>+I&SCf&Ydm3tp4lO
zaO1>7Em=Mx#yZj4beP%sd`?f(4PGC&*Cg+b#n)F?y;p~=HLCcKApY6^)7<wp>gVnM
z*IYDYc%XecHJ^cDLEEp3{dH4#rOlo!ogU|Pdt2^lx$P+@Cw+Ny(^x#Fz!7xHW|mLH
zn%nvNZJ*Dp&inP{<zz+Ywk5&K{i6Rc{A=d7JMrh|XXCm*KX_!VOswDSNM_@ciAZ?#
z>hrzo_e;~y&-?kk{{QzkTd&8xytX#_>T-elZ!eF4obc=W`}rG_k3U<ve4f{0x8AP4
z*xb09k4Hge&usJjbKm#>|6B6vO6KaiXXoe7Z<njmxV+r|yzzOP$@#Ufqg{{xyL5J@
zvAVl#X-L$TjEUOo_iW112OVs?tL*J8_4zeMcXyR)Ta|6C`2Y7isNB+t*|8zZ;!kD&
zN=f6iC)1+yPVWErdjGT6@&BtXZd`rz_4@tu^6u_>+G~E#<NCT-&`GUpcSUYUaCGaJ
zo4fn{KI`)~pU*t6<9ZSvn3|gEXZduB&A%UyK_%U-?fLWjWUccqo}Ho@Y*hH@$d`9_
ztwC+YSJ&6am%Pc^n00lPe$5+p`I--^Y7bZEJUumaYuTOe`$28IwR<@P>vxN4how9_
zGZR!i#po>E18RnVDxo8t!rgtJmP(sug-p|po@V`Shw^dR@|dvoadWfR?NnRr)_V$c
z=V0dLWmjiiuX<|p`^{#{k4J<ruL@nwBVnMBzwc+7n$L_0ppfIY{Sv@u_v67LWwErs
zzrI>Nn~`jkeQnLEz+3Bfznk@X-EO_VzrNmnbR#^zcI!2pb(5Z~-G1*>BfH#;(A8m2
z=l^>-{}bpw#XCC+E&qPG3`%Uea^bJ9tz8{@{<wD7niG!fvQt3Uz5RZ-J6}vUY6|Fz
zy6yMts^9JZ|IZ}z(vnv<d}o_oUB&$j)M%;w_2uN5nZ~Q-f_tS*Pkp@}KVSaO1NLZ{
z-8DZy`OGj_c&(=B8mQb|>OCD)GKJpdk+-uEkFP0o>yen))z!5sIr}ziuvz}SIgZV2
zPtRGuU$ZOs{oe2A)^5Ky3$%l}J6T*mZq8}F-8zTc`PaXjaW(Hqhaf0Fetxt0{4&qU
zYA^5aug}}_@z|Tq=j|eQm1JH$?-0HwVxr$%tEa10uRCS?{Z4Sft5>DJ-)>KTbfnYr
z_nXa^H>IAwQ*>JQ<?ZeHudb||e6X4Q`S1Jx>$J4Bi;v5eKY6$Nz29`b*sQbatM`38
zCT;m*K{Ke)q3#JvJkj}kO+k$}y}e&9fr=*3U6D^tPX2r&x&P_*{eN?#wqyhryn1Dr
ze{YXW>6O5nrPpIGgPQvihDz`EeD(wNBz5BUSlIu%*dG)bIkR29&O&`offHy~IjA^x
zJ-$xN-|lA$sI)74duwUz?y{Lisa{&z+M5d>AG@+X-ah$wpKoev>N201lNLI+r>)=n
z&1-$!-mbn_-G3k2?Lqmt^7C2q$$y?&{@Qjs@3gyo?G$glohrZIZjT3f@b}y8&nLRe
zom}J!Zof1Ii$4bS{5~F+pMP$y^>a`Id}?@HWNG~4W4)mA>rUzQ*q4`=`xh#58zmp>
z0mUAuJI=-<G2z<UXm!uJ@4N4(URvS_Y69r(d@|_|s4@bT{Fgk{pEk0~o%ncMKEB|S
z{{0UR4;LR~6$jPmXUzBiJPT?Cf(jr|qHbhnPn#ZFrfKE(@Y%V!v!BnaUiWIheEpw~
ze;)GJ-*~mdH2Yf0t1ByS=I{Tz$~dmqu<Xr^n98S9C2cAS_Wi#5{#lE#--=!90~fo2
zTw3?@bo{eB#piVmQon+lY1@9x+dXHdaeCUvM@O$t$oTyQ)TUoPw@k~*ZEMw!hwa73
zB-58{+GGT3w)M-|UfPg&xaP;h_R616ryCbOI&!D@yzNZ0+$d0Gz38#nvuV+Jp8ayR
zMp;)@@W|O%^h%rSSqU-JECo&YI`EoSe|ys-VVE@g@n;oKb4+i?gQgw{!$q?uUF9*q
zQ{e1p_w&i0N8<Z`-1)u#+t&3<-TUQ0-EmL}bf@4j@7A=2e~;z=TY&D41f47J<;~5_
zZwigm&w(2g-1>VA%I}tjo2uzt>#zUw*d+U!PVuudHy=$e{J$HNeO|3z@3%egZqdV5
z@n<iW&tLa!%GLZIA0C1l^=W5kechRV<IVp6|3DUk+CIvC7D|WP`OojE{LJMM^;d7t
zheMzm2Xv@HpWUw)n~tBIVW^xwr_c?g*mJU4X!4;)J0iR)L3)DyZKoDKKDIRf{=WIu
zrN6(vzW#jO?swpB*u%r^&yPvx>nLP?&AzzksCZSg?a$Nt4fPk3_iMHB$^L5XkKIx5
zaQcjvw<quHEZ+ZN<JPyr6YBnbo?rhkIlkuOQGG+s+rr}B57(R4{`vw6;@aQed?&rx
zbXsqwO=VG^#iI@$DHDymyURh{;H<CuFZ*OHjefu1U;pgv?CEU0QYxNtbw8iZsd&_B
z`RRnRaqg`xGR0>MS(ob^<2AoCA#!ut(@Wm^Yj-sq1dRxSQr^Wyu9DVeIcuwZ|I9qC
zzu!i_=7VF}*;!Nb?(RyxyQ_5PzhAG7tG>L@iQcBuZ~w2N>~`+<Mag21E_v(w{{8iJ
zbHT$ys|t@iIXT(5<i&-OcXup})6cDunta79`B)FAXe>UdIz8v(j90g}gG<xddAnA=
z=x8lGIOS8`{=eURW|?S$#xFz7&F_{3SABakbM?AiT8G<swXKpAK|VUz%nlme^8EK{
z^H<QQ!kf+K?>%CgbN|ON^Gn<F?}G*_U0rq0fU?}HmCM6o_axk}{eD(+`J73N%xo!N
zUR(@4Ui;ko{>f8QwTr*sEx$gC@mKo$=yUV!?RBHK`RuRzTXa-39Ml~8+5i7X|El`s
zAWPrf-JSmB#YIW`x|)d-SD#%GxOmh3y5Fhq?(77O)9CH{@#s#?=d+eS9yD*R`1okm
zeAW2Mr&BZU@2dr!@g4P9^9ZPY4I1+J^XvM4KUY`Rb^HJQiYYp&YWZr#;!msN|E_wq
zL;l}~c90g(Io?sm4)T^oDQ0<hW;~x)t*0Bk?MwqBbJ5Mz=}Rj=KdbzBRD5-uFlbTt
z%bT0i-Fl@$v-LK8w(pg(G-{VEi+FZs=H&19s`I-Ut0tAayR$Q_t}1KNnOUaVpymsx
zxl#4?Rc_(^%I9;ZALh5W;TG3Bv-Nu1?Besb=CamhXH2ih1Z%Us`2765|6;e^OY35H
zgBmSsqqg39wYAXI)phNkx<!6-t$w!G|7fpyEPelkr~2HGZL>e0vtGZT<?3rtMyr||
z92ht;^YXIPTU#>cSHA%@lMR!Pg{1G1N`7-=qvg*hla2H4?AY`DUUl@{`wN}h&&;#k
z-H>v0$FEnbw^#lL<t9O8x0H{Mj)K~fpC`}%vt-sJ(fngQk~0mH-LBT(FTEZc9rNU&
zF{l$f+23v^Gr!FStH+|R`s@EBgNDIPa&MWG-zjw8RrYq*Rm0+EXHJ5`@0etI%F9bj
zw|--CiQQFla{2s!_TS#wtXi3!FaM*MNvWelVbP+73|+njD>^t>Sadm}x;qYUwTND;
zdv2@O`Yz+}Zs90(nbp^JZrjVZLP1o7mHon_4xTJmmMNYtDHi+f|4iJjd6V<)Z!_yz
z@6&a!Wfg79wzbt(w^6BnAKZ80LO@Gf+akwiHm>?`+v;yU!A?#bicjvkabMt6Y!Ptc
zxELVR$#V7T)l#YG*x0qD!hxGNZF*(%^7Z0=yF=&g|Nr4vza(?KU;g-;o13TV*|9Uo
z%gfh%y&4{|HEZguNtta&j<~Fe**R(Fk3DTWcUtcI@re7(T<dV(lRtJ9K4!bNHhOu{
z_5@~T<{oKtzRSz~!-I|f)%|=berBF+^vg%Z3@`5Qw@*7et95Jk^{lf@CAV~1-yUdW
zo?)6Trsg~Ah|J>U%iBFCt3AB9*!{-F<o0Vi4(sFh+gX*oXh=NVwo*n~T6(qU?1n#q
zXPFky+I?~5B462ni*9^6rMC6&xy{YZZ{28A)X?Zyr`a}(bwTMu-*R8pjLjmcpnjrN
zzpjSH5BA9!)7<;z7J5(D+d5C)G)rX7nl%sJzvnkMH=koyJImSXY{BPezBQlEnisvd
zEh{VY@bYqUaA06!VoE9JziRgT+uOr0E-p^3*SEB=IB@;Cc(=Izu|=-k6DCh?{`>p;
z|D}3g_H}f29-N{X{NUwFP6h)bqeF*UxgWlJ*Qe;*cHrz;-t=>G8n<pWeZJ(?^a&Fh
zG=rC&xH~id%nZYVqN1kx^W|e=V+%h$@mxD=N_6u3dwV4;i<aCubiUvIp9Hs<&Vfry
zy+3|=8T{t<cK)xgu0EbIiT{>CYwqc3x)LTC0%h;-=~n0c`SEdvO{LMZb91}Z{pV#o
zJv4F89-EyfUz>7Y1RV>My=Lv&wQu~c-%_!)jeYldf85?G#)d=h(|>(`-+#1Qe6_B0
z{_}Hl4=?eY{NTwG76uMp-qy{Vjh~&Fsl442)Z8&hJ0mg2s<bOSWUIHI-?253n^W#q
z+}Tn1<J;|g!>TVCJI|$OWp!;#KAv=YTkf7ktM0Ci-fmF;ujc0coB#g(n_*jBw)Xs_
zuV20hh=?o+eSg-_&~S!Dp;Amt48xwgPY&L^DY-fQ{Iu6CK`TWTyZ2vvwckECICx{#
z*Q{qB)6UMyeEMF8;l}24{%2=rhi8AZ{P4~C!GZ+}I`R8tw8Pg;v5nhRqS?OW)%L{0
zY&YwVA335Svv@7{h4eEs6o2Pmd&YZf3q$R*Gc#uxBr>@KwoIKWdTo6?e|>%ZPQxaJ
z0~am`96NSwPSB_6Q>V5@Zca1omzI{!zWV&Q&T{|x;3%FkgTvd~JLldW$>igGS67|a
zSr@;*@5BiYhWzz&Z`_FZ^Xv8cqU5Y~E8pGSt*oTf<m_d)E$3#_sZ(BaY^%l0%*?os
zS5#F!dUJF0hRvG~Ut1fUox5kT?yoN|7l+=zD(J+a_zEe5*8cu>bXDl;3)}PKOWxg?
zY5DG0uk@zETSrcv;@bc3m-ew<>E%T^IXOCO)~vZQ!OM8c^y$}scIzZ3Cxhl1<o%XJ
ze);<K<D;Y9R=v6!8UZ^Me%B@@B{lW*^jP)!`uksB)d@O}si^!*;ISh|Se`z8`oBQw
ztmEvZ8$`v$um3FX-@0{c*j?ML+1J-qe0?SQ?99x?MLB21SKV5YdV1Q6TU)h38G35+
zbiLTF3l{=Rmt2y`y|rbcu0znXUteGEsQS7}N+^@f+1a_|-5tr`<$j@--)?M7wy62B
zK`JP-?O3n$;_U0|BKFnnJhjof{M{7aqKj;zqM{j>m+{`YdpESt*VFUh*VostPVh3m
zkfxdQ^5x478#Xk|ojdo`MoCG@(to#K$6j9(X>3#XC*tA8dwZ*u&CJC9{`%UydbM^_
zQ`40>e#Uz$Kf67=f8EW^&7$&?id&yd=f}s#mCen?b)&aEnJ{7gnKM4Ev-jvmY+%T}
zz3u3Z!p9FDKMr1A_hVn>uP-YP?XIY<tW?y~<Fm7~D<~{<3<(iwFR8Ju{}=O6w%4lc
zO^5e%y@SV(v(KA14|FD(<&wwR%F4`_m-(*#`sdNn?vDrA<r5CIaDMpu^{Bu7-y@2$
z@mmtPqNAds*7~x1{qki)?eDUh4+q(QeBb}S_s*S|8qmGuLZ1?|vbz5KskxaP8ymYN
z_qLduo7>i7Vq#)iHF3AE=xCT38m=robK{1DsHo_xz9YV6W!vs3bzWN=&D?P4tdDj1
zyEUe>cQNJfum1J8oG&dcjbXuu&rd*!?Ckweh7Yf<YMbQT2>7<+*=`Njy~|y@#WXZE
z1EbCEZQ8u~;xb?9n~!H@uL@r7xAmBng+;>ib8}yHEi05V$!NHADd^e9o*o{P%u6o4
zohHXmPuHKSx9|Mfvqw))*H7*D_3>G-c=6)Cj5}Aq{`SkAGHu#1>n1ltBcn-Q@6FoH
z8_d6Mt><L5ieFzeKmRy8+kERg;{*0xU0sJjCFYbVEZW-IIk&cOK0emlyl&k$-M2IC
z>+PPMpU?l`?VriE)!!11bO_D~&TK1weoj$Ap<(BbJ#Mqjat$&rD7d)0XTN3o!pzS1
zq0fOsv1QNoE$f#GIdLeq2z=^`*qp{|V`Fn+ZM3<Cwe{hP7X@{rwmAI#^))aqu5Y>j
z{70{@uHI4e(`e0_HCvvoTWPw?cXr!@2MHmep%1(D_c?rjclW89(f+!>QsL|4jvnik
zF8uJoaZUXGdC5^<iwX-5?kasPARy52?Cfmg<F>WGL<9u|3rb5vldb;Q{d^)^^ZV`g
z7k73V+x`2I{A@>j-A~qs4<B;y@Ps5=)w%UZG@52#J8<X_)8pg);T7&@!q>+o-rklQ
zvAb;TwKoZT4Cl_B>*(k>@Zex`VqV@kneT6I8n21pA6GVAI@e+L(hZgt774$<y_K*m
zQsLp@nejMoZ&mAw6CNdRZ-w^0{83a?bg2A(ZTqE5K@w6@TC&<*i>}>0xhwtrypI0<
z^_L@ZZ(U(zc=Pt{!quz0eP^4kl-Zqg(`ao}!@CzRI_AuoW2HN-_QQk5FkOf8qM}28
ze}BKYIo*G1^5VsduTJnNzH$4uv%mj(zwUR_b)%Psa$m^YEV7MH*6P5OD_i`^)nm5h
zNQ&u1ENBb)^Yz6=X8XTigo~4Btc%_K=uj*7hi~89A|htYx}4d@Z})>?x?b$6tvmP`
zUR_<?{`dFy!$*#=C@LzJ-g@w$HYqEsYtJ5=*5h`6zXY3PUSer%Z2a)y!-3`V>sCE0
zso9!ybCTu7y}`@<c2s;++Ou~rs9s&@+`h_EHvZbRYaYJ7p%rUfyTv;C``hQwmuKUV
zX!!T{_i9Vocr`V(BJQ;R8CO;WW?Wjr*~TZ^b#HHV_FYp~>17*Cb8ZCWZM-Vq+R}31
z&K;Tg_5Up6_Ea=FHnXj?l(h#n0{r}@+2-BZVfeZB=doUCuJ=9v_GMpPB`RlEqfwoc
zlG1YGghy-ln$4RwO{v@WXJ6)>9UJe&>Xw$4E?m5LaY68+O`D9C&R@6>G*8u)etzCb
zxz{gWF7%&ox2g3-{gm0WSBFY7nP*?)@t<ci(e~Q)>&Jh5d@QOLaQfW2b)TOdeBbQW
zE46ULhJbH7(gHWkn-{lsV`^$@)aHZRl;+KwcVln$_Cvk<ii(N^Bqci;nb`_Fj?G`b
zT>aX*Snlxf@Gq~g`@g%fGI;rhvbRxR-rbG<cBfa`JRvuC?XxK^mot)&uhx!^z8!Ub
z>h$T4UtC<Qp|9WG-`{`8H)PAf1C7iZQ%{Te%(2*b?d~4^_<cQZZ*Nz&u$U2SRhK0;
zPhCyz(5+ihWygziV=C5pL`Kd$l(%^8yZih56`k9zWUiS!d2(27xGN}2eqFT93q(70
zv}IjgB^neIw4v^Am5gnb$ZWIRNxO}m_EvqpurgR(CvK0#!Gi}guB;F|zU9^TqvG)k
z)~w;_7T2HlHtFVyK;@fEe`i^rl#-HqWdHvsKd9k3ukdQt*;%F&yq5m>aG3w&N%i>)
zs=vSEGS~m{bb9=P<;$0smOF9r^SftdY5n>8H!(4B;fFslyUTcQ-n>~*QsPokVe$S%
z*2a>TK`E)JiMO_7&akaEyR|(({`H<ad#lCs@9jCbz_EEl$;+U76R)OyeRcK4-QDK5
zwr00CG%!3fEq!yt@WqQ48CMtCfm*R3H|^QGH!(ZA`{H7E<9PGxZ*Ls)^45jbO8)ry
zeE#8k_vG^L?Frn;U~6F^@&DKL{a2>=7<()Ynqyxt*Dr71wsh&zOB-daN*o*<8fH!U
z`25L}mbupDkIv3EFP&Ahz<0K|g{5WU)m5PyIyxbinvu87$_k2#4$U-9pD=s&>Y_#a
zCr+Fg=F3)GRCMUw-Q6!|1vQv?CxUnjo!bLKLzkMCA6V6`=-l>T^Labxm>8Kmckhb!
zWnNz=D<mZJ;PK<;=<RtcEfwqk{`z`&SLy2wd3UWOq@}N0>2WZb<=$c`E-u!I+~l&_
z>{ekx!GTU;b%XMEF|Egce|_D)IsJUnfd)nnPR_t$t9^Iw+$s3+AyFrOU(Cb8?Ck8A
zJr#m~e|>dMNm&xMH?QjZyI$vZzK6H-_lN$d%gM><dGR8HN79Jpc%SU$RmH)@z8lRZ
zy}ZBQ-fzBLZzD6i(fZxrMRR8yN=r{~H%>p7@a)V?uKs>`dpR{VwI5$D`%j!OVZpPK
zKR&ZeIL-6#g;?t8>+=T&2LAYTTL0<<ugw;gmM3#nRxDrM{_*i~ZJFQq|Nj&B^YeSv
zb!_h1wQKLBX)ar~?2Pq+`@2fLSBqI#Sy((cHC21laW^-&Gw0hUPnsm6mscHM`u?8m
zbp7~gwq_<KDS30m#l_jHtE)?0AD_E+E$m(XNj2YD2Jdgw{Qj1^cGt3hIX5?@7L=8_
z^~>2Bq?{1oXll5;-2d^Noy9jcrE<FjrhHrY{cant^o8B!`Cs1Om%n!H+NRc{FJHc_
z`0+teM^`sh`ZuWNk(87?b3eO9AmP)KlRIjDZpyj5tgDM_$F5yUmX?x>G!9+4BC>Jg
z#;C8qR~?(A>MbBE%WG|IT~S@_EWna;XNTbG@b$-DUS582U99z)+2;M_K3gqIUx|q6
zMzv^%uRCz-mQ?iiyrVM=lQSOvoF5V%u552F?>pOUs_pdIv%7O|Z(F!$j|?Lt<BLm6
zxsSKJ3XO>9Q1hL2C3DTnm6}~$UH=}s%+lA_=hxKK)X>rjx-oTYu5d7@gZaNpA?xxQ
z32-g!bT2V9H1x#z^V9FL9yoKRN3EJ!Lr>2wBt#@ADConNm%%rGW?o#xDkCFvVST*)
z+UPm_4E^%<AkP%MxnXEi|8LK=!r<Uw78aI-dwVK3Y})i_!i4p&US-Kx6fn5=%efX6
z8O^h+?fUeo=*s%|_;0s3d3cU&NIbmdot3wT$AO8;?lZ23BqS)r#Kcq_582($FQ0UA
zk?W6_%jZ9NXApS!#tn&PHr_*jetu3&PCl%tXs@cOy6J3CP;jtl-ZUWzi4{|4F9j77
zii(OIy}hoXp;Pa))CY<vPV{*2^l9tU)6)-Myf`sA$mt$$XJ@BH-5-l(esi_VKRQfo
z=a+wUu$leE<>mdeE`6LjcW$qB`MU+_=jUbI*s$=_$6H$pzC1lWz2e&&$u(=%WZg}5
zz8$-(gmeF&Puyu|W-Kf!tV>H%dv||7zr4J>>C(rq-`(8}s_2-Qm=cnb7M0{ACMwRe
zuU}_c&SX{l%jDa;yWRQw|B9WRZ60p*?O3n$j;gO(z9C@_v+uQMr=+Gnd~mS&!{^Vz
zmM_cR-`l&R@G;xIzu%%wmp;xu-X{y{1nI@^TT>EvYi;y)Pyw*qfBvFXtGs$Se|Glu
z9eZ<g^TxWrRXcX>G(5hy=BLo%cK+kN(&jVD%j@o|sH!UJ=<pOjJJYy%vvF}uXs9Tt
z4JB=!cS3hU&HUW^`()?Wev_OuY0{K`YyaNP-w$dnpPy%Yc~<tT6BCs|$K-zaeBR#J
z+=sDYx&QoAW<D3E6>m;F%;q!SPIl$Wl^OT<*%rs-<mmkQ`}gCgr`~HV&0TgrdXyw0
zF1|Q)b(q)jr_Y}!pPr`s;nOFl^>KTzOzB&{HhTM`UteF}*i*Ur5@_UT!<H>aetdkq
zHI4c5=jZ1i-`iU~!=iA}rNYX}${#Nl_ZuW0Vp+S>IU_4eYtyDpA@}B5>Fe`9KHh)4
zLr~eE=0^c2kS;It-BI_~s@Sov_tB%Ih^VNfH#as$>@K@+Efx-23$S+9rObKJ+w(wm
zM@Mh()Y}#t%HQAn@ox9~3k#ju`(FO2`uR!KEbmSSs1SH~xSio%-n*xdA2*+ztbX{!
ziH>5YI={JAtyfovKmPUgH7Gajc)4U-*#VG=hue5J6@Py2THB=X;NITqIhQ_O-j*Bv
z=XL!5NxAp-r=OSWk+YS$y*=N3x?U{E$v1A_2G!tmCVvVH329OFp7!9xMCFPvF9aDt
z?M>%)KG%$l6^DGa?uQF?vNS0iICzk8v0Lw|%ilw9l`Nhr<>=_Rqx!qvy12bu58l3C
zb8fD+vbHui!-Dne`;F7jY5bk@p;l?4$A<FvaXk`-PET*t{{EJDWkq1r@9I})XPbkg
z^f15uiNAe9u7P>;`nJuJ2NenR-C_%bAqB#T>US3xyKfZ}%6`14*y*2s$D)oiXU;@j
z4|#oUt>Q$FisO&_%)A5FY}g<GIuGINu8rHbhwog`D*)F0sc!YUb#9)XoL|0v4cuQ>
zyEM7GyL;mF>B~)L#|eBY4+#xjxM71pTU*<O>(|4rwr$uT07`DFtWW<Fy|pFr)avl{
z6Q)gTo2DCm=*$_Pmp9Iw@kvQZ$vE4V-ty<NmbNx1#M*eJSG{p+5xA<QrS;*_QErp0
zD;#WWY<nITga-sPu=C3;*tJV4_tuucof|bT#<};)9lfy7`Qpl8b&sV%piYdkTTg>V
z7pSHO6}vxv|5i3JnNl9IwY$H+efxIvo}QiuFJ5%4SfNo-Q2}b!gs+QnJl-e!@WF!y
z+v;y0`c{>-wY7D0bWF%SU|I1Y!KUU%z_toA8ylI`;p^SX%FNEskXpEC5!2PHSEFu!
z|Mx0J$WdTR(ZV%Tr;4ii%xGZc7Gq#A%fHv7zyFVrp`qc1?b|`No;h=-;MbSTbDme7
zl_n;9d2#W@#l`KXHhOw`-q@VpAGR-#A>rH{%ZRO6qM&Y<xVZR_A3qXqZ_70>H$T3s
z^!0~7KZ|p2Z{xkYtMsw#Q~@WBO7)9OCEyrwy2lt67B<0a>8AO9bFDu1EeZVg_BJ~|
zKmXM7846F%$L+6MTcotg%*)?@`N=me0$Vq1+SIgrxAmPncUC;s*pPqUZpZH3hc8{4
zR4(#~Z(-eGH`#W9MSNHCLl*Zr|KodQk#nVxL-Cb^th?zeizn|F^g$H(_4W0w2wyL!
z7qg?GsflUE?AgjzR#I_saVJilYTCTnIBZ=^XW(MDkA17k_Evv)^Yh~q5*7{&3{))7
z(~H~F!N|<^;6NkuhmRj0%7(r@bLNae{yiH|nG+fsYG7=9SUkR_G4=E`Muu&<x7##>
zmn~Scrl&Y)pO?4y#QF34pPiiz>T_0qfA{xk{o>x)PbDQJ5*{Dxm9Q?;VK{L9JimVY
zK9`sn83qL<B_{9bdaikSdgo_kIZKOQiG6)-?ZxH(@;UeS$)2BY?|yliZ|eTlE`crW
z?d-csUN(Jwef@JEsENF1a!Dn-0%(j@v1P@x$B&!2#q|>Y|NASz!l<UER!~~nx_h_v
zk|51p<?q*-mMaCOJUKB@fQ50|v}r}$U#&}C9I%!u4_YZACnr}>Tnriz>FMdIaKEH+
z?AWn_l9DNV(_&&{FYYKzzPE8l_VsnLQCl(;%WX^F-I-ag)BE7%OU>QOs=mHrb#`{X
zH_?PGciJJdq9-0VUoWfu{cX?Vj48AFJ|E_{4>%s!V8th0Dr5G_Jm*T`jTMhKTy&B)
zdu7oTxIeHLDg%l@kWAq5#KnD!B}!$ku6Vow%mKw@uT@`>prD{d;UkvM?^f*Fw@<>N
zKtaua-kN7AvlP|T*g(aan;RP!7uSd9)iXGoK5Q5B+V?u|{=VJ~8w_5&c;OKK{q2=s
zU0qxZ`Qlq^KOPm2*qGEBrsuG~>Z_KRUJOTaa<Yhs2tz|o<Koq;wbguQwN!q7mid&a
zgq@uol%DPE>_8bcFeavlk(up8UwTT)g2>HjGQyukrKP(kOc03KTP3<k12k3#s$=Tv
z?3kFD4b#ub{P^|jQ{PIlTRUd_d2e85HceMgUtixnCPwDjxw+cbar^6Pr%apnscU&z
z`MWz0WgpI+IC(O2dU`rTzPS-YL-_hQ#){jypuXo)@9CGo8R<#>B5P;~`HAo3>C?_N
zH8zhPKQ4TDh;_-5C7>dQjg9Ta)z#wX=GmUMRuY$#l<es4KHSPJE+8-8zh#RFM^l5E
z@2nGQ7d)2+Sy)+p>RVMNU;9N+FMeOorAt9CUc5MP@19)H$`CWnGk5OHDR)^nO*guY
zTU<{;QISzqRds@g%8M&2C%^gQu{3B)#>J*`pRKpI=g)srwd$u6sF}2G-MUSmFD-WG
zzd8N=ts|E&3wwHcYG`XWuUn@lBO{Y?eah_F(z8r54_PajgQ|Q`#;pGS?xM;Sdr;Tn
z(&fw9fAfmU%iXW9i~axU+|~EWpkx9{6NlaYwjn2$DT~2{0J0Dy{RH-5B&oo4-qZCy
zeEM`~mT9(#+<en)v2$~++n+p1F;#z@|Mk^XP%rMxnKKs_yYtVOF+)RUd-{1fQ}xH^
z&z#}$o~AP~*C!z%p}}{yS>l-)h71k5(c2P^^+;|ynsaMO;p1ZwJBw7+{N`{3ihwGb
zH@CKOE4%eDFu1t6CH?yHGHR>FmSao3r$2c8x_i<jp^ilzjm+$imd~%7B>VoxMrBZD
z{`>oTvCm0&A0M7yUthQP$yy(}eOr2U*xE^VdnFh^9mJHBmc{P<MSfl;o%{FOPntY=
zW98?xIaZ}y_iMk)PMSP9b+$n5*Q?>6*6N1`2bs@#b}rkvX_Heyfx*6izp@z`R<6{1
zc6N6AOyhJWhOjjepdxGGjvX`7eLywtTvymEPo+C(bV}WCjzdL-1*lQ!D3G$7Cwupu
zJ25v|R!mm+Kc&_k8W#4c@0e?7sOY-*{d%(n${rqKee(Rdvj7WdgtDN#+&v{l<^7D9
z(C~0&RaMt_GFRWMy1mR-ddbqIg?=Z_cZ=(%JXf`|lRJ6x<cc+GS{fS}<M!2@w3ZW}
zI(6!fqNiPN_JI0-tgNg8ER1h&Z*Skd+uAJm))8wpa}&<cjp^s-DeCF@mBr=V+rt?s
zl9-Xv5x2MM;N82j|Nnj8UwQlr2e^1SvAA!s%vb5BD;{5QlXbTQr=XS6ugp&c9-rtA
z7C04nd?lz%xl$;yxG&iJO5v2neaih-eMMkauym=+wl-erBv8_@C|q>t@x+M}XP9PB
z3)6D|jYs6<<`%xXqWR+G%a47F13@L^+Gz8ea|5ftzG`LTm3r{y<z<lP`uq9k*;cph
zE`ML-x2o>$?sE6}cC{Odo_aAf?A>c?Rq~?2xt)&@G*dKT&YYezXME-v?mT(!oLfze
zjg)yFPkw$rM-u~shK9z0YipxHwZYmu4JVEsWnHB4=+V*cijR+2&zwE`RBVBM<R%tS
z0T>o0c7H)u&}NNq>sRc2w&mpA-Q^!Iy30R2Ia!^dL4W_Bpl|zPVq<xwrKP{Ty)Axw
zd;W9D$r%d{9B>E;3p-`T$jQZZXlL<r&`3*2czE)uDViHLZ+0#zF?qhEMZoFA?oL?C
z>{FkIxA$b<kk0;o_p~%MDYG1o^z`(bdOzO1d$%XK2s8$H)3U3(`*8mLzihIyvL)~D
z$#QaX?s=Tq($&TF=I(BB?XWcqJQM4Kj3Xca`T6<A)@<>)^Z&p9e!qTtY;gLyIgV**
zYG1y7-CERM?y9A&y)pf~+^%IJ3p`ik96fr}qUwvr-aH4{<?B{FUg0L|ZV0YarYr{6
z_`O!=qOat?>a*(00!Qs(Nc=-;ojtCy%iqB?f$Ezni~By?`}q1A*8VEdiP+%q@Z-^L
z@#L?su7XBPijDq(#<NYcuO(bs;<;yW#+(ly3S3-V6m)fYzrMbH{Nv-}py8tf2M#ba
zDJ<BsMZ~)7&4jyxv9r(2x0l~t_SPvaO|7J~bYt;zzaDvexoz9FF*H<vf0y|3(o)dX
z9Tw`Uvz9nEvw^0;K0ciu|LEuE=NY%Qth~eYCHMBW#8Xo=HMF%K&k3<r5%QdS>}pN|
zgF|+GKd7s3o_ELL@v+|2_r?cq??3H7*Q)j1-QACy`RyLe2&i=lJo4)5>crI4Rz>GF
zhKg#rU*FzFXRq11)s#=(Zq2(6DbU;pJHOnKU8S!B_Se;>q^2G`ecF55$=0b;Mg8Vj
zG=kb@yx^9_;tWPB@a(VR`vx)HC<SwKao<@cjk9M<FA35FH7QD8hdt+Cc|U!3+1p9J
zPbxn=V3ab+P%wXZ^5#uRP(wJmC^#&v&3n4u$#a28NlI~ht5kO{ZVAykx*~9K#qlSL
zwrmmM<mB8`JbB8Lmh0=|7uWv&R#03#d9J*+w)VZitFPYO-CZQiDQ{cFqO7dEW5<pY
zYJ%ThTy)MZKL)Bplady_`4h9NgcH<?dVOte>iU_5kB@!qJIU(n6so7J?ELPJO~nU?
zGIzt3A*bf>e6<4=3Z*hnS3K4L*Ce34eq+UB4R=|0xv$b!AuL01LlTmhKn2GqNOFM`
zA)tndOsR~Sy}dnXu+Kd2PQ%2B6Yp$Xv`ERq!s5WSYhr<cfpdgDJ%0JJ^WELu$~HE0
z%BPe&)zsM3{rTwr;>C*v_5c5U`10k6Y-jhUPemePVv8~_FWYo)d-iob(AcJxm6e1+
z0)v{*j02Xc@t}c%!bdD}b~PLi-a1|Q_xJbW^z-xPO#Yahl+^U|^YdiT(3bcD{fG?=
z(cAM}{rvczFL@Oh7q_m+CnN+sbTeg&NJMnBvaxY6@5v4|>!K$dZM@Q;_&9j-Bqu}4
z_270s*$XQIl^OEISH<rvVrA!-b4f^0IDbNF>84FW*Vn~1_x16;dHWVrt=*f*q1ZB^
zTuj$N9o*P_BC9abLt&x^s10Zy=o%kCzucr(VWP)^#fzH{HnS(++LHO=;$rra($dP~
zmpIOyJLlo&=T=&3`sU4>Cu)4NX3zfIcYN-=d2%j+EzQl%Ifv$iXtmCqDfvDl=4woE
zU0vOa%ggyeX{_X>lQ1Xaj-5Ln-rAbIV#NxFc0SoB>omE!x$k}4vB+~p&f#``_nI1;
zqN1V;I|`F;{wypnci*0OcgwGGF>qvq+mNU&1=5<Got>Q@K74REJxv!>Ox&ES2by0l
zdmELKo({@Od#k=aniKLj@9r+v`1tsi_V(l#7Z&b$Eb!^v>NRVQytufy@WBDbjzt=`
zb5^Wb!_%aY@Z-b7AOC*8U$}VjVat`jcx5aEZr;4Pqv~tcTGkh=tgJ7ttQ5AfwcVJ1
z-|k-EPV3rVCZJKcBS%~!qN0>kR9GG#>vi5+^|iwN@uRD&!*A>=)lN!Io;Z7U_t)3g
z4_~|}$jZukV}HGUO>He`q{@0(6blQ>f(;u4o}ZgL*>-t`Gy8+LYR0|N=EpWBAFpsx
z1(od8eejZ<@5I@&Q*S@~d#qRb!quy;+w<<G2n)u<#wI2u9kSLEPd?svw3S<Y!n}EW
z%F4<&Wj*fPz5DRVlO<QJBd+;yadU7SI4)n$vofUX+S=&PeM=2{dU^t)qPqC)emIor
z?%ch5vF~iNJ&OykE_7zUv%8$1jg76KtZdp`@$~d`lZ*=u<u>cG)~!6)%zpU(efgl3
zB5R|zK9coTzMvAaZC0_cgha>5$?A*4*T+RwhflMIWM?x_hRugG{1U-+0H{J(h179?
zbUZ-Cy~yIe#ZsVN2#5pG68QGb&CN4RGKDs6+N8k2)Udsree1@J2bcNIe(?6~SxZIv
zySqxA>+0<0*;FzmCnrZlMO}-M(B@!T7rXnIreeMSJR8TD7@4BtV#A6L30tzRa$UU&
zsytdYZrm8Ar?M_EFtBmT6p<&-o*lY*Q_^>q$wS%B-L2f>Ngp2_<>2E3Erv+Q&E;hP
zjk<)bjcWb+`ns}-iO9l*3+GH;b-!2I{K2bNUF%|ZC;j;FaE4W>mY8l7OKokfi;K&G
z6)QMAJv}#U-TG8^>TG*`oBz*d=Npv0iC7z3!N*`}X$eZRRaI6|+w*$QobdrID2R)T
z6L1xLdu!`q&_qqu*Q|SiR~Ln@4g)#l&d%c0^Bct$w70fC-2Hyv;rILhpHp7tw%{x`
zDBIWbA+mi)P*77#3(Jw?$3cTfJL>=2sR(guX=zosKh{!LXD=))+)?n5>CxlIA8+UH
zcMJ~~@9XQE;I)*4oBOeB;M+-)CZz};0yX-ZnwTOYB2L_OJ$UY1U%5}-s@1C}&Y7cA
z-uLO#rwe;3i*NocEG}+tZf1VJB5V5m`TD!3J$n3j;+#1=jsh39W{2Ob{P_L*bJ^gx
zS@)_RKYm>J@sX>DxcK2yr@Y?H%DTVL_Wg_)P_l7u=R0}MJ1a};)z#JNzwd?=$4QxH
z9kE{KwxDmZMCqJcpg!jQz&@+KByhuVL*Q{xJ2B@<VHPAU!3+MwZnDesK&nCQMo^Lh
z*CVpa^Rm{h|MI1T!Qu9{+>4-AU{gu%lV{JumjD0%<41+*l8ZWvG?K2ZiM+8Pky%Sy
zTalwF=VEeTprDSf?#7CbNj~%K=9Y)(fd>3oxy2SNSir!L@?6c{UcRiXEMj94t6RU^
zS<9urwq{;t)6>(tvAcZzp~sGnjvgK!4sLF3vnFS@Em@*c^YiKSt!7&b3JO3C#fL9m
zoY0hv4-5>9*peYQY0{*G)Kt~zigl}3pSG4NS9b3^a&oe|ps;Xr*xIOrckaaGE&TfC
z=4McPcFD43MSiQ~K#iMgYonjui;v%5*IWAfTH=uo!3|rsOtIZx{M^rHo{i-C`2EiW
zr&{0I(;(o)@iQGU!ecmd=FE=%eo+4w6kF4#u`w8!n!482**!0rrL3>d|Nrm%`j2n7
z-+y#(Z?ymmV`ymTp5(&v-`{d?wzTZnVPRAGiA7CK?aQs7&DG!EfjaiDudhG;_xE>2
z4kj&a?aJei)@|7$(#|h`tV>k8;Qzl`h6}&4y+mC9e7l`rG`Y06s3;*Vtu6ihypMgy
zWqqAOL4$+h`f*cyXYDR~E2X8aotT~u>h^)^jy_PcUj$T&d<Bg~Yz;gPO$Q>2>w?R{
zt;fZn+WwUVvQ!_2l;V^B$4*Vv78DX{vMheKz<<6SXuSA|m~Ee=G26?RFQax^)PH|>
z7c}U@#LWEg?c3f?Vf9mUXDd3lE!eR`V!8kPXLCaSzPi4?e{1&jq)$&ya`orm+QMm^
zcILt@)`g~<Hf;ipM80~J1zO`FU-N<Sy+_O(t5UCRAMV_`HA`%sHpt5>gO?{AY+~hl
z|7CCG=d?33joDpYUFS?*)xL72rkGAd!1A;H*Ve^$yLOA6G~>ExwxyC0wD95lqGO<z
zo`BN{>x9qG&Ti_oxq0)ZfUDrNY11ZnEuCRmthOXb)2i&v32U|RemUDovp;}#Ei!;w
zpN0ts7(A8+o#Xtet*`H1S7-O>)29iuXLmO>F?B5JICRMA-o+i&e}9?k#qLt6=2cZw
z1GV;qI$2_Ol{}Q~pZ(=a$xTyHaq;#uXM8#qbu9Cpedz4j-g29FTH4y60sJXbrho!x
z>C&YFt`pTxHrjGty>Vj(s7Y>~$5UNhEg~ZF;OFP(C(fO73kws=ySL}0wUqdk!VpLa
ze{{wD4dCbmWmL0Q7XO=n`Q8mU9@q=Z=Nj&^?cjlfIsYBO`5MxZ0M!eiwqM!rZ@DQc
zDJSlw|I4|uB2Xqs&{tGavNLe8TjI}8Pb>cYsa*Sbu66mbmBGs`R37Ww*vQD&|1so~
zwQ6~Oetz<!Bb`OZWo2ar1qBak%Es$PZ##0dTYM(>1^u`^9NgU8rpq6_zq&g7$B)PT
zf+8X<8<USODt&z|<L)lg_YpCc*4B?tP1OeRl$4bX)6Ph|c=6&x-_k<R$_>y8lK$&o
zWO6SqbY?$t<j9pw#$P*&pMz!&OqX2pS?)LY(3Z^04<0;N@Zo#K?QOXqe|${lI|(Ym
zzcV9B@DER?$AeD3-E>kjXr;)sY18&3XYyocXaD*4`@Mjx;M%CIO(9xGr)UN%O!Z1k
zPd{!g7akZGxXDuzw7O-sd49n9I9m%VD<umHiJ+At>(;H?lU!t6{x0Uo(W4K4eSKZ=
z`5Et*uU{`NcIWq*ZN?k4QbbQr&%ns&k!<kWHhy`%-Of!KT^lxT1a%~yotw+OGK4ES
zI{KdA&d$ERX|chco}Lwdf0>q)lz^7w)O@>{KEZ2gl=Z_-wS}AR?yU|l%LCOdKRzaR
zECL0l$I>9sO4BIopHslScW|}7AJP(lM6t}#757)TLE~En++F|=K?WWV>;ZQZ!CD|A
zOtS7fzkDfSVP#d+)a=~p;VZzhHlktPgb54`1%-tZtJip)t;qfK<74vD|M%P4+BEd^
z!jhHFPMkKa?ZJbDXQ1iF*6zPs90LLbrs+nr85<j)nPJF$?b<bl2GD%s+gn>fEwg9m
z=byJ+`pY!q0>kxnv4=lAJY4C1QNq*HlL0hB-O|#cprYdPvcgf|!<(DNr7o8>-rnAR
z{Ajm$c5X@F<Ng2tt`EySXOeP4;LI#j?&W@So7S(_FOCTb5%HU6)A`{;f$6f#I<V|5
z<nqfGlEFKUReyZM>f`HMdHh1eWHsMOz7?x}I<@ano#>H}lENY`E`HOpsHn*4@2{_w
z?w2{1En8Ofe3^T{9BAzPeZ-y8mzP}2{FVf*410I#tkOh}gp3Sum;YyBSy@|SBjfvw
zJ1<|nSm4~wSF~PsR?DwxE=r6HH*VcJb*^{zZ0Vew91HcwkkJ)zU{ex5`)Yqb`t<ZP
z2RC<fh*oQ7XXl~9TOZ<dCweGwFr7MeYQgg5>eXkIx|CQP9YRB=N(E=JX=`iuNE)+&
z*4=)7e*WT?%wQLH_rs@8b2AteK5_vqruhEu?&CQje`lHJ_pJ<G{%CgozQBsSv~zPh
z<?H_lMn*=~G#3R#Ms_Y(pde#a!qKGQ;P21R@Zs56>5fGmiHF+~&(E{HaP{iG->hsb
zEDrJU^7el|Fu&K3O8oKRq1XL-(VP40|JzS-D}H-pBeSr&-;q_Js|5rE7_zgoj~qF&
zAa-{dsG=@=bEA=&oiE|U1jRjzSGiVJTF#j>r{Md$Sf80jtn=%BX})>$29)zcLP8Ww
zO+`V=iraXl6SA|rj~sD%@%r`WzO$g_dP07F|J~i?+J9oN?k>*{2@O@Wvzu2O1RChO
z>jEF>JO1S9Q$=%gaWgZsj0+1G-&?pGR#jJD>^)s?lV`C@+}Y_bTCQB3svQo>g5dIJ
zQDKIV*6oeS#~(a<*0#)d_NTr@7gs!<u)oQQPx`C$r}6+;{xN-J{$%|k@L0?rSy-D2
zG|2yRHMsSpSkGQ6^OT2&=fhd^`x#GT+yCpRsj)F!Sne;+;80RhGWT9_*0Jo#FE1~D
z+%8{t;OXh<i8(nv%Y0`msj0Een>Wv*_!$pqmDc+G|D?R9>phhXeS54&vibA#^UA8K
ztW&2>E$aUD?#@nTb#-;nbf>gg&I8%0vzIJUnPXAN)Guet^r5Vo+uq*Z!qT$P@7Vdn
z?fe(_*Vlh}cUKy;h$|;2M<j2G)87eyZvOfCSx`)jt<wdx9{0t|m!PRMh7Ab^nOfS~
ziu_i@ou6k5%DaXC{#4$4Ul1D`8xj`ARPp;eXndoQnf<~dSMGU%I~PG4&`AB}!aqL>
z&&;(JFMoH3kztN)wHRnN>il{4{dIpq#`DNnOepr+*C%h^cjHFHlV{IBojzIXG8a!z
zPQBP&E${B`UhFwpZI5zMcvKV@Gc)rqq38ZuT3Qn(O=`MxC&t3s`f~Qu|EEu$bgZed
zDJm|0`2KzWG~MV$t5$I>UAi>m#s<Z`eILq>C)(QD&QkcMZo)bBk0`9-oO26OaYE`z
zkJ!NdE2UpqtOAdff~r!`Ac>o7`xVjBIlC72EtY~dpurWZjkmY=nR&L-!OQ)g%C_!t
z?&|7#@a|pTnKM2fOM_foT_1w>3Y?y<U-<HpYRTJMqJ@QpQ8%a0x2a@OS66@W;>Cl>
z{&okC^-6=5golKOKfbWg88oLjRXaR`SzXCpX`+Jw%hK6zIhqurU4HM|UHV$gs`ORJ
z^N+^q=RhM~{|~y%($&@Fb?=io*v!r!5F6XOE%&yPfq}r=+uNVZ_RhX>BSOZ$PNw|*
zJ=elQP{;JbzS?RY2?K|+>G`?tv&BKv#{Xr0eSyp$Pbfcda<V!o>_Ef7_x4o&cx)Gx
zmX-!`QlG4~h1!$XPft((@a4-9P+zL<Z`Gd<hxt#OJjuxL;`Qs~FE1`eY|oQ@KIM;!
zx_a_~21Zb@_w@FDe7!zflu-z_7GOUU!>7-mK|RMKM~{BwJ#q6`uk^)5uG|*Z*2xbJ
zG=kP&G;Dvqyz=w28+)tGpSRT1{QY`;!?tb5HY6T4D18+I>OwOF1O+us(~VC0`|Il*
z;ZMb%pZWgy{Tnn91DYJ}?PdM&&D1#OhC$4Zg2rN}x;}Y(K5J`hll*%!pa#s-)6*IE
z*qZnC^?{bZS*SmG{{4QvdqIJLRq3l1P^Po9lRI#`*tqza&ypoe3j9uhGB0?ftiAUa
zFL*}J0y4IG#qF<~=_`v<m>q9W>lrfC4let_1;w|Y&*y_SE38<x>XEGL<BIC)({b8e
zprZKRy?a?cODubOdkcSlN(Fhi;?on*Bt9skiHM0QnV5)t{P;0y=MNc%sBJl&+1J+{
zJbjw`e*J%2m%t<IVs{sOc@fCM#s;b*qW1szb8@o!jg86dPR`DPQc_)Wt;?0Ht!J0(
ztXt+cw+qy0zO^ND)Bk^;&ri_|t~eedt*@_tXIH8BQ;R?mLr`b>&+dm`Utb4}vIq$Y
zU04@u-O|#M@cY}_8#{~DpPik({A%}k#silx3$G4ad#F=b9W=!@S=}ErZ?NUZAO2}N
zkxka+?-DL9as@U2|9xFwpLlVR>yFabV!C#qakPKak;YhCxy27%y(&6gKR)aS<DS*4
zwI@xUY^idYM^RDH!^h{y#l`NR_T0`+|F5sEIwvG3^vT<wGgP#nt{>ml-OZhMcUS8|
z=k{x}M5axj-hOtrd9lxl>+kOF7L<|U(bw0{xw&cSwVxBcmi~CyE^ndsMA^nh=HbJK
zGt6?O7A;!z<ec~8W4(d`0u77Z`-^-|_y+|E&6zv5@b9nEAHRQJuR3c}`N<`Fz2>Zz
zQ)S=Z#e(v0_4jwJt*xwadny!fXWl$>hG*l(ji65M^C>j}pq><{yg<zNf|JE!3Gg^8
zctj3dLx7v$pe9*YAgBz1Xn`gujqeZJ<rl45#TC1&<lw8Ts|$a8Nc{8TasSr3ErBH^
zCiCoSPua|yJh^$s3<*=UOFC?9Y%|RB<${8OKm$&jHW@8hwhYuGGB7ZBAltwC+1c62
z*Vn~r=;$1otnUBe$H!z5F|kL#-|u(-{OoMy@yD<3|Nm#6lam8l=A#q2iN$-G&cPoa
zA79*6nhjnLXOjo&KAC1;Tk+?j*sou|K$E;#Sz5(DuCA<X{Bk{acb6w0YT?ZCSuXkI
z>sQ0lS68fbuc$i&1`6`Y+x2vGaDcW7mCN)xLJJz6s0Kgq0@oAPpxXR!8!s~hM^nJ-
zip^<fC(NF``dx$+Xm|xQG_%05dBN({(XV%`U8}ok)21u(KFlpGEe{U!+aGy*d;7+s
zr(QcbIlvX@&AGW-0xK#kKr6{X4V7j#-c_Y{E?x|LDemxo_1fs|Nl#8p1kG0NDt{mM
zy5jk{xrP7#)$*PE!Oh9(czauJ;rDm3YofNUx@LNHdwzV(u9D7Rt9_t)|9X6VZyT>P
zsMCI9e|`Ph>%Ra0{Y@>ubjb`nU3M7Mx<)MyG$6$Rq-;QraL_<Y2zYD-+B!FTWpRpE
z+KlJq$&)*3f1B<5^-7yZ+Ki{Mv9ZYBxsB(c>||-z{l~MHEMLAj@o-y~kMlj#CWQsA
z-C`LxH>sAClvEslsHddFl$e<K;p<n|oE)8^q9V}Vsv9>Ve*FBYsH4O4`uh6kvcb8a
z$(&|({!e`iC)WM_8ZIFr0q(26-F`nyw*KoY(LaCwe7NjypLlMLC1~Yk`;<SWudZ<R
z%iBMbbxxMCtC9Ho`@4Hx-M%}Y!`H<$u3f9!#xLLZ^78V-=g;%Y$;p9cYo>&31~t$0
z_4#-1+_|+56v3aqU-`FXHmGuG5m;0RYWKXls{QQanKM2!X3SV&I5DmA<0IBvTeFYb
z=yfTbI(_=;43A<JRaH<w^UU>t)6;Y(PM&;Nab}u_x3_aafx+h;D_3fQR`eZnnFZSM
zHp8~s>~qE8Hr~LHkR``lW+@vQ3Z9;(>)g!7D^gc^c~z+P(sI6v`Ae5AQ?jv<VeobO
zyZQ6;^U3%2RAyXTGxN}Qk?ibjo61iu&PM;B#X7h_huTZ})td!t$)R<uKof9?c+9y{
zIHkL{_o=Mo;x{)pvsZt6GtrihoBQy&xz^de+B!NeMMXw6H8ocx{TJWaS<G%-{>}xm
zW+N;2odQSGwR?*DR;=J)=a&nq%G*+S@Xa#c*$<vSZ=YZPFY;YwadB})MMc7a2F4pZ
z3Kt*p-G9%0ef)m6&`{C$5>h9R9b<cbet!G%<?4I(>=6(aZaz2Hnwf!%iwiXEzGR8Y
znuv`~ng1*A>&ESoSnS^4wtc(#ojZ3bjz7%1zpqw9ORH(-%$avSJ32a^IDh{5_4s;T
zcXxMCixD)BS5aXB>a%I;#^>ML;}{Vku`U08-<vmYqV_M(x=<|w8c6wm0lYS&MZoDE
z<KF7;$L85q8-Na<IbKv;EGQ|-86O|dchaP}x0e?*RAE#1?vCY_{QGgeohI#zcIW&F
zEGskP;pM$L#qG06-kpe-N9KYSfmVKgmgTcV^32(@AAi5!Z``l0u73E^r67=|Rderb
z{W%LX{Sg`(>J=~k^XJbM;p^u~31{*l>R{C65+aN1&<DREk?C#-ZsI{W(8zphV`Ed{
zenI2t(W9GopX6$4cz%BV;zf&`@_H0F3`|Tw3ne!eJappI{CRtGI{&dg+3u>ZuMS?j
z7M3WUrkhrM-__kc`NM;Q8k(Ao3l}O%ndil1_bl>Vy9G3{yUcIyDVuxy>+4(p&dg8;
zjXV5$y?&GHi;EX8W?Wk%`Rm);ZqV4Dk&)2j<NeQNC$GM{yZrE(Gdyx~axX3{WX{RS
zNk~XgFn1GRk+G?m5bX5T%hU7V^7(aI-|sv<Jss2;_nfQ-%J&Qg6(16wJb40I))=*$
zq4v}i%^TZtr9o>f^!NR6%C^6()FR;YPgCd~BPgdjaVW0Rjol@}FK_2^exB{d+TUdy
zO${$zWaz}~5cu}(+lp1IF5S{+VoW$Q!w_VS-y93YYCi!MP#;T2hX=GI7c_HcsAzxg
z+&PP?FDniuuaDb%XkF~?2k+jkdloWlas2+ej-H;7iuM-k@^=bGMncSNJP#)H=-1cR
zgZ2nUMn-P!n`>Rp2g(=;2@8HTXELa(tIJrI`8?dXX_FCX+t&oIrCEMUC9~8PYTYv2
zktX!YUB32+qGWyS?lRYqkST|fLqkI?3LY?2eS5R=S;(wLYK)02&pUPcG^pAB=g;T!
zC(fULF55mEv}myW-JOGTt;-V<6B~P_%}>c)|8r+wt#tUhn1j#G&fZ#fxx1BH9CSxh
z#h)LBK|w(R($cFxxJ#d%VaS}8mbRnpt(2FS*M}b;A4l2u%h^7Xoy=`)Y`kRIGNb<G
z%a&c+Rs8X{U$nXM3T<s|ZBWBdO-&6nCm0hGGhyDmzGim*tiO+n89KVVodW{}L3!lQ
z&tlLbtdAc*Zmrt_T1t0oOQ!PoJ1;LUSL9%F>yc3WUbDaM?}T~t)}5=6divqvVF}|j
z9?*>U&f@1umzH>P)q_&OC-YA5{ASC9@<V55o4fM!^9KsB?37;_qP1+<vQK@-LqkKS
zTGad~2ozwsc<7Lm2#e#EjT;4fdwN_P1&&NqcK_6O!q>^EX~pv8>UDoU9)I-j?{8N}
zfg`1_uXS3NzXL52(2xSnWSu;@C%NeJ@Avz=#l*xGEnT`)LPkc%OGT*g&5ezZUR+%4
z%FN7s@z$*<&=L>X;I~{{TrSqu)*AyCyFEJ4$n4tbqV((M&rUfxxkWBYg0eC)N2cq?
zf9g94nx1p9wY4q0u)y)rLg#jnt9Yf&I;y|D5q$ght!r&<?Z;nVU++mSD*XK|_u`Ek
z5pVA8-Mu5}C|97;#12J8#iWdk6&ZPXdb4KD>XMX{1S$OUqYxx{@ZiBmt=!@u6Pwxj
zyEbmzm~?+%t!r#-tf86Nv~nNF^a!{dK`nZ2thf&!a0RvYkXr@NA$GV>VD8;rrHeW{
zJ2fVHxOBQG9XoQQW06KzWo2d3WHnz<i>KJn!=!iLzI{6iAG_T%Gzt3q>+8{u4vu?<
zCYPpY2D`}0$`+oTWttQjIrGiW>+9pYv#+lcEiEkt9b8)Ivm&lZp@WZ)Z_)bo`E%?3
z{P|Pi9ya^ZrJ$YjtG~bNTpPVzOxh$v;oq0b{#*N|Pn-6s&&Q;pwY613PEPN849K^(
zwzeOyt`09c|Nh2CXA={XkaU~gq?{a`ynB0Qmh*syS@x=SEYkQC$Knr4PEH&vcmMfQ
zvt;Sgg`ma2x3^urCA&hjv#aaSL}m9U=gwbP==|{c^W)Z1;pyk+9er|g^2CV~6~EWK
zzP5H_?rpP*%F05oWs*fjMF!>XVq~n#cvMwY85o?Moq428IJCppUAdM0=IZM3h@C}C
z-^>zn70kW0<=};d&Y*>d5>is2q!<z+qUJxZr=4G(sbY8cc8#tLTei5Qq^RuKyVp|v
z$@A^^>kd!R3>FX<SO30e_H1dh+*>VvbFB)!j@@4uyW61lSILwqQyfHGZ@zoaD{Xe9
zjaS;B=!wTU&Y$2W9H{EZxq>?TY6)Iu71)Eh2ColX7>R&&LhG4rbFIsh{`~kTVOL|Z
zXYXFaygL>y?(V1WrGu6{9y;VS$FjJsIH(S^6jxZ???jyawQJX2+~02>6B}!({up$$
z;D>MDKzl$c+%H;`m6d^Z_y`IK9kT8^rm3mfxPHC9kdRP9LIQ)gw>QIq$H)5v!@}6Y
z!^1&q=Xj;fo`9FvaLzK#{x<zz{pCxS{vC9g<*YRE$}a1gvqEyN<-Ou8j8msh%{u93
zGQGc_pNpFtR1SKm2t9f7<iN3GZ13K^v#9;G<<5<tpPxT|aIhIP9lCr=4J#|_!d0ud
zet&=eT(%Xo2wERLMaFTFX_3aGTU)b>gy+qfGe=>fM}_-kiA5Sp>gw!QuU^f#x5pCH
zsC8G8TC;1Hl&7a>(e){tHyeZ2QMg~`0Ih+WG)V|FoN}<4eN*w{*RQ#glaudV<fu#!
zJRaEhix)J^23pc$_{yT?&wbGBR;kRVaF85$?t|m!es}N!IM5*7;u&-2%7QkhB_Hp5
zh**9ksvQPeknBIt=HZ->zgk*a0wN+U%I<v*BCZmWl8hC%t63ZmOi*;*Q2st{Z4Gbi
zo(e(dHlBkMmE9jadUVLT&+X^O<MM{Nw@g4Q`NG1&_B_s*1KNmVS0kbBKkvw5_kM;w
zcdr~gf1bawu`%juv5F8UXk&_?vfGEgMTO7K&0SrvaHmmXV&eY*sk75(%ve#dc*;E6
z>LR~oaiE>-d-m+Pu(!J0!qW2LnVH5XPMkRK@$vD8uU~7MZ_B>EF5~{bz1Q>()cyHk
z_~-B6hp%3Bc}`Y4c<Pkb!~4O!QYH^3^nv2zJ3Ky2K$lB0Fl^#~nk~25N&b<r6NjS9
z<iO*gg-<7bxBcP;G48p87MHi|S^eefS3yC+#!g{%t(XQmNy$#l;AIcKzP=8ct#4xG
z-ca%~2(&tUbJ|&_)6;Yr8E)RZ30f+DZB1k|XvNOOMW8vk`v)4CLCuuk-`_7zKHkSA
zzK*l0VSfF;nZZtVph4&O`oE%}VXFOge-kn@SAMv&CTeR}u+t*V3`VP;_g5jWD&b&e
zW@d1RjFe<?Jn-S+;g5g6-_O44=3D*!-O)p>+!JTc<OGe%&9xSvU;l6Cof*Z?&w)19
z>@I(Q?bd65@Q_-^q7!%CI0~?YgoUlLlmxY9>lU!SfK-7Q3uf^jg^a0(FPAN3g^Z|Q
z`k0=d&)@0Nlzn|2XnudLb$Qs&d=|$8z0&4aCiJauX<=cQ@b*;f=Lpf<n@6jEetIgv
z;<#=1hfhyWhyIgx6c7*+TGUqZ$7ha(V3R_^<z>DTJXAniZBErIb1-eoxw)vVq()U$
zm62i2oH<YARtFjXt96?kaC6h<&5R6UVq!)8p(`c-Ll<*_`zfg9kKrqGqE~<X%tjva
z-@#COtVhzK?2W{xO`CqOJzd~C+iZf@(i@=tvX2+L^@0|185tX2ozt`b+S=&Vd#pDq
zaGW@CA|P1ltfOtf)=86ujvPC7>RxzGPR@ge4;$Tjr9Sd5OWVTm_x<U!XIodU)C6bZ
zhglB~wMOizFl=gWHq5@J6A>NF%phl5)e^coEb;HJuN=I*t{E8`&zHPfo|9<W_~yNK
z=%GW0u1shHrQ84TeuhavRh1RPg52BNAOW(En}?@Gfdka`D=8^S=?}F89iDLM<I;?v
z8JmiOKQnIKRwL;#`I$)e)m5S@LY$W_Uk+R!XS*fq>MFnZ4fa)EJbXESF3j%gU8lZn
z|F2yu7xF%D1DDq~Ui_WWd$0fIipLu+njUq#E+SnDpHaKle-k8Y#U~vboKxbv5iz9(
z5{7B|dL4AI%ky({oxQxcR;^m~L~OzRU8UT%)!&ZnD10m+D0t9%)vcGWUnifPWje#A
za?_#5v(0i3^++0T`Sk8X%i4ACRd1EJKeGRIzW!hHQt#=D)~w;FkC~L1kkC;7|Mz|H
zTFPa?`cV!4zS~rP;}H`Rv#9>ICTFuq?$u?!(mQtSNO*s5FIPW1E32ZSqNBDs^H1YI
zk%`l%yGx6My5%mqD{?_}i@>7BTibHAzaMQe^S!aMTiLx&qjt^NbMtJu87^GDJh|HE
z-l`QV7(Up?*Il!@R<{5DzulLP-+FUpWiZ3P=d)H-`ZR3WV#4shIPaf)b-A2q>fH^6
ze|E96I2I}%WEJ-)_I5oR8+cGeJf_GoF+jWg?3GixB3rlk7$2=&eI`ZV;vLuKOED+U
z9AA6qd#|r!s`!lW{BiEfXI7^zm~;O@%>3ec#fPeGo>x6nsF_+_`OT1Vb@=)=6;F+@
zH8ZXqKXS~ltyj6fSGm6yOhVYbi{*bGvoPzk!9aC6GLLUqd_qF3#?{|)O!Du^fJPR-
zzq_mGDOC64A$!gDyXByv5UsE^9TO%9Tr_SiC@wy{(78QD-@(4*g}|LVch2nT(wVz8
zE+VgMXYun#m;LRJ-p=3OYnXg&LE70_3=Q4l`bjr8rOvRcwG!cCUFI`WsbXcNi>vFw
z%a?<{^eA<npM0kL`@7gJd3U3}RlL5o_UHF?|EEuwa6npIKu~bv%@3R}TtGl<RngN^
z92^`D2?+{PrdcXgeMcj==gES)ij!2myXHB$o>}bPAF!(=^P;iNxmIrRfZb)e7mZhR
zRDKiTUDTBDSmM~Rg@+REpGbZjkhr06#ey5=$2JzOFaQTZh(wNzmWEkhVUCOz4=Aws
z{)P()34M6Ed_HKIzLS?17sG**Cpl|>eK~k%XYs>Vue2%_N^DL$duUDMW`n9P89p-%
z9E+Q0t`1)h+A<okuf{U%%#1`)@fV;}&JeIQD|BstZ{@ctC59D2OSwS9P<MBizm^GJ
zeHC;t%DH*A*;ma&cb2`CS{J*!?a7mrz2cF-fB)u=NR9l#^5yvtmXgayj~`#0bhN9Z
zvvcFA^Rp{IKXaU<QuFDg`UDlu&(F>p|EgB;JanW}`0R$hj*b^s4|8AW?C9v|&<Xkc
z?Ci(m^7RgrRIaQF<#u#*<lx|FXm4+Sktyc5FaWfn@9ysM_Mnw6)AeE#va_|TrnzQZ
zT*S)8C&N)+U%z9=j*fZBg)%ZS51v0~UmDbzcXwCjyqx5>B3!KZs$T1AO!eZCFkleX
z3K6h9nY1PIG8;2HpUeKbzYpHL(W&ZledxL36KJZgk(qr_@$+*vMhEOS6!IiLJ^@0Y
zxBxRi+!x398TLVwEou^$K8~7%{T`~SsVV8}^Xuv91!#yYdd@L*^5o|7`?ca)Q@JLo
zWbR9U`s9hj+A!ypAxU?4m4;n(=4xe{q@t*-%v@GhHmkq)<k_>PhpjetiE6X8IyGLo
z5+b4<#&fhw)cDsuk4Y_S*60}PZjn*-o_6HV&(DTgS2Xq>pROO@2O3c@HNAS~^pV|_
zpVjWwevg&0sSs%Rr(WYdDMhq?S<l9A+@0|vkR?C~Z*FV^ZI)dXx|&Vl|7Xx4(xCEw
zng9I0na1f|vRRC4{vKofwXa|L@On!Z7nj!Kun4=cHT$}Nm{?n{wE3eyKR-`U;RKyS
z5)dE&+SYn2dwu6TjWgHQMlTFnxuN=dUP@}}!kn9%UR+-<KgCNG)Z49^7cf;T)F~!L
zCMP%d;>Kimjj3K=UR~wx>+4&zJhJ8A-`}7?@DpdwxV*fy^y2pXc#WxETe7eFeKA=G
z>Lhe@aNOBd%57$5_Tk&NwxE?R@9*t>_~eO7)x3bGr>DCoB`I}@YPX%6Ywf%;WRZKn
zoJQQ99WOEueN+jlJlZXO{PJ@Dhi~5S)YsRuu(5%bv@A-G1ZOC48T73er6l^+o0ub0
zi47eF=Sq0-w9M1r-+ii9s6px}5xa+%8bH%4=jYk(sQj$Pupnw{7AOx%ndj+L%>20~
zdOP1FmBb4R94DxFe%@%<%+7Ci*lOc4-`Q-QlMJ%2>1c>>ojrc6=HJifX%Xp>RwXYO
z`1$$Q#O@Az|54Go?ZLCNvpYIF4L=)wtf{Rnd~rb$w8SDVE>0tQ+nRgVudWI`ede^z
z`OC}wKfYeSe^KP-v`z0PZ#{AHBxu2hS?(<s&q)dC>Ff+A&Yf$ETI=@z-`|gq`|Uq1
zi+|9|J@4+9Blqsby-rS^w|8DgM+aA%_yS=;K|w)L!R3B)ogyM6l$4YTo}ZHiCC9l|
zrA<LAL4!~aA3RW~S|qS?<w{UF9HJ!(8o7S*^yxycsahO7JfPLupoNW9i*ByGngu#e
zDqv*@XtD}44YJ6E^UIr?!d^>-=313*>e@X`deXFMZS(7XacWKF0*zJ`6&DAt3{pM&
zym$HX<u5u9fu;<!rgBAZ%W(_}66zAyU-$KkSayw&dt98{qQ#3rsV?`n8EA=~pPygF
z^SR{<LbN~&kyh6wG5I@PeGfW-ZBL~!$d$j}ny<K;6|y!;)N83wV`Jlr=<VxXbc!|i
zE|!;e7neS60FM6H9GSy6EPib)^f|n5;_+h_j~+AZ=}ne^s4(lR%aOUfq43GZ!jg@k
zVngB>SVip5Pfrb#kMZ=#*+zX4=`MJ8$8z-_JC_u`>H6_*&(F;T&DnzLpQ5Ly7#cv6
zZ!a$`?da(_vaj}cz+yMvgWhM)U%V(dS<Uy+<W>I_ZEa=c<m5mLfI*Wc7mIbSeSCcU
z>phL7k(<++rbqJK+p!=4w7c&6yV%vcZt@8VUaaqg#hl~*zu#s*Ykzn0<VlUdMJ!cc
zUxC)|cF$7_NlH>O%e&L@;X}cZW5=8(sa#nd?*Cb3db<6ajcPY<-UPKMuL)bkRlhX_
zo#@cm*qCv1)6y56hg4Nn6_u2jw5D=x+_;gU!K(CChF$)u(A8=c3ng~$+<9YnxqgV2
zC}^d~moFt#G=ted=VT-#D1h26Rf_~7BO^g`ogrGHp#IdGH#s|Y?Mgb(zz9kymzVjv
z`ipd_FMK5~F5dp(LqSV>`{N^>!V^?Dd8JGo0s;iscqACi&CM?g>#|9^+ne?2ne`>U
zk*>^<`Fq2nZDZk=<i|7GKn;w=-QYNq11m}dOD{_Vm*PpFdKMIs{k_RIKr7!L9%B9T
z>9oF@?be^6%L6n(=i4m}>SSbQi+K8d;r~NjqS_lWE-J<BsR;Zc(!IIxvD=#X{c@m@
zD%+<^iwg@c{@gWb>eSXNS3($e`9IQ)+@#VauHX0LN5yBptqgg2c{7YsxsLV8YFBj~
zEi5fPdS<3^<zf*d$^4iP@6XOOW>-{HJaP7{sBLRU#|n=}tdORJYeZ6#5@_b;?d|Q(
zlT`jG-{j7_vx9M}SL=rl1%Lj2zaO9>Qt|7{$`_GNFRPhA+s~$WsoMR1V|?+m4roBo
zbiVoXb90+jJTva@GUb!A(WsggASo#c8W28o_%LYI{*xz97I;n7+EMtp?M0^3%W9*b
zudl9x7W#pjP@h{Kd#?BuyR*pk^OB7VCn*WS)&g{k>pLwB0JY~ixVR4ee!pM8YTnTV
zc(8)=M?W~=?alfM-$)<6VX+GwFHgWx1Iirzy~#4t#|<Dc2QFFv-muukCuh@fak2a2
zn4LuuW;qgf?%w@+FXDLAyaq`bnI2F@^Xu#DS<?cwroOnnUEgcEo^Dm##Dm<|pG01+
zHcmLu;B@zfl8wzD)ioP)Kr1cI+yC!zZs$9A?3mjZnQo(^Cmu07i&zZ}4HqqsXgP29
zn`dwJcelM&UtRn+X6z|ExIfwV{_2j7jySfs20u_sF62l`YHH&1b8`b$hIDjwIfaFZ
zfm)Z0%xnn<n^+e;kL>ZDuIIQk$Z=`V!&6hWH*DOv@z><4I1zF2cF;EMB?gk>dNBvC
ztPKA7Z;yh$K0jy~)TO1~f})~Fzdx0KcXxNYVe+vL#curbTD0CjIXM}0%)o}^<9z$f
z6CTg#0*9a6Z#R3hK3MHD=lKouWywehS3=rd4uqatn)SUz4dIi^12jzjuYK<nxHT$w
z>ihE>laDV5S_wKusilSG#_ijnL+S#wrhfSRxq0r~xi31!dd1hBd|d7P>&=ag%$w8B
zHbt#Hc447&;8HKqz2b|?-`)y6V70MN#<EFJ*=<41&rcF|H9Ow)27xwFCCvS)DZ-U=
zV*_JjV<UL^;G&|Zr$8aLyX-B?`pq(+z&-pv)WyZ+f8W{{jG(Y}Nr{PzlS@iUS`f5y
z1E{2~`y=7!=LgzSG{sBRs^mq$irsJaWq}S{`tYG(MTpj)_x1mqqt?1TKGys3toeP=
z+}fh&kuAdNehy26Kn2nF_xG>=NtoHNyZn8YUA^CYJKn8Py=iA>Ij#)pnx}T<;$nAG
zb!8P*)rA!wAAR`#efzKPPiF=%_sjg}b9Y~@^wBO+=jZ3<x}Fz0cfoT7i;9X0X!Co(
z$`H``CkzV`54SaicOE=u$O~@d)q%?zNPWPQ{P;=o{TY3r1Pv;RY{2maDTh97Ec7{k
z%&-q!mB@k9`?mM{|Hpk{>Atcl)q6|MO`(Mg7k2dZU90iGzb#kVYpPbOUF|Og0|Nm&
zJG({8g)V9@2wxvJ>;Jz8&HP*XJSU}WHD_jI(AU>zIB>uIe=jpT-wT=T&%U#r`2T<Y
z%$b>6|Nno=BV!?;?A8O?dsOk5Nl8h`$QqiSQw}C2CvSb{l$)L1jn**gJhXJll7!FC
z&Vqbg@<IT#7VF`|#s?1)G^To8SrzL2#pU5V+eFYpjPP|aj0~XV-JpS^{dIpqJ(+{t
zM?L-g+)`3hLbOCdiwO4YvAMD$kXcbtF+gkTionHfFFKv(SeNr@P34j{&pUE<wz;CG
zP)$wEf)K5XyUX(}EG;|dX<XTwechyfnO@8e28N8Qt3;Ri&E=}EueY$a=8n@~^LH|R
z16m-nDU};kX}rJRf9Fojj@`Q-U-q|m4G0j(y1q`gYEk6I!k*;E6335S1a~k&6*M>l
zfwN8`L;}=!N0zWyh9+_E!NF!%{|y;jtxWs&?E_8KhlPoOYO)U>3R+rQAA*)*EcKdN
z0GgCA?(CX!<cJGskhWjW)+sJ--nqj1`g+FIN4mPYglrEct&Q7zYt{dKzO9EL9Yv2l
z40Ay}o)b=?>*Hk2^X@QA_<#73q;XorU;gg+Et!|qR)lE1xxJk~GBUE_?bhoCH9rbi
zSXmdQo}RYoIp^~CoYJ5@57Xo8IzgLZ*TqDBaY-~XG6J2u2+Ag)X|HqV+E%aDKGq}2
zyfmmY?d+`1c^aS~7nGCh`|zOv6c1TjrFx}I58c?93|dFSC92giPvc6rztykD{q_sO
zRtGNklLfUrL6H}>cGio|LmyN^DnYG*t=ZzB(0_BY`OF!gJ>PC+gUacqrlt$4LbWdn
zw}N}GhCQJEyc;CFLmJY0-+BvS4X7vJ780aC^&$xrC14Gpa_qQ)ncu;?`|IU7IXPDZ
zE@tzZqM=yTcXZ?S?e6dI?G4;hQJ9jFl5l@t?T+&I^Ik-{xVn{<nYHmsvrY9{TKe$k
zW^Tv%8;@~csI9Ga_1_TT+|DOz+t{UWZ->M6dA8L)b#IS$i^o3_Qc_wJK7UEr>Z^;~
z1whT(iR*TizE;xE;Am`YEGRD*w>|zyLxju1!eW7YzZ?e_7iiUTPHtttF2je9A1~S@
zE(SGdIXD`ER=WKC_0`pXGl#18G|=h*8CltjtHbp*rh1jUxgls~X0~WK=h6TT1_n7f
zISwA4mY|heR;mA#xU@1@{p{pEt<Y6VDuqH8yY;&G3%{GMzEEqb*SwZr|L@iRug$r;
zOSE6!-tFU~qZjv9mxD}vdFkk@{qcyfBezp}Fz5b0*~#ku$3W}p7%pDC_~GM6P#YR_
z^yh>L0((B6vu+CSD*f=laYcw$&dp7%{PK37ZI92ggQn}nx|}!WR##V_tpDuvxpT)Z
zFZW;j?Bu3iX>+rmTMG*dJNo;#&-(t%6=Zx9D>rCLW=qypu6_IVMeHuqjfsr~t!rcF
zmrHniYb$G&eY`7ZQTf@~=8OziSA`yay?(!5g<zymt5f6peZRQw?kZ(w038$IJKOBX
zx7+y__f!_|-4D7K<=Gq$F|UOI4wF<QcFVlGnf;@sLP=@Sp~tXhQ$Spt+`BtFo4G`_
z4xBsZ_eDk#w5Jv1GmXeiOI~P-9lv=~viA44)}WOxyUX6XoZn~xnv)I)5CEMI;_mK#
zu~_HWX7%id$CGP%G=rD%RDFNPyEKSXUS9rQ=nqyK&d_;l*XlxxujT&ob^DD3rQ3Ux
zIi%g?e!GEdWJtZd{J{<LpQv3#NMDil__346k4;2EhIh}+wFadgP^B=}s`SvAnZ|;`
z!p!pW@(d00=ga5h<bbmHLGQEgudECPwMaTT4$QSKUl5>iVI!>beEQWqq5to8zZd&)
z{?hmR_5UYbi<oAXdrRcUUdxgf7rdjAciy>s7t{>`o#R>Y;Q?bzOpHl<{*^4#TU)c)
z{r&wxr{H}FQ3N%~`|W;tJU@AOYxebH=J#uouljqQKXvNRw%pqVpPqQyRDI#7tgMVW
zuIhPcRp@G#wZ`ky#Rd1jxOwzYQH7u(<AHs(zq$TYule~J)D78x5IShkwcy8(ijY+y
zp2f@aE`57)QrKsnjpXCw{qARHnYx}g-2LWF&T6}dukVA7RPB?sX7l&=pQ0BV^+l$8
z;>?+yzO&5^UcWB>^z?Lb+v9IGZQ7KOpRZr#HZl3F`od#Jk1lj-<yw?3VhJv1a^^sW
z&^8ouHTNDqrl|ogfXw_7!JV`l7Oe-5B|a7r0oCSw(#s)(YdJE(rn$F7RK2Gi`S<sC
zsU8PwgJtovgsZDUca*-K_F(C=!ne0fSA=MRdLxHgxdT>T&A7Eiv#F`cAmIQ5cmT>H
zBt=v|P6o6fZ$si?(A@tdRqv$ZeX<`ue`aRTiQOf#IsLp_Ow61IOP`6$%J!~{-Mz@E
zl}o~^MB~+!mCOtl_5W-@Yxj2SumDY)z1@CaY|oWHd3SfU^2u5~cy)DkK~a%YR+g66
zbiH2pemTdrVTW(tl<e#43;SHV%0T>9zl7l<Rh^ABdkPr^1qC}73D`D(s+tb2_V1G>
zO`kWfFLZU-!*g@37cJ*Ve9<!R$B&8|H*P$*9$#<zc+sNA4-dD4W+>;^|I@7Ma;^OG
zLhxSod)q%>ug62xgIbO^Z$3QG$oxz?#6?9-?a<-F%<cU0Vz#av&g#1As;UpaUXMS%
zG5PqJ9V=ddI|QKc2X({_AJgP91BbME+r~n0_)k0ziUKz2_TFF#c$|Sc5gQ79O5feF
z{PFwuX*vD)eKtZuLT7e(tdTO!QczK0@t<$!>fynm7rU$Fe*J&h<l}u$k3RpeZ)+<H
zYR*SQ%y^+0as+yoAOq-7Dx=g>4=yeBp7l60Gt<N0U)<Dx#Z2RL(8>EhUa#M8kbI2i
z$M4^V@86d<PCIiTzW#6Pt*zOh{pyR-xePNesi>%`KK$_T@Q$jlT3516L5EOXxe@}}
zwC3mMcVmD3{ueXTKv%Fa{XZ{tcULL**H>4a9UK@yXElLNWBB~+EU4_-SoSvR&zH;o
z9iTSBWKbs~aN8nwaP1TL&|{KHRg>%EPXA9o?nxZ`?ry(N|JTZ^Sx=rkd2uIl#;1>;
z-S*$P6LV)rA+w~U<f7#fDrS9&e~MN6-}l<=GynAC-izbM414CA|JqpiWMh8M<N4Z^
zHTh3I?wxr2JGk@kXU|2@czbWM%>S5^kE@j-`hIOJ++t~ErKGFt`|Zcp?CT$HWv`!E
zI58smcps=(+?;mS#eZW&UteEGXQv~m;P>Ci@%`Oh?JMtBhpfC*zvsv&)9h<J?)`FC
zYwm2#4hJoMUJ<rd>eHuB8wwset^T{Y{M8jrP%tg^ntI7HY*mQnp8x-T&oIlK)sXt=
z=#e9!l}VsR9_Yvbh5yw%o12-J`OWPD4Z{EV@$tsa;^hyPrg+BfDRewL%M>&<dUm$?
z;?&dAK-*8k*2neEm?3e|_-xkCPfuC@*)DePujBLv1#2y|b+w}75&w<OIKFu%%jNHj
zYw^_G0}ZBk{Hy*`rPKeOSCq{@A2hP=qR+lx?)2ko=hlPgrL{E7_%5D4xc>O3ANM9`
z?%BKd<6(aLgg-w%S{;A%=+TC>vr<2P{^X2MbIZtB@ofM8U$3-TSXmFAJ?r~G>GYLl
zzS5vI4~N@$g>7AToSLdF{_1sZUfw(Jh~%5cdL)}WIygYbSKPZNw>kZMTYo?QudlD!
z8CHN+u+DePPD)R2ckh=wDOdmJhvAzyZ_eyEQM6?F^23J@Gc$lrs`s4q;m611vme9O
zMkPKv(z)mv=k%#lTi@Q^{`l6`Y!5%bYd@=(t9br+wR%0vTH$tcy$fFtvdd@ei=X-F
zz3?QJk4z;>N{gJ}!wM5NZ#Mq+{(gTOuXNYEq=|3dya8=u2A8xVT1^#~=G4{1uQ2#g
z>C6fq<#KL43J#Ni#1Eg_xSDE{Wu)7=y5swwe%!n8(1Yi^qAcKIR8$NSl*?uqr}IT^
z$!J{WJ9|<5{<;Y&oS>fX`u+d9LRW`5t_@2*)+4znol8(grsu(f1W;E3G!}n<UoCk2
zcA9I%t`g0f+FH=8e2<K!&{XYkF<Z|WS67E;$2P1BTMatUHfDdFEF&Z1iqO?!3=a;q
za^Kids2o@Sx3ovn*zHQp!aaNUK79Lj?av!`@5)Zsi#;^I{vW5bwDgtr@$%okePa^u
zdi?fn@6m4Y#ns>6W!%}Z@!H1V<$j4DA07Sh@uT1tzcpH+s~)_&yPKgQ>1fx&pru|N
zy}d`R-|t~&0G(IaC9bbmw8(&+U(V(JzS@ru4l>_-xA_|Ph04cFf8V@)`|$bm_5%kT
zuB;4p{~`lwYEE17Z2u`xJ5w-n&-eTF@}SPy=VxcX%GuZbu>h45@Av&acjokp6(`S}
zadB~Bu_}Mp^Xcj7?s>_DpFVv8buvO$1RTt&7w}-6JacB}h7ATKudnffXEKg2vZ?(g
z0y;7Da2s#sq^I^vmM(qxdj0-m4-PgzeD_YTsxKf%=GS^qotF=tLHcyV;^z(XFY!sB
zk`|OFo`8yt!cQ9uU+g~uYLP5Fl<@e)FHp&tcgNz*{r&N;nYMj<dpr5&rqr<N#!Gj1
zmoE%j2^#n}PCs|x;6cW_yUULsXk@;)vpD_6jT;^FG<qga76z?ro;#P9VZ+v~SASaR
zcuqQ~Znb~azCWM5K??&dik@)9#Kdgr1I-or&Nc(pe`@~obTSkp7iovDTabEsnuniX
z+w|$vpB-Zr*N;20(7FA=n>Rg+-TN20^-48OpLKsl;NlO*<?A0D=@e#Y$h^EP@!p<F
z38NH_PoF-0`1}37vWCV9t^avnpUuu!vb2<39k$k}!dO51&6B9DS&l11K--iY{`K-O
zF*BQrKd%4t@i=HVz@x{HUC)`UE`ELvv?BB2!-t?X-Zr+j3q!OFK{fo&ot^XCU0l9+
zJ%lwh8=Mv%XycU@kdRpMy~4$Xg^8JY;_TVk&r+v7y|OYGw1HAcNXVe%ML@{<I9W+a
z$sKintw5(xym+Ber4%V4FE7u+&c4{Wov*6@{r&y&^Xvavf(Ffv^@a6KO-0S~?i`q`
z?hnfU{QUe=Gy<Kz=q$W+`SQc3Pg_Ad`JSAZxafJroQ@8TFK=#M&U$~$xAib+grXgk
zM`0t=e4--1kCo)eXmNnYC1SxfZAd_l%;k-RD-^(EMkN~yOXgY@vt3;kdbxUHR8f)9
zx|p3!d-m9X?kcqsKOePOT>sXt($`|ArfRqU`}<p2L&M`+oALTh<@amDU$4AhwD14F
zYU4E<bwXE%fvy|)@bS3(Yg@bee>I@p3ET7T8htkUY+d)KVqsnU=Crf_9;><@zPr2J
zu=-mLsFm~W?QMon`m^5N+N#~u+`RT1(?x0Xya(U!*SoKe+Y8zv*we$)BV`I2>u>Ds
z<^A*L&xV|vMyvN&&RM)z8I+`Yq|N=lh;$#87MCb{aY1oKh!$vt>dBKQGcGUVo#Lem
zntI)odb$e~c_B}3cF8$_N1*=S+gttp0cg^q&A@-Y-O&dJn*{|08Mj99dQJj0sX=j;
zwH0(I=D{VNlR;BD7lY3}dUA3y>p$CGY4bWxZ=L&%%<Q1(z4@4vlk>;h?f1{@@Yu7r
z`g_v3IhLTKb>rgZJ-eQplLP7<gJL@Qcps?ndGVs-_4W0$OFlK4a&d4ttPENT+ENIr
zOm5$f{-UxlYHJqgj*iTKdq69KUtC=L;memTr{u-N#iZMNKP#E_W!`|)_MoYTjO53E
zs;}KMXOMnA{|0C%;{~`^0qRrt_I`d3YHa;K0!kLp!Krm_y;2X4%hzAIqw@5qwDlC-
zXffZ}W}<s87+qZ*&L3a*Qxz1Zp!t<<G2KI-o}S)V^RoyP7N9eQKRi4Pnp3V?6}cvQ
zyWba<?x|Czw46EPbMx`cnKM1Syo??z6@qT6Td{uswW`T#=H}*WA~rHHe0WpY`R5-i
z=uphNcVj<qY;I=0wl@0sdgl}MOjS`)vtCGwWqx{c^2gur_a{!B%357r&BD(9_}pA;
zP__guQF;Hqzm;3OYo2D$^y%Vz_Uze^a#HBc-QA#xRADur12;A%Z_K%A#3O0s^2J3-
zX^~PdblxL!#oOE4lYf7EJF7n&(rB1_ed&@V3TkS{R@E0+Wna^AadS(0c&HWB32tWN
zH8~FI!>^CG&$+$rY?j|E&@G^ibs5T@LPbSIagUTvr@h#_tLQ1$oH=vO>~LGt$}RqA
zvcDZDS>D>7-(U6h)xwmMlRSKVkKWvz4!T&O<mDw+ZgIUMH#R1_o)-npEZ^9kFArMa
zTh(>cvgU`up+kp2W3r{MuN^#lmbbC7k%NoN2{a~s-gx(o8xbmMYFT!5UtS3A*}GRz
zR+d*@UcT}4k>tlS`g#}l_9k0>>oo%}2B^%D$py`Bn6n-}cJbITLs@BeX;7sMn$0u=
z%}&i}N_?CF*C!+GKD)V@`O@Xfrt;FeH!|B!pE<KL_x3hWx%d0qThQ8ntI}62*4Eab
zQ6NyW0(8(Cr~|!d`6P$4vrL^cGBp1D`SalA%ax^|WhD`NDhy|t=j&z6t#oyD&8+?N
z<z+BvLw&!T?V$;Z&H<~#bQun`a*KbsTYi6`&rG8kw$<A@R*JQY&pYky?cLnm%q+sy
z`a<*2*}2x@pvJ)WcXtE#*VSGu*5S&JNsx+;js{KHe}8xP@YU7fpk)FN{{8*EC>=B>
zSvl#~P2Hv7ZqA8CpwmTuJnGhGV0iiR<%Z3ho7b-WX1hei)2UNP^~1I3{D-si_kkLe
zu0EpY?%tKXyQ}o@rqt6P9vo!ev15mVnwnd2Qbb0EM%wv#YfG7Ku71-lUuW=ZR!<Ml
znz+4EpbhLQo?)fOpUT($aQrMMYf->Z`s#|~&reTF<EBrV)MT7~ZbA0-bvHI9x9?1!
zb@%7z=MP`L>|EwMJL&PU-W5ShyUt~U`f?2o409|BnU?#{cLR-s=!m}l^Yb%kW?afN
zt3^=R?ZDx~&hIDJ&Y3%xb<JiTOG``8T-u>Shc*;H_e)7hSy1=)mxM)u0uwWH;Kn4^
zi^6A}76v37ZsVP$p7-MSzm&B%ES4pMBKt%#XpCq^8)#%&U0&MV{+sW?4TW34_5Bmj
zL?&otdU8K#aC&*d4U1c_fr@2`k2A9G?lPS;d9q>QBbO<9u~MK5dq5Y-Jbjw_;rrKj
zcW?V}>vl)2bt@?`0XYmbfM5BErB}-I(wF<2)#u&cUoX$d$OzgyxGr|LTE*5%o4P*|
zpp5YD?(V|R&wLpiwq{)g?U(uZ`1s<Gl|fD7U4`G?L{?N+gLX!*joyAtI)4u%1Lz(T
z(42!&>M77Uv0;@PUo7#QEFdi0e7K$e@WqRPuOqUuwD#=T1KK&Wv-mkzRE8aB$Bc?+
z#HJKZ5iVA@e!1K)-#sR^q@JEOGjZ<IpZEX&YX|MuKG4W~;>?*N=k5RV$ji%vHZdLP
z5R@>_lL1dpE)$q-mg^J{ARuLy)1ei*>cFvMZm)N!cy@Gj2y8i5^x+umEhCg6SJ2^u
z{c^Sf5)vHo@$qxdD=R4}X-U{ILPvUi=URydFZW}eQ2*)j_WO0KEq``yIePTy!obCD
zn~ryjYPVgv5@M_;l>Ons!A-|EZQ8UU>#A1G*Q?>6CAy$BuQQF)XXVdf_3-z<ZgueW
z$;s+g{}ukfS+aAYvb&Os%8@(5t)P{gUek0sV|SN<)>%}=2XD;^eRF50uxZwn1G7xC
zLA$k$*NePAYkr@F0X%iMGGx>G&C`URe%ZKnYwP^^@_+vPnJ{Zs7ij0*-Cd=iS>|Ov
zGn+syzYh-%e)#^q9W+g}Q-wkLcnP?$sRYk~T;2d0Z=ay}W;UdNfeh<H(p)=F;$smW
zP)P(C4Lfd<Ba^#u;X=^lT^o-ilfwV={uvn>PR`D$_5G%IzdUjkR`YRiabbD%_%SGD
zgBt(MY`m9h{PwO$I@%>+RiXj9hB0B~&%3+J`Qzf^K+UPF>+5>2t&L`80Ij>8X`Bw)
zTWnGCV#3us3tqZ{M#^t)PXBmRJYGRdi|crwEc1l_Un{=6xCpvL?9QD#EbB#*|Ni<q
z!>V-Exuee+0yd?1?)m+0_YCXub)hj0|1SI6J1z_WZHW!g5CNT7+GF?iPL#ewe{XN=
z_U-0cAuAZ_>+9D_n@`ma=j-h31g&ikjceGKe4G!o=-txN(xUvGOy2!{Yd=dR&ktX3
zbZ>{l?ai~b+S=Pel@e%}tERSgW8Ph>FK=!JzvrFR(b2J@pn}l~)LjS^oG^X5dR3Ea
zadGkCr>Cc<_RCwB@myUUZvI&5^yH~iTc>J=C*9jq2~H&2^ZP%1C|Lcg{W<6w!`8sX
zZj1~zHZ}rMQeASkRUC1u_Z}W@zqmf${-$u%yuz|FxBYd0KitmWKQnV?DkmrB##izg
zqE~hnKQH+6qY$*uKWnQLXymV%ogZ`|k<VN!(T5KoW?Wv@`(mbw0C*y+FlSB;ED3P6
z^*Xn0$cN0lKn6Aqd8I*xN(u+K8UiT>&+=a0P`Jf3^AZba=grmC;ezt={omf+R<^K^
z$lw2W+lx%G^s}=}E1u6S2U)x4@3-4-_WifEWH!Iw|NoxP>m##lDvdyW@$Bn*plg9%
zM}&lkfc8jf1~1Eq)yVSI3R}~m>OHMvUSeTTaPY(_Q&g&L6cri$=h+xORw{h-=n+qy
z&v{U8G|j%|l9Quz>C&YQd3UYWK9;pA*>G#Usj#{q=+tV^&VpZGUw6+-4y<_06f3F~
z;^5`Q1!{K`Jaqc<`Z|B=sVRcC-5nh-rXGO}Z8oU;&r?uUWer^wa`Dftz181Aho^#;
zJ^9bK%eb~?=7H8EUI_yR@9BE2`}f=5xqFw<X8+@t{r3MrOD{mz2R?8r1ZDlCqg<dv
zIlsTZ-@bkO_Rx7}l%N0l`g)OiM9=H%>mUF9e&77%)_L>h-Plw4**h*}=9-t9I<2KI
zFR8Y)wt^<2Z*9%i2wx||#LR4%aY4Z(?~VjR!J{Lbpj${l$7$^>e$Jv_SNZMD&BZ?-
zR#jD5sdzf2q^S7KwOaZ)%5xHEOL4KkNFQYK89baVEe*=Ik8fC<2hBa)mpFcGVxaq%
zXRx&Z;KnAX$pM}jJy#6wUmSzgF<ZdZ%*E8~?Cz+oSqsC~MoHLI82tJ32Q=VtakGwJ
zO^uD$6ph4BukYTyYkL23Txs?9cSnDGd|aw$$KIe9y9>N^c$R54i_T`9&dyE`4-e3q
zz<bN<qNVfm^L3)OaOg&FyYlnS&Arv;PR`B`-@et&kd0jR_;~;0ZvA}?kVZ~v-|n3|
zBj2+A0qp|YQ~9~#<4(Cfg^lal`Q;CtJI7c5_p5kQbF-j~OwNa|lT;M#?C$xz1`Q_Z
z!UmH#Kzlww_u<{R5dq$s0Xq5M&dy?Xu2!an3m1aw=UdzJ^~+W$Twd;f{NiHwi<?rt
zE2^rTCaHi%xIx>6%ic=W)YN=9sXo7BUS`<LnKNfC_c(I&=)v2!rKQdDTBc8*{vuQC
z>9w`dpt0s_ldC~j#ISOUDQIhRGcq#1xVn1!f!1fAe|$`yq8EE>$@OVkp<Mm)_H`$_
zSFGUV<#mmSkofoKvp;BJzxw+-&>)#r`8ytIY3a4s%`z{sfDX-W<B?R#SX;RwL~BKe
z*4p^!tyxp=U5|R)d744`xP%#K2~FV}>D(NdU)yg$mTQ3WGh~A9;;~~3>$`g)t7$;1
z9QDAhPLN{#h||Kmxfj>{{ROhL>dT9T-+!!&-TmQVyF6&;NLrj)TvU|Qsp<Oq)q9*;
zxjekRjUOwW-jsb^4|G<{^YioB89*o896!$P>FEi&TFlAGDaC$$Tq-D|Y~OCatNcA*
zd3pJskH@4L8ct8we|)T0dPUS$t!a9(S`|wrBqb$1e0^KHyStxV7ZMWMQ1&(ol;_Id
z-}~_8i^z@unds=l)8F6OUB2GIoV#)=C_j9EcURc<u+qn4th@gF{cCDotE{B7XnHra
z#~{iGI<c)oP}xL2|HcMJP?HmMn8CBz`JiK{K<(D6^KJz1sVD?376M&`v7z#F+K%13
zL7SPct`0wbq*K^1<%Gc8$<N|aK@FZiKR*k~%k#_2%e%O_K^Gb>;kW+-S|``h*~vJe
z{(5<Sett@N`r(r&IcJ;agJ#jIzQ5D0czJsI?Ah6$?9X^lYT2`A&-6VfHpyBRu|T(_
zl-%R?oCKO+b3A=yra>YT=<LL)+Tn-p-@pIDGs$<BN#)Y}>UKMinSe9oEl|(!env95
zJ{AX6$;U0gGa|V;GN2-PV<A@?D0&z7f*OmU7&Zg-GC^%Z*2BjpPM<TU=fj5r(4{da
zPo4}|eHA?Mv;BUZcE(%_&=J2`S*zZBymBSv&YsH4J>5F)cXyS7W}7D}yB|7t&hPb&
z%gg;i{9UE5xuVps&9kk(usU2HbOYMuWxj`>&#zx+8MZFQa>uS+k9NP`xA_$Jh1H>}
z+dx+$-Q1Mg(baY6Xt%iOe!HY29H4V@RK2H(><Q{gJlyv1P%F1Z;UkuYKkM~%qqcx{
zbuch|et!P=dHersN`>XJLHQIkhY7lL+;ZByd3~j?uPw~Iy^U#F=k|(^NnhUF6h1rK
zeEX^Onr$DBvF<X<yQ5LXBq%uX>Vzx*|4bKE0)b5ye0+SMmC~Tu5C(_m=jMVYqnO$G
z7*6b8{ccU<<_R-qXcVYMa<w`!dQQ5qA<=oV-?ND-oC_B&Op8dX)CyhIQuz2-;-@Dk
z89vpY5ET+?0&Q(Me3*Hzb-7zsmR6sftyaa$)5`-iF02ezzp^Is@{4T!*j+6zUSvFZ
z_H0(-%+$&s9~5_$zHWPbyx)0knDZo+v!2@L|3yzySzVLAE`C2BKR-Wc0eRx%0LKlW
z^@)(;*j-M#ovW)BJc!E+j&c)l6$~2Y78L=P>X6vyxxGDK9yCa@WsAuatx&Gi)6=e2
z_NsV>{hX5D>eRSlg8>T*%M06oACJo?-`!PO@!>(^%;}xtl9HXEbABD0*(7YMwmf@%
z;b^z`#-gWQb1aM51O)|O+}^(a!O~~f*F+jySXeyRe!tE+C`br22MnFnJTS+ycth3K
ztkruf8DEBP%?jm_wGvTORAguXHEhnzFa#a*60pCnw&c|n&ZnoQ9^O~`n?>JrfAaCZ
zg|)xGftF<?B!GHB8#68{f!qy>_^+?87k+sWXp(ay;7iEn>}zWzg@lAaW2m6D3g9l7
z?;aJ;L+|(h*UMOFv2WkL6DLj_IM~b%8phqRV@Jk5vE|E`FOJ(=m2qW-;I^EbN>!_F
zu8G|(_V3?6jnGw7UTC_wxU9E<Htbh$Xaq0gdGzQJ1B0Zbq(#XKfu`nW)8o0hxfAEj
z)61H7^u)=N2XAgppEzMc!!qC5hi=}C{GyV0CCl{R_x=AL*8l%K|Kjzi*PgZx|2U=A
zty?#%zx?g3*0Q&^7FK<I#n5nXZ#8Ibi>T@OH+BDhrh_&#tL?pZMLl3omYUz34&(H5
z4oia;R(^g~@%QU>&|*H&kpmA8wSqPUEn2k5<-ACfx~{m7n;TnDaPY%NkCdvqK*N3;
z3g>|q$m|2HU<I#Z4>rh=`R3~g6$h_dg^Qc{p@}EoI4)n`!zHTqVEOzyC(!bT^MZON
zCLy1{hE7uHk++X~UH!utv=GM2i;Ibw`K;|lB~W`QGcyyk0Me~bX64Uci^5i$`v2H=
ztouCUgF8EmfBbsAp7F*1UD5k$DpgceW>il*YF+(J=g^@;0&;SBQ^lXFtEnyWnyNLc
zzx>UO#%pV%L1%9>G=L6n{`Tf()3wg4n^L{s+}g?wx@5cNtgL;V4a0%EcV%~%z1?)G
z`+Vac>7^lSA_PUX!$fS4J~}hUQuyud?e6_@wkF`^k%ysI_#QcWH1XG$mrdcbu77xV
z7<8ac$?I#pUQ31U?kWW@k&6UHy$W<KRR{}cVZ-U^`tEOUZQWS@J}xCKZBhF9d9xl*
z*NbhMJ$v?n)<<jO_DWq|=6m^0ueFtxl%1WOhnH8=^5yE!&du#^WM=1z%ap6EtX!ln
zBB`gRH%tB-Xkg0BOsx3%xvMhgPo8x2^XpqtnRfKN^kvWq6`*N@|Ns7)#^;N0v1VOa
z0lpZa{QW%%`#PILhYz#r*Z#a$|Nk%3e>u-dAKq@izpuq~+RHODjXQdJTGp=B{qy%P
zXjRXVW5<%-+}H@ZIF?~S($Ox^xtVQzvRV~uCBQpv&VQ_)nt8+g){n|$DKk)O?lEYH
zIN#^+vC6*tt9?MDOXsC8!_o?92{cIApSV;hvp%!Bd!UZrjj7t<pgWP{YX1F?iH-gE
zY<4~q18Ci<xw-k=_ctf0EOhA<s(8J2J7_<Opt0_u-S78xFIb>3$D+{b^VXeFTeC7Q
zE#b_`UHiSHnw_1!*<5N@-CwIy({!_sxlVii?d|P=l_4D5+=t`q|FU{cy09kF_~Pak
zjo4jVo*iR}jEuCX_@J=NXXYZyy!`zBEn7?iKexQTu~8XxWr+R%Kf<7u*Ku)jtHRg!
zffffY4Ct7r?vs<V<^`u%x4GVht+l_)K<lsW>=XtaR1O-Ng={@IdseTbqvOT?#J%;(
zYM^RC%W2=QSK6SmsrJ_wP&NK8-CpI)*|V-GDJoXw?{tb51xTCa95^vi8MLb7$FE;W
zS5^ehN`883s`Ke-x`JY2X{PF5C%n8@_d6GKGvrdQsfQYw*(Xe&-X6ENDzoqZ-|zRM
z%2U<6JUuVg`~|HiW>7FS4K3aiyxcGBv&p3R`oCKb_=|5`wtOP!EX<7S>tw;Z4nIFT
zdw5&!?F*1qbqn45<v@kd#l`N1Nk=#=tgRQ9zrWWMK3g8thvO4v``yOX-1`}_6u0n=
z^y3>A;4MZx;J810!{QitJsoJC2sD4xw)f*P>55NJI$ubNDJv*2FfuYSFy!awgNFKK
ztx5#;oGQ9`>((OBfj1WywZ70417%gvEy9M0hgjw&b8>QmZm-={@=_^bW-92A^^_Eq
zLx&C(JUJn_;%Zh!Wo6>qTU$X(QoFmmUvxTc$+*Y_%3{rIyaJ-4tvx+FUtU~vF8=fB
z>FKclQ?flLU0C8N47$7bi-?v|#bc)2ySvNXzrVXXao)VXwb9$1mIi?~DS{el0V{)4
zSy)&U3=A&3(mSKBq*Nsd?`4Bl+Jkog*8l%&?loPHx4gXk?8Yx&N<hms=FOY;h>goE
z|DFw~FaX{ADrZx%pfre|0n~W$o~|dlrBCPPot?#?t=6DjP8&9FJ`6gNg`c0F;b(c`
zy)BuOpPk$2!T@r>k)uZ$Pwdy;zIwH`-+a5ZmAB5{-Ce%+*^@ic=6N0S5-z5lpV!+Z
zs-5)x-Cd3NeKw%;?-`ld7R2qX0?om93aK(MfX@3kJxv$10yg3<wB=5EES{ZbE1i6-
z$1x#c!L{$&OyAz$*RN`F&AhrwH0|uH);?KlriN#2&hzHY1Ldj*rPGqXy}1cG!DyCw
zK3{!(y~m`M88ak6n~Jo<);Q$l>7|{Uqgk~qGBq_d@pzvsC~w}|TfH!B^~IIJ>Y!ux
zKqo@l{rTX$`uFcc_MjnN&=G;#^X@V*fLzhc#>>D^Sy>6%_;5Razi!c@0??f8*6iyO
z=FH*Q8nw3gPLy=O+OXuy%X~p+%Ym*_VF0Z)0CgkR$J?*YlW8#5yKwyCMM1BnLS9RS
zK!N1q!V;n-Dy9<wx;tz^+1p#7adig=hT9W5I#x`8$9>?M2*bVV?=37XGwWvLtOYG9
zF-$&oLQX$?oy??3lR(Q(#NSKhaCuJJQ2YDa^ex9WP1TQ=1D)Hq*uDS3g9i-O*4Ae?
z?%87l>J5Z_PU(E}CI@tWXa3%=Vs3phoC^P2ylVgdh+7+F`se5K`BCquZ_T*9O?T1a
z#h|0k7+&1pZ~yG<Y<6jB=_gO0f{t7J@b#<co=G|f=hy%11Rb`UcXt;<!^_LdlW%X!
zl`zek@@z>eLqS>DvET3a_gfY}>zJh_16nu<8tpd$_uejVC_E7YYSicRfCqtRw1H;|
zq|EqccJ(GpfhPeW%|1xq-0;ox_`1gKZthoCRyOy^T7zoZ4I4LJtm;+q<lyBM-EyIZ
zPtJxz;eYY7qoAFEzrtg4a&&}*g-zw{tG;mDyLYdnudl7YzyCn$w55J?tw60H&>1_L
z!OIv<?B5~502;j!)eg(Zo0r53YC(gRHiB+JyuMC$nqF*|UG1+0IX5?fme+u8MZPGk
z>-6^4R?vBRbL?uRQcq2BTpP93<akhUuwni^n>}BzMKg(a761KJ3L0PoEkCJ#XgT43
z?I|gJ2Y+8**X!$I3!j`26w!~9xw<NpdBXqlZyPok=tOVh*<JqL?c^j?R(;WSb3KDI
zH*ZQVcI!Q~B5*ONb=cD0?z}W8@z$2i8FsZ+MMXs}{whjJT9e=j1$1cvue8~Vy@!_v
zt-SJc;Yw4@*j*;z8<PM0`T1ERe%~HR@y^m`XCx=T`!Q?g%+4P_Dpv2e)?wINZctuO
zuwj+@Hqfbypabnp>`mA{z1NvDYgU)vT&smiN4pq4`B!jpb07Zo^|fKii-5r5)}JpH
z_Y26%_O4l@bK~}H&}t;`TBX`wB@92+Q*<IXxqR^22pW)Bu|i|*`_R~3B^y@>^D`*e
z*~Ps+a^TcdZDxi$ckYzLy?*wrZOayu&AFQ)ZU5YyIZcW8pMbW<fI52W^3umm!22_9
z-LPOi3|f;2S>f(y2k!p0Z3ImhaJBVL?uVou@9BD1|9oE;yZg(&V^Mkz`S<tPs(3oN
zxv{-@^TtH}bl~c%6I3{N?%bIclNtF$k8NuiXap8itxcKIa(cQx=v4KqtHa$}xkO$3
zjd#n}{a}=nlLMVkxM$BEm-8Dlj&_TK4!J9>+Z(bn=*9j0`x{)RCI0yE5Y%1)T@O`J
zSqU26UZft`lX-dB!xtA9&#<qzbL*GueRQ;&nE^C@R`at6v|S%G5Ob)Nn^oV`{@#uS
z4}yY&K?f3orXjMn-g@=_Y*R<ai~A2?6Zr=~+4=SBZu@^fm_ZxH{(imA2wEEp+Q|mG
zgsS%Uw}l}qgPNvyJ$(JTdu#UfN6q|p7c9$OUQ%5Xxf!&VRAhrskF<H7gw4E}Gdn@c
z>{hSe$CO}OZZN(0^)=m^k4MF!%K<>EI6-S(JUu-@8$LeVt9}of2UwK8uLRWlzrHRu
zaBo%V+~mn>zL$2L{{8rP|HjPAYO8HlF0cFhYeoG2ea{|mN<9raVOCR96Ld87<jIo{
zls>Bc^YJ)nJAPc;yld;VMYurM_<-673sRpg4_m!3K*L1d{&#+@`nQPBC#S;41d{LD
z90$z}A2%?AH1<GyjX?#&@ne;JkSNcY^BmR;fJ`8QS_`02g?~5AuI2py_m=@w2(In#
z<az|UUw(bu-hl0Su~W3e`JSGddfBS(-=E5yySuJt&HMBBAiF&13<b~ys8Z&6JqHdr
z{P_L*_1?;<rj~VoEEqtS)J4fle}41z+LIF#m1o#g8malrP^juUdUH>uv0I-^CumLT
z>+5gdzBNod!~)vP1G*KulF=$ZCSjKN{HnTdZz5M*%`(Zp#v@<*Wn$?4AK+LHlBnkd
z4X6utipj|IfEt0`({vn@l9WKFP)}C(S5j1D^q#JF6m%x0jEqjzGK1o0XB?}ltU%kJ
z&)ff(nWUm<V<Q8)WOT7xZ@@Ai$(ELuj(M6fVPRrU&d#9ds`+x!eMRhUvv2S3=U=tY
z`1kw${);ODm0et14jewr3|h(U=f}seAZBNgMa_>5*J3}#r-HUp?k;=lQ<eMr+S<Zj
zUtUh%vm!$?cv;WY`4=`P9ApBW<OMpOZDaCr&~dp_rig&nmw_hY4z+TxeaGIInVDJf
z<HN#d^$Z`LoD^OgU;X2QVo-1}sDJ|v--1SMb3s+Yoci|O!^bYR_a;k#H`!-`r}}Q)
zu=vj>-QK&HAJh`;D+E;;pv=ByW8ptpGrqsUyUX61)Gxb|WeS>=e0Fwrc3teddKdj!
zX1P*+bFEaX|D2g=Jj1Sbm!x>-){2iwcXpTagASlu8?{wHNT@06>Z*mYyUQZB=gqx(
zZ^J53i}2<q)lHi>Z?&8D`~K#~*G}BLDS7VPxkc#_OO`BAxw1Ao{M(P&`TIJTEKxDm
z+av?3VnM4e5)ZL}T3T0EhhP6~pZ(>-L+3RyJB4y@Z)<IDX9rDC_4M$74lV~Z>vM8+
z?0!682Cu~Ra&ZYs@yyy9rCY@Uj(f>x&z`mItNpEHViNNHBWM6_wt4=sz182(>^W0(
zXK%GQXwCY!x3?!wo5sdaP*C7-exB{euh-)j2QBq#67Rw?-!juUJ?iUam3bdOe?I*4
z^K(IIX>QL+pgT}z%#b)MECSj>-O<4jv#Z4O!=>rx&z<ATzP9GzgM-bc`@em884T*u
zflffmUcYzQ&#%ynD^8p`C1e=7Lwvs5q!}|ha&K>oe0$j=E@XFE?v-`1(zmzeUasB~
zzCI3gX^CFUj)Z5aNg5(tbA@@XWNp1SnQz|Ts=T~)JD-6zG8ck}dj8%p2aWtCKYno>
zyey!v7SsZ;0WAmstrxfq-j0_68V&#z0-#wsd$T?>@LsZzfXK*5&{k2<Mf5(iOgz8H
zbT0_d5Rj1QIMyr8%y8-QWzf!69(g;N{5>Dr&b?Ok+;mD^OdGxttg3%~%uXTDjGmiY
z+sx^aZC}2Wfa-p&sazK?UOaK~<V73Fz182}RoPFEbN&78Ei=Q9U%#?ybIxqO9z7Y9
z>vosFKQ>X>Js~++xvI}~W$<!7P^T?+ciBtZch8@<uMS@i+IJ2bV19aPs$u1)lpa~@
zurDIr3xigg#8=O^tK|w05C8K1zPzKOW5%s5D_>NCI`AUV7nwUi;KUBlt+!!oqc$DS
zzP@g4rBeIWqT=GiZM@Q;t06$A`swTQgLbHIOgie~FRZ4m&8;1_=D?oH&jRA&?D_fm
zpsUE^;^G!9kL+n?=Lan*)6>%f4UV1rxGHq@qjz_AGfkTr|MJpOL3#Q0U$c*Pi8`O3
zXImOKd%}c<pru|jvuC;f{QZ7EXf@ZKJvJu!_hiD?#ayhE@{Ed-+V}TcG-#>+v0iBj
z^Sn843ghGB-`w4Oy{G%gEW_ls7o4t4;CVI3zE?<l?g_ZE?n%B6YVtw$y+Y=0Ad5pD
zgNA?~gU0iZfztx7w0n3n8!y+FD$hv;pyFrCF{7KeZ!dOg<=U`)ySVMqMK-%D-ny<1
zTYKquRQ4{0zaJhRwy5~9;Mrr)veRR|(pKxeJv|*ODlA@IU7dccblOpP1H7}d6SN>R
zL`&4}=M!O2ZETu-ZA({o>i<f`ou+XSd8?|vzDm5kEjQ!N4#PGc$tJDPRWJ4m>~-&#
zW4hL9TJ*%jXNCde`#qoeK$ri{GR<ZJ&+cBh5a8nKn)vWgYg2d^s5{%z+M4*~#l<~^
z2mf<(ae>x&Jb3@Uf58F;(8OU)K4=O@2tHnOWkn#fb=jK(FD@?rDtCWlGW)9V^?A=i
zr-8Or=kNK*26pNU14c75GtfBUi%6%`w6vt7U80~C#-m4%K$nPjba2c&v)DZ@PEJNv
zHnm?}O)csy|3hihtd_af<+DnT|DJ1Iz9{i<TUtbFCFovOqtsIww!KeWK^HT*xU?)N
zP1?C@my}K9^Di$i7Zes6K33XT@n};fc;Uq^Q2c;~=x4NnHmHF|;(s55?2v^N*^r&f
z(Cpd+8m<TBX2?MOt~qn(Dtb<OAu0C$Zu$MApq6CT6^$D=Z+6a8zVr3<b<ln&&_4RK
zv$I$g{vY~%;)I8bo7=0}+_SSx1*N32&Q*$?K6;cDbZ6F$jmd>yUxnt}*x>k_js2R_
z+OWqjFE8H|pS@}GW>9}=^`BdJm;1|~t?vg7_svl841l%zp3PIcv!n2F!T*1?IuRQf
ztjpe9uv!+NVUT%ArRK-O_NHr{N2SGIaB*{kG6L_v+OCd{j(^gKNjBRm6HozO^7fYK
z<Kz9;cO8EI=xDc~tZeU6@9A7|nr(|0D}&syr=sv;uufZhJ3Hu{>kWy{paWBjjrtcZ
z@3*kFo}E3<HS^96!?O4H)_z~IbIu%@oI5}2-`uSX3Hkc}_{Zz4Ar1wscN_#wUcSzI
z*Tp8bW72P<2cNErsInSQzccmFnKQPg(~sm{2)M)&7;wbvi0$?DUDdM|EfQ$rKK=La
z!}BXM(-Iiwo`0}M?s-YyoodVHwKgpN?LTYmqAzSp^=6zbIdA@ac~F{8Jv|MSIIZUY
zez*Jmgb5QGN?%`-EU<cf@UlnA>&wge#q{HN($mvHy~U;8)7cn6JKJt<N{!f@)_Y7p
z;AQ^x_3_|sG5v`JIWl)|Sj@U%@hkEEisZ*H+ItsEOE1sx*;shPyfXQ5MiN*Ew8_-0
zFE3}#qQu7=3jg)?F7E7IEN|9lW!6`B!(tX_ach5o4rmFqb=ez-ySqw3(^MAL)`w4>
z@_M{;o^3VPjB_8duB=e3Vp(ij_oo81`eKvL;;gHyKm#Zy`}9;ionBsA8v1|Qg6ZAs
z<ZUV%K-;UXUKKS?KWB3D>^df9W<hD`?rw4YtiAVF1S*5Jz;TP|7<@>1boAJ<F1dp%
zKt2D)#>S4$&V!&mUwi)4y?y$$byetUu6cekc`*wz4>T}Zy<fU?Dd;XG(4k^;tx6xf
zeVcpWWJgEGJ-bOdr#HP&1Qp#K8ugpg&K|n6vv}gvsY}cDx^xPG&SE<G?-CP(TaQGe
zw0RzAE!P(fw}WTS_<T*TE$22{D!$;qrj?ac?C!Fo9fHai_Se^g#>+oHJG)`~_TzIb
zi$A<xzdz~!zrPvR*Ufzqc;6y&8ff_9$gyLKf|vV&CL8uveN9MCZdUi7_u$UX;v0J^
zjTbFm{P7^We8Ty8wrV@2xAyk(f^M#DXkb{fWC`eEV$f2$<;&H<w~)`Uudkbzzo<Go
zH7#vX^!7Z^;a563IwAZ2{Qi92e&XD@y!`z9Z*Fbv-p&92^i1P)gYtJVpv#=~<Ms&H
z_6dNKz$>&QP~fu{k_4cs0-gj8fs(+dL&pM-AG^pe?Jg_rZl5EgwWhu<|Ju<jV(SC{
zt&7{+b!w`1@xq;QlO|6N+?o}7<k+!Q`_yNz0xghU7@%Nb5%KzO<mNQTl_8+h>DlJ>
ztf;uPzkYw*`O+5`9`gDpfySIcyZJ86VE6)C3jn&+@7y`R(!V!0Ccn70RvI)`7B%Dk
zw%q79H#fV#K4$IW;xffv&p{nLe(EM?SJQFhMg-^>mjkC|?d*R%VBRWz(dXjB!|jGO
zKMFu6a{T-E&#L^@zw`C~loPBD&$g{DYn*rf+__`o@iiaYmKoMbo9DR%1PENZbSXsN
z=Jci>&_c1JU80rmX8hV#`R$D)Xe455_H`w5^YFLxbWVeAM7Xffd1J;!rOCB{`(k&O
zZP>ciH6&!pvDsCdHgCST#8cS9$_g|9x5!;I?fJR69esUaw|jRLKR@^4+S=JC_X@uG
z^Ye4W#w1oy0DgLUda?g}JJ8jU3=f{1oD4dj9<*~#NY%?>VZeiS`8olcjTSjFZ*N$D
zVlEk!d7t$6PPR8YcOM*+FOGp@NFEeJ>h(Eu{%kD#cMKe3=HPt$53KQL^5Ylkwzjh7
z`S*@IKHk6ZZSJLIn>HS{m$j(~SpWRi_Wb{C>V|xcjg72Tag$VZ;`aRD^>xl~e)1$G
zWMz<RZm>XbYHDihQt#=H9{1Z{tExXc%M^6TMq1jkMs?-nqW}N?I@Qi=Za$nnucd1-
z=yukJhucAGnXjz7zA~5{bdORCr|^X>nZYiuu8JlmBAe6CAN%t1GOMq*i%ZC!Ldaqz
zLDA}8^A;s&S(hF^a^%42)86aT=iAr!?W_Hr^!(i1{0gnd(<V-A1g&UQRRvw<vTohF
z58uAEtzEnJ#l;rTI{QV77lZD_1MN23uyt$e?Ag**rLS1j)zvRP<~(}Y!y~@4vlDcM
z#pd+$A=gzr4>hrJPnbKm7j$6awQHd1InV&#RIN}JKks8*y^H&LgALwD`+~F05`8ni
zy?i+`rJ%tNaB+F;m}2e5!WX3pk5@pZ#D%5Z&CUGo1qB6xCM9z2?~8r?{Z6>F?Tl03
zlP{e;bH-=u%XT}TpRd#2-r5?myG(ao?Cxcy!R(%sKK%Jv?08v{e_q4C?OLI$5*{3A
zoME0n@7izBvSd(Oa?YHb2Pb*XpFYh!NhR_7ySoPF=GRwGRP{V`Z*MiP!Q6=T`}oDD
ztgO>lD?NAa9H^M_@aT9Im6W6uwLOowzP=t*x0UWKetvF8@pC@E`F6TVAxcV%lKNrG
zjwXWIo?2R7Z%roY#qOGMhVRO*H8DGb){8Is`}Z%eL2t#iYu9dUOm^S5e+%exikh05
zf)5WIC)X7IdwF^J469Nt8ylMoYopCCK9<<pEv^qbdA<DoJy7_ADlwzfQyp^N67$>^
zy*o407@Y9q_xE*)YA?#azYlbEoJ+rI3}{At#*B^)8w^0(@qc}N{o{T8|8DQ;dJkV-
zUM^u>rUTm8wJG&<m)up24TW2hL4p3HzZNv_SPF_2PzL#xd>@h<PRfJVjlBXV{aYIg
zzZ^eyu@@AdlkLs?4sIyCvazt__07%dWp8h_9ys8zWB2aGH9tQ^%{Tr!KUQ2XCg6AF
zzxn_FxPNeIOHWM&%@1wO4%ZOj0xiT=^_n7JJMH4nKcCNo2GBw4XftkaTYK*Ra!?<K
z**~qOg6Y?Nkhka8{o>^0<OH1rbPE*r3rk;LdvR~CwOP&$g$$>|nYXv;s(6B?YZ4L@
z7yh!a-~aE|YQ|;4ukZhFo0KZ49lq|!)z#sk)pl1_2D2YH&G+Zyarwa2VY)wl|4s(&
z+Hf<I$cvd^pPiiznq)ZK#v2?v+qT*av<OLFp1-`j{OVU#?`a9Arf7mDTRH+eJ36{-
zVdW-U+@6X?&><wp`(!7iN<KX`m6>75vSm(_RKC2p$efs%sP^^rhUo2i2k+gJ3kwTd
z<ZftncDDKPoyE@u1O*%WWUaGm)l^kkWv$DObPB5*)c>pLkv2bfAXuvX(o*l_kB^T2
z`0=>kwO{GZrqt7*b@nPMDxh7|rM5;!LZB^{VPVs<)QiQ%#Z}bQR@tU!85tP~2n#oB
zhp(IQB~t~os(E$TS`)waS?2k2cE8^kH%{&h-<age!osp*@6AV`bpX4|-WufHu{bl|
zKK?<;v1V{fMOxb3{*5#wi|#oBiu1|#-+Ify8TeNsD9MQMNIzEvw{ZS!1f`-EkfKr+
zoL+9-ym3Q8LBZkq%H7NIo}ZfwTFRSuXUD>_y=iA>MQli5tf{Fv!lUL;Rb{25q_iMJ
zOHf>#JvurXbmACSE0dg@+@j;gQha=Tpoz3?xwqA-L>7a#*zMS1VUm9@=DAaCFlgC1
zXo#xf&kw_@@9)+|wSbPs2koYRdV2ctiOTMviKK&*CmGH(&zB2Z8`bLE&Ij5&mi7JJ
zy}jMra&Lofw3uO#*tCF?w_RHN$@-|RS)k6{t?VfIx*v*lKc9*(S+;D|U+dbtyGlXl
zeS=pdiB9tY?^bckKQ%>jlZxl37Ea+O)!*N(T&J$Cep*=FZ;Gntq~*S|)e4*r8yg!>
zHqXDOQ^m7*%Cu=}=K1$xwr$xmrTqQ9wT1t`y}kWu_xpX?(Gd|RUSC^l{HMX~$lbfK
zd|X^YwrznwJ{;zM+9zwhD)#iLQ<G$6WKy!Tvn@?bLhQ=l%>fn4r^Up?KHb=u%<AiP
zY>9inT+z)<sZV2fmz|W9l>GGa^75z0dZkZ4JvDW5{GJNMDw~C8&YXF|D{ZzS*4xi-
znyTld#fuiP_@>r?+p)Vg7JfOrFYq|%oWsX2jvYHG|J%(P6tgma!5Mso!3~RD8w)=j
zKX$PX)Yb*HUP^Ohs$}21ef#wNzTbXdB-}K$w7ksB&8Nr4#5~zq{QQ)4`MW9Q@9t=x
zpKBdnR#-Uk?AfzVU%be;n9No9{+?~+#YL_~pP!vg^_=u%Rp{zd^Xq=Cta)?8@Zw_5
z^yFma`u~5wFFI~uB`GPnskyn?rv6{e#l;e9qqpasto{9M>e{tyQ#~i8cuoQZ%Fg)x
zb)R~r&0YG_xA4i^>D2%IdVSGxfkjncUwtyaU$gl0zde<opS-%dTDm~VC@n574rK4s
zIdfzpr=|XUcX#)urAwE-dHQte$2VItFF(1pHCwt0v}I*`Tk8wf58$YtV!t$~^I$W3
z_M1y@A3SJSzyF`q$&)8RH%Z)jDU)yg^MCnvb>GxeQx5K{{r%wS)7E*m)k(Lv<-WMI
zl$$|8Q<D>vnkG%2EGQ?}_wMd)?s;KrT)V{<7C%1+x*!j<@S2<Z^567Nt=!_EvqiRM
zv-8OuXlCaJ?Qr6evyor`jo*SMUqAyehg!K^d$L3>UA|oS`I)ax-Jgip-xrs?y~R1>
z)Ca#g7L5%J3?*-Gi85SR;K&Rbu>{?ER{zgN$}~%*!l^JNvTf(iowv4z%ST5=bxEAm
z*jQ+?v9JWxhp7cu(K&ObL!){ha#VwMtH25Yvp%#!z}?#3-X64>nuCKwz_#n+&qv+*
zAnQR#%7G><U+wDe=Lby*fU?}TH#cA0*tqzB=Ft@)D}|bxngm2dT0o~?g3h|pnhM&t
z0-DD6nPU<7rQ=XVMFnU_At)(ayLN3tYUJCN*r4Z6p0uou-mYYAEnWZbr#i!etgEZk
z?py!7xxd~Xba>{Z`{i;r6%FG0aWD4#e{_`FrsBha24PY8&dyHI3MQXduhTv~Ir-ts
z7ng1^UC_GMBS(%rINB{PVO_T7*yf27Csw@Q`<=zd)5YaWS;9fcL3_-g?oYRvZppp;
zi;Gyd<=jj<(0Ss<&0DvW%*@2@-MjbV>T2<AxwqNe-Q6pys~^9-yu72Us|j>8o?)xB
zQ3}VIGiM&Wf8T%LfJ4aYFyF`GEt6CpetCJhNzG)=lqn(>mX<4HZ||?SSMhY}m$SXH
zZhPis(2}h-ne!P-mMls5^5Wu+eYMs_MMVsIY9=pK@yx2PD}A3^{`{OQXmxznb<m-b
zCpPt5xf0?SEZKi|clqOcd#hLV8yg!ddI}vnd>C{G$ZA_{Pa)8ho^!tjXv1(<FQ`C=
z^hRIZu&7La{G_+mx%J?&lk%YUFC>r8*|V|m6Zrho$4~k}wf<sxGrxOP-{18%v-2-X
zKHeu`n8Y$?&Kwi7S&R*8zOy)H_^kmg6FfJ^GOPQ1JZMf1RDWv*FXNbTX2+6c%an9=
zd0)PK8I!=1@blBt51&3A+Ee-2An6Fl6zy=oFCK27Yw9~XIv%u%|J<-)gTqp<sh~Xo
zSI=uH<<2t8?K;{me)#xt_OGw52JbHa_9havQse9_Q(=?2g~msFxxq)Z+}OYf>W!Y7
zs{QcEla}}Ue)G+>Dh;aE)6?U7es1pJ7EWOnU(j&$A81oK&=7Pg!H*xH9(K^{zs>CY
zhb~^ccp$j*c)ZV(v&W9H85$bCxUo^W>iauhZ*T7@8i7oOg@xb|%#S@ztz4o38<SkG
zfVLNF912|(;`x?$8Uv{Fdg#_IDPC!_klk^cQaq>VL|&TkShDxw;dan5nxNBXcJH<Z
zEyJx+Sy)tDTsn_$>g?ItNh*sMg=j4d(K1~JDg&ji`+V#@%^>YAZsvCn6i1*g3uwHd
zuXnOJNXQ&iEFU{|QW_)5F7`r|fcrX$kDsi~y}fOf{qbYRvhJ8aW&Jg6+O&!<FD9P*
z-7ja`v~=lGMs*`O&~0ErD_tTYBqmLo1iGv-aIqWctk<JQUB6VYh3>1V?A-^tatL(Z
z=gG<HhmRd|dwgGXl8U0L>d^_wQmu{5?1%2(mzT9FInW`f{NT--HKm7}*m$KlX87#^
zr3%mq*#!?6APp2|e}8|QnjZr5Yd&!v>ycdi&31Oi%S%f^SC21t>%FkAwi-0X&M;xh
zlon80^O<QBu_>kVf#%5>KYso^c>cV9uJN+^&tJZ{goRCOR999~s@h!u>H7p4f-Y|X
zEi8L_YU<(T^Xs}mo#;s_pj|~57rAoq^B;e6bF*uIW&vn;?aIpFuT^1_RATm4edYB}
zk@1^nv+`S^hX)7fYOdek--9+<8yFj3t~e%AUcuh*<446sWr<$UCbGZ3zJi(sIk~x@
z`{iV8t3*J{x^;A}#M|wt__*lgzL^GUYHXmz7SGPkR<9CSeDLzZExYUf?s_5E#R@J)
z--5fH(9wd<-o>)g>h*7=@7}NgHM9?dJEQ#4?!waU)@FYHzy<RbP+1Mnh}YIet5>ls
ze){rdCusM4^6|cmtE;Bo+N<o|mvC~D>W5FCgiPi>yt}iQJuxv6v<_rt@N!UM|M&N|
z^TL1yfs5T19T#5aJzeikg1i5_ckdV)xW)A{{?5!hB^?Ly&-?xV?Lemy?5!@(xwXZ!
z6f|oBTC;y@s`gHXxmQebZV05Go8#!=!LexZ;?V!`mX?;F`@TUlg>&Z2Il|}Z_VT{{
z_LRtD&FuUE3!PYd>p>?x1s?R=q;q;vy8>v~VbPwaPo5;)*pLX?TB_pNG;^k8!}R5o
zPHgG{Ehv0@YwN1l%MP45!_zBe>a;cM>X(0WVt1GAJ=odPK6B>GYvN&yZ}oS~dZoX|
z<L=GP=@-{T8iQs!OJ83D%^pseIkWR{JOAUo-|q!iU%Pr$bl$vq5qqn)F33DuSWs|a
zP2^?)0Re?7k;MTQ=3D=%bN+wq*hO$t7gP*F25Q>7nrauzf_kHTqM)NK!TlpGE^zGK
zg)GkcyP<H!2GHDp*xIOv2b<Y5?(MMzpB}TL<fTxboGlkSJ3HtKuyg0mC9#_d6c-mq
zL`8wNo(5=$WL#etyN`RlcF2l^1us`vfCd}my1%ybN~bks_IS7R$%4jiWh{$WX3m^h
zP*4Cm#s_o|Cc_NVY%#OEI~hi^jYVBNJUG(M%s6P)_O9N3f?D0(72bY+ZdX@@3Q9|_
z{<Y891$0XA+ZgabT^D0<adAsqThg5!g`joZYooU_Fqmdtad>`i?!^U;%m;<L4D0?>
zXozrKOqP&+_bSc+wB2z_rtqRgiwZ#d1oi*le|2lCc1>+<VqTtJh11~`@%!x_J$eM1
zW6Zw34s<G-gniwfW71WR9zRaZ&F!_T{lzgWL<ibLs0lv*|MAO!kPz@F3@DW!-}e*L
z)qsZUx86Lk%&+9fe|n+ArF^2SpzsGZJO083WZJn_r=6W;QT&Vt)LL+HcTawOZ7oAw
z-FZ$fu0zk~*YmNnvmXqW>eD$5+S8?^q$D6HxbXV(f<*bhmygTW>r}BUE`4%Bu%)Ht
zz^z+S{`2jw?s)&=MaS;)_gpi4dI}#Od-?ax#l`OTAE+GV7M~X!_+d_%lG38<?dp(&
zcLO)3q@}g_&Nln#Ya61HnVAVXr)OjG@r3MbZgFvO2L1azKd;BvgBAmW_M)7cqN!XF
zWF*GP$q6bj-n@Mank@k>a;p6tK3UC|#mD`aih;ofhx6W(T8?&$?_Zd?!Xoi;K;TC3
zDG{LY5>YYf_O7m8P{ITam8{rs!vYkDT0CZc|K{0Nw}Iw>o}8Qvy6G)1Z{4k0&q*7~
z-bOiIp15%aXpqi6{n?qB`3XXgmxXA3-lOj+q@%0*@WqP`w_YjG>QA;=Jw1^(H>C>7
z$n-2&pa2;zjeE=T<-vmlP>+~j&PKpyW#WvPGeuuidQS2wI}ExR2Q>I}eO>I~$H)6k
z#RR=4wX9g7;dogx%+XvAG^>8H?(QFHe+SUwzP&pjXY8$zuq=NkQ}+H|ue5m{L&Z+#
z(&K%yppC^Fn>i1df4%S;G}=@1|L^yRJr#y+{POF5rDlYMiGi-bIB>uLGy)D<;%B2N
z*<JrHDd2YA=}kJbzvwf+%uh>8o1o(PK6a|_-`8!upUutqL`8ptmQp(ZN_zaFAJn*Y
zc0CI2-%Qwd!{Qfs%p)KWa*lf?=v;0a8=Hd1$9O@dM`mW`ihzYopbcx2Co@}HTZ0Z|
zy0tZXk-MsvSlm{l1(mbj*su4V)Kc{HRN|{ED_NsVBJbGN|C6yUdvl`ra5v~g$qOZq
zKvOIyPMvb9so8Uk>C1Be`HSlQ{sP^YtfZvm(w`;J`g7)*+~S$r?_OIQ{qXs7cF#!<
z9zAOM^z?Lg?Yj>T53|kl;mL~$s5p7@BxwHY)-iDx7nhKV80cB3JT~?JWd8m82b$PR
zi45C&V8-m(+@6y_8*fdsuPsP9IjKqARA%4G_PBP?+<*D|dshCdIeB=FY|Fj<;raY}
zsR|>bu-DhuUw^&xU^Dyvhn_vm{_U5}o;t-fNo8U7^>qOnBA^aT`Jd}epz#1_*Q5JD
zCy{{aDp&`RPgGR8ovRsK8%ay6*MoB|ELGkEZD9EO`@6E0m6V>I9<=bfu*_E)bO^=i
zX}X~81K^|f7w;={Zs%)N@dWLeJ#+RfXvx)HyYq(*F_o2-fo^THDtYmtZMjG~=&m1&
z0tG3v9E~cG#bvLqXo7YqfEMsNI51>gUB$}a;pKJc)6>%v=gsSL?G{tCw3Gx{w0{4;
zuBWG`AHIJ-{=<{}duyY&Us&kO4!ZAa+qP|>LAX=Xbi21~F*&gbw2&TDAZ*XOD`dOs
zpsZC1$Gmy-K;Zy7i@xsfuf&&^mTE+A(*eyZELozWqN1{(@bR%l?yAZ`yUTKK+_(YS
z)*8AxOw_io;LeT(A2w~;Bp@!{{_O1R*LO~U&i?vx9J<8mDEN?sl#@a%EG(e2mkLTt
zTU9)F6g}kvUHmGl9R@mdv|CIU<c>RgDuus&`?g`*HZfZ+(d22<rh!IKn3$Nh+>75=
zV|lDsx;_2;Jjn{9MUNVnJHG_&tLf<A(3t9V<ml0Z*RF}}t@_&Jv=FpW@5RR+Hc*42
zy{oI%Iiv(Un)5UHe#Y@*3l}9l77zv3bfBijt&N2%R@|^~SwDa7Tv@kXsaE}cKR{Pt
zH_e?Zo0Oa!%Du9kPqypHlN1+MSI&7~&K8%IwauI<sTaGeMM%}_z|EVHrAei6pkrqy
zO=?O%KM!;><_wd}NsP-(_k`EJdG?IW-rk-^!hiv^=H$4M)!{bY!}9fi8fVOq=&jzQ
zbNKdcY0&PiS*F>b*?+U#TMEj`%<1Rm2pX(S{QCaBeD(Ktt|1{J_bQ*uUTqU!8@2V&
zBG+!vHf_*Jo$J=ETjVa9bbg+#glU!tczx=s`hF`*%fzp*u7VmxHj0wc+S=NnQ}?WH
z&+wRi=8VskHIc%g`_<Fu*Q!;4&I#Hs1Rn1Z6ch!W{{Q0A((ZG2&#?2!bi8<xVN>(t
z!hy+>{d4BXfKI)D6@vF%)IEik`OnwOurdn!`s!-);>F6Kot<Cnj`zuehN~X@`S}?<
zb@Sk5z%Nffzhl#MqZfo|6~4J)7_u^m_3y8*%}xs)K*w$OtBZhhl$ORf-oT5X@tI>6
z`)U`<oAHT?NVl(e0ctot&Hzs*wR3g#I)C{U86BPc^3qb!`JbRk*;OH$E$!`~?i54A
z)z#t2e|~)Q@b(tASy>1=DDuO@!-C@C%cE?5ZQEJ&6ttkaM>l#K=vcN1Dx7Phwl>Y5
zFaPVy%jPao?Jl{C8X+qJ7~|`Hrp}wa6m&(ArluxCL;n81VxZk(mzVqVS}qePD=U+*
zEK&iTRkBt(4z#^hQ&aQC*6isIJdd6{d-mu=W%q)or$nDTdv@sRRZ-pOZ7r>>tuHR}
zEGv6^t19>3NB>DG4=*kC&d*SKe05EvF=%{vbJ|%UTP{&!K0ZEBd&gW~K}o5~*=PAZ
z@C_AR8`rGS*^+ZJ==tAkYolj>(boZ8dmgv9>fyJyx2^p1AI`4wnBCC80NSAjx~}@h
z#^jIZtlu**fYPX{_cR4FGqKatbcJnHJ55Sn1b9pWU7~aF&K=OYva{cdRXh*f+M3O4
zFt_6S`}^T@`K~Vam!HSC)Oo4bRM3#cf&~ho0%W#%ep}GWBae=Df4mwV4?YUaU8D`v
z^8&8||8fxAHM0kmjOITf7l?Ss=YV?EUk-x?(<a-Sf!dYrUk)DAobl@F>c`*S-ezFn
z=H?Dr9md<)*}01Kg}7c!!_uWoPY8Cia&vR@NEkd=8(YK2ur=%Ip))g$4U3=o%(1By
z0xg~b?OkqYU|?Zo1?^%5os|3WW8>7RQ(qLeo;-QdF(_!#x!<65S!HG0UL|{bdr$sZ
z|K{q--3*{si|3>d*W>F~zT2L6S4vpTN5FJmpn<Wm^Xjm*ptEu=F6Owr$d$X7^~G|(
zxradKhMcp0zrb&<6+_&&`%h0#58R#?Ym#-v<H(9bwV%(LgX)fJYo$S}i!VOrINHn2
zwJiPoJW#hDeDIlh3v9B4F+V>alz~7yg{tb$&$IpT>66iikYk{|4F2=&j`qn~gYJPZ
zdU~o;uCuGNp@HGf{(AZ1=jV>z+gpA0-BgW0CgZd-7k>Vio!PcyhsBJUGeL7%&z?Q&
z=<YuKeYy?nU)6xZwCwC|P+#K1gM(Sio!7?hp0?ciCFp2{En7^MEMM+CEp>9;VXgzm
zPV$3lvs&k036G!j_68T^%-O#&{}W_Tbb=kI_x)HzM*4X^cwP`RB)Wv(%<o`DRTXGP
z4YY5kVY<3N{nxAEpaJQk;^K{kkKK5rOguhJIodpZ`t*~3YVt2F;hbfX+4S@Cb7ea_
zIj^Ncf`Wpe{Xo6Fyt~TZ^To%<S5#Mb%Uyl2tL$wTXyl^w)s=&wQ@=N*crqO57S{(g
z>U84w$<+S(5@=ih<b>dkUAwxZt}mD~XHLQMbFvKj^?BiIqeMG9J3+Ic4b!>1d{Yho
z?FUt4hK7cqMctP!UrvPV{yup7_U$KPi}P=7@qGJue*Hhm-DPi`N=mjI`#$Bxiwq4B
zt}`=@k55pR>V0~8I%pLV=yn&-GSOF8S0BD}C+4lB=cEm#ufrULrTEPCG-hCS{=b^e
z0eAlUIyzSTn4A(Dy$<AG!HEX_a<)Oge;jOP2c0|t+LClqeg1;5wNVTWOO~kAe7{=`
zI!Iz$-rZGIg%__xL`8wta?P*(HuFW`iWyZuJ}7>Bdwcn<gL~b2rG7kU=1)jZSFbQy
z^yuaM<<6?Asx!a53^;Il?*FM?s)r68nlNPwi@CYEh6tC22p4E2qTKlfH$Y3P7cNS;
zFR-@`)bE%x{f0R!s0K`Uj1aMai`Z??yL)J3^6?8>v%^8#8qd$OJ^bS0V$dD0GiJ{Q
zo!cI<DTNc%#;*!dT(o%c#)N}Rpe&i0nR(%x*rz#jWEdw)&R?@e2h>eD+9e9=5u7=5
z=8E4hGf_=V%@<cz3irv|^LcxFgEBn>C>}v~QN7>$9dvU>VtP8La#vJPV34&cX;{C0
z{ezSD_XI9>dw64GGWam`1kfsZ^L)8BUg@?wcVa*nnbg(QfmXJ=9_#qSz@Wh3>Eal|
z;-6)4^5jX-4hPW8#@hSwDxOX4?d*pR9ReNOn&9+N$}ERNUS1xwG&<_N|6D84i4!M+
zE+}kN7hYfV^i);urq7^uV}{b>kDt%mCtq0Lcw<-T>T|u^W;r(+^6u{9oE4yBY;1gW
z{?=OFlbd)vC*80Bbv=&=Lv9r6nJ{<m++*E|n{*z(xw-kq&f?|AN*Pu}Z(ry6Zxc6z
zjI8X|e~+3x;z4b``}_C5Fnpm~0J;L=-|zPU8X}9_1-q6z@2$D)8WACJ=+L2pS64JG
ztgIH*|Nj@DA)>bTvk7?CDMaLrbk*D&7W$x5wr*|6=j!Wqc0G7(;q}hm&qAQZwY<{H
zAKb7A5y_FMn(MQ-5VU~t)z#Ij?Y3>%as+fLOWIkf#$d_zx3{-1&cDBJMf7&PU*F&N
zi)x2CEDUg%mI^w+Wo!0zx9{)ny7p&^fF}M<obUiOw2mKVX3z><rBbHh2s-oP$PpLN
zVv*|a??Q8@U0N4wT~S>P+Ud2bwSL;PX=+<<R9#x)X;JiqW1f9|U(ix7P&WcJ>u#2N
zi>0`@_{-bd;@skTBDTv8rlhAY_MWb1QTj@RjZdZnbRSaO-l`27Hy)g<?hm@a1a!_n
z=yaUx>tZKPn6RL5*H+CPH9w2y&E~mz`}X5cPfxSWIZ<(Ece(!;4!7)IUtUTWr}Z3r
zRLlTMcT7x72D!IPCdW4H%euO%23*4~I`kNNbCz4iwKb8gRe?F+zN6IR?Nwj1&dj%$
zKi(&6d~@z8&w8#_rp504Zm+McW!zI!d<WEiJ2h2%F{tmceDNba6%`iav@-@LV~Z=T
zrdVN)d)VKGjC&jbA4}8z<><bJ=Dod#k5#tzF7B)iF36F&Bre^4&%}&R`njlCpPHH9
z!HtC;@i{V8mwk2?YUKOQHgoM1QUx8G^6=y1<Ipa~gO@KmrOopeq@JEO!#rP(jaN#g
zDnv0Q^4Pz>zZZsReZ1^%uc)ibyKUPxP!S0|G^^~8mf*_UTQY^&c%@oE+aR3VcrO0D
zv#a#ALCy_>oLgH?s+fDP3|}wjHASNlbce;QTTyT0+}zkeyJ^;}(V1gkA9tZ8rDx5W
zH3sGHVpv#NGxzS#xTpj=ZNh)Po#}@Z7Z;Zlt_mjbNiq`!XPIVCdm-30^~;x%8#iu%
z%05uW1P!E@ot&z|37QUDz<F{;&dp7%vAfGc_ilWCak2Y~$jxd=$;l62zSOL+TJ)%O
zx${f4(?;{`YP&i*I9yy@UVOD&_8|>)Wc!9fkN7vzi>`NrXX}K2FMDvq0yK(n@%2&A
zOzz@NQ1u25-4|cE`1smXJV7fD&YU?TAR{y9{d12=EiW%Gmrk&HT=eh|E9l@O19S8C
z)}yDl_ot_(GBV7WJ6BLZ05lPH>xtL`dD|)xucbov|9&V>nmjo%F%eX&|M>Y6bX(-K
zY10<DFG*5TR%Q+h3sc)2co4J~a#QMQ8}a$f2kQU-j$aeCmFwZdhiW?+YQMd?2|9HP
zG@0?|`~Lr~YooR@FnD@`wmlu4Yh4biYz_u@eSdV68#DoW;_TV0JDxvyppc-n5wwe4
zN~-JO;r8siI}}VzuBe!cs3<8Z9ex06aDdK!`gW{ee*Le{n^I42u{&)3H6Sh}Qp}bq
zaAU~cs?w`311>M~4Yrnjb#bwKl>PHud)Zf_!FF#u<3P=A*57R_K7hwwLF-cj0yh+P
zaP@=2wLOmA3^X>?zTyLD6{qJU(7MVgI*~!^eM5Xo8Fy{nYU(vjhm%1ge4PyFB8lDQ
z?^nGGUlqc6eSN&R>AZuW%d8U<6G4|*r$mA>kzwtxk}t2XpHH!hn0;$&Ht61R(7p7n
zt*lws*RB0k-mC{{BeTuAumg0z!R6)t?lm<wpy8hxGbAdisvdz(jQ;-JJs?2f*4AwG
zDxYT134Y-I^t`uMRtkeE1#_E;g|Duz76+}@@SLocnKLVBeVpx@h>c8ht;@ws=7Mh0
zJKV&|{bB$Azy9gU``=0*$~@f5{ptIkpT(f7NYwr3xkN?HI`)iplFGy1@Ar$F$O;Mu
zemn;2)}C1C-2SO%;u(>8Pp$(?>NvezQhX|`rsUN;E&?5Pmi$;iu=5}|5!!<X`;?Rn
z!GQ}|SK{oVa%_LST&A_=)VNi_%lY(Tb}aa{BXF@BXqW?ZBG%lwyi0>RUtL|zJ?Fv(
zP-kPu&Yg-D783jR?JFoN6SJKZ2x_LNcn0ZO)qge2^z!imogbtXzODzf^y%-fudAxd
z%E~G}JYWo47n5nkeL>!?hC^Lleeb-|l9D5b+xhQ*a5=U*c)1^_c+9)MuXnb2J`+RM
zl@*Nc?(PRCcYZz0Z~x$Nzdd-vU)<g*klmm%uv18NL*`{QP!0a?-@ir2MVh3=pS-=c
zHX1a5u`X^eS9EkV==Q7B)6-m|qNGwH-CDUsP5k;mOYi=|C!#*QxTp;3`MCGXwd$On
zpyIjp^z+sBvp-2!Ll%N6DNR0N{`{3$-Jc53wIaOIW+Jv-fuNbYUS}5-HqbDs-@hB6
zo(3$GL92BBfhyvZH&tI=G=f&K{QL7$BXpI>GQYW9{dT`No}QZ8tm1j%#0i6y!kzwe
zEE<pXN_Wd0evxx)i{|<Mm-(Q57}oFiG#@$Ql9H05U}6&TwyvE|_KMij{cnwojRRMO
zXzrb-8@ftlo?Y#)Hg%)AzP>)S{V)E^7t@RB;FGli^|L@bKnn^CKy6%qe}A8uMy$TG
z&5nM4e%`fTlgC`|Lhhp@ofSVmDAxUcYYsZq5LA?d3W`;s+MpwaR)?)Uw6FHJOTVX!
zOGpkpv<wmtv49S@@LDRQ8?~jOyPF%d+HaO=b`t2+g_<7*ixw|-?bnQPb7SL^vsv*?
zDf{=gw}HD#G7nCkxDm9&Nk><g5p*!&1QpKxf4@lw1qW}nyT3Wz-?`7-E$v_vYn6TV
ziwg_QEjm9wl%8H1y&-{7OfQDR+}!-f&!3408W?RX9l61)d6)2i;}sPF1wUxP@1KqN
zUydJBtOZ{d30gQ&k_?_bwKwB?+1v{{|3h=unKM41!u|Ywd-vz(=K7Xhp78PUaZo3H
zRsZg?w_QJeRDkv>-MJ$ZyQ`$Jy}kVaC$IMUqtC_l<6J5#EZ*JQ%WZCM4(es6o|<C#
zpd>^_#<ohN_}Q7psZ&LbjEzm-g|80d1)Z#8Fw;UmZqJ2Z<sb8x?dgzU0Hx`j#m_<a
zz=LwZw*32`<9t99amCNh99-bod|^eP^2KDSJD^hoik^5dICKiBGVJ*?i>U#$7y3wt
zAm}(~CT8Z=vl%=)3LBTz{{HrGvcH|<>uYO2zPPB&(4cdA!=_D#o}8Qv+JoIAYc00B
z?5&WECa9E9Ik|q@VpY(zkJ94MrCy?-0U&NM9nfK3Z{EHYl$P%1leJ=~__?e(XsMT?
zj*icVC69DscZq<;878aye>h+N?8dEIpzgq8_kJ-8SxI4I<IPOA`rzY0?_Dqnk@=AA
zW<HN^>Fuf7;TtMHr-8y4bO3~kC+KW*&<5q@{_-JfA_Bj3xHW=Se)7F+wqL!%;793V
zX;Acma?h{C#}n*+Z0_P}jt5PzLL*Ne6nRjk`$0$DoS3K#I!vx%I`{QiX1S|=?Z~;g
zsiV95@yY9;!wnNpPErLOjx~4g+*iNW#qI_jD0_90J3~QXp<`0gqFcqwo}8Sl9<j4X
zl~2Z^0W{6{^V8FeYilGyxB2?cHUka878Di=+AcddRX1Af;K73&TwFn>pFm4YUcTgH
z;Nassc4?_M=$Mp)lchjIZz`UbUPnew^Zk~7^=P;F!*}oc)~wM1ZM_5C1Jc_YT6-6C
z*b=B$acxbcaz)VL)gdc|mif+ZGfY0lzyP|z;Apq_<H!B>Yz&~<0My@#n=P}acSm7k
z-nDDjK(P+$VXRrB6A={!Uf*(YF*^h3HU`jrm6tAEV(|yfs@r^IDFH?Bq9g@VQ_<4b
z*H{^D+_=F|@soRA_?|s`K#N)wH%m72N}DNYXmG5J+Uk^$pa81!84mpa_uU>8+m4Qo
z8qwQy*!W~LDuRsI*!g4xY?(xjLDi;h)5S+G19n|q70PX#e(uPbnZ|{mo_K<e7X~#y
zn3$LZL_}Ef^YefF`gQ2|adyyhyW^se@tBw0;MEPF#fzZ9>Nm6hKpK-;Jm8g1cW+qy
z1ZPvwi~;C;g)ij~4lw@s`E#XRnATKKOoOf(XycV$6uv%ghHbT3*_#`R1ztvM_W%DF
z$Hc~76`Pu#o(>AXww*gIudR)4U*<boNlS|>c)1_wegrYS7>$A?L(rjMTk`MAndjXB
z6<DByoxgl3VQ^^W65UYpGAL$u882wi*JkCztvNS^Zg0<b4+xlWZ10&fJ}qr+i(+?|
zF{ueBUs~e1$X!EB&2J8ew6rwn-iJGPWcc{_vcB&wdD-;gLxJPv&d}|7v2$#z!@d@N
zes*?a)>W;N_xEIX?%WAF@FDB!D%Ap~!hd@U4<79n2c7WC06Hh3k(nJd2sHD_F;>ta
z_bt}t?-&?B4c=9utCb851Gh5#y|mPO!<H=~mP&$xfg6uOdv;xn;o;$+q4?nCeyj{3
z>tZAs85w67CbKal{QB||bW&4LP>@TXrVnVh=DHZmH~06;KYR8p>w8gA5ojcS$+BgS
zzTdAGH&GP4c)N4CvuKab>5l&X_MnxZ<JaZv>p<tGft(K-()#vI%y!X1@TwF=C86eC
z@TygCWOj5MNq7u8-x4&7o+G2A^f)0mw->bS<Hd!A3=N=_)aUL0AGx^LopH~dDbHu;
z?>l&Rce!g{rh%QE9eAzwn>#x{^ZF*o$jHiq7QCOCV;Nkk3t8YZ!zh&t)ZDmQ8Xq4o
zV_zpTT`yM1a8<y*efvQDc~B+>olAP~pyS&q?>mLnK{5aQ{Cshnl@Dd@Y9v4t>3jC>
zT^OLTAV6b7#ziI21&sG=KJ$X+jayn+CfiP&u|+$2n+_;Latf;{sH(Dl`}QsCzdz{E
z8c=uOR$KhCq_3~8f`U^>SQu38%Ggv0#Kpy(ICqYXVaDv)$~HDKpl!AfJbBL_KhB<h
zeqQM99S`Qmn_ph$>s(Q>!}H%9rUs;egNEt#@}HlbJq)@TW%lfD(2>XI&-2^=`Oy5p
z6STlp-S{Fi<VK8tpfgWz+=#e({O_-?hxb%|2F><@CIq_0beq7H)6rceFNJ=6dAayw
zo7{t^-REn6eKEW#9?{uxZ%O!a=fCgk{~!MN_&DegpF4Xhg+Vt3L~Yfosj1me`Z~;}
z_E*T46>g4`R6rX*zP`G;qx`)b=yor&+*_dS$)KV47av=|qjKO@4(J@qSBO@QrUYnl
zK4{Xy#pT$-l9!h}e0^Czd@_0c<448T-sGIz+=<hssb$$TcSCOS1a+E0Ib;2QA6G9g
z(9zLX*1f&IUw)FxN<W|4rM|Pxc9g!Jrg+>~s`}d-(DkgZuCM3!oMiHD_l_M8`tAP-
z7|g5ym0Kw(Dta+H7+Ree89<Aw+xTR=miy0FGBTRfeg6N$e}8|kYCW<{M_rwLsrU42
zmH!_eZr2E0)B;*(bGV)V_{!kr0jokZ8619pdt3PHOD5=Qj`;e&rhfBmGADsfVtR0}
z8FXv)Qm?67>h#wIE^d3pQV?vCc}WGd7w`Ohdv*q&xmKcFtxTW`&#$eG23^Uk6SE`W
z!xR@6m!s2LUoe7a{59$yAM16_$<cw0G+bK~3A)y1ng4vg2T!Hz!RPjQ6`q==+bwOL
z_hL^yXcAO2_*emR;KriQ&wSU!@0WwlZz!JLbgMS_*3-FLxOsSVE_|M(0=l9hKSS#A
zRmiz7ET5mB54V=pGBUcf#J~O0v!mVOpwZ2sl`b_kHVg}bmU<<%3$;K-$HjiPeK`o;
zTTu^MbO>s*1|)7Q^pMX1Ejs;j{8(itxPBHDlWqqojGwILyP@i97HCP}^ZE5|RaI8I
zN?$MARsZ!>=;U9Kpc6gr>?~$4D=PzyKHuMOuNA&dr%GpWz{((1(CEk8TkH4#<I2v?
z1|3EAw(8_0)xb?Dp3Z&gCiCoSx!Bp+=YIG7IOSRWuMda$Cr+6Hy2uc;c5~;>odu<(
zuAiTsO-wsh%oGp0Ru8(g!fNBq5YxOn5};J#;LvbvFKBDq%}uPjQCkEIW)>C|7dOwI
zJ^O`W%j09Lm7w{t&6_vBO4ioaZfR>%GBF9c0a{3$FYNj6yY@8jI@6GxCCio_x^qWn
z+qP|s+y%2hi(>Xv8ap{VU)*0`zqLAgd*0Criq6m}UXEE4dO{;2B-r@ndfvRr0Zm+k
z4vMRAo1_x6yUh1MNs7*yGiMY$Cmox;uVkVMr=_K3e#NRsirU)T7cX7}Z5{ab?k+cI
ziSpg6G1F2(g)*oY|M!dVrAwC*va`G8Y^x5OKhHmJ-n<&&L-rdA<B}c+ByPy}h|igG
z2(moG{@dC6kTo!u#HE*ixM5MB{P;ybWcr;=y8X-1V;Ap#e0==j+qb<}u7sS})B`#~
z?YMk>$ldk9%lT%RW`mYcaL&230d%6t(jd@@=MUHK|L64k+gs4F4)^v}&;D}$14z@G
zo0~ynozSILCRtZFKufK*<=$TQ?ahymk3oA9KR-XuJu7U^GT+&cKszpv^-52iG>NIY
zy86xS?fzRkcEs*3V`zx4`|0{*M#>Y=Caa}hqFdL?28)V{vdYWLv#_u%sQ>@3puGI}
zG~MV24<0m3m>_WE_;F=3GqLyk|L=Pd*n3WY|DUFv#m^!8kqj-$%gd+e$IIFO|Fikn
z_eXQ)$bfdnhpq}aIM24)r9Vr=$jB%mHTCHAJkZ8hVd!>&MM>{LYlQCav(<~;)dCtW
zD|>s30W|Op+OeOPmj^m8>&=@tEdE}{j@`T|30hYSnzBD<{k}u4y=ThQsiG>LPS@AP
zE)3APu+&?8@;%Fl`2RMtT3T9Mpx(q(tx(Vi^2NoHper^(1745&?Ll{Lh>3}TcKFPn
zFJDtrlaQIIS><As1iH5V8}G~R-e3z*E(DK^YVnxyVHYvrm$Pwja$*AAJMr!9?bYj+
zFIxsW-x+*>glU#afs-NV#E<Ilc^Xr_T-@B0%+1B;T9r0AEp*tPcNbLLT~wC3Lee^|
z$o+M;ppv!n^RtEF>*ERv3&E?bA3bWixj8-ga2qcNKfn9=dA6?oT4$b~o?iI&mMM5q
zw3{MVtJ8syW3B27R&(?69=)+KdE&fze38=>J%tz!96QDaS{QJkk(t#$qvH9wxu9e0
z1NYTbZpphVB_<}esv6X)1Dy+Z<cJGs^~d`C|AZ`7O5E9@P!E~``||QK=%nQI^YcJk
zBj?SV2kN~3`TJK;L}bY=lUDE@-OxF%o(pZf(p+CFo7s4)&Q2DQ2hARQzhB?~;zb6i
zDr5j{QYd+MM^f3X=YjNL4{d2_=`*v<`574*7r84c<Dbgs@^AljyGPPkKuoMH`}#V^
zX{jLh@7uQzG>oPdvO=NCCh-P%BBLqkK6Ks7AJ9hB+F*+u8PK_tFS~meL$<%ox?$0J
z_}Idxq{kqIUv}A6egYlT0P3NDPJEBtoCZ3LZ_#n19W5;^EiEk%Zf(s5T?u)tU%sE;
z?uWzMnV=Q4lE!TJ>wfF**|UemSL@oFo0~yLeLGB2dGh4RfkTIwEG;c3sBnTdtX)|d
z?Aot!<m>C}h8Y(WR8&+lVk`I@zLuxGs$kl+?8}!D(0L5u>tY=9^7LY2V=t}@R-d99
z9rh)IZR)&vee-OqmGt!dO4mkh&APF-+8i|OTJXRDv{3Hbw{M^|R!mGx0sCqy8-=?M
z_i~qb!-s)*K$o`1?~ltp++Fte*1?OQGpd3<ECE%S!qEACNyXg!S5;pZJ=`z+?`kQ-
zpQWsUjHNFwFrJ-ddic)HV%L7Bqb@~7M%!|3GA#}2Og`QRx=<Yy;v!tEv&?d}s%#P~
ztfr_L8yoM~x%1%l>*9#9DbNH{<r`^Gm!m94#y3aC_l>mD;RH~*3fe)Fkp$WeCm_iN
znuzS3ynoId8PMH!2O60{XNos9H-nZ+Em^uW@&CWS8JCywf+ifQd=f!5J7gN-&Aq+S
zX=!N@JByZj>c=ep6T7>N_xASu@MxXetHbrLtc#8Ql5q&MF3H2g<G}RzI?nR)^10nf
zv9YndHZwn-Jax(`CPrqKd4Are?)G?34-bdAR;8fT&1=8Q+g7!7i|d09%w?PB({tYL
zHxKAEU3d9fmh$p)(DhH**VZ`R-Bmhq&Kw>F(9TQHy6>Q+UYzs7Z1Q3j%x!OHm$R*E
zfs7&@IC#)8_i#5T3;+G~bw}CTS<ogYw2(A%TJPstp=xR>+RV=Hc5_pzVcHo9(B3VE
zf{%|}bz*mkynOjGVt<`2=(^*im_<pi-`v~`8nF}8jcU2Kx4K)dy=x|7R{>~QP<VW8
zYp1Y!m)z+Epy5c+X)lkD^=`elyW*qLp~Hs@zrTy!v2$nQi3y4t!OMCY)kT_noxeQW
zn7?Ah4U3#Pdo~oBY|QWAY3>CrBTIbz1T;m_>zpEyBcr8d*0=1+l@QSWYS6e{Z!fQr
zkx__x!m}q&7P$3FNtk2^JUcT}xhkaj)Y-GHIXR${G&dw4=SxXT1D#sb;Iz=8U(ObE
zZSO^8si|w$=ztcB@=BYT{B*5dGJES*Q_#r;GmX=`<c_WYoobnOcGe7wLM6~vu8WT)
zWQ&W7K__2uwK~223p!+PVZe+t&*Jp-^g!Df1mxt_?b=rLHS5Rk--{zRr*-u9ns(MV
zKL_o1T3hn+66k8MrlzI|keYHU>kCjUCL|~r85^@gy7Q48a-elf9UUfDR|Go0eH^(t
z4YZNX(9keT-Sf)&c=^3mUz?^+7YB{@fp*kag(%wC*d(N-we79`e(2C4r>{wgaVnmN
z{{8*UYalDC{`K{BcMlH^(6rj6rQU}xUK9j%1<!j-YPr1JpL^DXp2(~$txK0KO#qkH
ziK(foRVvNDKb_Wp`0QERg9i!o_`d45^T|5xulqY;!UWJ!M_0dsE?MxOZ&&g0QR}N)
zlT^JY%$Tv_+nw88;FjiIzBkfZT4sFG>iVGk2I}@h2J%63gq4Y)9QUNZ*LgiNc!A~O
zm!HquAOHFJIp_>g(0~aaAK$9#XV0F!xVziD?ESr5Bkl{rLPDSoYjSdZQ>KW3t_KAj
zPjr7@?fqZ#G`rmU<qjS`?7X$IaV2P5;+?y9FD~<y-jaFw*c1OX*Oof9a;fc~Io<5q
zwQGN7PHF#huCM0bpPg>}`_8_*v$OfU{r{M^v!+iMXGnN+V`EIszyEjc-u--Mhk}{e
zwIybHKg_wi_e?+f_viEZcXHZ0I#zJN*Hzxwn9T0v<aFiUmCs!>XG&Imd()YDc^T&n
zAD+l*6KBs}{ma7KJpA?jv-|DaU)-OjAKzz~eC)ubOG4|`t-G^#&Zp9!pHelZdbPB+
zDr#zS=H=yq7EXz9vBt#2xb&wNsQb-%@G`&(bmVP8X=!NnXTP#CGrNC3l4s1G4LX7t
zbnoV(MT-ndUxl=^v?M${)XJnT)(l!0=)9g8ybg0Qc;gsob-OQU;~1pXSPET#28x3V
zuMdEiXFkb2-X{wx!9fQUE?Kf9<4*nax#a><QdvI^vVcN#&6+hAb{41eNEkS5<-E8y
zdV9g^Yr1RaUtZ!V%<Px3$LHtsZ)>BsfB1Sm-g%OW$0X3~|CZd_VPECVH&>m!e_wvK
zdA^&2LxZQT#5GXEK~PW-v}x+%Vu{w<+w)h~p7-_ga&mHNI##@L<;sY?Ri>b0Nltuh
zId$q(Q*UoCXzx_`su0g39&Vk|;!oD5o}LEUn$y(OWb!UGEltV9MC9$Qt-=P9f`S)s
zH$vM0U5t^_K%1%Oe%FuLkr1^1Pgj5c`OnEpwP$A<v#*Wb?v|3Ga{r366@i8NUCW(c
zmOVVg$|G+V^Y#{KwC2G<X3$`IGdn*U!<Dts;>-Q#AA5Iqx9_{&(+twj@87WaVg+un
z%iO)O>Fk~Nu(bf7G3igo_gy@4Y~l6BUeJISXzyk(sK3>xW(MAyeMwx}y&kj>HgfZ_
zbH5`aBTt+=XZFD5k!|fS5zwfVi;K&=^Wa&2pKo8T)Su2zp1J)dC^CM3%l-51cK(mI
z+wX%8+1Q$WJ?ZMI&<QG>p{v7OXPf1Qa9@%(%gLBjAOH2$)x&+V)}S*(d8EyF{QUf)
z#2bG7_yO8Ogk>>_%NOusl5-zG7qZ^moW9zul!K4Yt)O7TvEofSpvf}rur&e(OF_fk
z4ryu2UOn#V;bG7h5B>l7m-e-5*VtzJs^rBi*dMt$?cv|=_uKpX`(I7@QT+Ve!)t4!
ze>|I=U-15(t<QYBSV#w29NHQXWxl(+{CJnB_JcQXdL}BnuZr_Hd*;lME>UgJy>^GM
zUl0E<#pS4fRFqUrZSBuxa;Jj7zPg&2nb~=6u66RQEtwhD*Ufz;{-R&b_R=p)QLPYz
zCmn}AlxW-y3JQAg<jIn<-2eanPEg^rt@;wM``$9&*){jSeBPD>T8Q#S8WaiUX3!~x
zj(d=HIeehn!X+Qt$(j#3!E~O@%FlH^K0N<E&;Kt`ptKRZH>4%$^cAz~KevZV$9{Q#
zUmkoinTm?ag9{6tK?g%FTC_+&PL7X3BX}8)oPC{6QH)~M*H=q_eZH|V`RY5*Nhz0R
zTkY7ro4I0V;M8rsvwYsZUsnG9UO{njv(9PI4J=P4`(N0W8@)9hau&(O9fipuYokIh
zEJ*^z=;1cr%RBCE%?|I)o}@DKjGNJ&9S-%-krTIGsijd3|6cvxw0X0!lCtv7OkqL6
zKtcEpo)7hJ?p8;feR<FR!}sl>fldpHPAFLVTAmTpO3jk=xuJHk=VWFYPwrX8=H+dH
zE7Ow<ZqG~PX`7kFpO%wUw5?l8tM}~(3p?2<4;_~@2Y79%tN#&MeQjOD+AZ($*M5J!
zE2eti>wjgj@9&1LEnoX}=X=ne&guH`$Nv2M3|hWZ^5Oy`1L)}AQ>VOmWUWNvYrjr?
zFy#?w#b5aPxT`-N|Cwo={^9!mf1;wIq7}d2Zh!drv9f{U$*Zf^@9Qdley+36(P(+l
zO3*!4Z*FXKer-No>J;}<8`)K5+qP}nQTch<v1CwFVdqZEU*F%a|F~o2N=+YM->;JX
zW;Y7w^~$!F9ISJ`m2`ZithL|U8-?@w|33S9qtHYAjl~k(vN^XlKEBc?`}`+J0;IGL
zr1auF&<UgyCJ2Dmqy6~skYOIr>d=r71tTLN(00=D`?cy8OaIxttq3u{cI_JI9w*QR
z8CG365fKpyPfkn(t=;_e=@V$Tm1*|12RAk*@2LL1?nQ-@ii%1{pF;Hg+V69#7K>DU
zs@}GEv2ug@^6Ki!%7gdr#T95(a&U4A$~tb_QRsNLN5YWl=FOX+;~_zdP(wpo-`(Av
z{Ncet10y3L+5V1>6@iZ#tUw3A1u9?IRhkXjBihm5fBfIy--S<4i835`y?%e+#l`N)
zcXkxA?VSA~Sib&`;k*0$`;Q!PVK}fhdOK);Z9BjGB51h_+H)BnAAiu(Gw<5ESZ>f2
zB=P%XjML6I+}@V!>aHZo#m_G;>$t7LD&#F_)q=EiH)zgNH+tKVR&H_7<vO5?EDX%9
z{h17!CIt1nRYkjHpWg%rw>e61=g;eh2RA%s!0`Z$8JV}NtgH_YwQ_?}L}F$pC&P#D
z-`x`v6+sQ(hK2?y|437psZ*zd4ul7_f3B^K?(S2TuB@y)asGUJb2IZS(`+@XKG0$k
zIZaK?SC`MPkJ;Ijc6Qdoso`-4LHi_2UIbheY^~UJk~Q@Ezu)h>`xK&U_%3ZJc^Pz3
zFr`~s{K{Mv&w{eDw#}P2ztC`Taq;b160|a8ku!K0cVeEFmez*s>w2K+5_Ucrhsw&G
zFFc$;?N&!e$5*j|;cFs5mkZ3Xua^T|#0H9r-{0RW>+1Rz1WlSfO*eYcs#RWp_g>yp
zS*#(#)myFN>E!9z*-_!L>H5~}@H4Yaxw*ylLhQ{-UIfgstrk0a^r%$+g}XZnm7krR
zoo;a7|M|JOhZi_DCuC-Fy1Tp2v8fbFO-%&_1{<Huio*Qw@9r)P(b|}Jn9VWsX}j!m
z&N7)xtiO2!|AN!Id-)sl|Ht~AcO@KGTxAc=1uyz!pWg>Zl!Xhgx~eMc?d|#3Ef_za
zHNSskL*ii<_sPA{+w&GCAMXRr#09Msk#*nk<3~kHON)ZFwKT((`O}-4m_RA^;lqcZ
zi)QBp*@JHT1np8)Rb_qo@+IhqkDT1xhtHlZ`)6M8z+uL$SzUczS2R-7(?Q!BcJAD%
zp{IAOzVEZgB+wp3E-!WcpFe+QTwdn8_3XortVvU+hQ9tT`XMD4G$FRi+RP9{FLHBR
z8uakOLTAv4MP={qbnY&Hf9Te&TMPa>goT8#NJ~q9{W{OK`opW$>lamjf5*TOA0OXq
zepS%cH1QCN$0QXiwv%`M{QPWK`YPnh`}^@FA~zqt4A}bm_I7<fdApt!D>R-wdv@sP
zQP$7T&#(Ws?CFyyDKlozK79VXe?ZXBgySpwKxr7cba~bGcUjsSizVD;GMB`_<xSS{
zzF_k=7N*I^6=OF%p0Mpk;VaPPeDB`9Ta<i4?z}-YXaMZP*RQRsS8M<I`*&l-$E2@O
zyUX5QSQ)JD;_fbehGEzA>Eb><KA;QbuC5M0eD&(o<?on4MU09kXd-_>fQCWQlM~PD
zdKCGE!b3tHOpmWS2pSL%3Tj%lN~^cja}wx&L&uj#Zf;8D28~oJD=UKz(*VuqDW4QG
z_quqbmpiNc=ciQAN#~iFnOn=GJty(}doSkV;<D=ztb~Ej4gUXQ4B7<%S)v2#|AG#C
zdtt5~5gq;b)KqPT2J7;73bwYg@iiY?tNvbG><-!*yP`rR+0f8%k#d0YhN7olf8OTT
zJHNlT*D&>z2<SY!7q_;qei5-rKu)gDv6&5Yu=}ga3st}e;jFs5yZE_Zb9LZ_vuAm$
zzrU+}W((SfU;b{+JfV}q;4t<Oe*-IBY^1HvecpKAM%tS1Ws_|CmZN>a)@5_jlaE*0
zfhkxdY<d3nZSTt9<w<{jd^9jN7M6AY#`E{*@0BM`cz|kKPft$`9i1x@4(tr!;o;3v
zQ{LX*uCEufqXBey%JXw`n`h6K2Hkc0>{(mh-Cdo1>OPT?k}94-{N{Fhm%Rd=pY-r>
zyRy1EJE(B{`}_OFU8UJmrc43dY2iED%)s1STs9bVrp%Yu*ZDyQX@QOkve<OIH)!62
zW31=RvajiY)+EK({ZzHFvH9^+QAw%lpao>Jl1lQ<ojXCv9W;gd=1oq?t1Fz7)%}k>
zIN1F0T6BKmp%%`9(o#{`;2qcFs(Dw3t#w)*wsyjtIX$4nFn76r+@6kebFI03JY0Gs
z!@{Qh>YX~j_M4=bZWK#+csQs5Tvt~IIyvSAxM_7s)Vi<iMq$SaMR36Zs!SK#mdPk(
zdAzaM3Q5x${j%*HQbN{!--?QhK@ke71^@i`2wDZ##xH+P@nTfLhWDMHpPvWa53qIJ
z?OV5$?Cs<GJC9fuKjV3KcXxa8@jgXUQ_+<xSKio?DSYbGsf6TYX3&xhSt}7x_sOC_
z!N<qP#r<0Mlqplv<1X)KWoKW!U;zVY!SBt@>Nz<%pmT>o7woKFzwc1_{o3{;M_eu%
zwt`kZKRY}7_`_n|k3WBN=EZ!-S-Em02Pfx2_4zeQR$PLDfs<8M{<zKzDoT_hi%Lt6
zetdlV;<{LC(6NsB`~RAOZZc!Aw6p}RZrqlCAGE0apy$!urLV<mYHL9|O=irRm2`7c
zDhC%A6GKQy$O6!DYTv&fUlqEVMP1c$SM_(jf8Vz6PkeuG@2kt6yGmX*ZA?C%bZ(9%
zXlwC<78P~S0O+%`vp@FN|6#tqKEA!PlhdtNs`cb#bx^Hs<JsuJ{l?-JD4;jq4~X6P
zSl}xEZ{NEc9#2?zqj1H#8-*RO+GUsL-6-@3e`666{>I|`_x1IExk0m7_WwTeKY9Kf
zbV<R7@86F<IXM}0&-2BPDT`OF;`;x+{(t+ox3@vV7>gcrT-}x%4La2D^YioWiHVA9
z)~=m6V+P04AWnve9R-R>$;pL(f0Z8eJX-nZhvC2H_5avcu3QP)9hsG-m3L=HW7^qS
z2XEe#bnlZ9lnpEc9jEc+gdht$dw1WW^0&9P9*+O_NgQ<7s)m-9)9$jjpsvir!|lur
zpbbYNVq%~YuxawE`=Av3>-BnNBcq@ak(;1EwkmnC;N#~T0W)XLOniE3D(Hf$7aE&V
z($m`~Ob`GaOT1{YfS{nMrwnLgq>|DkO=V@}lGoRGL5CF0FicL!$ypQkSh_kZEGUS{
z*w}c+tXZq%t3Nzo+_Y&EsN1_G^Riol)uhGJ=6Rr#j6vHu-rw7Mad&w>gF{-H+Q0Ah
z|HZ$3`({z~MZ>D(g@T3V$zHFePLScsCRyvU1v_>~fMx<demn>Y-mEJc7X>?0x@DKY
zyHU78??(O#yBmcaC5P)4OP9&4;x3a}#a||)ba%t!7j3fbubO1rUp31<|G8?_Do}v<
z&NfrDvy)r8bm@!B%lVi2&StBxuLm7**{9(X7bo}W^XG>T9yEyQMs@Tl-#OAL47#T2
z@^b&hOP07KGyHvab~b4FKj=g_(77;ysSoe$EC#t7R7fNr?{l1_0vgFL(Ye{#)#Vfs
zF~hMg@66e=8$pYZXBaY1ojMh?(Ry3{{l1Tnk25pu`~A-P&-MDh;$B`}Eb3SHgSNn5
zTH<+QXR$iyqBX0&HKAc)k3Kv+EMZe&ux8B~m*aw6(&9F^>;HeRPkw)IFX+}Xr-cHt
zpkbAh4<R+kM4#H<Z@1srl*)bS(k0N=MbOmiWHn#Vr7=at#Xpb9EfP<7b!8=J@MT->
z?Y4`H-Luz#rjqOG>OhNPl9H2IRhJxFuxXRf@9*!A-`bj8_~C)0grwxdi;LYCB@3Pu
zv*rstoV0(Tc&lu?NA(+X7v6r^_BfF;8Kt)y9}Ae;l*v>D-YA^+{@h$^4i1h3+j4I+
z*xbxGdik<2^wb1pi@E<mlT<1yEH`i7WN2t<VbPfCB_bk{aHK<!gP$MN%Y88A*Yue)
zImN}rOWxiRt*fi!;N?B~=jZ3dq@<>=udh2V4SIN_Qy5&Gt*8nQ3~an#_nTK!Q`5uK
z)3K^*S5?N2$jxb>QOrAc?+S{Fs#>i4Bk_r$YJJ>ZgUU}SEv>DL3|8guc<SrxLC5+t
z806ox$+@+Kb9>%hA<1C<tY5X7#>T>ul9Hey^0=y(OS70aPf}6T)ANfLOkKEU4bR<O
zrOpKf2G7pUR=4VVQ}DPc{r1jcb-Vw6ifyXCaDdwK&(F=xmT{3c&zsXw;^N}cJOAV7
zd_`~pC<r>`QbMBR^mP5?&(F?+q6)Md;oIBWhruVjIZjf!XxRGW_x=BT4^GZDQt=Fm
zw?Drn^RkqYn5h$}V>HLIc-7vO><oMM?)?b5PwQ|SFVm#J<c}X7I)i2)qPOKZ78MyW
z9JqEZEJs6WW-_Qx#<!Q_jrkX)4UYw`^8P-%dE?^?-3R)d^_i^s0`G2k464WXa=fts
zDX@w5^5Qbfz10HRP_SYJho7GxXlUHW$LGUge*1(wI|_fi*?gYok;}!qyUPz>zb+0s
zhVT3L<ByJZU(J4dYpe5ezqtakvbhtOU+k^=>g46c1v)WDN{VZ$SF5OY7z2Zit?kCN
zvr^4ccK!YR;rw&v+to@<ojNsOWeDh63mY4o2k+j2*7t$V6+Lpqr6gvO;?f|{rL-&A
zFD&<;-}m(N^vCb+?q0EKl~YNH$uggrN)}7&WI!AE@6Wa>d(+X>#3Ujj5)y5E<o@O}
zXU{GSTA7fRre@Wpb7e~*XsO|yJ9l;zI`XRd%vkX6y=C#Uj5VH<Sf+ZhdQRdgau!fh
zS|r}6z5slLj;RvpqP%BkXKyTh9ronuQ_#ND`hTD28|K}y*z@gHcE-IuJ708EC8ngX
zcuoR!oM+6Mb?C&27dzz-+bae6o;iCKG?nz=alie#!rH5=LVtX@>>n5ww(NO|O1jom
zu691zL(_DlL02+QnKA{m_#bo+(=wl#OiP1SUOlg>^vk?#j{1$l7p@8W6+xBK-Uvv4
z0u*g8yJXv698Eg@)4WWkN)S>roiF?N$Q6{1L6^*c7Vt_-OM{M!dv#@{gh4{XvAvtq
z&Vpu3xVX7lmtLLk*vxkD&><#Ia3ic`>sC`CVc~@#T8uW9Yb!xh993UeJy?<?DlY!`
z(o*jgt5!Ab-D|sM?OIp&OS_lb+k;jz$eERwm%Gomt7TEoj^X*q^5uU0e_7D7)S8+a
z(4|T?6(1Njr=NF=iIEZEVg(hOpncw@udgjyJgMi;Q~mmbOTDLquD-MCDkv)}E4|m@
zFiEAkme0QA#e}f$yz+K?8YhEl9$#q9lhv|n)vAIY9}+>Hv@U;lWN-ENguJ}I-{0SN
z_bn3-Ul+s3Q1bGU>*HUQ^X~b7xpG-{XZ_!=;WK8<$^sRoNjEkmu2{3?NT;wmi>itx
zXgTe+oSRMce;&(&u9@!X?KRB0q5*20JwDcJyuv(O$W)|Erc7p){Ws}V+GR3}+EQQq
zWlK1|P`p{T{Z*H2`-;Skk2gHN(0#Dax%6n?=Ne`<o&!6JpM$&(>Z615ja#o&=xc|6
z{`P-cPEJ-|ylR!#dC#xs&z#`_Ri1BdZqAl*xWA)N88mV{W%_h(zg6`UCr$))R3=Xj
z?tLw;7vm5UGv}Ad^JRIrx8)X;m%F#~$-1~_Ug4=^nCl@9YG-k9G^|~#3%Ye@UF_~_
z6-rh6>;AGV0o@*L6ax#lC#O!I2F?EJMsEY%?@=PN$Sw8uwp`E+S{K&G+q1B-fi50n
zXgG7m2ecO}{rtS6*VaaZZtgzl>A7UX27^CeF8iN2d$!eUY18c4(rW(mdbZ!I;?BLb
zMNqbX#mS`OikEnQ^JaF-wtM`)k>62r96Z3Ic*!1A6K@3f$F@9w`Lc6m@bW|F&-1U1
z+FJGQZ)$4lj@sYb9CHLNAsR;O3mIx39%}9A?LGSS^>tSDtM<yu%An}}_wS$Sy8OGl
zMF0K!C!=y~GH+0ytaaPJzrUrQyu1p!@9ft-(2cD(HYWes#TXD3#bs=~Im(>bP{lm&
zPQ|lbDxRRKcg>nLU#582{rmAX@bb(1T2r|useG&k9U<*;-U8C@cj=7_3=~`!yF2VP
z-*QkFWbWL#j{geh&C`dTi}UI8=d1b&D?+qx+_;f&b5knl{(=WBDzhd|6a<|y1!_`$
zdU6t6HF>zCD1dXO`4ZkT86}}s+4hp7ea^QMjw>n!f+Z|K5><kryZFwW@c|u}rmCtc
z#r(oN|DMbJeYK#)XD;sU-F>Ud&r3VR?=I5?&F{1G%e}Ci`3H37E$9*?C#R;W&rHri
z*BP^%<)+!z{xWfLcAhwAPS2-LMSnie|KAd{(#6q{5wg&<CGl`uXWz<lH#av^zVQF*
z#l^*Ye!W@^s$M53I)9nqv!_?uJnQSunTE-2a+gkUo9kULDSG1JF{!2Y_czcz)=y4M
zJpWh1a}wwTP+L$c%c_Eh+`TU^FM}FPU%q^ix_<Z09nb<|(8(B8er~--7rXa^E)fRZ
zxWNEg1Oh7FZ`_C|Fq+hSdAa}Nso`-e3w4#1nQw2)b&iXZ1BGSzy-N4hmqj`{wjAtp
z{(7*^`TXHNXO~4A9tYHJczogWhQ|UEHQrc+$iK1pVgstYQqs~uqX@CP%RrZrJ2^WW
z*8i)SF=Ix;-(Oz?R)$y<K599bQvkXtOhsLtnE`Zqc6|JODf3A?i=Xpt%e&j<H`nUn
zkB^V5{50*i=iPMzZ5fy?E+G}$c2bnfm04xt_Ag&bK-b5Bu8#cl$tfpi&9P;yhue6Y
z=gyS{UG!+N@?Y+a4UC}W1nXjUHf_IOC(Xyl$I$TRO%7-t>czFS(x5F2-qZCGPfyd;
z(A9Nya%ytqdwqF-;bSJ>ckkX!P~r6S^fWLt3yZfue{r$<*9oAFs4t;yJ3-T`xz^>!
z-rU^0vEbn$sq54AV!KLTUt4*9i=#`3IB01m=*Y+|TTHfOU-$d_<K5le51&78Z|9d^
zCBJ$5cK52PUB_x&Ty`ZLS6tL~1QL=0fzC;g)ClQ&p8fatH~0cht5PmiRn-+Qb1$`3
zDSd3^76<JhU$R7{_k8#A<?5i*O+csQ_$-eHZ3ph?VEFJP<VyP9x&NL{k3aVPe*OI=
z?LW7qzEEE<xopp#JpmyhEnmKrOqn+A(6M7~$(NftIyjCTJEmlA9$pai_xGc2eF16d
z?kiV9KwX98wF?$7ynFW!JQpk@({p=!e)59@jRge-2Ob`7XH`|Rd~l4_#l=NMX!{A!
zhAE{*ZtuUny?wrhac}PJZ70s3zn-i#X|=L@--|DWf139s-rkxmzN`HGx{t-rK%*r8
z|9)Q>pdlbD%bT8_{^ss(aZtZ}(V|5kw(tMzn~<cGrFEmwL;8*R5^ZRf1tmUEn1Qpb
z^cxG1#M`4sk3KwWe!pe$Vr9@&_txy|pi{)OrgDA!_z~2Lt*NPTIWBVS;zhyE&Q8#X
z+fwi80imI+)z#Gz(b3&~%gPTPJow|oVSZ5aBssYmba}_27EY<}9+N<uDNXY4#RPa&
zKDt@{#pZaw{P9Vu-k|B}O`A4ly`F1Tdg$zIb5<4M_qX%+9|g4rdFL}b>@Iuz;otA~
z$yZl}a`5rBZQW{`c4kK7{(oQBGfnCW3=C`pts~pp=@S|{_1G>I&xrkXdl!^E5)l(y
zv}X@!W$>zRTZJVhL8~i38!JGG>CoZBh6N8CbmI2RkQV<_|MKNai=rnSP0h`&?utrE
zSySNoJ`Qx~)2}ZtqpthUv&o#GKO?Ag-n@AeR6J|f2CXz%mz})A`oU#kas4>Z;&)Ry
zZ!fPyZ*OnkSn$vZbTY$%$>uqrEiu2py*0jJ{#D>&H@J+1G<iT798^YL61C<N>^#&5
zE<9s5KF-L0d1<MHO@%>FP*6ZjOb_TfrM=(pH3zLc@_zq+K2XQu^)=rTA4Mf)<%h3d
zbE~VXM?^*@URdBL1+7$N4jnqgqIyLi)M1@DlaWC$ejiVEb~flp8b8%~lnIA>Ute5w
zUj6*7{UjC6nKNhdPVv~+(>vdGQPJaLyjwCZI{9ZlS-M~W!_%ivx2~H$efr`B3mj_i
zZcIL&<$S~U>ebcZpoQ5_o;(4y@IZ@VqPFMtPMRdNB18)`#hy^_SNyo?mu1NdfkTH5
zfx~o(G9RP?8o2oR<HyaW+1C!-zAgRuSnuVC?*4xFk`j}&^Ye5yWKVhq1x-3u>gvi0
zT4xg$))u)r4YcBnp`oXT2eii)bf593r>9+AR3$ZabX=aFn`<g(UGhRe#q-dQkB?2|
z<gH3H%HG^qc)r5rO3TK_6U=VpgGM-9RJg49GMgc_6{x(OU<RqJZh=;wOw)_yYIRyD
z*RW>I8W!-$osEr+5!-Skm-)_CGg>ClEw10z+{`>@&YY|m`}%)2N=iyRX$*h+L02|f
zIV}cFQT_Q-V_{(dItX{s;}>@)C_1m=T>$C^fVK*qpJ#jZ{NtH3XP!89s%i0JWi}oO
z1*KI5dU|>t-QCUs0RdaLZrWsY<j4`w0c=c@I-kFJ(-XQn4777ofB&CN$8NQ9i-Q*3
z_VPLz85x1bcWaM}C|OuYu(Gm(x`*fI*(N3@H^05T{qWVRqVcs~MM2$g6*aZ4K1~*L
zJ<tJf6Tz_n>b2c_bhLZoj2RstA0J;_|Nq}Bai8<^?fZ?>&n@tuZ`aY$AuwmslLuGB
z<FD?RXI-x6<Le7L#^>4D*{kLMf1dxphu`i8!}@){v_MPk1(n@iSZkf^Si4p?@7|u3
zA8%Y-?4FpH*Z1%5?`)gAtSqkJ;NaS0%8S%`WZSnKtaC;$a=^_8Xjyb|-p-vnfBoOT
zbg3$6Me3eCHeYwGU8}1XzfVVN-WpL+QOPgY&)wXd4jOm>jc}@}s$OOLuHxzB=hwHO
zB<bk!<I4DZ-@N&km-$Lv-(B|h(7U_4H`f2J>ya|`N(N2*f=0O}sd|5r3^W5(p#J{;
zJ<{fU|Ni}BnD^xoX#LXBF3}y8pVge4omrQQfQq9JpFV+>zC3vNkdd98o#DVz@970!
zUIc<xp@3G8H>f)w?d<FX-C8IanJ*+P47v~Dz}d6BuCA^O3{$;Wjg5_UBGdypf5O%R
zY+#r<b0%mRP}%!?x)v+{6+UKCQc@B+=~2P}?qM(bm34QQ>7~n;L5K8*goP#j{`MBM
z;z3JW8+6?OXsiIV$v1ftPwu@vlEKUUu2uw}4}SLS*$k`FtgYgLCqGzNTZ0zSet&nD
z`NNZ=vmYPtPrkAu@YQ7Dd8baCXqY>9ZpRFlD=ZryPtd!O?-BjR0-R%@BjMl{$^^X|
zg&>Jrudl8a*NfY;VxOEr0z=)OkM5uWf~QZPg1Y^2RWDT=IlsO>F;Tgrr^h8FMTH^Z
zc%SU6*Y^KrTbJvBh7-QLy&YbVWH@Q^WW$ON383yhsL7X?r}yUV+lw2M-9gPMF)=Z=
z>Zs44>i+d>&=Nt=O=DV9z4l&P7i$d~x4wAsB9m~Ju#^;N^W=(KA1oOvs;iX^3<N;i
zb|(1PgolTNOcvLV3*ldIex@-yXvY=kJX+i8ZxU}_egJiAZf;ID%)X`rnoc$}H0<c?
zJP0b-KqKgu#cqFhX5QOld2WtnGw7BTzqRtIsi~mG4g;vjo1ns3{{CL*`rSKsK0Gl|
zdC?=ztyx#KK%=<v`|Cibsh)ux2?J_a)&Kuj@#Dk7gLyFyE-o&-{m_nh;N%O7T)ACb
zTt0l^ST*_5rJ!Ef_y2?A;^a=9I`w5n#}f@38<}P{UeH0bpraxutNS}mQqhUnu;A8S
z>+*LkK`TWjOzN1WRVK4a`<wJ7F;G=<1l(l<O+zaxO@s{cg5yitzRm{JiqhZzM+mff
zGJSq+oB6#8=4sQWO;F)nx^yY%kP4UMS7t9+qVo0gBo$B4Kw8<G8-b7a>hJ$!6t+HY
z?fHsLf}kj=u3oZy`QwL&+d(HE9BSnTEo{D>zaMna&FN{n!m_~~Cy=K>jyyWrZF(&>
zHg;p(-zvk0ET>PMa@t+?HY;}fwry@<VbkP<PoC}&R0iEx0J?C_+FCj^H1x&2z1D2}
zay-h)hwYp<7C%4t<J;|g*W(lBo||j^_}ACh3=G1;!l3EWmoHy}Mi&?qjEy%R>z&PW
z@NzHrG`-j^(9!>@s;mqjE_v%GURx6h8l$)>{l@0*4$u<17q0N8rzT>~H)>0Uq7~oC
zJK5{^wt-e5oI7{!YFS-xclY7z@%6Ef^RA{ufKF07+|IA8rNy;#=T6WPXwdv$!2^fh
z-=Gcmd3k*H_V$jRohvkxk1OVGybqeO>+s-%WSS+qWim>Wn8A~Ke3{*{?$w}c+5i0f
zeD!+r@jln0BBQc5HyB%;8bJ%fPM`KpaQe%|$9Jq<zK&z67pt_iG^h_NtmboJhx;Uz
z8M9|gzX_0M0F{G+f`S=WSBZ9YcQZ2d%iFUt@JJf5FfuZ7@bb29-@g6C3@6Y;vUd2o
zHKlj2T@(BH^JkThiu~Q(<?cQ{JZb0Va26LA_inv(Dd@<NBM0u?iwm%-oS?#a?%X-h
zK5p4oDMrXZm7<Og4}(GNuM*I)H=t9PLqkOuEnW<ov^l7G^x-kqS<lYRUHx_M@qYRI
z11g|7@A*h`-hx-dYiewqoSY`ioy*GrnFa=R;6S(1eE3lC<HrvUKhGl2^`#n9y<&Ei
zaDvWQX>Mj_P*7KAH_yA{@crH0!XF<JZ`{1e>F4F*($)nUtoYm3(ILeQ$^m6EN=jKg
zkR;#XF@IgmPNwYa*ICV*SU{U3e|~xjI=CuCOLUfbejn&qiOK5zYz&~*grlRQhPJlw
zoRI&ww&ixSa*HK^wq@(+APpTcaEt4?<m9aRbtTDJNL;)fG)MqyukL=oZ*`sA`E%#o
ze0+F7`^VNsZx6fu<=}*r)Kt*%M@NqyU6Gk`^#1*L2d%%eOtZxxM_DDNq_jkCPP6@<
ztm1j-*VoryC-}wH{r_7ITCMfr<44EMX=g#hZlL>t3kwSaG(;q<%XC0}6Yw$xFQbH%
zl#u1WRXv09^*~38mL6sV@AFj3`cn4(9<RK-{El6_Kqu-)?5Wszj5{v*cwej2LWi1~
zJr9<sxIcaR6trCT+xz?d+TrUM7(mlXpk*G<&ddZ&WzLz<(ZM5X&G)hk6tquzpsgjB
zBG80?(s9MCh<-U+r?N6L&{7b)+Fu6_9dasBnWUJWo({UC`e>IZL&LwnzZbjr%Yo`9
zh69lOZ?1WH>rTvY0?mxgoH^5?_Lqs5mzN3Kh5UPaIzh()yt%Qlqpwd)HnanDP@#$n
z%k%T|uUFhTd6F}}<|C_Hznred%!ujw@yE7gUY;;*TG-<UmI)Sz7nGHi85kKk`T6nr
z`1mBGr?Y!bn)lOilFGwZS65egc@!P#<(}t1eZD+b>mtTUpdq(f=+Mz3xBLqW95-y(
z;1CoP)N8Hh?&_NO_t)1yk8K161x>ZyfX>UgBC_$ZfS_PtFsM_ha&2Gj?+=&#?GN6#
zArZXXuQh1p5zr<S&~=HGm6Z$(!NI|2W}EZRum896!Inp$RTrzn*B?WjN}n)!va-fp
zi^Rl4P;vX=_xt^aZ`_dBxN&2}_q*j6_g0rPIQaSTfy%E569f)=e$_WN7S_|#dvR;4
z_Mbn01f-<8etv#__{b5K*Vos#do4ZGDXe~BYj*g>z}8)5Z)Y8IGb$@9YZC4>O*+D{
zWa-j}pU>O3x3{yeS+gc<&-<6(B?5iDyuB0C(!!okUN@TwQW+H`=~yv<RsjhH*3PxB
zmqRTjK%1dL>am2zxkhGogR(afGiJ;<aOMmTXv&b^{!fFXaoU5Y)8pIb&zA?Sv}tDN
zPkMQ2>5EHCxj`3UTW!0is;>U{>-G5dsZ&Mg%$*C`ZKpBSYs&QLk8f;DE+{EEa-fmf
z^|%OV?Ivg;%;do3{`2`-of>!Su+R|UVqs-X{PW{uQ*amP-uNX;mVovxFI>1VU}eaw
z$&YNI1Mu>8?DKfKrG8!bDZg~tG9?uimiaZGI$vm9IRP4oTDWkbho7HYWu@i6pXckH
zR)#EEuz&$nR&sG20<Bazo>OprU2OF;Q$az&iFSnyb2~sl%C@+;c*?YC*LKaDJsWgk
z#VbQWQ#E#exg($rBzNw_h=_|jFAd6EBmGM6y^D*A9PSLXYCq@z%#$ZM-TP!3mo8QP
z_i6fm1qB5LWw)LK^K7fHsJGcwec{m4(*s=)>d3dCy|opz%KPQZm!O?3pxNqzhfW$(
zy}*UVw{OQbrJi;<E^_F|ktMf2f0?2g4BFPs;1Cib0?OF#{c@ch>T?z^Rt9ZUjfv^;
zp02lW)haIN5tg#PJF>5@d)TeN&mkyC2y`C7jvW>i6%`8>EMV}SrgLyh=4FF~0}K}p
zzpnG0ZI*F)S?>#pO=XXcaH^=PD%#u2Gcq!Q#xI)L`9an9ySuv=yLO8$QhpU%Rb{nj
z&mPdp;d_2Qo88gd8@hgL_I1AP`S*|QDt*n9#4vZ>TK9gr^R|Nj>^oH=ub&CA8b
z<;oUBfa~k)A31gmG~0dkTHd`qoxIX!pq1E6lP2C-8?liIbe4BcZZ4?#2x?50fQC#=
zA<L8m1y9OC7I1WQJOMAV>2v;)6tkm%QBhHG!<H>93^ji~9tU0B1`4a*hbqa*$v*RJ
zBtgwa(a;sa%l#CUl$b!PBMS=+86JFme4L>{(YXy2NedS){P69Ym}Ky_f5puL&VrJX
zobmDT7M7L=Po3gwX5+mSvA^IU6X+0TF)=lbg%*;MlAu%6Q&Uyhc%@o;dU!&@!k8+I
zbY@SP(z3h!ebVD&y-kx}#XC4KfTmgx9B=>~_gt8=bkioG$?E=~35F0YQ5Dao?c2>|
zWMmj@e(p`Wx2G~<N5R4eOMY!nILP$n%}wE#FJFSj+<bg`j{W-Z@UUsyC0;>uy^5q0
z6BMtqUGSf8*9+P%l74<3=xPK|OG!8~GP0ng#N@<T2he^v5k6SATwGL?Ra{)0N6Lhw
zuC8u^3MVLqKRnzHYPzim(Q0XL@9y(7`T|<ey)q=}{=QlRLqkE(Jgo;aD8Rur1~kB3
zT#AnOftQF?8Rp&J#~U3T{dH?^FE2xe&9~!QKYc3Nn>txIIXM~BU19*OLlYJje)9bJ
z>g#XczAgOt$Tjez$1+eyjGdj`!qW2U4$x)EE-o$-PZ+8S3Ji2~bU?cjTAddDyZQOb
z48!CNxwp+6UmhtcDmnxzmF@q&^q*mv%w|>oF6ObquN{StS(XTE>*(-+E_w`GAIGb&
zuWw;xwdy+PHi+lX+kgD1XqIuXulr*$O(zmG**|6K)X?bnS5^w=-P@z7Ftg&$4$xVk
zvrX2OzrEFZcXxU6|9^iaOtYpOyY=ty?}zW-_p5qOdtnUPi$6I@1zw<jeRY*vQ&ST(
z0qErHyfA3xhNPohphI^-cNJe;?0ykccpG}Qb#-@xCMEW*Z13nu>4Yo`Lj<6b(#~Y?
z`Y(aK7WFo)pY8pREK!${kpVTN9-Mr>qWt|m&>3!3weRok&A7jB?}~~m9-^Y62SGbw
zcoaeF=vdg;4qdyp?bv+l*j*(DK@$)v!uf|<I6?LBxw+Qumc`E!4z+N8`1rB0zn>p;
zKGVN==PjwH#aLKa6buYD+*-!U02=jv^5hAJhuXZ2A2*-Bwx{rM+rc>>{?7lmqwruW
zxA=mfl~=Os@9a1b(Aw7aXmP*YDzh3shI{w!aq#dQS>)QyqN1#%lqCf{cT3Qev#+nu
z!^g*^u+R{+{c_bRtsA#*AHH=fs>Ec{#)Hl5%ErdQB|J(>i=s9@4v5`&UqCQ0`2eJM
z<KoiGXw7$3)SB;N_vhd5_dmX}GMJ%Z(j*}Uhq5v=9bH}1ce`tTZo0Sm<k1%w7k>oJ
z@4mdW)WFQ_*qxolAK&eMzsS8`j-g@B92uS1T_FWtlbV&?`xGoKBWw32ALonNRkHF{
zE$D20=vHpqWt01l_siQCOKe-P;6Q@;OivFF0a?dwd3SfU{`>p;`mVg3oSsXUf^5|$
z@r#R#A31tdQA1<Jt*FRI$)uzt(5YpNCy)Goe2lfVwe{+?-(OyWMrpV`)c7MKBSELm
zuYG;(+O-p>PF+e?Qc_y9td;o%sM>Y8vLZAj1hnh^$8-Dtopa{M+}T~uuN%FsrMa0o
zuKsW7kKezg-{hVCQUe;7-?Mk`!#8h0GyfM0J32b9fCskBU0hVsAtSp=N|TJsWI)4>
z7rTX}q`EF#2<Sb|#LT?<?((3OJl|TrT(}Ux!piEnFo1ypw8{^;&Xv5<dBopb=fbgG
zX>%!q&Oe~SUrC9HLBUf9bT)vjb=j4Q_owyu_gq~a{@Qq6&Yn-Fv@Jk=BKvGP`??;`
zd6v#?Jc1K^_B=e?4q7N%R#tXirp4FWyScf!Sx)#QXp;Tm%a@&nkB_a~{qg7L=Y?Ni
zg@R5#G0(rZ=37j@#*V^+n@iu{lQlFn1fA}A=ImM1YhK>og2KYg)z#IGFFQIqr0hMH
z2CZ~y2Mu&7DP20cv-tUkW77E#PEFMYO~K#YWvZj213JPVw2*F+%8lE%L6?8LxV*go
z#SRtczrVgZ2L=j$`t&IwF_F>Q+WIT^JAcnfEyn5RIJ`VuT-rK7>utd08>rjS3@Y=U
zKv^%2cJ%hH{e0YKzTIBNNhW!Lfq|fVEf%}?ySQKER#sMCYpz_etMK6C<NeYWQ*A(#
z$Em5Q0V_j5{b$gzc8P~rKr48gcJ8#CWuC96v9zN4`@5q%3Lk@Rlm^}6cla<fXcKHs
zPL6=6XzP<FDJm)|2QFU@E(w`5al-}!(5Y~sob>(OUC=TApfmAKp9bwL2Za^r2<rzA
z5-tX|f;Jkyxw#p%1?gkO^>wiu3m>~_O!aa+d8DYIpke)beb8Q{Lx-FqqN9}!4FmuF
zoMBUGbZ(w)ck%OcoPJuM%IIFzYhBRD%lm!5*HsC(zj>2$<j9c+zrMb{v8yzD>vJO|
zC8bMz?2tnyR|M{=|8EECF#q{e1G?wn)s>YmuB@C~^%ryv-tYVW`#?8YgDxnUX`Fsx
zkt=s&r)Qsyt?kyTKub+cPyWn~j*c6JEB@Wc@96O8yHU7e-;F{fmWLl`$Ap+znt}7R
zJ3Ab#!`H<$ZrxhCRXFu!=ZqN=pfeo4zq=cpAHu*OCME{jRANy2D&!#N*W@QBCQeY{
z1g)ENT6o~ZMCJLvK^=w%2b-%r)b&M0ML|2BK!qmg<j3@La}G8zG6#f&v}lK~OSrNk
z@W$qJ|E<2AJe^)k51pK>K5_2c-c_r#O5Wd-ZD!|hn>caei;P1BkDH!@?htZvaw_=u
zr?U6>+&ObT92JiT-5%653Dm);gLgwRzrMN(8uR0mwfb`AZWF(}U5}u$8|W+_(1EI7
z#3yugba=31X@S>cEML!VGi&hsvIta6u=B})#v`vB-gNKYJ+`mL$M4>ioumTVP<HIt
zu~)C3TULEpA$RFyzt>WyoE)8P`S;furu=<2JO9z#@_U9a9J5zRn(JM-w>A5E0cb0L
z!*sn^(9y0If`Wp9kB`H8n^QogkjJE!zrVj{m+CXfSQIQ+m<;MlT;;ar1NqVw$=N6G
zgARM&nCz~iqT;YJq^nOkTgGAetvR;UVmSLrnVFfOCd;jDxzUfS0s{q&jEo*Ud$#O(
zic4>FSeRH*adBWwOwTO0xqtrtWnCiFFD))0C^%8$*dk`|Dtp0~kM8U&23^^=byxVx
zkVmiA@6UVSa%DznSeTNs^5SFS-i+YE_8>vQiHb?b7mBxnGk6Ph-IvlNVaTGd4k@wo
zFO@FE78MzRd>j!O30kkX+<$&s&`OueO3OZ3YtU^|JTevmB|e}nmmePY+h4QdnLS|w
zLw$XH-m8G-FJDSPJE9LBJh*7_i=&HNyFsJI;o;$1vaWiS$lTmj^V0})+{~6OTcYOg
zR`oQx!C2xs>BBke_YdZl-xHK|owhD^cbopcAD~q&pu<T)mu^3N*x1y>1ZquOUgmqa
zfsxtexC+YrRZw7{;H~ZX>#y$Jwr!h+mR8mSmn#yXp`nQfn^-~PX@Oy3VXtdz94B;i
zd})<!f7K24KB%PY2A6M8mWREHr;x1UjNs*dnYHi1bpWSnSYl%02Jqyom7HA-hqSb`
zPRtGgucbnuWiosA?%kMk)99jMYsI~1Vxpp=0U9DzUYB>sSe0-jCML2OH|$F}DdaJU
zMOj(d!piE<-Mg`W&!0QzS7LJ$G)Ut&*Q!;2{~sYaIk^p+HVMgkYUIT%*xS>?1L~P<
z+9U)T5_NN9)6&*vWB{$q3JMYeT_e~lZO#Q67`kEs??f!^>f)L)V@5{l`i&b6<?L#1
z9OztO7_}*dGi*%+Xsh9l-Mf=tU0E5iEk{yESNG%F?e{?gtnvF|N_>=*j1=Bjgv7rA
zRif@-mW7Lp3XJtD@r3#UYisLl+lKW)D|xCS=4XL!L2z+#SrEE9OhZqP?Zf-tK+wkP
zh6aX~wzfmJZ%3#2?A=-RR%%_`-c|d~ojd0i6&1DhH)yXZue8~NrPJdsrQ1weIcJUx
z=n$qC7Z-bYdmp~FHT!Dp`r_y3q?lj&`S~q+%r$w|tS-><)lVnY7cD-)WUhB14!J$d
zC@n4B`_(Y{Si<dXxlNZqxe!s-y#9W_{(9E&cc-W8zgFZmbu%<HtoVG^d}G<$C=oF+
zCI&V>8IGkvoi8sh2hAb1^UEL0UcXn(LQ_ysQV6vE^qaJj(j;vV3pCgUV=Zb+&&};U
zJzXEPSa{K54nbL2T`MNjqGQL7W!&7P$^hEis-~uP;{5sW^|x=|e*EZY_o7EH?}9qc
z9UUAVlUO__2}nwIo;YzL>-)+OEeT1<#J9J$G6hY#Q}X&6FKGMA6wP1;o0|(1bai<_
ziy?h|kDi-ry)pH)n8zd*Z*OnVX7TUu?luL#j-PFo3tAj{(J-Z1T0G<Z_4s;FW=qJ<
zUj1+HE6`M3)9dT&xjo!mT&|cD!20%UFI)&{X=}6lZujnr?^aM0H8nRgGMt@d%FHlj
z`gCRnA75Y4Am^HxokHHzbOfhO?C9X(x8}Rb{+m}&@T4e+1uF1htiZ#kPM>zJtFx1l
zk-2g|xh?J2mzSWe3(p@s04<qdXi)J4Z()9Sr}N}wb!LWd@9t&?NZWwM#`ac!Z}VE(
zw12-n=(hJAyLV^bQT7yy+LF;29#;vvmsDiRlqY8{T@qUC-hb@H#l?&aQ>RY7u{~cN
zRCgyI?@PSDueM3J3v?vx+1cixxe%^arxKZmI|>`Wf!bnXx=~kl#RUX_hR<!)l$4aR
zqTrK)LglZPi7(8(y$v*(%K$nf0@MZ0%UgHM_UO^0N{a*qCpIP>U-&C&zoL?oC75*_
ziIpYs@#9AhPR>C7vufZX9yG9`?AGH@QDIS2Q^T@cB})c$^`Ly+4@U3ldaWBb8iH2+
zl;5uvx2^iZ@Zm|zJ@72cO8dUPzJihx76#C|iqogLzkU1G6dag5W#YufD_26GTY@Yt
zEkWa=76l4ze6m_r^920-{6JR<epqh*mlJ)V>Z8KPO}F+!TBQu2M(<kNx<3-2CRH1c
zq>_T9pkUx-g_R*%Q(p*xTiz}%N}$6MLAx*f?f<ecfMys#-J}~gB0@q#6K`$Fd~su=
za!_zEt2*ce#Y=pkbRcMoRNd{Z*j@g<t-qf?CN|cv=!u6;+#ZR}&dva>sSNXK?rVy0
z9XWoS+t2HYMMzlKqjz_AgN~3;@nm8Etq6k*`F{BF<;ahZk3pwx9Q5?uva|SkR_*(b
zkB@`44cOHE*}*7$^7!F){=!E`IKQ5}nwgoYp`+t6+bs9Nt5;m+=H{S00ov;a+ME(D
zp{%?(>bi<&lh@KF6;HO$rNNVLndyO!IR>5QvVPw$uM!tU(1D$WkB=!D7zlvYRkydZ
z*ZupM4!uX^<jIqu5qr=riYq`9$U@LYUdM@qx3{)(8yXt^c)5H&Xn|nNo(jRkZM@Ef
zg@z$oqHETy*--vIZpV%t9etnyo+YB7GDIn>3)GhDSfQD8T(RmS8?O`#H#fJ6s_McG
z8w9RhyC%i_A}}xzG)lcLZm*VwX5eK|yZ6I~0-LHY9wj1*n>KG2l$Gthb0_BO=kM~K
z&>dgP<IhXUt?N|e6`DPB=E6;zgh0n3%$_~F>cyV&_xBbpK6z@PbNiNE`9D59<elRp
zx1-SUE@-;_+#Jgt<?rWJZDwNFuwlai^ZPZ;D}$GF`FXgwT&aN7BpomKy}Z08%$dW}
z>cnVnZXOXCx$?h;FKEb00@O8y4idY#_zGI{1^%4@-*HgZ%ltyxJnu-md|k(<Pelhk
zJ7=}6SfSC<+A4WQ;iG)+%}uPAm;1MaR@r@d!KkghTI#)Z)t43XCU-78eZ9eHVMc?>
zr{t8BC52vFXU~>y<CEpGwzj@_(c>7%`FD4h^Fv#D0g(Njhi~7OUK_n#Otu%aztdPu
z7Bt%hYC-yeR%d`F{P^YVTzq_ZKnLihq^5TExw^QxEHTE2l~wYX1D=AWp^1r!pta-Q
z-ri=9j*h-q*kU{-u_#tVObm3HBxqZQukX<|Ug?0qz(&8hR+&6Y_$3S$oKrs;d^t2Q
zkg?T?5wt92_H58F;f4(x1Z2IZUAlDX!s>ASExEVF>gwvQUhD4anlN!9D2y2)-8$&t
zl;FgJl|Mcxmc6~zI%kdyXwl1?8yi8{kYT}^H9VkoJ)rByK<D_}-CZs|XIe)`$BUn!
zz5^tcfjZV5vh6D#R#a9hnwg0eKRdH>TiNGlzMvVP<l}v!6M8yk&3b)(ee%6Ml`?kA
zpKsc<>Cg<rWP`Lb5)2Nhsj8s62<5!`ySkj}>g+%TGUy(Q7Z(<G^z?|#+4Znj#!_gK
z3aI!66-$;yPm1l`CaK8SR0Qz9Jo5M$>#ffpJ{;(`|Hn~Z|6l65u#nJ$_wPZ23a>4}
zrOyFSoBCtSK2rwh9RZ*Te<Kah(Ui-Vs}~g&EeKl4z>t=fc4KR{xR0+dXv7KR*bfg5
zf(}NgsjX#I2Nma4W*9M<6%iO12%4!};Mn}&`Say+A=WiN46dz@=b!4;`r$*tMZ?Y&
zoG)%~*Z=hClgsf5t#Y<i4wIHx)%K`(o;Y(RXMxM7w4@{^adGh-J9Z?zyR(y_A$E6J
z;>}H|9$sEfMMaw&c@|8cI@NKKN~wBXm9KxnW2U#Zf2CHPy?pseXGe#J`J`8s=eI$N
zRo@f4-|y@8oo$x*@6XQ<A3hv-dU`r&43(RkTSP?Uz{QJ#-qZDtu3o=S%SsD0{vL)U
z0%La+FgiLqdU$zVlJNNS<;#&-rrDsesm7NbPu^cy860*0_uudLK}TV*Rjzt7QP~}I
z7WkVxJB2}G5VGzoG=rCgNXyvO{xZ>v+tV@6wi<MbC<ADTa7t<_=oBK*vVea3e;P{b
z3Z_n-`s4ckf2~udh=A%HU0u-PjewOQ2BxM*4>U4QoHa|!O3jqX-(1h4?2Uwqr_qY}
zN3XAo1s!3<2wLk08VBeQR9<zr{P{Uqo!DI>m6eq{N?uOdmn<YGXvzug1S%;tC#9#i
zUtH||c=!8#!S-U};_UYJ_C1ouY#%><1Z~%zF`=WQV?`cDXn53jb$1uOyrdcu8VZ^u
zxOVN@B4t5SE;l!~sQFH7f>!dRy|{S&`u1DNpoK>#PB`qZ`wN;854BDVpQLi+=+T$j
zi*nxF+R6>;L4a09XI;_g-TL?U_rv$^%h&(^egETg`~Q&vPJee5Kj#Yy4!+9#T-|Su
zgR3iRh?Xem-nv(>xXR1RLCxq74-RHrTQl>;iA_`H&Fce=r&(A;l!z$qC~RB?ITPRJ
z`%kZ>K?hHq;K;td?&z7B#$Ts^R)J<3B1)<Gd3Se#2B3S7&x_mt{a$rVFh8gTYXxeA
zyC6@;UD-fj0i4RD{h+N(f+;USE5i7!%HG@%WMyU5(9l@1ZP{Ce`e4u?Sijvbv}Gek
zGZ?>Y%e~E1VZ?EJXK{LuynUQ)!Mi6<QZ~e^mzKV`pa?Fw8LZ6pDz<eBt1l{le=lHV
z2x#pPyL=5pd3iZ#Ajhd&O!vbn?ez<ikM}iA0>w0}39h8n{OQNXWY99m#~YVl2bI)<
zpc|A{#9>73ibUPGJraC;d<8{Cs|x@A`S}@iX%B<dMPtyx7$q!`pc%gx9KCK~VPdzo
zW{1DtwRNlMrcIl^%<x##(7;epQE}kzU0KjU^0Mtx;LVFj&8mO)-`?3;y!v(T|Bu(Z
zxfR7t9<H0<GNIS;kgBNX30{x1a|PC6fet)E4%tb{w(bj$N3m!{xJs1luvp+MYB7Vy
zr&FXwL6~p4+U`3_Vb3OXvbabb5$55XzD#A!!{5IT$Im>*&~&P<Z1VHuwEs8$*6cGr
zUpTGg_wnDK1FNcbz1#ae?r<mrgNZ-S0%isV28O6P`uqO`vGdFA`StJ5&(D*VbaipL
zy11C!{C|L%|Hm3$28IX6AAIL!V94nE(aX%hFiW}aF~hTv@NjJnjT0qo3?|vO)!(kH
z3SIr>jPZF56O%0$qjGcChOLddx`@qnx^8ru6(eIuGk4y-%l`JcR*Vb{X=gX(-ZqnE
z1X<p&-a@7?dmdBv?Xt<||No41c5Yt(iGhJ3PjY`g1A{~Hk$f2jh6^$urP+V{{QGr%
z{nd4`yH#q-nSU+rw_8>B_m}C-@^^PE*G6ymySuCO^1r{oYhySU?6j=?^@aDk?&+X{
zf(^H}W<Ou7^gl2lV8L<u`WTS1DVo7gigv2hmftuBa`x5m_{_VzN~_*%JkB$HR(NFO
z%5|~3SFKp#At@=jtoYBZ?Dcz>-Q1l1`L@LMkifu&Q?<iib?fg7@b&H8XRnqXIc;0+
z?X(qq3=Id4@xB22Ni6m0sj16^85kJq!v5@IWMDWexW5qUn+MOg7eDtqJJZ<xQu$$5
z`MMtq?f!f?oc-?Y-QC-#>BYV}ZNqRjBqimEDgV@;`z~Av;FUCT*_?JZC@E<X|EV+8
zZ#EwPa?xG>W%>T!bDy1?dpl#T|9rcseKkAX`eZU!ocmueUnNhJUEE~a{Q2uWC##)&
zSfHV%w#-%T4<o~Yw?`oE1Gy1~na(Zsp8lo3{*Uvv+||X;&s9C2TR!W~s_e*VPR`Dv
zGBP<UgdB=DCmrR|jo#*??l<Rxu)od47t`Kv&Az_My<cvYMd6}8Ionl#{?uH(b`2C}
z&FuVUG4G<6`^~-7DXgyI`Tb6Dzml>tulUdDr%rj@t^I!Y*1p>6ZW)z%X1TX~-{0L|
zzyI5tn}>N{JgWX&t2f>I;lqboIyxcK^<sUVGca6uQ^0Hmb1Rf?Xb=_>S~OvTfaj%;
zkB?tn8LZyg)+V)%>B614w$)*!rKMI?Usl}Oo_{|h_uZYHUcSCppPrun_1o?I*ZlQA
zn%Q_H7KF!Dx>}dLF$l?VOG#02e!gR!Yq!|lOLeC=<ppyx-3*VfUHbC!a^o64h6A~e
z3}m79A}IT#w%_j@{$R;4KVn<X%z2g1W~v>2KIzKFWcR<X!uMagoxfk#^VOA=ljqg_
z%A7iF+Apii;K7?$S5|g)cLzT|H#amUM#pp2s#TY^WM2NVegEIH1q<sr`1!A&nyM`-
zE}m|6lw<w%YVY-@r|Zx5Ym<L<d;9u*|9)j(mSkWsiN4dohj0m)rSL%3s>H*4y57};
z&FrQB{#3^9ELwVTS8AkH*_#;)tr*U_hK5dk_3G8S-EraJ%U7*hwfg<;vbVRMybml6
zjf-2iWs6DW-Z)+vi-4z3pMI*^J87Tvx%)edm+QssSOA*GYxAznzrU~6%g1NWFFOm1
zh{<ZcMiD8~F26LHD=;DI*Fo0%+Y25#^~&4FEq3e8`tqKef#Hu0XzxAPad1N5LfP9}
zOCKI?Umd%<tm?x-_OCCO&(~5`b}lU~y|p>L|IwpICJ6@^F3)6`)yOVi6W~2f=c01I
z&7ymItIeaVYkq8)rWd=ak(oX2@0vY(K-u_n=`un6eLoi6+LpU|Z}s<6FH2SxKR?%d
z&AnG@sr~<-=i6SL@$&MTbo%L~Bb~ya6C>_czu&uTvH*j{js+Xt<!iT`On-Z8Yj9D~
zre9xQFMsjkg<89G#I&VNO-%8sObi#+M1amzRffAC%6M>G%BEt&s#UADl)sOQ-B%Mi
z*Sh@Lx3{;aPMo-~_V>5UBOQXLPM^NqA*k%LoQb2L{`c+sQ|8TE*DbEErK{_!H{E+u
z$(I*_qT=GO`>fwxI5*c?R9=4lu3c8DYHC?ePE4F-o<Hy5r`!5AHZjKO=dRTMy<Y$F
z&CSiPuB^O#b^p;xTau1)?fr0w``7RL|MPZS`Tpti=c&`DFJH7s$<)Lo<H7<*P=-9#
zE4}>N+uO6xeO@_ZhD7AFQt$H-)0UpM|NqBK^rwFN;e!WR|0@|8eR8iY_nT)^IlGI2
zA>-Z-M)Y*<;9y<xVZpOAGZ$OG-xF+VYC362TN|4vs3a;XDl*Bwro(oD@lVRfj~}f{
zUQBp)cJ}hz+uK$yS>iHDL{@g~n>RUozg+U}>g${K<!<g#&>8wCW9DaNWCTP++$g=i
zdey2cyGpa=#eVjmIpdR>mbPluDzEJ8>q6`5_7xQufBp0MeD;qI534?%RR4N9{$G%z
zqvNvR{M|>698q&V0y+fz)TvV?_iMjvnwf=7`ttMn{MRQYDuZ%YP0gOpkjJ3Wo2O5o
zz67nI)?UBo(jtDn2}^>P`_1%YU|8V#kgWt7n{bLzS4qi<TTCaQtZZA(?XZG^4fpE*
z*ZR&daJ*E${T*o6{PKSv`|Bn2SR0;c>+1Txy|wl7GT+&=?lj!HaA5(vT!lmV{o3uI
zbKowotOMOg7M}06e#MG_ii#be8{OBe(OJ4|*{pM)XZp@I)6~}Xetm82<qe64rPk)&
z-4!}>=FDI3|NqOk{c^#%jqB|1>&>9+J611Put2Q5fRTaWgKhguxJzM-ADS_G)3vm;
zR6M7pt_)uvcWXo9;j3SDqqn_SxBH#ZRCWg4L*Dv(mw*J!_y6oYb^5ewt+~bS?CW~G
z@^&$)si{>jmrmyi|J6TXf<S9qo0f$|#J1ein{;yT><9#1`E;O>IW#OR&FZ3h+Syr4
z@Bevb?%Q@=6`a1$p1pczrZMl7pZ$HZ)>*Hvto&4AvueeP3#aw>ule+;$oAil$Gcvy
z+dXCO+_jS?30<CPSN`kEOX+=}GVJP=D>KfqFeoH!H9}8s3=H;1PfS$)`tSGq?0b7E
zv#ze1y3BX>GR@#+8ft28m&&)FIXBz<e1U3%!<4ymbx&{FQuDLOQid-zJ^lX!<7ufc
z@0Q>H>NvMv(ll$zz3TV2w*UWpj@p(pQ{`o+`n(A$TXS!RfetTj<CD$WaA8lkxPI2(
zUtd94_1)dwPYWzel8$hkoo5@(Z~J9}3}3rh&W!~xFE7tNHAVB*_Wb!TpWJ?TVxsb^
z8yg>&UbilNwM5yy@5hD{`(xifX!?Gy+MnO%Lj!1yF6f-*b6+}7obZU8_O<!9le4pF
z$_at9vrN4^J3H+(m>CvSZpgX4&DR|ki!k~?|I@Ekr4J9WZq2{{@0G$OcKMnGO-)Re
zbNzT_twI*N_lIrIyUR13iNj>##EC@~GN7V8YI|O7FmwO3)R#|APPWtfVlS>AcjdTz
z{hGz@{jW|<)qZtz^K!QyiG?3N6kN_cmUCxEU}a_Htv!{SU%h%|Qt-ebH8nN!&ySC<
zE-ZAO{8u|{&4uFgw#!dX*Oy-Lb*)|PuN9@QuNCdS%f-u^yCp0-di9hkB9(jNWbJBh
z1T3t)ZoNZ6TYL4%gRJFuOT)V@b~yZccmL$3)YB!8j&Rz3JR)4QGX~s}TpPPP%(m*w
zg(IE9rC(kIK7Iat^|ozcuCA`2V)S7V186)D+-ib_1c;us^?F>jZ~c$M@?YL=zdy^5
zu_5jB<Bu9<X5VHpU!4>Z8@u+?ry^B#_1`<r*t8#BxMGEd?awEZPn|jyl#}y@_xt<%
z`{Pef*9TRnwILaPj*g9T^?wRWUtjYLUgnc&;<6{}s#fjStKm`G^XAG`zcD<#bl>rV
ztmfa2N#|#LeRZ{H_uZ`f`)U_&UA0PU>9S?7RxY1+sat>Fiu`>)-I&>UCY*kHsZZ9L
zN0gaCAOf?VyRc^Ow_Dk>Y^%3PNlE!EXK>j3w8Uy_+F7a8w6wV5+Pk|-Pn|iFGqJwA
z{Ozr!3!U3%o%;|Sy*=;h`?~Mee?g_d;`6`1yj*O4ufkc`z0V{hO^jXqPDDw`mU;F6
zDt%|0y`A-%TU_tTBvtQ{Pft8OFU_$m{_<>g{;NZ+-22Yp%2^Bo9$wzwTZ^Cj&9y9c
zv$V7<+8MK}<mDtSEv+k?)BRgpTW9)x*(twEe&fD<aem7$yPN)NefU{g+AygFl!Ahn
z`@KBUDLiRO^}C(!6DLk=JALNX#^mF=wdF!WLQ^J8DEQs<2ebnWqmi*nJAB;_C0>Sx
zv_?jZGMAxY_Jglgpqg1!MC8P_+{kH51(n@SJT3B^bm{VC)7oDpXJ;55E?AjA$Ex(z
ztG9<Hg#-pF_8-5Ta(`#>b5Kp_>hAvA==_YG#n113GM<*2d2LPP_JwK%E^cnyek}Z4
ze-sp_51RS2PEJy-dNR@d%I@;_ZrSbp^4Bgc^)@YdaA5WPsne&gj^3WP4_qWge&d%l
zWCf)^WX$+x>-D(HZ*FeBdf`HX6{|zT@4xTs*PGw33GNot4XUcz_2|)~Ew#VPQd3eq
zCe5q;7Fql2<#JG&@i6HA4CC}Z(1Ew7H|6a(zb)5NhEF$sU(9)%&prLG&J<e6Z2!}f
z8mapYbda{yQuBKi&erAcu9)AiS=`jbv~=mxm8({Ht>6D|*QQOIMC9f3tv+vi{GciN
zGiXQQ%a<>AReW4@>C&Zjax6szTNL1YW)A7^A$g9&0@Uq$xp%q${C&Nu3{jK*{Hb~R
z<cWs4d3gHydAXbF{{Q`+{rA^bwo_*$jMI9mzP?huy>05unJb^qtM*&Da%Jzgh-phV
zY%uuyNPK_5^>wklQ-58XsvYj5&H~ycymaZ(ldr#KJvh*)rLRBz`s=AGrEhKog1p$u
zE&gS>{oj)XFW-JYrM>>nCu7}823tEj(2l=Ldn!L~$-Qkhb;=ZvNsAUQo;r8#+Uaps
zo)<4(oV4V@gM`{|H`CRM85uY%c(C|~-|oi){(C!q`)|v=|0RxL$HY^oyuQA_|9{u(
zwNYDxa&y=6cb@?@6JlcKsI1(!EesTn-|toPhX0)Y>sM9o?QOnycbA9nulwus{Ks7J
z_?p1n+uN?*+gts##OmtK;^%I!LHF~{|Nkf5xpd#rgRI;2w6wfVPt!G?%gErc`3M7M
zUuARAQ?JXM3{eYCobZsfEPAr*wOqfu-t^P$uKymtTt44y?t|%|6I09HMCiutnZfua
z`^Mht?P=%ctkjF$_2SLV&A!*(?|d!?Dy`T~oq6<tiGd+OiW#H8WIDIRbFz;*Lq?;K
zvGLZ7i%Pwc#%{LN-=?TUPE&okyV>yC+UVui<LmFHED97A6^+_iv~=H(N8DGhTsg7r
zt=sEqshPL8<+i;#vq8t((9m$zs#QjFA5E8%k`fUUE4%x3)hey6d3SHMyZ&oz=AL!x
z+_`C~k)S@O3}5@E&712#NS@yG<=yW0zZUQ@G(2m^n$bUeI;{^X!c|pWYkz;6ni~1*
zZGQdgSFf_>S`<2gPRIQ6^0IHb)I{WNtJ~XKTaD*FF;6=)V`1jyWtneoZ0zdoHJ$r7
zyzXOn{ENr^_F;K>d6T!cwXuO}na<8ma1b>u<KpIiT3~VI!Ucu)!wU}`I<%U-A?7^)
zT4siZ*PGwGmsiKg;|vYin{uO9hp)f(>+9>#z`%vt;p<kUpPwgXo;OF$f1XbJ;Y6#8
z9MexP{qUhcR7`A@_jJ8w#eYuK|2ba&qW<6W`jRIn1VQyQDD8N7cr3P^mYVtT(a|=p
zvo|-TcGvwp9j|3>9{%`ve|S{XtZVCHSD%|}{TfuPtc%?p5)!fmR1Nrj-TCKFjqhwT
z-`(Z!pMfI!K`~|uXJB}s&dJGnF*<+m()j<st}hGzbMCB+S3=}8DJiL%fXDS=YonGv
zpI;v*t{*og_jY*x+PvG_*50f8o$EWt;$p!<NtqZ11_qxb2F%vi11nIn+p@((RaN!n
zIqUZ(b02RP5)v}0`B89ouJ!d2E~X1dyT!kLJTCwG#l^+Dik@~=eS5P~P}xnx#^z4R
zEJK-?f?|S|3=4yTf?)%C50-(UK$frFd0HxHyh2Y8RJ4T0Pn<Y$+2=pU;{X2&2X!u`
z&2j>gk`}#`Vd3aMzWBzCh|(7q9?p7w_3BkEef{vFqD}p$AH3faw;pr=OH&im&274;
zH-W;or-vtYSBdAui4$kp)$U3=Gb7PTl%b&kGp{l*94M8suZzjs9)0xa(N7gNTH4yX
zt=>q8ieAl7*y}&vZdq~dvy1NXxu0%6pI^W3)2E`Zudn-Gym+z5YHsf}-P1vij*aVu
z1R3V|Ex)!Va`BlnXR_C=kKXP#bLLFlf79|!zW%=dKQ4dY&t+n|QA@sjDLH!dXy)&4
zZ%>^#F+s)l_nXbXzFhX-nt$K!@KOc_mSthfz=Ly0g*5{M!=KQ8Iom6X-T6Vyok>fI
zpPxJV_~VKtOI-4{M}xwru5O>s=^z)EmPwN*f4%4~FS%~t-*4~l>!02<tLEO;?C{Xg
z(3PuJtvY#Y>$mM9phgEM88x%>zxwm@^R8>PlXMGD{Az!9b<O(q`9%{L6+D0b{CVo+
z$-un4b?4^U-cI@Z@Av!bzrMcaox;d)!NvevG)`7hQUaaq&?{pZH0jCLs?dmt6|CH1
z8RzHOYU${h#JrGR?l;$Hu7Cj-7ne!i9Scw({Q2<_RGJtW8>imhW|ntn#f%vewx3QY
zFEg%vc4cL-RpqBASHFvjihioF@%=W}y4+7YY)wE($rk<3f4JDiW8za&m;U<xzW(ml
zu(eSuw{5%D?#jSmqK_@_+-dsssc7fjyq$ORrcRmi;>O10BCEMl1_=#8K|wyx51v0W
z+uWa%lT%AmGtk$!cbb0uy5;k#yd)(he|<WwZ<=vI;p>Zwhf9{7-}C)m^(^D`KAqE(
zQX^+sm#+g2#ih*8y<KD>1M*6v*Jq0z4~{7*E0;bwG4b`fY8$zoF?#Z1j0_j{U=23e
z>H6_unVBoSyu6;2?SA^PqU76~$gTPJ<2*e*XBnk-O`1G;>VydkCQJ~xyz|%`yV_rE
zucxJIT3AH9y|wjo;KctL+S-@*RDOO^Vs&-Z)$+wQaqGh;UD;b*{`A?itbc!go;r2P
zXy!}f<YPU7>*MyO+}>tnZ2a|3@p(;C)2$cfPHz$s6I&Ml=aKlUTU%Ez4B8BGJ6b*R
z<?eU4Nnz_^R+hfL_VVlXc=MSY3=R&-Sc{QEhYvsfS|utiz52<Ml(X~g<4>ME`ReNG
z=`T(83rR{=mj3wchTbtU);BQ;addQ?w4|ehV{7JRxA^+MU$1@z)qy`gK3?{zMo&-A
zuduLi(vn-ZqLwaS{`y|^d()Vw^&pqV)%{GZw2@o7WXX#B`};QOc<=xFHa|2rcCE0w
zU&f6MiJ)x%(uaY8Y1(1TCMZM0{#EPOPfv~H;^Yj>$XIdc(4i~aa-%Ot);+&lem``7
z-Cq$oxpnFDYr{Z|?nABIQzuVe{NY2v(c{NopEbXKWr^qHCm$<JDn2BDMyE~Zz7^iM
zaU-bU_+@8j7ngl)&Bg8a>sIgDW%cy=b8RcDTL}v-{q6sn9DaWN;6YaNYs-A4MMXt3
zk9LWIf<8uXI%v@C#*K)-Fa7H;P1B8jQex$s&cq<FLFe|i+{=Qfr2&ZdZ^g1@ZgTzZ
zdE2A&wnww`$pqBa?ggEpG-Zm2s=B(is;cY9j~|OHqTbmy=I{B~7PdZ4cl+(N-`?If
zk6OKIRZv#es(DqfH23~^)cxz(?0nD&+|C%iw>LH(4%ql!CuRp|7%tG&we{AP%*AJC
zo4<b8E+6LM(V=r1)RqDdk<7EXS+YtHwNdfn_hLVIo5Iu6^CC09&4Q)g)4e85nlwp7
zN@`W^?QJh_=kLF|A@OiXWaP?EpNc@G-U3Uk^^#iU-niONC)In~E}fraxp>0{1636j
z4OLaw;^*f~=e{hyc=2M@zn{-db8l_QUiZJ4<M)%3lP4{)EPnO^6hp1t;x#j0ns;?~
ze|^|4f9hpP)|C~3UjF{(b5mUE>h`Jm&QfVVyl}=0iLKe!-_82n)!khilP1S5Zem*e
z%xCG+rJ9<Wp5^x{m%o%@V3=jfb^$zX0SbCJu50q0ZI=1(&ri@Wrq1agXXoaZD)YH{
zc|oHjrpd>8ve*6p*k6C;_4@tmK!-w2S|X|)_M%lh?!x{5|H|Xjex3RE_xIDHowM$+
z)$1Pbmk%#2+_-7erka3f@iBVS4;?-XDn#{Scg;BWv0C@<1E%)Fil;X{DX<U`7hitm
z%9YjYPn__$T*<&-qK&o8Q(1p~H8VROw3?9XcfWe|>ZaUiM@L6c$#*Aj`%9ns(l!+v
z`eZB@$y%3zwlnlz<CC{r)6>KA_0?7H-R1A6srb&fi=Azrf9?7F`aGrY+lsB`Mr}^(
zH8M6<^}KrZYFAIsm1}FGO;b)xaI60O>C=>{Q?DxV>v5nqRG8Ss@7(zK`1sSZ-Jk*R
z{^N@`Z88Ga(;`T9EF%L)##$eCc<90zKS1*nC*PLE%UbB`>W0?V?#;O!2CC~OO<Koi
zqo$&=!gsdWvdO&>n^HP2UA}yEeY`!W2LkF&f~F`QJxaP;cw9DWPsK)+mFw2|flf$X
z+;5j<^mE&<f3*|0<*r`0Zk;RN%=;eq_tk#AY1%NKfkFPer;B6A*X!}K&wY^g^z<~Z
zEoeOc_~I1J;HWDMRmgSmzTdy!e5_daulC-C#O6<*Kc_}cQ&LizGH1@3e!E{M3QQRo
z8auHyj9<UFu&{Z_d$x|nix!zweR<(#{w8W#>W&NcM~)wVePN+9XgnA+4n1j-kY`Xy
z$(Bu<H-Ek4t*>ci6*WmjMrO@<yWeM0^!^+<)XHsI_ot#)%G9f~vvXN-52&XoEGW2e
zqOv<^TzL{G6&yO`q#Lopq59jKz{JFb51kkon8cYe`VtHb*C$S%ym-qNlcmd+X=!Pl
zD(Q>w?&`X<DfP5Z`hot~*VlfRy}hMrX&L$V*Vo{Zk}Y%m(ifMW-V_oL@L;tI%M5%~
zEF*)!2FxK728JDcY^xgQpa1vwcWPwV<nz1B-mY4;N-H!p)HHJUwYn`nBvg+K3@j#C
zb7{+|Q(mQSZ-u(Lx}G|5!eH*>;F~vZZqo5SJzanL;fDcbW#9Pik|U>qE?||v^0OT}
zDLO@Eu6=zRXy{>KM@NU-?>>3^cc0CI{pMPwS}`)}*x1Cxtq<S0aif=?-?cwKKTn-A
zXHDGRs+oSw3=3{1VyhnAH|5?gX%cL0Z7s5p$;!x>aQI<BV&X&odm(o(<!zd0nmsM;
z?5wLVHs85(N9}jc?YzSOxdpW{F$J|>zkV&Unu}gfF))~TPrDoRe?DfL`hb5xWaP@-
z@ApOD-kzUdXuja_v9R@VwWrVf%rbdtHs#0m%gg=m7u?;X!^+MMnv}8AGCKXRz{IlW
zK^42mpU<D$+SuZsN`?mqEB7B)-hLZYZ-B~?ef#3>?kWxT^6CP$N+wNO^y5c`r3~NY
zoj60Dh3!J){AW?j*RKmnNv%?JZp*l~Ceq8t=ZoV^Ntu{}>^*Vo?S4L)?B@J3{oI_u
zh=>`WQKd<f7VRv4J_|H5gSE%-LHWwntDt#XDZ82-yGmXrSsmA(GHqJc^K)~pil6lq
z6%{=x+FA1Ql4@v32&gZ|#m#Lzm&1M&>RhJc^wX-Ips{PvO5erq{JwK60^R%NLhI`G
zWo2iFhJ-9R*vu}i*S`POmdwe|&d*<OTm5az4(UgX3_mQf_G5&<y}f;XO@918O(Odu
zbx(TD?_GFxb@kJ--B<V3{&vd_4Gjg&S_b>uE(MK1+^_lE3p%Z4`st;z)@2e}ZT26l
z_F5G@Xn;2sLt<lfZ*LP75m~~>%y!~!*=%s2Sz;?hS(=tCQMp@wzqab@)$p%J#p7q3
z`>4G+{rol1DZje0yFx(2WBcz-mk<(K1UhQy@v&Yu?uY%;bfcH0&#PQ^^21K>AkO|@
zSJ!{}c01pDl2z%eCClg6MJ-*rbl<s_`4;8x=4{Kkx#<4?f8RkPyoU}So;q#XGSC3d
z(W6JbJUlMQ|Nr6s_TJv;=jZ3A|Bzv5n7?2u=Hv!LgTse|?D87=`u^+p{aO`Q`Baow
z%EUuh-S5hd!pG|@9d1v0^8C5By1M($oja|nzvWE+`uqL<_}AChn+LGfhlPeN-L-4i
z>vh+!UR}9r)vH&(*TwDzjfn5_XqJC<VPUh%$!)o=uCAG1UR?C@^$pF+TJ`J8OXbs>
zc*L0)F4PoYOgS?!9PmAH=FF98y3r-SzGUjg?TOfyt8H!`9=p5jDrl1O>+9>UKRrFY
z%(!>Onl&N+|NULR``)Th?W@<W{o26M_~0PBJZQi+BrNP&%G(bQ4@d1PS;@vHQ}K24
zr%y$tudkh*-uXe<($ezRgJyov06J(;q_VQ|*Vpy+YxmXuHUiB=pYM^z()P%6Jl-d3
zTKX!)cdk|F@jlt$y1IRzK7IP~<8i;XjZF-w#UB<nEhsqHclj@$l$0fXGL}VmOZ$&2
zPe1+iuo6p?s`oSvTiaMrNgfq->+1Ux7Z<yS#>A|#ez(K9TU;MBclQEbQ%bVwMsGV)
z!o<L!%Z53a$iVQ&Ls3zYi<dXFpkPDJ?P;lzw{{dRZsU<$1e&(}oc8>ghOu$*`#qog
zzP-O+|8;ZyJ&!#_PrX2kH-y#wOs2BigXTh=+xaxDt)tcb=YiIgY{|N+HP@yx=;qCv
zzus&<FCs6m@5#l-cP)K>?Xt?x&m`Bi*{@o&X3FK4SNdeFeU>vYT+qQjZ_B{Ibo6Mq
z_}03=RZpKj&HVoEZjptIlwnc}XwA+AXa1893o;J3@q#)F?{>Y`dwYBP`I1k$;qme7
z0~fo2l)t*Y{r%O050Qqfo}Hcjw8YAHIa5ZPmbP~3_q*lUkp8^ETxJG`1KFuo@U{z_
zp&)=c52G8k#RD`p)Xpa>^;Xt6ttTrh>&u<u^OCE+t~JZOwPM8z57^LDbo6R&aXk$)
zv#`x+XD>ZDIr(XUg-<#Y0|UbjPOOc;mWzwswY9Xo^!I#d0u3WeOIIKM`}g<v>n)tZ
zH6iKqQX^;CRBlr9pO<6BTBl`g9X%~I^XI3hMHVur&Yk;rFkR>LrQPrMy>141<<Df$
z;ht6?+u;5IGY;H;duyw=b332u+=u4qgGkK`0+N!N?T0~^Pk?%lT|GThQX|c4j&0JJ
zYg2j2y_F-Rw6qj771PEqzYg5YWn@rzfUR(Ch<;XJkrFvghOhn6qeoL_&8qq;Dk+(1
z#qVIeE&slqs+!uYa|{d%Zes04NIg3@xB4__COmR;+TAv(|HXfP6z;s6Cn_#}`tipV
zYu5OHr$1d?T}`Dt-d|qc|1yT*Y{%h;py{3?$O{M<7&5{n955TGJJ{L}7lJKlYiqk5
z@c93^xz_6a#}`kUBm^37m^SUzrKR4Rbi4%x1woAkclp{BE8)5oTegINhQwzYr%#zY
zS$X>DrQXx^RxVoPWLy0$BqCzQOP3!rL8J0dpRQc7!h@HWSIQ(~f|}o)6`;+UwZFeD
z`^><=QGqS)AEZA=8Gq5OvXH<23~j<?(ITbPl#~~jmU@HQ@LyhDHcdXpb9v>5;Ly;}
zsNH32KYjkZwfub?D=TXz`gFW7BLj!W_Bs)9a2h}+9Jqty<JbGnHhXztq4TofKT(yH
zJHb=3U#|prb$4F|t=(c~=gT<I!1(KIeqFK^e_h(QH#dKsj{mo4srU3(A08h5b-mim
z*~!VI>`g@OogEhw6#v9R3%W`hxzLc17f+|hhgDYY1WoMSExjIl>fE_7PtQ(pKc5d<
zo7P@IL&GEac;D3Hj}7NOG6$V$)_;64E4SDSP?vVO-`p#^%k%%fE8l+^H2<O*ye#8*
zpR85=zdd|177JXv#b)}o%|Chme7K)qUr})}Xf8kvw4G;vpR9G-0-i<<6&06-3m0<n
z@lDIUy-CMg+C1;d1Vv}iH0#u<Q)l{tCg!$anet|M@LuP1kdIH#s#U9emjCGe@S&h`
zZ`{#i$FwXhBSCja7Zq))`uZx>ikETGrcFVAe}CWqu4;AI+K}kz*N2r@W|2CNox;Gt
z#Dpz;%oC6GNX|0Lopr2FcJ+-L5tl8GUA=z&^vjaCy`>g9IzG9#x0%juWe}2-T&e8d
z7gK)s@y8QSi+*n4XapUi0GdaCc6N4Xc=+;0X7;R$i(IAb>-Jccytt6@euiOkNO17t
z=ku!11?Vy`G-9710But!eR09D_Sct-7Zy5S-CJGW+R|cjD>-tSn0{Q&iVNG%&9l{p
zH$+9X!&cyIh<<RMIdf*zmW+v@r5E#TtG#}`yFWo?ZOqOf(6S5AHbf)Ax~wlRE_QWw
zUE<c?vtZ4dHS#thOX~msn`MyL)c=Zsfum*`XpDjbIax#4_2tISSEi+|T)6NcyXn8<
zufM*U>~EK8GNta>8OhexR!v1kM@>yl(4gQ;pC1!{{i*`>$#$2&4+D2A)8}j2*~MMG
zdey4%QA-=I^s=+F%}>89ndR3y|K`^0>7dmKR?G|yY28>liwt+fW}D?+`t$Si*7Wo9
z#BAsEzut^z)}khu-JXGg;lcBx7}HXqm5D}#hXoiIGv3|V37({!Wtx30cLgKEf}hyN
z{1~>sxwEslX!qT4_H*9e-l6gF`nR`<3JNY<vP1>ci8M70<>chdy1cCSWy+7nna1g$
zwNRd(p1VGuv-W+i;9w!s7hQL3la8s0$(=SS28LPo*m`hzm#(di{(3Ds|K)>&&7iEg
z&UD(vAU3(Ve#@Z^x>#8=e_!9w`F6D_k<%VJ{ZK|4D!KlmS{PheFfcG+tss_(h=^p|
z*-;3Z9*l~b1seT5bH?Z9wza*|=2~iMZv8f&I{tlVx1Ztnwe!xM7|_s=scC3nVBoT1
z0fjz!d%f+q*FJibRB0nOb?VfUpy}+=v&}pW?^my1e|=l-ZP0M+*Vot2m+&z#oE5^F
z1s@({mk)V;ZEa{!(4twhq)Ol2iM+i%Kiti&ZQq|y-k=6BXoXT(*tC}+3JG(p%l+i~
z-Bndpi+11D($&4X)O&gg%BVw$+MkZx+o0Ccqodtl-)ufV>l`D)g2<v7m|aB%4wlr^
zR8XFs<F`C&YnG}fXd&Q|cXxM#TDhN}pEsZR!dy#R8?=-m`8eNY%@4(bf`U?(MN2?C
za>32{b8|1Z@k*OyTu``r<;sc;8!nV6fo8Y6Iy(bHL#MtJVPKfG7VD%2lVe84il(L}
zm0EL?+sk~VYyW<|9)5jy$;(BLkN3|$_1St`?rcAY1`U1v>9^lbyZsha&iBb$t1Z90
zl98EBLsj)?iQJzHJ(9*IxwlMuWv#<DZrr%6n1Laq3~MdTi9SF(+23wu{{FvVKY#x0
z>gzL$;P|os^mP5zTegHi!uC^zjaBuxHMh3suV1o6#doHW>&cTRy*xYuJUlvH#{5{h
zxBB}k=XSnVmzVdq@yV`wcXzk>&wUZomLBaEm)2roP}mS@cH9$l)bP)OR&H_7(u7qj
zRs_s8%iU7>InDOZhr?W)oD)+cSFK%p_4oVz>rYNrpY3P5Zque9(E2jaM)95=p39aW
zlob^fKUMAR>g^3JD%vz@(j?GOQyggE!I`1ZLdJf_ad2+>v49QNl&t*99XldG>yPL7
zEqCjcTKeTn$z{*Fh3nS&feOhF4-a2m>MahkiLc$+Z+Y<F-`~R#U4GDrV<rOw!;k-1
z!?^G7@9(Fd7OkxP{mp*I_a7f0Yw78Qg@sMyKlSJIzS`eYX3WU2VrE=`edzjHhJvk~
z-M?jdJJ}c*4xI1DQW7@2E+9AnxwNf~O?ai7r3~NB7(Gz8URcfN!rt%qvaL8758*Af
z85kPGT9X?f#XT~)?(y&M|88zuyKC1jG0T)XW%-&9jY&yKUtX<V4=NxuH8nxYr$b_6
zbFFym)|I}#25PH;*041-G5x*&|L=UzSyL<G_t)LpS-d>1`mO2Z&JV$$X}JA=Z|`5}
z+|CDD^ESsXeX=+M!;eC2A$!1o(#)AFL2LTHyu1t=%FMYPmY26~SJ~TD?sAnbudlDa
z{`B;8-}FQLm3!kVZR9}1ef;)+Hh_BRpetF<&$H#?;<~iJvDruc5WlF1$cy{`|K1Oc
zj9mHg@$uKErfOF`>QpzW`%}@{(gJcQXc-f@O%<kn88ZnpWXM^Sy;-p`csXbhAZSS%
zbUi9)q5Z>$52cLLdNys^G-cMTEGyAAP=S@VJsOg!v~*ENaHq_gwd%^15LMVH?!$J_
zg3^{2mZ?*wfTlP=%eg=UB0W7kwLhOu2L)`^mlugv!VC=!*z314EPYXMBlN=o=BT|@
zTdTgm%e4}=ySC7o-E&gzZBSF-#l^+z`R06odD(qhs-&Ka0_v=qauK#!HBJVH16ZpQ
zHc*)@Yf}+0spQ|EO3xry*H$GZC8@X8b$@o8zy0Sd*3M|!`FU&G<*GdR+MT7%axQ?{
z<Ef`az@1T}8Xa|Y_sq;p(1=Ay$ds2dEGsTt2w-Jp^_--nq;v(j<UDjgg@K`t>GZbT
z+a)Z>DHzOdurIQZ@y$#5_dNIB{qN_`OG`=BOnq(+nt9!`$0qmQp2*VDQYnjq1)DZ)
zGO7FXW3_qQ|J9%=i=EHsU4D9cI`0)GjuKE}f6&Mdx^U4mC@5%>le6>I+}mcLTY{v_
za%O00Ylp_g<?Rq*XgGjn+W`Z^b<lC}mpK^|QJP^oM~@x5S5W`|-(S$OF!`&B0U=>w
ztFo`J)6&uka&v2YDf43^C>@`iq#CuOU?FH$YI=NKBq)h1DJi8yPRq*91}z{3kANi<
zVj0L`sGAhKyDam?g@wzE1s)*v+j$l|o(5W$eVE@KG@P&^aPgFR^YW}XaV0Q@#}W?5
zd*9sOAFnsv`|a)R{}1jxjx=|}#^CVz@+mA6jtoqv@9Zqj|0#KTlS%fqHMawp7pQ_Z
z)6Fu?o-%W$rst}4>%vk}mTb$r3mPdkx%K*Eg-Plu5w;7A3_m7fEfaJrpH2<W`zgtG
z;iL1R!-uyPJ@q<z^yo~#M)^&-yHEb!wad!X#6&`iiDAJ{taZOb!p@?nr*!vA2p#?Y
z_V)Jm7k@u^kl;JZ#4~nRiD3vR{a~BAVEDuG_3KyAuqdCbRf-iWqnf6s=l8qi^W$p2
zhSq*ODh{fH89w~S+L4#nMe2<;F?<G%^{J`3fyVlhl9HxOnzRUXNyF8vSC?G|?NHi+
zwc#MJ1F7qza3CcuP0QFAspC3z_UzT5r7-{3@BLlgYZUv~;!kb*v5Xv^wovY=BGOE&
zH=JISurYy$MI=xpj5F{Ve}F*PY}Sn%1>dgGaY>oD<P*EHlN777%aucilv*7popTep
zskZLecai4`Zs+CvC!C!<<8{;a8R_pD{SA+re7CVKe|P5L;r7kt@9%Bdx;1p}DJDZx
z)2YY%<<&jo_Sel-nK@&Ihr9dnH9Jq9JXx8~+>q}XI4w1@6coPTYzZQ|uYdSZ&?j#{
z@8ZRaU%q?^nR{62+nbx4dHDI$Gcq)Ug@q%xW`)-M{d(PG_Srw5PV0w04_p|vcG@D1
zw7FALf8M-#{JF8Q@#m@R4EIG)2k1V8%Gp#*ICt(`&b>XBd-v{r`RbKdb@lHxGZ$$T
z{rmH?iz`y+*6rJyi=LiZ6S48pVWGm+S5GbVp8o0cdHd)6_Ww@s+y4nDRTJG&^RwtG
zC&Pvm)a?Qd>w{Kb-DmOGEa~65`St&1t`1+HmXV>cc=6(uSF>(z%?_V+7SzF?9JO|u
zw0Yi>Bb~yL+w)@O>}n!PjTjD?pJf6KFM<3I#s=@B)`qpUwH3X-w${hrKmGN!wV7tK
zB_$+0($k-(e-_t|J9BZd`{(QN^`QaW3>!*JR-ra%r_KBO`+NG~Hr}6ax8J{%V|MxS
z<<Iud>;HT_E@M@aG4B-v!!$kA&|&!e?%mzpFW<gh3+jCNUqLl6;iI&qq-TA7y_L1~
z<qVUc_1EpIA0$sZ&&VLQ%<U>lwWyPKeO>J7gU#%lGcPaW;o*65sFhn%M#d*{TISZM
zm+#)4+gJO0)wv}}%l+ri`<&jj=)}t4<^LL`7#RNf1!74I({!UZ<=otKXLq^&`nbKP
zW|?Le{r>j$%h#`|Sy@`Qx8<JRS^WG`j@fFzrA}L;a?j1z>{2o|HvaFx%fL{d{%-#*
zaBxD22g;8hKL!Qj-Z=lo7d<BJsr_x{dFkrasmktsPu|?z9ICd7VNd=4x^w+ciy0bz
zrlaf!X;{Ch=;^5~TeqruT3K0bs`>fJrvBfb!@skyuRHtXNlIv?jzj*vJtxo3HvjzO
z<m6Ss3=BV7SWybUeO~_l{>P3Vx8L*c<?{JOPftzVQ~h1<^5x5ta&qU6^-62&q%6$L
z&OY79%wF{W-(Rdoocj0o_vNgupPrqat#b0@WcA|j@9vhAlswt}e&6XEHzGi*RlBq!
zJ-QZol$V#s?WqVX<zir%uW@RV&gwpBD1gC(+eT()(_UX+zdUYz`uBHtZ*EL>zv`)D
zaQN_H%ep@mZtm`vFJBHW<zry@pNJX^mepTg1n&F)@AsOxy}!CQPo6wkQd-)3^UXQ!
zMq=H`$NQe1n`>S9>q}-;b@k<|SEqja_AS!bHSo!wpPxlVnHY3@#ZZRuXKb$8J5M`&
zT}nZLf#;`BPfxFj-*2a^tbB7{?e8@=7cN|AGW+bAGiO33o?;3G<*#6o*7v*&2W+xK
zP*(39c=Y+@+>X@9w5qCGn+*PM|Nj1d_*@2t1N9%D?&m}stxfRUfWB<YL5Le=4%orf
z&CTu7{rmIJojYeD)qCaj*Yk1=49~(BzXAsyj1XJCa^*^!x<3}4pMHIPt#b0n5f>{f
ztF*JeetzewrMd5K&Awjr;laV2TU#`lnVEMMJal4XXAhp18nrfT*Y4e$^Y8ClWz5Jh
zZO$T{)0<wQjI)SM$5NynSK5$zdYVr3Hl6S9?w(#9zJ62M*;#k?)mqoq*3O(Y>(sW~
z+ePp0>@=Buc2zJV!!)$w&meuee*8MCM%TQW8k_WUb38$r;NyGK<=gY`t9kC)wX5jK
liHUP;tFJLxF&wb@Eq=~=M#RnI4b33Wdb;|#taD0e0sw*DQBwc_
literal 0
HcmV?d00001
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-jaccard_similarity_score-20160908-100026.png b/Code/MonoMutliViewClassifiers/Results/Fake-jaccard_similarity_score-20160908-100026.png
new file mode 100644
index 0000000000000000000000000000000000000000..4f1465baa16805fd5337aad14f75cd3c04a0cfc5
GIT binary patch
literal 165112
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@u0ZM$pfn_7nd^PJ!NIy#8FiQS;QLWEmNy6k9^
zTGo}-$5!kt5@j{*R8{+SL}GD-(#E51EP)650v9J8jO$P}6G>uCyk|e@?)1{~#B$e*
z)%)i^KRNmMOw06VbBvAC{m$gKcf642aZp#n3m6EgSX6JoFt-CQU?8aC-$8~Fyv|T!
zIzULpFLve&op{~B!9YmGXn>#v;BXF*d(MoEj1!(d`hWgUU|`^cRLSb^?{vQvYp;pe
z$h1i(`RS>tS}*6#o3|oh;UVeO;fgjkGMjXim6ad&UU$vE_Vx93#nVP?yiy^Td=<6C
z^0V^lr=Qr=vtYr3>vrdN*Q_rpE)LvTl)5GVew^yv3FSG3vCnT;?BCyK{xz?!v-9GP
zXFu|vzkS>L?Ck96CC2wGXFZ!gNoKmM=DMGs>JR?;`8jZNnr}o@l+(1-GxP2DFPR;(
z=-Zo{%#qU!OJ7~t9`%0r9y9%%HS1${i+z1{wR!DY-IT~<%jef|J$PF?Uq}!R_O8Bn
zcK<}A9A4F`bK1bjNb6<V9%B{HCKb>3XDdrrKK8vH9r5>l(FPXLce!68Yk6fX1UBh7
zPfI;={CKv`VveStACJr5FM9nV_M6_f=a0f-u4kO6yccHhd{5=)f~TiMYySOwuJy8Q
zOXQ>_Nt`9M*MDD|opXQozITh5Y`v8@>Rw%0d1HUQy;<(9FV|kx#7kP~buW$=6}|Io
zUH|PzU#uRhn3;*quldBOqoZSxc1FU*)peogWVQSSQ@_|<Hk%g|9DH$me!NZHABn^5
z{O%zkB2G?DT()h9g!-bswb0YN0U^+FPgdEz&*lBSy@BgucAAH|PuGim@cK1(c=&bm
zF!#i?Gcy`HIyiRh-aXypZ%ECZyLTtfo5yEuy?at#m)j(jhnvsaInOrBz0wpealz^T
z>Pwd|CuU|wUOHQmJkPGSOMl-FrnS-A-R|xxjsIP<I&AHs%gg<{7pA`7_WxV?=iBq%
zTbI4*cy)Dk@}nc2FD@-T9liE<?Ps%V`)-L`)&F<<`RQ;;E5ApN9w~SVJ$m%$!J|h(
zXVxzIFLvu#RZNUb!~Xl*d!^08PI`NJRb{_bMihxv;)W=t>=YSU*@rJ){BV1{VdKWe
z-rlp)YZn{n>FH%1)O6|)%HrM2mz<m&vNCAtlGzJGmwHVtcy>ne&yUCbKRz7h_uggc
z^1h|K@{Cx!Y4$Y*ZEfy{4<8;a+P5k7wAks&d!@7PoqgZE=$e4))?*R|2@Fa~N)x6`
zX<4vffl%h*-w$%v)bf74Zx=82#p>~sYipw!KHNK}_@yjE`n7rfJr;&u`@UySpME`d
z+tmdQzUWQ%-o*&#y11-QKH4Sv;@Vnit*|v5-rn9fZr(h2|Gs?owKW&3&Kz#%H!OVQ
za%EktbXZu}hV9$iw{JIBQd0Wx=B9D;sek`|zn8GBGTF0t@53igSh%^lLskZ{K0ela
zc(Hr`m0JSB!pxD=HWoegI&%EDvVnoXw{PDJjEsUb#igaYe|>#@_|hdIJw3e__xIc9
z-QTzNd#zRJE0L=2?|Aj~^=HhUefZ{0$*-@kAD>~EJYo9u<vQY`qO6hAHkQASoBB94
z(k&oB;N88w-Hy#{3w>r9ZP>Q0ZT@`uZ}0E(KX@M-f4pCw-{0SV#_ZXP!`4RK*pTSF
z@Os>oH*a#z%(Im~c<|td4<8z4&Xk-pckacN!RkwvEz7cTyLipI{N01a{dP__H>D=#
z<g8hv4=ZMv83bfyd$~ll944tiN+j+7kvof2%ii7LjGVTWP2l;HCksMW1{IW*x#i{M
zO}xG(|Gr(xiwlf$a&iXd=IyIjYuD7)8kW8a*}CccJln%(W*T4Ikm!8l)~!Rwj<K0$
zT{-aL;^M;h_iU$bs{i*>-K|H0QD0yGY3-|9Tea){|1ID8`PHre=jPk@fA~-^MLV1?
zEiFwWcp1;3Lx&0;9%@xu9~>MzOJiQRW52xpu`QXG19q3?f}-)-HL<B$p-$`L_7?p4
zQJA{(_4W16(^7e)Ogx_cXgXhUa+2zb;N^TeIywQ%d?a~ftwe6#yeV~i(u4^N_V)G>
z(b0!bp5$D(aN()yfDPwgI89P<adSI#=n&Inb^oy0(OktZFR6Zce_uZJ^t9HQGbQib
zy=$0ofFWjAiRap!gNC~k53`x%-H`|j3o9rpa(aJn?^MUg^;JJUC@Lu_1uS;sjfjdm
zbnl*=ZuB;nq@+dX-m)~Doo&82et+GHsI6LS)~-#=&Fy95l}b3+#46Q%5){>ikB=>k
z+L{H5>gHzVRiUff8kyN2-P)RMb#>+InzG;Da((7niT?Zdub{Lv^xo+W8w{2#U%q<o
z_JsOfMNheQmA-BZTIzN1+BLD<TU!p!G)`w=`2PO>@d=8~51u_^<L2fz$-2U!si~Ru
zT>D2(Qc_aD`Z(LCG5;R6%Rf3d*Lv68C-o{SDhpzFmubZAGC6bhY~acu)tYZN(@&f_
zb?LPY*WT*yZ91oS)coA!^{auAS>d!%)Yhz}lm7kqm^@>~3<U)Rhqp1=*VnlwBq+$p
z$Rs2tHcFXhJ@|ay-rdiyFDlYES?)(QpR`4RLQG6dLS`nXyuAFHn4Ln^-`+IpoR)g-
z!EoaI`Qzg8HH})Ks}9_`BlGms)Wa>D!XeL+kJ_ks3IzoPg*^M&^!)CwQthVZ=7-Oo
zu@x5=@7TRtSwVr}e%<ffh2J+VNIgC6;FT*PbFE6Xw#-@g*i=D*Vbhv_*MC`BT6T1G
zIUVg1P0Y*d;}X?UFftOdw6u(Rzj0qF^RKg_yY@w!Tr@i`cHB6yqq{r!+{eDYz8ClQ
z?mkv2`s4TC-%qE<A3A=V{o1u_8#Zoqyu8d;P+EF*P~L+BjT~HDO)8$J4E0YN_4M>?
zD1RTv!p5d`Kd>u1<cav6YkT(C=)~=j*tc)rhRvIsr%n}pb#-;SYq!|SvrAc@uj&@p
zUzC1+UO{1D;I)+(R)_0zC~nBPX|(s<<b|(0pFBxnVPiXV?V4CwSy{&YeYWT3S}zZt
zYyba`aZ2Q|8yk~NpFMx_<iNp$jPKsPJ8}Lzd%_K=K;hi%c!&L^6?u7jVtO$h{B}Pa
zc8Zl16*;XATPq+hzdk6;aD8e@%7a^5v$cwY4x09E+c;<L+}@53j*!)1ykcTv1tlde
z9v&QJ@9(V*+x9@F>eCa?nhyur3knJvrcM=QVqz+IaY1qJd(j2=XIv@$ccFC79xW>?
zsZBb{mX?xE98({2-P&7i?&Re3;K>t~;^N|vwNavif`U@ln;97y4UCMO^78bS`OWRh
zy1MG%ojWnPYghK#Wk2s0*H1ds!kKYngW{aIa})FO`279-d1S3ZBt_PqJU7?+;zDQk
z9Xobt+^?Q%U4HGyA4ZYW#q15r?tKf=&(G6{-llWr?AeFUp0%0f-b(oU>#M6=_KB^>
zjvP5~{yhJ=bLTc}*x<0U=&68^P*dsaYb&Q1f3XfXtX~_kk;#dpqN-}uS8IQN|Bw{{
zj>*4yB7bN6wo^r_3d0N8kva=i>v`qvWVU8qb?O$=eemj47dyY)gX{72uKVl$7Cbz}
z>f-LcddmK?w^B?@OdpQR*Dt91`%A*E#^TfG&xH>Uv7VW0Eq=I-*Li2r(=U3vOI`-$
z+}k6m8@0t@b=cYo^XK;`AMbnkdi{R4ni?BEc{?6$ZSASsJSMe#eSKZo&Q9*_t*wVQ
zBpwcF(%JX(nRJh=wHO~C9|u2w``o#*LPA0pwqyq1xOwwsO~2n<tJY(^($3RTOWxcN
zjEjpqaqir)rQXv&yxo5P(dYB_?Ms&~-Q+t-CDZ2oV)y<B&!4kLM@N5od6|9Y%$X6p
z%XFQboC-cXaO9CRV(FK&b!z96oiKZL_txy|*Q56>fvp8t6uv&rqT+*slxfzIvbVcD
z{QZwF@tk~Nkt_F>{QGize0(QPoH%f8ZS=<E<9s>y_sOn}-X3PHXKXC&JIkc8x0iQU
z*;}s2X;XJA?W^i-Y-~Jn>eQh-JBuH_ecO9(uC?~(J$v^CF87lSSrZ}n`r6vVcXk$E
zEz7^ZA(7e0*x0b{PsNNGGeoLvKYsiO${BCoyt%M3*&S3E7#j<}eEIUnx7+!Km7h|k
z{+1OGXxOsF1eChv>wYNu`1%(9{FDl+<6?K0xxT!#l=08q@V|fle0V;;UP(iPqxRRA
zgYxx%8bM*Mr^h$jEZ1pw+1o4g925WQ+u6y*?k+oedb&O+L58df;WW>?b6}b8Yyolc
z_9;_DDypl+zj911eYx0owwXoA3xQc?xm^dF*$>~iAz_|($DydmXqI_CpS=8hrPq^H
zI3FMH4`+M1CG#@d$&)7|c9m%A#qaBh-Ced)Mp#<9d&35Uh=>Sq0uNrs!zX9M5g#9a
zWo>l$`)mdVb8~Z0{9j(?dw5OcW`opIQ<VBGi=J>qZOiFY_n)^Q`FP)oz{PCm=32L3
zT^*i$dYbNyz18NguCHHTwzgYL_t3W7+n@krVPSdj;o;#QKcCN^IBi;+u)5!hFK2st
zc(!C*WRjGW%(%8j^47N8Zgu~83BSL+<>2Hz`2BwU`p<oD1qB5`nR&9B?}K;m`qr$`
zQBhS*{PN<WMb#ILq@<)Nsq<~C+m`vxe)Q_<>Wr(aM6Jr+a452@i{Ib3HhTM_>hJG9
zeEFiY#jf_*=DpS5ldi3a<ly0P*`9YdAvd=dR2V!y)_Y@DsWzXSO~<XR*{iP>eti`R
zs%%ZOt^}|h%fGdSv$3%el=_^UoD$O0+vE0DX+A$#_V(7pL#^CeyF<0-oxL7k-+SbU
z%a=Ddg>!FjJNobM?~OG-i{9Ma%-+r~-!^%2@Wk(yR#s9MFJ1&y-@m`TefZ{0&z3DF
zHD9lW-`JSU&L?ZdlAWDBciv2=)6;Y}=H0b=b8oM-sCHP$GIdo|$4M$OHWdPvmX-#l
zrmP>z1(M_9<f69atSp-6*vyuAv`h5EhYt=QALZxwU%3+E;^wBLsma;d*(t@mf_qo_
zd%0OAnN9ZpelY7sZE0A)e!UULw$RmKt$q9N?X6D!|L<?c?QOa_xw#)-uip;}pB?4z
z=NWytcKkSdU|?WJS69>W<;zdKd(zeL>;3-!a`N?m3}a$rFK$eBpQ07YRsQ~-YgCj}
z*qVsO#KUc(mHwMIZ!Uau!w^*eKYR8p>hw$FxUGAq?=E@S6kq>WG;~$S!4ngeC(fST
zJ!6K%Q+`zu_q%OpL|ykrZ@E}9_vlBThW+JX_jVL2m%X{ss296S!N5R3-EYo;W4+Q7
zCrxT<X6Ij2^z_uJPmz(JXgqRqvU=e9INO>Z58F?iKkx43#PsXS%jV7L=e6p0D43Xp
z{A4y`WMn+`PsLNn#@5!b;DLjMg+;>YX}T}&?A-imucoKao40Qn8T8}#x%~e2c4P5#
zKTzgPOiVN|H+L^8GIHya>AYX}+c#A&bVtccAu02`o>if%7v<mISMlwQWKM4G)SpjJ
zO>N%2d-tv1>kQh~sc*}@-KHD8O=JGgo14=G#l_nfyZ1kOb91xnJA->Wi_>r1y!mkX
z{JKMLZf?H%tmo`(b7gI9Zs#_hz-N-X+-jz7GhFuG%Es7O7}RV0^XJcnU8UJm^kSv9
z=ifgD%0}yAt^a&D%zsKD&EMbO#ntuU?EHO=DxMO?X+59X*}9^lQ&UqHW?o)qQT|Rw
z$}FctFLu|1e}8{RY|oR8+Md_@e&27tW_JEC>vtz6D$lSiURIPlb>hTEUTHH>W5%NJ
zQOhZb3vTlbSDyc~@U+E66$1l-Nh*myKRrEh;)Fv;h)9co*7@R-lT<;q%$l`pFYc`_
zx3IQWR#jy+PCs|#+uPfP4-PO+EnIA|E&KX9Q1%36=nEGDEUc}?E9<|+T7xpv{rdm5
zOw7y=pFd|04i27US<Ght=L7S${QG^2-TPO)J!PAEO2lWj8Lyd{*^4_njcsgf3SM8+
z1!aKjYik?}3O0ECd{pu7!2SEX4!85SZ`^2TRraRi)Ku-q@9ypf*}3oUx9F1h_x4_R
z{B`fO|9_s_&oE48(+XM9FweI7(7AJbps<{%?7kuKFx!_G7nu*du6<rrU9GI8#kK#>
zC+<s^E*VsP$w;ja{u6!s*Wn3U{S)smN9y3c*KtJfzQ|2b@jS6<&9u6wr$o1IxpOB*
zP)0__$Jh7h+UV^epK5ArTXjw+Jv%cq>$q*j2Zucs9}g|qBq=GWWN#n8_D;Y3KMfU6
zq0MP$gFNFmCbdpb@syC1?3`;|zDl<I?Jd*9tSqfLbLP0XxwU!4U0)Zw^&Y?Pu|8St
zlt{7L+j4_XSATgi@zngqix#!$oK8AF&sOVY*RM8y`E`@_WnI-$^qf>sQUYq62JKY;
z{q3#rB$ZCR*j+1Pck7&1Qd4tNy?gm`a7AV1$|b4k>D}!7ax1p}es*^Dp|fXwudE1k
z*7d)5?ZbzHiPNVqpC&ISr<W2bc71((__EmDWxgJhRM_}rR)ocIDDM09N?Y;trid*W
z6Qkm~#dKSAPCt5dv|FlQcZK(KJ*R1@g|Dt?Zru~UeslTzdrs3*4U>*=Y~AEP&qna(
z&6}s}x98oBI<ZM--=9z3Q;XX9WQC3$JGLlfWzeIOlhsdsS@i4v;dcJky?gf-l$D7+
zKQ}k{q;>JLo(<c!iG6*2UH?;+XlZ8EJ+4VAod*s$Je}`9*Gg5zQz&+K+0}@B3G=Uh
zyL0I9;Z_yTMKwP^Jv!Daed^1eJvJBjR2D0q-eghqq{Ha%`u+cezJ2?4=+2#(w>Mo}
zTr_@%9JC9TaFxHkw|aZUpC21Ff|vDd*tk)!{@>5#n|hMg=tghzd3q!3>MG92X-98u
z%?`bEeQmV5il@-k)#2fu{asx`lT<jZt*r~6ospcn$FBAlN944lzrMZ>y%fDAL$Rl)
z=g6+o*CCfSZ`#zdef#zeTegUlzrT0&Wt8dJgH9Zv{+{CLO+Vglzdt4O_O@J5jBQLl
zzG~|Evu8#7<?Z!0fvT|T@9#2g(xakgfr8=ft*ybH;a}8!lQVB^$vm~w@3zg4m&@m`
zTB1F#cjnBQ7L}itc-@;}nB1b``Dk&!U63a~2S>o{+mk0vYEkh#bpL*Q>K$%H7ayOV
zW4lTVpPmv`^qlnK;^KCrw|{<qcABJeahb2Q;^|EuUS2`ZYCoM+cbb;EvHpKu>a9;t
zPlEzBdV8MM=ludsF7EE!k<*U;`T05YQoQVECl14m3kr&-H+6J$1bF&;dkd$fr8!MY
z6_k}-J4swXKtaV*h*!!apz@pld^^#pTA`q52lWbFudNN(Uss!$m#6pc{{HpTmcO)J
z;#pI(XM&1nkCdrb@;=4Kp~3Sbb`~w2pyJ8G!qRc)PE2Z5SlF~8zRIsw_m9N{UfI3W
zVAj2}M?d<A<W5SB{PXMedacUO&(DibQt6zg8@+0Y_Otct_x<ux{d=@qTuDX6MM6??
zWzWkgQ$!R!Cq>EY-e@~?uQ_;`kKiPg&WnrPSFch1{Q2|IcKJGult{7Y?RlZg#OJJ5
z^PLs);%j?b8&~8s*Q%<jg-=CzV*O{#n9=d%Ny^k@B_$<LhWz&Crqxy3k{1D>favZH
zKAnAi-P{SOk#p>7qh_YPkP5tfqoVX}_6e&$N4v!zJv%!)t28Y=y*p}a7N@$p`o}*%
zi>KQ7X5U|Q%R1$RfTHIl3A3CTUcZ)lPj8t!cdmiCdAOu|*FVkEn?S*F%Fuh7j^HGf
z%$V$~MdxRjr2Ny!nIqzM*+#QP;QIP_@wBwGL+8%<#q20>RL%eK;i1zc6~mGj0b7eb
zC#k%;wpQE7*tj&WSuy*0^!B{YIdf#T7OSeMaVaY+Z~f}#<kU1l#WQ48i07Sswb5^P
zH2qy~G5`0?&FQV3ot*_mMVBn5i>wL1eJkdEc4<+Oker-cR<aw%)qP<y_jk^^XU{e3
z*ouYO^AGLwN1DO77ux#&iVb`)SMZ|sxzne;b<f_oA))NnbKvxJ{f*V%^HM?0jlL^a
zLVo=C@nG|LyI|{c7cU0xyu8{jmGQvg!_JTSG9NyCxMAy7S0|^YW8cc(-H}`ywKd2)
zes7g&+`gL5z{PF{4<B|`^}l>>!mbNjq*vQnuZ)h0O1ictQY*9e*O$hP8x7@bt6C~Q
zKU;Z6xW2x=qN?iAkxt>N?V$&c9dmoUZf0Iy9%w8N)UuT}&s*_y_N-Y_HS<j*EeaIQ
zoH?^0<)qNmFWlmK3GeUi<>2CSTIw~m%cg%(e@2xU>-x|4_Ev-H-I&-|!|HE2TQ^Oc
zHtp2h8~OM4bRIe40vdM$HOV!vFYy%q^6swm%$YN9Y{{H_t8&ZN{WE4rq@<^VYNXKB
zVWB5i2QFq~<Cp7se7yhhot?$5ahn%zc`LUjd;U}v&fsM}jk|a6Hu9a8$|GYT;KcFg
z+wJ^QUv#6lfkr=Te}8jb8?`m$oN?i!BTnV_b-Jcb6<xG=@y8z@lU>~0#G<}EIM{4a
z|IY^0cZl0twem^n`+Ktg{`~`qeS3d@ec78A7Z(REcH^D8<zO@W>e%e4D5-Dn?sl(>
z-M#8<SY~#1_lp-9Hue8xq|NiLy!>Ty_8@~n))fs7MU!*2v*xYcxY2OUnl&Y>f^S>K
zy_H_-HT6=(xm#Pal{GXtPM$n@;`Hg@)8D^*IkNx%-~6dt7@64^7>bIDww!Ce^=#L_
zzrPpz&9&0X3=9lBb+@j#xY$%~xk3HE8jndW@Av<YvwX)r@AmE6(%IM6Xnv8IRZ&@a
z@bYEhlP6D}+7i3F%yE(mX!L56&gwnRlP66|NKI{3^PQz}`Ptdo?83srI?>yFQvb0x
zcurP3c=6)K6Wg9Xd!}S&1{(XAVNtlqEAH*Btrz##*RMV9HK`?XbJ|LqYHn`smey89
zdwY5JemUJgYI_ddxFO-@=9cx+_3gbi3vRspeN{F)e(CFqt7>X$Y?D+He|>prU}hG!
z?Dnl&N=8OOJ12j7edVuJaqG77ZpFCoGc{P)*%#;D-lmnQ?AGIOv`cj2lqoHsCi;Q<
z)>qa=Zf4_^GC6Q#V{+)J*|TPWnh>A?D}VdHOP){7P-{7GsFnNSt5;p?_y3DZ)z$PA
zdUj?eGlSIeiQV1YYX0+LUi>^gMU$Dq>aEj%tJj_P_Eu|`*N00OrF5LDmHJUVPt<9}
z+i!Kx&&j^Ivs3u%tE<juXPHiY*|tuwH1UMhohw&F^78VsUYePiNtk2^$l29&D7*Jb
zT#;+Nb0=m^<YqQAGqWF$y7faoX@#xn2wd!@sIJbg9lkEa`r7^b@_&DQ4fd2a$q?x2
z?JccyYsgF9wBx!|Th!Jp(W2sF!=fi1Tj%bx|Np1>#*G^qr$v^`h?kX-DOq=V!q&~J
zS8MzD_*^-6byKSMl{JyUxx8Bw4l+I6vq0iDYv!x^qaW{x>&Nx%*<<4~&qng<s?f_T
z?}fjtUdxb>l(gvM@2JZ=>hHdfsg>CEP4nIRU?n(MwEf_Y7fOg$o6Gxkpnx_`JL3=(
zBxGb{1R8%&ou}ftqw@2zPv=*zT*=UIZEdu8WnAqkCQxDY@oxG3htKENAG^6Zed5%q
zt$+U1q}ClQ6S=Y>(Yg2K@qT%B29x}IF}mkZpXQd6le1zKW^_0|&(<*io=wTCE1Y+C
zl{%lEru*>u^L8##trsPGoTh4pUTLySjcn`g<_68Ye0q9%wd~_}@79F}bgQxR$sE{I
z`FX;uSzWu!-z%xByU$!+aV+)pv{1`qmoE!1^_p6>wu-x`q{O9P&UQoARjnn<mT55?
zOxKBI@|^VH<8k@dCG$3HF!=N7w0_2w6@pdY-hkRiKYspP$>Pa;V4|}7g!%LPpPik3
z_|Tz67mBrhd2LQRYr@9D%F3Gf_0?62x<3}bzP(*NY5Cg!n!o;c3abmq%C4PO|L_ni
zgF{u-u44{Uu7e7Mit6g*x3{+LD0?eqRr-phzP{ch<AOu-1Fu9-$A8)~4wdR39~K(D
z{qgbf1QpJ@y1J~VYuBuK@b+!5ZS}Vom8$>WFYdQH^yla2jY&tjYCfG*&pJ4tYyba$
z)(i>;1_8-+0RaMhG8PSwkM|$Ge?NYvp68@<*Q;J!P-Jij3!8Q<z54sRSPsPr^X9F)
zyfrl~4OFIs`qArRb~dT|&s(u&^@BUt7rAop*u6XXSdXMd*&B&lTeI2i?d>b7t6$6X
zEPh`jCNAC%>JJ_7lRf<R_xF#Vo_bIHc6Wchyq=z(*71t!>eZ|^noX;@X0w~JT6s-c
zQYg25>(<uo+s#4c-<K~XTN%DK1qBBuCMAIe`ZCX)KY8-t-s<lkK0I{Z+w`<y|L-fG
zo}MoJ^u+VZ+Guf4PtStVQrE?9y`TmTsBeFHx&QIMzrPp$`jXkw(xUNvX8QSgin_YI
zOTDKbGrwQ6xGYbR<;<BgU2nXfpPzqxbNcxUpu}b`@!<XYe)+l|j;}xN`u2BGOKWT5
zogIas;g_nfuUf@)qYj)u@4vqMWHURzf@jde^N#aBt~%Q(tgdj{sHV2|>L;#qyz7I%
zzdj>+>z?i}t-ka{3o>O+ZQ`k~uaDVT#Cp76zP-Jjy-&unY0n-Tk4Z~D?h?%wh<$!y
zQOu44#+fr`t_WJnwaj<+vT6D)4Xv%M$9}!Kwl?}nb)evi%K!iVD&78M^}6$sMEkyd
z`#>r|ec?50bW%UOcy)F4#QF0<6E0hmc_Nix9lB8Z<L2gc!|ZE1Z*Fhr2X)ClKR<u<
z)@Liwyv%a{`G@Y`kAK|%n1z)URFIzfCcfmQq@=X;;iE@gpQkT*JwxZ+*0zNr-yJXS
zI(6@!oSmKBjqUmJpn4iKg7f6Hb-(1Uvbeofrb$Uj1)rXH+SL3Ac-mfg=FFLpbA>-X
zBzjD0G0VO6;?BB974O>l<=GfoT3TMjtXKOLlN}Ku0UFGfGR<1x-Y=JNaS>}xZEa$9
z_UfQ@JN6ZqeznS;|L7mesI9a_gCC-FdB1jb`1(bOhucn^I_0!E?d*kRzS5xSqZ21M
zuCI%A_VM9~+f%Vn=l_d~${v%Jh`m|eX_v|fvg*d3N@GxgdTy@uVxO5tr~Xg;H#>h{
zV5Ym{tg`jY|M+e&ED)23{9qBwd_meQr{nMM?~gy9w?BTYS9)XB*DMajfUQ}fJ~NG6
zbC;*)Zh5Peo|6-k5qGe`zxMB^)A}#&?X}j?(YdfHR2wwP85R~cAyx9^$&)vBm#;ro
zz54CGeSHrPw}Vy&L~KgooMn=^=uYCLn>QsvL*OrE7A{<PV_&WHvokZBpPrun`1kw$
z?E*}o*~IDbb)a@N(~sT%8858-ulcKMn{2u0%dTRvC2#F)D?TtdbvQNKF+TYC__*sf
z|M;$S>(W;tIX5;i3aj}v2rz+a7=r``Q2%dk`KfCnbC%xF-H~v?JMgh@^saR&k;m3V
zZoaUuwz@~&UaqjPQ0jDQYO3R;B~J5~3OGI9eC2DDyiElIgNKg~XwvIgm5OH&r^<CT
zZEbE)<@xpX^@}S4m3br#82bA949v`qEq3oWD1R3-^<!poa`WMK{^V0rG(jVOpovFC
z7O$yVt)MWtw8T?uw`KOC^EGDq_iTD3joJG8`at7~r>1JNdwY9(Olpa*`^lP_nJM+0
z-}m!OC5g=&cKY4+d)9jP@qz!}?Q`X9DjGnQ)Lg63Y)Q{aAAWpH-phQUxw-k{<9_?3
z@9*w{<_Uv>f<Qh?z4zwk=8xCo>l44fyDQ+NprPSW`Q~stzhcXQz182la-tLC%Kz+@
z>S4=x_uEy{IE}|^x?b<mZt>)UO{_D_^W_@$*IOihdvjB&`A1x8Vj`nri`RvfYP<Tv
zb2n|;^x(yd6(8HByLQFrC$H03S6)zPBg`6meBq;A{W6w|O1EdlKKF>#c(uFYW75LM
zCocS6^CNNDqPjC|1~s;do|BH%EuCThRkEF#jpx7;&&dMP(%lQ4+nIh;r)LTagW9ao
zOV=#Sc8QhP#OLqp>snA?@afYh0U4PdzqwYRdBIIOkB@W;-`JGeeeiAN*4VZ+KTT|v
zAH4s#{<ZO?QXjGBQIAXaocnvJ{B8P)Ta{;K7=pZW=gu7gAt9#n^75w<vHNOvM#)!y
zc_AnxBXgx`D|fKW`PljIg>t{_y|%OX`J$wwT@m|gEYr@->6A21J8<KM1Zd7;j%9Jc
z#w1sUqu=MQUVT0C_nuCarhs`b;|oMy{c>-XaXKHUfg`FNwjh3gomS<>jT<92CbfFa
z+Pl}bMZoH<-3tGk$;bN=KR-L0ad($#-QTa_QyUBvS<=qUS^3ezbJ7;JXPQki@9*qv
zesy*A>ZkvIKA-QpZS{g<z0%3AudO|C_UzG($;Soc<@;H=#T0aOc+Q<Wr{&oCe$t5(
z9y4ane0XDH@`|9PU0(OrMsEkr=k*>J75$LW;npj4@c40d=wt+F7?GV{PC-e@>9OC!
zTU&B(i-AU&H>aO3`0*hTG~dxJuJ6{)CkvXG4p|-ME2*={`+x8k(cIcc-`?KVdMeWO
zs(zA+qOLBlY4)`%KW~{#OqF!v=(TrQp!?z4xpREQ&(0j2V_6JZ@d6sN_MWD5@K7r^
zsHrn!#*FJ(msg80t|@<a=i-d@y0P+aZ*6r>NKkn6_%W!H)|>j~%^QUljW3a2la`or
zM2UALKR-LWz5eg(c((cM4Ab;tyRxsZQ?#;@nmBQyR^`f-D`!}jue)WKmzM{cg#gKa
z`BDNJ(Z9IJb%s@`R*QgCIdAP$z0Z+xadL|mF9tPpL9KwBHzS|Qu=C5+tj)gOzU|-Q
zigT{E{;vBkq_QX1YCiiHySq%$z(8Q;%$Xc~d|}Vd&M;&?dGe%(msgXDr`CHe*WI->
zH3eT@1UBFPV0LW&x?kVkcJHhGtz>O2&CV}(M1TLErqt8Z6jfAMo}ZiBJb7~P!sFV%
zW-9&o<hya}R@byNwNIZvUv0Y3{kl%lDqQ4Sp5c+#c96VuKlxbC!SMLnP@eDr3)fmu
zQMn<pIqvwYqWPk=AFo<&*s$%z?s*!1e}8>-PDxQoN=h;)c@ZFEUnjHNf4*Br#)=~I
za#rW-9lH!tWbJBym4JFvnwpv!*VfGRy4NFVydm|pSo7`AS-ZVHNxn2v>n>jV(TeMy
zzVG>s7VoF;%YI({{axb0CRR|H0-Cq+_V%9oXMWu;&$klQ)zv9!X^)O}i&wEO+`q2r
zzUulu(^!e3wUbm5udE1^FwGKqcYlBX-{0Sr&CJ9=Y3=6bbkNY%j2SZ+Dt6!BxqkDv
zN@0}I&-_`x{1*u$I_`Vb_2T#OFub_5v^y%!%d6|w|0j2scnUK(I5{~@e12{Do2A~<
z85m@(N&>i9tZRO3DEjVMdu4SvzZ1uso15Kr-@m%L`p4sb`!9Ct3^QiTSl~HXt)r{!
z(4NZA3N0Gb8fKV3{q*$oionHfQ5%{Cn0|kItG%tN<nGeqA0Hl8{QF~>l$5lg<Ymx_
zO+5#j*`-64x3;n}F)@9(8Xo`9{{K(@qN1V=$;bH^>e+Xn-qf?V`n%Z8`kI;=28Q3?
z-@Dh<?Tgx{RInv(Z<W>dwVspJ1f2GSeVEpi<euhR8+QBMCf3ju0gTM-d@f#ITx-^@
zz3)-~_2b7z0jA&I--n;B{`7>?Z;nNv&et<DjoBFt>i$$bdH&p)W8pQv2k(D+PhPS_
zh2g^M$bDXh+eMH6*je+_NX7G#6}$M-s;{pk43k(uH4ej#J(Zi|zKWa82empubDx)&
z`CetxpKnvybie+8?D}0iOLOJUpF4M~Q&>GAFK?Zp#<~S+zOx=YJlyW#@2~&u+s++3
z7P$3Ffto	zPCkI`j9>pM<QeE>K?3)a2yj<2z-?#Sj)2wjy$~+POKFiwnO;#D+qq
z-aWj%FYl0kx3Bhhmu`mlwA8s}HCwlCb@lMzn5Gli^x;E6N?O`06ZvZ^gV`Ah-rd=G
zJuf@4rlw}X{Q2uYwu^MVz8f*8*tO8$%S??7srH{gf1aw0zqnoWeSGb@-78F6CQcM=
z5s>;UYHu}p)~r?6{T}YJDt{-F66yB#*4A#F-)h%{e`!T;(`jmI0+nDfdnyDC4Gkx#
za5A&;1Ze+OyWY{Z=CFSJJ|1^>_pJ|#9e!J1JaNKf{qwl3S)mb8QIDRSoP6Tkxv<mv
zeWgw7xTGhyosn<t6?WFVRzB-peOTDEbMF&lU+ga1SM-$Y)923@SA}YCZFnPXp7-F?
zRPCtO9sT|FZ@;~A{%9k5U-OsIlPGSj&{ZN<<?niK+=yUdWqtVR>1m7FUt6MfZvQwp
zIwo5l-jh^X^qm!Xq3w&kPhY;|bg*5atf<I%dYW#qcKrG{Ta(;dBA_X&9!cXXpG2)s
zy^IcvwtjbSZ}x|E^`Mz0L&JkjtlR~Ef0d^05@33KtoO2n#FDcMo!dYB`B}WR<mkK3
z^=wRgylrf43qL+`-8xrpxzEg?H3w(#@$pSi;gpn=Y@PP{@^b#1++1+``Q~PJ&~&$5
zee9dt+x?Rh&aOTW8bg0^b+vfj-CeDPkB_Zn)v~Yr<RV$|<lVczu(eSSZ*9%~@oaW}
z$SGO78j0-d>sl8tR(5iBF3o#>ppiK-KfnLQi;P~!N4J_bnPgsAz?c$w3^ei}<THQf
z%+C7%zwc)?F1@}k_VCr!;aATsmMG3&w7=}t70$A<vWU%Tyq7Lr3i-6mcXn6~quRZD
z_g>uIuJ1R;qH$~X^;NOE=g*g46}GnP@9*!)kB{|gRZ5%X9QgP5ci`5n&>z2lOW$ex
z_4W1Q$jxatwqy!V(~n=b@yyH1%M0Icf9e$gTMKY+uhRLaFJG=S-0=Fx$Hy}aliO~6
zooibyR{s88sCECM|Iv|=qLItjeV(~_v$2k@E@&=t>Vjv}_2ae5FV{qet&LjxO_?ot
znU7;wnAoo`FBjiA7(ClB`IrMo<H2Tj?ec8h7cVa_x2XBC;ow_tF0Mn9)%^|f@7aW`
zi;;Zy?i~X|adGjFU%!&>?ke3;^puN<iRnt;-!GT_KR!Cj4H|)qjEv0s*)L~%=;Pz#
z+-vV2Il^LF{p|>-<yrfyWa^&D>i$VrSB0|0-(Edu&YUg(8oIYJ1RgzibJrPL)9h<5
zFE1^fIBQl`fpjTo_=!W&AoG&SlV{JgE^pqn$)NVvmn6;``sa2Y3IGjoPntAIKwNzJ
zq-_ZYnPT?UNIE(?e)#Z#fdMpMn3$LdnhIOyKYv}}-qNS1L}PZB`Tk5ls`uvBHG$Tr
z(vp&iPfkqSQTkfUtxslUX`OM(*~yb9Hw&x#9XNiRecQHeuG8v;UvoOQw6`-e)cttK
zegrZx^W#A?|CLjFPns@Ld|lx0@1K&Ewu<$bUi3DfpU&Fri;9X4?XCVk<-Ulkp`oE;
zM1;hq&6@=!C09-=|M>~D+*f|tvSlx>ub=Pt{POg5$(JVlT)d(%rDI?1Z>{-@AGMzr
zQS+VE^5#v>m)F<VpZLB(?@O$;_CEQzzX#io_sb`LcyO@d=clE&EZzEKI2Bor^~rWe
zZ_iu#G}}v??{FJ$^TdgQpss0Q&fPtgo57QRbLPnO+HaUNdp2l(i{Z!rePKfPcOKpN
z4YX(uny0JcC8n1!BQ3DyF|GMgpcB7O1~h83J@4*=XV2O$FZTy!aNDXc4mmk%ZW*o)
zU+<QXprGbAr=wTeTuDKJ!HEOZLEc^V_R!Aa=K<?tEcc!=%ef&?S62s0$bbI)0d?E0
z%ikp&?~`2-wpQxSojWGm{$E}2sOi*n{eDT~w1hi53O{`O=y-mfZDM+QdrJ#TN^0st
zzqwWxrLU&=eb2nMCep*p3)G){@boEbc6K&s-qgD6O~d5L!fiZ~i!N7o1t(sQyD-Br
z*&yeJK}B`-;_U0|3=9nqHZrqMm^ZJlPu4o=_O{%km*ljywLz;Jet&!Ge1BhU;8HJ9
z2}#L?!OQ(tgsz^pX-;b^D;tkQ!_UvpohPY)mPM_va_g09oo$|f==^#9dGqEOn3{sx
zv=gRGVbRyu|MKdpcVyYaL#-CY&v^FzerK(st`1s}0#Y?qJA6a&bHAM1+j!5;HfLw3
z`F^+j!}ssU)92T=&9yFH<k-vxTDQ~2E1i&%((?55^wq52#lG>#$jWX^Jj_<|@)E1>
zEEC6q0)wn;YdAe8fz~)ZxUkUq#F;ZkKr55?JTpo?1!_~T4qxB4eY?5cj|a>t>FJL_
zOQgERbgwX(_|3BcO?oa!JlwV-Zm-pyJ9i4+-?PoRxrtRjejj+)xi)X7UrtWWhK!3!
zU*6xB_nmF#+An7dT5Q$K&ab4a%ge~fcw=)qf6C9V^|yb5`rE(0zAk)uNwwE;k)fd>
zs7nAEVDp=61zJoAns(oobCb#1+ImgQ&QDu!f4J;#uV`T*Az%AN@Y(tK{l|Kx58t~d
z2U?#K6(x0Uj%BlRJKw^RmzP@SEwBIoZ-#BPnOnbH?~)}dpz=msKMpjhesODd_*P2`
zLqoyG$NSsYuh(A{vXUu1J^jv(LgwggIgJx13Lfj1k59Q>I`_Pa=b;sWiw%mO`G8g#
z&$TLb^7G@HG<ovJ4-cJL*w|ie@&5gKk_u<;?QN~|=g;31|MvEFes(??hgL4p4^OAZ
zi&ge5SfFrbjwPs#w<2bz5opv*Utb@zM*aHw_~Y|zt1qmHGzQJ9v28W9u#n&u*E_Pe
z`uhct6ZcG+BH}Tr<-vo5t;y_sG9CBp|I30pCP%wOK{JU{w8Qyk&YZcU>Z=xL2o1Dy
z<>RBHt=kfh^+<Ync^z64xfwL(30lZ=ZEbYK{yJMwgy!7a6Z!t*^2|PNKE7k;?f>`m
z$yzUp+goK|Xy^!97We*r|Ah+y5z*0$JtwQ3k`D(phCt(2ZM@QpQcq8_x+*Ot)wR@n
zx{|H!-iWfRSC`cP|JTvm>+0mhly!AgYoDyOlDWCKw0WM(Vz=Ice}8@^&0NnjQ@f;g
z|La9N=5aEB)*UZgxR8UF*A=wb{LhcVBgc;~4p|uln)CL$*~%^c=+aW}8AhpGVQZsU
z>+9=x?AY<(+S+K)619tq-8YuKjY<tjy}By&;k$QzH*Q2oNJ}rS`T1#r3g_S7-$8?I
zpwXqw%+8&~&maB!`x~?nxncix7Be%mj-DQus3<8=b1e7vHbo5$j(6|g?Wq2)rx&-U
zgPEQ0LAU<C3%l)A)zy{N)!FavD!u%3#-liY2_+K~5i>Kh8P?@`paJ))FBwnuKC?o~
z><|8SKUp|AIZyq(ckUdYd%xV#MrQU4d#lUW#P5$=JMY1R1R2{Zk=$Eb96vuho0yi?
zwyX5@qT1izqHdcdAL9WH)qx^BfB)aM0|y-L>@MejeSQ7$$H)6OW?WR7q91?nLAHL6
zU2@QUP{E$m@#*R5<ac*={<yyXUu)IZR}0<y<v^=_zrDE$PWEoSQd0F9X9Rw&n;RPw
z16q;#=g;T!AHIEadwp#!sPlQ`h)YC7#DUwlrPclCg{)j0x;m_*r{~C*mzM+gR+W~#
zyCW$lC%2>cIUi`DdVG95XdA%MB3stb^>LttcWguA;RlZ&H-j=~(bH2EA09CF$ykCi
z=bL+bqhEjg7592``gu^v>@`(uVcp+f8u9yV=GoWx9XaAM$GV&klzXnO3T2#fraZ53
zZ7otIagV#HqvKw-e%u~``L*9>78Dl?i;0OXDtvrQ$<T1)iN{P#Of4#&QvVH2O>4Pz
z)uDCGrP#Q*c@tDTXUv?r@~Ny<i3bZiJGZ;Ldt!FB_AJwEwQYHKwSt0zK$FL>uB^;D
zo|2Z<#VM@T0a|as&CUJr!2^Ywni`jslqD74-pq7NmA9+WaO;s!+_Ps-OKWTEijb9)
zW|(A70!e=O@<l{cD<r`3eV3?q3wXuHvJ2V$y}hDeUtbp&6B9dh^Je6i_xIyLbGj@n
zEF8+p%5&evCnYVCFv*y(B69Px4coViU%Pf~QPkF~N0a^S1SKUUwNjDSnrzbPUa&x+
z_xbgbTCQ2QR=&Npb*{Ran%j>bKRB|pvjcaPWP-{q(D-)qEv*)ThYuefI&s1yW`A9*
z>fcXKPcKS7-Un)?f&^cGwygZLWP*z4j@`Sv_w2D*`!!=z-QTK<%l+j+)l*_}vhtfZ
zZ(QEq+UlB;vSdg7|9w$Em;28LZCG&vEmDk#jO2`tjt1>4`uKAB{I2Tn?^aIPTl#vM
zgk8-JP*9|$r7bFXd1;aNbiGF}E-ub`es$~r*!^{}Ju;R-AuEGiBO)R=tgWp<sS4EY
z+F1HJZ0>q%b#-^piu6N=4?EA8IkWTBRPFAW#_3(t_2XCBu9r5?>*y3#=c=!-fB5Q^
z)|s<sTie^)LG2?KC#R-UmFr`7tEEJWHM8*sd0zk4(<;z<j`!ookB82m_Xj!G-Q8VK
zN=ob8e0%*{+w=8PBE=#jBducdD=KzONR0%g&*VB6mzD{sk)S0(si&u{d>X%_z!4N>
zJ9h5m3=R%{`0Sb5ukY{m^<s7`2n)MyA>j1;ub@-M@qYPk{r!J}K(jG7ZrlLvK?z*w
z#CmaGZS}{){PrEo{pY_bS^M(k%SFM<{SF;H>KYLp-Oa`;)gfR1CouW$%a<>c-rU#-
z8ovf5kr}gRbL;EtUtH|YUkF-?{pxbM-RaY(h40sV?ggikEn7s^ty`CLpn*|IS=l*R
zUh_>I=feLs5g%@9JTvt6_I~*0jgH-)56&N-&#zxKclm~$e-AV=FG@c@@6g@5u`_1Q
z<V;UbfB5*Z^08iN^*&kauot!3XBNBnw@jQk(ZI+^NZKqX;G}iQiwT?7&$BM~du{pX
z(Ic03KG~M;?rsBPW8rn{)`4<e(x)dUAN~3HSu1tx-Q%D&3?DuefNa*$)otzX?~mA;
zHTA}Z#O4Vqo@Zv8`!B6Y{O)yIru_T6SV1u{wNq0xm3w-7TXjw=Sy@GKC?1)l>g_UJ
zFV^K~muTzMsZ$GziiEztx+)xB`*kX4QP4N(A6!SRK}*Q9D%*O(bFcq=bd=jL^^^!G
zoS#N?_4J6C=id{Vq|$le!iDSWqB;IP<BGknJ1awK^3jhzT-!AD^!!Y6Z-qoeM{~2Y
zvtQg>T@LE!^&Wrv>{*v<w-~3ry?tVSzW$lBXI+1Odg^+5nl5N*jcZ!kGOwSD-TS+y
z=|*!^S64rkTJ&JApNEHl?`$(sGcz-%X{m~*H{G(%`ugfBsOmd(@+7FJ>D-ihx-0GM
zEYKinhqQT~#%WR0aLq68?ncj;J$v<9@vfjbuR9lAOSx6^<)ZtkozK7DufHC(&f;1}
zYcFr@^@oLpg@>+R55IBi78g4^yP%Me(zmy_mw&aht^DM|BX1W|QBlDmEG(>edXt1j
zLBhhfqD~!a*60`}9%2D!-Ml<K85tRu*=D&%*2V6=a!PF5JHbUCO8>0>B0KrlI@1zK
z^;sfcW2elRp>b<Vrm~EzZ0pXQJ6FW)+%&@=vFTXpT)X=bvtDd2tNZq5Ca7!!$!yrL
zLE!1Bslv+ceIhew&TQS5e7sL~QSR++U=Pop-Cgwb6sXk)T8)!B^HI$^u9YiSE{fis
zcdC5v?%lgHZf{$AV@KiQO+DLwdd|;2d-km8=JfMoZ*OfCetLR(c%OZIeEi41-|u&W
z78l)o^y8fFo81dH{0@=HMji(!pR3|x_+Q3UP;hVP-s<nimif*G?eGIF)7B1Ka{yFB
zPMIPCissjayUX7nn`>Pja%rATWz$0Ec2I?SV^`_x*?Csbk+g~D{{8vvzhmdlg*i7j
zoj7qq<K?pp|96OLhb3HC;5fsk(rD45MP9oszqCDl{(P}hD;H>3`Rr_S?_HK(<U0HM
zj$K(9JaNvPo@byfm&Ny@h1LCz^hg?mMxDdfMold#E)fzEY6@QN_wdwIZ3AQD>eZ#{
zYHEvoXPb3&bR2j-zy4p?>t*G~@9r*t`1EP(zS`eOCnu?@-j#vYTM(*>UlQC?I#ICy
z?>FhXe?QYfLtn|qdKekLyuQxAHS6jjP`m!`@9){RW)>C^y18d(nKCqN*s#I;astE%
zB_-zETU$68xc(lrU9??MU!Om|{;#QzkB>phi3yYP_(T`4S)(&!)~rK^4mqjT-rAB0
z>K$|lDtoO+b@?xycYhymczF2KEy2tEKqH=@mDJs0x?U?%fBk;7dOc`^kxty6h@aoh
zkNRHzTlL`qqnghQ2G2<XQc}O%UM>B8SUkRlF*!NeXRg)OC9|Cnvj8qGF7Gwj76=RO
zJ#LnBgCRLNnMckhVrE)eS{uLp9|2Hko}F#}@ZGz0pMPFk6Um&Non7+g#z$Y1>Ch&D
zNB(4W|6@nH#W&Xdt(q}o#)HfL_PQ_CF8*J^%+9Bvs>-UVsR`;HfjX|{=G!ObiHR=0
zawP<`T6}Hv_O|8A)#dE#dahgvnPXAN^z`)f<5M()y>@lF{J$z?lF<NaoP@27+OTQU
zp`+d6g5u)riY(LgV!48YFHg!_bPm*tm9PIJSpWCyb?McQFZ<gcJvmwZ;+D){&_Doa
z&p@B7^@k4+oooJlJf3l3!9nTOv+vcud-pD4YnEtCOpMnqO_ZScGB1h2O7LR!n<JgV
zD}t7Cty#M^^pdn`){-;VO&R|F`}_OG)@<>r@9)-bJIoJFzJZ=I?P{%Za&rYGBsxx<
z@OWDPU7_lB+1p#KD}$FGx_D90xsB)GnVH7kyF5eAfQEngWUU??Xk-S>*n<{oZAv{2
zYGXLMxPT_%LNEEMXkEIqvv}gvsi7%58yXtQ^V~o7+y9f8ZJzIzlcV$R*K7S7w{L@1
z&q$c($;>j%4!d;ra`gRuwfA5A++Fq-v}_{j_qVqdUtS1;c9v~U^97Y{5*7syq}R^A
zSNr&Qzy3=#0jT4_)WvE)A*YT>c`Sm0lFQ28-U2nlg@lDeFI~QT8Pu%MiQMFpTK?sb
zPRtI0#qRyb`edyy>?(b2elZ4?vXzvSs+#xg*)w6{#K4rDn!(EwK0P^^zYuA!C^(eA
z*gfKV;o|asWBU1d2hW`G(Y<@;PRz{ptLNAK;#}%I-R<-=-R`xuV5Jb^%eR=lRa=+L
zc7Sl<<bPJstn(MS%^Nlx=oZ(%a%sMO{kk*Pk6v9JK5^EpuE51^j?<nhoxZ=nUY?Va
z^TU@fS9bCtxpmS1<oA7%Z`NG4;JL3J=^}nm%~zx;!DU&16O-cy<{zwEI$y5cddbO0
zTHwuPl@}d97<Jz0<cjP*sOM(D#jJEfDkrVGmS@MidWoY?Qm(z$;(x#A^O^M$GajWu
zPNmpUU-$3l^Spa|Zg%VMyRkBO`L<d<hT|O!vJWJzYk!s8ulxP>z1{xW-({iw_WyoN
zy!ZJayZn}$IlD?;UYa=X|C7o7yJ~)Zy2#H8F%3*6XqT0jS3jK^zO9xGW>opRnE7?T
zGVT9<3GTQ1_2TY%``>Rio6Yuper~SyrE0rB9}dr}dbLt7ZcoLM=ksemoqT0q-|*(m
zn?DbCGyZtJ=i9C9y}#e>zHRroF=e*t?KL;k&YER!i`;y6R_?W&VvFCX0-Mujo8Fc=
zX9rgS767Yh-+UgV1t9=d^Y9H+;933c+qYkTdV0FtT7bbqi_z+U;kQfP`d`mkzb|=v
zYinHn-><9cem<R^cW1}N&*$y$3;WvyUM;_0d%fTO-;JA_)2%B%J;}fK@#*yVZQHkB
zzn#Co_R0I-CzSg`wr<{h`RC{7{};_?Yp{R3@wnXQ-4zEBUVvF&@D1uGr~ufTmUC*a
z<sb`y)$payM-Pb2X|oUCOoxWd!@9Q)3=dYYykIzf<7l^d_0Ol%t3RJL|NZaxd+X|N
zIp%qHUc6qv|J|>zugm9GKkhZJdcXJkuFB78>F4JBJZoK6UVb~rEOuAP%ewje;7ElL
zHVGgj@BDth|9*7--mCB4<=OxF;C$ZpdyIVjpF;gT9}eA3H=FIN?l<Sh-Rp8PGG8vb
z%a=Yp)H<*3*UR6PW-w#G^alo^1<W$V{I*{L!q>;WeRXy9>GXB+`~S`U-|=tt*|f{%
z_iKvv&ohJ7!ic_!lf&1=?A-KLnZY71@BY5KTeGiMeZ3lPUHj|Hw)2cXZdZT1nZCXD
z5c6r82Jicq_6$EZo3XRAv){I3YIyv#TYuk+L#^Dk|9(E7YhPb?8+3v$%*_lR;=jl<
z{E1ZGRtpz`GWgjTt)NU8HI)JVJX}Qwc9<lDULdppHB=Z3SYAM+;A99>37idKv|$+R
z)xZalf{_OV&<zgYL_d000>fY}3_m!d8|<Kp?uP^pbb~>O73L5K&4Xd^Xy8CXhJk@$
zG;rWSF`9DVK{1-G;6X83=D>r3VYEPohs9`Z1rG`uSLHu^Z@hu61%TT*T5}->#c0h1
z4~@~93my~$TXX%}_!iW=Xs~~GZEf`1_wVz6_f$W-vNCwCWpUc=bhslK82-Ekx8Wbm
z*jf5I?7Yq9%X6*&-}<Kc{mfzh|C`tEyCu93WDZoropf-&!6NP3_wVX<_t%zft37AC
z;rd+b>9_CS7f0@Pz*KH4TlM+29TQYP0|P_Df926G6e2hnMso~2Fa|cqjCQ_Z5kYul
z;?L~8zd3tX#~iTuv#d9_=PSRJR%T&AU=MSUxAxKn4;FDB?B(d<-NMmj?WmO$8X_=N
zXvN3#ZW<n|+_C~i#A7)`V?0E~U+J;z-k_W*+CRmqH`(#I-n(+<rEYs)eMy=0JhINX
zy)xanU8l~Hfx#0aW<<cH5X`wCdJ?!01F>LO14EaJAaVf(QWt=s%R>o$h+_f9Xvzc^
zjDZo1!5xK8jBy$#3|&GPBO|RCx>PW{%7vk8G=M;n3CE)W1P=;OeLI?hkb{F^G>ahz
zhr@6#gD!kOH^*}F-QDHscXyRa%E_I(wl*5HnPq>?--n0WH|O5o7E^XJb?1{w-bI&v
z&7aOKzxVQC5_0G;By1E~!2D%r_4~c%`g^|wmA$(&Gd!+RwYj-@=ihI)i=UjBXur3t
zsK{vh-7?Tp_o=qk-%{S++q?7Ywdl`px8I-F{uITy14+ga-x(PG?K^M(--exE?hLp7
zo(ZwL%Tzr<CQIk-Q0%w+m0|bu$z;~`wq<W3<Z3<~wE1$udFG567V(oAk<DswJtKU9
z@z;&r@Au6<c<`XjhXc%?(^rSDKlk_h{rUd(e@!-T-pm~bnyG)b{eInP<MTF?Reru)
zKEG<8II=Me5qDT#Fx0+Ty?)=R((AF)O|!4fDczTPdfLzH;-4<M%Rl|~dj0u@&h15K
zO|L(B)UAI`G(2YF^7(aEck{L{-;L^`qnR7tF*5wARri~7;>3v)md}-ym0y<awygW}
zqv?9x->=srcNV3-+x>pun|ph$rOk3qRKMRl{rS9Vz5V}wWzVbs_cP89b&5nxk<rRQ
z{`b%4^EX$0eN}v}y{+w8eEf-*mzQ6DTV`x$H_u(JQpL0A`P}kn$K~tKoYvnzM}1y}
zl6Y)MV164?uZ4kup?ea8?1KK-iifQ~pH7cIXZgOw>ht>l7q=D{7vJ1h`#bV^a&q#|
z4~O|bKb;=`Y+7{Q&vJHVhUXdEZ?9an>Yb$R)eMtMIcBftF@9+OBZn~gKs_fY4o;l#
z=##gvJNL6wSbdU8_VsnKA8u{UzW(gR#l<^+y;^<VYX7TMt1rDREB^H4r2XGNvAfHj
zUh>wreVvn&qm!JRT%T&kpi}*}%zE+SwIx=?rT#BhE?oHV%o(3<xklI1?+sz`b>Tgq
zjKu_IcD^~KWv{NRoOO-i!h2BU<vc#t`}4=+{^DO>UapDUoc8a}=JR%^4;*kX%e%AV
z!PeR4`R6V!b~m=Ro}ImZZ`r?^vNAJfX6BurPHF%D@;Scd<I$X3TVBf7vNJ@STeV7S
z<KvJ?VRwtGQmp2l>kA20tzZ$;-G3bB28aE>_p)=<eLO0Db5CWlZ#Tn>bf%I9yRz%C
z<*D!Q?Y+4@KVGix$3vBqGmX<X)&KvOb9a~N>uYPhCxI5DTb8~Gxwbxj{#5O7HP3fD
zpU>O#_uK8tw_C4&db9bwn&+;&d1~tF#Xp};|IN(IaBg*&(Elr}3+n3n5y{M<f$zfc
zZ8<k5?S8+{y5Ig^#lHXley@q&Z}<EA`|}%<j~iK9TK?a6T&`Ltf6qs^eLtVg{;7WV
zZsBp+o7-}uzrDFRS-$RvqWQgw<a_o1|H@bvsr>%-_B5+_Ou+T)NL^G028Jvp2lf}m
z`TKsRfu^*5e0`rjIXU^}hD2vRS*t0t^Y>N$vt?#xj@+1Z)be`WhlA{upH8Y5e|T_k
z&%a-<C1qvLM(6LH`u6tr`RCWeLJmUf2!VoYd)C!eJ^lUZH8nK{zx(+4&HL)|<v*x^
zI&#ECO--%JQV^mVO1=<&ZpVk3Z5bL;JxAM<(C`6KqYZ9QD8R9UA*iB(abHX=+dX&H
zs#o(a2KTxtpH18RP7*AoBgll9U!Jz4Z1>!Y7sIUP?%cKf%asck3ewV+xk6^7|7aui
zrgS_*L#O_z(ehmV&eGOsu3x(Qs#Var><{aadP^IQY@L*|s+t9C)t6S$Qq)BV3=9c{
zNUFiA7)JY6kZ^#Kqn%G^KtL#>dgm&VYpNm2LF9j*-FN*$Lrc%USn0NSV%p}&?>r!3
zhKNr{DY|ye-MsXYEmQr{*S*uUH8nArGjnF9AY@I)ml=pY`GWq?(9lPpSE{Vt_590;
z605ngD_6mmU)ZW4Mh+r`qCCy6+Cr+77scAI<iK_!hy#xl5UL@<qXifw9H6Ab=#UCD
zB)}9=<)Wt%tk93pyY;qg)v8t1ZvLiHy(Y8I?m`Ute=vux26|wVvHiBBZ0^#_Ggnu8
z`SbGfrl+MvwZK;sU04pyA_a0GIFmgC0|P=`98!S~a`vBfBdXA6dySmWH^gkc{Wc^t
z^n1^|OcSY0v)QHR85-*E2JLTGfA^SS!yITVfWnD^A?rfkc4MnsUdxTczfYMbDJ6C8
z%$Y3}ybY?UmUj*de=lT+I0uakh<ei%t5&sS2YW`9o`2c+vc$?dD0FH8NcqeA5ast!
zlyA*ay&3YIgW<vdXL5WDI=(}oMEaljzRqdMI(hrP{V~($h+X7+oH%(I-z6h~#ON6s
zF0o2hS5y@bc67X$C9B0>YGB3Txt%X|OVk8~T{l(v<(iZNcIiqBer??Hh*$B1S>=iQ
z55NEWnQgfL<#k#6&(A+H@Yj`<)x14amu7dyCYAwnH38<3D&|r=%rR%oiC`>a&M5H?
zicKuF+N@ki6=tw&)-q4crEevjuf8q2{QB#yd5pp5f3h(o?5g+&?JF<#hV%peEMAtm
zX~Tu{2^(&Go3ij#$+JzHHtBFRh*{oeVDJ$?{~u%%14F_Vi1iKiAzmvD4+KrByItIt
zV%dDKaY_&i;{~PX(hLnRAN`bvsO~X?j5UAI|K%xmTaGdBc&{#OEr1Uzn%YG(w?Ul*
z(agZWU?7E(3PIvz1_-o$2{HkKu@s0Hs}r$Qsj%7_Vh95R1C{|W%;kxgL#Tr;#f+c;
z@=Uu8E@wB)!=5=981ihdKi;tKj}Lg@;DbLn5gs^_F-wh``!5gM>Rf-xRetGu+S;e@
z8L;aX?PFwMXox=l)nbjleK0s-#B_t(d^04LPWk1wbE(STZO?g57O^!mYc8$WEVJdr
zPc{ZLOA2(sJ*fnyuakAQ*)q-GI%m$nz)<jdr(FBjr|DcEQyaFX-2%HC#DU@i8N~E}
zMiVwPxWLqC&IbnrjKG|%ouD!kT77JHyKJJlbc=2Bid}c}s`kd+HU{fTNUGcm&Khd-
z!Rb7K%fxqbYik`_^VMz3c|w;PPoFw9HJ=MS&e@>&p$g3KVF%X*2ShZMUNLXhReibL
zHr->Iv4o6==27WG5OX>9+ygT%JA&&ZgHTAd0T$~qU2o2S?4Wi3KQJ*cG)z=R?g=F<
z!QvEfPfXbrY$n(&28IJ3noF<zsL}M?|JKrZ)0~439K1BaInb>O>?NqO2EnWTn{IsL
zU|?XFp=F$lF#usg%mnZVDq1mT$RW)IXmElkEUlH%00IRJ3=h5lI+=4DoP}X7T%hZF
zdC8PZ-+C6lD%<_?YgO)f28IM5)T}VW%lC3h;==g{6Slt9biVrXOloRsWD6g|fl|~o
zVldT9)6_2B>r#I8xd}Sy1{M>7Ksm7CwGwi+W=J>%sTdg;+z$Dmx`u&)L4p^YcVX@W
z(KKvak0w`80K+g*$rW0o_;fAH4D!mXJ{C~A`|g*jz0&_|?n^T;G|V=Bc|CO9N`@IB
zlmAJ~tB_%5_+bs{am)ZO)rnxoOiVx9;(We=s-Yd0mkVN_&f;qDG~w-k*m=B=q2d2y
zNDpK(c%{wj1yh3JUE+|F*eTw<6W&xaGcXhstNq_~%2bqLa^@%b!@~WK85sVb|7;KP
zoEmru&b3hclS#Lg-KM<fWnegPwlJ2J;ql323x)$FAOC==gNBdhm%o9OBV)H_<Vpl2
z(?G*60JJ#^vIc|?6qx!>4)VHf+_viW+hx~ZZ?$D+U^q4p#YG8CrkFK0sG7W^0<NV&
z=78`47HzE6<PJ}i4A-#o0<@Y;IC6H2El4L4Zn#LyVCBf_Ss8rOi`_NldVIa@?d|#J
z@7#$gdw*|k@N&Puub<ccc-TI3=FFY1&L8WQ{(L)s|J^3ERRAl%?KAV|KcCM(pFY2K
zS~EL;+VMVF%ep@m^J+ewoMTsORsHSF&;I$l6A!n6=16xwpI3cNX8+?p>$V*dNHN2}
zAQ8$`(qQ=Qtoi*Xll|>ZUR>-BnuSz3S$y7h`tNtU_1EwH7Parsr_=R&`$1FV-QC@X
z=Ye}8a8r63LH+g*_kVx6><^kFo*q~A^3+D(*=A3VipQS`kFT9Nzy9CPUGJVhI@<m7
z_4@s7rowQ&Acll6*adI5-+y+m`u*8wXJ=oRxxY30`qcja>eKb(&n@n^o247QEhR5c
z&)@!U324H0;alXL#taN@w?P%ukN0!!>+L>&{v0klfByXQPft%Tes^bQcHO%>cVgly
z9=6(iyODfzQ>r&;O~+#Q{<Qb^_F7hd%h{HH-|oyykW1kB0Ef^5=AMoA|9&XXHp|`h
zs$%)&ou58tgC?iHy}e!j^u53B*ATh-KOb#AolvfPKDYeSzu)iI|4)D$0AeI8;k>|j
z?8e*e_vhLF|MPj(<K}}8P94uba&K?-=MRVZpI=!S{CX3p1Yv0SW`dbvK}IknEaCu}
z@#jy?xw+QmS3iD!eqP=4-JZ|qr1zcQ{ce}`{o3z$OYeei1-ZGa^!2P{&@A@9zrXW;
z+y@6x!e3mCVFm_<;P*#5g)Ivo9hsFZt{0P$$;<HAuYu3t7-%KQ<>mgM=(@S5^7GWk
z@%4X8&2nx`m}^~r??dgs4~O}0Zp*!0diUGj@ApnWdi03*zckpfJmH#4k3IMH{FQrN
za?(>CHufMdSXFQE_1{Zzu6efAX8d+P61=+^BtWzNhTqN@pMP?<{Qg;X`I-sg@wKL&
zMK3Qcm9ek0*<Jqr+_$&4C#&rL^T}H;X2%3s>#~%`$9g^geLvfNH?REcU(g;~%i?D~
zag|S}M*nUFyTCx@ugX8=KrowufnnWz2HAw3x3{)xgJ$U$I=6p%y?#F|qtyL+xm?D&
z?9HjS_bMLuf({%2-7UWUkJt>`>TgdP+2u|+^V?2Y8@>J6nVH6xWp5(h?fd;s#;Rn+
zT76EK1z<X3B7<zgnc6=ek5_&^Yrc8QmMNec)4t!YulJj0GjnhC_qd&B+jymojEy%x
z`#i7q+s!#Pl}7P3A6>)3!;S6j=TDEXv&`T7HEdh%?XuPTA(KmBgBchY5?Da-e<yeQ
z-D%41eNRqIRKC9F?8fBd*Z#PDQL(J~QNSl}XY-~KrW{NkkeK=N`)n{1K^X9Y$1o5A
z3=E?KX~?0$K<3cvq%+%4s=EYRjJ*6{)|_s}gg+=9p@xmuO?<_~eo69#-JWL@GWT3e
zSlG1I{sSIGdTb3RQLD>iahgln`cd<hEtB%eoe~UcsO^jy3V&6)bNd-)6rDTDU~rDy
z;Ud%9s12HgFBpDeNLYf}+;1?Qwd~{}C;R4uS+|4RR$ZQX`qZgS9I^}#@=+7s0jZ@^
zq~_}*_x?fs@(<=rB@930zrBsvI#Z{2(Tigi27RL1re1$->TLE;4v6~L+k41!U%|4M
z|CT?Uw07&Kro*k?j)9PJ2ONzJ{~w0zeQ(Re(2)OS%XhF467dc-oItBuy^u!(KuSk<
zy@Nslj2lJ+2OJI{V)VQOP$+;g<_y-L51dz(@4*9=VD~c|c)v9_I(zNj^gCA`7QCpi
zc?aqlF+7MzSt^j1bbH&qdw#L&<E#C5uADyoy59879H7HEeuyF$We0rMY*n-Szs9fn
z{LYER*I&D5>w<euAGDDR#s+EY(D&8-AnPCGSKNY3%7J)L{2emT3FU#PVY-Lu>gRi~
zA*2WQa&KRY%6>0tUTPs@CD&hl9^`LOYX`D95XAezeS6#2Z)LBl{@$uS<-2#!p0b^D
zpi9XZ82J6*Wp{nzTGNj|(@SqvpX;5oJI+2T8(z)I&4KrL|4j@2y6-z^5Eo?jj+M*z
zqE9py$Ro!sNEO2nOzjwc7(E>X9F-sfvwcUq!1=ld+yeQLzb!X=?bh!-v#n(KWc!cr
zO=mc;|6H{UsQEGfoVgyzSq~<H6YLIa%=G^E2J?aSk8DB9X%6^5mj<uj{qO=D$9Lv#
zz4qtA=g7I=<`pYHUw6I#T2$RD#s}da<v<Dh!Sc_&+#tg%O2DHu?{2KDx?j!0@WFl0
zaZqXa<7Lfb@X|85%a`G~5~Lo4ckqMtfS53hIaf`MgCxrMuc^S+0*oF901ImnP0yr?
z5!p1W(pOd8gI9kaiqWfp2aSKeRX_CuB~J#1JLcf36ciR8+_&Yve*5;y*I!$|Pnlg+
zS^2iek~{6ESbxF#JDMN`3=O{#3n%}bh{{&FdH&Uw?{lOr%lFo8xh8b_lWyJry+zBx
zY8l?mg;xqc?B}lfzSsSL{^K}^tsDAB>jg+Cfyf4wMiEE^bE0_kyfIL?fH6^l1FaW8
z<^TIFC@s-{kDt%s1slY`0Pp?F9ov?>ckkR?ar?i`D+<=vUmvUYyj~>A8rJPy0Imxd
z7#I#PM`rsb{6($~{%dS1gPpVI0Ip&{wzik7y7yhKa5>yAn@yu>9vbYR@EJ|>@W8-a
z#717=AkzGg;M?1_Ub|I&%vYALz3=$rdyvH>3=9kv0<dbRZb|O#s%q=fy>)MGpDv4w
zi`yM@P6@unWFKtrZG(I!&UQb;4>7oDJCNJ`3_nEYeZyElRg1BJYV@!}cp`v}iTzJ}
z|1Wmiy6X&m`|~&Z7&f&%@?6Q0*)@SlFe{t8t4T`c(876JmrI>m(bndmXdn}9!tKH_
zN2;l7Syx9!W@d++(^^fIgOd(yj^RkMKlf5*_3Y18z1RQ#t$X+SH~XHSaO)U`Y3CPK
z{=z*<<0H4=_Kdcxk%MA*wyTNkokdhVKR^Hd&*$^=Z*R-Zy}4=W-QDHi|NVad|M>GY
z>(*^cJlrN%^<ts+236z`W7xpM@`AxT@BO{Kd;k4<ZTs)XV_B<`6}{5t-wrVIfBAS^
z{{QXtntwl^@BR5~cJ94BKe_TyCx`!B=Dff-?MC|i+G`&lAHTi7zW(?3_wP@t&wta*
zZ};L_bpG3&&*%N#em*ifI{W>-y>}}f_l6flqd4Kge7^?14M*-(KA&rrcjv~dSFeuV
zT;@Bw>QSfquP2lJttvk~k)K!i<;BH)zh145tNnUad#4tP0UKCAet2_QfB&04>vtKi
zudSVaru^-#(vRQo7k_(m^V{3o*Fop@ek(@N<<P*l;f&vWySt}Ool5;Yb?Q{Tm>m~Z
z1~0Gs{x>|Xa;a|gwl7~U`^T>og>)XEdK*+XeS9Cs&|v@m&d%c8TU%ak`nmObT=mEA
z_dk8T9$)_A!oogz`+HZz<7<zWLH0F5H8M<Vmj;E@v$L~7`_=Vl|NnB?U%dXmZgzI|
z-SYdjwtqex4$lFvOM&TNNZ7f9Q8uA-?V2?uudb{-{cO4a{B^IM&CdUK^*iV+?R(Yl
z_xjDTxcKW=Rj9aL%!}#qbuaJiEMB{QefeQt^OC!z*Z;ozZ~ys>acuqHuhY+bdvo*h
zJlpDjXHX9<R+q6ZTa$deFV@Jq_}Q8JTX-2xgX5#@-JP56^0ilPZce|wtMv8JpUdah
z-AdY+@%-G}{lD&kj>Asc_+p~F+|HDJ5js|tpHjBpud8O~mwU5v`Mh6u|Jzr5NGQKw
z`@R0ZBHTX=3=DrV_m?evARb?H(f0eD&*r%-2aJRlFzak|m#^J&J+6AK`Mrw8>GNy1
zt@`}@eEE|T6U*M;ySpv-_Nrf?6RnG%`B;~|d9iBsx>x^xzXwfkPoKMe*RET++wWfU
z*57+&Zuz~R)9b(^BXB!Ed<UB!ySwb`jpY8Xhq(2>9Ok#*l6<_cPsZ}nuU}Q|{PO#L
z+}T(A+p6kI#{IhAx!dm)dEefipa1*Y+v#(+Z`*dw*Zl64W`4UL;dP)@-Efl`KJY6#
zutyYu=63b>|0&Af|F_Kk-;d<-yQSgp_x;ZMey{rd(R8tHS821HABQ)Kb-Q*SedM(c
z)p>uKLHXy7>Ghb)jm+#;1rHA7+ksA?@XmAjuY14d^V$DJrU)BBW2h(pd@S98BE-P(
zCw{b%0}GPTxh+^oFfh<;tcS=t3E>hDYxE#HP$+=$Xge4j3}Av9W6h)OU~o`Ei4oln
zhK2!@8ZC360l_fZ_lAcA!{|Zjh_D!~%Hd%l0UK9@i;M;iJSeChIRB2`ySt|%c0I35
zefDH4MVEwwDQA=x9c~mbG|<fuZPd*QZY=RWB4Fq({>|kt<K~VwG2N&q0gb9#b1oiM
z($I=>nQd`Ht98zjPM*ajT6@gp+oEmQ^PQ#JKUb}-i@D!^|Lb4odo?iUW2q8}h-_k3
z6~bq8U{+z7DMDT`1XecEoYP{P+J&?h02~Gk45J|h4G7Q_-)K652L_fd{AlQmh7JRk
zV^~H@Xn4994IM;KFz}4l?(onUX^joI$BAxWWZ(PrsR*>^FM504+gaJ`GOw?Tt^M(^
zUA*Sq<9_>hjqGw6RaLuAo;<m1*|J-k)BWey{d#$S1M0whfvV5~<~4<&^O-+?{`~g#
z_Vv@_s#bP(c7hHx=5Bj(zvi=Vcx-9t=FOY;{`quT)}mm6u)1H#_q&i;I$yLs@8Od=
zuf{Pn?0*NEx>~#a-m6yexQze*{)U1~zMZ#wt@`|$P5yR2pV-@38yjCfbLNcY=9@Qf
z=I#6W?Ai0@yT9M7)_?sD5fY#l#?<4SFBr0KfHs^SIpPAk==BunWZ<)B&V0F<KL6|8
z^82w@eygdg@Ba7eHRz7hrE#Jt21GEkfb@sQ*Ir$_{obu-XJ?<E37Q6b`m1%0Rp~1E
z`ac_$-TS`0*?j&RXf6zNTj;b})Y&ub+efnW84kp6-?8Jyl`B^&Kd)T5^4vVz+aDhv
z*Z<MiE?>9f`@QP*t9Yf&z8n$u|8l4JeC(%KG$ZB<Utqkp;eOrkwY}2j^UUvW$-I2(
zEBDOVvtNUz9IuAQ=YD^8S65&E`|tPr<8kOddGh4BIhMuu{(O0PS^K(v%I$5r+WX}z
zpG+)!bK_!izwNb$huih<E<*ACfmsR;>=B2TEn8+)_vc6D=c7lDuFBi<@mP1&{j1^e
zcmICBfB(*%7|_kC+n2BY9}k)by_LP*Hho+9`+MKs-K`G%k398r06ba9Cu>!5?#=W0
z^>Isc86sYT!}r_U+rM8d?*H|4di<?Dm7h=j`F!3!|L(5R-240fF1ioeVO#d?%}u|#
zR;33S{vH*N&pF;FEB+UHAQ!~NF;@TIIULmA|7R2EcG{_CObNQt`)_eGe7J7=<3aP^
zkH_WrembSCz4__Wr($Aax3*@7M{mzt`|9`m{qIjqRQ~((`F!o~e?fa#_r8B}a`N8K
z=d6AG{kNx{o_6{_N@Oq`5IqV`Q|IPdSHD=;UiEBdx>eyL7tj<MH#fJeZPk`$cK&sD
zzJIyw|NU0>`mb-d-#4?hjlDY0wtCmgWwUoZ?z7(YuuU2?^~TN3t*fV3_T$6DtG`qr
z-hh$`qMR2PukE-VU%&VH{Q7;MDZ=@6zgFhn-uCs~?)RXRrPtosoOgHEwe|7!=ZcMu
zjX{&uXV0H6|McYKy4~+~f#wh!nb~)JK4<;^9c(WG)a-Q(OeGDbd57D0&z?PNYHt2r
z{=H?zhX<DGi^9*IJ7;EXUA^-<Y+nOJ%e4t##rJ`C-$M8xvf)45Xng|;2rwS4Z@|F-
zCJaV=*B=}VU}Chp4-N(}abUDV3l0YmLC@~~s#y^zXG=8v-=BQEZ|jyVTW)2?ghg-5
z$*iiX+IpRVf#Jt`732eo8cZME*qHqHvHbrxUtY$CS5G~ib$MB~Rne1p(DK!WP?Y#=
zFipzL%slcuKjeSR+fu#B^`*bQ{NJ)=3)sX6R(M^}@IUo_T<n&6*DZMN>$H5F;?i>P
zMJI344M&$LolSuPx=9kx_-8!&^3uq0_ED{lvua989Lq9i<;cx){U~zhsbfTR%KEL_
zvtQ<{)3&qUr$7HY{|-h5hJ@2U-M^ln4?0}B;lK0#zi&{hYzBrun1^nT?u7#-L@*xR
z^8gM85P_w@hV4iINrUld$^i!hh!{;dpiltg(Ub!Y1`sj2&k7U@5KOH-C-4dsV(jQb
zH&{3@FpO?%M});_fea6e(E=GB6r%+)JSZ3jqCk!lzMqf2767&n4dJrUO?vRK7!4eF
zP+%D<7~S~*3!TxxfrSLPL733}`^(GV?Ck8f_xJCgYh7OU=t$?gySu;3-@m)Re*e>_
zPeB`i*2V6&DtO?at*yPc?(eVs2-qHdh)I9Cwt<FE{^aY$@4GYCx;!d2_U(g%&3E@y
zZr+@J{@a6t&3^N2e%>w5&d%Oj`FR;=&(ezv3+LI_-`kpfeOLAOyxFs7zrDTvef}Tt
z;VuwEK~r(-LA%ddZ7V-5iQb-9`t{Y-u<-EJyGmXLx%bPxJvCL^w(84^-TCHbW>%%I
zuDs7nKQ|{cGjrwZ>+84g+xKsJ9_SDlxM2)+w%|dYKi~82?*na?ii(W<Srr`-kx^N>
z^LW4f_eV#&-|zeT{l}hHUtV5*dvo*h<^J>ksaB&53pK>gW{^$bzJ2G;n-32UzrDBj
zclr0n$NTI5{!8Ce{e9i`{QID3EctDy_fFohVtK(3ePea_`ly(gKhO5<*l}aJetgx>
zPfzFn+S}XPYghm8&e3l1`YSF7*MjyiaSJYB&PjZKe}8^r;=|d$zrDS^zwZBHIlG!0
zzkXGL4=c@l*`CXSqG=l+qtyYiZOO;`?CSpfIQ#c-JAeHC|AOb|*}lHBvsl);Y>l*e
z-k%G-3=IF1-oFdo9J85$=l;Zl#~LC!xww*a9UWPIH%#pn+xV5^&6W=gK{umS99v}^
z*93DlB}_cz<!W$Cqbb6p<*p8sk$rW)@#eW3)~~MF_jTX<UwjXqAqN#--~PX^SQ&m)
zs{74(ad&rlefhrKyQ8n3oUC5|T{i#zzTC>nouDDbty`~7RCfRO;d}o5eRnS|cCWXH
zj*QGqO?}G0A9+Hl;s2Ru&(dbko^3y;_TQhM;<?NR9Mv7zEe=eZHtp8Ed+$z9*Von4
zdpF;{_Scry*4Am$ru}>RS>C=br?PVA-o1ObZQpKP_vgp{uYZ4ke_#IaQ0x3#prg!S
zA=mJ~ufAmAgU`>;@2>dxNdFc`L-U&p>*E+2=9mBd_4V7gZ&e>29Q=24d;a}fH*UQ6
z^z`&xtI}1gzQ4c!{nOLa`|AJiv;Y3}_4RdedvCpam*+pv=H;84o9lo5gBcH|5BwK5
zU%)JrFkLV9)v;dbyL+p*^UK?nyt}j0%*?Fn^E2PquV4QzE`N9D<-^16d+Yx0y1d*!
zy!7+4v-51LudR*Ve(UDV%=Gm1`ntlxjoH`N{eAf#HF^Ko%JPDN{mx?d{$1to<ND?8
z-(6nrKi9r~-`cfn*TwAIWWRaCh6@Xw+v_Uc9qks^)zR6qZQHe5w{G$8pKDp{20uv*
z>{f<)N2Zbn=64?+9$vd{-L_r3e)*?gyMDcXhv42<S67Gse|;6A3`#aIKfCZAe7GA_
z07QKVM;Yq{35~X{L7@P~qpfRjFo21HXkCLX230Ym?IKuEjJAtlApvd|Avhq`XyAZC
z0fI-j%R<6obQBRD4xl><N9Vj?!7<v-frSLaXgdcU6azAf2(x{3a10g_45L*!JSav_
zzCZ-U=n4&ZSd2~x!h?cfRsKP``uqD;rFYp1{?y9z-Q?H2KKX%&ui_-drf3t>>kkz8
zF3LX$a=UUxNYHI@cTyvZ<u=O>H!tTM7CWv!xY*XA@JsP{&9v8+{6+JslrB6z`?>1i
z-kAIE+uxV|XUw-7J&gb!5e%cJ5g>)d=!ScEU{HO-J<Mb*>+|8qal_P%4qd?k?XD3R
zIm?(Liniz9e|OgWe$MxIcfqGj+Ei@#{QUgl>u)c>)&l%LU%Wl<?yDakAMgF~sN44E
zlgXfi4?jLS%D%x69vL9UhYdmtn00n8cJKdo(Otgu$%%<}|9(6U3lFdU`E>g4SF6|m
z`*i2)>+8QCH1kKr$LGJlw^vuJn|%wqAyIeVu`>L4zVF|!*LJ_(YzCdE*e7cp2AZ|0
zdbjg=)#G0CU!P9v|NruaTYt|5e)~TcK$C^#?_#Fw$JYg9BTwQmFz{=dgN`vgZ~uSK
z)vH(I>i>Q{d$Uj0y6WxL>$_@x7MbVW`Ehx(zs*ON-DPj91hT=mGl2X8#@<e#1293e
zESt~U-99(h`u$9Ki-LsDmS9;Jap1nH1A9c0dH%he+}zyLHMzNKcbC84wr}4)-e}|r
zDh7trULf=8{(ik)_U6XM)PFA)_vhK6O{(k$pP9MwxZLaS_v`N){Ri#Lnvd$IKe4NC
z?`2^4f9KY%sMoJwM?W*qzqjVq%jNU;t-o(y_9nvL_Ujef&4=6h%YS@$`1@BZ%%LFq
z-{UtoH_x@L{x<KXzy04WzPA}RyaCymbAMlL?2dwk^XvcZoNHa4cW!;m&Pz!fGw$!J
z{r>egXiDwp^ZEPN-v^li!w=T~-OkOr|L3#W-`?Nf?<>u?;Y`@JYDR{CJ3$9^_V)Jr
z&9m8Qxx4mv*>eB+?;ad%etU24?p2_P)xW>KzPqz?bL?ug@IJu%g2DUEfkx)Nzh150
z`}JCM?f<{uZ9kteo@-aT>;1mp>w=g2<?bv0^W)>WIhL2V-><t3y4vvh`@P@ex{of(
zzP_&X`@6d!siof2S5^IfyIuYV+QztT(-~wFPS$=pslNB~IqTYAFPH!Q@wor(-QC;u
z_x)Jp+|HM~Z*zoBRAl7MqHlN0@8@oe$l3S#eMarZ2(%4D5B^`cCMDRg^wSCD{xAQ2
zzb}7$thesx)9LGCc3$$<-&=Ctdb!`+tmNd!^KPGC{qM))evpTsZr`}^qr!hwUw@b|
zIwb&0QlnjESV)Xc2_QmZbnPr6EJnM^@US4*RUVx$frr)Td<k+;jHVoTXpGL6z=L8q
z&6oU7dVg>6RvCe9jqw|&pGsj{x|BIGtktBY<>Z9xicdEb&6!wy(yQ&DRQpDmRjq|G
z#}vC{f{ai86gb>-xF^_ESxj=Gk&k6I_w110zaQ7WdH?$K-usg8Z+yS^_J01_e+Bm6
z_wM?(wJPs-i7ogdbx06SI0C=p3nIYKz{L!|Lk21|Nn!zNZ-yZt5p69PgM$!;HZ7hD
zsC_90k0cCjtr){4o*3Fz7$EN+202Qh6GNLQ+Y68k5>_!p*S6pghHq6cw1r^!b~KPi
z0|~Xu&oG*jFp|V*b{j2|(8~MKf*T`AjMi?WO#q}e3Wzz{PQpkMqm9YY7B?tsATR~p
zk_NT>lao{}|9-iAd1dhOH9Mcpx>@)8?dRwA|9{5s+O}(#)p5D%oLk%T=bPo;db0oD
z>;0b&aqHKd??kE08jhV}kX_Je{po~q@lnz6Cm#;;pPw2YH*?jhRXj2l2Ip-)`|Q1b
z_1d+x2L~Ew+Ef<#*?c?_Q*=`G=YwYcOY7tJpP6gDz3~!iH>$Uj(aJ&CEcsZ^owD1x
zJ3k!aE`Hc5{%l5a-^s=OcC++icRks1*>CmtTetJ~+n%@kos+lo>9jee*CH+7?Rfm@
z$K(F=uUEs*?|eS*wu3w)!~g1f4QmJGWwVoZX`&J<=ht<;Ts9*Qjd-<uK88}wWwU?1
zT#li%>*cb#Ur<w}8GiU1Ik0COdbi_oUr1<Z>WvMFrN^VT<;+~@-2Uul`uwx@|9_r8
zl>L6s=W}cJ|NC__fB)ZCeOt4y>#@t%6ujH}{a(%Auh;KqmofYcuGzc>uU#m9A=euW
z5A07e$S&ZVZJHgntNi^uv)o&23ikNVw=3-zuYA}lzUk|===CKafuE1M^^MZc&H0}b
zfk=4_3=9h{8iPD6rWZ4VPu6Np$sXr+zLjg&o^4{~-gkMc=c~P9D9R&DB^NN8B$}F<
zX5QTN)a!Wk)~wL)KgxG*+qP}ny=>HE6&f6Rlab-ayQuAXbJy?tm9_M7eBIB~yN~Zb
zy(Oj_b*1{P`QtC)@wH#?_wsBw^=tq4BkYq+p8WkdS7ox)i}$mpKe@mE|7%Fp);;~Q
zcy<!+P2Wpf=7mF&z{>c?`{iNMtN;CtF#nqEbzb|f$Yo!{yI0nKyx(6M>|=hkBzS-5
z|GG7^f0-_QJ{6KmUS0q3{y5Z-`>X2hulfF+b?LJgNUe|g*X%#vlOcwf=-p5GqSngr
zXLr<<YuBz#lVxgnpVn{t?L-qR_oq*%_172t*?3&;bl&c_(|*6-Z(sd(>-Ft%xA#_m
zFL{5@mfz;X0j}fudp;iHkv7xO-}@!V?0(JX{JmwDmUvpe*>L!uu{_GY#rv~6h1H*3
zaOT&wW@GT}C<nz!)z?>3)#p_x&9D6yd235%aCyzGEt#1Y7r9n_eHHqCD`;NT>-cit
z+0#s~#~9z;U9P`pTmAokGc5{}%x+~YuDY*@vc<3H%9SfA|Ni`Zd4GTX%|M2Xq&>{g
z9GbKL@3);_E_oN9(p;|MIZY>W(mdPhw7p-ioxbdEKUbyl``z;3*x0%2Vt1!~y&CR6
z$!DgKYP(F4N8bLw-`?#1|Ic$0zx^MBySvNJH!w0AWnNlRWT%0WXcm~Ty<qUYbH47|
z<~zmbZ7p9enS5z$_Vqh8pU+nQ`}zFyjpY8N`S<sEPFmb&r6sK9bK=j>&zm2%NvnBI
z(~qAgTYkrI{hm)=bzfJ<FOA*JW^iLQY%M^Uq;Z<hy}I9TZNA?retB(e^h|lw<QmYl
zY7;ZVhyBH`*KU9IX7l-TM>>T+pH!cp(yhDg#Fdr7ua7<VytK%*d(F06S=uq%Z)L51
zy0BgD)XL@aX02YgOUu;M^yTH{{%Srm5^DHRymWR-Ir<2Ug6F1N|7%e1y<}iG+lalL
zyx`=IPp9>b^Y86BGtbug^Ru(3r^nYtmcfrS&6otb$MR13{o2ZxOQ)aeyYxaQc9+TK
z^z-MMSh-L2UDAlH`FOPQ>(y{>`TxJ~|DV^bzi$VlFr$gRsi~=?O+`W8?zh`EEoL~N
zwc0f|H#hgDA_GH1et2x`+|&B|ZGxBioSb7>{ONz)uX~GJyGveQ(*+e^epWA+tl50d
zN>xqQ-`Cgo-<Rd~Pg}*~KnXr5IC%24wb9FykN3U2x;nh<e(iTqZIgOjCpI@XH`ZJ?
zYKw-o-{OrqH#hD1cuZRR@9mejwq}RL*M8mfc<Qsg-|wAX6S+C;RqAQo?Pq?yULRk!
z$1VBfB-O~|Uei;37gyB$d^$aHM?vD<{j>RGt(JtY4of}0h;#S1TiL}wpH5FdH^(y7
zJ#)&lGczYokFT@*{T`Hr6Q+Ln`F#HJUAwGgt;=+*xh}BiMs8A>tnPnq_4<9Y%HH03
z+Q7_r!c97N%caVG+iwwidp;bp`E){=SAJ7x#FmV}do`cW=Is4?E!CZ|Aua#go0~h|
z?Rvc_<Km(>+ivGsKI%~3lyh^_oZ4?UXPRUNty;Z$^V@B=pEYsoo!E9eFS_i`C7rlE
z7Tx0daSvageD&&;&5sAoE7z^_dw*~5<=y4)g@i9n0Yw-n?_P_me!FS0iPh(4XT3{H
zOU>?<1lw0Xh~HH3@X((B|9*o4s_sLx{1n;cCE&WYe|yG7rL|F8y`G<&yZK(#Ytw*L
zpRQiJwk&jY*w4G~>!v?E+&*1)d0^zOl1xz1>aD-mWdEP1`ltIYzW}9UPyxWkFZX9{
z|NXMtxuCQ#O*i`5fs<1GuH9l!L6z9=_xtDn`}_O)-+d=PJw3hoR@T|)wIcg}JnF9h
zJ?q(z-FeDxJtrn8I&<wWn`K#?cC251zG3n)lY&jhl3!k08o8&U@LE*%+K|xDsj|y2
zMr5zuTJ-bj^yf2@`!ub&7}iXhbw2$a1H*+QXXe}6@2&cJs`B~V>3y=+&$e9lJ1rU>
zGx7Dh-Fo3Mg|2?qZ?}}ZxncNxetq4xTUo2m%(vhF<^=D%TiNS<pP!p+oN-}6kCdsF
zu)5!wD=UMI3m+W;aeu$v9&c6tZcg^Poy*>=;LW?aDRt-1XS0n99vmonaX~ROG_>@7
z&AST=o!NLKCd|&;rRhCgPuDt2^V!+i(--$yY31JD=G!l4yXkh`?$q~tzn=pY-*UE9
zDR)b+pPlF~H`Dxn&E_{Nc(Z<edHM4C`gp6-S5q39+0$NJSorg(e%-`{&h2Rj8W>+*
zSs7e*ukyLiY_qi>SN#0+6cp^BH5xe^4zjIWwaV-DwY9;ap;LLyZYcbIv)Mmy@7HT-
zKMy~C_3BlRjHQun)fbQ1X1SnZ@XwFq_I}sb#a>?KJ3D9F%{0sJcZxw})D+pRBA}%}
zZaoqcWy@|T#_lTd{Qd3i<)z-!-)uO{2Wu!zm)#in`^V#c<MMZRHYJ-xf$mr3vwE>$
zQ?iNI{{Mg9Z$2(pJw<kL;IFg!b(5#*Mo*Jn9JuRIm-eQEY|<d{SvHkLY<w~iWj$^$
zK|%lh-QClD7d1d9KwEyhk$k%EqJo%y+?;!RtDnDE+<(qhJa$U3zpd%)oK2qRET7N$
z^M5_-zJiB`Y<|61tg5PeeQx=^nR2#OOIEGYdcAggoS((RmYP2wk8960FMV|-%`)Nl
z>-hh(HYOi`cFy|!ne_R!-_}0&nQyoErp@|&A0M{Mr+s;G(elXz=b}TL>Q7!Spa1XL
z=Xbl`?@KGUuY0@ox>3rB2_V1UOrKv1s%Y|U-}Bf1aNb<QxHo-XrP|};{pa_7zZd<Z
z`yS|2akn0ciw91g+M055lFtkS#r^-jt}nisI$iW%%)^bx<+7*62ZPr1RQ`C_Ze0BA
z%%S4A%BNFf3J$XJ&RAu$IsLrfe7jnsv@<jA)PBEf`Rm1E<E$$yKrK{B`?{KK_v?PY
z*>c%$rd@4S+0E4HXXe@Nescnx8YS&&DsFAdoehe3+v;y;Ua#LjFLHBQ>f>JXa|_$$
zW(g|0rR;vY?exQT`F)q3x2@jw{eHdu{=aYYi_cj;f1+Ri)BEnn!pFx_pU*A#TOYUA
zDCfq8w4cW3+~sRce!ttDUv?{Vd5@f}Reb&5(tST3b@RyCSY)r;nFg{l@9wUr`+mRE
zw$5ta{qx!E%}2$eQx5Z*pP8WOys6^jqnZx~*<aq?p1-T??X28wH`U(W-kv|r{y*ph
z@8YLZ!$Co>T@zRHxYs=GdThDx`+Iwf?-U+?D*yk7d#9#!d-eOh=Ckv5WrA|w+U@tO
zE-&}@|8!qAZ|l{tozLf0d-+B5fvRfzzc2l{|G(MsxbNlN-R0Nf>;HavbJMu|US;~t
ziPA^R^Z$K#*e*X!cIm~Ht5%(Alg^u=>OF0W>{8FDEg6BE|5W{vUhLlQx7=^;rt5Ll
zsV62Vmd5MXe7WcznZ0)FtgHV|-`<irdF!>P*YW>8AC~{O;mwJqJKpVj{i-(cm-)R4
z<>cdixd&W&4`;96J1y~W+fwi8dYLyjrQX__J$;&PblT!xvr``)9^N~ne$xCuPt<1`
zCcE7<WJs9$G&P@rVZlVJpHC)lE_r!r&zDQyFE1{3e^?1h2LJ#41+|QxtlRxA>p;uX
zUH^W)F8=fJc>09}j*^B+F2BCK+<eIVf&JevmwjfN>0Xbk&INUl)@(c`C25uu(b*{t
zin}TQ{{DWRU;jJW>|Vv=H=9oDmA-fSb9T4z`5A`F&h30>uZG9Zb(gDD$-TWz*Sf5^
z^5aqQ%j@I!U%7Ve*#TyLpZRvRVXx9}ZOPpEdfo1#`?cSncB;=iF)cbTvh2<KyN~<r
z=h=S0V?5Wo{M?C&%G}jEpH7Pg^~`L(TyVabIz9GO-(3aJ;zu3{0|ijdxLfe!_PpTW
z<$h;F!(*q~|NGb<S$?<lbl+WtXXoe7k1e~Y3c98E*Vot69h=$KUOD^a<>lgkKc7FJ
z7M*ue*x%;k+V@O5wN|ZMdGdVyzt1)w4lrll-Br5nMpE~ecXz8>^VEE1OaLWeP=C=V
z)hlXyUToPLwv7n~o9chw@wfl`rP}Avs+@a!D$kbP`EDP%ucmTyt)SAr-8+k)KYQ3N
zuV?MH_{q_ruDu@)af343v0mx$vMKNHf+~{han-u!cM6=p-Ok^y6SKoWJhmk8ob~%X
zdwx9X2K7xh|BP9GVzR&8%w|3-4e8u1fqj<GX6*U>Znva$S<bs%uh-ovy&iirZ};0%
zeG#)%y{Dys>VU=lc2VYD(dlzbi%zOePdPC`QG3qsW77F1v!91f+VlNh_06=|xtkIW
zHvM_wZhz|e{Q7x@$;X~taOOXIV`Fl7MVxNjo*j{Q`=6hiJ3Dv#U9<Swuc2nQb2guu
zV`<E9_akB5{(rwfZD!Dw4A$j8KRrGBiuE(7neEuj_Vi)9{JLttt+}_&rpJ~=_E|jY
z5Ir~7INk49pX}|NdzRTB9~}kdSy0)uEAO1m=QDHae!Y}5%?bhKm-4*g>Vs2m-MS@H
z{bu9NkH@56_m#fBrh7f6*thI%>2=X_b4|0u&e{EbGpF*|OkUZ|2YaPVwO+5^UpKGj
z)5$IQ_w7JQ@9FgTdA{a%O+a0=yWbr^zObwP^~8MtPhU`_H7VG9&Fl61?H(WNJss#S
zI~CM*U$uJOsf+INbFYTS+a7M`Ki|kMH)GbUS$7H!^MaG!_Wb*4pU<rVC8BM2%Wi{O
zIi8a~pSQOMxy<hWpU<Fj^k!1G?xvcbpFrJ!o&W#+{`}|j`Q^pWlYlK_nfe7jS8
z9@H8I-Lm1<D>aqh?uP;>Xw%NlnmXCv&eGJ>bm#APyNeGnvOhVgKL5<O+xhWjZ`eLw
zaOMY<8!vBePOtj*W+tbw+LC3<)J{*+^?rSAZSmKu;memTQv>xfI@RaR=rzA*!OX^^
zVO`c-@qBLirRDzfL8-;_-*36vyQSBkem-x1UNU{o#Ixr2Z9o=+GXHto?<vpD%zSxc
zWAe$Brwjl8{ht2+@Avb3)^8>pY-Ue?a$;g>KWI!~u2tzNU-P?D9Glsuif>W@Ww)8>
z^JePr`=NAPrq~Bm469WB{d(QF?$3`cnU~el=M=i#t9re*N7@`bo&f7#sjC0~H@EWH
zOv|TJf{QLVvZqe=HPf{ATU-Pxh2GrQ2r6d4ZOq40-px#(cQV-DHuU>_ewz;t_bQ*y
zoq8^MOGcoY-<%m|&F}9~d~7Ne9$#DP)+aOb;o<i5?{~}3GqTGBe2=)jEf>_}x>I;u
z*7Dzv$KF0S3qUP2(S6VKK7BaMpMGskB=3Y3nN{!ie!sLTboHiWlNGz)@3U@~EsMy?
z%DS|(`1zZS$K^6V*WcLve#MG)+j1XV=jl*Tay`NoktD$C>gtl<aG}ArYsHZS$KGQd
zs#1%8+}LnrMTe=`8pq`RPC-W2&W5H4hi2A^i`-nhOavzu?X$0$`F*BAwZhMPXXNJo
z-Y%A%`s~e`(#mTx&yv#K*GicmTOGcB!lX$}cXyX7tEjNJ_sbo<u+X{k_|vr4*VY!4
zmmgmhy86S@>G6kd+?Y|W;>4l&q}hr40;gh&fD=bxptydVi-SYMp`*_kF6=B$KQq@_
zoRN{y%WIibQ&W>c+8GHM%OaO|AJu$k9k_c}_T9U8AHIEa3kaBSOUGfpdA^*Hk&%Fy
z7#lx7|Faz(9UL{^Zl?cuHamYq{r@^uwI|v4_EctET_w6`@#0jq$N#pk3|{`|_xt_r
zt5<99`}s^dW=DbJNzJMG7Z<s1*t*p<BxK4R{hT#x*FJpruJ7mP=ZDXp<?R;Jb*ibc
zX<u^c`&sk*3Z|x_`~QBEX5*JTBO@*)#U(E<e`dbDeD(Ktp-E148Jk76xps>^{PXkk
zjeWJ&HMO-*-{t-P_BQ&>{r&RA&(0iN<l4QV@Ua`8=hXGSv(3K#YLcxmXWX+d*<NIG
z+Syg#Z-5Te>GnMF`^l-P+F#{X=aoDBdbxc5E8B0^)<*wN68dDf@NCeD`=!s$NP>E5
zAHIHNWss1NcyOSRxuCfC@RgOp7x&lKx3smb`l@nQR6Fdzty@wbKYq-(vO<tSK~<G?
zv0Jax{<^;fUtR?ANE)>id)YNLH3^7{wjS*k_ck|(*k5P6@5dwVJ39)QZ*R*D-t89y
z>S<``>A8i3h{VLk1_lK+@k*N|e0_D*!`Jud&CTf-*F+lMGu#=mr^2wLq@>{OEz_5e
zI+)q{60WU@d~ta>zmk&Dl5Wo{XP5cT77!F{Y~>a|6%)K~-@YA%kJ-%f@13z$GT)NO
z6<ttZ@a^5*?!w2%JkOtfc6Ro|hYuS~v#%xm`}1>;a*?3Ce82wwKSH|E+gLul+x%6&
z{*R!ry5E$W4V#_Y`96I8dURv*@e0?cY2V-7{qbh=`6aW(Bch@X-M%dyyv*m|tE;P*
zK9-S@nJ{x^XEQths<TXAX1&)H77|Lx%j@%;td@9lQ)<TLWxW4>Jm!D-JEW$@=GXW4
z{a06qCm-*VwNchSyDD_`g{9u&F*}P`d!<YdHL-GUNIfm~<=tKBlP6DJIzMT;eth4$
z*xgBge|^m=7Jsxg`}(1iCpo9<#Ws1U9BSj0-caz+iATbKVdBJzmkR6Z>R#O1s%@5k
zZ;cuEh43{IjjL8^9XWdR;GH`%AlFV(^}evHH2co3Qtw-w$;ru}kO*BJw(_i+b^X?)
zqg)o&*2-2^Qa^wGG~&L%xWIqDT~_7y5QdJfuBK_z#Ds)|E^J72o|$Z%ey*jvn|odC
z?zYm`*AkEQNN(7=_2{jw*;kVotDKyeW|`%3X=`hLd3#$t_x856S9@KRCPw|UUAS;z
zBO9;O0_S!<3EL`@&v(wuv78+2^mJFj!=^3IJ6x1xY^y}v`{kxuZ>#<N?Z%eO$wrS?
z_T=8)mUw1{At=dz`usUtcKgPS2ak4(TdF*M{QLd>@QOcwetzcQ;BY7^GCFhS%!Bvu
z*Dp!=)7sXiWMUHXtK$E^zecldu4w4!xI{!qRDFB1@=QgHZS5}+VKpCz)6;Y}rk|Jl
z^7i)jYcpQF$ncqI#A;_}x1;?1yjyt=PhPy}`1GkrCwd#t>1n#oi`{yk><iyp@v$k`
z2~^Ddbwd<0NgE}uUcLHNDmpfHZJBW3=1rSk*}i-|+28Kq`u+cY>8l6Hrk|g8^v}=F
zqI!1h4E+53HJ{I#-`J4YJZaL(w$<V5lkV;+J#+NAsgIA(hpXZ7i4PC8dU+kYzBYRM
zhRV;+tjf8sUA%a3iRWa4^m8(*s*m5FnQ1)3zJ4F5STm^jkZ@+UIsa_4+@RU4FSbN-
z-M+Zk-7x>2jn8beUQ0J`Z|=*>d=Ec9-oG*bzTMWyhI<<log<>6lFrO9EbZ&<>kI4l
zb@&&3mTB><-50OA&b3;wr&lK8RrNnR5kEh_EgPAe`}_H0gLzE39bP-neK(8iLYih5
zsI&J~E;=CKgT7jzZoj;}+xEP>S+@3de=26ooSFFJ!^482A}1FYmiCfW55K*=9kC^2
z;+gky+S=MGYHEirUlyJ>Z{DTd?W<-VZs$)v)WUgb|MZ-k9D{-f4r?MdGBGkTo;Y{z
z80f^bF!5gjF0QVL&(6#&C@p1Wc=7UO;?GY{3(Crltq5HF;K`Gg&(F^vzH?_zanRG<
zMNhfX&dt#*PT$ultbXX+Ilg8#-loNimCwz!ULH2NC|ky=gyZqC-pP?aEK6Pl=)~?4
zSsk|a(C6pp3x9k_G|9NoknClbaad$q?C!F}BOQVk6(1IS*?DrZdh)L?FC%soD9*F1
zT{Vr{y{Nc2Rc-xs9hdhP7CNupC?+O$$vSrR<S$=JW}g55>&r`KhNAuRC2cAU!q!AA
z+>)~=c29-i<z>FjbLYx3B;4GTx?%hF<4vsGDQ2E8FE8g;^PAJLVS_<j;8Z<LP0r8H
z&Q30S3@SJN{`xw@AhF5kxv`N^)B5%L-`?Cjti9^e-JQkk-qUm@{+nxC^P>PXnsP1u
zWK>kthmRivSKmJy7#KLis#HrxMuuU}?I#EC-IM$L{QUHnEkd0v!fHMNulL&r2L%a;
zh#axGx2LjrYt4D4h6xh{bmI2xxb~>{!QJu$c6N3@-tB(BA@8o$%g3Rs!wNlC)!g2e
zJNaKZsQxm1wTt2J>-GDm{WH)0%vKuJU|0Sw29#@>6b_s@!xOzd@92kzhf|MrxG24N
z^~xzeetxjmzfGGq8RXxyc~)3kTf6nwpBbu3N}wp-QT0{J$Jcjb@pHc)zkaQ{nl5IZ
zf6t|$z@VZ0x?f3&N!|ay<ueUUuZNtUXS*@=v>2b}&l_8_#kI7x3m+b0-I9IX@0~<=
zczDc?0>-egup4`;%h&dnUvb@E_xH-H-BwN<iY_-Z7_GqV07b1;_5c6f*pSE!Dty<)
z?lwApcUP&mmEYVMGiN^he!u?s63@x6WTa(fd5w*YRhI<uK7IQ1>pvy$_;~sJ`}_V*
z7hWlro143*=I5rkWNt35S1}X*E;KMPadC5V+k0%;^5v_qx?K76sc5G4FO8&(jE+yA
zKGj=Je6`?g(2cI{?$>|sCFkX>3oG}3dvC9G-2S>=R&KE?mfN0jhn8O2RhnJ${+?|5
zxj8F~->eE<y&>nOk?N8l*|)d1PuFt@dh+b->>YJ~cL@otWQ&cBEqQxO6jYZNzj=9i
zdEuiYoFKQdv9Z0lx7T{#?{~Ycj=#IVKi=x3t87R}$b#D6-wMjg))nUz6&dB-+q1GI
zWL2Y?ccQnyzx(R2wF#-Iq0evh^z>ByfBSV`_Psrp^K2@WzDL~OS1Twh+snwzcHrVg
zK|4D;FTdqd_x9Cle}A8CYim2lx}5LvvEIW^PEMXUd2;i$wb8{MC;ZdWmfi8aH%%|L
zi%-@n;nEV%4<A0P2)F-p!KVIS%)8h<ckkR05Ef?U=jXSuuu!nEnd5A=@6+ecPw!n^
zQT+T|M}L2NdpmnfZ0yI+=k1F<j)%Lsv8A1#7yJ6BsCL+c#r<}Nrf3F(iiba+PV38D
z`sgaXY{Sx}ORwH?3GnvjuKxb+sJnb^%l|*m?N6LMd9dI9-w91cc{ew=6Q@s4w!3!a
zic346?1JUX!?SY|6Bpije%1GEQ<Agu;i%(ZzJ3i13|#oe<Bm=BH=neLF1NSkGCI6V
zTNb;!EOfSSY-9O-+rQt-`Hmes#-Q;1^OJ44w^yCLAIk9I*Vk;5ygL!Uc0AjyQMq?{
z>gj13nwo)8X7}dVR=0h7d)r(7dQ5Qau9B6e*Nz=y`~CfWc$mr5%PRtvr%an>)SsS`
zvLN&FGB2McR&jf)mKJ=h_4DJ4+gqhto0E~j!OP2=>hgHqzWe2?7H`>Na!)X%Yu>zh
zTfSerlRKlTAlG-c+0oC>&(A!be}CWFviXevwtx6gz{0|!U}z|qmX>y7V=}v%?<^Ky
z->=cPHm95v(uv%}a$xsQbwx!*3F|VQ=OL>eK04a{;mem4J-hW6_tjSSNEk9roH#LS
zH^bi-7Z>kQ7I5NFlsEaBy|M+wYT2W1mUo9kTwMIii;K+PzJ1%Ub*t;?X}T9TBsx!-
zKK=2}&(C+%{k0Mj5=ux*TV_`7yVkJ!Th5Q4KNqfA#T8%sRkZ5c8%^VhKhMrK2dUeZ
zf4?vJcwge{YingLYfW!%W;V;e$K&tsza`^hljXagpP%2@l*%n5D?4>Y-+q7lzap=%
zuXn$`F4nN*MZmKi#_8u23=9O~;^Mq~j-S7=F?nO*W4A3?SGgvu`%kNOKXZM3eDe8u
zwxG7dtv3mL4Bx(e0~zPmC&MW$Ec|STxPDy1>uYN-?Y^^u`Ib)W*<;7pK&fX(;o}91
z7ax}S{_ATt3p@Mb>hJHoe2!0_J6E>u$3ylh)22Cvhlf9ma1^-m&hOgZ>hEqjIXQce
zt-8F7k0Bv9m)F<V_sxxsi_dLb9lkznHS3FQ+qRuJcW&MFq?_&h@~f^gl~`L_+f;mD
z*jxR5U2#rI$`T==m3-OR*%_IcSF<nveRXy9)htG<+-Zl>GBY`ql^0jtom=qr)zyey
zB`bx3K3-oPt`AE0XL=KNmA~)XvBP4=?%l~}XPJ8WEtj(U^+Nf`@#EK{?yxiPN|_v(
zsO+AQk-<@4|Gz4?;De%}k&#ng-nu)<^Xvavf|_Oe`uaO|?0E3`ynT3))xN0hd1vRm
zxCd%~?yHe}_wF62VtsLO@zgne`o+b?OO`A-VS8;;s`rs&$C55AaFj4g;b7yJTl1u(
zMp8=Zl+KL5`HzqHyI)@BYgqLq<ICII;cwSz-ZE%iTln~xQTN(^v-j_}2Q_J)PLF@|
z^z?KI!=#o;mp>+_rnW9wqVh7CnVI?7`=`;{^G@zH{?)$DceYu@mlqSiY@9bwuBo~C
zsoth@r%na^`1z^**ntBM&(=+wHEY&|3l}Er)(nh{oO$ScfW67tS*C}(#r2o;Z{4!x
z!uojomrh^)Pn$e>ahNoddHy{a|M_-P?XF$BcI?T?$xrnHs=vL7+-uJNPrxMe5=(1q
z>!stS-A!A!Y{}}?)z%K4&AaVsVQJ~ngU#$u^S(@-JGb}2g9K1V#@Xm!Ol<7N%*$#P
zR#r&|8W@d^A3AhsL*`{QkdJ@eSsT4QAun&;lPNA&S0o=_t<TNf9d&-{^y!bUtPIxB
z*KcocZ@=Rka^>KL#KRl1uj~2Dwc2{^?jB(wp$+Bl<9_`7S?G1#|Lmd9tHakHx^pL{
z>UeQ!Oog6*WaP{{d5hP{*;F(HE_S<`y=Ly*xly&@t{jRj0#6rh^8(RM9bH+Mm+?-T
zJb7d3>##XirCio!Zzk+Cc4}th1$8Pwjj6i2x{OOpIFD~R_5Esi{K7SBc(lXTOn8@c
zbBU+$OQyfGtU>cypl<8&@c7!J#_NJ|@9Yp1>SU3x|6^$P_e=1XH#dXdJ!4HjH>VMF
z3hiA^O#=e~O-)S+yBdqAty!wy|A0Dl=jYiruU)Il#LQgj9@Z7QI!sYpn|pKm`D1^6
ze!jReczM+Gr~m%`uK4{;*R4mQF?4m<$G$Ztj*gBmZg1DODtp7>@9+Q2wDi}P%#4hT
z6;~J8-O_1&3+hVm-fgX;qhpYGh~?R9H5C;WOH0eFuc;5F$JcRYXJ_xJ{k`oR>x;U&
zI#9=K$`l_{4;7)9T_v3U^K2Sdu3UL&<FskhK79ES5@hu6&6_u%ZaYXz++_YMnV*@g
zt*vuzY+!6{Z7ucl3ftZ*`{vD?f`5N1pFDYT#qwgjzrX)lwdR{QZ$5l*u(`zdq~q+R
z8$i4tA0Mw+wJK<~b;8x-D*_jPI4T~mpr*!l?%cVe<0Wry2!^kVX>4z2e|Kl+;wLSC
zcqI%NW}D|9dv<pA!u9LpU+?fxIn*a>osg8&G*vr%)m1lZGcz*|Uf!dJTDhOf$r~gv
z=*8@4P;_oPaQ}Y%$(KKhii!?(3afv(TYmqfZC+kp-|6Z4$p;!3Ir#X(R$uqMzpu9N
z&yT`2@%!W6y-%*Kt#xs8OS-Zm(4zL&mZ-V2XJvP7op|QK!Dc~0!N$bHZHDW2^NZ%r
zIFy!}+WPtV`Q&$Zb{6&f&$E$iYis-Q=kxi(r>8_!mp=xLLGP&jT{ib|QE{=LoLrxz
zahitW)U1u0H&4Fl5#a634JvM}ziq!?*F1Ob+)axL(-RXFH%E3&oGAF2??d^!JAtcN
z`^?PDc9gxH1<uc(KR-Nj#ARpqZMzWL>TfPiPEB7nu3M*9{CLld84?lE(c0Ql<zixD
zM)lrixwocN9)GsG{Qat{reDKXhp)fTq*(=93(&TAuWi-WSFM4I-5gbf6qS^i#P#Ej
ztc%^Pz`?YczxKtp+}myYYJVqvcyQ3b+<dy8j-S8(@x|`_30YZMcW?YZJKOxki4zI?
z)(bi{yu7?zSy9n(S7xxQE31sG?8GTkSR4fsQc_x8yvW#EwSU#dqNiRiZf=K8o#J};
z?wvrV3#bbU8qyFHZ0wV@PWt%h=$>RP--rkaCMG7(;KYpCvy;ESyF0_8P)XP3fA_0b
zSx=rmT^PAJ?b7q2qM{Ay=jEnMpMLoAW#PNKN*~V%*vZAseQ`_X<*Hs&BO|B4z>E9m
zczk{O?3t3KrKGE?YtimayK<92`TS43Am=L+?KW_2JmGspXsGC?PoI{QGa8tgEjxLS
zp{u(a6iH8>q<~smRdrF@ayX@>rFkR_9NvmOXFf1l-G4*TQ?EI8wV<B;);?)T$%B_K
z3wMj_x6Pa>+1^qU8Xo@m#l^)IrLROLO`7!K&(Gp1)2A;^JluBadf)Wv;>UU<7nfbX
zIaNEn;L{V&XQoe|K4oQRXTN7S_1(qA?i?H(2lV&<Q7Ufll=}7SmxN&w%QT(Hrn0xU
z3O!EvdwO=3Y@RY@ipb8{ODifXS3XVCG|#)!uz$b(qQ#2?Lqk=KAI1x?bR13Ev2*9c
z-S78-N|EDBTK34Vi`(0^IsJUnwKb7O!u(Gvzq}BXv#aT-`}<2%Q#StmJln&2tG{2^
zU7l}}cW1}BkFT~Ae7U+hyyD{{)-z|$WZg}5zI*ie@yBOo8vpq9dj0E|IrC@E>}2Pc
zJ8<~0v**hnyXybj>Ba8@wL2uFq_kwBBO*Hf{HfWxQ#ioIg@sSns^#nJ>x*5x#kh{&
z+f~YaeSQ4$&QnDzF28>$6&V?6QT9fHjaMq<`I6ht?R*cft&NV@U$=MCrH@<l@7sa8
zL!6wPT;fYXeKk2bxr%>(ELW{sHD$(x`6o_zfCluUx97D^o-AB^XLb1c2XEi@MsLqE
zeE;sxLQfx`BeP7iHzXWnx^erq@$t~m(8O<VZtf_3J?#wBN&cJn_Evuc6*q>4fe-KB
zs{iwm-Nwe|!=t0zTX!z=n`hIhzwZar{(rx;iw}!1RQ&t1v*fTysipbtZMlc%SQdi@
zQT^sx86J0acTfKD;bFzsS5t4zkzN#0SZLVQ-F<PHuXO9<PoF-4>Zlz%cP{jwZ|CK8
z{QA4Qy9+-*^L=w?XYj)vixw%(m^CZu)02}~n;Ty)^`1Uq)~v3T!OOK|rq7<;?Qi#!
zC3u-n;B4!bWlNSQXlt)Nw>$Xxvu7an64qrpd-m>~I;C&DtaaIgXJ==hVf|^^)!m(#
zmBkewAD?q;i>K$ykn?k`%MGf(<+!-JpU#oFu{}Tj&xgbO8@6nDGNW&O`1-iS-{0PL
zbaWh8?B36?=k}e`hYvGfUhdyMZ=T%qmOm}6t%@2N9H4GwVBo|%zUo)EGT+--%ns_m
z&YQho@0D<;i-)i8(<y!P`DCpgY(8%{Iq#mlkWdq+uv)_VdwXA8TPwY1@7~1R+}_~j
zeuaLg+yesz!`8)gPFDAS^zrd=hK8`UQHft(T#VS3GxLtGmVHRlMhT^f9A;)_683d9
zd-tsmS}wiz%7>315B~lAz3}g^Qik{UHt#BX+qGtm4nxDXZD!}@+pqsne2Bj@Lg&~*
z=XQg#H#e+~%h}aPJU-qZe*62%?fLf~b?fgt;BWs|<+GeBN7ES_*-~5k76GRd|MjC9
z{J@nyhobzB<Nfm2qdeC1b)Vz>xnF^U$;j9^J2p7?_O{jtooBNB*0*$A_Z>RqbZ1}f
z?rX1)-MY2woNI0ir2OEIE-f|n^72}+c5QDPue6p-bWBXoojWmGZ+>Z-P`_x^Dz4Vn
z)(cm!wr<<D?a;>7*4B!Tk6NSdMt*xAu$(s-)P3Eu#bis~U8!Toj&U7NOG{HyR(8%c
zvr&F>KP)n`bI~FtaE{b-;aC~%>dG3ouclMYcb0>@dwaReJ1#D+4<8;nhlGbOuKoS3
zG%v^N%Jr4O%MGf&WR$$T#46OuVqNy;z>ST`iX2RJf4_!<D%8X6{Kq$?p002Y-F4$e
z#E#v&o&Ej!w{6?T!O!2`-OYXK)G1KmTk`IXB&aIo<a{U_`m&_76f|b=l5LK%d*6}8
z?)^);)0vr>1w}+!($CNP*t1edOG_&tHg@f{+V}6zsS0+wWbF*NcIFIE@G_r+mzH`n
zGFX?tJJKU*EFdb%nw_1!WB2aEH*QD>3JT7dtkoW&bF76^_`>S&^;XB#)YOzzR9tl9
z%^5)X7Sy8fo~F~-+{|oaV*@JlXUv$9@cG%<6X(w#pJ!WrVX-^^y+BUImI>d5bRE>e
zaq`4AAuWxq(?#j;%S%hS-+O31{qXQ`L1E#_&wRoyf3D6p&wn+iV^!a!%a=2atQB1}
zLBpJH-tefatG}`+lCi6iICt)xfvM?J+15SoEADRyJg(TH!TfdhuE67p|5-|9%wAcv
z2&69P3pRgc@nrsjzQb;^?E;H@wr$&%abW@DqeqVd0s<I>g@r+N-PyCek&%(05vpCK
zuMO({RNM=kx-S3zz7yxp9lN?ZJTNd&u{cjJeqWEGbK8R#7Z-o{@Zo`M=*yno-i;L>
zlg`XEW)BSwH83+f79L;QdUbU;GsCwxH=Ab~r!QKwrl&Y)pO?4y#Oc%9#dM=qyk+`w
z<;s=)fB&y|oK|UNWd*8TYies58JgL653LSg4;n9E0CnEN)<(6?nIkjLaB7>G-irO(
za&Iq+-(PoQce(zj&!0h41TU+nDsU7O7CLUvySt(Ebr>{!C#k(>0EchOgk6;t6$*NK
zeC~ZRjUFmZ3l}QN$jUx^^M<F>rD>jR^{TUTJ)TIK=gGJz3Htc@ri#6aj*9x!cWkbU
zQe$^F_nbL%9=v$LVQXu9Z(>N-zI}E%xw%W%OS-$eOGrq3=sOyFyifMxrd02luUBSY
zU$-ZDB};gC_)F8P%l+kFyn6MiZ;4UHW|3{6>4$jpxmKl*WZjouDVa0B?pLQ(pUjoQ
z8!H}f2;85z7#uOZVz)K~9-r9%%l9rw_&7}1iccCGlb-^QuY|C2pgNBS=A53U%fZW=
zdQZ0W!GT5zvmA+K{`1#8Nm-?+rNveK{hh0u8yhI&U9X<e>9VMPOTeev^6&3r*F<h+
zlai9UaHYn4>%K*cm=5fA%?0(>udRz+J&pUq`uP2QPft&Gj*pjTWo2bhh<)(l#fy&2
z%gYi!K02DUli@C?@BHlzsI3disUqUy$tNZ#UV1DkDVcF^kLB@}8drDs!}ssYUtb^J
zuE4RQ;33nUJ9j2bpU$qYudfrafq|Kw?}==%=9NOjpY{vauh)-_iHnQtn=wN|CuT=L
z)t<z|Z5q0|PeuJ-zPr2oxb>lGWov8cZ{NN#+{;a2U|1i&pY6lC+dXo&Qmez(E@FKF
zDkJS(%HdgR((KvYH*Q26Id)7*Pmk~9$&)MAt!wM+<NNjHWiz+9-iN*upkPT#N)iwk
zZ@+OPV#(5_jw(V6GcPZ@#91QL$+B(Rwmplr?yAqPX=-U<0Sy5-J2PLqc5Q-($|cW4
zH8r(8%0*kNzGfXcdi3F`soENvnvD@UZqxN*mppe@nz$hK^t3(6T6Z5FZeMym_^ddn
zWmHg7GG*TMxV=@L`)k70*R5OU;p5{H87XOEYMPjwth{&GoH=tYY{?A1C%E(Hqi%hW
zyRKXbnbq=3T-LhGrK+lG?RT~G^z@SV_x|R;kNK;(s83lQoF;Ov<b%@?G_klFzA}d=
z4wUqB6f;R3-BtRU&D`8P=gyA6cONT1KYRG-Xt#%#S5T4BKhP9u{l6LsY3aq`>*EYe
zOr}`tsi?S|Jo&@e%<R~ysoG1Wg<rgQk#M|E7S!ftNVvW(7S!5W+I{m%XJaGdwYAah
zD}$Fi39y*t+z?>rlK~a%j0^`49-LvE-WR3IwH7q@*2v7hXvq?mCWV9>8xns!ogTmB
zxOMrvp1ixe9-f$}EED`mP*k*)k(q5l@$++_`QA2O=_TdLYz*b)<u6{oe0XJL@SMp)
zp++@73RF~86Q7@(%fZcknBV?S189sv&E<a0XWqJ>PsMF&eoQD1T9gGUJfA;r&)@%7
zi~-cxKiVx0>IN}1Y|Xx&^!3$M4L!YQl9L6TI4bimGL<-iYutOm=jYqIXJlwFF*ARB
zaFDsfMd_v9;a7U<>h4yIukP$DzH~Ba>eQ)w78eGFhPKW&&-YSqIePS{qP{-A(nJpV
z+Ao50=FSzAkvU_n7Jl{WRS!SEX_oG$yI*a~zb}`WnK?)J)8|i5y<b*#_V&641qo?s
zYcE{9xH)`%+{eD-uBoZ2>tc7S+3HW%k9Tu)WOPvyv?_hYlAfOa=Elb6a-X~mp;a~d
zaeEwme0sj@xwEfUx=FzyJY2l?*O$i4n~nc{p8x+t-%25H)K7Gk1*MLzz~d`>t@@I#
z6h2wp7i@neUu1EgayM8&WN}}xbg9hI6^~E2%Py~5@mRx6)?ExNpy4LF-0YP_POr4N
zTR?!oGQYW6-zy3V44$2xy?h$?gj-uOnYp>STUuKky}i53Wu`uQ@uEY{w#wsu&#mSD
z@+MhVI0OX+SFBmn(%#M<x2K}<_xJb3eyeIg{lWcpe?c=23=Lbin(FB4g1WQ}4a=9S
zPntAo!pxZ`jn&N0&$D&T$<g8A;d$`x9p6L`76uIsjRWuQ?!LG_-hS(yh7$)5GBznZ
z`1JI2#m`TwK0ZDvVhh&C>=XhOe_>%__ZN5tZPxhqe#OpbS5E%@{r%%f_4yB8US7`7
zAZeWDQLi5!9=<qsciD^k`|ZEIyL;MLEzmJ8E^ft|HB<7K9zA~C+%2x3^!nP`73<a=
zJ2TTbF*UXI#0igcp5S_17*UT;oHk8u?g}Ak>FzUUd`$B0NPPSD?NaQAxpU`M9)AM5
zk>*mdh_G<8{l6c~Qc_YcZf;gz7qjz_^*pZ?D^?s>=-j@c>}}L6k#FLrlTGzvceOCH
z^IiD)Q@;M+&*ficS=IluF)}t@xOVN@Y1VsA2S-MBPM9FDYuS?po-1;W9z6=`z3t6&
zkX^oS#p5fzR(&<#QbEH_w!IfrdCVzaasP^Z>6~4l+65#4isKD|pfck#U+J7*i^1)K
zPhf$?5~Xwgr>3N|SQbA^czJ1QQUCggjZBV?jv6{TAw@?2q)f9~dZo>iZf(ijvv|dv
z0|y*(Zf;`D%*@QVu|e_NJlk&2xUH3yl|ZM9hOX|>eYL-rl)Hqhdr#9j*vQO2VdhLu
z(1_{%{qmF5{o7hwSs6epA3$?)i(I=c)Kyn430&+3S}u@wW=7+mKQ$)V*L>0#f6cS4
zHYk4PGiB=3LcdiqNgH>>J<c*SU|6v2{p0+5dk%tz;Sv%Q{@OC{`MujlM~BC@`r8qA
z`Pw6f3qNr*H7r=50GgV-vLcY--rRQ3!f2`Nyu3bPbw3U3MW;IY`i^Z(KE9#ya~i0u
zij0gbC@!9ySCp8R)^_1SK*`HXt@#0<SzlXM*sO0Q|CXGaLY9`68Mn4*&Y3euVWNk^
zM2`!L-TSNRJ^m_M7d&VvQ96IPo&VyBK;@a7{@=cRyKwR1L)po*H*GRHa{RdW`HNRq
zhkyL_HT$Kks)`Wjv3~jU)@tHQmoD8=^t9{C9ThdTM`vf7zqqnec+Q+TOP(J;bEc;}
zWa+N@|NG9k96H`F4{8SU@$p^qY}s4&HR$%-kEc(cF8ul`^ySaa{{G{jfs<{y(J!;p
zE-mrglU(FDIY9LEi4zkn?fK>HrrZnkQJQF=?p%8UlEV#OS$qPwK^9AZtCX(5;}c!~
zF3Y=82r3#N)l3&GZOBAkDSYJyDoHHh=|yInV>8>se}8}PD19yV<;$0pK2cH8gU61s
ziHV7E@bf>PGC@8(Jp9X>o5GEaje8dF5l>1^22J)jJ3BKsv-7vDUakG!BL+0=uwjG1
z*;%HOzwKjY=X-EvW$=Xy7Y<BNbT&vmC2~&l=dP-+T29W+A75NlW_T~w#3yGXvA6pB
zvpGHT&d$y{k(*eGpP!q$o1ymQrKLCaR-13yyxCGcwC~fWPgciU+S`>C6c|pPJZWHV
z?w*#mOlXo|XxXPHo;{MrY#%><+^~5wGsDZTDVdp|4huuY_JF^)wq}F+`g`{5sc;L^
zoH}(XXl03siAh3kE~xMHsn3N&v1QM8_&no##*Gm?8zXqa!^3BGYTdeZYtQ19EE^+u
zczJnyWGsa?r=NFQAGdeG%9SUrr+IDIzTG`2NNCmS)rqO8s>X#EjvQ$zw|Tc^%N7L=
zrktFdCBn~CggAS8dn?@^uX;91$|OVJ*VotVoi0szcXwTMabocE^8>j@OG_&uGgGtJ
zcWc(wu5z1o8A4jKw{JI3N=}|QcP=k8GxN)zg=J-K{c^Tfe%V4wd2n+9-sA+A20vHa
zzXC2OK>Y>e=7Tb%&_HcStc%;rB`z)w>IN1+J2Ua#OCwcP*4bvchc>657m$_hwX6MA
z;J2!#{N0^{2O60LB_uj7E_VOi=X|1i{iaPq!fHMTE-rRg<Y+3{yl~SdqYf9Pit6ge
z$K^q*i`bqoIc1)6!@#Ec8_)Ii@$0uT>|L;cA$C_u<LcGgeDZc@thLGo1qDIFPFGil
zgN6_4>+5}HnQ-z-nLLo~?FLN&eSdeiqp#1+&yR0g-d(Qf=x7lUkq0LxDoa=tDBRkb
zecXCkP(@YMq754a#P#E**s13`vp=}2X3WOMW>Ndgq<;md+wk)MqW)*Lw6rv`-gAFf
zDfg^dvtC?W++L#8w0N;H4=-<}`_n_$uZtHJ7JB%D1|sHt;Zr$x?%amWn}c7=>SU|6
zR#sIdy|}P&f`>}R?QOd6BeX#IcInckKVB^EUvhoY=FP^pw&$O>mI|LXZJLL#Z);y4
z-<!8@mp(sw@19(*l<6bc{?)Uxv!0xo2pVx$5#qeHCG)WLG%rx8Z~FY$>C@bom;1ZV
zx2wJKZJkcND>zqzqYu;(ghv{vHh2ZA3Q%HrV!xFiT35sGE@%uo^YSv#AimN>jsv@Q
zH*d?n&SzcrreXJP>*p;sUtU~fuB@!A`1M8e%h#`oSy@rpiEBJm4)sc#Tc|#H|MK$k
zj?PX;KR-UVKABFl+*=EF?UDkGDqO!Fe!BIDsg{=3ggJA1=FE|~ar^e-%*)I6C>L(8
z`B?;=ub5$;FL&nbSw@C_dHZ9aB~GQU!=S5h9?uE+nRj;=tGl~9XxjYVy?ZlEv&ER0
zm_VZ$y3yMftXRR(+1a^a!-fa4Q)lnjvx(o5Ay`ved$sJLB|}Pj`r)HTSzo?<35p3L
zV`I=lf*m_|Its9W#~IpqodW^{-mmZijfMUA`7`n1q1H>!Be*YIUlZ9ZU-yHt{@+ja
z{uNq{X8H;(0#5&Iw=m3wjH!GN@bu(d7qheJ#*K(MR;670ayAVSI&QA6tnV{oQq$9w
z)zsJu3ky4XdymT3|6%m?^}TWHmXp%NgtN0u_b6+{CM7K@af*nEk>TRvy09u#d**J9
zh{(u~eJ6cOOHC(Dnv`-bFfUIpYD<Qqt-YV0--eAFL4zEhK7CqpJt!wfXVRoe3PPP1
z_Ewj_tdz8?v3NhjEBy0rb2BqBP@A!^(D2NeGb!s<`pvca*msiE*D2My?$3@ddzLI&
zvcR#K?b7#Uvp!#1;wgO3FqElO=I4sXS3oJ{S1+V}2pTTvwetHL04gs)Z9}tH7NF{(
zA6#shy|Vb~3~FNd<%0X8pys08D~qqe#kEV9FK1@3DtXZWY6OZeS*@(DzP#%1@8sm<
zsT16`ax^tmetwpCds{B3N$8<6Nv}#rORH(+O3kn}5sj9`&pz~>I{NMH?TsZbgG59`
z7#hCZdGhq>!BeNWvahc@+QKPpu{>nox3{+sA3Vs|&L=ym`p)s=?BVNT9Npa7CQV-1
zcI1f5nHh$QuPqZZGcyBK1v$C7ma31nZER#185uo%d|GDCoLTa4=dxvL?=$Z7N}KaN
zKR4GoBt!(%jujRbp4ocs^YioW5fKtWK|vPkp?z(<(n;Un-8I@De}7M9^V!+v$!~6K
zG%z)tYPY}sf1S^KJK6kudmai-wZ65dLBNUQXE~zyFrGPcW=C(YtB(&4s8pUdjg7&;
z$jB)!PVRZhDrIwXanP#IYwP3tuUrY~a8U{g4gJ`6^zPl=<x7Qyl9G}>e0doxAtiMw
z`}zJQ%a$o=X>oxT+BCECD+qN4L`I&p7As%6bg4z*BbICHV!PS-<ro@n#RoSjJm|Oo
zH(}<Q*>mUeCMPHFsrcAbZu1V*TWD=<-BI&%Q^_TezXKv8IYA4vR8>Fr9TzQ~^J^iv
zUwITfl7#3cD9eAH{cAB)>hT8T9t5a{K$qfE{BM43Z8Up*eLbkJ|M%C|!|L;Els3O8
zd~~GK!{0yr^wFQ}{BkYp*X!@uv**FPcYP~^m!Fz5J8-ev!W}!H18wn#+jv3qu0Hea
zV&8oPjT^sSzd!6Y>q65_n>J0DHm&W|tE`e27Z^c3toI%<Ev>Dd;`3(Do_+aHv1Lzh
zuVMBz9i7-+A@AnyD}Q&Vla*U+!HN|f#X(OEjEoLlTI&6J>(7&*rK17@3U@VJ?p}Dt
z3K~S%-z}vLSvB;&ajtc_m-;7AP1K}t;K~&dp-xcyqSZyo@%cGWlm6Am$H$F?=LH1^
zGcvHTv4Q5tRfIU7xBQtpeY&!~KL5_0J5QWE>FDUl$l~abn5g(Z<Idj7&!EP}rRx_!
z<7rV*TpJ@mecg|J$9=1+c72)E)!FHomZrwy=&(8M?1Lvyj#$f;Pn|lo;_E9>FE6iv
zn3$eRmx4H&940?GFt26R`t|26CF|MP*fwn22I?Gs`uzFho14Zdsi~l4cY78WI?683
zgS6J{z@q{p&|xO4bN?6B1>3`<EONjtJxE?Z_kR(nR|sz7*}Z~Em3@B~o05{^QGfo=
z)gK=pTP{&rrDb6O8o54Re!sT;&!0b0$9I>#?b@)xfbZlFZXTW^7Zy5$dU8*mKTm#j
zWu?*a+}vEypse4^A6a*Ind-&wI}_7T_w!TgmaMB@Cs+Qc{`<?cjZYS|>iNg7UyE{Y
zZvz$6?;~Pv-oE|#*4Atguc^7&u<(&fMn=YmzNJN=!DunvD1-j%Ut~%XGc!9^tXNT{
z>#)D#qmquU?$ilhrmd~5pc#}68#hk;ZFg^>GrLXYrxs@;P)q)>1EM8=W`-g2v}w~W
zozxWSWLdUs*`DN;JjKPue||onFTlc>duvOhi_*a}GmRA|dL*Q#9<`PWfB5j>B~Qug
z>*J5#-kyJPfg|&cTel9KKhH1J$<o)?w<o!1bHPKWBS(&aW;#IA-dnbAy|_AD|I9pF
zX`xOQK0dw+moGn-4Su<2@7|^59s(?kZ*OgFo;+DtOfQC`(}jtfoBN*N&d#2mDRIG_
zot+h*pYfWQn1BY4Yd#(opWvaAW&N;IZQ-W7`|IPY@<46rCntqDnm`j2j!F|B%+B8z
zc>CmXM4bNOMIJOf;SO%vgIj^14j?4jK_iTy!XK>_s4;EcJU)4Oc@;G^Bk`4;E=pS?
z8tR^&5@l#;Zf-vFc-NJlaCQHAHi19hU%PtMwXkrbknqaBEn7@}{QPOyFD)r~GWN}K
zzM7hv4OL&WB&4Muzh1w;ZRbu)h6fiHyWiN7DcmPx*`(?{t-x<(4QK&$ueAAtw{Oo{
zcb)R^@nK;Q5fM3X|GxacfB(3Sce^O<srcw5c`?Lmx!>G^pP!yaNylFK@pk+DD_O<M
z0vEd_-rG~j!Oea6KqK?a$A=CdE_`>#l7)>;%W!Vi!n52QiY*iBr+X|Y4}y&9gxotl
zT|Y4;<%o6Lsaa;Zvq}yHpB1-yBD*ny$JW-?!otGi{KUC)Wu?q=PFT<KGB7flWNE&)
z>MLk*MaA()>!P>kT`E?Z=y9beJWp(61W#;i?2X&Ez0ddW-D_J?Qc~gm*w5J+l&Xx@
z%g$=~)fb_|#t;z^;c>oq@?>F9Bh*r|o;ne9ZGU~eii!%TF)_hI1w2mYCtDZZeKe`V
zMQO^^sgB;>-oIwJ3a~)x7EQyYSq8?&hmUj$Z%jJM_2l{U#gUuSI(m9qX3v&pNO*N+
z<&Kh<LP5d7mg=GV#B`%TtL-DUWK6tMY+U{>=Fgwc=TDqE^+<Y3^Qlu_KYsjp@Z;lS
zflikTmo70e?5X`N)})YdW`-dLCuifbWxwv~U$}f(_|~mkKVB}MU*R6edGFpmuKNF{
zil3aASg+ap>elvr`DK1{yLhF|4qU!0{OsAYj;=1J<9)J%0s;-SzrQ_vadEMPX_m<Q
z6<&dHaeUUt3j{a9)&f{t-`QU;Z=8Pa$n*L2eA?RDCK(qPL`6kCJUtISJlwu9_qJI?
zM8tzvS65%ScI}z$>~1;RD$t$<c7C}jzvHfM&yNoY4OKKVn^p`;5KsQPz{`X4Po6zf
zQdehxduyxnVz=Ik<BD2(nwp$<ca=`|o29%dYoCkyl6|1n?{c<P4$jWa<sws^CkNd0
zn{UUfuC8v9eXXZlWU8BN`yW|Qo9O<8`X*RgsdRCj^FKXsnR>$B5!7ztlLn8;DAtRE
zJKmrPn#D8v`uN0jqn1o7m;JYT#R?4uhy8Vb89+<?zy6vVY#cWiG|^)J_lvNQkkEql
z>-*Er&H@efuUogyqW+&v8;@iYXn1pV*xE<3p)WxTjJ>DpDOy@ePMtc{sQcHuySv$~
zt*w1#7%<-6mit(C>g*#&Tw2=Nz*C&}atjPIE-2i%d9%>(*!jio{RR~u6282>EgoO@
zQ}x!?Z1wWRBCpz?tOrf;n`U2g&=Fg_X_HV?RMd(UD;O9+YpPFA(|tTAU}xN(3da2W
z{Fq%Op1<VQtz6l8>XaA5`+xH$c&J!ZebI>8mUGfrD||~OqhgD|r}vNnd{Adv9W;K_
z$}Rrr-rj1425xb^182|jR#sL@7$h)&)|Vz8ZY%UVdHv?*bU|6!-Z^t*e*FHuxcK=w
z4NXnQni`v`Z*Mx6`Of~-cOo`3Q?sO`<c0T~{VP_ia40G=Dk>^U$j|p*KlT5_xpRAO
z+=zJc<VnJh4-Yf$?lN7qYE?i~RM)Xy>C3M<-j~T-yL4$0XHvc6<bad+;dSV8GjJUW
z8vC$&WwB)6iu+gi!LhdzTxQOJj;*cK2RDjA6>k=}x&^UPX3m<G^zYA4P=DpU#uMA1
zkPy%qZc193lhQ;58ylJVHJ>=+_Exq2_)!7s+87!dX5E}V->#O++S)oJBjdqke|u1S
z*f8-BOGtS5;~yU%8yFfM+?stogIQh4Sx3xSMM(2bj=PGGr})LX7w_)uY}Sk2b*1{x
zot?#kA|hY()q-*}GczqJKdFG$Q9xTxadB}kuB;S(pK-^<-5qpI!;bp@c3s`w3zsi%
z_nT{#2%6E^U9%e2ru}|lc|NFbtk|-L{oGvZ_J@bt7Z*N02HK$WuUcL+IXM|L+j)Oq
zt&H%eudl9Z@7T2~>Bfe{8@o!i>wdjdPf1T_X4tZIE65Ky_x8*z_NtpSX_7(82?5Yp
z>91eEe*FD@pOFC++m=NtNl8gR*q-G4{`NNG<|frQZ{Hf`+%UMatCah|?$4JOxpK?c
zR7@y#vfKCfTQq3p&6yd7ps)qE#Z*;QL6N#G@9rr}Mf>gf_m6#eczEIZ_5881u`cfJ
z%oX2fNgAi|JbLuVLjB3}H#awL*tE&1TTJ)D*6eT<6%~ex^1Phf+`?yPB+qgF{Q3F3
z{ln+a+x231EdUjiy}hg--rWIhB|CZY<Q(Boj^I8wcyz1|QIndzve+89A2e5oIqNd#
z7G#Jv2~<3Q+R~tY`nRXk;~!mE=)7Xpsz<V}Pj~Fz?H#ZE3ACE+-Me?7mBL@Xew{dB
zLIWsk`_H#)-L}mPG)8>rkdsdIHlB?eH)iepA;S>0J+D{VJP(v<?En2xW^p{w$jn~w
z>WXGXWu>B`qT^d}(CzUezrVdbyeaiGXtnv9`}^h3&$E3j+r2t+b6VoHHIXxHtG9jG
z|Nob9@iU)$hEtE7J<D7E?#{~MISL#fzJ3ioy<hs?p33ICyUQP+nyUTc#zy5ofB$YQ
ze;)@jsasq>?Df&-3=dwt0u|~CCMF^qH*T~je<#z_)Rgh@XMN<(BGq?ycegh*F#P!S
z>(S=(cFqnC4DasjbnZS68czT3kLXn&`1JJj!xt|)T3T3k${(<{vQpC2>~uD|`r!Th
z{?*~@A6;1)T=D5i=b0nR*?6T6oIcH+etzE5858EWw6IuMSUfm4*IL51s${Ka;?A8r
zZ|p2qKi*O!Yf~XmS62tx(6%mich+3_PM0RoOl-1~9TPKnpz7x4bY&Zxm}h$=BqTs}
z(sIAKk7i7mf8>bEjoY^$KRY{H!mg%b?e#O4m-}D+HfxdRik$E7@4J70cen7x1x3(O
zWc~PkQ{HXK$;s(?@ggJV_O{+)FFWukD|jIOt2Ag11s3t7P4vEb+;8s|8Y;T0^mW^U
z1qyR43YqNx|0!N8Un(Lg+4=nZeB=J~^mJt{Ew9ebkZw>Vq951u<VnhuY10<1S;M2L
zsTr}W1XL(i9DlsZwOh=h-~j^{H}}UcFN19=KY^CS{`h!Y{^BB6?t341{5oI%uet2)
zt;ADPG$VEvse%^5oSdw_IQRB8P=0@3aVO{27EWpNyfvTQV>7a|51&2DtEs7Z#!ysL
zRKl`Ig-_0=Lo;}phT+_-3)ik4TNAnY)z*Od46d%Opq}csoSRJ@9US)xL)dcT95@tP
z{#YYMQ5&aB5djU#GAIajW`VlZmPJKHQ)InUL1Qa*b#<UMW+tYl*|OU=Y;Xt*oA#-B
zB}09Eea)Yb$9GhJ*SoehTHTnDk>S_Z*XnyW_gZlw`XW6NhKsHhMn^}t#xvBeD0_de
zxA5_?#JjsnU)<cBzV>nK?y{rJ?EDrgkI&z~FE49Va^Uap?;8^jw?$nK`Ty^)puGHf
zP1$%8&Z%#2=kIrYe5`lktXW;k?tNFP?()dlL{zEkmO6t=0}4mr`jV25^*9Cv3B9|w
zw>y8|PqyS^J&n_+Pd{^hMd0F!<4@e~{jTW!@}&f{1)($Z#BVnhp@pfZr-8~m6BCn)
z;}7#rPt%RqoW{$>C)4rbMMg?`I%xL%;>C*+CK&?P)<ib1jo$vLZ>0&S#SPltcs#&!
z|Nnp1B_$=GWz>H@9+%(Rx4-VM6lg7m{{BBrtlVOt*<G2SPuG`vi-S5*<vdeC8&G)U
zY$PfxD~-;_?=IsN6BGOJ?c1?Amc<4c7Zi5v*s);Enx5dGt3iQ*jd$+EfEL#N0(GrV
z*a!c<oCj%zcbvL-@#4YP*VoTHZftCvn31vKh|8*{Pft$=6)c~3C~#=#>xU;PU7a{%
zM#uYozx#elfjW<%aeb9w-ptI*51&6L%b6P)In~we6B1t8cD!Fc`QM+PXC8y5DFXv1
zf_fvM9d=(|UCp?%V&WbB{99Wx7k@a%D8FgS6cH9SHl_uhE9y&MUQ*SG+aqyyw)ynm
z)<^H$k@25z_jE#!J$S4OR6M)=Z39>G(81Fui|at^X~6LeE5SjdW}taDP{$dZ*TF41
zP|v!%ukV?x<I<Lv76la*mtPfUXPMsEUthnru(h?-!^^9wy}jM&@yaRH-`^$v|M&OA
zi4zWvj*e^3%DN~`yme1;--;C+$NOZ1EAp-s9(>a$YYhtBKfhkDH#$Fi#*70;kFq+q
z@f`g2_V&}fUtblgK0o7KwQ5zx@c_@ax3(T$>OK9zt5;m+=H@Q0t_!oTuVZLvYGUG%
zu@LC&?2Oo5w)W7!&kLhBCb6pd%mB@)TUc6t>^lrvxDXf;!jhbvJo9;NP0fVq)4@~b
z+qP{3Emm%1W*3l<=m2%wyiQ-gy*+<p+F7YLcXx}QpJ%)Jt6gYwox7kDhvI)8#MJ18
z?fLO7EiDgTuiw9}R7YK%{ouiapyBxTlvN93cbDy`{cZO7$I))_iz|cGRn>xIKfT-Z
z@%}v9YS6YP)un;9Y;0^?>hJFCF6Y;c+7ghYbQQFO+W!Ba$(1&mnw-m)Edy1NuWp@;
zox5IhR?Dfd(9oqHN<nLl*m$Kh3@5%?&<CB`LSHRm_sYB!+)6`<vKuQNgC@Z9U<EZe
z3COw|ii?Zi6AbYxEZq1dZ<EqQj-Nk&u2`{Rf~2xg=YrL%yFt4Je|~x@6ZA=3NQfyu
zJ|5I35fc+D+HH_+c)MNC$Vf=pz0bwdle46>G%+C|AiHOe@7gP%5udcPvyR%>ReVU;
z`FG|Db<pU;zu)gKxxSb<aUy6v4QS`ul`A1E?Ci;(o}Ap1TvYnufun@9G-yP7+O%mI
z*VoCGl$4}^w%*BDm-PfYJ@xYQJNA5jz24^-Cnu&$mo6FP-ZBBL`C%|9dg76ip8ojB
z$;nx}8ET)MnR#P#IzJnaM8o=hzr1qoFDrpYw{?^5F@je=a442WZ_N^wv#n~mx3@a^
z{k^>coh}_cJx4x0Jq=nbxoVZx*1t*u44{sNZS^+=(7xL_9x6_up`xIY#yI_4!l@~m
zGQyvd^Yi<Im;0Tx{r2l?wv0sq!?|<ky!@70foy*8AYo^@$By#%psgQ<DJKN@PX3Ux
ztFb71cc*jBnl(|!_2Tw){Qdp?@afauKM#g9%$+OiH{VY8dqiZUWZj>S?j9;as>_3T
zO(zFDeJc@T%=vY)zum(LJ^SC?-3_YE-)&sAN(;2TcyIOhup+Ii4%8^6{r*mwK3&<)
zP7bu@_S2_N6~`Z@9qW+<c>>hJ0WB8&{q60g<EHlI@9!Pmntgpk@pHeecfTb4{PYyG
zV{e{KWz&-<DWJ8ke*@j)>;Ibe^n&Um-YHY2JUBU7eQTYZecc&rHSuG|j(K=`Cd&DH
zdaf*e{)m6>t~|GZ__VY%P)D7Im-piOcze*kI$K*=P&x7Y=yL`EVc}-bYTX$#6zuIm
zOR(H?a&p$nmxA`}eS3TRw2io+Amc=jmW|2BPubWf9AH?oe7UyqJTJ?_M=YR-yl^2v
zCuWDh<z>E;e>;OmPCP(!9-tnYc;5Yex;u94;82?A@yuOmB8R4?=AOrep`oFw71h<;
zN)tUYuCAJ@Ak^7X_VyNMRaI4!hl<d#Ug_i3O6K9~Vg$Er+0wGmxt+_sPe#y1X(DLO
z9aQQ$JwG>>RaRD3QB$+C+$ZnfpU?gaLsy42tz5bC!Sm<p9Y>Q6UcVj=+7r8A@nYo}
zvuAT#T3YT&){1p>Y)nW^RW-@H<RW2~GebeFyVbFojZ;rguPH)DEGH+Y1-z2xq-#vf
zoCQmls`f}2I$6~H*#UB4?(J=yii(O&Teogquy(EPojsM4%YF3T-P^1E;`M88+v;y3
z*Ve^qgY3S4KR#kx&dh|QBqa$+Nlr;g$vw$Mh2P#pI_ijV*VWZI#l*}3nV5XMkMrWi
zi%$Rl{blv_^;NX8npN(T2VQ*xE<;eOksB-S!&hiPYZmyZ9K5`OtPniD^7gZ{vss;;
zok2DxZH(yX>Jnmc6eub#Ze8X(8??~x>6{5Gq;hj}L93+qB(GS~#w*Pgy)EaVth4Ib
zIhLTAbOE!xI~r4_PW7B$|M^)jXb+QPaB%Pp+iJ7pEvHn4I$5Npr4t_<X#Dz1(j-IR
z{Ryw&s3@(^lV{D++LC)a3{-)BIIX|`id9@x)G2GDK*qIETZNdInN#PzzQ2DzC~)`G
z{f&C|v-bBl&Rx59o$6U0^yTZ<*16W@pZXj*6kBRGxHKtn>=8dG45|EI>FewBXJ%%u
zShvotolo{k8GBYGXx#486VI8SjjO(7@JN|-l$)#r%}2hxyj)pX+4<SeZMnCT&d;+g
zC@y|H#m6)yJw5s1p;pkmt(TV<1H-OeyFkrD&@qPFuHSflef>tzR%TOG4yIe%^ZPF@
zc27Ro#CqZC)u*x(XMgxm0GhYym$PO1kSCt+D3Fkq)%D;(!j9d$i~UZVm#_cRIMX;?
zNlne|S*5zV`kNaYnPYdAJe<<AA9M)CxjB}gReuT`m+sz|HqYw;9aL~<N8uddPwt?B
zoxU1S-GMp_n*>>EB@b&Dpu{y~%@tBD^!xk!<4;abe)#q+Z+Uq+Xo?$j$isc(#qRxX
ziHVBm=G&jQ)U*dp@nvMJ`0_P5FR$-lGyCC-7bg}Q)m43e2hz1BX6K}Gk*T0PcjxW@
z%l!NIZ_nZtb0$p^0<{1@Tb26y_<VeQ85#WN**Hc<O3KK}3W|xf9qW}Y1~0OaI6K??
zfAs%*TefVeH=OuNp!?|7cYN`iTiox(K6X_S)Y8_TI;nSs9zQ?7h?tm?ot<3LMv0p@
zZ-S~L(3&?vK}F-Tlao|It0?4bDh_Ds#@pH1tys0{&_reT3U^Rr(9Q$a;S+GW(xAYx
zqwsOtnHF_xYwM1qN%t;>v?*|$ICsviwA3_eO9mq^FYmpH9bBu|t#eCCT6D%VH9w!<
z*Vp&n#SkW6r>X0gEMa;0@L|P|4-3EC0r~LPuU~r>3x2w{sBf{vSLsjXfyV=Tz)duc
zpZndxb-<JNAUW`~r@*KBe()l=6Zc(Z-R-oswL#Ou%l+rO)z#U}GR;=o%uxIG)>hD(
z<au_rrz}@~3JnQ4aQryCy8pZu1&#}sFEf8w_r1eKsYl9`tDR3a==AjqPft%b%(|j6
z$EH$<kB@K9;}uip*Z-3Q?TmYRdU|47+A-_CQ!Cf4JJu<zUhwXYrA^%*i37WRW!ZS8
zSoHPvx4yFc-@n(oziZXM{}%stF)J<DF~M3%p|03d^=v`>0TFQ%BbUU0)3qlr{dv~5
zNNic=vK{$TXYnY_^48K?@@(G9ncnXntkdDr+N5Ey-~NZCm0@|>g7u#z=Ujh0=Um~A
z!<O%#@fiEh`291c)v0l7_H`u<4UaDxY3YA{e6$ju_1ZZ3SWmb~@6X?Vzuzy-n{sJO
zX7ItuGq3Hd{SDf*Qhu+JecrrzpsCeIj~|0ZTT9;EiG01USIX3Bu2rc{8RNIJv&}&R
zC)0GJlTJ)fToJgq?cDw4Z{EIT^>KG`3HejVXeB5pC^%6vXk`e)f}e~3e7@cGq5p@A
zi%ZJ68x}4uE?;&f-WL!Qy!g7K*V)D8=+w1qb)TJ|-+!=~{dG*kzNDjEJu;R;k&%&2
z>ZW@yTnK1sZB4wgB2dCOjc3lBISdS-)hD37Ncp=MpLsTtmzVhp+pK(9`u?8mbp7~a
zOTDKDtdFyu%Y9wN^UyTiXck|MbI<43_kl*854Cc?0Ij>4JGa!%toYd(K@-K9+<Fen
z>$TO@*+FxeyGma#2wR<)p3cs2;>?*A70(xUcbi{Z6PX++ZMrsgw^;CUKUXIwra5!x
z8rJ=(;E}Zod2Lty?M-8UKY!TzxZI8Q^<1q?lT;knhMms)rr;@5R8-_+BMI_qBlm^Q
zj*gCwGZ#MFccrGK9XfXG*b3P~RZq}9Ue0C0>m8ff0yIQGedsl7*Mc@-H{VzG6#Dn;
zwZ5>A`n89L+Zi1;Yk&WIyDj3B-aSyGLdEma8@)eYug6ROk@K7c+Dj?yqkite!DdBI
zp=mmiOs!6h2b<Z!lA!S*kSQCJk25gLn>R0NJ8xy(|Lc<ePE*UDpOa;9*qU{9OP=(n
zKmXPnoAuS@$W-RYRKAf0kq~x{%-tL2Z5s=pV4#xZ#}dbmO+1c3nsc;5SAmB$k8}!`
z>N&{UR+*UP-fGFdzOGX?q+yn6_M+0)*CO^-Z9Vt6_V>4=prwNoCL}yMd8D|s)U={B
z$#ar`ynOzm&NJ-R7dC+Ueedt>opoK*+}wOi?rpKuQ&R-3XLJ@aR$Ww8RXup|qTsb_
z*A}@8X1%(y5_BprXbC82rlO#*kdXnjhZS^$QWGmTXrY<UOe5D1OO`FqPc(J>{CldR
zaoQP!gC;I6F6-s>9MqMRl$4B|!`H{LGVIvBJNvHLlb?U%%m4lRH$jE-^|iIlQ>RXS
zwoUQk#fxe){B&Z~TVGb^%=_PXE69%LiD&Vy(DiY$T&+yu>*HKIg;WFfR+TQcOW0rd
zxUEx7q}@LF(~r+8>o=UA{aoka#>B@jK;d;gxw6J~8i+Mtv+~c(Nym>}?5$0fkam}g
z?|=I7YlNJ%yIlRUCm++j<fPrr&H55^WWXA(Cxas9&rGd3|Nj04ZHosj5iKe%-YT|W
zzI8dD?`$*I|Ns6P*8i)yxOmnaQ06)}w>$B0+e@2$DJO+`<ZN##t>^Rq)Kjawaf!Cj
z{+wrLW^!<IJEx_o#l=lZOiyp0FhRg)jz!>ul4VC(U${=5F{2~v>MBJuv#`yPT}xL*
zZdQxhk^w4LUfIaW$n+d;=Z}7prtp7B*y@RM=A7x}?&#<^p%NkO0s?6#?%s`k-OTB2
zm3Ul2+AQZn_3cSVj~!!T$jQmsk{7%${ro(}ijNPUf4)8K-L<vRRr%4IX3UUa(63uI
z@4gyn*)Kz!joJBp;SDuEi##T^2&sBy+*LE{Q-mZ-@{{O>4F)E;w?w|azV5y~@2-NU
zP}usoUirEojMC<LE>~BD3Q9?7Rrx5+nKP&0!2!mbtS{L4WEv(<p4_=ysW^Ql_vv24
z;%7cSb1Vek@BJ<Z+WTyNzebp$;Nv4#ov1Awlhys(oE9GV@$oUMf0mS?q2Y%Q9|UaO
zHXeEH`D}OXZ?mXvIhxgbQcq9&v-kCXRaMo($4sEKCmF{$7gR=^@Bt;J#>PetE-t6V
zZoMx3$z@?{qgd<f>!;|&Mt#u;Ib&1vLm>6^G*R2On>!00GQGO8Qn`vpD{Wr9Yx4?&
z8y3Gd7Ov2^VgBicMTkg_jF!%~-ozXkEiSV@8#6vpR_S)G?%rex>GrOsUgiE?=l|NC
zo}Qqk{&oL;rY~8#l#xM3Mh0}!XVSAXGgpMHob-V6=nS)5sb#*i+a4ZnPyX`a;w;`Y
z&`wU!QlF2Hj?OSj?Q+$*u)pvz8^Z#(UMX<-Qm@2NP*&y!TI*5!`y12oD_N$yN?tY@
zr=N@XvP|pa$B!NT{q9*=tIoMzV`OAxT4tobhv^sh9;RI%g@lCzw`PSNIeIkm$>+3d
zYa%D8aQ^@MzFyH&DDCX5)DP7vo`=NaYZ9AYc64;a*~c{afs$IvvRP)iU7$7ClT;R#
zy}iZ3$LE%ipm68T9hd$zF%d4-H*eltSQ~AwG1aT&-5p6#sd3zh`|K=J=lOQE0s;aJ
zU834ua>w7?xOwy7_3PqZONC;0mtBpydF+y=2-lv^=d1&?rh=-2RUs>ts#G>#TotPQ
z<>h5|+v;yEix)3`QFw;S-)ZXg-R1cpQP6&%sf_;`dl$<~yMr?FZ#NJLVN1K4gChi#
zjUfpcM&7+)fmX_P=~-GzR#sN7h}ftk!qxhsu;tXrlLy`9Ygwjxv3gE2c^_$MX&JEk
zYJk?%h^<*uUB66lTG*iC397w%dwZX4Q{1_8r`im^HA1Rh4hsVmY;9##y{0&H3aRqg
znN3nrw6?zOB0Q`A(o*l_Z*Ojb`dQ~5cZ=&EyRk8O;=Flzk4_%hUH8`tbQ%R{7NFss
zc8&L>6hZsowuoO&kEXY_wI%)f@>0UGNX4yRj#pe<oZ;vB<)B0Xnh~?9Gy-iVC<`!7
zcquLZqDtPpWxb_~i;L@V))$}%b4k;&vy&4P6pYxOCwp$bJ-_Fq3u_{cS=iY@>v{9{
zd~ACm*m`qIrf`UsDCl^RH*a#L=*P=}0z7D?%j&STF8%5uTeGefyuW7~5gonQxt%XS
zYwCy3pPTpY-TUI=8K?DedpG3XHcLrOU6^xo(}(Zh+k;kuPJ(gmSG%&K@G<BNJJ6iU
zsZ(5WadDv7y||cNMn(o??9)?IC(fDEBc$rJAb7bSNbcTV>zv$N*M2n_f2XPG+1cIc
z=jVZHA4Wz-P&Pe1P1m(Q)$E4FCny4CJ{a5L(+%@q7*!{vGX0YL_yiJ?P*+xFK6mb%
zgngaO`hu0mPfk|fn0%ZsW`CV5!-GeUnn1Hvg^!OlsT<D?T^;5)Nd+{CJ4q!oPx{jO
zczaMKzr=I0f~U|j-`Q-fP78PDo(PYxO>KI4#{2iTw-28^Yn!Sa{>sKK;Q#~3$il)x
zwRt`^^78VaahuD_e4SrkTN}8qrgHB0)v>#`b*dZNgSKSPv#oyc@}=f)i^#4yb7Vkc
zReyhdouI;LW@g6Fu-t#X)7r4b;p^i-ivf1L6yH&J@UySK*EF4#rMD+M|E{j2wCK=7
zrV>!~x+n=Wxzo|n;Sdrcl6QAkD=2`IkM{*=O|AI<_j_V`x_Z@;vXygTYXMvoFI~P2
zItyk+h}N5%o7pQXD?w#SK!89~Q&YhHy4s7%v*tvtJvPs_dO^@iP``J{(xnSSRtAAg
zTNt8sabvQ3_l>PF^VR+5J$OF9zRhdtq4oR!b=|oW6S6wY_w$~Qpn`dk0jPBMT6*YM
zuk^%8lbE8Tqt~w99`R_Z#ivi71f-?8r+T%Xoo)X3<KyE61qBD#<!cz026cXWdpr7z
zsBneQsyu#qyCZG9(hGuCez={#-*Ii&Vz*wY0IjK@gt52kt4n`|*$s<b8w<IT9=|xg
z?_z&%uz<9?y;)ygj?Ci?`A?t{$Iv7|tu3$)sKoJ#soLSkKqn^E{3y7%ct-2y^z%_q
zehW<0jM-NsIoGPx$-#jER2RLvx|*2*6uPb4;!0LlQoGCEI<1Y`%Hp3@_3hg?(3b7>
zA%FQLB_%=AWj8h^8>XF+xcGR+TG0IfcQlS(z8w4^<yo_|xQJg;l2YFNeYt_N-wFr{
z{?&)J>;nzI+|J*hX;<R!>+8BQXz7FJ&)ZG2uXV`zu6Xh!Wli*UzKIhjf>r~lcsl+4
z_0=@IsPbQ8ziQ>LFPhu(@2@Lm?K8hu!3<h+6A&OU%RFDN%H?5DP!MQO?o_YV#qRw~
z46m-OU0rz(G#WK80JMww&7GaXT2ny_BthHzPEFNrpJ!XGq@lr)duxlJ?IMAjH*en9
zRjM7LB?=l@T<$-AQP5H^P-)%N)b!!q?)P1Cfg1B#R)KE#5RjDYJaNK9#=cHwlFGuw
z!)>67;{Cn751%|ysdCwT@Yuy(Nc?>3wE;)bUvS*@9Nsta_%Y26Scz^9ZYbZqVR0-G
zlz~N#fMQ9xzjv{;wEO;thua??YUTd%^?H2ouB^|m{T2osIDDAdYpKxQ>hIf5d|&v#
zRn>c1!o59}J1RaddJ%Z$+^*8s8$g5YH#Rzd(O4gIv`dtG&pOcjj;*b%!$Iwj)AVAc
zwr$(y;p1cSc0t;KlP5VJAMZbYVxqEZe^QxN=&F{L!OM#lix^3n>;3q?%zu90g$n^s
zo;~Z5YwhS*5%CC?{d6oXC7ap#k4@8!R`3-1@9}L?_Vsm+OM?`RjD+g{|1}rkVx4DO
ztyZP8uq3we@YSoLUQ31I>wYeM@$t-|udlD0o}axr{k+p870@1;-{0Sh+s+D@IdkTX
zJ(b2v%E}wFuj@T|^5nqHo08Yp#R}Wb3fQ%-=gGTweGeWaw6wK#$@yD=;$W(FxJkIw
z?uw5}B3!Juwq!Oxc#!br{r&ha6=}_&_6Rt0pawoq^8FWB1HWx!;g{sc$br9n!QbEC
zK?fnM2w2Dj>TidKhtHLM9dSz3z}d+Ov>i=FMI|H3ZDq)z`}gI+ZK$}72V1j0>Ac+d
z^6u{PiDuh6dU|SDFV6rS{0dqc44O_|vu2G;e{xtGpKO<Q_&NnWJ-;s+X%A29?|12!
zvjrDKi)WbT#e8@laj9BVQ1IgF1JF9|s83m$8EB*8iV&?MM~*01TT6$o4s(5fZ?9qc
zIhl)(XZCte*K=GN<hV2lwBK~YrcIlEOs<M6dw<WCN7}4Mz4at$hpn2=j04A?t5#N4
zg3ihl(~IetF+;*m?|;GbbFw`WhE3-sWh;bM?ExKVa9V%=k!x$Cf8J>5P1XUY(aJZ{
zcfn0UNQD!Za9^SyH5G#!B6GxVSR6}+bWK2cV6nWk`h2H_7yd+FcM9AZl{>Nj{6uB<
z1wku88$p&VQJJC>DHOY_q%mkEXti%nPL4}|#<d*<zH;)?mr`F}TMKG2Udb|L<CEb?
zPfwrAeQ|fmOQi&>ji6IF6rI}^6g@p9VN<c;jhiN~w3&#(+?SdnTx()?i#a+vGBmLB
z%Ppw-`U<q&;P$p$R{wOn9fb$?AO5bTq_n91c+?jLa04PGA}&tu(W6J8vcK|knoZRg
z4n96UP`01qrFv_7e*BWyvUv0I_xD^=QdB~;L_vekE3RgNR;App{VrSe{he-=&E|qX
zKMGfbXt}t$K74m~_bmQtoI7fNZ+rIh^Y!?8$F*UHFJBh+S{n2v!%5bzCZgEL$;*o?
zCpTA6Kp^2`|LNl8eseGV@wvOFQW(^*TJAU3rC)W<zR3Zc9$sFDK;sEPD+}J-Fl0Dz
zJAc1!g_a?>z>qiw>g$0@3wdzYt}bUz%^T^*8w+`oAHO&T>PugQlqB|Mes*SkAHmJS
z5^yu&#qnbozdi1^?~*&HW14?Y=Im^9_lgROq~v7N_b+Fg=ex}`N(HsuL51VJd-oQ(
zt1i0UFn|91XZPpVeCoVr=s8KJ%vgXS<L)j~h6nHW|39{`_BWTz_9w^LPW=CW{?w^W
zH~!aK*8ci(aDt-qg?+Wvc`*(yE-q^DHrtyQ7Z*qE4v3D9UX0c<(uj$Qk}}J=!7$aU
zm6@GS!Q5OtFE0<YVlZf>%iCL9UHdieeAdo!adUfgYN|FvgIVsagj-uOLE9xyP1Dt`
za4HN64i=P^<(=x)+RV<cq_5AvHS4NVMux@|FV(E8t5mC8K)Vn@wQ=d|YY%^YeLX=1
zwD1trI)k;`G(u`>_B=~}b*Pn_p#ikW@lXpV2M0&P;>C*}a2|c&x#E{?-5&{Q^Sl<X
zrHAhAt)4i0Hg|Y<IH)Ig@ZiA}!OQzz2>Nz`I!DJ1%=+@c9ZX31|0VhHo&);~`J}-T
z;08OA#4&V<PrtstR<B~&yevTD!Q;ow^78Va5$)I4)^_ytxVX5mfF`#>R)_JL=id{t
zRSVoWY0jLU;N^Y~A0BQ$ar(4&fsKNK!-0^bqeqT($Q{hljo)`?QT_d8iyj_hb#ZY~
z5fWb@3>ssbsaalL9<#fQ*Wq9L(coo18-MV3$8W3qTLo$_-P+21^XAQp$GzqT6(15n
z=igO+ezxeiu-|o2Gbxh{&=y$*4GoT~tHZ@@7a4$x@lC1Rpc?f3y<TVy3L0{s;-zY1
zYwOytapddk>w=KVbB=AbSk_i4&@zJ)6O}>xz_dbFb;t#-n7+Q`%W?U7hqYmg^X~5Y
z@oM$@1tD4wA3aj4a!CZ0P|N-2C*9tb8?Z72be`d+O`AR(lg>}Lu)q;i33rR>y7X(X
zfSX2j;320^NaYq+(tS|2f#eH0up%2!ht|(AN9HhC9Xx|*?%7@bUP)7v6O?{d1}z13
zpuMK)bb?ljUb`j+^6J)X@ppH2Dp%<&N_zbA@^aAni4d)+*A9Jt&h0pV^AXk;c6N4)
z+zq0c+4)3lnM9rM>{zfs*1Alh_I|gx{=P$=9UUEU^^>C3hIPv|f%@znT&u#@gC;oz
zMMOa7L|lA4L$=k4(c0P?wCeBR!Gj+@er()o`uzqILw<h#Sy404FuH^U$I_rqHeRU?
zxwAS`^kSuE&YZbn`}X$v^W~>_salo1V9?gqzPOlkX@CX;11K+XaWw_4+_FOZ=Zni5
zliklw?OPSPdf85)5bz*@+8uj;r%<h_Hk@Doe|>*n9<*<7v3q|)c6N8(-Cd3=LlzZ3
zKPUFT?kKdSqTFAr+z+a7A>?A|-^UC<0on%+Rs@*`4qv3cj796_)YD=;(&l{A_2bzX
zjvPA%IyPHVQ}e}zh0LH`oCn$EIpzhe`TP63^U|Qi$H#grK0IK2^X84ode6Dm<zlw;
zJS{9NB=*h#?I^4G_GaeMm`Kn$8gBQ$-`iX5;p4Mq#_?yVpwmb}!@QNBQnqAVWU{lf
z11(nqHFZ9GC;%-H)(&5%bLH_*tFHe3<6mE2XJpXR(_0a_dD(-`6LT~~xIkwygHFw6
zP|(%oT^qIa(D(cG{mXo3zxp$;>g%hSMJ`6c;KAC17m9W~|Nc<)QD;X-S08kkwrk;@
zJvN|4iJ_}P8hd+tUlg{0dN&^qvdb?hd3kA(yP<VoUmtRpGPw*iy7Aya!jGRn58k^M
z_r)UZ@z1HIIv>64+NNlS^VwE?X$V@`vVFUGxo90Hs1KQ&%bTB{uQAoD=EuYKn*ByX
z((S#A`K8_EP{s<Df4E`(6WXVQcP>GU*5k)cf(8#kwFPAS)$pGF{y$9i_Vy<E_he+P
z%Z^-G87wF+&Yqv2&(N@bz5bdtYe0vPADlev-pb(RpqgA%v^9Erp5wv*(Ba*X&hzFS
ztB=%wx#-^dFY?#N<MQzrO`a_cT^-h1m%}Gx@u6#(Vf?yv>oV@|v)%XqUo|KiM76`N
z?76q%Y8Gg8R!&YXVnagXi@;XU!aUGz5lrE7>w=f_?fd=Cx_h5jRau#tS^m8qP)h|;
z)LpjH^Awt<8?BaMb-8L^$B)$W;@qbnDkU*B#O^K={Z*~=v$VaV<Hh|4uqLdAp`qZ_
zRiT&PT=BgnXJ6L?TIqFVMPS9}v*xb-$wmJ2?Y6!U-uJIJ{ro)8NfRGFd~mqADb=+<
z*=*CMO&jX|R{i+#1Jw9fblh+!Xh=aPGU$uM(Y~egTdLmQvkh4p<oZS8C?BYN;gent
z8AQvOvnb*5hC;4x(C}<~Z?Fis_&4(l+)#MKqV?!8!=B#5$21|sYtqLf-tYUZ=QUlg
zcW?D~u?PV!hRe(SK_?v*JU+&IaPlm-ni`uBEm0+9Wzasw6<4!BcUFLkzxVg{25wAp
zy{IfC8oh1XwulW0jBLD8Ej>LvprQeExY+vj`V0vV54D0eL+q{o4(iZt+_>?@rKQ}f
zLRL0`PTa`5yNjU#bOhkjQ&T|;7C_s~?p43%oOk6*-klwd-`?JS{OaoJf`S5vsw%5f
z({#Jr`Q@F~h8@0mQSjThZ(^VALZ`HTb8h3QWSu<2J`Y^=FVb+~2Q>j)TwD+DUGgL~
zB?WZa^^Vfl(_RF&Tqt+)PfAh(rL6Sxa>9NgH8vF=7~<mMED9gBya+sV>To;%$B)P5
zAK%$oyvSY9={~2er>EzJjT;Z{tNra`9$+|e&Kw?db8{J+ihwT~PA{x8Emc)nO|!2Z
znW*gUV-fiAASih!J{DmGWeP~pgTg)kOY-9lg^=+}aL|L}3N-F{!@?D+N8<IHo0~Z}
zI40P}?JP=FQB|E;ptLdT>Z;ZY7Xm<gzZNcBxTEBy5a>Ya9vRC?-RJ+uyScGdeR<K?
z(ZO+Xae!g)${^Jx%a$=Qym|XJa9xZgXwiG|pOcf-Pn<X*U^*`VG#hkxS83t9JC>l+
z;Xorn92^IxXa<9({I0AFW)EKOCu+M)Ao+NotCtrSXyxSU@byk>!;%lT@p}0CAOG_5
z^1}xY8unIy?~=Qm(#9hh^y0tH#a?N1P>+IzjV<ZrrKJ%YlUU7iZZy2#|6fi!eBF`r
z_Wyfk%#gU4EF>s+G5Zv(DI8)lNu^Wn;F^y|)GKRpzC3=sSXy5E?v*UlqM{<MH#$B)
zf9$!aYi=%neO;_`TH3M~foFuI-R=LyoP3<D+~418V`sK&W8s&_pWV#O`fR@SCjQwu
z>G*LsIeF>Inw%0)ui$xa9yrw>{!y$7(eUZVjTgs`T};c*?^pMqcS5eezyG*&{+`4`
zokyfBi&S9khNNw8-o6zS7jHi|*ScHosLq|8#mhbJhp&y=`v0TKv-6iP3%B#jU%T_}
z(o$~Fn(rMub|~oU^A|rqxAn&Sy}`@<5`TSpsS&))r!hJ8)D%b1%tq!V6~@V(;^N}%
zg34|ST)V|U)l0*l??uq<590c9M?gn-p4Q*bF>lJ5lc%M{_xyY|dqv1fAy7y@J3Bl1
z-k!>ceKnSk9zAmD&kX7o*Vp^<ok!m8kEoB6i_4c^k70#Pm;46dy;3%re&%+1AtE*R
z0s=P_cKrMPqe`d0pI4N1zIjN*8|g*i&FhbU`f(#5@I$3@>(OJ1Ri+RHl7~;9=3X7X
z{@9AZ#auGG%iqg|t%+cakB?`Z+$kt0x9;b6^ZPZR?yrTVCFh(IHe0i<f|k!5T;SO3
z(ytWr_0`qxFIBT=&;HG|%rIZstp_w}wrTU`z)dNhEv>BwZ{L=-t^UTsaAifH^Xv2r
zlWyF&@!;X%_D#p-ZL2^lK7{>J?2L?z9z1)-#!ygD(4gW8I*9jKMYotP=y=l(DgPaB
z-sFJJ`1ttoqld4r?uY8-DxRR5P*{A``ONh+UQG74ySOJ_^7D62&q+HN=5}<f=m1k4
z9V;Y?N=lA^PA>d*J0BFSH*eekoqeqly=~2lz!egYJd1aIEL^zg!RI!v?%u`n((PSc
zNP%>4pJ7k0v+GgN99Yf@jURg!9!daBBraU^==DY$JF}FYmzS4=_Aga@zgvEBbGpCB
zq?Xv-Wr^qK*+y*3k-U;+y3A*$Qk9RQlarHxkWdq7GrIqLJ5Yt(+}!+P<C#N;TDc!S
ze%$OiSuOF!g@r5P_U?Kyu_ba}&CY8~C0nC<K|^DTij0kojVoezn=w2%)XEJShR(XS
zrc+SatwSnYLtkINqOvkGZ}+ZUk1j3s2G7i{S#x25Bl8rU$e;%;k18rF6aW4B`QqAI
zX({u(HKlK^tPGxEUvIZ(?_O44^=X?o8|U5M$IGA*xQJy{=<2q`?){IN`Ry1OV)j%B
zZrip^$z3Gv|G&Q<zJEXd_xJbI-RFbE7Zg8cy6ZJfhciAto`sclVcy+ci;gQQDOKfq
zX8jB81GO_xya6@soZEODFE8^gm9sB<BQZ@cwoAV5$H60$0}Cflo!Yu$g+|G%E1Xlc
z!^Ld-Zk{}S`taG==7CGSM7#egOyE-2*5(!z6a=-5z%v;#n?Jp|X$(4UE`R@DGyhG0
z+CgKbpmosu>;67?^-8NsX5kHsFZ&N2n|OTR!bJ&>A*0n#lJ8&mF9e#;fX*T*_xDZ)
z%_Vt*O9?G5Ge6K~+QaGdYuol#f6vlQ$iBW#R!lc4Wh3_#P`FI>YVGLY03BXhR#pZI
zL(mCcesir3o;v0ArQ;B2-J7~PyZ?MUR)&b^Xz>c!X)2!YMd!wc8>gK)&~N{*!?~Sr
zVbamAsN+Jy!WUPCYJ=8=JU-SdY@#@Gv3B^n1(lzldHDLezP`5BR9YMq=Ac2|#fz2s
z<n4N*wq}8<#5P{(HqeC8@qT%B2GByB&1q*3H83)Rmc@eZi#d4kpxDpdSEKXywqCgs
zq7%K%=Y3k-v>PY4W?yd$TIrIJq0#WCm#3+z$)x+^@gB)$&{_*a!@wsq)Jng-iF9#s
zQ7|$RGS9yUIvQz;mnvxOj=H+~#m9nzf_uZ@87V+RBw}}&Zc|fJiClkIms3ChXz`b?
z&CE*6(pMs&D{hu7Q33hx-Me=u&YW>^a$<^!jZMtY*ROIhGQM~39tS6<<L_^8OXcqG
zF4y1p>y`GKo12dxncO*j-n_o->+2pu#;qG>&zAO@s-;?`v(U)M=)$hjY#u2S4(E10
zQQN+oon2jre!t(Jzj1eA@Wl;<J%^7iJd}VKb881ReL!=EY@l`#sK@p9hDAt3j?CkY
zh0ys%uB68zCBMF8?%1*8Ma+_Evu1UH2FmpH`AxI0>1?RDHfiskjMv9{r9s1TRbOAV
zK6sFDlQ%ssUB33q#A~7ZpZ@vrxL<9?u{~E-1TxRB{U!-Io%ZvOH#awLOgPANXGh`T
zBa>&|+n9X3>r3stdGr21_UvlEy**!9M~BDI&~QiPXSIeuuA5_bl{k8MbR5+a*jx5i
z3RJU$4y;c(IqAfiGe<xNbr(K%i-?Q_&F^)K>25l4_91BhQSvdKnr}DLL5=!5I~+iZ
zz#NtaC4%Z`UtibNVQWEM*!S=IKRrF&E!W@CvEs&NF<S;u_gnC9b@{tHjdSPDePP&A
z`R$G5udlD$SFF%jaW%_hQVXA~)q%TrWwW+QfqEaHarU}D6&DxJI&yNdI`?1OUTO0>
z*2y#W*Z%$nTAH`%_~c2GK+^{^3zR;B2C-jWUJg3F_r&Sbmuv2xI>n_MwZ*~1gTt!i
zg+hT-;hVQ_Cr+4<aOEWXGz|j-fz(q|4z|nJbv$^GP*GXgDd)KYH286AOXjTk)91{Q
z0cCGFIXSVPiG_h13vXEHCqI^GuLTWNLpsuCX6N>&zpQ26Q24L2H(3Te>|L27^Y@0u
zts55q<)qttKl_8`DheT8Y>_J~0+s)Kx$Hm7Hz@AjjfFKoKY_|=R{xB7udc7}mo!dG
zIMyQx8aI7*c6K}HD7KG}juw=cyWiheYgq9iA!JpE=a&^~8?&xzT~wa2cFGiyl+@Id
za_3K-a`N)(;#3z}9=SQqwd(KIE55Vl%$c(x<)je9fzPj1KmFw{C@pPWy?XVtZFA?!
zhOLb{dR_5JJmcS!lhqd;H}D2^8Q<^!-}mNC4rp{zQBe_eY|*uKvE16)+AJ(A3GeRg
zTy$JyS?TL*pz$v;ors3H*5yu1gFvUhN>~=Di0MYPFfy}s$V~)|nnPOwO2%7LPmAT;
z+~itZ{qxh)j_z*lg8f^zn1JS|zpyU{&6<^zm^?c-mpeZ{-z4WoK=GM-_dwH>N1mOX
zt@~`rJT>20BCnjKJts|=Joz)1x>5cwxz*a?>kb?|c(CPihbd_H?f3ovTc=JHy|p#F
z{nyvmi%VW!^6>XRKGQfIbhvrRyE~G_&(9qNkM?W3EcctcA^W->kED^y7mc*%4-Phi
zCe%twOh9V{)Ya8lSXmV<EF`|ZzAkP%@1(44mB`7HCuiN}m$z$~J{@#G)5EuKbqkC>
zf`@xEk{?U-*Dme_4S9hks-;1b)4mTk6mHpA*mL~Y#bcn(4QQaU7c{f6ya1dcjwL?^
z=>s+X($m{}dU(#}I!jw$;Es%p1WyGhDS;dq5gEBK`FJ0wu@5>n6tv$Z``Vg=?D91V
zRUtwrE?*XY`0(L}uU}i++uN^g1hw@3{rQ=3Ys<<7FMYJt)ZAWw+nj#hAoG$6Xt4t`
z8;`@=TU!|!#Pwnh@Z0}sD0+HIQAfw;$cnUf?(<J=D?hQ6m6Zi(h%9m!%zJib=8MbA
z`9b@sz=JEt*AzTvdJLK)4qY9#qxd-=Xzc>1;4goFPt;aSP%v<#`pWtFny%nc<+Rje
zJ(8dU4;dLGB_%g(+}OBv>o>WeNh;up#piR&Kin<9|M0B&eG$V|1?$$WdvR;4HYnlz
z{{DV(($TJt?(WNTB*f(8`ZjDZSSx%YE`4?Qdb5i8XU_QO#P5???l-qd#ZzqS<4>=y
zt~TwzxUcqi!1lb@kaaOT5B$A!=~BV3FPSATFR?~%&olixL#_PZpUR4giU)Vg?}N^C
zeDLN?%mX{~ygLpF2?~Ak_I>;R{o*ctbw$u%WyJII^WD$Svjv??#v^IOl9!ifwf@cH
z7cVpttUgbeJh^$Ub-9v~64U-apSX>TjX{SSfL1CvIy$b1+Pdn6ps&-yfP}ZVw$9Sd
zdr?)tDFj@&Z`oM*WFu&Xvga@;Axs91zWrVXNd=G*p<{`lcH2qN;-%hTiyWC;aQ$Bi
zE-kif&ABPGa^=b&kGk~(w&g_r`2G7aXlLN-YiqyO#rMnE`j{-N3|xH`bcl+J3kzsq
z;CR3M;=sjjv;I}r9sLX%#WOGv0C~5jX3v9_zK<_1cAsHgt_NBU@cR0CW`>xUm<O+4
zcY}@>@tJAVq%HzF8vMhjPfk%$Qc>G-Ize~GFf^Q=uK)PLLT8Qebu!=H-OZlZ?RvaV
zwtL483mKaVfp6cwMIFC%`SQhGrP)7z{786qW@eL`$=rvB+npz=fDSp~YGpdy&Tsz1
zc9Kfs#YL`aGtT`1oggv8rqbx!+uQAH*66&sw^#b!y?dY?>Jt>5Kio{8ztDHK*`nhj
zpzGZ@`1p?9&fm|Qo}L~N8JQ_NU4=6+FtBNvvHYDK4$*08YTI&dGEMbry}P^o@UdfT
zcXyY&2LuSz)YNd<^mlZ0tSG2pEdkA)D;b+69%2D)?{@fi(*J(_|Gm$is9yq26q#gQ
z@%UEJDWp1K-n_g+okw0>UqAoN#y4+rKs!i52W5h`n}L>Bzq+z=ne;iHl$4Z=xevbn
z`1qKqenNfSr8^fEItxlkWxWz?1vRcgLl?QXw}DD^tM|c+-FQK_l&lC{Efxkj!DmK=
z*T;KRuXPy?+^_%7JJn0I+TPnT&`&%&JNw74U!YU7UcP(@IszhWZB*;V<l{+yetZNi
z9RBt7HE4V2jT<*Q<fgMEJO<4|_4YzWAwhLcVvfwE_F9xQG+|?DFKjKq;|-wMkqLG=
za}FhfiXTWjRHD6iv967c%)fvCKwHTh{>-2M;X^@7d;96Se%0KnkDD$oc30NY;_B?|
zToJWZ3p9bZul9G=ykPy+QCqb@`{+RPA2Y6ed3R?g=++};MMcKaS63WQPt#>&0Cgm<
ztPBS2f|9W)IFMwPQ5D(D##`|0jAYH<uh%;|I}c7&c4v69UyfhiPUi8k-sZ`ZCqK|U
z3fiKl<})K8;iDx3XzT`bkWJdTIhlgo7wZ50OxF<M0$uIK)e73?x%uGgdC{+!zASd{
zKXm#ucj&4RM+b+7YsY*=wL(C<+o$QpW=-V2us!c?*S^}{O6uzDpgZTz&Nk=1bNs^R
zSEa{#xwqKf4>2?{5{llIb8vI|`3H|5H;1kcd-(VJ{p&j&LGuKnywLdqQPA;Ti`)&e
zL1)a>{M_{Bqq2M7fxCC_wg}Ih4@xkxyF@^3;JdraFRqKVc5!oyx*|VszO-46L>sR(
z8$&^Hv2#U*#jf)AdKFq9K?54|Y^zVryYP9=;>F5U-`;fIuls%0W%A7F7cK;J|8rQq
z0krEs`FP*MGc%0?R$pBayqxdd{r&x*s~irsaDt{nz{_|%nKpu^aV3r&J9!*5%WlXg
z4XSCD@PkLB6LaR&fD0AS5L|n&^Dl5h04oL!4jJ-EyGKt}^DTIKN;GC~m1t*YCn&W!
zIXQi}SN*<I?(7@T`D5}m9~ggqd)xi}UiJA0pI3yg4*T)(xV*2)+z3#kVQ=+!&`P0_
zmzP{$NBH>gfV}eY@$qb3k*zABtHX{qv2wfgCzf5he0k!eNlMkAt!e%8_GS-V9^Khp
z?*BfwD)CSYCujt+@XL!p(4O1XVQVj0-P>1N-CesDbn5SeXV2O|R}VNgvn@Jqs12G;
z&<b4z9+{5be(cW9;)|Qp{ikS$`+bQ3Ek{*_E=Sd31C4NQ*<xa0ZJoWZ?D;uao!DI>
zH*enj@!>H4!<R2L3!FAqeSZh;%_=A`tXsE^A?{7Zugm`Spb7oN#6%`_5p`>8Y42$|
z2jAS>T=@N6Y(-^d<dc&&MM6SCF8v8+LPA0p_Se@he)sy}!$w|dvptVG&rDX0ZC$zo
zv<tnXg99{gef;=hr&cb|YL@%^YA^06OlCOn@$qrPgaZsbvQ{GL=jVyqd|bUb`8eO%
z_Sce<k`q)wTV*UtUxhUO_L|gkak2aCDwl^hK%;ZuDd_wy8$mq`!=B#HOw#W5NNeG8
zb7Uade9r;UBn5aeEU1s^E-iiBB4<w1nzd^KcbDZ}Sr;q)_t)3v_3QO#ndNF#>1+lq
zQVm+_C0Sb^9v*(S`qt~b=jY~1m}Z4ELa&Ie`So&n#Kxr7hLdN!i;9dUO`7!J*|TMz
zSKXfmI&1Iqv$M{hpPl8lDF@XoA3hXRR914%>N|6FWAgD2U$4g>K6j2!Qc{w&&)U*5
z@(t6!=<Ru+9rZCa>zF~qBnO+>L9Lvf#m_-w5fdf|?EOAng|oA>Q*BmXN5_k=hhU2V
z4m>#64BG6!7_`O(wDT_Q>@3hd69F0`9Q^#p&&{<4WxI{dTt=0jQb3LNv$M@XSE#9Y
z9@<g(c*3k%T|a(QR8&_#-v9sa`WJ@2TH4y)#iE_n-`^cPeVY6AwYAQ#udQ|MPYVML
z_DY-QWyJ1$zJC9|Lvt*PC(NDOd*Fb>kDos|=UgZO*}W<Cv{dPRqtsImE-rRoU!kOx
zcj)k8(2X*}>V6ASPEG=K%0caSXs7)3KHpg;2SH2e8JXEQW?eH0(GmqsnO&cz8@=rF
zzG)SYj1C+#YyqvEId1T+*UXIXZ*<O_CQ!8J^MKcA820oo?(KE{FDAWQ0lYHd@C^%A
z@SJx>^5YBto0i6G+^qqcnXLT$Y+?2HcUJxRx3}@muluF>=<#D;o0%1$%`8t(O-=0&
zUm3*eKhMVSq06(>+uL$Mi{(HI2pKwhdt0|}HxCL5y09`>y``<~l->HcbZ&7yP|Fu|
zBzAas_@C$Y{}~xTOQt|$p}kV3psQ9726s)IIkWT2my(b*5rLn#E?J_oCT6G5&6_u0
zTwDygj)TQdqi^fhe^0H;-`&x?lBT$R^08j&$LHo+gZdqy?A*}6aCTWfXm>*ve3?|i
zhX;<JW_oe;+gn>f?M~3x!}fbs+;4AhcaMmeadh5|<m~M3`1-%1_J2Mwo8{bK2oDce
zQCB~F_pWSw%|})?9*KYlOLktrd1q&_VfD8h&^4R4Z%bdicroMVrll`7p1HJqeqGm>
zFC|Bg9%Vdn|Lfh;r@29gNHjNt3~PAtBIC=8i_RaGtdGmfTX(U3#&i|V%F4?16-uAW
zUR+QF?Ox%Rx6}C$;W4QN)G3|iGw0%B_r<BFr-2R>U}9q8nWu7XiRa|&zX~5s&F(o2
z%9Eh3f($5n{T^;8<Vph7#1hB$L82B^i<_AtOMn`UU>#<C5Q!&Cmn~B=G7^G}IJQQu
zy#|{90nH^jUhXV@d&_jm^5v)H{QdnwQ+mD@6MwD<UoWSmtZZ2FBH+f28yT|I-`+?n
zDJuuAkF#~W+_^RRI3K8s?>Sj*hDoLnXz=6gMlMmU1wl)_emrcK*C}G$)!ohQH{Y(;
zwOdS4O^r=lKkiCR?THDBpmR69rt9feco~AGS-8dZ9{l+DnBh}={4CS#w(RTc7#Y&e
z&+EOryF5GhP_iaSuvgj~bh3qZfsV2=^Xjm*PP5H&S$x#){rUO%<G<hU7iV5xCiZjI
zB7So{jf}gyN*B2+C@F1{nDlFYeWW6|3AZ^pJss2^e*C!Ko{a%CN(bsPZO@l)_!C>Y
z+;?`{lP4*S!IO3dXoyTu;mqIvcUz$PXOBrOA3hWa`=r%@h7r%({pNXmte1Jhf5q^O
z42^U1Y`M+N%|S-JeEHI%=EsHyp7FM=PN1ud9-TG6Z&Gm|bV`t!nb=OyLf|udK=U)P
zyURegA1?@7t>`)F*^;Tx|4&mnsU$zUrG;h3&Yhid&0Ugae4=d9$1UDSLyF`l8w*!#
zxM2<+@`3aX4}<F7g@=+J2PA?^b5Ku_PuhKd?C!FI_wUPtvg%Bu)PQ|8KbgKyR5_`%
z{?pn34bXMY2M##QJq{Wz1GQ29{r#;r&u0%Pp}xAx%`0to<io?mrt6(SEw4*Uy$gSR
z$#ijbJ$V0q{D&pWp1*v_X>D!&=iBXk4^L0WrCw77ptG9?zP!A=vF2w{_uV}WC94A$
zvw<3R7cK-a9JsX9+c4<}2WVS8=voY`vNs)EqFSIs4?w$%l->Il#O^Np@bRM~WKF3-
z{ym#1n!#+KBYmBmn85k<eqHpJ6>864zU*AGMCHz&O5yxHAKB*2oy(o`NYxWOedH+I
z_4x7Q<}+t}K&zxd=Y|~Z5;a|aR8mrMMf`p{Dag6nU2<1b!q&xfHZ(9y(F}I`q5-Pu
zZJ}%aS4e<*C-3g=2JbvN0@{f$B(%sfFE_Whr-vu-@l4Q}NOLTU**rZxL1QfsU%b$$
zQc1j$WeQr<1nQ5lz0Y2${*~dUdPc~q5YOW3+uL$8Zg11QbN4PIgKgE914lZAU3=4u
zc9*|D_U`WP-d*cAhA*hNTl4X#IB1h)h?eLqv)ry(rrAl?*TsSshThp(T=?XK;1SRY
zlwgi|TVgC`&YbDt@9%!JOVqVrNd#OYi-T4s<#Q#0`hcM2kuqj{zn2-@u+Rs$(L|1b
z^1pIFxMOJMm$;!Y4m`@Q*#RDI*l(D8Y=PHQtsg(1&%e09k@@0d4skiTb(OVKRX7*B
z^<JvtuYdROaJz@Mw{t+igq7|l+@Q0+C#(B|ZZH9DzWV%YQP^tJ@E_Zb9DUAE@a;`x
z&F{C{8A|rQ3tJZ>>FMdYOz!lXxt7Ijf`Wn_Jw01a9Q}Fn<jI1vvTJwl?JCs<^$*M5
z-U1&e(!ODXf#c=Qt9vSob8c_rJ>157dC#*xDN`=+i8r~ow?#gARIE_Hc*?5K)r+#O
zt^$n}f~Nm=m%Y8Px4Qi7=VxzjZU&v&3@S1}=RJISa<XZ;$=ZX>?8#3~Oau)POz~3P
zRrZ!kT3Y&IvY?>g-f8dw;EaolSjF_?daO!cB|JYj_r$4Fpt0EXmUS;Lse)&Q0`@#T
zJw5r-63<z8cYv<<e*3m}$`p}`iV9F?^~L4o{SP#KmG$-gzi=FN1EoCqZ%dah1)Z@r
z!?JkUvkE^yzM`Tcm)`WCntKxI$NOYK2U=EreYLc5Z=i+<sAmTnzL2x6O1QEju%o9(
z#OCGd>-+2fJJt8Ac>ehJ`+fXDlV>l#yu94e*Vndnt0@x`6KKc+wC^5t4bRER>WmDa
zR`QjV!G;A791dRYItYsQ&rJ7M_Z;4L@!0cT(2yfIMZ7o;T0-@lbzit-d+*}j^U{xD
zY2so(XyEZ2cg=buK52L9`R2zGAHOJndP?-nJlolzx!I*&Q$Jjb&Szv;7rUEHU41#z
z`<sX%8H1W11%k=5TKnyOaU48&5VQ~c+18s!kFxsCGHKkp_36C4{PgtY<%<`BF8$Dt
zzt<u>bNy`de5a*Bpv&f-pPSpP;`!mr7ZKZOplvl*b9_L}CD20BKR-UsdaUX_?Z{+x
zf0thMn07wdf}fvKL1*-UcId{%$=$ho_u<QzoUKlZRW^xza<*DkESrz^a&z5+tfm63
z{REw;lX_}O<Np2jQ@oa@ZRS=|Qu=j&!=3vb;5~s|6G3BRpamQ4@^u^v_1E7$mlt~W
z?3t34mDF6TQX$Jl0ieTiFD!I^`20D$yu3V*w3$!w8mCsSjC*@5m6Vipo-L6xx>x;v
zZ~M>B&lmg5G`g`pU;fjlPY<3yUvByD`~CXtx2JrjOq;f>@~>{}E)xa?Tie*;J;}%W
z#EMNP*;aoO`SnU^T8ZhT`}O~2b8l}udU?4&BLk=(`0VWLi;La)Ei5b+RDXYW;^axt
z34EYq94xG?7P<G!H7z%@1-In1xW4g<vPwT^1@jKy0Bsgrp#k201X@@63*5?+ICcy)
zfdraE{qh@h4AJp^`EI$xIV@~!N(Kf33=f_@ZS|b2wy^g1x2EMr@z<_h%eb~ia+Ybf
zT9wFVP{SBB<P19csWI8p(-Sl?ZdLwHC&B15sA2r#MTU!u%YzFGodZ^11&!{8t&8D|
zkB<kn=e~3}nPgw%=@!=qZATIm76uj7CGYRW7XSJ5^t4$0)NId57nXPmgU%ZGq7mX#
z@R%w0?ygej?Rj@6Oq|&0JKM~0X;9+XS*D;SMZnr9Q;>@_G)_DcdnPO>xR(pM11W^(
z%BoOqP}Oz6{(tYL)YFHqUJWe<wG}`u(DwHB9gM8AO|!*7SBHVN3x9uq|GL#mc7|Cd
znN6+S;#{-(&fGjR)41^ECDlKm0pZ?WUhs_g&Yg@W?zdL{{q=R$+~iJ%1yNhGKx;c1
z{>1Lo4qer<|KBg~;;r*<Z_kfDb8;tm<#kgeH#fKQ)m5PzYk!x8tc#IsX5)2we{XN#
z{<_*DM~{LAG8w>YY%4!M`|)n~d!2VjQX6`cIY3*&YMosV9;*cJTmrS@Asfd)yT;&=
z3)-Uuja-?(hYlSwNIJs7!pfStH(qc<`TMww$}^@yXCFWd!Wc5lWIjO_;egih9y)aB
z!k)@v(C#}%M#c#$oP~vjH}==tgH9g2b0@}Uu2txl8ERAK&h1?ry&W`OX<h!VC2FnP
z@jmbl_D*5-N0<HWx9+$v{x9>{nVBFPK*cJ9gkchklvxf3!-><Uol8ng?p43Hov6%J
z{_>LQk>kgeO-)6!w(dGm=$-4ZHLCaP>+8wCzrEd2_t%O6bkNSeefwVA+`Qb?obNy{
zcge=>+uMUywgjy_(#*~e-IV~kGUMDFOV9{LQ**PRgv1Fm6(uDtC0IvY&1;Ir!p~1+
z+1c68wx68#>e5ng3B#n8Hy^n~wG>oUkG2SRe*LuW;IRoRoYC8IDqSzn*nVoNHfU6`
z;>QQYH*ek~BquMnoHl)Wdwl)ht4Zs0K&N+sZg76T=QAJZ_*{kmEnczpHRXkc2Rnt;
zx5(*xgN`!?-Gii}!oqL?bO`M%Q|_>^uoI_GAKp{>`N8AI$`xKl?CO4V4xE?>ZZ9(&
zcye;`#>&rW;PT^=5d$a}*Z==F!>)GMiojOz^5P80%up|=Fy@o&?oF2Y)>{W2)qM<W
z_bDbr8hrhr-W;UK-&c6U;@96_uh)aNslB?kwi`6}b@QfVSXfxp_lYW;4<9}Rjj8_q
z{hj$l{kc6gpnXC0cX3Wld=A>47Yo{v1gc(se0<FKL|=~$bO>(Z$w{iS&IaooJT70~
z<2&0-(bg7RU>$1Z{`jz6eo@WOPoVqf)%@mYRJm*pSneka>gUz}{VINHs&@OWt=ZXq
zOP4QCzP2W^;`!Wi7C#L?CnqM*u+ZUl{?{=Td{6fKM?PZu^5shjXb8TYPqu08THTnK
z7=|bR&&df2HoA6;CI0^QRwH)TmIt0kA0A`<WocyvItmeVJ6GPlJ)I{`c&rG~0!<}P
zR`+-F^Xq#d2wGMMAJ0)MDlXnw_BLv+b&b~4Q%v%+q9$!hJ^kolGyA6F=jYq^pPH&Y
zyFh89-+a5=D}C!DBO^hpA%EOWWPEYw;GJ{l&MjJZV^h`FtTl0aqdqS*oUng$K~<HN
zRoR=4RiUeyPS`)xR8nFBO|l$lWOnV<J_G8l-?$NxlAgXe<>aIpR;5~?;~h^<R%bq8
zuLwFZqiMN_wxS}Vp`l^a`_Q@8<=a*W^D`(I8V0^Tasa%IXwIBDTz9UYJPEpc*YIY}
zvo_Fz(Z#*J!4_|3*T6<=o<I_fytKPCc;N0QY?1rP<Htb5bM~;_-zP}Q$$xmLbyj`;
z?QOo#Yjsi?t9F;YRqzxtGB!?3PF}oI*L`i6^CXog&z{XH@cOK@UE<0m(~JuYzrVe8
z_VVHa-BPz_kIjzVyBB*+)mr3kyz}bnaL^%jpm~j`?RmOYGMm$~v%8o1&KCPoHPa{+
zlr<QIXSN?~W(OUO^yAy@e9%z;6#e+PFCJ;2R+UA~4+BuU?cw3}!`H5fF@Wm+qut_<
zL02|DIXT&|{9Vk!$+P6l^)&W;`BDPfWza8Y+Z45S+mHQ`pnXx&@bVutQ)Opo_v3ND
z{euS&KzrSp7?P5cHx@p216^VQ+K4sND3!%us||Ewz`B@Df4iSc4s7(Eu9tYUOBB?S
zYdCpiN7>t1_Z~+^MuG<8_x*e(%`k0q^UgWa=6Rq~wvK^TtxuWK0=gB!ceWX5&S83d
zU1z`jKZ#x`Qz6@D+S?Nkvw@QDyLazc`+8-q!?LG;ckh=={QK*xSY?nu=o0A#j?8D@
zetLRZSx=8IGc$9;rcF)F&CLg19+5Uq<2iKr@WkoUmwzp7b!rS;?Dp_>{(e!DnJ-sf
z&C(FzI{Wtd|7)d5{i^e0PQr!*Y`&f41}6pZ8u?>}J)mWhpdq`898l#CYRDZwR@n$@
z^Me-8n}Ihp=z~`oTzo%2H~HkZcXzoNHf-E@ahGq11n6voKY#v!4si%s5x^*_6>`C<
z?%$uvoLgH?CawGP_oVv#gulPOg2s5I%=3B{EKp!!VR><9f=)@3{l4_>~6>^t19
z(#|If8a4ynLV0oVjJdqhW(hAYECgMMymepPrW8-mEpwo&1xiY`xav7PKgN2j^5?4O
zpewPX*0wEQu5S1LPjUCXA5Ea;r$G|?K+9$X1v|xrgqnoa{Spo~v3mIV9XmN$z3|f$
zPZd>F(7h5Cb$=|JoSa<xHP3u`d3oZ*iH&W%(vMcJ-`Aw#2|8QrKqE6~er}3(IN!pB
z3l|+1(X+Oee)#ZVL3#OcP-X>n0p8!+EB4p%GpG&W)++@%0XQ!&uj0!K!J?uf1_n{B
zkOK#s*|(ORte-pAs+24D_BPX3`*fqX9f`01`?X75EAG@(?evf8UqFWm7e7De+An8Y
z@Z^NxlBG)(b#-~&`(!}P&}Zl7W*5q{*j0XF;g_?y@P{3ADaW;6x0>1cC(N6tR}lm%
z&>@-i*uIO$j{PjZVUZ&f3meRn05#r0#sBB`pe3-oHb95(L780|R0=%5pZNHK{np&u
zVV{kchOGwq*(CQ?$mi0X|2yK$GB2sju`2cY_T%N{<%X4?QiT0fuKoG>x$yZpSy1n5
zYxZ@wj0}yKn3xOOa--KoZ9SD_z9tLQ6g1E8TkbzU>+ZDQ?|&A0KY8(j!`<EeV)Bfo
zQ>KVqSsm{G?FVSB&Xg%4prvnovR0sTu#&#KxCpu`{m$LHrT@}9K{u~2^`5@SceWX*
zm;2-6W6;2#X7I8HpPrruZCbSZ`9v7pXk6jq;&OD_lCafR7qu&Zhj0FZu8e&DzW>9A
zg1N`-|9%MuT?<<N?vCNdlxL5>y}d1Ao+kr30aM+79s|RhH*Y@t`~ChgXerg!tg9^k
z8h&MEW}wAdk(<*%JB>goc$weatc&53E6!cNF8=)d{NteOb3BDWi`;kYusAC!qUJxZ
zXT=H)(8|*fOV-cp?d1hc!qxr#mAUWRo14a<ql-X`OQiGnEd2RvRp@Hap}Q&R>D>~c
zJEpI918pifJKH?^%~g-Mu;qTTpf#zp&GWBS-Z_7sA2gBP$}R3=GgE@Ab<qJ%wydpD
z&pp}C@1Hk&cJ``|XV}0yT|iqPA%j30L5n{?&4Xj0E*xmBfH|mG2W?K;wGp&jfCp3y
zfU5^^5;$IwBcrwE&6}JlTA^J3kKe0hcP-U_CtuI!%IGM-D6P??8^3#_v`GS!*0*`A
zr>|<XtzK}fs5f@8;jtTwj|oZZNlm#SAj+*KxX~rKm+j!B2!TKjCapt1|2{nLYqp!4
z`$e7D_sX+(BySeaseH!QxP8O(IXjD=Cmm|xT=ZOm)!5irLxjsD^AZcggsD?oUtV4g
z-VzwOdD*d_lT>Ct5$-;F=8S-t7-*05*B_vOOFJWxlAbPIF|!cV|K_*<!>}}{bH)q_
z(9!f?Q@-fM?#lQZQzb2HQNX|e>Q{X$bc~yu?**ziR;<tf?IwNp?AfB{5>sIZ=<F_E
zf9>&H>vFfGB&E9FZ_SzYh0kBTDk`k*2U?u!;%_MBwKVAKR&#ZAc0E147uVOzGchw?
zToY-0@pDH<$2~2vMeG8gMMi-KgMx!WvmSGgzrM0^ag|d0%2h#2xegsVG-3AaZqO9D
zzCQm{?eMmxOP9XLJOo<V3|c1)%1{6Q)mBtjC%?Y7_QR)7Lbhi!K#QzE`|{?@ojY;X
ztW|}3vaYV$QT)8GA+;?%KfnLUla#I3b#!$vu8lVDEta>bXaLO-WX%fPS@e`^&z?OK
zri1Tzeemn+Ybk%_lV{Ex*;V?QMc;JKZ1a326O)kVh4%LLZ|?8E-_U(zmR;?x7o4h0
z(#sQaWPEex{Mnd)Wn<x&!{DujeZ9d3-+JqASj@U%@iY1HisZ*H+Cl3}+-1Sa|86KW
z*;x4L__4s_$1d_qy9YP3@p6^!Q}MK@|My2aDtQiQin>cwdl6_W#&U_N;o|H6UfzDc
zZuQrg;9U%VpU<y9)^GoB#jlF%>tc6QeqMI0GBY!igP-4hZ`D_x9p`r3xN$>4L4kph
zkr7mVURxWzFht8R?~X-}yuIAktgA+y-Kqa;6?baJMXXz2_4O6#_DN6)0&0evo13o{
zUsV3~R_Fn%jiAlepfN1>emT(TL|Io?u`=u^dn*O%%e;7zp%b;m<AaxBQ&SUY+XV|d
z`{!e<|Kk%96i!XiYz9r{8W;$G<|Y5{S5#7}a;|`!n-s_yu-J_kw4~tR!Glr#@9*uE
zo;PnETU@HlrcIjyHmCW5Hr{{^j@`M_5_Gu5d7)P?FE0n}joJ6>l{RQchMk?=jcvKo
z_s=YLjf<1Z$;l}J9WiJ)Gyafy-W`eRZ*MNX?)zT-?TzDNw_ctNr+$Fe6!7u!W%(=r
zRIjhE&$+$L_kz{Nn3$MPwVTiV{QUgkn>RTJT$4Wbp8k~x+Mamv$gzw3zujb|-R(iU
zv@BlTuwYHT|D?ZnacA#hd9yw%v%Wg;p6M$a3%QORJ1H;iE(}&%nj-^>T1zV{r%5Uo
zjeG7rIM@uj2&U%KNp+3TRa0JA9=f}u(D@6?;?f@<63@)B6h3g8`@OP~l7OJ#!n)U+
zoMCGLzTS!2ng!|%w9QH10y>Q;>xu^Gbgs_MP7ZGF%R3G>uAGo6X=!O`wf~w;{Xdy$
z)26BY+`2n_ecUShemUEyw=+~cC!|VFQc*NFzkcCz3pX$C(Y@8*K~sIn-{0NMI)3KN
z8PJJJEiEk^QR-s(F$*$JPt$#IZEf_v|MQfTlonlYhR&!@1>JipVOgYNRr(4v)4BTY
z!{V2hmV%ZBe0qACb-f5^O~?89_U%)rPJN;2wz%r+E6{3n(2(#{?eJCi&P=|4*<D6f
zme=(B3Q%zs7#J9J-{kwFque=ncZupoZxh*Y<^vNmvth-D1kmy!(5b|g_dv_WckHlO
z6Tkmn!|NXQ`EHA%=iAkS*2(SIy*v5Jia?FvWjqWD#>T>@r|TcTwKdzcuF<Q0cj05U
zRpIOPs@e`h3iG7LFWPGt_kklVFK5mp!=uL%vBhIod+*_6Kh4eh)W9+O>W0Oy#K#$3
zy}hEg3td1X+@SS}yGmateRy!NpuD_&>(;HuDna8)8_s=L6}nojs_CMXd7g}0j|5}n
zw7{K3si3`CQuD<psVwxFX|$@|`@-q&b-_VF4_>_B@b~xknQwPDCBIBmNT_MX42hV%
zRiUpxy7fvebZ+O1*io>saeAk?u&{DfQ{Zg#d^sm4C(tw-Xs_0R)9bJA+qZ8;%+5^@
zN*{eV#ySghaLHWI;-10}4;=68F6RfW+?_vvKI3%I2yCrN<h0a_%AjS{9V-$*>x%bO
zf>uf`{<drBQdKqISt*<LZ((QvZRUS=cD6;uhXpS*-432P<MTDW_Ptn+mwm&(<u6`j
zfR^VSZs&LZ|L^a^w{LrOqql)}z=Ia-`P=_(Io!?<I$L|u@_mJybQUKc?*r{=1`TEi
z2sBiEeRc5KH8KBrHV2n_PX`qepyT?R`Rxw;`}^DXQ{I(r+qQvLls7duPn<Q2D?L43
z#;SzF&d!dZ0aVu=Y-0Vnuk&5*)TvWj^<sBDcyV#@h7B76{(gG@?(Xi2kB?aQ?A^OD
z{k+`0+8^<HF*_P6KR*NYUMv3n+4;iKX#=P}2ba7^NnnxTS7;J|qzZUe?rQ5jeC#B@
zv^yl%Lvr$p75{#2jT8^wUD3-mZN`j_E>Z1IPQ|t=>gtP&o}TLH><p~+H48P(y3*jZ
z@W7hL&0FN=8z!?&@lpk?%w^VB)|$yDZ@1=p<=fla>koVPxP#V!<=klKl{P<g@}%e2
zUoS5&zqr&}e94j}EA-CPzu)_PL;e4{wdVH}m6R4WeT44O5PI_Pa62f!y}iAianGK^
z&)MZ`7JPFy2`+hbgp)_wjAyELxLZKLgmc!V|L_0*JHMf{&Aj;88K=4bA06dBGtc%n
z?^?q;(8lSE42?^dFNfM!OiPtaJw5H{sj1qZ_a?u({S34})V9jx+S=&$J$r1nCU4R?
zeCLjga~sdWM@PGTzqNnLy}hk<?p)bLix!#OyYl(bQEpI9Ubk-DjqUmKU#vXz=GIp3
zix)3ul`npGWu@@0l9x$E`7FC@ej0&hgN__=0rduIe|>T6m$PMH0Ilu;Z6SJafH5K}
z%4uQ1gWd1<3Ga!JG3zVKkpYD}xFY2`c1%-3`guO6M9nXORH6O7i$N8uncu-17WGI~
zs(U?1<D90Ag<mF5oY)w>JrA@b{K7Z0%;23H58KOHm-(#!d~0j=_qOR0?Gq+UaGI+R
zK0@wO+qDa~6+jn^XoUvt*6dihY1_7An^I4I_;_4C+jd{s+bGb<*V@{r51c+R!=~cH
z0+0IhM~^-=)n7PiMfLZ0pn)yWiBemyXJ22}d*p}<sCosRP8Jd(0@{Z&(>Oip)s>Y^
z*MtNGr{?SdZ7=EQ=<u?soxdnStNfK+#Rr9&+S;#H-*0YCe{p-ee%aewU)#bZx1TxV
z13F1TQIWB-vhu^1FD>)u%fET^#>HRw(Rus-E+r)<pyi#Qg^^`tWuO5&tFkv7=H})X
zKes%(?BNmr@#Du2A3q+vyxc!@z2~GB(4{0tyTw80U%h$rMnFWQ<-&yk&=lH(D5EfN
zz#U4wpOFNr_!Mh57QQG=0JT>{_`sE#xf$Qf?q28h%%F?`TC+3@T=9LHK5JIjL}mA+
z<9)JG`=9OGb+LJ6jjh_<GiT0(nE$=du33L?P4sp?(1MMiph?$eTX{@sNk2c2Gb-KY
z2g{fJp{qhTnb~*_{Q3ELtDL-joek*xyeCgmnDvcq;^X5zCbiW5{&w)rotX7*(^NRw
z`D6?ZSZ$1}mDSS;{u|}<>dxJ}pnG;Ki=VBC>+bJ&e|>GOpomBdsJ@ANe`TdGXsO%h
z=jXd;c)7TQJVNB78yk~5y1Ig@r8@WT-+%H>W7PD})nPBcGQV7~K!JIU;Q3?6*sROn
z>3o<DDzO}|uZt~wbHi}*pNBPNWoByr^LX;}^Fb@9zQ`;t`}!&rG#Y<zZ#5_a*!bmo
zHl?2Kny1P$-)+%5&|aIJMXI1RDxaR7UYvh_--~N&XTOL%RQl=)=f{s9Ir#b8r%x9L
z$^ZZJ+#b}T+O&DIVbzxm(0PyFzI|J?T#6N%9p*G`%;#zcC45jlCM)e;4?gVz+$4Dn
ziX>T3%(z>d_5B0K45Ue-DFbe$<bmcB=h;>Z2njLi>+6HoU%jqe_HXa&Q&Y9G?w|kv
z{{KJ!4@!qOZ`;<U;`!pvPGb=+)<1v$CT3=8R!zJ3^Zx&T?d$jb;`;jf`tj=bdzXLS
zzw+j0P#5CkL*Wbm%_=@5{P}R0zoWa``R=aLt9`M%N;ua>Z+H9t?k=d&<H*hXeDC*r
z%_^RtUZ;+ZPKdntljZa4j1E|B{P#CsBXSyOeY}dA+M@XVb)Zd34bx>o7pZ{G7UJOI
zI@BSk?BZ)Cac{?h1T!-;&{$C$pX{ot+-GNIf-X!+N=|<G^y$*7+LxD>{&=(b{D&te
zg$08<K^ZI#a$s5r6R2qfTANt*?ha?<w1*EKFfe#{dpE0if)>3TI(*po)%3*e`S;s4
zZ#G`DcCD+wq1D;h=Es+MPZyAs?BtWR%CJ>8H5HY$DmehVOyJFpjcjq5GN1;os`s=9
zkNfS#Y+ZMNW-mdFqV8_c0?Aij_f~&jRQ~?niIXP-@1DGK_%QRwj~}z1&zyDUj1Oo<
z?)CNY<}a5|oMT@vw>E0)r3$Mnpam8$m(S;lQH%Te>8YTM%$jd$-JmHH&}`L>jme-r
zB8{(m*r9o{ukMEVs~Z-rhmTcug1QyU6W&O_1xNpv!=OHeri|G+Z*bF<HTiJ{c<C~v
z-3nT|vSstut*!+H8_q3%H)|JY&)J(B8$q3jTd%LK4nKaVmHXn>>~O=wETH53Q&K?N
z9Q$M}nXIj?zr4E2&DF{TI&|Z?B<L_S(1z&S+w;Y3kG^>N<O%4a+KhX9cAn$@>I=Fq
zv=OxS>*M3&FYfN%{z~Z!XbkXppDbt<fZsfu&aA7eIODvIrTqKzGh%O*DQKxTm#EeX
zS<ogz(9{NKYT)tle(^0A3Mw8qHHEGWVog5Y7y5hVHPAK?(B`Gg%*?F+e)0S3Y~6aL
zj)M2KcX_FS$1xUvznMP&<Rq1okB|3He}8}f`YKyX%gA{KiA_45lWbB?i8ONao<DQO
z=ia8&?iZ47nzpvFdH440%t=jEeSdqq|KlI?>;Gx)|9sARQ)_GMp1QwPhxtvE;^N|p
zGBQ@YkaT-^nBRVib;*kb-=h5d`rbTxq;&hnjT6#lITQ3_cd69>d^#PZ&!*~2hNJh%
z8K4zP+qQ3?{{78O<@B_)Q_s)OpDt~lr(<nlapL@ZdvRNT4P#^D%FD}qv(~GstDl~v
zauT$DI!sa?+#byX*ML{R2OfgY*gCfFVjn2dL7kIQ$f<{UIiSjKOERbo2lXdqrQ74!
z)6>&`&d%Q_XnR=0)z$UnvuDpXwYRt1<lnQYyuL2>)4JH*Pbxn@J1Hk8w`u3joiehr
zx>d^rzQ4aeU0gp-$2|XD%rq6xbul|P*`%G3`1$4K<weUm)3dX+>wmx9z9?N{?wK<_
zH;*25jRWn5*K~XR?d|QN`}=BBrKP1KC#ghEQn`8TnA^MS>*v>ee&&1ebI-L-Vf82a
z`~L)e;Za-_wpOeD>(y|p{`2$g<JU!PUBxIq(eU%vuTy86=j%Ox_UzOqozvgn-JQI4
z&6<?>`1s!9<vuf&uCIx_d_lOgqvM{G*dqM~bx=$%YSNtQ#Uo|n@mTM!o}M1)eAJ0^
z=JcGMZNA!e?&Dnb|NnR2p1ce+194%Y^M|irUC+<61x*?L`2CxiK}bmG!^3uYB}+?5
zK|#S6_xA37ur*0HZjZ!Vt5T=ERbLG%J|sj$%y?%%d40^zro_W-EBBUtc@el|$&v?~
z&)Xed;MmN-Q2P4X(Vw56Z_K}M2kH$U30Vx9P=&TYqV~&yMhFjR9sd1vdc1&)OwYNw
z*31l`6@aeYVh4{OX9rEOFLvu?(HC)_mO5kh?A3d}y-L>B))t)HBSe+F&dtMf1hkvv
z!Gna0!9C~R+}sRWhyt2t)(BqK^Xlum*xgA_PE4$LzxTUA@iU*27Z)5Kco}MitY`oo
zOx)I{WN0WDy)CCPXyuVfs@|YowF#gRD0QyKZ{POD*Zp+;!m~IzIhi?f+SPd*ykFh9
za|g7}cu&Pgrt<gqSQ$dr#oT;Sy<DN4U;fyZ%*#HXUi*1@am}-@U-$XP=jZ1qPMVZ-
zz*W_~rpBi3&qw#kzxK>D$rP%oskyMol^b-(13SOmk<ZW1gQ~{f;_vV7c9-9;4L{(e
zq_k)|Gxt1D$7Tf!XsS4BOUA;_pnbm^N?(UD>nSCtr>D2im>~gLIv2h^?#8}a>zLSB
z(4o$6-sFH5Tpd5|{>A4Z8^0Wnv9U2|Ly?LKOX#YQi$7Qwf=6NYENE?;JZl!0xw-k)
z>wNNdJf4#-EOzJLdj0m6%;pm(Je<!NORZeF64Ws+dvgPHOALel{S*z)Nw?<5%U0jM
zyR(@6{hrT#x3b^w`OKFR=@u0=YeDF-<oo+-chvvi_v-PQH98)XS~@y7Knu6Bo_kGd
zF-$%tQMIT5bebusfeR|%e<gxiVo&;eC)<NpAAm-hKn>&#g;&6%M<?Y$^Vz+@2H?uR
z?uNzB*LQcD_sLqf@yS|&Zip)=F220uA`b&--v5BrMo=GVXYun@u{Hm^W*Vh}(l=;d
zAk#F->07p#ELjdZsJ>ZTf*G{(pr*DKbiyu=yqydmAKxN%$=-Rk)k;Q2lg#&MG_<y|
zf|5wkQm>W!!UZ!gZ^;Y>P5;F1E_2;m_4P_$?4Ali?`b-Yo72v+tToPCR`Iy$`~7<G
zfh|3f#v8J(YVFv$^Wp6LeU8WbWUrpHE_%WNT8;hj@p0}bFBg}PPw+O|fvZ<VH*VYr
znrgoG_;{ae^Xk>B8^b$~$NM}vf9;wWJHMPuJD==@-R1cak&y>4T@rHdlL74<c0F&*
z)z{aj5x>tS>-sv~s;&Z2t&o7~W>p4I+TXBoqvPQ=-m7u?p{qo^rfQ|0sB}vPUHG;+
zo!`mH3A9e5=;^7>c`6}sar4eCcYgZxY3GcTkSSiOQ@oZQdwsv|_u6CG%YGb7ZRlOh
zEv;UUH2N2K95f!J4r!(ROn&?X+-ZT<zW>0ZfiJ*AM(W^B3uwIP)AxJT?^phl5f)xt
zcxQ_Kh3%U*9a`+(Um{ok<%QsyHEVcwoT&Ko@ArGqfs6e7?oLji<8Yh(?S8UwwKB=c
z$t`*=8M3qJsmZTrKR-VQtrAu9oy8Iz9o<_W?lGz5%9Rl3b0%D%{bd0G0-(zTK+}MC
z@5a97<(4wZP)L|t0U9aal6kq{%ZtF2w6sSL4mN}O4~N_NKi>cUPkgakZ_w{qzFTr`
z8dX$RgElXL2KKYAt>I+w@bEaWG5L7Fwwy@Ng~cDdjMPA<`ttCE?3TQ||L2b%3hL^|
z51a-K_v%6WKPy;3M-eUapU=n6&JMaP3)Fj7@dTOl=x8@+b@oi-^safC1&iJLk3Bg#
z`Kwj<Bo!4kwS5m=k3D>Ib90vb`I*M-p!=Pg+4(`ICeN5TGjmRIS9t|{!;Kpe7lnJ=
zE-&*1O-O>q%gV~icGUbd@|$bbns;~C!9z}ekF$rbk2Ae#E-YtLA&`8m=ir~8pI!Y8
zrE09El$qz<5wKn8k^pWpfyM{E^+Lu6X5Fy31sdwxcd@s3G4cR`$;QGh$&W>P!1b{;
z(%{jP{J+1xE>f4!m6w+XWer)Y5{K1cYp?XpwW$>Hp03xre*O9drEQ?o$y?gnm2GTf
zKx?#Cuh#zc{XKuHQ=?n2ROdYPp8fmn^EWJ3*Vor)I51T^d`q3b`BUk*IaZ}y@Av<=
zn=@z5g}v3~Ev>C9`z$RjAD)|Q9kDe_RNq0}6tvQ`m0R2({hW-8yZh>YyNim84}W-g
z*f8^w3TO$etf$+{`}en}M7nu-ammQan*Nh@ba8QMRX@2&r&|uhbaDB4`s~@G7Zy5$
z8uK2LSd5L08T99SDV;U~EhjF0eQjl&Icr*4TE>+Xf~!JSF8Y4|=H~SC(lIGEXU?42
z@-IR3!awHl;J>ZnD?vvg&N9trV`pc-vNl>AG?Be&)24z)M>s)8!(=_Ls;WA4{5X5|
zwKalU!eqq7#X<KPA3S()(Q=8_Lv{BbUYGs_8Jo+4G<WK5fQDp4WMGY6&{`cxSs75c
z0TdxGAPccxwD&r@mOehlyCv%?m!_s>#=Sk3S=ZO`GJtwqesir@#l^)z3*FwmdzaKM
z)v<G@<(f5XKnv?NM7Xx(-rjbAd%dizEbo>+ucocp*I$)x{C8oYGw+6DJGSKCm*bbS
zIdF2a`oyVILB_zxtw4K&KR-LGR$RR7&<x{rzGc3%kD0Z-tGAz^R(EfOx1XQe(^FFg
zg@qUY+T{#BEBN+K@GQtwhG);7-Pn-Ge5_Bld<kJNs&-89+<1Kr5elrA!3&1b|Kg
za$FeDF)y*CBK-TIlV{JmMnp&~TC}L(^)+1v{r|UL-Pvi(#Ke@4m#0^;F!9RzczO3e
znS-Fc5mTnLfNnFmv!hTd|3znSZ)<Na@2@W}l`~dGG&VMZR(<_gHt&DGfBT|GNwCy!
z|LyGk8=!&E70HhS3O9fTVL)98dFY@Fs190T0q%5w8lL^VpFt;v-mnM>0d*r<xy3<^
z1qCZBsoUFfnLm8W_RGl7`1gJP|AR-5x_<CFJTX=B=FOX+9a1SNOXBL=#lKy&ul@7!
z_#$<QwUgETlg`bt1eMZdW!sJwhKGlPwjmubGCbBNyZZai<$iOkn!UZm;wt=(9(=w<
zNKkOET@4fXQU<}P9%*T59NgTGXIHI=xODk4sLsE<+#j^TMNUqRA#R`K=k@#lIemV1
zw(!9L#wohdVIP8w#0m=wLD%(yM%rtB6ztf!Gqd({_+&L-mNm-BLPA18D?Y1w9-5@;
zeeZ&lmgfzNkeD~pT3lv)prH}hqsJCLN_q@h^yd+uBcr8d#wRKcsh2l^PJ=t%Cu>pt
zO$W5KYWno$WigXf)<kdjyI^G`W}JRb=ga+>cD28xBa-e+@k-ryT-CE_>QvE~*jUhn
zazs>=REDIaadma|nOUaX3l}c*@bzuoym|92;S1?!XSJrDo~Ed(>iQw*uz|6$_7%{)
z-y2^2Ns}gRNIcA@qN)lS1d|dM^q$nRVugm|Yo65`%=JLW7M-lS_eXj@sE_=m3SQAZ
zxwO<9w5l@i-X6{ePi0qGm%M2B_4RePtQy1pE6(c=pO~op@$L5eNhc?%f=<zXHGQF_
zr6uTC2PY>d(E2#g;Sr#a{Qu|Zf^EBXPjAY(w4Z0m{+TmpI!;pA`+il<tNG?RbM|j6
zT(RSZIq1;#OXA?M3{Ve7&kVHuuKml=V;AK?qZ#d8-MyeidMEF%jouErvtzb-{-J{h
z8DGA9Sx{2q5)~y?R9yV<$rDf|r=qIbInOIZX-`(F!{^LR|7&6=saRN8Bz$^uvUOL+
zrX`^56lL%3%zV$Q4_a&J`1;7t4~O|d*Gb*D5z)(iVe{tAphbhA`_3j#oVaMYluO_~
z_3Yg{&)m+ty)Bo6ho?ow6LiGZ&Z4JV=9ND>!pW>J+-$C=vFpi`6wn~r+hgJ`E-oP@
z@anDN+Z##Hj9BI8v=f`w{9;Uwi<49F1RY&`ZCz}4&{8kXxGamBVE(;)pskSa@9izM
zTdSs`!g70i{_(rJ%X#<o^jtmGEB)0f|H1;t{EE)P2bUL?ppVd09<SF0PcA}JVxN^+
zAGi~kzXg<8A)Uon;LOQ&?AXP=Ugx7n!D~~Wtk1u{540X=(c;AqA3kIh7Z(Q=UAecm
z9K5vD8??m$#5K*nCSv=wSK26rL&fvZtE;OM^YZ!>o!ee~{jQ^<^We#omTzxwFRuOl
zEx%%^1!#X^10(Z=4T;VdgL`i6EPif~azX%fzKMl}glX0l1_l)sm4u^Rq9;zAIPmCb
zH>iX5^z`({%jee}>Jrr!5D`(S_&K}$_qSY7vD(?$xnc9>!;{th6Y}%>zkDe<v5Cjs
z-TlUm8xOv{y}f9;)SZuyk3W3;m>G0&=9i1^pn2tKy3uT)OfuhIo|BUkG#>T%Sg)(U
zs&dfgG~XMyZYgPLae+^Zaksd)W5J7}q9V|O5tICTG0%H>IyyQ$>fx~`VOwPaTEg()
zK?11#FmK+x2`Ze|*T)|Rg-+2^ua=gUgpZGoE?O>i29!46yy20SmcAIgf@SljO`s!r
zKtnfQe{_jz8<f3?u&MoZ<-q9<FE%?_ukAfOJT7i-PAfwmotUV+Ve@9^^>KR_1ZX^X
z`&PGV-o=E+8A*==3OD9=bb+>@OG8I=LSk}c7Ci#@>op~$-L1{QWy_1N#YIJj)aTbU
z-Q1l1_~K&sf}$cPAD^CAPOlW5+Y~G<B|!rS)Av=rd-o1>WBS(Y>j{~eoaN=^SA|!9
zo;-VY_mwLlHnqP*Kyx@pI)!;RT>B9BwQ#OgDd=`Y&=T`^@7^s+mz=xMx&2YU{Xfup
z9Mis&n|SQ)?L*c^iDqA42by@jwIvg@&NyaAf#ZRw!>{h|x95|wXjrjA<I1W~@6yBF
zpo`=_J~|2--r<wAV)6I)zZl#KS_%tVfdZP(VhH&!S6W<rc$R7QgV(RMD-<QAv$L~7
zJCChy&+wSNW{pnB`Z!r(HJ<~^=htaf@d*lEjP8WbOZxfwefa+UdZqbiMrJlpMZ+&|
zXY#@5@x<A)yFtgZYHD)!%iCY85T2{zIm4=S)q>KLHLtF&W)BY!e{+9-{OgZ=vQ`g3
zzI%FlI`5vI6)6ucFZ?oj&YYgL(c3}M^yTGc(1}{VzP@H}b!uGZJG*P1x(ImsUQ6d2
zZ{SDBWPe}nVtF$@Q8DTE6+ghWC8&<%2j4*9{N>lp8#h3Q$w^q1XvFQQXuP!4TUkko
z34Ey4n#j#;kB{{_S5@tLu=Lp5qut`5HI{ucmWy^(e90~T`>Pama8>m7yrWyQuPb;8
zMQzP$J#fI`%gf8`Pft%5x4o!gVP*B`^LhL8-_taMm;1S9Woa>h7tl@744yD|ZtjVh
zP8ODyiAOpF!7IY<eMtK7;Gl=E@6ma-)hzm=>iYWp>i+XUhn`NHKAqj)-+xQaO(8Kc
zu|>-zea_A@{krStaeL26E!o%C?Oo`4Y<1-3G|*8_J(9*Q{tJbU9X-lwoOb5HS<r1L
z_XIAl1RcGgv`7eaL#A%@wkwr;N?%`7`^(*JoPKTr=;-{<=j}`F_O|A~Qp{~?ZZ<4>
z;sI*dfUX2v8?}{z;rhDR!<UwN3knN2KRrF2JI+&ySJH@Ol1k#&S62<p&5ut|bmsbF
zJxK+0=Pg@=`n_g${t*B6SC^Ob&*xj}+{z^?ASKmx;X;6lnp)E7X}X}>A~vOP?)&kG
z+h>M>;}@4iaL+3sa6`U_JgBz@UZ~Mm8*BirdJckmZJ-ggx1hOxNNp~kGw0CCsI6L{
z4M+^2KJTiKl}$f>R9t0!5xy>_aq85mCpuM|T3cD|e!W<{{oA8rh82N}*+6HLgO0X&
zb8|E3#x2m!KhTX2CMF_vb#)vZ91hpl#U|$F>Q=2Y*tv73hlj_7%0J)l*B|c|*AJ18
zj*OgnrapOn_NCeF3=9eko-U3d^LBAFl$DiDP~oiq`*r%Oir3fHf-YwY{M^$tbEYIH
zS%j^P>YS(K(=DcJqUT^={!V6H%+98$tyv4p-riz}`*#2R{{MZuN?$JuT<oT_jO+W=
z@OaRPnBLR%KpU-G&kJ^$>uJn^cJIO2Yp)`_K>YCe^WjEj_75l3=V#dNtN&m3<JT{#
zim4wt`1st)%FI9`>-zfo78VvA^ITM23JMHB>(44bKYMtfkvZ$Qj;^j@?k$tK|L;!B
zv?zMQapugK3Dc*u7Z(@HSQafg5dTT!+jIxjnRDlYZVqd4Y-U?&E1Pw9S80va6wta&
z&~7X@H@1{WvzO*;7;@$`Z2({UvV`Bv@81oJ*5k*1O8;J#0PYm<y=?BCY;WfGaAV;=
z@YEsb*e>T^36Dkk`uq9I-rfSOkz%g+$?`~l-w&pKd3(3GI62UP9F5HETyc>`KYsn1
zb>{nbHQ!kaJSVGx&ZbOCPF@(I1v(ITZ}s;>*RF|yPOflpVEFUrkBh(Qj&pOZAA?3P
z-rm{@+AsoI1jg{;&(C7eyq9*^8i)CIwIR>v+f)k8n>TOKGpQ-FXG_1kvy=J3)9-Ij
zP1OcnziC_bh2g`erljDV694b_$=mmV4uv)}6a*d0vU#&}uaxP7=g-rN#22@>wyvz*
zQ~f;;bVbC)ix;KhgBLAcyf8q+p!{8ov!98ScG#MR#fz0e*A^Y?m0p~6b(Mj+dAPOv
zBo**l7pKDyd%3yN4>T}>wz&WP_SO*8$lbj=`>&*5GaE0<8f7IVt)D89*LA}?L1Stj
zGu->-R@Tm$G^uG{?e9aEFAIZirwLr_#>?Q~<irG8vJ1L+>h`wW;J*bIuS7&fCZ3yP
z`QyuFe^>v7La!bkZnr3TG2s>8yQ`~04})%#P*+z!c)G)DS-qXCmZIXpCG+`M_w4z+
zKWL>(MTLcskPv7gyM_pth6q<hMMcNF^Z@V~7@$r^N1Q!qaO<4+o7smzEt?I6aFLuj
za1qenkjGzMUItBJftF5z+TBl1OavXleCF)gi#v<cLB|S!&%zG{-75{cA~gN{JlCo!
zt1Ww5ZOqNX4;Ve3Jb7~Six(N7ZPDy}G7U3l&b&2wpD(Cb1+70fPCs|x)G4meRUwQF
zcXk$o4sJWT`~AM|7cVj_EG-|tyu2KgBYuB-D<~kKQ1Ns2_mk@LAAEUv*`oLv4@1JK
zDVm^l4xrOH_Uy4)6Te>$)a`n=`#p=k>6|A|Qog*uFK_?v$Kq@2^(U!-&OHPznJp_5
z+Yqp)jaPb6_Vsn3%k8f{o~-T<S|45b?@uMOzVP~_qg_>ZQ=Y%OyPGX4#RhaOcq21A
z==^D`{20(>A)wjH3r-tBv$FNqzFDfAHd66SdMqF)C@KhU|GT)Pw9J_^$D~d|?X(f-
zrrOxuWtn^UK%?5GC*#W)8&<DgeJwsl;N|I)CprKA{w{9Ye2*!7UChDt`~Pu)HiUHr
z)L30PZ61ql3?uPU`MfmH6lHr?bFK4wVd>|pW_;4_(%*a^ZY%`#9KTp?ER0KfyrFPQ
z;$smx>GrPXUg!0bSDO1>T@?ztAL;7xu&^*t7Xx&cX~EP&P;`R!GJuM*`v3nTb{46M
zaIvOD9$Oc?8?<f=wBhNC&tgy}1l{TEwNz;1#*GXOT%uYXvZ@}Sc{O?Y{<pWcKR(dN
zylVDR(Ck%RT^)FO>X5y*w)W&*H>w^T>9nZ)q%zO8x(#$^(5ELSe|$b~FDNF)R$N^C
z<?U_pZZTaU+sg@Ydny>~>+9!Om-B%pvKttgLF>71+`9GX<YaZwsjHwF?F}0YO5WX(
zEG#UP^51U8y8r*b>V4*tMP+5j-tYgPcfj@7<9~mDgF3t`gO?{=SrI5DKA+hEv~)&B
zrbjb)*^D==FII=I*Zc4cbS8R83ABqlQE--FvfIQu4YS%`U(7cg`>{51GaI*<&ViSg
zm-~M6d%DEF)v0l!vODM&I)=D?mhbxQ|2Z7(5)E7xqIvN3iY2olqY`P8%FjN%yzt7*
z*|QIyI>j~Ds<g>zp~LNMx!iy5y?gN@V?pVo4TW5w<4BV3UzmODSmNV7hmKu5vQN_n
z((lce0-c)11)8N;{^5qj5`8niy_w7ISWMZ!%y;&oOP7S~|Nk+Tv#;ZUb}{Vi>_Dg3
zfi|W7{QNxm!GXp_%efR!8-WJbmj-o$?k0Qr@+GKY+%IP<AR)maFE77UeT~q>T^lwS
z@W@yQfNnHk<Ck0Wc@JoJ(~AoWIk>rvPtIO?Wpz0Jv}w~oE7Nmwa<25Hrlo-vKc6^x
z^5E0c(^+*@l2dYXdn-RbQ#3INdHoS|THB>1o+r+oGy7nqq@-lTiX5(OFE~}b+}zl5
za&tlD9VlPs<>g70pPZ_~nS88AaLa_Alh@WpgNl@^($%0-CSF}#t*oZTW@l&DbX{<&
zPL0)+yiGcwTk9uIoY>LRbLI8>8HZ*c1W(o~)^5!2h|>pk)nt6Z1=@stH!NJ%i-Ye-
zPy<(9pfQ9+*Rvs)f`RT?n>kZ5?d+`32lpqca0V~;Gd*DSxajFAQP93-19S8C)}yDl
z_dkE~gn<FHDndr4M}PmHOHcG1>`PyXOz~0$H9tV-EgU+;1ZsZp@VJ1QAE~LTRZ3F@
zX3m_sVcRydo6@2=_xH)_MsGXw{ZTQ)kMs5any;=7S5{Iwq@wRI-?CT@bg~g>+3)|K
z=j%a>H^J2aXo-t;`MZSM+j5)2yT1SVSq!?Y@x<xVmo1(>dZd&vF#>eW=7vP(HeTsv
zUyrd$o8=gsl;#o=6r7m&0kXD9N$caWUg_n(K7V?8dh5Ky=3fKqQX<7{8&|ljirTvB
z)ysh3Wj=w`R#z6g_iy<(cl+O$0qbXcx;*d2*F^A$R7V$hBD6h@-HcC^UAle63viDY
zw1NdR5ZKX`cdQ3=Sc|Z_pUcXirC)Y+cCCzS$V*Oc4qEC3z635{S4k#lXsL9MQ!5wf
z2G<ppZ05PQOhDzCrY7emoyDcEuYtA|{rdVk-AHzg@7Y<ViD_wVr>E;5K6Hr5H2Ye}
z-`$Slo|6jR-ZEv@HPL&1Zth{wspQhq-OK&wBMqg47N}gf5CFQ4_=`_7=;9nut6}fC
zw>LH_@B963xA~qE7GGao<*xqr=HQV|Vbi=>LF?meL6y;5t5TsYe&9s^@KEcIx7+WR
zn0>lk=WLM+ni#jO{>Ecn{_e=l&FK^8&0AOanaOj~hqv4Bb47vfD&2$_-}&+J@y~w~
z&WO}|avfMw$LZyg;`5_K<L-}RPeI2`9Y3b1B-9KZ#)eE?xVR*N7tp-`cSqYhJbLQu
z?Js>>5>mCY?Cq@`MNhk4J$CDrO8ornEC&zIk#2GQ1tD6XQoE6x_x0!V_U?17N)58F
z>9DY{9JqTo_KV75(43yfq$Rsv{JDC3iKd;M+`W7EK-=j+MS8Ea`6|#5wxX&k>*}zz
zMl-oD$lKL`7B%fXS6W(n^l&@>{SQiyuWn3sFL`rAu>Rjq^}M^gSQ%D?t(A(2jb+sr
ze!ctszQdqhbD)W)y;WZit%=+Wx-dQ>DoRO5hX*v)5)d%q#Z0FU$5?-Y?kEJ!gd92I
za^vRBhbJeiZ`i)wy{gJ8C9-Yt;>E`%Kkh^s6##8c`SbU0;j1f}CpPhTP6{diS@ShL
zxGvd$Yt~g4e+4BY&zj<Od8i{HQlN<;86_n{aH8Zowog++y1m1L2bBFm)Ad}(jwvcB
zC0}3c&JSvxaEs|Uyu7p&v|Xg+^)+5TKE4SmoHJ+6RQu}kD8B9|Yp=AqnC;;gEv>Cj
ze;fYIy|ly=w6XosWAOG4UTL!xvibM-?Y-stGJp4)HK5BDqShCCPuJ^x^X85Do)bTI
z?%Fl$kL&aQTQV*xfyP-34Gk-Pd{9g~JFE5G-Q9<eA7=+0N(wq6A^rTk&Uu<V`7sM_
zw{Qx7`0&vA&!5ldL6*hD#B8YjT?QIW2i>9f>gwvk7Z(&S8iN+y=)f1<fL6hY>%}w#
zt#s)Y(|z#pVIwm;--4>IuOhZ&2>Q*jXngS^<Dzlv=`&}JY)n3WrS8P7b+Oi<10y~d
z8JVS@o6|UTswjhkvNH1|m50yg*Mp``uYIom_9pX0WlD;eUd)Q`JCFCv*Ef6j@ZaCD
z=Jugh?u{82l|WlRKy9iQi~D~(VbKM5#V6R^0H5e_7Zw8-<)z!d96Sa()dO_0cQ1JA
z^xqAOCH&wn{PGIW3Hqh4!$5ls=312+-JIP9T8#eqSZ{Fcot?$$pxvlOMxd?hAHIKY
z-@bkOf!4OE_m4gYU5e`B!t(C!?sm`yrw<Pff{ux1ydLOT@al@@nYq^D*REYVaq841
zi@2p;qIdS!#~&~%1kHkf{oh@0{It7+@xgif|3~&zelCD4Fi1GwC;Q>kr$dL^`9Zt$
zK-C|3^V{VI>*DwK2`alWFzD#&GVb{^hpFMy)6<~6AD{(NPEJlOxh8CT3LBR>xAQ&R
z|NpOk)b_ky_kKA>hLlLq(FSV1vp_w1(0QOYHmCPLSnA^9qB>b+|1McwK@gB!>oryD
z;o^Qf&|nsHP41B+M;6rn{>Biu@8yD$mzOyB`Nj8y%t<{xE%DS8&5BP?IRE`TFJo<O
z4cd^U?A|A`qpzoP=FG^2=ccQ0?%cUEKZAEF%bz(Hd;Qxlz5Vs|HK<p-E$?m@=whx(
zDqFIyay2$KzPP-c|I~DS{i;QQ3848j=U)%LYiV)S-GjvwcsIoo{<`&x7Cm_0n+IFm
z1e)T3E6sm#VIipXrWd=5<-ya|Y~R^tp|v^r`Tff7eIHI<Z$V$CWn2Aif&YBFRo!xo
zpxetJi?k-G`_D_bx+)a3Xbset71a(~5V<)GR0M#wcJC}s2lr7j3%-5(23m*a<m?>U
zTl3<A;*TFc7#KkL31wWqS;ezzuJ-9oC+pVls`{!0+GH|$ax-XY)QO48;1$I8K-V>a
zu2cXub1POp3|$ex7`)8q;EKS-3=E)iZ$S$$J|356W&kax^|${UvVOMAp5BVbOm}l~
zazIxf^T=9>SXx?c*tF@;x3{-J2O2PdHn)OC36?Bh&K(DuQaAd@3AvO~)gdZM>eaQi
z+zcDGZe{)ON!(`rk6*t)$NmU!Ix7J>$zkEbg&9{@iGmK8J7@i#fdRC+2XxZn!i5Vr
zY~OyofsvU-Up2Yl%ZtE^!Yf*K7Cvr!!RglR-+pPWTd&j%yIL#I5Xk2A^Pqtk(CHe2
zGBQ0EE(HAe`BPCrfgyHxS?kuVTVL!vv;njO2Gk}3&EM?;uh<vq0T0Q5=T*QL)h(6=
zjktk|OHjiIbi?bvJ~`X20|y+g9`{-*G+i$ibO$zQ>>0E=%{cwsk#lpcS=Xr~Z>avB
zS5Z~9DmLWbqodq4e?A@u4I};f`ugIQ%wQK+*ThdxPJ-s=#B`%n3N}iB?$Fv@_O{^j
zGhfhYq`$ttK5^m%184(z(#=h&9$sFD9v$sw)i>P(nnpX`C(FUhd(~pv)Tyn!(q;>C
zZ*OCo)@fMy$mOE2R|}`G+JS4=#6Euf2x^~ocX!_^tgo+kadF{@QV+YktF-XrBiF0P
zK?@CEU0r=~Z*}>Tr%w~#-r5SfXZ%3xqd&iov4YAIKR-SO&^37O{c=a+>;I-sGS_2Z
zFgG^`bv_vqGBZ0NqX==OjK8*KUr$I)RV`8y6b$S<rVhC}X)5R<Y|ud{pp~l(po$hW
z?v{JYgy8__$j79kTuYWM>zbqKv)HW{w3qjAJOAN3cVgZ~<mKss>c%ZwOh9W>n#6<z
z_s;!Mvf|LhRLPASHwI`;1?}^Ee7rv~JG=Yc-QA$OOzZ0E7O6|gAS%38&@x1Lg$G)7
z2w9h^sAR+kTFkkx#<Gn^l8NEPy}j0;!#jhQ`!QBj2G0YnHvRtYuCV3hgk5ECqrlT{
z>tc7`yCC)W(W_ToiHF-jw<WB)o|KgI;Q8}*&{<LQ>;LV1^|hgaVUA@n8|ZKd!_XBC
z4Gf^&_3r(0u1me9K6vzK(YGn@Ifc~}w6wUU>&J`jx$*&25rLWtb#-+C8X}-0%J)<l
zf-VdJIRSJaYfQ|XlXeqlY}veh`*F~nly!e9mMmL#=;qDHxBFL`W?uu{!JTFP$4E5$
z+M0u)c?@~^{!2@}AK%!R{Nd}@qut{A44^4p(9y-)^X`H+k*$l}{piur?ksb?AJ3nk
zouU~mASjqP>Hczt2b2Bn4!*p+yzto>Ne2D@|8Wf!s46LG%{=4658kY~sA+5NZ81Yb
z!&UvizrJn<^{LLyv7BLBZ6>B42U@D!$bEEI*;}b!UtTW$*e3VjDgXT6UtT6}vQJP|
zs+t^UEBk8u{kp?5jnhHfhe4z9p!>mMb{c^W@5sHqP0`vq`b)@S1y3Q+CX2MQQlO1j
z*5&V9W}D@L_7&FG*I)eHk^oxY;_RZr2HqC`>V`RM@?!zP&V$Dw3y?tz^<7+!fi}T-
zczZK{_>_5V<Hn6y=6xGCZw3u~uc&0(Uj9A~H01=!$w#}zzy6xP5;V&>d-m*G+3o!D
zZ7QCt)R*nMw9Hrf&c52)6F&DG`}g;^pp;bCudlD2C#m#4mXnhMZAWL(5ndm<I_$>o
za{YBNJDFOY7#TowIc+?WO>f@hyt%u3y7>J6he5-};zF}G-MJG3YH>XO*v>D1=+dQ2
z4c$G*HzXbg-D?6m&y?Z9x>#$_@?6ja3268E=JfNko`B9^dUL}NbkUeoD_7KhvGCPl
zzF%1if=vn^f!F?@pJ&U=;4{xglB<;|F)<OeM-9}tb?p}8jPrDH2`P%~kb~Sb!zyiE
zrUSaW=FLrGkcFVVIZsbdH!OV>!k~Zu$L5@yMhCTzZrr{dR8Ex2?XUc-c50e#_72C8
zMWCnxUE&=SBn0YRM^3xiH~UiTJ<r{!8yh6nBZe{?Z(UvpIv4nofBPlS8X-_1P4QAq
zN={}3ZMPP%_7VUOsD^~Rk-o$Z-pTeCG&FNx1bm0ZF~!;q;PG;K&=3wNPD4U+WIzh*
zK_@1HW^dlU1)U?OtgOr&yQ?Hn*5Aj+Waay(p{qg;&b2Oo@Z<?gt5f5@zrR7pM=wg3
zY~>QwdhqY>@2vHIzg+eQP4lBK#sc-9_4M?t`e#21p7sCbVSanitpK2-hE!BkK-Z_t
zn>P=%n&ZrwA9D_bPntX#wCU=|ks~YS-N;!bWuDjb_xE>Y3yX-ypwbM~*bvi=;)qC_
z^XkgVW~<Uy9rF}r@?$30mzS6C*u8tT-L`Gpj<xYhgXYZ>XM<KNsZILxetv`ys6`am
zIdR%F(CE*Nn>Rb>DO~|Ah)F#y2HF|@_xJa3>utHW&3NQ&Bp4YPBX*aqUC^4c=Fs88
zh8Y(WK&v46`1m$#-+tY~eUgfbsw!uM`>{i3&hSi9$=vhOTikQfgxRxyw}nsTv9z@8
z=<7RnYN~eOg9D5+X3m`XCiZM<<gtf`+ZTpteLT!>54zbJbdkix#q3PX%nu(wK5VY|
zhZz(he4?zs+rAt<rfFq%?*0vnU&;6X^n$0)LAyD+`oQZl{@nm=m<b5nPzb6<|ANj8
ztE;O6t%cV){o?L!bI>rs)sMHfW`nLI;o#;L-f?L|pR6_8(x6VzfEj4T#O|`Upi9K>
z?X8~u<@<+wd#fKmI@%2y-F)-rO~KDksU}%hIPUH$J^bzM?W^Zx>dyEnZys^HZv0
z_R-8+TQu)gK9|k8w?}g2%9RCWWycmew}*%eZqL0f#_-{BzkSynPdCs-;8V3igMQyJ
z3=Iqn1RW{X)ZBb=e|<gZB9hnF))o{Nf)=v~NK1Ev_AUSa_j}QDskxw~;GdtJJ-n~>
zw~N1_1!S88-|q7F*M3CJnLWE3lnsKGdfnJxzyHNbH$`J(;cM5f{kh2tx?SiHc-44E
z$BHA~o}P}N`v2`M(~vb0f~MKmSU}U(pi~Ol-~kE?&>*(=$s3@9IdX1p0xc;8-`U6~
zshORf?J=q4++1ttg#icd-@m`)z08{Rps{W(Ew1zPY@L^SO$A+Kdhs&Pt1Bym1GJ`s
zT1B9Xp}4uZL9HSK0|8L02(*K;Gvx^AP^mZ4m&B!)XWX#RhYXcM7ffIgDF9t8EH2K@
z&d$Ci`?}xPD$pI3d3QR>-riamxY&(JybH9}q4xJT$CV*T@9*tBar(6L@jlsw0U8&U
zdW%odi;eo?(!8tUqY}{zwC40mn<t%^pa`m^s=mHr<>%)I72tAmax*N8)y#5lftIy?
zd2=)POGskf|G(wXl_*j9B8vhvSk@Tn)iCYa1v;zZ%ZrOAPMm1aIXyvzlL2&#AE<qP
zpn<VTT<YFZ@97g}%;+e3dTL?m>uaE0f3mmtR-1#4YyI(~0yNILe*ZtA9U(lR?IDB)
zU9S2DLk=2;Y(SnUcxy{$@Wg-j4m2{yf1Wf6bUz~K)D%Hk+1}{wd5jFJLRYu>&9zGW
z@!?@jvP5QTc6RsA&(A^S$rll$BuPohj-DRS=}8ln-4oK&+vE0DIW7!1aQk-j7n{Y0
zmOKB=y|o3r8#^dSC?(Pjv^z;aprP*XuY(sa27a+g1kYS8Jd|`FH2U`|`SG9L-o>4@
z!6x9Pzo0cmi|xTVdDaaJSI|8rNsmDazw83t0WfjmM9>mH&<+aFO0!p2RxV1HjERYn
zd3I)I^O7Yhper{)!w{f7f@OX=IXZ5=QmyOv|C8FcZ(q~2F4N*?K4<3HN`p5Bi;Ibg
zoj7~8RmBq&acchabgCAC&Z0kXppjWnTzvW0L&XfM{-5`eo!_udQ(2k$_xJapLrbBv
z#h`JRZ=kJ8k|Cg5#lF4iRCe!M5w|*MDc85Rx7o9^vw0*87}WjewQSyO406ST2MM4J
zNDq<<L0y+ej~|0JlXi(}gYH(8HqQ&${m}LHw%muWUU4lA(yY)F6bw9h1e!m4CTue=
z-TQ0d!~MeluD)jY;my6sDeL||ThN)Mm7kw=&T~?ADJnABmUowHX;A0o<^GF7w_{&l
zFE7Hy3O+!2o<WV(6g6XGW6&@G<Q}tz-Me?c@N{eJb^h{fV?L-0a%*Fu2?*tP@HB%9
zP|!Y$PSB=r=M)L>B%|NKqT*uE8dcC;M+ckPLH$3_g&<$Plz<L1&b_t8v6V~I<-EwV
zo14?2wJazwjE#-gL~T8_L_cP6ld7s};_*J&Eb-IdUR~t|ue9-<!EgUZps=tIG*J)Q
z)bx2#gulN(v%ayNrKKfk-gK6Ee%>Z={{2GY;-FKW7T5gz6xDBE^@Rh}Q+R!CE$<$m
z9)J74BHd!TPTTYDK6v`HRoXlcblbs-=<RxwCQoK$0Cg!J9BdBURg!ry`{?6d?k%6c
zeLJ?;y<b3HzW>Y_pB+1PthoCj>Dif?H+B>%PntA|MIYSWgznm(C|LD1q$T{)rAr1G
z7Zh&Xz75)iy#jo-)T^tjL4yxQMn)S7AG?`kTyQuNvq<Rmqods~ZfsNr9sGE2Z*})P
zXH}o1Bqh*g084{9TUuB^BiJ(x5}RH`vK?LS{Icxb9ZQqEI}xupt`1)hIv4HxySvVy
zLBxs=2~%{VuN~k%n($a)Z{-_lEj=?nX?6P?8Q(Y3N{16b%Vr91So}-`Euj&RWRq_1
z>h4{vsjJHi+PJkccsZzOIdjJ6s<1(EadF_<C{xgIO7Zh^qPABTeERfBKv=l>!-oRU
z4eXJTkv|?Z^DhX{04??hwGh9!ES@xZax>_}=)}WqYW0EgFVm8fn>&TolYV`9xoEk>
zRP<FUeHRVQ&5u7jJ9}Y(#umBz+j6BvxLQx%xpVsPVP;S-Ur9+RWIbrg#?jFcbo^gZ
zQj*W3`wv(j_Hus;U*;ouX0Ek3(o#Rx7wZZ`4#L&~fL7jkcyMgmv<VtJI?&#LlJC`3
zp~1f^j`c`_s@H?f>{sWhfEKoay2bnU?E{UyU0WZY|6-+6MRoPzGiP`}bDXWMt*_c!
ze@;~4Z0DCZJ7A^d2};eD#m^Sh|No~Eyo?8Q4^v*=y0Sjlrihd?mo8nJFmGO8PY=(D
zO+4Az*%v4Cyh9rAwUd1n51Pxa`}<2#Pmj;f&u`WB?{984+tvPh@bmNYRo6kQtA6~b
z*!uZi7<eJZi_(Pq0fnGTd%!UWZgZ|@21nxIW1tP$!k`fVnJQV(vdbJ9-~Yew{|B`<
zWGo68dZo?Vy1Tny&Dgoqvg-T0-rC>aW}abvQCL_A>ZW#dIAmpMMQzLJ+*$m5QU3jX
z`L*XojxToafAIG0+Fg~6D=Xjc{SL}1pv%>KXPc@0Kav$IBP;9sFD>rYjT<*UR0r8{
zRh2#2oPOS<>O*eX^K-I)-q-&Ru0DJHx;O)<+Z0#x?|)@w<<siNppE>KcNHGo9~tqa
zKJw1p-Q|^=WtEf`B|Tt;4!a!qpZwl$@gkecZy&yIXA(WaC|Yo!qanD!>j)zYbE-_h
zY=x{O2b0XjE=CDg>|K;s%y}@wtn=7SjuP!-VIgyPHCz}kJ}!{q??`xJq2wIkD6r%n
z|Gu#0OdgRAcUiaAXYaHM{eC!VcO+Bvs&%h#?k?9qbm&mXy(^z5H8wKt*|W!>{$CB_
z$s++8A{zSo;dXlZ`s=?Gf4<(Y_-pmn?CX!Z_4heUR`X5B&OZJ2X~^2w*VlvYl(@Y;
zA2cYwtNeYRq;cAT+qb37%*+-&&b+&`_<2S73avM{xASk?woNPlo~E|;VfFbnOf!Aj
zK71&!u&{XW;9&EQXS4GK#KhX(@Bbf{kYsqHFl6K7fZT-rioP2juShz+Qp(!z>y3P^
zq~i;39q4nOm2f=pXkV~t*_>A!ABP<2bKcr0+ir5O?{il5_jgCd<7*ld54S0rn{Ph^
z+P)?zD7f%%LX(BH_2C;gBo@2%9%`4bTM^?lW$M({HEY&***|-`{r<Hir@Kqf+i%~z
zX%lFe%wrOZ=OoaAc?)Z6?f(TcuX5Mb)qy%`fBydcnw1bC8y6RMV{f(jpTB=y-7j)(
z&%Yn`bKdNE^ZK4VdBS!5@5kfvH@0L7->Z1cn|n-n)s`(H%a$$EI={CjCo@x1X_DWg
zM@`|<CK&>Y7B3bQ5D0j<X2l8)K|w(Yqm+(@6c-m4US{?S;N=ys7+akhuUxsJb$)&9
z?q%Wnb*d^Vdp;RX+y&~mtE;QaSQIqmzgnmT+C&6e75eS%ZO~1spk)@1j&y$b_Ra17
zzFODg!d>O<t8Q)0zHX3v%Vg^FM~@$W{P55jbn!;;G9N~U8@F$RTj(V(CfwUwD4B5l
zr*@glD&9BdOZ3X-tlIcEq*r!%)f;nBaGV@hEQN?<y|K8Oe0*hxY<m{7HQ&l^S@&92
zR@N7Hb{0>4zI5qQ4Q=hqNlG8*+0}Nvc#-ku-rnC+uWO2Mc}!Zez1;ur>Q`c?O;REw
zBX`vPHWLySo;YJh$CD>1py>lpoucCD1X_Di@gd=<L)Cn{+Ap6zU)`MU|K{#)@%;UN
z&6fGi?dp@Y4zpr-_3)vh!rX{``}ToWA6;1JY*_oNBqBOGyvqH{y}i}k9?NS%lgnbd
zQA=W8K^A^p-~zcrLP8?p?ygd%psvqvZW@b-ifYP>i-|E+7>4|P{yg5u(C}iE*~A??
z9BM)5m9Ac`ZDV6IrMz>0(Niwaz<<(FF3=#y!Gi~zf`tSHug1$bfHxVgVz;ri-I#aR
zDk3`i@nwJe(0@u>SFGT8eQoXGHePAaIg}Qvfq#Po0vP1w<@c>@k9*l`eh-wL46?3h
zoSAPg@7%@{xUXT}^y%R*k8jDk>NQ)i_2J!xtESDK-Q6c^y~?Ki%?(43Nuaa5R@vBB
ze0Y#`|I6iojgJMc+I^D_61VoddZTdFvA$s2Z_<l)9qe;{1<5-g(c^v2A?7y<J!0Qj
zyxP2VD`+d?YMcLGug8CUHakDdaAL&6hYuGiUy1&;E#~?9IK5q<LjV{aoSdxg;pgWT
z6eKih(j?H~BA~jD0d#8VljqO7d$f=2D11ESzisg|pQ*;4lfG1~Z0_#nZV>NYr4@Z;
zN&fuVA0HoIT>brBfQHD2Z{Lok&#z@mPfwqkt>Wo)d71CWYti}O6K*GUfrc}D=2~q%
z^f~!h&&m&TR6MITd$e_PUwQuGMF%rGALtUbQ;c7x-=DsA?OIUBS1(sdNof@$A7ljc
zDzp8+AIhLpCqajkzPqy%wC{-F!M(lJ8oIhi9~^83^@}<DH2uQD#5Qf(6jEnd|M8LQ
zpU3k59Xvfb?f!gluBfWw^6}X9YHs;G&{_c3;|j9N12jH-c^UlX-rnf9=F?xD=3ctT
zI^?R3u5RJ~f3;Je`^~fA6c!f#^769#)1RO-SppZk-RfCxe4{X~7gQY8p@e>2ux**l
zB^Gc-S)TRAA~gB<N;y!eR_G!8#$t(HnatPPPbbwmxVV~Duhs?~uk_&PhA2-@PA6w)
z(AncTcXk98c)hK>`SHcq8M9|Ues*?t#_eruUuakzzH&w6a6A9;4-XF)zQ1RC<oNOA
zv$ISsN?(b{*;c7o%@f$TapNN87i)T@&9%grUg)k*zkT~Qb46i!zPY*ijT<*O{FX{L
zH8r`oUx<u}`B2ryE8X_xO9^PX%FCB8HT3n{*RIuN<B?!sW@f(lv7@8ol_@;Xb)&W%
z$lw3BZN>}<P@{Hx-d!e!9vMra#csV#?d|PxdBSxsPwVdo9T*Kdo}QuN!vn@UckX<6
zbJN%)`x?*gvbTrM&9#2`^r@<a=F3^7udf}vdsh~8OwW~-!54RxW?!7>!LA#z!J&j@
z?$O=Op=S>sWSls0BIpXO3u_{cK{wo_pPO^A`u$#ZXXmT&Czmc;cIeb8uYjP9WXAz3
z3(JF7S674Xl)1Pm)tjMV`*!o9;^M%tFgAPp{a)`kt?Kvk_6E)FetCJBT{mirfUJ8u
z=ro<1H*bO#q<~hFAHT>6I!ZAqY0;;5&$s8@b$WcP7nIZ!zrDFBVN<c;MTgU#m?B3}
zP<$^^exdV^CunQRNui5^C1T>@d+a<XJ$Uedft{WGVqix{hm?rt!T=2y=&5^Wr%aiW
zaDQJds4D7{v21$uDCy$FmW=!RY?+vtrbGvZuZd`!FhL+@XA$dM>+)kKCMth?a#C1D
zU7g#{YuB>K&1s-2z3wgOOctY=K2N1QCj|rqC@9HIJhyq<wqsvjUN+3XXY;hUnVtU_
zs9QaM{`yaBchAl?PyY7iX4U7fB|kr<g4Vg{MsI7`yVn+Ufa;<}N}xSve}8=q-g)iX
zHL;?dGPBKcg{Fjk-|%=3xUSx>xXKb-jb!xweP(~75R~3sOpk-=Z<(_jAOB&u=F4o7
zZC~*Yv>^BTx>&9912zBueh002xOlPTSTj5Sg?+WvM~)qH(wpAhryS$s1G;8(!n}EW
z45!X}`}y&KQY<UC*n!KJgA2Ugf>u3Dm@=j1$PpLN_UnH8e+^5Qs?M1+XG%S2Z3<|&
zT%T8n{?g^kL0jo&&YXGT{Q2YY$17Dl4_#dB&bsun?#-JwGp?=*ZGBqcGIeL&->Rwc
z;Rm`wv!5<se%&|%TJ_lRO0w0dG5L63;_Yp@H#Vp9%h^`36c-oo{l^*^7bmBqqcf$S
zU&f*Vv=C<7wrvay`uh4)&94gXHOaeU;W0_YitXhN%i?DTu3s0g{q;pq*7f;^cLAZV
zudWscwTCxsFi1&DOS-VYafWfaU#q#Ux{AtyBS%<-)qDh|gp_XpH+g0y>_@7I*SG&&
zR`kYV31^uMq89jEb)!)0IJmh4Qo6@3Jw4sR+Pb@M;pYne&EntQ-{%Ld$F;Hob*s6>
z^+M)t&AiM8+J0D3vEv@kg55iJ9z1b^1GK3A)z#GxU%WW6`yG>nU5$l`=b?qp?Fy4m
z8r1ywkY(>SpS{!D%WFgV`#8`*I4dhFD3w`GSK*X4%MqC3H)q8P4bY|FY;0^VE-mFg
zbLNbT`=!X3DT}(gxmT5ae&!1r2S0i8WN4YR=cF(HzKglIxXgOQ0N$h(XbZYh9CQ*U
zXe;2m`}_GlCm9qza;f?E^SOjc#)P>2mIv?LkpY)He?A_U2OVN}X{q<r=c%cw8rs^z
zqWvWiE-o!EI70Z>#OxHhU;p10)JFB3tOh!np#?O%7-5xou!;4>{r&d4N?tD7V?9O1
zbB1+!UTgOEH#ZlT>vLIIT0VSmuzCHSV^^<=PS=mW7Nm6d2srg#V)@OxvRf8ZoUaF0
zy0gQRkAs@56Lx{C;m?pJQl%-p<ae)q_wF5N&gaI)<iwmD9jm@`m%q=yuix6%1{x>p
z=<j#W%UgGf!3s2;`0DC{ob_>g3%<Sz&AGo%cDjCi+vLf@bLP%{_~Z#_2(i0Q-6t?m
zP{lKd&wO8vk7#OYD(HUa6DLkMY)(51I^<+a#ziJpR@MLw5zs8HkB^VbaS<gI6_&l#
z-$BEw37MIiR(<ClFPb90W5<K5pt;!3&(A;J{eB;)7Pq%|adFw&!wl(^Sm_uW3*X+B
zdw5&!ZBVBUbgK37<LsanjqLI@4TX=79lUrku*B!#z1r`wYofMtot<qC+JAiN^yyGD
z|M=Zyyt3A1A~Pm*yxRQw`g-mA5kJqG-%t4W=Vw7l$&n?VlR-z!ZOOYERpOFZQLb@G
z#JaEQMq$SaJ#bsI-Q-~1V!JXKrB&YGniCYpEBa;IJ6;J{_x&<5HU{lgoiS@x(wiF_
zL7{tLp|hn*6f57iy#-HCiLQy+x#?7~x3_mndV03u#0b!-^pB7Cg9>pKRaHezP0r};
zd9Hzhg3t|12b<XsgBG#=`r15k;=~sxq9)Fm@#EC-FY=9zjVDf?bWBQ80v)r?&CLxu
z&8n}j540%~G@fzf=+VwT%_DQI%MGf(<?zj4-D$r+{=uWBaBnX!&{f9!e!bF$6zVFT
z2k*;)H*>yJad&qI%}3_m+H&y6$HyNZw#y&7c~g=BbU1`w>@LvtET9uB=Y;HG=a)Nh
z`ZV`)zqw9}-FiXY6c!d11_m!LuL}#E*+HjUUR@R1G<lL<)t487`~Lr{ma(Y_s4SlZ
z8lOBf!w@ubH_JR<&qDF#q|eXKC*R(d`{Vom|Gn1b?+%<e!J+Kd)6n0~Z)0Oqq0Xvg
zy5TV>fK86pIj`@QZC{agBR`JcnlH0UwmnYVnlJF|hR1v4%49BySo7`GE1UD`@Avxu
z=G*e_cGds?egDL{b8evVxwmh5<>lqSyuBS>Vly`|F0SwY@BROsZ*R*5-J5o?uqEs6
zF4Je{=5|{aKT|L_7k~EbSx0wwbBrE41E^~<apFYKd7KZHJOZ7~^Z&E`f6%C<in_Y8
zrY0w768`bA-iHq!GzhEvb@Z($4hjkaZ4+i;W9#Z$R0;~s<@4*h^7sE0tE{ZdxV(%v
zDLL7&<V66(0eAV@mOFQ1Ks$R1g5F9SBrv%3$#h=05O6WD1hiWOG^025{qbL?ZrqRn
z9Us~wY3$;D(K9S840P6zczlhb6_=o3VDk}1$YqqWsR;=U=jK``KRq=SG?B=|%R4o_
zCfWZf7Z+DTPEL<ouaxHe>R(?pK?`#FWUUv4t`1|mJW+2~^>@9Pm>AGPf|B?5Wbf`S
zXJ=Tlbm_zT|KIBqlare#tNSmC-Cfo+dD6N-4G|9y4~LKt5zxx*KYwaw%$jxR@?~K=
zJ3G*M2QNBYth!~Nf8F@_!s~?n3uh%9SG>gYyEpAd;fvA@j{|%+JQm1olXW+KWAVl6
zM&Syz8-=UF<Kp^m+=$4zyGzv2&`?81$E9D+)}ZoJ3TVvd)G4nLmqgGSr8jSKZrr@N
zF!S=VMUOemK@;0cmp(ky%B`WH5g_TXzy7~n)z??8hRMeiY;0mmLgs>oTR?Ydfl7*%
z!OImqh347U>sd`Z$H~p@?BUT7SC{AG<FldaYnIPkE77G(mx2xxEqi+lbU7vygIV64
zj{o2P|C8t9;$l(1x({@=^rIu4pc<BqPe#M4&re%d_vlB+eS0%z&g|?{77-WUbF2RE
z_4<bo4mNvuc{TZ{3Cp&3bgVe|5K@Co?2Fo6rn_j-q6u^6^nmu6-PutH>f6M`#!j3$
z^Q8GVfvZgM@$sNTMy<==fzG21IS0Dyh*MZC;m(di&>b*SCcJ9CbSVhb#0B-_E-rRY
zOh{<hw8`k=#*Pv(Yrep{N&6SxI@IU9#17Q&I^O5JwN<v=qxOx3OKHDsdlt8~-`9UX
z9`pbB`4e=0Dnp!3RAFi9QP54m7Z<y8`z^OMG&BV5x2USJVo)$M12v*7EiEO?awNob
zA{hMr{SRtx)z{VKZD!+b+Pc+L&1Xi#g9iy`W*W1*xw(OMf{Spmo||XO4H{z$+`4Yb
z5|-uu^WBn?lt4Y}Ns|`INafwxVF)@eAU!?3rL~pQZ&me|N`}4B+w(y8J$ZO=Ff2$u
z-uL0#H_(}O3=Eso&mX(CHu~d(gUk~Rw=UXLufKHZQbki!QBcJpoxdkAF(GV{ii^8@
zw)P@F4J|FF=jY}MN=S6v+??Lsx40NonS6V5vl*26Qd3iBSe0s7mA#30sj#cPy}hBt
z#l_|8{KT)*!R6mXj(`9Dfp&|Xoo&7`_qG{mz0KuizToSc?%YxE6jJdNk`3;t|Mz)5
zL);!s=SeD0AHVXMXR}i;IncJ`$qB(Tb1XL>nq9?k0CZ1W-A`4s+*>LNl2^sg&$9*X
zMiLMeZEa~`VQ5&obm@%%7pp#SbsZvoBY%b2hQ|VX<-UO`ZSb%XXcXzi*A0*NNLlk;
zWdo0ZSgZ$~<+wI_d(!oFv7q^|^Yd&$%Pu7(B@<6i)BW(_!vXXAHH*c|Megpex8Jj8
z59rv={QP{Km>mI?*OvK8m%O;Z`0(MwD$9m@YopCo)YOy|6c`R3JQ$!M0y;W{0d#0d
z_O&$^S3mqbV}``j13z22#RH<ExLTbWudR(feDo;mxpU_V%F5cBo0)rhdR&gH%BoC1
z4LU>UDZ{TRn!%uBEkLL6KYjWXbZg=g&&e#yuk;zGp9}f*e%ZITx0Th^*)1(CMbCZt
zct282O)Wq}#K6o<Ox9IBWZRAdXU_2W`T51f1auZYKBoD<`q`P8TIrKi92W*SOj6k!
z!{OxO5+Yr}4ld>vRXw@0vl!Iz0G(n3x@PgxC87G?x9@|NZI<7!75ANGA}AZE&BMb3
z%Jp`&U2eTn2M-)raI62JzTiqDH8r(}T_u|P{(L&^bv}G;6nLu1)zvl1&uy2_!hi=i
zz$fk<nrB-b5D?Iic6L_cn;RQJN0dA%+8K3!ddCa<8-;NRpaH--=UGX|6<5W+G5>$C
z4>I<5w9h$Y_l?4T&5*&U%r4pISJ%bvZUe>K?{9BUoH_;Ce79%s-iNPWckiqHy(-4K
z_E(9EySuWvd3Zq7+n4wE+xz(X3d+m(-?<YrWA<#&Z2(0(We#-jHqF1WfiW^NvT1VH
z)cN!KrOope?Aaq@W@ct!ZZ0nC`8uxd|BE|2Hy7QwbMvO8ZPgcnIcw@JKDS=*|KIQT
zpxeZ3Y;8f+olWg85#zKo4kaZfDMpgVdL)}ov#%|1?G{_KcoN^wFPHrbA0OidHz1Ve
zOr3f)TVH8{if4X(o4j?I&)U~*e6mr;Jwe?;HCX2xbkYoHBLk??wXOd4;N#=t28M<Q
zL3cB`U+w}=PFj_|TJmX!mHvA5s+UjQ-rcYJ&D$$w8e|D7L?<XZ2Si16ZB9SW<>j&K
z$(fnP9bH|A_W%Ez54shvt*s4oi45p;7=C{Ky;a4kfw76l6OS*PmArr9bx>$;|FZW!
z!yAhbYfv2n8i3L*lPQx~CHuzW3#jpXeS3a9=)RF&Y4c;C%a~41R!=_CAsEW{B>(<C
zSvxyB4SoIVML}<k&CEbc84Qz;^?0#gFwei&bKd^H%+aGqn<i()XJlyX*|X=u=JfMk
z=hw&W1&t#<y*o#G*IeszP!s9xt*yecOXDs-XDm_jRZ&$vc>X+ScL!)$;hME;wf8Dl
zy}!4Yb&0Z)lF}vk0NwMh?ruS0;pP=9G>#lO($VJ}vK};~1v-1W>iaw1`uh5kx3@$Y
zCQO?Kx}^3o=%|B@$?V7a<@GHzJ4J+qn%>^tu54^9%+<;S+Ex7V<3UjK7qqRi&;3fm
zMo>ljx9!T&KIbL1Z_Hh0C4+}c1v2HW`6fPtj=mL_mbR{6uMaB4pPii@UR@g)C@5!F
zvqGHP3A6+kbe!$EIhIrT7M!1L&JS+|-AYeLXjmJ){m|{(yDxo~wJtkw`}XYSBNZDJ
zo?clQ47x8P?%v+2YilC2;;WyXk(^^y+Et&=AR;Dq=*Ep5r&1MuJ$ZL`_j;S@DxAKv
zOd4m-oH<SCWuN{3zboFnyU*3iG)d)Sb{A-a`)Lc%aSxy}Ixa3wF7N)n*r#omPfyoB
zeCm{!e!Zpt)$Wdt1J~p0d*8gtdCD!p)ygC$CI*_+Tjn!U$wIL+Eg_)+x=h^8&ThlD
zZDO*W9bZ^LZO6ZDR}S_$yDZx9c*3$9g&wkREL>E$KoYX;Ac?Jse|~)Q@b*3oDgy%o
z78o_u{r^`Bnw3gE*5g=FvE#*xsPMZCzjl?r25lFxsr?ml`eey@!~lWTbnzFHugfmD
z_B`<>x452yg@ptsC#Qy<-m&%j|8eb%>6<f0<_BbHsdF2TpltAK9v&Vo*>(T4g@uLp
zd_HH*!N+&(KqK?k2|jy3=fZv6In%0imDr^hVtRT3rZqnbJSMd`xAQrwO$N>PU#;r_
zpI5m;?2@3Mps5XX2zXId{;4UNpo{vvyu6k^_w)06ad9y_=<ruv^~Jvyty#kZI@We=
z^mYb@xmKl3&CSd_yu7UH%CQ9x53%m~dM$eDyrs*QB|Sek7j#+~sI%H{_se7LZcPEf
zm7wCS>2KSr!;nw}HS7XPZxnWTh?L2!;w+O{#b?cTwQb856CNoOj%(Mh%`ix00xjiC
zKPLmKu@1NK255*_RDWA@PshTd@DYoUkPrg{Xn=eA^zfzKDWEnA=o$skWav!e^euCO
zzJm&bx3{(i>*-%GpT#rzbjl_xk43kGf`UM|IB(0nedz32-iZ?@YI$>m7HMj0YrD9*
za{8^Roo$wT=+@Tk!q?YyYkoXz->`WzGsBYQ%O6jVuXB8UZZ4=8mNw4=EwXHFZSCmo
zy?Q#a_7}gNUcl2gZ+JW>3CPRyJ3Bi+ef(;UO=S@GOHj!t2QB#m_g>$a?0#m3A@k>F
zXIFozIXOu+Vt?J<PrlMFF6+TZMXU;44QlL}<=)bme}8|yJt(K8pP#2WfAhwTj$U3}
zr%GL1Kvl@1T}L1RDG(T&bX-v>5ZdG1Gw*OaKd3ctQUA||i;FAZ=Ite4zxEvg&7eCt
zFg$wvIMhym-MV!Vo6~r!zPwO0m|LbBwS}WwOqc1yqjf9RS6Tm^oxiUWwA|E@|MN=k
z`|lh4UKJJ>JIBSz1qB5KL_~0Kb8}B!$_ko;Pf1ZRGB##azq)U!_jJ&8u%4ct8CO?L
zJr(Ka$2Vv0+>hV)|CeoSYy@q=039%3ZEY=MUl$XQbcr=42DC&_snAsowE9f&YBj&S
zUCmSO7od|>%gVNi2~S*SRrsjIP5yZNiPzgf=j2|y7WVYFPh_Md=v;*pDMl^r?S~H@
zWCWd^2RcW6!v+J;&>NGmaG*12_5d^ixAC#SM2$BVOZXtYJ;BaHea^2Ejw||Ze7r*6
z%1R1!y40JuZ$V3%LHn8S-Mbf{A=1&=={Q|4_QA`SnpVpUzJ2=!I%%V>&JJ{r?Wa#g
zH*VZGaOX};iOE`S9-br5=hySKIx%u{bAxuff_6~sbep6yW5x{7_UfjfS8Dfu_pK^^
zc1BVsZjZ#VW5+bKv{n_|Tj<PwXMcUXgV9IOVJS0>)59d}*c;4pZ#|goZ+CE2=xWf$
zz~bU!P(S1UkK^_%Dx!;*EMcks{w`E+qNcunIMM*sojWli;^L2w^-7EWd)Ly|2C7{^
z?MKj|<*eLd3*z_JMeHb06c_*VAGw<eY98qqLJw<xwYTi;El}4ebl!aHazFiegQZ<D
zv9XGtlRj;9S{P6nBU*d6!CyaScNy>HWxm0cdUkel{PK37og4<Kr$iX^?`;4r_m;6L
z@yNe_#o1+RH>gyEv~@r!6I5I-(JYfu5^4oW^nn^df%hk=dK)AhU;s5N?d|13y_5U@
z|COJ3TJ$Gmdyp_}Ex^Cu??FeYfvyO&S|+e?;ldA}J~^GAXPcOo*7oo3@6~hS_g0Bs
zym*m=lT&a?!0w*j-o%_79tO}R%rj@tCMG2*SxkLrY;F!(VtR2~ZuG^#E$h6e>t+4D
z^Uv6G(u8T#!rVJcrZ0TB+C2ocM0=U<>@3aRyptzSIu;fdPJMp#=+P4=PX^lM-QQQ+
zs`#c&OIw@Uxt-6|&5aGTEJxjc9;hLtp`p>>v=DUk*_Us>O~l2ooY|OsTtG<Z5V)Jo
z3lC>oe}8|_i5Q@fv=1KwEW0~99V;p<($36K)R28S>Bo<XsmE1SRXKQgTml0HL4#U(
zcXu%|1O*3g%)G2-l6y<!^mKi3!Ko!4d3kzPWp7q|y0bC)xPqt9u|C<=pZ<XEVW|F|
zmwQZk5nB%^qzOgA*6iz`+Xhag7(Hc3$;{MbIB@Hh)W3iKKy@N$rIgV!0Z<V;cdl&J
zw>Ob5e@@j7-;i-pX|JTi|IL1LtvdSx^f4w7b~Q4yhe<f>FL=lVYR0aM-K|yMw|wc+
zhrhnQ2JJt)zpvKSMKtfi0>_TNJ~sykht|!D7Ad*7xFnpIpvW|-^ZA1Z4WX;U4qm=2
zoWJkqvQsy&t`6T=^)+iMtK!O)D_>k#*t{*73)EwqGe-t=taA4CbsIKpIIu2u_k$NN
zI^^qqFoM<%$HdHeF~g~#kWo-juoE`gvFf{+UQEZ19Tq*Z)?&54z69<|sCs%zG-gkQ
zAn0n{MXuc}%T;1OoU?wv!e*XnwwRP@R?CzrBA|06fBw1u@0)qex0~q|&*zqd4%PwP
zzIQv&vppgz>e0WyzqQVT&b(7oQv)?;PJQl`G6juvZISHnkTNKf31a`v3mSmxa7jF_
zSPE%GfUCYB&=f+Ktb47Rn%b%V|8=9cxja7B3z`gjx^wAL)x3LqG_~gWoj!f~^6UN9
zpw;8AuC4~{ix&|Q36Z!nS%p(lQnKk%r>L-S^MVBmOO`KZ2HjMqIQ=weJtSx&!NDe0
z(2b~bHoeQeyDRkR$9=WGLC5cd1_YGddIBu1YknAj*1lJKOv-h;A_<Ca$dvJew{LkL
zxayxfbqaKTQNjOzwJhxH+<uzJR)wwx)u8wGR)hL@Wo2ay4WLWSo}8QvTId5h;gmtY
zt?TilM-QGpRW;gl?a0xi4>zB;Yo0t=_|vCP3=CYYOvjELn_*q92U=!T{0wy4a(qG1
z+sBWXl$4Z&PCAq@D1pGDSy>ksu?7VNfmU@)nKmuy`nuQ~TeHQzyuCqtZ9wbaQcq7?
zlst*=*0x;fn%de>&_a;TPR^RzTJ1d@9>0!5=G-d&{4i_~*S`lEsRViXp5?=(SFVIa
zL`HUYc)IWkfaY)@?Ot&6P7Tu3g*5M)WZSPC?OVJr@9wULx3*@VI$rzx+tL01zUohz
zI(6ZW9TI_offbK?%~{m0tP@uEQ!p_RS-5Z^L&M$O<=XQ9f1Y0xx%tD}?e`ajua9dI
z?w&YdLIWc++k*p*%o+Fh*+MSLYyS53_Ty`7qYX?=uioBm`u_fY`M9_^(4Ze^{G`=s
zp-uMXWxQ4;FB(34C}`w7%E`xfOgz3OF!6^BXfO1`_wW0EetypFp*C;vVr4!Vi-zp$
z>onOfq@SD9x&Qy)_Z7dsX!6NeEZAP&{{HrMebD)%FE1}w*474Hg9h5Q5f&x}DrdUI
z^|kEHK?~iFc8hOJIVp5-<<`Y3R&dO<E@xu^O?XaHd3bTL`>A4eb@e$Gg-#(h3&Yk%
zwN9EO^yS@M>Abu=(0xS9d}p(no125C7thbLy?py9ct`(tXfIqTO8~U-(zRRc<2%7G
zQC!^Ip=S5~U)@{%Js>1x$x)Xj-C{Zs4WRY&-qZC!Td;N(KUeS+dUkGZ^ut@W)!!WS
zrgM9Ey6}pE#%;k%2KWR!kMw~Dc|pAv7bVabViLI5vLgS@jg6osr2Brqvj*)vyI=E}
z7j)n@==7gSDhoGk5QyHEBPbi3{pj)IsrJ)VJP*CQyL)5x_jg|FYd@bg2NgKE$1Y1M
zDk_2&?t6K0&9kj$<L2fDjqVohlv(aSzisz!>uI{tYLHq9v;_&YOLg|_?pAK`RdcMZ
ztdb75@g^POEc^SbbW7&tWv7aZi;H9S*Tr^smYm*@co;MjQT+TI=<ds>PoHksy7g!S
zBXdH+g8SbC-rU%z4B94V)pqXXjg88n163FdjEq3*N+wR4)U+}AI1|IAOP91_?=0bu
z)6<LCl)?$xE_URI3&R2F{5_4JgLz)B-yf!TqjKkt2GFA5Z3WP(UTRA9_jiic*3xBV
zWf`}&tbAdy<S}U419YWSK|#Ta4L?n-tfcJ!{YYMVdzI&YP!HyKzr1@ygal}+BIAMr
zXygt&W2&d9$f%~KHp3vXX~7bgD-$+8p0MjiK4^`G%Mxx#9s(^5P`bnlStAf6Zr%3_
zw0_sJ_?d=$zoao6CnqOpAySHwq+7onuerH-Bj;9a0|SBi_5UnIxL9>`bT-uet?H3B
z_XExLCL|>-+U{J-Q1I_hrB2iq4$ve`U7a1ngP)(DGc+_ZvmZKtp8w!M(9JdClEEF?
z;p-Bfo|+muFFGnp$=W))yR)Qy?OI(WB_+^8q8T%0te7JzCI(u8X=Y~Dbm=7<(%kh5
zxe2GAf{qDva&lq-FDd=>^z_FU7nP?>pAMRNovh|7G$%*~)U(RIrn7ZDXbp+1nxc|Y
z)(@3dr-cHtP2ic<70Z&6k_1FVTE2WKVQ|RF(Ros2SyWVHkaNR8Ct?F=<62Yjq;)%s
zpYuH_vdp`)qp|Gmt%K*z@qy=0c9*{goyK##UmkSl(1Rr|E=$&f$1Cm&2nN<3fF%2l
zj#tcOGF7o}EL@iOZqK{hv~y==t79Zn)V7??r>CbU|N8PWKtlvHP7PX+Dlae3aA2A5
zY|sXWMT?XUdTw10+V^i=t_O-1l))nggZz6oE^cmG@1xfEFIv19G*qy_xt;IFkH`H}
z?T=r+d>OPp7<4Ye@jhA6X?8CrgBH^n8w>yZ`Ex~1%F)}mqaC!~&a$huQt>>rtMqk3
zLPEpK%ge)m8%|P5Jlw_`<*_^(v}%5iU9A*olgphQhM?6}lE!JEBhHLw@+2SYIXKHS
z8?>ALVxT9xgoMPNYhNd+Xih&ZASih8HFSVn@M`t%@9*1}FISh5l?5I50~)-1%DUb#
z`Iv*+WJNVKw}PNcu1Aj^1r0QVM#f=dOD%zm-4btY$pj53&Y95B@kJEWm;c+=(NQ7^
zVu6O?VXPH-Q>RV^WmEroHlWL060)+itb|@Fu(Px8*trvQ<0nIdUG1+0-qZC!)f2;k
z%a?_x>%}^yr7b%#!wIxcJTo(MN5MlTE-tPRwhQm?@9&S>Ta|cbh9PK=v219^;dXvy
z4GoU)buodJ`_j+P1C2Gh^-8H~%#1M4zjx%x$;lJv%!zsVz;c28;RRt~VFm^U4sLF2
zJv}`Msi~}<lj43FPEt|S*7o-1^b{{Fbo^@a^Pl46ldlvw1qA~S9|yNVm6TR}2MwYJ
z2L~THems0vp{0%vkF;6N1O4Zn9UUv;5|4v!<7w*vdAvhPsZ2&mX(Q<7#kaS&AHHxw
zVBfxdpe(VwTpx6sCaBHFaA8HDGH8)K=$PmSTOP&iD&brmzW&(H&(8w`0vbMjDw<mC
zIcdVgiHaI?Eff_MLHnUWF)kq`1?nlv*Z(oh$<1YCkd%}Jm0wLwO`us5!u@|8&=nT$
zqOZQay{*-qvS!U17ImTQ8ygZqmw0Z!U&k#jE<R)C%+RX4r`H=UIt3X+`myzW$z1_R
zWALSr^F>B*_Uy=db!w`1#LlABsn4fPn|9*dxob&~c1JR1U=)IutQaOA15Gy`J9g~G
zu2OB#6_G20mp?jde*Z`dr*J@6SleRve$dgOFRrW<UgkSn&1%~<RTY(lCnqKv7#lY?
zH#6(S>|od#)A#66(j2Q&u5aJIy|})9{)-t-EbQ#c3JMOD=~py^mw{5Qm6epyOddu?
zMhWY(H4mmFfzC<*-HOJ+;ZRUuAi~x9$?qei7vFo2e?GH*o9oxw7k|!AnluSi-mKsE
z%d13WRXXS-^al?TR8&+J?ARf(|KBfdNC^bmRNBzMz$0noQgX(s{P(xF;dY=aB`(26
zXao1ACnYr<I&?_uys@z{XgQOv+M-`iUR+%K<LC4F6KBrs{PU+qLxgK;aqZntel9ML
zHiCx5@;f>_rh{39NUW^9pP!z-xVc%~Z;nOdG~H;>z2B|#=gWhZzA&@%X}p(+3JYs<
zY-R)9Y+Gg7ASWcmBrPosS^#r%b2_MLzo+uE!t~RHzrJLGu0^}KDRogYS7J&^$iwGf
zK(p_emsA)WA|fO}SGR52WF+{pW%Ks!?lCbkpFV#EjZ9COJ{@#>8|Yrg#hjo6I6>!7
zeEj$kG%B%Z@#2S%9yQIGBLnK7gD!gpbx)38*%h`nYGLT=utmu)wroy6uViN@ck|}W
z51&6b&z&m^DyhDFDY<d$)*{g4qH<QOmlxNaJ9j|WobLJm?{`N}4`e+GsE_>X>+7#c
z40GewdQaE8dQb4*dKFKnsHiAeRV5{*tQ+tF%XzbBODicW8x}u1!<GL1{r%(1d}kY^
zosnQX>2ZB+#73t0`oE^2W9AYLFnoD+)w@JRNl8f+v^L{6ub|*dD-g??55Wq23%WqN
zsj2A#XeHPI(B@9iex^%HJhcvcwzai^PCozh^Rug~=&L_JKZBOd&oa;N`}3!U;lStT
z=NTE8+4(^CF*P+eKYaI2&uH1XU$2`4Y6YdFxb*e)zr49AoR*gM;{N{qr+!{t9S+)2
zG+}~(Bj-_1U*Fd5Zf-AcZ_tLeCCipA+OkFDKzHKJA3rKUQ$4fI^Tp<b{QmRj59t1c
zAHRP)t4;3gTO91=?fvlaW6-%|8lYviEam0pH*Vf!toZo8>*nV4<a>K6n<i)7zq7L#
zbZN_yB}*1;*Z`V=(|YdQ&KD}_b=^HC=EI=_jm+9S3*vVaFkW95>wJA(Ea?7A2GBVG
z>*DwGRaaN<jbQ@~dql$nJuV_b0(8pvzrVke54CVkP~ik^L;v{r_{PM;Y#Jh5IuRQj
zN_;Lkf);2#DYE2~wPI0LR=!x+(a{mI;qe5u8=w?_eItkkO7SpO*73vb{E3;FD{FER
z6B!w_&j0<nX2*_*?3*Q>3l}QRGR<aV$hf&lwWp_N!rZxQZMJXRcyMd>b(f>cvRext
zI)Ub_)6dVFIxl`_5ona{(rLyo2M##Qm^DjDRh89frq9p4&zD|Y?4JDm+}x&1omkfv
zcf5nFEe4glyUX>%*2jUGS2u3o);{0U+iRG3h~>zUBQKsZ{F-T;zM<k{l7zJM;uR}a
z9I9;RlLhtk7*8H~{D>(udV5}I<(~Zec5m+Qmj_*L(IKb|o?!-Uyw-`^6EPcfExMEl
zGrUAy6}>&r!^g+v^|iHvGBP}^PK~14VF@1}9er_iwK!<iDQKG4(3Ab?^XJKbetfJ6
z<`)!vsRBy9xYF^@&#?yotK5C64xT&5_wwaShPawO(8#iF^*4?4{BkxO+j4Jrb-8~H
ziHnnyGR;!4Y7^N1_nS22ey7Nn-{<<xwE`U(&orsiJnxQ0%#H%a>H6`<&df9hT@_kU
zRRvm$kbJx^^xt~BuCA`8`Sa!f{Qaw~qs!1BXIrJ9tnBPy^pS@*zBd2t?(+Aq&dTol
z|LS}<_qw>fT%gX`@6V5zYDGZ@QtkV(=+FmCh8??iAHIKI{`2$m;uCs0I#wh;kcF&=
zU*QNE{lH!<P2>YD<+ya|lFM-gC8bqDkRFbb(kgy%lkYK7lW)bhKcLyU`hPYI3l=P3
zU;uR^rs+nniYfp6%y(`2Wl_*BfoZzYpm7}uDXFAuYa&67wu?)>#Th`YhG{yHN*1aw
zn?T)FMMcM-72n_8-BI}1t@Sl*2z_tW*GoxOcR&95`8k~L@UtgRUc8+&6Ljf-V97Pm
zgvE0I`C8|Bd3ggPB32xA*_DiQB<K6{qpUl3?i4*&{pCet?Cvs7k7d%JbtGoFw?ZoO
z^78s#UtgbXC<tn#KnBW`lvZ8$^77hH`Z^4BC<Evu<;TbSFRqC+zH#$r;*%2-KYaUk
z?RM_zkiA>8uOGU5SC)^D@58rmVxUHgN2hE%XvvR@%dQ>}tIrw13aM^tZU&uM{Ateq
z{q?P{MYvk;-BYx+umEjmo^UdSp#i<xttxeYG@YCKO5yi+cddLDRX=+C7<Bv&LxYMZ
zsLN9J{$A|Mt@-<Ys)enOTYI*`>hap`_YO@|cGvnF_xaDy;y<5G>q}S^ENDo1#4BqR
zQo=GfH8u6?DaRX6o}}Ekc{9^+;yciwEa<Y9hYuINITpSy#xX2R40I{<@9*!!e?+d=
z2Q5U%$;|~dvokL*J9y-X%hNTGQg6e?je=A9IyzSTn=HcB>Qur3YP2XR`GV#w-|zh{
z2RbsU)u~ZTH|oHZD<YsqtD_^Mif2=AFYmXvx7+1xt2+9;tyX|;?mB(?@ZRe030YZO
z+S=Mrx!>t~PHO2E*XQ!`aB=z7A={qS1a1<GTJv3H0aq_tkja`ww*)06f8LTePCYfn
z$|GohYilcLAtGqiqO2=u8vRO~+lQjUgP)(De{C@}uj1Di&91Jl1pyifiHVJ%bM5Zz
zDAc;{F^NT3SQs?A7U1=fPtJyepP&E7@88Lfj&v3j79P~!|A&d2o4cj8RZ&rqapT5~
z1*N5;vQtYuJUlq+emrD9a`Y(Z+RbOro>`Q=k+^f`j)0t8U*_dyi60*w<>28Fkqzy*
zaU%jW*)ntHOs(_L(b37DpPij>`f1ao&eZgDc71()&{eEEckVPWH+PSTne*v0s1ov?
zuJ`cM)6-3pyFm3CzugZ8(45k7`T8|6k3gBNqk{u<IEi)Hn-w26_jGi0TsaJDVNaiD
zQ`r=^w+ht1K6vmT=q9FiKG`YH%irBOX#fAGf6ec=+cU1OlLehYxy*Mqmyge`6IZW>
zt`(p9`0?Yd6WTgDKw;ho4s$_kzN;eOFjp#*Sp^zAzoeR&n8?A&d2zO4ww_+V`L)s8
z6Y}!n9`<ee;^gAOl6G!R=kb1dZE;bChLtNd>wdjd|MBY=m){E6!|nX-DxMZ4F9cGI
zB-{Aq<K7<knAEb^y+2EFZl0#5=D`;i7k|8+zkgx)`nVkxAC*9-IqcbE13H31*{$b5
zBQv{}j_M_Ku2!b!=jJ+BRau=neHwHu3L`VyfddB|N=y=W>{w9M&M)s45FoHFX6K?$
zHRtEqZY+5j)FWl;6=0;KwCGnqbS-9x{@S>`QpV}$K&N8G?bQA8<Ktt{Vxh3LQLX3g
ze*082f;JDC8~|ls7hXY700^48ys>a`*|mPl77@?_!ufW!;BH}I$*g_63xuyuJKit<
z_{2nI(7|>^5!deCja|R*xrMd0^CXoc$B!Sra3SF54l8y4c~_jQ?k*0{5RjDYjNM(f
zk|%Qi|9`)Kyja}-rRu^gt>Z^oUx5xx1LYnDPy-&^wE%6@_z!O{TskpPS<zDnbld5*
ztqcWEPE6d@=L$L(Um4^;mn#Ar9}5Ty20DYL=9c^h9jgRd#sXdx6;mQJ_ZVZzs#BmF
zVynJpp{+KCjN*ch<<7gi3$zz}>b&PqpMsVx`T6-p`MHJckKJD<3t92)p1RoY-o1NF
zL7m6J18gc?3tup}fWa)#H8A`BeDdD9ZtCf$KRzCpe{CUnHGS#Qr5?V%Yrh-~VgT>c
z3UP5+(to3H#kLLi1q3JRB_0Q_0CREK)dF7e#TR(@QSGh{lj##CG)z=>KXm2{4<8>N
zs0aI`$g-=u8?^fL#_ijS<M-DsO6CH!pX>j=jt}KKeC*h<L$`0w_LkKG4O4+?7z2ZV
z5|Oo_J@hd#F`)7JXJ==3_buKG+U|04vbwUR<<3*{?@m&A`IcdqiYF*CK3sH{@9bMN
zIq&|yUeK%}WU2{t9cWBU%!J94n?WaAetL59#qI6uU(5i_^$S5aoUMpEb^0`DiRRT^
z*DhTWs;sOmozwAZ@uyEkpv|VBJ*9zxfm5%4WOY<hx+Dh5RNthPlrFixu?PtU#ov<d
z8-**D-6-tX;yg*^qF{?<{l7i8uHV~Ry`67zK&>cI-IBn&MctDo37tqW(p|bT9&|_5
zgb4zBB^~1TR2ZswHZ?XfzIprh;hQ&W{v@ZSs#?uE2U_uQZoYm0`+dLp^z`%$jE#k5
zJvH?70^+l>v|?gn0-~b2{{8)}Y-$QxamWCgBvi1olk1nWJ@oACY*uwuC8bsK;R!Uz
z)04BOr{~J9YZopEoS$dA`msxhJm{`B(9y~B=gWf@V84FdoqBrO!qn5#K!?t%cpm!n
z^t9`76(uFxLw(MsN9#cKCa4(d0@bP|&|+v}*^AGz7i48*uE-q-*AS_)UE@F1y8fSy
zm~K?dv$M06?d|0c)Qc_Vk+Bc}9l*)Q*S352?h`YjihqC0O-W7FlwZDlIViFZmDd0H
z$ZnQ<tHu0Yh4bu>9`30rDGHjJoa+AbKzrM-t&Lv(rb^bjEJV`d{msqGU+g#pTIZ~x
z!4Y5kb?OTZtHy5bE8-Fo9KpfCOO`BgP@8=4&>^R%HD6v_ys@)*`2z3)J$YDyxcBSt
z_xo3G-KhQi%vX2G!e1InN=%?RU(gl6ckaY6IP9<ct1$hvVd^On3oENfKR!MN9Tg4^
z)LKwr90UhO7pNWt2L`kr47`gnpV$H(#%X+I>Fn$b8YyQ0^|>S@B|&EkRf3M;%)Y*^
zvuk-NbTc1|=OhJBAtz^NK`E)IhgPjljLgi;pvzJmye^r}wJvvier_&kO*n(Tm<VXa
zu%V%#r>7@q9qFP)ixfPCqPFF5s;jGmmjGwI&Az%yG-_*>s#V*$2alM({{414AC%j4
zbakixU-t_%Ne5~Cf|hykz?XSwTUbaOJb3VG+;QK#AyaQ}&sR1u5Ma2lqcEAlp|H@9
zVL{+xH_-Yu&{1qhyT!RrgW3b_pl|@!P0(-<6nqJ559}&^f6q20J^k>xbACTfm*s;N
z)L1cHEiNl7^YHg)XYiQR^6u{L<n!}vKYaYi$N*a1y<W_wN8VoU?(Xt-r-h)sN_M~B
z7+Y9duZ~gn6aq~YY`<5<{r2{D@hMYEB2Q1#HOzus4$lC}63*>>i9bI*1??2$leJQ@
zSSW$m<f=INq|0%^zHaU--~aq9Hp#uU<<#dnb3m&|GSM2F(|4?#o#p)c+FH;~BXF$=
z>II)U<1;n;)925wF3L(uwnuSiiom;|wE_VF6N)m-z=gaF`pVbNSM8vI#?#YuL1SDz
zyu60l*K|Oqw1GC0G>DhKh~1RZ`C!Ve<ota8>gs9+hr~q1J9q9RBqu9dh+cJHxpJk4
zmzPsekdTnD@WhD|8E5*m)&2dI_~F69MUOczV%t^P0qOZw#KZ(_1qGmcpG@Qa{q?Pz
zpP!!(TETMgKqE7&in5YYmIU%pb%zJ&W<JmffS?m!7!p92rPlm3Qc_k1t$jZ^S$%Qs
z?{6MnUP5!GfEHTWzA<-kL8<RTeuMVp`1|`?SXm|g`0x<aynXcOk;3%TjC+3UntU>)
zqq9?R&Xg5(8oIhi7rXagSQV=6F^Po%G?2Dv@nXfvCm+0e)wMDC_#)?azNX2OGB&53
z4f=h{I9<x&b`NYVz_|xkRt8u6`%@{ac1aer$l>PZ^r_|R{QUgf^78bewq~)qySrOh
zS{^)kl9QQ@r(xs9jW2c_l8}%HsZ{e665(Q1@w_y9zxmXaS%r@C?P?96SNkqf<^o+T
zUr|wU;QoDiVRgTj?rv_-DNGR&5ehmwJfPcFdV5<}uU`FP1#*Sc;gSFL_I7?jK|xTU
zfzD&fzP>K;#013?=g))E^vs!(d~!A&j?HYHeO@juE=$Bf6^>F?#|_X3!U{#uO3>QB
zzrVMyT&W3}JK`=bE}qKxWy1yo(7{XKm77AQJc)^k5gQU1Pn|mD;x4FUYb*Qk;lmSW
z&V>B?16slWI-$_<<(Ai>hYwG^xZE)*IXQXCv}uc?x91fU6$SClEq{M6w!~y^(VH8F
zTh~cjm1M}OU*wI6`A`L#3Mqc(V^jAhV&@tL1|MJFkC*-J4_?0>Uf=|3vUNk7Y%VVK
zK>+~`EiEi3Qj9>Md*+PKPwz}6keUuqc>o<RhIlON7-H*zmaN15J(b3wA!8A7ac)1a
zD+Zv}yo!oTK3nI19W5=c;AK9Ijg5@EN?tM<8*lbnZ(aFm$+XFx3s2r>oaqzB?pe~`
z*w}a~cGcWDb3m~LnzQY5v+C*Qj=K-q2J_^E;GG?X%#iuB*4?|UqqbxyT1g2C2JTJM
zuwno&EfSolmw9m!D`@f$bl|C=px}>pyWbc5{Z)E#BWN7h<QS-wM`>%CCMThfekv_$
z(?Z{URPf8lXI<x=J29YQT2qq~R7`Kl6ozhUncDbeU+wRG-{wA9`A|z!v(ZPbdE-Vy
zA0M9!TQY-Z%$n8Jw{-HP$&*2YR9o`yN(rm^tSFc_eR}(qD<Kw^mYg2$E-oSeVJk;E
zzMR{fettv#eY=#D6wumd(6Ykc-`+AZxVpOjc)5K3hr|5#pktgiY~3n4XBueAuL?7d
zmV-J;l9HXE6-O4k>;Kz<Dq_RrV;mlCF1%;qdw+tro;h;{bnruuoUIhNxGjEuPP6^e
z;X{We%$?i2%y)Lufd)nin+gLbXJ^*s>#Ff}Fe+kV7TAf4i~o5Y|G#Pb_VT6AH*VYr
zTCM;2`T4DLAR{D@-423+FQ@J<e}CxeRZ&Sv$p8%z28QJ1WYFmgy;7!4+qav)yR);I
zk@=tfw|6!cr?l?>|MC1~+XPnM8={j=2&s86xlC-yVOlvWX?NcthNOlK7HWP+thtJ1
z*%?{cl|`a-;x3%lFqk2-Qqf4ETZE_E(>(gfMX8|129DN(=Ee;^Dhqkfzvr(HG8c9T
zczJp5p7_w8i+|5qS2g`=%W<uJ&yQq(d~{UGu4c!>BnF0t*^hs+F)*08*gR%nXlUz5
zmw9k*mT`LDuWxTx+tvQccyeOmb+)V9^6#%JzgOwLE%)`)>G5WBITtX#xVX68Z@yiw
z)nWCLx3@y4rQW@ku5<d*Lg)5(0Tc7HZ*5r#GGbrt@2pc(G$$?j`uckIyE{8?ZA@-2
zdw1ui2HS=GKc7iQPAh#o^T+S&Kls?i@9cWN-`V`r-`r0O3=fWPd?Wwswip8g149E_
z%A+HlRsa8f|N8s>|G1SaS6Y?5nUQvW-r8qpXRltg$jQ*q@YKnZf&1(J`YdN+V7MbR
zFQ0+I!TE?W9|J>1N5wJ5cYB)I`Cpaq|2?<t&5gixg_ZUH|NVOZ|6l&y`u~5~UNhV;
ze{i5N`rhw%yWhWhyZwINl<lYL{(L+xWm~o7+Pc`)EiEjUE!}!$t+(BK@L~D<x>b`V
z3H^N}zCWO(WQ)qn3k#jCYJO};N=gzD7hfK_I&9_%({qnMX8iy6S4&H4(&?v@Zoj>@
zv-o++?QKj<OjmZ7=kJWsyFBv)^L_ak(2=K+)2^<l6Q6HW8KmwvXM)PoB}-mBogRNp
zzy9axs^914+pnK9M`o^FZIpYT%*Qe{1_oXx<`>{#aZ|OiiE(b@x%mIj`TsH1>lZ9=
zP<HPFop!f1@2-`l3}16A0|UeM_UF<J3>O4G_AoOrNGZ)LWO%=F&6+C{mEB9ez6vdU
zcPBFU))vFLEI(M=4;P-^E^vF>-HbN5c7FM|_j{e&`BrY(5@K8ZEhHr+Wv_IZ?&%;$
z$HwhKwa0#aeLZ#J#D#zU)bPq!Y&du8+1c4s=gnKU|IbtXswWfOc|@zO|NQ*?Y0=Jg
zymQ3G#aAy|=C&<YTSv#Iv$NC7(=*V^tLxF@$5+=x8ecwXmwA4k?XMq?`@bII)}P^L
z*woDZYL;pCw6wFczBbp#-`u9#et6+h@9D2rE}!=)NS1+t*IW29BPa|QDuOF3cmDeJ
zHv0MA_woL-OgihYFf%ax;X7~6z_38^kt91bWtU%jb8|Cj>G08G$5y#^i@mzM+<)%Z
zW_JEn3l=ySr=K$k;rOxd>FMdS{XTg9{`PkFy9LR=zr76&3|!dN)m4?f-Ri{s3uk5+
zI-j@uowN60v8R+x#fD9rH=EY}`r>BXaBo$pw`LvAiE88<d0US~U(oSZEE_WP5v
zzklD?Uq3U`So$o36}$MII~{_`SJp<G-`uwL%a;<{&u5IiJUv%#KE6q(wWZ}nBfDI{
z?{9B;r!p}-_%GqW4)URi*4C|Cxp;Wie7^U6y|c5kuL>gr!ygr!`_Rk^joLer>-T)>
zTC`}9h_rO|-LIf+I<ri(#h70l@a>VezgN=aZ&mqe$xD{~g+D$dZq2*<tL=5}tt}TH
z9&X<okrEabHZ3SPc<Q7{i#j?uE?a&OmWe4SHZ(Ns>g=4T5*iwsd7y#u)t#N2A8Ii$
zNU5=10Ed0=x#{tBE1B8(VybH&9%A(jij16j=+L28Z|grCWZ!#@je+4q@`oB&qJ!ke
zgmXKKpNj|xBv>&sNNv%J-IZ~)OSJ0M%H<+5GBN3ESFQ5W4qKBE(!9ufnvUUI2Kyri
zS+~DCsXpIiE(3!@bK1>qxwHE~p~7$=T88g<sej|v+}-zn-`^h|9sPQ(4Ff~N?PH&L
zp_!h6fmiUn#ewthANSi|J2%%_wYHr3*N2CPuWn9156M`6{?wGdxZwEv+uP4Ysts+=
zuB;3;kKL~0-PqWeb#YPa^sX9rN5@9F`agvrWy0!yAt51Cmb~Y?9l0^76|{-;>GS8W
zukZi2^<mKGQ>RZ~-B(+kdv{l8W@hHH;+k7?EQ?KwpZUz|EsRY~O^w=Dvvc2%N8F)d
zVXy8Vf1-2x(lp&@o~w)u5AN?^lm+?e!U~=EeRoQj7#I$m??TJ74fF5!$y%FaU(@lt
z&nsU0;UN332hIHJc5ko#{w``y#YXeb3?=~&A3nTp8}jTvD?9t@`2BUW43pc0goO44
zq}^Lz|2Mn#$HVqthvok*xVbs~dSrKR@6}67y-ib22soGSYyYiMxZ7gKf^~cL*!0TV
z$MLm0$L=o6ox)zvz)+xG$ZQ32A2Qxw{PR;PXl>D^-00lf+pgZu-yi!vEcWy!5gC~^
z2M#zmPi2srm3n$w=E+H_R&{@N%&U0RX|=s(ecaxtxmKl@b`(A?d2&MV>C>kxSFQ4j
z-kx{$Fu#4yjyt>k=Gm-#e7xU#(!1U7?ONO0rS(4PK7IOh*Y|tXTXS!3bF=iYNj)_s
z`rhvR`*v^d?VT-s;pq2g_g!6GHBC%HW}D>(?Jj%k^PGX<!h-@VjusXXS+Zb(g6AdB
zA@<9BrCHh8rPncCxG>kYI_&Dzt5!u%I-<7aM5gC{dvnvv)AQm~?eH(xqVr!qogN?d
z{@&iNr?l5+{QmZ~t?MiYKY#iQ8S^a(2b*r+%8$GztJP@#`_=08CZ(@J+RigF>~NM@
z#*7?bAohdhJKpd6En&z0K-7Dh&c$GV+tB<UF_WUU=dHc}=b3rc>$TfeJVCi~vcKKR
zM~{;7)1`_(J@NFNXA@~?Xqa_-+gdJeZdFfFQPEjOsa^j*_SZ}3ec@fWa3LsdB_$>K
zESGrru_EvF^HWo`mrZ`yT=nI}!pqD3XP;wWSa9$WTM5Vw$hhwP=kxa0A06#3eQ<y=
zc1M9@`1-iDoAV;4^~u?0t>ANT4h#%j`0CXw>2=}Z;j0%ddUWgcx3{;i|E|3fFm>8A
zEmPA_xqf%h%G1oul{RwyOWwDAE`M`lVYj&ctMm2$Ha`q{e|vZNdLbd9b$j`Ec&_~T
z_?TC0=F<`@U-chLkJS|%+&|mCexF;v+}efC?bm*OW@TWgljB){9&8`7t;^qCS>V`w
zWsxhl?UxJAzrI}dpE_;YvRALN-rn0AZD?rt>hA9CFMSwz4><GNE^+M^d%5wrT=4gI
zcVDlOwW$c`7S|7(Z&$l+Z+KMHDn41O3hT=q;&By@XJ?yVpJ!YBq{Qm#w%prRubtcZ
zuEziW74BS`rmCi<rKRQd_*n1d8HUMMb{3~!_WZys6BBU#!^6X`_g-J*%B`xZx-$Lz
zysn;}HRU@RQzNxBG(LnWF);9UrQY6_YsG{d&>(i*ns)iR2vJedTbtASLF3BXa&Kqd
z-j?g-?S1*)-fC0O5lhdWWqo*Xa9J?pkDc{@9?MG^BsA#7?pku?N{FkgtLG%pMT3V9
zIo&P29t&zkJ$m#gBsO+!OA8CHq>+oIrDfac_j@i}2=JY67yJKf{Qsq!)6cK+oo#l#
zPTc#_rqt74{(L_FI{yE!=?{b6pFVv$I4^JAw!FKmZrzId`u27>$ge8`7hl<w>V3H~
z?&{X;@W^SU(epRzc(?P(?s9hBclu#LLBYZQf^u^I7VooG_nWiB*_DC8B<D^8AIN`5
z_`rHuivrNm2bb=a-(P#`l$U2vZthwYO+`h=$jHc9hRJNqFBs}J?bu;a`|s!TQzuVe
zoTeKc5)z`~+11k%l9skCuI8hwtDBqGuXo!XowxgaCS_gt)oa(ZR8*d{y%rS}&APQ^
zrFeIZdsWr0OP4Q$>gcPh!?pGG{cqm9S@mw`bCZk<3ca${Vf%kwT@S8nzV>;0c&spY
z`SWu5{8dYqxa|LNR9{3^R@c+2<i!Ng0Qig<5=W07o#|ov?(g^e;dy!M;%dK!?)`L1
zyZ6@vCQnGs$-p2bng^+qk^K7L`k_OIO!Dv9q^6~v+Lp`8#`bFO_j{mJqf%S``rZ4w
z@7ADVvdx=u!9y=!-_UL`-7R&0e^r?;xPI;0tAp(FSN49tx4Pf%*NKu<{uWhVUTmFx
z@${)vB2rST1eM)1l$D(|H8q!g-jnwC*Vj`gP6X7|?PKGUiAc}={OqikzyJ04f1ku{
zKb=r+<2w6$KfCywo15Jk85w)uJz!#Bcu>m+Z6zT&_(QOZtLw@&YkVf9L{8gP`g+;c
z?CWvS_jeR7ez)_vTyQ1B1&uvF9(CW^QMh<s?YGFO)24a-$}1>)er~RmNyY>(FRw3;
zy7i^jeUWu^bmZdW3rk2?kaK%lYGl;*yt%)=zFuxu`)kFLB}YmYg=23nl`yC7TU`43
z+AN#OO?UFPpE`Bw%O!7pP%E?F{@)Ie8&cEKR;^fZqGZ|ixmKmGmf0`&pC6W*y7Z+F
z1H+#%Si29!N1(Mo@ArP6S5#DVWr?S-?@S|CP-T66U94(t`RN=#zrKfF4F5EYjf1D9
zX1=_%w8%o{)R{AX4xW#gwzT|S<#F!PeW@=lEUfx|xBTm!;`5+NYtj<+c@<8RuI#BS
z-uwMt^{e~)_aAin49bnB+1E78&BJ$>y`6OU;e`hWn?VP(f})_vLMCc=+1h1(b60f=
zt7pBxw|Cj(_d5=^^RF&_ea$>3|MIe4K6$%0N0siEEpFxpty8uA@t`?sXVKDK<?r*X
zE^8k;d^k1o8vi?PKEAO1b$?BgkMXFgs8lTEVQ6SOxGDFxnJl>7h2(Vx`)S7?Up(3^
zesxpo>Fj2Y_xu0v<Kp516>0nH>v^Tkd}OUk3}Uzr+;3@bKmD-a#fyuJvu<s9smp5<
zHEpS|x?jc03*TdQm3Ye6ewhd=URH;%U*$br57fGKa(4DzF1b1HuGQ0L&$14;@vd68
z4pfd#nK*Ib#l`NcLsy4={iYwi&F8$$=bm*jJChb%+nto0e057^@Xi=LR(AI5k*im&
z3MwkvWFyzlCuftf;=&$j*_a6vCkDQM&{X|y=kh?A7=_yJ&r=X>1Ws@{ck0xsEmdE$
zN?%>^1eHn?mEEUIpT2z6DlJgsir@avhKEHA41bs*y&&Y!klJEd{0!WA+J3(-+lrMz
zN@x4+wJ%=0c+D5$eQ9U$^N^^hRZEtr=ue;dyud<4P;lYK<l|b(%FY)rUNpbEKmWd+
zZtSj*)6@082Q9Q@Wo51U^YQrAh0g50b1XKV6ZqIAs{Q3^c)X^)ef<7^U)S?auaXBf
z>0htkziz5__^GEwD^pKTE4`+rr8Q;Jq(z>S)n2xW$6dG{U%&R=-fC?vEw9_#^UXte
z7#ivm8Ne+*B)2;>o28$VIXlNPc<a`!%Yqpe94xY$8?`lS>ZQw<*YBP;fByO}U%t5g
z++Fef++0v%e91F^Yvt#(zYqEAFWCS8dEV;%@ngqceZ3xkeS)Gh&(xVm53-tzOG>VM
zKCjv@c$v@6cfbDp{Jb^eqS9Q8LZ?ZfhUDIl$E0^vd|YI1%*gN|+Sdo%+dy&=0|Ud4
z$&Vf-y}hx~IsM$6z_74sixw>cojf&l>eQ9q)AhJGISuE&D77!KPxAHco#VHBdR7hh
z;pgV&6(16K<!mC<{pVfz`1rW0=l8qi^A8<9%sYMN*4p3SZvT3B<oI!IJG+19Sbxsw
z>f#Cw55Hfqch{~cQBl$Baoh9n$Azzt`|2iz=;@-mYWso5A2ZI(Fx1k}n2>vWla6;Y
zJAYV6$P^V&FJ+ch>8fSEv(t85vG$v1Q~9<m(NjxXd-CnK>$boD^Ye4mww#$t%F26Z
zrk{Cpb94T0<7ugx$9g2o7aXf^X>T|Gwea)*?q=@1cMIF)E-iBH{&FL^e`WReccs_(
z<ZM<P?G|6{Ki}^9J#Agx&~`rAJ##r38t!j;BX5<&h3Z5GhCer;&Ht;{uFdjeeDM6=
zkK^{Qdd=@$Xkz6yNjSi8^vID6NcBHi#rE%)%b-@x*7EmphnL<1jjNxXW$HaG^=`@h
z+}ogXWmn0{c~!48^{>u+Twsw0a<=KM{mVhE<?HeFvDRg8z{#wsiD~JwWvdn~a$3Ll
z+bkm^BN1`&bgR#Oj~_JM{@h>x$C;Up=fYC&=~HISs(Pz1LD{`;#fA+5<#$V`m%X{M
zaK{dd(C~0=MMX#FHl9FGp$X1r=9n!qYj!@F9Z&Zz_nW(`S(QO*@}505si~=&*4EMK
z=jW~6Uibg+_w2K?OxaGIkuXeZ*;V>l?e;d%;6VDkN;geS&C+iX)0R${AYl990CU#;
zeR~%Mz28;!b=6Cj{ee+YtFBxLskD*%`tq{-(xpp3RoF~ga&2vN_VGShP-6Y}=efPK
z-rmn~l~1SM{^ye{=g{BXefjzP`gL>W$mHJK<m&3`I%&y?6CSB)X|Ilo$A_e(EK$)k
zFbJ4m`)%gQ7|_T7X0h?-oHM`emuB;Kb?3LejlRdtU>+P7w=QmP)!l-<o|Dy9ty=Xd
zX(Ffzj@cc)9~2zCST}mxisa*cuWoK${!(WC=R@53D=I%f1GV$!_$|M+EjK#7_Qi#T
zzh1}x&suSAx5bVJ-&|c>GEPoXU1rR{kTC(;(ML)_56Y+M$LCowIw*_C$*lujq*ieE
zZJD-~)~RmSeUHK2;RlnMn3zn8o_OfS?3lp#<@JrN+0&Q#&tF&e_SVZcH#dL1_I~$!
zyV|c;!`V)qc?4<<BuHWN_>Yf|ebpH<S}t9_yfxt<Q?G=fQ|zvii7JuPRA26HHvIJY
z^VeJ1>u36ytXi|i=k#>_>*Db>3s0T$y16Yj{q826+?$(@2F#V5mbx<g`npvsRv65E
zG&w6fTU1D>=<wIBE-usDTUWYW_cb<izdC*9%#_r~s9hy1W%$~SjE(C*7*9)mIk)`Y
zM<>vL4nL;r7#OxcSUNp!((SilMMaxH`+HAs`T`mNe12~3<&Te#n-)B9@SSUQwPcxK
zWo4z5ecc`zzV=;ZZ&!)wM$Pd1Bzbw6@8v0)!Jt5Lb$6eA?xQBZ&4&iNUoVtX)6=g<
zuU@<M>Z_}(r%srVu;7dipWcf6%gcO=EM!)#T|4#g!wbuNXRniGC{niH!pFdncV^T7
zzZRNEQ3PeiOwYXys==?ViCnyClTqy6s?gY7B^Or&E;dO##9}GKce&He1+91bV+v@z
z?h0sssH|O01n5Qz(7po^k&yKM)X1nE1q&BC6`SSVSrPyDRrslM=dQiDxOnQUS*xzD
z4qu&ndmCtMw(Q-Vm20E7ud4t5Z&~nOJ$-%u;AK7+*TwF(*ulWSP$7#gFn@S9H8p*C
zHaq{-_Wgg?z7&~XtlcgYF>UFsTT%K~e#{fq4tufl`Mk?Zy{D(#{<bxG^=$L}b=&V%
zc|ShZYaElo#xBmlz%Usztuip|0BzCHHZ=|H?Cjk2``vEe=Rel`_))<tW#X|p{k+*+
zCi{|?msD%NTyzI@u-C=yT?HEV`S9Q%7cZ~r+%z6`@jJ5!)-xOo4e?1BwI&0@12!4H
zcAe9c4nGX=@#zT)3R?HKrM-RjxzCdF^?x>kI+t6suY)cyF5&yra{FyqNy(O|ty!ga
zzZO3~2WoVBdV0p`HLw3%VIyUn*2Bfcm2!KV&go0n)<%Q6n5U=fYunhw1TXiyx+U|n
z&vGV)2h*_!LGtmwlTV9QZrBizw>?@_RrPwCtg@2QE1o6Cj~$zJ?(3|Fhug1LzrV21
zSxZ+p^!z+qQAtV7<(DHtnMhPbq(WP;?!e2EtgEX+z5M<6zpJXN+jr^mW$C}V_gB2{
zum7_cbb_&N#0CduHXe{ax8>emwq=Wn=cUX3_G>}ci&cMrXBxxB&`_V1gfUjbz;GZO
z)RqDbyxiEBtm^sv{QT*+--ZPSPK?o;4jSLyv&SZK+R_ah3{+KBK^M1}#MC~2dwaY8
zwA8EB`)hxHTeV_EfUB$P-mS0S=IfZ{-&<pTzb2TSPv$}^w|L3k-zw6NCw%3<yE-yB
zIQYE+v%{oMpFT~QI(6xrH#u`{tG9s{F041rz9yl;%&;Ia0b4AJwYIiqo|vF0Wt7sP
za`N%VjLXY>XPM{ED|>%$t?z6zNxd(9lhyra`F)UPWo4Bz&6<*wlw?x%B?Hu6d-?L^
zrrhY)*VYDKUl;rJMsokmb6;jnR`-8(q*M5M-1MnaPrfa?e!KkNpGw{6Z9WqxPP}*K
zv!+Z;LGsh5PhVYKeVzCEY?I7It5#|0i!m}>*kFLspJiYukoNNSep<BiNzu-bkdP&d
z-TP0yELm0l{+^egpV?e?`N@+fFaGhPLR3_A<)%$RpvCb^JSR_?Hf@>y{y#yrzrTep
z_nYgJUUhc&`+ch;H>aK4q!T%9>CMgQ+27vW{Q3<(zAd%Fq`#RvPtV3Crk!7Y-@{$E
z-+~%8;@u1k84=jiop$)T6+3oBxVpL)?Tjhfeb=h`+nT6tIV+DGaq*pF5$NgZ+11}4
z9uP3$WlXZ)T&vQ{rKdNENJy*@(~YWFd7^yElqnkO>h6BagMDY!n4fz5u|mZYv|y#I
zY}>PQb65BD@JyZ=XPk6|qxAJP-)*_twzjdL=6+C6(5p8ab-Wc76{{XJvR~O(TkX6w
zt+3$W*`>>uXCG{0l>*iKB`=j;?tb5^q8q<2=I76!Rd2Um_fcbFcyJxNS1w!#sI-xD
zb$8d+)buQVel9d9Xwt6I*J)N~m$$UH$4md)GxNcNgs-o!`x~d732<_15<hhY)KzkD
zXi(AA(eXJu%k=Wg%gfiV-JX5j?|7fA@zm#~SjVvMA3n%x{{51-{>isx+Lo4)wpCvy
zq(=Vw`@VjC@$+*pe|&r_Wl^wTncv(jD`5tP{Z9?h8|w@V3=dXkWo4yAPHSpv5|NQv
zGhu>&Y5u)CCDYDVKA&5DWplcJYg^l^m&@m0`}6a&Y5l(%Q2WTlB&4vgu<CKIxk=rh
z3ZKb!A7E<%cHYgi{qx~4XbQwPz1p>;WQ&)V*SfuZ-QAa0g|7bccKiKRyLLrYR#tZP
z^q53soSW=#ck;te-hzUIXHB!O`G5vcH>I8iMT4uW>&r(+ySw`OuFe1dCq4JhjzGWV
zmrK+b80t=A??N&>=+@HKep<F0lD@ap|F64x<;n`@c0MmZzp$X7Ns}f|78Ms)Z(scJ
zp74)fuh(ZkJvFsxXH3@3O{sIYc6D(rU9u$O(h|?AhppmYzFv=CUH<-FS6A1iZ*On&
zidLV8b~`|QhRDrnw>Bg;%hi4fWMySNxk)E9H1s8Cw4{Yo*k`#^U|86)r>CdC?$+NI
zkea&mU+tBXuoi~p$&)9mJ{)A<TJbT-Gbkx(QB!mC*3{EtwZGqP2gMcWaLcHutQ{ht
z*&fUxL<WXCO8v(d``i6oaxMV0O+Z9QXwi=!6{_m$pd7f&c(0z3QP6qY?{k*<%q+V5
z^?myW|2Y<lo}f7>P{|v+r{d!5nRbgeYzUCA`OrAWZ+RP^>?%fPwi$j#O8WZ#kB|3H
zKm0J@`nuSwi(I>3zth&y`BF5qQYI$g{+E}RL3Q_$BQAGqzu#R}%)pRw0bBC_!Fg?c
z{Q8~6&$GV2ySqup8`KM&yhqQ%BI5FL|La>aFR$DEZ@K+nPf){t-_K{#o+u-F=Ei%|
z?(eJZ>grlmF8$}LjCGk$YisMN6DK}6&CKuY>I%xpSYeiXYf0JLTQkpntnB^!fT{hk
z;^|FK3M@o~g%?kmG9}yo;lqc^J~J?61YmRC4p+H;_ut>&heIljJ9*pB&9zp)y-id=
zV8Ok;)u*2p%{=#I7ifgDonQVM=su~v)!(hM+4<!{qM~MjhM8h_mw8SCjg9b1o4vTO
z&{?hMy~Xm&D??X@Y1-PxPAYkK$FjA(J^S;sv#+kNkDt4D=gys{PMpY?!Y<Cj%KGxG
z`TZ;T^}nMpYuYt}`e!#bCKv6D(bCbGa{FzVr)MX42&${2V}<bqIce!^D{%&f{nw6Q
zjCeCJG_1F(|F<Vb@A}rp&yOA@UA=PU#J1el)>chJ!;iNPB-hmJnPr-tW_7c}wOb6-
zp9D4PgMx!aMMYITLCqH~Ztl|SvE`W$54BEO^6FJq?(J>9huithXV$p?{arh8Tkh&z
zyLJWg&Aji^FK1iw>r3WkNjqgj!;jPW^$K?1on=v&v{=gF{gsuIL1%((Og`@Q>)rRw
zx8Lsj_Pg@!t*xg{pPrl=$;Hhb927JObQ=2Ms|*Z3)S(k@&^9N8%3Bb+I&9KDX@$Oy
zjtd(S55KyzAv<!~L#O)!;^NEC+y9TTw6wgnDYd(+t4qam;>3xk&YZc@t-o)@i4z{4
zK?w;9Knv6+@BAS6`T6<lFD@=NEqM{3s-iOEoMB%xcb<Pl#Edo`$wi9JZ61?s<oZEr
zr}Fc&%<u2+-rABm`Jod7!yj>MjZE_iQ>TK?BUrj*iH4HWp^`rT?v9QNlT^KZ(hs!9
zzQ6WcOgBnHQ_~YNqr7B}U;5nA)0;v90v@b&`7!g-rJ$WLdOKtEL`6kkzPPx!$Z9TV
zXn)e=$-d7S86IrMnlc&LRyEE)zpwUpN@UpH@3*(-uLq4OgoIp)-hHpm#1FI)wXkqw
zS6A1QqMc95c9(v86S+0#W>9Bm=PZlDMUy5?5|Ni*zhHsF<(&)+KTNR&bzRG+Peohv
z@5h0*5Jg4JdMUI16z<;4-25M(PV0lFR6H-Wa*L~YrlzKHadWTU{Qkzq<hXp}r%z5!
zUMBqDxRbN<(~lJ*va)NJEKxZ-*E-zO)AQA}wX<KEFfd5TV0DMe?QOp55}?ylEM@qv
zUb}YcVF9S2WM2_nn!NjD)v+GQS%%4ObH8uey!rLp&AGcT{@s4Cx3J(~FDRM6EYZ@?
z@HlwzAQvZR;OA#&ebX5kE+|BnCI7X@tlt{uFW9pu=KH<s_1ki9Uwe_~aQy7rn4O=t
z*&EmW`C%RK=r(3sLZ|(3;Cq86Y1x1ee}8Y?y7k^E<8_-h1?6pz)|>9FH{BaldieVG
zT9v$5@Z?E~s;a7{rDbGcVPTPl%(7xeh7Z};%I!ZKJPVlZ&wgcFw_e@CBI56_ua|oy
zji*eQ@SxSm7}S%lu#p2D-(K2w>HHka#S<n796f#<RHuV`9-O#34el$}tqTJUrSnQb
z%S6tjM~{LgRnE<^T)bwD4yYRa^z^irws!Dzy;u<;p(HCoyOf)oQlmDdboR;HuLF$^
z2L=XCTC!=A(OUeonlk&c{{H$p%es7B+53BUU*vVLGdy^HgaNaien9ue?(+QReYHQA
ze;}?ua;SaJzhAFG9ncuP>ENl$wTl)xX=-ZDGRd42SMiXw_V3s0pe(d#(V{K2zssDD
zeo!S`kh3rx(6_`o9@u>3h|Awc;`=YGUcYaZ{=Ofe3_jDcc-g;i+xKUFe00>R;=_V}
z?`u099UY}Ci$DW6=^F(0frdIjbNsJ(=X(dezP9%3?E8P*^7nq7rn1s^wprDulj@-{
zF>l`b{OI`n{CxJ~W4*r~%l}^is!SFxT<GQNdlgh}9XjN6^!V}D{`J2mm%Y8Ulv`ZS
zpoWj(fd2)orM!K`|G(d-&YrzGJiay*v@!y;6shp>vCJzg0<X(1$o0Y5MQPSwy<$Z`
zY3Wzq>#J9<4h;+}d|Uea+uPEwuR`;e9Aw{`b=7N9%I$4RN=ha<Hw-}KoT{qp#*G^{
z>6|W5WMJTB#~d$XV7Sxt<x2^uEw<cm?xjPm+^M&>ZQ8sUv|hmW+l}O?&1t=$0d%X&
z9iKiGeSLNHb=zy-Stfy@p;N`XAMndny-?JR+Tx+As`?fCIOI$Y`AJi!F8zMLKK^*W
z{PmBIkAu8^|KGRmuP!cTKm445;m;Z9A_GX}0VN-pZOOYEHCf&N+LM!$OTWAbeERgM
zrnz}IXeP$V+1WJd2uEs4iiWD{(UMiyTiV-Se|UJ<Jf?j2-L9^#Pf3D*4lZ)-290HY
zeRDH-<;s=U_bI#g$pj`QE_}D^wVrOwj(|($+ZX1;YDk{uX*!WfR*Vb{Zq3q=B_vRH
zK&U#<+&n8gyS9Nrz_#4en{?JjZ}$V8&H<Xdt=?ShJZ0Xzb=&XPMT6Goe7pDETu2|%
zv5+#)o3qm9#|qel;+Zp7I)&A@Bpu~i8?n(z-EU4nTG}#DeRuTeQO`+C%*<bJrq9<@
zS3h20S`%1VxpR)+@@@I|^Q>4I8rTlvY9xbBn^}S}_XAo2<t|t0!q@JceSO{4D=ULb
z&)a^_fX@BQnk5C=F}J(yZBW0Q?K)mQ(1B#27y_Mbn0T1Ya<1Ryl?+k~K7A^>Tm63T
zt!=rpFI~C>TEFn%`>Yx0)2a*%3?JA*-Q2vqb!Is?7QA|u1sWyg7Sp-#;^N|~t3p>>
zRlD~{fQIKl3ya#a_JaDFw|14T4qF!ky8d{@s#RX%`f(v8C0o+Y%vi`NtajpI!Hjb(
z3=9kf+*s>Y*28VQ!7eT>^XmUqf>MH&)vsm0tG~WlYM6YiV&yrT)0;rUT)s054wi7$
zfM#xWPG7pT)ca|H#gv&de>Q_=kKgb4+$a7D<aXQB+j4K0fNX=rH;impe|u-~@?YQI
z=UW|4_nB`OyK?19FCU*PcgyeRTCvxG4z%WLcXscW3%$I|S5!_;@ARg;Uy`Rcl{`Aa
zsV{mc9yDleZy(>x#tU2h@!&f)-yFy-wvgGR<IUIZY-nic<>|Teo3NZ*o)y0X^S1K$
zap2Yu1H*!YScjRc($3GTy$$k^aoU+3%%=OE6KsMyFh44=5D^t!3MzNb%rFEkpn9po
zz#t`pt#V&?_+i1FZ|ORxgK~4<%C7iWi!w^n)!kkC^HVD7D9v0>`H+~HHL})aFV4&~
zK6UC;P)NuWz4(1=Hf=I0eR;`MQBiT3@WW(KQ8#<`YS4J$wrydxzrS7GQTW&->x#zK
zoST<Q<QN$0`Wdmbl>fXzZTR(8S;$|1{;|R&?Tmz|h{%a;xslVBu8rQVrK{^ZT|Yjo
zqGAWAd7pWC*-XFI{#7ehTmX%(PM^LUw7FS9!J(Or_tK4x$zNB;|Mg;IWLzf9$ne2?
zd%Xx~ToINOAhd&WaB%SAudlDa{(RoveD0&mUf$kc-|c>%b!mxbS7+zN4-XG-t^Z&5
z_1)d*^LD@2ytMf-W2SNXtNi-kv&Hn|)_|6J{=c_bQbc6QL}mA^ySqx+xF5a-t+F{e
zS^f0evej$W_~`HbG6`hrkH`J5=T*N8OiNqV)z#&b&cyJb99!D?!N|zS2&&TV<ZXW`
zGQaTYDbbyG^UlsT_wTp+wc^&6%*F5S?taZ*|D$=|zhBv)k(b-s^RKsZi-Wq;x)B==
zlo-|c#Kq0qv}x0nxpUWo8dcHz|Nr|9Ds-7sKe!W^OjlxHs9W6m5)wQpWPEz$G|-rL
zR~Of1O*>^1lMuOn_lp-VdU<(W0^I;MWy+GgySrxkHP6@3*AHJGw>NLcy(ON)p`oFb
z8#(?xyR_6BRQnVa7jMnJu4gI32b#DuPCs`=x!*>q{qVxA+1ImPU0DfgDT8jKwvuFE
z*na?P(`ANP?yO}#GZ%sO4O>~=D(NdUH8m}=ntMG@mJin8JlKz=5;?l7^!1e4vsd#<
zo2}TjE2{R_my4h&vZ^l`TeGgNI(JV{*=@z9O+lbxr-e}r41ciC6eOIVXPb3()l|?7
z^#1z#(l<8(9UUFPGfl1B;!;{))@@Edf9h@7>8C{}pB81_+?2X%<;p<NhSoWA)+||~
zqN=X0t*7V5*M7J}uO^_XYL}Q!!~&4j-qZCa?fY%4;(2<yet2EozPReQrjt8A1frIV
ze;zDU0Btp&VVJxpgq@+`|K^<A+kD+oq6*CUu`60~(Kc}ZK5oTFTe*Js`8A(B=PvwW
zoPJJ2MaAXg$B$lqexSvwzUhbBuUxs3@#4b5TU)cIgBEjv_LLSD7Fw0Rn*(ZtHZrq=
z=H-j5<}M3<m<*Z|`1kiWWVIKzGK``8$gi)jP0QcKyuG(~cOd`s$H#JRUpqBbdu!TR
zsi{+^zI=6c^{Y!uyWM)FmU0TK-MMs-A2bJCX^3S&v|;`k!YiB^{#-zvWMyM$Xv138
z+}ZZ|`T5gNi(;iM^!4<@e0_U!Zihug%n%Y51}#dRGDYO*@#CP{Y}w?8%%EwmD_25P
z)zn_S+x^~bF0=hZ=$z=vZQH)_U14Cj@By2f3%W6et~d4^Gy3qN#7fn3TduZ}(xY1&
zD!shAl9H2CL0#z|N=Snw!OyE9wFLtM1Gdn8Fik{6B;(48z^=~Dz^trQ)AV9jefd&y
zbKBa|*VjPPV^wc99{=*`wEk?ruU&86<SbpbOiNYORZviHS@8q)K3QwE>8F<-I^?wT
zZr;=>Q^2Kb>D^|YhWc>y8Ab*MDHUurNZvuv^0#HavsbNH;W2gURM3J!=tM#7&!^L0
z-QK?b+1c64dwO^-uWYz)QU7nxoxJUkele&TIXzwf^d=q9P>80cr+nRyg)e=62;AN#
zDj~6=m0KJ%mT5MZnZcp?i2-JJk>LTqmzNi4K;Ck$pK0bLmq|}hN0PIRE~ZbJKK=B|
zlC0m~-YyG%@EEjgD&>U0-fy?ELCG7m&V6h4^;P-z_pMs9=E^eP**@xrjz>&ex-NG2
zszr+qm2fdI@M2s2!@%%Q!NMYfk&$uIKIvJx*VfGRn{QW}yEk@s8EBWlN}Kt~x3|4y
z`O$d^&)~vAcHh}%zMwg@6BCt1Wo2`%*clqw+ObrN4bcL!vTG+znv}i%@uNpuvaV`@
zR+@p1jr#QIlZd2b<_3WewIqx=d<d-m_9k$3*jf>3>D8bkV3Uvcech)&EfqAv)W*fg
z@F9QN*}@=j*?~gXXZ-u~Gipo5#8anEU0D-poO@$~Bd9KFYHCV}oVIG!sxSAd-)A0b
z;anEntF5np9kk3W_x3hTUEQ-Kd^H{c0TXQG`WG!;Jax*HB}b09fR-~xZ_itH`GLC(
z-*NtT8=*xMBg2A+n5$J77#_H5>F8Wxm#<M+etG3W=k}}v4UEes*Ep4yZvFK6vuVZ!
zg{|4w&z11ibR2#-;quFn^>KTrAWB*rn>!^^3=9na?6D?f(9LRHU0p$^r|H%gyx*97
zJR~AwMNbcp{*<57_EvufPv^1yaY#*FdM9stjNbGZz3JcH-(Np#mQ?AB3k%OVRK>*H
z(Y;&5%fQeuUmoi))q@hNtyx#KmM&lJJ?Y$B>*XIl6y)C96Z!Yo*VUWN&CSClB_&s_
zU28fqYs%q=0U;q%j`d0}H%vaZqWJl_Ws@JM+sO6X{d_Xn%K0T|WsHYM$D_xOr_PzP
z=H}+~*`W4xMu-I)2TF8-I1kwV{k>;@ds}F1>|KraGx^Uziw!|@R<BmCUzL4*9jM^H
zoxgu=@$+*t{hIq>J7_e6m#tW^z~TSz{r^|*|NAx{G$aXHuVGpIY=&P;|E)cho9lj_
zj$akJIxOqblFm7P>3iiF7(P74Hj&jZU&YooR@yx8%F5v7TM8aJ-Q2eJ&6^z1;8wrw
zw;7;mZ0+!MGtRZ}f2y!4+I<%^2L~Fj-<o;Z?Qk3K<#%^?gNA(f)&8F4*TS!*p>d)9
z&++;dd-lXEcJIG-b#?gHBf|a}UtV0~;^GQAKhGAlHtzCF28JJN)iBpXGca5*Ai4vp
z#RJ;H9-}uMQDV)SC3SP#TF|tmni{Aq)zs7kO?GWgJL{u<nEmOKCmMEkajveepaKQ7
z);;r*%F?AvK^Gy0+}~Gwb!D(R*lD`h(%^^9++18i1qB<Jn3+?-Q^LDSUw;AZ4+5>(
zJT+DO>fY+|%QHW03R@fHIVtCMn2SqG8?SU(?gJY$v#@EYl6o!n8k(A*Wi)gAmd`Tz
zndfru@kftIR%LHiym^yzcCIxjjj4gxUSS*fx^rYYWOIebB)ym&3ZO+y!4VM=b8C<H
z$$qYyy?$rO%SoWvx^pMy?X9h#K20+_|FttSjlZ5y?mzLcAmi<=t)R6~YJPK8?5+Mj
z%dc%ZXbQ^IG!zs{9UTU9ne9boWY#n^Fn9(<M9i3Fn!W7ua{u_~{Ojvv_fKYI_`$j6
z|Mh!+TgxK9*UQw$-hV%*-cP1)i&HZDI!CrP4GlIwN3A7A6O7Vo76-R_SaZ5?*m5it
zetp0pt0lK&!Z8<#iH$}RzZ_uZSDAF{oRfg7(v13NU#)-KEnjl)>E7sDTh~|HJh0kf
zR~`Ss=Egz4d%vfoMuwrRZ#0m-nzfZZFXi9&+<V`DfB$*p$dQnzzS7Rl&XN)mCpv}I
zjqL2^g{}@;dNE_k_U+&MrPu#|^Wov)n;Vne^X~2nb=1A^=Gwa0*`nHEPbT}@c}`jr
zxmoS=v$LnS->;i(UH<OL(&=%hrfP?Odfaax7Q@AG_9QQOR~0Cuf^hx9{rmU7YFT#S
z^5w~@-qTW^pPQR$BK7jst6#T&K0Q4>{r0xp;1KuCJBprq&8z$MvgZ5U@|znHov&K@
zB-`5B{`~Q{|MNw6`P6T3Zr<EmT^?8e_v@CeTbF8dfet+S`RDWb)#q3mmOVvXlrML3
zW$^M#ckjlQviZI{HC4Ov)ym~XpPqPfzwo(r;)F+^to5|2z4Lr$o2CB!^)*zT(c$tY
z)V5j3IVP+6=YM{Fj@(s}DW((g;lj;}7ccho^enlU;o~UDU{e>h3T0Sf!Ok~#cb8wf
zFXB4Uw))#2X43;c8`93slCdmOsjaQ`oRociUFye2M<wOt&h09F{cfgh^|zdRb-#1D
zUod>IN45OGl9~?(*(d)y#$?5BT>tOSm+#-xZ*EErU2ecTHTCC#-#>m-sDYN%Gc_C!
zUke%#0EIFH&pLf~ce(oC2%)ES&(F=>{k-<v9LvhrYqxL8xVWgRi-EyI2W1V~2addZ
zduBd9-v9j3(eBXY7gDaRiJY81zt-&cx3{PD_x}kh<zry@p9I-e1F?aj;eTXycJ{WM
zo0B%DpAVbsH2LSJ)B2Zh-ke$c``gmZn~k%tuRFVZe%-9>>+3@2vN0Ge-Wr0^%yIav
z)ul9d?%bVKU$d@in#|m{Z{L@%UqR~!e!g10-pImY#@pN5pWiLNfA+Ng{yFCNYmC?L
z{T3A!9lhEwb(Vy*^yyY^@kuJ?d3QV}#q6uG%+1aHex|pt&#zLN!N#v^lg{Z?%21br
zsf@Vh=H{DQv%~%7+s$3KZr!Tlj3oR2e~Q`I*^LbhCY+wGpZ@R9&&tQW=9e-|K0WHz
z51Z@Wnzc2mYtfG9YjjStpZiy1XJ}{`TFLMs0&V+F|C4t4I*;n=>Us75ewLJ%FJHV^
zx%m0Hz3Iy|x@2rBHY{?Qb@a~8V&nXKd(O->e%`P8XyL+zptHgwHzv96`|+sT=KG!E
z(Db0jfB*ii5@tv^hPKnDe@WPC+md6sNB&H`U-w%#zW#418yj2EuP-mJWNqE^>6CV+
ziB#p+tKq?`uYNjfe*ekd@Apnm_P3h}n(?2@!|)+uGisXl*|~7xLLMHTCr3JkCFSMM
zuL@m#DZ}K_?c1}zef!4#j9=bvj;wXrlWS|EMXxY1oRQHDMP12i?C<aIKTRic(p>BE
zWfwD+tX};(|M_(N_<5kIyFgin182~3VZy1oR;5~Z@7@hfXJ9CpA9WRF)wRj~hYug-
z+}UCH_U+ru%uLU{arF-x?Kju(F&NmQr<r2wsxKMa^6r9mLM`3C-MpPo)+;_f{?w*3
z7cK-?SzB+e{QPW{@yZ+b>Xzr7Vqjoi<>}%WvbS3OuWz8p&CTiO?E{z@4#aDo+N84@
zvg-|;HW(NdRIZKLX|y@*?5UZ?=|z8kebtHCVW93m?@Sx7w2_(Fw5zMbpC4#s&NPt<
zT^_VBYOUGJ{H{eOjvP4xF>vOe_*|$-VCsYVbiG)w{QUe^U#p^`q9&<q&%f_CsidSN
z<@dL@H}}`qPwn(!E`NV-?w91BG7Jf?B2jihJeYW9wz>Y=wQD^mZQHi(%sgA`{r`Tw
zmbZ`Jk`d_U?!Nj|ved51&uM+~_VYkHapp2H9H>Rh&mOyW?J9bCX{r6a_=<<Epu(s8
z-JO#^epIlrvwuEgd_E-NM9Jk_w`S=^Z+r6Q=H}4l3=9SG+$hDh&7^tr=JD|IK7Dp}
zw&$d~yUU+nSs9#}oqbx^-)7>(i4#FbS&D`m%@uK-c<$V}n7vh7Ux_d<ybH#tb`CsF
zO-WHX-Y4t5H}3p0-`Sh${{C7uc}5x=JNxGB>+9y&)mp{I#)dv;VECXfhBAshW6S5~
z=hI(aS{k__;h=N6ySuxwk<lc##fGe@Cf()tD%J1T|F5n4^>R7ZOvlhL^CT0>oY3U3
z_1BA^oS69K>sM9Jb+Nmr9qkrRuc)wieQoXT^s<Bmg<dyhVPWCWB}Tqiv$nRM6LEd`
zosA)(3q2Kn-ud6}$R-_QJG;Ed8UJtH-Ce%gkAdNVeZ`OcoM_vW65KYRW<CZ62O-pe
zc5rQLZ{J+__}G^1+m|n0s`|C+ZzDTH!^*2crQpN_BhF^#<mia&#du7*v!hViv*_oi
zr(3pey=!c4Wo7j=*QegSU+(O+wb7e%Zf^SW?c1{p3!PuSe(fDOO;SqAD?L5kEdO3i
zsT#w99?TeWC|-FrOS9|Iyv>_*<Sl-GhO`VWvV^URnHjk`?dh4B#-Q7R#q?rkOjh?#
zJKV-ADJ^~a)z#I-4-Pb%NcFA?W@JbcL7k>C$o%{FZ>ai(Cwj5FrtsVUG5A_#tE>Be
y|Fe?c-`=Wty1Tn?%fCPG@9*!?4(tpwlK!)QZYVL;QoMZz<Xul!KbLh*2~7a0wXc-`
literal 0
HcmV?d00001
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-log_loss-20160908-100029.png b/Code/MonoMutliViewClassifiers/Results/Fake-log_loss-20160908-100029.png
new file mode 100644
index 0000000000000000000000000000000000000000..232e6787f51e89a354d90308ada57cfe2b671100
GIT binary patch
literal 159723
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@u0t-EXC*II`E=PpcJ+MM7haHNklC$P&z)cRY-
z8>!$ox}B<0S6nvQ&YBT1X~hhQWRs)QZV0fdimj1YoV3UxL`0CKx3%oP{h4>CckSNL
zt)Y4Uyyd*-AMaTkm#5|3POdBN?D%(xp+pHUU^+lZ#V>B=3!NSK00#ph6)*I89Mti;
zLy3WqibeYk80O-0Mn?w&K^3C`f);|qI6zi3@yJ?<Y|>HI)m^)2^{4Fzo;&_mD=aLW
zkSbaH?99p+t8C0CPMkO)Rr2G<kLOF~{XevM(f@f17ATlxUUE^+{rl_dgjC7+nvbrm
zS6?0V_VsPmIW1vVQ?YaY?ZbzeO|!4*eE<A!?%xlG`6r}Gvh&HTc(Llw+849?QzG3m
zGFBXXUK#i~u=4Eu|E&A}ev_{H@}hB7=xV2FsTNjNVI@<wVhRcjQhpx&|2(e#`TeY4
zzkaQa-foa`LSV<vod>U65m8f9J8|}`Ye~tM`aC-|M8?tLW?LXE2m=@Q_vxHAFf?5G
zB5R7*Bo&WIAs4Uyxc$T0jz9Fl9G%k{cXw^QSF}mz@ZGzAS+Di1codp4f9;6}d*{rN
z(TUo^!OYIrvVFVxnKNe;P8%g9C&x#~?)&}Dx<}faFZb4##<_E4QzDN&IN1Dkn!eq%
zm%l!r(q6x3!><40HNW3(x2XBC;he&?{kLttE7`2y_{i1f^d%<S_!5DdemUC<TQY-v
zW|_Qfjr}~|Azpg*ipo`6`hEY%Uf***IP$k=V4$FqlG29i?|CI}Z;4KvIB|wm>8s)u
z5AD5Ox6a>Ry!&eSc17p52dmfbb1En>NIN&D^TY`c4Uw+>U-t^Yd@d;XckYa^5?18I
z%%Gs9#dUd^Z}aNa*{<QP-720Ib$=|(^6&NRtNk5TQrhuP>{y>{_rJft!%rL+*D@;5
zP*r7pzvnZbil@`pS63gtdD9cUJ#X&?t3Ch!{r2$kYTCNhbXEBJzHV`SsggPU{rtPi
z->;i`Z$skYPwO7l-|CSx4p{Cd>*C@PQWB~)XZ31ry_g*g*4Deb)_KjGVs<U$h{cz4
z*6$xYogRN|neXfi>*M!}*Zr-Z#4WDpureg<#8&StX;I7iu$E2VCa(@(|L9OFcg5eY
z*EbeDJyo<$^zZB!uU`NB`Lm<5({Xp%+Ye8t$7enH`sSwa+UV_WS679`r<fv@$^Qx^
z8vI-kpq_iGcDUQqQ&Y8fNm=dOy<6GVR`&98fA{nAY!kCi)h8(ym6WtBUYy(-6U`B*
zc%8LD$}}tC|G&Q<zJ6`pyVtgjS9)3b^xMx<Z*EFm5x3WB&z?O3;^OTSCI~e5eg63I
z;F`$I^NQd8yZ!C$?e^2t^^^bo`6(JZbw6uxaPXCt!OIt|{<!|q+Gz6|w{IsO?Goj2
z(06s+y7$tv6<u@e|9h^B-_OUuBeX2&<*U~(U%u4P(z<lBE+;1^AvyW8(keHEC%*Kn
zg`>o<)~$bke_vea%x+<6>9{apLEhb6Gt6?Oii(R%r}_K%xcvV1HZeP!+uGWCOZIg>
z_kKColoXYeNVl4rKgQQHKR-L0ad{c<o40QlhG<>fQJC!F>Z+)(@4x!Z&f@16_Se@}
zR8=`G3^;J~DC^l-riYJo3I|3+tk5g}|F8DUTx;=ODbuF8b7gaKa|2h0>3(^AoqxIi
ze6tmCa&mGjA~!EPXH)yV{>24FP?FBe%L~vDSrN5WD{6aQuVwMGj49GqB^oJ_Zc$OQ
ztaMFHMK|dr|M>9G!`Ih!f8E~)Z{F~DdwXxmxX5Jx@5kbEyPiCImUO6vv!J-RdFfKs
zSJ&6~FZG`O=+)KLuRcp2K6{pTv0Lw<soLQiYJL_q_X|5ETwN8KadVR@C=7FRd#C9}
zCtY0?YSla$ToP%#yR)<TdR#T{)m5R*P756lxA6+f%C7xxRsHRa<8r^bAlqA=8l$#m
zJ$$?UzMG$4-@#H}fB)liEQ<vM1R7R_u0C|=5YxJK>m&>k81!OxEciU*?d|Q#IyyeF
z{^8-_EbQ#kd%RQY>g?=(y-+sEzQ)tn*SBHQrl#e~)pwP@@B91vd-jyOyGpg$c%@o)
zmA*c7>z35DYu7UF?XjGuAHVK%<f>c2Sy@_k|9&J_R97FqbV+F5ym?ZM3!}H?9Q4-T
z%aWa)9kMP)GWmGl(Z%llTh1-7GJpB<rG!a_fL8cAo~1#Z&(6+%{CfR<vln%tn>KGY
z%)Mn|l5v5-YpKw;Z{IR*Z`1wu_ICP}%8*HuCo7&dV&j!sGI8FdNlcN`6i*uo2??2e
zx>xyJ_Qa;1W_JFpCGq>~WRs8eG)|u`F2cpC6}qaWql06PMWNH{U8=p6@wHz?XPM=4
zEe+~CHB~$L!-In!{{HTuay;_Cec(LXYO%T2<!#N)%xl)H5s;DTQFiaknDX(<mymw>
zRi968;t>`WE}hxa!{am4i1q8MtIb=tn##z?1gwv<<&iey(bUweTA$BRU0vPM(sJP5
zy?ZMjpZdI)ot5?A>C>lQJU-<N3gUl1l1tv*k(85@3(ycLC@ON=UG^4Kkj_0WVdX#d
z*^Q0KFYfN%Ue!}nUVdCUe^29=FC}X?9Xxo@z|hb!E>7-V?f2L#Ya)Yf?as|KX8-x~
zXVh^CtN5uYXJ?sCP~oio{mt};1cOECE0L<NuUbz{)plMOaNzJ^=Ed&)$Ii|+H$CM$
z-%fUuPIm9a_j|v~r9`^Dy|s1gx!9#%q7@Yt8B3*&%U3-6U;X`E;-w{?AHIBP*}1cF
z<@selY~o@nzg@g@C#FZznC<H7@b;xkRrl=O>pf>RZ>IaIs^iCxJ98|QOAje_jER|3
zbvCGG&DGNN)AeExU0CS+@ZCE;Zf@?7l|ih`Y&;G{MVrFzh7^Z;d2vnCkMC3So#n7H
zM9IV?B=*>$Lriyfm%BSTHJvM-a%9HWrLX4NSA1Z|-}_Z8>&gnoR;R{WTeFiN9%^Na
z-yFBMYQu&N4q;)_&i!HK7IT=Ex+Y?y)7-KT4;=S=yOsUn+qbs4b7iM^sY;n<wOAHE
zd+_n`aklvAulwdrn>eviP}yyP*Ho<lt*IZre%1ZxthC&3?x7zaA3uEjm|0z2Jt8V<
zk>6aa8AhpG@9yng9cZSa;&PWQ<bANI`^sxORL{;o_D3(Ux7gLyb%uGq+^Z`qnOmJ0
z%gf7s=30e5w^-i4vG&r0kB4W}eKLuhCMYAb=Hs4}$ZHbCMa9LS#C>ITIRCV1(+WyT
zT-y0$w;VhEsC1@rI-iiR@Wq|Q=@yojnR}*B5)l(iI@%?gad(&Ln>TL~Qd3)(`Obbc
z+28KsPQKp0KDYPx_C9?2lyzwkr?s^;3kwUVuDw*<`{qr~nHh%6pptItRM9tY-#&c&
zxH<FkvWE{3w?{oa{dh0)fy3?m8xsyPfy%0F+qP}kxY4nhjn|;=PsN>mwY#r8?%jJG
zRF!SL9_Re_*4Bj~S`VK*X*t#_{rIf;eV4MbZM)_e?iZf-?)AKR^FDm|(4gYk(bsn^
zt9+G7?B9KBvLE(Jn=cAo9kyZP#*4qJXCmtM7xUY07bEKai}kl&U0rRMbwwj0I(o7H
ze7l0e!h;8!*+DLQb7!Y8Cnx8Ity@E<_xJa^S5#PZb#+}>9j<?6O{DPib90?NJUE=3
zofSPV8DG!*_2p$pS69>K&Bkmz5)9ed*>7%b<-WY!|M<PV)f>y-$9?6y^ZeZ0!=QpF
za@xhU(dHFZRZ8aO;-Ds7*t(cbe!Cx_qJ}|0POeYcz3;&J^Zd&0eJv|jYOagj-Nww$
zx4?I{87P%(%~QQQU&S-(=kD_NZqxN*6VlV$^X~3Cc=f7iWMt%yf`?3D>ta@J6kfmX
zacEFb(1lH@-W8RVi60&uJP~NcxB#{m;MA!@=J#uw-`(A<tft21=;-)rQ@^~un}-L7
z-+a5?WxlhM9vo;qaq{HBJ(ZseUR+pcw108r<}^hsD=GP!4~%WR(rE!7ULI&<{`mEJ
z{NcNIWkHTr@%-_yUEUz;iiV1c%7fGT`>$9%dv|yDhwtCpTU%LweR<h@yk9=~^fX-w
zyBZ50AD=BvJ?ZD?_1@f^e)!}`&e&ZgjosbclO|2tQ1LMd6nyS|GL2iemaZ)A?e9N+
zsFhn#NT})F-s;1*Zb?nok3Uv^zqbAD?d^}B&#!k|?ACkbsr}zC!FxU)lLpn7yGmcT
zc}>+)R90s8^aLf2W3%)3MZPj^=aFpkoo%)-aIu?&Q3{8Su5RJuW4tnUH4>m&EFxmY
zt~XmUFDE1=HHEE>0tKq2rDaEN@6jJ09~VA4!nr1Xf866ctG=03eo8rV^ytFu>+3l9
z`Hz2ld)qMi7|)ZZPY)hE$ar~~uXDeg?S*B&(r<2W=bvBmiL<M#>%&R)`59Nut*xc&
z>goy#3J!dDc)0NUyV#t2dnB3Jcn<VRn;TSqdJ^>BQdgJP(b3Vv+uJ!ILBXo*O^5ye
zKf>1K??CzV!^`FKla6!<E}gf0hgIpT16Qw#Zrr$0>gB2jGM<w*)c>#h@%#7c&q>M2
ziJ6(4_V)Irw^jx(zp$^i`p({J@rMr|zPP$t+{oB?W9jQK78aI-*Vop*xUjJKnsME&
zL#^C~rLRIPtgMo5Y)IU&b?ec6wZ9*{f6s4iZN0bFz|c^TTTCaQKQJ>h^T)T_`4_k4
zM$fS<c9V^;E_~#Yb9a|$VPT<!Rmlpg4PmAC+WF-Voj=bXzCO-%ciGzuYopCM6erA@
z)%EuFc2G96YA&3={Q1Xwrym{bmHzSNvVY<8bFvnemJ3T?Uz7TKOCT~ba)v=7)1SY8
zFYc?Ywy?GaH9M`#-Z(7xoBQGC^ZD5<Vp7KbQ&ZmF+6rpvE)38BS+Qg1&WE3#o{rd@
z##{F0Mq~2vzJ*m^U%mRY>f43w`SEis3Yqp+e{Y*PQ*vAG?Y0vqJm%O`3f<n88$8`S
zZJ*Z3MrQT^Pz6*~CH2c=WASspFYoS3GhEnRo_}RUAhWvvyd$TkYHzIlT?R@lrdd}Q
z7+P9e6}7auet&;|T|zlIIa$$DXkE<CrY&1ccI@8G%y4eLeSc36&)Nk4<mY^zlO{}`
z-hSaiKuUVLvW<<*wr$(o?k@ML{C08A9-A$>x5X?iEnnQ<Z~y7jrw@0_?<fBG@zKN2
z?;4kj`4-umw{I&O8410<w$?c+N=ivt`KseGIXSrxU%t4cq^L~Oi{<j1WKj6XrF36^
zfB&y4P{FW1Zf`(9K*PG&-HXE3M(rqjE4A<czv@3f9`{>Rd|2RCd3A?X-W>~&Pv%;e
zyFEWQ*VJwUBg4Oc|04F+*(N0=@!WfQd&bwLtMq>U{K>)3?_O19WmWo$B{(=36w|@W
z{f<69-fvj^>`c&l>yj4%pu#@B{;#Q9zuelX`|JKzMMOkAm>M1zxLh}41H*K^*rxgO
z<#(05Y;y0HQ&d!BoH%h}M|ZcgkB`sH>&4~o?l``_wszvANlgb1IQ;ni8x-03`+ln3
z+M2!m^Pc&&-z2x?-R)YiKmpVkcXf5OsQjez@B9A$iQnJdwJ3Wdv1ZL028P3Jyv@zc
z%%G@!cX#*d`|DLaUu|8y@8{(k_f=OFe|djjzMWs*?RcMTVs>`-{JLM9+~Rsi-rnB6
zG41TEp!uB}YcE~+c=+()!wc#bd8eeP1O){N$jbIUc#u$Pu<KQQaZ%BO=g-@_#q}4t
zc8k5Zxmg{Qi7G#*ZOOkcw>oU?p%W98x1Rg``MiDdy*-s2JUmA_1eGVuoXJ^S{8{LA
zP(VO~UhJ-f_xJX$2wyJ;sv%mP8kyPo65ia{Xi@iP$2F^xD=PvsZfsC&YHAADniYCy
zXED3|-!H<Tw(gTBDQD){MlY`M^5SZ0ZvJ>&zJ5XE<}?Y@ERn9Rt_gGI^rW7i_VBFv
z{gD3GTIYY=YgFHF-PGJXamtjIs;{pSk8}tcn42GezyE*Vix(MRUR~urckZ0(yu&l9
z_f~#Zn`NHg_xt<%#lg${UfkVnE@xZSvO0Wy(&08<3F|T)85tP{iSO1AGlkXtTtH1F
z-Doy>dHIs}_hcDNel1>S7jbRthet=d1%-v1*TwEuGBLTbqQ3#rwHExlmJ>1Lu&7?r
zb5e`W>7~=WeSJm6#KaDrJLjjOuAcp*SIX4OW0Fc-{om5ksKCI9D?(RKn~)m$=H_Pi
z#eZI1U48X>Z+Exxih0iMe4?9ly02UbDZMpO*}X-@^U&eL&M7G=D=u?$bGu$&7u%|H
zI_ck^pRc~0oUG0rIqhhlto4?2_21vce*JG>{%+0$70)lPu6n1(c1_pqY;SM>@a4;u
znc|X?D@*^|R(})Oq|;se{9NYL{l(Awj@>V{?VmD5<ZJO<>+*GOKW(eOad=L00p*oT
z&(F+MR`C>KX5+cwvA^u?tb(#Ku}wPNiHF-HOZKmN&CbTgrPva&r()v-6;GdeHj#_x
zsCXVad)8Mu_wlh_r%5Uo_f!^td~lGt^j9-Gzsu)mXIphnKYG1>|23<AozsuDUXK%Y
zb#;C9CBFV|=!{vjxbpM!dp~X5xY22nilBgiLQ!$C>8ES!<MmZMg(j={8oh|izrRoS
z-TnRRr_P%)MP<#}wXVzk=9*lZZJMnn!qs}>%$X}z&t8_V_V)AZn~)m0CFf>PdR<u9
zv}5<z$Lw6R`OXAI=N6sQkA8f7EcFr;!jn`u{r&wX&YQQ+Z-4dobt^(vPTH_(laQXC
z-lI!Py<hFwv&ZJ*0!QYB0UDqTWD4p@{r&azvWLH?r(j=S-=RZ?oMQG?h0d+}@W4^g
zbJ7gk>TPa67c5XnOiEHR%fGkgt4&Q!O-s<qD=&VxN!e6vn2;Lz=hy4?ueSXA`<q)_
zT>Rpe%;1a5e5FgP%F4EZDxSBuwgxX36%pak*Vj+X%+%zQwOUg6?#q{whp%2~tqNVO
z_UY57D=&Bb`ZHBKyk+LhnJZ#;ZrV}zch|AXU*F%aFRlr*)sCEYR6M?B;l$-q(eC|n
zYbUOIeM`%_?9GLn{;dK^_V)4V*7ahmHfI0-_qXb_&HC?pNB-OIcWh>RsT*9Qqx;W&
zl8T^^kkX|~mw5Kwdwjfq>%FxCPEVda>uTeb=2BNz|M=pfa_O#xpF=z+O`hDkbLY+#
z!OQ#H>ct+Nw8%(GQmXp)X5~aV85tcFPodJ+*F-HXEv3HZ-`%x!LTY5rjSY@-^Ul;P
zJ%6-Yyj8_>QS|matIvxUF9xOLzrVh|+VcDRdv14k_r$C$El@x6lzz;P0FOy3hYlaU
zn#nJ3C&Jb0l>BB-{r`Oi=H{R(-f3Fu#<I6jrT5z9>sFMmPn~IPV`I~zb9zzj?{8AY
zQJEpR>woNtj;jp`U2c|pE2GEv=FOXjPM`KZv1yIrys2Adr*2uMlNmc@?p)nBZ{N0d
zcX#io__)aJ-p|j^TeoiAnsIH-Ot)QG?^ea_-F2+$MP~Z>d7_h4I;Y3iMdr_Z)Ds)O
z>YeYj)Qd~K#e41MPMoL+GNZY<SwllZ<Lj;K>tcn~)YL#_XjElqXD28tEcci1{qpE@
zX5r?vvqGRg;nH8vSguNh-#IZ+xmD+M)Z6z@PEI~_=8VsYO>0ccmoHtKx#o1pwRN%D
zDxN~z;(Av+u3x?Gy?Xt|{oXA<{ui#R{QOMn@k>y)S{t>sW#!71J4#<qJ7*=5?lWKK
z^^b+?=TC9DALYfN7+3w)RMB%%#pko;rkCn}zco)xPgfV=YIT#>+IQ{8o6YBYRvoW?
zzgJzwQ|R&W{_7d+uCA`2h8HMwYk!yZCYP*@{`~o~Yed8hP`I1t-MMfg_^da#n9c>O
zcjx9>Kl=Fi_^bWXuUCsdI(f@yTI$-;X#!4vem<Ws^*-WyzG?FN(x0E6f()zqS+q7;
z&Zc64Tz1djxeHdWe?6-{q~z<xP3u}!J%z4ayY}eK&COP?y^w~p{MEus7;F&5Y@qAU
zPp9=K&Y$1EG5Pqa@@t_#A2jnPBquM{W45_z`2PF-diRVBja%FE*9X=;IWdv#y+h<A
z)9h;wlT`Nnez#j{_t}%1dQ`oqIZRTi`S<gA)NxG_uC*rC*4E9ZUTR0ng;<|{xoh3x
z#fuL<Um3WVE$z&Vg%hvstF7L#d-r2-neqDi`u5IF&Sz(5FQ54C)vGQ}VYL<IaXQ@_
zlaC)de3%*3{tXHW^3vH|_BP66Qp<`J8WB-Zt1j#6>Vo=N9Ev6Tyq5;8th=uD_4W1k
z{rm0pVs<pJ^UJNcZ2#+pvd5$rfBU~8W@ctm&n0at3~Fj>K3oltmn_Mjsudda{$6Cv
zVz*uaDXA`IcD@B0HUuc2zj7rcJ3Q>bhH`CBp%#Iv^0^^z>sBnvpMJOS@i9k^M%(Id
zFZLW;6S*1G+AE!vRsOi0Uq0!|ia@Eq*Up^b(ck~a=+mc91rHCguKhf7#ta25EidJ@
zZoN_x=6N!oK7THKmk}Qm6eRTM@#BlD!}Y(syzH)g{@OLM&FSZlEq3n*HQuIH$i*Hy
zbV#8k;C&UJ%}qf|6BCid#6(b2Mb55<<H1S3v#zeL9K5`t)Bk=vE?@ZclxUBvwHPBK
zqtx?tK})&r)&0)Bv!^on@t<8aU$2I1=;$1|u`xMtZIo&6o)s%J=Du}RRZw7PX5+o&
zA#GP<;p6MO_18|tl3wd&%a&Q){`vWf&HddAr+BHRot@P>S>0dB+FJVN&6}VGS4M^g
zpPWs{w%psRZo6lmIeT{NJza(yH*O^S`0((=xpQtwNsGevE&M!1PdjXlgQFwkG~MWB
z7w0o7sHm{q-Bo(HPuBXw^ZE5zPgWjlcx25sd-iP5fUSU2!rNP0rBc6My?o)PmaZ-@
z1E>Yle2V$Nw%pqj=FaV{`}^zQ`SbqD`JmC94<8QftNmT@_LgbsU(ldt@N&PE<q^Hz
z-Oi4VjA}kJ8oZ`zWq!FlV}=C7g&UgRBA@lCdQZzZlX-s8o?kEi{QR7lmbUEQ?!9|$
z)6UJ|RAjlfHhQ_AezvvN>aVY_E1R2(Pn<Y$MfCP{ZgHUDgrX-NbL?uR#P#E@oS3Y_
z`F_vmzH52MkFI>RKC5`C=IdWV6_?_4babxNmzR~fxwx<t6%`e{ytFiE{o7Zsx;AVu
zm}65Jl%3bx*Vm@vDPfe-;a2tW?zV1e`?@{%Ebj}jva;UTQK+1glk?$T_4~{xrn$F7
zKuv<mIkRWaK6iIgJD)69bo6bb>&q>Y>!+{qnAFnBEuPi0eA={Wpdrw%uC9VdM>v~b
zCwR=)IlnbM^6B&Ek5{kX*VNnFd#&pJ>C@bgkM%mo#mVja@rZkEa&1k`hgYlDOV#Kq
zvVaCTL)J!#{{Madzsape70-xGDVz)$cQ>yqUA=Oprdz*UZ&MRfZ{e>iD}ybnzG&3c
z)_(kUJ3m|Y`HL4Tw#Mo8f3N%fEf>`D3|$>|bdhWKmQPc?mR_^Ic63HH>pYv_*xa+1
zE(O_MllX1D(8lI;)Q_*%<J})0>pi^}d2T@T?3P8^4v2CoB+zfZ9q$9r3l}eghJ0SX
z?sjhHd-&*RcgB?!6L;;|zkh#NrROA2JNoo=ef#ZJSJ%Z#UtJx3{OaoP!uR)VZ``;6
zp5kbiuj}aO-~e^Ma&K>I-M`;H>)M)?g*nY^ybm5fZeG9tpOmJiW=BVdgM$OZEc5(z
zf?GoGvGGVW$k+W~)Q#SD<h1_&o(U5Ke*FG@`0CZGD?b1D@#6*0pTgqe!xtC3U#;I?
z{$6ff%uc5A^76Tj(f;hh5~uInk@@`W>|yQodzw}TFHgF>%(v?FJiA({O*+aN8XnsE
z8X6pGYHF{($Hu(9wKXv}ckR@7&z`X{oH%!`EodbRgN$vJNLpIjjXjl{&sjZr`t;$q
zx3^E6J7=a5@c6iV{gG9ns|!9o@k~ieTeM(-!(4SwAtPhsz@0^@4F31tPSFg$u)vY|
z%j@g>j*gBWzJGUL>NVACFW(21h^^Vz*WK7ztX@-70~&T>VPku=bb8z+$vZQqPHk=F
z7EijqE_O%J(=NA$1uCAP_RhK2CfV0~w0%WwZg0s9UTYJ2JA}1b?D@NQeNv`b8B5vO
z*^|G$xoLGjz0kc+hLPdPlP3w^-rS7(DJdx_;Pis0PQO=cM$P|!e<h65c<O#W6;DY?
zQP9!h0mTuhkuNXb|KUTyoBR9aC#htzELi<&+N4Q~Hs?*(j}N=P*14Up>UH6>Gm;Fu
zj(e7um+#oQQ_<8k^!dhJ_ol8~si_sduIJ60H$v~?f&&5sVq#+jMMXh{)1u(zexL!O
z{(k<HpGWKG-@fsE-mF<&rLV7L_E!3{drKX@c~f%Y#EDXwjEsyoHmCD5F)<bV`B4a}
zs3fe*);K=@{q=hM#)5}VGFBxVFJHc_`0`?+)%%zKGG5q(3SG6R|M0+ZuDtSz6DJ%J
z6BQ>-p8W9j>(vvlFY}dN`-zc}F)F#B@=SR7yE}{tF$s581}|6eoOG`8{*farxwp0)
zoE~4-d3m}2;;OH&80LNXzGH`lj7<e-^suA1w{_-B$)=_z0U@EL8#f{t90CIc`DCp?
z6BAi1G1E)m1!#z5+}N=2;P++zmEQt`gM+u^-Hp<=wXl$2FuC_}^OnV%0%G5vnQ3hG
zyRN9nh~dGZR_+zy>*u+}b&KhG*=&Ecm}BP5nQT{&-uSw-Ywp~+=N?>olr7{8nuh-U
z?d{=TUteF9FFJYt{PAVJvmZQq)YK<yoi(NY!vj!}-L^J*yOO1)<o9=XgX<kuEV0~g
zBCa2Iq?w%`G$b{*aqGc@2P5{^?G3APbYu)$8`YY>?<d>-f4{Vgii!e4LYAD<&#vt<
z{#Nc;xa*mJ^1X?MwVU=_pO;$r@{+1e#RmpPM#c@>w_iWS&&zxC_xt_pi({{CO7&j6
zZt9#lJ!{tJTv-{+Ui|#r)l=e52QFO-%6|LpxO_cmLUrTDjUL|Kmw%i%eK|M6G|c92
z<K{~?ud6}xZGnM;x3*+{_K_Ded=|I6^mW_I%gd9mtO&fZx7z&B;lmH#zwc+`mCBfN
z`Nn<Drwi9)CwflulHH6vZMhO<+VX$os=3Zz--fL60(D?^?NRZ3#c*f&OK<)6R-hVp
zNA-8ToSd8si(I)uLm;3LP0)OG&W#O>P8?U(MvK4S`(5tW*VpV1PV!A>=aV@w$Flgt
z+wJ$0UR_x!;B?^FF*fHmo`ZjWex84N-2vOGF9*)ewceO=QfN)|cE0&_zcgC}GOn$W
ze0F|*|F+!QQYCV+2UQPDKCt-_qr=XfI~l(0@BUQb{`c3{!<UwNZ%jQc<}=I0Ghe~m
z&yP<=RyHwf)!*}mYHDgLLRJdp-QTx%YWStSOc!pn{y8_-8q^e+V_E#=TKFWDJNxVR
zUr|`VZ~sR?SlzE>@nYp$TeI2A%gZ&UdU;H00TqUxo}Lwder(+J=SZh8Xi{2KJ1pVn
zr>8$Y9Oh@V;Y^C!k}>hzf*H$m@9mM~7SlO!tXEo4QgY=z!Hwnb??vpXFpP<bVX
zc6PS8dsdcK)V7>XMd!8^^WWaxUA{5rrcv)M(dF6gsaH4aXuf|b>&E!^t-I)rm9O^y
zTG15z{q61c+TY(^>L_~#%`CgWHg2y~*7bG0J9b!n^?NZ%Wnu2^Z3TsejWcITetUm^
zJ)gt&ty`~hObfjF_ICdMtJS=r(OR9aB&S?q|H`^x`jv0p+kamIRS!2dCRe=Q`+Y<0
z@3J>{cZ)l5gsckT1WjV@e!p+^=6E~(WBa~OnIdv#rm=hW^sDKd4%d$#Il{7j-!H8`
zS?jhRKPsA;F7(UUf~s~AF)<|_9UehJ!3|rtw(6X=D1OGXE%)}ai}Jj4mwPR$YU>u)
zzZUHl|NF{SvC`gyPYvT&Ha+TMe=_~pjjbFXQp`U`Zca=5|L^ZBhLX^LxQGaeZ8<la
z;_Ls4et&=8-OrDYjZbDp;kixcWLFvfjGUS-zcys$q;vdNUPw)!zf^YW(Ye;;3N06Q
zZ{E?h?zQb+=iiq@80WRIB}whx7h;&^8#GDIw(7vOYhu!7IS2my{H*9H1RBv?vqlG$
zR+LZdT(E#aQBl#u$H!%{TknPS@%9$h)~oGjh)7DVEI+63n^`<%-}8Ih^W#CIb#ZZV
zFYfKNUKO%((Y=+GFE1@kUDv;Em!z@SiW|3XWi6Hb+}HDR^3$E)bXKQVhAsWNcKOO<
zy{D(^Pp>$C^m-m>1h-pEcf#b!%?A!Rw6wP$K6j2!O-;?i)AQi3udhvSow>WaT+wsV
zMfn$1*S@c-vO5;H-6Hw@)w_3PJ3Bi&dU}q$ySw}2VSalD4n}ixbDx<;uF0}VFW$F&
z`lOScn0#9l(Tllg&x*YG>xI3yXie4UXTDd~$H!~i+uFu1p0jqXZi@i8L-+Zmw|@5A
zlD8H=OXe~>SUNrK(6_g@K|P?!>i$XJ-`$PaS7QkpXA>6}|EhPqtgH;wLYk%%*`yu5
zPC-wPZ*}<kW5?y|d*;lMnQLul=Q}NRZsX2|cMALrFK%p9wkmtm(atab=*GrmPz4;e
zCZcg&?CwWjUS5vcU1!G~s&MRcjr)Pg54J8?pa7bL{rK^t)#)2IZz^hQbGNp(8W<X0
zJfW?l<C2!P?A!st<Qq3{I&vg_;9KzvG@thE%}vk@h2MO;wW1e3em-yi+9vP8fkp|7
z0?^0~NZ@h1eBFUrrr8%3I<v>@sSxz@^HYtxe&`U>=Crei)<kYD`1`B$$noRKR#sBd
zW;qU7Sz3=CJz`*(U;AxlmHDBW#_3se9>2J_IAUAQP2)RzAAZ?7f3|r((*@ZJadWi(
zALh3|GQ%+W)b^r^O^=^1pI_H?<cQ0WW5*V`^-6vC@PXk&%JK6vW=JeqzWni}rQR>D
zt)1<5VcFcdvMQdSAilV>__@*bg%$EwOxH~dm)G&#nsxQV&Gh*XH=nmV+{!I3AT8bP
zZ}*d>_}Q680jKBZrk(HJ_}*4S!{hN`sq?cpZ#HI-`17#&`~7<PemUDi2b<XiB_vi%
z6c-h3&Aq)XQ#Sd9&C>o?lFyz!llr@HO7!-;mF0Zl7tPu1U)L;^vJQ33Y16QK|9VmO
zz5JV-RM)Is3mSM_vqoo*ZFSh+#-<Aw0yq=}goT?y6DE^XGHvf~Iw!k}Y47P(dwyl4
zrKz<DM3r7P)wB1u*5bapW7d=@EcyBQi~DrnMy|d!V<F>=)X4a0>a9+V`)YqDot<TR
zV|%{*t?l{!UteE$o}|JfXA`mb4X8^qV@Air!|mCu@9*!a6rMP7V(Pl~SO2_bpYOJ=
z{G<XJs{Z!&_T%OA>n?Fj6L(5D*u)CSaKCmh*&}&N{dD%*pE{?E@>WS$_pLm4aj|>9
z5cA~j=uIh{n>KG2l$GsuY-Y=Rl6z|l=f#T`r82*L`zGL&@kZpI(h56+k2=>)zr`_v
z)~o#Z^?H3^NJz`(^z%w;YHX*c>mP676i&#^?M*z~#%S=T+^Mp1+SY=~bNz@0x=X!!
z(MwmvY-q>7xiz)5iY*5YHnVU21nT@eJ0qzf!c{8Jv3|Wi!-EeG4@W(16{u=1>0K+#
zFt_yA-|zPe-`+B<sH%F!6Jus<?7TW`t$?ItC#Vu~;+Wgmz!0!G%@?!?ft_EjW$V_h
z_lo?B3knXbjox1JZq@V|Ga?>soHlJ52Or<DM@PF2Yk!qIdHOW*`np)Q*y{miW@alQ
zH><6S-`}@oi^<wQ&h30tPnR+=GYbj|Hny~|)cpVZ-Rks@U%wWuSmBZ0P!$s+!^O?b
zdrNhX%G#){PGx0gdNDgb_&h&(=FE}1yUQOwf4*Gw%(v(B>mOZN8LTRopPk*!Cu^1P
z_0?4gs}hY(n>Kx6d-nSAt5;qB{{BurKhJhW=xQ-OdApuBZ*my?Z|zg@d~tL0@@s{=
zex3R}Y1*`9n`31y3K$Oj{~li(wKa=%!Jk_XFCRK|h=E~u`FppTnmxbXuiCR@iAv4q
zv*rv7L?_%@6{^jl*i)D9AKbfo*RhjZwwV0+cwGK`NuB6bcUhjB4>#BS{Uu>rW%BLa
zU2cXOyGpZnUO5<W{`X${)ynRD3>8ND5|6&$uWw(xcyZVV%YdqSleBqSeqVV`U$QG@
zT_I~#!qM8=nsIB(%5%x5tl}%Hs}CPJ!XmC8XR@PCb*(EGH}}=I%PL}heSAP|zL;Gl
zobh!(RU7`l{~s3@S5RK=?&HIgl$@-1+Q`Yt$>dygT(Ns)<utpffPe+Xf0t&*=y_WQ
z^_n_y?EU%c*uqaz;iZ9F4dvzKn@`!F{<Ucjs2S?Su_k`M+{~FXL5;LoCYepgdZn|c
z{C>OrzJjMv)t46wOZ(F2etvy*HT%+_PUG}*5AN-)j{3>YCv$;I<?q|=_Zb*scb8q|
zuw!pXKHj&oe6jwyBS%=AIGW2l*n9rRezKW*Mg6o<-IOc-rxxYi-4&oU)uQ^FPEm33
z)=$aF$&3!~CGvZ!zP>tm@1C4{zntk0xw`*<%NZ{0&a2(kyYkpF+v;yN$+^9kH>G-?
z*wpjmN5$N?Hw2E|%P!ocbNKpoanNE8v%EVTiY@m(?q71B^Xb#dzMDuH<$nnB8sbI&
z*EBM-A3Ae}=k#>_@c+j@YrWt1TMx93BIAO>jF~eT8UFnJ`|#=0R?w8r_jh-to`$cF
z>wWU%N&33WA08f7Y&igGCvV)G5Ev+^=0A@|ktMG7YiQ}OiOTLDUR+dO`*}qfOUT;~
zGbc@IS{=SVYwGD!rw%<n-oG$Ji+5H0>1n!w0Rau59?=qaclXyk48g2FU#_0N@VY5z
zO=Vz2L`UZ3WtmI<e>^S^YT2F6ZQsSpEq36@5tiWPephF%ubO^&neSzeR~0`#C@%Ax
z3z{rUI?|SYX&-DYKu7v2&>}U(mIEgyDqr1gEB5`tL1r22vNcye@7S@!VP(jpCnqOM
z?N$&M5lOhSqtL2+=M{05Ww%1NY$=~Tb7p6J-A`BTzxVc5@2LN8=i}>}n3u=L@ZrOU
z3zAbxe|^bxadq9hA(ow+oBQKA>-QNfN^yIuMCEJ02%b4}#-QNA0ipi<YilH#n3+HR
z{eD0DtK!u7x}U7u^Y7~g{|#|m1{#RU%UkEhP?eFP(bd&;<^1cH3|~4rI4UYDAA;7Q
zNM}@kc@a4Gv2Wq}J)gLIe0?|8{49#uUFNHt|LV%hr(zAyo;+buY&plz1e#+wapJ@U
zullN(5Kcb6F!lsn{`0^0N`vZkE9Q*v@9+1go}T77X-UxS^<C}l?3*@i+VboDEYs{O
z2fL0=HS?D=;s-4}TDEN242wb~z4(1=rp})~fBpBz2F1_M9lg7|{Ay;uy#28)nU@tj
zCsj=kT~PB(J32c0$B!Qhnwp&b^7eXLZ5TjvXMKHrpyGS$vDeV$cp2B%&Aq1gZq?j#
z&(F{2*Vfi9Wmv4Gucyby$;p{<X-Q|*^ysOdW?7#)b;B-dR_5hppw)(dzpq)N16p7j
z^?rxW+Y={Gax#?knXdYCdwc%tn){&XP|zUR`FU$UE89AC7`=Z03MY?AOTHE|*7n54
z+ws@c)vbu#Z3db#4P70kXm2m?+|GAZYkB^;{Y6i^s{V$AEnBt>G*AV~bY(&Ig^yUw
z^6sqIY}fE@m%6etbMmpCi<NUP-Rjjl_D@gK|Jaw4n|kC`zfRs{U~C+`|2U`_^5pNo
z-|v6CSlpkGm$z=Ka(U#888Z^z+}OCI@G;x5KH1gfcG_|i)~`SN=H_Ph>}zW-TJ6ic
zyzIm0&xdCkrwfRRE}gpm*WR#upyhLQe}6qZ)+;^3D7EXF)x-1l|F1|sh@Z3Zd)2Ee
znscAm>{=`N*?QrgDc7TBAgZ?)_m7|sP<`1W!f#b|>(o^3z{PI7I?>yBl8^N`US8&V
zaeIC|XqADU9-n)kjAJt!uSpYwiszx{^XvQiWUWDSGN6SMd-m*^Fl9>1j2RLoudZ<J
zE_-|Fmh44|wb9#;-Ok_N>)I{0F!693Xc~3Rnl&4;uj|dRua|3VYy>%a*B{UV7HR43
z0|y)`s;WSX7oVS>e|%l+?gvkvv`kcXXJR-v&$fG>Z8d0eWJUabyH%m9+iq{qPrkh^
zS3^VNfc5)5$pL>s%Z^K5UwhbVe$T<jhv&|nI|a|qNP@<nVt1DvJvZ0d^i;pJIp6j5
z@t}cp8ylO1yu3cp7_ga{*t~i3UR+-vKXd+6yZrrs%|Hzm-`Qs1@wxl^Y~S76+pQbD
zO+iD0!~V~Q!^V4+r&^W1da(6++~F=!?UHBT-`|(Ny)F0fG~MV2Z{PO5ySv+Yk_xDM
zp{c3);`;jg#`o(pGBm_=A{sI;FI!ml_STClD}`-rZ43YZt6j2enUbC!Ut?qAkC)5m
zd)f4>c!EaLL5kgar4*Hvm?|qPEeakmfLcI8LW@KrE-iNF2QA48T^;r+VWV?9pQ53m
zpl;L_huhn7z4tu(`uh6A*RQ+XdZiW?K0a1ZT<n~er&spwPG|J?JkZjKR|-=OHnS&R
zT;wWYUuTn)oE*5jEH`FfjU;Fl&HA{#8!|61ORwtlzr6i2Xhyd1%?(4)g44IRx4V~>
znSpw8(3S1;=FM9=uln(^UJh>V!>iZt>*}}r#i76Vi_n|5Z$T{~6;;)Te|~<pD0;#%
zXYSnIb=xOT7M3#4>)D)sK8tnc_Po1NUQ2}}B_#_A3mp%)@tXFTnwlQ{e!sq-Pu6Nd
z@$+*ZK7VfR@8_T5rTXv3V}2DiHPGT*4}br5r-c`y+h>_(C!L#PIm0lS4OGESkFS#~
zD=PyvOE+!ad~u1V@Eq&%b1$l^qdYt~QX-FCSs7gT?vAB}g#`mc+L;-RwZFeTT)X|A
z)9Y(%1DE^B?%1*8!L6;?H@4+U`}p{LxE7tCImerW(Q{HlR@M*uxqdT^SV03}44@$q
zCk~yM9RYi#OTWLnD<~+qP%r-8``X*va$m(dg*ryt|NpbO>fY**l|o{=QA_mfGcT!t
z0=KTN?v=x{B}-I}96RPTNd;6kNim*LooSHB^zF?}=KA{jFK=&)mz9-S6h2}R5)!(w
z++RND<|fz0HJP8UWUt>F_R942wYA+_v#*0D+CF^y=GM+93tAcf<oR=DU0vRGKG~-3
zZtl9jU&DJJt9Uy7{q^<X+qb=-C1GdI@PHEMRPFE!OTEQ;Bn%v4x9xehI&N>(!z(L;
zJ9>LvkN3%L{WM=L9+Wl9-bR63;^^r3;_`C-J9qCEetO~w8c?{pD)jKG(A8VcE&g@D
z#m$Y)s_e~*dn==-ip$FKdQLL2b6FS^SL_}sdE4DPXlqueP2C>}UTHIz?Rj@Wt9#z>
z`^{&bfA7ePi;D#X1QzH;Pb(7<6Km6r-nPKKUk;QXbaZt=CC^uO=|hJOfd>Cu+S?cV
z&Nc(BA)Tz|3v#=KmDQu$`TJeZ&$GR_Dpb3rwe{fb+tQO%9`@V+J1|k%eZthKt?c}A
z5`THVzq`v_U0uDlzw<@%n_r(QL9=6^Jq|mIpM#nz>-T)>3Y!UC0rcbk|9|aEmZ<#r
z^-IarRMh_859M7YFF&0r{<o*{^A-8~ppgUz2Zp>mI~vc<HeX!){M?OgxwGAVis?oj
zxPM>%e*J&jKY#xU3J5fSa@h5Cv7mJ<t3p>VE9Jd9XLrs`BhcWs*HkTrc|FEvW@c8e
zQ{TK7a()qg-sbEKyU1xD7cZ#`3JVMjv?zHY0Ghmzv9FU+R8-ti`x~6wet&=ec(T8p
zW3QCyshWR}K)zVAL}g9fUMbL`uZ#?hnAq5f6DKyFp02N~sL1&F+1cRte)d^cG(aP6
zd#k^L)}eyt$Nqdetq&R`{`Kwc>dn0QH#RUTDk_4q&%WR9tXbIEojDqxJV`ln<j8|Z
zN4pEk%gtBpYui`O@Z-nh{=$EMD%V79<znZPaj2-UICJ(aXkHGKC_qk_ZI=5*F8|Hm
zx}Q&{N9?UKWnyA_@boDwJ3ITIf4|?~*qF>N!o{lQGlSv4j{BUcU%wP<t>0>ZG_<k5
zOF?N-{nR5zTnwweWITNPR(H*sH7&b$?|yN6`+CqqFRki_hgb#W<n-38UE8{N@nQ*+
zj0rnxf0wadnFX!TR@9u_6!S=4SXg-C<jITm_UGTX1F4shm2GueD6lpAx)`XrrxAST
z<KyG5zrVe0UAuPehOJvg-`?IX?%ppantZHBaFb5==JfMYA?Fu5w{w9^nl)?H)bD4_
z?{^$H;E<S|t*xW0>w372_voLWpFu0UOi#VNz1^Qj-Y%x1x*C+&5_5BPUtL|TuI4jC
z;nJl`SDvnm-K~~(W`-gY6O+r;RiPlK<mKfpDt>-0>HIufwyWW)ii(abtgM{c+S;HQ
z_FZLfwa(48R##F6P3|k{>G{Q$ot~!qXli(zVCkzXf@WrBpjAO8Syw#H%&`nkNlTmd
z%O)r&s72>=(vJ@htzHYs$moF9j$SG*DmwDx<Kx!Vt5*kTh%Bo6`zz_?rKO-%EKZYD
z3=1E*G`|Zi{cDzc>&2P<wZFG**uGtSlMXj%(kC@+U5sYbmJCHu988@$HRIl%oe?{W
zmY&<RNvHe5g@C!0s#~YGw6J{qbXuP~JUl!xF;OulCZ=Wm`t_iy+@kW+636dR5fK{G
z^kTL4?A_ZMv{EE=b(pAg8;@XSW~SBpy;WbcE^bcufB5vND#(t>lP80EYM=!{JL><}
zt-QXw`un;W*5&IsxVeR|t_~OHYIO=(9p>B8($bN?@2A`9Kds#2E-o%DpoJ_OwrvwT
zJKJ15`}(@8x81y|;&$Cy<yBI$WkPD?n)v;3%CXS3DVHxFUEtX4^7Pcy)}>3Ag8X!2
zOXlQjm3(qG8Yz)t#m~-MJhi+2|GpXa_4`1w8#Znf^jaEpWldyo$;(Twpb3>n2b<ZK
z+S%8t`Oniyi4^OVGQD()o1b5NlMZOF(`(y*-`?I%y0s;9QQ%^?L#Ix8-MDe1!>aUE
zhh6Qjj$Uc=u0w~MN^ee@_qdH$+U4>xUywTr3JV3B+4;p@zI?eT@o?Lrg9jZK=Xjp?
z;!w1)v2i&&%XI6d{l8vmKYaaKdy3c6svPl0p3yUHDmP_ZT+|BE%hl>sQB~Eoul9Er
zXcxrX<0nsgf}H&Lp4a1t4+9_B7*~JGS(|+7^WN3-_U^Oyw_m?C`+C>9*xg+I{{D%{
z$;u*Jtt$c-x4pQ(f4@b|j|~T}hyMI{T;BEdwY8uOQczGJAZt}3(9S1&>1I98+~qtU
zPwVgRNIcxe$<NQfFhHXP6n9rvOssg^Yks7Wncd_R8#_C9<TTf~xOp=yi<g0R>;!0t
zfY#5PnQI;X<muDQDWK(~o^Eb!8#ZhZ04<C<b=iC$hvJb=VRe`D^K3yYYCtlkSyu!W
zyZ3`arfU7uH*Y{8?mbQCqR0Ni$88f-JZH?9(Q$Wo`D@#IGj=-1+w1hMGrV=fZdLy(
zznwdGCY_mK_-f}8$7Z%ikNfSfRnIYeyJEuz&^k=#ipomP;^Jb()0;RrIRl^n|M`4A
zXmtZ<`Pqz_GdUxt9o>+4*yP;AS+lf`^~q|#y0TJPM_0FX?%cU6;`i^9u&LN^V_)rV
zx0{om=}mp|Bn7m9%OrEs!Sh~6FMM4ppt}F_q+|alEm^vhGdMU{@${ySj*bh_?{00)
z1}zw0RQ2_h)5;LgvZ$`3-QwL%O-ysMRcpUq+`evC>Fa3{hDj};NcCD8^yAmBF8zH!
zoZi=f78<$r%jw$K+JX`cXz5?Y_q*js54ZDwwObBab!TsHpO~DySZ;Rc`>ji!r=NK*
zRQozX(Mv9WUf49d%rid{J?t+o-SXAZ&#!NWRp~0w+AC0$96adQ(%#-ZV}``y^Qj%Y
z(q^D_51`drp!~cle7znMGqY<*$dnyrZ)dsPRCe#{*s#Ii;fog<Ik~y62?+~s?5nNr
z{CeWlDWTxyexhGrT@{`-Z5k*6gWNvTIK8W#Uw+l;sn@H+D?dDFoME0n57brLuxXRf
zwr$%E-M$?S8moW2U-p8zon-O)<NfmDi`{yK?Ck6gojmEOG1UvyCN)et!U3vzN-dM?
z)nB}Nt@^i5=cVOTv~G-p(4h|h`$B>j@5jxztNrl#ygg_Ub;g|?hI#k)bUr;j{qeuQ
zzd_4Oq)ajx9-It6Tw7D~;K752kB^T(zPGnJVoQc#)|C~FkB|3DZ@tV7tCnm*(`rYK
zxIB6C<iMp%n-;BhwyODdGra<|b+GDd*4K9*T-qk2N*+9Tu%owk?Tb}^lJD*==bx$_
z-nM?dzL1cR)-EfCd2g8BJ$~FgRXhCA*X!}?U%U#i<l^LXtf{f#;^vP3vGsn%W8RvN
zN5wrnJsZ2bPjm0L`@7qBo{gk-*qQ^a+~N-&J`B8gRZ$5EEUMSs30_t3H2c$&lODdl
zM>nOOHmLbg;4|M&ww+Jb$<dK<(V|6Hp4$C*z-&|VLjW{C_u}GW(AxE!dwV3)&&_cx
zDJeO6mjUX}i}&vwZs!NpnN#ItWqXy~`xI<!<{W%p&;0V`%c#uE%*+|q<$7n%oVl<y
z`#RSO(TnxYX=!R)TwErXxVX6uGcT!tnt8U>-_|UcmD%0j?><#4)F9`^hOTv7f4k4j
zG-iMH?Aeb8&HP%sw7%#Ue}3i*YDGLg)|>pn66yj7WgC8nac;*8`$d(XpG{EV?Ck7h
zXwV8>rC?zpG21Nnl1BLYINKe&cPGEUw^uaK7aAgq_V4wcu6OYIb@8{iwmPqk+6r3L
zeR;Y6;|~uHgLdvXIWfJuwl@0W)j#JyfBp>G*)_{Fo2|OKddZR{3D3{X1&#SETC@n%
z*bglceJS5&y+Ate>#M6XOtZyqZOi30H#bj7O;xnBlRJ6xWX7#6nnFTC35kh;7q2d<
z-`RDCQI-MJtNQ%>{NuUh_f}4LeR==oi;LYi=HIvLk++xIwr!hetSr>25bBq>@!A($
z0)iL23twN;HOaXlz)<k`7;j2S%7V(z&!V1!CJ|$Im+gJ=3KA-Uf`5}i+wz#%`CMXR
zWI(Hvj`zzi_L{0CVVK0S%zr+gzyJBJbxMp9HWdc@{(SNVjRK!Id9rcqR@12MdA)|o
z#}t&57A;!s{@-DeisPgu;$?d`r=L%HeQhn<)Y|uZzt1bq?fHDkTVK(@0948!nrmIo
zz%XwfsPI+;Ewo~rf0_HU((gByca^+s(u>^{a^vgE`zu3Nhh<z{73vz^3~hZusDI2m
zn5_ga)*oo&l{TpOkN|3aI=B6iuP%QxD}Cqj!XLt>m*%-n;R<uzHI-+POG#m2@P-{6
zdYoY~F)SPT76t!rXxKeFN`3Ab1=%hRy)Mx?s~#z^avrh{weWR(D|v41h2VbCy{~UC
zyUsdu-gDo&pLvpYPcoMK&wux@UH;wN@_U)d$&V+M$Jc(nx^3IGTX*l~mX?-!iZg=_
zuDEmKUe)Wh^XmWo)ZVv!)22)Q_J6<d$FP8;7#J81^gddaD$j7>>es8`@n0Wx>wkN(
zxc}Rm&F8~P|NZ&7>i%DS<KN%j?tTI};`3jnd%xV<=kx3LJ(~VQ25LmZ&AiBOj0`ch
z_J2M&``i6Y*?zyS`u*PTaoXD2p>OZ+-@l4mTrcL^%)58*df)qL+kJG=WOe_t7Z(=V
z*YHD)08tH3E$aW(+^_u}+i(A`f}Kw$;+rKyj62H<hUzOji=S6L>QuKXe-|^q=96dn
z-O}s%=lSGpBCei0cP@4Q?VC4W_F2EnC@uZ^zwZ5Hb^mQUcUu0>0GSHI%d83?xkyV(
zpSELec-_Guo4~)T;GvUypUlhK`TO5qSs5&ASMy`i^YZ((<>mJ()92U!`<Xib@0-o%
zt3DiL|Nr5)yj97HU+?7=va_=<zuPCc_s^%(dp{nNK5h4SSNd_wHx})(&o?}lDVuY+
zulPnGpY^%q(^v!(v8hA|+H8YsM+nN4{rP=vj^*WN&z|MWaxnafWGZQ}eKtM5?&Zw%
zc`q;f+rMq*w|g<sUGC@I@AK+@y}VcV`|ZB}|9-#Q`F!3gzqwXd&F|M-)?UBoQ@efg
z|9^i&*REZ=b>BX_@8UZS-YL7CYc}Tq)WyhF&N)5};tdo*nBQ;+R_0iuhXPpT`Sl2Q
z-`JR(o1g#vO0fUd2%W0$cgyuF_ifx5c=h%A{r7&q-+w>3-}aif{@yG7_Wy2NyB5Z8
z^TFY~?e{xEdhD=>1k=-e8~8RHulf0O`r0*Xw(Q+|_uIE`spso?FTCIT{hr;wACLQF
zt*>RT-+OKC_IsfH0Jm=4$|^1WI^RwjtQ|(|VB@&J_-#hN-LDt^`*&~KcCB5$u0nJ@
z>QS}p)XnAX>;C-M)X(tX*QU*zFVD{3cavLx&xM1{?9*${mA?P?`+fX3&gv$#6ae;n
zzb<OB01ILbC4}JT8%2E9=P*=$e1EZ?;Y0Y^m^~FAAAue7>8N=8mkZAPrN6$symtNi
z^jeftcmF&8XFL#JdU+FaCIk8W!7T*`)Zk=TAhZBnR)C}-*nk7$#9o#c5Ggpx!&Cxi
zLl|0&RuBf9Y-W&!v%!o8FO0*1N1X!>84xiVI-pR1;?cAN4G0DXhS8jb2#e8j2N4!4
zMoVRQV2svT@SvbhjUK&e_jK4=fYCAt5x5Kt45MWbA~;6NAVgS<mO+TH80}Rc!s5W7
z@8qnCo>q%+FGE4;T-)kxN0T<bF`oA7KqK?r^82-??LfW62eZ_X`i~8^Z{FP8ENi#t
z+PioAr`MhedVBl(`hEX?^>BbXeh;{i+b0{^b;Y^`=g(hpZCdTQNpmvG%QqiQQUn{e
zg9*9oct_ycs;{Z?ppN(f(|4c&DkPVIMy<9wqW2;lRKeyTsY?(*@6-lxqIYT~kevtC
z8-mfPWkYruSj|+7PVK03zySj$XcapD4)2qleN2!cKtQ&K`QeYGrH_KHKmK%Qa=@;S
z$DTQ<?`LdIsC~4TYgr>>0uTC7MF<=EP{lEf1eA)AfJTi0M<@e>!w3nRees||3+ibG
zhCj0(TUed{{Ho{l-MsB_@$u`=F)%Rv2tr8~A6)t#zj*uh-s6wYUrjl^ch8>}k00M{
z;bUO<(21t*+~+$r|90<+pIf}}yIg<#+~=8~1oy)QC23Z8eSh`*svrXcLyh76btnUR
z3=9kp{wIL+z#YiIz_7pwy_7RRF%YCyiy3`bE_u`#P{4pXHKSnz4T;fo0}Y7LJOv8~
z28Pjs0u~mdg(xf}Mhgm9NQ_p#u#gxnDBvM6T2R1(Vzi)ug~Vt<0Sk%If&v~AqXh*l
zD5zFYeA)lz?*7%+O68A#T+ZHn*tVo;G9TYok-sy(bkw&v_8w}Kx#c=xfhWhL1&Rfi
z&N}Wq=qeCZRPaH5!$Q?rO~OuxTUGuYX!{a(@6Lm}vSv%-ZEfWWc(1pg|L}`_-hK3S
zG??RDkfBVNr$C)^%yl(H3^=x73@>7?nIUFu6JsP3a}j|v#wZx(Fe))CfruC)9St0K
z!Wd0C@SxxsO*yczz%q?GhyrKTewRwbT7Uy1rTp1i{t`3`1&bs7=DBm{hONGO$yn^`
zuh;9pACu14u?0<vRkWcL?EV`!Z@z5(e$Vy8?flc`ZCdg5YyH>9{q`N8`KJVNVdNoO
zo1<A<XZ`qd|7x}O`N$LewlzNrS6_t`_`7Ey*8~srtJmL(ssgRtK483g+ZULdV00WY
zYZ8bo@XHqd{{H^^&*$^Yzr46;W^NuG9sT;!Qt$d5-%qN~-?DAnxAyzL-|ydlAPZ(W
zm`=#7o-W65;C}wrsM2R=X5Op$e3nnn=0>ly`M)pke*LNv*Nb`a@$vEhwzqHGsNmB^
z4p@c;@m>bm1aYf^2M+uHeDePN{r&rAXJ^Y=7CrHQ|L*SY?Qh?{eZB*AJiH=st*$LY
z!~Xl)>-Svx_xJbzPk-I}<v=@=(|2%y9RwpPBsnfH{(C5AQ*mMS`hB;K9dnyKd-hz5
z!bQKozt^|rhA9Kn5eM!qWoOthhnb!4%gyxpTeoh#y4bycSJ~UB=jZ3Y|NVad`(wS*
zYuEnt;{+>*5q~CwtT?#u&!^Ms|KzR9)@;9DxBK#P|MI7&ruNBNZ@XXwQwgRMIOlC+
zeZaZgZ*JE4dA70p>uO(Wf+b+Yf#PSZB@FX6?Av$m*|W6m`S<Hy-3?yuw{_#jk4J8P
z`&M@Q_U-doaxm2(`v2okPfy40tNGcv*}D9l&K9<Y>2n!m8`SUYE?<8&>*~JR-}9=z
zzqz?NH#gU|Jrtw^hX2g`|9!!O^82;dA0BQOk77A+Iw$ufBZJQ4?f2_m-`iVVZ}I<8
zxBe=tsxL1-&jY1Dm_`N$oip4o7<Pje=>Ph9J$`rT>#)%KHJ^R$|NkitRrjCw=G)ub
zvQ{N4-oAZ%ulD=hRqJARU)z4a?l!x8%>{S)+ATNA5JoXDFeFGal{Cb@dcA&sUV8fS
zRkqdNO1{3jx-M>S)YXrVk5|9ldi~dj!~DDJ{#H%bi+%O|e*OEk+wZ+vy?)=T%l`JU
zMX0kJ8w41w4(NTo>~C-T_1w{J@%e{^P%L|px{<b-2*oyr!CkyFFpQWY9iv%1+TMnz
zRLs>6qk%ITI9L{Pp|o~DAvBtDK%oG}2BU!k4u{bJ5LhsP=!Ve&5Ku6HF|`Lk8vbv{
zKMrb`ax`DF-`a1u0KUI%4(0$Ca_0-=ngS-&b|VABRCG-TI58HKVQ5lEH#Y!7)2L%W
z;myD>8ZwY@U>Hp^kbnpo%}wBd7%gYO!7y3^LxX`~v~Gfggo7%2?K&DVqagzc0Vp}z
zxPk=4XyXbJ4x^1LXgG{Et{?$1+PH#*!)W&w8V;jP2uMJX+_)0w*|`g`7Jz|)vYd6`
z#_sy?^`|ZP4sXAtDa+@ysNjlaMv%_!7KKSH=86RxGP8tR*<xjsGAu4!(bIEsVRtIb
z%IK}@y%Z4eLU3Y$i%C{SrEo_O@6+uz*G=o@wezp9fA9=8w>&!P28m-3N$pWLkeOgS
zI!6Q!1`shi4FU=UFdm%-0S5z!7@a@^g#s9l7RcaW028AHGB_AO#OOLuP$+=$=t3cI
zFo1}J(Y5EGU;tq(=bMZM4k%zicr<W8p#Z@|uJDB@hLNB$$A8K0^7m!m-rVGqx4ZN0
z?d{upDvO_=pI`svu6FpkFSoMSZ{4#8BwqdbtoiQB&(D(McwpMW^dE7K3ykv|%=7QP
zxm$k!?Ww8SZ*Om3?>pPf_S3zqtHZ4;J|x_)|6lul|Npx8dp`StR&ZWe==}HF?fm{q
zQ?LmzVnc?%ZWRN=|2?t0%S!+L`daqx&du=n+N+Js>~fW$BYr`PQfq&|-TwC8-rcJ}
z3w2+uUSIa^&Q8!t*T*eU5BZHS&|ko8(>QI~v|BripU2<({baJgRne0Z@*gX&f))-J
zpSQj4E?@g4-w(8a0OkY+hJVd0FBqh+Y|XyDtMIX#{=OfNoYVF9ehIo?^Z6`O7_5H@
zQQxiNz<y)Fwd>bcM@2?fzQ{>UT{^%1-_H2@zh4W_GeOiqNimNGz739dcbBhUl|HZX
z*}~1b(c5ea;OiB@s&0UeC6c~!ZEf`GUr(pU%USKN|NoD<94rST8hRhDbmeDAFboR|
zTNM=_U;iSfwsvp&{Mv0xmoBycd;H{N_1oKWZ!_Nq9fiCx`S`z`3t?J8^q-a7;(8?y
z54E!IySuNp+A*8q$9~}j%sBzO%id-k?~|?l`E)w}+}e*v#oylE{$Bt8$Aj$hTk8M+
zt4~H*b6kIUv789#{=Djkt>R)^I2!(MKHDwFaNv=QZPk`;as9HduddqftNnH}z4rUv
z^1c6lz2=T#1KAJ9I!)pi80Q7Z*ZoM`o_F_`vflqMm;HagTt0tQ)$h04qvPV<otbG|
z`{(0v(2?7qCEM2J@3!pPb?e^VYU{c`KbWqAR^P)-W9U|JV6SjmyKddL$NlzUTQe^&
zyLRnbRCM&}SH0%<GAb)~+E#!20$SJp>dH#L`F3|N``h20sO%mU8=IS%nK|(@O1w6(
z3M^o@Sy=buVf+5l_dlP{fB)&}>HnXk5Y|D?Wcj=ZHU1bFKHMkfysy!9Vz7`L?I6KI
zf??QokQ(ma+@1_71X~<m&%bqC;sQ9wK43vVkxPpa<?tm2h6Z8Kb{TlUFfcHzz|iD}
zagdP^x+V(@bG^_tjXDMr$_=9-0||)HGy@5T1*5qM5)h;13?v*zOJGPijMhz%a9|j%
zwIKm9+Ju0F!)Ox%5)KR_qzSQ2ZRHc#S^)GG{b;2LNeiQuCL|n2D@{l^j8>Y^a2TyL
zAptRXE6s#Aw+%sKqK6iI^?#ep^8&=CaJ?7A%M1(*qbs%{K{2{w8xjtqE4HEGFuGzJ
z5)hQFD}|UbTF$`3VYHlq2F2*MTS!2RmNSrW7%gWY;V`;01R4&bJ3}A=LGsQJkham>
z1PTR)(M{~oU>M!R4h@LW+yo7X(T+bPAZXAaH~9AM#?|MxeUE=^cD8zTr0Hza%tJ*g
z&90uD%S+sTOG@a5bz9XpL_X&a2#e(DGTQKyU+2i8CwlMmI;*!=@5_7samD=))!${~
z{vX&3Iq#h8<)jcV!pPC}{jiW2q6dL~+aj(Xw`J3&Pp9+m@2lNg^)>5dCEQCO#sR(C
z`@b+SOe_EX?(Vty_Wv)xy|OZxdo6gt5F`)A)07<87l77<etvd#X*yU4PH;y@RxvQt
zx9P|4`||hqcMNHv1<V)bT9;duya-smdUfo+nw{6z$Lrgo9>W`P;2-St-Ypw9UIeW>
zE_&ke{{H^=7Z<z7?kZV1T|d6;*_oM3)j=!L;C3_Y1})2NU%P(&_I>;QegB_*eO>A6
zYimI(MF0N&Uj6OO&8F7~#S9D#4R^O~`oh5QPX~0!?XRz|ZR`K-k+-kYu|-`8dc!r&
zf&GE_@qYRDx3}ll{{6Le>(;IHf8O2OTP<r>^JDq#XV21R&z}ANs|&K}$IhMev$nRj
zziU_fYs&>GhJWu_UNHQ5bhw>=?YedUvTNeD?%jL$=H~SBOi^TQ`#<kyXT86t^778&
z=VDPT2maqYb%~iF;@t6m`TCuEYkzNB?mxfm>8Yu#VyKbg{fWuyfLz({Z*M`THMeq$
zTa~?ucz<v2>yM9*uU)(L>xYMjmp(_;vfHPDZ$tat9fgb4{pW4jyZ7$%^Yg8%zGO&C
zOWRg_SRkzKr(+8#KVS~Lk;+ukV4IVjy?X81wdiqM-!XM5YQQltd`KTDXN->?NDE6O
zqgzH{A;B;dS48g#o)rOG3xK}Fc62KjJZeXGE5U<;VYGP(4~x;;dEh}Ifl(!n2F_^U
zjNVWHPXi5*3u55>(d!$Kf?_mq5P>mzG!Hy1h&-C-&(VFd!VC-y3OrH&uh<=HK-up~
z=~-8B$BYhvLV|(@L!e-TM<=1c!7w@r1r3JLNhoMQj7~y917frUh6KcD2@DB`(bcEW
za2Q<`1__AKCIloLMpuPF!(nt)7$hJ@n-Gw27~Q}E4TsSt1T-K<7nVZ;g04-7<oD+u
zZ=3h|Z{vO`%|H*6s40`*WEvHnj$6EvWAX`}O<NY6G;7w8jh?$H_-0V%rj(YAJ}m)~
zZKtG;7rp5TOzEB=_451iJMW5rmEO-fxAWP)ciB~T^8EenuYc9qJo{Q<|1Nvo)8DnV
z`yf7pkq(xu=)0XKX`tUx6X1t&^pFY{`b~0Eg3+f+6*@7l!+I)$eyWkjBJ@k@Mx8Vo
zN`ogYaWy(Dg{=jEWt!2XK3X7*7Mr6bIoeXc(fW@5t%5b*rs+gZy6kUndv=!T>08<B
z=km!~J$cwJuUDo6E3U!x0uGT2jA6y@a+N7=eKIo-^V{2m#}v9|U0*l1_S;Q$f18gk
z8yBN44!!EbD4SsV?a5^SXV;?h&$f!k&EVGGWAOL)_w!paFJIb}dU{UTt<0l++oN_o
zofh3C`!K%AQmhRd>WjoKj#V+5;3Tl#rt4)3XCy2BsMg^rh9j1SM}ZFP5xsvO^4EL3
zy|uOY%SHEaoAB*<cfY*8u5X-v?#%D^`{R$4tY(kz;65ya9Ua%fE{;n*viM1`-h<h@
z1I}y|_+yLgNhXJn8Vi`$9D8<V=49P%H<Z4<z8?SX=cY}Yx*mh$14bNp<qQgCv;2E|
zOfoN}v_7A0k~t~$^t9A>cXqmZu)>sqX_0Ows{>g%7Z<s%jNbl^>-_qy*P=v^qeNQ6
zRrj|^><kMkUR_;1{b;xN`VW81@7Dwu?lHPAemTDK>D2nT9aoP$pI<)@bj0utL$7(*
z;;YS4jO-{ow*QdK|KCyTe@_zmylee_wVgXX{@>15|G7W*ds?5T;<Je0DZjFB-+%o5
zpXom}@4xRiE;BfO2!{Ueet%#2?gD{^`jEA$r>E&^mvJz3E%u(SH`BU2FRtd}(Wmp~
z+tpTCmA{)){cflF-QDH!5BKl>`E2&(-R19Jbs?`IKk)z3kxt>_8;R|r)@%%_M`SNB
zh9$qfwe_@ezs)55{eO(UzP`S`qVC$7$d#e1!)|TO4u4sHeQWl0pE(wWv-5UkPA&ID
zF5ebZi0MX6DZf{#9=p3tw@ie=tH&A?zw>H7oh*5AL2-IqRi>Za&nGG;C#ia0TIM@D
zXUj#m%0C~Ech3<3M;?q=;rFhAZ-bP!wzl{BxV=TsW~M(o%x~}W`r6v!zhAFEzgvF)
zYzwDwmn`bC>lJArU9+M$rFfpR`~3#w$oaM3B5!TWot=2NZE5lIb4UA74`dE8#;l@M
z?6t~Z?tsx*Y?$ga7BFw%+V}I>>^*<K-LCxkbo%FSxAULR&flk5rUKK)&@eS>Peq}c
z|GYWkaTN=11bW@te!p(^^!Pf<;^*gd%ce{!|9DjV`PA^Zm7jjp|Gi%S^ij9|x??U3
zf3zdFWCZfrez|a`>h;>AeM}CWtGDLd+?0BhkI~`m=bz8#ryuDM-1&Cf?N7I|*FUY_
z7kgz@sP^pqeU*H6KOX#fX1?F^a2s#;j4dTPQCl?lZNCJ}tA4lh%v@{pZZTc2y;WZ?
zZOOd6CHuOb{r{imH-Ed8EpDCW8M!Sd@~BMq)m5QyEL789URqlDxYs=FM|IBKU8UC|
zl6#YmYjeui{YZRvX6EKYJoTR@&rf;WYpz$eXVR9GlasEj3|@Z2(CeD{{hG;@pPz;P
zu{F!Qq>{aMYuLu*gIsR?a&rZh-JWc{9;aP4Wzu($tB;Du`<$O=+bzqgF=73_Ut06)
z|5eU1%Z+-Y!SKJtdz#M4C7zQ%ozh;Pa+ufrOe4G83}5rRC9S2Gm;0Y@6_1<2E?=|Z
zm-D~w$PEdOpu^Drd|7S}N^}kNH%{yCpOd|QuNk+Pj>q$JbBm7%x~IInwAAwVo6W_a
z&ze8~eBS<ipY^*LpU>OdTff_pyz%k0mR4@@w1<aUPygln`1ASv=lg!YI}IuVzP-J@
zy!Q7uS09dg{av7w!XxYde(jcBx@7O)Z?}K``Fwu!)v##GdXI}|W}EAOetzEn^|iH|
z&sn_|vG((<eAKC4_n~5K)YeVcqOzA(etvc{V{z{)&CpCxP+yD6UfUyOs>RI4qfs_z
z($}}!?=OqnTeb7cCGX-(p6a63exAQC_Sa466jpzB!I^*Ummh1l-<##kZ)@T`U2pBP
zl%<&mn^<RB7N<QsKY#wZ*xg|<yT9KpzyH+TzUch1Q#F6TUjP50{;|~asnQk&3BSI*
zjec7GGJRg9+T-K>=S{E21fM<Wbs3ZzTe-!TIX1JcjNM(f@$r;7Y`jt_M>+&w-rrxp
zaWO-{p_*B239O()>~C$&o({@KnU|MYzTI-!sOZUwnCiD%B`u3m{H)(@G0DAUa=4xU
z{I}cr^ULp5F26A`d(Xwi?#nAbKYMv`v3nbj<fKkv^|Vt{G-p~ACV{xjd=?64XPckD
z8Xh0}W`*gkOG~{$**krH?KjWKYQ90c%iea$i_S91oV54*J!@e#pA*~f*F}R=-p=1Y
zcX6MUR<D%lDYM%-lh4hyPQPFK-S_#qxtq_L-A-xdH9IlUU2f*~dsVA%1ZJ<fxjB7#
z^6|dRYilCE-Atbks`-w~*Vp{|`g%IZXi&3YUiG_~k(<**t+RT+-7UYL`shgK&HDd;
zH=k6Sy`=2zt(D>H<3Q~IU$dJkzu#_;&)fA<O+6^=5hx{9KA$^1ciT<1udlCzWB+d1
z?WLu!udR&VU$^aE)oV~G{PWG`^IfuAk5xaJ=x$W-;J}+bpU-99+>|P1o;PQjZgkr7
zx#j29*Z+NeW`^P78-o8+Yks|4UitZ~dAIE2_(N~E-=7z^w@TF7?d0#j@9XF5#qJWZ
zc00NIK@)e-_Po1E$2BUI-TTg{&CUsWBcYmqX^H2}^!c@2vWuVe%Gp{)=WKM{m^@|A
z?{~ZPkINMMY)rml!7Z-m^ZVP|%gg=e$CO-jl{Co+*mkGr^qk^zmOuZ0_nT*)AGgeR
zcG!|7OCR=GzdHd6;#*s@(--%eo#IrVGr`~fZ%J!u@G_skV^OUAcE2)?^+-;(ez!w8
zzV2u0((JVJ^WJX#%WU`W$73E@E0cDaA`d@{hb=b$emtJKZnjP3rth<~_WXLa`sMBI
z`DOPipTF6Dzi#KxXS20q%TMcWzj2{Zbza4z&K`MtyZS$m<yY_7@NMPtd8ZCEGOxCb
zd>OGR#WQcu$76FUpUvF)X4C0aHs%(!ze?_}4}S!z7Ot!e{(Q#xe8|pcOQ*-3`uTi*
zeD6xH!=UnD)22-^#b-@-zFxQc(sKX#Jd#E#>2piNj`hpW=aaQc>9_rM;?2#?msbWa
z-}C3w>7#uyi*;jnnJ}~Qcr147-2_SozO&6L|9-u0oPKW3maMB<?XqPNY<w~^=9b;k
zY?rV5!8QNl&-~BN&!2xfJ$_#CIZO5WUzg`=&6Bq-%lUSv_&lhzb(gQ*@>(k_>DHD^
zaN;^HSDo_W!or`o@Bf>&e*ZtKcDbsIYjM?YO|q_NfC_Up|9LT>^#1jF{QPaXx0ktg
zi-7`7OfP0ezuhm5-S2i~M{UoWD_eF$u~*u>EccXG&7Y6QcRuRUHY#~>;px89f8Lev
zKOI;7cIvmcx1V3%|F87lr|J7e3{x|IK9>JKW9_zETA&Q*U;pd!nR&L>C-0|&O10<j
zcE8svIy5VP``xnB?{>eBduqS??Y8J!+w<r5n%}d?y|v|}Z26tQHz!QbeK)`R^T*?U
zP<eQDU97ck)Rq&IRK2@opT^&7V&(qxY;#u|pX{u(v$K{~e}4yZ`qA$P{q26L@Jg9{
zxVfAQlw+FNc*B0qFTEbS{l-M^LtC%M{cbjYQt`Og+$inLj4Yp!s<_&(S7mCyTm<Ep
zSJ&3g<~6@#Q2P4X*=4iyW-&6e?Ra?7K4E%n*~!WNc9Cx+7^YZ6A7I$fbpPMC?LWWW
z&i{OfTR&xX?zWXhcR{IOUF_~>PbT}Hn_GS_vX|5Q^p3*EMRy91FLm#ile8#EICbjO
zwBL%)y7l*+SQEL~sOrm$ITepOR|YTl>$CgyLP>4iOuL^?CYQXuWqRK3cTUvStf_u;
ztwQhI{QleeA4ulq_4V=VcD-6<^W#Bt=9LwJ8<VeFoVWj9V^#KMM(XKlPZu=vc|}Iv
z<SL$HnjQ9T&*yVK^K2~pZ9aL_eVRO9#Ja54DEU}V$?I#nplGRlJ~#X+PyUXFZ6$AR
z7=FKBUvE|VD&)-#({sz`*UbVIT>iFSLtGDT-*o-U6wTnGr&Gh9HL}Z{V3W=X0I9Nm
zzh|=FT&t&hzu)sd-Y0u`v3tMhGmGkPZ+PVGY|QTzILlQ&ndtRiZO5+YEg6AzUsuOJ
zy;uF-7t}h~mV0|k{{6b0miH<i_ez3N@Xhr3cgk+(g33XVr;4ASi+#E^zUJdmdqd7Y
zkMGs}&Rx2V>Bqa>?{nB(dp|y#ouBsV%F3gCfuC}uf+fz|evbiVw2jHf#jL%0jdE^m
z02Kf`-|c!`bbygP<=&pkoi7%3gT!tA|M@)ABy-aFyQ^PpJT3=n|807?Z1%GH|NnkI
zXyykciaV9h=kEM`&U*7@KWkCzq?4c`0aRxD%r;xQDCO#g#KSQ~CskkG-u}KQ`+mh^
z-t}*_YJNOyznR!BYgGR3&YJD_s(!v&y}szI>GdZY4)dL!VVFFvI#)kt$AxNN)q6Fc
z&%W95xG!=~MIos4w)uR<c<1|lzm4+l>;MHo=A9jdM{m8~_xl`MUnt1tsxL1lt_)rt
zwr82NY1Wj}db@SpWeSfJWye>)-P$8*d~9yJ*2aQ|hu-XZy{_`*(&<{yEGj-cm{a%b
zrKC}cN7mI<p&PF)GYpO1mJ``$`D_L#!>+E#`+OE$EzaHh?N;{At;NsIoV=Mnf9}C%
z_VDsEQn@E4DBi4i-23@Pa{to8$Hzd4&aFpcA}Bkr-}A}qsAY@!{Tk!c)YP31nz)ND
z`<jbdmYy}uyR)N5*4oTnwlpMaTh2`F^?QtJe|<SAmAz&nBQx8R1<ib?7P)p8-7UTT
zv`sqi#Jb(@UimGYTJe7G_f3!ctkeGe`RO_7;o<h@uU4-=7am_bb@MqZ?cCej&X(V=
zo&I|Le!K5?iv8!+{d#GVe{au;mD%%V8mBLd-kz6vV?(0Zor1%l0$0BFOQ4v3+#Ji|
zXHT~8|C<ZyF6@4{OPgJ;B0;YD&Bl@!7Z%>wm_6tB`~CK{zrXp;Hp>Nd6Yf+z?gh1n
zr|HGcs`~os>8jQ1z)pSKYyRwru)ojhu(g}M->Vk4F6;e#eg8kx)YMc^TAB3c@89RQ
zve%ylxz_lch4SsZ-C!#VA0K=AZuk3h#^-G&FY}!(W?6c+?7Z#wCF$qq-K=~*xA?`v
z_Gf!OpIdFQ?O~hrvdGP8GYt}*s=mAk+%rKn;nWmONt=p-egA&F{__65{o3g5ev|h6
z`}JDVzOLrg_4V^X7QNs1JMUPZ?CfTKJB#i2>#D21y@`DC#PsxogU!XCPO2{tUmtg~
z=(KLP?D7=Z@;il+#%VsF@@38bf4`3Q1qXquzdt|E*RQLndB6AjGf=~T>$R9p!~{?S
z>UQq-wdX2SUxESw)baqu-E;f@m3%fI4s<2=N|}1~%h`TvxBsJfT(&$$F!-9!^0{TV
ziuS(_Nqu!?<xJyrKU0+`TTq6G%wD^-OLp<GU7#v)clmozSK;hzbN}gju|fOm{?`0_
zI=%AaQE}t4H#hE-T=t!5k{R^vcK-gP<7+>z+w<vE$;(Tshue5hH!w19de|l{W-Y{^
z>cJ@6AnG&U&epk&=jXvsm6LKdpEa}m`DC(j%83bCUSYHJ_W$|x=hO84XLPsU33~al
z^m?p$?5+~e>3XrBR>%L<njT-blc`G8&+_S%JzuXy@BIJo_vNkG*R`(u&b2ZHHzaJo
zUh$b>uuw{PT3fK6rK<02v$H*t#?y9te5|*6HY2&{VXOGE;N^anU#|pzzTnIsT6}6&
z?uQ2lGw<)K1vP12@;Bbj-5$HE<mDvCX11s4_P-<9_~quzG)@;&%sgB6YUT20SHt7a
z+J3(?`Q6>!;XCtAP0@ULcXv4(uhf)}kB^5ZAG(xqdB!0Ln~DOtnhys-EsB?ym-{cZ
z_Rx>qqylQA=GT3m%_C=Hq3qV9;dE)%+RD$*R+l7c{rt_kef6%g(vnA=>gzt;T0XDp
z)%+PO|LO#ftSZ_*ebwK8-}lEq-Fn{s{~vop&Ko9evywkOIVow7;PC6q%gHLBP6w!M
z{2b(9P&rZZ?v7>fGM_@m$669rB^ldp=j}c-$I>`^{ob-kPe2{3^>KSQU5~3y1+@mt
z@7H$E*<=z^_w(sYv)rh2R<GA|^$P0kd@>1CuU0;rnO<}?H2kODX0CIV&*#*9JSq-S
zW>xxXN-MYcvrVV<PJeiK`17mP>!01Let*_YIydCa4AWbY>2s%oa^uS7^H%Lp`1kAe
z`tzOY^JdH~zh@b|+;6Rhbime$%I=_Q!18gA@w95+?=LT_pSSt!<JKz``ldtm;4;Hj
zLr|e4Z*SKwUsrKd#=Tc+DyV{P;?_H{z_GbYcH^<xmc?moJQ5Ssd}pcr{B5~jI)9I$
zyKL!|BIz4>+is?T!ai^B*K0|xx}3?!`_3x1%LHxIJajEOe{THWSK**eOdG#^+{Qdm
z0|C@)kj~rT$hcSNe!R9}_O&%za&8*c{{D7$=ks~9pPilk-2VS(d+mGc)6dPB3F=b(
z`0!BDwyMNX`ML)vp>MmLH(PyPg%T)`{p|mKi77lPdNXtRT%+`JbGkm8J)c`12O4Ye
z*4uexZmo9VMOX1uPz!4Qzc0%{z4Pg@Ws&DB9)qiQe)~TKM|VB$x3>e8peq6wi(Jq)
zEO~K3Cw7-f{lCxiFK<dc4JuvI=hv3aGR>a$e184DN1uNt_uEce7rQ$RRHPb4buM&n
zPXo1EdnAoNom8K%6Yk(YX>R$wo3Rez2e)Ki4qEOv_slF)?b6rRV&B~WHQa5#-!TTY
z8T9u3cqCJPrx27Y^me^aV*T>}{F=zkmsSKW-jaD)P1d^X%(B^eyAFMy8MQU*=e`|6
z*=shsU5hC`o3rg^n&poN&8z1;=2V{(u%yNGx--9R$VbUdVQZs61%#UKtdN(t!q!Hm
zJ~=V*s^of=*wU+^KcDK?&&*!8Q*D0Dr;}XAZ*R?>{_^s2amC29<quoM|2_D~E?;Bd
z+{SZqj%D$sMXueTw*A#9Yrgo*G*S&-=CiWGCh<_qQ?uDWK#j_x|9`)yx678TI9H+i
z`0w}o=RqAkHQ!lJcD-H)YUYGT7$+a=0R`UP>hI^Y*Y8O(UNQAX>Gjyn6(1jg`eK&f
z?-YZEJi>p?`}?q6UQAPwVW|VC-1_sv-TqYh{o3tb+53OLvlhRz_K5ZSJ)2L7_x}0w
z-2S}${~yQeixyofdB692+Jyy<_7QgelR(M!O0fUg)akKdz9+p-zqz@&_~TLW@JPG=
zagUGn8W%h`FsJaC<kcx_N<b|eNz<$=UgZndgs+eL_3iEK`+uI9U!AgM3#b*?%*Oi*
zRAQFAzh}FAPLY>epUldJIL_I}M2;=-oLqEDbNQ1S$^C1KeCJw~7QNYc{F#3JPw%?#
zyYFi*2w#+Uch}9T*K0qYj{jG*G&}vwjKt>2@*iqfKK;GBYi-Z@$5U757<aB(^J-1F
z`|h{fW}j8%T2TJ}Ufgxo549_cLU(XyTm?1LqH{JL)ms1e&F1s}Iz7Fv$N&2@{m&D1
z`^bksmHRA|bfdO-^vl_9x}CQhRFk-Rgh$0yJZ$BWv#Hqme}2y8Wxk+szAtZX8rxQX
zTeD-gs{Na1v-8hQbeD_#_;+XQ?y{TJ@An#)ytn{v3DkUW%-i{NTK$X7&t7HR+LCGc
zutoUN%HZWHp3Q8$MfWP7r}o=^^8l4%xAS&CJ;*Nab9$O?_na-ysvdQ!7aihM*C{vO
zwz$tqD>XG0)ZN|mdfo14`+mPGUiiohH1Y@Pkrla~`upv+{_{D-er>$c(<(nddkS*V
ztn77>N2Zw0_f6(XJ~PA6@<9W0(P3Wm5S#1k<M;phb$$Oi$@DoBzu&Kq-<Y6k_v^*t
zr+Qld_I2#LnKpavhO*PT+t=(+Hk}H(8gTk=-<s!h%l#&Koj+Rk{+_LKJKx%EIZIQ1
zeR*m5?M8BNSlBcbP;$Gx(77Gd<U5@!w)yip>*p&L_nrFt{eJwK6{fd}&)ZH9_Oo32
z$lCY*zS`oGs?(pGQ0|X;xA{Apbj}33+FziAtsQnn>Mf{8doz80?8j)oemPsCj0+1y
z&)vSVGFW|Y_4jZ4f?G2$FMB#8x$mUj?l+U3yqER`4Y@Y6@kYJ-{PW%J_w$tdZ7#hR
zTm9guc>I~C)8pfwegviHd)vbg`kLRJviY1<cI&6gPv2h$SABms7c?>^9$!;<^l{?h
zHc?R3cr`RU^v~}tnU}R<7dPxH+W+@$zV^Spt9VsJE@+p78a4I*|AB_JqPApA1hp+~
ztG-0!`GUs2&RM-q+57dHcF?IypUzpoe=;T5Z{?>SRj=1Rw>fK{@#@M-P)j)N{JgoK
z!IkTA)w#dEynJlFMgGH^&F9nZ>?rj7_fKk`VX_;jyYlo}&Hr2X65C~qj*5nhD5jn@
zPdhWC=J(s}l`j^yf6D*=Er05|mseH>%T>Kt2r9~wkN3qU7AsHNem$<*@;?88|1+7a
z7_?v9*;%Z&`^_d$Et-3K+uEYLpU>OJZ|qyOHRGZZs5|!S+uPljwi>6M@#q%QU8NZM
zGICGFN3H)WcHOIboqBST>i;J$OEcGQy>@E({JLFU+4jHRY@Rx8O}IO+v{L==1+cXM
zW@n=F_ipvdzF+g%SNv{h;>SlvPv4#Rq}?RvhC#Qu{y%kfEnl-<%^v-IKa!^2uaDlA
z^U`lY=#9GHZ$E#%9{>EyW&ik>x8D1U1?)^aJ1h0~+wJF{oSYoKtL(;xL{O?)tr(gK
z>Oi=@eA;gF`_1OcUoV%hRt$U@nLfAl(ze{&psuTSZ1wfn@~7W!=dW)IS(^U$>viw|
z-RJZ6^-HtWeP#p{7R`G4_icW?H>eSPT&{Xe$=f-W#h>16J|E`1>QeIM8HXx9pEbV>
z8ZOSfoVGOke%0%>q5t&uS^fOjUq9#jz3TOsl0o%FkEHRXwb9!_-5gMR$#l84uJ<&Z
zm0!$31By>Tqp1(u<>%G?{gwLf&ri@moS@LOzU}wxc3(Qna^CX!98k>y8X(wJ_I8)o
z{Hx*VpP!vw{pH;q``<Uue|oXFe_8hRbvIL|$9_7%%rBxCoB89(WPh!_#iv1IQ=pzk
z_H}T)gZk7;OSEP4_kIoYvwFEibe_CbNd{<;<lo=l>F@V`KX<qMer!w0(!<LPTR;AK
zy?*@$#<aOsrABpser(CRYxV!%`~UNPet!P^m~_5Q(4krRprOR$^7Szvca*)obu(x4
z*-Hx?n?<kbMQm7b>G{fA-;dsJ<CR`lkhAyewbP(6hgW?eLeI|4-F?UPBWQ+XQpm2t
zg4^42bGOB`f`$xser}V_+mSdar0QMTWnc5Jvb(wB>;IO%y1qXC<B#8;uS~67mvd=}
zr<h($MD9(mlXrF&UtSfuy6gD;{p+^hExRpxZCmzrJz+JU73(rov)^vL4(f@8KK;1;
zUX^yQl<BHtE=ymY*5Ci<;G%zjet!P^bb5T4P2P<SiJ;;8R~=zNVPAi7)!lf#et+B>
z4%O9;&1|CgL-*}3UjJV2zd2|ybx-BzRW|<)aqItxtr4~TaDW+<H9^JtmW+!^i{1PE
z?(eG&-o5SA#Zz-?zug3lr%(R#w`$+)yj_~0v8#!}Q|G<BynK23`FWw!&hNjzDs;6>
z!2!m~9}n9_FN7yuTH<-MkKw?6hWTua5eGX2l{Y<~SN&|c{ohQhk{1&|Bki7()mBDt
z&ja-lL8bM}<@3*h+9iuzxyu=1J16^DX@bUWLH)o+X7)7D2;94-3;Fwgs)2?i*X?{Z
z3p8D_^V2Eq?it&j-AbJvYm{|m1*l4r&filw_4Tu}v!`pX+o1#+I5S<QExZ56QT?Km
zs?(R`-rjaIfB)ZAG3J$@p2SqWTx$7ZLGvoZ*i4Hr7o3fgj&y)VxBve7y84S=4=BFY
z?S8kbN5=9}-oDTm7Zy6N+wrJNrs6>(XmDWaYr8)m4#!kJohn*>FQF2Yzsug<O8xWW
zqvf9uhlAJ0?bW(o`}ga0N%OpzZTIVbXZeI%ojP@@=<C(+=d0K6J7x8H&FALq>AKO+
z`YziiET3C;D!Jcwn^$(OPT<zJ+ivS^&Axu_#l^+pyUKoic*yl4G~@ohTDu<)nnSf#
z?fZC4n(IZVhPL+U?Dc!6%`Ll?xink8?#II{kC0iQF2a?S!Rb@EejRS-4|iDK1gigD
zuibu*O*&_TSNVEryP676`#;MgG^*@Q;qg1Q-|vRzE!+I}+wJG)>;Dyl`b^w<I~L5k
zJayW&wbAL%&dk)Fa%)n`S<~yF-rS@%Ug>9NjL*j`^%V|Fm(JPX2&y{0`en;*B!Y&*
z_^e(mc(e2QJj*v54zIF|eVK7>P2^N@rTpD*w}GYrFE90;{$}HGIdJRJGBz{g=B8B8
zWTscYY33!Be%o&mpppAGyWj77d2esE>2hsZUTL$Kb!&dv%N8CH1Y2PD<3Y)r8yB;G
zvEMLRX7K9z`u#DAFY2v6pE16?qwq10gn`2Rx?h=m77rS-{KBPfZONScd|vgsN1#$5
z{^{?tpeo?y+>1Z+L1S;b-|vh5xWloT4HQjFkG?FwSNWX%{L?k(uEp2?efn-$#O|`U
zYc?K}nwlrDHRIwUc^mePR<|=2_kMcVE+1yIE_k`$w_DlkyOe(YH>v+uBi#`G@VNcI
z!h7}q|8^Y*&58Z``Z_%GVb;4lJ6G?C{P8O7Zt3;2O|0Bna`o{K)&?&>$CWLv8<i6L
zKlH-N;N^D;4)adU`|<4{yL`%>9fdbR{kaKiwv@cOq6r%KU$^_+th~Fsbj#oT`~Cj>
ziHXXWHzptNdOolI-_I>MH#f}+-n8pO<Zc7d2*2pO=sgvM?{+-y(}~+-5xcu=ZHcnv
zwC(@@{Z0q9gr3bv4%^}U9W?Y=_veR9{hyDnUg1*v^yi(QXKSq+y=~2o$2%YW{C{qd
zYq!?lHz!VkhNoU$U430^t**9qv79u+s!sn_hBXT+KR=skobCr2CAd>~TvpPy>PwOJ
zto1ve&AM53I~UXj1eqOKezz2qPeJojV!BaN7CN_wy;0frZrAHDkzf1wcfYcFy=F3K
zH3c&}pHA8xsq7;if;Vfw-`#vvEc%J~{vWPoHxk>u%-v?#R2IFuvhwjc{m>m>E_r``
z)UChFy<aZ#)|Skr#Wl}nrW=*NyR#+#z8z@(d86`m3s7ecG&l+>Pny|yPlZM2Zau{F
z|MmWV+TPQ2PBOB~OaQfdtc!X}em<QJnmM{z^ZD%M&FSa0;xCuqEe*dGk<6RAO$(IF
z^!9u>1R4p6&fA&VXY=WV)_=MDT`!lNnQwo;|9Yr|L4pG)<LN|hN?FSK1=QgKjbfOp
zYTNF9zpwh=m*w`L;n~w_vvWQ*XK%k(_4>=3o114%nmTRMrcFLG3>3Ym=|nD_Ty5sM
zA|^6264YkViP(^^RJ`m~%%ZH+)YQrk2icA5|NWU7x8d#rM`rQKAq&^6(J{YM(0u*t
z|B1fIT#MJN(b;~tEP9$=>?=Q~|K5A6zMi`1E<e{@zSgAr%|`d7*=F}^KHGdeBK-2!
z*6g^dmrJw!BCK|mzMdAi*e&(Sioi%vRcaBpI&5u^oUK)_wE4OEKga8D9C^VGn$ZYe
z=5taqeNN!Zk9l`@Jzdx?cWU47ce9Pp+iae7d1~L?vfH|#@vn3C|NnUPZ_l}D)NlW<
z0%UmM<6}Q(uW>ovCtG|wcl*;x-g+y))TV(d(Zl@qbK>?^Jzcl^ozY>fn*X!bWj&tz
z?(XjNS65boCQVk?+)chb!zuIfGGEXL%$%A}C#TB2zrH?R$}DHbVLodef18gkrpvW?
zkIPl(fI28s*ZqF6xF6JRc(UVh-|DuIrK{Jh$=T^^@cPQi$#s8!h3@(`ulk*5WMpKi
ztF~rz-p;2*vybI$ILH=yPxs%_>2X0UYn*nMz5R40*gw=J@4^Ddsn3%@RifAFC>85B
z8=TY5&I<ilF}L*E$|B|CpkM_JFu{%5?`V>BWyL9Lwf%oSosPS{I^oBMhc7QIbOx2M
zUtV3+-kNpw)RmRN#<jn`^hg@3ot~z<`qO5$|8G~VUgrfGwBK9(9h8X|G5mQpJO3GI
ziVHN)S9p0csMZ5T&D8gAKm5P3`}>YL@BjBdK7T$m@Ji8%NY!Vrr+n6Yb?S)InVt(;
z%MH`cZB{Jinyr7B=kOffrxx4vlNP-!I<qimq07@br?gxzJ^cLp@Y%0_zv_x!udZEp
z{@b4Wd3W=6|BBgtH*Wj+x4UBcUwy8tKVi`$XDgL{e%{smEmP;t<xNjdZ)tCLo|YQ2
zDuh!}QSr|iy<>YSKMTmn@VL9X@7TTDd6LSSsI6Sy)Af!{RCW*8Usro(hN1II!``5P
z0D(V${}%rHQ+ea|?c}$&wn|u)Xo$~~*3j4IKY8-xilC)k|EfDXJ0tej*>2jj>B9E>
zc$55lF$Xz&!?Uuqw8GcLEP5WcDugpLGqe7qOTE0Or)Nh;heK3U)I$6F1)CF;l(f23
zKEE<lQqpqE%hQ`QdGc55qT4rad^mK={KJor$uf2|5`uz)6(1fn{;RpRB9K`(YKz17
zcXxNr*e_B3?#{tIm7h1{-?y`=`m*A{N3W?`3-j;qn_-yD_U6qSkr@H9pFVxskbIo)
z&E4JN4<A0P`0#*n)22-U+j1iRzP@<*vM@6{-;?US9LxRZADd@e9rttIw=Z8nX??2P
z<rQ~#m2&_4_wUC3`ucsbPvSRi+jfjyzNTTOar&Wy2OS$ZuPWNw#_rGbNl8grIQv*d
zRaMdD8A&mFDg^85>Nq$#9rN<?_Hl1djcjvU+&Fu-^uB+;vbSVjc01_Vxnjw=xz_E>
z?0gA-eti7-Z$tQu=<RtAkM&BwxU|$;(|5Vt_xJaYZ_U1bVP9=^L{ya6?;5=$Ix%i;
zY;txr9M;ymnXKOjpPXx1%(nl}CvMO{&KswHJ9b#a?5~r(yQ@@t>B}q1T3TGo{pLE|
z-&Y&BG3lt%{MoZ+b-DM;eaus9wJ3VRu`Ty@TmHVEY*$x@>wnrgT|fR<E4O&X!R3uV
zBtK_;{P^+4&SG^N8=J1Z5{0+7<?g8YX#`q86Ew>&)-3N%hoG|CgEu!fyXtM)RrHi=
zSLy3Ec78bpbMx&Y>LKk99wdMUCL=Z`vBt#2#QogU)5B9yS^4nO)6?ts?EYjQ8WABO
zrW4VyGI;r+lP6zJJ%9S_*`qC-!UaD+J+0~Hc-hJ;ZT8@Czr9;TM8w4X=YKx#x4*D9
z+T5n*$AtGUo!;Es%r0O5$FT0-&*$NJQp^neayA$8r4E0NxNvH!wqfBT7Z*3TMTv*o
z*4M;&cyRps^0K+7hi9JqFK^qrKN9`&_HJ))ZSAg!D=IRo`|*%{$IhJ#o!j}An#`?Q
z6T4e%x?b#|S*F=tHE~f<QaQP~hBZG5^2A~~gw_2NtgNJz-TQPtReE}QR(!u(ZkTk0
z<KEFt0uv`r?C9^;|K@ke)6-MJuEt`|-n|c>J`MG{yz=;~tE&rNURoNicd!2C$H&Jv
zY~6ZvL*n5LIX5>2&GOs3E@o#Fr?8rWii*npw(0NpeCFHt|6jF9))kL~FRv&oD>JVS
zTYG4tvU|bnYq|{jW|gn6t(A7`m*dse)^1e~X<x8FK__;X$aK9}Cs1yhy<yYQ?((On
zMAyXZ462v=Uv4;C#j~TYFD%2VbVc}jIlDg}od2Hn-IjN^OVPP4;cy#o#=Sk3d-m+P
zuq8A2&E4JM4?TP1qoSmqot@ooTm9|9x3{+$8fKYhCmm>DoMBsCworPz(1ME@3Z6ny
zTQV9CHnUHE@&3l1gJB<QYHI~WMO(SW^%yEX{=B;;()h^n<ID_a&Yu1Fdi{Q}pSwTT
zYxTM{=ic6S@b>N9H=gI+-zVG5&i^dE%y6E4eP6%*KM6)g#-DbpQzOrn*Q%UX78De1
z<-X9_(cv*Q@BY5ngp2y(bA?w<);ZnL-L3s$-n!uBd?r%8mmaU=GVe8v$;#5I`~UYl
z)B59}8KT_|-5p?XMOR;+|K-b<2Il7OH#enr*Svdtyno`9DMx&*I(j1V^7Mj&g9G=~
zRL+<^Tm0vpD_25539LLsv|;u!k#{dIFYoB=bX*&?H6b}U_(}2OM~?)grBC;M>iFkY
zR8%x!+B7zA@6$=vlRK^`T3buk|NE(auj;jKL_~y!ZC}=sB}*P0>y<un`n2=iU8UW3
z9cFlJ*<1Y`6p$I0mT+!~(hXZ5$D5y@e_~V5{Q7^AUteE$pKn)dQ2i}usk>>G)m*-J
z@7`_Lw8?3<S#H6P4~ZqOu5iwrIn$#4pN*7xUXPe=RKn|PYrXojuAG{#-~aUV^w;L=
z-(FuYpLciH()caADn2HG(#7}p_rr^PuAV%1&MhuZZuf4MxbM4cJSXk&*vj(e%^QQH
zBOGUDnQ}91NINUlBWcWbyieBo@-p9t@80oAOH0dG7P&n1?Cp13d~kxI^M!4>x0B{e
zi;1<Zjo$vrG_q%9@baXSlT>F|7OPp6z3IriyDRbUudgejwrcJB{m$B^>I=u~>+9WD
zhpn9=H?^aqM?!pouwdZCH*el7xSI7f-glNsV3kVf?R~Y@;CXVtPcBOz-rSsiG_J(m
zb$8`wHGLyBC9RgZb7f;<V;??xbg0eb!ne1#AHI6U6&)SD)Lk*jp6gJXijr2xUk$$B
z6MJ~2FBQCTS6b9`qd#e*;>j5s<c}se3kiy@^PO#GU~GK&<Ye`UlO{E-3SF&aVIh&1
zm)FtX-#&S=u$XRC%fV)LZQE6W)z9aaPna;Fq4@bZMQdy8`;|7OuSBZ8zG{`VE?W@2
zJr5MvIXO87$;Wtn=2!^s+_`hZ#*GJ;&#&uRzwZ|p!-l%QRXx(?d^2ax<nmu7=ReQJ
zv8c#sRrvaItS?jrWM%)}`p<8kuQRW;l{IW_RBPhlHbw>;8=DCeCpKQV5WsNY)6>(2
z_5W&A)YP;rmjymr#_{Ot%3$``T_p$Gc%?tQxTqYmGRXD+Ox@E)R;906o}HbYe6&l{
ztKZAT#qCVUOU90l6FW*@U*lExpXZX0prGREbhJzK;hQ%+;o;#KTcft*-JMl#Si#%O
z#@nRgxnb+pv)ec94_xf#)xS(DYOUB@tJ0?KZtgjA=O(76F8$)MDkV3!*DUwei}?0)
z=gzGNSlDzad8OCiUta?kyY<$*f1Y-BmZt5rS0(T6ME;-m?!rRmQ`7a=fALs##5ehf
zgh|GPe_wBGNOWF$JaFxFUP%Fg18pV(zXN%`EtYuWZg^ut(gww&4;Jwn-k8vqY~OXb
zPNbbzlMNh!hBx|?Kv8Ee)%RCJOgacfOT@k!OFlW9AE$QLe0y<`d2jXiV=pc)_O3Mg
zYFYM1!Yt=T!;Kpepo~}l-d@e~lC-YcAN8G8U$w+^A{c~)g=fs#x1+_*+FJTRH*3`V
zx?h@NdNC(hUmV?0@Q~@*nVHPl+1X2$EMaJ<V_dL#v$0#RRI8+MS^;B~A*ihT`uh6f
z=<Rtwem<Z7@yEyHFR!k8*V~wxiCtY48eHJ?m4lPBasGUHy_g*gk<$vlya?Q}bEl%E
zrR2PM^JZ9;YE^xCvGB_bxAyLn|D~>7yY}no)5yq34qo1)TQV<yISv{tSNET%VLC5x
zciG!nmz4j!RZ&qnaPlPQf$p<{3=dvjUd|A=<#7WevqAm88a)SfrA0~~`ChoVgeZA>
zdR};0a^Yo(Mdc?IB_*W^)2Fj@b90xxxWMS%FBe+n657$*>za|F;Wy8QbFN?ej2RLh
zlUhzq)qbsi?PAu}jLXY<FD;hZT7JJ)JpKH<qm$MB6Oxjemif+hT7C7EzShd9t*b66
zuR0VSU)wra-T%>-mzO>K{oCCZJ5E;f{qj6;_0>ggy;5HNnOC;u-(Od6zyHtE>07s&
z&Y3&+>+=n{x3~SWj|zNfRsODL!v=$tw6sH4u88PHZMm?2d2CEfz|Nx7rS2iEpt2v7
zXiG{=^miCL{QdQ{@bj~?O!LpLTemLb=BB6F@3;K&Ki*~{gO-32oVyOTiM0RCu=uvv
zBF6)om=4y7H2>9L`yD9rZLtJM6q266Y8O|2epXOie0cl)y66`lPfk{U{Nv+e4t{?9
zrzfwZzPz;b$D?ljgyiJrZMnA>B^~W*wab5fZS7K<nY(V>xRG#gPvtLOejOd14OL&W
zcx0_a7(N{4w@<jV#Pe5cWXKLKQLTiFi(Dlvi&Rn~-EMA5-B|fKt)jY`nc>>n==M%w
z^`gd9!*g>io8@e)6l`r}H|Z=ce}C`B{`&p@Djpx}y||~cn1zi^%VOzA>#{czyUO49
z9qW}oeD|)b_cWc0_wR}`+_`%<F*UVyZ}oRA8_mDLUtV5jfB5iW#O5^KrlzJ3f4|>X
zwy}xXuXyG8{QADXzrQ~|)+^2B@AaRhtgKAJx=d%8&rBwU6(K8y($36iJa6}#hham(
zL#LXrSHmm*{Ma}tSx9i=#K%k}N=j9^{Bkx24mPuItoWD&YE4d3d0D<;$@R%IW~|t+
z@#w-r=U?5vMMXtZ<j%f$`s~@GOG~|faeMjAv*~>DB*kM=%l7+q((Bf(i`bqw_fqmI
zr?@ydB_*X#b5BpVHn_GnTHMgkkjsAsU;V$I%m2x|DzR#5Z&y}VXBQI_J8|MfK$Xqn
z>60fne|~=c_4$V@gO^X3G>OS`(uEC)&O3JPO8WZhs#pI?u00RV74Xa3xnyLl_$Tx4
z-|zPmQYD|Bp6=exC;Q;lt1kWhe}Y~bhJuQe-yhFzls}qi-*vdnghx6^#%#&M8xtOF
zls}qaFV)7Y$p<c95^wZB+91z+yiTP5uLhs=CuA*`3Z_k)7O|^D)2&Y?^2Nu}*Vht1
zJvkZkC8+1t*6hWO&1@W8Tuw8MQm4qdZ=ExD?!{H1+J9s1tV>=r6g@rl@We#r6DLnP
zZqK{>;lo2`7gtwJo0WyxcXyfYDtX!D+AYS&Fv~2r%dJ-`@%p-0hK7B$zm;rkWC{xl
zz4}&ieSd$y-EX;bE0^elcklQ-CowQ+YHCL8F4Nsr^72scg071jlig2j>Iq)%_wc;^
zf0wJPLO<&|%s0=M1C@h6epIBgn>y)>FWJ{O{e5-S))gx>Kx;~Ol)sl_NH{aY@Yngd
zd-m8^SXeB`zP|3phQ#Jc$(QU~mM>Q?Dk}OSJ?F=-Uypu#d<<&8fBN*vAn%Tag_V_(
zg+;_e&(4k$GYT241O-L4)zsYnv!~7VYu~ZMA|fj4(8-gY`%iCKy?XVf<W=VmxAT8}
zZen60Qvc^8yN{30g<YlDbL?uPUVaQwx3-qPy)F0fp;qq7z?0HdKie-0tNSH<es<QT
zKmWnIySsmV|FVAnzpfoSEN0A}U7Y^Je8S|(&7fw7ZLUIGf%>t>$NM*yzmMA|7cVRw
zWb<ut#2fd+8$lI**WosiW>8)7>FY-MqsjJNpmGCTu@u58mVI{L9>+KHYKr~7SOBh!
z9&J#Jk6-FF)u8Z^%b8iGt1mnT?LD}()O+HrSy87Zuk_wo^z_5q?e~+etO)e#UzF7?
zu7B*))6;^&!p)mfPd_@)$XxON@At&SL`Kg^AD)~P&bhNAu-?5y>&}^(#-Kvr$kC$*
zuUrwCZI*lJ!^6WD7dSFAIFyu_JUc(X|K;W7+BTYhg{NqT^WCrc%zLayve~^~ZlTvy
zt)F5G*2nLcdwi_dIW2A3p~+J6y>7vap6|UQ!N{<CdCNT8>bBF<^%py}a{a28ZWQ1D
zpOcHr>Gid>AHUts*S1(#I4M=qd%9lh+_|#9zQ5;xaMbekt*zOO&u`tno&5dX-KDmR
zUbVEeBs@Pi7qkix)E7Q-{P^LsXMOi;w$Gg_%O_{kq2@bF!&*a7P|_4q<6K=4$lTf4
zxgut#QA|wCf~#2zuV!6b6}npJ|EI=(*`J@C{bhgS{*FTCr>CZ#E*ET>JXu&rM`wy$
zu&9x-apAKwl7D~Nl)saiXIH!GzGd9%t4SXo90XMy^K2@cE-&|geLgWFLIUKiHeTsN
zM~}MJ%e{T`W{TX^3|Cjzr@ME&{Py-Xs5yMRPxh<0+1A|K({}q$cL)m;J2%&Qx&8F?
zb8{Ts+}K`SS-H4gx9-bDcd!1;FBJ#pT5R07@#ndxz0&4i$_p-KZC$^|p(!rG8QkUo
z*BlZ#9)*wwNuu*U%WsP<-nefBHA|d94G=zXm1FVdxcTuqk#1g1KBP3m`~2a<#uY0x
zV)oTYhJ}Uw>|45Y=|b0Tv5X4~82RMw)?8?Lbzx_5`j))AQr+VEVO3N1%g*&{pI`Tj
zQ%z0n#m&v?R^{*3eDQG8*Vg7<xpF0F3}xSb^Za`~d#k@6I&y?%Z`IdB9fHat^MY(a
z0|m|O{Ex1!jb@0`S@q`TX7yX!^Vfe!c@?lR$@R<}OX2yo-y#=sUr0YYt95JkbtOeb
z$A_N1{$XKZ8_!$T{4n_Q_phL!AY*lP^^v1TryffA;=eWhyc~~=g#akrc9*?naQMG3
z@5%~6PzQ!VUu@NU`+7O+@^>xEmoJ~BygJCwk54ad4~MX@uu1MMk<`=ELaS7il#GgE
z8vI;bTrXvqT*xqaac5`oK6``NvuA7D&eF;>k(x1M#)A0$bu$bSnQm>%<qi%GUV1!8
zR$W~kROIXH^Y``j{nX1?1!`eDUg<W|C{^LKQPh@<h5HTMS6@AJ?3mljiy@DnR^K{&
zm^pS=Nn_Y**U!(+Ru*2)E-EZMc(hx5;@r8tZoN`ZtNpL9i41=EF{D}iPUpj?Pg&>s
zwYRjegscc~tk;W;jRh6Tb$QbTq=RIj?azKt`xDZ9Xy(lXH6Px%LlOa~7JxJ#c)l%u
z2<}Q8O|b6*H7Y=*N>ESn^K%P>m;0><T`i{OH)qBE-AO4aD${hM+kSt4udJfNB5PF=
zP!aUF?CB}dFE1`KgUX5qM&>DU?Hw#9PM!qyqd+53CpN9Q|3%Z-Sa_1k!PBR??f?By
z_VMu%nRjK!*LQcNK?6Un+~Qn14*s5=poSJG9p&8L7yB|W^y!I-${)UeKfbg0c|vwJ
zx4pf6&6kVr2FAw0RVJYozrJW*TNm3sVS<2)np)D)F42t3%Xou=f&?TaI^=At4jeq_
z_|mW!G%YxB)~v3_$NOLJ55I9t=s@?`O0AF;4Yj|&X&Pz?3SPA5f^^n|goQu9?W+0t
zDRsuIS&KqfhyAkuVrgx?IO%AYSN|%m!)?5vepTV;XTA}UkuTpTfU4iJx3>z#Hwsl%
z272D#SNri^^?S$FR~Pxswesp;Y84h1R`KZxCujlk-`_W{UKK5UeJ!-g<Z8y16@rTv
zF9sE&>gwu$ElY}uoOTvHog(LN8n<ux@2{`h?P`BHtiHOa?CmX(IeQ-X^-O;b8oXQV
z-tX4VCtLBo-TVNkH3(|@fjSMKrXRSUkpRodGG<F8ay-EG1SCem`9A`r5Zp!#V%T^O
zwiW=AIG(?_xLCq8OXShx$BLdp4dUhNN(u@Nyt=yj;k$S1KC~QLAG$is!_V*7-s<lO
zxw*X2(YKkpgH$~a9qkquofQ!K?(XjP3l{=Z)YKNm@2^`CyW8y3r%w}R&Em?=&er>(
zyYS7M92XZC1w%tYKR>?}F*`S1QeJs#j%Bey`Ma1NS!=P$>i%te_u4XmMqwg0rErF=
ziD<mJIX(H?o10wzS$Fi}_wl5sr*Fx*DHInMCt+V_^XKp1#Js$|r>CbY>+13*CMITF
zSkQQB@v1}r^=#(b)mpXjN*`-|zFtvLk#Vk7>7lc;%>$SF$sRd+^x=z(iwla2n{`gF
zh~IBl_5EG%Qt#<nwyQ3#jNNT^tWUN(^YXHn`@gSZeZeiJbKv{^`u^SJ@3jn9ttxP4
zQBpDz0i~9U*`EIX$6sDvzVPzP4dw6SKut%fUbdSzZ-Tm*oSdAX?#{`{>I*Nw{BT^p
z{=k(hBDuG=G={A{+QiB|MegE?*4EaS`Wlv%pHzZ^f&w<DovpE6U~OfkWxMR+>C>m3
zD=I4X70;Y9rRCMt)vwPl?(XIW6&7DsxanG2M*fex_OgV7pTAwjGvnr_rT=8Uy}a!H
z(y;f|>GPs<{n~?<`#t>l`1pp+n@@kAmv>{s!b{0gwxEW@y4c-co*Nh$38kf_{W|}A
z`tuKKx8Dn@^0}G_N;Mf0-~yu%Tpxfs8_m3$a^Nc9@J7X>pfpm4=#_i~H82!;4}<$3
zeA1T+ay&N1?c1M!Zx1H}Xy`3!Yu3{E34X4{g@u|IcV2o~veclr>g1-LlatkxpPrg}
z;^fIj70+L;jhUI5pdrFLJBvXBnM>VGt3V@wYa%y;+QJOKKF^pl2Q*%<6SG6Wxs4~V
z!s~I^_Pp4VH#Y=tZ_CyGvSa;veZTp3y*F;$2%6_pd+5+1gS0a<m}VDj$+*areSMwl
zY_nXESw6OW@^(D+_4O^Stq0GY^V|OcH2U@OVo3Uh1&$UaF9iBzt=m9N+^nmsev0|m
ze>^G<YU!q=EIBk;YW}9w(@Ae{ZT)Fy52~-<@B7Vn@7}!)Ten`VufM#^SHiZ+WS(vH
zvLh>29pn}4=<r|xw;zPMyStnHmOE!;Xp~sVCM6{?Fih17bt)>_bm;QR@Sq@}f1l_7
ze=s|LpJPdhiHfIFUf#M($tzD?T^;_l{tGuR@6o;0-$B*gKE3;(<`c+)qS|2(etmsC
zL50)O($cGcsh0mdn}hG}?%r7N&<T|M7=FyF<K3k5xZnQYiE_bYCnu(yoE%V7eChFE
z(YS*29apY|%&{u<sxLeTs!t|QW_EXXZ)tDWww;%?LGfrZcn|{A1~6Nacw@q&4T`*=
z=H%}{8*tYWoGk36+Cbw^pr+*Ejq?AcAO%dKeb+%yk7Lq{_lXx5xqkTk`S6vM!55c$
zi-Q{BKgC%2WUWNZ^Y1-z`j?b*a}(>~Hs0pt%hm7Py=z$X<V4N$jrITkRs8v3*e7GT
z=);m@YjbXHirAJT>DDh7`{Lu()#1sPmUza*{FHk1_%Wy%x@V8gmDS<=`TPHFyQD0+
zcfkUMzlVyetE=^F#19-h#`gGl|M4}Eo4NK@f1hQVZBY6uWXaN{nl>vxt^{=l&&~>6
z)SEC(H=3=!zW%S9Mu<gThl7iY(gvQ+jujr+*VbJ8zwzI{zrQD>N^aY>?LyYpA8$6F
zUvM?+;*P@PrN=|2-rk=7d^d-Zm6a4jz(Ob1FR!k0N39Ke$az&&Tbujj$&(&lUQS6#
zN<l$E3a5>Nf`g~Z`I>@~jdA+97xB}dpPPGlvbz6*iy0U8R2DBi9^5+HJpa}G%L^AS
z?C9<W6-Yr#xng2srpWn+f(BhDPHg=0rNpN0kA(j`n?{|}dnBHl?tRr{ot>TCsvbO@
zOH^w?=H+D`o}LF6yZ0CT|5tnD`0>Zz@7IS{nJhluCer;^1G(J~&ckgr#-KJ||D%nt
z_=UF<^4tDu$Vmt3K-vNu6pto4OTBw_b#+H?@74daf9z-Dms@in<ct62yt`IBayAn2
z^?yy}Y^y>ZRBTQ=D<C4W<Uq=+O%)%L_I$rrePe63xSVZO%S2`OXV&+Y`AX}=?~7UZ
z^2*|{wNVzOudZl|FPLvt%4M2;P3P&#D^FiuUJlyK@!<9A?!?1w3;pI=tq5M;cPV*g
z+vLf@=jPk@Ta~^_xVx(qG!y6J<1<Ch`|CWr+OAhuSMUGy<8<GWCMnabmgM7oQ!^NU
zeSCcU;)=k<K{LGWHZ?UFBpzbfl5ug-g>Ngv*UP=Tvvcu*6c?8zYLLd9lyMr5lxfzI
z|BE+;t!`brcI~C)mDBd_wS9MQFL&g$z};oJ8C#=zq|N!F){6D@^?CI#mulyizxIFP
zmqV@G761NNo;h>o!ZKfJPz4sXR_xrlbD);^GT+&47cK<E>?+|rKi|H6=T6I8+j6@(
zh1EcHdh+qU4VyLvRrxG__Vnq}`!{2zrCL~695{NE_3|>`=CIYS&1}3=<N`&Tnw!7A
zf4O0Uflc){9yK+!jH|0e?f(5p&e$3i#}LQ_Y7?wjq4Br!%FB`+#n1UtBHhl;GF^Bz
z3$#P{v(s*&1aPw-+PpIZH3kg9Eq_p>uN~C&58?q05P%y4;6@*)aMv+g0v@x3wHZN;
zogcq`De36EncBTp#q$x<m;Z&ozGN~u9Pg9;Y^!(f^z-0{@9yjjeqyN=zt2X_zAmOq
zcxAAU56`ha+25xgPt^+5Dw!z#^!e-8-JoG(Gc&UpCYeHS-o9mI*q(Ry(5BSWpw`+<
z<8&>XrG?tz>tsMJZ+(6JrS5@CH*7FqaPact`t#?{gXhn~pL|yJJao97-#ghPH2cN|
zMbPfHgyO#Gppvv8cy0KL`}^(H{O9#7SfKFb#l^={&s*30FyNE5YB}01KK)V2t0R!&
z+4I?QRzX2g@G!zsuc=ey9_J@tSrPcFTOsb>p$T#G-4-`aohoWo_GX3s{I|EZI^W!s
zI#td$R4a7Vl=m{*a&L>JrKN#N-?OvLug|w%8+JN2{r&{E#g0EeJ$?A($rAhNetv!%
zHf#u}G6^*_G<00-*86F%TIIpJuP<kqFf_37O1%JA=Q1)fBJ+G=Z%lXu9sou(x_Q8H
z1!}l~M{-0UZFX3!fJbh+c{SO<eKqiq--M)+x3@&o&(8xjEf!qO0?mFp%|CvA!5<ST
zUKLNLv^2F-Q#2RX|Iyl{<2*^_$+KtE9!+_boSxpk(78S7-JP8kUtS2V3R&6o;6cKU
zojVyB-1=lXA=7_R4?TOMzrMO^Sof#GXTIIu3!i`7OrQU7`TRPknwmYEnx%HmnIrS#
z*RQ1O>tZLUaHgJ`!pLA#|4(L<PV$2TjW>3cYWw(B?mxKb%iG)H&z?Qw;NS?T61n>E
z(<iM@o0l3iHa6B@G^v-DHqSe9VxscKl#@arh2Oq?vnYEb@#^||{`&g*oI5)Nt;^mx
z{QviNs@&BVDXFOoV|SNzbafrtQTX`5<Hw*%Y{tx)pgF0D6DQu-S8E-%E~b->SL(r?
zoy7*`=HXR2i?6K;)dqFtqPOK}elh+%xBQ-CUY=fw)!ajqg#;%Wf(HV%HZEDBqN1jD
z=-@%dr>CX{SIPWh=jP{k|NQLiSMe7YW>@|^uCBCnu6@1S+NiBfot>SR7O#-f-yxiQ
ze_w4uVWHzxt<WiQPxG63J&!ejMr0@Ua7u%6m_&}p#vA=9I^eu_G6Eji-G4ofH6avo
zb94L5x0_r3vDWu^pDZ&&$;(Tu3<5GTF^lTu<L%~inHN5CVPRnb%|UP2w#{v-R%pSS
z8-^wC?nv(c_e&czZKD~yEaBgupP*@*Ha^)dPy{L|F<Dw#{uJ9BySt3{?X9hcCn!2^
zD0=F()IGFy!v+Hxn+k#L`S;mABsuf(^Yd@XzV7$%<duil)<%Om?Ds04%hr54sa{Y}
zpi#0}qReXQvYE!|Ne7!)FJzd22Kr_irB0YTmzQCNX|`C}`FU$Uv>bc=@NoNwPoEBT
z3afv4o1B%^HD`_tgMMAwm8`8dHYT%YU0Jd4$%<76AQ=(dPD+xsC}6m}%=hrt?CT5+
z?)`GDvu8_Bnmqa9-s*DDWZmBC?_m{QrIrN`7@VA(Cd`<@VQ+75l6Obq<;#~A#m{)6
zw&(SpnyRgByJ(e7<tG*~F|j|Y52a6?JLl%&!XhLr{P4+>BiHXsdw6&>_$_x%N>Tz%
zk4J6IQZzRg_n&9exOAy%{Ot9b+S=Tyr=~nSs>=3&wLFFA#)PDe@<)@v%^f!BARSOa
zIbn$jc<AlpjR|ew_A<0?4U+mDXk)enG$;p(T<5N%Z8gT*wrv9quN&0;saWc+=oA$t
z6%!jPC@#*vHmv(_JOAUm<@a6P+}J=P<kNJcl}t>g*gqC|d~a`c#`SfwK0ZDl{{4QR
ze05c*gi#8|r%#_YWM9_{SsNw#{QUgq%c4WHz!_VsNLkr)(wFY=m-|7}>T15Tru_Ih
zzxJEtG`-kg;(lMg3keH1gQm5i6SI4(zCL*Qva^j>TFZ8pR!d9Eg9DAspp5kRct2>Y
zy^U9T5oqtn?(*Q1(4J0xvxkd|t5wMhfnQ%<GJAV_pP6CE{J;LbkhHWk$UV~Lc_9T(
zr6*6EaCm-h?#12Z`D-FJGBGkTdU$v+FwB@eJNd)}MbMC&$h;ugLx&GvTpg|t8almo
zOKSh$Z_*43mX?x#e|>e%$XKz7dDW3sp{oNHyYX6BS}rVqe-E?-qe1-n#;UKcZfr{J
zJ|rx)Uo&{wfqVDlnA!P`{P_4-P*#?g!NcF*eQng%4M|72Kr009*Z-HT{q?1B>sHfK
z)Ajo&Ob}qukLw0$I5}BebY6fgpNs{AySsbH`Z(FMvrG@)+?>w1$D%*?)|P|%`~NKZ
z(DJI_`@2|Bb?!UM1eB>4Tz<*0$D$t;u1ZQuBJ(c%*r*5|V+Z$q*kF0w5R@vwlY5}T
zSsFAui<sPN15fV3+F28lHYoCbKdC-H;r6!N6KBtcR*8fbmzQ7P|BtKq(GkuayLV52
z<njtMBe^;KeA1~YnxJ9qGiT2hK03m=WZAN$Z*Oj1cv%ut6UVeQ>nf=C{qWhdHu?HL
zf}3=bKR-KrV|Tf}jje6rw>Ob`cJ;j9-`zcYtXJBw`diMKdA8D^aoNAWzfYC(Ha*ra
z-~aLP@#I4-oWK76yT88h@i9%?Wr0P-#fPVAhj-P^(>X0+mLpNGr_-2zeqQ3+TU#w^
zf0=-aWqW)3oEsY$L1y(x8t?e=#}rf$c~8?hc(9p$;pLYFFD@wR#O|8Xeg6J|J(Zse
z-rh3(@%wl3jSY!EJ{;zM`2KyrcKEu2kCuXhQ#nAL>A;Dg3CZ;I^f|WG+b+Z(vaq%W
zP46_GymIpVd45o%`QF~@!sqAa)`&aLm^t&{<;%kCd@=zAPNf#r-*iCJ@!H|*5)L#l
zvg&DhdU=7?vxv+IklmJZvuR`U@k3|N^4kCT;N19m#nmi90f7Y%T8`y^d~`HoPlchH
z&y0q{?flQJ+eNiP9PaO{1r4;bs)w|1*kE8`Y5DNdQtua+m-{zff3&yy`;U2gjBy3(
zZXqEeQQLAlb8l~3n09v7kI(1rzgpMbx^Y86MTJE>d|gO|*W=@q4bFf%+ifC`<NyB>
zFDfnu&6a_dH|#Edf6U+hZ^(o0E-@LI9(I1YJ)bI^oS6D#t;4#6S59wjWd%)lb#!om
zio%&QXLj`T99a{&IUzA|;g^b4fqSb;bMEbtT)A>3C`G-yv$Ofim5@I_9`~<^+q>)1
z<CVvz$JcSPv$OX|7&3i+cJ}a|%FhNhKMJm_3}!b@I}=c46AJ2<?fd)fcGCV83dP06
zpjlrdqfb-MgH~MZulu_p^|V-zgyABQ<-zL3#l=1H_WNA8f4}^?Wa-kx@9*w{CbU6)
zye}534uh(I69SM%cvnx)kpqp)j0}@hL@nahMwzOpsZIM9v1)7i`#4Zel&|@~=;Q0l
zEt7v?0pp{`kG<;+rhfeV`SAXKU-e`5R*80t>7M%TZpZNA($emKebQgRa~9R__qNCG
zE_>L_Z>LeP$9J}w>%XFj4O_FXCtX<J7_lWoFlu{VEV$=V@b_0Kt6H$Qy}doCUl|w}
z7_lkEv+;Y$^>wj@&(27;E(_)djh;-=3{J?*?0oSegN2Pvtitx&o14M)=1NtjW=kwU
zQ!9{`G<fP2JShVz0}4U2ZJ@yu(D*vE%?6phNpc1^`TlA^ix6gZK9`CLi*<2(yUyGH
zmtkh-YgxWLec$?je}8M+F4GdZW~+a9Po?m*Y15Wk@LuGeq_WVhR|+&R3+@iNhfdRv
z?_=c_Tj1U=$HB?z=;XvCBqSstB*ete)fk8WLO+b~;;*fPQmT&It41Q@C@_zgM
zy5`naR?zgE{l6cJ4}4tiKmX9-!_2?GzdwFuW$?$t{Pr3KOMjVUUScVKcPFrlC-m0d
zYV)dZZ#thmc~W!V9<(^eB!fX;UmvtUL{3ib#g&!9M#jdXvqI)>+Prz<lqoGojvQf%
zcX4rX)%+38tfaK)|M5eInEdD4)js{WV~0h^nuv`e>OtG>|NjyG`uckP)56GU6Q@oM
z1$7}JA|ycD*u(ePWnW#@+S0<psunzb#texbS?h08k86jnYH{zEoBGJ*Rq^j{xuDf|
z>uvHfGds6z*%CCzWA3@R*6pDF#?w<%wZBYn+M0b`uSh+=O3}zjs9Rj0?Ev>X9#C-#
zs?M&i3f2B{-=Vs?`p)ih|HhM7T0t`(fuK=UP^^MVYe>f#)IXBJHu(-34%rB5-^qhV
z&%twYZXO;Tmy}mryS6rZW9jR#zmHkD#S$(r^JSekeb%h54<8CjUSC^lay)o#_Vsm%
zmzVj1)-8B>c{QF@Rq=du_ldWHt}d^2`8%CYHbon=E`k<M@$>Wl`Sbbw&wcS*vqC}Z
zqd-$8t3p?E-DP+;|J}{a>ENn_=W205!GTU;b<imKj-5Ln-q@I&aczwxgMz9mt8LX6
z2hdVPy_krU=%6~##NPx(XV8SJxVZSz<AGD(-rf!xOEohy`?>G^>(|{+o}~E9G-3tS
zj-V;>%Fk&!aeE|;)6a!uM3sWNzo1o(pv8;-{{CjQTOa>u|4J8^5D{?8PHFGwbJn0P
z0BE)5gNURgCD76UIom1?gPB&A78VachlV`;`1pAL;>5#kOD!f^iEjJ+?|=FKf3;Ke
z<M&Nj7Py{ER7>RN@t@h(*Db92`f91g#9yFBNBR4EwNF2O_)u`;)~#ueTwaCT;X6^|
zKb=Q^hp@7_`Sugnql=1+&YU^pRj5>&M2$}H#g)P8OWgz39`Bcb{eFR#rx0jh<IS5l
zHRmU)a6Uaf{rHE6hYi!u$*?X9nZ7o9d(w>!i3Y~T&dqGRTz`K)4dveaVt-R}^TqY?
z_Dhy8UtII^(~5wFPL0n+wq;5_6&Dw8|M>X${!bO>=h<@qo!Rc8Qe9pB=iBZ4U#>3>
z9z3`rY^~I;vbS9?USzC^-p&Ww9aH5KdUI1McTP^ug_XhTCRtZF`1trXY}jz(yNu_g
z4aLv>TGdSA1O){@eEfLw``*pz=atmd*cQ9>9%^FcW?%p{x15}qzP-75nDxa`3G+Oe
zYwP3t-`(B)__DwK)AxCu9WQz_rpPsPboAW*^Ye4z>ub7O^6$$@o8>g9cyjRZ9h+lW
z3|c<<<k_=N)32{jd~snRXdN`4oXv{=^He-foIMNbhJHA$zdzwfhai{V3O+wSzZ<*D
z^A{cmjo6%>ZGQOb)vZ&O2hD$XcX#sLU8Sw>a_ZjRG6nf=Z`IeJ1f#DnE-&Z5wkERq
z$B!RO$NS{%`+R4c9lU&b^B4BunPqQpCEnjx+bVbZ%$Xzo_WwB6hDDzWUU~jB_dBlJ
zy`P@4mcQTkdmYo{mENbP=@$O@@X)FM>9c1^$NOYKdyzE#m)e15Kp{mnXxI`me-7%X
zJp>ii@<$Uv1vn_H!wP_Y(4wuQZP0Z#kly*mO`A3qJUb%^%8(v@eqmKIp%TVvJnLe2
zw}BFC+SyqVTeGJA`*?c&>hSfC{`~w5TDW5VLZi{L_}PNg)6+l$HcCoL0zyJTFT_Q2
zFD>x|t*rx%%FdhDXI=hI<j1bs-`haL_R`YQE^co7K2@Zoq%`hkxLjX2nYr-In>PiI
zj&O#oi4ct4RpNNOPZl&z^XAUZ$=&DgJ7i>NT)K2AU~5(=XjP)PUQC1Ea_tYUtg32i
zpuN~X_mw|6A?PuQB|rat&HeZH_FCuN+Y>qK@ybi@?(Q}$c@Y5W7J_<YD*_jD{Z&#@
z(wgMs;u6wxzy5#hyDKXv>v#t3(_b5=?e6BLWjk-xlV{IP#l^*KQt>Q0JIgfHb5aUB
zJNwO3r@W@Ac*>b%OaQH?dU<*IQ=`;VC*JS<K2JtMLc@EKO8xh{<)4=M&VF*NSNgP=
zm{?Io#g0qKQhRrozdvP~eQio^Ztl~K$;VGg^}5NK<;<{2IU#WK&>^R7+qX{_78VAr
zRbRSf$%($czE9EldsV-`yBmEi!(>x?d;6W0!RnEVFP_ki+A_h|$Y_e(<ri~pDueWb
zm-YNP$S!|kciG!Xs-Ba=*Trb&-`y3OcWcYaoV+}}_+2HQFAaO|U0ofXnw_1!v-I_~
zPlsB$Q+wT%fB*b>a&!9mX{*E5YK5-~@$BpE4XyH7T>jtyBgi7qsH6Wp8%^&?D(~;?
z4CdqHoVdH}t=8;WvrZ{0DuPz<z~|gR!))N%0b1vS>X-gU8x)U1X6@J@V>$>?$iy9Z
zDt6BMeZT$IMQmKO=3+)lubZ;Gb(zn!)JQ)suSweB>vZyOY;b(Y`EvfDJ9lE@wq{Me
zl)NJD=BCuAPft(RwrzXWD{by)W@tEZ|KD%Xmd3`x|No|+pLg=~G~LO*zP?X6h1E1H
z7Ji(h;+c1GQR|(>?)^fwl@%2lwwnU0K0Wc=xBkV8jGcaSt%`OQJ$>@`_jhrNe@{*d
zFLhtGf9EXI>{H$1`scpyT^GCiRO+cI6X)C2&U*h_+B|Q{>FN6MvmURUv~}y&J!xm9
zmL6A7QkptBC34!-I2L~wmsb<!%;}jiL*mKPrwiluR^2hZ%Fxa)589LPY3_MOX0`)|
z4?BbA#6h!?wpAuc$;qE<_xsJY0+lv*?%WZX<r6C;BxI0#%jC`N?Vx4P3=N;2o_^fS
zZ+BpkYxfU3{l?|~^OG(va{cvvi_Ym4(cAUdcqBke@E6tm{N&ZYf(vBZi;IgvB^-l(
z*~+Ql5&wwod9ruz-Uam(|NVH(4;uPixNzameeWMVYPz~Qe6i<bH7?&}db7>*j~(e0
zo;YtFU*xo}yVatjqLQATnhIJAdPsN`H+ZELXhIz_B5)8E=_p;m<B%RCIMOY^Q}Upa
z1~&PAsQ}cy`ta~DXpX<Uyc{&~&B4ca?f-0xgaZsqmMwd9J-$A)BB<1&^pyyx^sV>3
zb^G?>^z-uy%F4njj7l@^@3RF>vE<*gS?V5W>hA9T<HwH!=g<4U3=Gk=wUxE4`f}jq
z<>jDB=;-KZh68i0%O}j7$(f#>&ce!i@Y1Cq$YN;6tyx#&Uf(%#<j9{^;gyr!7Hbx$
z|D5jK&9(dR9u?0MCr@flz4>B3Xk)C0ukX>B#_0<#W=xncfq|W!eaEg{k4{Wf{yERO
z_?gd}J3EE1ua6JUh${W?^{Z=Mo*ol3^HjOkj*gHX$jbMvDUrvHc8h<GWx2R6);hyP
zYN>m$Y~-|w6DBn5*<%Chu&b%5dG)*ecc`qa<lyE${e50pQBl*%l`AhTUdgAw!#Jj@
z%8F0ku1DHD@5TA#emUEO+}yQaGF(y^zzbcB#6U&=gtla7p})4EPQ3FZ!vs*5-9+a1
z#24>7K{Hzudsw9}8T9q_fo6uky}jLzSf8XHvqRwYbp7LdtG|PmE~KWXAHIHFy!zXl
zMxE0eHf>`1ut-zY)9L@ezZ-LJo9)x<E_`)G^UM4D^3~tofJ*48a_(E}e!W!pnPI@V
z+;48v+_`fvJzfzN7bjQt{$8(hJKw`^Z*Mci<>)+o_>j@x-{0(sc7};m&h2fy_wL;T
zEyTLK%vZZ)VP&A0PQ(Xs-_PHR-`&~iWZs*3f8X9ilO@;RulvoLmzS4ucbDm{t=aAI
z^?yY-Zro^5@PGky2-y3by3yNQ4!7~{+^`F@hsbfhUG0N6Z+Ze3yB$1tj??XZ0t15r
zgQtsQ$hr&j*PfoLz5GCli^~!*a0l%t3kwTF!#{CjeR=Wr{U;Qal$3rwPjVI#6coJp
zI>8=^UO9c|PD@ZvWTLXW*e-_JySqw3EsS}#)yqCCIhK2EP2>#wdOJ10IUOe_tAnP3
z7#e<mf1iAElIo9dxAP5)pZWaw{af2+W#Q|)yUml5l0aQEle{}SF1SWaQhE4%etlSm
zQ|XU4o6mo^oxfjEON;C7?(+7vYjYPqFFZL(mCM(ozC5PE@0gCdI=gcl&%r)fYlYKB
zIyyQG3^QlWoS?!P7Z>;A<8k?&2d`;^LbmwX8ON9y8PKkm+*>A~!OoxaivRp5EO~v6
zH+oyn!~M)hFJzcZP~qI9v%lytr{|;zlP3qCnk*<daaI9nP2khdpV)iPobj2W8NAHJ
zTElBn%bh!Sf@b*D&N9p8>UC@G7S{)@0X{p+RQucii7K4a_2czgUtW3q<>h6D1@|kz
zJ$?MBVEL^-plwnfla}1y`RVog{d!=Pb#--14dz<)$XE(ZQc3*!>gt6I6A8<rl#T!U
zRXl$@Y?t>+wED`y&CSdJ+UR)y@uNL8c6$$SzdN#{{=Xf=g0!=<e#(hIfBN|)D-}AY
zPvRF>eSHO5a<R;Re%uSDFP@XtK#j1D{{HZ?0Oj!Qd9fK=qjGL;T6*DeGdq8q-*V@e
zm>5m}WqPHru4sPC+doM~(adby6ty7rZ#yDhzI@5S$$9a=^@|4&8vN#3Jp`>mC^Jw#
z#`<EZvZ0~iRIN}*o?b!1>X5D|17FqepVHqx(uvrxKxCPslG4^kOeIQ6r=CAMJDZ`Q
z>g%hg)iHCXpI`pR#@1HRQ>g6C4Mt&M;lGa`y}7q{x5%>K{zH0Nny+m3{W;29-#J%a
z|D0jW+gn=~Ud$-?{LFX8%$W<z-riFEb@<BL+uOY}ok|~6NAc`iezfB5^~c^e{Xap)
ziGA0>^HPRCB9%e4`@Z!@AN-Dj%&>uGcpj$rO8i-4DDyiIqz$ASGRwMA@#q7vlptu#
z;Qsac-hR7Z9LM|R-CbN*ii(Rr>pJW&ddhWcdwxGi;`DU=@T!o-X?b~l`TPHhEq3qM
z`|{(})zyZXmsIX~&hv8h{D1fH-P-Q&@9Y0de|~=6JuOY`-~UN`+}zxtBhzNs)$VG#
zEUB;O@c*@K%?|<7>}y9ZE_VMq`&huqD{G_0Wv$DOY|FjPW&7^+>+Z|T{fjqGzOHiG
zXwsxfJ2aUD1t&87IO*-;^7G2-aQ*xGn|`=g9)5Fk^YRnNLyX+}<yaY}Xa=j@Pp-1P
zdGjX2zu%|-PVZm&<lVi!(NB`KW-eHu!0^A;e}9e7dUZ85wgdI&AD=${rRv(cSZ>cr
z32AB5-W%?fqe@~;{`co6sPdDMl?AWInxq0+bO4%Uy0^DFaIqWjnOUaZFAaO+)<$hz
zaQS82PKMa!mluYujaq6W`Zu^Rai_%pf8X~T*8VC1&8sCJ>p2J-XacWd-S_`r^_e-A
z!cx6#mzVhlR|Gv477+n$PSLhKc3<v&@z1n(cXzX=r#}yuD=#a1cK%_$f}!EW*-8R}
zf|@Pmpq&g%S=ZO~^4tFrxOeX!Xzk9W$1CnVJ3IT~%a@$q-rmr;f;DT`PL*@Mx@gfN
z&|2`N#}$}9+>ia**~180)Tb;d3|^37q?Y4hBnE0X^rz&2*6i3%GEB6ev@yZH>u8%w
z@}W8r&|H*`p`qaA<^IS0?f<r1xe~(AFm<ZvudlD$>;M10zanbuszbt3_VxAkKYsrP
z_5Y48@tpic`qP~~mBOc|=^kDcx*D`YOYhl#dC)u&!;PCaA-PEXm-fwDw-!ZiPP3@^
zkkFXCN$2q4!_1(i&*sxK7v8uLapc%BB~{g>7g{efv+)EZXnlPod*Qy!`-XqlD}H=X
z%(}9o@xg<HeQMnsGA=54Olkp*cui6PEgm`g&wi51!*2b38m%uoIy~0yV3^y{!3B!W
zbMx)_JttjQ;K=;r*RMy1`R!Ypo0~5!UOCBaabs&M>%Hptwm*LS0F8ecn3{%G>0B)=
zDmt{lvDqNu00U?*(aXY+(}xZ*?XCLS)Zfov_3h2d{kPes&T(7p`1;z~hmRjK>+9=>
ztdEO*IWgqq(W9)*Y`mb#JaA=@>eAzZx^V^SZPTZVv++u`yt})*czGT(Xnh2vf&LdZ
zh6ifsleEX@f0d`FCuq~$RIShj7c-{FxtkUh6&aMg2w-7hahRm?_j#G0A74sjTYo>l
zS^m8<*Z#;$^|DP;Q8YFdPCYf{qP?D9US6K2&vLo6v^3DP+=&wnGiOSkIdi7Vwttd}
zqPF(xDQY3=-rn9dpU;|0*jAM+JRZI_s#P<1nS!$N;wkFE)1$ZNf%@<qyu7RdKVo;Q
zdOrI7%d~Lg``NQiv&HuPdZi6&0#8=+ZQ8rnwn2RT)zs6|5`TVr3fc$v?99x?Zx(1B
z_7(J6w&9y5-~V0}rA3dxHKVAOnVHz_?fJ+1WUWEN{~nWA)Ya8NGsOoQ7*~K7|E)T<
zulBcqfIvetJHL{)Hn*sDn9Kive?c(;9*qj_on@M>q^QWaY}vAk?{~`|K7QP6SNm&0
z%+4av5<Ae8P9rn>hc`EkBch`ZU%o7CXJ_}~%F4-?7Oy;ZWo7Wj;^%&M_SH&*mLK2Q
zX<SoN1KOt@5gDmzJ1;9_br`RwrzdEX=KH(5Ad~Oytv-C`PRz@TA+6$fIzj6S-@M5I
zZ5?N3<7wEw-F(j6xl`r5ry@rAK-o(ZRMLZ|>!EW!n1ctP?Oh;INLwE~TNL3x->!A-
zTHR&7vybi8;wpN1Nma(GgkyW&T_%Pbw{L@T(%Pu4K@~=iw^V*k^OywMu;)BU<?rK1
zJd#FBKvk8bahk&<l^?%<J1@TYLS8)m-k!>(26L-QUtVJ6<Kv6iUst>Ecssv*U-b4o
zMGK1^plHs!yUTI;<%9R{%SWvh6V(pW`BKR%Wuo!)<P}|OYiUq@v%BnVT&3U20!vHF
z4`06?T^GAs!Bgne6isFZ&_G{G<go*d%%GvnJf`onc4#`C+;iv8(wv){AnlCKjt;KF
zte`zwYdShOa_;YwwJv{m<nHeB#I!WF^78T@KYl#;`~7}<YisKz<yB5@ZfxJ)-R*8@
zV34t|lc}t%+^}_P>-O#Dpnb$IUaa`i;pRIn6(q&T$arIWzC3i}>Yo4qet-D*v2piq
z>++Af3)TJSJpe65aByG%t&h8NC+5nU$l(7`IrsMLyrjIU$#1!{g98J|q9;#MX3U=b
ze784C`7?b`o4ZfWwyU9m;m!U1@-JV$+^}iWA$Iv126=h;l9!iSch8+J0P0ReMM-^o
zbF;ajfnknCA=4(E!{^TN+1c5B`1Z~1@v+{ia)DF9#V%w`T%ZinvN@4{@M>Go_8U;|
z9z2f>Sxx^DzHSn{2IrDNj>pGUp{v_&ZcYakz@b$lS37%po}?RIydUA?!voqG#mLMC
z+QYIUcDES=XuC+n&LUM%pF!EZ@4?&c_rofJ9*3=qvGkc~)LK5-?7-#a{tq8KXaFq-
z`1ItYSO4ejf?{G}FP0g;y|p#C!l?AoGLHJ*c7FLs_x4ubIn&Y6(RBnAabKeR=2$HJ
z?;Pso#dT`Be!pGquLsBF>qDwcLP1k%eX`b|g*uzl&pS<0v9Pjw^<L`Zr|F#`JD#7P
z|M<bd=AUIx*T?KMV&jwH$j{F&d2zw<rC_MCrKO~G`8yW}2ZnR=Y`GaSuB@2&Z)-+=
z{`wCs$Mnt3#oPJi-5eYk>V7^Ix2gRlBB~VvTIccb?OWdP@bIPXCRLG<kw2bJj|UYK
zplS1;pPz$v-0s=4=fT^zz1wncYuPT!`p{&3SXD(u!N5SEv9WPS!9yk$Pp8dkXCJ(N
z&8@Gme`Qsu_e;UhPVmxq$nGcbcnfGl)TM$PkB>J%BYaYQ5I$sbCK0?AQto#k4=7SW
z8>XOIj)C^Su2`WVV_mk!rQB!P|4SJrpgrX^H8l^OK0SK=QP75}uUR_L+juTsya?*G
zS(m*z&~N{*!?~SL)3z&cWzbTu#(MV6n>J0DIFWI|gS%O}y1Jm!rk!7Y+Pei>!K=e`
zeP)~SK0ekPTqP2^I%=!dvokXf^Cq9rC<t!3^!aLdeB!k=k>H_z5hW#~Bya~UUqw@s
zQ`x=m$a(w!Jf4$&G`EAM$pi%i8V($Ah}l~u3R{`HRI2susrco7vOj+ONO*T=r&s@S
zt?hYtFYOmoR#sN@6q+-4uAr3EsxKL<CeEDM`S<sCWdj2N_dXd%KR>>l++0C<`So8i
zRt4UOO?Y*6HG6z~Jh&<K5maVMzB|?{{ma_g)!p5B@x=pIuZr&5x9`V`#r;#{{2|3A
zXt8iRsICNsI(Rv$bJtN&xtL*Lw!{LwloYZy4Yb8E0@SdX&<0up1uAJXEzF+G=H}%+
zx_o{em$bAr=qULW!OQ&?&KCQ)uA3Ef_XTKy$)iV)zRZ2`_%XA;zkft@w6^WN`$FQ0
zod-WhSm^7oH^0@PY+&#~f5x--$>-)+{`h)5e&OYp2}wzdzF4gKdQyEpXbU?BA75CN
zNa!r<a=l;Q-g3LUyDxSBdHcaKj-}1>Z@RdI2!TUfb=uUat^fZ#x98yCa0mzx0G+V0
z*p0WMvNG}HBvr5e<x$ty$GbZ?FfcJO6+Ax1J7dO-5B=ZsH53&Y7rXaAb5&*Q>gsBm
zKVSa*W9d_;PamGB><(I(!@|n?QAX;)zrVjh!^!d8Y>!yWlR(P|K~pvQ`~MvJ{9_hm
zOCM;>ZJmh>c$c39xZMF>z4<#(2V5T=-T>YR2pUZK`y=f}e?6}mbds_y*}3a*TaB$$
zuiO9ot-5=rq|SW4Q3A9v#=(IBRID61;xa`yT1-w(?!(8Aj_c$01}yWDT<ZSk_5&py
z!wR{TCVxMj*8lMRd%MnQ3Bx3ooZMXQ*p7D(A1*vl@(MKO(IaKbb#+zf;S&>;<98<d
zY)(5XGUMEjO!!y^Lj!2KZ)^5-w}1cvtI}6XK9syV;w$LIZoj#+V}**(RPfwGbX=TV
zQ*$#Y4TH9Kf|j#y+SD|Cx;UsJU+O*G{MOWu^WPn8X6NAH0hKR@4j)!LZ4|XNt97aO
z^h2jld%ye`^88RMHwOpDfpc@MKR!6f{8v6|#glh;cQ3E^joVivxk+bn?C!D;A3p|G
znOwD~{k7#Ef8EKGCk@Qak2f$fSMc3;aB*q*XIuOHoGhsOSN;7RXw{!<Y=QfFbwfk&
znluLohC_!AF)-*xZ3(E*0!{k&qprB+1+4?%{rT%gKWH0fva?hlxD>L0l``0N=iNWE
z%y;$_ImfS7B`+HIWUU_Te!uT9sFTLKrT%~2p0C%UUtC`=52`7jJzMr=g^SD5b^i11
ze*KrTF3Z`MJV~W+@noS(Sz8$zKvNIf@7HM;%z6It>xoT0>F4KttdUH(u)q<t%LBBp
z(pRvfqeJ8vE2!RHu{r(xv)h(euUruU4XS{e$lu@b78e&Ubq|?)<w^+X6cR>8#tSb?
zPMrN~|LvWP)w16o|NnTcCMYDdM95`g$F1)|-oh%bIva(jF3HeUEL*#FW1Y^{tw(~Y
zSDs>7ctlLaYwgQJ>`TiwPR%(oDfY>~e;<tRKb!1o^m*Q$oiAS(`kl{w)>j;t?w2yp
zsQCS!w#AE;nV6U!Jbv6f%QRcdHZb&FT&cZ<g#@^n1lne{IsLpF=&YArC7G?_Qu|w4
zSXx?I92Q@EaAjrii8E(hK+6`BkMV%|1XW*OdHI`EP1lcab6b3HTkh?G_xEf)Cb2*o
zCJVyX$AMSmF3P&Iv)KK2`LA1Bvl$w~)<z}1y0Y@ar%z42y}gIHd*$yJsGmDMU4LWt
zb-fG|DH-cBp7rtj+nSr1LCxeJzkV$WTN~x&ZxRJw@t3qw{wrvN7gVhT)#re=-R(-W
z2NihzyesX^miz-xH-VJ2|6L*dZE*!y*RN#oq*Oca%KeSZ>{_-9PZ$^)Hnz93gN{y^
zHmz-M^>@&L4vvnFH@0L7zj^x>l(3hk3k5PBJ$m#ZbWO66vGHcv@1H&eB}}bqX>HZC
zUFZQC)~;Xf?A9vos-UD~Bxl1ox1(bdsE2fScRAyp%8Mz_&djX2=)!MZ_NKvY@xh0O
z+b2$&*7p5gH9u&z{`&R$QQLA>ez6HX`Eu3oudlBkzaC!?I?e;sA_E1jrluwbFK?^c
z;)4^F-6zbO$7gMA4H~?%v$F#YM^`PnxV!v4I77?G^qiiq?>sFPw1^M1o$3F-zkv&#
zSeL4=I%aQw_38Kf_3b*RL5&^Injm?3`H;0yp)WgE9WcMsIdR@R&}MJv#TOquIN0pr
z>w6Tm%44B(`=RUC#X)W6sznz;#ao?7``;Dz;9fFhqubF0=U1Ti7Pxr)cVhx5m?2wN
z*nS7vgVw`?mf?aTqZt%mmkQ+U>w0e7hyV>bt9nlhsp?xLsvjq_x9Y1?r;zG|Nt2pD
zt&xk1-M!8$En@QU_dkANq4UCv8Jp%*{QI`#)b<Lds(UszHdE#WsPIS{xxD0biTtpL
zW0!TshlG9atN;EgW!6(vTC~V%Qfg#a6^o#t<aDdjR|l?N7r%G!UO_=YKvmzXnKNb_
zICO~V?yl12_3QO*Y-|$Jj%6PZnX-HL?r*DpPt^{0gLIafe|>$eZR;EAHC3y1$`p}^
zsHjEm{otbe_qVr+Sy`*Tm|Qh5G-PD3u(CRI`?j>5o!uW5Az4rh?e|K(Z{NP%@;{Mz
zXUE1%mqVV`-!FLn`0-)$J1-x6K5u{g-QC?EA06eMq7ldxySuElzn|Z#^wp8)Z<uf`
zEe8c4D44<BoPVH}E@VYS-4%Io$io&fgD1S)GBPwk%e7~l=QA-JI(+!yyLWv*epGD9
zzb|K;cE;iSJX_JYm2&ESb3o~FUF_};UtR`BL_}oN*Ok4x;`y@D?f9uvTKCmAEM30*
z@zvGge@w2*m}Fj3x&OVlug}fLhe!T+`3##%&>>FJKJ)ElL92G#+u6->ZZKF|TeGmS
zJvupA9dv3(qulTM-PYyr9^Bho&CswaboHXBtyx_9i|V<Bg@r-;j$(I}Ff!Owf8){9
z)4Q>wP<fVl{=CQYLHDjC`Yov!6c!ftnAB1}SL??&yFV(GN=jAY^FSL#Stre$+1bu7
zzsRYT3%m}wPYblx>c!2?>RwZ|mVOZl-Mn!lcpU!m<7TtmTN<|RTdm69@x;f+e|d3{
zdD^sTUgrasZV$ipTz%q;<vufwUR+%bs{J0kdv|Vi=&O$W9m0ptoZ)%*?j5L}et&Q8
z&pEjaIVYOHEd%guH8>g|jf1wMbvhETwJV_14{jM~u>HQc;YL5}an#xEkD!SUIom4G
zO!bQk3z^f-&T8%G;MlQyH#38ct!-jfR@a3K0j<-ewsVW?IV`@I@cY|a(6A0@+xx!S
zYEX&m-Y@sZ<);mgl*x(%_0!FBZ>20Sef9Lwqo4=JKR!7*nJp^V#KOV?bmrBuW4+QJ
zpPUrFaqCuAz1^uzJ!ZML79<{Si`baddMUW~-a_YggTzBEIrE=HuMX1%ou>R}%9k21
zZ|}qNY^w|Y{iy`4H=j9kW@MlDq!!S13|r3a*lYXn`}}+JZp@aR_rbfZ=*NeLO#dbS
z%~4TWwC4j$iIS4mgc&m=Zrr||z23$9SLM%7s-SdO`1lxTNtM@m!>pGtU)CJ%Xxv-%
zl`H-HJlDf*yn(w)GM7GI5tNms1sXZ#=jWfIA0PM9(oI)am-lG5czBiD#AD`np2nAy
zm}rHpSn#DssTZ`2$ngJ-{x)zmFta|#<8ZR`GkNJt8^A?BcN=eJMUKbcjq;!S|7KLY
zIsPZvUP=s<Pg4GEl;`aSwUmwi-<a^oH2WIQQm?6pHYOk6G&g~h0kkyl*4FI8|Nm-R
zr%TPZE`R5+_@aV^g~auBvCTTCL92agYHL59RG)v~+O@Ekoi0n-g;c!~j&_NHcF#<j
zJUMVxh$iTCxOwyDF*Hoo4hQW40G*muv9gexpWprYxw)VMnMcxyWo!0zHU>}!LfR|`
zv<>ahp+gte#ae@+{`dFyk01BjAA5Uydtz#8E2!0|7b^wY?xJ&g!^VxEh1K)d7cV^B
z`LnLBjx8c+%ZEiAE-o&|4!XQ#ba7c?x2LSr;^fJbpd%jS>}png5m`L_I`?-&Lqh{o
z)1&9@|HpK6cg+JWNIQF$_xZWG!Bt&Zw)OvHK<jYV#q3-JR^R<?<Hn7k2HVHS$GP(Z
z1VzNf+1=gUL7UuOYP#vKH?KQ({P^Oityvb;-*Oc7v}S>aZy>=9I+*9@@ir41vy^`u
z6~V#%dt<_l32n#QuE_s}#@iYDZ;Ky-&eU*zCja~52T+No__?1~^WM|b(;q&4I`#F(
zPft%Po0)AB5MSvIZE)<V`pRXTcIH5@wE2hE>-Q&pd2!L^XAJwvlP5tLxT&dW$~-3)
zh7FrHJ3BcsF&wybNhtNyl!Lv}=39<Wo-}E~oH=W**jxpzsRxY|gVwb^J2Mm12$?=z
zJnh_^PVMk@3&Pe$%`nZLcFDN+-V)Er0`l_xpe>)@-rk;&3hr+wB`G~SJDXiwTU*Au
z%;)7yx6|j(uRriV@ZP)o`}?cDzFJuS{~u^Y3TWleT<h|r$H#haY)E7VO;3W`3zIuK
zUc?{tfkf0K6;K1>;cUet4<2i<$-DpkXn1A5&gl~;PMjz^>ZN5-XaDN`*Vor~RDahC
z3JRJsZ&6i_N8yk1Xdb)1qz{E6&Hao2-I(y`!|%X)P&cLj(TDe2EoyX*K6t#s-mVQ)
z6diu={&yp|qBy$$HdKp5jm+2MZC84iE>)d0X;P7G-Scy@plxNXJ3MSb=fTO#%Uf7m
zYuhgM*sx`bi;D{js3Y-3<Z9)Y7Zd&J&)vHh_hHhaqc?9#rk|U0vF`59;&h$JO)R0S
z!(7wS)TZghp4$KaXTifmtY>DM^IyAm?PgzObo66Towp_PvPi@-JwZW13CkiCP=8{%
z|9qy3%XVU7VxXgq*2VAdD|~zmH2uY;zqG!)K28KwYHZlN`S7{9))zOWdV@Ouudl6j
zc5!LBWZZkH{C;it1N+DC-{&`|y10adKnfs(eHyMIB_GdP{(7A3ajfNje~QnI2`;X}
z^RtgUcnlHHxzX?9Dn38^%kkqAdN}vXgZ7SecInw&?>KmT;*>|AHQ#kV7#|<&Jzb__
zWhM3c`ug_e%a=2q?uk!GSn%z?xLyoLe0+S!su0hEuCJaydepQz{e04k3k$vc1E+%S
z4_N+u;`R0M(h0s74U3+5fQIZcGcz^f_E<bSH<!D-yd1O@haq68*Hj&Qc8&CB&z@EM
z`%}5@c>JCU#^U17PBBaTPM$njP*TFe5D^*aI7wws#Yd;=J)x_^W>^$13i=$PuB*$t
zaN$DGQYRrHp-q3!IZaa0iP;gbu=Le|ZlxD_S5^exdj9s$pM5@)RKOKx<s(i|M?}HQ
z%nY>u2ed8k%M_)9ckalXoo(*^^3u|&^PE^3^3Mr2_A5#X*MX)woVyO!sU#nME@k+`
zVv^y*@5++Qkg0yRnspcD<(-Yx{?w@?9{`<Z;d!j>ylK*hLY1YUIM<EZ;;=dGENDpB
zV^RyKG536a{jpnHvlUMprJb9z@{7-6aRGsbh6V;uR|9l<7H9*6wzl@t^p)pMP1Sz*
z@L^--<z<OKK0E{+hcb2E60X<R)}Ah6+NE<EG(HEKy4hb}e`QUiFav1(8#LPt?G#U)
zwOT4KFR!4u_;TIb2M-#g&GW!pl}t@t|Ni<KxTm6!ReV+R?Ag+wdGvL$yBB#*R*US5
z-BG}Jdb)o5?%lhcUSC;U^z_t^-|zP`G92v^ZQi@rR!Ld;;^uUJh67(;Uk_a5!l|mh
z>KJGd=yHE~o61ir*V&$PzIcDETj|B}ijR*zeEHI{eY<(q^>u5%$S5fVS$aOp7whcM
z;GbXr&r<&e&twMZT7W-){#@8o`B|p_|F_%upaNsx|9`)o;@rN}2L%Ujto>aE+K2u0
z^z`tmzO2-=v_}V<*;fQCWU8<9?eg;Vbqxp*0Ie<N64e5=ZQ}M;wHl|NTM)R|t!DBJ
zxk-~IZAdvO1Ui+2kB`smd?2rxiljAo2RdkG3$j;{yYH_@)&bD!8BfS&sX(4@$p<&e
zd-8&cV)>IZHYk>Y&VK~05<lK2d%8#|?Dn?YjagT<=7~(^umAto+(e4Esi~>p<t5dK
zhzQW>KR>=)_P@9>*?q>WSz5M%qHETy0Ub&A<x2@e!_1kH+n$SiPWtr6B$Wv?DW7v|
z3+HnG`E6_0=1xmCG&C$IECiitVNm%grB&?G{*!B?w_n(l>J2)*?CRCfYR8t>*VjLO
za&q#9jT;ZnG)@oLTU83GDnVz5e!pLTT)zGfBf|`{Tq)=&e9Feg!n4hCo7S(_|37yw
zf9dOMu1-!&*Ve_(etz`skN30pTwN0hn$-ZE?b={2?)l-{w`=ou{68ul4>}C7qq8%x
zXj$N{nx95ZO-%wa;0*zwmeYri9}lX}uW9m{s-<b$-_a4$p}s&^FmRrakI#nE*I^aa
z)z2$xet&!W;oG-kudlD?uAI3Gl)6BtA?D=hwDCwXsjI6mS+YbyON$G%vUJOqkSe9W
z+&gyfR#s48kgxw!*mt~N*1FBI_}PQ!^Xv7Vq`sOoV@AjB^7oIPo}Rv8)261yi<P}V
z_bcdJ_3-m+TfJJljZe1g;o){|TlcHm^6&S(ySw{y*5(uu@KDxC3D8)T^Q(4H&udZ-
zD`>;HvLrWnBkEs}6ey$HOR-5$>S6pHC}Xyy?#6^&yGvdQtqNN^>+#7jPEO7prLV<|
zjEw`=Ms3YeUl;W6&*vqJet&<zIA&)NXso2Bwzhb$1OHybj0+2N=0BM`+jq8^=pm`E
ztAdttfsT97-}gi5_+!xFC0(N01^@s3b&5;7Q}_F=`P_eVHgDeiK-Km9{rdmCJByzy
z>FDtA%h@n|c$RYY++1sA1%(Fnm}iIY?k)$N`w8lJfeO%|pdf>!BOGsTZRK9JY}tn|
zUyiH_U0uO=sAj{KEk~}$*Y|ErKCWf!dbJ{u#SnB*U9Vg7T<dZrMMXwEJv~rke!g98
zz_y&orOyQgCwk4$v~B3<xbpVmVt4Si(zYy63j;L$_3iC##nVPAo=(5Ny?yxP2}|U(
zhmRgLffi?+nxg6DZ))}Y{Cxcn^D{3k>13QHB73}F{`dq%=OSA<Y3c6xx}Qr0#8;jM
zHLvsU*|@m5DH$6FSMOfAQWI3^feOC-`*8<bUxBtftXQ$4X72&_%GdYz+pk%>7PQan
z$FE<9&Ytys>A4DY;LMqMw$Z=K&6Jgy)6dOuJlw|n^H68w2F1_)e^*$4TU_zR{qIIl
zpRen1+Z9>qO$Fd4?+SUdC7|{%Xo(zX71kBm-x~`y%5%5zu0+=JYF**uW1vMlTgAJ6
zK5tb$HBGl0bR6TJfWNP<u5Mqy|DP0SA3Eqnw$#(p9)bqT%J0{*tE;Q?NEk4H1}{J>
zt%7^cJv%#l>bwAzBgc;`o0^(lf4p+#O3)#;M_gZBSmeq*cV2i!;@a}nAuEMIi|rXI
ze&6h=;nSC3XJ@ytu*lfIZNr8G&(6;NSscs`%BMj=lP(#D<bQf{5;Teo8Y+2ov>TK?
z_~q@6Tw5ERn3ct)udlBYyDQ}7Ot<q_uZn^WiQAY2ItqcM*R2_}@9N8oixFG1L_xdi
zzqlwV1u=qa!J92@ZAvC4A-})wDt#>=C^+$L-T8U8&Mq!2@e&#hH#et)&fNi>b+vo9
zwUkN50^79A%+7tazmv|-v#t4P$L>4ZO!tC5tE#7yn_C;BxF~O>?XvB8cble84OLth
z*uT_!`lHkO`&(A7)CBEG2Q>ymRt9<a_#ByE{|~h5cR}!SKkyN7{c>x+#4NtPG1(n-
z9(7$^otJ;$*5KuSiW(Xmii(Oi_EZ{cg|1@B&(8-9eZ}pq@;Yyv1v(kHyZdt8-#<UW
zyMt_OWZu1d$E6o6Znh+GgM8`nIuo96i{IUtkOWQ;uljgb+J9S|xIz9a=*&8^C3&Dj
zh(K+@SAF0SoQE3}QS_81Cnh#Nd6M$>`uklQSYE1`nu>zf*98O!fKK=b4h{w#1^MjR
zvl+(ed}4Yr9lFum7Nnn_=jFdt>BP;Ol8udxAHIA6t%KVvv%BCS6R3)Pc6PS*mU9)Y
zt*xm)e_dT24l1BQhx8t7W?!6kb{0cJ_VslSf4|@FKGP`Gp!{8o>atZ*{x;&unwp$q
zVqyk{hJjUGuRuF&K&=GOQho4%jQiG#K$eYX&YXGh=uwk<zZ__F-;clF?}JX$T$&Eb
z*B+m4pSBSc6#QEcO25y}&*x_Vm6khqTAn$xDQ>gNB$X*TkwWryKNR=<{T6*?MWA!%
z%2kgaJZR91-IZ{4RVe6WA<&$Rpy0yVWY2^Ig=gpH&VI_P@#Pr5{htr#elJ<F1ax8o
zWIpWCRr_Ml0gf5+r$HMo%HH16h~HPU?YC|9Hy+Sw%FoZu-B|wq-l2J!S3o<EKwCj0
zH>cg$mMg6lzHZK2yYKJsyZ`_9_v3N-`Uj7WcCQFsJ&nox>f={eSHHNuU0=#PkH_BL
z-onc2*^iSdW@ctwYl7$Z^zeYDwLwFbpc&ktAkY!(pu3|%^QT9<M5oTnD1lZ<Z$p0+
zSM@C`Pj;4K`yE&gUH}a`v?>|2nO4UFJXqRxu<i;!ctis<athv^D<<<hu>Otv;Y8<G
zeW0DxpxL^L9FMy-UoN_Pcz7H*(kTq;w|{wgnLYV<U+e1C+4Jhxg|Clm-4d`jCDN^;
z!lJ3EX+!#Xxji*Mg?gpUua*6{?Qc{6=ZE31@9+CT9o%zst-02l+3CmaIdEyIcj1Er
zjCXdI^D}_f)>l+jCEeLkxMAD2u!@Bre}6u2588&AetzD=#r<~R*<^+tm7mo>htn9P
zo_cU&W3tW1PqJ#hvsyYjIObTDa!s2yEwWElP3_RttD<spauFL68lAX%C-2{Hui|;A
zOH?}{DT%4R{(t#DNzX|evaYUjiddfa|L^;H(846p)cDGkD?!Ja-?@8NP+p$j-rgS6
z2wEGxJ*;Y()|(p}nfLA62Rdg;D|{VKaPVcF<EoyAzP-II8nxVSk494-=$I@iDbONC
zW%s@Vckal51{$|-H@C5|*;Jb^Bq;c_WqyO7i_1-)xmKdV%l%kCJUc5OZJu{!pJdY)
zVOiPUW4+SPtM)`}O!DyY(K+J!%CO+UftdcKOP40Ty|p!BM}Z<}2-Ph2R>HM4k*(%_
zu9GHD-n_^1$<x!*Z`LV({&v>#a6A9;9!X=a>O~i$cbDmc#xMW={=PWp<|fN~%e|&*
zf#&^Jg|F}X`uh6g+4=i4pG<ufv^_7D;Xr)-U)El?$*=$ZXq)rL(AXGsmW++9?Zg=~
zI_~Z+PyYPu><p7kp=CZZn?PqcKRD3%;nSz4ojZ44DqhKvh%JSwsBVzwZT<_YkR-qZ
zGN7XrkJf>O+rhOFc;Irvqm7EC!V(f4cD26}K0G+caPQAwULGEogoK23^=;xWDz<}4
z_21v#g3i%C+9e7)Nu5W+z~Oi8FMm<(up<)`ok44nSf@#Cckh=wc=f7iU|=9<2cO-q
z7s}w4yJ7Y<9ne}eb^m!!T({m^SoilAXm=^-oaC0))`xFyZf3Y=a~`yn_S2J-D?(OI
zI;7ouf0}NzLFub2IqLJ79aaV{HORQ2pcAp7L4Cph{`rvO_dvTgL3_$C``hpR9DKf#
z>DO*oH#g9>SW&HzhUwG8r*-E})eh$?EGz^y^8Fpox9^3V-F@Q3i33khPyhJfU~|s*
z%In{C_8#n3dhzV-QRn97W<e>buJHA72M-@+o^77*_Wj-6;yo+G1O)@*DwwPU1)pjf
z8wbDSboE;5HMQXLv$HY%^KGle{QUe{cX-^rbm<c46mFfUEgYZ&>Thq$6_k-V6R+_k
z@kocDgkcg3!-0zz1sfY1UtC)|`_SquPp_;DesOzy{yP0z`%{yXoA=fJel$J4PIF1>
zE7Rm-JpY2OI_Smk>j5o-2Axcv66v-!YAfh?N>C#pc)6czL4g72T%CEIu8@=QBHkQt
zg3Pt_^JZG)cmy$l&(N*NInk8t{Hp)2hTQLq1vmPauzXt_0iKy*1&`us%1H;A`_48y
zx;A=y!S8RmM~)m>kb8R@Xcl;P+1n}emSurX0Y5*_)-d4!Xld@dx%X#-hK;vm1}m-&
z?mszMUD?V?>i75epi#EXGThwU&iD7#8m69_qN5%cbWSU5O^2v<n1-$MRUu(vL3#Q4
zuRq?n5wWM{=OzL1mChw4CG+AZ=PmP_+a+b1rC?+v<mu^oV^3xAw8x+e0_x44T|Uw&
z{P4w#4$v9ib$@?(oe$KF6LBmT)e1SVIsH87z`CX0(--C6-=`70tmo3^jt-BbkjQ%Z
z^z`(KZ*L^E!q=_Y3u<eEQo^N6moDrs&j*dP><Eap`}st8P0UWv@oNPI1q>hR!#Dl@
zcwAmkMy6+H@pG*m0kWW21ucJw+XK3Gpl$YS>G&<z9YaE<ToMk^)Y9UbU;nRi-@Drz
z5}n`N*?IXu_m%$n-xRL(N}CIah=5u}*5&UO#Oy2rbxax<nJ+By6lOReU;hVm@_zD<
z4-a?L{M>Y?yZ7+HX7;W6UaIQq&XZI?#~2)H<-Yk&+f(RRzkK`+;ZWrLn|C)V9tGDT
zS9n2dCqd_3LS}?Y4}%ZD75g1%{>Hr!)ap<KZ{DoCA}bwaW47eonKNesHmCW5dhn3F
zxazaa^VfaR3GMFebUZmp^>b}KJ3IT^&sKluJGb*Cg04RDvttJ>Xihvc!!Tlh-Cm~C
zSG4u?_%?3bSWr@O=Hui&n&o+Ud7#V)y5jn6^``@k%p5#CEwg9Oc6$Bd{<H1(>kj|<
z`8g5X!g-Pd+T(g;^54%dA0BQ8?N|1<yDqHXwO}`BO!UqjnecTnj*#^QpZ4rm@$BgA
z)Lc^P;<CiehH-93$0yJ=elD)Apbf7KA08d$2Azk-FK^e<*~!Vo%v|{5g5s9k+hI2s
zYJsYgIhMt2(ES05o<g9(@Rk;qJ3EWn-@SYH<I`#Vsq-?o1O*3g4e##n>jOpWw%prn
zpcOjHS6=%2`+MR4e}8r6+Z26#<O*75=;7_{{QuwIi;La)S;eK6i|fZND0zA5=dSfz
zx0=T7sYra_>XOgG#-^m9!SVduT<4FEj$YiF9S#~cleI2uS-CQE+HbSmTOz`0J_jBg
zY!;2mt}&6~HIee2b{o_+eq8(W+4*wtEZ-IW-+?;d)?~_>8xwvdf<}YDGk<1FB62+L
zZje72u~Ggj=)86C`3vBAzW!aw&XYDiT3*l{xWBFzWa-^qrKdms`1kj>VcHpqJ3EV)
zPnf>aJ19u#)O7v%uRn5$YAI-Ht`rboc^#xA^^^!`IGjO1PL8j<y!^=V<BOAz_suX&
zc3XFU{g-2)k)dbL+SbMH1|1^<+PBW|;Mv*Pps`WV0XtK*!?pHY`muD$63{V-+qP}H
zbvr3Jd1K;Xwk1oKE(~8EmvLjm!Y1yk2hZrdzuW~nT5AFK!auW3GcU39%h?81wY~bd
zh-261PoFNuMNH`E@L&P=7%HtwUy1zr^JhzZ{@q=o{c^U4Kw}Tv^I}1ZWM){G>&5Rm
zzg$Sw>%ohQi+}w4{T{S3(!#<*K~E2~HFJhVp%Unp>9@RAUyfZ`>b<ezW73f$M-JS*
zE32re2wuQ5Z)sNYu^z{yBqb#!C5Amaqc+W+Eq&?oWze`ksN<@l0y@4msA6Sd<=<bW
z`|2%~J%x;njd}O1cmX;w0(5-W^Yio5tM90I9{Td~vS`#YKF}d;?((%QrrFmHoId?}
zZoWb0tu31Jm;d+AU#2Jr&Z_UgizZ4zXV5|V{Gfacp4o+T9Pe(B=WYMHLLQU=`oYJw
zfSZAGzXQv2JPs#1ztUG!WITBAAanpy;dIfo$CFeNA0O-GS{vNHyZpV9p`qdR$DN&>
zJIde3De46+w<>)FnnpR?&fmUsXXUiy^>KTh3JMHBr|e#^`f5?}L80o)i^gTXvy*OZ
z$(&)F-uEqHXVKGy^z`=k`~S~VU$Ec#>Z;JfmzPx6L~Z3tOibKS_jlK~GJAXbAHRPu
z4p|w*wce!8xt;Im*6iz`Ga(r&K7Zce+AX%D`nw)O!pBEPEsCCaOyiabEYpqJa$sHT
zZiBKnH*$_onmieFuJV?=yHSm)uQu2GEGl__PxkC=^XKOsZ9gpH*mZkb?(9p#9UUt=
zCO-N9*Ow1;qG?1#1bE#@`utiph8H(BDhCAz7ykKC$dJG85NI;w$kC&kJ0|_(_3`mh
z@D!3V&6=`a{H>~|Q$j+5qE4`Wb#--*thLx=b$_-G&!(>hO=o~+JYKx$=##ZpGBgxS
zKQ||^Vr3!dfU9;s*?`4vz2*15AM2Io;O9RM8dFM~S!G-MOC)wz$-(^nf7v3ZDSA%&
z#`=8we|=9O`QzmsU0qF!7cahK+`+Ix@ubBD(Baju`glRLE039qB=<M)01&7x50>gW
zSf`Q<!6Kj`1@ORuA!w_YUF|OgO-;^g*RE+qZ_C;C+hfuZ|95rl!otEVtgN7E4okWJ
zkGl0YRDMpgsr<AAl(juPI6w>F*?6T6+`k|H+xYXZudhLsonGv&mbbUJFZQ2r$E9zY
zckbM|4I4Hb(BJ>3>Bo<X8#iw%Dk(9&d-sl^q4M*y#Jjsn_h>MQc4>vKN;ok=5i~-_
zkZ^XEDQMCFw6^ru*Vl`k+xaxY*U5lRNB$7>xa`}T$St|I!RxBNeQVpk-F%vEG+TCd
zHfTqEU|=BVFeC7gcgW)BZ{C0wAJ|lUV0gdxyBxR&wkU6s%0tkOzl?=e6%`c<s;aE&
zesc~?R`*ZH&R$)+&ePA&ZEw}r3p)yv-`v{j{c@#S`r$TSP|J7g)~%O<L8;>bWEk+&
z6wT%rFEYR<tAR#M8X6eh78)BHtEj7MoBD4xGBWz`e15%>nVHzxS*Fdsy}g$vhd544
z{queQ|D&K?1LgOo>)+dd`|@)C#Psy#f2;og`<roj8Sk7qa~K%*R(%Csp0M<a&Em2r
zCj@0Ii&WyjpM4+t?EhKNrZ4a5dX9@PE~xzc479Bs)MIydch`yCB?6jdjfj|W$+%bU
z{*O!xO-)S?AD<S`aeToc;8RFJwe-dt{h%@)v=tlFWCPE19|zahI%Z4WfvRxOz=0GW
zXd17-?O@v#UU2nL2N`St9mfPZvGLEB%l<3k_wTz@9HMGq5b%4CqNmWYUg_yeEALhP
z`(ruJwwf(J|NWtPE39gNe{&5A0(T@H9&XRB7dy3S&EG3|^J@O(fo_kQr0UJ^<WEh|
zzM9G-$Bv18Tch+8bTWNFfIw4obEVRM>mx^xE-ZR_>el-2@9uW@+x_Cmy}gZ<0W{!U
z{QO*K#@wncIX8tsXKi!{DsMTj{`gogGlPYNMZ*7oe{Fu+%=hu}0UZDuvL+(%rRFNL
z>}xup<a2jd>E$|q(E7FS@9!UfbhKMgR<`%$<>lIYE?MwOoAH2F)J)fl1+AOXi`{hq
zw4^=K#brqnq*ZWbRj78&_q*kwUI*x8yen5iO5Wd#t^RYYR~poxXyU$_es@>t471!>
z-?}zGeE6`SyxhH}#zx94r-PMS?7?M!`_PJ|A5We+6H?_gF*!SX^<UPno72w=NJ@6H
za*Jj3r>CSSC@VX!taR(X-~C9|rb3{uuI|P4_4B`_FYfH*1oh`aSBHVBI?%qrrsihR
zxU3kv|9?I+{Ree(3m>~NuL<1mJzY;xMTI3TE$zdnPfl-dZ55Q1?7X<x{qdilpBWmu
zM75Kyt%;N{O6fS1-7611urlw*99>Y!|EEr*pLeCS8K?mOZq><`9)F(m@y3K*55F&}
zc;kL|1L#;U(0S+}Wp?S^paisE9@IuGe0@z<CvMLS_4%(4oIA%?`uZ9x!=1g=;#0Lk
zPhGQ^q_QyO<Rs|vMeC3FT$MD*5CBcHAD6Gsm|wgqY;D&v-`R)G^yIHT&(F=>ZKMA~
zL{zkOQ|f84M~fCcJlM>BA;W}&i|f!-?QjL~LffhHQondj*IT>yfn!vZl;0eSM$O=5
z8U5n=aWbBso?d5zr+#~T`|-20vn|Ts$>iPJ(|P8MkA<b>!J9WFLHl6O2lt*h;jvU*
zgmaHZ(>o_;(DI`V`S<PK+}kUC?b<ca845KuHCx1=D<~;xas2b1+0pT7OTj}Y&;Z%q
z>hEkHo~_!FU%&D1udmrHEiDU@kN0``g-it<U-9Du=zwI<iZjqC_S=m`PfsmOJw1(s
zi|bMM_Ye)x?$W2Hryss`OA54YAT3P|blr>Xzw7b!sXMJSCN8w8{^s-hPSC0lO$LXg
zq($E<+WBOEc(Pf7E|cN@bCTtcO7on*zh18gl^T~WUuI<J7Sla6&$jvk=y0&e$c53{
z^FaO1na1f4o<C=omX-$HKJ)PEG4O(li9MXZCxVXFGY2oJ1J(PWO;3r=pp8$jz^BuK
z+Jq4~9!6?!+`%(Rc0V34@2UA2^ip!wmHqYgU*6xBXL#`JSzG4iWe*?s+lN(zUQ9?!
zYZKFrTHx9(=H(x_bX)H2N5|#sL1&C@mhJBCJ^JhGYtSJetkYKdJ2^2qIXMZ4h_qZ@
z?(aM;6?9VvsHFY!1zcVU_r`UL>3+Cdet#k8z6@?|XD=_%b#cpV>pnm8trIF`^qADL
z%y;&p%*)HX{1qR$3YJ{injK#9_Lk_$lP7QNtp?3lZOggY^nU+;xo_XTy|};Me$U>$
zl}z@6f={LW9n_T;*@Ui-lfAw^{&;---_}b@y$>He=vb{|X(_24z790BIaPXvQMZ_`
z({#Pq510MzAD*179vQcXy#ds4d3tIp*V@JPvq72pSg$mwaSvL3uIfDv)ZacZdv)Wx
z8ylUgpE@WxZ`!`yy`;pX!90BK*3Fv_AMF<3IzQ~w_xtsqeY-7pRDWN0Nw^Et@dMo*
z1KMT`+BC4xx&6^(e>=y$RbK@J1sf-+dNVPAPW_ms8~x~Z{{E-4?e8~&mc@_}i_gx@
z?VhOYe(3gX>(j+%qGvWHAD=RBLDbr)t%u&++<b9gZ8gJ%xF0JM54UN=?%Hzb^_9$b
zcXnpn+@w0oJfBZrU*BUAc;L;VkZE=JdeFQVXs~5zy42b&TTDQUVH_PDK_@|{M1sy&
zHz<D>1G+2*v<mybZ3F|in2y8mZ*M_I8Z#U?F;N+Etwmaznv;_gXhDps`l?gC(&h!v
z&&jH&s5ne}nsfZ-qo2yBjmqBKXk=#RgRd<+bosJy?eA}?&SDJuT??$ey}d!3@{b>9
z_n&Wf^xNCp3omATIBR|%d@%IdsI8#$aR2@Nz4>xyhlW462*0;7Vq=o!K8O6&)TOn7
zt)HGB>y-v=3|@Eq^i=KkA3uIL#VnEgzeg*z&SO%`g$n`9Yc-`nF>`sj|Kp#ZpKsW(
zp<(CFo!=tT($xCoY)`E|{v32Y4`}Z|yL?^8!^7>&6`$KS%&B7x-kKFU$GTkabh7u&
zt$BB)9zJ}?!NI}6@a6S&{%$edrj;u-jf{;q=G-)@sHo7`GpTD+@$++uUtU~X5xks_
zA>r4Tmp3-2^Skv(EUbO3&T!+#4e*k}J(ZuQ%vz-dUJ0@bbYTg&{<bkw(d-2sHV!&<
zsSY$Ns0itwdw7A>h(Jc+K;<{2KVSIeMc|EFw?OCPgSH03#yG!ERN-uFY~<24@l*Gk
z!|>tR?+^3i_n*G~`||(Jo*tK&m^t5GKR-YJ@Y%Dxkh(3rU}n|Tb+OXw{_~E!xVYFb
z^^^!hz8@1CgSfc(nz+4D)r^v-UTr>aclh1i-JtPBv)o$=PftyKad)>lXddeJ_WZ}I
z*Y69eTJ-A5s!(q8{Ch`^c8dot^O3x=CNj7hwD%HJwzbRGt$5&63OZ`Bfswi3*_oL#
z{x<CQY~nw&d@1+#@o{;6ZZ7ChUC=_y(A8nAAD)#vJ32aoCWrWBEE<BAdTH(nkp;~b
zg6?BWI>G@upp9S7#-X6Vz(k4{blULC%gdFOm7QO9y11kq0gveHz5M$6`i-TpugR=G
z^6c^B$!}d5PsP5xwDjYbmzQJu<M&pHK0Q5M|A^}=&~1%1v0wE~O+^h24fi-DFg__U
zjpyd(t}~i)dYV3LEr5$&-H(Ute?A=Mza<{fU>?54$H&J7)b`()<jRnLk3mpGq(wJ+
z8>ltxbvCpWbjhQQjSO^231|f&XeraLFE1JH?Qz%zI;=5#m3v5t$e}}rHrb??zq-<?
z|L&=xnwr|_*;DV;|F30mSn4%()7|YsOT9e2ytKCDW*q}9QUpyWKHMPB4e2ZBn57&9
zB?!<q%q#rTmkMr7V1<qAY<vLjKOO~74rEw>hWnhmj<<<`PM^Q^|Nj2^`o8ZEIbYn|
zntNMpl8U0LD(kan&u*<RRtC+e9s>1Y3YS(rEh|!e8vpm#S5V*S$noQ#>iEQ&GoagE
zz^nXB7Joa;Zx1Rue}8-147v)axT{A<)eF?by_vUt+cvlTb$>-7me_&rj`;ccIp~Pn
z9lLfd%DK78%Rgu>s0KPS(-?FR;h(>M0~fh)GB`v<N$van&Kh*08ff3{rKR4YaangN
z0$C1w`uH5_7S{)j=A77c=KexK!Hd=(LCYCWUH<(1JZMGA{rdm1VPRpQ#x;Y2jg8Fi
zvbTp`U0q%H<3l27H_V<8SsNRh4T*=@dZbLXZf}$}&rA6G>nmtQglI(CpLh56&VK&!
z%9W5cvAe~%#r0SYX#aY4{qOJZpz&wWYWIyBH*)auy1u@)R#0BPAGG@gbQA-q%ds?F
zYU*6;@<qkZ&lMCEohr+@w8S%VUEiNaN4ekJ*x0OpXTS5`Utd8ZE^n`=o}T9F;=(e|
zwwf(CI2g1cbBAB-z8{acL1RM3#>S`Ls;Q}gT8GngA{SjSdaQQZ$j8TLOZ@)7|L4RV
zcs~2^C(ud(@HElk1p8NQ;9jE)XzCDrXltVVt9IT@iJTLl;oall@d9b^xvd*-OxTrd
z51L>y2W|SAkn|_tJm??DUknL(dGnrTD<vD$|EmG5y)Aup#c^lR(|~m`J9Un)kK5aI
zcX#>c%X^9qvaV==rdD!qZ*!fj=KJ97TV8$r^)mW?ZkE5_ZokjKaPHi>$bEIww|`$g
zXRckX)MR!4V?RDVo;q()6=*vo=$Np?LoGVnL2W$H2*}##?E*qVhlDTOZxnYGcs+l9
z)xYQS>z$^hT3B0yj^*4Fz%D4bck;>I@10y+{--fAGJ@KIpo=kf?68<)UoZFk{CxME
z939Y!$M*kzFf%eTdYupHt^E89bQvG7l*xfPmc<I5LQT!hhAAfmO!DqXq@J2`ut(B(
z%Dk0YnVFfO;m667h1Gm!G(>I90-Y6C^H5d(->=vDAhox*=eI9jtQ@zeqOqrkhrwZI
z(bIxgS61qTFIr}<7qg?mEce!v*ZbsazX<BZ?a6rH>KZ=NDD}spT1L<)AZQL5bS&}a
z^z)ByZcYb{EuWib+YOpKd3kB+pQELq6+oah-EZp|K74w5T4y_Gz@W3UlS@C8-E4`)
z8~2Yl`gbMUzv|<StN`WfHqi7R=={Am?uQecK{LnF-;y6D+Kci01})(SxAql}f;9YH
zVQrT3Fwr?E5p?0-xA$9gPG{WNVF(((-D|u3e+Sp$Et!`K9v*6q>5t!4!g+bQKd2ns
zSo5<8bYK=}aQ^HpQ^VwAJfPF&Kxf}QJ3G75aZ^pk#YL>3gFnA~`Jxm5{M-H8kEfVR
zOH1FlaYMs)u}4RLzx!OP(jwcq?Rl|Bjvp6)q*Q8E`^yA0<@fRN@x_^!mx1!eNBdKE
zFE97sn08hQw6v_RuWyD?Di>(UNbxft(8l|T6DNZ9=j7z(PMrt3?a~jvNnkzbu4n)G
zb{srBXFmRzVVJz3__-hG7U&7nS6&CLPytOZn3#xodU`T2aC38m#)-VA=``-$yY~?H
zRYhH0-t22@4lZ)-23;}@>P&7<JNqc~G53MXmxaUE$GN7YsHk{0&7CW&q@=VZ+zxby
z3TU;Cw0WM!o+~?M%$}Y6_t#emi-HB;wuP^cd-&jBGiX6n_4~cc_tt)XcJ{;P&(2X%
zvxI^}pU$73A|Ngfx>NVVWFD>+VQZsSgsv9*_U7i~#~<Zvs~+6in!Tg!ZIq(Eah;l)
z+ReBllT$5^i+{U!@87SluMf>y?ggH5N!kF~LUTn{`jP=?%LXXUH9-rc!Ry%nZUnUv
zK&uJ<fzt_OXAS6F^!hjMcQ-2Xf=)jGoua7fJ?+S!pPvmgFR3hjzM`+QlXK7By%#}q
z3l2p^pv8WjiHF-j$Aq3JtM{DrgY&?9(4CNLqql>an#Ui5g6zk~#}g+_3OaH6in^tx
z<nHqKZElMlD=I9EjEuI-@42@%`?}12_y2D}0~!n;K72Uw>Fe%2d+nd*oSS0_Y8m^@
zx8nuf2laeK)Z1HIA3k}~^7r@m=M{G@Ul!h;fB)Fk)#0EuSfH&mpbZOdpoJGAS1)Fm
z+<HD0G{1K49N*txUqQP-W|?L$`(mS{6r^aplwCk@Vqx{CC!AT=*35kUF=}g8=K2f%
zKZ92Wspj0>CAvO-|FOmH{h$+_s;jF-w8MN}X0DnrZCV@XK8=fuTszPQ^3Qb&tAp-(
zy>aUnXlKODzVMYnto8r@Zf82(6aDhiQbA$i$xpW>9qn3J{r%m|chb_*+}YW$56xN@
zRsZ*^cuZ_8XvgTYv$G#xTN{1T?j&eb4s<$n#md6n)!+4w^~uhDUC7VRFJo1*LO^`w
z@iQ}xr_Kv_vO)1^l09^5PC2Al2CevjUR?oNGF*6L!mdR7F3{{7crj4~s9>1z3%oHD
zHdiBMk`b`rxA&x$ZgG97jNV_O`f)O#y~H0M9i2LFQB=PFkzdQVW?z3+5kIeC-sa%t
zeh-gy3g24q?Cf0l{oUQ1@73SlNH#S$2Z9ECW0uEFn>Ovk$B&Ku{rry}J=&0a+bqLG
zs^;g@>7b$VtSc)HP7e8h{Qo?UbHb;Og08v&?Gab=oduc_UJ<jis84-S`Ri-Gjis-Q
zYJL>-$lJ@=R(}I^B|%4zfTwu{B_ujFY%tJ?-4*h1>ap|Z&+|JvI)3>6{kf|k*NN-b
z#Z|qhwSaay*4Ba!!m?{~aajV{Qc}4pZm-q1cXzq#>;KF2zrVX%95kJ}$7}AS$&)`G
zWS4(%T7N&tCeRKI@S*75ra{5M8=+Hj7cX8cC@(+$?d|QKi}uPH85<{NX3l&KI)`;%
z#nk3wz0%3|_tpN~wd%{h+TRye1TJ=pSeiFk%@=gx<EENP2klE=UShqyJwH5SZWZVt
zke`eG9PJiQ%+8MP=)TgN|4*bJd@F%HD1Jb*ETG0#Gw(`k@X_doH~N1igW6x9K{?Qc
zGN3#P8H#BGP2<>rM)4;++NfBXo}A3=Icdtgz$H9VCLGb*at?L~DktRSt@|Pq+S%0=
zROK|W;LD3Z&{@_8W>5a&?BpaMBsA%9ZT6KFjRy`KI5a0*<;JaBpjG#vn|bo?@9SL~
zy*+Jr0aL2_X`{HkRa0M|KlbHIiHLSs&w20npy|!G|NEuQ^-ddlPEvrk{i<iZ0u6xo
z%iA9_zhBe5xB7dUWm-}acyZmC8HQYIgZV-8s*aA1FYfKFp7(#78fcUSG9B~j`}gB3
z0vCf0VC?}JJoN@>nbC(21#4n<20fhm3bdl`%a@WV8i7tPHCH`(@uK6#jR?>&o~y&x
zU)z^4|N3(A8#iu<T(b$yy0nCoPsU=x<JrYVMn<5NxFzGFQ)B9}v)8YSH?#2`0^R?f
zb!A1&`|Vj*wLr6Yv(0j~j+DMS;%_9dIRE}WQ2pNA%<R@L*9-28gBINuJ@v}Du|e@R
zH_MXQD^_S&fbN_+yaKcw3!D)_qiC><$jvWpln-8wgBE$m4;`*MBMn`R3EJCQdb|xZ
z@V5K$@qTUFg(p_V@3#YGi(RF!lP)Z9EGQ^wXl-@f_WSFrtKN;J$JS<DUFGGkA++z$
zCvP5kJDE*7hwt5!TOGFc)VIHCo<g9tqkp$6iS~f6KX2~s1r0766hHHcJEJ3itVgo>
z!-s;H-DSGRANNX`Ivwwm{rGnKeX&nQrJVfy;Z;r(Hzgco0^RTJ-Y0W#Z}oSEJ(YH^
zE-Ykz^Y*Q1+;Tq9aM`c#@8`eX2s*mp#6;zaKR*n!uC3wZ=kIrladUCWQa!mzN87du
zbOP#{$juuP4l?bj`l@yM?a?k#(8WeSz1J~;4n}`>Z*RA<d!L4_YbmIK`hWiY)q$VH
zxhuK3xj{=(+IXeg{Ox|S<mKgYaB(%QU90=-{QQ2<wZbnhF3z~SYwM-p-Y%Wfpfi&}
zC*!XSRtIgIirZVI5xPo5NLaY==ciN_R#rtF9iF$hwjN&S++M+YwHzcVrW?glUtbS8
z<a^t;Z5<sQ4ZC++Gk`9C03BRCFaO#?^Z7xSwq}RRSeNmnrKR1953{fO!XYUsSx{Vj
zcwg=Bid1h~(5`aO^=9YhT2GueZ`~J}#o%3Fpbi$IpM4OzKL#|g4qBiKTKxdd-$@%l
zJCtVBgXYdb&FU`DI4Wr3Tt#wnz1{OCZR&}Ei92h5n`wotI3RqMwY#&kaqnK+Lx&G<
zJ#YFY@9OIC_U+rvK{vNNsi?WOCh|gt$&SLuZi@QKO0_b!RVMM@fB$&g&%4K^*2&3f
zL*?f*P{&gveBGRH-$0$5*xhBWpx!)7ow&HTj8%!oac*frLBYL8g)ek=XvBjqijtG-
z`~Cerb49W0wz9XkQh&B{?!A3;b2{jNQ_vwR=g;e3Uw!e~%3$}#(qp;b-rQu}Rqy7;
z_Uz2e<OQa#$3aInY)n4>=;!C>x8gNUY~snz&R!F@*Xq3X!@skaE?Wj#`UTnx2-<2Z
zGdWdq*|KFn{(L?U8V>oFq$VG=J&zZ(`^KU`;WqboNlD3!OG`LG-C7x&ih!3ZR|!Z-
zb#2(NK_}e*?VX**yUO04GN1V5;i;+G5qqmlL1osa)YG6<8lcUB3=jVN{0v%@2%7Io
zI@)#c_HF6=_5b%C>b}|tUOoBlMt|Eu@HmPNc-;H$25>XDAH1L`aRaEC1i1+cG>HN^
ze*|Ss<<Y92pH$!7-3_`%^2wKNsc{iX`TPHT^4|CE`Z8Z>X8pkVhRMf7Ui_P+qG(`n
z!6Cb&NL*OBxl2?#ZRZWny|Y0VyswF9RCI28Qc-ibjTba#Hfi!??n=qO(MOIQd-dh{
zn>TM*^cAZXyZ6g=^!FcM8N7Vcow&_uzIXQ3N(-y|xm;f63tC#2b8nC2=JfN&z*EHD
zE-qOIK(X1u6<D{v;oRzrX`o|kOI}=1jQ{TI?cF?my10|GGw+^N86I9<P8AgvNJHd@
z4>N~_g?afKSAi~0j);%|9n34PA9vu?DXy(qSDlvo%>`e_{d^^x{mF(YVv>@a<>lo|
zmMzQ5pRB@pzwWoLk&%%><)@U0$jF1|&+{iA?{hucB`O-@{of2+ae*hE!3Qk_Nl8!Y
z5&a!#51DfYuS1+T<yf6c^0BrnvfwpDph>HPZ6c3PPF4ps?91NXn)<l-<ZW)>50z~^
zM~@tFsWzPa=fU^ne>rz{2!f6&n`>QOv}Z$$il>LScW}mBtB=ALN`p5hxq=o?Mr_Fl
z>^rXRHwUz|RY6T{*@Wqm+xcXz944uN&h1^cY}wCW<-IDN7BxQ#6xRe#-+tbh_2_dc
zBN29XcF>_8_x4oYx((VbvMN;j$IqXMUte9lb=$i9UC;ji|D?tB<3f_O1O->J_=5(T
zL2aJ+f(Hj0b>^pBSn4evXS%iF+M3A8>*Gy+{QN0;NUC(>mMur-*;e2C*}d+_5f{+0
ziTnS2;;wg`+&*QB2n!3#fwO0MV|SN@R{2dVe0$3jv{>ik<Kv*d02{9qOLlhl()5)~
z_9q?6r|ZRnMk)kFMO#68&g0_ZUfkQe`_kr+rNz(Bb@cSOfYxut#)9O}+x_MN9j@W!
z#dWM#y1k)+VTxXC)XSBt4udxCfmV-hywTqVUTGdw4qDEq2wK}`|7|g3A`rx}2DLW&
ze?dkAcwm!<yr5A=vnBsPz1G^_-$2WF3Q9{|Z*EF0-XlMM|L6DX_y0R}$-eZ}mB5OL
zg_}2QXi)KlZl&2(^0F!EXqTp~_f^ok!=v5ei|hXWDkv;G`StzRIhMs-l{0sNV$nF`
zf&yrQ2DD24?yl0!GP`Sjf)A~bv#m-vJxv!ha;c}MH$jE-c%N+Z%$YO4y)L(`{FDNU
z$^U=Nx9Xe*%~XR5h`PVOK$lN2+%x&vCu<GbX#$GPA0Hli`I>p{(P**&-Q>M7i50ZE
zd@rbc`*FVhU-RSR{fDn!4XytD>FMc@SHt5K4GjZ3SGu??5dse`f0{CHUf;jJzmw0;
zvz?GC3AxUx`Ww$Am4)f&=W+1yJ=0J947z6S#;se24jlqDU!J{r1KQ937<3NP@jlt&
zJ?AH@`(N0Y>^{f3oDXy(NDHShSLM=Opta16jg6p5yGy|#sZUQ$1>FX5ZjNPh(bH3z
z`S<tN+k<ZA311(Vx&Br3+9*>OH@CE%@=x_NH90}`_}b|0KRnrfmVA8Vx+UkP(e35W
zKx+r%Yd*F%oxbvP@ArGn`}fyR6Sw!DYt?#fZ8T`~Bw|xaXVdE|oxCgM!P|<!;|b1E
zeA1g9fcAmHdmf-_3$*aO?Qorr1z06$ra9RebUy=RwZX#;ieH0Qg=qfx{rmZ^lUt_L
zFI>0~bkQ$p#O!IAySqDRTQX>+qS4`=JEy1Xf4uB(@3{CPXm?E8)TyFX-`|1GO4zY;
zr>3p{)HiS5T-a5b{pQZj;Fp@Nr&for|M2;|{o$K8Ew4}hrMa7(Uv5F<<}?ov4~O}7
zwOiB|#_y|<++Ft8>E@=?kFVG7UzBxq6?o^NYquC^83Jg94QQ#-(;JVE_k;F-JUrZ<
z{OCw0C@F!`!Bnl#LoJ-boBq7pR{Q&#Md2gR$lJ81<&Lw>au2<@xVRF$R?}BaN$J$#
z@c3F)?@22Db1VY;`ueWjlM@zJ_Mc_qIZefLo>}g!Chp$(ot>RBA|gw^@La9__h;vu
zH*a*NYXmykReVU;_LyJZZc6s`b-J@>&O8Zfi2iBRdh+U(R==!u*h|S(m-p3H?@T`4
z7nxW6_0`mz^mO&;sHju3&GV<}$M4h8kJ%AmW^6q9c(3&G3qilkU)<chJZ4u(X65~T
zwM9WelWIOba@|?@_*l_Qqtqu~zLYF|zOt>evvW`C>1jIKj~+R4Vv@>9(48<DQ+I7t
z1g-gM1})(PEd>J40p0+O4T6N*!NY~-ps7J{!xnr@2WVtj1Jdv{3fs1A+ox5btEbFc
zSjEmKGXZo!cGlHZC%MIRCOA7gKfQ1vpz>f7Yth!Mt0}?3!InBYpbfVAR#s7Q+j3@t
z0>pcg%I({?LF??N*Z==pzI6FYua!YdpMdtJ+d5yJG-*<bwY7C6=$IgXO`&)9_v=?z
zR-T+TZQ3RkPY_zVbm^V-@%BI8-QDeVUR&tgJX>v0;JlPv6|mGxwDRMlqdVo|w`5F=
zS?V>_DaPf$nXFaGgt>F)KE1v^{`4lD)BW=H)4Zo>D3-stpm@7>x$kVX`VR-$TWu$H
zbc7u9c`5v$v*W~$OcN;{84H8kp&4)AyxCCj(CNsLBM*+t*PkicT6fCp-~aFlYJVf5
zqm`AEm}IR=9M;F}1&uY8fG#BiorelKq`}b85OmQ<znrZ|+-knl({!Cd8^_nj*@F6Q
zX=y%(|NMBpe!oG<iwip2Wv$D23JVK=yjs29px}W6gTvijrG+0Kxq_-J@9BD>NvmFg
z*5H4Cch}j;$*IrYI(mEF+5=jT%ii6w{PFuY=yX2@(8-TFvAaaxy?eK#=qVRyt;`3f
z(g~@cwpV0c_3zS7A=N1}mQ>|<fOd@~fQAe}Lr0)F0Z_}97c_Ka4{oo5x|xUTOk}`Y
z2|=qqkJeq02OrrDY59UG0{Qs(cu-0G@83Vrz8BEB{f^CS7L}h=K)sW_d!x7KNtkAd
z#KgpaPRJ~Ib0hHJ)MM*wetwd$F4F;RD!aWsUs*$gL#mgpv9a;Tuh;9r15oO#nr6?I
zJ~!8T`4^th&0Ds#=$wwUYn@gSzOyJ5v;|jEQWA6<AH#ur_vYzpUbwi}9W)O4Z_b(a
z9Xl+REMNY-%Es1Kwy?0Ub;pVf(7idG!s<V4XEv`4UViBAUC^qq_RX7(`(!MezI-VG
z^*(Rcet&<zpWpsZK;u*wmnCXzvXqogU4DGL|Kgs?&oTYx`S)aQZ_Cv_;`${&Ej6|E
z!-s;3ii!p0@9*8%S*#9fu~t-6Jovw{{CQyL)ZX9!*Yj#LD|B%1E#Tn$V)|UMkj-n3
zQu@b+!|q;_Lv(!Qi`6!6DmrA+Uc|vC<;AC<#TU_K5zg1CvMjZ$t4X7a=lS>c{pUW<
zaY(&U@SgX2_S$Qciu<x-PcQx0c6i_S$H)5xg@u{@{rxW*hbDh{anZoY=+KVB#|D{~
zRIaQJUw^=StE%TA{r!KGG8P&wUApw($&)7^Y-DEVbC{&UBVlmh!AH=RJT0wNHqTcE
zMMX)0MzwQqZ&TFQ=RdGnzGjlj$p_c}+qnNPeSC~}&!<z`Z2fybozlMWvc$vRUwn(#
zT+rcH(cAN0+Mhdhs!7EYba~Qw`~Nu~qC6*k`1kw$^zSaAiO!RPHpo9cTBl=aw&c%^
z39852rtnJ#*}ZWO5;9w|=f(up!*x^Se{XzpqyJN){i*i99$ts)rig<CCVWbEK9&68
z!9k0f9|oW%2Iyw0lP6amIB3HFx<Qoj^_9oh<Li$eYUSqDv-|J9HS4ND)t3y=UKXZl
zE5oa*tc;9|Cd{09lDn}x6Ep{TbF(^VA1TO~W5?XSsDw&c6euiOw5Y<Ny~oGL=fQ&q
z4XZ*|zp{@Pp1K`$YsSq@si2*qtJm+#`fz7w@$(HiH;uOB-;cYntE;(P$tJ#E&UQoQ
zWi`<5XwZhFIdkTGxEdZ0x`>T!y>-P01<*21P&&F0q@)zY9S7PRq7NFp`0=9xbj@$8
zUHy*_i56B?(>`l`eQ3V<NpfapXYKEA;I%$B6$YU7)JwfYK{@{It*yeg{-HU!xq+M0
zd`)t1g?teSEi5Q7_`zt%@Z;t3`3Z@Mjnj0arEKE1W`%~VjoNDSeB~wU_j{UScb6qz
zTH^WQ)>iGTD=QSMCS^T&{@niiI?JCwe=4c1oEEmaHEgx+2hfSg+&0JL|J7KUrM%oI
z|MYO(6n<DFOp}ogvdi)Kxk28$|F4F=*^(N}Xw%>a34`Jgq`EH0qq5}XCD;G2ckI}~
zbpEr`zeR?|#)tP-f1mgJ59l`Zw6w6k?kg`pJw1IPYimbG2WVjV&Ye4;+y635q;~As
z(J^m%glX0ljSGFCdHx<rW6(%zL{ya6k6nS2RF*7VI`z5FRY}7nmSerr?E3opps}ZO
z=gzgtwSe{}GQPg@6qGdPSQdkBRs&B`e0vKTV*m|7fZEH#>V76aYFt95IXOFnCIZ9O
zMuCQDL9-s<JN7{5EPj1;6*R?hP<!Q~&)>hd@87@wAY;`3XD?rN&Y3f(C=N96aRhV_
z|BF_)Ua8id#m^5NJI3~Y|9?9v(<~NG(7_ZvOTDKn85s$EeturuHuxiGo%l@Sbg`FP
zC#it?uBm%GYR}EFO#V>l;lTki<M#Ia<fC1p21Z6&AEf5>{Ym=x@#7-(6+yep-fk#-
z>;{_R3=0bbZBPTPe%gMoid#*st+MvzCDnfo!GfS$9YEHL=|-tkb!mNEXSuZe>#NX<
z!df!mNCm~7{kP<k8x@}(Z_|+li7A3|rtP=IHa9@IZ5q$-z`8fbFD2SfllvVQ_r|?)
zgCdHiDaU_(eeLSMLcqq>7SwYGUFQ7m-8;7Pvi5Z{r>E<?pPy&Tx;A*5w0WL_k`j}k
zprA$dHys&S*@v%RbN9M6hpmn3oVT2-_V>4^4_#A1o68v*y2bUyZaLU2Seya!lbmf8
zXf4^_-{0LMB4+%vw6?asv!jq1l)v;HmKR;#l<NKG*X#A5dNe0z&A<EGCr=gzRUVSY
zX$MZ8^nBy7%H-eQpV7-NKRh?rdc)SOx*tlF1O+dC_OP1krw%$eN;5nzPL7F*36yg^
zCb1|hD>Iybm$BgTOVCs$Xd3R<@s$e7%F0`^u5x{SbyfS*`<q*{!zJ~C)RmPNJM9->
z<ND7u^M1|JO-1kSSb}PGGcz;L0WzR%Yiri%fCi9qZ*McLSi3sXk#9F_Ex>ARP>7Yi
zjdIMsdhp&oxzEqeIwvG7c%iu}_|EzLf9jQ|ikqdp+#vt-V4aF;qVuVK-pHaHk07OQ
z$sobQZ7NF>>`(RojVOBK4i?;~h*0V2RrK{$=#JgHAD^3R{o=wxX3$ys3?5!ypi4y)
z^7H$XkM|wCc{B1&0IQLiS=-E+lE1#ZWbSoq&bzy7@0X;k=;+%;QSMW3?kauVRgzfm
z;NW1nCQx5rUmrBu09vpX7AE%Q?c0s@|LZEMs+bs_ot@qOe&6pt_N=Kv9v&Re&dfZ#
zKHcj<WxR6G%Mb5UPA*xtY*F6bT^-%sm;cvK>gafpT9LvjD7bgR#*Kz%IX4>k?S3#A
z8XE4X`)kFpz_FPPwD2x!ONL^_LMzbLIjLT^FFc`-J5Qu4>+AC;CMI@tb{+)Xb!zkb
z``z{N_CJ39Jb2?q#0RIRnfLZs^2ynBOqd|BWXX~Rplt<KrCE*UZy!H?oS2vh8erjw
zS|#`I-#^g#|38k^a(-B6xg;d##HD0V0^gXkLEgKKSJU1s<>W?1&(0hDOOMx0VVB;N
zvq7=D|E~r(tH^`IKP5O%llzTOucGOBxQ!Row*ar*%E{5$mUENo!Oj2j%}q@o=Kuf0
z{_Wehrf{vve#;Mo>S$5X))gyODE*a-JLC5BA!z8;cA=9+-5(1lCnr$JeY{^@yyD))
zi-P9)_e3`M{IvV=pjm1Ew<DdxsXLY=J#Kxz#AHvquArc(_<K+#5^}7kr$<0c?3np`
z&q5<3qX%!__D)v!KXmF8m!6&;!@R!+H=Eh{FD!Is2QAaOx;k8Z&lIg)EiEjd@&j}O
z=8cWX51%{<dBNYeCG)b|0jpI!YQD2V)?D|V)RKC7+SH3uO5c<<#eYwn(!%SxXrrR1
z=Z*d)DLEcNT;G&CkJYIx1y$-B<vl%bO!!p!=?Uky+}mx&>E{%bm6?D3{K<CSds0jO
zzMpOvtX92vc7A^RoBPJ)@9r2y1Qlj%y(Mm^?<oY@<on`92dK>TnyU45OOKXvc6K%k
zJ3FZTmzkLf+AMoe_5yUroOSs-j<{7eZf<TztM;mR+ALVy5fl`(0kj8X$&v@4d(`xP
zOjY4DG&F3wrWszy?+Q8#<-ebpFgUPO4}yy56&|3<`0noV$Nl#I7(ToSxf-{(YGLK)
zXG!fV8Sd{<UpmVmktu9_TyN^>X%FX?-@919*<M|p{q?oAhnILx{_t-1d(aN^4?(M5
z{QExpX6xJ^D=)wN!JDHM?B?b+L1pEM<<+0wCtuvC=-u|$!|NzG4^PU-IkD+rosQ%;
zWlc%xNmH8sdMw%~f0_+kt1bzFG=OZ@#qMSU-Bb7Rxcr8V8y(%;*m81nL8tcZ*<*9#
z=FNkbE(vLBYA#wX6e#%j^H<)04|=Qq|K6bjzWwUVOylm-z{J!^bLaNHy}f<^hlW1T
z%xKhdzWhBO*@}va1mxx8A25A6-Y>tn^7Av$Wc;E<i(LFe=S(v3No@Z(VWDpHwgdO?
z%TH1{c=RYMsJi`9dc03o`+4fA<IaMo;<B=|UR_z4TmV{Baq;vA(CrXa3*WrS0UdCD
zzxKOqiPhYH-Mjz%sqvV^VsCE`x{xe%b(rX$kexrC*=mOFt@>(E@!`SqdydJMmUx0L
zw)^+*_xqwax2b23^-6bt*%i3hZR$s%uMcC3pCsnx@p(?Vus+^C!$j)K+uPIC3#JQ6
zZz{Rb4-G0%9({VS4b(IQ2||)%^2v>$A`>L|<;Dc4$|W|S!!wxK`4r5|#Psy^Hf-O1
z{NLZ-7ePlF#qX2R4qI~o#NAPtd@)!w^~?;z2`Ze~*VZ&{+-P{LM>2TH{q&?HCTnZ!
zipt7^r%$i$310=8!!S%b!m%aiX3&=@T#w(}+zcAC&B@6TkdWwb>y=_;0PQ&`dg_&u
zmX`GL(o)bti(R7HA1?dbCxR|HGS8dy;OVKNzrRW=Dl0)XKj{4I!|nWuxw*YPJv=W;
ztRUk<OxM@Pi`#}??31(Q^7r=#9Vi6a^t&PPuz-{l7ijB4)E17DCr^ULI$mE}>*~MM
zYf<6jW1thAe0+FbU0bVN)wk+HK+C4-lP5Pfv-2-<Zs$91E7RD~@#203qm`iG-V0Ao
zP6jn<SlHN-9v$f{C@pPO@dRzN2ML09;Y?QZJ#=ZQx2u2Xn(XWAK$kph*swvswiSF#
zzL<Vo&w&F6oaV>xEK;@m@qih$MP$x&!N9<e>nuNk&JYa=5!n)@%O_{Up{=bA>eov3
zvdPKGEqcBZ5u1y;8hJJOL9PG(rHAWORFj>BR?7bllzZb|xl!J`pVt$VgH~0%dGiL;
z9t7>l0^Pp)=FJ-caq;E*EvnAUF!b>Cb@lP-d9d`<qc?AOl$DiLR8<#xP1PzWE4y|-
z@|WwUPoF?j_v-%h5*{9Eoncp7Ww|DFTm8Oeg~i3q`}f<o@yqk2r>9@s9HOhBzyR6+
z`|a)R@CTN2{n+#K^RKLrmj@k4Raa+cRsOCAbQr<)_<GR|VLNMT!S~&QHnDn6R{O<l
zb?5HgjU_LG)<kY*`~CfW`|8!JU##rfo_<~qG>v_IT`V)h-|vQV=FHhp_BQIvo14KO
zoL2dqIeYfw)9LYc-?OC_eVR0NYHJ&>G<buQQEJx<OVHkfJ)k=r;!d19$5;FNTkX4*
z`;^^!9CC7WKv#pDJAFl4U!TAF`#V=JFRpj@_s2hAFH`XZt?6Z5yZF?TtKspjix(?{
z?pl5Ed2iL%L!e_SxW)CRd^S?j(z<8rUbk}PO3+ypTcUJ9yIHJCUnShwka!`(B;)$J
zxi2bLfiu}eP<a(%xIq!rRJ8rJc+ZXgB`P@{N?((~?U1TB?msswdTQS2cM<JxZDn<G
zb_N|heCJNgj9IflEna4JJ{AVhvN+IIVmG(82TMiW^YZjSSEPexbm|S$QosFvzhBwL
zMh3JMIw(j;#j|PmZtFjP|AH1?U0D+u{Ke(!#;seAHnDQYRV18wb93{=Y17ykKnt)z
z3z2Q={_L<x*P1tXuI#<q@3EjuY%VZcf#z+uY%u|C==l&-dgA=~;~yU%{|K_k-d=v)
zx^<w9U7%%{{=rL*^-7DsOql#%)l+EFq)DeT0*`{0M1!*2=VxbyZCg3Mefu`UJYSCA
zML}s%P-394;6?7IPo9998Ru*F1uyse!xnBh$EuVIG_4$8|M%-1Yu68FtF`nS8yi7G
zouI*4(49@5lhqg+mMl@xiQgwvSXc-;rSZYk5W!waW41{uiDze-8km_Kn_-w7_p4gP
z^N{)dnqa=ySDt=*d;8b!XFQTdE#+q?Ha0giH#Id0h={akhpz*zQ;b?G2D)wpbZAlL
z<z=1oR&as)XP}x|MF`Sc+X!yD%YReW<dvS}0`6Obnlzx!-O)A`)kOPA9yupAfmRs)
z`FcH`fk9YU7<8F$XJ_Xx?hE>HdpL}ZjVB6g%Loe#^T^xH5ugA6zm#cK%g*BGpwkaQ
zo39QXKK$|T_xqp|&q2#EzI|((KVQD4rY0dTPp@j7)|01C6)i1)?mQ0~kKMU*=db>=
zXU_b1zenKzota_`Yu2n$@D!4>saQ}C3QW*G5!bW9vdYTJJ9h6reD`kb7m?74w_C4s
z#Wd7?dlMP6r$W$omWku#Wxk9yuRolguD>{Pb6UpLRZ}}wuKN7*`F!Wa7ayE8zwdH;
zTdwQ*Kwi1705di|nT{1JG{7D2rH4SxfETTM_U;8;SPi;p`NH$>Z*Dfvv#kd8zqxpL
zjyyiz4?d#n?JZF=GqXkNfvRE>5*?r=%a{G_kKWr`%{y;(&{D2vXJ&rBQ~%p#Y2k+l
zjuMiRiuU&M$BrGdsQB=}dw*rboqWA8v9Pc(&|sHauT*Nm^*Q<bezujLo#+T3lHi={
zcien-cO$PRD1JD9PjpFgKGn_}xed~>=Kno$N*k}|q79&axK8w&<C7BYPj&NpdL61$
znRsJDDrj`iy6nw?J3EURZFVny4@w5VzrR<ux0eT1%Wi!#niZ)>FK<rw{}!NlYfC2R
zu+#_L`uiMeYHYSd=`LEdNI+JW*W26s%lrHCb#-+gzI_w34ZR53<OjL}7_?h|hG8=3
z%nk<7<p>|on%_?VRbxge9sj-_@0SM^b1QasJ$>?|McO=%q2ih)=!Bo7BqcT;35EwZ
zTleoN`2Vy|&bF)e_cu^&2U-9;b*d<+Tb!StAJ_AbDKRmTP5%9zox-4T`kb7c#{cZc
zjvaGad=XS!KeY_p8n!NmGdenY&$nCI8FzP?zPi4iKRG$M`MSp>(3)wEs1-goA`5ds
z%eo&Q>jh119_y3kPEUXCwEzE&MXub8uRA(CbXD$t?pvp-w8-n_y}i|J^7nTZvpcu*
zwXR;R4Z8aVw19*GbfqH5&*AIij!x5!{t|!VV)x9MGeMiFf|vOS+O~SUe|LBHjs5le
z|2=uk#w+#U>-G5dxpU_}NOcJb`d@v0&XXr8_e_^d=*92jSsT{f(ZQjju73FJSzf7L
zHmP1VJw3fe&o#xQH@(>a?n$_a3QKQ#a$~~L<8?aLZ`^~l%v1u89<I}|{FeN2qx@+x
z=}A*M{(6KI#_X??RrjCgvcK+cLRMB6s2)4i!U;NErl+^};`(@dP-y~c+1rMG1Z{|}
z_?QG*%pxf%sqyCc{?DI2vFHSEpEF11$gyKdS67AJ*j=vQ)6>KA?w&8}(xpp5LsS-}
zuS7s2OzY!p8NerRJ~=78CHJ=2#*G_6M>9@V_ZN_m;Lz9C|MBxDXWTj+(CXWhlhq4f
zUD0GX09xdcaZ!ndg+;;MUjFs<_3iuj+k+0>Ip{rA)6^7vk-^8~^4x#_FI4gT@Zp1l
ziwjHE)m5qq3wMFG@Y&hf{rK^?pS!m1*_oLgeSOFD_x}kxclyfmvbVQft&Y5SzyH79
za@SW|il6&|j>L}MmQ(p|AqQys1$3-Q#zHFzNy(S>u{Z8}&-G*XoOEM?i^~_MJ<L{u
zf|46HZ`S_6+UB?XFlfLo`FI~wKQrju!XLiZm5NGAbiT}vby2!`^X9?p*TcW?EPB4H
z;-gaCzn|$DCQ=uJLz>IaYR<zkcyV}gP<ID!WZ8}WB`$B=gP6@yK5kU(Zs(1(dUJf!
z;X0M2NzRilZItis{~KZR20VtMYo?+p_<Q1&2Hr@MudlDW|NZs#tNiSlGeMJ35!>_T
z9teH4Irp|1kF1plXyfSm_4;9JqgZ?0nCJSngN~ype0=Q1{r&r2%v|;P%gbOFcX#L2
zSC#DS<QN`2c%V==g$s1jLT6_usA2u>-QCsp2Fs$i=YfubcyO@!tN5OoGiQEedi8vU
zU9A=9O5itda%Rk$mGtb)OwcTYfS4Fta&j`rZtrP2g0{gEi;9acZqJXOV_Pkz?ACLj
zLs0p{tJUidUAiO$I-v`+6hHH_T1#u|!ub7l9v&VV1?*WyB|kqs6_@)KvN}vRW?#)t
z8S$0Z*G6x5@n0d3c79%Or?9%%jvq1%Ro~zB9ys7|W|nEU_=5dMW|?NkRVgqD3SK<@
zf$xQjOG?7MJ(a4zoRZ(&*_paw*`vtaWxAl%?Q?7@C#ip*Bp}txCamV;u-tDhgUxTn
zIk3ABuC5AYU9YSa108}07K?8xKdWh(oSY20e87Lc-GvO37uVL__O3p0?b^0E*H$t^
za-qpL<&~n+n=-&-(K@o<l5Zy3PZHXo=-GRt-xZP-Uv2<rMVDmzNl_aWSK4gNzRnlA
zDg<;=J9sYl_U+{V|NerGsRNz0(I;!2ba9cZgk{l^7c0A#Uw&Ee-~eOB)+o>doD(Nb
zG)$c;3Mv=t>+373s-*7dPU)DUuA{>P+CjAaeqHy)#qRdsOJ84K54!x~(4j*W31__b
z{Cc%|MbJ{NJ~>-1(Bi1)p!>5yWA*Cl?BaSc0$V0%Nf#FvgO)dNaB*pU`MK14deX5T
z$%;Qe3N7`Om6TT1RIryQDH$2$-?O<WthMFL8J~!#s6~N`-9CK%+B$i1aN}fARnJ4e
z-|yGYPz)^rHNp1R{r!@E@BZ#`eqL!amzWqC8(Uk}^~#GLJ&G-Uvheat&=P1DS64+X
ztyLcT+wDD)Aeli$>i5JIj}o0vHN$g)YJ#&+s19iKP~N-!Z^X766Tpg+IQjV6R6IfV
zV1dRjWMuway07dhly-hzEZ^%ZuOA)l{_$k8e?m?UkMQJl`(JY>PiAH)C@XVINKml*
z{l+-1;UAN_-<*c9)knYIukXKdC1l2o83%6Pmj3teA87IE%$YM^bcUR?t@^_8?AbFL
zhJ_s4^6qx^$y)FG@Ti#K$NvAn?Ln>di4!O8Vfd^1?EL(G&?@Gs;c*B5|GoczVc=pn
zhK46kQgUu=U^LIWb6}coG|T#s`OE$1KRVdVe&YOj{SR~Y?%mtq`s(4US6!eR+~=0x
z)BF<9!Ygg|!NEsKX;BfliP3TD;+2)bU-!ptOmbbg{^9KJA@@qG=Dy%`332-R`ug?z
zrs>z#M6#8i-C6!VZsGp+^0S&9<p&j2lkF!7ZIti4(hKStsc4G+o;an8*K-MY3|8Lr
z<c$fSLPzQAEc1Lh$e9p<TeGez$*LUYz7T)z&><$!E-28Ru>)7Gh?wW!yJG+T!2{5J
z7G1NJXMis4ba7z`3JO|q`Q?R`!Rnx;poiOdA79sVy|SY)Swd10bP<Aqp`qjBW4&MF
z#qIi4JVASimbbnt{q`mjr2ON@kD%kzzP-K8?(gpp+U5KBSg$kaywcLwYE{b~{rU6x
zyo7O@&&0UfyUX)Iv-_!gJpO_%e*?`x{QB~em9M|@>(%g$Sy#2byu9pw!Rl+|{yJMw
zhw^^i@3%YSZ-01jQ2g;ij!!4gojdmJ?d`&6XCzZnQba5S94D!Oc9vbRQc?<H1~=wh
zi@v<LC|>vQpgCh#+x-{nN=lZX{^tY!`f1=%ZTZd)kGvd@$_<L3;g&Bq`dwU9%t3?P
z{i)4=HTca`1O-pNygz?3_wL8)qVb@`R39I?{yh%b83{TGvA(|k$+KrptFJDq`}>PY
zT<dxhD>rES>w^agpuxwRHzU8OT&;Y&^}2%Rq<@P(*V`?-<muzn(%#MvI)Hkib9>U`
zW4*sXi?~4B8*Bc4y}pNGuR!_xd!URrG4Az?7oej*r+r-11*(WaTjN0cM`CuD@q(vp
zEv&4#;+E-w7FFG=`<)BgUIV&Xub{vHG(V>mx=KMuhv)07tA}?KK6W`DVk6h3(Es}S
z`opJBbBC{sX`DJ$RL-u3BRe}gB_+jS`Q?Mxu5CLY`>eC0<6p1%0#GmJ?(TB_+TY)f
zb_%O6xcn0236pL0b!W}rcdv77W?Q5#AQ;GcNIq)H@hdBXk%m2*!L3z6!IR)Lx?~S{
z#!g6Z;+-4)pAzg(b%UmcR0IVle&UrdU^qQp|G0R34P$U{FzEWn{Jmera&mG&Eq>do
zBi4WHj=#LT{Nk?C?2E=Bx;i><TIGXJo|$3D3~J&hB`JZ5J6>rs37hv%pQaWBTKx?V
z3lsD4_3i!=6&xH4>iYGFhwAk8_3e4FM`W5#B$K|r{*j|cAHKW0n}d%Je9yznmz|&!
z1m51->ReW~?ZwPh2b=}H@^5X)1RWj%n(kHeops>eJ-O)Zd9Ay5TTj!A?J~{220BV$
zQM!=e#6usMN|cnU7J@FG-2d;F_LeB!xazm2J9g|ycz<ti#*Gb%({v)6l8^T(nwf=t
z@c|v9EyyQtm-B(O@cX;Ffor2o51w9O1Z`w7Krhn;-3wJ!Rkd)vyhTAm<+;UPNgp2_
zb*%#(9(B5)bJxdq`=_A8WIzXR=jG*n`2PL)hlhtNUsY;?W^6!B|NbQ+;A9OM2n(!x
z<1W<8>*;l%ZVLNv==jNLHt9(&N%oV1HYlEU4+|4B%fHw2=1tC*mzUey7m6GNMQQ1)
zkiW<O{`%@%Q)9De(V~Q$oSuEPzYiTg?EJv#Y1PG}&q3!KrlhFk-P^-yZf@QqXDfAe
zb-4cV(vX>REee^q#r0Zt?zG&rX%m-C{Q5ZCJG)A~4;YnJ{Q8o)us-kqG49&#ckB26
zJG6X$T^Hz<=5uqcK@C^XL65u3-zPmh)CxNDBWi1wYSpqwfB*e{54x+6ks)+d2;+x0
z@3k2~%^J}9!Hf(IHQ!k(Ig4+72xysfdw;z>sMTKb>I&!gcXyc?UX)nPm_0lBSdS!V
zssl8vm3>|Bpm%47$4QmD_U;VAf`X!p{N`Fo*wt8oikU52Oh8*s3kwTBeEP)n;f=3t
zaB#4Tiwj5GDml>VB-3m$IlG#U|9?$#Qd3(eOc3yyVc__{YSoLLo}R9+Ri2Y3OrIX^
zmc7F0@qO3I59=&Hfkw>)<>dO#&Nc@fZ8=Hh;N82j|Ni}xFiPRby0%8MYSF6=icgQ$
zsZ9J~IeSV=y*wz^*rkI&W%@>WPm{WHYD*v7cdZ1^`b-i39axv+A=Ej4v!~~e?}2ro
zt!s6EEY8ih=YMdMHRA29t(WU_a&vo|+4(>5T@6VKTNBav^z?LPMMcK4va(;t%irE=
zRdjB9q0hwv+Ka2ArY5zgkL&w~ht8k^2((cfv<PmhcKD*&-`_yvX`q`4*2mlL0L`_o
z%(!;#8Yt%k1Wfq%de-0H-$7kW1_2qFo(mTOKzICn2zqL0WYnbM=~}hcZ~5crua$O`
zyc7b(>6|$-plL96emT%~;eYRwUte2$aa(Tmn&|C*AA+717ZiZH3kHRcTo@d-W?cnM
zqVM_p?KVS0=<2Y<Q&TiutsE9^dc2ThX?kK}<An<WpiYIlI(u4L8mM6lYB@20mhjpA
z`QV(AlEM+^<>KOX%o<#fEnU7GGz!4L;O*_raDHFqkN$bK)sGhU+X-#*?KR82)v{oL
z!j9d$L8H$VPp5`6Fzo;PO&T;*B_aY^O4%b}==33I)e1gYE0roHL52sfuC89B9>TFF
zyU&KSp^goTPY>6rT)Y7uBdgq?2#RU(-+`c24oqe$nyiq_30?;=MO=Cks9`y2gW^-r
zf}<b5f4{cBmbKNQ{-4dE!-qlV;e&=vKR-VY+IPabZb?_p^K)|xN=r?5tgtaR7ti1S
z*Q}?vcVpe(sx8^q`3wyWK@BP=CnwO^;Eml=-@o7gA9S+d$K&$#2aX<P-T(iewUMzg
zBg3|B+dz9!y}Y=l>BVYQtlU)k=7!+yZMn_?0RfHAH*MMkno%ivea-iP(bL&>wYy$$
zik{n&c^S0#;>Zyf32EuW_wL<$@N-}7ZzUt6pbJ)|nb+1xg4X5y-{IWO2Z|!l8K8gu
z)PSY|dZkQ-b_B@&tJOHP)O-2_P*V=nt6b>Z{^7wvX1T5pLVkXJI|?7OF)Z+!s<k3|
zyPlA+@K^B#>Z+;-&z$jj0zTdM9_U=QxD!{eih`~bJ~PvpkpXlG8tCBGGc%bPX4qDn
zf%b83*<v!$ICOF7>M+nL;*HGg2{}1AA7bL-<o4{@GhyDmzWMe4A}=^8DFq4NGhP1X
zMTyms<Htc=DJ?Co@9*!oFI}qo>-&4qd7u^5)!p+}WPpd#z)gq~n+~_>Sbkev18qWp
z`U=xzeh0?ocql1pd5ejOMQluBJ=P=1%m6xe;@`jD`Jjt04{T=cxBLI6_|Bfn;3qz=
zpFV!ny!Kkv^H86x^{I^BDoZP?M{~>X9lW!%_-p^sqensO(?NSe#dIPT)ZaOOo`1RD
zT&JL*NgXR!J$(MWeQ)*mM;8`4gH8!}^Y$(8yF0eIw@g5*&knV6H%-^Ny)pUtg~jgt
z71h<wi!XvMmw9<<>590$Rv;I|?5z^z<mBA5TYoBdc6RoeS*F~e^Kma-x)iWFOt-oI
zdiM2oM}NQHpI`7pS~TzNt*xM=_=SXpLHnT&xAQMfKR@rp*|V$+64KJjMn*#Ud%sS5
zu=Lck$B&zfpP!SI>H4t0UOoNntkx4JJnGKXb$)z&9CVsHsM>2tug?RWso~(j@agks
zP;v#`n0z~bzv!MR9UW87czj_{QVQCZcXyYfo}S<Tj~fyXZ^*c))Y8)O0CY*prKR2v
zA3jtpSh!0?RW<R%1Vz?+JJ{#d27{P?l4f*tbiJ9s``MpwxAQ@kffiO|UtgzaU?5QX
z`dVv$KR@U|kmLRG-SbviO;R~{_%JibqidtLZ>arUR`TwSWMX3Ci`(1Rzo_g2ElB!3
zv7_V3u{Is+oD-9h!K;v5T#AzIr^$XxKDkl;>CrY7rA3=U)<&5wS-zaPqU`$1A3rLZ
zo6FXKkHS~XnzzW+-5t~=1ZCoLbFIUd{9mzP%N7$0OG`<cvIhqkJ>KtAiG{5Nn6za7
z@8|ZQiG|nK*H3?L6MAcNI)77B(}g{i#U7JF9#o2pi~srgd_L2(mEF5{TQ6F?7_{&&
z!$gYVz>|}cL1*sS)cujTc=6(%AA4Hz?(bW>|Hkw#HGO^ltE)n*-+eBBf6o<k0#D(@
zs=c4jS%Vf}`1txVGThx=ejIc*S1Y&pBhUd2GmX<LK2{2Xj;d~KY%C}!(D+j9+swxM
zrTp8n=d<l<t-vL2dO9;h+POKLy>87LHW+}8S_PfQHc8c+Wxa}$(o$nV+lG#gDQ}zk
z?HpoaWHxQy3`#kbpPzv`6rc>+ke>gpy{(NaZl&C{YuA1}?zf-!`wyts{OaoJ>Gu^@
zeF1GW=#@5CQdMOIWk$c{#uf9HD+fo;G|3Fw7^m+kG)*@;%q?51%`ErU0^iwYpi`-M
z-pvx0l|8%r*_1<<m-`FK%JQxa>;Cbhf}x?gx%oz*)`7Mu;33q%9!j8=Q=5)-&WT5m
zc=bBcrV@Cg|5LL4G~REZF*i`;E=>dthI{<nnt7Qm`}(@p_ICENcXvR?2krU!Z1%6`
z>tl8v`c~Oj_4U=mW4+QFHg9frTim#Qy?)m9b-Gp4UV-jqy0$i&t^e<r%l;cSY;ZU|
zO_x`0ebiR1RbgwR=6w!%3A&7N`}X>GpZ7QyUEKTen6!tV-?5jMmrtBCr{~X~8qfg;
z&h2~#MvrRQyp>E%MM1-<F)?%g`JMbyv^IMCv3a)D0umAt4|eX^W0P}lkL3Ej-)1$W
zih}OExO3-@%lQCNxh@6%^z?KKYwOqcX6EL{+jylx<$2=ljt-AnmAm`*JA1phgs{AP
z`O?75tZnMlsV_8F2?+=^eE3iR>hbQ|w~y_7?#)fCi{1M{qxjd>MyqEihN^*XburBn
zDJm{bOipIb&VJ3bexeGerluy-wLsVOloS@vNnC#pocQc9sb$ZeJw|b%AD=vV0-ASS
z9k%w+y}i|mDJe&U>$)A5Uw(L?k@-T_R?tce&_%AG*+B^d22kJq%a<q8wW>$jbnLz<
zYl6nYlbxsWo28tD^xl5l=wD(2Y8d^Eu)EQ(dbmzU8Z;j6JZaJfc~29wC4c<pTCwKm
z=Py~l+<E!s#19V+f=+Dwdfq(umdM-N+d->{4op2&`r|`l#@48uySqgB<!l^4S6DxP
z-hQx|eRE}3255<4`8yeqLE75dF*^zvK|R6f{JpJfqqj@#DSLHgWk+xC(N=D8mbIbn
zWp8gi1dSS$->+?lwkdyqe}6sx&F!_(<_w^#Yc-10LW5SWT)856dEdeNo>e<%%#ir;
z<A;KQfxy0f`(E7Is%@5kkEgo2x}~K>!Ol*uu(0sO#l`I}R<8Q~xZnN}XtLqm-QBMK
zfm=YAnYi^z-Pl>2-gw@$va%9%0@SN3E1PYrzje%8rPVKI+q841<^J~`E-pu5!w++<
z%P;J$E(gtsmc6|NU(vQb?=EO1EojTNwYBv@@0CWN!4=RNx6;>PCYhI9zR0XfIdk@`
zqNmWWudmsA-9SeMe{%7f`S*QnaZ*y!gt>Ejtx8{kZhT#|T=N>J^LRB2JpW^ADypWY
z_Tk&Nw*C9<LGwSL6Rwm(oj^+*Kr2StbgDu5&w0|N4f39uHzueE{oeQnJW}cb%8sC^
zsEnKwn+l(w1DyqQ;Mg&?ySvM;+s~Ufudi3yd{OoHcc6Km1Ffe(v)XremxJnVD=Vp=
zKYxPy&L&d4_i8@-&X_f;Yu<{8=jY}+gRb#QPHs*+JL}<>mzPhRIt982?83I(=;rIY
zcI^TkD3pDDo#>V@S+l%59frxr5<sJOCK&=TF)<tJ|JQ-~c>n(V1YH-Yq^xXM@WA0>
zaOlHNPfvSzdLI1y`#ZNSgX`jp91%<7_ApnS%)POJak9F<TUwf0iIuF1Clf<NR8-Q@
zE>Q`?q?QM*r^^5Rsf^iK1X^7I8o~tKom-#x{M=m786p#B%;50$_O_|`;P4>m>EneQ
zpDe4t>41h#fBdKbZB_)Gk+OWbI%v^i;p1b98X6w;6+D81fr;SBe90SIGJ`wo?w^>b
zoEjHYXj}P-Wp(&^x11au(5e!Kj0+1GL6eXhlaGI5_g--a<gSa0Tse4nL~L8N7M?ld
z<KpV-xccg&2M3!$>k$?>HZQoC@!;V@#j1H(AJ<u`8mFI=adB}0ot$Vjmv63BDd_s$
zHePAA=;-K+pF<i!^Hu#zM8KWUNHfsXRU3FbHOYR`qz#ImD&LZCCfHBo`Mt5^Mt>@3
zTK^!ZjXYrq8)%PNNQemN!WbF*IvLRQY;SIEc0C`orKN=hlqpnISwUxUTv-|X@z?A1
z(tFhG?Bs;i{f<nJuj`y=Tg?@<N)FUOJ}zI+1MZiBj<0<3^r_<{l{540<&D$NiP#2y
z1RcviQQ2KdQE}k~?(>W<{@1L0QNjM@(#bPtj?A;I{(v+qe0R6`nzd_P{ewXRr93hg
z0_^;9SM0;q$Jv5bv_E_H40OOYXb?SWYgXc;Bb}ftbbF;tS@go#<+=i@Iy*Z-lN_L<
z3LZXe?3Ff`lDTkkZM3<Cm6g-#t6Y#S3uylFghQgez^C)#IsgAn`FQ>@!w+9QCDBix
zK7sBd`S^1A{H}RUQ)9BSw9NAFfo78?tNVj{ux2?DCQ`h&wq~nW&C~j@&T?sTN(zg)
zxjASw>il{BbLY-2QeVj@J!wTz0yyZs`*|a+a!y=Iv=<7M1Fzdkez_4m7Hjp!ebK3A
z&?4)$DgJSBa!Sg|pp%V3EBy{0JP5j%+sMcWG=2?gBk}R^ElOYIR90rTXz}8OSF<)&
zf6oJr6~11-{~2q9ii?*Q*S6f-X$1>kEpTiG9cpv&a>&D8^Lq|XPE2At5e@5NciVkW
z3JDLtUKF=1&(hKobReu%$%_NrHQkDeij2Oq&0NpUGUcxQcW-Yss5@y@`YPny=_{aK
zVZ^2s&U;m_bxYpf5(Ul8?J9kJVNIm*l4Z-77(izuU0m#b_{x=#4^gEL7ji6p{P1C8
z_4jv*hK7QmB608Dy$2a(K`G=|uk^%8lawkn1qC%F^&Qlel$ig|N&D9iTI(-m%60A9
zHP8_S;02Q)2RJ!9gAQc?l{&87VoJ}10yROqvi4Sg2OaclSn(m@VsQrp1L!2_iVBM@
zQM#aG1Wu~YPq?)ub5Xjc*!x+^{hQOzF9J0}?aE(XQgv~2d-Uw=Y|t*^7Z(=??ydS-
z6t|)#$79i{M$kgBHXS*$B{nxEfR@3mvH=hB9)FZ*f2#R!1U#mWw(0Er@}&f{)D|@S
zy>zLnoNd*T{jZba;^d@EG8!f-yMxA57A@BbtE;nn^ym@j9J#l*w<~LFbFbh3&&ouK
zmyJiFA?xa@&Uq`MK(SEvMj~ok&Pnc@EAB)_L?rzB@^XfC`MMXHtEQr_MOl@WlhgBl
z-)}yt-enh_Z_l~O)a!P*`QE(4M~||Cj`T@MS@Lh=*6iy^cXkwljum_K=+Te8^O7Dd
z<oE<SQb|lNrenbZ1<+B=VQZt<#22iO-p&U)AR#Pl+JmJoE=y9>7J*LX*kqD%;lP8(
zm7kx1)*Ic}o<IL!=Et+M&5wi9)#h}6(16(M>+AL3uUz%u;X_7cWo6L9Mm06HU-~!V
zTqdc=SQIRfxfYmueNSa^OH0dv>(|Avt_p2lyjZ!Xx0g3g*;A<Q=TmV<?v+Mf{{HT6
zZfr)z#-Mx5LF*JIEz*tHzyR8E&d2vGw%F_8i;Igvd)0-6gc8!zm)F-^Ul$7+(V1sg
zyQ)6t=clJ0K0YQDvKtkj9sw;~vY!+Lo(0t8hpgWPO#~)8gU0f^+y83te*>@I1+BM8
z2CMXbXaD~vzh2CahP~C_LCIvp_U+g0({plq4mPtVe}8uuG*ZmT$q8B&-_zp~6(wa=
z_NJqiTRiE-g@rk;GeMVW$jQn5au$5?6SRdA)IcbHe(uGcoyPBVbeW^0qvhU&d5MXM
z{n?{4dHUVUM%LE59j0Hdzq_N5`Tx)J^*nN~Z*Ep+Nci;R<endUSay}Y{dLG$@X@13
z6&g;0GiL1hG3ns`|NmyUO9~2J^o9<Bg3^+T%8>`Xzw0F=B@-VUXq;i1J*^@2)q=|}
zC(NI}{=bF2{r(H~r|bXAE&8;f=&2WInQ2;DT0v>)Q_p=WXP%y(zVK?6pr9b=8k!wD
zcP9S%@$o{2NkL(upsoK!zxj4&cRxFk03GD0m~2PHAO~o9^c(jeBT$18JfHq4!TD4-
zWO=j|c)(>NXhR8jR64>c#{;S|NbdIb{NqPDg+CsX&R5XYU3=iO?<|vpZM@Q_>Su6)
z_G&$Q_Uy&w<@{~@^6Tt*Uj6#|dPm*gs)hTP`_49dx?@99!gG<cUteGUcr$&z<0KW2
zNuWX)yw5?NUt4=0sEW3+k!fsf+_Pc32z2!c3maS4yhT>^f4@#Y_<Zt{Cn+i_Dk2rJ
zRaI8k*2Q-J`uZBw13Y>1WFu&QPV)bnHxC{tBu#qtF@U8KbXOeq0UFR)26!e!f63*S
z1urixeQsC(@sVqt@Hf^+j~~bXFr4VYEw1OX+;6Uctn69ycPsCJ5`dtfU`I#Cft#Dt
zAHH}2y6P~)L~2XcRj)5LS0BU{KLPbJ_k2EQ&DJk#Rl-sJ?#@BbdE<eL-542WnP#`e
z*ZpMOUH<+VfBildP?+~GNdedVpp|@}?E^{n(`0^6oYKeZsRUV+$qw2=aQsrD^Q1|j
z;ZCz9e~gTbE^J6V{M>H-<jKu<?%XMgS)vCzFl1ZqZ2?iyuZOO`EV1&KbYyqKv;(L4
z9xY4<T^+gq-!E>^c2>|W*%Kx-<nQ~*23oAC;t3iwvMPVKX1~JT)YH@cY_9DLkFOQI
zy*=N3wpp%#fB=KK`f?}zWnVsi6x`rv>((RDSorwZ!PBR?K{wlM-dwz}+$I0wqSl7e
zQ{O=ATmJp|`KwvAskvEDMkeM#snuLQH#fJ4tyxnWroQ_4<z;Y6YU)e-x-TyT8`8zS
z{=a|xf5V0i8ryTT4mt}yG0(qe^X0`wW;;8(U%OAvx38B29X9%Wetlo`_PoSzZ*De)
z3kgoV1kF#N?ZQ`Ag%*^R9ozkW-|GKO=Gxlap#IXUtE(SAf39AkDmc}}&5iBPpFcm2
z*>ZwbXhCPRXP9P-?J9k}to|`*K}+jDx#;NIpXRLK0u5MRx^(HmlP4)3K&NLacnY!c
zNF;oycz$kf{I6$r8x=dXw7@O#DeTfgaycHA8|6E-^vqN`k08w)bZY5A)XZPKTKn7_
z%g=Y7e}8+s{r~s>|Kct6g8IL{zTQ1AK=Z?cMT>qv58#WBk7qb=xSfCEgb59c-TNQC
zxVRW}jY~?33d4e`udjC0|KE3FXP0@#1%<!s)&1w?e3+x+X%n%iV^`T*t_L?AQ(9%$
z9koCHT-v6>;Le>p3ogH0a53Y<z3TT1y{GH3fqI!&SA{yizP2`SdtR)g_f<s&1qMb&
zMpn7^*Vo549#`>v#Aws{U?In+;_`CPsjJ8O<=5|L_&fi+<+*d`I{NyaIYzs<d<lZA
zq|CUvDRoEHSFL4!bGsys(-!#6wPI+PZJw{BuFgK!x*Sxwv#t*T&7wX2_4PH|{Utx2
zPLKcabb7p!wYBu&c7D)JPON%MPA#ea{?4NO-JBPaA)YTwtU%*1fq{Xp{~WFM2?hwf
zpQX&t&dz>kSLx{o8|T;k0^N3%adXqsgO5X3hq+!|6?(dOp4LY2P%)&>1Dc^k8Y-4T
zixAMz1XSVAy??*m2Cd|%`tpKNUtgc$yxy);=gzqm6c~U`jWNx>#u2yD=l>S7sdGWc
z(!IL6dPVH+Z7(!erDSG;TFi^m&(8y0t^_*58noQ$c%SUyW_Es;^TB&|?69~ftOdGP
z;01s8!bhM{-C3sDY!7bU-DPWI^Wf1VrHZLmzVq#3zqD{Qwku8PHNRKEeDdT;&^GEx
zlP6D{Kc7E5JREdLvYVURBG3hVT#%LGirLxOpwT7kvNxc$tKdEf=t5u6?h|==`FSCc
zJd@RY4;^mj2W>53aLCHivazxG0J^k1GBWY?wY42RJx2~SGPCM0Jq5bH3)I;I?cZx?
z08J4Ee^FWG^6cDP?JB3%1G}G{SRA{%40OJTn%^AI(qm9B9(3G$bpBpeVd2C2v-M+l
zvADatJ9=M*%ws}F8csEXCfuQunUgMU0Cigy+uT5!(S#|~*U;b)*NZvu;o)J>SO~*~
z3=`139eH_r$9kp1U)*(id9<jgsNl^FL(meZYuBzVdcNY)+1ciWzrW>zmYOYFwrtV!
z73Y3_eqQ+Ggy7%1=hw&X2A$^!I@2zAnUCZ1b8}t&L-y43Jza3A^7q^Aplwz^cJ3$v
zT_ST)Sc^rjE1*op(`k3vThRHr7lS)GJX%%e`Yjg*ox5{I-P&5(y8N9>MTG?@L8$xB
z>zKEM3p9=dn$p>_`@H>snc`<>4*vZ7{Njd0XHaVr)C+TRYI?9VL^2{WQqkT%{{Q>y
zXU^~(J9Z45|0E?Pm7WO(3WAPSd~;(X=wgd6{iW~jNP^}=-`(Gz|Dm}Xv_WEuX7G>v
zT>_-^yzkxst$+h9LKO<-0nccjX8*krI@AMRW84fK?g6h<6$*_3RRP!5M)SVgWl{1X
z05nbU#UvDTW$N8srGnz(phXE6i$hY6_sN2C$)w4X86EzoSA2gLyXWIE=^57LdcVHE
z*RNRm36vn+`{j;;s*@QrI=*}<v9PdM5WL*)*Z*7Fa=TZBuI`%W<)S)e&YYgFudgdZ
zMkSB$*EgP|!dd<Oo#+<7yLtEb@kU4AW@;A@nmYaTbbb5p_su@MY0ywoTJ${epnzcD
z#Fr&jG8P344<9}R4R?WNJg%$??T#-I0quZH$j@K@-@?jD>hA9H_SLJk84?~GXk@cL
z;2biIjaQ1rbCS#X1zuUNuB-(0Iit4aXjXNt0<CTUb<X%OcRR`d>FMupZ*665<B?R#
zSZTFU(HpXfR^{T237}?CGcRb(8mNZ>+PC8YUY7IpAZYpF@k`0DVYHN+FE1_S-c|Ba
zsmiVO(C>cH`=Hx23LZG@*uC3%@x_FDdn&;T8UohG*{+G-KTmvt_@TpxnL&%9CMY_C
zHYb#qm*1PZZAR6%H=Lf6Hh_AH($b*m1O30Ydme1h*tB^wXl*TYk>ZK-=glkPVCy<c
zFJx^6t(NWS=>hd3udE1k{<4Itx&7D_8Gcudy{p65Cp|ea(Zj=|BG1}u(vkOz1qCm1
zLn_mimzVoP*N`7u8@*k@Q>do4)-dr9OUauX6Z8LxI<Jk|3c5|0!J(?kN=R53)X9D|
z|NPmru6cRuR#b+Z%(=0_@e9kUBcK^#(3#$6&+`8J_fNvE#$wLgxvuAf=I$(h4w^B|
zxU*y9zjc<AR1%N%NV3NLKFn|bVfGDu&}y0^M~>|IU}{_S<-pG3=ch6!{(^1Jv!9d!
zPTNlpgSM@J=I4VDMZ6t&x5LxJ-~<j*`19+#yV9VQcMXip;1$$<t%vSu?tAbc0dz`C
zJD;pmRMf14tS=ZIynA=9J7hj+OAlx#sFIRW!Mi(_pn37wT_ujo{pMcSkm!8zbBLn0
zHuofzm--BUo+oR~#lJ#COiWB{QM%T>IhMts{j;D^4^Z#_d5DFL$+9068cjB!O_s*#
z=fKN|udj>!`P{?BMHM{cxFSGPQ<H<A-@T&3V$$Tvf$QUJfBgKp(7Bxt)Q<wC>GJaO
zi^iePzg~|&{^{xIz`a$apgTqF?e9N0a-~~b|Io>ko)4Uq7JUL8;Psck?d%*&;mv7h
zF}4GQK8P*$$h<M(Q?k8~;9qfYOD0I@+u}c<*}4BmK~0&7Q(FE;n1L3A{y*9_CEm-6
z>(Af6iJ6(5jLd8aM>+&QeERgrb-K}mqd7-G19LiYdw%RZZ*5`m;M?2VPj`6Og8GRm
zX=#scY)rPO`l8V%XWO-5gF#Aa>cM;W<mOtHIz2x(7j&*YXr*lEst`fj$ihAu%TI^;
zSEhgtl?L7Ddt#z8=<F)cj>*#3VLNv3PJVf5X~gC<-f!>k>sKv%1Zs%~FY|eL^m%H_
z-QXG<5l1;tf%N6&<&Xb<zwe&s<l>^G_VR};hmz7S@$&L=(1c=HS($`Qg+Uv?e4k$I
zE(V5mF*}<;#}B@~wia}{=!2!NCeNDH)yT{aa`=j<ty-W3b1bZ^j0~GLZw5t3hKZC;
z{JxkEL92A+Y$_U5y{9RtskzmsH?#3dEr{P=H^ZjVXjS-ny$Z!pHqcQ!6%`iy{{O26
zZM_X$71FqUyZN6#e;z!3d^q?*XGjxoq#0;b{*8MOmzm1MUmHQY+9pov0Ix(*39<(*
zse}ynYTlUe$+Gg3%ArGtKK%WD|M9oCw^zjOHZzgp1znWADpdR8=MYVMdwI|XoUH5X
zKxcklEDl+mc6Ju%ei%?|4Kc#rzI?el!voM&k;i(a3m+fjJ?MQEbW(x+|3Ai{cxq{3
zk+H230bOD3<Le7L2lCI4$Nh`cS4AZyDb@Y?=<YMy%=e3k>*mdy5AS}zubY)y40Oo+
zhRvIuV`60X?AgP>u-LudEh<W??CmX8(ERv|3ygcKzB&~YY<Qt5>IdBn_u*$-+_^h<
zWI&f6|M>XW)j!bG-QC@1zMZVFx}S(`Yez>&4``WHAfua`8)%&nsASn!`}@$5BQF1C
z?(dln8h<!*_H5wRtkA#7pxzJYo}edBSfZn&8(**3^yByY{TH`phl6HrA(x&rGpMMl
zKHPr4uDQFLyYAOZ^(!lb-9a%~VkP_N@ncZmT2!?4_xJaQFI^J)`}=$Q{Q2^G_U?7{
zS6L*U;5<$Do3bY3Z*cT1iF<Q=)6qJWr3v8Z>AceYH{#ok2}@W&yNb=0)O`B<Sx{WO
zeZvNWH#asigYL!BUcaYlqO!Zw;)@3^UJU%=5(;WWf)<jv^-3*_+M2cK`HE8y4mMAm
zGNom6`gtW~<--q{zC>@&TUhz|*^BGz<*%)e*RNXj3N(mj|M!dVp~Hs@-`p_t0L>QJ
zfHq&LsIU}2JM(b<WABKF2n7=p5k^MF6DLnL&YUT^E$?m@BQqNV!?iV$&7fsil9H03
z>F$2}f1tiAXmu@Ue~8QZl>wl3*M|p=pf;#!))fI;cT-S_W%ut#GH9Co#l^)2W@cix
z?HwH<U682J4qw+2wi<MIcusDvVa5f8AHRNq?xOba^n5t`yNl?N4nbuBQBlye_LrBJ
zk3ZOX<3<FJq!9~ftIx4sX;$4Or*zcS**9+72s(29+q=8m%F4=5o;~ZD=jx(=piN~J
zs3}vD<Dpav8iM763_wiWwL!j9i~XCjrmS?3-OHCRK}U8gDJwJDSm!Kr@0Y9i|Mxp+
z1@^($Q!<g-F$|y;OJBYm0bQAWOgcZ|-JPAFRpAe&o|-mgN=u)t^`V<LC7s)N4!*g$
z*|79gNXW_{*45$bK}+CQ1}}f`=8aC(szs^k>5qSWd<?q&6twp3$Pt&nNB1sUwhT0A
z2O3A3FhSs;_tjqU1>(M!m-&KL9at7WV_=vwXAY=Wb~AlGBLnD|t_>RumMmM=HD{$o
zYwg=PQ>L_dPuE-M+AX#set%tKcc`l8p>4UhPh~ICN=;2&n0UAibO_%vpP5QkeXBqN
z8lX6f*pR?jR9q|w>!7=Q2X)Z<Iy$Z#dh%3XQEAaBH3I{I#>Pfaf9=rW!=Q2JvbRxJ
z*2PN8$;nMn;hdz>Id3J`Y_nX@8m=JENnhmmpE)s6`E-$(AVb3WdA2ibDvKJ;-!X!Y
zWC2}kdTm{-c7kMRng4t{*OC&GEm69U9zSMe;N#;<au>Yl4X&*J{J*jL`wOY}d;UJY
zK6kEypsI&Ppvx7-!i>457gc0UR#=7b7p^M%5OO>5N`IK@k;@%f%l*Ay8$=~_eG1Wd
zW#Slg{DX$`Mj=m)(~%w*1)RRU=U+W@S*MrPo8R|N{@yyxbo2M`=c2A}YSQ+!pRZqC
z<yZz=3$Ui=ABXm0XQp%Q|0?P)$S0PTctnW)6)dp(a{PBYAE)+W`$MN*O!$6$Tkh>G
z1rMEcqqq4?*NY8GNLaweE2Uy?Zhm&Qxxa1ow=28f?>n74eLv{r+OID!yUSXY1h}}g
zsQJ#CQXjUrs`To**yzvC&!;o|l>;3ElzV$y=93c>yLx)2+|9erE?=YI$;HWeF@1jR
zu@66E*Tn2Js((;(e_!pXvuCH?%?sa}byY-0X3c^H3aqTGD@$KrD=IEFw$?i}VZ#Q4
zwNYEO>KST3JUBSZEO*wrn4OFE?6EmJ-#(t1jmN-p>DM>+_U=Bheqr|2RZGvD@kvcf
z6SI1p{jU1+hYu6(=1t$dd-u)2IevlOf_wJtxw0|YeVWoA_Fv!L&i?=3y;myq!5IUd
zn{Ue`+YW9LW;pQv5nBm^!^WEbf4@g<$(T4zFLsr2`neTuy;4=rW~N`+obLbkrGI@;
zE0^e*z6?)2Jv}2H=j-d^!*>=vee&p0(fR&|+?Ezy?d|Q${N}FO|L3W`>pcJYcCq>U
z|883syZhOL6pijTWxLICZ!J06EuMX}OLSMw&rMpPtCrl`Tb+HNfsu=wTl?Dmg$!$2
z`67$HxJO9-6%2E3XYrE%m3;CdB<?u>3To88=&$FI6$*2!Z@GFw@qPc{cK+;#hgyHV
zTD`vH(Gkv{KYnN^DLFB-^M#zArps+(opZzB=<(yA_3vs+w=Ofwy>;U9<>1cF&RrEB
z7wy@*cWdEex7OBH&t1jApXOK=gN&Fw*{Xld8l9!fmuu_m``6Xgefsvz%zDz&zn{uu
z|Ni>=x&3T&Q`40tp2CwSPmR0N5NBim@5kb@x3`wY?X6l_^YhcLy1%>Ps^6L(J%0Rj
z+UAw+{c^wFY(5{dvnX}*;zd0_*8l&dzjXQX?8nD?)7%TS_U+rJ8dsDc!FKn#oLTOz
zkTuWeRlQotK8J<j!5Ik$c7`b)adGp^^6#x_<rdEZg<93uRW>#@Up}9=pDlZKQlGrN
zp69CQ?RkyYzkfRY`9SlR)5mVU-}l?^>8YvO1=D8FUhOy6O4Hmty!zW4Lruj~O?P*f
zXMcQj^w<6Wf8*y`m;0?-x9-)gt*hC1Bo@rGt^Oq6&bX9CcGHg+{TqyaDX(eb<D63W
z<@lq;_J>}*n6QEAmvX?bi}K!Wkj$g?V#0U-)6;an9_F`SQS<Xt)wi4JrWqF$O5fi4
zx~}<meC^k%zrMd;zh{pPyZTnM^78W9FBjdb-fq3#CFAh_&*$@Bk4fiisH-1;vgDds
z<);)-)@p2Qbe$(}RpRmS<Hw)onvd`A`}ZrGm6i47!*+QyYp<CH8LS@6*_MBQ-NVD}
ztKE8~q|9<=yt=wN{7LVNv$M_36=fM198MZG@G<;2TvSxFrRb@bZrq*-?eKLb)_e^@
zzka=5|Md{J{))=a&!h~KTI6cK1bPN#Wvxm(KW{BFJ731jOG~TX?R@Uz*L6ulOUn!7
zgFZQ1t=)Im^~qYVs{jA5>S3#R$kwdT&5s!?8eU9j_`JyeP)>=*f}BP6Oy_#}IE^pL
zH*V_u$6;aqOZkjj`=0+!PEIBT4;;R}zV6R&`{jb|{QYHbXX(Z4IPhrl{S{$rXMy(Y
z_DUKrJHhzn<KyGm2b)-}N?%Pm>ACjo(W9>1;(8%2E-n+FgAOHgabaQJuR3M+?A3Fv
z%U8K}i`_A*<zMXHulH^9?(+B7&ds&{S)&6wKw#(Y-S<l`a(0#d`ttI=tvQdgs8+~?
z>C>k-3t6s@uYV_6x_JBDyy=M&e{QldF!(hymM}2LytuT~+p6-@lUVcXe?J`N|Md0i
z)7d5kGj{B-0F8}V)&HycXTJMQ+3uQ}nlJx;zt8^g;GmkiOXkx@j}{&4m0n%{|KF?o
z`}e=Px;ni~g<*rrFXc6D|2T{<Dl$H}_o9D;l9kFCr+Su#M+=<~WxeP(5SA4R`+BGN
zyr!vX=<jcDFF!p!ottODeB0`<v$ITt`{is+>i^YjUL196FWZImv$K|7T<re(*Vos4
ze$VcJ)<i~a&C*m<RIJxz>I%EGFrzJ`JN^E?+OD3Skf5MRMMXtl&e#77PE1TZb>_^K
z4-XHU7CrGOeRbvJn;FxdJ$e-MWW$&I%8H5?C)MYNq@*mlwKe;BL&~}5pU>OtUwi*_
z_4<9U8cfc0FXgBQRR$>%ZJ;V{_St26vAgbkPUbm$p^aBsW&$6>gEgS+d7zPvUvABn
zD<P`t>f)96HYU59W?pguodelCd7;kk($~|zy}7yg@$r7|Nw2Q0U43nB^y#ZtuRcl9
zIQ#AG?d8Yis@I&@JY|YV?ccB0t%{%ZNSWuYnI2!aGh+4y#swye><@Ll=r`b&6=HbT
z`;TMwBIiRqU)&iq<g8TIbo}Gkd_gfWbmhvGS@-wteRXy9^18pjG>wdcl8^OFoIQK?
zvokZ5ci&xSTm5Z=$wJV<<$*y#lT<P<E%AJHdAa|@?s8CLS2uQ7$ky!Z*WTUTEj#DZ
zPEdisZ~v#@Ul7ZkyYiB1+i&LZD|o(~IA_k93l{>eu89m@xNu?Ah6KmPRF1h;rIXgL
zUoWN~ms1p!J=?l`UD~-hD<2>4f4y{i+@$^c_p4~?>iT+5(+T|h>#J$O0|!u{_wmuu
zQ|HcwIXN*k|E)-f==yM+g_ZTB0gtMh+NrBoP5*!0n{#*9RmPVL4ClJQ>2ihNTq{tC
zVN&<!htm1v<Yd$8Z*Ts{FJf}Y{Q7eF{H$MJUf$Z6+`cM&{k;GGUR_;%b$z`3-944Y
z|84E<?Ll!;!N+il>z6XaA8BYPGW>Ugq(r6z`!6cW_msZA_HuE*-KBebt4n`=N)`P&
zU$^-1`@OPOB_7J|eIZFnNsadpPnaN3`|W0W)}<w#oiEpDTUkY2ym)cayE`9#R{y_Q
zb9tHX*Q4U`1_#2N?lkZjx3;yty0p~W%g-;YtZZ9NO%0chb4Op_wI){Xk}od;Cr^&L
zePw0v)`Wvhx%c<QhOQ3NEtocQ=E?;N6!v~Pr7dM$wni^z$AYl6Q77-;kDqOxZ>DMJ
zWj#%afgwS54GSy7fkwTU9UpevSF8$KJL}wh`}YT2G`zRv-2BvT*O!0d0qCBlsh}GO
z9=tySIzH}v{lCpQX0xB2pTGXv+UV@FvrMbL-z^sv7GC`S=luVMhK39?nn77rKGC$q
zgJB1x+-jM6L7s6z#fu3B!r*Fn&;Lh{AAkMx`MkD*f`k6PAB)n?&RW{h!Ey6#+1i+$
zLA=stA?xGzp6Poj!o<Y1rSP#^YHF&ct!->&W#y;OpC@nMzWwG!o!mD!Hda0EHBZ@o
z`|0Dyi*IgDU!8w{AL~3r9%nf@xm5uRn>;n=%71@&P-l1f`)gA)gP**6w+^(J$ZCD;
z?rrDh*=9Q#JvS<T=F=->y6VD*ohqU0<6`UoeV%Vx`>Ui^);jFoy?a$(uZDl!zW?vp
zmL=yN9_y9<^=x+jr|IvXJbfx^Vb0@R{OpXO=G@{P6(1KB6%|dHH!tqR=b}$fPI7T^
zT{=749Gs*c9qG)vx@xML@2n$1Eka&?e%GeyMw^tqiP*fDfkCGSoGf2FY?r^bulD!5
zs(*jK-~a5)Xk(zLsA$Ba{D14+JpB*9@@^RQvOoOr@UWCsNk-#$Az|Uthlf~u<?Z8|
z+4-lHJZE14TGe)IYxd8Bwhcy|M1+4*a`M$}xzV||xA{g!M$R(Lo)%a6RJ66V_2qH-
z`jFq>-iGe4tKFO&b??c^$yb;A%d@hvojQHmJNMQW&4RiY7Zi^kKd!B%b!th=wWsgi
z>6Mq4dtTa@eEiAVx4QiN{F8&H>fO6{&#LUrjI3*GGRs7~vu|uj+*oyPy=2?MD_5?t
zPgzk?Q2O_8;f%}6{Z}U)?c(!#yvNAcc<SWI#n(U2nIn^$miBD_I?z>`3$yMNK03l_
z`}IojsS_sxmU>MEHC0v@Jv{|#@4YG8y((<&sr}AJ4+OCszp*8A@}fnHK;`HkJ+=#s
z3<V3~_Ex>zeBLg&qGCtYw>Oawa-N==I?KL(AE-e!`O?BI-abA$AATL{l?G*#b+Nmb
zB_3{D8MxSO(vm4tM9$8&4j0u9yRs$o@|lh<qX&<UcCQLv?$`L;EccemVS_8X%ilA-
zxBqxVIBH+bPUXjp4XGF86V*U<6(1+VcenbMn=dA85c;LeAi^&zl(xwJP}YkH-|s&>
z+%76Dtv&nfG<%g9vuA62f(jeZMRMQo*T*-r@fsN~d+IyO#Pi?3e_T8~I-mYLIN03P
z*O$idSMJrdwb^AYLC??3G`6b$x988_zoGkTDmOolh}vEDmWy}6``g?7+xg|ME$+9Q
zb-y|&IJor52|-pCmKCX|r=_`+YQ4R^J-nu7k6WKi<cl}Awq|#AcLy)`o9pB8EGBAu
z-rAR!m#+?AAD4A&OJ?I{=XSnK(CF#3`Ae28SyA@(R$t#skz;+btIwSA0i~LLyI(6n
zH*n_MG%9^@!BM{c&&GfMzV8ROLyvE<fs`*i3z!)mI80Xay>zTs`s(iT{H+-mmHxLg
zfmUq&`}_Oq5>H`QclX(IgqB{N>~9zO;OmQvi$mANSgNY4uXbwX`uX1e^BLo+zhAF^
zeKOfU>+i3xukP&Jym;{<o)v+M+s@6ijef9qZS?k2hYvgJMs3mfP`9(_X~?=5OZQ{U
z45t^^AM*L)9>EJOr#D|zOjL!|c4u55t$llb{{BDrmurQt0yQ_Sil6!XtL&9BEqQap
zaPy<7Qq%QfAAR09gHOg{fuwO-#`}AFch&qXT9{~h*kH=UiHSj0&o>r5_3D*2_sh)8
zoV28+g{8H%Rnyowc&>H%wIiLvpnX`AgQHF#YUSqM6Sp;MYS{X?wWY7Gt<1i@j`iHN
zwb9EvIyii18XcV|IQP;L&&eV}LW}0vR%<CKIbE8&KGkoI#X^3&9}el~=Y^)EEIFyU
zHviX`mt4HOp`V|f6_t_Esjsj1463TywJq=NDzB+pFDLukO)N?OQ2zK>@2ktp`)5wn
z1;qv^_^xhDc8}dv;yEd0`|YRi-mNRYSLwcT<x0@S*kSAAa*KkplQo$b7_L1`Dq~<^
zI5i1$yNab{q_CP#KwjRuX}ZzNQcq6<HTx${oOo+%_ViUDE0fB6rU-V6>0Ua}$jtrc
z!9Q_1IXNkdf`o<nHO$|=Ute3hHQ^vr?B1%-OLOzNKu6)k?k+ofzv^H2lqn)VfBl*z
zD9qsFUJt4m63whs816`eD~6VtFZvk*Y)U*LIR6T!Eq1<F-z#N$>EYq_&+*%HZU)8I
z{al)Nch}N6b7Vm6@P3<59i5zOvrkXcon=$GNzH$rj%U=qn#zB#<Nr(9R&4=oK{L(1
zcIL^EYtyGpS+Xtn_N&|Z`$N}8Z3R`FKY#vQ8MZdc3UoG&t?f?Dof4q<v8(;HqU!6b
zSr&zh-jr4Ui~RcPYUu8=+_UrT?;mM7r)Xppl)vw1+QNs$o?QI=*E<B2O%e~W2v4${
z&L?a2;&%T2t02d+UvTf0S{fc#>3V&A{Ppek>rVTAI(lJKs<*5~fy3c8-pifB>LTLe
z%XjRsm}^n!1QPl8_xI;|dF_xD3;zE8u5D&^?a7sEC2wz;UR@s_KPhBokg8<cLhbN%
zPv)1uxe*w>EyqxM-sKr~wY&1}>{$5h>}+illMv^2zN;4&I*Uq4trF9XdhzV+Y#mny
zh69c}7-bn4*jGnvT(oHM;+sPJms8Wz#cyc+jZQx|=i=7v>oPMqQcr@?>oQ+y)0`Ut
zjEs!G{{4QRD$#bY^7&k+^XnouIwdA1sx4t*$X;N7Nb5zv0jTxU)&7q|d!h3oA5gBc
zvr<{p^p9inMaB2~@9nM5{`KYMuMda$LFLol-|u#Vx^kgQy+kG3Ks}1Hv(3-HnK5n3
zj2Scj=WkAw0F|H9^yA~6Z1$aPcC|;+SVr=^rmL&#$@Ay^Po6xvtMc=*nwlDux<3`I
zt*x2Y*TsT@9<&jr%;)rMo61dArLUG8IpPw#ry_8&ny*&Dy@k%~XJ;B8pHtxX<itef
zRdIWN#h%~0cQ2?oWLGPSn`>Pj78NxMG-$qb=~7L7eScmllYraXa-TjrRNH$rbh)4G
z**TV%-$?ka_nT`4>OiTSJbTu6Yu44EqM}Vz-{0wadinb57CjW>`jx8bl#{c@Ea%38
z+}qncC&^Vl5#*IN^U2@;x9p$L;&@Ow*uW0%6!{cAJ0m&QzCP~XzkjPDHZHnZ7{CS^
z1G%I=zh=?3wbA0Y{)o%VulKk6x#R@z>H~j4ODJ>i?TIurG_<Pvvf|eE{Pl*($5wzg
zkI(b=@|x7%-u~<B>-3-?h7Ek6-XXZYVF)n#;vT^Wu5XwePF_?@Gy}=C@A-eMM{==Y
z^06oT-(6hXK55dVEj2%jZswSkzP}f{aN$BVwJqy5CLe#*Ykm(j)YISJ59-72tNkrj
zam;|HvZBJ^M3_(Y_jjQsC0pdGUMQxfrg~1wyT4D@Gwb@gxo!ON>rR~TXl-wwEqVD9
zpPbE#e!E{U);%}Px^m&?=jXCBPFR{|TyQ8XER?b;Sz%*i!!;*0JzZN*&#$hoPHkzi
zU0dRc(%09r?(W)pGce#7D3-6T3hnCZnxw)jXA^OGneXMP+Tl~CPhbA?^K;PXj@t4P
zJ{{K|$!`5}v2W7L-{1SoFqwhDi~Dfi_S<Lq7#SQQHxW@ZFVe9neKqCKp+i&V&0E(l
zUl;N3-@i#qdU|-~+SNw!N|{`Ec6RpD*RQjSf*2T1nSsVH{&6rg6fdwp<n>|#1A_%S
zB+)atTG##Av1jjIZr+uPQdWhm1l@j|d1FK3rrU2p&Cq9OXD|Qv_qX??XXoawo~Z2p
z>ekk5HTA9AvaYUr2|B)ThG8=3;Qz|%YEXI2#mzlg1=O_T7SlPgpHafKyTAWBxBi|5
zx3*?ypO~QdbFaFtu5V#sAt+r=(~FJD_{h=)x{hAfwkjktGEytcMomfSP)o=))0`Uy
zl5GnkH>aIEderrB8}IJt$0gbpS{6UEP?%f%`{Qx>t=ZT0K$jLhJw5&U*Vos--pXFD
zX=fK_Hrv;>>dS@n`L)YVP1T+)E4p+_cei)vJaZo9dPRN)2G>LeP>B+?w`yzE*H=sV
zWUW?sPuH7ek{Q&Pzwg_Ni_T`VeL-U+mYS!!=FE{fJJZ<x^|iH^KR!OL>RI~wTIlw?
zyCx+s0(S1+J$sG-L&GLeXLO-G6GKAo7xxH3Ss@07?8V@oy~E40*VlBHE?xTa`TY8@
z$!fk&UcSsMQ<<W;HhOzlM#c)zsdk=0-D0{|HY7TO##<*{SsktqDrDXJ<xGv2J+=LQ
zr`XHa_v*gd-z7gkJ!N8k0jf<mr=7jB*qt9#roUM+ZF}BbD^MlQ&M&9)p)Mg|0cgZA
z@9wUdQ_fV%SeN-Uv+-W)leO-Wv6(KhPN!@A`t>m}F;gZ^R5Uj?|M~0JDTAK-e<cnZ
zfX4dRRb3(v2etfu-v6gIee+E@2O$QB%!3S83=Di%mibCoR#j;k8g4xCcD|vZ;Vk2H
zzWYlU85kN=ekn6BFnG27<6vNDn6${5i9xPqYxeb5tJm+Fw0iYwHa?jZ8#Wl!em-js
z>h6?0J0s~Cw6o~xmuu1aFZX`GXKcB)*rMP;L)w`c3-?xkfA#6<=~JgqYZv56v>6#0
z`FK5-S+r=8N&Y>Xzds)L7nPP?ZDQp%NjV_^%8`?%Oq{sz#*K(xY4dYWmRy@QYu2i7
zZ*Q-T+gtVO`uh1w%F3o`XC!v++?jc9j^(D?Z*Of*?*|Xcge))o^yDN{cX>^1t*_q`
z8_?Q5S?jVFd%xccE-2WrXV0Flns?LfpEoQ{O;104_wL>!+k>W?f~%ulF=zQ07#t#t
zK0I&)4d9jAt_L;dz#UHp1_sbLAt*GO5TWsI``6dkSG)Ji6%`jx-o1Obm|o0^%FoYU
zUJZ{Ay}Zm9+(+M4>Md=S6Ofa$1~e|R(7An<?CndFCQbVC<+A_j)2F@HMsEjoutdbf
zmd%+X^Y+fpU`9qpP`~V^p{~A>QIN8G-<kbSi$6R#xanq2SAYNXvuT%4OjHK7Stkca
z#V>a2-I9CTtXIY|XyU|)n{L1Tx&2goOUsMR=k1bz>}jc~t(CO;-wYZ^EPQ<I<@)-+
zt8WH2)cpSTHaI0^$)rh>rc9o^7}T}o;^q!cOIrpiFDELygL)Hb$G1$GtnUBsT{Z(l
zf*iQlqQKA3pPHV2|LdO@7Z-zi<;=nh*WBKa*u3w@BW`Fe-*o#e>$#hKJPZvxU-WN~
z0;Qm9ZuKpq7Zn*9HketdfX2%#_GeyRrfFah5WOuYaH>}5m-zo*<E89sc7S3Fv^Dv^
z+3D!*c`Ivwf171nZN~iKyMU;uDrBJJ^|Q0HKYjdo@yEx<qGDppVt1Em+StUr-~WH#
zO+(%DXV0z;STAXi(7?tcq2Sro*%^3uS83_%Yr4jdET=X!Fy!9Z5f~X6>E-Vq9v3(7
z&!0a}-oDK(Gg)5r>4~TBT&vK|&dyy051Sr6ek>{@v*yehAK#fquFY(`L8qtbp6$!b
z3|$=-dUaLk*}lN6H#axCcXoDy`a5m>@_P04^|AZwVly){vo0)X)CyaZQRZ^m+s_YF
z8f0Btv-0`;`Z!R*X}>yd?=H}|$IZ>@#tnV!ixLmFecxmGZ#&Q7fUK-n%w8-E8oZ#M
z;(<mdXJ=4b6+8-X^XBGs)ADyQUte52+>)Zv4Ju$jBbKWI7q{Komb*Ib?5vrxoD2+q
z*!~KJIn}c;9QXwaek&CQhHLKapw?{TrH2<5I!l@7%~=()Qpxkz>G*$(_W%F;UdkZB
zp|MdSJUsmC`}^_2YCZ<qt1jQzUA}(N;>BMtIP+_2YkN;B`TZ@|6Lf&MNzIP}S2s5;
z8=E_4W-L9FFFt?4hLe-kSNqSm<Kp3&GJX2=TU#=NAN;wn(7CI>KRhI4iYMn>XD_d=
zrsn3UvuCe1%e|$cs_MFP=gvv*cvh;Zsl7TiRr}YU&*y#pvT_f%^Iu=&+HI0_gyUw8
z+2+R<Ywz5N0lDhq$B&zCzcu0k9kTxE`}gT3&tD(gey_^=@$r6h%avb2J5;N_Ty&p0
zXU>{8Z*q<vJt}HZ|7zuOE}o^2zi$*-m~v}tc6bIu?freVRy991fJVbjv#xkdnlfwF
zDrNUR4F!b;S9OMl>LhUO0ZKK$zrDS>%vTyTn%$O|ak!25)}G4E(2>SYVf9(E!l_3<
zts~IXRqXDtyu7@$<BSXpuHYKDpMfDl9^7jHN5ceAS3AHeW=DaeY1Wk!^=}_PR`z7Q
z_xo$4pI_hMO_ti>;o+gHLOdshEcFuIxpU{sKR-YJd|p>q2XbrV$ADu#*gM_F`ee2J
z{ry$d)la8we)>Q5XZO3iyI;Rvzu!!A?q?1jo-5|}YZf1uua8;3@7JnVS5^i;QK&jU
z&(_!DIq1BOFK5l~XB_L11a;dS931}5+`W7EudlC{Pt^`LYKY^(Gct83sKq|*;h|R6
zxb;z6y;g^>zqYIN^_8vJ*O}5^Ut1gO;?lCrXXc|59SjWWPoUj4w_d5t+uL$MMTU~H
za_aWmUk|d&XPla%nRRW=Oi(Ye>g%hSvcjn@VPVteRll>WE8u5nXuT*8?ie$y>Ho*E
zdZ9BDLqaX2|D|DDSNr)<etx3M$)CS}YwPOzUYdLV{IOnX&~)3+=h@fR1fHE`dbW#Q
zq~PTx)v4Oy=iW$6`+m3le&&%5!Bv5a-6q!iUt1d;zT9uFk>bqam$$dC2aQt8*Zpu@
z?A9A}e_t)AhYV_e?5+NO?tlEBeW0nlA0Hk{878?bOy!saniWe;NtrR>%+DRW{{53(
zxZHpKvup2?etZpTac<{3nYaD<{J&M2Om*=oDNF9vd_L=R`1vFeIk|O$%5E8lS~%5I
zm>DdD^BmY24jjZikQi`mOYZHkl`B`K9cN%*`0h~O5_&<Nk)eR^i+cnos4?=~p&caD
zc<J$R`T8sO_ExKUPS=m0rm}SD(v@CQwOHp_m%W*Bc(di=yt}(H@9nAV>g}Dndi841
zO}C29Z7UKFw}Bg#M~@wwHAiUa&1t&PQ>ILr^1tfmr>9>2{`z0;_}l+ovebL}s>sc0
zd_K?T<lW!*cenG3nKNhVJk@M#X<^x{JcaA|xw*mJV!H3D-o1LY>dl)RP(KFGcuw73
zk%y0tcDJ6JZIZbt_4Krv6VB|Eu`F`Ax;lLS>z&)TZ|{?_e00Etfg$|}xOr0a_!zHl
z%#HxiwdYeOPF%P;eEq7RrCy)Df4_d&-+paJ2Zvexp@pC!`41low&vZ95)>2!=f(Yw
zps^HrP_6Szc})i&Cqu*5i;9V+U)&db>FDVRNl8g*{O;Bx5%|J#_uX^6FOLdHO0Jx!
z?0zb3v*#o>emR}lXP5o>QE@W|RJl%)u6zGzx+}-g!e3urvd=iOQ&mk(%gQQhQi?>|
zH2wH>Pft%5|Cw`nnXhT`F&_70#a{ik-)3A}A0PkZe((1D``0F^dS6)=YYpm-FP~R+
z>J7)zruFOJzvo-{?#4#vfB*jR`8?U9<~wW2gb4y)-`q6*pFOLYo&VL5PT^k<n)yq<
zy}9Wm%h|e7<l(=J3kw<_J$eLcrB+r{h*+FHcP=buXIOI|Y%M^{oIij5_;|516o|Fm
z&D%a(mWiR^(z|x~x(l1n+pT_ly#I9GcF-v0r!QZwoVWkK=Ja&^(*`_0fBww8x+)Yj
z?til|(9I<OUd(j8*h@2w)1SP2sTm)C|Brmg-$MpGZ}0EFzodnMVM;8hLHt*cf#LNc
z`$MZhosI}`S)nkOdKRyCR&KE=Ka$z_<^C{Cnj#BoQCbu(%DcNOwM^u6VPT=>w@J<M
zVoG=R)&6E&UStOvh}fEa9W(%hbFlpMEYobz%zUqep%Z9SzNxu+YsyI>&?LB;nwzJm
zr<aFEfQLuN&A>o57gyJpkNfSffd=*#I5LAeFPE43a`EzB{qys)X~~NKP?es1ywB8n
zRj`ML$A#?mdzUSC?-#4sAGfy(R1=AciKPV@J%9NA{d&9FUm3TyWFqF!kNvs7``_Q+
zuMadb|9aRi@8g%1`|;yP@MP)kvRqzCBbEAzE>Tgl9zA+g^6HAFZtSit7xuqoVE7}&
z{DOhOCc*yypUtyOvzL8-eqP(iC<rut|Mu3_&*%N;S}m>r^H{#>{oe0iJ{;!H{{QbU
zs4L#t85q{m(jxMjU8l3Nlh1>hfuYW^z9sY`C|!d_bbCPQ+VrAgV(1rlh9AjENl7B2
zqDLQ;2u5@i{Fk+_i@A62UTa>E>&c@>k7iz35xA@BYt}y|7Ee(0FP~qxs*#y})|?Af
zpf$UP4YriMjRN(&UtW4TPd-_q%`E4}gNBlGuaEUgzq+?~_rBlntWC48`TYL=KK%4F
z-O`trR6#bx?k>B!{eE3^hNZ~6b9vie|9-zeJSu9|r%#`*EO2DrntMA;Pfst+y_ieK
zbw@pDa1qoJeQ>au^&USD&y_1HgRicQHlI9+kzo!iB#?~L&VcSg-jaEF+5Nk2J1ak@
zmA<<Zd3m}2_1Ek7zuVCOYK)738kP)RNR9C`lMpk;t73L;x>@MO%XWeBdFj_zp=;y!
z$Gv>{@~88vhYuhAk*ySWbaXW0aqjHwEGjKMTVJamy*;ng!RmS1_S>Kqmu~d7H3u$$
z#`D)tkFT3~Fw;WBTkzff$?E>Eetdj9Y00kA*Qc&uzy1VNN`X63{5LN9+v^@S*phd5
zSCXx^=j-e1>o06%U|>iH{Nm2Qz%YdclvNm1UE5h0W<0&Kvv^hL>S;nkLLy>fX=QVQ
zni)$hZZ$Hqn<O9Od3$$v_;mgFu(-Im#$xz*?uO*!e4r-F)m5R|pZ<U*-8?-5kN3&S
z&fz)mx8TVML1^n+D=S4C+{ZrGx|D-~A)<NpO-2R=jkk3_9<u*^s$Z{pZF6E`;;$!@
z{pAXj7A&}PCuZrAB_cl$GkCtbvT`!#N(Kgv-7oq#Sb;+Knp1s?@d9Tih6LRbj|kbn
zf*N;sm~$88d3t(Q{d&3l>C>l6K@)BF_tk<r4}N}qW$*5+Y-nKEnsxQmn;Fx@Wn|Xq
z@Bi~@o%0G#PR_25j)aXz>NPAaBcr$FT)eR{`D|a3C1@PCpkRYl$%_T;a#bhZSS&rZ
zG5NSj#s!79H#R<AH}|*!58H+Ag9bc%|9m=K_4DcUvwe@Q_|3CfxiWaUmZ4#wxL!;^
zP0b!q+j8d2m72lJGA=A|%(}U0=}kjM2C-wH3WWd0Qt#;@o72uF*+wsR<Bi=_@{&=V
z>D`Ibr!QN--?Mn8aXM(!qrA2+KZ%*)LBtn#(8?(WhU`V)HB$@>5yG-UVXpNor`Qe~
zoauWY^6lN-=r`&9^X)(bJFG;G1@69X)F*A8cOq@GrH1dzt(lkATwPra8{%3tgO{B!
z;MuujhlYZJgQKJ4&;2#EwP*XDZ)xL|UIywjALh3Yf%IF?^gS_&=qmWXbjcD83yX-I
zJ9lPXUe+5F6f^}qR};5)7ijkF=_%3Le?OnAsk1UfNJ6rcdET7~vu8(doL5>}diCsV
zbNK?L2Ys5s%U(3|+g<qZ@UW<e$dX28_E&$u-w&Uv6>3ua%tx|qVdmv!Gi8Mt8jRZi
zajaeh8UyhKEmi_GJF*u!A6oUI-{Ix~-WNwNgYKH<e|`IH8QbrN2519uzrGjED0_P=
z^T&sWpj8VM6+31c>b`t(a<Wz7BbR@#w`?(adt>9`3&r+-zf1;=LAlFS9+~(t;8;pZ
zO2+SRZ*T1?U0wF(256w@Y56;=(pMr99{fB!Cf4gN-`H2X`&h5^^8Nq5u1|9>w9;|i
z@gJo@eDe75<p(Oizq|YO>-G5AQ}`Gj=zx1wjCFrL9#6_$YFqYZ2J<C`@*_u&zWn)o
z{`EDHn?Yk;o<Xa_)`B|Y2b<YfJGb+J+Wr5&EVrLIM}(na6KG%=92TJJPZSguuNOIk
z)-E`_eE#<B+T`PXE7Q)-N^{@1=jZ3=vt=1IK*J<jp{rCpR|PHYx^w4F$-h58{}kKX
z+soS3+*ngF?b}iDcnvG7sJ6rt20Xs=Y$7MC`|Ev~b2o2#cXxN%*;%PhUQ<NBzP=s~
zT3e8CfWfm|O#aP{jn22X<zD{w_V(7Kqg=Xidm`ErS9nd;dUa#tV(_d<*6Y<#TUV_L
zTbotJv;0U<%kTHQ-|xHJ!YLfG*sb@^`i=E#^X~2fjnZ+RWMDYg0-otrFfsy-AbhXs
z%iU72WU{({)|(p}CoTE(^t3l<sfmi`(^FF~H!w1Px#%vRd1{L0vQ!p^1#1?8S8gyc
zM2P<t3<H&J2X?)futDjUa=@;+mc?$*&(EK}e}DbI`Gt4xJ~-HXwvRysG}jNBl>*IE
z?kG%N8?n*p@9*!^Rn|ssZc`O5|9GeP{K~?|$2Q%5+ttx=;r06c>lQ3nz;s@sZDE(F
z_N$G@<$~8nZT0c$+64CTwY9T%mA+Q<JazW$)mvM$O>=LVyuGtCIQ#lKQ_F?L5_UB^
z#B`&U2r9dsNZUM9_V~&TA`k!VuKm4DD{M{0_0MO{`0U)d)6zhY;eaG)E!6?$V`fni
zp<A=Ag35mHNjA2&pdRqc7Z(?^&O3SPl##L&14F75$gA}%3<qX`7LS2@*e>m$D!K6z
z=z=&Y^SqdU2eO=;nn2^XGiR<mH`hA*(UDHjQAH;;8AZZDgN*t2Y>pl~cIxWY(8cck
z*Cr@BgT@Ix%kwt$_V$`uE;VIkVF8s0lcvm_yY|9`fS*5q&YZ*bWBZgTBA}%dx3}kC
z-<EqDG}Jfy?6R=6Q7=2y=NVYf3&z{)i;3v^Fu(fE#^YP+{#Nx$7%sYS^X={Jpmx;O
z?Ca-RQWzN0lWx2%+kI1!fq~&cg>BUr@T~UL@OaNjRo~yO1$B?O#dHGV;^wjON-c@n
znw9zc+gmktRtAO!QBcQ(At0#416tc@)Pm-$;`UapbZ+N+b!llgsCC;bZLX!G<8x`Q
z{df34Y{Mf^+)dRE2dy@fY*X}%+EK9Z(c{Odn{R@q9q;X}US0O~mYTY2rfJoe7fJTJ
ztH0-gqIi4${kn$EIhW7QHs6|le%_zkOUvKfSlBJDzbfnMs#g~lHd~dwSpizimV0|!
zQF*z!^}5Rig@rp`&rFm64<$68Kbf@ac2EmwLaI}J-i71x^*LoO-qD-WdaJ&@St+RO
z_Ts2`JgDrQrW2_oFE4-e$Po=qO;1ivPA*PPLu)OD1BXBb3WLVtu(eT3ckHmJ{dzTA
zD}LV|K6$$}pv8#V+TLZmW8>oDqBf`X-rAm@Ulzi^z!1TJXbLbmcwUfiyad`8{^`q?
zkffwVdU1O+^7G#_F~0ycn~l@^{N`9B76mbU_xADWQS+O#B6@q?OxdHKE?v3=S~@0c
zTV=BU{hwKh61O%aHhaEY^ZGkmP4}S<`4{ipy$c#{aqE>@nS8wOr}Oh(X>&8{S;4or
zWCm}XSN&?`a=8Mb=ZAw@*p>D4{1&_QUb?zE{Ij@%$E4-Um)rgQ63i=Oap6e|1H<ZM
z(4YvzPrdkkYnCig0W}Zb+z5<|i~D&$hk=2Cp{^S-9?Gyl<wbu(adCP1b$9vNCD-Gs
z*PdYfa^C)bO#YsaZAC>zK7L#e>N-0+14BYYnD>9*Q1LMdG>xLCr<ZkO!@@nF!P&gm
z*Vgj+rPbCyDL$RH*|tID+}Wc?mmcuFBx_xEMcCg)F+M(i^Wud)Nt%b6ixEw`Q>RY{
zH?#4A`q<!^0bYg&Ea35628P!wVs>ttSNkpU?w-ov!oot(^dD%#ZF4ds1H*wuFZvl6
z7&J6N`54@uv@pjU<z#Fyb#ZlFS^4={)b6siSyxshmdPwXWbpHE;m1d=Z$ahp_WbML
z-rfd{(B0ip=nR^^Fqm*}Q|f7<`&Rsa1VL5s*)-4)v5k#Q$i^hs%BreavZq&qwDwAw
z25rr{dS!k5ekahGsX<;|T~=jpGMua!8a5|@0)Iiz&dSfAY`(Ooho`c#613D7)PPiZ
zd24I-uP>MVzkWO}|N70%&7hITlbMVR3<+kxz$5ove4L<>`vvw)OT#lVR)CHM3|#Cc
zYGqyhZ4Ictm9wpyF@cBSOzEpDntQ)qi{_bs*d#744%FD+RsLQNT&#Y-Uq9b|ikz_U
z;?K{|gVw}k-QKo#Ud1C$-+4ASpIo_id8xO!WZS~6+1F2{ZC>d;UGMuJiNgk45)ZSn
zFDcdo)yqxI&0n8RkJnOCT6E%bOACvui_42|Z*TMYu`v{=fmUKLOi^6!KR?XFqr=F^
zC}sO?RnK?t-bHQAntE!gHfSlrT&q&A+}qo(_DC9ES?(`CS(urD;Q(lMmw{o52&fij
zP<5<l@!CFPhQ!wV`*FFqwgm34`}>J~9cVqVW%08UdD}rHaN2PehW6}hYi5FOODyAA
zetAQpvt(P~qJBdj=anm0@@oXXeE96yGSECj?eA}(d3qI4r?~3>-|tgr%viBxi3;0=
zZqPnJ$+n6Ax1P~oA6NwPUfs_<duGSy&1GkJ@Ll3t_1|tL28M>9<P#GVK}FfI9?8WI
z9wf+Gm-$Rq_n)?W`Eny;V^INt1vhR)*#3MnIn5nZezIbepMUvet(Htwb_dPN91!sF
z@aO>T#xl*kbmT}0Ls#<qdwY-8ee2fWcj3*=%{zU+%5BTJxkx;|CQv(UO~CH5w`cku
zo3Qan1Z3<e$35!lpc}pI%JlfUOt+Zjpx)E}-~0bx25l0k{apr1n$z`SC*92ht$e?-
zDpWi7{=U0!W@tRFi|hhjN-WuSaKEXmMdha@ese4oJ-N8JE*<F<zPhvcxzqW-UoQK1
z_4Zz!X`DV~-n@4&W-u_Q9|E<;9V8#Ue!V*H?yi^b>;G5(tN!@$BWONnSNZ#OQ?<iS
z9X)#VNDHWY2U?uOz~F^Qzp3tFVbd;MzC3mMbai`s`^xI-*|MAthC6rc5c%yEzx(dF
zfCRx`UtR{k*n8zl$kHWCK=UwFPbRu^-F3>AXnXYdv8?Dt&9zZmy+D&@mzH{8MINvG
z_p!hJ#mw}1hMEgYK~BH5ueSQ%fuHkit4kgq<GuN|EOcd%tE^Q?KtRBRrlzJV+j66)
z>c`)Eb7HAeQPCz)$Zt$OK1=rKC(uGq7k77UE304g{^#9(Tefq@j*M$-B0-bO&6gM%
z=1c_l#~2=1fJV)Je|yWl=lki`;c=C%@^_dS7#1*KWZT<>mbo!>CI9>LGtIrAYIpg2
zy&{PXVQZsKojDVdmX@|~^CP~$(^Dr-oLKewtT{LDeD9!&iXEU8U7W&d1`Tm7Syxwi
z?lNwPTJ9(N_1#_T`Uf@!1{2QjXHU7j%(ttnD~Vw*hmPwGd(eoiY2KZPvfZ(Qf`XuB
zJE9^YArB-E8-R*3+iy3LL8XzWCnLkTCQw_l!RX1ix3^aXEOcu8URN2rvnbVA2~^Y`
zLN98k<V{xd1udavVrK5Pv9I{BVA0~mk`C-Tc^@7e1bIo_f1Zi8)5?-3Cj>*+$NgRR
z9JF|^=t&2&ux0<l!|mD@77>n)j;n%~_uVXHn5J|`osp4|i-Ti=3TP7F#3TeXiNBnQ
z!NM3ceZ_EUhJ5{>!0PYs&eqrd{FLe$6csgVRmjSq7e9~7*WXFJ3F@!gLi+27QsvY-
z@9BCgV|EsS24O8$vhhl3=;`@6xARSHZ+CCp44G~)tf&+>PCsX2%@n`@8Yu{muf6()
zgP|elz=qpz%QibRFfbf2jERZqy2F&Q{WkaB|EH_B=ie_2u>my*crY3S>8GdZdU<(G
zDtXTK1+?s^^7FISdB0ySpTDK#We{i+&hGN}Wd&Xg2G?I+US9wGjsZ{TiU7yBxHvwq
zCvzS>ehgmvU-tHvlu=5@pTB=q??$G87WD)#_se{FY3Zxm+t;7;oO^m_@pI6X8>%WQ
z8ag^>-dHU4^6}|ev}n<fS!{fhr%hY-^Yio9FD@=Vb?Vfme0L6B@Pcsgz#`k720jLc
zfVMO9?eD+gU|?V<P(lwiulYxgxVXBzd+##7u&L%}k#79HJtxv<o8_*OG)}WHl4FQy
zTE9MjqIX5z>BEPeK`Tp?l$Ecpi?wD~Db}m~{q5?jtE)}(?pXNFv)OqdG9h6>+Sys4
z1y(bsoZDG=UUf~&QjYpFkB)YmR(wd<xnl=tC|k#rk>QUb*lD142^>GLFZ=teG<J8H
zZ`tlxJ3G5sw$)_|XQ%TXp3vUjt`)K(A;^ot;QF1N#iqs2d_dz_`g^|wHO}5WT_<wU
zudlDO9~@}(^7p^~=xF!UxpUXHw6K7d*gtu4t@P6qPmuCSA=~p}K?}#`oT!AZE8k$2
zcjv^0e8V0&+g&%#gVvZ?m%n?$_C@GX@u&We-@k`HJvDV}+1seAD*_L{v0z|OKg#<8
z?p`S4U-G+m?~2OHr>lUfj(hj+efsdhz*3YU;`GsO@u`z1FaGkS1hio6z|AKoCxg21
zv(58gUG}%X3MzzGg=&LVYJ%5PZ~Xf6*Ds?IzF^Q5c&b(R40_n7uxPxvvNE{p_1f(c
zcI*s)++)u0L9K;T3rbc-Z`V8goFSlPrg3`Kiwg@|+s>=5tor)u*XQ~F*ZAB24Vm=h
z?c25C@wK7V-`*6K_$)8@^u!Z%EGZ}l_V@R1%e$-P3EG<Q;^N}3>+AoXe$sModC}8T
zpk=O1OiX9`9)V5-_5K2y(M@xAlf1Yl(s-_A@v%1&3=HbWF+=3tZqUw^V?C0$c9*XQ
zHAnaC*~9d_Em1>R`S6kwhJ?N|XMCPMd2;8gjk>z~%$YNPuFt-@D)hyBe-BMfO)fsZ
zu)Mr=x3*+1o-#$`>9c2EyNplFpD|;FcKEs%pU>NyTdv&t_SRPKx3{*Qu8&>l#L6pY
zbK{81xuc+d<H9S+nup{+KWvwO1?m%ge|MMrk0d+80u^uv03Ku@MnSx)s_M&^%jZv<
zK7Bf9?P~4sZ<;zfK9-i2w{{jUXJTRkRi&GgnHmm*CMzy4_YYqmw->aMmnprSPxcb1
ziL=ai_Mh)TK|vwA%W~b1Z`rdk`S_{JmxE89Jh|y+4(J%@f_r<b%RyTy)Rq>@$y$|6
z*uQ^2XfejWzrRnPKY#v>hsI-2P4wmE<>eQuLG8I48yC+q&tK;*SGnZEA(q1iBJ%R@
zSAZtyQs5mvkmKQairieQ(x9}oWs@dPF8%z>_veov8IO<ka&dECUKhI?)W~-27Spt`
zx$|ZP!-IhTzpn2Wk&;@qI()sBg#~1-(w8qKxp#MkPSpwxN=jN3wJm4moH;UEv#<Nz
z-BlW#le6aJ$+b&CX~7_|>EHeTzw4nx?4SS7ow#IY@$*-pl?tF6l|Y*a9v$rlEzea|
zQ2{j@LAyXeo&`;)hprAYwVt;Wv^KCUamtHi*c^I@)s7uIHi$gr|M2zeU+4M#>V9)7
z96A{omNJ?zV21k=!q~AMbnVfL7a6u+E;ye$b!w8z-F>yulR(ooyz+K26DLmOS-`AO
z4DtdqJD-M`S(vn0&V_Bcw^ckr%RE5?b)eC25PONW`TuwK_uoIWV_NC&Z@HmsB0jEr
zK6B>GqT=G>1f}O9f`SV>Iyh3((y~rYQjOYEu@O`k2QGF4rI%|BjLe`Z4)AQ{ifN#5
zc4FTD``g>g4-dD0eX+P7G;cX+$(1W1vX(_Ipfw^lH!YP6oO|j}D>o=~{(i6jza6rc
zKgp`{(~_Hl3=B&Juz45vI<Q^E#&1tdR4#pc%XIQ&CWbkIkdenNSyxv%nJ>7%uQs~h
z{@)I{x*v&a<M-ctv%*hZSy}mi+LtX`OhVViM4q?(J_j^1uwa40=EsrOR)wwxjpTy1
z-o)-M(=FJRch?Hk^q2qtqkUfGGs($9R@3A4T|NB#!gdxtjp$-vXlUL!LlzP%2-4x@
zqxbLEZ`oqvIVn*h>&}jiVQV5L*6&L@D|K~E<mELL3=HbuzunFUZ}|9p)_m%uNlGuz
z9mom_nl!KOSEj68O+^0wzuQh~&V_Zq7CNzlcY`jRsvZ6cv^i?FS#HUX4~d(Vqk?cv
z*B1L-T^)X1I)BeXS?e+lU0vVz`+lzr3JUrH+GLk@b{1%R9_SRyGN02{wZFc+{|DOS
zv}x0(Gku&48!W;%qbE8BjabkTT$P`nX_}dZty{Ma)Z1v|kzCZqEA6$bcy|^ki)b=F
zI4EtFGlS>wg*B0zpFDa5S}SrFyf<r(WwFeJbCsYqlAt|UZoN`VXBww_O^T~}sp<*p
z!h@FfO_(4cENnG>b@=+Mo10Rjwq#5M&ES9rn{8}j0s{j<`&~h%ifV_wSiAk+r3s48
zTe7d~ZB~vxH&NL=WN+2i-Seuet6!g(sLbaRQgtU+^N@Ia%|g(U0?;_n<z>ES`!Y56
z?b~O>^LXBQjICxU<4K741Pu_$?cBL@SJBfh(1HN_Kbs03IvoXXBGpt;aoJn_J?!nR
zt-gL-4E)oO*R*X<;$@X;TPUpVXQ8pMcz4y;RoB+XumAF;<muC=D;=BJxcK=&73<l)
zXCh(iVph6#i@gLbs`m5i1C{!Y&1^40h4<F1t6aAB<?mwl{`>VBw1Ag0bFHp{K|o$!
z-mQJLyJ1T}Uw5j{11&M<leJ0-a(Z60eJMvX8?V+Dk%ehzXX&{9=-pZTJnPw+nO1dw
zc7Ou?=kMR%lP+Dlv?b-F5NKsIXlAdfYL}RP9B4&~s*1{r;N^a5>g)^=oXi+?y^NNc
znwzk?-<7q|+t2hdF%&pim%RyC?AF^QGillq@9BD)s;aKC)@3CHM$aETdbG%@^i{@z
z21Y59j0sYvSzmUae}8Xp^yaj)m;U_xEIZ{w<&opZU$=_K1-!kr)imYA1SaPFh*g=Z
z_SOELHRsB$h^~TqpSf0{++sQxzP-I2x;5)6Q~J!AGeP}0?e%*Wf!5p}YUKv4MEmpi
z@7BuCX_JMR8P;@w8u%!Y$-oENW3^(1#@&6jx8G<mFsP?&zWD{--(TuIT}w%+sXqOk
zqNb*&qM~BjaSc=4vw)WT)0FPWg9=knn!dQ$UA*$&!*+Sl{x_?_M=dIvR#s8<zi;0!
zd3s9J{TK^F#GKWj87@>8fp!YmR)5nlGz@%xe*X0j4-Y?m|9<`J>+7|3b$vlAs*iSw
zp6$!X{JyLE<FQ`pO*eBu`+Owq_U}J*_^{}||F?JlmRS4R`u_j*?@c*)ZZst=J=%EG
zN+)d3!cf7qHZGOk^5vmCQDqlCF57)!QF?Id<;zv&QFpQow+Y_$klw!Zn9)U<6-Tw!
zHHJo}xdpyjrzRA(WyQxA2bB_RWeyhZsH-<QogcX+OZ)TOM7jPazaIapv%CL9vUui2
z`+M`xOQt`W8XkAjTYv8qm7m@Fe{^5DdUa~dwQ8F`9}dgEEVoQN)Z#P4An`xz*P!Ta
zIVaD}wZ30o`~2M8o10Qk&wH=z7ISX7J8UgL&xv<;ckfo_ZHNP}rGN*LgZYa$Z_ccV
z+`K90=BAL<S4CVW8lSUJ{`&Q+=cJXv%hT@dsoeQ$)oL%jx0P{~Pp8^$|EhNKSg-Wu
zix)SZ-}m<R_UC=p?@p`;T)fM8efSLf`hV_q%Qd=Us^4z?z3|zA(D3l|7k~Vp1hn)Y
z_f(%dB|3kv>GL_oetnkDX6(H-ulC!`J7u?XEq^|l{N3jEhD7H+i$@*r&ao_L*Ip%G
z@<tf$NQMK)U;MuRzi!>`ce_eTOQ+6dy0CWN=eh5nwA=ql%-i{Nn$KJ-)5phpPp=AH
zZIpX!i^|FC`~Q9Y^Lqck>}%^{ql+@nf8P7PR{#F*d*6dZj>_K+UmF&@GGtT6#YKP4
z-v8rke)TKgRIjJX`-4SV_g|O4q`iL6B>6uN*ejn*bpN#b{$IV*({xWiIXQWA>gj2B
z3J&vTW@euJ@$vELb8iA=x;E7RxxN2y^fJG>v$o%>(w?mDf3Nt&$<OEQ=bL6<dm=pl
zhl^b0lZid@_IB3g@6Kp0pEJq$yp6H>y^7?MPZ_?bfEND1{rNA)-}dX3_ItlytzQ4`
zxKP8q)myik7C$?4^3KlU&&Q<m-)#Q3^L(wI_jEnog=?PAHcWQwv-|ZTWc5`ObMxn$
zPV0FG2Vah>?pk!>!NKOwKhM|ODZBM(tlaYa*52y!o1E-xc%{u!K0P`4^39twC)MZA
z;gvR9vU#(yXVHzs_NNow<xak@|Nr~XWBY%}CzsluF5mzAZvUS?#xMM4b$@=?d_H5m
z^W!n;&ljBem#$r_>uHpAWyP6!w$}ImecNuFb!COh$pekdpTAu8pFWe@fj<>ASPApj
zkIi#SE_upVXuqvr5w=>sO8-D(%I9ZiEg!ZB-z(o6zrXJ0#$<PMv9EHVDBMx_c#?{B
z*_#trRtA5*dA@GjlU4V!udj=(e6g_IsOrlLnfgB;Q=fmSy8r9i_M#65*`I$rF7NN_
z>&s{V=fmD>=dE6^`Lq82*Zp3rUhkCY+VH<e#?ol}{krO#k_=yxz+Hc+s~YTYKRVid
z+K=JI$5*djeY#V8e((D#cX#(!uV3%pxT5^mt?T>3%AD3;-(UZKPWipc$Q=a>8Nc)&
ze06no@mbUBDL+0utbE*S{w?x9C}aM4|NrlPZ;jWsGF=P|w%y1D<Ad{M7hT1t&Skjp
z*wozo`LyV~lRc8gMOOmdRXw{Fd3<Vbwt2Vn`8-g%N>%$NC2gJu>dbz=egB`??QOZ<
zTchq~@73tC`EtQo_3GCe*T9rBGYoHTO7*^}$=<SV-8vpQn;*5;x98lP)XZnKLb|(3
zzFq0h%e3?J<}T6zCGZffsb}Wd{${?f*`;Lv^Q8Z-g?tV7PJzbXpy9y4;9$Pv*Q?c+
zFJ7E@?AS4x@;il^T}t)e%j>7Fjo$uj>GZf$nak%+tNi?I>fD=;w{F|^Y*DwK*V3Sq
zGYpf9PAIldnR`V$w)AS~&QGVbi|<uFPknP^W9suSS@Zw@dH&h|{}=z6*5&W)vSVXo
zcm962yZDsm@+kq=sx3qw`fpD<+7+TTwWPFkY0%1)qg|raeCCz*@>}>AT)*y@`^W-!
zAOpjJy1=zz#n0!Kr@g$i^yZGj<g)ko<}U8D(t19>zD{r7k4GU|Q#T1$@A>uX7muWo
zigwtV6CWNPK7H=x)_>pf|C{~)bN>IF=ku!df|vQ6d~tDcaCG$U>+=?AY$|woXcAX-
zKf7FoLj2ED;YQ`}?wpxpX*^lo|J>d3`*RQT+uPj#|L^<f7mNGTo}QXI(<s&J=1SYB
z?Ck7ydp@076Sw!)LJo!iBh+gAi`3SwTYp~cubYxz^H@4{`IjvDXB(OqX<WK`^(wFF
z-uvh4|9!6cJp2Bc=={A?v$pPf-uAMY-_GLy2mb#Pxb^pJcyego`Gp(|7m884lsEj>
z?R+-NXP%AaWHsMY>h?cRZYt*E5LWX!@pAe6c|SitpFWqVy7Kkf?VmuQUit6m^Uc-Y
z-^r9-3AB9NV{DXiV#21&RjlnwHG8hDjh^l<SE;go|G%ndXJ$_R_3Ibt0xeLu_F27J
z!6Rq0<BbbLl>w@^etRwr@(dJN8KNa=o)<G~)~s(euU@@6b?)`le^2B8fzI|nv-kVG
z*};C6OW(+NxVyU_>yw?Gc(`rv^IzB2MsH3$+-728Qc^5g8<?J+o_2QD)YQ|{mPV~z
zrqKmD9_I2g-_y7A_s`w6YuB0C=KA5WrJ*-hGJHuu&aw;)-zNLcHe0%PuWk0VHJ<M7
z?$_4G?@w1KcyeN5HSZGn>NguxpMUdsKCk+n-T8li@Bg=zHp@Bj@woi_z{PG$mn}<M
z|8<cDsGfW0wWNRb%9ST$%kNHo_UzgBnElV^RbRSu=gqUcT}R9JeV+U0L%aPM-R*b4
zRp6Z+g^^pcLYMi@o~H8i*Y*AL>i=G^KYMFywznSZ0`=G7Wk?B?;Xvc76UzN(Cc4Yb
z<ks7v;JK;x_qURgk|k@`>b`yZcIWqd)t7JGnzcy7sN}^36BCms*Z2P`J$cpkw6MR;
z#6=q4D(#YvbmZLJq#C^~=Vtobz27#kXP2)ru>W<j|I?LV|EFio@1Lo@Tb!BktGV{V
z-vztN-rjmXf#pVgRCKg)`nfr0=31NQ@A-Jl?)CiNcb;!5d3j0b6vGQ&@Wcw-l_irG
zI=4SNV|@P1%=CFPRY0{tm#B8pWnc5B8;{GK?h@7Z(t880?KcVYd4TG^pU>ydFMNC~
z_1T%3ky|nXXU(1+yf$oe&CgFglE!MF3jO9x+iRd&b9#JT<@xWu(&oz+FHW9cdwYBS
zdD-$i69X5!m8Qq7e;UwYfB)Ip*~N!A)%U!w+F$o~Q}Xe?JRPP5=0>1lM7Rqt^qS?|
znDFh}w=LVZFJHS>SAWk3r>v~3qDP(T%QkM@_{Qc}hjjiPLt!-^kLc*=ZMnCnxps>^
zz2vQbc1z~vPmj9w(;gk^wET2J`SiIr8|!{up8u@+{_nW1MIM17Gwti^o}Hh+|NOqJ
zt+TwAPIB!Qn;LL)w}r^V$ARJD(?Myc_PVu|RZx8V{a#mwFK*}wu>4-7`s-_Jy`!U}
zZ{5BPDmBgTRVcU1Rb_zAM)KC%slv<4JJTT1DJwhs^trd9akXEs+V6@Jab@F^nc>W5
zxny=%)$*^euRlK~o$ur8>-+2L@53FSEHNqN%ZrOMt;_SobRs59n>NkJxO$DGaoUp?
zi~IeyM)?*O7wheQv&qEN^zGK=8eKecHWr{F);Q@%$0V<6{&uArn_07G7oXPMo^q^5
z((=`c#gqO#+&)94TU`H~?e{yArSo<yJmbPp#fX-xPfk#DzI5~E%#F#%mn~eV$StPh
z;q2@TYFBK!T(x%Bu3ff=r_`TW;MiRBYUT20x3brt)m%R35^w6>(+eD%FYT}YuX6Ij
zLTBTI0}Y_7)vK?y^UKfkoozOC>h;IH(&l=PkM(*_dUIo=a`1A$v+4G~Z%$fWWe#%e
zx_!T1filL%jfTf%%VWA0ow)z^?)}u)*Vb0PTspnzR_5~5dwVKV)0r+D4n2i3BxwQa
z%xJp?F4?xtteK4$bX;8VhlA|X=U!d?_ldgwNl=DYbZ&d{I{trE-oBsD?$mrfJJUGb
zuZ>4?(#OZgpMx5Wdb?gMDk&*>(jEUN2~>P7ee*^x{mqSyk^AfZ&U^p(c>j4&*-(DJ
z*4(=Molkalwp*`MXj0<)k6YK*p8fFi_<@BS^8Jj=Y$;DqP2Ksp&)O*INXM1y*Pnmi
z|GySg?$!S}UVny}-)6$BS+h17GroA(m9;fW*P02Q#2FYKIBdziy$uuud-vMDefzfZ
z(@FKs+1J;}6dn=G%*pX_c6OGMmNu^Y^CLv-o#Y>bx)06rPtIAt_o=R~=Cl2BVehqV
zIX5RQTed8w>gCd(*S7DQdjIdca?6iLgoESb=eNt(?O5_?-pgmR^Utl_es5N<w0YWr
z2F9KL|NSohb~AnXwrysvfhouPWPjc~UpK8=f8UNbSK<;MAM1_WQ&Cv=`}X~`+uL$~
zu2+tB4Sce&T~2G|y7G*ioHOG4KD2_`?4FZ6C#$7iSl|e1mVJ7+`~9;mm;FvZJ3AXx
z&QJ1Yd~hHgxdq6uV0KAa*)#L~KhMTFzXa7gZ2WR_IEB@gY}{!0`T2Q$>&@=crdc8T
zexA*Lc1nAF&H1nYCDzpad^&xy3aHio>9G7i1JDkY-Nu{4qc*4c*8Mykziinuwe-2A
zVaxpHMwJDvzi{i;tZuzs8dJSglaKYBRBV^|H1GGdHIbLkrta-_7W`LoJ*L=K&41n;
z&&g^}C(r+ra?_GQh5@x`obqDd?{}x0Sh+vlNbX;%(FN{oTv^O3WugJny>8d5Ro`Pk
zQ=`8@?X{ov|KI;t^?bMEabHZ~QPH3K|9}5qmY&xC<%qEVl70K?=Ffh7|MW87*_+bN
z&f2nNONn#j`>^=<`HIeMpw^D0T}{PJOLmcVr5cN=UaGEvOM+IW+}Tl>nU!_x^UBq$
zwXOLZ;!dEo)If#xWPiJv+qP{3m5qxRD@Sk7^W7Td`~TnHVo>q8ckkXeXXM_3()GOR
zcRN8{MayS1lD|b&f4iA(oO^4FOzoG8k$bC3C#8V8cK`qV{`~&`zxSz6zG;}6n(lnP
zZug}-cjl<v+*O(lY8F3e=6`l2*#B<!`$?+amo8m;<j}&uaN9OBaD~*HU$gkll(^%d
zyns<J&(GQls^*HGoY>2Dso(b7jZMXjFIay~MH$p9SOA(|y><Kccb+-xqqpnrE_>^>
zHR>#=K*_wc#MZeH)Vyh6WIpBh?qlBGuh&5RyyNoqHK1tx_3M|)N#uT(m|n~bm76<@
z)5F$AO)WleyZy`)xySqOB}c9e+g$wI&-q#Xvd4Yadh7Roi@GVf7j&3`-Is+Nva+%}
zpG@-RS+Kudx!=afU9K`kZ^wfsmHHo`!hPfO{PUnz&9!USL|i8>bZ!Tgk)VZ!-s{*F
zs2iiyS{vr`NSo=LlxM4T?~|GN^78WcrQErJBC6uw>_7#I@p+rcpjwOH_DjI6Tel{u
zEOzTX_2%a0&u{bVtrxrXdQIYyu`uwr|64M1=NCrv`!&UB=jP1Ze9lUH`J5uJo0faK
zoCUx26Rx^h7A!}1*O{5d>XX&|{epvoLFa0eonuUXa$@4nzu#`3KDVIX>ieDI@0DdI
z6x)|9T&M^NUbkMUsk3Iy+Iy{g(TPo|r*~-!Zc04d21;;y_uA&>=2kvz6%Psyo-FKd
zW7yl<oBEvb!eL1VcBI1XhCh$z;l}5k>hnATMSk1J8z#AcN-N#yZErSzi~IfX@uzdv
z?^EvXD$UH!_O7n3wz9JNbWA$`$pvTrvr9ZD7oAj{4sr~rhR@B-y}6U&3lnNZ?6slt
z^RpfaLnZC-b!WC@UOsj1<wktHo^{_VKOPnTd?nal)f2P}M+G#BVO;X!!rpJWx3;Xj
zeY>hVJg#!-8<rcV@l=QmFP5Se7)zqoPMdq-@!E)uN>ja5V`F1ihG<1@OghSbPwnlt
zm*30ZZoLkwH1EE?d1q(w_nYBs!~Pa8iM9}Vcz%2K^>tUST*0WtSRM4kLjKO@LJCcX
z?YH+-7TbNEc|PUps?a=#<<WO4pU;*5Ik#JHSBCu*nFwr+jDD}Bo6bA3zc2rBu-@kV
zt5>hq?TJgiy)F0Uix(c%)z!Cd-~Rk$vVYq3b+ML@I+QQnxG|%xt<A*DEbY&ak1Ip8
zQlB$j;709%Xf!gGSQzZNF7UNl(j+6m&-UvT&`6Kv(<#Bb7Or_-ta0ey#hW*0-v9H=
zyqb6E{(rw-OWITvsQJv8aO~KzGxP2DzwyE7RjA(BS)2~)0MDuW^%7Df?mf4w^!29`
z%KcBiUXMRN$FevmK7Ri8`*qf!zHy+t?9_wJ?9=CZ$QK@$Er0UucK&(L0NMUutM_}=
z*49o+d3>xF+|ztA(f!#WZv8W$BI4S$YoIm=D6NR^|8aEE>6hN`cE8`J6R|;|-}c*#
z*-sdMIH0DlT?cP%&Awap#}H$9Y^rv6+N~{_pcD0j!^5Xnet!0J)#`Ox)>G{svD^P}
ze7EQGxh>nbKfmD2e>Xe#^fcYftgKT@r^n68uYDc;^X~h)>7ZQm_3PKl9}nBTwVpX#
zzj<?}`urNB+}zyE{Ct0RclT|1cV}g7o%QeU@8?H^{e7ydt8dO^_>wSn6Ux-VuO?7M
zrvLwwe(~S0*Pn0S|2Oxh<=$(h*JG#0|9us{^X<0VpWbXf|IGgW*@)=q*`Lo@>z|&k
zufK7^zGt97yZ`6x{Wr!n^Hkbp%Od{$TL0e)+yPbjd1blX)b+J*vm>|X#g?ZRG2Gr)
zTP;`dpt0t;_5G8e&;#|bC#(CP+rIzr+clA!)j(zR{r`XOr+<BQwes^>bKd#P9~#jL
z`U~QJ9*OTiF-g_C2;|t^_y6Xp`OTTZt-r_M`TY8S)qLwd-NVy|d9fN)dd#&h-}nC4
zxw+P$fjHay?mZF{@9r)ycbBR?vLW&CB$caKrl2j-UtV6meC5iNWy_YyRKMA%*|q42
z6GN3W>hxDh^Rs8qY(5-duKap6d~?CWLm{iLf;vyiZapU~pU;`R)O-4~x#jmXtv4SB
zWj#NOhb`Y@K^KLTy}5C**Y!)O`rMKrP>r-Eet+Hkt?Bb?&9>hyi}tho`NZ}-sPm%S
zXR*jy*z&;Hna1k-e;n2Sbje%)DQGZdlB)No-uxQn<Fe&*9u_nFLmdHRc;N<$554_=
zKE>4id<rUPFWtH|OVxYYlhyHmvp`K)N#nF7OP8wp`ue6W|K?FzT3Y#T=kt5zdlxST
zjoRLgaEUK}y>@%rt1Bxl|NVGuT>0sV?f(7G=hxe1Ut4oh-R@(jPRtI2lk$1a@msS(
zL0to*$(9H1)ct;&s?Jc*P{?eBT<~~iWoH{_Tv!0AnyzM<x(25F{PfiF>y_Z*Pbby)
zKkq$N8(UmlT=(a(JgBU{@%fE?-jCQl6@{Q29aHhJHTCI5_Fj2=yYn`meL%(Y^!PeU
z`~N@BfBroGzm5L>KSdzH<@4*T9v|=bhgX1kdp;hUwECsCS^m8_vu4c#HDXeiGhFBv
zxtg^#s*DBMf$<-&Mdzo!ytFiOQ;KKU`nb7XODBN_uyu8He}0<2e~#DEN!9Q7nty(F
z_VjZ5zc1Is?%ww1iCikE)O)>V^QNk=uRtSS)os<=^X|@?9#^Hgd~R9PyZ!(FUAb~)
z%3Q91U1w*TKR2HL(+AY3$h^F4>Re_A{fq10Ai05|VPC?}PftM(0BL-4XQ#3H{F)-r
zxHM=m>2MqG?d<nGlE#~IZ*Pk!yP2wb^;--x8_$VTQ?=nkS{swy>;C_~59)&K{B|q5
z_~TLW<v}Z_%;jWY*gFk*IFX?t&!G0#mmV2QqwttQ*Qlr{qp~+Q?05Zd5%xQ=CUWzx
zmFvniyOhM^YYIW*Vw-|rG=qW|=U^bigY)4btFLB(=7<q~V&CO1UuzP)%tzCDarmxh
zv$BmUKRxl8WuiI%&lC02=N9&_UcK6TY0yb-{XG+!`K&ZbOG`Do9`)}F7IBTM`}s6a
ztL6Xwb91eW&)a@~^5wGsdGKHy<AUi1C=Diu{;-uHK_aeNQ@xJ$N>5+5Y?<x+UAuN|
z`pi((vo-trvnj!Tn%2w>apzDP!3XLL>i_-e|Kk@Z0t%|{&c5%rWnNykW&8H@v$ITJ
zzIbus*Vos<Yr}#?T;2L)c3yY*weh%IbeWz*rq)!iSFc|eKWr6GyS66s=bLo<=rSRO
zy%SKw_wRzBl{HVwyB2wbhhMK-VYwma{ytk-Sy^aH1vGdDs*GF%Q(jzHn3<7rVtxJJ
z*PD!ACWB-M4y*lYxOVNDPUI#P?eKLz;o;#(rC=SXSGVai!wXf^HpYe3rDbJlN4rFK
zzFamN)G?8KvOF3jbZt#!<hGp1RadjR7J*U|sCf?>$XmI3_31s8pNp=BhEJXACBF$Y
zZBhIEZf0)oS<rRKpn3%qDXii#6V}%})qZ(@fBnr)hA#>7e>HRwX@G&jZc^;-vZtUP
zk@0z(;IdPU$%or`f4=mupXIH;*90_Jzw`OL*`T^heO^V<zu)!$-={vm*d9}UxAf=L
z^>tHk=k3-#Z}&Ur-{;zeTeohte81=OrkbChgt%XJ^I5;y04m@>(RHj>y7=qW@N|&j
zufq4w@~{7Od8Tc3*{xf*PJt$aP{)Qg%>VlSzWwvL<#AS4R;T=4PQ6$8d@iUfzif8i
zshjEZ=la*a3I=s~KH2{}{{O`Ly6?MVicYG6YTM7xX6HXUsXiYxvKLflRO^wQoediQ
z+*$nm*@wgY_tXCt&;K10SMjh_=+py#d?jD{-(O!-)tN3F{-SM-9AXa~!bMz<^+-<E
zjovn8?j>!|F3`Di=So_a<w!|MZAv)U1RC>uvAAE)ns-y>=Vx;Y4spKUeQ$mI{x>%^
zE|%_A0FB>*hV4KpWOev@zokJZCDZ3je7$bBUi`mL(}P!r6usa39Xu=dWRmx$vbVQ3
zO=f)Ih?-zZnpdyer4=4mnR?Fp{hl6K>uqo5#DR*ul`B`?Ebe~);9xUkz=YLv(ym>*
zY`)(qe!u(P#fuYv{rZ)svq(RBUrpsSoybYQ-|x2vO<IBGilXy&f`@oFBp&{D%R2d3
zPtNUay3=FJB0aY<d<j8sJAsl};^DTZH<J6$PSFeo&D&hLcI_Q#;7TWE$A%?`=DqGU
zzXuv5292TJyEo7J-45m5Wp7Ujy32rOAxun6KqCX7N?~b`ruB5YWjl9TZogCHopxr%
zM9{eZN%?=Vev^)Ni-QL2PV$=H2}o0_J@Mt`W#ghJCt?bZie_eJ{yf0!530D&%rad)
z`xV0rU2J18-xJvucZ0HexcQYYd2{E^{dqROZu9kkU$58ipLejCJ^fG%XJ$^$nLj^2
zpFX#w|Hjtr@N-tL*Q|-#YXus%npgMhC1`FhdVAhkP&4$hpSAAy`}Or%Sy`w2mhxA8
zx#(`3dTPohV}=(`Q6uTX>$~OmYa=%#ILcMOF>L-*vO8<*EbI4sjJ>Dpojukoy%{!m
z|NqZtP<2qhf?0!sp^6K2`0k6=+_`f>BS)97U7Pmp8)&FG<@L3-E5lZUa<!k$$0J*|
zZ=XJwbHn|!^X>mD?++GnUAOn!t-k@x2O7bvuo0=(_SUzzw=dtjw=exc&D~w4H@9Yo
zuezGm#wR<=bF$jfl`A!UeSK#dBszhXl9w5=@5o-aQw`J%T;e(T(@FojO>bm=ZSY$9
zY2tm&E~VJm*xw7;8kk#Ai`KkPpz#EE`(J_cs$Q)GU4>q`ej}fA<L^}~S9(qgS$(xf
z#<J-AhRWdJ;6B@LH$+?mixg{pk)|E)#O*%`sUaBt>7XaNO{u4g{{4KOerHGFOq<Fg
zG2N&s&z?OCS$$O}exD6!NC?!h`~TDafBMapw&(8bEC#iWOiWEvpPZPO`rN@R_tune
z-@bubw6e0Yk^Adv!3Ar@d1s*o)^BcY)dqFk-TLL`KJK^Q_eO@H$`Caw?mk#D+3%Di
zyX=&0+qQvnN4tDo1+>-h^r(3JnIoOT#g~1}mo8np^i9YEWzfinm6g>cNW`s)-mV8a
zkF9Ibi3<yzFJHJYA^!ib>#6BQ4XeXeOIj2pfJQe!HBIVsh6~+jBcd<3udR=tKhroJ
zG$i)-*H`aJC1qu5o*>8WEPkGLu!%MGVSH*H0|VbmPZ!4!wQpXt&GY?yeSPKXemvY1
z{NgYumci4~cM6<AjVRE>{=Mq=XODCWZ_d5FZB4|+MQ>bwH7wFFN;@+n=jNuRZ$ucX
zcGjgLcljB<ur{;tdj0?Rck-Xah|&WMjFoS<UjMd+U*67Uwpp&0_WJPEVXITs9YD=v
zykq+qrI!ptl_pwXCtwWLf~H&E@B5tx>PBQ;Ss}#T$p3n7`Ms07N?$|67*tF2n%_II
zuw4$6rk_so*7J0Bb_R7&Z{51JsraR{T>YPqph2ADa@9G@d}dC%xY+&uXK9@-C2ny&
zos|L&_ZF<Mdc=vyGYkp)cmI4gyBO5qetfJ~(jdVB)C8PU`|ak+wQGF?ML;v#b>BA6
zfBL9fU(b4L_)VmK{7kdlsGF8w1h;P8`tr@2GdDISgQ6Xj*%mHTbeFF!xtaN;aH`i+
z=I<h|6W6U<m$!m(!FJTjFkljBk-_x+e^NoyBiAC+Q(s+KnX3NP3RG-^M*T1Q+uI&)
z=hwGxw_6mna>=q~YU*<eoTQ|sK~^0*b_}$lWG)-ShjjEIBb$#$gjcR#e|}-R+^@!J
z^W0lgOtY^oS-Nzo^r@=#@WxrQT^`O6g>O<G^7eIq+ILNqVpyOK+Ea-Lw+-{JT)FaO
z-R^f@#l^*wz$Mn|)u)^J?Pdh~+m^21>pe}!)7#s7*REZsJl>jOZMQAiyxDmF&$Id8
zq`d0?e!Xs7@!^5b3<Jg9-d@lY&&`<(4Dwx%ixF0WCJ+Bt<tJ>7I(u%eHSf&-l64=u
z<3Y3OJOBN9ZJc&yhKZTkv*Y&v3b*CmjVhC>y#dO~ox<v%@#r&~Qcr)X|9AfX$@O(#
zSIgA@`3PPc^7noH{x>eaCV-~s;(uM5Zj^Il!<X0B^-WDpf7dWP=tuRm!}^PN?#uzr
zHLu_ID+`pLv$oCx<<BD>f|k$c6ocyhJ)h56r>0*zUQ$-JZ1G}c^SdR%=j?vJsd*JV
z|J0Y4mp_AsrR)Fyn`u#)bhGn|AZT)~{&)U=-Pz{(=g!PD22~n=uEzfj1q~hEx^)ZW
z(w*;iy#}|V&}J$bYC=fqY8Elv+E)u2HG<YOpaKhZxYoqf6jV)sh6BJuw#)i=d^{#?
zoOq~Z%hs)_x3}ej<_`7te!1i`+e}w~-;X3v+gG{YW)o;w$O1Kgf63aqbt`C)2{da4
z9!UnZ9RGY-Zhsa$1yT8YE~t%n>f93sP@t=LZjCy7VxqEf?XNGk%+EpDw`-Bc&I$WK
z=kf0RcuYDtICyg1-+u;nH*VgXsUm4xRr2iI+}W($VxS~_#)qK_&HmpPyY=_YSU#^x
z%k$H-+4*XoW_fpJEOc&vw>AIrGT*!RuFVGRk&E0_k_l=kU0of%JZR;U9^-Q-O0UOG
z*RTJ1dS!?fXtLKh|K1)@^D}aHS?<k~G7g~T=E=$G%U7<{RCe#vv1b1!VUiK>>-+op
zDw0+u8EiZf6RyWq=br!d;o;%Gdl?@vi(+(n4>Ya_TKT3}_*4Cz3xDJP9{;><-MV+D
zUQeB-A3qN?PVn#d`}3f_*Qb-}%a<+%HQMeJYk#dT1C5q#I<0rw`u(0@CtZi{StLy7
zyf}%vnPS6yowz+a-n1~ELv3=Mys<I)|BHXZein+G)6TwHX5|6u!V4<9f#%7e<(=W>
z<^JbEQ&O|@_gRAa!B@lM=Waf4XYJh1hg4!toy+OK|D3G^IR{tu!n>u+_pU!XJNxs@
z^EGO#!`2!#`1Nl{J3H&or|J7ald9*eUa#?)Yqj-_3P#K_$O|*SDA}$)uR`hT*RPge
zE;!p4yhom-k!08#x*v6@?ZMwOXsxFUpFzFh^1G$svu4kptOA;ZiH(hwtNCznPSvZG
z)o<UvcyU5?dQ1|7Y=b@OY8wXIYp|77C8tbMPE62=+hg(gSg*EqtKFigweLQIR`9)i
z^-60cN5j2!K`4t081~G+ySu#pN&iCcU6*fd&Hnz&uHeCen39XGppjEgR|bZ9IkbGl
z1!`5-e!n|CeO~3VHzGHZFD>!>d3yh!(=qjbzy5riUmsn@$8cc&S(Gj|!(J!QeA2zj
z=SvqaUi?Pn#$)mQKfwK(*X#G&B_HeYOioS)4f=pi`AS{R$neJ#ZM=^`-Yrl>(m2g$
zTh7g(GOjnElJD8GXP}i0<@amLL3MQbyF1`jFrd{dpt>8h00%UmyeZhSVegMe-IcFa
zE}x_VI>;D2rYmVx@*?iHS?;YXZ*v*G*tu?vT02da5jl0pyCK%)SS26t)3s*5cNsK7
z0qt>vhL0yGIvXV)>)Enp%aWBVSH7{~GXPJ$z4^KZ6!dTG?ZE@(HVjpYsN;nfvTgqT
zcr0m_69H<N`ph&^UF_cPmz(<*yxi_kE4Q~+3v49+KqK>ao<Dl=`)ut0zV!dxs$Zj6
zey=hewCHh@v84kz=ddvF8K5lvV_0x~MTnOCj^l6lO?kL>`@K__mU?eaIXMZ`(U|I`
znm(t{Eh;MN(^LI=%c)+f-|toDKRY{nI;g7*DOwm9-k(H`!vpg(eqxSFfd-6<pPk{6
zHp`j+xBO0_J7`e>sMb-v!o*Os0j){L@FfhCTTe_>E<P$64jOh$KHm3t@o#^Nhb_=<
z6@#4>YEUu!>6EMea?xj|(b6|O3=RFhOHl^P7=CDgvPsQL@Ay+25)WTmAHV;~l`C&P
zH@-{yA;VyC0j)>PV7Dgq^t7jcKA%6oqwuj&@v}2JQCl?5o;|xVY<1+mno3Y-yZD^t
z@;5$w37?;z|9|4Wi0j1c^?S?guP`vw{K4$<G1&D?_OsGtmn{L!!hy!*Wa@rAge~w9
zkFPNlR`)yOYkqgiv}w~e1zS3VYE1<XHobiH>K4B#1B3kj{(te-$O$iC(%0A5)1RH0
zxpL)7&;50OC#lSxJJ%D`cuaqHXD6tOH?vdbLD~Cze<#|voo8&gcLX)2_8ud!l)_ye
zv@qaK`Tg3;XEW1J`7tv5xPdw~v*5afby*H*In?vtKR!M#z8+it^ltfmP*VrA-Y9Uf
z+tdh;cu@8NEoOZA;)RAaE5n22WRywzhPdQkUtWSjwe0P!sVX~vy;==k`S#+%Lh!5r
zsI7VX{=c%5Q@@BJFGOTuke|IMYHir*KIBkou)jLXH2c%(_<u&Grlyv!*K9T_eRXBi
z<QL9S(b2_Er-r9}eRUNyGIG<BfuY_Et=!7+xB2J-8m)V=u)XfVJ>S`8sb^=IW@cu-
zY%}s8Vo@I>gB|#sErg4{WDqmKJ!###bw)uio3*B%Vt=REbtqqm;e{!B;Z}d9esBH8
zsI_U&&&_44dMQ};{$6Yu6T^YyubTU>qm)Su3=8~G2R#`W7#xI9J<Cu(4SNfcp{g4#
zLmpr!Fpc@*_B7q-X`j#A+k?jEKuyAoi;GOm&6h{5P5b%jDX2(3XZd{2CSyhhyDeBE
z?Rzk2NcL#l`Bhh6*`5FQ8Pd8~+;9DI$>gF7j_jbdzqhyLo_^RaKQDB3SSn~H?Bh{!
z<HAQr?vz~i&CJZyv=(J};EXztz+ig|yx6wk`_{U@zwT5#?uBHPdWq|=-n{Xd)FWqW
mRs8(i*(O$Q&?w2?WB=KcxNgk+Zgx!{6oH<uelF{r5}E)FA|68k
literal 0
HcmV?d00001
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-matthews_corrcoef-20160908-100031.png b/Code/MonoMutliViewClassifiers/Results/Fake-matthews_corrcoef-20160908-100031.png
new file mode 100644
index 0000000000000000000000000000000000000000..fd927a423dfdf3be17d92144f940a13da1e7b260
GIT binary patch
literal 160552
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@vh-1h4wU;qEFe>=HF#p#U8g&9dJ6rTxv_R-#A
zC}tY^^2MdyQF&VyR^8X|s*MU3T;&ybBqk~BO2poa)0DC@JUbV9bo~9>JZJvnIdd(8
z_S?x{zq)$swR_p?|K6)!yR~}j`^^jw7=_RWcVOW)$-{vi#zv)W9GI+7MPNJ!Ax`v>
zA*fUXJ5J*~l+Xu{pn4cSFyJzd!Bb@cGfWvOEvJCXIE7A@5>&M?-T`Ku#;Ht19}k0R
zs%XGvT!RYEQ01S1%eV<HxI%RZMUq(6*H@~u&n`1gKbKM(KEcauwy*Cjlap7nbMEd6
zHJk0b*sb@}mDe^ezrDY|{@K~ts~sAdHr>ow6}EQP-giejg{$7}eE#J5bM@J0m+h(i
z>^14o;lrt$Z*IxGz0D;4d*L4DnM>2p&(n(8u_5p7u2g;R)4!()7W%y2D!;s=gX3n7
z+1c6V`p&m|`}(GxO$(lHS8KH8?*844%<NkE_x9|n`B@ZJ{xpAS;9|E;H)Z~dcdwC|
zezNdt{ElyLx8GltcX!vR$?E+%X0zwj|NFV-UC^}Ct4vK46dY8&r`5c<?&}wneD{@g
zdwoAF_8I)G{$(q}cojN1X0vn5X5YDUr{vWY&C`#i%=2>W&Gw#bDSm#=chlS_lMe74
zo{%W<@)h&E7)?*Rr?Q^6zP`SGb(yd9+uPgyV|SN@R#fa@<B?GC+*SU5-mR_K%S&Hh
zTbX-%8y7$S^$QD~Ra1RpHov;5V*Xww{r$bYv+V2lweiVn>FcjA`TBJJr#icr-)Dv_
zN)J;x`2Y9)|6wsPa}FIoEPvZ{K1<m9$gKPOd#d6md*_+*JeHr_FmGO=kgV+5Z*OmF
zTUkZb{{9BCdsoTJNt}CKy#CC6UKE~u{c8C+?e%+-Ds5msJTUo)?P_ZnkKv!Cjg3vo
z_jj>pXPJ60cJD7+WncKHWn13eEPFj=m8m}*lQ=FdE_-{+s_e~-PtVWKzZ(1V_OE}x
z-<Q6;r26;!{{L5Zzu)&dp#0SpO<C(QpTEDqU%#?4SoYPuipRXAZ*PSj?H2d{ytQA}
zS}i~Sy~+IfaxZ6wxA97=#mC22FRH6bagmwNa^C*`o>x~^D%;!dU-RzNe|-_H5Rbi8
zUoU-mdHL%(>-Q@%E-s3^yLA8BH8Jdyez*O6)U99g`PtdyHx{d3KGrKODlWdfQ&@df
z@$++$cV++hM)rPPvak49kL2Qo&h4k}-~V4&CJOVd!r?#0b?>BL+&{V?t4y=5T$p27
zT=M>&?ebqUjnhvV@NCV!ZRWf#eOB78S0B$$yYu_u%a<z;9B_DgcJ_C}uP;s(zq?~8
z+4j)L@W-8<#gm?F(#yZMhl_`2%JSvuv)0Q>NX$^}-28H8c%Quex)m!lO5fdyytz5u
zzdYVZsn5S@j%BfyfkA*}@v}3p)}`!N6SchR+nbfv<?k|%^+-k*{Z)4jTgQBIue58o
zSZG4RgXCAf*SyYKcxLG`2|>KZC91XLzyXJyJ9pZy%VUE1B}D^KR2@jZx<1}Mc1MBZ
z>aev%8vCoiuX}cG?&@8ouUFOl{G@l@w%|bn8=uUI1q&3Oo}TU>7Z=CH!*k_!{{FQ$
zZbY;vOPlAdv8(;%F$q!zsLejBW^Qgi*Rt46)oaRy6@iOYJbR@~i&m7U{`&HARm{#!
zd-m)J*-?=A_5J<$>+52RE8pxae*Wdx>-DQcRtA0g@+IWopPyIP#ah3;z5V>d9g@ar
zC(<@&URx8%_f$|&aMR74Pai*CoNHY!^D685I^F#I{G&&Y-aM_OtbBD#X0WJckjuPz
z^FDq59=_PEcTU+<zjKRRyRU4?46e@co}#f(Jg&m=_xJbZ7J7DeammMe0-v6mI#t=7
z@8_>ys~nrzqV`m544!@Q;>Arjb6#Cu-VchBb91d%2P||dDlWdfE%&y{-TwWvXU~3j
zXXoO;#cnHOb{2j5@@0$tewX;#uT!PW^VZl@emZgbw6~~M$c1+Kx)ncu{1CZ&zm;3u
zB<qUC)z#ttb#-;8=GpH4^Y`!7wbACX)@5fN-k7NDzAEM9BqN@~|7?W*&oa-Sr;_>l
z+S*MwbH06lk*MxB=R&vsz7>mHyKk+(ygA)}u0`RYmp49qD7cwpmV0}fulF>az_+)y
zg8TuBpV-}HSATwf9$Zq-f4V1qX2$t>wy!QMY_@GX+AV&)fswi7;UU)FhMnj4hOdt^
z^1W=wcK6O5lk#^lH*?HPv#y+Y_)os?>0!glE9dS1gW`3COQ#ShRu($7URmJC>^s}+
z>_dy$XP2q@&a#+0f5L<X=k0#`l)kz$asB%BMNdvF%(}Yj<z;{SQm>?%AAfuM`ogB`
z#fB_!V63dHT$y%uR@C0At%pCJJZpW@a}Kvv>8mME3hn=VXr5R3O!Dc;$?ld#PXZRZ
z^=`?&uDAU0q^`%)<Lg#tU0rqZ_U-6aF40S%aNri#yYc++m$+!J>NRVhacOtH4|#OM
z=gZ@M`&HT3*L^ErnsBgbRovcPY`juST3T9EZr6al0xI_6_tkv*_%ZPBudiDZ53`+q
z9BdS?`t7y>Pwvf4M-%5snr4M`JzMDV`uh6t*=D(5M^{y?DtURS>iOLAlCQ5qm+xa`
zVOf!Ka?-B4zq{^Lz1E$o5$JStQ)=;y(^*$nEp2FEI6KeQI<(O1^{)w&KBhkX^Ye32
zadGh1S66lWGw<%&nqxM*PtG<=zq_L&pq)=PWL1b}Wp(xG>(|4-zPfsOdVJl?N56fu
zWN+-R-ygL#YiZ2RqLbIJho7Boe*N9u-MY7<_SNjH`toAorqt7?jvsfov$I<jxVUYZ
z&&)?AaYFYQFPn%82qe_&dri~Hv_F=mGke*}%*)GGhOLb{HPd)`O-)V6>M&hU{G}?D
zKZ^PFe183_r_<xN)n|vSi3k)F6x8gSI%SvP%u7F&O&>o=>^!e$V-vG1^VZ|9FXl|X
z_O<3<6Dt=VU)Z@hma_A_gVx3DT(r=+eU(!y*Qama!rtB4d38;s@$}-eTeGi!x#%tr
zvRW%_&5TXy=hro{a<7WrUFNwjT{G5MIQ2;J^mp~r`+q*04Jrk<Z{Pmu>FMRSwq|F4
zd2#XNyxG&L@9wMJeQR6p>ZGGxCof+PuB)qC6}-Ifa>U+>kBjcr{mz}L9qwmmX9udd
zPfgWces6E}>n|@ae|sz^`#S8tCI9~N&eV0+{!gj#R`q&WZUigx9Ndb}zk<(kHq=jB
z7rQ&_!UD%%e?FfVm6FQRkKdTosu#O!N#WyTFMoV|tapB{W%06U`tj@9c%@fWetrh3
zp+OCpPGR+|ySqwnZBFkmdU8V1^VQwm+dn-yxmZ*?Y(?$wZ(LkllT;+z7T(!eoPA+|
zBPi0g<=tHsx3@}DLE%8${}l(D*<atz-yeE=Tkh3OsouHw_Cy+|pS!Yt|G!ne(&kn&
z)ejCZZq2ypv~lCctecyb9y)YLL|Az7)6>&e$L*~G85gxROVu;$)|Qnjnp#?3wZFe@
z-7Y99s_MC`^!2o|x3`wE@k)8@n%_|T-~gj(&W#KEtUvWg8k-~>VEFm-r>2QX$j{Hu
zuOICeFa7Z$(bdJ}#nkXP&x^$`udbf{?Ck92OsrfQIyyeATp|~4Zcg7?`8jQ>cKEq@
zH_D%%lLfiz_O{&MpP!z7{q=hN>t|<YM{P>!v?_nMM!xRH!BnG*ox<uNyUTK?>PCm%
z-CcftZS?jj+TnWbGum5QGw<)K&APj5>%8iBmZCZl7wYQf+trE)3NB1K+O^WTo$u6K
z>+NOl@2wS7cFVZD%=gxYMCVDKn<s6_y=~SjZSL1AZ64OnC;Q~_<He7U_h-Mnw6v?I
z=Sung+T~tTwLEvt_o(^$D%5wDiKnBZW7hqBd-u*gQhxH(y}i|-bouw|^>{8`-q2Pq
z(Jz<%?KA)V`5Cn_sddq!MKVIFyr34^uP>MVw-!D1YHe#<6}Z?96uDx$QA-ZD^S{2Z
z(D~Dc4<4U(bsBw+JU7oa`tR@W)0Zz_?&Rzox+cO<*1j%gbK2QUr>1IeO+POusv8xu
zv-o*fMa2$2S*s<WL=n5Y?AwmewNarDA3n6I{k26&N$JXpK;>$qsz>*QlRvGvx;lJy
z@N&Pd{{HaQVQaq};?~zNGYbP1i*~<WDDz4fD4e`;XK!`*dAr|h_Wk`94NCuaH%M3I
z!`1@qDxJK1`Es-Tduz<^RXE?T|G)Ryxw)@P?!COcJal!K?o_Q%Fa3Q#7U{+BTjSa-
zwzBs3w_7_37fYGtXlVYdRJRNa3<MQZ1qB<P8diUQclE}`<k0PTv0q<b_fJ1J=i($)
z?<;E}jb*J$JW@|h*(jeadc5%QvCI<_6i>}IUtjh8-P)L)MVW`&c)2(^LAAi?;-Koc
zTaH<++^MA5|Lx~-`TCHzx3;Ekz9}LlwMt0U>&30D*;a**T9*0EUBz$zC*a<_dndPP
zd#d}-3z=(G8nUw}wYup6sM_9DnqB+#YWS-g8y6q`s5y7N&~c}ViXBW$OjlNi>sL#6
zCM&9bzHnlqvT4y14^Yhq3Lh>pofU`M`LqB0_!zajY;D=wTdMN%^6e2vj~`#{IazI2
z(bKM|Z8@Ndd!<XK5Z`w}A)!UA++r_YTwJ^=V4>3{aM^w7W9m|miAq`b_Utsvxv@am
zz3;`#<@3u{{Qvv?{?@|BZdcbtUVdm7SNk<IbWKDcue8~e`Sa)h`}5g<ZRBP*+o~@Y
z^!NW+G*Q`It@?b}zTfYxP4n-?l)t+Z7!fhUYpT{#=XSo8fs5Vr>Lr{fweiVj$^ZZN
z@87PfudB>*Z!KwLX3x66ua@tzs*O#|>1n!`A0BQuEqLJY`_HEjHp!;{c9*|jw|?I*
zucO`K;rr|Urbx6+(~Vvh9$y=3UH<Nhczn&n62F|BHBL@WQ*5itO5fZFEG#SpHEe!;
zd8uq}ZvOSfMdh0_mZbSCOZ(^Xx=L0+V8MqE1-Umjxkhi#3q3#2_U-+q&U*jXRd#iM
zDsu1a2+X~`Ep)P)Z_Gb|Ba6??v0U87EB)%sOygDY`}aj{&s)3y-!JdgVQYg{hpjb9
zKE~6Ye>C}cU*?Yw53_D;SU9itTO_DjPd_&&FePQlwRN$pLsy5bbnO=7yYBH;YL?*n
z*h$~s-d;XUH(JZgER0vmBp@PUM&7+WD;K->XFWMFQOd5SV$$>F-{P*Xjb5HUzcy^&
zzI|N0yi@n@-w#U7Agf+oSy}ad?{}5E|Ie+9-oDOnuGP|KXJ>1hn1n3L)UvXQnmBPH
zC<XnEtq2LaZ^^&@@490NUi+5{Eq!7w39B0vf@i>(4E>FX5@{Qgj{00SIXgYB>g1OX
z9}LdVwN783e{<8)nbzfbpRcWre)i$vVc*$j)6UJczP_;6IQ`s=@9*vwXH|cDb8}gu
z#IqfRk7Z6ND=Ecno2+4Db7#xVoM+e8M#o<J{_5&!6Q090uU0NUvpN0zt<%CnLTA``
zrDmATK6__(`TD(o-re1uwlZj`kG{Ts@$YYM`Ep}-6de5W{kwU$h-T8U<Hv8Go?rD!
zb92B#C%)rinn6c$uC1B*^4+_<ec$g@fBPh=9X6vaamHfz{%zAk*T>!c^5u(3a#GTq
zU;m%auiv$2y}R#xySpYlhk5w;%+|;6e-}{x{+{jU@AvDs|Nm+K|7U-uMBC3do6pbU
z<mCMJ$$PrqOh!h=WoOfj%irEg)wi$xwIx%cEpzkDGY=29@7`0l*sa&+u)!Iv&{Z?0
z>&KU^ns1!mmnqS9bD=Z4v7X+!g?Ud-Oa$q+|M^6?z38yPnPa`u)>C44m7LsD__!_j
zcRRnlS#3?t8MEA57E{!}?Ja+QPw)5M)YD>@4S0&5oS4Y>^y#Uo#<^y*e_jobx13V{
z_v`g#i4ti)KRuN_b@=dM-@^tz@$vDWPfS$iE7jlgp$X)&qut`W-yB|S^f~h1r_=gr
z+j4H6IdH(?^PyI5zTEs<TTYe~7aPy7|5w@mY00q#p?`cXf4$Mu*=bn(^i*ov`FVFU
zYi2HcX)u4rve)Gg{(ir2&U@H^oloY4!Sp-3%g?{Ly?s5%juR(5s(&7S|DIjG=D~$)
zzrMcqJ#26$eO{&7(eHDn?Em-cbV+%+xpw%vH=FDX<IHBConxLq&pGx{asAt^*JVz{
z9{u>_<m6@T?d_2(0u-0eD1CeDYF+P_IBVOD+h%F6+0pfL|G%&Lm(w=S)DB-)Vr6G$
zX6E|V?#}Y^`?c2>=KcTo7o>Hjd462`#%Y0{uP(0LFst1x_g0EjTjI6V;pg|1y`ANJ
z_s-5@kfXNWt2({Vrm$vv#>GQ>DnBoK`qzJ+%}r2pys|P_x4$x?>RS7hK7DOa?<G^B
z&9dS{!tz~(kB`kXn|=1rm&^XLr~K#HyexS$*Sh@7GT+&=Zf;67K0n|7eZch<fy$>h
zetcmQwk;=e`uqFp^J|j!KX>168}s$JiSOq0^YcIvzyJTg>h@1@d#ga^_4M_XRnA-e
zPcLG_0TZ6XYXTRy9p1dZ^7FFD#csUQv%{0><LiE=wr{NY@*?o^-Me>de!W~C8}~nO
zrR3zyx%O+0c?M1TCFb+G>fPhV$^Ska=3n{B{cszvuerJT=hy4^muc*;`npO|L?orE
zx_Y*_e%zMn@w>~;J}tkuv-tTLCD*PQqFNyZ8vdt2g^sPA-95X1;(9SN-jp&kF`W@o
z^|F|<^jjP#VSobO{@;(qmo53XZ!UW3b=iRDbNv5b(=Qj6zq?cTBW;V+YtOYm*B#4<
z+P8GlZ$Hr5J#f)+LdP?o8NOg{0_U%<ub1yGf1ma3&CN+mUcATv6{UA~mrq~5eEHML
zqg|rKJ0~ZskJ}4s9<7bvZ+G~2mPFgV`v0{*fB(LHI>&5w)%SP0mrcI@{eJ)U>G1V&
zYbUGwzv?x=7qGYLtIRFUm>nDLRX&&f`|tPrZ?fl9SAwdxl9!YIec%7zbJzaUk6XFL
zuPk(C4_zB|_2G?PY4cMCJipJq?7VaL?$c+_o?ZD4N(?XLmix?9I&5H4`>Uiqwn+H>
z{(yx}-|WxNvyC>J?JKPAS8}7!rvBd_DZ``|pUYRC&#!-1((Ba9b+dd<$x#EIUOC&S
z%1=)USIxGm++<^8W0HMMC-wBSvkUWne0T_I8SMM>>2%6_<NAMpPEAy953XG5HTB98
zPhn7dmy?t8<hIFE-tYVEXaE1t=2zF&uGWj)WpM>mU4gnnpuVT9b(zIn>w*Uk%VXPq
ze|`P@%RE(8<M~h1=hrR+h3lmyo}dvy=i8u$VMfM^uyrvj_y7B)?ON-*wxfe1c7I*$
z`hCAvUH&oY-TS6FB9~3R*8l%r|LODR%SSqeWuFNhHZVy%#Nt`>Q_uG6m0&5eoEgrM
z-D0{Sdn!JP*w214$GY5)lauq)=g;1sc2s?RW%<_X_Huvuox680U!fmg_j9R`kkFT7
z()kugbI!~#)O$YZ3Md2n<*oD34bSdczdnD}tq)(nUhNQ6mN~U5boH{lySp^a%)(Aj
z)7?Bh{YuT$p!qeQI(ZIX=#ey@Vw~>RzDqp5CeYE*aoY9S28m63_UzHQtrxRngU{tF
zGmX=Ou1w#uj$hJn->vQW`tkAcwLhOuH}bu_Fz?-+ou58@D3~=_{_e-vUHj+l`*tgP
zSM~RGhkwnMx?lT!Zr#tP;=l9G@>jpzdL7i;oc?_0tA3TeKcCGu@-=qeSD1Ewp6+1-
zle9Au?dk8IK3%#o`FNC_a(;fk?+k;3i8|Bu<Kq++6+we}dH43rd}OC$u6EhDK4r<5
zHP8S4{vQ7H)YRabwV>wK?QOYS+}y#(`($Nb6+Jz*bfU8Rt8Z^_N9`(Exz{HB+#J3A
zpSwgf7xBqjy;wfK?$XW8>2IHAMmifm+POYvXVArq7qhOfn`>46ZqB0Dc3NA%&$<yG
z{(jc#vKZOt@7}%pG~00RrC+*JuaqM?b7_Srow<2YTeDUME%lmZTfMD~Uw++r`~NY^
zGFQd#uk)N&{{3C7?`$*QZZX|U7Z<yieti{scX#>uxcYZ@cKW=`|N83c+*4hm+G?Jl
z#^K(a>+51CExEkhKl{mviGI&z?CWBdWxl$xF*)n%s;NtUbG{H16zuBi3Od>)Dk>_P
z>ThIU`f7^ZzaPn<J_abEo8{lrk(Zahx+?Vay|nFlcfWkQoxj?tmFv}|rQK3yIV&bi
z5O{iizP;=Bvd_<aWi5+bTDisj%pzYM>y`fX^?H2hmW;run!(3b?(>|iHfc#SJHOS{
z(3L^1a&mH>+u}E;`7YlSy*=;chlhu?0v0rYEM8u9*<`A1b(ySnna;^=!fWI9MqOU!
zd->nr-=f08i+7j5zxA5uaDb0bkMpFmELn>Jhf9A|l)`73WG<R(UH<C9!Dc?rgto*b
zKWsNox_Q3n`@6f7mgq)r+u_3n>TiRR`Dy+AD?o!V-^{mudvjCyu)&*T^{t?!6}zt{
zvazx8*MnyMIj?*#PnkY_`ss2_4UH2|`{PBl!_LS}|MKhed3#mOn@^0w-*@iby_-u^
zYs#YUPcAHUp0s4b1cBwd9v$so9kDT~tFO=R`qs<Bucw?5)x5Z~INf)iP2}5KTZ7yA
zWI>&e)|QqPDJLhb%v&9`HA_!eP}($W$<E^EAlJXTxY)hze7NSu>hF1#6%{W)l|iJu
zy!?9a>3T0uP1WXmKW+K)<)E>Ml-r%1vkVOlPkvLjeeLYlqwnwUU;65b=luGAJFl&e
z&!4Z(Cu6Z-v3tLkj?Nj)k6*Umue&_MFnLSnWi`-n=Jve1o32Z?O?;N$b)<BGV>6py
zso88_P;qr~vijUtp!R6t<71g`Z*8@z{ItZGDXZ$&=MBy5{HM}3uS`7L=2r^pD9oNc
z`*eE9G9St1@}?7Iu50AyzgJm5_mbhvc|Vnvm!{j6f3=-F<;eTvtHamt`ct>3;^U&f
zzdt5|n)XjlPTpGmJuh}oMc~JeANl@Tl)szPC8n#TnVX&AX7l~-?(*f?Z~dmss(yQI
z?QBq=0F)()pP$RRvty%^laoxHkJqmM=YIeGoqcA8;jR7k`)_T@Ts&cd04po2<)02W
zH?Q;CL$dB`gDW!z28M<&Nb_?koppbIWj;927_~XAS4l}JWN+2il*wt<rLUHN#w9{l
z27$WVT;h6b-rU^mJqeU5j~+dm>J?x7{M_4+XYcC%+i$knlU$a>^m3A_x6W-N9%u8s
zI~)F67Mg!vu|k7a#v&jvFi<OM%L=dQdTW>Y&d$2Cqwv<Q($%ZN*RKP0ziy__FZJk>
zG|8C2C87ZyatvPPbMeW^$*On#SN(jkxIad%$4<x0ENs%8NkuU`tG=#MiF|iqPQ<($
z&koDoeR@$eyz_qex|oTXvp^FbZoN{emFreNIqD8dX3cE8LHG7lUfok!EUF(DbMM|g
zBOYgH&+GDEzSzB0p>2sOlFFA&VvlJoeLr*RnYwA6@4x@}_*nOL?U%pjJXY?s4;T7f
z|L4a?mHVpU);o4rnO*w({PTzYgeC5e@{VlJzwh^H$C6)@CVf}=cr*I%1*e5htvbRN
zf~($sIbx++?CN!8O=Pfj*&FbP@lx;US^xh0H1Z8jJw5H}@Av!PZ&_Rzv?giljq68d
zq&=yb8dU%9=W-z-p-Fr1^-7z|2wmV7)0vTTyOZ;#=i5p1G(ai4cYWO6s?29+X3nxM
zUuS#MR7uIHEpbKq`FVWD=UJ6{nPy+Ra&>ih=>EFetvNS?_U+pT8r^<*dAVu%yE`W9
z**jl56um#Y`1zF;fzB5%UR)KrdKzfbVNd1fQ+MyiZrr$WmPuw%Tg~H`y;WE5y<2?e
z&Ydat^>v_j{Yt%+=_*Tedc9uG@Hziy;>1gv=PfUj^WO8ESK2J&a2u~)zah`zhx4ZE
zMlb7=wLW$FwD;NB=HV-YmQGQ2=K~FA-`f*;ds}XCMf#;pZD~h}{omixUHUI>e)T)c
zwNYEWgw=d5%&{y6^)qKKTlwnh>eu`K|6M=JG+XWEzjLpuzrDHm`~Cj)Cr)_O{(igN
z$Tt`?(6xH~zEz;^ij4NliSzPTe);1d1WV!$QAo40n_T+kY`?tQ{XXkJ1EW>_zdeTz
zAD(Pe_y6DDsC_j%qqbx$G|j$dp^`Xz*~*Q{$J2`XCqIAvTKlkph@|97P}|@2`H!DJ
zSLWQ@bZcAg>_?9uZ!LWtwl)8L+@z58aki<ar};{o=WS8{zVlY+=IZb7UftWfdtL1A
zWuO)iD5<T9+<awKsP^A4m;Fyo*Ps9NtMKIRpiP@stzW-h<>mML_2rTE4-c`nKbD(z
zt>yHQZL7l8uB!e0ZRtwhmvxh_oS3Nm^!fAUpsGSOzV7?o^31&7iTn2LGx9Y)DFK>!
za(g-T=6R!!^Vi4jepY1u;>@=Xe{KJMxxCWOe&hf1w%=nW*$Yh!6}o@&$dfH+CTWN3
zd0vvQ|FiJZ)6>>h|9?C#|8k#ORnpvvCvR@ez8;p6vII2y@%Q)l?7O>4XBnk-?J9k}
ztcjKTR{2xEzEB^b<NlBSrd_F-D%Dx+=T)XzAK~?A&JVq1Dv`FJq`5M9dEcoinu|}I
z@QB@A=6mnny{H`p3qL(Szy8|VXlohk#6v8xJBwTe1qEMST-@$__fRXhsG#7)XLTxe
zlb_t1-F|kCW$<$U`PV?hK1oM7+IQXEU7meuiD%}!^NVYD*ZkZhBqa3Y*|TQ>(<e+=
zFk^<qZ<&dbK}Kr-^@>ZYu6@38F1a(;XP!;u`u+c^y3R=&CbfVDsQ>={u5Dm&Vd1+!
zKR<(_&pEQ{`h_iCXSa7wy>f50%GSKQQEQ{OUt1f!eM|azIZ#TRU;Aw)Xo$L*oqtu#
z&Z0?6lw7+qKpD=m7?iS?`OY>2&4OHA5x6*I*0R&GFE1;v-oF%<@EC#)Py3??=SiNw
zemz{)s^r4X;^$8uKc4(1Z;QI$oCzvhb8lZ${24Rp+nbxo_g8*R%*)F&^1WQte(cDT
z)l=R)m?3oV;6Wqb%c)8}L9@(qSG~TzKKs>`m0i8PTi<uRd-`<gg9iz&uCAGvm-!m;
z9FBYLwJv5SD3STjw~GZ$m_9u{ee&Dx?c29&g{@g(|L=#h{htrclaBxT@nc2E${<i<
ztnTmE@a4aJXPbEjZQ8wVxm%x%<(Ds){a>G$sH|5m>AP~q42h%1j)5l8{Z4|q=hOLQ
zEFP5jMcwOP6}sAM(zcwNk2cvEx?Nor>RmWn6O;xmEFvZa{jE!%a^&OIvbVQP=Ekp!
zv3z=NZuIW*_vbbkzV|Bn+$U;pZ!fA5;9&p%PqEt9H~UtFu0Cbr`}W4h!z<sNnQ8p%
z?e_bZYI~21zMk^w!-s%^f(?fbA2zN0lrnSKN>S~wB|rW!v-9n^lUw=u*;yl=!*=g3
zTgBhZ*=Djn_~5~VpeA0Qto5`<ua{o&xBshh*g!-?WXhY3ksIxHT-u!Oe|KMPG^m~U
z>gsAx<0<d%E=$#D^=}`4KA&Hnm3(@d?#o|_Ek}OVzP`5BuM{-oWBCmfNRn-dH|4`G
z?Q#P(ET7u!D}5cNs-lwe%XrcxxyhL`?Tvm_`&I3EUHRzOuG-(<MCOBfte~kAKhB%W
zGI!;u@6FDLN<C5<T)m$E^QTWii`{xn>i$&x1x@MK)a*%(KQ&!{{q?wN-}`mH*Q#Xx
z{PZ;Q-R7xl{!L?or6CVq#C)#9w4Wai^KZ?$X|y(ayWY)M24*HE6-#xd*gX{&i?*LQ
zGI#&^IhM(h`LmX#)@E(ZzV5fwYwD%t^Xsx^-q}?BJ@4+m+S?1)curO`@(up~_kI1`
zNoQu8WG<4g{}VWI;zUsCq!qsIO~Ja*q>xAFR)Yp_zx_UIet$~ltXKE<?_U?Y`&q#E
z7w_iR{`zupZ}oSRiVq2(K#7wR7GBJ6_rswraYgz2dne<JO+gcAM~@y|S^oasx494G
z#iXTIH?#Ar-E=$H#QOB@+qHjxf45edbZ>8Uc>cbh%TC{I{`};m@?nFZuXQagEh|7J
z?Z)KxX?n4*0=B1|6ncAOqjT!%X`y?oz6RY%%Sw5+x#sWJ>rdakTj$u!2Aa?DyS}gZ
zdEe<Hr+PpU{q)pS@8IQrr85hr-FdevFE6j^aj$vFzdx0GKOU3zdmON9zj0xeaOLFL
z<&!QgaAZDu<j9LBCnvvr<s1}O@sM@r?%mm^rf6DKe_P{xcY>m`kxJv|!lPE2yUX5g
z+OuxTrk#ctudWWCTXyj7_Wb!`IuQ%*>@0r0^ZC5Z)0e020|jB~qxz!H7Zx}+r_5UR
z>+9?E`>B5t&GYYFnP*!)X|H=YXxQ4^+}t$df`aSu^rOE%tN?Wn+Y&SG?WqLK5Az%j
zI6u#JZr|o#%OdvI?M*v7Yw9|?D{G^}L2ZU@xwl0mC0_=Zr=Aj-&iRXxk<rNa@=AMl
zez_|%43lHjjx0}I_ww@cexJ)%E-ZAGt=sYZ+S+I-qm&Mw!vXjA)dt^*%UV+6vn=(W
z$LXrMbB^zv7rs6YG#PN+{C>@1%i?D{Y@XHs|2<zXc2~;(Vh4wYK6(3hTbzG`nkq$k
zzVD@Gg@J~Q9UK~zl$Ey@JUnC)YrggSuG-&a)3a|bet!$p1^f8O_4H$-<n~XfY54n^
zcd!J_@Z&kCIoKtp`)boU6W@0G>uVx|6%`eKJ)4~`A|$k^>g%hQ{r3MZ+}fHQx-Q02
zR5R$v%3iC|S0`@Yj-IUM8|35D!zHe#^RjMI-nluJS9cU9-^?-Nl{9hzjqQATa#Gn-
z$}A^h*1O|(@5bJ*`P>VdZ%v<9=~nvsT4+GPggtxre!ZQ)KlA;)y`V{Iy_g*e{{H^I
zD?9)0sQ9?()O7v)_sdJ_%fEd1P;m6fkrmGEe16w!K&zM@KVJOcK|(dt?Qd^yZ!Lcx
zcXdr<@Yz|W-rMf$@BK2V?9GjZ`ul!3rJkA+xV!8vXo`8ReSO?)v)rKj`)a@5tA6h}
z>0aIM+_ka0!?eTJ1WeTmy|T<#`tF{};BImKYfHVSgIXw{0ynd3{#4M!=YdA%UvD;_
z2X*d2Z8^{!|I^dcOJ7~l1T75!Wy19NwP`oo5+$lWpEWlvdlM15D#R1iv#P1t1DY|?
z4qvyT@bNLf&U(<?``cSvx7PkHD}8@2wz07hG%Eyh=Efw~)7fX|T8HaKZ3%dOZZ2qf
z##HTaKl{I5CWozwP>hd{2d%+c?DSa0cz){5O{u2U-*Udby&djv|91;0WDgv0xVy91
z9W<Nt?d|Q*4GE62wpCXa`uF!e-2%!Epe)iSYrU%Q@iEX8p;q|1HQCqKfjYUMEOz?H
zx%OTOL#K9r`D<TZUItCmnPy&c0Zp1zd|U)tqyg&4g2t~wW<9G@Gk>q5s-xrMJzekW
zudlDap3+{wWGBC;X5^+NZoN`V6A!no^qQ*m>dwy1HMO;%l>nd?N9d}Mi~aWhX1sfC
z(-&d?=HmApP#0uN=Hyq`*RK~+^*V9<xVw9w%*9(<v#09E+wJ}H>9l6vZpUV}S*F?3
zzP-5#>Pms)GQR%rR-emPzP!Br^zq|ldo$h7p_iBWZq2x;)Y{gzDr##MsM2a?;|<wg
zS9`ir!^9+Hs#a*wWHn!tvNsXDvQ{CWv;kUvu*ik;?v6rG102*50=dF8``Qw%dDqv)
zUWQC-Zce#>+a+?Noz1F@i;F<ryhV!^J$d(To!3+?kO%#a@BQ^^^(^D`KC6-!3;1NM
zR(MQQ`gQ;RzvW+FUk6P%>ItU?Ctq6=nRRhd>!Cx3zWn)oes#&qOI9T>CV*z5uC0v*
zHSze4@Bi_r``3%b{U!wu9CB}M@k~86<>JT3$G2u()oN{R-TB7<@-pAA7v1GwE}b41
z6cI6_=-HW-paO5}^|;M%!mqE3-I{ciOE+#$1SmOxhOiDBY^nKKG}o>+Dt1>%;B>v%
zOQr9_f{fLIt?QSR?)5wOIOe>#PQ-#`zO!E~ogQ~deSXcNTU)cW%irArB?mrvyEV%0
zeHqu+#e#-Fmi)H2`*=!wy@rN{M`B{)rw<=4oSSQ1`sRjVYg=2^(^FIV-liXsnk6PD
zCkL7a1I_+{mH}N}?jK%Iup#gMzO|sarq9pLcJ=rBZ|c2r@Ad5beJhKfpVL%PabaX+
zJT*;sHfY-4cedF|mrkK?<u!-fc%^JAHoUsBa`Ax!4x%~{0qN)GUF{Ope)8<uvV+a+
z%U{R^f1W$}TD~T%G;3G`T03j=@X_PPrb$OQ&d#@w4__ApT76_%_2os%|K*q7-rf$H
zv$U%CumH3M;m*!tZ4C_%Ww)LaU;h7OhnVv}W?k6_pO+iWX8US~ue<W$;o+@mXQg~+
z8oB=a_pj>b)9I!;Hw>og$KQK72Ne9X^Y>i@HIvKV#r!^Z-L~pWz_~e=pu+O(Y;*s|
z$NR5eSs7gV`&+JL+rtSB^FrqH9xhn5K4j&jx*reOedkyNf@bwxTv~F>X8-x~CuD7u
zY3+xD?5F12?>}r=`RPeuK)?h(Ihz+7e(zMdx-K@_vgpZ$wb9$>yi&=0b7N!F{<^(<
zayBcrW?w&b`Eszo?bj*Lxon5LygW~rpZ|pg1s6`!jm|pOBMFL@M~@yodH#HP8?UsM
ziOH3^IqmK3W_fp3fYw?ZY-0Vj|Nn3Mox68~!UQyM3M!KqS?sh@(+pnb6ZrbtTGQNH
zCa$iopdr@E&(A_XK05mK-R}3RqPORrj4S@~;-Xf>h6Q&2{}i8{Vd%VX-#$=^xBKyc
zdGGgo)q1}T>i^a7N||`PzP|qYp;qqHS<AXawbT4Fic9B4ZOsDJ0aCVATR_eUT^*)b
z|L@PMYinnNMj4G#PpMR{Uzap_*2c**&x6M0xVX43wQve=sr;Oldt-wms7Rft<a%Xe
zvU};fJ2zAR8^5{-8g{Au{S6dKU0q$5+IXd>sQb%-iqrr9zVDx$d;9L)SWuS`wDhT?
zg99|2XP$Q_ppl6+WRVMJ?T?4;npM*$?b`q3+1w>9t*t8)4mM?Oo^HkfJr@AfJUGqr
z<;u6CrzR*mhpdS(1jVJGpde@w5U4EPn0y?xn&s3~?eJae=Spt$JGJ=v-fy?EK|}VS
zatu_KzPq~{RQtx&|1I77^;)!6*qVs0+q#jPmMrs~y-d-$E#udhmtEc6!M#$ZU+z`E
z-}&dg;mWz|)%@q_%s#tp#R?5j{q_Cb-OHfv_^+?8y*JHk*9u*w;t9$&PEJl=PO8t(
zINm4Q)zdR&{rdHP{{A&hIKWW)_Lk|*3fruQhg!S3yS=aSE2bR#HDTKKh2iVtZf(h&
z{O<1V<#BtfcG@fpTIzLcQ)>6$*^l1c-MuPkX%}d?3$zH~;v!eQ^|_(nGAi%xDg{+!
zywYZ8=H<xA$gI(g-j;E9SE(Q8i@LhHTN{(x+ju0w1E8R#I6I4;n&jRxG0nVmB()yY
z*9WCLP<PIza?_*7kH20C_P117u=~~fL#^CbR|G1boo5?uoOWh{%2fUMxMp_#YYmLd
zK_&Gkj~<zNrRU_9Gx8_bUeBC(@pWa;pTB>%*8i^qWl~Ue)Wpg?Wx|97hg!KoL&8!P
z1q*7=cwaiLzhB4S-ygJk<@2+%lc!IgE@hIjpreCBH*(VvP0eVp|5Cp)YP~|&$Hlhu
z$zB4DNtV5hdV6cDw`K9Oke8R1em%%8uX4LA>wW2s4T(|Pa%O@i)mN<0xS3-nsvj3~
zxSjv{fkx)1uU~6>f|eB3{eEi>Y936SIB{3m+gX49{JF9z)f<!r4jw$H+2xt_c*@25
zL6Aa+fq`M>Q3K<w(~Jxb(_Y-#x_aNwXVM_0OTDLuxwy3K`~R;x_vR+mlP;ekH>YKO
zeRXwJ<mP3dp+N2Mbs7Ku{Ish1vEka9$i-s1Q8veR!wsDTnswlnHuGWUlPTC)T$~14
zQwLhCx+-*a*7I|7`@i1$QN1#7aT{ngfU<kvgdZGmy$t^yR2DEF5PtLf{eDm(uI4iX
zG#=|Y>CvM{AsdriMYTdatjpebgjR3QyBl<Jl4|JItkAWQo7IeW@xTn3Bp@!nd{gS_
zRbErIqBbVEE{joCQ*+x{{CwK(-MjbdC@MNKv+-Pbb91w4-W`j-ujBupnv(taeg4l+
zPr10cFRuz+ePvha>oxEAVCFF}C~)skujgQR@ILG0B-Ntwa?tXOH>o!_r-$F)R|_hd
z=USKh{rmS%Gw=NA)84FHA^|x$IcX*0FcVaitG~Sgt?&jl%RnX9>C@VW*KaI&83Zb(
zvaYR}*(IvI?DTZ~?AzONe?6TZ4=R)Q{`>V>vd-7W5>%0a+AmLvVdgO~{9spRlx3Kg
z(9S0tl#sBXrlv;bRQA<Xsq6jq82|qI`Wm$2$j7G#wAvR`q2Ab#IP+RMO#6f_RbOAN
z1Wn#vt9yHED`>PZ_x`?E(CDKIs3HVS3xeh#Q_s({y}Yh>|9()1pcL*K1_p-69+nb@
ziYCy?;<~yzzo&I|bw<9y&(F{I-`49l*DCYxudkDq<lNk}vi|=+DZ84Aw(szz*MDqT
zSXnbqPEw7$%L{W50|Ubc^VHLzHGG%eU0WNiSFZT+%a<+J)zjbH*m!G0VsqO0d26jo
zUuoFc#g)IibMnJJCM2yeX2X8_G6(hs^%>KrPk;32(VSEH_xI(l_xF2xYU<nnch*Lm
zhprCu-CO<r+V%MQ+)6(mpPp;$<JUJdG>F7v*?H0rTH;pn>q{o6@%{7j^YgFXF)++i
z0H@9~=g<2;KR>@*Yk$GRCY6;Q6O~qGoj-iodEvr^Qr2Z_9zA*#^KPA<Cuq6p_jh-L
z?<c~Xh@fr4K0iMn4w`t_CC$*F&cXSD;R6dd7uTg}y3r+%kMaKe@#Dtn^7r?2A>$aY
z%<}K;(Y$O@`uA7qX_hYy4Gf;&|FbTs`S~gHl{JGxGLMvrhkX5?!m#qk`JFc+l+CVn
z^qM9m_rjTzO&%ffkeHN7WFPO74gUV_?%PTQ28JafU|+nxu(0`9zx;Yh<FprRx8Iwj
za`gCdZ6zhAg9i_O`u=^o3TSE@v?j`Hx}L7Nxw+@1rQXv+7C11re@jYE-dgf92vo5B
z{QP|To^{iwPghx4^YhcHu(eTXccd5;T5D=+XLjofNM|28Cbe;+Th1CmICGL)4H6HD
zNs)wSRFWJA1B0e3lNE!_LC|90K3VIm7Z(=(dfaaxva2N1)x|}_$||b(*_n;<<|!ux
zKy9$){`12=K02!Exi)%x*u_Pzp}Wg+L9NM)7cX{obX;iV7XR|~dVKm-UHGyBM9N@j
z&;e~6vU#}g$0Ke~=jikE^Vg?phl7^Sftn18ii+Qoc@9rFn^tVGKL7qc&?u{#@2n*^
zZbX0<WR<?Ua`C~z=FshVcaPUfBN+>4KF9~{bE-H58oEwC-UnI~sM|l&IKA(1--}6K
zPHC?Pts6c0<{ehIsdq$IR8&-il`}DXNZDENuqo}#jD`RH{yu&Fy#DIl%nbi4rfP+r
zdZqU#7ZEYkiVB?3UFi0Yok3wO&t;RdYu>RiJUChO-~c12PW}D;efZX_tDANq_PM}=
zp@QY7JVV2lO{t~OMmSss#;E64!L=uCbQ2jkkVbd<frDXK?DPZs1Ww@Dj`^eh&Fzi3
z!Hf*97qwjk19$sL?@X0Dmb_eJ?dy2u=_dJ%T+fp&(wlZ4Fh$Qj0g~u@Qze+uH=a&K
z-|X37IBE<uT1LYL8W0Sl=>`@Oqj?Gz5~BqLEF>643kq0Jj20BIkQgBa#f<go;P!m|
zyRzM-GRJR9@)z%nsj98DwMOdXKiHoPIt!ygy?FQCs_NZk`~O>6KTV8_+xPY3$2=#n
zen_zWNMQq=Fi~N2yfDY^e`M_WbCnI>-+h;tJ)Q_M0HTP20j4bK`m5hJ1!1BL3=Dsq
z_su~&kCoxT{e$R7MmVG*n+DRKfN>&g2-qbcIT$`RY78_eM#Bag5DcT~1{M;dc?uR1
z45I}FEGR|`3Rp;t78J0M7%eDZAwkW8V*kzEv&D2z+c7*o-jVXuK_t<~$uTn5NyTxA
z_#MfuoJyL_8HPU?(<X1tczn+F%%Lz=s}KdpEwjS}ompHRZ#b>;)pzO3opj*dnHM+b
z@SI7un>q9G+0Vaq|6i|+`~LqQ13U6`6azy5C&tJU3;MxjAxxmA9Ne!A3=C|H7^6=N
zXsxvdM~p_6Dn?sP0AqxT7S4Iu`)>|xEda<DgUD&4&H;r05}rDU(-Fv-qiF{e3Q#;6
zS<rwOaz!G@-J?kv6bev0nv|gdF`ASS0l~n)Fx1;VAkU0ubWkWj@n}Ye2E=GaM+C%Z
zMn?$?iDB0T1bJ_?7zBj^6cbqt&ZtN~Hz)J|zrVTn_Uz1FzjxbQ>+)~kZs-4hy0`pZ
z<?@?1Z@%00dYxI`of~hr-@mu7_P15#rzfd5;0FYQZQCKVHvTm$!;kcNb-!NTtNDEP
z*|TT2Hl=!Vb93AN`EXcQSGV;2-tY6i-~0FXw{_{Okm_%5UiMkPd(o}G@5P0M&boSf
zWp8e5G|RnJBKe;cY$A*(P!(9f?6ZO2{?CT%@%4Mf<0=;J+_`hrysB3#-|hSTZeHcH
znfI#S@BMsl?)>@h|NVX+Z(9A~Ap7mD+2Q*8ek8H;$@~Z}N1C)^U|?8h^ZHs9BZJ;O
z>HIwxe|>#@dwc%<Q#ps*c+Z|Y_wC>B_ut=czd!H$yZYnLL-}n!IGEolaGqcH>*fAU
z`Y<<v>4H>Yki(LX_mw`MTW)4+yEkiJ^6|c@&+Cu(+yA@q^78WCACF1v-|Pdch7kvz
zfW7nd>C?2dv~x4hpE>j8xO{!dqa&UBzwZ0_^Jm@fx7+7cJnHn`ssz&lrVSifUN8v1
zc|N~B?{FLM^E2!B{dzU^x%jKQ<@etnXk@ni_v7)~TU%dGdW*DPoPmMChmX<f0L$)Y
zv$8>_tel_u|I=xG?eqFa(&yJ+TikDV>)P7r>Yq=i>%T;IWyJn#+zbUD)6&wc3LhP@
z{QUIk(^Yx<em>h@bKLxX&E<D@ckll9>veQYOwQwDz2bj<7Z(@DmftO1omTz*UGDpP
zd&U1Ctr2Hn_%{=DZ1$HI7ehD8*ZoNB-Nu-3iSq)Z+Kp|wx1*w>UVV9a+1KBH{Tcfo
z51N-PTXt((?(P43KnD+Qum1k-+&tUcmo5dF-z~X(|JUE2KYza4`FvjYE#%Rt2Jgq`
z?KFOTJTAYz_V+i_TO19Z+w#_mGdy@?`|U>ZT-)kx)8nc#Q_G&6nJFeFc57#G`fT(3
zb+4YBoLu|w=X21iTkYp{zg{kvt9r3;+Vttwuh(wh^>*8Bz2E=9p${VtOg$<Na&@1q
z^{vh6{-9F??$>^gjoy}%nV7h6{r-Qul->K*%&Go%Grjuh)bL-gR<GanbXxSPs!u1?
zf4^AVKWpyXw?95UmbI^|dHUzemy&*)PbX6U+rx|p(+6$|EnxQ95guQ=_4)kzeb?iv
z*9I^5+gkeinwYrw?)UqChn@5B_1&6xcUS0lyPr=cFI%?Es^&*QJHLF~*EiRq^F>hy
z+z$L#WVAZavisGl)m9ZB64?3WY~IfVx$>7%)z#_obwBghvw`h}5k50Y>uXscydV75
z<sH)QOs;`nw751jNzaa27U@52x^3jLR&IA*_9qX|G;Gm&JZE!LyWMVih!zHhe{2|o
ziCP$giOT2$g$smG-Oa#YFlr1mNJqm48W0Q&qv-|~6r*_x780Wc1uP^+3kq0Bj20B|
zkQgl}U_mijP{2ZhS_Q?b^Wppq3=BVJ%O1a2IWPQt#fsZ+uYLaf`KmF@CeWdJ{~bUR
z#RU@|TU1q6zODOT_;pHqRn@Oczkko>KyJnVV+W5)h+Cd7{`m9ztFNyt`9EFz`)}=M
z8`c*G<lkEKo%_6}>X`H0JoD`maPu4L!IREA?qq-c`bv<Yel6IRyTKFsU%!0m{r-Kv
z64KOmohQg83<u)h+MGZ7{QmEsB2Sd7Uf2D<Ryhy3wFy<maP|C;Kd-OCFFs;mcn~yy
zogCb12;;zfV&=iYK7(k0keI{H&puy8tiyZ|*!TE_&H2^oHdo%3z5e<0=PSs$-8BM8
z4z*hX_AIs_ZMg3Q_A1!21MMaAo<I8h{_5+i#d1&9{{9>NypjvDD&U7MlFMoe)?dB8
z+8v_j|DolpQG3n|3?I^ona{^)?PCr_2%@+4v8+-c)0hu?SGB;_0-){FlOWT`QDeYK
zqJf67HX6jEK@1K7I6>D!V>J1J!+pr*@PCQ-`3mn?F=%wfxiT(JNWMHV^V;O6ss4)>
z9+P)(Q{@j;&3*cF=C?VbcX(r{xr7fKS}<aCl_V@AMoJKe#-B%wZ$G%d^Zt9;<Ar6%
zf@Afjue<*GCZwtMVSYMdl=H`tci*emuiq}$AD_P5=IZIw+wa}K?*mzf`2n(%1{{bD
z{%<V$&OWzaefy@R|EFt@KQ4Z30p0I{qU?W5^w+;{Afx>cCjTxf1M5a2_Op-fABG0U
z2-)5>x}Ogk-wdM>4hxCVjlZyv7~S{_4~fx&0u~gb1qCc5MoK|(_4;P`Alr|6><u@D
z58Dx^vHURj{(JBB>(Twk*KZD<_v-1>==bmQ)u3aFcCv^@mi#kZ4L61wE5rt6zk=2K
z=F39+n}1GDM>q!>6+dhxAVYIdJ_7^83TO)uA<~0!6wE2aa34h3fx&LftJgOn!SJEJ
zaQ}VlzQ=ERmhXzui(P+xGh+DoM?2K-9~f~rpg|s<KLr{jb_WV&W}mMQ+rGJY-jlV*
zAG;qfL<$KzO=yhOtUxrNLHd7q$Dc#A=|Lh43=h61AX@Mcp#?_hBbNq<xP>TT(1Kb4
z<uWiZfVb2mxC{)V#=t{kG;Cl&F`8~*Au&wy)SrX*?ry#js+S<KFJ0n{MDwy4YHZ7d
z4mY$2sIt5{aw@93;h@tW#!M5XsGA)fNtu%cm>n-%I_DJPvq3<b^YY8K8jfg}2|IW@
zEzedz6Idk2>G!Q?r{0aTyRRkL{${_U0}Cw(J+yXgg4|5(a^0Nb@bz(Tmrjq%dVg>4
z+dDfqA8zOWeo}q@pZm}C;`iP8`1pABqfYf*|Ns4tj){4*`Mlk3=59#M0<r}(1G(0#
zfp5cE+wXUZ_kKQSEo)n~rTl*F_N7agg4U6Ou58?2lUG~2*Zh9X=5BHQZT0{EiHV85
zyO0Fc51|rPN6q@qz>s%8JihiSyL`=s=={A`K?h4)Rej0mxB27&T5%d*^YQ3>yWcmG
z`@cT!x8GL%{hi&f7mLr$v#nm925)$P&5NF*zkoR>8MGeK+uM8ZheO=b>DFa$Ui^GM
z|NWbrn`3trJoKNx_x--#xAs<lpF4vStO-Ws2s4#5<i44mzwhP4cKN*P>tfC4%3GCW
zJVxEMd*HsR1N)6*da=7emu%!&-rt<=Z=QGO#iOI$#Sy3rZF9oGCV~!tJ>Dm~eU84q
zetrz<{NIn=EH4;t-`M;8-tGMTf6Gq)%rU#Y1GUclP_BEnnt@?^{`q;fv3n{$PW$XV
zT`%<OgJ%A`SHJsZt*<fj+Z0^BIZ@f&s_4myW&4n~DmVPMEPm#bes0drm!O5N^Dav<
zY_n#xI$&1z;6S6@-!GTzem<RE_V(7+!n${Nc8ZCKSrt4uux#J|x7+W(dvLIM_AeBt
z{JSMz8}Q-v`u*=Ny35bKti-Tw^U+Fvh6mq3mq5ktE?fKkUUmNCH?OX)o@-ON>2N#$
z_VV}lR)NyfuU}Qy*T>Jl9s&z&Fr6U%ffW?w7Zy6(em-Lix(ea%hr|4~UoJR<40yl)
z|2|=LznnYee|~)Qn`?CybaU;iSFeu!e7%1Ey+enb?$`a!1qJ<;mBFAjr=fd4ozgD<
z^B-(BocIiiu4nh^|No7v{d(1JzTI7a`@dKI{r&y>$K(F$KOc{qzl)5B$S5rQI4wQC
z`t4RRF)_1uKl8Wj+ps|awWZRq`@&jNC5GFlY`@>R3|i^j$}PUD=&9H9b8}yxRG+`+
z<vh?`r*Cg<oxQIv?(6UO`^*3S`Wjt#eO>JC$@M6ihv9}2(iAboshE@3v@3nCUfKgr
zh6U+9YLk~;ez_+-XVuiHQ^Uf;pW7nksBOC7$=w672}U!w<lm3ld~<50|ILuor>&#o
z?e&okE^4@~0uHJj+&;@M3(lXv?%Ffk^vQGb&8oM(EYSi>K|BdpxOz<}`*T~QbCqu_
z5_@h7Q3NL&))KP}fSBp?0S#?h?9K;;5wT@GNG$?mSrtH1=$x&;qz+pP05cVHUU4+y
zU}3|+Fd90Du%KO;HoS5fEW}3B4lE>w+W9FUcMnVn4YC=8N7D`{6d-uC+<}Axh@@vr
zbF@?jg*X@|M1Z=w3=9kjuV?wF`7Xa)dHzO-wzl@#b?eSmBQ}g3m<H{3{JW51lzD&O
z*0jyqpXY5_Ic<9RwtaPREr=f31jwmBKZGy8EIIOg`Rc8e=WnV!pM7>-uGL)VQdF?T
z&~0G<uSb;@+(TM<yMvkBCO6b44fU5&j54j}o~u5#EGjZGv$VAI9%7i8p`l(8+<*A6
z-f*VRt?l`1Z@xLTXL-)5r%&guT|ZxZAyQA{zXeR?TtD}kx?NGTzt8b4+IREK&1IKY
zLc9s~3d4`%;1tzRzi{iT2YVpPY9TT?*4>{m))8NWh9yJ^h{Uo?n*(ER0HZ<7gS0{z
zWC{ZV<`#fvWOsrTHF#mnAB;K&6fj^+&(K)~9%TYq+i)`FQi;{v?>)X-H*LD~>eZ_~
z@Oz3F{-}ZzAp?U!_~esIYJXpwb#~pE>Ql?2;_lu2^{Y}4J`S{DDL4@_Ff{C(<+ohf
z&OUbS+3Is@miKeM<y?Llf{68;OlZ1E=#E&;cdi<`2b6)~Kx}T|J*4yxavH-8DU5VS
zrK0+S{I|CP?(3Mj7QL97YG9Oir{v0&*B?LaS$^@tG5Kg-=Png55zD~W{*Q{o0)D)V
z#Z23ydj!ET#DFc|kA}@?*kDXxLi0T=WU!^1&p+Ql1_l4Se*eAqvBkN0A48^}Ui$iL
z)i?0va`TS#a)b0Y*h5p;56|z=Y4iTg;PsBv@7=#|^8z%8_J@CGA=t1F;m|U~{-s5q
z?X$Y|dFkgXCvBJO&zC*^&=NE>{Gk2>)ZG0_kde6`$MddU-wdux5A1(%3_ON?;C-!C
zHOO{kEKf`oM?`JfLqttUKV!~3-wYlMh4}Qt{Q}6uxuk#T&X`?s>(kGJBpNOwJLpF=
zmY8sP0aEy96Ep%q9ELw@A6tmcuSbprMR1@$m=4}z1y;ns@Id{}s`cspVBWkZmv5ri
z3_plDTgDAh?|=<ra6q;KER=xkHn0e01v6?4IAE|IZZsM;qhSNizOY~b_2x$N6f`tO
z%NuAwFffc36tJKetzcjwF<SY;LSoPt6n67brlSA7sM}vIbNr_9yjMj#OZLW{p9gAd
z?}s+aA-;Oxyz~D1z5DJ}+0@OkeY!F(Zr_)G|I|Qp<PV%t_V|8SD06({k3ZF=*45`G
z@A+C$^V)(BJnkUhh1@J|;C~fXYYQGR_!DF|7sWlG<v0Dr%&?ADO_0bLZ3;uffq}YJ
z(}mO9?a|i)fNY{_2CqwgU+1)R)qnfG{d?{f?c&JeyXb479o)iUxPv2i(NgY(7aRhV
z7TscH`y1V|ZA#Y?g%iC=O|DW~I?QyVJiNMdgr`fhlq%{<aVVA;ow)z#yXU?~w#CKk
zF3+6#yF$nP{P*AU%%9IQHr~D*rPtMpoEbrWYEZ%G({q9IEl3iEJuz~e2!^gn$URB0
zMhy&IDkwz;NKpWWE)Qt;9V83E3ow?#OmM;I6hiu+5Dj2bp%cTaNatLDl`uF6VR-du
z$!(MX`+x7zqoiGT^KK{egocK$e7)<fAp-+L7;H=xVop!z(W6Im?(I?Cd++Hscga<L
z>1y2EpFzioG>D;iFu|u}_g$g+^F1~#eOuU;Vz>9+y^`IrAV)ZGqlA`0**2A%*S-mW
zPG(%NavM@l9&BTR35u~GF}jA^q?BE685tNFPHx|^V@BTg+utOdLqkJf?aHeLkMV%q
z11il$!SU_9b;phwXJ>C;a((xmZyL^5U!F-xOhlUT=~0PSVPatT6AemJ2`hHp&Fehx
zuX6L!Hw$N@`EmLAyY8-wkAoV?z@U6wypw@}VLLc7|G2}038G+ipS}<y14ABaI!_4w
z;Ht#HaNyIjTj+Bs4Hq#cFUU+es8)i!KQyvd&(781>z_TH9)GTlSK7$fc=FrZ+n;yq
z@B0ycJZ@Ks=6So{IiO=S*F<mE>$m%rac;i7{gX~mO92w%Add#BI<QL=``i6Y;gh$U
zQ~Ued)4ApMPJa1PQugM?#P$1rt$JU0eO>J7K3VHe58LIR{d_+EymbDaiTCS%>w;Fp
z*8O<c{y(D%ZXSq{FvVxPEdxXI?_aOif4=B0|8(v4d#C>W{XJRb_qVsFnfYxdOpmM5
z1RY3g^X+lJ{kfZ)(~Ez7d1>?QMzZImySvNNFE8`8EO_AHH^<`Rd>hpKlTh-5t)#)Q
z?A4W(KK}mCXQt2F`R~T9t=XTyT=swd=H}*~KcCN+?zgS|Rq}4{_j|8DR!#~DovJ>s
zLTP^8ugrhHUawz>w*R9?j?wCX#P4sn^EYQ+UbZHB`@6Q|&!0V8_rG%T=jZ3sZ*R*r
zx3x1jpMH9}{`24O_wV0(7&N*G@+Jf;`#10z9Mg;2GvnsXo3rKS&z*aAYxeb`hlg4l
z`+P5bkASFxk_kqf7Z{J-n5rGVsqF2o*>dkotgipBnUK6bcK0<5rM}=m-2MCA?$6KX
z*Wde6vHtq*f6tp`cBh@4weL97hArLV`p+I6?au8t4B5PS^US$(Wk0<5dE4rAM&!%l
z&9j&4=;<xH{r29mNH>2_=~u=2pL=rEyE}c)O;_&rj4A%LadukS<uiG+cJ_bYyy^Fj
z&uJCM`!`Ls-R@a`e&?j`v)5UkeY0%lU6ajFWjD_j?fI8&^z!*RuXD3K>vQM)sP!>^
zZ#ny>ukrlCuaE8SrF?k)%<k%$^C9(<>)x$-^VRp!EaNke-Dm!;uz&a1caHhrA3dvY
zF4#TuOLfJgukrTU|KI;-NZ0}nkT-8~^kQ}tTz>q2PbX+G^e?&HS7zU>FMebH?fw1v
zUteFp|KY|w+v-i}=jWyNv(9jNzyE(-T>am#+m1`DVrJ)i^59_e_7b1a(3d4?mtMb>
zJr|(7=<-a@(9rEAJ$Fr_V`9!cI~#rJb*$W_ki`ox&pdhP&>!7;j=fUn<~p96ol^Qn
zt?=y2<9V}g`Wo-fd}enqXTt9tpO?+NtCN4}elg#tI%6d1G;>I(eEzk5|J8zbJil&c
z82wz|E4;t|<?-rspa4yeIeX{$Y~CvQ^7&D-=C6F}`)jB1i|6%_;LP?je(noGyI<yC
zdjGKVdi~!uPrlyYFvq6SNZo(lo`)N~r|WGs;bnO22TE4k^6t*k-~Y#`{?AAEYipy+
z|9&ifelGRwEYq92O0(}LpPyq{eEIS7b8}ChIpbrNduz*^|Nn32@1L7{dmFEr%>kCG
zcRQbNDt>+r6ikl)L{INpw|RrX`}j>UO?ORRm+gLf__?s>HlEaV-_9<-etUM__SbhJ
z4=wm_^(O0v@1t3l`(bfkyXR!W_rmAC#=9f$E!qEE=F9E=m|{q1!GdG+?6kQ5U(J6$
zKlfmMuiE7Qw=6#Xo>8~wc}|-7*_vZlkJRp&@A&@lyI}9n##{Gz+LyEa{d3-Q`OLc}
z#b-00?E#@Q^S{2oY;8XNT7UCY+<)HFLGc<t&YItUvanq)D^rQ#*h~i5gr2vzwrc0^
z`<d1!V>wAYu0qkX=<BPiGS+1}x3}k?Z{wAoq_Y3dCvUyjT~m6c&7bvIzuQsw=H=z(
zpHHgKfAaCTy#J^F`Ct6zT1}m6UH<Hx_4}OXo{T*kZ{EDwSf6P2^3^W6mHao{I`8VF
zdkg)4a5iX;H6*T~IbhmjyL}>{P<VO1`rOkU&k#8Sly1_@y+8hXf4|_J&e810X?5$s
z;S<@H{V`~c`Pn<mr#((z)mglJX11U4?#RCEb3t>=PZ!=Z**tscj&}XymCOu}eLxZZ
z?AfzT)!*Ok`Soh`&#%|xHy1uW2J)W$-!H*^a<)}}--8yETh{%lsQdHr_-lD7P=K`a
z%byGOx1IWa-*3Ip(5HL9-#dN3{{P%&cK&T&dY}alglaGY<+eNQ@--8#$5rd9`^`D=
ze*gb@?D91R^J~9F%GLdN__{v*>@3rnvu5pjxMStYl{No<KCk?ERQ&V1-S3~BnyNi>
z_UzLiA0IFN|M&a<>;5RMEd~ijrjiE3^6RnXPcJNVwk&xO@c6!E)t48%_dEXee|>%Z
z`H6|jmPJoa7`VeHox#pJcI3*Zdhiqvm<uKvu7XdK1GAw7mImKYt+t^)f>JbW5swBC
zG>pO2$WB3?Mt8q~g8@WL&ffQyu`OfLd}$DmfniM?r~waVH{4#cYE_Aq@yoB@w%MKv
zD77+PxoQ=-=LBjl-u8fZ-wI}5EuGui`m<#BT~Nnq)vBQDrMHv8W-u^pp9t^5C2+jj
zC6*2?E0WV!fqEZMRS-&o7j8L3fPrC{^hihZA1p#a^vKSC<c(>JrXWztf#J~<1Pci;
z-2fg)0W+b*XaGS20z%O@fG+2Pj!A~t%)r1<@cYbm+XDi=pNg3o7~D`ZvP5-g=+etG
zJ=bsF{x+~}6}YpS+t0|r;9~$9QG}ae@a@&EbB7MqfJQMFBaLD<aH_#){Tn74-~Yzo
zY_#$`Hv@x&XlZQsW<~~vFhoVopu7mFM!!&kQln=e#?TrB1Fx5gi9Nggw(PcCYR0Nn
zpK@CuE>ZS@*ZK^~OV(vKnnA?Z&dkDClI4cEB#UZ;X)0(z%<y(reszQ5tS8Ue7!DYq
zj;lsYUA4+<x$)$<{QTRCc|w;PPhPd^mK-xfgCXj8b3*8<*H+xzpI?^k&h0k}2@PGk
z?)A3g3=9cAXy$E&G-D3@pFv+wqdJ3ufdP4N{*V0cvK(nw28O^dr<E)$?^S3o&OdD%
z!^p=ugJoi(U-gXdS~D~sKpJ1vn)v?u_7%z);(^UoyQ>Z`*FMc>V5s*)q!dsZ`SZx4
zFK_#GJG*`Hwoe!4ZNJ|4ct;f*!+~J%@G?jR1n;*vzxn(3?eD(-z8Wm|3UUZIHf5IQ
zgXi!ve2}l&i8|)Uz`$^xX7i7s_tDM+KM?+@>}v!2uT%FK9;l;aSO$jqWisyDZ)eNP
z-(NrPQ^5Ay*~bfGY?&G4&=z1ESU&gp&ELPHzyJRGN|V1-#{GF^95!X~h4YqMNHhE^
z)CV8J4hby?`M?q*X{<n*i2x}ZTq_$#T?2{}5FU*wP$+=#fzeb93I<T`8gqNjXxNY+
zHjK@OmmsYL7%h9CLCG*$_P|17wCsU}1eVQjqh${?a7M!h8W0Q&qlG9eC`JoWSV)W(
zqOgz{Ehu0iF<MZ-Lt<za6n_%l_c=aUC1t=<Z|t_mn(OAH1;-vOG3uJ?;*q>~npl@m
zi-$-Ki(rdL*`jYvU7TVouc$S-ZP>)aq8i4=Evc5UIDw1ZMCoRr;&1W)g@$XS7F$=R
zm(5>(^XZ$NZ_1a~OTvQ(#K^!Hw!mC&dI6(3f@Rqx+Ncr(1D45kltuC&+p#PfL>sJO
zz_#497e2!YG6d9p!yM<7LK_@nV8C3DYeK~A=V$;y!x%zgP7jX;5F})v<Y)jv0|G*g
zW-&-OK*^C+1|^(~g|3Cp+xzv}oubpal`j^y7ybM5v;NDQR&Md4H#aukssH~sGBWaH
zfyEi~`!&YTk3vHVLLFEnw18P><JYfWZT@^XT>1a+_s@s8^`C6L9(Vft{rdUrauo{k
z^?$#b&bKdr7vnd_V&eSzf0p0x6#KI^A2eHoI7kU(n%GnZ*@Vv84+q&T%iqP^tNng=
z&zDQymG5>wFM4)n=ADAWyp>O<hOhhiXK}yXEcyCBhVgYjQ|HxuI++{61JV!2I!26E
z2ZXF^f0g9z|N9NJcv?Dr=@grfM}&X=c-;RPba?OE&#PCj-ud&{?B}+^aD5;~gb-6n
zgKF8oKR;z`Dhe+DT<F|h^z+lxm>mTR+e1ML;P}8Mu-CiA_0#U}tDSwW-v0Ny-S4+m
z3&B-@7#og!`(n$`@IN{}{`~s=|9<tqyH|4A*K^X=ty_EV|6lQX*P8X~({pokz0FY<
zPg~DskWFx$V_R*;Z};PY>3d$b=APq^Wh@F5w6(Q=KAj$Kc6a94G)W$|$jHc<$00}c
zPCK^aJ!A2f$@h6dHZw3VEU;%PX<#k<ez*Mj-12)r-OInfy}kY8=SN4oXaD>6`=)I9
zosFr#|DD;Ge0)>+`+KX;ffkP{yZ4>>`XB6=58u5sU+xM_+q}5ef9C3S(o3gY`VI~0
z7k5_%FE4s^W##H~pu?3fOEFBF3v%$CvfH_pzg{k1|9WQi`@QD#>wdjl_W8X1f1AY@
zHQ4!NZmg=Tf7NS#@5I4o_UFIs!Oq-KxAmHj+GC&Pm-j6{6RN4Y_1Zq@F+UFP|GnX6
z-T&iJ_nq?lwYIuU2{Sn_FiyMi@Nj$auP-lazFc&#{PXenWR=S=O+d#;%T+#^c&FlV
zuXOqTzu#`h?5nXXzgrp}Uksj-yWzGqtPnam%fN8mw}EfN5zxARP@+C>^Vw(LuUD(5
z1bzB;JOBBqsoIrauZFMR_4`V&|I;@&H}5QZdg|CsfBU~vw%@DLZa%00S`&Kh`t{;J
zKR&Kmw=S);)bzal|37B?1;IXo5f{`!=}?-l{pXX({+}Lo>p%PP@o{8y^y!7p?Vs*d
zzkhnp`u(0)?-C476j<ze^`>3E?!;;R{c{c`Y$$yG^?JPjq&N5X$D>XfGVJbQkWD!G
z_U>+Tb^m#1PEJ<;|LxvP<8-sRZ}0E_zbfAabx%Oq_J>>7!<+-9H%N~*7okA`rbgS-
z;9!6e!?w9N%eEH22xZz`)RHp67~UKCuzpI=rP9S`(%gT~GYXG2_tISY9@ZthjaXIm
zM;lkE#gM~|WZ2cHqc@>JYkgwFdvH+%<%1|4%(E`ZY=VHQ83qQ1f45M52C}3fRTZ=(
zCgCA&pMjKZ0Iw1_aA@V$G$YA$tGVB7Q`dQEuH5<!`IvDAGjQn<;elM5GB7aYY)-rn
zSxW&j3W6grPvV;d)(w${ki#~;jpz>U*?IerY9gI^h4-1CWvK55uc`hJ4?U3&oB(D8
zdF{%Za`R2b{orS-Ub|^7{Q^mD5e`V5|AuAPW}Qr#^RndD_bEHImM*z=3(^otU_>_R
z--2se=fG{svbBRRHLBda{2lCL28JK`$7=a!ES~!(4=TW*qXa86yjM<{v`#wJ%o^m?
zSGxkeG;6_!T7gt1Oowe6-Y_L=?M$CzGyRr>nr1;>S!=PX+LE>QQ4UBa2;Xozj2tN-
zA%+c@hgFT%hbVxk^6AY>=wd(Xi|EB~!(HgQuLILGmo9njHuG#Bs9@cdHzmmHKH>n@
zgwxQJe8UK5#lpaFV45)G^tug8kz<x2A_!a5*1+!J+Q8lWTh74!|JS=Uuom!!*--l!
zekGmz0$U5v5W5&X^<Dqka~_<h7#J8lV1tnd^n$X_rWl<ov3gs5DrRa>Q1;$+>2R|h
z;G5mcW=5@M_^JN`mIfOJU$%sAy8oa2{#^5tRqwxkwAXM92#hpovXD3`A<F3{BOc?x
z`#?%1N$99XciRIoQ<YQKd70jEujA;@b~7pD6ciOTG)ydHUGHt8Cz0<U$lKAi;K2KS
zp5TW@y?5ecpZ9!u9hy4z?(^iUk9RLi_bZ?Oycm|k8nn2;2hqX!3=9k^fuOn?Nq}KN
z7n2n-pMinFQ{)0#OJc<$w2lIUgAgn9mOi-VRT_}g0~cVJ-~zoh4lXq6q|s2KWm@ul
zB`ym~Z2RQmG_4MVXXO5?hqfIb)H}lyWZ2@$&(AV%6#T9E7P)@W;+myWW-<0>XPfI=
z!OA1nU|3#hxVmD+iW95X@0(Ql`I)HfQ|+sJDnEyWgowyO4Q^=Cgr)rh(^srm5ddi@
zFfc68Srd$&PZ(aYVdR}j7<nha74B51hZ<BcvU3PVc2?-b$j+e{+1Ud#3PeYpgkI<k
z?@;pmy9k<i!O1IocX$`y2hph6|L=ol)QXlM7x*=*v&{47weem*pFaPqmer~7Rf&hc
zUfxsrc@cQq;h*^du$%%iYoCy)s3>TN%P9Ze9#GB#Y3}Ok!mijzR8;g7xDy+%{8|K_
zc|it&9J0%CG#j87Aftr^(dE~H>$m2X--|41u{xdOWjy=RnPn!MHP6DCk+z?act}i&
zB-j}K<%8;j1J`HppT=UV=GmOE^EEV(U~KpwjZsGs*W{b@%axts!Rz#ki(EY?g~wGc
zeW1di6R|<zyzTdxi-xaMkV6d?PHA7yEJq1W>PXC5`=WNui$;b6vsP`d`T6OoYdgb(
z*H8Pb-+8Q$+uPNL+%!EfUBbF7r_b)!i$%!{A50fD@E!PnYft58qryi=a<*O#%e=B8
z@M0mfECEwL<i&KOrbKQ|Tbg}+UFN+#l@|*cen??fqn?}mE+X3m(!4^Nx;5!OHM`$$
zHt+d*ExPjO)9IhDMdv@=eBMsm3O>hEqpKUY$Kvtv{`1`Wdjd+PSb@$M0*~U~+?*~h
zyVP&jlS$s6PHC^7V)JkN{=d4@V~RX=)tEHwyTx=*1-i>l-TiLY>K7Ue8?M1al7S&>
zTf)Jnn98S9cY;p1xs|>CslEUG*H>3h&)t64%w4WBrS4;Q{1VT}YOHFy=N7qke|oXF
zAAJ1Ko12?AXIxxll66HxH+q}T?{9BE|9xL?|9buYx{HR~ps0Fv^UCV*^)D<+k6l{o
z{rT7H_3J-vzP!wL_L|-AcDWwcK2!aE?{rDyv^7T4-`9QLeY58C+3vpZbe+geD!fuA
z8dh#|Kiy29pL%YN<yCug-KZ@dhue6&`;K0}(IKc@^mJ<Yv#r<Tw5`16egQf9sCc|j
zznpDXA5(U#zuiw2ZZRE?)6;aj`<QBYbt5;aJU-TYT6_JTNzcyCe%@~XCvn@Ytkt2{
zZ2$duyz|AP?oTI_`>)iUSl{{c^YiCt&F`Q2zVG|qMT;36ZdU(%I=%QXuX)P9KR+!W
zG%$a<JpZ4G_jJ9pme1!*wtlxmnOjWf#Jb(@W^wE7P}u!$SN6q1?#%@c59!40C|LS^
zGDx<W-);sgx7ZTrcD|Pv7CJX_{<Qk}s9XQj$K&$plYPxJt-R)fB0Ke96YI}&<@+A*
zX1{h~j%Be?`MWz?GB2x1=WKAiSjc6bdTPp5x%J`e<D|@TW`wPcO1<oBzIJKI(dd0O
zl^~(j>vn1V{rz3v%5UzcqvG*P0vEgOe6#6v(W{lq#blSCi%g$eYE<^-hD_;|KvTK>
zuh;D^x)SJ~`ts7!t#j7An_*vHx6E(utewTrmt|jHclG*go#<^kuh#_IeGmNe<+A_(
z>;HW%<6fI39BBCR^78U0)yvc8*P10C>pA)LdVKupldt;p_x(`f7T5E6e5^Nkf8F0j
zkFQAfN}HdX8Xh;Z?(Z*ASyqN?UQdgk@i8#O8*ffK>-GEFTjP=!7q;ZwG}`~`>UyJ^
zA0I%ou99{&6?I=%$1hDiJx$UqC!*|L<?}PMOjo}+u{G~VhhXN_RiV4e-_JYP%%1+{
z#>SZjiB8A*WM_kB_&yxw_g@{hw&-r@by3-^*K}idnQXsP<jrUGV!@V-i%MT#Utj<4
z!%o+3G0P7Jn2SH3H3#J$4XZ50dsVO3%9P(J%)GWHvg}4;yG+3WM$0D?oQn=HvZu7m
zmU&!W=3D$`<MC%_&F|}2Wv!iMS6gLO`f7^qwi`<9vLyk(zP+72+0RO|_V>55jqGwW
zK;pmO?ap83J3Fl8O4Rn8o11!Mt<BnH%ObYjDLQ>+eY}0Il&RO>Utc#rofiG<f;0cw
zx7+W>O^cV)kJzB_e13f$$Q3y|9=2s(UgleND|0zG8RYFq+;+e2_nh*3l|QfV{})<v
z#R)XaENPJ7@a;x&|CYSFR<m=rMMiDUn``^+hO+(tpXZG$KRsEbd@U0+UwN<Maqpt!
zE0Ozu-+g~+bNcy3$yYr0|9zW(d8zkw5L-O1BJo;u{$3FKa6A9`Y0-I+B|TP|cXkw7
zzF5%Q)fcGVD`BW~|KGRm-F<=Twm%*;TRv<N?&=HF7SoHF!6$3Ar2PH8oj)FR8y7q{
zkhA@68EESLv;B9b`NrvfYQD2V0xl)pEk191GqGJZXn)<`oLw)MS^j)7`SZhe`E{G}
z4z+NmMkf6JJpcckiOTNJ=2gEtd0f6e=JBkTmzPgJ`#P(&^7FIQ6B87Fp7gJqG}+(I
zvi|Su`0N<-x<5ZQ{jUA<YW4bM{`2i_CimMGy;#@|I&^47;ayN=KTZ0D?@S|AP+FD$
z_o01~c$NL%FPA~VrmL=fZIY^Y(e2#rPuFZdck1c%__$Bit;gl-_vqXY-uw64?U@#Z
zN%LyI-JFyiSM_pfOu<3ctut0x=<okiq@}H0{P*ki=lg!Y^L~GCuW`kP2Xkt_-IO#=
z^C`Pu`yF&K@=Q=VDStO-dVJkZQ1X3wY3a-R`|D?!W>3@Ie#a>H_O`S4|Nr}bW`?11
zbpGB_P_@M)VW6=4?Y8JX%V#q}&+%R_D}H|NtY~=5#NzX|=JmfW&tElP-ZU%Z+uic}
zTk`MQ9ha}KiL5(rnR#i6OxcaZo9XjwjZ#ib0G$@}^UG!bVo(PE`}Mm2=Cre$-fp{{
z_UFe(SNFB0ploq#YxeZ6uC6aHFROEl>z(=ie*gSFS?guKv(0X%PLJJmGi~<Nr{DK~
zes=cs)$sVaiq36oO5$oR`<kcz|NGs)olo}D=lTC_{{J{`&*c+o{^uco{fY8@pXYAL
zx~g^m_r32%wZFco{Ga#mob~%TpwrqOv>d&Wy?*be@As;w|4CoJ_nTKcpX{ce&t@;r
zy}fPc^Lf=>eKFc$cm5>a+f(W4zOwk$_4V_+y1H~CH!XRg5%2x^`FZ`*-ydu9NE)d`
z=WKN4v-|M?R1E$4dkA!h(y?CY=~wT6;x)fx&?{{o_qg8dR>tB*%HogOr1K))9{aL>
z|Gz4?KAFhw&R1>W@wKL)U;|~7uh*jW&(1bKU-f$J^tIb=flANqGwUbWe!pYvZ~Ham
zq9H@V+SJ?93=At4`&qx;QuFbsc;&-Z@lA*Mtf$0$|8!b^dG_^nmVduoE`GoF`?aJ)
zNxgEmR_gOAl0YRCBQx8QO`D3A@;|Wu^<uHlY%^VDx1JN4%jZmD<CS{y<8i;fLE+n<
z51RQeZOy)J^Zico&8pXHFYhdV{%W_t`W@CEK}SjLtNs1#R`&X{%KbKz($3BjmEC>q
z%p6POxmKm8K0Q5Md_>S4WX05<Ak#rNEFbHapAR}@@BZI+<=uUMr_Q#iEZSB2dRo}p
zsHcBEpVzmX9-Y6}6r|mm-*(Emxz^&cyTfXJJZuLQiJ+tV!o}OOt9*TD7${zkDfR^&
zL}ikDYs-rpTa&J>iF|oyXYswt=W|P5UD3R|yF5PC?DBH|^BWQm7rkD){aL5_ycHky
zCS)&m?G}4_-2PvoT*ZS%ldLNmZ*Oh&Zs(H?n{_sK``u}Qi`||sXy!Y0xBUKGw_Yhx
z+1+7h=Gj*FUa$Ld(LFv<=vrF--mhUdr~Te{W>f0vQ)R+R|Nd7$?llKB;Xp-`nYZR!
z(BX$O43mwruB=$JxaMgapX@A9w3^?mNanNu^Wn@)V|DTPnnIBHOyl&lJ39(fi`Rvp
zn(S{kbDnK=+Um92y!O}q{q%14`?Mz~Chq)xuNoAAY1{9XX<H>FPSc5;<jiNOGFi=c
zmEKa*%u6cM<Ek=$eR;Y0(yi<9^?P&T!aYF?DpIG%mYoDOf<7LTem>dX4pbA)U)*nJ
zrR?4p^Rjen!NWtFe%1atCY_&hJ+}PpqoduM|9-pu{AT+6v!E8i#l`N=-|c>XE^T&h
z*xs_6n^IG^Cf=K*>V0W%^>?2+78`$=UR@KpIi~LC)1NQ>>vvtc1v)BB*}YF^wspF0
z%nk!t>#{T6`g=ocXFE2tJ-xpFUnv{E+?=YfuR_=BZs!f2rXN2~*v~@I{BB9`*W%lG
zyK~p=ez)t*{{R29*UmLeb~|VJd=8J4$%<{s*LHy_)6Zwk&w~Q!tl4cHP(=o+x8K)1
zw+5|(T4m2%`?%LUC^B*;xBec3?f2`d53bC<{^H_d<E$$yz*XnnU8U=GKAZLB-CgU~
z>vre;`u={ta-W3~sNvabes2aS*~wa$>CCoXz3=lm>zk$5V~xw--BCFSN<DW=uRjHa
z-_7*-bIab|O1-%$b?4J*(Vvdn|1$(FmWkS$6<YA>mSO3uD<!Y5>H5wx@%;SkEU3iY
z^Z(!P$UPN>X=i3kyzFPK3$m{E``ziFa=!A@N%hUY-|Yq^ahop}oL^pE?tg1r?(A*3
zx1Vjhop*YXYxky-mzO{(^m<%%E~p!DJ8!q{@;OCb+wN7pmZ^Bq=z4se=>Na>|Ia;j
z>eQa!?{<6s`)mEHO*-#{`uv(n#^-H}t>5iP25AJv<-gzW&u>0&H+!0HwAh?o67_!`
z%U@pX-v4IfaXHIZD;5|1`}sUvKKtID%5682y6@C{KKt_C-s(a{ZllCQEj&^t8lZzQ
ze|>#D-7NQ(is!$7-}k4VnPGUd;4p9Tvzh77-fq8tZbjhYq9+sGpOx?b9b5I~MPR|F
z_4gJyHW&SRxqNy0`FS_<cE9cF3tm2_;!&rhWl>6>{l6bMn@*~^9@o4xMKk!*^!<O9
z{`v?y_VfS0_y6Nk@BaDu*|_Y@jW;_U_idG2e{RROTiM0`em-Ab|Nr05f8Y1d2ZiF*
z<Dly5-QC^KzwiHF>u2-v2vhL2dGUW=g=_D9u9y1gNasw$WH()vUsYA__kO>$A@T5{
z<SVOwzuT?9x9aPuMXueKR)wxEd3i}yI&Vj!-M=4?_xyO&Eoqt+0$MEBBW<qNE?1Rt
zv5>p?tm*Y7-qZCYtx7ULiRanb+2XRC4A;O@76I;{cDkfZ#fPlZ&pkoK?~^Z={m(x*
z*qp5ydAH!GX!sL%`(J_Y_Iy4k)t|rRqT9<$OTBlMyqqNe|Htv2kGix^Eo-PdCYk;O
z)UpSaeCuL&Pm3`xe01c`6LtHO`t?6ggCb<>j13X#a|+#}w&lz`Iaz&uiQ&6?tA{PZ
zMHgMgmli)i_w%WK{Y-cH+AY(9ukCYeW?Smq&NtH}GpINI#+xmd{Xmwo@yX2i`|Y-V
zGaK)zD=UM!J)(Zs{X8B2>}q)YS&(C7YCarPy$&j0LBVsNk=Z!y%#0|X2$|VSr<i42
zSYY$%g!0aRzg}P7UH)FGe0%(+6wkbUKcD@1B)<OyD5{@M4HuiR<=fV*t69DK68!(w
zGX9vgE;f2j(J9UBJ>Om~pZ||*@`qBR)KgPT<D&D*9e%yduit$vJN?|8pQ36HUmr=+
z{FC1+Z*TYa_jmvI_x4U!nVqxAGjHe9X>YdQuLCvbz-?YoQ>=F4y9tWUn=boVr@p$f
zGP3^f*U2jS`+g)<eS0(W@Av!mp#GF%yG&5Qsic^~qoSa2IA{0!%`09Wy}e&9$<+V(
zSo!T{dhy$>*QedJ{K)luUUi-ws2-eUqB+;P{M?~d?&6<Mr>Ec8kO&$Y{Ct3!KjpHo
zxvo{3BFGp}uJpJ6TT*KIXj*jMNl>i`YSRj<`>oNNJZ1L7!|myhj&xdnK4TnS<@@#B
zUF-99zjM~@dbMhive>aU&847<7}Vf1JT4P#I~&w9irrmywpBcCMk6!3nCwP@;N^b4
z|Ns5HyvVg%<^R8&zn~JK@VM;uOKfv)=WO<^`u=V%sI$CcMJp(=)_s~hKO{eH1E~B4
zRc)Yrns~S^bp7q(^R}SA+tX{&`MR^2es#UqUG6)3+O@UO%l+ruS-#)%8I=D2T(AEd
z{`LOKmBGuOH8As?*pPVGDCtOtlJfOg3!U53j?0#xnW7oI>EEx{&q3w*x_!T1z1em<
z50taMrk@0L2tchhZ~eVna^5+CS|Oko)T#OZzAV48I$VExd|l-^o6l!JWn;hXw}`L1
zK%J4dx3-=R4UY{qWBsD&+?Mk4($b%&<Nr+pxh#Hvo#pd6#hZ?bMW;MFGxO^67SOT7
zyUN~zTr=&gn)Uz7pr}7@_dDg&lart(N|@FH^^<bdZvv;4`}<DvoUFFgv6*eAS#A`l
z!!WgPZq28YH_PwWf?5#ICwc3g>{Ooz>JU76)UB`A&Gc(a=H*LkA~$czy=?|+dxS;j
zZauZL5R?Nx{XMel^}5;lHIJolrp?X;6>rn#oIR;NKPKSNt*<W@_lM1Y4)P-?we2W;
zoE5YC>$T|gA0HmV3arnI<^O72kFT$_`|+STv~PR<eY<}9e-(@;y9zJ5im(0l1JrZ^
z)o;goBv-CjaUwE(Zm9RkF7w1gEj}|07XJEp*8KjSOKSYuXXe}6^V@z2D7%?D{Z>!-
ziu!+_=UaZekqk;9pk<yfudKYRm96GKZ%*CcUrWQ+$AK!wQ)SGH`ed!sK0Z1MitD0#
zmCsZEe!af_WB%3Z_j|(woEUyofo6>wtg_~oUOTxd_4Kujx1eUtJEtp=o72{Qbd3k~
z06w?d|9PnG7gBEX;Q+IwMZp75F$ZcE{`oY0{~1uP#QWr{wwITeg92AG(k?!6^I5ag
z4UEi1&t|4y3)+-)c8;ZScx>s_>F>nutO#5TYSi!laa2D`Gx8&-N!ZBDzHVF1JQa5N
znu2o{k9&CJ?e^qwy)g6E%mwxC9`_i3+C2a7nkTbBEz@-S-;w`5_SZjIHakyiHq$Rq
z<M{3N`*!xfF81#$dHdw#<kLyQ6aH^ml(6MdUP=72Ip-L&Z=F~;#dPldTS@Epe%rLs
znR9Q|*H5#w5?vWfe5YKF4Hllgbj`W#`~SW*jr+a6{_ksTpP=o39?N%6O<M(93-JF$
z`TpN`L+AZ}>0dvqtE;Qz{XN_2w_C&2{N_YB?ArCPRXh$<0EYd#dwE;#ZJV!Gf?r--
z><+30YrkJ8Dn2e-{^Uk-|Ju6!SN7HZ2G!k?MkyYk22uI_TJ!RImCygbipj_|%)GQ@
zPR*y2pqA{UC54ZVS^od?dGmR@-%CLCXZHHNpmCrjrLV8Cs;{jLUgmT1r270lm*)Ni
zonRXh7WQmGGoRP-KH1L?n)#<)b=|2A>ee5ZDL&(M^t>~_tqG`*12sA=i=RE|vwnBN
zeBZ}jreLwdpaMz8(x_d&t^&05{nc~Oh{62-f1ZO1u+Qh~|83UkR(`+#|35GB_3Jej
z<!?S~wtCIoyxnhCy)TLN19jY|+Wo(s+;2N+$+7q8pw17Eq|uUVn?&D!JT8C!eBHOr
zAz@)^o}dN3Z}$Cu_w(!e`n{LbG^^iibO*T{)cSFCU0ZtI{(lW9`d<}4wyXX1<dV1k
z*^S5Lc3-lLzr4&BRO5isIY^=Y-Y-F*_Tj7VH}CE)KYyT+IsB*2PRC}pmseMZNB+&5
zXObD@XYsJ*&CciZJpb)IdHCJ#_wzuBti*4}_j}dPZzT8YzWzQRR9&pw@u+Lk@%=x~
z=1+Tie~rq{zu#^bf4iB!KFH4h-(T5+^>KTP4zh|rndGgvvd*UD#RaBG*Y;(v-@EPC
zeRbbiA&+Mj=`NUGb}RGh|G2ErZADrOKx@2TUSA&%YTkBrb;T5)HGO$+?{BZ{S65e0
z=QX>bAf3Ob&{4D7Jp0<3Ifch0Rr~Yzd_0!=^=F}`u)5!w2M3#tYkz&o+4*$Z&WCN%
zmv)!G-}LLuqn*#^oqlm~@#H_hw}OUDK*K89Ya>6-x|KRTw&?5CaPbM7BtT2m#p7!x
zy35y^-2ZiLdsYmnvu5+_#p2A{+j8A{rM8|rX8knj|KIQWtKYw3Sg;K=<nJI`dVrDr
z$*0r$=NZ{$CX~IsH8sY(_}Q6PrB9bETBPJ}^U>wkmzSTHW~=+po72_R73C3Xt`oPX
zqIds^TNRIcH>aGOwB91{E~s4v>ZWCH`4<2G*Y)XQo34xb&N4YUJAdC!x9s~Bk9#-m
z5-9!n=&1JHi|M7aOfn}O?G~>;+WCra_R=ZeF1pLF{dj-gwYAaHuigy?WrmtxFPDQ-
z$={{f;WZ1R{6J08H+w#xleDk<Gku+`RY?XYEk${RmgnsKdhIIflB=MN5ueT&pTFX?
zXjfu0ubId0vbRO2G?&-Byaj6P?f-rEeU@VA-3=$zW~V%#TYipJJm$mF?EHN{pS|ji
zId$;){Q7xox8Jk+{buv|>FYrKk9pPac7l9+Luct0^LrJ_pdsYj+j94pyajpc*!#Wv
z-tGH&Hvie&@_Q>kMlAQ6YgGB^38;#bwJ!5nAGbHlGWPC<l#`RB?#G+w-Lc@e`;h<|
zH2L!OwmE3bL@YWd(BaS{&|tc0-lwv6JD;b`&fVrY->w!^u9{le$J{<M(|Gx@-4*Y*
z->>@#8g*J1yF2Z??e{Z>`R!vIb|rzfhM3;Fn9(j<cH+v);LBUHua~^LV+rbJGrsKl
z`fPUovn#>=u}^<0I=3zHooxn6m3%fI4uH0>urAS_#vAPQ`}h6-`%bAf@k*JTm|>WF
zX_@crKl}fG{|_431?^p6Rn>93yv)})|K6Tg$G^V5e%|bM&g5gg((5;YwuG44#pi{I
zbj>!&+;nPVulYTT`St%QbKSMhyt%nKT+0(QpWzwwIBgl|?CIIQv6JiTzkiv3-_j)i
zo{eYLADhb6Yqx35{vPW2>E-hIX@_~u*VOHKw0p&@bJbB>GA6cii(iY{w&?6UTWiqR
z)7QtM>sQK_-zl8B_3iEL=g*qokBPqcYR=c|@%Hm;K6##e3_9(5mT7iacjv1<PzAg7
z>F=Gz&!0W+w_jIxXNl)z(2)LC!L<e1ziQJhfBnAyKdz+3YH8u)V^^Q=)qZF8#-<|l
z>@3sMb1aL!<mw-`il2ICeBl3=4~O~FKRh^C`D*3zpuoV1g34}7{O8-PjNkufmF@F6
z#eSedNag>&e^0*M&OaaME*n~~YS%;10pk5~wqDcDhu^4ry|(zr!}jMJkIQM_X8N_G
z@Nrik14H)KPuAY73=Qi$wb$=40u9CP`@Z*m>i4_lppmOfi(I?cY`<3p>Nq|-GjnqK
zyh^pp%Y40EU0rY9F)eKk_O~@vpIZ_%O)qv9BQsmd^w_e<mrl>l+x^x7^+wn2|M%-o
z>Gjy1&t_$F`9$yjcBlA!OzG87P<>=}zvlC#*C0bzuis}SYhAYHXvxvv2l?wJc<b*q
z0X4}Mw#!8o-Tm?Laq-R6=}$Y9`&Jw+ISTF{KAjrAEcNuXm$$d)_m&?4jky;;?ln*Q
z@!?_W=H|*tpn`qpuUD%-AC~`T02=2#S^9qO_c&0e`_=9{Q<!HjopNno?e88*W3}Tl
z#XeG|Ss_Jtm(Q=8b#bwK`t!Nv>yDNjUA1P-nbPaA(?Rni(m5LrW?k2d-?!(@yOh1R
z^L9TysXjku@z$qXRyt1tb!S$_@2_*~k@&bYyPa1$ER6LFpRCoByXE&|7jJs=dj0;m
zFxD@iZt=HU**9~y-`!X8Ho4z6jJxwy-`uiWn!Hjb5sNSV-H>?r)T)NO%~LLcMy^eA
zZ<X}E^Rvjgv0+a2yPaDntf~M_n7rHn|KB9(!=Um9+(gxj-Sy-UxBi-^C8f@@&2o)O
zUtI}3RqOewH@`-?{9a``sCe6a&MLdt%pzj8N$xEZ&@BYL$3erVCfV0?++_+~K;xq_
zwO=l7owF_iG+ua;`)>K2!sCCwuCMo<t{1!Myxs37CzSiwJS{nzb$3^3T+PR$QvF*q
zE-HZ<!k`HQnW7VlmOmaeXIsW@oMn=^DJb!q{ogOk?R__=odq>gmjy5POZ`4;Q=(U<
zbl#4KUa719mt2cXPu+ah%=`bpzn~%QXCDspuYX!{H1qbh+<Eo?e!e;m>T8|6f7&?x
z+?tQ)US#hEjmo{<et%uvogIabd*p0)9h>xZP2}dV-#<UyN}KF!7Ws1BG*GFq>-D<m
z$ID#0#dM?Irmx7J?Q4G51QhpQAG7gFrTqW<eZAhI|I2q4Kc9BB?ZEv%&&<J1ieH6?
z+juW;&%ZClowYgreB9%+&DYtabGHOOJ3l}EZ-uMo4##G;)oWt6WCY&K*$_MV++6GD
z*P`>+7A{^7YBMc%?>`6X-#Ki0RQm3Y<>7XI|KokKm)AybpW0{p<$^P4p2n*5Rmk5v
zXJ#5--c|ZK%Fi=4xbJyIb{1#=`{~Z3-Qv$dgZPh*c7w`JDf2*0cF+`vTc6BKVLyw+
zsk<xvXPfDQdTE~Ob3+1lJzAqN&wsw1?b_(=>-Igav=lp^y(#13BB}Gar><tN-#cxd
zZS}f~w@#fpwdvP7E`}Ac=fW5n7W8FZT@?x%{>fgqQ|<emVt=<DiH(=$3hw*Zo1X&e
zSWQrLF1qBYp1Qc#Ov@nmt+YXc18BrX(YY<;ebUa0ZqlLRU&8NrmNoO5op2S8ox;e>
zCL*~#EVlCL)SK1s_kMnxUvF*y;~@X0(|WtF?5I5W<KyGY3mls_?H0b2Iz4upczliF
z-QDH>r>E&=&jFAB+}xbL+_{|(H1!4=)CRQ&BR8i#y%Owy_CO=^=eh4|(x>kH^ESW!
zG-&GK$HVsY7Z(<~y00@0k12EoO)G)sU2UtrX#AYD>;1mpo8IkuJuP(Q`83U?u_YH>
zL4yq2Zs+ZmseZFjwLT9tigISI_4YOUc;4LKUk{oq(uv&k#GCsCs00IbTdxFd+Licz
z@Aq?{?&2QM*jv$Q-SFLIzu#{6@0YX9(v18Fn#%Zm);#^>B-QMakB*kPaRHH$Gf(U9
zxB2}1{QpbclTPO*x1Tz73N$z|)4KfK^tc!IcN9L}v`b>mrcFlM?^Uh79>SY5Ehs8A
zHTB)T-|uu{cWude*RWL$G*<Aq-`)<?mjbo2uk1*>oxA<)6wP2zB@EhcxpmHlio3f?
zK|R%}tJm$)lFr}rQR_Hp_E}KbEd|ue$*=o7d(*9q<+Z=RfhPMv9bKvZ^4HgNK^N)p
zSw5LCr}SDRD4&CR3w7Uj-+$V~t+(Q1#p`QpKVRSf&lF_(i;Ig-zj_YJv!FTd;+IRO
zU;FX9;&HF}x#WIZP`Y}y@Ao_H)i>8v_)fj$@$5k}|G6Wb!o@cd+o#stUAs1CMo`r4
zZMmOMDEEWLoz{P>xWBLV@)FO<pdx0bQL2~ja_w`VR`{L|hq&W+z5Dz9{`tfF_H%^&
zZ8nMpUDcgBb*gr*%8dn%&0pT$-hON=XlO7vGBPsyBG>l2Ww+OEiSz>1Kld2_Eu9{x
zwYn)8G?o74vVXXJ-klwVC(pOfuX?po>U3`Q>e#ZIs+X7fuCCj2kWG5Z9gFwp>;Dyl
zBK=lZ*p9c`Zs#riKI!Z%Q|-#*&p?w-YvO|cU*3>-c+>B9yVI}7miwNcXB)geZm-WA
z3qw#P4$6v8Pfwq2BOi4;w)*YXmseH>gL)TR^6u{16#*K#e)4wv{d1t1z`Yy)r_ZmQ
zW`4hB^OO6g3O|3Iub-EBd0A-wtuH^H&tIN=ysz@#&*z(KetrU#$dlFm^;Yi>*Z%X&
zeE&&M7;nqHz07;M-pcUxaiID$1~g)1QJA#tZrN?nteNZaHKzQwUjjfKw&nBdtky<v
z2ak5%DLk$@??3<PX}YKPRDRy{a@p)Kd-L*lcR(E#Q1xB)<;6tM(g9YrHL;(cp9jrz
zUCYS5yv%oV!oem`!}<Ha-|y3p^+-l;NO0_Ze(LGAPECeC@hi9QnX|5ok)dJz#--lV
z)9&r5yjsqfac|Gg?!A+1K>Iv@JZv{kKGp+jAy(OeRv!HR_7+t1ZPI?Oe$x8=p2?t6
zcIW$jzds#hmtRw~C-d?$Q1uTQxdJT%ov<MS<m4TNkBiRRet!a*u9#z4ys6^jBT&2J
zs=YO+j;i~zSbpl=*Ey%AX#V{BzCQkwY3UI`_muOt-*v3g)>i+1yWP0r!vj!jQu}UV
zQY)wd2<kwBnnX3Pqwi}eBo>P4#YF6lJk_ngFXC~UCdkmpylJ1_Y(D=CG@JS4<mAmI
zFE35i`w_pdrt(^3`drW;-_8e3+?N(Qw=+#Xbp7y`mzO~!Z%?KK`$fJy)I4j?-*2}o
z|9-u``TxJ)*MoK?ftrWw_k8jyyPdloG#?$mYu}u%#q#xk3h!0F-y0GVvZiQyZ;^TF
zt1CV7_IAtXmfe~@?eqPr*K7BDyOsU&*4Av@rP|j(GsfVWw_nco(h|?fSJ%z8udf4*
z*KFD;eBnr^FlZ1urt0NV&;pR~-DS_t%&dGiGd*TSOmopM+dYTYL~bquU1qYNneW%7
z?!4oDva@Fzr$4*ot-p3@$<bXem(9MkK7PN?Y_r_0OSgb-v;qzFfx^4w<)tW}h&jjQ
zs&$yz`OcVLkD0vp+pX14cJ=?a|Mt#WYgKmr{~yI{0Rfz1N4h$WWxwZbJ=k%q>6iq!
z&;c>w-i^nPh)HKXy1M$<iooPfsnQK@XG1SWbR-;YQi~8^trjq7SkW=%^Y6p*#rlcg
zcs|w{R~O8?9<^rb!=CKgqHAY9gq^$h{G{-Y-@hMUTIzjhxAp!!C1qv9@^>*lb1Veq
z<m3)LfBNJ}!kHO{J4#*#?PHy^e)HDs>yH-q+c~AAEV;Np`~SDw`7iG5G?ufg$uNDt
zQr5cc!Qy_qL-TB_TcnpU9C*L~|GN7IN2AW2-IRLTpzKYAi@W<`zqwY2p0~EPE=)f^
zuj12_&Z~2zjoy8He7xe%55rYqYqP#oo;-Q-$GhF{A3T2CY?ga#MyA!yu(eUG+~Rr(
zPftyCn?HTpG`8^Ya2`pcBUxq!wq<W5l9G}PN?rskKJV@2b?A2f{$76jKNqsz2}sGx
z_C{~do4LojG$=@@jYqPnp@HGY@87dQMy`oy<QCWC5P$N#^3M;$nAljuiVq1oaeHp~
zT#lS~db)n{nHh#0+}x+P7e0v2-`kqM|F2l->uXaj=EnHXvpM+b>FL4`4;=68tCc=*
z`s`k-@^?KC54Rt_crox(%cqvMwxo-TTz3>aWV&?e5>K90=33s0pPy27qPO|f=l$EW
z!aq>t$dMx+v;5}GGR=PU_xt_p`S<o0K6c}gu@K0<zRvaWvEGO8-}kriN+&%(H+Pcy
zRApUV-p%RfkM+q~7d$^F%i!?z)YOO1pSMdIr%Bvd@~L#`#f$|ST(e9vn?Q|&SKmXg
zl`NiW<LKzPqwKBJxw+Qt51yW1<JK$n@Y>pF28QbD>OX%zpLhE|_e1HTiy0d-FRQVz
zu*|4=_w4L!!-NA2tN&VleRPx?RL)#@S@N^aZRM(2@2zCBZS7rLT>fk8IjAdvK-Jm1
zJBybea7xOKDe?PK?-&|-<oI#%3jfgcak5gqZr>^{6>b(e926Y<@%8%sVik8ya&BCB
zvd9diRjF$4(`V0=Y;9$~efy>nw`a%2=XP~}Bs@Jm!#2NUy}0_s$&-#*Sz2DxbU3T4
zs~4a5_4Pe^xSfCPt8<&`TTOFke0p=!_{gzii@c_46_k~k{krqxN5zq&M<dU+rMuK`
zfAc11$<n0@LskZ<MR#=goIZ8xkbM20M)P|W%zS)&n~qP^Q&nX(&%5K0m#3F?Wkq69
za`2`&>+*Lk^XJRIy1t%&ZCJOcc9?>K0>i3RN$2O;t_WQ%R`u;or=)S(3Aw9pl$4Y%
ztPEDSu(Dd@+AU^L@POgg*6jA49-cY2)nZ>?U3H$U=DVTrvD?kXvtmz9Qr(zxQs^(+
zoW0fGkG;LU{cCr+xK2caYq!|LgU#$l$G31qMn;}Edv@!sd%ss-pQO>1G?hDbb?E9g
ze)~THmzVpqGpvc(DWvSyb6}#f`-KgO&Lyv|aGpDN&Z6SOf+wD5ofltBcyORG<L0KN
zC!f2yxg|Y5)*JS77h^-GuzJ$NL#;E+a;0u<%k4fl*E;#^EYpI*!h`1bYnt8r<r2@%
zGR?TQX6Bo~&W?^Q6=<YtF|7(+&9*jd_5W4z`}e(>sB`Ms+1VG@#ad4;pP}$;^Yiob
zXYUcXDs^{H<z(^A!V@DyR)_K4yLa!yr%y?bB{o!kPOGS{K793R=r@g!mJRtwZdkaa
z@V$|~e8b|4)(wlK92q4ecC)_B9GNQ792rA1KEav6-D0{4>FMo{kM}F9s<P_o=~>kL
zFsP}iDR_NNx1ypV;oqO15(WtkZvxN0Tf6<9lamwExjB~2Yu2o(dH(E3r|^q=d#$(S
z+-y2G*ZQ>F)i-nI&NVE371ASXEoNzHSx{DXOnrV$lm7lcLJS+y&Pw%2nQ}==N={Or
z`ugSN<sN>1Zb!RB*OoC>`S_fP|7Uz{N94TbX69-7@qGuI*_jz?YHL3}IVs%I-p<T0
zO((L+viO;Tp<&>&8EJ=mxw+O?eSP)f!b0Y2>tegz`{fqa{QUH5e(0)Ii(+?|W!%|e
zI885Bt2#tUX_3;&ux|`5AdnLE{M_8aKR*gvT3Q?eMW$#5v(1|~@58rmZDFfjKR-LW
z_L-kb+n4wE<+~OgxO&y}zSG}brLRxP`C6?F>n?kH>)`3r-1FwmD<~<MVmryTu&BtX
zTTJ)MdP#qO|0#O0QQsmiU0oH*Jyk38)c3lqD=Q|x*{I|6``g>E?^l}T-dd1ya?&RE
zO%iu>T-Vh9|M%;<?_8_Wl>X$vPg3s7FK;a5NqF3`vGB+Z^CVEz^ht={>eyJwlYD>1
zv15YC5Gha$8k+S<NFO%<$0C^R-qWjm?3iKR$w{g=w&&0P@NPxy?lRYYIa`C89|gw#
zX_9?1mQ7o;uPf>4@o8#m{`hQrM#QypY3n4{yHmBp4a(oe+_-V$z_o8rmwt_mjAV$@
z%liFfvcEz8J)6}r4R!DCSe}_<DeULx=i%we$nclR-QVAzN7{@hc)8!!Q>-t1XPF$F
zWtx3qXL0(Qo15AD<?Y?Rzq|YO_~S>90v0;4b_$;o6%%VaIa&Sjot?!2p`z`4vQ7Q{
z{F5e6zPQ|99#qf8?k<~ZyDT!|anh&ohfkg?iI15#b7tp<4+TE6Og!uNRD66?@$1XV
zH6PEsdv$g7CU*@ZAt9j$4<9l<c<RQ+@Zrr(V+Q@($IhSUFMf9BAybKx(xUJq)(eCM
z1qB5~6+JyYJ32ZXTwGZC<n8;q#r2iU&Bgin_%bdp<K>gJQmJ;)eDvs%fSg<(DE%ub
zF>TzqF+ha%>8Yug;~kb?&APbAmHX!6S$9E|+U4c`k6&J1zG34=$HQ&B3$JE<6>r_S
zW5)@(z*V61eY{`(_{quY6X(t2>ve1X_4W1Z^Zj9~U6*=IP3g}pn{A$dZU6jFbqgOp
zdBWoF@Bg<l^X8_d|E9mcwxss=w~n437dJPyoZQ@tOFV`DR-Zb3n)~UgsgrFNnaJ0E
z5d^t?#tezLmS5^yv#uUGJKLQ5PtK=r-#{aS|396(x?b6=FA<Vxe!GEF10=!pB;N<8
zD0s4gCY3%=f`KSG0xlIEOPS~K$ji&u{QY{Jt-oL1Ue3K=&NU=t%1rgi`4<<t{`m9x
z{KGeIdZy_{FY=jb#5R9>;bS*rf3^9WHyfv&pSSk@i~|P`GHQpdIk3R7nStSc?RVK@
zz0%9$&!qW!P1o!F`T2SBiwg?_LPd{uiy!~>^|hdY00TqB-YU~$eX`l1-A<q9Se0^t
zQf*b0RY)i(?QW?4p7-}-)z?=G3m+fj;N+ZWu~f#rPsVY&UTnbnI9pI5%q^~W<$kXO
zgH`D(7I$~|H+Oahe_E2_392Yotk3|J+6xyh{PFE}zM!b+()%qhHlMdU{O<1V!pFyW
zPfnh+bY<9DDYrhEPEKJp28L79bh}puFMo8|-=3A>%xrW1_`08}a`tsP#Xg|&qnrCe
zXGcdzN7st`_5Wpme|vkliIuzH@2^sgu0{7#Z`@K<Q+uV~aBF}4{(ngu-@M7Wx!7~!
z<jKw4;(9OiIjrmcSWKEcd7%c^y_(Oy71h<rUte9_bbN}Ixw*Kwe%zVzzE5RW*9I<T
zOG-{w_18ErU;k&Jy}qEJU`JP%Q(2jrjEu~OCntq(KK7hAcW&?I^z*OIpY9Y^pD<|>
zlWSnWaz9y+kw?2kHyxkSCcaSW+lPnFE$!{E&!1ku{~uRqXyB$4&n=mk+3wxD_v2Bw
zeoB9)ASlk~{JCLqY-4^;@?()B#|-;=lO?2=7u+yEwz2S2@?(kPAfaFZ>Ejlllr`s2
zB1q_De{Zr3NXXAIM`mNtQm@2|i(DnFN>&_vygGdSu^%5FuPtH>y1FVfaCcd5OIzEb
zh>b~`j&IbMH*X%OqWgDlMeeOFj-5iP1s@(brlhAYE`ENl;>QQYb+NnEDuX^}-`itp
zRq~?Y=jZ3l3{qw}9lJ_jC*9tb%g_+Fw@Oh<i|gaZk4DF*JUiIT4$9LnFD<>eGFV-s
zi;2O*)AQh}(A5_fI<v37)374<_O^gfQFXsL2juJjFp7&$ui?IsetuprsO@}hZFCX4
z>Eu1G8|z)~RiB#`v%8EpfB#>zclY=6Ge{UFwfrl#G&dK2_wL<`8yl6ct&7zz_Sxi6
z`|FEiS=qKa;Ry>CD9G4WiFi-fbIr@sbL*9AW#g54@ZsU%N$RRfN?NmaFw6xdlocHv
zy}eiCR|p9THvafgF-0qsOHNMiSL}zqd-taHYu-KF&j0nfhK-HP{=eU(b8>Pn?5QlC
zV^bOQtwKyuTbp~fS?-}dm7gmDZ_IxZyQc8X4Z}6@`{zA>{(pD*`+5ItzkWV%uWV;0
z_wC!au$_l@E8e_$^Tv)s<@>>GACy8i9`Bb=etvFl&E1CH;D{WV%Qr0AHiB9L$3T^f
zMN-b3={L+<j~_Ga1;x304=7F{<w9j=Z*T=vL*Wrn@+kbbIOpaj3F|VQW&ZQ?KKxh{
zxp_mzMWrRnmd&a(`sp=AqjCNIe^Q6rcqiL-9gW<OzzC|OZ`_Cw(T|g<{{HUh?)Uq+
z+1c4Ox|){z&wup${r>Cs1@F%CnQg}V`uckJni`v&+}w?Mcdd9Njaas3UuR=Da^y(D
zxjB|Ij8eOvc%GazMI(^u|F7%&4U&#<*i?PtczSyJ`Rxp~XJ?s8m}ZF>85ybgXUR$R
zE(<t+`t|{ahO7T%>i_+*)QjEKa%rjeYy0$u>Gk^jyu6^A{o}LQ`CfA_)P#f{UF6yw
zur|u{%iG)H2Tp&!urc{K)A`ck;=|wG-ac!)=qLv__u*@6qe0XD3o1T7+EMyitfr>s
z%j_6XTkH3?x6XfmeSOO3<>C_JQpjips%HWP16Bs9s;H?girHE8;nSz4u+^<$t6evz
zo#p!5e`WpVudlDa)_=0I@G+a$6pe}Ro7DOF`7JCgPRIq%0<~JLO1<j)K#i*O^YdQ5
z*I0Np3)Bg?ne6rP%gbO;s;CEb3qSt(S$t(>Fne5F+^^5UYoknWE}nIDYxea|u^tuA
z&&h&X!@0M&{p#k3-j<WO)%tOITH2#CGmU?JE`D`I)28wh%hlE4*Y~H{{dmB9Gui84
zcR+7<clYV?y1Y9(7Vcj>BW$&39M4xPSl&;T0M#VPGSZL)qHh1KH#0}(F(@rTlLjP#
zd`f;i;~1#0NS1&qbw6|cy7={Vv4@v>Pk->@#f<k6QBhK$p3$wX*^du2GEY*Q0vf5y
zxVOhrOeaF2dWw>wk`j~szaPq=e6Tj!d`tfQxNjaoDQRg+rlz7#Pfx#Ie*f3k*Bcj|
z`n&?R7NGdK-;EnL7F2(K_v6E1epP?X>obkhH{{>9gLDX67u?-d>iqiJT2+5F|CvUq
z2D!IPKogp5;tTxe+sUpDTkGWH)bzyjtg^B3<tN2_G8PRF9wfx<sSwP|%j@XxH$R+`
za<c5rjmEmazaCy$8Jux-l_<lD`~Ib`uN{@n-^2LesngfZ>F1MPUt9a)^78&O6Lr1H
z%FNEqx969ZmNv<`A#k)?e7dcWpkUy{qpUAL4Nn)>2DinHZi^j319!12lJfKQt4+EW
zT+B#FPHw)pw;I&j&A7QqH77SWwLewR#>PfKRJ8TZofwmh3kvsJoAvbcHXWb5E@ER+
zK&YtiER&1z2FtHzJ$&;<r`lxYr+dNs_U!{Tg||fMN}1=K;pSwlsH}YW=jZ1Wr%pND
z-BtQ|?{cm1bvo5HD=P$7&Dg)+UP(!5!h{J8plou!fBSaxS*F=(SM4{0Gd-wH@J1TB
zZP`<sECq^QWz?qV;TsmqpoNMISo!fC#_8u4#O^Lz5ww)+SfA|b{g+cqN=(G`<9gWn
z<rH*ucye!TnP{`}XY9Tj$=KaxN1Ir=A3T4qUM;goN#EL9nwg#N$TZ#P1*=xoZC=>Z
z!=ur~R9|2J=fh$C4I4Lt^nHDCk(po4=D^P4=Uh4t{+^zWe}8?wxUaT4=iZ*kZ!0dz
z+EfS}Jb2Ke_!$pqM4|FiO3jCZ>>D<3o@_fy<orC_!>dA93y6ue9XaBn6T3@9H)@N6
zmlv0llhcK*+2K2O?>;SeS*PmjtJW)5LS$^KLjK!2OItDMo6ppY-DOht_LgdLh?0_0
z)meDHpD<&_jQsZR-qZCCUb`lCc9!Yo_>KoJUv?U$o;o2H+I6s*{qc{Fk9SmlR+EvH
z{aUW@@!L1I)nRMbRI#7l(|rhJQ~AA0_NcXDS67Emx1Dyhprqu;<>mgM!s^w1?|b*|
ztq5G)_U7V}Rngn^l9G}hJb1vs&(Ht2^5cgO4xK`(DgEl9_o`QwzrXk5=4SORQM#+b
z)@oJjbRXyrIQr?F?|i#jP#<7R=H+8q?@xV72WMbV@8Vl8IJZKgQ{vb@!(Q|jp&_W=
z2h|-Q<)9u1s2sSp(7D|p=Z3+ZU8USzix?^@%LB^G%hyC~WSVPLI>~0C%-LC{&P7E=
zpvqKTU46%{U1AXut2MaJ&9~Rjbo%-3{{H?C9|}O_WcmAhE26e)6%`jxoHdI}U0r>3
zjK>^xZEbFG{WzDTBqbXgn}BsOmN%6>&5NJ;oS9|Ht?b@+<j2Ry51&0_W7tvroKH+I
zremr1^rT}wk~0jG+n#uyeSc}G_lGZETrMy31r6R@T<orFVIlGD+qZ~KDV&!sT@sL#
z?7X!#`?Or>EPH*M`9`T+Z2WRLTe;6ODkv&4zP+{e@Y&hsfqSb;j~qY#_`*Wx4<A1^
zu37~id-(FA(Y0Ibq})}VRbgwpCMvrpU0UM#>wTx#g7b5&#qZbs)_r$(w|a6&_kpwA
z9UUG2>|z@HK)F7IW$E(ekDr{J+|ki-;M`p6!oR;tGfbpXQd3XL`L1edVQFb^2PF`Y
zbpHOoY|+utTQV*(MXePpetvGM?V_8mZf>t2Ey$ptpn#o4Pix8pGcGJ>d}Fxu<k_>X
zAt53Ail<DO($XcW{px)G^y%WWOfr?KLpFQ+`CZ#TT}eqvKva~~HSofg%;3M3FK=#M
z{>JdE-uunwN=i(i_R-_x{ef$vw${8~X;u2_gj_IJT#MGW+}mb<D?9u8+UCxk`!7BC
zUS;LuUUNvZv29}^SJLASaI;YYRu*uz*D4=7rr7~XLXd_eq&cA}14=i`6+k4c9eJ|4
z{_dViVTORsX}%`e*L?OX+?A@VtQ39q-(E@S5YOcZvCvS%x<3^<(c5@#-n<zg;=2EZ
zp{_3Px^?Sjm}ZL|>yy>44$%aS54^m*95i0R@a4IhrKKdVl*xfTm7fg?9ypu~o)zCK
zWqM&-ZgkGAEhis*T(Cf4j!mUdVPRp~yfa2FZf;3OIs{qGwq{&f!U-DK6w{6JnB}vM
znVnC;!a`!=#EC1y*3PPXxO45=wQnvid3}FB=w|zVW%s@XSyxvT6c(P`e&N^W^Y-o;
z85)ZgFIM%>k^}W>R)wzqRJ+fv{-4bKn$NsUOiT}6y;}AE->%Zvpe$%p|1aj)ic5u`
znUs_k?H3n^_D>Bze*6e(%T`oafZ|G8nwvo*dYjIq$&*$6(=8`Wn)Km){eNjt3rIj%
znAtUO!sN-y)jBWN#q3<PUqR8vM&|qb`|dN1Qh(g~sc&d#Xi@ZpW13!U*X!%+odZQu
z($i1NdGA{8KR@aBx3@FQ^X1mX@8@F(`#&!zRCNE}Z_)d@ONE7m9=v(e)6Oq{O3vRZ
zt|coXD@)67j>W?L8Sg-~$GLNE&1}2^qN1wRHY;yfv>rZY2x>5b+6M66fy`k@dlDo8
zsw9vlEI<uSB#HJH|BwCo`Ps1YQwpf-FKbnD;CBB0x%n3#FK}!w`25Uwb<CXoiHF&E
z<ZL8Bjqc@sa}7#fT&Q`zEdTyK&<Hi3oQ+0h&}Z$qJr<x^<>BFWX`6jXN4a{W&Cg|t
zw>;Zf`dTb0IeFsj+1;R_-LvNRr`S#sS-5cFuh!>zd3iAvc@3L48@u((^}f8kTzb#t
z@293}8x}rtS+aDg=e#R6pnl-X%ge>HK2JW{Ev{@~5wSn8W9!3btS&At_4;Dkkk;OY
zqNiSeTW$E|Y#LUrDkv>&4O@M5`TRPrwPD>=UtgV+3tnYi{_e@{2byYXYzzUrN-|5{
z-;<468}_N?Q)*h8lBK1jr>CcfkB^I&7gtEAYgX2(Hy4*w|NCR<H`i)uJ?~u0VmANz
zcCBuU9UmX-P3>1ddv><@*Y_(wd?+|_{J3*y=oI~UxwyEvO~)teSzAl{&$Dr?s<M)^
zuj^UvKi?@dG){&6qw5MkKfg)plh>ELyp(ZcgJMun(1#Znm2E0MFl^7eduaXse_GWh
zn&A4|C;73&v3-KzmLFtL;9qlXumx&I0MsVPne#v4u?U~^aT9RmU})A?m?N`MJA9pj
zo}S--%g^b|Y&;VTL?c&ST^*i$pn>tntJUj2ytufS>A19MR?CG80i2UhZcjMK1e#*L
zu`O3x&bF#$p>z8)>wAk_xpg8pxm+qK3SAk*s_r*OK+nOx@DYnv__~~DE1y(<dn0+T
z^0_PvD{JD12M1Tg?X_AJzFx0dXQhpeO~JP}ks<5jWI<if1&+-L$;ryqI^Cb&+%yhZ
z6A@Tpv%YwZ>)l<Yg-=dQbkcROull0#>e|}uwv{@;85tVKdL*0Gd}m4gv5ecC=6h#v
zb@-ta7Z;cH?C{}Ow;qYcU8S#I>HA&G+FDRrIu%q)7Z)GiTm5~(Dy>yvYeBIdxY*5c
z_0>g=&1{>FPkwcvk@;7*(Yd+S?c(}z2hN@2(~a74;KW4bg;%p4zI>@!?USkIJFDfx
zhk}?L1&sP}dm8rcwT;@A(`lG|%whG_MY*@Pfd?3u-Te9c_v`l)7Oc{`bNBAUr%ziw
zC#!+1DSLZsllzosA08h5^*tmdMP;6SJs+sunSG51G+MMJYVFmy4@bHKj;@Q{z0BTR
zP*8A3^>@9HP}irYrY^ji_3>u<{K&UQms8prxN~;4xuA$h%ZU>n50y+^1J@)m{yI5X
zosj{wYw`PyDSMtrPX_H#`1@Zka+8XjeO=D6P9680938hl8BLqGZ8?$6-GA3O1_TJ~
z`}4`$!rD6d&W^%@;$mh7P$RxuT;I*ZgJYTRY_&?S&)R{DSU}C|`uh5tiz9kYobX@(
zHQdzv=k=VNtS()<Z;?jDj}Hqi-8O5KzPfU-Q&^oVr)1*u`~UxK56wMyWqW>nkG#Fy
z!i5W8+}gVOLnS+(%z=M@e{W1U$Yku79=W5EQBd&Weeb}Zlc#`s?<XGp{dinnBYNAK
zH-<XbHY6VYB5w2auTy*6r3{mTk`kBO+j74?UlF=G3^a4{=Aw?%%}uGF=YqEN96EQ-
z?_0zr)4V$o^?qBT)`q@2rMu{2M!=>N&x(qQ7w7xi+u3DgWK#Oo=JxjTzPh${_WP}e
zy944cWtcED+}fJ``h4&7>Ed_p-c|KilLrm8^nn^`p!yY(Gmn5eVEI1i!@;1&nFKgr
zf|P?QVo-LzzA@Q-j$N%(@$++_?&wUTR35wYQg*9NrFcbL9o^j6x<s{?)$1%;r6uC(
z=;zlbxqJ)H)m5Q~7dSQ>WM9*PcDRo}Jly{9@ndEN39Ax~K3VIw88akKPM#Hiv`f^m
z>Pv>tOrxU@c7nE&etg_-{|G$3GF8FaTH4Xk5tPYATpc$i9c5qurSny*UR+-<Z<cq5
zBRcx^?)ZfDaeEW;^ZDocsaK11KY0H>|I6p=6DCZUus>7k^w+=N?}G*nBX$%hR(*ZN
zYHn^WV_C$qHS4NVL4m=(|Np9UZf;_&{rzpK?W)L>w6sN`tHVH(ZEn3%tp^S`m}FdF
zC@U)ib$?1qOw97{^`xGjwy^B&El}6s&D*!B{kow3IcP#B=f;ME56-XJey@t#($cb{
zqho@Nrl4Tp#Urqun@>=XkdUzO!*}ocgjBsw$hGUlgoKDlndhz9pV9Z}^lw$Gz{I(>
z)u85ob8m0&n?M~teJ9b|TeHRY?Aa5rucq?m;s_HnzQ3R;mv6j#xj+pfP>f0aZu_SN
z;<U%Hf+|kXD1L9RbG;~t<GjA9H+fETGxIW^nMqU2W&dqfcJE_guqt`Mz+h4HqhO(3
z@uzwDzQ_7xx##+|UtaEi_~c2>r>CbM2TfD$s|8Omg63w_d}cIQ7C!^co3ZgqwIm<!
zd-&*R_la}o&TU`u{?*mhpsp<&pG-&U>1ikBLT8;g;qm77cK-5rcNjkuHFL+u$8X8H
z>h&q*6DUvK-Bo%RG#A@%|4-uGyLW8nUWxLT=KIbz;{_!#x5bWSWoBKX+HGsr=rA1k
z^767_@-d#1!n3X)Zs!NJ$dixvy{vD$ee0HzwYBtt)BF81wnl*>ajI76B+FGHclI=N
zbi8;E?=T;^x3}6b^O8!;-YQXsf)^JQfBg8NU}-5CyQ}2jmzS3>E_UZX8GLGM`TMw*
z)>cJBL&3@F{%(7#zD}4ouP=DH-@?kz&osi<&3PlZwEEW<O&J-PAKr89Po6q;=xDe2
z#2GU<`1$$wh5g&#(!%26;-X+^C}>;#&1I@q=!D6Wo0t2~Ulg)3s7ChT)4sz;yF?$e
zCe<J64tTjf0X*E%+Z!wZY6B%pfo5X(M8$qDD*)G};MQ>=xJEs;@K6%8wgior8iFQl
z=KP6?js5uZ`TXQBFD`C!U#O&_s|%XG>*()q4_ke-k(vF&x7+!TPfk|1D19X|%PhC+
z!-s;^Z=U}C{(f=j>aYzPHy+&meqZ;~)6<h59B4do_UzGZxwjuYdepQz{d^I#`YHFt
z7aamc7SDdG(X}Yv<@c`LH9w7BU0)yn;(7hAm&+rzWL&&&F)_8fxA!P$BKz?%-Y3tV
zElN8(>&4~e{I9O8RIWD3Jap*LhVu7upmEWDdHc4-i<MtpS=s#V?(Wy`KjprKmXz)P
zf4M>WH*fCmmj{L0%AlnNrLRK%e76fackUc$n)Cbpdi_GDo%3ueo4&ohz1Y29E@D@S
zW{H)okdP1q!?$nWBrFOP_WgV&eKPozu&8M3ySuv=hpY@LC@MOnzyA*t188#a{k^?{
za&mg*4ktlPey^!o2M-@+wypYdV5#?XhCMd+qS|3c+IXc^{56iZa0)+o_N=Y$@2|u!
zFD`a;b}}+7S-yO+*Ho>DT_r1@a6bL{^?Llp&FTIYmX-@sPEO+B=4Srz$@KF2czYT9
zx|mNbpWfWvEzT=t;&8M}^x}#@Wl+g^;B@ijMXubSm9~@Ar#!#6w_3uoNafY__5Gio
zo>o>;VmffT`18x<^B+Ar+C52qN;7CI71Y&{03{Ac@45rjWdhCN8KTd+%xMBAnI5FV
zd?P4l%{I$*^7HF^6R6|2+;8re^`g$8QrB;;)yzVr(+{6KX}P@IKlxA#=Z^aSc5mLk
z1&t0bS+)$+5$@>d*l_CTbB2JWUZQjC>*eh1?0!6KmtU|->)QJG{<+rWi~Q%?S=9d8
za#i1MfBk<uP$_z5h9PK&;elPHuRlCE$b2)|)3oYKMvt7WRPwQ&i~qmR-|yBdrCRN?
z`Qyir2cMpv?rY~C8p<PQb3^O@y$^qW7O#og%BAi<&t+}YR)fk<DQjYPi@m<K_VAUJ
z!E38NS~6_Ozc0rvu6JZ#?Qa1=!N$M8zb9W@<Qh}+FFx)3yx!H}>y<1lB%0azkNtkX
zzaKOPx36Yq_xa9_j(_g(J~U|lao)UnAcr5UZ}|S@i%Uqzl$Mh^ho79BT=?va<eNJ?
zh0EXHJ6ry6^4z(yzrMU|-dp|MYfiwt%gg;2=ic77qvog4pFe-NVnn7*nbI;<JKSqd
zz&c)OvxFxnCVu$%@nHG=+VBT|GPXv&D6#4kJ_TwO=tOK_NIuqcu#uVl)7<HomU=G^
zUmtg4XYukQoKHJ@dRp4s+4W*}G|aQD7OOaWXMg?utoy-xI6~jt+M1nlYm25??yZ(n
zQ?(!W+yA@pe#@ITZ+bRtFaWJS`81_yLm@22VH3Te;yzj8_c0StT>$AjBh~hx(gb-H
zukinm<MyC3>R7KdC@gR6tF^BC^YJ)S{IwS!9v=Sj_xt_U<HABh1y4>08vCV0%E-uo
zawceS(|^95tD76!qQ#31Yk!r1N1**zb%|;x{r&aT!`Jud-{0R0zrTxJvTWI-cKJF`
zMo8^fzbYPI!&qKk4%%EY!?xNC6mN>oZ40WtzM5fGy6VlxC6Rk74EO!}l|4EB+M#>*
zK&h^yuTRVlG@JukbkW8u{o!G|{H#K&(+T<c{TCOzi)SsgW6aFV1UVfvW6;dbe@gCn
zQURoQ%ns`vGhV!S5!7H{a0r~jbX+@RMZ=LJF2((+hGp;WbWT)uf3)}ez2>!Ra~mIT
z&AxtYZS?jt_A^*#*i;(*``BOq;M7!Y(1|tsxCIy%IJfitvc4U$n3Y@X!QAqD2e;+k
z{&27Qy{HAK=dpM{LsjhBsI6Roe}6yz=jZ2(dn!Lex-74+ulJtev+v|&^~GstXMtK5
zpyhNAY_EbER#v56mr9C0Durz16joahvNEWnv(wST!=v%K@AkaAU&=3SGNZJG9kajg
zuYjm%t9JOh2b<5^Iq$Fgdttf%{F-=hvuBw}TV3Dtot2-}yrycU9?M*@B2a{Ns#d7e
zRIN~OFG%JkC~$WcKVOu6eH{lkx3iNIlaP>*fS4Fte0=<wxz^&|)Agp>F1tBJBakV2
zd)`#rHrHQIr^i2d@SuTD*6P9b`*qp{e{OD0|M2ze(RX)ugZjxe-|v<SEt|5w?(eT1
z)!)~>G1NKs?d|Q0YopCo)YYH={&#b8I%xLq$M4_CZ*FY-@b#<f?y|QNCQek$3_3k&
z>eSXHOH@?U)Wm)$f#&IhKg90_&#RtzWMN_P;O6G^Lytdx{HPJUtVdFPlTQ7gkL+1j
zSE<^pTcu@WY<$*Y;?s_vo+IJ$wW>9|ppGIZC#R6wW}b~3H%eF*E%{J!b5rWa7Z;U{
z{Zb^~-PzfE-u{0~#h#FrK_1@T#*ba5Jw7wj_{XQy`hkmFIGgwHSsAr;)kSOeJ?9oJ
zUJT0f40|}fo(C1RD}$FWa%$ybvk$&==T5=@f3=*GPl6{z!6iD%lzJj~Z4J^GDOky4
ziDRJYH3%D$caOEUww{zbxG3k&4nb-2yeszetjqPTt&I+UP`PsDO3+O2^K*00TF!Ib
zS@l)x+S=&$9Xl+RELkFQ<BnsX$m+e$HBnJg+w$&aeYq3yxap>-cG!XI*Tt*9y*c^4
zR$N?sOZIiXySvMee|mbFH}BV1tEzv0EQ^YYQu-4o-nn}hR6~HuVLLlJ&<K%~X%-7;
z%GB}tx>!L;$<E5p&m`Z@zkYX3<Yv(L8E9%9Jh(71@AI>>9^T%~n>QEld(Y0ws%U8`
zDXiw>&@HCBA^*PJn)v;4++sQhwq#yb@zuWGEv^q*O9H9@_~mRgJ``*5+b{0u=!oNm
z=jZ&rU&YMw?sODBJ|=20ZN`j_tE<BoXJ20jio|#C-u?J`J-+og=!7n-(pNJIl};zV
z(3AfE_Fyx+M&za?GnZ|&S?WFAtm@&ptE<BUHzv7);yETJrr`ZO+lL=ltkBr8Yu7B0
zt}ONP>^gr?&YUwxX7T#&Cr?st+`I{@Jr9Crs=(1gW-M;azV7#pL+t6t$H#x|KB?8!
z<lZl*sI9GizgWc8@#G{`!;}*OXXaQ2ADZ$h_s$N%W_JFzxpQT+uCL48(CXTKGp@Xy
zU*7Hgy}c9X&Fh<_>b<Ds<t5g6$r-`g*#h$NprVl*v~c}wg8k&uqT=Gi`uqPZif^g=
z@gXr}MF69$b(xEg4^P<oxL!r)wi9x}t9Yf&4&1yc`S#XU=exT~AHI9X$Ijkfb3Ran
z6_lM#7FNdYsSs>zZ2Y;e{MVPvBgc*<-Pn*g!@69LVL|!(dmbJh2l`~K*OW2-S`oMy
zv^)#socT4MI<NklEe7flyDC>RD1m@c?zuUZJ8FNMMQzUm&7(U7ipbd2NEoM|b2;3`
zJ8|;l<gNQTSQ;Fg*%HsrG6gL|`d8hxNI_klz4-aLqyF}PTlnq&1Uzc_1X@w{{M=l&
ze%tDAJg={>Z{NOs`^@E=WMX%f9DH?kHSayehp(=#1}zQQRsLQt(P$@VImcA(a8SpR
zwNKWzO62vmwa)YHYC&Z^sP6(g4dg?Fn;To*kB96TTceEqQzbv?Ihk%rF1Y8qB7gti
zZ7nCCWZ&AN$tPox@FBv_j}Nq3?b_Pt*_B$S4^WsMS|`t(*%`dtFY)|5TMs|KX|{bP
zpp}AGSBDpVeH9wAE=Kb7bp7l0=YH=hddhWfo^AJ3?eM6#%fvz9c6pgEsImps%ZZ7J
zZ2Q+-+)?-#G#LB&`FUkqTiNpW_jEs$K0haWGuaEY_U6TljE5gzym-M>u2*+A@^u<Z
zYv|f2QyJ?rp43xQ9NYP1K_lLG_EZW-Z_nHM>*#X^(5j{_TTFKB*zw@vVt0%3cQQ&!
zN?bLO-A9hNTv-vQeE&P2oDGL-pn!nDg!jKe5pZ_4Ij9J_xv$n5)K{$i{Vnm*5>E-U
zoEZo8LGxa&TA=YyK~c{A|9-8$wJz2=G;m5yeAL>o-oCzRw(~+PEiG5=-@kvAMpx9%
zqSVkpk*jy_#+H_pgowHZ{{H@6zuG0!Z=TIcG3_v)+UIl2uS}RA5E>}*b$0%~!0T(H
zmtR{Q?q6C^5U_aBqLhBkvwN$*UpX~Zd-b|?>t3Chs2tkswwO=OCPLPtV8N>g4;Jj&
zxpQS_XXmElCcCFh5!ve4%=St;f6u~iFD^P?%`jQDe*Jo|3m0Ep;XBJDaK25YQnim}
zpS=A#u=Vfve!r4?d)vycMJrBE(+xJyyR*V9=SINR?c2lkV|FN1`)Gm&*{v)sSDu}1
z9{&97?B!V|Ql+1soP5<IX&fRhF1|JA=BBKem^p6@m)_W2zJArkj4KnB-B%s&mk$?p
z4cwl0cU4<!D`-V_NN#TK)eRdAZYFyjhA-qpZu%)7+lSFNfKI1cptJ~Qd^>A?e?{u4
zDS@U^y&wyf-TPLoTD8j4(=%&l(bFqiv#)#2o1oLXckkX^H9w1PCPyrJbhLZ5_cWb}
zwr#Fbrdd<6l9LzL{r!49%gwFr-|zGD?Zd_O<JR1|b!%1fv7U(*3oA9d7MW#Ua(R1e
zYxcr@HMO;={W)g-^X<-l7Zny>9JW3#RyS}_%dYD0@0gCyx2x5vPT9mTRXaRPTqk0}
z`)XP1vXE|3?PYe=-*oPO-~az#_12V=lb*?(Uu0ovxl%iP-4t6kLBWgJ-hrW^Q}=Sr
z0}ZuxaOqoGN^ab^@x<A)u4iYNt}SEFat6)E%UYK`v9_<PtNZZv>r~rWA?<v!hdw+!
zEGRBM{r&H&U96eEVQT?ahl38FdGPqLa;DK~(4@BKWVOWW>ta3p{n;6&=tK&=-}_ze
z+4=eTTi<U?KR++=-=CkqzE4@TYDM5;wm*OV7!*EonW7UJ^sVEPj70&%;dcJxZ*OmB
z+;it>bZF>~UAvOLzPkG2%F4;0F67(o_YJbHXtcDqKmWaN`gHNIH4%-!zP|RJ<+JbW
z>+7HvkB7g1`>IvH?%wyFs?`b_a;pFTZ<6|y{$9}F4rpl}XrLX^BuD}^4?zpAc#wL4
zkZE)a@X-2U&^j$hN^sA)yQ@^fD23zC-@l+$Pc<J7vRl;r*zm6ywDNJ~%9THUKA*4Z
zuXVmtSRGV1|9yS@>{;HsyGomvFJJ!T<de+1yG*T0U$xxaoPJvF=p)eRSYu=344cYL
zpl)VWmDR4Yw_TIf{SO^H$hdCZI);Yb<?of0m6_+wo5#V+>$);%DP*M$o2XXE5AXl`
zH*VZm|JY@k^WuvlJFIK&3CTH^_lAqG-n@A;ZDy}d`15mfC(fGH6};Tfaq&ga?CQIB
z?>>C{cI;p?`)AwoTU#=3>?+k>7r$RGGiqm3Qxm8+Ghu?j&BX$Of_tYymr!+_;99Y&
z>+|#T&v!pq8M->`LWapE_stTkRw*eeGVa{Db4A2PrJS6clzta69dmQ>i4!OOycaAd
zC%0ki)~U9$TpzfuXah~Y9%y9VQTVv+-<^`Tw?zH?{5H8OYi$B8bI5<OKIt)Np<7R{
z^Ot(?(zbTca9m-I%;6grF8{xS6cvIMU0dMDd}UQA_wKT{hZei{2kfi)S;Kwd`Ptd+
zs@~Hc{QLWRlDg^sHEVQ0^ApGWWCKD)`}+DA;>!9LX}q|-UEeJCR?5`%3x(DF7UbXG
zcVlBR`>k!c+SM}MpC0$yC!LvLXi@lxWmV{EwQ8B}$+Ks7zrDRZ`TxJapjqyQ>9ehV
z{Q3pzw})M|l<H*z4GuUsG`tDaIk&`fGLN2#dD^=>JL@l-OnZN3rZJnjSLWSaTc4af
z^Ll!GU1NVg|19(TzOc1X51-GkcZ-RU`S$K^_qy2K&#Ln-FY^st?kBrCwxRa>yVx&p
zZVJzvH&4PWM`Bgz>a-8<gH^qzOfZlIje{PCj)RJMEWgay@K65fXSvyj>W_f-Ab1};
zrl_Q}=sNH3Hc(5?Jx4}KNo&=cw{Jmf?s;Ubt~_A+0-6lEvLdkJ-=CdNJkRF;`tovy
zaXR0zKH2V%kB@`KXBZmT`Q;KG9%}vZ>-BoW+*>9r?Cjq2uKcO`@}lv^jfj~2b+TVy
zT{YfO;2S9N=H_PiOD&&3Yk7V=ogQEC_LeEA&9ZLYI=1s?54Ccu`g%-j;=b^*e(K!0
zy^YN5NvEgj284?8@$oS<psXhe+ZuRzneS|a;%7cbjvqgK^{VJ(HQz(W<?H9Xw*;+y
zeSU84#>B&Ht84#fnn-DMF@=V<&bHO)YI^e~$JpP^#pO%Y1JGJyB_$>9Dc}2(Bqb#^
z!q!AAEISe^!fI)0nKr|3UmLHq)8dN{{`~yBVe3}c#csVm|0G=l3tnDQHTF@z4w@-(
z*sooFFFANks`&f$`+jkCEqYNd{_oZ5^<agd(G+7J_45}NIxp1V3R@Gw*z4B3(7Aoq
zALFh?4|c!bXMDJ%$kok_i6Lrh*3|bKH7n28&jmGl+4<!d7_`FI&4G$-q-?<9Tzv4x
zBv;UYQ1CJz!yOE@cXkxs*qSY#cXyX+c>rhDl@*L@!@7B;%_MB>5)Oct*(=!D-8(b+
zWcc2y(#hrOVIr)csrOkYiZ(F&di(pkM?}o{SA6vDU0KkQ3+enlisc5zkD0!NPoFWP
zV^iwsL)Wf_ebWd!JI7LZbK2QMCnhR`76k0rxs#Cr)TwLb7EgM4Y3U5ZWVW<3GZZU>
zJ{xb_Fl)j8-%~Y<pPw^5Yyz6TlZQ^<ZE`TrzsJIGWlf~<{p8?J^ZxI8eR(;*i0i>=
zy3q;A$&2fAPJtHv8O)7o)8jHO%lq`N@m5rw<caQQJgcL&YMDs!=H1)FX>DyCvNmdK
z!2X2&#n1a@s!eHsuW7h%{*iyLUaR$+&XEQe)`oR*-5)<kfQtC<QzY&OCxMC)bI|gr
zAC)@C&L@Kk_WQv}HU6ETMg5>rWWmSJH%i#|AH89bROA2GRKDf|W1pODSGTynlDfM3
zeWov`r|T~+eSPi6gJ%8>DJO+)E}k`a?_OKbNDGg=-JJ&?MYY2c?(8TGt1Pb&(teZP
zX?l0!kNtl?&;Ng9j%D$Li4z<D$4z?p;6a1_z8_4%%X}tU%&jbB{I$CB#|K5N@O3?)
zvxd#RH-?#JU2(X*Eq7z)Wwqwx%}q@OpPqQGzQgn6d`PHkP>_(ho`RB+(&mI*0Z`*F
za=|Rq>}S7^wwT6l2$rxedt>nH#w=N@5)OudH4z(Y`d=;u4gUZC`854ra(4Oqd$x=F
z*G6V!Xf*uav;32suz<8Q_XGRqYVQphSBI@_TBNaI^XAjvXWXz@wgI%PFp0cnXV2Hq
zG*0J>+Md@7T8ull{9fZCjT;*hnL*>5puxeZTA_!&yu6&+ujx8fD^x&GP%)-KPEfE>
zD|FS2O07*L*LH2#WAN|i`TC?&Q#3*AenFGIpe?uz4Krp))ck(C9kh+dM2c6<ca}<J
z&}UGU2%eb_RQXspN&oKtdii<t<{f%GZ{EB=)z|+|pE2V^FK8XmiJS`d5>WR^i92*_
zRw(EwLJkfNhs(=+Q~Q$(L1VIZwZA|^N1&+yHC<g^Q2lg#gT?iAvCiPVA&#y-_hL;t
z{&9hmSd}O!c=+~mneqJ%1rI!Yfo$rj63vnMwHiE{{2~+_kYDOm4Gjf@m-!s*xBu61
z<w^)c!{WutRo~zBf;L(g6c$djStxVx;6V;PKJW&e!pFy6n$G}@C4p8|faVvD^+<+o
zbohU6t~EnL*40%{t8={WeePs9aP_KauaxPbeYL;2WP(FQ_wC#F<L&nQYpQ~$?$}{*
z<mgdFRn?;pl(OyZ?Ky)Z#qKfwwXb0Ra;O@V=0aDs9B${2e)>A?-=CiWBCPXkze$R?
z9{lt3voEM*{P6Sn{Mm_Cp!$R#I%E*J;@aBi$8T<K4iI78ntk0ZAVA<={r_6<LcOy}
z875MoVWYX__Z$-v6n2%p<%*7uzL^}!!q3nD<^6s6y1F_I(BTz@I(^N}%)83p_Z>Lk
zQ1bekZ+*IS_VSAv7xq*Zv#_xpx_@6@R6A^n?WCh0K7Dff|L^a`?fLOjbfd$*S%|fY
zFYNmH`}gAd|NmZGTFU*N=Yu+^*#_QGLEb95&#xv;nlxed?CwubPdhKZctXy7)tfgt
zJW?hcR&)8f7QLuXOHEIA4h>~tV*`!LhFx@)>SgO%q@b+Ke6&mSvb~wAy83aR%O_LQ
z)7g97n$`X19XNN6udJ+0?R@VdjT2|im|Sj|2AWCvaee>4R>%UGnx92JGYlC0=h+y3
zPWg0qU#)aA8?RGEg$2Xm@*iO$N44$+FN^r?^yt4??XQxWpHHVtm}ZF_>y>6VH#cX{
zkN58u*FQE%)f=>o_RJj1;CBne4%{-=Gx$<`N2Kl<sL^HxD{vDE3kz@TsWb+4vR8+%
zcM24#sHjlT(BJ??24ptw=GJWS5-ZtnZ*RAsIpZ@$GnlRR_czys1cg0&_J9^NK0P&c
z;)Dqd(b3VMy~Z3oJTB+w*#<6h;k>yxvIR81^Zwr6ihqAB=ggUNVY$CN3mY3~!`CMF
z$ytw%bb=a|@9ykmmX?+V4S6*-HomyJT3kj}Hnm?pw3SPA!jvg2*4EY~FE6oz<Ss5|
z2Tum8$?7|aZr;A#JuFP@)HGdgdwY8p7M25-F9&~%5NifC-oYdC`QT+R&?b3LEo6B#
zcsvPZe^y}*ObJM*=A88N^A18<7>{K2dO_P#zrDZTe|vjAGsB%bcOJZc-JN!Jmgl@P
zHP_b1^ScHbBphJS=vq{tbLv1N^I3zrF~Q6IS{G?>@bR^|Exu@Pmiq0@&9oWkHkG`%
z!1(UnyNJzcy$2sVxA7c&dwYA~j}M8){%Y~h&&?GS6l{F(AR%LG)D+F&V-G%qMxmaa
z)bS4s69d&VVQZr}&rjZZ;@mk<w%V3^o6R*aU`>P}!+~yb{ROMEetmu2-YachbXmXP
zanl}O|1NR;dEgd>I%o-78*E2RN4L0s(&uMq!2y4FH#;bBUtQsBY;3Ifez*MLg9i%L
zE}Ec8z`54tPRlPpd~tE{iL+;0SFhG)Vqy{y5NKfIl{z7J@l8nR(Tj`S7hZn3A^W=C
zl4Z*lrJS4uGC@#6qQh^lRpiliPmkHu{t^K#6fd!o1?_2@Ge;(5T}<TvU72@wY<wfQ
zw6mk5!EgEDb91dH&Y8ngUH!YJJb&Xc>%u3`o;|v-(D}m4k{f%g%`aWP{P4w#j_>!X
z`9Ue*!oudz`-Y9;3#Fz_o7N_4UFNX-^1~Y&lLJCUudWJpPDoH-VqyYqIl8GF#RFRR
z1e&(PvT-IU2O<G#Y>6Q4r~z%bXaaX7AX{xT_i%}7B^>LK{PAS6e@cIn;G)Hg*M52~
zFwqjUpVoW2-iObh4|fPE2W-s>WjL_6`um2Qn?^bJ_sO#J%N?1WzfTji`Ymt~i<-}j
z1J<GcPi{^>|KQ!bK2Bk^gg-w%ZaTg(V&cS!pnkyBRa2jw)L}Q*`;jeYSJUzP`}^pt
zY1W_(#M7ZYtQ8zqWp8HuoBmEyQ&S^ylL~04O}_4j<F||;RaMo*)6;Z0I5`i#yu5s&
z2A7mc#)AEmz3=H)uQ}N*uD>Dw{=S;>2O8n)WI*Ypp@Csb=4H2U9hX$q)stUeTYKSU
ziAC)%6NUwOcX$1|-aC8t>?fR0Pn<jnnowJC`Q?Yp{`L=VZcf*T-DUFY+uQDj28N32
z>eF(8U1!etfM#1k`U@T~#O<kI6c-o&@%y*3f&znX^tLIsi$eBrT-^X#I@{8sprXR^
z{M_8;MH(4bRtPpVH9dI$zF#YJ)d{(aNgE1zpj(?jt7pKg7D03Meh<OBVp(C0Vjl3a
zH^ZJ@(1JHZGe1XI>3;Zz#j)B?C)Gi-K7BHlK`VBf?SE$?#Vci=*K^>2!;jy;qo1B%
z_@7%lY|Vj3N4o`ug_WyCx;Lku76UC;zp=l5|C_*nWlv8}*Z;6{(#)Bi>i+W>G%D2Z
z1ugYDc<-JZzr3Bv`vqbPyryc+Fv%1G&#{VhKYsM6X{K>{(P9xTlf0M@`+t8rtq+>2
zd-CMT3Axsejujq{Aia)7N;;aFoX+ihN9WmAFVNunKk?0e(5h^!xqOO>iaUy)a+yf+
zZrZddrC)XGLhAz1`Z!R3-!yyLn~yq&K--|#&wlYDL!*ny-`~Hbz5TSD@2Z|2o;UaQ
zN-HWVT2y>c*tB``!&k4mqPORrl=IbcE_YiMxmm5LsmY-BSIN!Cp2xcbcz1*P)qcr_
zhK3h1Og?=31}aCu+e;ot@_+`eKudoMK~0vvL~y9KZ7lRjzAtecv{o2WbS6uH*El7D
z*BTz%2wGe$aU3*ACUNYTCTM%q{F+akbLP(dc+p*cVb#}HZ06TCPP0y^`*>9R#->#6
zM~@$W)fJYI=&-B(b>QSl&u<m3Y~t%WBQNj#`2BnR(q3IBC#QdHnL40z+&+T#OerZb
znVFe^_N2+z|1r$Fv!n5FJO639qe`F^=6kEYIyJNLrt~LW+);S&|FKzhVS<8!e`R60
zrQ_t8Ge`FS|C|4!#HyvOP083;c&b)t)BgSTVtO$e)i&LQe}9#}D6x7`Vs&RnA+wp8
zSy+AG`Fd{;j{_eb9<B_WabRoqbx^Nv-u(ZQX3y?!X6H}3xha){m-lJq&&i-Z@R1I|
znzIrIx&w}aCYK{Or#)OgzwXgaM(O1nz$M6$8|H1WgnQ(M#s7o*G;P2wL&$3V$I$Vj
zbM+evxxfP&pjAfTAU@|U)$8{Eew$d=s#RH2pFh8{G8j}G?yI#H5*7~JQ&ITi*Doal
z1A)7{%iT979Zl)axVWRhx952q&(D|3=L^Wl@PvkbeAq63=<3z051dNk<KsCmpDcZJ
zgcGzASX3+Iz=eg*t<p<PvaWa>DtWdXex?Bf!@nPo`9s!5i7s5YFys2Vxldk#i=_J>
z(nSRYFaAG<*qEJ{r^hF6$1~Tj{qFAa#~&XbFDNN#*}vbOiJAH0Lg)7ITdChmKmUHe
zUs*+k#cD2JU|?WCsOZ^QriT}~g4T}dSKD+Kyt`xhqQola?k>^&|Nrg&Cw`jc&i?xN
z|G##Yyc7xvbzL2{RzN~RquOL8Xc&6G1ZYC*+qZ8YK7Zc)>+_`NkB)Z#`hMl^?()R+
z^me`2T_@zct&+tT3Qd?XqeC}(o5S+Uibh643>TJo3ZD!<dGHu$fqN#nn+G1svw+0S
zo+IE`0ZV|IiI6>0J;{&v961JxE@X+HYooV==95<X&Nc&WNd_&4k+CZA_-|bM{oP&A
z@k1AOm*=yvupBsk-2K}MmoHK;Zf;)wZ@+t=%*^*Q7HNd-mgHc_*c!!fV5)ZbhtvA|
zMJ)2pK4+`=`Tzf)pT(>H{uh6Ff4_YjuXG!qtX08dCM6{$BWrk5ZMpyabKAMMu3f9U
ztK?<VfddX-UR-4U_U+py_bGa&rlQtmZyNlTJG;2B6crVL>KITzvazvoMeOcvZv>Z~
z-hCLfKr`>o4n_u0<}WBP`1S2Ax4OFeN#RqICrxU4dwaX{^2-l@e0&UAs5Co&UngkI
zzJY;2{=T2f-Uu%3=<93qTYh+&Zgj!#Z@C&>O!D&J#$5RNIPm({MInWSg}=UohP4?$
zYf6tkIXM}0=EkPf(_Zre_~Kf!VyddF%HG}Koa@)VVS~YwCr=iD79|*^ay2zIfi}k8
zRGuXYUKI%rbI_POJTm^U!<KA8MqhhCi=aWXL7(MwK-*nGo7zBqd61B@S-}H`o5~R;
zy>89t=30Zct)4h@<_Kt3Yr+J9oO^pDUte46{PfgR(0tC#WFb*aPfyPs6(5x@UAi=3
z_Uz~fJLb=y-?H)v7ccKr+oq$S;hNC@wX@@RAzka4&;sU!)73SR!rSxiGJW_o{it!;
znGL_<#r|*4y}iwG`Q?WX4mO`SbH-(7(NoY-D=e(63w>vsZ8|>r+yz-PDYKl8oyE_U
z6ciXjSBFitU1TCDDS2aaI)90kY~8<~>3b?ZGU@5*Nf;)vfO6BSQ0<$_UWLEE<+ecT
z(2Ex@f_9b7{s%hqMx*O@;o~2h8#FW`lx`%kn0}Kx+Qk*PAtAiS;mVPwB=e0&h5kk*
zd5i20Tx`gsWtOud!6Yo`OLlK;&(vj$F1ddD&TfDH&G#F-n~(gKx%YY2NuM3I>GKjl
zRB-RE{%V+XgyYN0%j`?Nr;FJJuGqi-^2PW2|MNvo18utjE%Vv8Z{Lc5g-tIy4}DMx
zDFyjrce#F3bMwaf|8+~2E`7N7`#sR|)CbR>x2K(*)j3atMcUomtS>KT&YX?;S2h-w
zBtKpOMj6TXUmQPnvA1`!v00xLNQF#k4hZGu$o#!wv1?;t(XnHJ5Ea$^a<)z}F*2Y*
zkwdNA-Sd)*xWsfiKnv0W7CM0z#vE*B|M=md^To{_pL%<GctD-Cg9i_Gai5Qm=lC_t
zGOpp>%a@u}O(&%+3KqQJoWlR{80)QX@9*b-C|)1C`<vKw0YSmNzf~fqrCwA9PkMMn
z_ez;Qc>bJSUS8h9(z0`2a*>XX4rnXjxw+Pd&!6X?H*emCO^<B1F&wyiH}*51^wZPR
z-RIlYg1QQ~wq|$FOB3o6(QLYMCFI7fTcFh)poJE<x8){gW@=W=3J?<$V_-;6Pyg}b
z$ARnDudlgx(p{XNpZ~12>{Q+8u+M%0UteDrxAooe-<I?0_3P8s7yjFS-u}Ogb@{s^
zpP!!(ToIrMS_H6f-@c6d`}W?f-=FmO1vsz*kM9dS4hl60c~bJXn>{#mtx!n6b2lu0
zZ7jTkgo@O4ba;f-d=B(Vn=>#73JMmKm%BSTG2Pmh+nsrN*}~}Uc}?M6rEhK+vaqv*
z4mYd#^n^1fC&y&H=iA%c#cj`Pym|A6XWtBcWo2gl_<bg`%ctdDSkQRzd~au`V@}SR
zn>Bg=K-U9-w)=z5A2G?k#xrl;yolXpx-zn|pgsg>SM=LkTX+7d+1H(Se_!wZf4{gH
zKqpjyb_sk?GEx;269es$u_}AR!2sHu0b1pdch|}!?~cWB`{2cHyvcql!l{XgjGmJg
zyf4~u{rp4gBf^4$Pi6HX$MKwM-?V8HXtl@`y;!Mh*RCyk&hhcGzdgun8bM1sUTCT<
zcj*)Y?bEBNt-ZJ^RQqDFk6$~VEGR9ni`@+x_WU9<`Qxv-re{9Rt@)xEwnk!C`Fp<j
z`1l>WcYj`YsQ&QefUA*_kq7VIl?CngyttTsf4pQz@8M$?TYDGx)h_Pqg`>&UZ)WF!
zlRG5Q!^k;zk{_pl^9LlCtVn(=k#~Nc?TcGmwP%^-a`E%?`^>kKoj7q~L3uelLq%of
z!AqBf5)%`frc2%5S^Qi;My5wMdK+lUW5b3G4!5`EK79QeG@&r-?(QSs-`}^tUO)ZX
z`uP9TuFaSxrW^I-S8?&5A0M}GIaXq6Y5DMRzx^@LGQ%GqlPxSPGUD=6B0-xW1GeYI
z>cs8}`4XZCn)ut8d^~IK=Yp+SS3le>zd!Tq?j_5YFHgR{F4m&@o6bDjYS8N9qlKQ6
zHdKAha(vzM`m5`a`tQGz5>5AX%wTx%;9&F4f5y-L>~eN-`QrZp+FGvBFf$WNJw5H}
zot3kv#O<kQ1a+6bytud`Xld6AOSkD0CnjD~ulXyiAHVO&%gf6Hx97!*=thNnk(oSk
z+O)Q{(c2GQzAU`dYpRg#@fVjaUk==m;CRvalWeg)r>UA68@M!6zMlxnC5expu>N+F
zm2U5yES@7{=9jlI|4Z`Y4TYbYK(TZ9*hy|PK56ys;0$uZqVgapHzhunSQWU~O(SRt
zN1u%4qEbf<hBNbQr9m57?(QyU)i>?Cy*(eamr+qsaYxlxt&~W&#csWzbmMRLlZB6u
zZ;`st)96+%(L<M(dK+e3P*}2L$pVjwN}%5Eo;`aQ7*0>qJ-jAzvw*O$a>dGzt}ZU1
z1#zIh7ii)4tE;P-8P>(@1RoKjrpEU0;lqr}%X%LyJy!nxU2M&tkH<kf;NQG?Ghxb<
zmPM}Jk8W;GpO7l4>NTZd?b@|BYv!Li-TLj{zkm6Ooi87Qhdn(+xGyq;%Q=nw3VqE|
zO-)VEf{u6h_v=@63GDKF(b?PEx^$^3sA^KyJ7qu5rjp6r+<cB@vD+7s$)Ka9YQEh}
z-%;~((+f?f7gh_^_4N3zUAtyc^<~9Jwx_}$KYj$AE7U2h?&2@#blvkbCnqOpGSF|n
zUG5RrpX}1^kl=qKT?&eUxDAD%fZlhpw-+4zeO90t(7$1kGiOf%EXp8yl2?E>^4`83
z{k39c&{6?$@$@6ENuldvBrh-XJ$!n)K4@|ZG#$17-!E;q9*Kk9=l{ohd2xY878fi~
zxEQQ4zYwy2myu!Hwrv_=Yb4gi?_Xy*Z_b>aDN{rOKex=Xs|D>`>N`DM|MBbf``fl}
zH{Y{&@5is#;~#%|dU{3JTB&9J^YyBh2|PaD4=Nu0=2$dFZ_jg_mYQ>W8?UFQCujlY
zn>TMjYdbF*_a3`{-~RglnTvOqzh4x#HVU+g8?>R(H2Ye@?QOXc+w){WM<dBvmnqoT
z#C-7qE#YvF?38l=E!}phRQ8<of>W(m-EQUM=Wgb8bw$U{d!I{*bW2NHc5QB}ru6>2
zqHnLRYTwye%)WBv%0<g(sF?NT{i$BsH($E+&z%*IpR1+k$lU!=3a(+l_158%GV8;T
zQjLy|R#8`9Ew{h+x7oew_qNJ<LfJ<;1V4QJ+S=XS{X$di^tEeZ6DLjtRX{H^)gC@P
z++O*sIQ8_jztgABuoD*-pJP?(^|`Q}Pj*AWsjt1_3=9eko-U3d51l{@r6MCEBerBr
zy!r30b@@A)wDa?LtE;QmCV%_(4Rnx=Vd^On#?wc-dwPy+NIZODO{6jCbOeWQ-;1QB
zrF~|ZaDommcyV#@#`N=Y2fa^D`SbS}Yv`(w#>I=3x8>e$Tjo1E>EolLKmPrGFDNOg
zS+y*1ZNx^U>-B013J-L36qS^!zJG)jJ6-z|)T^v3F2$VtQMqu>gX_FcS*6=w+&_Lj
zx%AJSfVdB@+lsntoxhZQ_!=Q=Z$3r*&#r}ck{%1}m94Q2JAR&5^3d6{yr2Ouw|=>`
zr8;VAY}wb=G)|vBy&*M;g^exiU;Vv3l^;HTcHUX^lts_T7qrjp<>lp|BH&_hOZET1
z-#>q;`u*za>g^kjZQ+$R<B8su1KKJGYTZO`P6O2>d#k=OF@RPRbnS0`cI4JAsq^z}
zgKhu)`B@wh9W7lr@ui2SXXED0#tfiA=1D3Ke|~;G>oKU;wWIK{%UNMPTU*)0#Kax7
zzs=^^)vo&b-p_Lq=;SEJ*GC@qa&O_4w~P7w_tb>>{vMN#fJY2JbwG#qpE|30O*t@8
z*&Q^tb}`sz($=k}ps|%juH9YpoPG-U&pIt>uMZ277srk*-1F%5Myt9!4gDXb&N~n8
zyV&3BTzT|5A|#u87t2exf9hI){MC=0iq4=S)OVJN<6^ho3#-HRJtnm@v-3ZCKEM9h
ztE;OOPaA>e(JmUd&akO8QuCh&I@$<y`j6}RdA5n^>FQO}JR`Q{NZQ!if|3i5q!G*e
z{r~s9@H|xW|L^xM?hC1r$2O&&7Lb+g1x?{(U0ub{usVD_Xdo0+6t(e6t7WYV$ji$s
zC@#KS^XAEume<$UgVvvJ*s=w*x&~B(G;$v;EG|AgN!9zp%3yVqj0+BhZ|>|Y2JKeA
zbN4RmTH)0-KR;D`c)-Z8z@d=|v@dwkqD2?hMw>H$1`+~R1Sn1vZnZ3XBT@D3P3Q4`
z`PF6fcg8iGlNNunCgETc=opgzetytC$tpfU!Hd@3lYRzUf+wRUfB*S>{^9%g<w2Kk
ze*BTY|8HC9>ad6H@^uEEj85fWx^!tn>S;01no>xW_ar4X_2Ip})f%z8w%q)uG@(dc
zSC`k((GfIL<~3bUx2n&x^5-X2zqwYeRbO9yR5|^B;+#1>t=!^^;`i4T6cq{Cx@(y6
z{f)k1@#=>86me*~WKPZ->0jpHHll_;NXp{X4U3yMEWYF?f!go^aT^M^fR2e+?ACi|
zqO!Y)_=c@{cco5G*Ehe-Jw?u@0(4>r3oGlxL#^DPBe|CQ&HeCl`Fzk+z=kbbL~H{k
ztgWp<XNV{(GczQlrY`+zrQ<p2TzN@dc<tx2<`MhrZ2jihaI&+rAKiH4254&x6Ei#C
zkrqy27G0I#lF!e4O>%FE_|La%UA=nsvtz8FLgC}%<DhwnIaZ}yQ?<jz_FVbV#wXi#
zzy7~0XsI$o!l@~mGwkc_*mxuw)~wN46Te@suC6ZaXZ~u?R^*qLmq+Za+Intw<;-OD
z@U>B(sWZ^DV#6D0$sa#{Wau6H|EODkL*`|*Bgc+)&B+Xzt{3YR5Fp^><OEvbdSz|2
zIB2r%$z*@f$p{xecXV{z)7%3&Zb(CZ!-fq9mif+p@c8lM#~*d0w;ecsoPB-VUZYP&
zmy6!ru>@_MD=aJoZMo43UDa~sN{EZQJ7~w)wr$%MsZZ)GEH6L)<mBX!ACJpFulRFf
zqVf#OVl{C6tS_vusmWRX?#{t(as7n!boTW0bP>Inh%Y(|gMxw{yn59ITJ(8hg5sj*
zGv??<Z(HC!T`#TLJnxjWSzqD}iz(7?r0?FaxCQQVX>7k?-j@70Aa4Vxqn42js(nEP
zo<v`-^Ui~y-rC~c-o<YZwQ{crSm@LzzS6e#mxy`(J(sXBF|DvQD@s4EvHbnpHM;!$
zJ=c?yR4?u>&;RlB=gNBp&tk9budhG4yKZ&l{<^(_*Je!PxBI~WN;%^3H4`6yWaSo1
zczJ2*j_U90CQg^UpTGa_wB`2CA3ge{uYXb=l$IhlrzzUl$b5fymw7_%#hi9NS<pb;
z=DiMI&ds$3txLYRH9K5HCqiK5%9WsfklXU_^LcxFS5#Ie{`~Ybt+Lo6Iy$=M^I3BV
z)2t~kG}YS8^)9^q@$oTeesx>!?GImG25-r@$OLM)-`uR;C9bbmB_}8txG!C`3e+1C
z6#QGvFK^e<+uQp>^3a}|pF)3seFcq-D4aG@@pQVqEjMswkm`v|Jz~01pke+Q7KMvm
ztaK~<_U2~H|CwyOQhQoem%V>+aj^twapcDxJ1qWuI<4;(qjIm2ncblJTaJsXtD?5H
z_val;m#WS(&29s2X~@03jY+&KIXk=i#fyw)KRW~W+FxH9_wKc=`tpL&-rj!4&Yhj}
zR6;hVoi#{4#&h=m^fPCCKuN#!^)=Je@nX+KrQ3Tym*>bF-jEOPOD{fh?C0|{d-EC0
z&izk%EYXJ4{Z=(QXMg-y;^RO1;Dlib?uKNnj^A%r_v@wlS>K?4b;<3Ij&?5&T<q2)
zK5JRj)~tuK^Y?*|%Y1yiKl$UMqY)dESV2qfyrya`%)h@+!luGNMpo9<-?WQY+N@(<
z!X_ahp$XHbEvvH8)#c^n<aCQs@tdsX`{~QC>~-duTH)(t!q&xbGF1Gn>-_VN)xy&9
z;K`GopEvgQ@|xw`IB;DtWj}LOQPHLsl4_ZUS~x+`4qB((#LAuY>B-3*_5bb6a&NJK
zqP@BrwDV?BI@jY@ueid)!$D`su=B|{6ciYMc9aV$yCwYm^b~Y#=8H}j7nh$>&_1G3
zU}9n-2RHZSnm>QP-&Zy=3VL1H+1c6A(_`{Fe$KfWhRh2WE{xccA$aHRUC`>Rvxd>p
z(O+I&1+6?YnmxHn$}DHb>iAn8lUmN4IkSDoi7hXG#oXOfDO^@o<`$!TZINsDho{ry
z4_&$>v^ILX8)(hS5)VNYRaMZIPm8iQ61TSJ_q%qBB_8PzT=bj^bgZb1O@+X}fBzOO
zpD{;R-48TTyKvz`(AtSpQ?)^(6F+|bTo|@CYSDAa*pLvBM~@$y%G+0e<H^g*>*(lc
z*u8uAfz(GE3we$o3ru<}(O0|p$gzw4pq|d+Bgalk{#Gl$Vd0e{b9iIn6mXB{3YcM;
z{P+o<w0mc7vV~cnkhHtKS>L4IUf!UfAQSo5yEiiL1$DY&cb6$@XmGIe%e5?Bs%m3n
zlaQO+JJUEl>E517&|zo0N?)s0X>mSz^awO^Sy5TJFz@cJuH@(E=7MX~9fiq`uY0s@
zY+^os1hw2#Pl?!6f8$|h<8ipUDwL5Se0|(ee)~TSNk_X9udRtxS~g22u40{@rKO~q
znc0R78w6}!ckC>F4sH@G_nRBAyDax&u@6^%OoD{Awl*j)^UK>ESsT6m!|(U|A75PT
zz9?N#Q1EH>q(8r=1%cbwDM6so+%q$c*%?4b^<`&gM?`AAS5);B;u6>E>9_mE0Xime
zRme)Eq*Voeetw|Z6tv6nc)$GNg9jNWPMkPP_%IVQvtjl%ouiy7?>EWU{|S6w3_8yD
z@Avzl(=;cjoLuv6$Dhaj_E~oBphat6UtJAc6{5NJxvHAlqeHFSFD@)(E_;73_svYV
z@~5XnK~)H7?Z&gSvjg|lRIYt~XK%H5?XNEf<?H`6etv#_an#l<rfFTJPfv-0(%jeA
z*W35+x1Te2ZgEZed?8gYj)-(ABV*&j2L~8ID;+^=-hF*t-`?8#@#XUQhmId-Pdzn7
z(DtH+j*bqf8ar#9_vFjplQFR5u_F0CXuP2f)J#*CmR3)HGy6{BV-0W%;L65Ap2MJ|
zGZ{Q$=l5;{D8;-2Hw)SlA8VNA-;?p5Z+CP@;p2cU8G)eXii_QPn^v!0ea`;+-s*B?
zT@&3+I-nhypl#<{v&BK3{9j*RXa9Qt)q0+N)fWzsKkx1?2aS3jT;2Ql=jZ33d<I&C
z03QhgmF8bwT->mIyZD}fo^Ek{Q1iR9vlDbwncbfc&J3W@tAbBYJVms_c-;GB3{Q8v
z9`Bd$KXJlijzuBUwr$(Gl07{=K?i~?U#|Y_++6L9g&$d1SR5v)fC>mPF)<Dfjtjrj
zRXh)UdV0Ed!?`bizVH8k^vcTM!Y?lZLBpFD7CJ)*#{T^MYnXLKV@uA>pf5g(+w$&m
z+1uM+Ssl**^z`)hrAwDS+M(ikV^eDPg3@Kp=6V5MzP_#z5fV+!&4n*6C`Lp_g9fQV
z2N*41zWmyC(88^!eD@jWf;#0VTzqGla86e9Wtvd?>GH19*Cy)r6N7wwcwSv!zrJdZ
zLnD)imzU8arH#M7zFuCXV`~dOSz}M-XVCc}Te7ZlU0&{Qe$PU9!lX%yEDpXt+ASVs
zKcT+%(wzy4&Y%S%$^IgsCDWkM4A5%RM@PG#|Cj@+j;p`DaeR7e>c+IQQlKSOZgHA%
zXJ?r*GSvV3sovDw96CQ;PyN)>Bd1Pr#l^*eR^kK&34wO{fp%*C`SEdvMWGUCiC5j<
zUk7jBmIjZoO=5r*F0XEwzq(=3miYL^@nedyH_Ue)29-#VQ7#E^l4~zXgcduHVX|Zi
zv%a8&1O-s*nUR@|;l#h+psB<I2OO^2C;OT2{ju9H`B=i~X}TS~y{@1$<Wf!ue0h62
z{IluT^3+pP4jyP^2CWlf^zMEC@Nj!UX{l>TiOH(a)ostt&Sqv<7rVRd<>lqckB{|Q
z)cx6U^Ui{o@3XG2>jkZrI5)?VgP;HS%gf6dQ})ZTv#=x_YT*QJRevxw3A8_KvYPLu
zT|Z<PKtsI${{BvWcV}l>A>*$;S?h$v#KxoD;)f3%VzMrKbK&>8=g+Dbt3pCV?%cTp
zI%lS$x>`H$PROPd&m+f=Cxfm%sbu{1?(S}oLsQby9$i}My`%j7ylcf@YGe1Fu6WF}
z^tyQ{4=1N%M1(}#z8X${fB&2t8yI7Em7M&@=Ii3(GQ}L;!aQ;6l#uPgB~!J-`ONd~
z1lZR7`jQ#4D&%BGw~v2Sl@(~<;pgY)prSD2?k-a&C#N&7*w3%$m9-LaZs%iVu&}mP
zHZTyFYh5n3$7>I0Ep+($xK-+3_Jl2R;RF>o`~Q6Eo;Yphw9L!PW`5P*QuO-LQg6`G
zvVxC~Tu*H3$-27g;m60vLF=hOr>9JqAh0FlqSF^2p^o0g(x5uT&+J>T6}V}!^DsCG
z{MuOf1vcCXYKd6q$Xsd#6+Z6vW`1Vi5$nVo7GAv4W=GD>HZOdAO&7ERqxAJPP?zx5
zmQ3ZUStlbmr}6G8eciUN_V*&+*=AMy`=YjFG=6=3T{?4a1ZXduj}H$hmGjA3Y4o+W
zw}Z9`gBoX#oC1r3mib76$2EB-Po6TRrKN@C>f^$~!itZNS_Q>Bg@uI|e@?DSzO=*>
zbXeY^MT;iPnbX57ZKlyz|L5cJwBJ$2d3P*8r=q;RwiYzy_QF!F)m-mF*shXH6*aX(
zSFeh8i|IP8kJ}4cv~zJYs5{^ZkF1K1k61x7yZdS?&nAOvs#T$@LFXdK*;XAmderrS
z(?+|WPlQ3IY~8zeub`-i>BF<W<@SHS2s=4BfzJMD<UZ=@?|=N%RPBuk2bn-8f#l`o
zrBxdB&wBA9<D#&STS<wD-Tyzu&GVwS=f&pS-u6~k-^lmb7d@TI(!ak-Sy)*WEi5Fq
z=ihfbIZ5^5<HyaQ0Ca3-V`#Ad_k)?4jpx7wMQ6}b=!4z&=l%WtJ-cq_yh)RoJSPcA
zNp%%JKbL76K1roV()id7;Z|@r0X*Zd57fv2XXfX;W_@{Yr2m2|h*ywC#s*My?}2n9
z<Us>^?y}%UhJ;z4nYOkzXc9Vfb(rh^y1x&eK5aeLE8RUWwJ0e$IdDfoV)Oj>Po6CK
zIq%y#>w*Ui;NceN=5=NFz9X|tvsrYEbwP)9b$5fdL-xJ@m790x&YcYvACpXSZ-u<h
zPQSmemV<|<W%lgZ3rbT~)%|{J4yyXi%*;GIJuh0tt&6eTytm>1zrVjhJw$!G^Njg1
z3*MfbtiEB}wqs9EPd5aeh&9h9^7&^~Pp6!mH50E13JUIxu7DmeYG+XKA;HDnU0F+u
zi{ZncpT#Dbmsq~Pzu(^4%F4vd462g1<lT*W6X3YaZ!T!x#lp<X%T`2h*HiI4)WRtY
z>VJR^@BnSH{B&C1^}NZdEn7^^?)Erx<j8@uXL)Cv=eMn1z4}F_+S7M;cZ0e~kLFgN
zn{VF_x^>~@%a@>$#a(4@wF(w~w5k6m<Jv7|`eNs|Z{I5Z{rMRk=kn7xAwi+3sj1-E
z8A(tlX|7f2p+`r%LG8<ks3@&@w>Km@_sCj{F|+XqY`JF9)Z8p6BeSL==j*GhmUh==
z{A1W|Sp3>hxCNA9?`v!<d@(=iF}QaK8sq_W3FSc%>HJ?r+Fcqv-&dC-1DVJ3%8~hH
zKI61?*>g}kWMjq0B+vzX#~*_ZpFJ^A8C2UV>kEUn7%lah8e|&>$~@}o(uET<Z|*MF
zSM!_Gp&h=C0kp>vG{N1{!U7ugxV+3a`0uW&>AKO|Kn>j&S5^wonKK8phn<N5v}VM*
z{N00Qe!BykQctt27g07f6$RD$1qByu#Kgthw`N}l-KzjvNpW{qDXX5y@l#&kpIY<F
z+nu?3*6E%q=%~8G?fkCi4LtW0Hk#$<=b!bx-_g<W;_V~oMvI>ZI)&9Aynny`XT{}Z
zzMvD5K|?E`F$B;I%9_Z{XTBYo=hVve5VYO@VY~c>+}marmX?Zkc5<MV&N~VpgH{l(
zo&4-xYPXo~p(a*t(6a0D@^a9b%$1*?ElQucWTLXWlBOo-#EBCbHogD#?%A`po*teX
zH*Y51-j)km-u(UDT~__t-*J1ZQa|uNQ}uKT3%eE_mvYN*o=xZG^z)!efT;Q0o|8aF
z3pk!WB59n)1KMg5x;pIO?c34sJ(GB)&1#n0``0{|It=dZYk*pKpbQLZ`b&f2bFn;l
z`cO#vxIvDLsu`%ww*}lkfE3(d4WLRKq~Y%6<^F;~LQS`~=Y!5*pO6|^7&A#_P4srZ
z3s!}oZ2?P`s9b&Q>FN37_4@riJ5H2bSrN#rsHh0qGPP#yTG8Wi`)WETOc1!TBGCDQ
z)ke_r%XP847bPBUn_-m7m3D5<O3ScKDV`QqR-ls)3{G=j039~~y7J`br>CIGdTaJ|
zlm6eo!RydmyF>){1ob#Jvw`-i{&?JP&ycczpGoE=7SORd44|_k+WBOI?z9|_0SVsT
zo_~Br;NmTPOP4H3INZjYadXqshSW#8k(*dzca=CkKGu8olc}rty&Vp>pPilU>aU=r
zWF$T5&wl$zMaXbna&mIBsCF3W2modVPy)@&%(STbqS5eX_bX7J@#DvjOyQGOZrHG)
zLB(@L`1*N{>YqI(wH!F$psZtTn|gZM(G`J<4H6HrFx=e#WR_X3lwRyEmh|*=kWrqV
zo))FAraV}hKfkq=)yBpKbau$z^Ly+5S}7?heRy?MTUp0g*MFXk<MBS(kGJ#pJ5EdW
zn6$()^Xb?B-jh<M&7b|^MTUj7b@x2SpFGm-Ma{j*65o0uaax)qb4vFc?^7{o41>ml
zUfr;m5)Bdu*VLfC;fBHz>xvKHW*BIr_U+q?D?UDoIzLh6q|W`Pw+|g+0*y3YUhdy_
zeE*L}+&MQkF!syan|(6+=;Z7S8UX^GiOk5zIP3bt?Ca|iudWIOt*-?wKb~h>%@vnb
zqo=0_IyXmu|DUFo78VODD<vZ%p?B}zF*MxVoc{Rt`~Bv(XNw1%11((Rk+BfCyv&!G
zVNKLluETA-haVnp2c2e6QBeW9ya9CO2WVRC*O$yKd3U8i7e{>j2-;*NrXR;sU0n@|
z_=^`Wf{yNab#=9R)vAj-ckEEm)8qU8?(X60_j}tvJw2U$_lWl-l|R2;uWu6Tdi?Tb
zC+MVE>oOkDSv$?m&Cj-4sH(Dp4!QdK>+8na-(?qrd(+<D+6ua%V(;F)FEm|TT;AL4
zV}=|%Z3n9Qj~qF|zz`H147%0AXP!-D@tsqrxHL627d@NVbLNas%$^Ft!oot(0!gna
z8j4ku3^wUJ-v9rv{=eV%|G%nTw{zYV=9Kvh9=>?7;%CMCdwW59s<lE_u`s;2x7T{#
zuUFcEpL^b2Sm<m~@?wJHdDAbl8uv^eAL~8b$}J9>4L;T@y*TM;7ih)coVjy1W?WPP
zotyLU;loAgTn8slD^`b>jsmu>8sJFJ2UXPfLFM~#(Cp_)Su?)hYUVdAz~bO?A1*Gf
zjwXKbZMXhDhnJU@ZcIMTcV%5{^cR_jOw7!t>(@_G0iFBP_5R^{(9ZJC&dv`XKN@~>
znG72HS5a3_esrW$!YHNV*;m(Tsb{TgW<NgqoB`AT(TUk1;BapJ?xkK+onm6<Y)qfI
z2ebo6LxV$6Q8BHuu&$=Y=G1ik^*<}Vzq<?S2}W(t<7EIHOOkeWmTJb_2;bReM?oi5
zmAnWzoBi&^#l?&aetv#8c9*Y@jH}^Gxv#O*XQmP8NQ)PmYU#heyact5t;*l6`MC?U
zD(&69z1^(bVhU<%Y{AR@ME6|U!NxDwBdF}QAo+M7XjRAYKH0?FT-_?rethdramc};
zPnkheFkPbBpmWSYyH+zZGhbX<+WqXu*Voqr*Tq;iav%Nu@ArGq+{M|uJCv1_pw$~_
z2mrJrfBF16t%{|EDXFQQ^CskjX5;H_g7#mnSfO!du61~^jj^%t%$YM6J(CpOpU1Pg
z{(s$%-@g}^zrQ!@x->U8cL-!>yZiTdcR^>swY0Qw#QpkK`|s!To&Ss{sU+UrRhpmJ
zo4KptA(NA{b7E>LYkqz{Xc1~)U?6A}(z$uI+zcAQ%XpUg&+ltwX6K62W&^e1&q@D@
zO9ho5`}24XAFBk<=(wAI>rK32k^iB3DyX^sXO|(5^mAUbzPcQlyWk$*o`dg0L1P3T
zUmr8bk-3|9Z%-#Hx7deApZ`C9@uFjvX*LrBsD>zddMdN_{4^ELR&McQ?((%Q4Gj!}
z#=fBa9-via_Wyo3f4&v7(1{gves@^dv+7-YdwYA&N%Ok8yMu}(x0sY&@9yqyfAAmy
zH0|)|>FEh7oO*hCi_$p*w`2sK?d805`Euc#8-_k}ECP%7Bpht=@beQh_202A_x7V>
zz0#nA=RmE8HEVQ2R)v6cZU7B4`OjFfLgS*ak63=p0$m*)o`VMuf>v&UmbFz^SAzyR
z_U+p@Yj&)Fpy0**him@3`hZ54ru2g@sgRSCdvS3wd&8UEW&8iBK3pBX9@Km;dwZ*M
zj>Z+x?#7f80-$ZL^XAQyuqs*cECMuWz9lo5g_U*YSx?)P9cH<=5>8H1-LQT8@r#Sy
zCr+K(x-NEiR^R`h&*yjTHWF4<Q_G60?-tQyV({?tx+L@c!v}-e<;p*QKA&Iw_np$S
zFL^5a|NYXA+M3nc)5F7X;Lp#`8?&$LmAt<vTUJ&Ex|j?!T=eRSCMfZM7QfuvyZgb_
zW8hU+&XouEE!>mv7}j71wFUS<)1#l7dOx$lT6uqOSb!#sPH~&{<;mCmP>kDCp;*;+
z64W03_2nfqLqT!z;VGKIA3h$J=Z;I=wPwv4(CSQ+%u6m`L?&O{Rhs?h%VmEF<FuY@
z8+YumSQELK4YZtS!x<CMR)U2K7jkfM9XdH#UGcP0Ol<7NvbRy7B`*gLI(~6coMn>P
zB&r>@z;CV<2S2}iR+bhh*IL#+KE}JbetNd&B+%J`COJ0(zKEPs2X&?W=2|TbUJkk@
z=is@y)`BuJJ-yQApyq_b%}uGG%Wi)B_%Y*d>rWRKmwaaEfbc1H(4w>K>+2q#xBu^Q
zagi(N0vyX}lO{E#o}LC8(R{?lWmf;MrsT~HLF=+N2Ob~q7ghht;BdH&cVo^?BgfY#
zrktH?Eq;A{{PF4Wb)4DR*`V_5+_`fMo8BMVQ~EmW?A+u|h6On{H-Sz>n@}5`=kD%4
z$G$%9bDllFoQ=Wk$;I#Q>{PC5@|<m&Ep}>(W^?WDZwo_K21%G?2!OhXpl#0+Cr;Fe
z*<rx&;N)a=(CJqDe!sKcY+Wds@c6~yV+;2r+y~9o-2<<sxY%C{o`h}cb*?-J&cNWl
zIViK9;x+@tulx4M&1s1@HY9%d_%X0%ztV#f6O|XK&zO>Sc2?rC9?6W`+jJQ+@+?BO
zLzdutu(}Ky00qs(^-7zA7EGvkI;Etj^vPPcfsO^ax;lJ@UG1(HGu@`no7Z>OD(YQ5
zY%Rd<a%Io}GM`L?≷yJ{(vRx%tD@@c6_hCnlzSf8YAwwESJnmfYK7vesoR44`$)
zrLV3qGNh!YDw>#x<lfpMXc@QzG;90q?d^(RUo=x9uUX}-<JCBAv@P#$SMBd_57+Pi
z$HV|yZx9z3_u}g6>5=Aq2c*TH9JzK)Y~Q|pphJ@;tNVkdQd!v9AK%X3e{}o(y6&v2
zs}7z&&tLoNOQN)ppx{$MSV~am6499O_@s4NS=p?3wb`p*UtgbmV?*Mq<KEMBI$K&;
zl=XyOzc1%CYf<s!;O4IO&i0938MG8M90?lO28~*8+jdO`bl2L$!|i9E%~drrG6Ege
z4!T7S)C_KTBdk^Y>tS^(mnf*8cJ%q_m@PRsg#-l!LE|0Z17Sd2QypDhP&oh^Wx9Mh
z_=A@bYx=o42SFQB7Q68>9JsPF7?j0%WUWGqFBvgR(FkOkU;ocC?fg95tW^czsa;jG
zzQh~mkfz;<0Py@!Nit}hmj^s1C(+jH+y<T-0*%{r_JYRYAnnDwp!MJE?ChY5BKP(-
z*PoxBCT3=?tmsqm<lx~E*>a(xPu7}E;dl14_wuhl|N8lU*NPPyM~)xQwyXR0M)J;`
zI|71&jOFF!ji-IQzrMN(Y7q5E7%~Z~`>{-@Ei`1<l5vqqJAB=hJ2ppUKr4)H>?~HF
zG-=X>RiWCTkr3OeFAg6c9R&>p)qK4gzDRvm3uw>@RCL$>vjLrJxhiyZRv&0<%)dWB
zf4o@S&!Q)yZe=A^`}^C`mBGu4_I!{z@y{-`Pke#8s_H`Lc0P;BPbyrZS}k0nS_~)t
znO6q{2!KZTL0QaWqEgfJuEWyeFF@m8JdjbcqkF5r3kV4{J$R7dGt-DQc)6czTG}$m
z6p|1;oy6^}YW1CM_OzniKR!NwZTzfRlR?X}PEJ-|b$ory&ZeNHUXq0qBgFM$3|{oD
z&&<s1=<PNAz56iJiI05G%*@QvzV_*Y7M0Zf`RIODzqj#?HMhE|>cPW@nNv?qVVqEV
zC^#TMz%1`hM<X+P*DUQbH#R1Nwvv7MQUdDRUtaEi95h~0`YMFsrg{o!fa`<T#zl)4
z3(Co@`w@3_Uv2eftB(u}Ny*8g>TLV||NG6*0IGUzx5w-(^6>LByJZ%97}V|yOnUr;
z@3)#XxO4CqJoVp}cptRT6eJ<7jw%6~DhBI-N!*>L8@=r3|Gm}UpZ$<2-pR1H^!2p~
zDx51<uH3L~+qIfCZlHcjOZfUY$-<?Xfx9KH+_}0gR@%K^&eh3@38@|iFWx)*0u&ga
z!M5}BYzs<DMQx8S5!DLe=#@6VR(0pzJ-NNr-^DhZFaaG)o_>Db(L=4=pv^Ilj&^s?
zOEFsJGqVYF2++YMR?zm|g-)#u3@=~41kF|+>y>U_8N3{H8)egUDf#@E3DusSo}k@}
zphKG@r=9(mF6QFm@}C73yX^C9tJ(bh{r~*?{eHvd&CW-=L>WOd#Gs?{!q&xfHnZ~|
zx_2+`Ly)13tu3g+;*qzDd41#S>+9fg^<OWSGfnF(e11-L?(xf)E`ioaf*J}9Kkpoj
zIeT|^xncS_8R%L74sLGe)6;Y(PMFZ}|Ic&#A8$6F57=K<d(rs*uH4((K*@JS$jV9A
zHhz43T>IT8(2Ag(ySuLH_`g~iyW1@5`nt70cT{|Q)X~!ey01Y;R~NKureJPGe9cGD
zh}6WXQ<qlUIdq6=v3viqL#^Dby2f^q(-IRC7ykV5_5bsdq<+i!F(<)O{zr}(%KU!D
z3o120>#{)=$#L+&4@d&s)Jp`f9so;#=7<)fNc_#eJp*z!E~uj~FZ}e_9Lr+RbsnH0
z09Eg4E+;3cih?u7T<h{#XRYh`<?Upmx97ROzP9$_0!L=hBI(<=t&h(RpE>z{-EUro
z2ag^t`Vlez`gwD8b^m#w6(I&`XCy8L`<&aBd)px8gg}q1b=b#>gH5c4X=fxrCoU~q
zxG=4f(JDVCVaERbuYVrx76&ybVqy%+-b8HP_mNdl@S=U{!vCPon~RIeE$Fe8pgEzB
zA3s`Df71aS4Ygy31*jAPtt3(NpQlr`%wTi+c{eXFF3|a_GmX=oCaJWvv?M$@(6}Og
zza6MJ%DlX+bDkz>69f}8GiZSTXp9YXfb&FU_cOo5&w?gaKxdVLmV?~9DS3Xry?a`k
z8Uwg1TllEuk>1bun~I;GTNt`JjLmj?<>zM>_5c1v$4%KUq8)bTjsJ_E-)`rFdUT-n
z+;ac<Zb?Z>Lc+p@zrJLGnx)-hx<<R>S=7|kLFd)Z`p@v-Xt#LRanM%JB}-HedLIR^
zhc)DpcJBmD3;#^NVUaUu4rnas{)^+sz~a52<pKzC(A*7*_?P`rTeFt_v{pTB1oFqR
zUg>PP@ZbF}-h*;n@$+*l<@OgmWLoAoH|vON5@<XHG}3)<Z*}0-tWclXX1t<WAr7m<
z)^12V%(i)NV(4Tw-wRtZgHuvcH0;8DzyDfT9J0uTbBacw(-)q}QzlGkkTT6$A-6tq
zvzm~Q5NHr-j!mV|<Kz9uXBZ}f8hatDLNt&6KXVaOt7l!++LCiq=-jz;pm{0Kq%3F=
z=doVtj;=1yIYpq2uT@&0B_66LH|ccCIf7d4F1w~`hx6H1e{)GlNa#E6-Y3(UdwUyb
zaid#YniXgr3a7A|f{qT)$&)7;7^J18LEDtM#r0fnZc1g<7f}bz#f7as^ylYi&@qRg
zF$mCH-0Skm6=zSM<_=#M;}{YmqT<=Kc(JmQva;#>1)$NnoSU0iudk06-}B||=55=K
z%`(ltus+`YY%*xA^S{5pFD`QB-t+xl^{nIOIX4*U>+6>+U*0`K>(2fAy()Hga=Xjk
z8r?2e{<%Br>Z*lNTeEI#%?|H7zPs#g*Xr=~k6v9}?G~rj*4o;7jgxJY&hv^(2VWnL
z-&>Wsrcw>kd6Nar^Gd6l^*y{{VF_*pd`Z3!nvm-QFAWirK3)LYyHN;P9{_4096xqa
z5;Q!RY+=UtG_0!13N&4AS^NyN?q$*Q87$n~+&_N&SOA_(m@-8KbY-E0O@#qyf_Ck5
z(2&&oh@8a4M&H?H2ag|DKmK@i*xExg43j6!nw9k=b(x~7Dywz*JC}k21JD&nGiR=>
zO#k9H*XrqytzY!4Dn2MM9JqWr_~S;q_4D)n($3B41U2-YoSY0^Q+9j_sA&QkW4*Vx
zy4dF3)2FS`+w&ftnyT#<r*;o?f-PuWIcRak@)<o39weO2et&wpK4`b`y}i|-Z5_Q*
zrb4#;9UU*`Cczf|y!`&-V{*vasL-z!TeGg3yg!k+?$lK6cHh}%53jBc2Mzvi+O#QP
zTTY~iMu5W?lf+AxFK;Y*>UCzmy}Y5JA*lcJ?Ck7^uU=_Y%{mEM;<3zkHXA!TyG`An
zh}S>Z<!c()`Q<nw(rR40#awf8);!wC#L5L)qZM_&x4XM}@7}!|m(84F|NoEhx^?S7
zr=>qW)?4`bneW<iWlujp&~kkiebar`<?j-%tO#6n+}73>G}i!Xi-PVHwpENz0Oi_?
z$Btd>1?6&3_65(nESCQb>W$}uJL!<NAY}2!FVHyfF|Y<u_6KQ*o@-TF^tHxwQo+AJ
zKeul=W+JK+A+XeYy4%4fR#$&R&Gq_mzjt3<9sc}BOz|#;zehTSEy~`^c=mY127^00
zi`~IXXgD}I9oI%}?b&f|%Z*#N4qd+vS}fPm-+%ns+1a4380d!1$H#h|r)q_sd6abX
z|K16AWb}2+LFc-FHk^YF!~(4i`T6N-@g9M_#m~<%UF$RjmGzRwY@lP$XBZ}fMn=I)
zF9jqdIzD_T(23gO@xjaR&)>hGTM!x=81C(O@c-w}p9>2f9s-Tm&7UuSYfI+g^SpwB
z7o!h>SHE_2d}=&3RXh3nySp45949{hcz1U<sNhy!Z^R3_n)SnB{*O<m$Aiv<0xcB%
z`RS?ac_A%bU0&_*bw@zs_`<@><>lo$H#fDae}1B%t<Ak{+qPB5A3uJ4_Sy6gUteE8
zKF_wAXV>Gu^K7d@>uQzP7}<iBl5b2pD)Qd#Q@N~l*^z0w(JX6)PhY$k`23{R^YioD
zo12>j#XFA*Pv-@<%Pt-}X2|o~4bm{Tf-KPa)|&^OaXAcLmeH07TA-=15j5ZS;ut6{
zL9qzYuuVwS%VCnrMPr}1|Ns7O1l_4EYb64ntmhDymDR0kI%!q&!yxU<3`T|DhkjqU
z5YW=r_Uy+Ut<Y5p1_l>qeD;~v+{_F*e??H)?ZLIR(KohaPQJ#=ccxY6bj8n4OJ8OC
zy1B7&iD)EDTYuNK>dS>c|6g2OEP7nUvq=XuAOl+S_|4=Y=oSF?ez}LBUe~+3yG4)d
z=;#>K{i*1Yu?)IkwXxzcQ!Z#&`O?zvbM^j$f`S+KH^Yb47#SHQ>}o8mN?tTvT<os>
z?!(TMlR_>oE(td`r8b3kC1z)L_w?|HXoYxu5t;n(&6}PbJ1jseGeBL7IcFBXzU%Ha
zMI&)drP@-*X0{vK^W*!}&!(oOfz}3RTw2oEkb3O-^XKiLiT#_KQYGwacD(uw>J@-m
zkbi%Db&E;2`jMyds_N@2&^-ngmX?V}It0P}Zv{(BNzhh~TU)cY)-`(NgO+gKyczk0
zXK^wpLNbycOSB;};q&>1$B!j~8r0wz1sACjpjq#8_J^U%@XX9WL-LT^xkc8tD&$K`
z4d{-98(Xu*v#zb_{P*`aXpN|unOW5N*Z21BZYVt#zR-#FqOi}k>G5@)iq35g(^9AC
zMvI-Eu7Ca4t_k3=wQGN(n>Ok1>g(@!?-Wu6U5p4SqSLB3ub!yvuB4>I6uv(0?8l0|
zRbMZxi?s%wC+rrd7U$y9@`6(>_uZYH5|%|Oe6m(8pk+A@-(GKRZ)ZO>O;@{OuEn0h
z#%*@BzgEbB?t=j-0bTl>b#>K;FJDX^87V0(D(_c0y-BBv1+?Bp@TGa}uM*H9$NKU6
zLTus|I57ImGC7%3pUKDoI&XZgbvfuxfs4UDO|7l1&;Il7jox7Sm*Lm@Lx&H8?pgs|
z-8R|Zu5tEkY0$v}4<3MSQF!p<<711O9|lp|ax|-6MXR4S0<Ea)=->dIH3HhZ7`j@l
zOGLA2$r6>AT_v23j*g(AquFM;1rH7|Zr&qZI#J2hp#EPC3k%Bw&<^K<0*90ol{<Iu
zGBOlDJ9F?*D|hKUm+$MmJUtzk`^^RI@`#9x%&hzQ{li1&l(aO^dZg-aZyw%l|9`xd
zTil@hT?}Ynh@_<CqURjotwi7nazq+X&p)%b@P_#=@U$9ej1*k>1|C0lQre79+Fcx!
zyCJi0poB0byuLm+EIChn{lvQMd3T*&URqkYa3^C@a&q9doJbcJmyEc{XG1|Z-#>ob
z4C*sj%FVZ{wE`_V`unR?Szr0od_H-*oC}}r{{48oeb14SmbSK}!)?4jJ|33`-9mfz
z@&5n+tgT94wfy)|aklj*XuCoqGkejVk9>lHf-jH5ipYtOD;XZVyStlV)B6uMm-$K`
z<-d65B6Mp5D8c>v_it7Ct95~k+ZsxbnI|9XiLtdeHWoHcKUd?O?Q<WrH8*gv8|a9M
zS@JfgH-Tnn*2L@#dM+D$-!wBbQ^K~&1a!#qnl(B{4I`%|W@dJtxBoBGEv|2NTmIDc
zoSQ;rWo4jKY_ECR&YU?j<H7<)(78iz?(dKP5|Vi6&>;aixph0FOF^fut_)V+Y%Tca
z)6>%tJBw8F?(S*@En*E{ANS(gT4{y{Z*Fb|O)>Jx*>o_ma)Fj*+yD8{{NU)L4d5N9
z$g3vhp`9JjN+wXI1jia=GIY;DaElpSwIWtcCW2PEf%1v}d^=aa<({)o_safzH$A@2
z@I~d?sI66}y?qX!n5bL~s#^slBz{c0c44;yXeZpMDS>xHj>O!&aRan0TEe0rq3`(h
zb+O%`9IC2%^u*~CQ;r-x`t;>_ODn5?r@b}oU)|cOEhHpV@aPEV(Z`{y!;Y?v-fob0
z#{x7~4!RDxjaM49NZ4ntRp^B%C8b4wdZEQ>;J)-1yESH<p1X@*){2FnpTBwD?0NI}
z^7HdsT3h!%4PB;dX(<W1p{VdN8>pePGDx+estR<C&KDC!=!Jox3qa1#w{M?2R~EFs
z3Ur%9&CgGZo^u{8S5|a(b#*;>_pWSaX6CHpDxQbR@7K1UIpYI5?x?J+?8Eo(pt;w8
zWj>OP*(XE5A-ePMzKh`PtcuPX3t!wn0Gnf$2CW%s=Q(<8VLdabw47`WuJcNBWbVq@
z*Y!L++z#59YPs*(zI_*)ckYp!Y{kvZeb(2WC-GdoIq1%VU8S!Jet&x_lmAM=Q|Qv=
z%dBgSWoy{Kn1hB@{q6sXe13lZ{Kp?V3LkGMeC&4Q*fFWfnI9`FDjX)Myt%($e%iEY
zY^Ix3JVCRJg4a5~{wlTDe&*}e8B^xWne*WF>+YMI)3fEeySkh<r=5N9{(b*c?eHwQ
z_ZJp2gZd4hpP%oZ;pO5o<vo1w(Ua-%bqDv={uX)fc4=d>`{td@TW5u?4wL-CoLOIA
zue?U^{IzRhyUX5Q`t9AlWQj`2yE~GgC0LRF3hYcxMJKEKx6Pg{ZB_b8rK-<!chy%d
zCue6+uOno281LWT-`hd6k&%Z!-1V3OI;&!;cDRz2l@#ct)jfOnUR>%eesOcl>kA8+
z7cE*OASA>T9v<%E?*15b1^3qM>l0?p>bkhtJ^9m<lNwQ5R=ilL)(GtlxZ8j8g{=Mb
z0(T2|j)Qj`CxIH7CuKp!m3t>x=|k|!AFmwHW^U+Ozt{KnT7P?Uvw5PjJ7{&((Qfhc
zA1j~z+xz;w{r`{}`}Ki~+a9<cOHWQ__MG(K=~GsDdHIqzHw0O^L<DS4KLK4w$1SGg
z@b=bLP?zZH{$S(ub0(jRE*~y;s0SVY1sW}cuEWski``Yi3A*g^`np(98^@8mce!h~
z*aQ_$_dc1%sZ*yuORnvcx6f-SP5S$O|H72WW2-_}7refv`{mtT>Cn|-tP}2n_Vs}-
z<a+r2eZQh}TgR*%lRbrvb=$UW16`BC#v`$yG6!@@(E0j*&5Pap4_&<)`uWEsRd3J`
zwxXt{=aCR4rA0OU&}{aUSyECGG%Hf}_7-d8v_Q}~P7X;)N-CaC+w<-U2ni*H?dRED
z{asH+MkXOSS-Gm~WMN_9!KL2QHzXhD+md}<@Az|@x<3-2BN=BJr*9~D=+q-?eeHy{
zuk*u0t)TtWpuxa-N_RG;o(7#o2-*jr>OJj>&A#&YaiGxv{rG)X?ws6{bhN9Zt1HOn
z{2di_^~V<$I`63byex9R^vR!}pI_XP8N9Z<eU^Q_-M$}>xEoI&seZrryMTbe0*jlE
zj&urV+}xxJIu^8*TbwH<-3q*E<kby}w#54y8w-otdnfmT7naNa2JJg6&5?mLMt2@Q
zb`qSMFZP2Ih846;Gv`j?<0or8CMt1oa0Jv|k1ZA#6KmU;eEiY5xz=6B=gyt`@oxG3
zg~iX$CAD#WcyyHe&5e!B2M-<uoudmn{sXj7?)Y)`yu7?c&u8+uySsyW`?t5{3fmri
zvbW}^kp2HZ#xXH5A^KO$#lOG1>%7>l7qrOg%bT0Q#e%;;;adB<40H`PXo5^DWQ9V7
z=FCYyKR*X8I5>WCvU=dE5Y3|-K@Aw!ZZXjC{IOnX^^AodKOAHI1sWtsKHeAl$7gl!
z?QNh=osh7w=zqWX{dKmWZKvRR@{^YuWOc~*tKsn{C#jr#e5`kJa#E5>|M6qTPCY)}
zKV8*x(sG}fN(Bo)Mn*)OaCCHBls;og`uTY$_4M?L7CN;)0j;}}-CzHIU(DXB(wnDF
zdByFo+xwAymOyxTc;%H9fs4{-v~0`0ed_J4t-&_mK0WomdGTW4wyj&In&;e5h~HJ>
zInO+QUQTMNYQLOq)P*1;)w{b&CwGhKYQ4X?+1=02Z`%3!_WIY?$H(i1t(h@r;zY%&
zc>!W#VxNxnN{jX%J$CHWB$boDzr7XSa_S3s@fUazIB1CwXg=u*sC#k$Ne?K_AyWkH
zkUi9k<)zir!4nOT1n?!lprByFbp3d}sy5GC+w<q=WM*oHuZakpXI;KdModhty|wiu
z=sH#Hur(UdQBkKLixUKeg_ZT=_C%Bw7EV<4oOF7cu6DnqvD?4D-|xHn3$OE-sPyU8
z)zz-&4J=QdJh^G{;>CLk9y(nN_PKU<cX?`le*VpC*TSZ$curIC1cgZT_jkJYcNV*U
zv6)=@>q}<ky*-tS(m6gJWS2j|Ev6G-YghlT=4Ug%oxvj|qf|LLxlP^O-G5$P)sCE&
z`t#yqcTjYs@bmMpeeO5Y$o1cc!~DIr6G6iSiK@StD!}o4N#DXk;_t7omv?z@U%XiP
z+1c6cH*Q4y`EuF6tNeMz^^^bW%d0P?<>!M|ql4C~RDXX5x_%9OoWYL5$85K@<#yk=
z5dm5PmVJF))Ag>cpv7`8E--=?oBaRxH!(GJ-+!NfpU>NawvQf7cJGsMtf{ft_v@AR
zm)F<%!8f+fv9Fi={r&y%MXud0KBk=daeEHL*Z*x@?mz$8kE$!1QoR{h_kfNe=HTFH
zm_A*c0W^0CT4fKqgW~6>)GMpQ{XaMrrbM=Z7O-!;E-$VX;&DV}@)1xMGVnOG+d0`f
zXAb1-g1<M+A-jY?<3&e~os@+w+pPoF4dCPgt-RIK>+0%2B{UNglZ(HhCFp?txmKkG
ze|{8-=*2{Qu6TZKu3^oO0?-tYaoQP&-DPiC)`=_zO>~-OiGX^G(cAMt`%OS+V)F1D
zF~48a{PFSe?s*zLvu8`6n`5b5)pl~@)~&5Nr@P8;s4o5V^mOv+X}X|eU=FwQGcu%}
zo@V;{-o@u19v+@ymOCqQ-@7Bnk1H!HJAbWkb7On-_;K$JjsKvb!Hvns&%An_c4>(x
zXrce(W4#X_J!*1p=TlTxW?t;xf351>y}i|-<E}U(JY8JA<Ru&w2K8p1GK0=2d3>xl
zwBJ1Mj>K&9e6vSNMx|wCWuR?1%a^Nz4oe1&CI0<>zkT^~^`PM3jrsTOcI@8WJx?<R
z6upUwjP>>PJu;R;Pfty~{EKy=il;^WzdZ|DkA42}F?ou9eB8$y4-dC1dJ63-eZ8z=
zPvz%lH#R1>8$O@e13Eh6$A^cYDTuheRjdlXRh&I1iTwZn>&EVP2b<Yf#O>YnXydD^
ztDUE%s;H@PMWtGS*4NFLA#wJ&rl#fu70!hV7h06RoAYSrB$dQ7GYpT-(~yyFFY4|E
ztpJ1!8wi0X{PW&OgJ$~cK+6F^9TG3_=+Ul?g`f?hzrc+*&<g)+o74S4``a?EuagC>
zmH{uT%3x!VGRaU#m<yWtIxxqwSVVmO{;(YdiC^B|myfUgI<+Bn8R$$@&?VsA;`$Yh
zh7F)wR1P0z{`~y>@dpQ+L3QTE$v$r1-`xc*F1q)@iC<e=dx};l*R^ZcX1xz}vCO=&
zK@oI*&d%cWE2~1i3*S6C+6_9Ma<N-4%Ua{yXBCf|uC0v*E%~2eR|{Sc4@xFK|8FdR
z9vC?N@BicR@&b`8fhmQIt_2I%?_Av3#WiJz>$^t`w{(|!YL<Cd&9?5GI(62JXF*v9
z7c6|jw5X{=wWIp!B#)%1Wh)dq7M(EKZ~w#6^xy#otLqQ;$UQIdGoJr&&i9WBpG$tk
zT>pAhT*9Ve!>QMkCQSkzgasPZZBkQJQd;#Jdce>Mz75;AyB8H1-K%=NmTSGdU5&)I
zZ{MQkdD;9+T2%Dx*)xlR2MnN#A1*F-KYZi}i<_I9hnE*<lg*2dB~4SOiq1001l{G<
zE$3=sZEZbOT8Ht$aryd|nKLCpOCvtj{QdPcaDQEGZr^g_do`bZ-`w2HetEfn`|jP=
zQs#L&RVoX;yuGi^;|q<7(n?a9t2F(z;`Gy}ZTIKh-Bon{<>TJd4ASnhW`0j^SWHd6
zzar^zMqBUVuHIlvkdXPSjfGmrkFAuEb{Ca)H_nj>&6#rwEEL!eRbsK~hQ+MJ$06(T
z@9#VH-`_*>TsIeNEr5qcdF*`g7qe%~P*7KQfBSXL9GMw2W@Hp9-7S21N%h3jBG3j&
zWo2ePJ-r!LrCKRQl5^(Fap_+k+AD3Ycip^S-X1ioWRQMNX2$H<(|?z@s(79_ckbG=
z8CHr43Jk%^d>W@u7gzJ2$K&pPoXcDXbYDQj%Ok&^PLJP^aF9vHs)Pe{Ykea#JLqzF
z(E8!G+wULSl6g6#E={<#z5Vdv!_1(yprEs7x8+7NIJmj7@yXluwDC$OU0oI0v|J_j
z(fjxO_4V~r&(8RF_VQ(6S6A1lc|9E+FMb|^t{N^qaHLasW5GiwldLNo@Av)IyR{{g
z*>e);9B63kyjxsf%y!wevoj2ti=Usn`eN%Om4~06o<3ipbhqHwm&~ch6B83bvl*a1
z?A6ubhYuWBa3}jqVS70PXeE<v)477u(xcOKqd~iTA|fIl{Q3FWqVA7HT=iSiE323P
z`grhYxA@m@X@{8E`5xRYzkhU7>S>q$MaC6YAxGE6>{P01v1;rMHZ=1)3W_Ia1P9AW
zFHg#uvub1hmE^}EJ-v%1&HA*=`qFM#Jl$BRb?n$mDQS0GsFuf&G!eYhceYuloMU=r
zRn?=<=k1R#aBP0??AfxSw>LH>M{La!W#g04$gq05yY8<QsQV!*+G?DB?!di!a{Kn}
zn{YA(v{3HF#}-Me5)Jbk7booAZO!oDP%F3SzU8k!w}~I`mp|UX$PC(T`0#MMvXYWh
z<=I=eq@XKoPO`pOvZ(m^Ind$r0%BrqKYmm^y|2yA&h9hMMzZ+Xna1Yk<{OHh>VJRN
zdM^xk@a^sG4VyM;eSgoPq@=XU&U0aah6_JrDrl;<rY7jvV$dc*k4Y@d%*+g_%O`1w
zaDh4^pz`WdWo<%2LW5rHt_7~$Vp8>I=h;@zd+4$Y6fKAN!y3En3$9*|ub8-MbNcy3
z?)`G06`r6mOVHJq3l=bdX1c$>yBiw!`pp|2$i5!O3tJxDxOEFO8O_1PC1l&>x8mJz
zzWRF?_HQgamHc?c@nZ{TB|L`YI_Iqi_pOuwg+1R@7HEc(S;Y&EiB}s7SEzyF@Ns}|
z?9L+Ayu3Wn0T7^#RNvm-W@fl_`Euc(AB8t=-Fo!m;^Kmm5)tba(<G#%4jnnd;@rm5
z=%WU@$!t|jMQ&>9(xop~=-t>+xY(`xD>F0mR)gNWkDoprS{uE+;LQy~5fPCC*RF|y
zR&##&!or{vwT0t;-S4&ca?XW-j-80ukid9b;?@7Z4o^S+b_)#)69cV5Z)st9dR`V3
z;FfvMoj~($A?y-TQlRnIAMfk`ckkF?5wp9DmjSfy19Y&%T&q$cn}rgJii#6XrYt&s
z!Sc@4y;WXbUZDF5L2CC_i8|c8zc%r38))H9TU%R``jx&uS!>Yx`NYIT(5Y<e<Ms*&
z2?f1toA=~N%8Z#aLA6|yn&|2K_vP=`|F_M5_49v)mB>{wa9Z!$SZH#5-%n{osDA6M
z%9#TeK87r8)`u><Y9;7AY*5F(UB0g4$Bzoo@SnrY^K%|NNci)<{(tk@wQC<}ZgpQ6
z@ZjO$_Kwa@M<1UaxA?=YwO{=6_k3)7Ay{&4WAbqUF)=n{V`H0|9~<tJR##Ww*-_|x
zASDU38}aIot;hT2>)R$@(T%C_+j_7#s<WeGp4_|!KTtrrlul}FWK>d8stD%4>J=9!
zw`cF(!be9qBO)RWoIJ_taP#a8P-p1;JX_F#Z6-N40zNERq8$_*3_3aI#*G^ZpPrm7
zC@5I*;o17UySq4N^p%|a^78WPuT`FtK&OA(FV0+{m-sj!cVj*%fi2NA<GU&%-JaFm
z>uh@Pn4<5-!WGMIScF99$gJWt^ScVVKU~(j?7^3pmrtBN?VOpp@>HqkBv1#Lb5>u;
zQPABte@(f?^=jBAzcAYw6Zf*zb5cT55>s_`HE3eh&CM-pR!_;yrAt+voSi|FL~q{Y
z+_-UL#heB?DJjs+t9SO*Mt@jxD={G<VC{A9NlUg%$E839@<9#1ySvLz>ncrC;VdjH
zY+81C-K)Hqf-f%u_x|1Y(;OULUrGw0+jnF^XE40EyIUMI0NSugb`?9XR7;<%b(gFU
z!@Voc{)esK?`bZ5eeEHrIGdfnZ{?rVjKDxa&?20dmzO_YyZxS1Ma7N>o}S@<K8rVt
zzTLJaK;z4=>5X5^nVFeACN256?$ob;wTD5er#-8?78Y72$M*#uJ+|;x(>%4TT=T
zIWlKA7KUsrT(RwjMTl_DoKvxTt3>7G<Un^ug04J$^7QG!Q>VCg?%b)NsoA)7tLd4u
zXD7~_saX}W$m*e|HuF>e$$y`Jo}{ucaIxDA>+-y<V!qc(TU%Ri>?}@SDjf&jj#2Vx
z&!<z`8d_RTMMXtBSzqwW+qoR?lLcK`bL7a84!Kb6tWWb|E<Q6lzdQH#wuATY%TH1{
zc=9A?ueABP52fz?a#ug4Bo#bvnsxfrDbP??h}k{`C8b5P9z)O6v0AWUg8=AY`|bDZ
zxLchT{%P2_WsArp6;R%kHqUeU`|B&K|0>%(E8FL_flf>K^5SBa|LU1`wN~5m@AvKh
z_sjeA<caHUZA$HSTR+>P@R9L67xND#8ee^UeHA^0+IXeeX8N=(bZ##?{-0|Ds91!h
z##J{gUTrK~bqrK2!jfd*(PN<Ihbg#Ngr&=;ph1jgc77#0J2^i;KhWhLNl8k-zPxM>
zT^*MA_0?6->2kNX<+}F&Is@8@J4q$+@2{^0CMHLgcuqF?wX5putAn?0NyWv1Ho;aM
z3+@sY5^8E_U?_QaC-RGi)!Q>Ojc1r-3Q3t}wJcbmuqE>{8w044H_g7LU~ez49lj29
zTn6ZpIQjZNg4x&B9Gs#V%;Nv=P3-P6-nh6p&~2zXIy#_}>LQ||l=SuaxmuaR!om!U
zjSp|lzV6b$s#H@`^TU@fM=mUM23@_;BW=$2@ZrM^Teck8lzJLu)s-tDC2wzqep#`^
z`PQ~v?&9L&BS(*d?pt1TT(D1C{7Ot<pde^r-R5-vt<sVLf`SvD!JD9<i#tGjMHehk
z04>otckbK-70&&Cze$4xw`N~Y`t{{y#Ll9nF9Nqddv$g7hK(B=XU?4YB5(ztv7zC?
zPft$^iim_f{A!wg?Ez>PgPd*ElBXv-Ua`&NTN+naXP1<eq%i&T#3@ri>jZkFOu39^
z^2o`_EjoT#GH1>wP~q`LdeJR#Ww%o5_p+oMnN_-Ge1UH_7J}Lzy`c69-&HZ`_7^Wf
zizTkC3<mY#71Y()uU)(5;o%XWw`874rqHHMn*_wg)hjNgpTBrfkd2KEbnVl`iGnh+
zvQyQ=!j~;s!gBNG&5AEC1gGi6c7aB26QkZ%UplU*rw1C5{_*kg!xt|!s&wXpb{yOP
z`@zi4C!<mByD;Fu?c372(c6w3>y-|Sit4hf{q^8rGdrlY!Q!(zcHh2zH}==tKYH{C
zG<Ej0O*}6zFJfnr>b3Rp{YQ?tfVSbtg?50hZF_ZPCFrC$295u=uO2*T0BxauaG<eC
zT_rX-E350g-EW^<Y2nZ%3l=b}joy9?bn|2JGoOo(1q20c;irT1fwm@ISm=E9U7DPL
zK*Nt86`<Mn)01EJO`0SG8nK=^bLNif?|D0Czfkc6ElOeab>H>ssCazK-o3Wp-rf#>
z_|>tQ?P0(DzXLx%Ki_I28F=@=<%K4br%r8M8@=60Z~9}<px?DMlAwzQX8N#&hlgK$
z%y|^l<ZEBmUF#fDog;I0L!s8OeHVG8+gEk>B1DeCM815PIddlH<d(+9Mh!i^wv8JN
zLATo$J@H^T(8enbT1>fTkIli!ueLpUl(gsPv)LYAUO{?twfFvfyPXfZO!V5?=!x^@
z@p(>q@a!2IsDmtN%;r1GM9_AT--b<_4oy<^*1D^c`tQ%r6X(vcF@RQ$f)0t4v#VKg
z*02>6K%o23RlTQ$?09(e_4@sNZ{Fm9?kM`O<k6IA(;nT}m<-y&91s=7m7bms+U5N9
z)m35JS=YAY-VR%Q*8ZR8B$Xx0m)kGyED7(Ivjv^(3R+e0MI+=mw4ruqPeVt?3(1S~
zt3dZHDXlu()zt;s(z5k>_4jvcukYUgT4U<gE7fZM|4;DSm%4jawrdHAh_sa7t7La>
z<2l$PX$(p$3=YsO+AS?CYvT4seVC$hX^H1#1y3Q+l>^Ss&OWnDR-RfvQH2xK^b}hr
z{Qlb7=u?*$9_x`je0kv&&`QLD0)wXJ=E9$!QeE8KK(Pm^t3b_=$jxb;a)A<{UYbRS
z@Ehq%EYi!1U{SYHO1eF(sn>Z{!sC!WQ0pGl`VUQpR7k=(b6#cM+@$*N&u4!I2hfc0
zB3JGuOP6YjFNoh!z^JCCrsTdx_|?_b?H?Z>x8L4<o^gTiY_o_R1&U&NF&&qe`zsq6
z34u=0XliN#ol%{i4>}L%;PK<^%a$!$bX*ja4<#ifv)0G&D&ahO^ysPMYHDg#pUdBz
zT)CSeArW+xC+KLUr(f^wt$w`s`#oXPd42{41`V@kOW(P3$E9ECjJN*YkUYj;GmX;=
z9v))dl6{@;?d|RC0oUq5hckg@|CV}-3ohpReo}qDgWBYWSHt67zrVZd+OI5PuD4<y
zXgW<ztqnY0J5LaL?(!<;J$v_pnnyl!t+pO|4VpbW(8#>iX6if8W`x7-{2Pm(`|a4h
z8*~oNBKJjBN*Wp*+w<-o0&Q9O`}_Oq7-J(N(4NjK|Mn{X1zl&s%*;Gx+O$I#E(myf
zdWQa+w0zfomQ|-g3mys|xqvpKJS|zVe&4UI<<2W7&Ys=9XOGR3=g*xN2E6#ntIZ(2
zTq{Rr73VkJ%qDO*`s>ERf5-Nr##(S~&Yb<Ast?>hn4osU;wot8TI}w!#D|Ak8BX~r
zfJQ7qhaZE|JZQ-U=oBsgNOK+;i-7!l_ji}RZp*v7>)~a8d)J~OqbEg{Nl8hdEvd!D
z#XRzMGIe!zAHIDPvt4x!bVeO$0V!x!-E*?q!n(h|7#fcE%RgSde&3;4rrDr{m``8#
z%UZLgr>6%#&YIfX%)BmsKi`5kwYw`nKlAYR23?)NFhy76+VrD8{!g1UsR`5>{q*$o
ziSy?{d!<2r;{5#lz0o~#f`SV_f%bHPcH2C9{P^@=pU(dNb|1CFmzH{OwOn*AVsjer
znl)=aT=Lcj?JNY%PVn&ZhQ=v-3T?~1t(M{R_Te$stHJ^T4VuBr4xB#C4Vp4ryg0da
z{=<@2S3D1txVX5K&R-I+{izmc1W%B2^5n^jKmGXj_O^s|na-TKb3cB&oxj+3wi)<l
zvYL-a#X-mRZ_B;C>`y`9{TVZ6fEEH8r=JtC<+>VJ{_c)rQqrO#_U~b9qaHq;9^bZg
z>(&P+J6<iTpT{?K;>3m5mpe12TK_+dJd!ctWXgn-Dc}Rx=7nu6T-DwS>eVS${kj1f
zDoMRze)agVg|`wO3)t3z$5V`Q=DbRN9FV)Auw&jl(4Ledox-3S;d**|K{J1QKA*D&
zU0%n-%WIf(!vM5Ll2_VH#CDay$B!Q)_SIPW&A02_v&SZ+guBwyv$Nr3iGN_A;G@Tn
zLCcgu^#vOno0fX*>u%6>H*z)->i+XuIy*U|wq!6e?5O)|1!~T}ySrQ2&Q9*ywQHct
z6SVN+=~GsFd;5cv?W=>A`yK5RRxkMU#FOE`p32Xli!nf#ziineGTSV-Y5#uvegA%C
zADo;8y5Xdzw)W#;e*2IgpIs-ZfUcm?(&92RGh<Q{SzrA8+=q{#YP}}l;aAYH*=A;9
z_W%EEo~ACmKJ)T2soYJUugBMCW-8s?Sp7W@G?9FJTW;{~Lhwmc;qkSh7g~}eB_uTd
z?_cy@vDJyubJ7h97Z(@PBf=LtJ32Z#N+xXGTDp_}um~3`XkBmY?y{-Xatu}_FBVMS
z|AvX7y81U)eWBwL&Ft*#AHRNe$u-Yo7T1e8;BWtzWu}i>mB_*htB{+%;(>vIpaJ8V
z#_0+9`TX(m@h4J@_TH<U)f;S^BeRP48?UWz&Kx7q38${`n7nZL$T3aO>Yk96-r!o0
zGBZ9~-(UAEbfdSqoSvpTwcpprXG7s*x12jW0w09zN<7{t3rdYvB`+A_<Kx%F?iMqe
z$-~vkw7cvr=+rULkom>rS1rf;<(19M#EN#xfLEqkTU&2*=Df7TQ+UbJrHQ}4y#-x&
zQM7pq^k|mF?)_nUe~b+cFRng%ZFBnhV;hr?2Sh}0Bqt|>*5iPdB`YZ@C1hlDY)n3$
zbhJx!(eW#@9z99|?Se=@H^<Szfq{vM>BFOL{X=)|$b5f)|M<@0=O50R-&aslVmjQ$
z>ztL9we#}Yub}Bmt-C2FjvZs0t`~dhk;|^f&(6+X<bEL%G^D#F^YSTOJNAZy&Fr9k
zK%bwTy?mSX#p~<q*B62AnO9n63GSr1xGZTF(~SyQ%zso&FXji&vWvCSW;q9z&#&te
zR`+}H*6-;O%b7lH<@YMt_f~&r3n(kT13E5gneXgHb$@>~EnmD#Pe+G`TTJJ|>Db~*
zt0`K}&dxJt%t$yf0W_TO;`;jdsqf#0g@r}U@{=+1`wHrYy^*fE23icQ4jSajU)A61
zJS*w(h0Vu~B|f$}cucb&9CepOq}%72*5=8qnzMSfc27?aXf+V%z@}~6wt4vYv@Bn)
zUibfRIjBtmS`*g7DeTg()#9}9z`<sA#p$O%g3cGy*XI`#69a9y{PXwk!<R2t79G+O
zT-nvpaR78C1ZctX*X!}&zjyi0Hd8b(0Nw9awKMWmxBfm3Wo6|hOO_lsbH?ZCt!8$9
z&^=2cqM{G~{QTUcrV^WymDL40!0O<^gQ9WqJBw7GotfF(&M%);X{4m2bcx*ta?+3o
zyKdALk1rghUUhYLXU?9zxXf4j$FE<94jx>1M{nmOm4|oB?~9r!zMQl+dOPT1>QmCy
zMMXsyc9mwUsHlLJ;eIG_DdqNW5AsJF&sfZF-V7<vW+mMhu#L@;`HCEr2$4c);0oBr
zE?l^9f(mEx^K-3@jf_st&a3}Oc}@bY#nSaz9t~Q;z;FLYpslTKMfmzR-##u{qy)Y(
zt*NOAw72l}U8XOOkM}$4O@F-m{XXZgFtJxxSF?kf8^3=aK7O2CO-*f)`x2{12b<Xq
zOii!e?&Sh?HskhIg@VrU`S*GL|AfE4zIOEWT|3SC0(6<yj>5+u4sq*0u>b#)A5<qX
zoH%jfz_YWnL05?6+}`H<Vag-hx<3-2!IaF*%$?cWwryil6FPnKrsQn%{A088_eDND
z#yZ<P|JrF@*3OO&4{K=us^it32@?dK{$C%rch{loAC}3j>Ty~qV9OLZ_sXVJ@24*V
zK0iAfY$>ayuD<-x`pSF$?Nv_m{i_!(hgJ=%EJ0&VGF4JHEJCDnWERZ=ca#<`Zv@pG
z#}rrXbnO;%oTLIeTJ`Je>(?`cMQdXl^3u}Uetmt-%mBJrJ~=rVG@4X-_uM(Y@O3eQ
zrt_}pMr>dR3=BMR=1hyzLWlSF_8QjztLc$8_sh51p_F@j8z@3RXN^>SeYG(6_O?^?
z<|~xJ>u0u_EX=bke#Z0c{QUkWPf|dq(6IB#G%R1P4%*MF8N5sZG9@Z(yDSVe5jw*p
zbCTP7S(^%jegA&FPPdtuCuN!?0$LJsb94Ii+a^zsipL+hwKW@bNxS3a&h43()pX+b
z$?OMRX6;sY&%9+dhq>O0sKi7?(6LjX=B2*=`a929Asd>TmMJSKt-1{j=oNgPo}Mee
zI2+aeQPpJF`%6_raH8JBmjSOn9((#K5j2wR?4rU38b9rOb^|nd(a~`v0W`#VQ3fQ)
zCpb~!f1UlR7fV94F7K<Yj@eP*_;ZK%bUn}k_7C5`?|<|t>BQ3_(D7dnT5fGkIVrSb
z#|{M(6Op>QI?#Zs?Igd7mrJKBcup$1_;d2{khrKQDH|Ib(Dnw<CXncDIe~GTw{1K2
z_V#wrg5p<anZ8(;zdLa7pyT4}w{G8ld~U8aXxQJh;zI(DoQ(viNM0AWmy03e>MGGU
zZ{M=|t6jSuU*BtfuYwtLSkH>U#h{(VphD2i&8?%O!=YPD*C6$j$i-x?gT35Z<!^79
zR#aAkW)naMk^cSt9kirw&mJ2M5w3{H$f?$rpv#_3U^mH@I{5kVfsRfE<*9`M4wF=#
z>dp867e7D$P3F~AQ(p*nbbJxYKNqU6qQb(+$oS&U&do0ZOQgWv3MC~&_&|)5bbE&f
z4=BmbSp{yNDk>?(nkOCM0JTl#*ZtD$>FqTve;2do+pTQS@VJWSp=NgeFRxr4fd<L5
zudf4*_6iCLPPJRM|Lja-_P4jTI!8rGffiJqoo&84=KH5lL6KAb?a|iIXxO-MquY8@
zGqYod+xh2zblG+O-o3c@;&cCB?h@4oohQ`N!U8%ed*Q-`pvA*BwzePt{eBO+SGKja
zb<uH=Hfiw{=GoVDKx#l!>$}U|CS+%WuKGQE_AD=GdH1icuP4r!p;6_dq_oJY8{B8;
z=y=rtx~FXapHJLRiY()*UaErD1ONZ`7j%d~*qVsO#qRw|c6M=JW*oAu_`uN4FCX@E
z!q)o#|1vHtXnb(e<2q;ui<+7mL&KjxH6D{%l->Ij%+0qSy528i88rLx#J<RVH9L>3
z_x1FwY@7T-?%s|y_dY#6y)o%1*Nz=K4&1*l|M+<S^OKyS37}a4=UEB&14_XIB`b~}
zTPgM1tvE;K5(~I%zE}>Fs{O9su$Yzn7}P@uiOrdFOH)JRz_qo}fe{fMiq35>-Y!#A
zR8-{P<P5ZvGs}^fG<mY1urRZ;voomTmy?rYQopk9l-T_EJr#l%FJ1&KT8N2>`S9!Y
z`o)Qd+oI<5y=nrT1N!pPQUg;{S4T(3ov%SFNYBnTXZ2A#_xO0f_Mgo^%xmLZc)&->
z+5LK<44Qb`o`3&XpR6_L00huBhL@L?&M-)1+EwyWsmf>V@3-6Uf4CN%&&bfz)59>O
z)}PT~vYM|!<)@UE_V(moUtS(cyTW>B$AUdaj<|qsBYbgpw|P-f5d#BPE7P)N%Ro07
zU%GtRF!>k{q}LB>^G{w<u}M}J+~$9|2DGjD&ku0(c+=+1iOI>$EiEh+m6ePdyI&r-
zaYG_7FtABoRNcl#=JT_&hyVWm{_%YMvxtZYP~-pop3i*;UV2QIkdO#@{dJPc!X-<d
zNcuXLGVV{m^7v)ItG|TDFcKbz^!7T>dQdHTm1RF@iVYfb#-NzHzj}q*k6NUtOME;*
z?MIxe>B0BXXIa_UK*JXn<?mz~HnnE2Tet4i@oCehd3bp}I(fYXbgA>zRiPffzO7rg
zZvFJrw)$JbnHh$sT>BXwJbBWxWsAww>n|t&{{H^)Y5o027CN_s7Qd~D+{^~rWb5b0
zr=+B0kaNQTboYr|@M|4iT|p_St_KeiQkB)!)IgUlFo4RN4<8B;L+}iqlT51CIxW0#
z`}-=;*^GDZ%DTF`g3dnx-KRNW!h%2hUf$ZO4LXd!SK6FwUdZn^Z{8T>-?IS?GcsIQ
z;K*F_@8|Q1$GzqZ4B6M$9X&JC*!0$u2bD*9xvv--8#`B2Sb(<Cg@mvO3k!oT+*5Yz
zVPIGjzh4fts`1mOPb~gkE-oSFA6dXxx-PO(FgF*MwJKp?m@#`cv&L`M^TMD5q<_EP
zub*NT3vRAjSV-jM<$)Fh#8o_GWjL^Y|3A>Q0t-9);Y*i<7#SIx)Kz1_tI(ALWQ(7k
z61}MWLI*UEIom83v;+^dmmjq8E+s_;wC5grs@lDK_db07+}z*K@8j$1+ON$6E*CF}
z{BFx?>V?Oqd1&(E382{$;T%xw2t0HR9$GUw3hu^dfDU!}@cnzZ-L%tBL9wi)tbB22
zae9xGDHo`Pa&E3QtDontgzxX}7L=8RMTW%1#PopbgSNJ|8(T7kV`5_k#l_n}{U;qA
z9__F-0u~!3>i>Qf|MmTSKj=toKR-Xv*w=*l^Z6MzY}({hQDI?ZYz*4FbZ~N3{Q9`P
zpp}O#?CjHbhXn*QoSkjHIDUT}lbUeyw>LKzxvvmTJ3EWDxVU)9(xnG4ToBl{ZJXBh
zc0Spz7cVj#FLz#D=*&LHwmR(Rj`Z{MBKFtWw(-mNUAhzmIzBP?))qmFg%<zs?RfC$
zXt#!z7865+=>M8qu(bfu(cp!N<?rXk<;5^C@bU41dY=pjPMqL4JKNknDr!~{V^vj^
zm5+~)OP_~}OUQC~lpnZxQ*yGJ@1Z+8iy0YwXPdbO1PF-fL@+RbcFtd06WRRcP0qw*
zuFFfk#X+<1pu=kyE?jtO>!e9S6_u5W=H}w|f4@v#z}eX`&)-INRh0-A>!it(6{nvT
z6c%pYUH%@_-#OgQ-#&l7{GPpgUHey*f>$|!+YTZ8((a<amt}$OSU0?3arN-AK*(5W
zhle?6%JJ)~tDtEChJ+s<9)eE60<C>wNS*zu26TyG;p4UwhFgyvKfXL_{d5)1-DPj9
z+%CTmtFEpF4T?tWC|LMuC#Ybmu73RY`~BmSRK2I1|NZml!zU*vd-(f{8?Fift*_c&
zZx7mbk#=_0!E4vTo=$lWIyPHRkMH^U`QkP!zscHGi7>PAG;H5)o?;}KVk8OLu-wKg
z{b;hk-NC8a;S*-fTD4tWDEO$3uC8JJJsZ#pl@sUAwe|M)p1Qx1SK92s-SYdPH$QmC
zgHCzMzP83ODoU!Sx3}=eheXiPOh=C%Wngf2b_T5^-g-Sw*k<LopFe&)cyn{JmbCbv
z&%e{|?WqK}vA=6FfL3vUZqJyk?$4z0`!nb)e^Bm@is}Mw47`6|KED3%)(4)Q9UZUK
zm@hJe`aXhzSATtd-42>Qeq8wYSmMo1sT|zghe3PjrfP>DI(*pqK}*uo<;#=L%rJbK
z_k!`1U5%V^TF<?@170p)bZjkUUtN!{KYDVqI;c7Ttyy<;bj-N7$FioT26RH3P0f#h
zFDtAZ!NU;=hue5}RDM<iH8kyNe}Ou-&h31nw(|sti*V3>wVgY6GMw_;?C0kfcGKe6
zp+iiSm6eN*UEX!$Mudu*+M_!=i!G|Zt#SMR5;WjqVPUbtru@SLM~_KMYz)74f@T(O
zZOy(V<DdTK_ICb*2M>bIA6D_yD!+U3Bxn7fkL?X7j}#XdJLlx+=*8?{nCZjD0Ghf1
zoxR!4FRx@~Hm&>o|A*JsMxSau@@vhKB`myBCIQud&&{<qFfs!7#m}1GKLQ%P$jRYh
zcyWKfJ?J=j(4J@c`agz#^X=A7?>^7?;KRei99&#YbLYmk+IL59&01>17$bjno~<;f
z(B<OhW@G?$*?iQTU0hf|w{Jj444Rg!C@HPl{i;*00W{>&vFh9X|Nq1}IXN|SbXqoU
zG!)Z~YWe*9eDc3PKN(Kt{o&;27q?kzF>Ts3&{XHuxc`5@-@mva(fKW}OX;brtHU>@
zo)$|<OMCS0?(P5$5v}WAGpCoYx`8$|T@t=M@9u@Q(dIS3UM|;K?tJvvu~%PT28dSv
z`C*upoUAzg^u#%Hco;Tp-YjfAMFAX-E0*0bU&0Aq&N3_c@sz~-pxW5<=rKj#4TUC$
zk6o0JUd|)EJS#_Lm8KbAW>fFtoq2b6B_3|$1)W#&?(Xi1^XK=2Mw}}DetLSk>TBG+
zMXubS3uvxgyEfru3g~#K%gcOS`<DuX?u7aL%y;T@&^ZP(X3hjHY}Pt|eSN$<sGs(%
z!s_wE!|fZkZVj!DmG{s5w>&(ql2uYt5_D9Vk&zK>e&WqdVKz1!^$(qE*65hz-;?3w
z<UA!j`)ep@m3#huI~G>fsk_61f|}MwZ-2COdYq8K%)Fw)!bZ@IEru<RkFicIE-7hQ
zym;}ajVo7bn&sc?IXl~&dv<3>$BRlO&3}J8Rl$v-tCBl+?ldqlX=!b3eG%Bg#lz#0
zlA>ake~%|VK7MNU?QOY-U$5WKXK!y08l}3>vSjt5MT-myAGwH#i!Tmb?6zUc7M<@>
zo|7iboT-^$bxD+sjctO;$~(UCuRJETOqw()-6r&IKu8E^lM!e@>-YEf?Tw9%_ugf#
z3(zR|@WAoJ(<0C%9w$zpZf<R5b?cE}tgo-HsH*y;)>5DFcuFE@ZX(|!IA_kR<i~${
zdly@NJ9{5IUoLY=M0)wN8y5A+k2CsuKbxC@md3Q396fgN&dJH@58uA+y>ll<LxihG
z&Q|Jv?f1E#s(ycadvUQlzl)0t$DE+upyN$;#`L|tz5VgMz15&B@#oJUgQ_nXd+Ye+
zZL3T`qlJ^z{SO^F#Pt09eD~>ku^(<_uLq5<X|3nw<OD6pJvZN8KO?FzCN}mXX!ziE
z{(jf8GP9hVoCz~#tcY>Bvp(LQ;Q+t=AB7^HONEh<kr~(4%slnIZ(mn;H>kk?8c==x
znj5r*^zJUvZQHhi4uL2tG7=IJGDtYUaB=agIr4Qs80Blf2!4BaSG!7NZE<<I`{QH1
z8>_#+E3)tQ_VNN{0F&%%JfMZ!wyXR=_mlYe`u@BL+T|L22)Y(6<T>b$@xQ;nyH{0N
z%`(gF+Ln8piNVOosNnN6-yJ)4fU^CDZQI0bG+#=&ySsyS5#8RN@4mb2txLbN)u}62
zL?)>u-q?^h;be-0RmqCD_cCi%*3aV;6&G(mbjS&0{q^<n;<mHGWbNx@igwC?=72VB
z+63D2T2WmMy4u9f&d$KlP|#NCr2#0Kez%z%J+@NP%umvc?<yN~N-F8`6&_FqY|m<j
zFECm4{M*~x9=^V=plf6H*VjM&ymRNy8=F$OLCqSy*j*fR0(urLQUa~zDB3BrapOh}
zUEQM(4mK-JKKbF*>h*_i+=%$n5mox_O(f_t&0Z-}r*=Nsf>&2GMMOj%ytugd#l5||
zPi4=YJNMzsmz})QW*oD^K(}TjTv`IYZ^o@xid9`*9dy9&$&;L*b{J?S@{1Q4ppC0v
zRvZHDDuhnEwo132NHJmzeknGuVO`eeXJ<jh^QX_B7Y1l3cnUEbxN}Elb@+NW2Zx3S
zoLk@D*;x#l_?I%z>$$hLdU4#|s#Dp!%ikXZ%_?o#Vlrd)Y*3nHQWtHO77qb0F|e<<
zn>2YcXy6}oz}&of^L7+J=K~$Q@Zdqh(`BHuEJAE!Aj^W5H1GTQY_?SG-4;&ad7o5D
zk1uxb-;j6L>d5iqk6&F~&Cn3GHY)MN1Vzw6L-{<5xn|CuoeZj7L5tA1UT*mFr{>6!
zBMy4gl{GavK?9biSt2P$k~TIrF8#}cE3B^E7t@JoSg}GQB`wWqVZeg&_n-#w;T?sK
z6H-%Et85Z)Sb%0SUM1ZJHFzPpHdyZWva}l(A+b52T<cy8p20em42p5^R5ED9^>W$&
zf3-)B9C-lhqijq*z9HkH(wX`8@n0gMrq7zywPAxnN?O{Y(A8m}Yp_r2?_cw2){`eG
zKC{hu=huFd1g|m-+9;+U*8@7;9Nax)`TFXrv!^GgiYMs&ThP$MMP;tSr>8_gvj{6!
zt`ya?VPEja_;R@o<K8`g{?ve~UeMYHFK_RMZ{GAAYzB1<g1%%#O`Si#A2fTYsp<JM
zrdv#RL;3r-8M9`AZumUjC)?cH%e%~XcH4pl3MP4XA|4!hRPdPT>!nMV9z1;5xXgF<
zp~HunK|??{KY(uF*|2?kdyJmAji#Vr;N2t89BQ><(d=FGYBGMjZ>j%e!|?A?(~4Pp
z_UyT^*qtAAVALY_g;q-1+T79G^IBu{j&};HgYL-!tpqWe$+K?Vx<$u@+m<^|O;1Q*
z0Nv01^CxKeO<!N%BKJ$2IWmjV`@w6FR!T@Ow=wgpd?T&&HUU(uf>v~b#<%69+dZto
zW$K(&Q>RQ(u(FbB=aU7k`U7?QKx^yt_4(QP<y_|5)h2*$WAaJl;^r2Vmge3W)3>+!
z`=J8|7~<=GE{)TVS-dJWEiLJIpR87Qs(Y_g>$cq6U2?uNKo#7|l`El_DP7g;DlIF!
z_9<o8@)avMJUu;M+}ynUo}OHtlBuca+uPgSC#(5t?U^@ua&x!1{-W~t_oC+c^nfm#
zINBvz@pkKV(BOe~__~D0$9h3`Ds0-ciGcysUw^%RKVNck^1;hp$9uW8o;`fnIA@N`
zlBG)@9&Ba@)wVZ3fUXJy6(2^%#;lP3BXmvJM82vbtwX{)ckTo&xdpX|b8ne|wh=Rc
z4m@vZZ&$Xrmj~U~wcKy6OOJO*`dr&;G0?{4Q&Y7;XD(iR93Wc^pNv;lR%Vv3`=JOr
zld?)@?W30gujX17v&HT%Tl?YG(Qa`;S=nA`^SlE`kFu`c|IbRwEN8`2&ZD5Izv?&A
zpcOFE%Z)(mW6WJ{9Rx2J+fb-=7&H~(yhIkfM8>aj=gys=L*e@5?fHs}i)|`CI8-vF
zd3th!PX7ZPd-3wp(nao9S6#Xkq@tptpryrSUH;C+(UCE(?q}+W6eG|{T)a{y0=A3%
zG_|x2U0m!A>TT|gzvBLC=FFLi-`?B=^+H|*mUuZjGJ?+e2OSgl?99wX$1hs8wY7o9
zMHMHX)Y`Kz_qG{mChX>&(<e`I-rZg9UQ)8<(@xL|ms3+TLBjz;LPB32-G31J@EGgV
z><bGRK}&ERJV;1MPd|L@m|H62uVcN^pi9+7L_|2|P3h=Zk+({{3Umatl9JZ?(A8mD
z{o=Y&EYi}_G8P36PgOemWUZ5~tO%5_C{O?mx%tjE%d8Gjw6U=PEzkY?`#ZQW<>%H`
z_7viivsuyla)sW@8yl4m9XbTsw#mjT1zLLC*4Cy4T3!K~Xk5VQIsNIgXP~85KY#uV
z&=4^&H5Ij;bWJyM6N{dn9_T{wmjVALO`6nH`1qKjsj29-Yu8Ra|NiD?vtjZv(7y3g
z&q0f&z=JHd>p`pKA78k9U>|6mA2ix(gH6r&Y<a;k#|MpCi_m0{GH~op`M&@EU;gLk
z=N|{10JAka{Kl<YTI(gHq>{e8xClDB^q!7`zprm=jGlW*iOHtTn=h^o*9W!TlaKe+
zzN=nlR#a5<;NioCclJ2k|MK>>_`7%SK${PLeR;X~yL#B_<kZxq-)C2b9yxQS=e_6D
z6|df$ICSVxk?ju~(3<Rj-}nDtX=7gSz=7dFkEHRAAAkNAmzS?EdEC^}!m{_)jtBQ&
zU0q!hc_+U9@6ofM{ViFI@X^q@*5yh%IzCUA%~R*$;V~$B;&EoSx&MKbBn=U+DbuED
z$xoj)E$m17=lAOse{BcdgLrF8rh%bh<L1rA<@(FDVt18r7VVS)%|@I!(a_z^z07Ye
z*GwNab#?WNk2CMC3|?MgHAQN7`TMrbn>U|2Ykl<SQP6-9XsQy_ZM=F_w6L&nhIP5#
zp+ko@Bpu~y6z)C<>V_{|-Uu%6VCw<D`BvsYW>JJeGwYxMn9$_MQ;r`4Po<b1Jht-A
zxw+P$MX{j8k|)lc(<|Q_ySwbhp32SN*oBwm-`{6oYI+oOp+?=Gil=HWpv%X$W?$F(
zGb``zuFOKGyGzf%zYP*RE?>{%IZ44&C?+Q6!uI_5r}cNvtU5DAGgv@UvU9-#g}qS*
zYdS#{iJBUlqod;@_lunM|9&n%b^cCI56_Zi%cfPw=H=;`<=kkPrW>7AY_qVdt1BTd
zZ{4RmlaH5`l_|Mh^1QQSLDAl-uZQ|%tp#LcV%|kLIx>RV_H}=Man1nmKsW%cQ%W10
z79Kd-Eq*m_f5F41xWAvYEiHFmI_@$nYFCM7)%SP3H*Q4SyW*S`yT48r+w6A9%S*0b
zDx5x+XnX}t$eG`-34XfMxt;GJ=mf_9f4>_RK5}7jXy=pt@cF!b^80&xtI8i69XR&W
z9F*4INM90>cDIF22IQZDBzDl6;Va-ttd&xrx(J*pKnja1D=RbZ?%I0mwX3VEhMwNF
zM=p<SYkmk=m%VZD@$p%@K3GF!f{JIpzyIIutIVcV&I7HU1Wl9l$yhdlhS5z;MdNF~
zih`C;c}}{pr?U9V%ggRN6+lPFRQ-JZ^-;He((`k3L1zFkF*84W@F3tJQ-Hj@Jmcj~
zQOqSH>Wj+3OGa*iHghI^e021buPkUyvXoTRyHc)JCN?&<h}~st8#IrCI-6WvTvPhx
zZ7LWR<OF`TpI?9I%o(5T&7DVjxlOibTvXzbFkrB=vpW_1==@yk_U!BH9)iYS&dxRm
z&AS~877`S^8VhZ>g|LIx-(+83*SdJI^1Z6px=-0xva+&*u1&tSHkuu@@FG~~s%>Q@
z=$6UHzP2GNr|CvRm+>FmQ~CMA`gr@N`WK3einRVnX=`ie_G$3=w+HE4TTAot@oAlx
zwW$!8qyjp?MC<(bmzS5Hnq4<9JV$2H^8Q-TocD_3kma-AcrR{-tnY@$Rr`yZ3E=U|
zS;b{#$6j7uel^a%-~q$G_y7O-cMErJ&AhC3QTa;buWdWe?YF)80(9UHL&5)lwM&*Q
zQ&LrB)zsAN=<aqdDKTMKka)OlNA>r0Ckk6Zm$QBPpMGY>!Xn>EDtqr;Ie7Q3tiw&W
zP|@5gOY-Z@7Q6Sib$4@%aIvNsN#3jbo%`kO?eM3jlT;QuHnV~6NH)*c%Lp=LVrCYU
zkcfEqGx2cS)M~#;Dtm8wv`LF+oI87#cjLy5GptHi6*2yrJpXiGUtdRW@6%<Vt5mka
zv&n(y^XvPx!`CUOsIU}2JL9-H?JNU>dEOm|z(7IJGU2J(;au~A=73`E*4At-`E&pO
zd_MmJbUt51M90U+$CH12c*vx#5_@%jeLZLp^ozuj$0A&;a&|QxGiFHi=IdRZ9zW$%
ziN;rgqXNyKHD7#JS-{<+!2aIFa?;DQ-ppPF+2FB66O@~vg%^0_0uo6k-;YV>CwzNz
zQ^FvD0d&Fe6x}dw9UYg942^GZZ?}JaeVuz=Q1v_$xzPUJUS81E!pnSTcgeY?&zL<s
z`N4rkP)!Otff1CoyY=@SxVYH8@clj8i;p=cPMDxj#WHtm-QTLGZki$A-oN3KwPMh)
zzI*%dVP-!+zozAvcsHk?7qe|T_vjew)z7E2*DEM1GcWg>>*VIf25m*pv#maK;DE!I
z3eaSX6m*09RmN%4rh$%bDSLaX^~aA2(D)pKLB<6I&<+qgJG-i#vp)!f&bIvf`}@Qh
zGdLJdoI2Ii-p(#(U&q7E%?+9lxOnlRgk{l^2cDkSLE{Rbw%DfB)1bqk)O=@k$aR)n
zIMmAR+P`3Ph1Ha*b?erFnth<txVX8w=h)ZFfi@Opuix8N^)<wP((a0nN^jo2W%bn(
z1CQQ=SKxJl!XLET>FN#8=sj%B{#WRHCwTN8yp}TQafY6Sg#@Vn{_*iKXyrabgO8eX
zS(#Z^cei2csVQ9kkyqVaU0p4zzGzsLzvJ=t_P+S|MUS+39_UD=jLXY-dwP3a`xgtJ
zn`_;!?B1v0Z@<6lt5#2M@5Qaz;b-Pp3fKPnB51ovz~5}=f=~A<9`jyQexb9EedVtY
zhxtKX+)?QG)pHU{czF1ZUAwyET01&k>{QYe;c9)M2p*4Hk;cW%y|Maxo{O7X(*1q4
z6<=OVd@->FG#uL0+&p#nqPkBf)j`{LKn?(Hn!K>U5p=;`P;fA-zt=9%Xy($TOHb{$
zR#Q_mFfj?K>{anRar(5dq1?oC#U&+2KzCLC`~6;f{_D%j`Rjf@6~D8$I{Ycy-Ck+)
zq-SSlR(<~d^3Bc7pw^(2X;urLtkr`nD}yyOG(c(X;@;}=sn@Nntq)(mEG%u7BVe-j
zT_SAUry~oJ3!dFDuZOHsMTmd~en64ZF>kK2dtbuuZ*R5K6Z&MW#s2>KDr`IJ9O(G8
z&(F?IoG^jG-{1e@V~*|F*Y!YaB_t&!85aC0-dX&dFRt>bC}>*ea64#3vP{OVMnY3l
z)1v4J$E8b`Cd{7AZEbD+<=x%rpYh+{-34u?ytr8Cs;8u+BxueBbei_}cd>t}E&EkG
zL2IrSyev7rHhOzPYHDa+vBjdUm|Z2FZ|`d_$O%>g?SHbHCIK383zS_98ToQ?b9?mr
z{r=;7tG_2CCojG(KjG<<CkL)w3;StdW+nzY)noH!V}^t$Cnjo{Ulp_kT|nkBNu`SC
zQXy#GmV?9L`MJ5S{fml030&5?%q1vD=+L1<6K2lrjN4nKsG_puj_>J{Cr^TQ63j46
zX7OER4O*51+AL;{C`+y$hU}mKEecKot%v~aps>vW?SF!9`tkev_3dr(+TY(qZQIU0
zmP|_pE#Uy2>T&iguhC4NZZX{;(BcL+P`^0yvfAFrhIbDiGAb)8_edIpt}ibrE`Gdn
zHv=1=42S2W4dw6SK)b&l9B2%!>$THY(bLg6a&E3Q=orf<PoFN_vL)o{E)~y+?Rj$-
zygV}T^ixoGjE9Hk!nWLKQ0MxKhgG-q(iM-6vAzQBbrV+eamdPAb!*#170>tf+ZB|Q
zR%yZ(_9}yp2RU)VBj@feQS<zJEh?TLzJ5Il+S(Jhx9a8Bvz%sTW;?3BYB7Lj4l^?|
zK}QHrx!&E~9T*d%lVx)$akhEBm@U&)#?#aFkAs#KJbJ_gT9PhrF9+&cAHT#2It#L2
z&KBghr!NC0sU)78WBD}h_uudLU*FYdt^WS5cgKz$Uh&2W2N*yVgSYTYHE<D*C|;Hq
zfj3)fLH7EA#!Fs-chQ2HM@68Oz-D}zUA>EUf>zBbC@?6y^)#$px$;F}$-I60>+M0a
zv~_=fJ-o2c`NX+%VUZ1d40(BZRa*nLB_HpzsQ+iPXwjkq(Ad|zyVAA4zq!7@xA)?%
z((H?mIfDZN7(6FU>6V^vv+UEl*xhXU`uZ{ZY9z(P#6bBTbn5i<>FljejN01TGiJ{0
zlnd@)<rZ5Iyc~3sg8rK~Z(RBpf8G)3C7Bl!u=C_(^~YacUjFgrvj4+(@6OrFD=95n
z-UIC<ltiSZsVONd3rb3M_Vn;<$+*Z=S6BDq=4N%!VZ4Eh-432T>-%NKp}l`Tod)d|
zl`_lec=9A=%Cu>#-q_SWJj7~YVZkwHLdUC3-qZCo^ViI=F4uc@b~d}Yx%rRZzd@5f
zpi|sl2(~_a84wZ-UgzHNA`+aE7tTt!pV8Or>~dZR)D#5`54#uV$S74!yJ0cw^qDg)
z`}f<QIeXSH=?Di43(JAir@Omdu0A-l&j@sD<)^2ouf}cPy!r6j=<Qo9CPsix82R-1
zGx%!2B})`kRapfE1vNA@8rH7W1vREY_fD6;zxU$aUhAHo9+&<#qV9b%E58{2&AqlJ
z5;Rr^YN?jJy>;-~HL=^<^V?_7mIlqoeSLjh+0ZcX%M2&bM1pbpxhIc`c|ZQ$&10^&
zBF4*$EA9Ne-tzmk;a@adTwKnpdLH!W2bbt2lV;DB26g_kv$H`1+@NCx@9(Q+WSFiW
z?{<4zF6gon&>-c9C67{5Q$dHUgDRg_*Vp&=+y9d|c<>-Y!=Xb?px7{)$+J3at&ol8
z%SF}S-z6UH67A^j4xZ<CX;r8;=oog;`3#5Kcv<~Dc0Kv>@-k?bM*02P_Se_fA3kw{
z12OyUAEa=JK^hdmt2DpyhKftKuPD1=e)aINg|m_#gBGfEWVQE#7t3mz@r8;@FV9l<
zo8#c(!UCF0zq6~9+jq8EtB+dq{Q2_W)gU%=L0fJ>yKz7g8#iuzQP`4oX$dE2apQyu
z0+8_ow$9GZ51_rMd;b6X4XWYS#qZav2rBgQ^7?Su-(FEwm38IHl^&j+2jlDivL+`d
z@7T2qbO(Td?V@v@-rk4#?f*1@H%z#`UbA-X$7|8~i6<wio;Z23aqCu7At9j$PoJ_f
zRQ&yVed64?y|&fgIOc`?uKM<-)3KRN(ZnR=i-wiHwl??KS*F21E7z>|@%7zU^Roza
z?A8|ztCRQc$$^&JZppmt((mNr@+IaGWYe6IY-&P61E`t>-AZd!qVekL>g9WmNmpx4
zn?9XAI5_yq`uO;tcMiAngLcDPSXdl5b;|2O$&&7Wzh3L_*uDGlsj1op;E5h?1_fJN
zS<sm_pc}Cs_uDUu+?)nl#jrR)W5S#{JUe6hX3UVdv$tCO*|TS$g;0O~{CV*9t!|Zz
z(%hrRR@#~Ig|h!{1C6(b7{8f4EAeqa>4w4;W;ZNcOb>&`=lMd}r9s2-!CRr@NJ>he
zwaB1lTcGulpo<bGoJ`rUeY?2rA_MchI|tTAZ@;k2R~mGC`WK5sy>hlvFJHa{UA6J)
z)29%z1^4$<3WE;4+>m$}bS3G<#jjd6i+rD630n)0e*V#M`Fha&Q=gnIm*=E_pdh6x
zow>qdVr{J4VlSS~@0~eQ^3dVKpc9Z5Em8t4?EU@iEoen8187BO#rwVACrqENUJ>;6
z_rrF1(0I@L{r~0k_kNl5qOc?iu?-GflUO(vK5jZy`{5uvsBhxs#l^$R>)P+^;_~Ir
zLs&#@O*<=f;%U*6Wy=noI>iOL<8=Lceb9yCXU_QCyW#vrgoTAgK~0Sf)EG5N={U9Z
z$Bzn7wYS)<_s}%mXck|OQb&wc_ZoV7Vzy!v&m}z;u#J8rT@`i1!ev(SeF59*92qF*
zF`N^6`s~@Gpb-RFS>6RXi>ER&vw`O2k6u{l%<8|~c6Zs^LvL<wo;YzLBZG&B2W&Ma
zXuOqMT<^$-hlg4HSJr~=jJvv8Tt-$FbVfGluv$e$MFS(FL%T{}F9^^m`1Hin!pf>k
zF7!1QH+SKi8-_BLMJ(=pGLE3t7Z*2d+-O+!<wfJZ+TWnjo)1fQxz870us#1i=stB&
ztC8Wr!GnxOGkHK$$qWh4&ddZYNel~{cEWJ$qDA%kOP4Qy{OD*m=;F4hZ8?#72iK^0
z-q@JjzRm3lCo3y!#@$_}X=i7(&NNQ%l5>Av0E(3Vf4_sqio3eI1tlan*xB2;#25Yk
z@q=SVUq{D^cdNs{dV@<r573rN7FJf!nZF%9JuNYM$J=<NLCY>Hzz4a3noB;4pgsKz
zspg=IvT9<catf>2oZh&C@7DHw`Lr`L0^co@W00_^FaX_s1DXMv(etVc+X8#Rmloj4
zyGrVY`4^K7g&nKfYlAI8V;zvOC6}v*kFAuEZlA{n7MpWQ*0Kn6^d;z=mZG8}(E9nL
zLoJ-3P`@5u&nqu454ze%-%sT3=5&6yJ{eAPbMq4^MxYI6;3Ez|i|Lm6&i+!wSoQnc
z+rlR&1X<YGK{Mz98X`ZQO!jAB04)U-kFQx6-hICO?X9IT1$Cec|3pO{7X~cwoU8^q
z(dPcXTF_;qJ9h0lbmD}^mmN!*LFd$0f6sf$^rcf+J?ZAA)E(dd-`M^A#hmvwfB#=s
z?{rr3nh@|vB(VL+!qRIls<I|4tU~w;rQRm2dTa2?J6q*Qp3BzDcQ0A>Oq;RjjhRTP
zRQr;?L~ZAdLY^9@BRwt(IK8_sUw1Z7&5`B%Z@+iXlh>}Z{r>k~%G&Jci7`iBf8AFT
zX=!OW%RGPHukY{kEtb~4xwUom0ekb%^>MK;U%vG6_dj3$tf&6mrw<<{oK2g&d-v{_
z8hi^E9A%A*i_5yd&$gSJ>%wyX`FH-?7Ckv(lRho=WZLGFn{<}Pa4<0(IDCNj1p@<v
zgW)I8CCm>GwMK19=>)B9SQWbZ)z9biL7V!%wA=r21f35gdr>bYCMG3v+Pc`?%PuYT
zK7I7)(|PiT<CPXE$jQmgGD_|G_i6fmkqW!qTPAydzuUd5>g%exlMhb3nPZlFXGdVS
znC_)bsi#X`UQ(T^A0M~3>TA&de}6@#q@q@=_h$IVFZ<lgicgO17jIWrAG1x&m)ZZF
zj~_hjaNIHQVqrsjci-pw7Zw!~FDx{)tj^t)wJPxd?OC`UU%&S8@&41tkGns7_)y9q
zp#c<9&u=btZr9S&^Ap#LF_?0#E^2F*s=vSg(c{NoA8O_P^zGZVHeP8FDJiX&-*V4x
zPCtL`<KyGJ>ZaPt%FZiSt~_<}<iz>&=kM9O*Vld1?)&@duB?qVFTY`<q2bXhWok5M
zO-11|=?nG$ex|>@voqMX`di3MqtueOw@mkbJSN@M-935r>eai-->*Aw|35}lE5txn
zl<&#;`hS~)f`hjv9%j27*z@`8*S+suS*E30zWx58SK3_c)z0+!wciBQ85tI&Br(V`
zFfeGe6%`e2$-Jzl8?nLR^fcYeQ?<jNJbbt?zW(pk5|iB)Wp8GvtSozbt1|BX>HPD|
z`+w#tf9JRVv*6NF@8_1M&z%cv=aZc>ckbG|yUV4$INUd7U)R%(+T!v5v;F_Yo72yq
zI(ybPc2`N@|9^k4E_UZ%{_FVE1B;!GFMRyq;Klrc{VyyIEPndtuiK)>4<0Uf{Gje)
zVS{^jA1FQ?k01QI=<%KC&(F?&z3gwl(r2bo)x%bClY$2hr7tf%?PLB4T9^d7dU?(q
z8Ef^e_T}Z}wSPVyuX@~T&L!jU|53O8muu1an%df@3xa;nHp!e+_5I!20|yQ;o#&Uc
zS+Qfsjyt#Kc<;*J_tVYM(Xr~!$K$^4n%Cx3GRSIl<=)<wd1FK3s;I52+W2HwS(UyL
zsZg%Eyv&z(2{QvjK^)HlW(Ed^qcLG&)28XiuXF7d%l!H2>9WTRM^BmGuUR}jzAn;t
zw%OGW4-bDmBJA%mY0~7$rrFnY-rnCI?>$ZDVz>Uj3=2)4uAZJNpk$@&-ghEx^UB)a
z-(Fo`KOZy;6uK(pWQom!Ba0q0xH|85OuSgg@O$xn23PmvQ1)XOn`?dY@jg&${Ppea
z>f>_NZ|0qk-&+;>{QUg#E>^{<+Tqu#-|t<1ak0C&MT1@59gDN`?c>$`=b6m8@-HSP
zW=q0Brq=d$@rr#ZCxu$u+l@We+~y7{dvjx9+Syr_Pv2f$?AELGWi#mP%RX7_AA2TF
znK@Ily!^Yh9&@4Ea=*E|Uhhne)QaA=X3w5IZ>F3m{PXYg;sv+&=bFvdIsNFn2m?dI
zT*C%F1_p)&H+ENiT;w;$qVPB`==R*nHMO;KKj}X&%-^_iW7YS&<)!cL?7SnNa3ja;
z=Z_yRn)&T6EO2b*QE$oA)6>hkv0))7p6mYpTIn~}YMC-)fl!Hzi0EIoR>$Lv30$)5
zuCB)&6E74p%y0r{;sA*f85<t`eLogWnml=H`TMxoT_u|589<v;uPpHtE`5J5_Vcr|
z#<Ex6y)$jFD}LtFD`o0+eO>J4Vx!~5-`+%mO1#(C*PoA#d*Jh~yy4c&_SEn1?ym0W
z;80aj(a_fR{{QRxei13DRbRf8@JgHcD7*CpwDZaO9N%IsE<T;9ef9sz?d|RJDxXQZ
zy11<Hoo!a;k#<i!z9w)*{Os%T^>_I)Ww^V!KfSuMbF<FrORui3e){Uws&jL#?|)9#
zIelqY>FYNW_!t@{wKJA5fRfq01&+;A=FC}h<j4`G^S8I>uXpQ}dU;xZ|CVAS5pnbU
zdsp7w-Cg?ThM{NB+gn?&Zc6puxpSwaADcU<LvQ=@$z;}fs;a6lXXoz&oeO+*L!$HF
zkNx#JS8}-+zyZbai}zh?AM*hbD?T|ES@!QvkTB(M>T9lE`1nDhho4{A?QOZC%l%}(
zzP%kTC@3gpTeZb&s@Bq*o6}FHZO;7u?yleF2MM2_o%QnYn4sc2$0BfV^>@93iD&fp
z|5>E!J#B?suhgxr+0*9+Tg}^?e*V?R<MN=e&FM1odH3qoFOEqT+m0M@X>Dm)5w$go
zi<9%>pP!#U>*&6?u&}wNwsvdAMWw@@Z}ZR1v7BX?+}0;+y$rO{>)*eBla@@GBBC3&
zC!+NAwW|$`%u{B~TIJd;rfF;({QCO(@>7Ymf8@o)pNNWxsGQy;A}_CRZod7__3xWf
zPm5VEVP;tHBoSN!I&2KzoaPHEQ>D!FVj7<t8XC?r%?^8Ke~Y2v_s5&*^D}R4$-K3%
zcK51~m6Lw|J2h4N>h}EjyE_V%zuVf|+pDUnJ*(tn097Ur0vA1IFlg;#Mq%8UZ<>AW
z#p8baYx8VD=c%ZQemTEn?pL=*&FuVHM>+(%`uop+ehoT$7IZIQ)|C|#50-or6%}2&
zVugn1_I%g9x9ykb-`TNo-=9yXg>27+N1Ur;w&GG(QE?I1j|)jkT4ZEw{PgkT$?2Jn
zAt6(qou9v6*}YG~FRMOynGYx^x8~k93tbhWc|NkLYFATJ)0bP>>od>HFtn=ww<l^#
zhGKnveeSI-Cj*i!n8d^x7#Jo;OymUTS?l_Le`4z!;&v9L&b2N-*Vp-Ag<1Z+m?iy>
z^`FeW-6g6WvOaFFO?-OZy*(@K|GxAuDlNUbr}FcaO{v~%qqch0|Gs@+L{@g~|9|iQ
zo6V4L@N@*_()@ss5*dbN7Yad%PefFfy+N}?MuZKVi8c4^*kQ5v%O!6v4vq`j>-Q|0
zX`HTQV-sUG+xPTz{qVoPzFys&?tj^^my?6zLL0C2l!+4;UbzzT^vRPG=g<4!yLWHd
z;+uD87$$=Xeo*V<_;L5mX=j7x+tq%uNsgRmV`CGtEho}hQ&zbA{=>Mkx3`v_oUDHO
z?%i0>N$cfti`{tVS{5I3F#4Q!X2!ya%I?pk?WQl$3SITWzy8<cWxlhQ873b)ar<`k
z`u+cQ{rmTQzqCizv9GVMf4y6N|Eb=@lP6D}EY6FZmUez#uEtzTalM#;u&`-C!NH$v
z-}%fk@pN=_+*SCv&F=RbW8WDDj=E7>E*$9;j*R*6-`mIM%CobxP1DXuTn=Pl(3mFS
zz|O$H5b(zK-;c+)c9*}GJzxLlqx<qdjhdfc-`KcV=k%%C+|4&X?b#=sez&3jHlM83
z5=G~>Czbkkc5%<o&%eH-@Ucn81qILT{|_G9SNnTQ)z_@$f8A{v<n*lgxSH#l7eUf#
z^PvTg7p!<;!Qiv-@d5*Ii^uQb(IZDzl)k=pYgg%NBO@b|;%7d4zun5_;^n=1-v0lZ
zZMnBs<=x%2ELqAh^ODNfcXy*38yi1;`V_P}Z0)Bx@-`I#g@uJ(Jv}B<F6_H=_wLho
z@AN#as=ln)vv=>)hYu4irau1s?c24Bi`_%lMwwm?e6z0Z@2}Qh`~Fr>OVzZr{3)nf
z6qA=%E+1%F`fAFlsoLqwP5M-AZDS)NBg<{hpE?y(RaN!w^{cC^pGzOoTiGXXzb<`#
zZCGYzrdIsEJ#~M-hKH^QaGb6eJLzm%@KUd-bH2Sc>E@O@13E}mQt~8&6$69o5fI7H
zkhDJi{JdX(KA#sA6I&){TlK^;dSA`XXJ=<GH@{bLIKawc(vKfMY}T)j-@nc<`PhqB
zS653}m8_65$x!h0^76Vg$FewNU5usgT&t@tAr=$3#r0OCot;&A@Ai(u#X6^h*2nGr
zwCDeq%l_FfFD?Dn!@huJF(`!1HMFew7=m9|Xz*C^fl3Tesms;e2Z|7pdkdZ0MTCWw
z!^5xNVLb8XO^#>KT&q%(njZzAp0Jcf!Ge=B+(5?^{QLKhi-$+&!=D3<%w1hwMY9;c
z++Q8Ld)rHnqlaEzUS9g{j^)qazgPRrG+OrfM(k{}+)um<-rwCF-p(g`N!Z_J;_q4;
zOUp>m9w-L~P%}19X;oqF?QNkkF>~B{BqqLp^XlsAuHN3zc0O4i731}(r>D&_%bivA
z?aj(#z0%Jutt&n(Smr-}Ub>@4P|&2TD=QM;&v5IJG<JLW@+BzM%&U0B397|!=kE{Q
zUH10NN%i?J<p2L@H_N$^V6{w8M~{JlK@HX}m~BzG$Smi^g1Eg^D<e0j?X)+rEqKuI
z?d|R5ZoN{PT3V+Hyeyj1=T)kme;v5kZDq;JOI|)cAvZUr7T>S`_w)JJXS4HP%}k$n
z@z&Ptt1E-mtKD0fS4M4Jb#9L3<mY>Jqqm(neAxNyEYs7U>t0@38oH|_v-%iwK-0y-
z0EsWsXr&LhDbeZ(ZbERKKYUpE`~Ux4qS~u`W*S-5{wjG_d39B2>6aIQ!5?KnD~0C%
zDo+3Z@9!+T+Fjq?++6HEUGJ&%oy|JlnVFewmu7CQ`B~H}YaOPksX1xM*VoszO-w>w
zzI^%W%F4-VJ~I}~v#pl$`}smQVuQl@*P_~C8Bb45joO^nyQ}2oq~|$jXPI*G^Iv~*
za`Icri;18pm$fbn>6fz=k(1MVS*CAS_h*OQpAXJ+EsNa*1qIuJXMt8ofGW_;%gea<
z_@?dOzh6bu)HD>dw(aMqr(a(#pYOHHHe^rYVYaXD?%qyG*?n_EVl(LI$*uYK<HYsj
zrl{P^G26L&_v^ji?*$hXZF1|ASvgfZT*@!29ui+WXMoyq3=I6MoLafOe0;9_`1pA0
z+_`J>_x}w8oiw*;^JY;&!G&|J%U2~G?OK+6h*39YM*uS$&xz0dRdtUaK3vGi%=YBB
zqS74y)6;ZK>;Kin?ksY>^j7}fn_FAGV|SID+-v#J+|$$Z)7P)2g2E1*F2@}MFXRVA
zKr0K85*ZOOXl21F%iijGTyqZ_uhfeR3!QhapKYGMZvDPrUgr7tLc+qPiRnfyiQ1Ya
z>5~x;+W8AQEGqMoisz+EOTCNZ|Nq+`xY+IG-|zRsC#(7LsGBJ(Dmt!>-hS=-{rdH<
zuC9K4Vxsb=&!2<8zPbu(R8>}0S-s6Ys~x^B<o&(9p-a6)L1nkuY~Al`yrycc3S8Xw
z?Ck7xgN2rYf`V1Q-){fRJKsAfB4S1xzx=w7kB>`xq{V^q0BGU?<W%Mt%I<wvve)lj
zmVJHQ%ir(!m*2Ym5afK&5z{X&EVQcovm+@vSyWnj_2c9H*)J|EytO?){@r@to10R%
z=HItFdgO?NU#@)k`nb@$yGm6(pPrsRJvDMy&CjBDmA}8e-CFrME%;*(D7&tU-@k5|
z?`$m<6&L3=o{JL{okfI%7Nwn?_3~J+wBPO>3=9l5Rd*n*a~F;9b#oRiTC~HK>AR}2
zvGMt1zyFu~`jQ#Dx9VzN=YtMViVa&EwX*K-FHp_gZ~sr@^rkQOs^34YF1xuYm5Z0x
zbb^qBrz@z-c7MSJP=&Gx+?fMMpW4O3g8eTnG<2-|9)5jw)%)@?-^=duwM&drPrb;m
z|2-SD<tubeMBubkP|L0O`8iYB%XyC;KQ7*{A31I5Qt#<mFE1@+wY$BeFxhv$-Q9T~
zW!zFymi+niXUdEjE2PcyP8>fDT6rCuk+Gue-JO*iHW+})OK1&M`r?A)$B!R(6+CQG
z^P4l{`JUL_WwUInx6LeQleMdf2wfGj^YPB@+qZ-6<2dfpw={UUpO>fS#eVyLE2c~l
zdHUqZinzU1S$B7Bjft7_oA2l>)9kEcJ(A0kE#}NJ&3^Ud<m5?9f|h!%tor&2R4%QL
z+pFSv^5jWYy}Tl}{knP`ot+nVmA>9m`Z~-rXl>M1ladz!dw;*%y_37FE;@#Rf#Jgj
z185Xj*8bXZZmzXD=;%`I@N*?H7CY?!JmmlN<+A_PO{u4AX2(B%^ytgW<@3dMtd%;q
z)N``htu2|87cE{~`s9S*R?sO)?)_oiV!EGfrcaolz|YVB_3iEJ0YMC^lAzoI=|oyE
zS@Cgo_cb3{^q8T51(Kt{IqBkJ_v|k(F78~vyZrsSmKGM>*j*v()~$PWZS8C)Cnp}Y
zE$cyb;M(o?CY?>2+~41yc6QcMyV_q*Dvxc_sjR55cpETZ<?YSQ?ty`URc|&PpE7Zx
zqUWyC*V9y1`p!0!GRv8vq@*MwCYENjOpu*V=E8CL`kLdPK|?=xb{3cUJh1=`v){N8
z!7FLxA}1$TdCth#SX5eC+uq*Z`K3&AYGl^UO-rM;<z!lMbv0hN5U@64qtnER6DKWk
zY-Y=Rb!FwQnxC7Bii%9~@7a8PfB$}gS8+tlgzGB;7jyl6vo3bGT%r&IgO}auw9Pkt
z+Cg2a26keKXHNIxPft8s+uF2DO+)+b|Lyqm_phpFW@e^U>8mLq7yHgOJ9+*3^@1RV
zhRxvgp3lH=lu?%bdv_l*g9hIViyiSLG7R5J-rO*(tge18J*72dW0I@yT&qy$cD|`+
z(}HhqN(J4m`}Os8|4An4=VW>%44uN)$C=K#@=q&#-J0+Bs{KJnUAJ<JKY9ChEw8kh
zhKWhYBojzK-v0Zwq;w&1@#Uc52Ggu77akmJF5ch2e900GGqW&t|9Mv?sd|6Xtu0V%
z=a;`WQP~~TT5fU+J9PLk?~+aH7dp3}+N5)Kj%Bc(o}QFd$qQTiW1Do&&a=JE_fqCG
zsHq1k%hS)#(+XbJ0~&}kzgOX0SXfw8S{nNO-QBN0pU+?I)XKGN@gYXgSjzR!(^8-6
zO=o0a_zv&4f_h4u)BU$*U-z49U4HFIr|{=L2UdeNNR*ad{q*!SuX?NUsZ*yey}7v=
zG@37KUFI_>WOrF^>DybO&TTvsckkZ)u!Vsk-4#?N=QA+$^?(~n3=A@o;O+vW+}hdZ
z`C6)~uAq|%q)f9^{QdnePkhi2wJm4mgb4z*KOVMET9S5l7O3F*_3d`Ps;6!Bw=4ht
z{s!fl$%efZACHPpoik_6-s<nKE-m%0WV>*Fj^$!C-&rfFzrO>G@4Z~%wkC43Tk`R~
ztBuU;pZ3U0NUYEdUbZ6p`ntABGeM03UKxvk+uQT?3qHgY%}Wf3kB{HEV~2*WuJ2N>
zsgu^PU$1j|*X!dE)0RFy-hW$DQAV(v``ucNc>9>xSb0Zqs${#s$iToLQoS~6>!jt&
zmp^*^nETES8Clu2H#et$p8lDEVL`;g#|#V&lREmC85q2jtoRsaY_0m5Rr~kr^`he9
z%MFaoprMHO`+oc7@BKQ>Z@!(br&jE)E%z#)%kKUE?|0kfS)g0#edpW7R)2eQajEz8
zDU&Bpetu_@&eEkzCB4%9Qc{*YJ2!Xr{Q7^9d3kxW?CbZj@yo5L`ufUq(xpq6M1+MG
zZ%jT8Y6zS>c{1zvwzaRWtX#aW_P3Ujk`w6snw3FIO{%};+{`h1dv9-a>8mS-vR79K
ztNT5PRC)aRb+*OC$hlUfm%hEd{S~wf#lj*YE-sGM?)&Zch6@yC&YW3PUcUeR>~-Fd
zuBZE>G%HXBWw2Sn%+B}Xalie($KYnyyE~TFYD^3a6$K?S3=9E67Yi8}96Vi)Gcpuk
zTNk_f-QC@*LskYAm6u;{V&yg|e;2d&->=tMcXn(9jf>4T&(FHMtF)`LGw|)Lt)?j_
z1TJrUtEZ^wc;5E=oIQK?fI6&i@9qu<?La+s>QbMqwTOVg0x{jF8GV^9E-o#gMsc<A
zs|AkDPhP!RwPT0H&Rx4e9rssPS5JR9CCwz`f<yH7ysI68$|8b-inGs7s}8O?-X{yn
zBG!LD>@2B{xN@`oTz&rSZMjm`Wo!QZy1su_UsF=r`+Ix4IywTJoSHUm+Vo|8{a^2e
z3m1C%`(NLXc-SQA2uJCQ3kOTixW7BnDO_I5%fOJ}4;gsW_-12cGiBz?%HyAv-TPJ)
zJv~+C)AA_g?yk~bpHAz8(spV}%89hiPc6%@>Aq)R_zddV{o-XfF!5p`xcA+lycpc?
zJJ3Aas&o|-Gc%~&0IGuP|9zfsnsdXT^wky5`}O~8-}Np8wW)4z%LR>JE|+oW@9CK`
zfBt+SVd2up$9RAK_>pmEM<J+hcy6vWs3XO1_v1i`kFwWPt*P&Smw*O+_t)2Z29=a-
z$-2G{lv`(Yq{lcoG=Q4?Jv}^2mo3v$S9h<gtNZlro0;s{9m48<8K<UbcJ=pP|M~g3
zsJQs@2M-dKE?=Jg>B&h@4``NoexB8`yP>N>Jf~`f8p$4B2ugJyKYp|-e>bO%S6Z#U
zzCLz$nXjg%=Bn`Z^FTdFt3`KJ)zm=kpsTAwFMI3nUGnqu^XKzIR|dI)y2@)JH_u68
zkS!12U-!5A9>@RrI;Vq*iasfOu`oECJO=G6>Z_=@e13lZ`iY6kpXY*F-Nnz&1b%;a
zmsh2E@$V0Z`M<u~{eD%})m5N|!Yq@_Br72XhMg}gG`K*ae(_>qfJli9=$M?x3p8F>
z95`I~;ejKlb0Df6Hbv#{Q~mmj_WwTee|>-7{(Qlt*|TSZMms+~K0doE>&iUaY7tS<
zrN`x}eIz9%CoPHIp65B~)|O1rNe`MzN=}K1iE7DKYyQUwJkn9~owelN-fC?Fg8<N+
z%+*z)^FBAT^MmFmCQh8#CNyjElqpL<X9uLGuMS-u=H=xTR93ca$?e0NKrN)2pPTmm
zc*G4FYP+!^F=|J_!Zv<+z3}kx%Y`ytWo6qyj@q%q;%1In<g}$5HW>W;{o8xj-{)QB
z_bNfnFXK5^{@ts7Z)^MUh%l%rl$N$EDLMJ`9Q)sIHdnS?nk(4NotJ%ineRTvFQDS~
z!b0b&N1f_d7C16{1{D=;;*+;q)6l@MJcf;l;lSZTuyD7siURdaSBI^=vOPaOa@x|;
z*Vi&HFY^U8;d0DotNF}Guu_w`uzY^qDp0#1Zg135uc=0|><kSyc!K}mpGwg1!}qQI
z{rxIWE8l-lkBp2gJN?Y#&Ye3U`)VpZgN}BIf`-iIT9@m6zjOY)e><P7ktjc3)}tex
zpT2(&Pe@2;e9q1%6A%(IC75pk=suKr^X7T^_)J;7I{V%AdG||RU-P|R^SO6nNg68~
z+pFF0_gxP5w_SQYzCIR|lL`d(y7$YmU79H>DY+6<bYEWXAMWAN!NkN=bpFoWyPyF^
z-S~ZXG}$kJ<_~d<Qh^#dO|0CX_QY*WY7JW#v(hyC+6wRKdX?v{t%+Rx;X{G%Je!;I
z1Q{7L0%LqY14;}H>{k~!GUwji6*^TrJj}(VCC6+ws3Yk+&nD7$mdV9wy3rxa{bVm2
zK5Q^DGWznUTmMsk6$1lbXW#c(?kTXf0L_aQ+-G2rk(Fh4bv(|<U}0s&*VWX=Y-6*3
zKkH}v{3Azl|NZ;t<>@)G<oERzpc6^9<wU;wxhiyZ$l55=;Ew@5v3n{4mwHb(lRexa
zU-!fDa65na)m5R~e|81$F3X*3Q+dh3=rd@G1Sp{_pI>+B#6;z*%l+lQzPSmW1zR7t
zx9I<R<ESke6We&Dmpwe({yaKL!LwJ&G$<-+R%6PuojdRT%{v>s+|TkX@BRNTzjt%<
z$=PUt3g&OWkFuTvRbBb}|Ca50SnSEg&3*a9!^5U^e=3+yGB9XJ?qCGXiaB(Gu3G}N
zxG<;cnwhij?%FzO@?_uR3=9wYK+U`_(hLrT4xsMOV+MvUW-GpT;<D@&6`+mWpl0!;
zl9!iMJ%hZwy0pU9%y_<Yv3vh5+u4g>+}gStRQ1l7A+dAk&de(-0;Oy!HoUsNUf<Kp
z+dJ6Dr|0360+!k4`C(2@PVZhX^`5R}YHE7Fc>kYI-P3d;7peKqx?wo?@s85h*J9ff
zFJHbqx9sGZUteGQx)(&GpPv`HIqmGbig(YREjx3@$6BpO29%SqkMX?!-p#ESvtz>h
zJ%NkeKrJO+m0}*y0MS&f(03K@-o9OXxSjvDp&$c;DmU{BPz~L+_4W1j*$10ge_h}I
zZ|RmTCZO&-s5iQQ|NeQ^?<`x}+pXVjOTBZuN77hCOl;XS-DoWvn>(P|y9iVZeUWB>
z)j|vm?rxwKUSUJKx{{KUprByoJ!!j|iha*>%w}J{Hvx12rJ%CgiK|ybCxJ#ackbE+
zD$>@iTPJ0h)DnEx<In9wO@}N>UtLl5c~tS}@nca@QB}`PI^N#X^{!r8>djrVt?=<N
z&^V3lW6K`(`87e=*VpNO$UX~NKUVQEX=~<X(3tPM+HaAU1!bnKU;jRqJ#l;feZBhn
zdQh+ltNVo<?~}c{*uDQwUd@98jI#E1G4gdk7J>$u-dFG4oKSf1?$y=d{u?)Llrl=`
zu(7fEG$%DJP0P$Itgf!E?GhtHz@JF7*=N(NSU^E1a@61c?-KF23diGpvXjrI1-EjE
zK6&|aWqkeLP|(n2YUHQSpFyW3U0D&Re7W#p!z{C0&_OP*zP!Br>C2ZX>(}SM<G)j%
z969aV+uP|HiVO!NFBX1Kcwx@K;O=_-VDo~<3=A@&vh4hzJSp?}`T70t`z1{>E+~5h
z?QwN?&py<`xvTQ?vX>fV4<9`WdXdVqUsn&5hLruDN`M;rtHalyO51!A*Wmft=&e~(
ztG>Kg`0#N1>#5;!fdvH{#Ps8I<mKgE-QBen6&+t+Umt$FPuADHmASL0=ZgCLnnk?Q
zW}uEVXhs|~7AqvQsPgl(%o7t7XW3M4I@TkZY_&@8_4W1FrStbJRCe!sQn}x6uGOzc
z-TER@Qdt@^Bme#T_v-HM?aTb;uHqKg1C7B;o8_GN`}M{3_4B{IzrTKd-LI1cLB@|B
zJ^J$LwEk+hUMVS?ih_4S?Ng?RfQ}z{a&mIirWDV8?^78V78F2-*LD8>dc8jD(vr?|
zbFG(mba3!W7&w?_T{&TEU-@atzn|ypU;X`l|N7&8`*pRyzpaefS;QuMSg`cXjg0~J
zA$|S*+nuEt7+zRZ6oAw6qQ?&$L9Nohj=pAg*W-*2JQgipEGjAa(!}|ij-JMx<l}uO
zZ{N1Q-@9ptu9;aFXc%a!c6gDvs0XOo51JI<l`uF^;Pe}Gh!?JD!E+m9_SePU-Bo%S
zGzG8bJ1gV<zS^vNdv@x@?OBn0yl<uVbiH5ye!u^$t6HRHHrv<!-;c#XK|xa{PhMR0
z_0`JK*Vl>)3k_w@N{ETyxjoA?+obGGgseq@!uj8gjg6p%6}!sbW@$(=FdUVKX7i;l
zFE7u2a$@4G9fgl$x3lKo+Tsan&u_`R{N>r~{9F183=9r}7vQaN230{>b_SXFva)T^
zY2=llPU2$=lXPhZcDZTV;p;Nq-rDNr>w8vq8ZS3@@v8Nfj*gC-bi6-){8&_6e7d$)
zKYClvMrW(z$(wJQ)c>og{rz@(W!swgs+X#udCQVlj@cqTM_F6TA06R@_ZWZv`X%MZ
z!r<`nIJDvLa_94TlT#z3HmCV6oHupJ*6izcuOb*282DTIV7({?jm{Sq3=e*sn`gWF
z)z#J6e}8=i4P?n4Uuf9SXMJ;j{r+YC^Viu{e|vFhsrM=9+|H#-mw1*Mr~m%;HtWKI
zMy>F5F%Nzo?G~RpWy+FoZ*SkWlnmGd8dh@elL>TlYvYnC<>KczpK!_sJh2vh2U-g+
z`tfr4{4dk@|5+MvzOAk8)n$MC+9RC-b5hgOwKX+Y9+02r6$Bc5U&6#-p=`w`CkARp
zPP|a~VFM_n`&#;%+gtmXZKCd6W)+Eba%ut<xRsTaD^pKTyS2M~y_2)^)TvXK%37Cc
zC@47SMr|>Wz1;EOK|<}<tKsD`ZL$07_8vNXIPz6M!;vE{x%c)&CLilDls&3<tY3cp
zg9iy)v#<O0+kTtz(t_{xi;Igv&F*da_v?<ozYAJN!mukf^4DYe|10eOee7Sh*kTD$
zO?EW~hND8TB-JghzY4S&wrX3})m6JHK0Z?RYk8!huI~PR@ArA2skhbP>+gNEtW)4%
z*dT7jCnxfkjp0GZ3yX>XP%By)n$v!7&^cYg0y+dK_(i(^T&u4flNaphBCdb(ZtI;#
zzrMaMDlOd_JnK>F<72&DJv}9}7{7p8TAOr0U3dir2hhoB|9}4aHLLHr0cafvC@n1R
zw+kvL*sy2M9v^q3uA{82)3LRwRaSaU)#~c+zy9>}^sh(7<0bsK7#u#rW}aUD`ubWc
zbXCa0d8Nh0mwTnn<qDNV+$XF1Uu&1I12vd5H8eb!*?2Cn%hxRE64eHcIBwGM4qonO
zDl5$Jzy%Z%Sj(I@hiB$H<lo$sx{&=tuG#Eh{@05Ws=vJn3<;ScSN+B?H6_L4*Z!j#
zxwp1l+>m%!L{M<yh7AUj4c|UH(kX0J_ow3B>nT%2a_{f6g|soAote2fYHQX_V>y|S
zsHj<>6PI<Pw`KhP_I8$Kaa!K>)sdUi<~4pfaKPbmVeidtxwDV;$*$i2@9X+yi!E5h
z#6|ASFiZwjY)6i`?A*2M)bZo$=PS48-TiXb{Jw-2J5p|a{d|7C-j!qTK<y$$-mb+r
zZbX1)foEA3FVl<Jq2QTyaZ#(2v$JW&1qD#zoNbnSN&epl_QRfx4Ch+<n%N!qGcs6c
zLDnxYJXrC<qC%iV=D|gjnZ}+O=K1qpa%eom-^M@xZr`6z-mb2$CpYOtP6G|IW?ow2
z`E%apn>j^=g%{7vH0E8>vUp|mcF^GH>VJQKd+*x20JOseH1h=tq14mUGA}N2-K66!
zsvQ;r8j~-2>UDVK+x0<9y+8{HUP|yaA7yR*ewg1r<Ij(epp5Wt{_48*Wp8g;ReoC1
zn8Ls?g$LTt-v$~s6%;Hy|NO?4UTe$3M=i&CB$Yk2f|vEEXliSFPYT&plKJ)h{doEM
zKO5Ej=jG@qGaUGN0cT?%YPtXXYdeddKY9Ot{_pBDH+iH?PL!~S6hoWqDv{Hcw(&}5
z-Q1K4T8X5Rd39B&-_{2YkBY~K9B$)H-F#C-PHr7&x2dC}W97V!I^Lig@+SM+t$cNL
zwX_$Pd)US#SJ2=c=p<*A)b#Z1udlAovMOB#stT^I4wv@JIJP12@RovyPQ3DVG3(Z?
zTlQGu_@kynyGvhBJ2h3i{P^cDUrMHGg`Vo`WMI&UgjLfUS4#6cKRq?|>+ALVy(Zb%
z+J3!}-2d{#MCHnPCr_L(5aeZeumoqGkn4SVdV2Po8yj~zZw56?GBQ?Nx_lWlR|uNO
zv911QGDk>5ZdcjcRXdBHYpJQZ<>i4+L!AN|1pD>%wfC-C=X`KW{F|_Vz=DPb2G5|h
zv}I0CPEVdcPqz^5TD)Y5O787#zPGpKUcR<Adg`=kYT@DGTQe>?`P={9^0LB>1z-Q~
z_@gH4>Q5)tx0bz);+40vxqlO-QOdyJ#fBKRW;oCS8tAI|`RUiM*Xvb1_f~zq1ZqnD
z{QO*7UEQ6ToiF6;tE-^p9-y4Tz|~%dQr8_gyuIkD7pM~jx~KH{xw)o=k6dzZY;at-
zaN(r9|NDwzqq3}B?Qh=X#O|w!oT?Q%DK&D^5>{?84Lv<S(3HT9ji9E)QYq6c2|upO
zZoN{WFVaDMR9Wk?7uVKC_Zv)nyrb}OTiN@2bE}KLetUbn^x+{^(0C2V(%;|SUfow)
zy*2M{)Vp`@mOYkw{OD29apTjQQa0aAiJW%1=AOtCzi#eXrrFDu&##M`U-PN+Wry3E
zsI6YMRbMWE*3+HRUaw(c5z#HKKdryNf6?N_QzuMV@b&fe)yc>EmMvyt2+)DdEHe~D
zX@{)|$jMm)I_rF@X0Tg3pDd_SoicHv;_S0(`uh5yH7dEcx0%X{GB7L%05zW%s4RjF
zwc6Am24q1#01e<vI`sGTU3+tLbLpQSg@-*GCn;K4MG33<TsS-1+}GVuNmbPqba?he
zW%r`}_5bIkMn-MVo4c^&Tj}<P51TA5D{S1od-tZzn?YT0&|F^mi#>^l+m<c1oPxYE
zvyeweZ-+goD`8o*WL?b8NxRoLfYbcV^!b?w8W`JznHU0Upq@PN9<-5-lasTkv^4bh
zx3^E9KArk|`X$h+F~PrV3=C6TKpig7aA^bk<9F}Y_1pi8$lvqPt&#afe9gz!dsVM>
zQ&UqV{kW#^T)cP@Tn9Qnx*xqIV<H=`l!~~x_|^6C@!$d5?Vv?d>c)#T<}<Hbx2|8I
z^KoHe;mKm}(%;|Se*JRU|Md0i*Go(+48+9m>_;^6LjC;uKr<y9HW-Ai2sl_`!objF
zYJM3s;?2NNpdzXja)Dca&jM-lJPk9mF!|aq6G8KER$>ec4ihit!-jaljmioGIXSsg
zXU^<-{BxqRd&thBRBJV+fFM^lw^f;!mqqQZ+PW%iZI)GE;W;CpI1zEZm<!+D-Uj6b
zQ06RtcIM*O*VjWAyY<>IzdSqJeE<8|PXdc#_t(X)Teq&LynK3ld;6)W+UlSQgpD$w
z;c8GUg|3T<to{A%Y<b<sN3N=>sw-=Me`5o8=b+(VU}c_n=R%jL_LOPUKuHR;wD9Wc
z@aZbCd#gg{*M6I6_w$J`XuR<2tE<Ly#26SJ+(S=iR*H&>ph0)HKAD;C-<+9gJj*z}
zZ&&&IJO#;yNza~~oLu#MZn=cranRoKmC@VtKyz{`n%36Q_Wyn)zYC};DFICzE-!j|
z3e>!>`t@?TY33!B!z<<Yo||iZdXvuDxV=%Je0yi-XYdTq+UV`)_+Fk#E_8gz%Fh0J
z_4<856%`eY&p~BlMa7Q1ySq}KBh^6+b55-cUVdd`vis7dOHZb4_MCL*?%l0PN4ciz
z#YR1R_z+ZQMQzVp`||Sg)#dN+wFxsbFx-(vOMC9xDC2nd?>KG+9S-vC&CN|Wb7mPN
zHocs|;MJh!JL|=lmzS3%TeST8`ug;yHNSsJoZd8L&YV9TLYCV=v#hzdw}ECL+<K){
zJ)<@zwc7o7z<l)hacxD#gPLp?*2nGDI=!jL`eXk3Lg{X9uJ_x|FSP#o)~u3&A;4tX
z+qnC=;B=?q2rAlHxy3TRytv54$9L`GVs}uGRaRAL+1kc3GBS2`c3w0-Z<B1L#lYaO
z@B&&o`~o_=L{QmH!_Lm`yh9LlpnrAXVmG$SjD7j%=h?Q_eLJnc{|abi`BT`<v$M@X
z-Q<g#Qcqu5<|}=<u;<nN{q_3}J_L<!;TQ%r&A%5DU;A}x=Z<5k>FKZQ|9`LFTKYN+
zl$398&%b`OTRe61O;F_zs%LI*%Qco2K6)U(o4f4I4aL)&=Df=O*eR@D^5;jPXHY=E
z1km)o-(0Jw)$gXq*9H3c^ne!LU%3)eeVm11flC5-5hTNdkeb@st6Q_f|2~%gf1*}j
zPtULR_qWjPd3U$e{4CnJV~2zf2LnSvJzDy`;qT_w78D#jb@F6odwcuJ>gw5jEF#=`
zdU~z<T5qInwmf?QbO6QYz0>E+S+it`ifQhxkgZu)Pn92Dmm1mC-Mu;7r5$vPGH4#n
zdzwz*biLS5bJj*~c6<2n;jicR|5rYrUw<#a>G!Xv)8n_~-rjbn@$=o?<*$EzeZA>s
z&Z>xwi*9YrUcO*~0xK&kDE)()MlVnBX&M>^f|h>FFiiGwH*7k}TIuTQs;Q;*YTo_z
zIcBqCVq!q++IS_6j`+O<wKSj|Glm26K)u0jxwoHHzTbX*{oZd<|5vaxFo;-xkw%$y
zl3VLJS#4$c`+HnGJX5AmpB}X}YwGhq4-PhWb$17+q%2w3((rgTxV_1jd3{|hE1y*u
z(k_ay8;<`bsVONrVHt#6F6pp7X6L3Qx0^SZW?us>uq<Lf$IQ$;_uJ<ub)el16DLme
zGj2HdsA+fg$D`t)<-9j@%v#&qU!OI<9}*A{FfU!_bkNSCr(d2-_Fq-?^;O#>CWe4N
zu<}Z4d*0oko10QU@A-cFHJ7N?j1CqCh7S&Ck!lkqtnN2u|Ni|<%*@<2_5}|b7A;yN
z;lTbb>B0iXWy;__-;BP192v|N6ltIZ(FYG6<l^EAIy=kM_qe0s!ADKIxj8rj92^={
zKr1{H6%{{y{%kyli=kmsCnI=`bHnAIKcCOvntp!Xo$H_>FqNfCmaIrR+Vyi@{i~JB
z-%R6WU|67m=ExbvA0N3+)r-AV!o#3(5md`yt{`|F(!9tx?Tmpe<52-niSYG$ytynR
zLxa%SO*eDQE-QkD;}|xGi;GWZ+J4|x&bFHO|G(W^8@>IFC_e+kgMH{#&=0fxduv)+
zSUk7qJG{TUd;2W2+*$8;#@GFH1tr~HDbp?4*Y&KIvjkk4V^#WU-ScUwD|2pc`t<43
zreLMxf~ZsVPv5`SfB9|G+#5F{=Gs&Sfee^$SIeVr`u@$$&8y<}?z*-<e*J|D0hbG9
zqDo4(C@CwyJf;!g<<$jRq6j*PKv~)OzolAw<g{yRqti8H85oXAn}hcyFw8l%r}DFp
zI|Bnl#R{}Qv#I&`@nct4*QAo_9T_h#Esfe$lG%9PEbmUl<>mg{(`^`3LBorU-l_jE
zm$1jpx2xS!^wbM9b2VAb_f)Z%gv5%O#_6lFudi#nWGVM<@{zwug^qEc{WqYw(npUL
z{rdXa`spKn1_n9RJn)iMaDYRJfHyI_%Y4Jv$4!MVDw+B|EcWy!(Dsu}si&p9I2SCL
zX`J2%8WKo8-uLoqc>LMo)88K*?GD|Z7YiD#Te)&2XcoZ8*m!H*-zw02X+hC%tHMX1
zD<joBSH<q$R#RKct6rp&etzCn&_Euqw3)?Ig^%#1AzPA<^W`~+&o}>n^8WpJP<!On
z)zzU}vqCQyGB9Wq?f_2)K-~+b95z0F_fD_8yxjBB#l`MV-@eu5=jT7Xl3_{-V!dzZ
z%Aln->66ubL4|MLogE87*T@O0`2=)}>6(Dr+~C#L#x=FIl2*rMYd@V-|NeDPYGl6#
zXV>P*>i)0hmfuVKA;Zw%e&i@PcYrO15fuVkv#+Q9kZFiLGsDo?xsB(fd5xZD=&F#5
z^Z$KOul;s2eUb|3;--JUUf<eVy?t-8RPm!DoO{1si{|3sn9$$fzb)sclBbuyKWKf-
zm-qGmZx=Wn4_N5LdUm$CKO-aKvc(b;=gzH-|9^K!;o*`Liv{p%nSmi7sgM~mKM!*a
z14BbnKI$q+O?7qk^E*=`y}Z4Rr|>y=PMkMy-I_IPtmmbtrfS;S+I}zn`s(WET3fA^
zlO|0Pk&#*R=1tDltgBw0o}Q=9otsutZDDU`7dKr${+f7vO`^rhzi;pC3<fPwuZ`W7
z6Ui%Oaw0)#b4+Zkue-*yIkklc>wmpi-2dg2_WBjk+w&^x>KPdt+M6N83c{5P3`e7g
z8YmNX;JmOY)!TQrnJ;L=)#GEmpXbQhR0Mz~=vIfVExPaR<rUN`W%@?;atCNN_~pyN
zot>RUrKMB*`~ByA&bzw{w9~?H%DFXVZ*PIp6f+x7!2Y_wpx&aDP#2?^_>-%<%iq_$
z2aVU&{{EJAYs<>4tE;Bw?`(wChYSo}B1oM+Bu_LfdUau8^QFs|ry^FqNt@*aAXdJC
z7F{MLCN5jdr19+E-}m*}Dk?7F>tX^63O0aOFRfg;^46x*?o-qC*Z=rY0cvJMMn+~`
zUe*ih0MD2qarmVCUM^8B(8$EE`v33$zl3aKJNGwA#}m|uj{pBF95ia)Hu={5MXueT
zuKe2g{c)gL1++*Y;Q+(lFPFT*;~W)bq5JD<Bd3+d%O^)pn>2Z{e4x_tr;i>Tden6P
z<JYgcm!6;d`1rVdpb`Uvml>AQVGU^J4Bvt>2?zEM2WFY)ulxJ^ySAE|+v{s<K|OF)
z&#hTkFI`yZ44#w^TN^bg?|#^x{QGv33*WxFwl-QTeBB+{^OrAQ22JpS=64=Ge8|Pm
zA6`|pOH4m*4QMmhj}H%}EQ^+ahE+kME4Ec%0$yHP>g!(n1hnQZzoX*)y}ec?FDA^Z
zc*JR%alv8IlsR+O9B${=R#0#_JKNk`@ahgw`|{zT)?e%Y|I+uJV{vh%xVXoqPGNOW
zv3y`<0hVmEHtA>=Xt1P>PgZO8*=3tjPiMWmvlBEBv*h;ncYUy>VImA(>mEEvsI08a
zJlZAtGtXgv>Fa6ps$OY=_6kJpE?fI@1)rj>uI~4=FH@$7fR@99HbSxS$*fqgK;iPo
zH)%(^L_tHkpb131*j-O7qc^AZ9y)yZ>-qYB!RPJ&?^)RL>~CEm=n^%r>3VNVy15w`
z8veqT{~{$u2L40$@5h7IH>;f9bY(-Lvu^Y@o$obQSB0($TRUrI1;Yc8d$r$VLA~t!
z{eQPjnlwq}uG}17504AQ=WUlexAVQcTYlek&ZWW~yLX>HeAqel^fXXKkQy1auVyD`
z^AxC10L{D0Uer@kQu^}kcK&nFevAzp3_zntkB|48PdHN;vNFgOwC-tJ{{3}RrilD~
zn_nLs6f_CEi*9w8uX8)!)oW{`eUES19lYG{?$`a7m-}lgD<3ZLVPNReh4n;{eD%N)
zbYW}p^K+p-K0SBt+%d_zqQNU?6Y=%+_30(Qr`-hQ5lu!BchCyH)JV_>C8#l3^5Q~u
zT~BHxXjy{nCCh1`VgS?yI5AP#H2D~h=cU!__i1^4`ts$<ot?#3HzvC`bDrH@^t5Z=
z-*3^NENlPgLvu__3}~YC#0d}E|9?J%1{*h}p8j&q`hCWS2M2HMEMETdME{+KhucG!
zdQG*SS6yBG`oqJ+Wj;@CyxXz^bTI1`&;o;>pP#QTe0*$K@~u|L;<M+)a&mH2&t|5B
zMtjY2Z{1LoWMEKjPThPnXPGmSzrjq0Ku~Yv)6>(dLRJR7Q@GT`$}J);t{xs9Ui#)n
z;NGgQppuVA{rkP2DzLQxtO0j^{Q7n3=uubDCJfM^Hk+L8=}R9UAAdXL!pE4MMXuS`
z*M(+fttu)i3Rxd#+uGU+o)KCsxw+<N5y<cN>;LcFv}x0oRiWCTPQdy-pSrZd*UfqV
z)3W&4i?inUuk=cr^DNoA{=fl;sam04x3}d^Zf|#=xB1K&AKSlQE}uGg?%Kg-c3xGJ
z_kP{nY<w~^@(UfeW?h|=RM=SZ`}@frNn_9g%)P%}t^V}=`*cvtGUMZ;qpPB~uVdqp
zSa9V^h;GytkC`)PM(wWyW$FYAO9qCc%#gVXaHv2DuPrZLWPrvD&GYY>$g(nct$BNU
z`)bE#Hdek6?@P#&Kr<`#^z>FmZeI55`}_5c%<QWio7u{1>#nbh1*I3zdhz8g&yE~D
z`ts@Y_^@6nQ<I7h4{V%|Y}~jJ)SCunOuO1&pbcC)dOLP&1~1F__vh!WZMn0xLRU?B
zu48K(3)-;ycI$PMv@;TO?d#)oqqa=gzkk13?yVFJLk5PU&?$PTyTKIL@vd%epaO8&
zVg`p!(3V5clKF=ZAF|HVkKE+)@Zm$hpIa>y6&+=*%S>bsCxSX*I2Jx0eblsjb?EA8
zpj`rii`_&k{#|sJ2knvrEnipB)Y9^*|Nr}b>CaE8)yG&E7ThQ@2Cb<8I|M;2u(-Lm
zdi$ftk4xX(vE-FD^ZEDh->$N^vx0(xKnZ0kXc4r_?%mh_c3fW{KYjJ;)pIXdh_#)6
zucxEqlbD!@*~&8pEid~1b?4<>rP*8a?*6*ST4eC@<;zp2PVIVJ85TC}(&fv=@!{*^
zVl6E#zjd%NICLHW&lVz_1Y$WTrlhB@j^AGg+F*S)ZE|WP7dQ9h{rmT;XsW2VfNq*O
z)+?QEv9flKMWNF7vP92c|8MR7FQI$7`uyYhza?4NawLy>bu)LDT10$gU)yD19HNl<
zXY1Na3!e5^{d*yoanW{V(WTtbJ7WG@C2n`j^N{xU?oC}3x#Fmn9JBjV1LLls^I1v{
zJH$+5V|AFWrLrFXc+-BD>e3FcwZ-QTyq;=PZ}YwM?n&zui7)-{OLK2*P@Fq=ZuOhn
z+j67x_W%9XBV)Nq{j-;G{=Gf5b;~un&djy`uDs%<^{dyf`F||@Z2$B@)AzDVp6XAh
zMdzKgd_HG#a-U_|_N|}|Hrwx2W&7Fvd=h*9+WPqU%6%4#mK!rJIIp$pefbd)P{=^A
zgZ#I>?`!q1$5rR<+P(X<ALFkb`SrhV|2)WFH(_@EKFi=`J|}N%Ox|4d^pwwBD^t%;
zTi4g>g0=w8GtIs>CFYj#zTbD>Kihr(Z(i4;iu1KsvrMOYsd9_!ow@(_?)|R;v6Wg=
zPucAc7CFlJ`~4M=$u<9f-#>qt-+s>hzwgQ;ca>zS`OcbhcDDKRU$58uXJ=<0>y-{K
zd**)bAnWgE_5aTQpQ#zV>`AZry%S43Czr{xe7aM7KK1LXt3PiXx0}{3UuW_7SnugR
zS?i)xn#-S@F+P8W*ZfXEktM?yUX(V-uQ}@TYd$f*ul@OSy8R)c2M(96U7HrU8GOW6
z<=d^-zeW5%lWsRz)qC2MfUv%omzO_(vAExFYm~3Ix3}KzH=9h%&EIcZuF=IKXJaw{
z@0)bvnjaq~c~xJte!nNU%xV6{y1&1CW|?Tl#>QIyd@^}+-QQm&rKPH#eAaI^*!=l$
z_~+mE_4DihJ+If>`DO9<x$kSz=ij%Sz<%L)uk`fg^Xsh4?-V%8)qFU(W&3t@Ptefe
zOyl%t(f5Caf!HdN76l3Os$Q)$DrQ`89@_PX#NHQ6^|>XNe&5^i+x=?RSLXMu75cNy
za!+xp&)IPOYu(>pslUIywT%c_w=wy6+M632Jtw`ry*>TZ6wRMsmfOb`g}&cZ{QR8F
zj|a_?rdc6<_WyotDz2KFU-x;o<&Ou=pKm1hFI~1wtzEwEN8ao7xus$Mj{pB5uX^>X
z4!ii9-Ga()Pqy98)3#=2_~y+9UiA!dQ-fXl#YL{E>J01)e*OAo^ZU)_>e%;h-uO5>
zJM)Wum5cxTD*UwHi>bf9zn@=x-qxI3Ovj+%pI+G7sHxfOcB&n2<2{|de($#9zv_Sa
z|JVHgy8iEap;M=xK44;4kb`Q?^F`fyTGosf3|qHsdGc&_{<$wNFBe}4bXWE4TIBJm
zz1i^HzTfX+>i>RCRhyP|xQ#b*OGaSb=h^pDUSC_gGHmtkwc@T5+2w0CEZJ2g;yUr-
zV)yjV&(5YU|KfG`?p;ZniVtzu&GYZgY38$9!QNfP&My8Y^Vyl1nq5lV;(9(ygHE2A
zX?*|t+(jCn9?SpV!TyRN;eRq@=nWDK3=f!h{Cc(e^39twmn~Z+Q+}sVvrFm!2mb#P
zbfdRDIVv81CUg1RX_m#$rp%4(+O}<5Ovy#pl_6S^wpAs3mQN;Znq1YpdfhIq@VLs<
zbGF~_^hg>ndow5Q>E`)=bN)Sz|EIb+{rtV;wYzs)m)|W7_p^LD1sqCEwz~2AY^Hjt
z-o1NwWr$YfzM7xwm>s@7`+JSCVXyY8`nowtd7pvd{i>+7&-$$2otUKRy(#f<8|bQA
z%U3HF7u~CT{`66|zTeUyP3w&!yu7@UMkyZC^yBA&PX3&GdG(*a_y5=a`x^h>^t|2g
z95w%Wa{?E;E#0=QY`d*%V9LQJR#nky&;R{?e}4MDFH6tNv$Zx(I|ItWMb~4?pME&Z
zfByTv?|W@NoluV4nB=PFKQE>%t3NwC`}EZCxS64=!z_0&FuW*4j&25q9|2j}*`E)~
z|1*gH|Lgi`zn7(UCl<1}1}@pXdpCPl)qGI4{CUiL-$e6!70Oq$O0TcI$}V41@bBgP
zf12WP6^SQXpB5A_G6blhwgsvS&zfFOxwOP{rbS_r-M^3h)8}5!?v=N<TRy+8>e<=Z
z;bmO47o_v|OsxMoz5ZnJdE4pb_bS!hWlKZOSv>CHku+NJX3Hgu9S@o#cbDbL)%|$5
z=hv&%GflI@q@<)iJ)51McDRif6r@HKA0BKHW?bNJ1l}P8O(YB(#HV_xx&|%@TAA|Z
z#>ULNynA0)u3xWjz5e=-?e)L6pP6B({QXX`KPZAX6~9onvId3Z3?5mlFR|CR=iHq1
z_4W1T8#iujKmFqEu3fu|{{4KO{_@h&m0_zjyOgxU)||MqGWhee+4;-%?XxR>cIISg
zcx-5y7Q+`$)Uf@Q^!Qls%NH+Byt)cbv8AuCy_G7HF-$s=$NciRTy@UPowm<T$N&2z
zcmCgF`+v%>udhG<@woi_iOTNFmMu%${&kVYrjnPJ=6NmQU$JuK$+_kCW=@+ntvq)B
z?{~W|U%FIu;Qptx^Y;CHoBy2M{)c1UzMs#0W*Vs`AMZPRYO1zz>8mR$C$I1Ow)M~N
z{r{`4t%(dS(q#DJ`}Y)Nk0LavUaal2`E)|2^2x-V51P0qsodU{>z$sSe(Uz_%NH+B
ztbVssJvTR3vrDP8v@|m(=gj)Lud64mwy)~9|5wqq=*HupA08gwT>1G~&b>XA{aed#
z*Dt7e(8&G?l%D+Uex}6L|NXk>cI_ngM-#sOzPoy7@$+-Gd`1l_nc3N=*F<hMs{Zz7
z&$nCI)obdX8P7jCN!8m+gSp`^>cB(;|B7|%^wQ^5rk%6-d`87HJUkqfWu)`>81~!!
z%9y4fA6Jxk{>R(=`e;y{QS$QAobr2>lGbH8X=i3kY~>bTwsfiL)hyG~({xY2xVX6Z
zoaOT=b8jZs{l0zw+0yB8x4zaMZsUFV=FOet``dDF7yW*_J^jgviMBJZueR8c@ZK!<
z))Zksi^TP>|Ni=V`rF&v)f+e%zUiYy^ub?WUxUJ{udi>*_U+GqKA-RJ>+9=h^YMs@
zsp-_Y?)t@tdCgP){P>uepMU<^+UU&%4-dsuy<9resx&LE;$f@L3<E`XxyqEAGi{%#
z+yC?gRsYL0x<p(jR(^h#dT&o<^_$gUt3gH2j)FwasZWaw4py&TzyAE@^LD$he?52Z
zoQa9amjpqEH}Q}~5zxqGcyly5fA7?-+1Hot-D@i=EBo@zn={$#_fB)>w>1$~_dBCH
zJ!aCeW5;^r?d`U1-J1G*+OwzA<Ll0UU8G@D@Zf+<(FsM{kSo<|qPOdT>e8&NtV`?f
z%ez(X+O=zv%3`<PQ*Ul=Hm?8oXUn#2(`MdG2JLrV+;3-fHOo|2S9j-|O{Xv2xwGf?
zyhR$IY+Cbe^Zc_P9v=4A(w*MSeJ|SE+Z&u@=iAwW^8F<HKX+74E^_TI`hK?@)NIi=
z7G(Hkf>x{;rkt2iQd*jNW`-dsIsW<i`SOh$GZy#T?Rv8%Zt1>#b=N;Uua-2)2=KH0
zdgaVqYxCuEioE!zOwGTr!13k%{q>WUtXrqY%*Jy<d;OkG*|j$|B;MRnm>gMYoA>6%
zMo^lWl=A!A+nGkGUUq+9`cIF!`rBg1gT1k}U$4G=^TsDQIJnRH-3}4giS<9)>rYJ6
zjsEngTmRXX%YLWlSQei;$I@W8I;ad5_#oOLe{1pcb0V%2Z{51ZBW0q|%+7!AAiI1_
zS=jo|kLCYcfHwKH@kmZuU;8$D=gVcYi!S?`r(RnV391;5^-52d|MP%-=Zi(%mu}vi
zdA|PN=bxbBYt!cHBQp$>H|5>k6?-4l*s*@U#~3tCQugM?#BJNQf!eo64t=Wmx;oyp
zW}i5pUPV60%Uz<{;MD!&!^6ysj1%wc|NrihG*<in=luUUzu)h-H#Id)O=ohL9~!dy
zYSv9bkn>@9@5O6tqd}E!UteEINy(E=^?4`G&9yE*BIv$k<x0)o-rmfttW!G*9|x_J
z+3}sF4%8ZzEx$9dudh$0>czs{Yjf}Iu{?YB?9MNjyg#4KuQT5N`|kUqN1f`+7A{oe
zxBU{}dDQm#ve|j3bhqD`#4Bx<a-e~6=lgxXi@x1VU%qXdnQI^@T7JItub<Vezi-Ez
zD?vFoHYj$B>7D|$t8(t{GOf3J6(ZsaYVA#Wb?Wk!D^t$bzAN7O^;+~~6;MK7;Mn}>
zK{Nlex7+WZ1GNx*XPc$|{q<FKIupZhWz;k#9}pfMUibHP{Cl%0|6Z+LpZ4LwK}q|%
znpv}E8Rg&Gv&p#n4rqr<Z+?w(cwFVv-Ru4ra{OL8J<e-V&G+5+&+^xOX#Vr>`~LSQ
z&%`Bzn$$=2>n6^cHET}kwMbC9y6L$zBRl)Ft9a}bucebNE_Q!D!I`h}dhP1)_3s{T
z`eeBy!T)+pu`j6o-YKm9?6Lg+ikp@U8{&;oD!31dcdFm-ooQcRCs+IBqKNCnckkY9
znp|~ffn#&gS<~xJR;^xFb^UAopX2pszFv=?|NnRW|NKc$zTM70FB%>*@&D)gfByby
z-)0<_ueagl<*mNM_CL=o@6L>?tHYOX-MW?iRMqshwl*F~BbC$B_0MleJbdch%ddQ2
znz^;6dUY-GSQ-TCy<EO?XV2^4`1trTIfggks0B}rLu_np<)cpZOZV>010|ZWvb59F
zbXSJ02IWFf!B|pKGG*?~$9DgJo_~Hbeg0Wze%mRCepc{uzq1$J<>!X34pa4fc4p?}
z-|u$o|NkieKhW)+`?_Vz)XMKwrbk6ZO;U;8mg8AlTPs)bpm9#stChRo#_p*ojEaut
zKheyM*0d3oiTQ93<juamzBO@st>(_18@W9%cGcCau0<z01eMFAJ?y{TNIrdzwZU#}
z{7vvgI6Mbj-Ija%(#4A#vmeyFy|wk`&f@e{SF>KddSz7j=twMc|KsER=NlNAPx<K`
z1*Kt7_v**v{_{&bCttd7VS-BKyPeNBRegO`^CnsTbQ3H0Bo*tjHz!U_)&BfczkcVL
zC;eCE-xrTu8@4(5cpr1oi9dTmP20++Q^QZ4dts{PH|Iwqzut>CZ$Jfhkpu4n`N}5~
zEkB)5E<VUAuJZHn`{(D*or~Q+|NYMA^R{f=x>Td<%GIk&H*PfC|Lf{{uXSt<`@pAq
z!2H5+AdW}Y%H*UxTZem(#Kg?Y%ifk9&I=S#75~Nu>iAvux1TGWw?mQN?nlC{+qWmH
zD7*KaIWyDv^V<AcZDsd9pGiD276$&dUqfc@{32w2w<H);({4Uzr41@=Z(1%bE;zVv
z<?7X^XQt1aX?)(s*z?lWt5ctzp8oupbpDye{dTiJdmv&s7;2}ZOhGj4one|C21@zQ
zo;~Z4FkJLzPF(Jh4#Ayox7|K<Zh?69_UQNgmQN;_n3+8T1@4K7%E7_Gn{QVIih#Pj
z{;HRbuZiDp2dd{@yzr>5uAW!_@8^{(SDqXZ_6L>SH!B$~q)VbqvEATizWU+%=O2&z
zmuqy{&f}N2vzcw4f9~1Y+213oxBr!yaj)w2+BLDe&ECF!`|`yLkM#8PxazlCL4_Kq
zWvjRI$s`jqv$Q`yKCWE5R@Yh_qsFRl1Qj(uK0E|9$(Q-fjVkl&2Q3WkT6E%2D|hh9
z5ToK}XTH}i*Xa85<GB61#$ERwwu;A{nCx#iQ>F6n*Xxs2q|I_XVq@>-{Wi<HbK`Mt
z>Q8V>hpG0)1Vv|1xEdxOTe5MZ;pgY){gacE`|N(b*mRj8VSh4ew@E)_ZP;l)jiaBQ
zo(^6aa_R2fxn4^rJv}{r|9ju7?6-Wc6+b_B_Rh}Y@@li{Z*OeBg|5EJ{O)|)-r|CT
z_uk&wX>4k0x^nH>vkM%XK~=d-&4+`j>5K>JR<4j+@qan!oHtn7`k<I|Ym4UmUsslI
zDtdZ~`5jxyz1y<ocQ&4X59*4^J9@tV_UW|#{^wPJBA^a9s8c4Vr4_z3=;mXCroFNO
zAC5o2d-tyG)bL$vqqi^HyxABMn<qd=vdpzEf7YSg=MfwnEF~=sD&z|vA6pu<a>`t8
zhT2)ENojurW66(#d$|vO-38UV%jZ>PJv%pdcCer2Qub4)9zJNQy?piRR8XI1H}BH@
zzh14Dw5cdK)-OMQ*|KG4W}B~n<HPV`GHRLjhZR)6?tZ_|8q|qt<CP98^IN~6?CmYk
zSVZO5tKr7k*VdSrm^?Xae*a7xuXNFsK=;%S4-TfPU+TV7_xmj<8H3vk`TxJ=Uj~&5
zH#a0YzuWbC9k}`Z;Sl%dJH_Xhu3f8pdwc%*E>Z1IKhM|ids0-jy88WI^Uu%EpI_W>
zS9Rd706#;$FKPqSuE8|>+MDa!_3I^KV`DA<|M|SR<mIK1)mKGaCyHu^rM$Ybvhwp;
z^WgaS`Ig1cK(&LG_0+g0zwiIAd$;2;xJtj^%zrmG_w%!}nR$8VmQIhG1*%zp-hE#;
zUD)5oke8RY^2Ne-FRf+fFJHYn1&WPt-@cWUlq}i2*%(v=Z;kT(|L<=xs7hbFcriHi
zv{J#_>0l}23oEE1zW?X!{U^I#uR9Ggep7MP)a><p&G!F!s$cwi?e=Fg)90O>e{Xt3
zbo6Y{D8}h&y4o8j+<UR@cHU{w$k$uLnt3YivSktfPS^j`|GB*W*K(DU>UJMHK~0^r
zx3*?iTTPBjy1gxT=l_4dKfledx1Rt1&vWCH6B9tgNcVqT+YTy&L9N~YKl=aA2wffa
z6tvi(hL1tsY5ykVWX$lZ38Xc0PetLn-S2kQJh#4ovV~K)=wYk)vpt{BRbOYk#q1d!
z9i4V|*3_Gu)1Pm>9(OzWukrk!KGSp}gPbJy-h6g;HmES)yYBssjmopl^Y4AF{qf;p
z<@34aRZ6{a880p@^qiEnb(WyATgt61nVETce#OPbeYW3jh`0t8DKfmVzk^!gGj7?k
z<;lO_@6Vss-#>?yTWm?x+O%(PZc5tKRGhPXK1U~VlS=;HuVFW5F1@iOGuY4KVawii
z-(O$Xzr8*G{XwN)O_TksG`HU=^1ik<di(KP#^-G&N9XS~1&!aWO9yp41>I#XPVW4o
zv^nkUDNsvu&yPpll^>6aZ?5?GsOInM`16IwWz&DiF#J1(>aY#`py9Zfx}Q&X{`qwJ
z^PkV>m#<x`+byntE_~mosh}pr<>mgMA;?*?XP@?aYxwo+*UE1<)4%V!ck|}Vwzf7o
zokjXPo=%H4N<B42rvA^znI@T+*3F;zd|tKQ>hSgFj@y0Ps1vb4;iP<?bNtSt)O~-R
z>QA5P)0wyX?Y2$A3=bL}vLR3ZH|!6{&CO-wm73DX%)TsY?J|uno#<^kpzIGCwk_X#
zv$FomrAw3K|Gsdq{PXd6x$W=Ay+=R|$-CwE=W^@s*|5f@YGvW$V^3c$pMMTi=UwvF
zf0}OpJF@QE=J`*TPLDeU61)=ZpL%CUq35JVX7*<*m(M!|9v?N`dvTfX?4aP_$?bAg
zE8d7O+|U=fnzc2m47{TanhzY}KOU3LPdPbB6_mI@19V<XCmEl!P+q%s?axQz`)7D9
zodoK3gT@uq?SGzJ6S;ZWn<xEuK+WxIk?E;dSA|->+wr)JmoNY3CRP1?Ka%{c-)^~6
ze!q6*%9WbdqBr<+kqTg+xmH`>$S}P4{A()8?7{_cP_TevsrLKb>9W>kPo7NnKX=yr
z{v1i;w3HVY7VdsK*RHl|Ti)GSr}cKPS#oQhX~KbqH4z(?%I_4qPt%D6jd?!*zW;yi
zu^!3EJByz`djuWV5@uld!GKzD)-YUN=6kwBP`T)+X!w$?TTPRX^;Dk!t3Ic|>74!l
zKXR+I;{!!@{&>_~{PC#x^tn#@rp3?Bh`56L?m;V4o}HQb{<mMC$j^`c^>>&{85sTq
z2CfZToeEmJ0}WILhA(CPHlIAeV_t6SF$bTV<pbj5=X))k^n8B39lLBvz^m7<gGG*3
z?+X@jjjMXOR8DKj`db^5-9dw!bLxJ*lr+nUxM|67;W=t^Az^-~)>IMKiC#-5ZA?DC
zZ0F9(>&y4;+xNyM!G2rX*;#XnPHCp5GaRTpjWTC)VD}93{ClABde>*?=KdDE^2JWt
zJkQ77-92o5+}v~L&Vf4ESF=oA15=K42=3-xB47PxW9oCJ-ynP1+S+0&9=3wY^v^H-
z>vz3TVYsm#vgjY?`3mu=Ua9l%Yj!E!y?a;Q(f9rK+}qnq%F3Xfe$Wuwy_(NwMO-KD
z+O-SRcnaVDEA-~fFHYIl*PR7T8idE!nr==z>*eh13{nW{TY<XdZ2WRDWlDQ}qNAh5
z^yB7;YKJY^z1vz?&F4g`c-)N7=dAVH<*G73ttzx&da!=o>ebqyu0yZ+y&3NEwO<<K
z&ON_dT3Y(_&*$^!FD>;BUK<uH;u^LlV&cl+<<HKV-}kAltp&C7SFhW(>P<-1O3>WJ
zy4~-*qNAhbs^4t<^8UU(sMgin@t~>ZrFXp7|9^i^`>{0GW!~?9!~_cn1_lO;18?r^
zH2!|CI)7f>ua}#GtG0f9ef>FTOhs?+mrFge)@JelK2868MA#qHDm+vFcm4mZZ)~b&
zVyT8UN1|3k?=~FfJN<Ne{JeAL&Vhm`JifLRGz+x8=Bf72C+hYyXBww3+q-u!sPZdD
z%>jG*|NZ^_{7&(C-}LnKo0@x%Md$CGdhXo0I~9+6Eq}k+{JGP=M(MarvCqHT^}qAM
zwXV0`P8Cqk7&L@t^YMuA&Y#a_pY~fe9ck!HrtZf>=+N2c^Y-yhlC^>O3coec+t<Bu
zVR&JTUKZRIMINY^a&F@R4YGkU_OWBf&dj&B@9pii{Pkk-X}`t&SSy!Vpuu79X*wq#
z9qrznb#+yU*3>zL$0T=tyOsU<sD7Q{R4-M~a4RT&LEg%~wno!hlHnH%TF3i9Xn5>Y
z?e%+%p3ke!JJur^T;}((?A@K2vu4eT-Ok4^XJY{xdcGO?MG;FSvOZ#4P9!Lqf_jRe
z&eciv`Ex*XZJ;so3k#jgZ(G;?`T`m%m>yde>A98R!gthM^n(GE&_Ep{(9kT_!S`=#
zuE$mD&Ye3K)D>`dchB4Z_Zuj=xyux~%$hap(v2H4mMvS>BW<oX)obaSn5u=-rcJw3
z^Z9J>W+5>K2Ek{ZE{-8H?P{y~tX{29ssCX;MFm##yk5V5-x-&xm6?~9rGk1qkGixk
z-MaN_UwhM>f<v63%wN5NkKxz8MNw<RPWLe&ffsM>P6(6+ioAUH?p@=od&^g^*53c`
z>-utOuX<3EwBo}9P<zMM*LS9Qe%#HOUzDuN-<^p}pF0)Q`q}Zg?{u)g?bO1@$5KyE
z(*@P{#kVq-Ki&8Howu*A@6DB8jNrv88^fFJsHytH#2w%7Rf7fqZGOF2%>Jdot~z{e
zSn+Y$a!~aKYTVwdd_GsE^h%)R`#qnFJ{}dXU(hVi!0_WW>S+Ce_G?$KPF0^*p@isV
zZOgd{Y94{I4XF3#?(Tkbrh~i*>Xa>G!{7NR&3=Y&H}Q1SP0Y=g@7!q#@2W2o-|=i#
zwo&G#B|dX34CVj-IDY!v!u}N@TEGAJfdlj(M;1fE|8&%z6mu2k2zSJ>MxzfA!NHSN
zR)(#XG)y|OF7flTXU}A+-)z+ETJ*%JYO&YSNsBasR)!dry}5C>F7MUr*Qd`hGbo@n
z<0mZjo(^hXp1!d$**Npk5}lYG2D-YSVUx&hIgxJta&wE%S*rj4yZ`_9O~KViK*O(@
zmzJ2Ao2MV?5KMi3!9C~B4ntX4*~q<BrB>F~oAd7O0(SyFu49)xF#q<>;&i#14+nds
zOtnA*kKl17)TsEtIH%;2r{#+U&6n=oo3}Q4`!mqA5_CFY&xb?YGYt}*^7ec@1{(66
z%T;>}6x=s&&V+OZQr_O$3hrl!xW0Pz3X~l{^OC9Qm%2k%Uj>aBaEs}j08L43DrQL7
zAEIfEl#Uq|=tpeNiv^7&%$hap%j@g<;86n=&?IWw`FV4HettfE=8bGn@6y!N6x10x
z<+l*D;^8!Cl;QRI{dTLv)}8{5;Gehso^q&#^X9J7Y|!KYs0IrZ0nGrK<==}b<6?NT
z9lZb)2Xztu{{HU&seR#1MrO7rQ^VtKZnev~u_5Qqj*V;f#4V3nJ8iCmJZM51)aO~e
zSo!VSx0U~XJ`WBKo($?A`TF{%KEKEvTY5Eg=ciNJ#qV}LPdhWiF!edZfjY=`YnWFL
zup6YEnXx8%d*1c$pmydt>-T3^#bYLHzh7sao0}_XS(MV*df_){Eh?zuhEBwsJ9iE=
zQDXV!g0peqqa!gzCsje?-#<P+4vvnFF4Nn4CAr^r+Ct~{XE&1j&ptUh**NRU3fsE4
zu0<!BSh>BlSQ_@NU18<N1#<-h1H*&byCs)>cRrmK4Vt6mkuXsBez!dSoZas?SFT-K
zrqPvif1fSrz+y<FENYkUY_q4q^M8eet&5qtGI;s4xz74Q(b2Qlty|Y4X{^@U+Y1^H
zk&>1!{&LZM`dl~ppp_x_%KgFl=v|`}!;SxF#Vz;RxV={Ue;m~ZHJCwzN5RW{G_6;L
z-@s^weNmd~rD|$wYWc85_|latQ;r=wW@2i(6x8rCVPN=Yk6MjXfBf;dfBC|NitTb$
zFMhwfyQ44})Xche?V6m%>)2~+A}50e0p9TZYQQ<da3fct_Rfw%`4`i&85sWkLM`>)
zxcd6~zT5Np+?Fj{R6IfD6lg;J!vSW?uUCT0Z||=7_-M<vZOeA=-raL0C{$}IXhh%;
zxBi)*&*#tgum5#9RsEuSNoncR>-+zG&2xUae&4SwHh#G|A0HoIzH+7J=VxcNtwH^o
zM-mE1k=3yG$LH$*tFC61y}427z&CUMbWrycl&C@7(;hinD_>vVpBMY<rszg*n=;o;
zzx;wDd+MPUPEcwDjRpL9|Nrm)&!^-68G&*>XhyZ>ef529>xpr%8rkJei0}K*$|GxK
z^7q$QZ(rZDa`Frh^ifBU8u*tkU8?&1etmsh-Os0>F4@&A)6MDU&wY4!7&NB_D)K8|
zuibv?+!FCuuU>hjr>BF;i8;03ZvH%?ZU-7=e0tGc9yCf|oOq~Zlkm&dX?n4<{{NZ(
zzZf*hCTX1ZWN!JrllT9<y`OfhM-nvL1ey#5En5J!s5YZz+5`U{!rEh}_4nJHxBp*r
z>(;GJpx)|J?f8=u6rGJ~e|-VP#Lk^N--LK=0=0=tN|rz-!a!LI)U?RjI&0UiU7+Is
z>{;;0$B&PXjS~(uY?}PCHE+kmHc;L9_U&6xSt6zvGs9bduSxK7zq8!>dnRxSt35fP
z+^=IT%<xMGH3|N?diC11v<nLyK|@@S;pI)Kr$0@e|3_v1?>o<nj?0!mnUUP5X+2ra
ztmMT770<0vXFCLyjdE{oiDiBcYJPMr(%3m+U&7s8r8^(CNrQ4o-QRx(O4qMmor+u{
zf(Gl)_%OWKjG9FEw2Q}8D1s(nCq4OkJ>Gv3sJU8NTDto!=zP%r?O)A6`x~d}L{2)|
zEuMaLRp`nPEz8F}#zk+pUVqjd|0hXns@J=n&*z<)X{<gyrpOaCd0b{>n{#bV<V=&y
zpjoqL8z&v<*i`&tF{r2g@9%GQPtZts!hwc8pH6A-zShnw{jA)Gp@zeCYt-6lvd9DJ
z7o<bArrPGE{Ck{xul`;C`Q5vBS8J`mj;--_?b@|7GYpfj_g=4m1)8}?ogO=F`@O2w
zEl~^BXJ=)ddT#f9=bft8Ydt4*3af)cyYj<9_RpXdu%HRKWxlgF)&2c7$(wOOei6z_
z;sbFyQCn8LX|YSZwIx&1Fv(@zjz?Wvwrv9y*zb4#ZxQx8@$>oo`_83bL_y1bKr`G)
zN4p?B>8g#HmzROph54G_odT*VUaek#?q>S@xx04l5^<gQ_V)JY%kBSW-kiyBA$=#x
z#)t;~rxV@fPChv~`SiI3{kOMd2HSmI>7V-a)Ks<$H`7659r|@2yFtU%Yc`)dHAOS{
zlpj-r9coXKA;60H#h&TVX&X>&aKHThv0mxTRbO9i*|zPQgCxV7dbEt<a33^ng|yI(
zk&gv55(iyQpmK7WZgfz5{Csw~3WeqKs$S()TU%QfpH!VL;lSRoe*#+j>SX!8&vR=*
zb=v#%6B86ctACF5$wrrP?G4x(b@%b_K3VHackjjq2{OFdk2U~!VLNCc%<n&jDyQa0
zZ%#X#cb}b4W=6N(E{(%&yxJ={7#fbCbekFE4}k_f-tYbX?B(+Lde*IWX^)O{{+zx4
z=j@pByQM$R=GO(6@i8#`pO5Ose@TCTe?PzT`MlZZ&Yjy7{35yT-{<-1pp#qQ?Rsrg
z_2q?$sp(U9`(J_Ea&88dNiiH?M4#;W66+e6^5w<Fn|msYZ)$!q)Ya9^%*;Ib?Ck8~
z>#^ma5n52eXTI-aFKDa)v~c3nQvF)ZzrVlhTThL9gns~^VS~Nqs;gOB-*6z6?+m}z
zfmSP3KAjr5H7oQOsPDs9d*kzY`}y0pZPSU{V*xtJ2dzxA@d{ZP5+rgo@BFH(ujJ1E
z`%+n6Uhe;t@j%^C@I69s<7+hfZNEjd@yX6g?zc6YtnPnqMd0F~=;+;`srgL_2b(5w
zz0}Ui&Nj}tuz*L#qTsr~M;yhK5IE<sFjyq)Kug<8gI4Z&FSlKAvpM#n<<hNNvq0&4
zWr)_!=kuzK($CGQ`80X{nOUaUr~KF$ZmdTgXkn<jvnlm7s5A$SY~9?L><${f17*@<
zJ(7}EB`@TD=kNdfEvD>dDyY)&TEWU-QSe0@r9sJH@xf=dnXa;1&k4|^=e29sdL)gX
z*?ymo)T4TE;3>-ZA;W^>wx3QY&$Ov5x+%%P@MoqM>NMb&T7H`k4*Nc|>VpQ!US3}x
zpOuyM?Z<)nMm2m47p%Xcx}afS?#oL{L7g8^vmdnT2(-%0+uM89)vRf{(bGV)zjKPu
zX<AR7bau9RK6nVH`1!fN99awuH)dn@^%lIhdbwnB(FI5LrF-|<MsLqM`><Vp-c;@I
zG|&M5!&Y&l#6vBhF@?<BTwUv_LZMny!TG+Vyu6;pl!4*R*?s@RrQzv<fq~&qXX)!}
zsi5k1<x0=}b$=(R#Ky*YP6}M?miq0@P0;-E%+4=N@ArH@XIIZNpPAu{4QfqSqtVR9
z3mS}>tWsK9Dru155LfwhYV2#!g2Q9I(x*=?7QeN#IQ`w;@Aqu}ez}~woPps(I%;M0
zVIipf`1;z~+h0MAuAQIHS%V7k^y7W9ps|h<6P3MnmTU)28-rHtm6VlDo6E#-U_Q!<
zO@;&Qpvn_8rfFUN&Sz3g?boZ7PbRttg@;e~uX!X4>JRPvx;B4mjAwq3h%2Zgb#}J-
zbg)5KGUGRWti|!7=^zI|7t?{3prk%$VEFJKHRUGE2kkKdEwEVFF86C+wK?*%`U~xU
z|K9(%`~PeG|5@qtYq94=Mg~3~)PCWObW>APP{3TibZL^x%}uG^uU^0Ye1Mt%$(3OL
zySeWl9qqn+>(;Dy@7@^&y<Dm__0;conq7y^^D;Q_zYa%PkHS!Ue*XQ=2=GKR-{C_w
z3GerO_Pfc+z_6$LyS*ApiNwIrz}$pdvNA9*OhRqNGkARhIfFa?hZCrLsr&nD>9S>M
z{rn6JwyV)*(7*WV@A=>~ujbQ9m6Na6@1Lgv8X$P}>Q&k8?S+qz$>lHp9=)q1^PKhj
zJ)luK(5TI!R&J1ov$oDkJv}Y;%ZrPa&*v1MI>*9b@c?sNouSryX^>~2$Zp%!VXLcc
zeqVkLo=0?-F95CNUeL_vRb5>T8qYq=Z*QX=zU~ZY4c{SdeNb0%=f`8xmv7yQD$`;(
zz=&3OzS->BEjD$ogZ%cqySwfb9OhjK&MEa0#h_O1Bv4-(R2lsF`I&bCGsBk+|Jgg{
WzKy-8w^#*~&pciIT-G@yGywodN`CzS
literal 0
HcmV?d00001
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-precision_score-20160908-100034.png b/Code/MonoMutliViewClassifiers/Results/Fake-precision_score-20160908-100034.png
new file mode 100644
index 0000000000000000000000000000000000000000..3a56169ebbc54882c2118f01b4eb1b3dd8cfa6da
GIT binary patch
literal 168171
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@vh-1g8w(>jL#=NLBWZ)#h#NJC4nQ=3DniTlB<
z9r_C*qO_(?-It}e<IAq;X*)$Zqx4p;T(NUOhxV*l-aD5!?abE5&{LRmU%vEx|LM8h
z-{aQZ`n~V|`OjZOjMLN3ow>Q(^1FcG-(KMhogMf92ZQ<oVL^Q0;(ZIox%iCe=wK*d
zvchMC;HX0|f@d^p(1V2fAu?gg6qd+o8*^?NE$;L8@MzFEePeg|`p#sx{~`+)E}W3M
zFKF3+zLO_Urmp(@Pnbu-fMJu)<5yQ#r&^u=e`vGP-<hj)KYaV<wl(XjkAU*s8+m{8
z4MJtV8vWX|tSdV#Oe`hREhc8pz2j51uJ`}qFCZ=5eLb$4*MFW(VE*mR>HH~?$DW*=
z{MD|1<*D6<*Xw4+h3qt6#`i1#!@cVF2XEe#ym|BHdMmB}8eV_bhDYjoAO5%SU)h@*
zjnB@`UR?9@(}YyX*xhBdR|Bh_rbN0$MBMP+|L(MewdCR@o9f=&Fx--PnJq6bZ$hdh
zue2FU!mjTkE->)r(}%V2+<1{&>GY;!_RpR@D=02@uBfmGTNm?l)#BxjlT<t=eL2;)
zyxz`p(!WCatkrg9Q&T1PR(%cPSv*TYP)O+0q-6L1CI8=+PSbpy>U{pQmc7<|lgvrG
z;v%+WOiYrvs&au-SZ&Xf8-Jf0hwiJAeEL50i|@6y(e35;YsD266$?sAT69i#baqy*
zEc_9lvdZS?rcX~-AJ}L0ce!=Z6OMg<zeV>*8na!yb}iNF`hTy=AO8E#Pg1Me*X8*k
z`FP*a&FSYSOqlTD(z>7X9m4I5P5#f++CR;V@2C2{>lJ~gg8VjZ+H_&5w|GiwYT|_j
zjvgK!7k-{=joVXS6uT~@Ox~`hW5o&$8QUt6z182{oSc~MRX&%U`w(6dzL<aZPpEqX
ztWbNgf2NA3hlfXl0MpN(KP}4N$(ZHc>A1VQ{PB&A$un%Lzpd_5Vpx!UeH{l6Ps{S<
z%L9)eKYo01`TKh-Vs>r<r>4`>^^ZS3-XC9TBH}rz#WefcgJym^hs(=+<4a3A{s}Jg
zpWkPgd~89|(JuYJxBj>EpHlTaw8V4rh5hyQH*Ve1dZ%u*b!G7KM^{z`Z`i!KdHQtm
zb91e~uUhQFvfxc^?V|9vkNfT07B5!5SNHp^(frr-sc%jd<wwcM$w?R_Fo@~L^#m?<
zJ9zr^>rnTX@~a~^r&&~g(}{_VjsLaPTe|(v<onrwCcn9}Q~3Nm+r!J}*LBUat={+Q
z#RdB*>o)zn>~H_@-QC?Y%yOmveO+Il`KEg6drertbeypGFKz$Y3!b#Ndgblqgw=cw
zOwkP9kakuo=l(v~Nh*o&?(AHjQW~N9?c28xU%$5Q-McsNxV5$Q;p^AM!@|PU`Xv7b
zS5#IWyng+AsJrvT{(gRj2aEgds*V~e{(Ao5!-t0T>-Eo^ITQD5Ypa0%-&sdP*T>10
zzq@nr%gf86-~S6g^7vo-?A+XLZgD*Yb#-=bF`Wdv#q~X#zJ2YCTiPwIpLBg)?2DV5
z)pc}rPuJ}GKXv2l`r@7Sp>MNua&$g@{=6~e<fQPTzyC$T!oonV+r0U+_x`fX%E$Bn
z#2vnJD#&kL{C+-$KaAX36W493`}?cZW73it^>I(Dxs+hQh!3ff+?%pCYOB-QsI3Yu
z2PP`JGcZI(MovhTEG#VCQSni!>f0Mmet!NLGiN5gzqj{Q^85Sy`wf$i9XNlU-^|Rc
zps2{{^|iGVXU$smxoUOzdbf%Si<p?0gxuWTRiUdF`OmkrD0?%*%BQHvC?)dPrqt6W
zeSe=$kH4_HJU?V@lxSF3SV4KY`(n3VgQO!IA|fIy4y&rDI800J-LdM;t*zXGf`SEw
zg^g3Eie_C~(`lG|Ou^hdTstQtL*vYuGXW719rgcz-+$G~I8{6R*o%vcC(fV0{(JGh
z;^%yJzg{R`Sry7%R#v7Fzt1M?>Z;a8W_BfG<6!MSeX`aUHYU4QR8*{3e{-p~_?uf>
zy_M$(Fm;RRI$d7oo0y-^Z*6UDl6y;}TTD0T&w=o1sV%Lo55K*=UGe#>`NOAAS&NH{
zd(;0uIVtQj+l=?$zki@KzIU(fEc5)n(A8ltYxldZUz&2DfpJ1=<ZE~Spr9ZDIk`SA
zQLO`~PH~B9hq+{AXo%^>tPs>QF%j9c=BHQX`FXYzQY9y=`yV?wS^eU^+UhC#@p9X?
zZR6nOb#-%VONz<6y9?xjLx&GDo0*w?`2PJkC@jyVcQiCGl)Sqm$<8Np;MdpJU+wht
z_4zL^_jmvM>uX|mHn+RGdrM18!r57-QHkBtF0NUl^X1i5?!3Ib4coT4O;+>Wka}8d
z?)Au>MXFI-vsynrJ$?ArEvdS?x*ty_`%joYeR+9|e%zjpi;LYCdrnp>C@*iHI#qPf
z-o1t?Cj`D8e|S_?U0qp2gX7)1cOdhgo|-BsDA@RZ|Npr4*>+W5ID(h?IPR_b`ryS2
z4t93-ko9r0d#k=4`uO;`=^-^$)rHa9^FDn1*x1|4D<dl_C?nJJe&27uk9SsW`uFE&
zvCljk$*Zfw+qZ5t1;yU_{r{q5^DZuOT@k<EE+;1^U}cc1ii%3c+|?Pk=GfQE#qKI;
z?C$1%^XAQkMXudKuiaIzua7_e;o;$jj~_E@YisY=wQEuF^K%weUsgCi54^cCnLQ=)
z*pH8oO}8yyzTA0Q>WrB)GnXcwpJ%IhdQ(_z>Aydfpz3p~c6i&;rK)k&Z%x0vy)7=T
z7jt3Px^+hU44<E!b)IWgnvk2ztFNzr<oI!Ab93=~_wKC-TRZDq_07H2=22U-SlQXx
zEv&2-Ik)pgY1^#6C8Wr*XYXFc(?%(g*DT&o)ebkP_>gdAMIb0j3knMz|Ni>=@tpPh
z2mk*5wpzbl-*b|Hyga|ZzkkiQo9R0WAGh5*es5PP_u)2P=c}ti6Eib8%gf7M+}$5P
zpI?8CD|*Y@E6;DPn6c`dzrX+S2M3!2m;1?DSXmu9c8u-otE-2foSgje%}wLAAKIp5
zIzM^-{BgJbK8N4m-adT$mKPL0J9aGaoo#kwTW)mc@n_GTCH?sD@WZE1O<T8`zPhrq
z`RC{7uX*Z!d`K*LeT{eCym=e8Y;k#dYU;;txAPxAJ3G7T`1UoW$(~W$a#sEeoU-ZG
zhD7FH-{1GoGR;18?i^oPSy{%N9fr@&&tHGzzQLCJi(Nw5C1&Z}um5lB<mB|=$rBc7
zY3VEL<K-_e_Yco`{^f1-w5bc9E?)8ENs39%4FOPs|M20!0>|cp-`{eNZaDVktgq+&
zGXL=S_^HqO<?WB1n5Z1M)JrrXGIF6?uhb07;$@Fadvia3{`}dn@>2?^7zhgs>*(%2
zJW17C;k3~*pP7p)-n_lNJuxw{@p^oH?E2@48Fzdx%1H)=DJv-{oHnZa`BeO9@!Gh(
zQk!&=udE1^y3Kns-Su+S?QOXkS67M7nKQ>ktx7U#KSTXj*Tst$KYa6s$J*MOg_ZT;
zarycyGq*Eb{<=~~SeTK)w(5(9;hcSsCr&!H?tbm}xo$uEJ39}aooz09-04`1Gy@kG
z*M@|HOe}0{hb~?e+_r67#*Gb%`~H0LUi*Cg`)VfDRN2R`4`0}~-R`kc=pI$ipzqT|
z|AR8dWHn!>tyxzUJcTArnq=}#eE;>gx3?>6X>oya_NGlvUte7{%(|lS<jIqaqrRc?
zb~Qf)<ZC`Kt_oY*RrK^!W{>Y|vs|wH{QR2FXU*Acmrpl+r}OGque5=&vGZcL-jcS?
zo}Lz+(-y_gda7nG{JLV&q+?%?_sKfDxU}p#e`lGmw2W1W$Mc;$E7yOKY=5D3`q;kb
zKOgtogOc;t-&1y#zE;xI^n9PrDiNmkb*(**rn>9OOL~fmj7}V1KgZXW?}V)d(29Hh
z=iBZ4j?T`;>C?q^baewaCb=FtcI?si`*oMC(l1(-AMFz5;NWQ3ySKLU@wr7jnast-
z#fI6}bXwZm7Y8l%di62p`MJ5?XVRaapYI+MGslY8#>PfKNT|uRTTHXf+;tao{np9v
z_x;wZsja>GcS73PS&6T%tXwLWeP-{w+uQkNt;<}NdQDA8O=b1>_h(^a%bFTmdtCJB
z>0PV-Nf{(Cv<SQ^7jpd^>-k=jNAmU5EBjSo6{yl>qx!3Y3NY@k_$9v#LMEy7zTN-#
zoAfNx?6z5^*^A=$*HwIa!YLyo!@v-}KF;;@G~L3luR^zETx6O!apI59=j}IEeok|7
zaY;BiNmarmW5ThYY&;STsi&tMJbRY+;>C*v#l?rWW?$b>{XOr>s!;F8$xj{?{sdK@
zYa)$LZ0hlwYqc=z>Z%iG&mPU+|F^A`Tl~>vf4j!s-rip~9vx>s@aSl_Vabbt8#iw*
ztp5HERMA#dS*4ws(Rg;Y`QrnP%&&fHOSRwITb=y>-`|d&o|fij=DI&0-OtRi6fS>%
zFVx>b<K$#@{|kF6i(_^cvF6^|;<(&zu0o4LSeRH)P|$_F)#Vk{)vFKt&#@2;Ugp!d
zcdzZPl9x?hQ?(u*>y@^s_@J=w_dDyB_V(3>zrDWBuN}S)Tx48}&Uc)ovL=4NoO3(h
z(MD$W4K+WD*8WIIPhV}nskg7MP3QE74<8s9o;-Q7Aar$@Mdc?IDYKjo$7Z&L8#V~s
z-k$G1->$ac*%`@Z^%U(uuf?j~(;mFte!p$`a&@cHS1jS-;dgcxvoH6X>l73ubg%OH
zT%rDO%c3V7Adf#gJNxn4?e`8{T^+u$>}}MRyt`8BesdgprA)7YS~uMd4Ge$&{eGWu
zbCW6)GxJqpyW3kb7k`#oI@7XP%`E?352zvxUhcPa-Lfh3=l5^Ry`A*_-rg0lyUp78
z<@=8J%O}6RwH4HI^P6Y0^2f#ev^2F@X1QGQ^72QH98s{gmIk$urt8ISD1Pp@CFf?4
za!pK(%%n+^K$RJ&VD<C!vnY8XaI9axf6Eq=CCipgvzY1nv|YaLz$8`g3#&r4Sy)*Y
z#_TMzsQqQK@87TNoO^pD-TURPM#N^lxv_DEU9Hus(A918Y^y<~iFy9LBNLU~H<Z1-
z6{P-w!C`mV+X)jVF7yj8E-o(pD<~wyR9|0TdSjt;`=Y$NyFgyHv9<kpT)zInart_e
z|Ns6LK0L(gGt0#D@tsvA@2;*Eulw~<-Nn`Q;GsiI+1J+{ouKHPkeJvwS=~SB=clJH
zE-Yk@+Md@tWr_%>fZDcgn}lW2lCT>6_<cPG4mey{A0PjB;-^<vR|`r?c23m}UsV15
z-O_uX&)fg+*_M0z(ZOc+jO*)U7cE{~`2L=4&W#O>2M->+u_2LJNlD4e);~};YKz0p
zqNf|Ouj}=4mbup70kx4kIy(dZ&z(1~FYD^6%qzjSx8*vQl$gx3ukY)VwO&;9_0^8D
zw^DUK9<t}$+{F6w<;#o<3mT6ZhiUnP65b-$?tqO+t~`=PEKg5Ob@uY&0{PFT{-4a#
zQ&TTnxp6f5&NfSYe5|*ltLu>U`#sIZ>E{woPt&!i`l4}ej^*OGuR4l~jIXb+KfW?}
zIk*da@+2q2mH+!nUyDhZ=k>Vv%PDGUaoycjdie5k|H7xIL~DM(-QLmP@BZ`CQ{Jj$
zUO72A2Boh;jvPJu@NvKWu}e$6y=~QujfEW@9e0$z7CUt4(1qpx@}T4xu{n)*Th7fU
z`MMvBfq{Wi$2}%3`M#OaC;IvM8HUWDqVMywvlkaSv)k1E5@F|)ad2{C`u65#^IYrl
ztS5}lr?x0=+PwMWzu)gcZMEFn+gfMOmd?Akr_*<~8OVw8^?$cMa%tGJ#|D%iEG;cx
z+}&;d>C>kTd3UY$e7{${qu^oFwU+1k`+l-HxAA})<5s1wT0q(S(a~-XAD<)3d}kN@
z_>fppSvgfAJorkl{^=Qp$q8v`Z4C_!A!{N8EiElQyuA-szu()w*u7uL(lS!^+J(A)
zy-6yPbM#iFzk2qpZC~wgP)i|td*0C-8<RICALn~>V<YpkXZ3&eGo61;OHIxA8SwMV
zW&eq@W`TNpN=8OPzrVjferc)q#`N=YGIli*dU|@Vz)gdb7s~u!)~R|r)z#VE+M3-y
z+dN-MON;B-vuB|6<km0On|^*?=HG^{jk$FtB_@4xwp}Mqc<lLjOd3=|-rrXXsyS8E
z)ROM(D2yuf@$qp<OjNvA_d9p*yiUbJ<Iw69k4RaA1P0L9M(XKliPzRdMm_iP^J`P_
zl&~mRP&M1|r_UsnHIbXyZg0yC-tOzFUL`4%{$PD)Wn*LGiIXQC+xcVz*2me#?5hEd
zh`6StEJ?a&lsZ4_`nuRxKVBuBsBj6F&wO@fri5*k$(*@!4GSJPSXfvnn3{?@Iyx4V
zl$e~1c=7Y|b5M>0xglz6*24Vz`!;Oabm-mP-GcJ+{qyU7dA|P1th!%a!!z>OkEMoN
z_%4;lJbC}VzomsmMMdSn?c37KY&-$;l}$`U4#fXmxwH8BBFAR77nhcHSJhwK_hE_W
zWP{90Dm!-USm4~wS5RIKO5+CA-*R&9?h=)hl-#g+^W}=L%F0R(ZtlZ>e}BKYF4o$@
z!eT+z)m2j81w}+!M76^noSA9-;qzzhua<k)6s8x7YK1t=Hp`tbYgX6g<^GHP=2}Vp
z&cC~>b*^>!BG1WcQr{CZWb-?k+4&dw&Ne%7{=9ohiAhaOO~IohoGoo_ul^|7I=@<d
z>6l`}yHELNs^_uu%PDARa7>#v?Zv&l*7Izu+f1{sDd_3(rKP34xWB)C<@qBMj50m`
zUR)Kbz4w%7;k|qJJUl!cs;aC&8RN!{h*J5WukV%J`xcbGz6Pp^FRlz$|MBzZ!#g{R
ze|)>0zp?PK8>nCSI(D&&=M39wv$A)0I{Rd;m2`A`KDH}#8E@gWss5&OtXH~ynr<|x
zg%9dxu8Z5-HD!tjD3oTK=eynBmTS6hW9n(KFE1`KS5{VbbaXh(x2yf|;2`rHn@XY0
zX=g9JYM!BVm+`@ii;F?UpPWra!-NR}pf>%-$Hy&-pYf>q&T1)qd~9mPo`v6c<=!?c
zd2xZUudnaLm6gI;VQV_xyvdnkTP?;du6Lw`Q<z~&Zp_0cPg+`9Smsz1GD(}~xja8N
z_v%mIulcd57cOj!^Ze@#Yq2O989Ks7L0t4(R6L!grLKLua^*^=X{m{6X=>}@_G+~V
zfI7^wb$50Yc0JF&xoN3^v9a*|`u}^6eVa2!=HdcJ=EUS=<#%^>F21*~;$xDc=Ohje
z4gr37yDJvUHf#vEv#ZqmZ+TGAqzS2!D(dR1x7Yr7*zPnfbz|mbwY58JDn2+oe&5o<
zqIi1Kjm_!(RncK#(>83`BGT8__vlb7x75RSK3OdlPa)?vo{Kl+q@+OXUTO1dJB~d*
z-tYSL)z#LWJ9qA={k`qcXU(k3%Y2<CseF9cE}!-G^!fAR{c^TJ|M%AZE>rZJv?6Zr
zt{s)1mxcX!eSQ7v|J6skL|^@|t@{(9T-PgYF1AUhd#ZMLmdtvu>x|579ZgM4Yd;@9
zc8n`>+R-;RH=Ay=um0xa;^M+#Y;0Wk>B-5U_mQP*!`4P=zLPdcXqb>1nUb2ia=U5P
z6_1F>$j<8T?=oBeKkm0T`Nzl0d-c@$moHzw`W?M3XXY`x(0|fqIWvxZ+p)t!@$@DM
z<FuY*--4I>ae8}uE1upo!z454rFry|Uw?mp7kA<?tocy@61A`2XVtSRXKThqr^h!y
zqa99@R6s?2Z^_Q;@9RE%`v!7<PY=)9&nGtNfO<BCdZBVz_xJ5R_HC*6bS}?HF5C0&
z9@(6J-sGF_EECTYn{@2{|0&-4?(4B$X(fGq|Lp3ltW}_Rb#CXodgI-rM@m|ut5oLM
z)vhY_`M4$Y(`o(v9G;V0N=mjo`uC{xz|+&yw;p=({CW3>4+VkiVk`?EALH$<UA5`n
zmdxOZvuCd^oLBVpROhFsr@KLQ@|2V8{Bj)O;o%S8y<0ai&GquL`2WAAA1m#XwN}&7
z(P`Pdd9$1Cije2F_5Wgi{P@9<ot?cg|Gr)C=R12UgG1It1cs~#a5R+l5*89t($Uc|
zd1q>15MYvZ#bd|Lot-mgNPPV^S>2z@bJCI7`TJJhEBpVi_TiH!DtGSQJ-V~_xyiZO
zUtcm4)6><ZOtY43j9q!={q61k9+OnEuCH4wIQ`F`8bKi;B^6Jh(A8mAE&M_0RK+tQ
zA_6o{n*B!FIIU+wYUG(&rmL@HuRb&1K7RF_RW@~hA`H(<IbD@gRa5IabjT@ie_d^2
zUf#OE{#EZX|NQtUb$nay?J!VG_|9Io(N<a6dB*J7+~MKjAD_>!&zgIDLVEHktN*8_
zYIogM_nD!P5_#=~zC_fr(!eb4dA8NdE{3go^6XjHuF}_B;^N|KOG2-1R#a4!N`3Y3
z@9#s$kGr4Pv?h>GKW2x*sj1rPHMO-{Z@t>G#RQaHca^=3%8EH1WiGX-LONArX;o;)
z|MSlFf4@wwnyvVE-Xw`xdXkcoPLos~zJ0s)BD=1JhJdVf*%dASwlBJ0mxj#ePK@{|
z@M!%m=SeDwnVBm?+1z_17KZ9`Csy2#36J4TT~+4a@!$V5pR85Jly2+tcO2^K>Vf-e
zDnI`DS=^i4llwWo{%`5TxpUW+u37beTk2`CwY8zE!$ix<%A|6`Jb5~2ue_z~eCpNZ
z<^HXcCr|$H<;xW*aZvd%WA^NBHQ!koIp%8fJtwK0IdkSnpRDyMnRLY#4sLGYO*-92
zyT!9}?r+PTZKc0&h27Qp_5U=_oIUIM_t#g^@6yI{fl|BU_SHm2L_~1#^YgDYTU-AA
zURQE;@;ckXM=pw<lPcct{qB;OxUi}^F>xWNk2N7Ra><e<E4IJ>JkMeJroNA*hRgVj
z(qcj`-3SwHZ)9fIdgt%$Ej&r3^TC6JwZD`tEh9Z9so4E^z})+G)vpb?x3@_p|9$lA
z>}>UvNKm<ZMRM7S>4xvFq&_`0)oGH7VbK$hwYA3S=R`K?bnEZ`6O_E$uyoJ5O@TEr
z@tf0pkN)}o^ZESM?{{YGydo;ESaLmFwb!}i=ysj=m2CWSYXYa8pJS;E^4?slQjzuX
za}-lA-T37kZmHQBWV<qGb(rqa^iO}k-(P)v*3t8-o|8cJaP^$UNg2{JX3t)IWBLBN
zzq?ihENuGl`Sax)b?@)lK78;%K}T12>n-i8g|0KT?tcFC>B`gktE)nn#$CUCJ34z#
z-iy6uZ*PU3*rWp*^H`hQHShR@!q#=0;)3Rfuk4YszNWph-V<I=EDQd%Nej*kQCl^2
zJE#WCySq!#$Vi9*G=>|pD#TNHO?!KL)zz7c{N`G<?ydf=WMvhVt!l{5&h9hIgwub%
z-O*j8udm#Gettf`=cEl4ACr2g?rqo~))lz+K&+Iuw)WcGzP`Sta@%Wu7Cm|XT-nYp
zF8QiC187JxAwPdTU$9M{ar(I{JKDBxHU0JNZTF!=PBOMtA?qt%ckSM}(=sPF_iFv>
zd6(x{7Js;vy*{&beZaz|U;Fp}d?xKNspaM6<%e(Gic+pKPCL^ezyxahUb8$kRl7ZM
zb6V!wlDTu|_P*cuo3B^e{8+nu-HOsPJ(9+tfo4(duot!G+l<W3!((*!yy)7yl#`F|
zTGUfbJw3i>&z}8wxqSYW+n~YutgBiUR#uN5_uF6Nh+iLP+bg=D*Rb%B%Z=N&lRrH<
zS@GjTVrL@AF()?l_}l*tQI3s?jWw+MQ!zI)a;cZ-+8x_-Z;MUU4!^b|oMDD}zMPJZ
z&V(5=R%~7MWk=!T2XEeh2T9jgfBy2NrM0#7+P7<Kqd~2y8~bW^U$f)p<~}-gDUWCL
zQX`g(>x@Uk*;xLaiay-Nd-(J7^QK|H!zQY5f;_%=@7`mTP0h^{Cr@tX6jsZa;_2@0
zUh?LK;P-cT4}X1qUG#BC&D3jcywZ#E@9(Sl@PP5!`uO-qd-HB?Vx6uZ?^aV|)70E-
z`fcyGTiFt(St5CNcP*{ZU&_hP@9yZx`0dS2W`>F{F9bnNYqQ*23MM8ZnVFfdHta5Y
z+oa;j!OtI_@9pR3mY1g|BqS8DInB4X`1jAB4?!LCkB^TRzPqzi=<&oUQ&>DFefW4>
zKHH|exVYG7w%OVv$<^QAt&J-UO8xNQpny}x)4!KE6h%Hy+q%_MM^~5ED%?}W^U#{e
z%>e-c4HK2!r%8PK_4T!fudnOVQ&YDdVq;-hQ2zejiF4<U@!S7dP`YN{`D0f~_pO`y
z{9g5YTMk8$*Q~Xtw<w;Ps=fST*s2@1Z!7ER@qK@P|M)~@cai?NX1TN6?mm0+WXZbb
z?sZZ76Am(g`ijNR&t1)09lbTH)o-p<;^k$&pthuU?|RKw$EG{3jALymzh8TO!57_o
z?=QCRdpT*w3=Ypp26=ZZcI@1_a{K8`J(k7K944t8-FD^1zNLyin(_<+!otnJzP`@R
z@%Hd&SiD#{Y)!<%ciW{do11Ulw5{5;_TSIvQeW54o-J)v{;p@v9GN-x^>NB;Hs=1j
zvNBjST%`W_+;W8$(8!PJw*341WM|Ht`Qqy8>29+_g`6L!b$vTAVN+ISW~ZEO)q`(u
zZ%0)Y{QUG(Lr2FYCudDnbmXVV>3Xpjmif*$I{x$4*6bU5tIb!1ukSn9%%0tne|?>7
z)b_l!rE<aFR<4WR-`CW{R8dtmO~UW~#}2*wwclmAxVQx5<=0<b<~!dmws23%i><8!
zKOS}KKY01F6O_^y>jw3@hZbu3U9V<Jp1DZQYzd#y(;Xi2^Xvavs(2onr0TupRsW0`
z5+)fJ9G-uDc4p>c!)yBQwqB2G7GMfrA9qz-Pe1w2O7H1<u@7Fn=m6zXCyw6QlP6DZ
z*s#H2ecWD?ZPLNVUq60uuo={2t=jr*Q5&x`o4maI(Z@Y6`6W-?_-<onX7=h|pV!-4
zTS2{)&FSYKeSCbp>iEJfMv>Eg9iGA`XVdZd`T50_pPxllF0cOnj)RZy*w4?;H`f2J
zTbta@Bf046ajj0n+y#60?oFD%	H`#kIB4=jK|sXJ22pa=W^!>cfYJ+a;_@R)keA
zwOVHpyyW*X-`NwUPHjCm*LrdK`FT~b+bx{mhl<88-LtGjF1T0wOX8b|^-KP#!j}%r
z?EAU8j{(NLSik$^WOe2ruMb<OtE+Fxxhd4l#_RO{-rlW;_Wk?yx@)qJv5^r2gQcbA
z43o@B*Zx_TzjNSd+?;-%i9yc3uIKV{|HoUe#~Ht1KEJ5y+ndhH&(9VXKR*X@G-#}5
z!2*Sl)nUHtANR}K^F3JK&)QvFRMfP8zx}tjx7&-KpIaEWw@T`_v}x9o(w?kM|Nj2|
z?!C9{^fd4&t<QWrS<sMhNQg*NQ`3b7j?8O4AGGt!x2bq$Twgag?z_rqBhYj}g|D%(
z@z+}Mr*Gf#hKGl*ee2#Q<LKzfsNxyqbA8Vq8-{@8t5<$~ds|$-_KV=3KYuQ)4%Y|y
z)6vnft5CNysA}fy*@q7wc2?edZoYlLy8pZdo|DzO<kzyXvuoGgSgRi%9^NBoD+QWj
zSD#<g^z!m@?Y8PKF9h{scd_W}>#vn}XK2{4!GIya=QJCyl!jl-nvj)3e6m(c{{22V
zS>2-amB^htcRt)qpP$((?sVYNrArI8{QY)2f8v}uJ(Jb_AN~9LTSG%5;Jvn;=c@es
z`@qTh`SW%;+o}brr>B9Y&zqZ@<F0@D{Mosgjdw%QQ?Hb?v_-|w&vEeaxjjDCEBboH
z{rdm1pc%QSC@E0?P~CstitnD2mRKap1e~*8)xTESEN8{m^+`v&82-)T3H`%vBW0Ge
zV#azWXJ?Qj9v|<|_T|&^3O%2emZmlBc(=Izs@FF=IymM&4-^s;Yins?0Zo+3T9tr0
zx1cO2C)cMHx+>xBu2PHoe>Pdy)~uX&W#OrIhAWk?k8}!m749y0$ked^Raey3td~8<
zJB8I57#tlPqkc0nF(u@!`&}<Rb!%MM%PT8|kM+rRFLZ8Cy1gwI)H!WxYI^Ye`SS0U
zJQug+MsLZzEw*yy${X8qXP?^=JoUSnZj^?f5jQvY;qCY9x*s3!UmU-`PU`oUTC-*A
zKFizJ_3SKuo^-g4cSpfPCONyB74u?3_S}(-TE<)Y?2II6#QFEPw};QpHvjnLW$;(K
z*wTibJ1v=*nYV6Rt@c@bZF6X<f~{?A;iao{t;<2hJGZ#rf&2I4(``;ineX$tdGqEB
z%VM={d3U=`PuI`(*`e{zhxg_8DaR(1Xs%ozzSxboqO$Vgsj1o(KRzhFdHeSCo$V$q
zicg(gC#kfwv}EL#7Zf;vqObgY9H=|}_4Rf09r^#1rfj_%Tv$>PGUvha)qUpM&gNfQ
z()p;&-rgQGrTY5X+8uR&ckNmmzbS=N#q-bvMQ5+Q?8%SPR)GpxE(T^co&(|WwXIK{
zq<rO{%=q74a?1;ejXFPlu75T&Ik#$GbI@LfKUeGZ?G&$0sa<9N?*}u3*W8$8?<-uU
zPx|FCRXf~msn^sAQ>TV5%Z}esz<BfK%@1F{9-X2Yyroaj>A<a9QHHjqd({o5XueLY
zeZ4^3P*3aZLg#kSh%9LSwXi-ePVU{kz1_dRzt4W6tF5hlWo`8KBgL!LvhM9JUw@@y
zPfuaG=bANZE-ZHEulf7+I;j1yYtP?5pU;Da9TqKKyj5+URP^!b&z{e(XJa^87B(%F
zg`NHJr>Cc*e)FtN?oE7CJx|IsE937C<pnqEZr!*sr6RZXbV}qa{@|dci-Yd-|IqfA
zw<usZ-Y<WB#syu^pw73GgpzL`U}on_xVNX$qU41DXy8CDdF7+RzrRW=Dk~X({QutA
z*7M$X;=6V}S)(7jym)qA-&gxP>F=+v8Mn4*f(o#(wNZ*18XkAw2N^!y;S`@L`C4+;
zdc@+6f;kO-u;%HPCegVnQBq4qcQpS0|H01GRCMLam0gJ{o<a3JzaJcAX1MTc!UX}}
zStbYn{r&y%r22eNjsXq*D7HA9on;DYvaP+^*LC{jNk)dbtFNxyw)#=jluIrKSC4qq
z&Rf2BuPvXvT~DX5x{|6Yt999%1_7pZ>()tFm1rF6m0oUlznPssU|&t;-Z0BECr>tR
z-n{vd3aBL9v1`|(cXxM3{r2*{uI%3TB1U#w#;#enIs}y;JbTv0$}N`g@6S(Av#(*l
zoyA<!>}iiuxK#c8{JL(RJ$u&llJ`_~8yg#u!>@1UbqFfEB|JRT`s2^%^M*M$42~M4
zo}8_EH#;$L;jj0<zrT0pXxv@?epP*oQ|F~6OsdLmJqPwwehygZ#OmVW0$RB9>gvsD
zda<jvGTpzkv-siT$IVN<rzaijk(^;yYjx)ASwT_JR?FgNFJcn?T&JbJxwlt(vbz7V
zTU)aYtG;A#C?@3R_use?;WOLJ*Y@F)Q&Y7wE-m3KDk{3L$d!9b_I19#zCO@wVp^Ko
zq{-lk=cBJR)@H2IiuYP=u<F~&um!qa;r{}s+K29Xy-2G+`}(@8l5Ue!Y^uJjIPzJ8
zlY^sS?b@|fP1n}N?haTNW68qKzSwK3mVi^j^>wi;;`Um7dwZMR-rj!4?%ml(e6OFX
zcAYA=ebT7~I;RT?3j=NZzA|eaU8$BOed%22x)@1NmE+{Zv@Q2`+t=6EojDr4rfNN0
z+;8VpQ?uvZ^Gny)L~efY{(XPoVz-xnHVP)cW_6y|tNHrR^Yil;gC?Mgo^ZUny1G4X
zZ`HxGXMJrgbrlsI7vGT#TE<)Y;({V*eyctNRIL^i6g23ZwkUkWVwQJjMFjhfUAwfd
zHF~9neSMR5e%@MRxnEPxZ@Sj2@9pQu2bv*RvqlHB$YkTjjj#S4Z)WE=D1R5zo1W#d
zf4NE9l5V@F&%WQU2Z<--=f^+Ww{#zmuDt8Z+tVa&nb!-Ry7g}5lq=gAO<r%@wB@Jj
z*UxQyvR!+tzdw4te*du}ox+8`zvbrK+QRwo-@lAIJ2u9Bht6<Eg*EP1EBgKG7bw|U
zT3QyAlpF!Ixqp4hEO~n?G}$O4^3%+9AKMoenl1aEcgk++s{PSl+I^?Iu$H^%I{)_-
zQ^wf)*{kQBKH4qrEh8^6X<nOAs_mM5*_2m>6Yc)}c+4*%A~L0FuY12-rjLXEt^e0t
zO%-=93B42=cWlRI6W97LPNp|aH8nXWsVJJ6g(>GmzWQ<L$&)7zla>U1_WhU)Dp`7G
z8@{jP$+R!MxZP*k(tif3p;ptTEN>O)s=Rff>dXwYg1^7Mf(CuptX+F?nXmMZA3qLU
zyB20Ec58R}dbfFo&+e|&ymVLOeGc#5>*n_=m}i^kADd%YyrJY}kWS<#7AFpqtScOs
zm-#xszP6TeMp?|l^_zOW`h1j|2rovwj&Z(#l_D<x6?WO}3iCZO$2?!IjbA?QRb`00
z%d}F{6=`Q@DXOZng4WlSy^#Q=t)HKtFV4Teub{mAdc?x;@HwF2?OR*3v)}Ho{JhM~
zB6xMcLZ*GcUTN2Sy&4W$(01w4r4LW1$0vPya#Fx)MR-6_QIS(wnb|zs>abTTCGPI-
zDe38p7c6kdZoSjg#B^tOxqsoOn#`A0Nk=+_?6+K*uHsqo@6XOhc1!si7#GCvuX}NQ
zy?jw|ap8vtj-c7q&Q8$szymvrpO^S~n6|yTd1qg3bm9JWZ`(F(*>dE{%3wih>F$lm
z$CF-NSs9hs^~_gw*@@Y!lK=kwTlnQg;NtVl4CU|d9sTq3GiZ=Y#-<`5+jOm{c36h2
zvZv6!+V8P@e!ttjqx`+xxA*t^Lsy4A{QZ9a@tMZy1;4($3<?h{DJeNJ$FkTU{hSPF
zqNDoTn}d&zc7Hr79uHdbcJky&h6c-Gc2*C4*jj*Rpk*%}US5}?GE1+n3ia^v(z^Wj
zwRiZxz@^2RFJHcR!QnY+!lX$}-`?JyZIbuw*)vevyie8|v?gT9(xr+91_EJWVXs1)
z%HQ4Ltgo-PsreDGIxqC-+bb)BR|GHbyZBKfif!-Sy{6wp#l#-<+y4t#KjE9w)isgA
zpo!_kL`A=OHl1^=%ai{7`C0M*@At&?bkK0ntS?nxUtM+1$<diKY0`(Y=Jz$~4E`Iv
zW(~gbQ`$TaG{Gt$F24NhVV3QAcb%M^njU@qs(HC>mQ|_NJiFSiFJDTwWL$JgzW?Rr
zWzdwu(Z}!Z?q*kP36owKk{0@Z?(EswUtB5=n3O&~{o!hO{K{}XIs3Xj$M!k5^MTeN
zMjd}~`@Lqb;me}e*L07HZkc+@H}coCUq;JnR=hwI1d@+kxBiUXUDn#(&MqV@Y?ye6
zMMX_*(SijB7F<2w+Zi2sTRHiZ7Q>MvM-u-0_!zOb$`mx#RBW_jBWR*(?qh!E$2mU#
z?@p=Jy4sR(^~o0Tr7vo=dSiVJ{Q{Rhm(Jf4_~=QE>asa=a#vN|xbW+e$YZ5iODiiU
zj)m8?p1QvLJSVg=aQ?|x`itu$XMtvVR|GO^YHFT1d$zT=mp5!}6l-{RxQm-xR!i-~
z$5x@UrcBH4GTPQ>s+M<b&vQf3+EdUrL$YUO)FhRoHn|zLX+F{xb$==%qM{z%*qHp`
z>({F{${!!&eRFqrcyjc`^5v<L>C&gbIXs-9qo>CuB}HYPO=Z*JcK+ng&(20{NMN)o
zd(#1GgNCh*V(>9vcVYU<V^#1h{UzzddMhS4H)K~s0|Uc>eYL;8aOEc_H}5Ka{pj1<
z+ZL6dQf98tPfToVXkbuLQ317D1e{*X30U^%{d;~zmP?l}Z~gZ4$&&|1I)yiE+7$HX
z!2K&(*VpwX9&SrK-Y3h@z$<OG;yWt~ivvev?(J<;tK{nI>qW%GwCYamOg}FtA|mo)
zZ<YlEs0P@i^Lp;OrJC{kZ0i31EnoY#wYAlv@R3XBaVrZ81tle>ZgKr%4UEha=FVMP
zF+VkMb(n5MboApZD}%eVi{IYfeqLp=_OI{n`RnWJ*Tn1$DxB0jcdjgG?(FZc(wJQ(
zp4s(LQBn*NQ>GogdFvKvOwOYA*Oqf9|Nq)m^V5inn;TS$u08qu`nuS|Pft(xwz+rp
zs%Y%4l7p*4R||-VwRun1dw4y*-c*C{>Z;Jg2O60t&YQ<)ZEfBAX?;~&?C!FwR(iI!
zcb5pKd42kP-d_9J>btwkohPaM`2Bl&#hz7q2BrJLIr;h78P>$?6x#pq*Xm#S3>@6t
z&Q(=bLBYX_o|BH*1t0VM%Jc30{q<Y*m6e^J^G8T{-Jg0fHL`90etWk*nNCsdFb9r>
zf%da6U0E5Nn48<nDXgaPZ1SS>ZkeGcw`?)-nAFn7D=j6<9(?U5X#I_f=OO9*Jqx$`
zue__fZi!Lu3h(K92XEet%>GoFSy=h+k0qa+&5EtH-{0M3SP+;N`d1-%nm=gT`qWbI
z=?b2c&Q)zSQT<x&mF%%=#lL7xzv+6hhqh*457?R&dek%e*caWesX0FdoD$B@vyHl4
zTwJ{M*V?vkXX9HoZL2<35tzGg=T6IeHJ^QB_Sea3YHE7;__WNOEBouq%g;fN(sHU(
zaw2;>I~!FzJ^cKReSUs^W6@Ku9lLfZX=!;W-|0S)-ga!KV>27WzgOxSfnBpTe}~MQ
zHxIN9=;!C>r)$<tT5)WhSM8G3;p?^fHu8k74%4-;w0wABp>x&R3BMOj-70r&JD*Wm
zjLPXv=bnc|#TzRqFo1@zZf;Khx^LdTb91fPJttjBU918cNddLrKr04Thp#_2O*gvW
z{XN?+Z*PZZZ~EFTbA9En3tn$?5)&6D-85d-cePw5Xv)g_pCwi=G0OD$n|NlkhOcL>
z{e%CXOCpc?XdT<qI9)HcY5x5A*IIHET{_=hy|y;`v{)qb%tyQ0?qvsFyLOF(mlrgh
zW?1$n;>pveFMGTrkBR=O5=^#5Oi0T5IjF;UzxXe#2vi2Gl(PTxff>|Jm3VeNzW(Ul
z-Q`#7_y2ykTfiyd#013?XU|^ch`!Y2swF8YS@G-3%4=m;3y-QF61%=W-aaBC0@Rw0
zl8^3}Hs{;9bLWfu`~P!CW_~#{(|AYm^S*0kp?A91tq_)%=T~I0`}4v1&W=Lo*E1H~
ze)Q;(Ld$^}hRGkEoD}~0P2GQ9!j~5pC#Y~Xv+-WCo|l)G_u}?;ebDIU%HZW%epP#F
zei|7W8-KNmzr4&Bw8HDnot?qSzo%#hPnbG&sc77F_rt3~PkMPLJ4Z%DEJ!~;uj0dl
z#%rgZsQb@5^6BYm-?FtgH>WS&ut6aCSWn;`d2#XfLx-GtWGsUo@4UaeoFBBdO2soZ
zuJva#zuke&>E{g!9yoxO_PwqD@PM&T-X7E_(GC@#FY)`uMddwTuSG{qZu|V{lZZP1
zv**uOhriL*%>_+fK0PJ6_U+A^H!HrqkzBKO?bb)(Hukyq_sMp4cB;l5pHfs*v?c73
zRn-@bur(2k>gwu8J3CxU-`$b4v$Om0>9l@nT}|za3yMdp0_77E69t?Setmh#u)vh@
z@4;qvP??(&>6VeP;@C!JcD|O$lZ8Pu*UIjF8FQnrFFE-rDJe;z<$(J9nnf4&o;-b;
z_~yn&x4YAY#KpxK>V0o$y#p;_&6>>c^q1rh?fR3O)>P;@S5#F!I?Qi><m_y7!}51A
zYdK9oOQ%6=2xiXgJa6~gC;9%v!|kB#V_|JQeOA9$(kZL^w{J&(bdS@E-?t{Oze{Va
z&-A7HzJL4XR#vv{+LO0Oj<|evVU0c3BiX!Xk4^6npSf0{tNG;YYAnv2J!_bBgd=88
zMc`|jpFe+g2~Y1b+LGtv=hvolx}&>W`{N${rgdLz>;70Q^Pj(N>b|xw)n69o?^^N8
zHF&w-)riz>8#V~Y*Zojz5df_bzk2)ht?gH)gVwM<Jv}}9Z^ro}ox-58cDveND}Jv%
z_T_A;q1pPWTkjel>(2Si&M(IkInA)<M*(Q;DF6OGwx_YqkJB=$m%N_UHYHS4Utb@z
z{`|s1=Nabt^Uj@Iu<T6wv12=fmU@9Q6=>z3YqwbDo7>xRrOV#lT3X5*{C%a9lT*R_
zdwYZGOIGUq`tlOAZ1T)}d-?0@VlUq?ulkZP+2?_Yv9WVajZNO29gRPJRLuSQuzQBd
z+N4ueHzrt}m{B;fySw{b=l`dtr?;zkTK#TUcI#;nV9MY7bz0TbkBdNqi-+6!r&slR
z85tRYmikPXAh7q){+`10%n<u3&;}))=xscZR=)O~?lq5Ro9Fk<GR+39m-F!Sym({z
zmvbJX^3JbsOgg5xYsN3ze#I}klaF1IUpiGd8MMkR?d+@@`|Itmt&Lv3G5_tYtso9)
z55R*54~*hZ&oH}i`?j>We%zI+`<8`|T#oKCH8T_A<Kv6iQLymQlDC`I1jJ41leIo{
z`?j>Ere?&}tf_(5O~1r_e|vlRjcKCivzN(*zc?&{RQgmEo{2AIf%gGC?6t$zI8;<v
zfJ*Y3e?OmRTw5bKXU?30x3^5^Se0@u_n+_P=EipC&K(AZ{Cz*wK#kz1r>8G=>y>(O
zXQ%O<J9i2mALCuJbSY>z&kTdareA-YIC@{7ontASnVFe!aS`jPu(e#)*4A_EYNevL
z=e2fsbF=Zw#U$0N4q4d*8Y}zp;UQ=-aMhO=jOOO%Z*Fd8mz0$J@cDDF|B)-<A1z)@
znl-CyqO!Y^fq}rjeV|UqanMT9!pCl)of=P0OnkK=_tut!KR!M-EPWMnWnHXv?5+~W
zrCw7(?d3Q3_scgnHvV`vJD-7JZ}s<M$9knVrk$0#vND)Gc2`NGiYI8Pl##LV#ns{Z
zUtV23y`cKnqi+2VxAXTWK04AFv9HFmsk!;#!-tL1=6Mg^+}sRW6c@HGX5~MLJu33G
zUj(=1-|zFAYqc=_{Jes)vSSCE*(c7N*?HkYz*^2#`FlRHy?OISKtN!@za7>0_tjby
zJ>i&TlG$`^ZM1ZW{x8t@!=+1?42qxm$XJzdoSkicyjR*Bv^i%>{(U)Vvz!K<>3_Ee
zgXUaTtkC%L<8go2Z~I>_ltHU*Kuz-3>-YDqSfOE4_eUc8+M0uRcb9)$U;mf;>}+%W
zU>P<(nU4AO|0KD^bQ=2m`9bT$PEFNTwzifIUl()m-rj0Kaq)ImZm}s9a{T=KUtV41
z1})iaX5+oEEjRkflP3zMrlQxbUCX$zfDyFDlkfkNlft0EiK?%!GOnx;TotmiX}SM=
zB~w$;=jY}+KR-7&aC6#Oq4kxYo_LnLy(Q{9%f#{Rt*wCzomlVetriD4_w)1fpb-`D
zLd>L>mzIJC=XaI9ZsQWwdH|~NzP-JDaj`r9QT|o&EfXdPsHmwu`ta~D2N&0&UTO0W
zf4|>%=4d?HEq?giIX~r^kH3!Gxg!IrGL@8+F6^tVHp#yy!z*Rd(A&!kYFo-!7O{Xl
zdUm#XVrpt?!Jj{W|AMCRK`UnY`1mqzZCP10Kg;OXT<h`+OFV_wUTvB?cP?n9EXeVU
zjEo%o{O)tDN)<eXK&GXnq<|K+_RHJreU;>uvyq6e{VEFDE%4$+2B`AAyv!H0Kd6;U
zROIyheWm#qf6p|{76aud7kBr=_wLF0`T0qh<w#7^kMBF$Ev{@~Az^1{2U<v_7rU#)
zcedHVQ>VDz@BhE=+E!K1rky+g{rC0`uW|2{YE|`~wj$hJ540bIgOBgnionGil8^J5
z<lT`7Umth$*4FIAw6wOR-qW*c3-VuVHVmD6e`B&cX#dIlx?h@pbFEnG>+3;V?M_eA
zeQ{x7bJ$MpwLbq}$Nx8aVb@jl|L^yWwZF?irI35S9B72(;$rv02L~8S-rtkWzP2XN
z=G^7WpuK0#cXyRuTp6qms?hH4Dg~|DY~z()W>~m1?d&X2<}%2*pa9BKf`Wn{zJ7JB
ztFr^m0M!2ecJS_9+4OUBE=u}4zjnK-V(9$o-mzZktE-t-sbzw?+O`|dT)ir~Iqj_0
zR~th^!x^AptA200Wa(1S4hPV-EYND?7cVl_elcBgKUm87lB$7$z+$&v@bu^Qyx5Z0
z*Lb&W+je7DskYyIyIwKfD9{GApmzQ2`$5wmJ-u+@Q(#C+$`UL6>Z+<FP#!FJz_2QG
zbzA1;WtlCeTk_Y5gdf<khi%GUNEM|Wx~k>d+uO>js;r<zoANxpvlqUdDCB%PD{$k+
zjW>1{s~_u=<@TH;AS}FC;#|njH9Cd=KAqMFO|mU?Zhr(?Q2h7T*TSElQvZB7%>Uxj
zQf|-?*~NN;()n6eR#LC8tv&qh?QPKJmnl;BBtZR)CnqO={CHgc@z?9|?&s&(K78?_
z<I0tgJNxV9*YE#lRrmAhbfft6KR-T#W^h0o20?3Cb#!<{wZo3gwJtCC_{depqJZK5
zzwi44cbDY~-<kUI_zzdfAa+S(JuZI!<FBr+2E`m`dx@Bs7zZb(W4D-YLUwjHXp6x8
zeYK#ml$zRFP%;9QV{v<{KuaBaB#jNy&Paf^>;wh|u87*IC1+dJvSy7AsCd?m+H%1%
z?24+nxj1OR@%6Q}iTU~KuN&$o--(pc*Vo^Yb(IS=1HN;oC1^MiwDCmyPPg23RW-Fm
zxwp4<^!2%2Ul$v=x2hDhcrP<Ev!kcy$hO?uCWoYh<ENVNU3}`g=lR9yim8__fR=>3
zytC8z)wQ+RC37ZEo_ujzZuFNoH-+a~m%FWv+FJ1Lj%CiB9fEy*eG%JoB4^I;?pm1p
zphHmk!#V5s3mlu-UTu8W$jn~w?M-CKt1Fzd&2leU?C<X84qFq^`0nm*(5NS<U;X#j
z*NL-dcLy)`dw6SWc9(r$K$w`A7-%&zsNA%x{gv?X(NPW#jsusM`xibtBl+gu-ss22
z7fg|;S`XTD0h%OUut1@rx_U8a&3f4ziA$F*fqGG;a^_ce9GXzKTobuh&cvyt^sE2d
zo14a<1-PIhGBGz-ca~|kT2OGXx2>LuNr=a!B|rRk7Cnt~Is+Qp>gf3Q8?tEV3)k$K
zGc{8p#R>}xRYCKA6K9y^&H{~mZrHwE+|0~uQPkEf&?-&P_^4RFy!|z+w4+_3N+u>D
z7M7Nr+1c5FYokmr?ys*e{PUx*bjFe;DvGB!dHDH-<$L@3iWU|Yg8I#ePM-9<ar0(p
z)Yh!d@AvEDWA;{sK9=I-<aC;r3R;G|_Vw~*%eu<m-r`J8PftuuRn5AxLeZ^XPPeG2
zXv?9twzgL_X<mg_p1!%c8Pu{B@ttKN`0m}iL#Ix8g{+MV{qo|Xb4p5zhTP`T*I|N^
zlA19wF)dT4PF)eRbJL4kTUX!MTfIH(Mk}{?mzwV^j_By<#O!QsDf2uX&|bodxX5X)
z5fKrcAJ3jYFCJg_b14TGmyn;IAK3JjL9Sc!?nZ$cGD_CgyRTG--Q1EnIpflj&JEkP
ziLG0=4zyGA(W|SglMXa69y)WzCnYs?<zc<JJrST$VbIdN=;-K&j~*#WndNAtou8*G
zXIr(TFmCA<Pk(>$O*-8tC#!28J9_(ebja#3-|XML(&k4R7@1pk@7}#(<3_=M|Neot
z2qe9|wH35PD*v9%-glv;e`m~)IQlpJ+#EqMF)^oUse(d6i?;s1xj8-Q)|SjgaeJ!{
z9XsY`VPVlRVS>QMs;^mVH!Picanh%E({!U<j`zv7wzs!~mW$4tH*Zno=Cq_kEu4@3
z{QO*X_w{6T|06pJAG`EQnYL`*x)l_B9sT{{H*emIx_<8bd2vvU92gk5$ZM+Bp<B12
zcI@8Wec*t@#*~vn6X(y5fAw`;>~1x?e?O81Wn^@0Y;9XXQ4q3nQpWv#dqJ~gVLy6$
zcm(C-^ybW++uGdRoN;kcE2v33)7`5o&Z{!ib>+H~XU>RBQt51DX74I~ey&q5b{7XI
zMPz4dM{UVi_+#CgCBL4$ySqE-%nU=YN3UHAyK(zAcYJ*O#l6+#8<UQ51qK8Jy!w1u
z)ygXB#3mi9vNtQXu1`BV%V}DwVcHpqxyRE}Q#*hBsCfALwf35|Yg-pDUc4f9_qLAC
zPC-pgO{qlhs=ngq=R~(=Ul$7t3tN<Qv`fj(F7C;*XI$0Q)eqmlUoW_A%dYTn+3z>g
z=X2WI+k+BoN~9QQ$(|EO;g1iApnXH21-_s-&&kOFh2@b2j?G72US4i`uJHdqP|3I~
zqOLUX>BJ*PT#o+j7S|Wsq{AIK?dXq>kGFoizoXEZN7gE&qPm*f+uQr$vuA3%%HC@A
z$=R+Fy>=r#d6m`wTU)^!qz;`v?S13MjgDQVue)w;PVatxetvfB?F&Y0yVq^noqAeK
zP(ngOMn=Zv=clKxE-o!Mw&%}3m%bzmG|+wY!^6X^)2C10uxXP}U0vOyZvA~1D*wjU
z{|)7lu?VQBuKq7y{arr0H1<c~pHe;Zbys)|J5KZKp3r{TGG(=M+NPYJ$y?I2v$!O7
z?p(HZS<Le{?1wk}<1m-WyP6i}RW@_d(<4)gS|&bC%9(Jw=TNIv@PQLyB3x_t?yvvS
zxL*86jQ)wI1z$hj`1AbEVaxouIn{Lr^X?VhDLg(EwDd?bc-fTI>-YU?xc>V3?>jf{
z-i?iliaMp-Z*%E=?KiuBul`xz$WEH;JKJn(f8CeGOBXL*yk-0L>6_2n?Y>iZT$a7o
z)@sgoTXy5bLoG&ykB&J1D~{Zl<T}$Z*-g@}rb5yzCt{{eWzo-H*Z0Sjy}x(&byfSP
zdz<#Zl1py?^f%D!{q^bZ>;L~weRXB!)3y1v*^;(ZB|ATz(muT{_cmYE|MpM!_Pkru
z{wt#TYx0Ay``%sM8-BZfa=7)R^*?_{?<`8qG?98br}*5<>tDZ@Yotf-udCf3-~X#f
z<NoUP+p@2(GfFzrap}^fpmP?Fd+gpn_OLk@_kQO8FU#$xMs7}<D(q*m5agBO^S0a9
zL~UKA6S-;0mMvSROw|sT`;gstrFxZZ^|vW~eSJo?zrHZ<E3=sI{_EG9TbC~f@7lHN
z+g`Ubv(4A%+}*X+XP(W@IR%F}*Z<xZUu!QOQ{X6RS(K8Qovp1tuObN)5|Mi<3V)uC
z|F`LV)!)C>P0f{i=YM=HbFTP8T>Gb;FOG`G>l8mfr<;7NM|17kwM&;SU3#bFvhVMG
z|DN0b-x*VMQZ@C;ionzp6BOBN@7RC4k^J<Mx4!P<<Nf-%xw)xdUR(r+-mll|^`*^n
zUX<S5_ixX)Tfgm!{(rx_{%J<-yEoqc{{ESnnVQaRJeuCq_15maH?gAc{p;%F$H#h8
zpPiYR`s2ex5PrI-TTkotwY97N?z5TmeD$vLilxu*zV`TQ>mNV=@V9b{`;-6H{?k}m
ze_x&b^7YRtnoD!;?b!(mg&t}1bv&|GTR=33pL1`|&k6ajx5~V_-~6st{`$Rparb_n
zE1w1m_51(-eXpJOn7{sq^Up8K?PL9HJ|4Mr?ONEe9?9Ty_W%EUy8FIv`}MDVSLXkY
zJ8%0v=I5Q~cH#Fv&-*@Q+qP{+SyxtoVq;Uq$47D3S6A0rO}YPi@ArGr&(6#YR`Z<|
za_`@_?b9Fk+wb$4X|z-)X2*s%H#R2U|H}8Y*!AxBs`&S=ziz$!T62w=fq{X6&2RA(
z<q!L<*cW7`ou4=N_q*NtckkYP`R2`;O{u3h)&2doCU*C>^Z%oN%`(m2RQvl|-1NV{
z@Bcp+8Xh~fzvhW@<%33cwqGwmChgUU*r3oYu7B=)-M7s#6%Sj_+VM3X*?it^cBioV
zvo7s*CuGa-TzvDGC(7UUYskId_r9lndvh~#Urpua{>dsJgFbESuhm%{w)WIf@%TG$
z9)D1~eD&(oZQHi}d1k&p^IKrwtWII|WfwD2PEXT4Yj<k)so5VlhNWLz<ofg0^?lRc
z*S@db`KU{KR;|o0&|J*U=kuyR9k>5yxO`60sfN4fA06%9oN%xy=gy9g3+#7RD!je3
z(^ytkcBWNnmR$9ljf<=9%S4~E`~Bw4t*zSrc0W_3dfhhngM)~{;6c>vS_THb`@g=v
z-kfx_>rT;W-Iwp)`Aw>M6+HjclarH+5A&KoxxW8j>D%>xFSOg097wJHpZF5gNqcqx
z6f~aO^6t*sn0)-(t~Z_P^G=xW``FtfV`(J+;{f}t5~GU8xA)anyY<W6)t+^8Yj*gv
z^YiDsEuPq4|L3u<O>BO@-LH&gesi_#p0D`*-2VSe^?4Oa-|v>kZ|*-NJ?HqX|F?G*
zr|0c{yKT>7+4m<>r^jA<^Z0|-(kXj>JnDY=;>C;7pR-J}KOL6;XRv&J-LHmY&pj{Q
zy*u}I-fms<dlkuH>tZYwzHdxE-q#~xsI+$N|NrMR{{6oH|JknB>rTJBySsnocMqA`
z@AvEL>we$9|Lh>UyvTe=pyW$2l{7fMaku{!7!@7;dFJ_=wEL;Kxw)W%3lz{c|NnfJ
zw6Ck#pP&Ep)6>lS{PU{QV~hljvobI+czoJFU*`JFn=?;NR)3zGUmZQK>eWh{FBhCO
zmp-w+|I@FHPxjUu<wMff)^5KyYxnzo*3akH*B$GVot=AoTk6?arj`GGKL7lXzusbV
z+S#mcg5M)IrFd@cKQQ~shlhth&;S2t`OV`Gd=Dh+MsCdtHOsj%Vg8>d>OWt{|DP3|
zw^Q}FY<bM){-dkk+}y0LKDQ*u?#Ds?XIFy#eY3N(=hb{Vxh8I}Rc>zX&uiQFnLbF*
z$j%0p9CaVN<DWd89)E5_;^Dp@wSRsbw?Efwes2c1-VOzjA#qhNm)iV#vH0em%HmzS
zc76JJzW!gwef8$!+UxgBTIxML?b(@`XYD{ovNJFo2vl}pmpCF<|L3F6EECPQZ{P0K
zn{SqTYv20s<_`BaCcD@D`#e7#v?}*gzZod`eB1Tw)#~E^f4@JUSN-nfxw+QHNk=-)
z%&|1S9$#OZc4o%KH;)ZDOr?4k|C-EE|MPTw+S^-O*H`WpRCarED|@}{4`$gWZv8z5
z`+whkzp3i$t36*Xd1vP4o?YTO*{J^CpX7II4qUwcX8tRy8S~>UZNA^D&VRS-^}3Rh
zk|(F*{}nwuKmYz4<&E>V?|G{G^G&+_Y<IazmDktTpI;Zd8&nd-RJ~mK^N{$y3C8Cv
z9<P}5c+cl^rz@Y&HBZ=Hf6nrG%CR2FpI6t{P2K<ZZNBHEPGR-5hlg5sK5Ub|bnTj1
z!uPWq-)}mtm;Fr;<WB~MzFlsbOHF<YFv!f)3|^LUW`<$p-m22|r_FP3O}XrEZ+rjW
zx9!z`OTO%@`8@mnnXT93X3zikW%<q*i@Mn!?Eo3^p{?Muuldu}@qb@s$GyM%zOH;*
z&dnkbKb8;29{dyqsbFAW=;H+?-8Gvx8!w+%l_gj6;b7c!`@df<TmF19x%l<k?ayXq
zuX}ktcW(8&oi{h7ddF2fY~8YD3(t{4MyLT`sv$Whdow@7frrv&IT2;=@6{f7x_-~6
zQ~TC`KYrQYes1aOYfnMugxBm#KHg{Z=fmNd28mAl-$QZ_*aU`##m_-$%J{s^<Zk_a
z7K`0_v%VEFNVu@PU}(N^V`K8?L)`i@1wXH?jh?LX_*n1j>u+`9_u2HiDHlIG^YZ#v
z`MMtuW9oiB{cEoQF%LreUc7vH^3LMtX1^sEc$7e1eRIb6{Fz%@vp=t||EvA>?c3ja
z@!RuarFz}Y*?c}zclX@g^80fq``cMwUgrDy`d4+I855q=%RBg4zun?&XU^d6S6*H|
zO)vJ=n`D{EIl<@6zJdtu<gQrQS^%&Bn5f<CZ+rX7W?wYo{u`J!uqr5V+59)AQrp{K
z&e}m06c@}k%RTjUdi=ii%#02HgcdOKB+dVEM151r$w_zWe!t!MZrAHcD%IcKoZOUp
z8dN3r$lKd_ZpyvA?ayQR{~qb->1{lcmtLEJvRclqEt>H^Plf-g-G8`^*L%{OvRj!i
zU%j$&+Aqz(cl_gV`S&|_wB^3KxojRPk^gOF`s}K0XvE9ewU|oh<^D>WkD+vB`s{r-
zmqShcwQW1xCzqG`o>sU2d9voEcl@buZ*O0|d2?p!>1j`Irq4e+xBTAD_f_$K9*GxU
zk1c;XGkxC4-S@t(i`x#0Term%EsLMYynT$EmKYe0OE6j;Q25>~|3`saT+hef-~Zpg
z@B5$EzORm#t9r3;&;P&g@0ZVYTRd^vv}w$BxtgllVQWrArq7)k>}UBjLrxl!dZ45Q
z8|MW^ww()|+n+s~oqz7E`Tdycxz_LZY`*UAa)0&3j3+yv&yzm!7$rwAG@qE@+AXG=
z^-YmMA_i3F-Ok@{8y;I4daO_O_M68HdtUm^G+KJo-69Pmn288GlmI6bEzcZ&@iXv+
zFP;)KtCoX-ZF;Y?`Li{f&z)-HmA-WK>eV-oq5cF@8|448GqkT>dXpW@MGy~eC^(>r
zDReTRUun^WA)>-mf-nTk(!vm##DQ_|1%`-+61w#ZFhoWj1P)+0F&aYfpa3&Q(-1fq
z;KYj2Tm}yd5M#6)0)+wskCxPkuwY<dXc(=_P{U)iwnqt%(dGwAa4?KEKTyMCwE2M=
z9;3|<)bJQ>exQa28O@I$_TS#AhpgND;PDUr>)FQlj@e(?sH!U)BXXRv^QoKDf!1!F
zmOPggCXLc9Ugb?JOI9vwO5kMdtv7RW5PCgTAZm)<F7Jb`p5EfG@+96YvYq7eQrXcX
z-@p6ozV7dP8uw(b@hyI5Jo)!eo%u5l|2>-|#{R6DpMk+ah|vnw=?rt9-U1CtG<;v5
zIcrK#*7+A_3oOoLn5?n|i9*#T+!kEG%)oG<DRY+E<Bux2y92Ae^4XfFo=FQ9L^AJy
zm@q_{=F*anKdUBrzO}TSu`Ks`kQZ1x)G&q|L$D)s)_6|3dP^B5%D}*|qgUsu91<VI
zJWwM5G84pv;R!AcXxC9XxMPT5dQ=u{E6flO?a2b31OYLjxCBE)1;yzgWfvmX*@9>Y
z{&mU3*GqG2`j;#VnKTortMkC4D+h9&5H329yE1cD&+*Ay-nzZj+$+TsW;EN^6=L%p
zA*3OOJnyAb^z7pOjaJ$&SHHaFZIqWLR5p(j$?e;BBEl^}aY%$1Mi>rs6plIwl6s*e
zmPAh15So_F4|NFx!-M9`S!zqC+%m2*mEkj%>diV2mTI^?4>4kw&}iyA`D4YTZFg7L
zE)8!!=#{p4B?n}LuSyLu`WBIZD?`1Qi7@QJHUrO1QPnJ9Yc@PUlmIy^mt_Wdt+ZVn
ze)!>q;91~|%@E-M&65la4BLDzn@IMnXWs6;6<lR1u_ncAb{BMfFv0>^ndZ{&^VcW)
zWSxI`(j<5Hv>;e_q@h(A?%D-Sh-}T!@E=m5ZSXbmogC!#R&uWtU;8{Q&}G12XEHFz
zH-LSRAf16IlGkGv$#+!1CC34?0I!#iK7Uo2e5<(1$oKZTrBjf{BpYU{fZcH;OwBVa
zyB}%=h<bJ<=q<$KARYvtVF#ND;Xp_-OH#TfGDO5e+{}O_)kBK*1nX>UNf4^-A2%p!
z8@y&MJ6U1lc{}gQyi2POCa7+{8PbAWEpa=5YJdPwTyYOEO$;233w9yJJw#$tNHv6k
zAU`{TOhoXpR_9c!<py2c3|j|5TVM<f3A;0JrMm}eoRE?wf!hRE(Z|5Rkl+YcHYI4+
zj~d&POTNvS=W}^mw&qf#Ayly`;KGA}VcQjzlUZ+}6S)iw3?J4_%R&^zkffGiholoC
z1nM6~ROIjfTh=FMI}5b_L|a??=KlKnb91e~$H&*dyR%cqqCf#O?FU{T6940n_@^(I
z{lD*!fEWNJXM{7AG_ZdEy1w4l{`bxEML#|~{PReB|A|kZia@hpbL{K?*{-)OeHF6r
z&r|*9eb(<zY)n4>>9PEOi}+ucrhfvh-r$~w)J|n!VECN2^BV(0-o4ZM`{!&<KmSbK
z{-<Z3jO8R1%bFhrcHeiNfBNyb{CRHuJq3re<E!6p1y4$E-}iOx9E-xF)oQ4Q6`v8l
zz$kVDG}rs|=~J6;H<H88m%Y0)Gr#7sbmhmR;>8aSwMxhRJ{|wh2($|NGib$z=ci-R
z`Cs;lL%j&0X5@oB`t7;>f6Mtl&!lh4zP>K|-1oP)%fEh=1}}`bdA`o<yzTdxcl-bU
ztNF56{w!#c@y`Qx`xDQerLEtMQUo{r+!9mGz+nFV(o*l6d#k^fKHpvb{@k-?X?k&c
zDh_A=|1^F76KDBf0dlopF3Q+enSkb6-`9QL{pW?d{VD7BdnT*Tui13|CB$V=@_>xc
z0%n~J=J#uit;^r-c~@f~5mWouZC%XHNoUWVm9ek00ZrpiR*C=nD*SVQ{U2rf|3A-v
zzWct;y!>8ey8U5P2kzVgD!t6#E6e}%xL5Uh?dx;5x9$D)tA3Z6C!d^6#o3<=o!dV>
zo1Op6zy8-{-5AIc3#dyNbeQ}d*dr1^emdGMzTSF&$;+TgPwrK}-}`VYXrV(~<<qHm
ziqG3#pL4(V``w#&?womgdiwp(@8vCvROJ8vIKJM}y5vOwpRCoF`)82n0UwB26hHGh
zH^;L0>`jpCy|Ni1O2E<bpqc*}XjvD?x3Rm+Vr}bRE}gy!v;yGAgJ$zRW$*9pt$aE)
zyy)Sf)|y|J=kKekdw8hz&5e!9^M74ge(&>p(89d4uU@@k|HT9I1c<INc>m4ep#8s(
z{Wo`)=Pz|-(Al)~7Bj<+N`Cu41)zI#o<2D_IsE*+y5Dc-*wtG7{{H@a?f1LWRes*S
z|8LsOoN49vDxbglEm!$uVoqM(v+(`Du3p`I_Uzd?R;60ycT1;Bqgcjpqs@j<HlgwD
z?d|&Uzi(atH1~atI_NCZ&j*<KpL}_Fx$^DS>qW1wtX%!R`cbF)rz=`9?+?P(0tEX%
zy&4{WHp9egQq5EC_>+yy>_u;GY~1tj*Xy5up4-m{Eq$}B|5xKT&t@in{g1<2?ZiMH
zgyVot2HAvzf1jD}Kly$C|G#V2uYdmO>FJxB)BWdFzuQ^!u{(axuX(c8Wht4NFL!0n
zul;tj=6&^jkb=*z<NsSd{%8SOYEt~+!NIkEIN+v&7zgGEEMV5zVf}80^6`H8^B*4{
z&;Kzmc)4HfXO}PkH*eZBNm$+Q$&pUsT0cnp4WtKz#g2UKKMY#71mZw(LbT9e>q-uj
zI&D%4sL*9#U|6vhI*4!;V-TUiQXSmJOo-0L+hYAc5nMMl<gT4^>FD#<o@!g4e@U6O
zE!JDpwE@w-I#3U3u{Nmum!7}=njBL36RJBD1`&oy%+qj~g{~n4?Sbx?I%}Dy=F)FH
zalGw^d)yY^GKQ8Nph>mc6Tm5RM=rh=7z4wOr{JE(f!xLT5-`J^B2YJi;enY6qW1~5
z?7*SORY(I&V6ldu#H?xQ1G^8b0YYGz2ebm)3Xz78n1i`5ur~N0s$t{;M9&o}gk@5R
zt`6D^Y7{XrFc|E|9f!}FAVE|S?t3}KX5Nxq^DO_DR}(f&x|yTpglH^uKveB$4Du46
zzg~Ujm3fyZXWlB)T`Gdq^K}46GsA)ESt^lhZJD5<z`)R;y8+btf%Cx(EPXe4p$S&N
zAm)78M04qtc^6kdESPaIBcvMK*$+Vu<_ESohCLc`y^+htYAwY0>rABa*A2PQ-T~Og
z3VB3lzlx^aO=#v~h;Z?}yktsHwcGl(!-;N-1K&#K2=5DKU|`tr^$uj&_J=%3pfbD<
z#u!@p)u^}k^IRqdhK9Az>tsM)Xpn}M5qtcXPI=e96S=ZD+F$%~?t2ji28JBl?~sLK
zcc9VwV43fvHP_@Aw+r6aWME*pQT6UP<BWKO(-ziGVPar7a0hBQ$R-8`gK+Hq{R1&*
z%DgmVYxd1c399z<UzT}$>y#j{kIsl9r5px^;;cz2Tfc#tIyb`b^tgV=m%W?ex~_=v
z@sG#5CKOIcD4eArqjMzjKo++s^P^lBoh@G5m6YllOnxyQF<QIzkXh3Y&Y%d6rUf^6
znZxu~DCBFtzIf=)qkS#fJF6Dod~9v}`?q7)8H3Z8b>3SVe~yRv3{<qKV3Z0{DDDNR
z#2n)>!O(?SmSpsS<{d!#Avhs!>69x`)#qniHQ<pvzVSN`1H+AK6muGw!@N#rZ9Qi)
z_xn7f)kl+NzAaOBVrOVzht&8GV;C4L61H9wn?GMQ^7}mF$-c{8nrsaNIoU=5M8Xs?
z99X)+ujmqJaBsuozAB8atvN9z9ZCd)OvW;LjhszEN*J(|hHglC6s!izY)mht<N-^A
z2`oi8jiP498ZXV2TffaSoSi6P)R+8TlA+)s-(Md8Igc3%W+E3H3|1OTQ?^E>&pKD_
zKl5zT#xrHR1=lkc1n3=>oM&;I@qrO|76|Nm1_p+bfb86dw<0H%zPB{Kkuu9KI9qfb
zV?hAle~8IDQB2+yrEdAsmWkoV={XM>4kTK=!l(%E5>pWla7e2h-wUcs+SgB+6qWs6
za<f#M;$w?%keMN9uzUd59tYNVX-2NSHgnnMd%<a2BXl<3&2xcF3_+9~hyw@Z=2cs_
z{rIDEa@Y4cGjoi5m#^H)1sM#2sA|{?9`pXE_*zAMuRBBxLVi#uH_cnV1BE=FtETGK
zYxj)POnID-6}|yY2|l=F`K8+L`)me=JL{eIoB74aGruu@4k~9E+QD;P;tQrsx|%gN
z)9Sr#YFPJCquXzfwVz~QVEDh_biw(Tb;1k{zY8VT^$K4<&hYz`C8&#bKoOL~4zRA+
zx{ZJ0`AKW4&(A!mcDZC$)N1}oj0_C_9NX)m8jF8iKi2s=x#92AIiULX!30qDec-fq
z@|-WA9>4*|qVt>#4F4bAl4yv123C^rU-m1;lwuw+Q;NlRPzPYY1bKO`-TJ*JlK1e0
zLYeCG3=9eWAnPF^4I+0;!5W))#8FBlhUr0Tw;p|-?s;wR^D`-vGp&5rhBojq9H<2a
z0>~H$E;tGEmG#3F-yvcMvaA`ioH$wd9^MOTUx790#UKjD1FYJJOneoRi5EgfzYZ`W
zoD#DkD!cnUN~FMS=7UzJpkYTd<fM0J`{H{LlMoKR!HZJHgCwxj72v88BnQJ-hUjI!
zqr_){Ahgt44J)-64lsgq4a^LN>h<U;(hW3He+IRbc(WI)PiLT($QBAPpT1d3oG+n;
z0o*kVyO*QK&4yr9j~{qHC1_LBT4UemdzYWd+8B|x`)<btMuvagu%L$+_G2zK7eCmK
znkpOYVKw0Y1;n`+RX+m*Lk6nz7#OfkonYt!4H82f3L_UF(iK!_f(oRdfpS4jk;4IK
z`K;k4n$Z;rOQ);}d+l?%^1bHfD4l6H^URe>82F~4hE4-}Sa$BmpOA{@CZyt7z+A8a
z%`Y(vN+(Uer_9i>|0QwR3?m&=tvW_?85KhrbHT)rY_AOd0Gjk<2du1q@MvmKQ1)Bf
z<gmjADKf|J!ABDKV6(prd_J10tFKyJF1c5IYK>TT>bBdx&{=E-h6hZrhS7rqSE8b8
z>ZYaKtv=^tHgnnKD^aZQMuNBptWn9HJ@?6y@1QOPI5T}a5s0V`z#<F`Z`e?4A_fKq
zG8^@SKPE5-rceuVP*Fp}Ue9O%LDL+V!cx_vb_@B!F&df-51f$8{f0=abs|GUGfIab
zEf7ng&%nUIjxu+CCI_BZ-W?vzC*U}O6J+L-Nsr-;zJ%-8i@p~=u)>O=ei7C-8ORX@
zCt)QY!vlZZMc?!}@cRDUX{(c-?_smp2CD~OGiP8c;8~EUc~Gypbjh__)yLMfC7!V8
z+nWvwZ74nv3vSnx`QfgSKqcl}MbI2h!gHL_V!aIBxIOqh1Z4Pu|KM?(gm!3u=8x;X
zIou2k3<vDM9gywzGir7~>b~zgLFyZ-q1k?i0aW3>)myiH-+u1XeES(S9gqreFZf6T
zhC9xX1a+YG<I@<BX1?Qyl<?mITH6_afJlNAFx+r=2Y1fF94N6tdbGHP1_hYHQd|=m
zK;Q1H-~Vq``Tbh+e*1qF(@v*?=6~<(tNs0d-@C>AcBd|0ylDGhuI|S}(2<h=4-|o|
zgAobWL4CUe&6SUP%|E?dKL6RXv$HEdomBt)uwDMy)bO~I>GNx+J)d9y&p-b61!w-J
zd%xd1E$naearbfg>NguD#Zmj5yS*CtHXPsg=hNw$KOc|pEPWl8cW=*3mCC<guYdk>
z+5h?6@_Q#ihSk>}1FaRAJbCiY<)A?Ym}?jqsvm%Q1poH=+x=8Ie*Adl@3-6E+m$^%
zH5GLH@6Siw`k(HW-@kkP{Lh!m=YP7LzyGYMFhVnEU|E={q`~&vS@Zi(RxY1+YH`2a
zuieMzS3aA$`~3fz*5&V>92Jj0b9Ht2<`})tx3bqiy`8^*ZmvFx5gTrU>d6Q1e?M%O
zFM4}xYqi||vbRz1?(CfWe*gb}{PDYE^ge^uQN;iM6}~QR@2vIveravbyL;;E>+7Gt
zUXOqN@woi_Vx$$?pt1I5mKO}wZ=TPuKQ~o7{9R?u#)vzmf1hT-)&kW2>%X(3P}w~1
z&W_*z!{cjB_4j@W0v)HY=l{RoKOZ#n>(v>cy74mDz=`g1C-wLLDLVi7vdP`rf9rSD
z{jHi;`wes>!f&T<kdcXkA84KR7^U`q)lbVI3qTUKb6#Nlc4KSy^-q7l|4)107rE8q
zG6T>3S3)WrW>Fad(vCSUy&Wp`&W?(E*G6S7Y@Mrc<F<?^OMRo6*|ba_?Wm4<NufU+
zSSB`K75lAl;@u|836Gz5UJvDaf5yi6L)m@X`}Y4I|5zQqe$}nr<?nZ`-<f}Z-#pvu
zZ_BU6?Wx!}*Sfr}?9H8>#dEF8^X`5J4NNgGBz%sHjeUDz;o-GwYa_mCNN4^2_P+Yp
zm(GM~`j4V-gnt8%d;R(P?(XjEd#k_OS$}(Xceko9^MN#V2lg9B`s8eHEq3p(`v0%i
zy6nx5l0V<?*XN&}rYmb(RdV-w&A&gDyUXAI3(n5JyX)%5$H%YNLdU27$%%Czb=g$D
z`tWJF^k$pP+_%%kx?3Zr=|6hEfBhTKoCU)Tj{k4@S^xid++X+S<8f7AmIG;OAS?am
z+uc1o+kAKJ@3QH7v8!G^KHh(KXYumj<$hle^V^4f{q^<ry}i}f4>q&k-j*Bv^}W3A
zn_F97Z+>lC@nOO7e);l;hg$W2D?s8mr>I?9UaxKcv|31D94O+rz-YE{vbulSvokZ-
z#q7K^+dSW@;zL6DyE`wRo}RvT&6=91@}Hlc*8Tl@J#J6M$Cuon?EiiVKHet_x)tl~
zot>MH_sehJwCPeKGyAThr>8c_aYAf@k`YRbRtMC+-_GA(`t{Y-clY+*zP&x)y6B0=
z_xJbTgYxQ@wA0gcbMNl@y7}|DdA7Iz{{CM5<3pmnT}{UMdA4)y>-S|}U$?dT`#b%=
zsO!uQggZ3wZ8%x`{cic)9fgaf&GY`8H`UhGp8r?5>gw0m*LT<b{pHpV8ncDE1T<}=
z6#f6d5P}b8?PCR3lVCQK(1O-7P%Z-l1GG{?2so&MYE1;6fgu4}$05X4V3e>t7zR&;
zw|JoX8o<>tlmn&~U@UPlz%V!j!w+p3275s&R<N01;sC~&X#l*L23Ekpz#xHP@Mz$`
z!iK28c`Sb#Hn{n~J1RCdcVmQ3br0{>?Ca~ky}!Tz-RC{913$ovi$P}B7>9+2TbH~j
z$j+9ZW_zmb*1o^L=h@Y6T6f_VeAOU4GHaa0x{tD4LoHa2?o!Hr51wphU|`UICAts3
zRxz^i-vr_{;d1*@qo;#r1whuqaXjW?@X=%n51r9G3=fLY0uCM&qoqGQC`PMBcu<VC
z8xTP;+HQb{#b~1n9u%W3PIyp^Hpk&X(ExAW!h}Wx2Nn_xqk#ht3Wm{ME<7ygJOprH
z|Bc=C)7QQ>ZFv0twoY)*f`t`9T28Z+mN>NBy4AF30b6^)iuAWD+l*E%R1DzYIWBgV
zNswuI+k!<am6W2Qq!zUYWOF%gQ2C%E-gKkC*y{MJXM5rvm)7r}|NGZJ#(X=tw?K^1
zE*B^iz<9LF1r7!fG1}z<g#s9lcDca8047F<YQez(B8Fs_t6^#Rzdt|c)&KjsE%)}d
zX}Zz3_EwjJrpD@P&b@k-1-e#ZVY}QerfAfez0;uSfG6MH-M#&K{r-E8`|a;7bZ)=3
zqcEA@=7WQL{hyEfYmYsjUw?0Q{=S>f&dy%{U>PWc;P`<3Tn5>M&f0G`(`D`J_Wb?*
zeS7`?f1q>d?S4FH&fEL-8fe<H{`Z`%TepHN={3Js!MYtXi2^g^-%FMk4Bl_%mfy>K
ze5`lvx^;1La&K)}sXnh_k-y!~C6m?t|2>p+@0WYKdi}mvSHt7?PFjuX2XBxcj)3Mj
z-|cwZw=M5()ybOc>te<0|J$aYpO<@oU+vx>kGk{hQD-$+UND?~^X28`wQJVIn8im%
zzC6^*J=d!ARr&q;r&GgkZA$g_xBvTPY7}fS1;n`#O49$|u`>Mld~UAw^<}=Z^=5;%
z&WqRo*Nw0LTiVVi`|8KX$Fa3vuZHKKtUqT+sNBIQo6wniZ_m#8_5Xfu`sr`~x8&pZ
z`<u3HyH@-C?)Ag`_BBVpp-$XR>z2O2IPJ!%Q(nvc=I+X=`}O7Js=R$apT*a{Kg@6c
zX7BfVpxLCg>(_^uK0MS4x}^-{s$ajV%<mL9Uym)n`~Kg5<MTF`zg~~8KbdoWp6%P4
zo1dSrLF^r6U|^^}v@!X(RoR;xs+*0|&;9Ye&9LDOC_ZwYpPO6z<)Zss+v;s=qqoP+
zssHtIxvp4u*}FSGSHB0%AL)v9gLY(lKkGia2s9J+`|bAf4-XE4E<?Eg_kS}xf7$oD
z<^R9SBS+SO`QNg|x#~V16~9}2-nRa-8-tE9qtyYS>Ms}FtKV+DUiG-wyz1M{^wn1N
z|7zU(WHP_MyPJD^+uBv2d-;sh&uvLQ-nVYot5u-G0sQ7z6yB^{y?XWCvfH_Pzg+UZ
zTlsu${mbo;h=P&z_8{|bZ_N(xxBV8OzvqLK{htrc)@5&AoS3M*cK!PDA0HlepMQIM
z`})Q1{omehzh8D*cl(yw-`}?7-><t_nVp?|x8$;~?T-h|^-qzPiGbGe3ow;5sD8f|
zo&WXIY5nitZs&i0+;3lYJ+}PoyWQ{0-tYY$SCh6eVoT!THhY`wjS*WSbk;rD1#=jf
zK43qCK{nxJZ1GuBS&M=N%<O!Bo*B3E%kO*Q_T~Pkv*!2z=!c`Fi8J!??Vwd7VEqu{
zz<*ZQWCcWkfq`Lk>H!`U<hFzR7FDi>tpz}h1cuS6M0n_q&a=XUVssK39u%YH4<abY
zEq_MK97q_BW-CZIfXLBm9TW;+JesY*!2lwNAKq%H-&k(0A9byoq1}GgPa!83F`r{P
zN>(h2NeNLGw3wo=EMt1<aYVq-Tl|~bU&hTHZDP7nPXZcMx8__tt)!t9<ucpihF0qw
z73ISkTMupiX(+R?S>x4@ImNN7+u#5FRP)~c!C~mqJ&?N+h*>H{#HuXJ-8z{00A*VP
z$Z{;BJEP741q>LEh7LFwz(m7n+5v|Hm>A7j;9vj~^elJ6biYGKN(vV8$y!~xxY&Jq
zb+32U;Wl1he}Db&QeYP`Ffja?4=ctDCV~{&|0|4E_xrQ$&gz(;?CWut8=3zLLHDmS
zFcd_>*4NJPaPOCs{rGeC)!fs2V|?>Fa1x_iHzDEuTiB((+GL!+lv!`CGLn7^TD
zr#Q?3Q2N0sl>KHPQ7nBynDroOFve0>5wTbnbC*BnT=%GRzyS;*uuOK3h7KrTz<4xt
zz`+0^MspS<96%)I%+F}(fWifWM?(h^4j__;xH>E0&|It1Rm<ns?dp{_FFR{`eM|1`
zZFaw2EH1YDeo}q@mj})KX12C>ca^@LHEUMZ@jhA5OxpCsY>*Xj{J=}afqg~+X#V2!
z=g)6%ZCyP*zHVpe>af!Pf4|Q+R{8(!cK+^Ht5(mNJNNC>@VLzL^K4};i<VTs+qs<I
z?#Bb8T%;Zu0|P^hC%CB*vqOLXpH18E*X<UMui1EacX>Eyb4A|%zu!PJICg)(T>k&-
z&6zVk#>U3!XVTKscmI4gd-nYK@Av(Fw|mKM)Ul~>IrRn1J{!vKRW1)*9rpEzu)ogP
zYilAepE=_*zy4q4{rdlZEBEH#-BlV}|M#n`b=jMw^^lEjFhBY*Fj^g8`Tgtl`rTiz
zMMv+i`z!f*ZS;1%So`UZkN1DS>~CNC;6Nj2E^*(_XS3h!{eI7T6YBoJg4F1(ceoh}
z9*T*J&z?2QD%;M~^y<sY%dKmEe6YO#@q}{!mw&(Chi|R=`U*5X37RPF-lq+-A50fK
zEoK6_;_vtS(VNrGMt<I!eI4Y2ojZ5h{rPY>uKMlPZTa`_tqflN>v6xm-mi6FT`=On
z)bpG#7=&}~?kb&YQ~7Dl&rV_WY3t^nUgkS{TAlr`7mIUmZd!U=z8*A58o$RCvJDWb
zxuH|Rfqh0oaB#4!UCoa*KOa3x3N^o1@wjsD`&X;iziVWd%gD=H2bu|e`|{O)(4<&w
z_1mrKXUg8)xp{7`_4(KJ$j0p``2Fo|_Wgae>1RN5f~mLI8a&lO=Fc|IfA_fG{@wNX
z`rN<2zIuPw-}hsYsCL+v%FoX}*FDeQ|Mwaw#OnV1uw?!+J+5k{ZuGV}-|L}{1XBec
z|J-eCim&||T7IYSxKS?40hQ>T;BW^WQ~vMI=ksy3U#~8`xiWZpR76C^?QOZacXn)C
zC13YrAu~JQm+SHMx_3ddWb?l6OFrHQnkNIL|2AG}y}zi_vkc)P;54;1di%Ezhxxz1
z*?hk2$%%=1JD*My6B7gNwX6RAE_T=Znd$Rhe!U+5e)s!**;Q4$R>@kIm0b2UFMU3@
zyzDTqdC7+d2gSt1qGDol{{Q=X`l~0{7ck<0k<bEWpB?7+Di({!RV*~WU$c3B{lA^Q
zv(3KVtA1bl{cgGb-OWiyyTaDRR30lfHa6b-^;-1V^XJRo+}OBo_q$!7<S@^+de`f9
zyY;@K%?^fxl5|V--m22#;^MPs&;Gq${q5b|>SLWRLN{;TeD>VAxL03c?f}yboSQz~
zL7Tl~`0yXTzX_~}fq`MP=MD=A28Pj|J0dKwOu3AXYaoILI<C=Bzd8Rn=!A5R=4<v_
z`wbT$6+7zit}s+v04Mx-A*je4^xdEis_2>um{7NwGcZg=*K`2G+z<>+qmF?D`QQkd
zKYL%Y!PWvm+{G|B95(70Xb3>4(VPVdhtV<z8V;kSF(e>H>nTV$FpSpVkboF%+d#sB
zVYHzI35e153?v*zn-Gw27;Qp8!(p@u0SSoFCIloLMw<}OaG-k=;=qmFv&D2z+c7*o
z-jVXuK_t<~$uTn5NyTxA_#MfuoJyL_8HPU?(<X1tczn+F%%Lz=s}KdpEwjS}ompHR
zZ#b>;)pzO3opj*dnHM+b@SJ)4c=AlkdtZL*{=Z%s_x=Ar26m(+4x<x)&`4%rU>FJ$
ze+h@?S{5$@Z9uF1{A}IcZ?`~mBe(PS|6Tt5Ugh(-pb4zk>vn^7wr#&(SN;3j+t*J{
zPR5*R+fuhyoZ-Ry%3m*+SARZhK701;?9<b9b#-*Ud^pU%ean_Bd%xeSzE}PG`}_A-
zRtCSlxp}$uyB&)`^C-^kd|P+yxUn($_^mCOms9^Br6tfAuTvcw_zVt$=aK6Feg&N(
z`Rv)VRaLK6F5mV0-R|mVGt;Zy@BMzRy1cG#-|zSP>#x2!$S$9AeO)YQ@0zSd!2|ib
zvWOUAU|`tsX-)KNR)!rF`FlRPy}rIa|Ng#O?ajQ>W+v9ww|~Fie;?$}d%OS3&JVZ!
zaDe%4!C~IoUoV&cKd}$Rm;+ONK@RJawZ1mD{NBwkU%ssR*(YlqHt)Zv{l6c{%l+rS
zJ0_jKC&e1NI0>qGvNK56wCU4l&zxzQZf9(KS-$?y#ZF=Mf0uqgd;a|Q+wJ$O9(Ahg
zUG0KufKUfm1VIypph*^9X|p-T`+vP!9X>C9Mfv^O?V$OgACLRDXJ23Ey-gXS9!eTm
zvb<mrelsh3-OKCo^|tB%PV4VqW3yjie(kr&e!E{8(cAOhKAj%FZwb09lmABPGaNWN
zd*;lSM>>U{pP4>=`s!UjpUwXNMfQHpXW!lB@8A7;y*|INaAU8udEAHh=g*!ky<2*H
z?X0(VcW>WY{XOo3HPi`U>PI!`Aj^x3-NVn;{dm}J3ZGfKy)8F8GjrwT<^JZjwtJ2K
zKWOF$P3Yd<mizzvzwh_!@4vgd+q(K&j<>frXggW`%kR&hKi~a)UbS9UIoM<<q1XHW
ztK-3b`+qw?JJK$?G5BmM&ECtvApU;iak<xTZf*wcbJGUx)Z4OQ!-aEmt#9wCEDlxo
zpZDhTdHeU@@7Kp$f+kD9UU25$x@XUw=={A`bGP3uyZIeyl$(KpVV%xCQ1q3(xp8rx
zZFSYVozH*0+x;H2=aHM6yY}zb>#~+bDNpZgK5uthd;OkE;qkRsb+_LMx;ok4?xwqZ
z?Ugrga*p@QzyI;^vG()j%a>O_ndq+f`#<s=Bm={>X$-OnhxYz@wc7UopU->0-O2_{
zg|Cg?zHP^j8@1o>ZZAs9%34+W`r6uEps8>ZQ`4&t54VG+YgeUjzgM*y?I6Z~t)L|E
zZq@2_uO1w1mbIz)uqVAw#&XlE?iZo)bw8il?}aar1BazS;<dj&QTJ{#F#O{kU2F^v
z9T0)#4587`0R;>gkA@C77{J8nGJbF{fQixBcW^L(iP712a4<j!==?H-10qL52NViW
zJQ_OCfM8%?py#fF(Hb2d?o_MM+pZk;g|7ub?Uao!NP-79)-xzZ7bGFVXS7H}gvIbH
z68{~(_jh+z>~=<(`upw9-<(f<Rk3gl?nvo)Am)44)S|=r3;T{Kf~H$tS}wj=6rteQ
zm&><k;w1q+zC6>4Es9DVbteqxKdm~~JZJeljxQCT_rw+GU;qC5VfEem1GB;FxktA@
z!;=q|EoGzU;lM&?G;m-cF?!bsJS4C!A}402=4iHp1>tD6f`!Crwt|PmNXk|Xs^!1G
zy}eiS`E1$ydv`%6M;>fux32&9=f6$)>uYQK<n8Zu>+ib(nld<b%1c~7u7*Jxb=Mfb
zHlx*nN!C?gGURK&1iJUhynNhmpI2JC6|}u={k~tX^v}ocuiMLS_hZ4=uU|pOM<#8o
za6mU?_0_j=3=Q?~Ua#N(Zu5D&*PxRTZ){8s1#N+QKCgNmXmgML{y(4m&+q$ii2Lt{
z!~CEfbj8olmHzznlzpoiBJvm*7(PrWVzxRU^!v}}^U<-fZ@*rTzdz^gjg5=1$5pRA
zJzc;2@v&Ze+uuio{kLRaU&p>t4Mp<?70|(nZ(dzpZTtJp=C^ltexCQUk(u3WKB~9>
z#Db0uEc^WI?6qsxww<|t?b@#D?|H9ZzrMXe6xF;nVDmt`wT}16MnCJf`}N{kF^ZCg
z{oW0H8;;0Tzu8##|L=F*&-d$o=YF<CQFGw_)?IhG89tm}yLRo?ef##M)_s0<cGbMP
zUoU_E`U~2GbtTyUuCaB^j{?xagX`}jpU(Nf9(23d&CTiWXa4<i+5h$yUWU_tARE8E
zy?wovTm0A0=kssxEPnp%	@}x?<hm-rg>c-(UaeNGE86-S1z#$S(PJtA2ODhuQi2
zGXMYkdwYu@!|9yV-Qo-n=2wFb+`Mt)#gmhhXK%i}J-__dmzR8UHaFhg-MxBO>FcoT
z>*L>p=DN0OAsffAf#nX!DSR>(7gn#|cMCMx1)6FDop|~3^77yBcE7hOeRbtoHE62p
z%uM6j-*30Sy}3EP_}{(i_gf=$c9p%2Dt~|P?U|XzvAarEuG)UT?swyVc@!%WsyQz(
zPP?N%zvhzl`#qPJ&#$}HZ~yPcy}i}HA9d?nmAts{%)0yNqN!7->ZaeX{eD-h`{*<4
z|9#iQyIaxculRG<3Nl7$_1k>%c)$ODoq67!7t`bGUY?q&4Vu&YzNh%rm6c{@X76_X
z-Sev7{@;spbFHK6q@|_#KcQ}PWZ>r<t%YHcG+GP8LSnQQhKIyRs)Z4r2D30%>WrT2
z4GtI(F&a3aPypl6tCYaO03xtV3lMR(1NqqsbOXqC0qxUmy^pW2c#<I}(z8(P=|KyY
zy;C~60@wworMOE<ylpmmrJ{0cj>_EDhy>{seT&X0nzO!bHoNAyGGakTCeKtS(=e``
z7iJY+x>jDazb^j9-hJlr#b-C&fBzx!^Mk#5X>#R%B0-*m;Q)-zy@!$m>Y5;i1+ZhK
zV44^vU|!aaam}hiCt5>?p}`4#yQ_l`MvDc#dBo75f)VOm7`i+$rn5vabYWiEt%0FS
zMG$?{?q~qPV;#g84Ioe`!0~7bf(HeNF`C6dp#aCDWe_|lK#UPpNN<U6zY1FmfW8!9
zv_=CZ2RI(B^5H=NI>l$SO@tgAqm4%7&|nyCRigxl!)UhyIXp)DWyqm12s*9}edb0+
zliKB~G@j3^&QtT7Go$kJv!~7cc0c;x<(f$Ce7$aW(K*ZKDVLUb?tIjxy{Yu|wf#Sj
zpm^dyhN=Vmi-PTU%cAF1JnFntbXvFa)ym~Yd3Sc`#OyGTHqXncjNg3o%%N89&1q+6
z-Kl=RxAM)#<D2sD?~AGX`Sj<n*X#W+zC_uA({RzHf$ze>Z8<k5ZOy)(_Vd%z$bB`H
z@AiB?SM%dx`_2bV+@Bsa^KaWz{`c3{n_Du2<7z%0wfXbm@XqJ+sy|(Hmrs3jV`Jr$
ziSB+Etr;Hd|6a74-=OQ}vU6so+g5J&otyhACpdk!)$J{5^Q~@QK^MRF1}upxetA|c
zR1;X-RDXZYY_ML_-(Z2#ZHx_*Jwa}ct9&}ON7`J^dzy}AS?-@7A9p_Pv)+_>d0EZ>
zzu&J`$Jc(n>NC?w^?F?O+l|?_wziRbDhlK3|9<`R?RI|s>zj-gk$;jS;ZB4azH+l~
z_BUjwL&Y=C+M#+0EWY;Ua%8V6JLDfVE8T`r%kUsYXaRG{hTPlRmabo~KUvN9*Ws@_
zi=WF??@fDsZS73c>}!SBpP!pMJHGy}DKj&(`u7c}5xzp*f&E27_4jvYudEF2-)&d=
z>Wazivpjr!^DgZ5jJk(<$Jd;BEH4;jb22hC9v|<we^*sr{(a+h|0nm-HsAadhhpx7
zFDC2mvNJq5;yc4Yv7KMu?%l5sA3lH;uUofn+V_9fe)qR#UyrvnI*|FgetzeB70apT
zkH4SvW&Wc0?D9$b|NYqxj@-*p)!#Py-d%Y|?d6*J+K?Dt+xzeNMo7e8^ZWmNV{X*z
zCFIFjf2{rX_V)C@zrW9a!yF2_PVVJ<`>D58Y;A34+Ejju-*x;u$Q6I$LP2Tl%FVQr
zpWh{GJro)0L&G=U%-Qx^fML#z)$4X?H8(fk+?ae^eqH{J4T_(ipFcl4f8WgPbvvK=
zzkmDswRe1c{JpBzYwcs||NVTvIpyS}ocsH1#bZk@&cAp2{{8v0^Y{IHvIl<7IVd3i
znXL|Af6mwZ?v;1R3>O@0n5-PwXImDh+5P+RSjMVEW3rmBRax!lXJ=o&dUfi|OylT#
zzfY>qmnjDc&9o>?`t|GAs_%Lc8x%mse0g~}x-JOiJh-=pCMHvCtG}fjY+`+D$HgFf
zOdXVrbfdSW+}l%G`RC*D;`_DVRXyF@+&-<Z|EoP&-T&P3`E|2Yem-oMzm#Ee>Gti}
z8<UT#d0tx^JzY9)hvMt&>(4K8?VhCa`}=$U`1tsB`+mLp^8Nev=e{VV0Yk1bsDQa1
zUtbG4$y6tHm&x9}dn+Hdihug~e17`jHr}0IE_qK@0c{%%TN^diw))$XKcCP0Px|xk
z_xqi1Hl6--R6PF4zu)iu{r&ytRX&?p^ZV`gpKmswH%dO%Q?^eR6n1dDfcMze-wX_Y
z%HyhDF4c+NrUMF$^Y;JebnEZ4$lw3>+r}R@p1XGKGD<r$!~TwW+L;-9e!tsY`Jj>g
z)0fNs=@}Us#m~>3T@||e$aA=vAjSv&r@|Ldy~W@$spsea{h%ZLKq{cPp`Ho*=-~y!
zw)XbT)!*N}xwF%FclrBsA3hZ9?uYA^efi<x;mXIo=9_ANe=Czuy<%DP#G~xpotXy@
z9xRhj4T;*A<XZOjR%q?t)B5|*bct&FJ?v!oSJ~FqR`j^nJnikRt)Muavu)R`vuT^}
zwlgp={EJz9@x-aA+MDz4?&9I$dGi0?$GxjpYa6GXIq~Rd_vVt9m*&)dyP0c~`J0EA
z_vzp7_s?Hj8*OZ1F=OGvg+4P36fZCHJ$+`Taq-is;c1VKbiTDqyKOrAZ1U}r($cNJ
zEfycUxY+&k)$n-P?|UypQpUF56}g`u_uHr4-j;j(ZP7{9=_#kCXuh?(x5CiKXp-?c
zi^X@3ON4?#q5S>5<oo8q%l&-I%gcB7yRuh*yP3YZ=;<jQ9-b|~H5OkwaKNGL&5en!
z-C|pRYZOHNcsf1)Qih39?yW6l@~kf$l$DhuH>dfQy}dPc-n@A+<#$VG+SUFljNhJk
zxJ@U1pUwNd-|wxoPieO(c;K+_=d;;oW|^+O>(1Cvzh|y>`LmtR=bdh3W;d$;_vcR4
z>$R3uUoxiYMo;_q@1KcO@0pp#>Y$yy&(6%e{O<9#vj>~mi$6R#X#b~n)5VM@bIb2}
zF1~o;&CSim)!*Kj&70s?^yI`uQ0`2hTN<{z-{{qwdwZ>W-IPJ6y8f?zV85yS{k=b5
zF8jZH`}XY2^m#YmJ>GKnSg&;SzI#`%PJQ?8-JJ4!l{0NBKWSQp{x+R`wxqoL`APNp
zXYQ8Yzx(cSkJkUg_vW@=o$>!abNxIoZdF~WEs^ShEhbC-w3fY@oFbWgdS8m<u}S`m
zu1Kg%+&JaUZq8&C#lS6*TEfap3_QAnv@$LC+t*m%_rJW;|LmWA#rN8Of8C*X-E{fy
zzdP4Gf4=Wr?YYl$KG*Gk|LRrNij^xB4GaXh#r0BT-QQ_wXgs*E&{@L1ZqJd&$NS}v
z|M>VgFgRHGamuH~J9bEPc6OdPeY&~3ySrkaXKt>ph{%s(`J<mcecJzb|HH>I+jkZ}
zPkMD_<(&C*^X~8K{qUh6=l;IfV<(@umzJ7(d3!HhxR6m*RrOloleV@tHnaSDJufdW
z-`wZKq1aM0?Z@RioQf?1P8>gvJbCiuz@bA-|Ni~UxV}zynr?L4g9iz3?(7skc<^Av
zwj9Y@TeI668W_I3y2@>7X}L!E^qoFg>x6^^hVbz4AHRM*y0Fl>qo?P{Lg)4euU~gh
zRCYgf-~faD|3AjBR~Ur{2RGOL{+4)Rf?~$)ZMsvYOgR#7w>|f^STj5Sv3q-~17l;)
zT4@R2ym@nmQ7TtSNy&w^(dIld76OOccn=?FWWKmI+B_pWJNeU-lNFzyaK2t)G<D7#
z9(H#27q4F@pO~OH!z@?I#@5y__m&BdoQ=e<U%y`5-)}!@(xeFYsXK4oijuJ^;ZSz#
zX;`>Wamth_3zjWoQ&m-!kdjLJ@!_FG#RmobdYii6-*m67iEPfhyUQ^)R(7s+dE3sN
zmR9BOcuGr4XUv+F^!3$M4K1xC*{PkY!`COhyR&n{#*K{|HyVEV@+BcBheujk`pisY
z_Kh1iu2DX<)ja>6g0^;dDbLQ*Pft91<ZNe^^6V^mazfC;+In-J;`D24quE78MXwn?
z2`VTs;Nj(sJU+quc%SUy35w1U$0vAOm%TYKJ-+UwRa=Zz{Xd(ub8}8wwfRh$Hto=*
zOG0vTauNIMY^UkPatR9y|M>Ca!TRdP{Z(JN3=Iu?CT$WG6l?_f!qby;ZS?kIe|~=c
z`0VU#w#Q1!%9T4CboKQ3c9*?%a&cj~x3^lo(5I-#D1Y5*D^^z451&6D-hRKX`{(E9
zkB{|A3mu<pTRp9O{qdPIXU?!H)ym1qF{t@bAY)e(@o2|l_x?{s%zIl}SX$cKA778J
ze>&$y?dNB{XXaXmA3J&D*N2D9d@>dc`uh4gx3+YCE^pNiU-#jY@zu-A{RL%Zdv9;g
zFYen}{$8%`&qsI3Wl7Kf{r$aR)22h;-rg?!^(C{SqT;~y>*DwB-Q(crZ{NDr^v&D1
z6X(p~ad&sWv%h|RY0AviD_0(Tb93{;#fzDpot<aQocZwLVs{U3Z|CEEvLEl3-%osZ
zXXlSstJfP8K03m7_e1gY>C@X6EKmRi)~&7CkM_5>wJoau|8K*F4F`H8jVpdir~CNu
zxb;XdR##X5`1y0;s#RQ1pFWkaud|tDp3f&MD_ipN5^MVTd8x9Y&%V9A-7aTab>PGa
zj^O2fu9=ydpFV$1%+BsUH`jWx|9ra(moGnl`hGtvE9;G2rP_b~{CV~Dk!|(2gaZwX
z8@6mYGRLy`!<(DNZJJLHuiyW#YhCPaP)^xf{oSpo$f%+J`G)ZIaTdkTcpkUp+_-tu
zQA4EY-{#Gmo0l$Cy|pEi+1S|F#l>YqpN?>;dA){)MuM#CI}J_EgC|aK$lKK<$UdDM
z5)*Ug^!dl7fByVguzr32Lg#i+@$l$8cWZ0wg$oxRT&>=@YnPRYiOH-#>r+opTcd2e
zvG}>)O6kk?b$=vwm%W{osPuEf%$c2%#%Tv`+>p@H(z<Z<YHL>)*RAdO{WmwKUrzhS
z@ayaA_9;_Dt{HMDwoEuLmRs%20V+m1=KT8i`+Z<+Z13*!_lu&p=goQi?*4v$adB~-
zxIGff{pL<eblP_4&>@5Tdp0|E?E>ebO`BGIXRYz{<eW5V(uU;Yd^!;u7*3r!HN!BO
z?eLLJ!4VN0;^N|Wb{4bCT9>sfUcC5+-jULBbw5wfgIh8$Z^*rE7PF^9(8|hcP4a1<
zswyiP85sqk&Ij+_@o8(XW_zx#smZzAZ|<R+o6`%wz6$;F=H}$mH}$bOIXY~-QY_5O
z%xfYyw|(C8=Kg+pK0dyVuCAuVi<MvBF#7oHtTd0Djf8prJrRAGX(hg{Zf;5{DlFo9
zF%8?cnZ3SYG;#7|W_NdYoBDq;e0+QbrKPzAd6Onj78DR@`1||&<5yQ#3%zIhX}M~}
ziUT_e9~Zp4W4U7G%7yOzavQd6SyP_JCu7lY;X(k9q!Ej{-<*b7v!p<_etLRZtzTDD
z^QZXa3Fjlr%FOb`znd=Gwr$$>*#Z;m^|ZCQFJ8R3Ci#TwEuGfrtSqfVhYt%%Nu9Df
zwg24x`|>kq&b+a=+T5*ArZaqfT;ktfUq5{R?p{@8)hBCxZ1%e2s&;mAi{1O(et&yw
zSo^Ew$+Krk*Vn~bl)e)2n`_m&e&4UIQkOKlnjZ~`huaj@)ZF%H_<DPDOPl8%xw10&
zb#LvTABOqsv>7V?{xbdb<z@49{dlL~VByr%)EoP1t@r(YXZ_~Z*46h)L!+Wjt-k(v
z%^ICAZ*PlFojTRP)b!}v+uIBO{i$qeZGCv8Q~1K=%fkI@*RFkfwXIU#uBKu2YVAdf
z7azSorLT|AEcaH6=VZ03(!W1EbbfPdYqxp%IW1k?*0pPO-`(A<ZfC9?zV67Ur>7sj
ze$CzJpdfd8J8!Uyl3?1oIi0rE-#Y$ZTk0+T=g;T!5(WtldpBlgW=3qy5)E4yqxpJ<
z(eu}@yUlWMDcIS`RaI4istr(uxGr}0qkj8;0`=^(rcPzm*4ADVy`7JpUoK@%6ezU{
zNJ({R1}_6;21P~14<9}>ELx<Lc77gjd3kwANJzr>cXw~>ueZ<1&8;j>zxw?A{KfhA
z_nkO>nwf!xh2_EX`Sos*k&=7%?!CC!o&U<UYf1O_)&6+9{eHpgYq}B=5(a*{(w&{1
z5+)e}TefUjuzEFje0=<q=g${!+9Z^jnfU{hp#lRNFE95`zOo{)qrV?i9=^U|Bq%D{
zx-xkAp)+TA($dl_3LY?MX=w!n2Q!<Rn&#Zz#w#i+3KA64iD>APwNCo*;NY6%(?{ml
z|Krrw)_(Hr8Pks+QhSS^`%RfTHSuVd=!<)Mt+lkY1jNMJjML9O`1bZTs2TA1N)D*E
zT~J)y+}q20tY5z0H2Ydd|I1geoZ{o<tG~Z%UA<a+_k<o7H@Bpxr>1J?>mUE}^76%<
z#pw(O7Q6Qg$jR}QmX@xG*vRBR-_A87L*rPFWb<To|3hcb_7;Aszkh0~_Qr~jNj-A5
zQfg{yYaXANTKV}|;`Md0pzI&DHS4GqUoj^q=Z?C+yMBD!S^WIN^ZE5=65%m1J<jcX
z3#-4s+tj0OzAg85n`!p7gl}(d{`mEJy<yfBjgN-1va&mN?RqplzV6_j%FhzZrp!$}
zJ?-l6GiOz;tfVqCGmSjHWLEwCWf~G18hLyI=unsBLoJ*uR;*}fY-F4>ckaS<>-x&y
z-&0gpW?r~(A*hkiCu`mI@NoO)zSBM)9vpM#&VBg)J*Yf%4iBGRs^Y|<_++ya_XS9E
zYGQEsx|qiG>(^g7`kVpOm;sf4`}XZK@=}v;YHBhldlMmJTNU!?<22pqLpN_qo;!C=
z!aPr=si~=AGehmkNvfb`&Z0$&9z1$<$WqVBO6q>yZ{4~d582<`-5uV>c{6HL3MZ&R
zcH_p4s>y}_Z=acI{PD8C{lSYD1?~TQVAhM>rSf>nrtL*fy&|Hbl+@JR9`Tz!d-klL
ztnApOrQQ#pJZYJ#9j;_(IMFfa=I@8?@}Tnme%)_g=XSoQGUAewot(mI2`?`#<>2R^
zp6FDTu~{S!l<SUmi*Ky`T~<+1;c@5gzr*ePH+Glni|IyzOiTLw>@3fuQ}Y@d9Vgc%
zu-o}D<iEOc{%8{`_bi)l&(6;NpCt52)6>Hv<5R@GyNoYSOjP!jn>}ydKYcaD`9imJ
zTK~kRpPzU1&CSgZA3kJc$hf*n^xNCp?CR?3XXaQ6Gqdx#q@<{<SAY5I=g)(8?#Og@
zc4pk$W67YPtjxUFz5iGPBXhx<8-_g6W<7;oW=%~^0>Z+~`T6-D+1NnkSC6D|!S8Rm
zIk&g<me1YM*Wb_Y<>duZ;_mJ~W!ki)%gcN@I5-^A($vn)wQj$*HhOd4$(HTg&97X!
zQt<hi@5e_SpyunrCe{rbH#(M-Y^gBhywAeUu54u`r5(0rMY(TfMFl9&+}M=L{kr4K
zg*MGQhYlSQkdy1{6jtv#e|DN~^n*u_no3_^OMH20=^ACDi8E$&+}xbLIQRB82D`fL
zbq@|O`ph(1dXH_+T&vQi_ICC@dHZu(TE+_(F8uNBcK*@X;-EI@ogIZU>}su;n3#?{
z235gt-sHTwzkj|t_l4JW+kL#enl^4UT;?~o>+0(8!v_v9?En97_m5gFLqkDO_&GQ*
zl)bre&}h?{AHRPuuKxbc!^6Yj^Ru%XYkn5x+}$M_U;9<`(xppB?yIhk+{|WM_2s~^
zUg^qW@kd`@Uq5{A9N+bIvCR$&2bTHH-jH;Zi$}_YW4eC4SpVlQUtId-Y&WEy7Q3h8
z@cr{=XJ235b@BW8l9Q8t=G)1x4qMx_Z=c<z%a@PNHL$aj)6>)Y@csMqvuf7$PoF<$
zudc2>a_rcm4I4JxV=7_TuyNzVr+0%H71Y$&PMtdC;pNrT)#bG}`SbJh?*IS&E&Tk<
zH|NF%#?Q~rg4#pZ*2kakW_{u5>3QMe#m1R4C1qq}F6^uQ&2~3JLEyuu&n=4<Da|s?
zZu6UKm3U@`;hg7b|Ni{!5ju5ksrU3Fw(bf74{mHswkUfu<H$x?>oS*uf(<&4Pxj{C
z-j?|0#zs(`#>LGoEwg>Yh67Wz!zEObA1|L@H>v8+qods)zJ7I$ijwN->3Q(<sp{gC
zH=yQ$kx|f}iud>Sel@FH5gZfKvtotDmzS5_r+u7J_3;s_n*Y3>ZMnCTzQ4O$P*9Lz
zpk`(!c6qt~@fJ?u569)}Ka?>mMMp=6goS~68WDS|OlO(r>wVn&>g((4JwifG9E$VJ
zq8j|5&8(n+0EgV%+{wqTUAy)vPbtgK&u_ANE$C3EA78J>|9|T8>G7SN#SyzoR)Pv3
zP|}mH`@uNdEO%0%(a#BU=JfDNn-%EUtzW!+c{`~8c(hB@$m>{GRh8AYoST<k<Q>e)
z$^y0d#dM=o7N@+KYg;YmJza0=t{*ZCZG5s_s@~HSEG%Z2b6?2ZERqN6w@gy?HpsrF
zbIuUdbTiEsn`c|yW?TL3LmK0*t}ZSgUthzrH#gjlA3JvJQ<Ct6|6$t?taz7K()%!&
zeae=J%+r_6+kd`w?p)d2HwO|AwQ!dB7Ose9xFu4vD_hH9_EL|}Pp8M5RptZ+Ufe&!
zWuHy;Hy+#SZ#f^ndrnpZHGJ2tTeo5JX6KR;ljf3758vJ09kH`0b?<dKV`JkbOO_ls
zdzLpZFYnRr_D^RY9&R_R{FL(Xxhgj|H>iDAS62s$%e*|jJ~`W8+jm`fuB4{M_WAkw
z_Qi{p862FQnX|90Y23Tl)~#QT*V@`TX8x9<1lU@DJr#n-jvecnd@9b#iRsz-`SI`1
z)dVl|X`DJ$w2eoSDLOiOj(z>S@X1B5K^;(Gb-y*+KNSD?@bJUOkB$5H+sEy#YCYV}
zzc_Mp8c*;hN9kn+x3^}CgIaHYe}C`(Z<c$@<jhQCcI~h=2fD@eD|QyB*xT>F_vGuY
z))#ZFO0x{E9XaAsvpn1G<f&7uzW<%y+sn(~@uxQJ#f60*K7XDZX?AU0%+99B&1nZu
zo#JBHQ1vw{B04(x=clJ%%{(`5+<0(`X0U*$=uxdzXO=EomUMEG>Z3fH(pMolcXkL)
zR`*|b{pXggTOU4r*m!q$`Q|RI;_vV79tMro&EFgw8@sXO<t4WJs@mGxpjvZJRc>Er
z=fN{GjW4c`w`Y(yuiUV08>pgrUFx(jpyT9Z_0PXPr@OhaH8nL^^w)npD!!-YJX1q6
zJO82Ew|5_WRQ%v^{sCb%p9B5&|2lZ3%{t_N|Nd?4p;di*Tdwf`avz_bBZf7x4gdar
zzu*0TcJ^mBJ6(tPJr#z_{O9vc^k7j|R&Hr&IdJvr)_W3-4h>?uQ4YbulLNiJ6%`e2
zNI5BV?(wWyv-bS@H^aN6#H6OS7Sxk;c6J7hZOF;V?fG@?(Yd+S9NgT@A3omd?Cm{z
zb#?gb-j%zTf!erhqqiG*oIJKJc6UH*Y_Iopy@k&0d_u=9tgIegTIy|JZ0wwok<r{+
z{v+u?1LK}wYx@M8I3}7RGOCnCfdZ&O+sMqm$h}`~&SOwH`1r?>6DK&r*T)^bvNBj&
zR$5w`TUl9Ia>*qAsZ*!={!{c04i=WTtNAfq_@sDfXy~5G&&xcMySuuiVki9FdEwHf
zLzC70XPKC3Yj=kW2Wo3;zrK6XT}oG1HzX|V-|5aL?77nptzEKY$;tP&$BrG_v#UC5
zecaxFxVXNjr>C1+ZF|QaYIpJab@%mgdken3x#@QN*YDrSUte7{@=&$6Dtn_5*PwEC
zu5~%6c`B(giC;Hrivy^9PdM1*c6^>)t(3a|yeW=aKQF8b)dmd)fesK{oc#UWUF~^K
z4zY)ZhQ7G5QTff=x6-n+r%h|KE`N7IVQS5Svq3vjQ&Shl?k+PhHqI`21M<P2o3Dev
z9~F;(@bmL?p?*sX3k5SXv1T^jrnPHz)qG|sJTCe4@Nhf7kbQi1M#h6bKR?f~C{$YJ
zJG*Vq9-9}hUmJUz@GC3ZcEtByO-;>(mBH#hbFD=6^z?jRwa=d&zCO-#Pxto8lZ78W
zdIT!}>i+(Ec&L?|=hDW|hzO03eQtMml{zOSDaFLZJb3Y<BY3%=p~vxSlhyq<6g)h{
zRu8Jjo}Zfw>L!7TiS%=G5-0TO-ZE&tz1Y29Do1I>nl(KiJ`|L^yCeDk=lS{x)2FvH
zv-25vooL&(&5VnS>q!69DN{g>%E-ttk%*3o(fRnkCV2aT2ygGz2Mv9FeM3S+Pg)5X
z>&Nd~v)yA+?eA|43Wdg(<!q}yqy>jRc%1M5|L^SPb?fvPJpS12to{9M&(9cEhNn-T
z284%;+pqhr>lO4q^Y%7fFK_SEX}w#g>&GujKHm4}c<J?!@9*wP_iWv;;lRDU)v2Ps
z?@aRV$)u*H&N)8crjkikR#sANlKlI7dnfPuVW+Rp|Nh=yVf$;BE;TJ$v`A->;q@!`
zt$)6_xY&J-@(EF1Uf#m@Yj@u^`1+u&q@?7-tE<}Q9+$tr_w;Ug!~eI3TDd_*r<WI3
zPfri1=MD;gFRwq*w>D>8)mjs^mFvLqpX%)Vaz}oAd@Q+q5<jR(JbSkE^GBbpWUb4N
zoS3Lw`14chJv|5evNsa1Ia&mqPNetN>rNE_jZIGQKl1GC?2G&B>%Y9aD}C+SwGCUg
zxZK{ByKvE>rc<Z9_Edf4+MajUDJV#&r>Cc)`1%zqZgIVq<;&Hxva$@y-^F}+d3pIg
zmuKJK-+z2<Z8WGd?~}Lhn=nD3Ei-j>{Qf#nOYP2`I~SJuN}nrSAGi0=wYAZS+1c8M
zOWxFeK5KqsN1<}nmlur>54RWhSyzA4VPa-}`0kzF;gUB!^7eAG&GX%Mm%TN}y=Br_
zendxK|M<JRy9H%r&dioQ!+7A<Eve}3c}G_SE?%&F`Ekp4UteG6;N%p%|Fn%C)RGnx
z6XW3LKYpZBc;T{T$1K<F*&~yfnE2xA>gha}H>Rehw$88rCz+a>nsISa>y?d46FbVw
zH~o9HdcA<W{QV^xYi?a(WH@v7?7}5WT4b%uOsvcl6dJ<0FX-y(PMkga_L8HU`sMAP
zU1ciK*4DPE`5^$h#%*!3e*8Y2W|vQg@7$3&b?TIFREfNRz=74QFSbN-nFj|4XJlua
zzkJui$jJEN<Hw1PTHk(sd)sZCey$*o=kn@s{h0lAvggj7i`bqwx99T7_H%Qsl?@Fy
z9(-iSka2B|WS^WZm#(gEMP;RFW^?oT&TZSwK7IbIDhJw}w_x#N=JN9LFYoWm->>~X
zx99T4rR&$9x4gKw`un>bg^$_h%$=K<pWknoeC&jUZ1k~X$4;C$F`;5j?(J<I{r$%$
zC^{SD+%VvgwF)`*^2Vi0msV|0__p77mI<eom6e2X8jp;OOhvix#Wu}5SFT=tt-I}4
zeq3DKh0B)@zqz^j<Fm8UJu;R-$6nqrG&Xk5%3AfKaCO*Pi}>l6FJD%@C;7KHJt3iC
zx&Qnw`Rt4g1sxrqM@p~f%#m4nU%x&tYHL>L`*qX2yu1QJLZ<A{40LsEz4AW5-h6HJ
z_G7QFuRq#9b?Q{ZgaZs8oxc2^Hhuc>)x3@Se>~#eQ}NO1Pef>_=;dX;lXp10eR_Jj
z?>(Cz#TPcEdW(pQcgtVb<q8W6%QM)vXi<~7bdL9<7cV;g{{HTL=Y_Vpxp-n?qJ&wF
zM03g;ODiiS3k!*D+qOxVWCZL@4h#(B;Nxp+Zf^dO|MKNa12eN}g<eYeKW==Sb?V5G
zB?s?oX=@7#3O1fP<+WqS4v#x7t^9615{<FD%MzcRnaTU^+1x2pT0VRzsHmzk@;dH!
z_t57jPf{eLrMur(oIBq7d{RhAh{qeVny()oI`_!g?($4tyJk(r*Jx4DuwF{{EiDku
zp;&b4zyXHL%uEhWPDd9Pma;cD0^gtGI6KSK`TM)O51&70_xJbTl5=xXV${vq*5!Iy
zT3QdDKUcqZbW`f-X^&Wcm6lJ+y|{?A?$=B8Gjpw{r^d{@wWrd!#Yu7BpHJR3pU;}V
zxV*go$XV`l^K7|OQ&aEV<<vAV5RjCVEGR8?-Cg!pW#0VT+w&hkJv|*%8YCnrygp$B
z>V?mlBcl_uL%@5wp6m5>vC?y<v-8V6INZ)JVOgZ|=kMQ0_h~a1EKsnpuvp+dU9X_H
z`0<`)e)H{kU0q${bYCq#8?*zo@3o+;tgW+?Q_X+gnV)+sD?TWE`t+&dYx09PH#aBd
z<@NE)+nMZQxO@4s@cp{qYkMZ0WM3H2k$rvL!=Im@8<?0(vATBUib!5wo{`tFc~hr~
zetUPf8>A)k6XSd{ebCtUGT+$&F)?>uEJ@jy`z9eZwY6JZUrAqo{l(6IQc_ZTX7Qw@
zrndh5{r$43Dr4@nLuXH&;!^jU<KXMdoByuistBl;+aqZ#ATAE-Gj%5KDtXz|(!#Q1
z$Bqa0_EsDDow&Eau^H40%elFUb=Is|ynWm(OmA*%WUi{Jir8JIyWZ^9#tj=BQc_gH
z)<h_N{IS5Xx!~m`RUT<Gp18O;BfsO*=FXM%n`hH0U;iiYQDJg&@|_)p%*|}PP7x6j
z>*tyC@$p#{K4LM;yQA^(YeaCc@O1t7V=pc)294Lp&7Hj~yDM9H=0fLoB`Yf_Ww)LO
zd*0cFZ%O1bH#Rl~jnH<B>rbnwxwRz|)P5<yU)$c&!XmjmIsMw2$Q{++^A<n;^!an)
z!$YiRW}Ex7t$flwb!zC|UKUU$1C_DK^}pYmM?^-R)RHPzQ&anD=6&(nwP$;n|Lm>)
zUa|GS#Y2afKqIyG*DhRm@Tbl~Rn_&;qiyFy=iAjzm@-AB?#?1t?sL7LA3b`Mke8>o
zI^)dD88fc@)>*lD@!`tj&whV@|M}IdU#lA$7$TyhL4$V^wpAu9OpJ>bFD`s~O7zXG
zt=vizJ2vyzzT1|2n~j~Fok!M6<k+!ek6MpLMn+cr`l89h%X?J%_x}3-a{lvd9@fMw
zw=fhxJL4D>G^yh9vQ?|JZrr-1WNIp^G?C-hty>+vy-%<H4xPI-`}(6#Pfr^d8#iy>
zY|O&MxGn#F-+~1SF7ED&y{GGa`1UPLHaHD53iSGQ_iXe0LpN?nEL^w{G)1Os^S}Gn
zttb%@kp-o%uRYrT^y$;Y@9*xeShJ>O_H5~@Z*NW-EX)xV7k74dU+$T_b?erT-`?J?
zx19Lr^!fAdQBhL&_SI@{)c%|+91I$_`rqYnWO<|^XdY0prRGppR#rejfWkiRhIQ-o
ze7~^;1O+v5i|Z-q>hi9S+bcAG{<hrPhYlTLYG&hoboWsWL&d*8me<zBc3)oZzj(uj
z4F?Nzb8~m>+<EZ!ZD}_*Hy)u)q0!OZ$;bN?m6VuPu3TC1^_8fWw)VnBi<Ii#?by9L
z`OS@udv>1_5)%4wT7Q2*T=2Vh?_OMAFaLUm(f2PegF$nPXJ#6IeP<Bp9vm#J?A~`|
zRp{yq3!T~7IB#m|>Wb!1n>2BvV&P_y^78VyylF+hzvWg`Rw|mAiJ6+3epUO^?V_Zi
zp>g2kNlyEJKa_QJbtTnQpIioYf{UM@OFY=b`c+NN<I|Uy!8Ub&B$(NFCInh-i`!Sz
zY5(sBGiXfY%GImVvgen#E`EP+@8Q?i*C(c=TzQ};T{C^gjE>Fe=O6ukzdygEu&%7k
zOwO)`LtI>3a%uAGgU#%q>g~>*I}4UBRV~daEHvce=B_MOU-05Z2B<eEZJy^c+bnlU
zpRd3F@wL(0GZt-Psi~4(H+k~p=EukTL9?2@e!FZ-UI<*ee0gKxV>ijA$=T=U*@DJ@
zCQX{OM9*t?`FpvTm>5v2?8=oZCkzy=K{@i$Qg1;aAtq~U>vM%52k$6+JYn9vbCu=K
z&-;3Laa~&*-Tw6S^uxDq%_@%Z_2m`Qi|P3C<x3T}ihcUShYvx+u0cUTOX{wHI$IAP
zJ!-nXKK}EwS-+l6k2gp@#`EXb>-BS_moXez9lrjE^s*06?|_DyyTx>!+}zl9mAyS>
zsb^*;wr<_Jitq1a^Uv{4T(@Kii>j)sfq}sUt91(&FzhaS+cbHya86E6%9Osf7cK;V
zW_GO0-%YW4_xAR70~3=YTQV<KY;JtHHTybfP;#bmx|i(q`SbhN@Bb%tdAa}dv$9Uc
zMn)4RPrm%(?#j=fKZE9cK`pY!$9g9RT5T(PbEDC^{9S?GiS@xjK}^oh&J`6E3KkX-
zZZDsl-&_5CL%~C*Bgc+iyKQmd;6X;v^t6w!ujI1i*LQc9gBpp87BBwz<z+B~y!rQ{
z!oq`dEQ=Q`TzJqz(Hd0$a&aA+YhC`~+uP{Q*?yn4GT+->&JXIM&Y!(s@0BnI%ZW2*
zQl|9H^_y$;@OJ)w(foV$A09aR%(Ibv`0(M2o14{-^-8lB7Z<y@xET1II(B<|{>HMm
zQGY(2*01>XMv`Gc?Cvs9n<i|1oNnRdQ|G5PH8HU;G3w~(7-U{rqV_lL=yK_`S7sU{
zGRfIgG(>ODWBl=B-qpqK{7;@dVPFUe4K4im$aUp?;W|GN5s`uy7ZiKs?e|^W*v>D1
zY>DUOir;o$A0B2uGsBSCy-#N4cR5v|&R1tIKYaZYRI~r9zsOVqYIcK`0-Uj}{<h|z
zQ<9yYmHLzaO&%&vWo2c}*{f=Qe+vi*NRaKfyrtv1>CvO4JA13QAN+jm&Ye9MU2`F&
z$At6Ixw)WT$--5uxI{%oS0;OVc}<u<|NLxUeU6`?#(6+YOb@7w9vT|@>c*o-Nqg%4
z&I&J|_SgEymPD`0N=rH0Dwf*X+83{0dCAV6JGWQef8K|*!^Teka<5*!TJigvE+{{~
zb!wS#EHpIq;n~^d88<hnUb%85;&|e^6)QOU<?Y>ab9JrC-rRU`Y+1{GB_$<;v@;SV
z@9)VvEffIFtN-};SW&3+!|V0?7lB#>rKLw-U0ogNK6U4h9~BnX*3Qn(%+sb#+fne4
z>DTx7{asyLclJ~Y-`!Q(+}g^@CueiQYSo#o85fzNx95rGAF#~2qG40}D`ZcFnSp_T
zqoZTR&rhnSXB2_Fzjf=@J#VY)%k?@P6dpWvid0rs1`UYX+1W8P%(X60y0@pYqqDPd
z=T1w|e8cM1-7j8b9P><dc64N%tnTl2e_yS%?CeRCnwr`9KYglXW;i`v|2Sy$HS4O@
zm)F<%_4M>^?5#Hc^5qMt))x^I0}U;{xVzi@^$Ji|O1)ETfv^*3yzmpJfss*DfQHEb
z*Z1~XzxF74`r+Z>7x(wqFD{><@MQhH{q^@>xP;i9I(2H%$u}(mGeN5N?zMgM=FN)7
z9tA%>B;L4v`|yPe6G}xsaW1So+-t?B=pwe_zDb`I-%s@wj|&#}Ide>8ePz+RxX<|?
z=PQdlD;^6trJTHUN$Bh>)5Bk1Uk?lkVX?KfjoDWt>F4Kn;^fK3ty@jaa&9zuPFCC4
zr&Y|y$9LlFS=XW>qgAU`y_!2)+B`4e#)d?TvNsYjF)<PDQ!Qg-V=JnwlP@lEU9oay
z<GOWv&(6*5ZfIa&IPmW7Zo~S2H6bA(27af)A|oZaxVS)_x_f#K=g*w^bNj!vUEZ|i
z%a*mhy}kYL;ls=f1}P^5_Edl8D=aKzXjmJ){m}jU@|Bg9I?1Paa$_!(yuH2scmpFd
zXz2dXA*U^QcccEqsS0&o0Chy)+!R(+R9v$dJQ}N_dW{hjx=tL5y~Txv2fx0)Uijrj
zAO{OmMrP*0YuCiSefuWB)%xP{a{l~xE=nhlbP6j9a3o}8MC32rw{oTC>x?s;txlkh
zQCV5phOJv$+uGP(dlb0_2MbS|Hto^#p0#Ur!82fD#j(3e9B*&SeI4s>TlFPD)?3fQ
z%BpL<rnI#5mW+!{r7AleXD=<7ZBe-BN9E<M+2Pj;pLoR{w=8<XQ7Xd;j-SK5zj)2T
z5mT_Z)$GoS#~yBfmla+q+!1*Ep_^>Gbg4`pjN@(ujz~}}!*uj1-@UdrT2NB*WM%o4
zgU#&8M>+&&7^nC3Og`B@V}=B10m#Y8>Ka;FhvMHSstIuXyXbV%|L))4-#6ynwbIbi
za`Jrn_{y(UtF##8#kZcFYc2lz`ugWjnZ87C&r3Wz%k;vPD=vY7f(#wv7PoHQO1ict
z^24`p&z>@saC39NxwltZPfrgts2vy-)RcI*t+U_0@)JvZ%}3V5EjdSz9XoXTH23zr
zyG<S{hn9LzfAHi<OH&gQs8#Xv(^CnX3WL`(j1C?@`s9DhvSrIE3M*4nRUbWi1e(D3
zSSTtgI%VqAja}-+^?yFHzvh_VbLUP>M07Osj~x>k8Kz91&ivy>?y(+8=KA{jDDcqx
zALkNwXfbK0`19w_j{bi4ni`vR@%#I>Y%#fV?V6LXFRz)I*^ZKzLa#e~Y$`vo6c!fl
zsQYX6=<(x^FD@!`urR%N@uEZh0%xmJL{!wKKCR;T`oE@=CQS+m3uAM2b)7MLwzGyv
zmwM~VmoGQ=od|JoU;vrk(!w%j+B7FeN5;Fm%f;u*FAV6|mV0|spJs78zr0wyf2n;&
zMpo9LYuCbR;(mR5tNrieTz?r^*@=@THFb4yf!2o{I^<O2d-LW^M|b!3QkS%}Gcy`r
zUth0mY&=<Q;Xl{uda)CxPQChI@5y`j<n~s5{dL<qyuJ^VPN1nHA0??QSqv@);0Xkg
zT0GpL8j#Y~%c^g0IMvnFbMEbleDqP(d)k9jQ?)&OeWw;0eQRoJ+EDT`=*6p7i}LU9
zyKw2!B#U<s4mKP49h<jqo!+%|vD)`$IQaVVf(q^_n!ya92E?K7_v`iJ&Ky%;8@2UN
z8?UrM@iU(e7o`;|RwUftR|{IR!=Rv}!_zIM`{?ST3s#`Xb(;zUFK=%}p-zLOBOG%q
zi`{DWL~qXn)yaKwwx<kKr40=YK{N2XN?)_3r>E!K+TvMbp2Ps^61KImDJdyQsH=WD
za`md{%9Sf`>?~Gav}n<X&*$xxO-)1ha9-rM|I+}PH2?Vcc+X^^%H)(37Jq+#o#<^m
z3=7t-<;~B}2TlJnY^eKN#lpg}V9An}R3A{gd$KERzWArh-m0%$6DLmO;NdxPxSd~7
zfaAz+p3kvyaq}veuKfJ`{OIJPt5&a$bWdKiY#CemyE}sZ9J}lOT5)l4DF|>}*jb!@
z<MwT39i5(1pJiFu*%PNt3wtkf_3f(L8<X8_s=jm-I+fkqQ>kpH|MBBT4_{x`(o)ka
zSFU_`ch~yb#~CZutvhyhw)xTLPmlFVYiMaTIVd<>Ul$7+myxwD+t7EC$Jc4<o3F30
zcXW3P&!4`#{JoQk&_dU4G0+OQy?br{eV+e+L!YKNxTp!1FO_+@;=YHw>~h6d7MB8#
zPwcVsyBx58VxN^??UlkMi~E#iOXsw$c<kXW3o2`Ton_svURit%JU+3{s;}fqq12+j
z!@jYxvW||9Gc1dj9eJFXm>97sg;QT#K~h5Ez>y;?fq{VmVPR>q?(1&cy0xhM{k=!l
zi*Mbyv7qwvvyQ$#x6)EmP_y{g*KC`L4-JJuH(y^~&d<gp(ZDNh#sC^QOU%mZ5?1$P
zV7PPV&V*UBy579WnPxb%^5-YjM~@$0TotMfY6U0=Ffep=b%EA?Ffy}!C}Lhz_xG2h
ziqOMjz0wt*pYeYA^5vDTL;UVC-9v{DPn<mYu-S^9E4p2OtzWIPw5$B^fN|fyU)g&q
zJ~A<Y7CU`>T?A^Bl)PwYWM)^gv6++Vqtt%q?%lxHSlxRpDTi7(cN9J4a&mGCh>ixW
zzdL;949|4^__R4wKn*ezc;n1YuwTwr$UmgBzu&#A%<Rh5tBJX}y7yS`-@7-j)aO~;
z{yJSd_rk)$AAi5!U$|mLhh6P21x3ZiQk$Itp`oqL?R<%Ue|<I4e53zLEjwm+8Sn3J
zZx?_5Z2#}iXaA3;r5_);rlhAkhlWm_ZoS7lC^ojYnVtWVsVbwd)6=k^pr(!vj;ebN
zR(`>O$1`P0WlpZRUjU9yXzlT{<CpJcm=vg4pezfkSbla``JqeA`M-4S+FsXgv4h8t
zyFV(lx3_0uWnH*qN5rv{H?r^Tu>`HmiQJsFu}`U-iJ5t0>FY3?sxKT`T3Qz6?_~D<
zd?vkO<w{2dfdy;U@Kk?$BY0nMu7B9tsMgxw-xRH_rM<koK#LQW`Oan&78YgzP3`~r
z`*&l}Q?Fy5oi>>u^YiX>RDOQ8aKi?Hwb9$xZD*+c{_gG!`+7SqEiDQ4sl2SLt!lli
zZy#V_$iIL5{{H&@FJDTwWL@?8W5rzaCq_<GwAHTm*Mj2b=Xiuq^?9f`1q2B6^z;~1
zeaT>uKMz{9D&1phW_Il4Wc5_pz`P^Jjy?ME@iA!FIV2=x!sN-!>gwtr)x_Q0+&X%C
zT)w}%dy`GIMZn1}a0|m+=m@yO?QOXer%z{>m6e681a#660i}1}f0KR{Z_B@L_t9nE
z@qYQmm7kw|RkMkVj&}C-?Jf05)6&wKFk^;>o%_j?CpGl-#qS3?X^13UTH?7T*(fk9
ztgWSm<>O9IPtSwDzrVk@H9P#q&6}O)`zKBme7(Zx>w|;MRl=O}ZL8UMd3nFQzV2_+
zxgr1lzCCv(_ix%Hbn@iMN1rFpn9))G{@%jc-`^fRKXYYeaOClnCbflL-=CbET=o3<
z$H&JXS$A=^I-NTiFy9zb2=rO?rCiD10nX)o=3udv{l9!4!^;6sqXbfSyj=14io5Lc
zLP%jD2~I*w7WW;_JuyMC;==>ROP4P%T(~gs{f*n(^Ai&j8HI&~V|ElY20E3=$jV+^
z?k~^6#<r>NlP72Zd1dhO1uIr`EOc%^bn)WEQWZ5VZSBCAn4W8Eqr0o`@2mYSASlS_
z>goy_1-rc5KYh-mwNIX;xVX7JdU<&{gPk6WtW}A|zF)7jkDa`6@zSM3t3p?AsQ8%F
z$$g==rUq0t+_@8T%rkZIrcIkJ8iLjau3xWz>C&ZyoSdFFZ*nA6ls~-ztw6f5F?r&Q
z864W$+6)5m{>zpv1NB)N`nj*>-`msq_;~-}yLacNrtAdexZB(FodW{}pFMjP5Ez&!
z+X>45DTw^f$i>AK5D?I?cyaRHPOVj|R;^ill9iQ}6|^+@%8I~<9R-TNzP;rJE%@H}
zq-pC`)1cts!02dhW8=+L!t7tae2F-o>=zj+sWg#8Oib(%XR*^lfnB?HtyydsTJFm$
zX~e?J#?ug>;c|YSZKjeUgSEBwoqe^^p`oD$rlxDleYa*`?<=)gmLa6Iz3}ldMLRpW
zojZ4CTwOKw$DbRwZ!a!?e{WCS`9+{29#SUkM`>P8>;cDk!Qwtdg8{<nOSw`g1&Mw{
zOLW(hCn=!z@vmRMBDQ2q{NXoUQc{wGkMG#&>H31w(%jP0(#Jeg-{0F?4Ql8yF*6&c
zosqa!$no<@Xn1(?rza;t9S9eti4~g{c6D)aurT#VoAa^r$$*ycJzlcOJn0C>o|>OR
z+w<;bZD82DVg<+D-Q}QZe?ED;Ggex~7cX7}&2JSI8S(J)K79HVwAyY_<mR+Biwy(g
z;`%OJ2)OTYDjv2L;K;FKO8WZzii(P$q3OUt!9F?Lu7l0&i=Er~)+C<-4a;?PcY}r#
zKi*f#eZf$3CuLda>M)DiUnbq4{u;;6Gf1&qSy}nDtis>lzkSjqp{noibmw&>WM^~h
z>grw#ocZCyhXY?<U!OR2Dl0E9??+jWH*eo2rluZ!Evxfdt##+lorym_JQUz+&A7kM
z_H{%Ns6(5Yn)>3-&doofHf`VTe!NdM(mnaql`A4MXU+@=4sPDMb?c8kprOyo&(GF8
z2Bm~vDO0X>>(&WywHg>0fO;GkR6_DfpC7w>SGM@sna18;-u(BcK81s`C?qb;?|`d+
z2*+Yl;C@gI0gp>W7X#EBc#N#{&Wgt-?=CI%o?)6TR#a4^Ai%*;v&TB4olh1tr)Xhq
zZR~f#?ft#IfdK&x;`(t8!NJ09ZEd__$GBLS?(D0b9q9BeZcjzyjvW?Ho<2>yvLevH
zz`!9lSGTLXd*RBJCr`H?DP6T{)r4u&+V<?RiHMGN1~q_Ho?TlL$!u?LUr|*BTKZsM
zX2!+<T30gLEZ51ygClHxT<_J@;l_Si)h}PZ+^}`4>-xC826=ZZK&zAY?b{a+8hZ5F
z+USqp-bRB~m>fCMQW}!>Z`X&Kr>CZV`0(Mu+e5_+pf2tIe}5-Vo!a{C?QLaiYw78F
zv7o^(7bU@6B`=!<mE9CHG&)K{W*Qh6G%R1P4jPyLCw-miOX=%t51-GkKQ_Pq-$|ua
zF$>Oeb11e<sOQ&pPzR5)JP{6wit1`<VL5XAxU!NG6TiG2sMoV<)v5^hWG!=ZaimVi
z@AvziJv}+6O`9gb)f%xqPxf_((ez1^l;#PP{ry!cA}R`+lmGf|Q9@eUF)KCWty{Nx
z`1-Cb@B8%m^TlPp(jR|r+`Jhy@&Ve#0U8vZ_UQ5BiL+*LH99oJ?XBuO-@SUZ_Ujo&
z;oomb%ggsmo98W9vV_IW&F$;DmFr@6Z|XbA;_LLZ?9ma<kCi7+oN(BjcJ|17-_qwx
zK`YObPqDtTm=t(Cv%`wd{FOPRu?VUiKxu;at8^ZuHP{Po7plNZ4PR$a9|P2egf>4;
zu6S(Xd-v<qsZ&`QUR+rz49YNZ6VADpm6iGa`Y$gpuitF)$yG%t@#G}c8{2ZFSFK(R
zYG8NE-QQQs?d<IQ<LA%Bi;G;>EH(nIZv64%$AT3rI2evRU$$TYLt0uIXtM=qR>)%M
zo6<Ko1pof}dU&C8yNcX=gG46KsP&VR!jkHf`872)XPD>5HT&x7=;#PYNpX35d%K;y
zv8&)A6KK)Nq)AN5%E})P6@$v=i!)|h6e^vYZ{I&-hJ=KKgoD5T`g=~VmwHcE($eCR
zl$7k5e5$Rhi_6K``Ssp?`|AJ8MQ_VF_~YZ_#EcA$f4}eTtu{<QC$p#i|2)@_XBnTF
zK)s3kh~C7Jl=O6EJ3G0;!a`6jxY)g)f#KGzTcGU%bNuR_Jb(Up`~AAZ$9knF&Ya2F
z=m1)Mer@B7-Sz+XRX91t#K^?$sbJLA)vbE>XZo2lK1YrmQBYA~0i`kr1&7j7)7KGa
zrcRyu@X5)^pr8SbdNb_VzsyBR5Oh3k)#TFR;^Kv?S9f1uAHTWpxQwsU)HOSHNSNo{
z5%8b2yY{!)s@1C#)6&|mTnV}MamJ#)%O+O}RY2`XScHR`jVD2U&%euFf+%nY0hA<M
zz^qBoJ_VQp^%!<QQjp?*bF-Wqpe-jl@%v<$*?10IkFSr-zxa5HX7GfmQ;(iL`t$eq
z_wDWN?04?oefZ{0&rIX=Yu4tV1@WGqoQoDOmQ<f=D=I3=!p@$2ZjPl;|N9#oneW&C
zx6K!Cxpwm8$%BjC`$5ffzqwWmi=UrcqiiTBDykY+k(ZO>!+l=$!quyw#jXz?KUV(e
zci+1F9cYa@sDJ<s=|x9N+u7Oq-uk0rVIi?^-@Zq^PCwer^c7kJoc_gLiGVB`{>k#@
z&dy+)iO-*&o-WYoVqjv@5}<M9(a~;25iZaUsB4BZtG>O7+{@`dbLLEjhOo6!i8nSR
z3UIad2yY6HjO=V`VtVrYxw5`KzpJaOK&Oj_o?e=4@6PY<?<*S`2L6%p^78|&L>Cbe
zxv)9i|JuhHCr_OciVrR<EIe`UT$_iA)9Y(%6Vua=TgerJhFZVBllAiU1`WGx+GNz>
zqBKi|{hjBES+i#KOx}2XRjBri*|Qg~Si#ZS+6o%;EGjB0`2H^T+Qk_Q`Yv05$B>jI
z!7&PIyY+%HxW)hOU%r<EpnV6l4nq8u!dY!rexL>+WJK!aipK@J>;K!$v#C_7oBMOM
z=VUcQ57#H55fKt<zO!27>;DM0wzl&2eSdM0IWRDgXVOM-35kw}hua??=@iz`(K&Kv
zrtxdp?OV1SxwbZ1a%r-6e7wAQ-kk?A4Rw!?@ove!?sshE4Q+k>;~yR#HcULkQc+Q{
zp!WASNTul$86Exj+1c43-l0Q>3{p>tXlQ9|>QgO0b^0`@Ts-%<)V5vU$JbX-Sorc1
z))(RHVj5SjT*(u3a`}oC8lcH&F)=Zr`^T+IU$s0xKi}BHjYF}eMlOTV3N+l#p*X*x
z^7FHUSFVKESh{M690HB5>g-I+$?38G|3_G9A_p5An*diUs5jE$q<H4cnTX@buMV|x
zKk}5^o_F_9JHPyeHIc><QBj93Ulw*+D6nnYwl&E{o0E=m9XWdR;kmiiKR!HU4hapt
zxII4}<QS)g0)KyfZ3Yc7&M-31yJPWDR>(z3(5mDGsEM~GVk48&LIE{3wKd8{#Xmo#
zel(prX;Rbo_xC|f(Y@8*kM&3zD~NDaT0iVmTUb>6;X&h%J4cQmfBf_FbAe75&_;n4
zC&juS583be*)643>u=2(9iJHnjGCI7bGomvFfr<jEl^icVPN?6^>z6B!sJ)SKA-&j
z{QS~?|MM;`V)gR!N}1tN2kIftn>TOH@vU38s_K1v+{`Jgrl6p}uxr<@AOC*8Pt3{T
zVF1n7HZ?bc25Z+uZS5-bx(VuSg7!`pK0dawPsuzeD2Rc<)z$UGr%z4Or%%7~k*Sek
zef<7ut|mJ#ZOsn9v!ihFK{xTzy5Dcj<8sfLRDH?NiQEJll>jwEpYPxn*8?q9<KW?$
zl4$kQX|_11H}_w!vE!a6B%e>L&cC;(aoaYt*Ahk9*VaTn;`A@Ie=(sSG@H9{VPoCj
zU!CVCPMs<m5)u;OKAHR0ty^Eu`QG1GdvQ&q@wJUJUf<lj{Kp)QR;Rdkr_Q=MIx^};
zZD{~C;r@VHH=rJ%$ukjA(ZsB*sP{XaCkNOE1q3iK%$PBw<9zSjxw2LzFAi8pR#U0z
z=3!p&z(GY-HSzAQQUR`3@Bm&P|N5(3TwDSiETHWan>KCwVJJS)g9TF0NG_Yg@8;$P
zn#BI|=TAUHM8~zY(T_hpJzY>##KZtv>wkS+taDnL+T$ggt}pYI1~s^}!`Drz$P?3#
z>j_@&r>L&po*TfnYV~SRuAO61$i&nL+Azk@z%Os-pdtiXyA9f|F=fh+^8F6x=H@F_
zt$K7~qVk%>Ct3?1AM>pJJN3zni;MpUN&VcKeqIh_<7~6srrEQldwP2Xg@v2-Vt0Wy
zA69>Rb8utwaZrE$T43s;O`C+m!oooP&u8c7_rKrwn=dUb4Yc|R)VQ2DvGH&_fAZ~Z
zxdw)YjzvXA;9VtYpuW0+x%u&be}Aj)3%9he0PQ^e`0-=UWbh1vT2upMJ@*N9HG6yc
z%F4<Y7Zx(lGS5F}#W%5d<;s;WZf;&)aY<(7`giUnPP1M;J3ITu-QDIQqN0)R6Rk}+
zr`~>fd3j=bI%L0s()AUOC+u$q6}0A0<}ZMCv3eKRIselGkNr=mZvx4J=4ZfjH@m^j
zaPXAPrIjmJCO$nib<dvHAL5T5Il{oe#v{SNu%qT@(d4*dP*z*y+FkJEgrJJ5s$+1l
z@Y?9@ZazLdGP1IuNk>rc`Sdj1=KcHaU#~DSPdz098e7WD%v`Z<-MZ~7-uK)8YnVD!
z6tn_9_x84peW!f9yttH<l|R0@Y0MyRzC*$&g=5W{H4^H{&tG0%E@4%oAtNJWQ2i~Z
z<i!QYM{b%|_)o^KjoQlf`r6v&rY5FUt5+{vv!(|$q0rFZ&mXov?ySYaoV|5_r5+#a
zJ-jvh`jPh!y}Z0utXs$S;p1me9lA03_=Rn`(bEEFE`qkD#Sv}k!gqHpK_wt)5`f{s
zrKR2lMMa>IcF+bvd3pIB3B#sBuWg`xAvbPBJbC)`;OW!cpv9w^nVLev!k__%7cX9H
z=sOV;87X<?%9R)HbM~)TwaO_fO6t?6PYJoXzUQa@pE!GV_m3YHAl+B5ivIfb3p92G
zQh)X8%gUC1Yd&pl?aM41_b>2V@#H<c0=+B%u0W+ABc)4LuDEZ)TRP_$q`6}btz%1N
zE``ABP7@b!)A(56@s;N<TmUVI0<}pZ+!g0f*q(p?(7k(dH*ek);A#cUZh{9WtH1Mg
zc6PqFx?23vqem4tr^oN9VAR&u*3i;=G&_Ia!EbMGgVxJmxpwW*5%8|P!)IrkXELh?
z^*1#!u`o4WIa|iU)L0?-_W8Sed#hjE+gm;PxPIIo2}eiA|4B+ezrDDq44&Wq^TRMJ
zJNx3wVD%llcQ4MqzHZH8Lt$y@?&9a?9v*CF*U;2#Y-?lNRra<EG{y7&)7kPZm5hol
z0-xS5%)bwrW&6o8$G%=}-MV!F;o<Gux10Z~me-7pjeYU*W#ajHwmia{zP`I_ZDD1V
zbfiO&gOl^%L}m90vuATNfVyf=PEOvKdRpw5=1osu-=iB64=-4^j?dTEH)d~@C<ACX
zC2+BuqMlw~uEViy`S<%k>sxN!0<B_lsH(DR=zqT4cedG${q^>bTXI07`p1qPldvw+
z5z~oiICI8_!67qK^UK$-f<i)vEEKKF-`{Ipy;|GE)b!#aSMDRnjxqiCF-Ow6OlMvE
z{&N<J*3Zw)ZJs$(^46BjW;xp`1x-!P1ILS#Gc!9kr=K_SJ8=%QL(kvezvTTrSx_#k
zsj+G3f1dX7(NPa?@8mfXc)??56Z=3p8MV*N3+Z!%+D-7T5~NdpSpb}BAeungA2jHa
z`|Zt5i;@=tSy@>T?h~!gojdpFd6x=klh5YOn|Xv!^85Pwf(rJVn^G%2K4Jx}FL-;)
zR76}Hv{t;MzyJBuN5u>mu3ta?_V#wrhB9V$K2Yg<e_w4!M@Pf%-PV&PO{&=c<ImA<
z@f(}dLAeyvqfUN*Z!f61_&UNzH(~<=x0ud>L#^CL|Np&S|M~g(blKpvIdkR|yuY{C
z?Rck)Qbk3@hfl?ae}8{3C?y5z@Rq#1#2ObD2U<RRZ*TR(w{OqBKKh&iw1C@pwwa=l
zk<iDFA1&(t*)%mZWqkZuAGy0s_ur4l{6BvEI&}Cj^ZmNtx;3@6h41g#M%93d-aqw=
zSYLp<)Gakkpb>%S=x7yHRnI?6_pV(N1GVQSon+V7*H=+j2lcbh&$nN1{&8jG=Cp$H
z^5Z*;pG&BvfHoL|dW3tczZ;~TnZY*s(5KIzHx@tlYva6mYk$4Hjjb&xbYgdxnOfL8
zEfjF?lS!O0q4&T62NpKAq=$z<S<z|l=S!<XwRh~?si>sXl;~6z6cm(@o7-z${tmRO
z;b8Hzqut_r_AUbryRq}jEdXs0FL@yV+5l*tf3KrF>e|(-t~oh6+j4Iovrv_$R@MIf
z>GXKebdzoMH<y3_0npmO;N^a%KaRVD78<P%UvJU>{Mj?m?!vatC*8AVN$uIYcjB~Z
zZJRb3g@lBFcIMgH*#!g#C(HJ)G|Rn}aDQK|hMwNBZgKq&e|{E=h>Jfy(8!!|c^U8P
z3ZK8v?f*Nr^T`_2{wi4$yIU;#`nscAGB01)S6f|CUA?*QxKBZWfm!~&J1^`(gD<U<
zCkq=H8Ce_;2@M5}`G7L#GXME{hf6*=hK7oAi|J%sa;jz8Q~O&?-G3ga2Ouabd)BJ&
z4s0xi9Z~*Im^iU<WAbq(1{NmA=EtC!<xihJrO0~cxwyC-xO^G3;;d!Tq@d=<YHDgH
zPM(}tYhd}{>C;yI{eOhMzrTOHjaT}WuLDB^BQsma`<%n>jg5^Gb~P4$b1WJsD!ZFm
z<Yi`Req~>9J~SgkL(Oka2d}i*0{{7Tkd6z#yj{wK9$S5V{gPK#IQivlK-=r2VuC^Y
z^^%g57MJ8)R0+vDJx#ZH*Dfm~W8=avFD|m3pS{qzz3cswqvq6#Y4fr-5lfaWd-U(`
z?;j7_<w4t1ckJGM{kM75myBzMGbetri&NLu=6?0+m64CLohefzL+<Tut^4-bf!ZR+
z6Z2kQTMHUmV&j+V0o9Suo++7|i*MYx5md2*R-8?kAaKnvby?--XBKsTEM7|#y?k|b
zbwF_N;RZ(L55M2<H@Aq3i|bQ#ZhLTMrg6l+8q2b`w~i{PR^Q!Se*E+E^O46VNQ0vB
z!b0c3fPjGa@6Ge?wRCoJ9_y8EckLDf9V-Gl?*lY%qdHYTG&J<Y`Sb2^adFM{puGJv
zU8?T3FQgKgXq}anrJ=9?+-Ba~xxBidwSbfK^Y86(oURvZ(ckT&6cQG8%3$Ij4^Pj7
z{r3M({FJ$L{knTzo?dgxC(sEKAHIBfVzX}T+TKHloFvsI@t>b(d-&2)Z_EDGt5-jM
zdwaW)kBU9?5P)ZAXM6woc<jIdhgWl%?b1O**E~Ed4wD1^zq++G`@^?y$He1n6hE3C
zy>UZAKW<OLgdSUP(GDIl2iN;M{@Q<gXQQ?1*Z;>qUh{P{Jesy>k;aOp)3PPkt$4ts
zG>conXvdQ_?`3trpG}gU_AE?u*|S;8j68NMf8><)Zst_Yr+r=0N^D%4Gz#kLe-!8J
zJ2O{O<GHcL`s0@KE*G>H-@9vUY%}%u&ls~lBQUCaBmMY>#VHK*Yhz(g@?#AoBvJO@
z0OLjFh$)~At#@~o-a5WH?d+jfS66e}=<Dk8?*IEux~8V)jO9F6%kp<JpuyCZ7M3N;
zmWkcC<2XrW^<L*c&FuUFva-1!?nFFpx(Qm_S65eeV_WX*bJyq2oqKUzto4uIzmrc+
zQmr!oTP2yAp02E~@Bc+Y?Bw0MvY=I*d-m*k@b+!5eBBSmUMW*1h9%3EffjRFRDM!<
zc4lVshWfa&`8A(7K?}G*hjRGNHd}ODP|wInh+ode;b@m=={`9rsjewgL_kvlpjAre
z=2~w|J1bT5@8|OwMyXv3GLKgM`C*uLc2;ZX>ad63-ri=d^RqpCUPDP~(V~Y;B}z(4
zN{f;};{~8}f2>b7`awidkx|&1h(^8GT^uvc812}-`|+8X#$Ct1zrWvK_4U=vLZ#CS
z-|I=&m;e5jJ4Gw>l+Wdec|}i8N$x3lerIR#ilC)klIojy&Ye5Aqw@2zM;}4EvDd9z
zmp11_k;LtjcW2!X-op_Z85cM2;B{9oFD|bs8i~g`b=akk8-U}^=vyx&5+NiBQF(1$
ztTiYq+xg|Q-m7VQ3cb6(zhB*d-U}P|Nh(vcLb*Uoz$+?tG-w`;-kv9Wull|16pcWp
z(%09n-ah2jeKW4Cu(0sO-QDJwE?*8@6{0ysJAB=N;xD;bsl4mr_IB~x{c!kLaeZCv
z*Kfv=%V(KpKYDPm`IhU8!otE8F*}W{%HDKvi|ZvE?GlwR$(ZoMu=Urs+xdYTlU%oC
zU+4S!`g;5B-PSTPG9~krJ%tu6Ud-y75x3lbep}SqYd>#w3af*bu(!0fCSF?;$<T0b
zZ?&?fCa1J{-j-XeFBZG?9y&Eu`{C=?-Ga()5pVZr3JMDD)zG@gEFdT-C^)guIPDB*
z9_8Ym%3{!NrAaD^dU|{hA3n^uu|e_Er%!9Xi8nGBBphH^6SGsuy8PXhI^RhupgD$X
zYa&5QMcMe}bPAjbqqbx;`p!0cX*+G^%udtnYYTF3Z%dnZs_4hBUr9&1M62FUD1de_
z{{8#Mq$a%Dy<aY3SBd7j*xg|dZv6ZEdt=qtEEX1)8TAI-4<0^j)Q#Tu!gku!sjXYH
zuOGU6`SO|I$hLIxg|BWK{<!J7Vy;!GkipCf-`QqI-`(B)RqpiZ(}&x5r7!HMEH?H}
zmAqlmwy|&u2<3xG2)po0@_mWp#{!R`ql^8$$uiRJk_dF%#M06dR7iskRhTkG<l<uv
z<Dw@XbF9nxKn>UKZtiJ1k&9~oyg5I={$D3(qmuV@y{)%=^$#6Bd~r)=Flf)fa{u|q
z8kyO@{M+c3e7w)~XqV{6)B5`rY;9%D^X_PTP&YIT{4&ESWKD$N$B!Sojz50<nETGo
zAF1hUXA90)<<=|p<KuDpz<o89B`+>8f|mG9)eZ-h6<@p0GlI^^0`<Y?%$-~K|6lDK
zt5U9ZetEqQ$D>r#)fb1Yjk1cry*Zs<#nZ{dqvPE5+S*#sj9YPEdSFsg5-2V~n?8lr
zd>kSoX56!Pad8Q8F#;t9K~e7Xb8{x%-kPoMJ!#43<CiZ7_x1OS+s+H9tgI{oZ4CFE
z^ybkcCGSZpyLazC?dRvWNyW41{=Qn*evLC5laHrZTU+mp-kw(!5;8@{bCQgppyK+t
zy-{_4zg|yeXJ`Mp{eGRW?J@)N{CiVkV`5Um!^406{eFLXsMgd!_p0BY{QLX+bXggh
zC$mhmPn|q@a?x><-B+%J>~w5qE1GGP`sCf+-KVvtdVTx+c{0d_t3$MQdQMg=a&v2Y
zVc2R>^rRyvJzf3#o14M^-tB&$;yLMwYq!|R*VoogmNv`LxPANf>HYtHt$tzH`s4F?
z`=^^yPoK))`*oU4`Z<}%r9mf!)%~U{_noa~ZEby8R4ZhHu#k{TzvhuXS?iRkUaI^5
z|NH%EqOv>4)E6%@ejaFKE;`;Pn;IP*4Pq}kF4ES!xCer2VGJlYSpt!+P|_H*$buAH
zW_^W%f`UaqKRr#I>ZQ6mMC)g}eBFf9$Z7BI?pELb>6G@TRiUd{{5_@}yLT@xZc|F<
z3qzftlao}RwsMPi$sJbel`{3(wsGUc=jZ3^r>CZ7?w>bzuC9K>28V51w@!8Mm(wk9
z`aDU+Gw;%p&O1xJ#V7y!@$+Y=+|3+0+o~m>pC4-F-ZXpm>^Co7Xyo7Bwe`S9_kOuf
zxtTf*-QC@Pem<Z7x@K+i@xD!S=gyrobLPs=U-S3<bkhr6HO2DyW{uR-)22?>i`A;)
zQBqnoeVWSYO*&PAHsItmQ%_Zub-G@xQ(c{1*7bF{Tdf0LZ?68Hmvd)F;PXE$tgHvm
zpZEWg;q><QcK*Zd{O(RpP3NxPy>n+n(NnLA>T2#;XN*97uR|@IpamnBE?;J3Sn4&^
z>HIuf!}51At84pH)6zhvC*Ar!Md$R2(A8p1O-%-Me=4SEg?fGII0RZYdAObb_}ACh
z8Ex(!jh>bYI&BGb%FCUdn;&o<wXFW8<JKz$S`hTIX0PvTGtjvyACF1rbIkJD13F6O
z%nU;hfB$x!)3@&4_nxi?TBWlv|Ng!vb&-B><jPCCOa694E;kIm^(N-X{KaTIv~4Wp
zNq+nSx%Amq^)(B0e8j<n2VdOTY0Sna)3IZR#oOmT0RaM+E?wGC{yy&D<gVf`F9JdH
zA-{jEjNGgS8XCB^Hkx~$&zxsxXD=>(e(uMY%l@wYNrh4-84O#adOL;HyX1~OTC#jO
zXzz?g*&7KN8JP#KUU4yi_F-(=wCTdG(rnO46D2P%HL08OPxWd&HC0>u)&K98mU`<K
zD4kvyw36$N?7y2ra<%2X(^WWk?%bI+vsY(&e?R}FOP31%{3u)zqNSp$dhqUD+1%UP
zj?S~KE}3VYdP>B_-Tm>Sqwmh}oPezb=x$mjs%>H-QdwEq(bXkn%Oxmy(YurTLT3jE
ztZC3W{p0EM_!7N}Pai%scr6vOopp3Vs-&l<C#c;zRVy?hIa#?%WmCe>pFb@sKP@>|
zy$ZD0ZtGT2+gYv;Tvz;Bx_mik!}X4upPRnj0d<K}PfruIl?vQ=^q65!t#d1g>Rl`^
z-TvbK@neQPz1T%Au6Jx^tN3~~95gg?XMer?RISiUkqvg~=fIokw&&dyvRV1lw(=9p
z!i5V#`(aZe+a^yIZdiU-*;5F#BCGCi)#@5vS=%a+#>PgFf~c)os#P-Gn<_u2fll;s
z@0WA!l`?hdPcHoQ`7>x}HFkHIqM@PSfy=(KfByUt5D-WRox3<_C1_z}OG`_K+|frq
zGYlNxI~6;pot^cyY1zga`@df%-|GzmorO_h^x3N7gTkJ@dp}-_&OdngFmv_ycdkxO
zOl5CwH0s6fdSSCY^YXG4;p^vJ)jP1S@G%=`|L(Q5(aJhHJf>M!F8uzk>F(~%cv(<T
zP_#a#!Oz9T#U-WDM2eRo<A314o5{&P`hS3gPTsI^adG*wDe=C5py0*R9lg#jE=Q;C
z-D?ZlE3?qK{Z(wkzNDjEJyNDzH*el-Qa9bdGI)8?u^vg#<_)_)ADly0hw(BL{Qj0(
z^YN%SXbNYU&&;NmmzQ(TyYgpO`TIWa>3R<z9qq38`}O))y_m@=oS;1<CJQb8|2$t`
z@Zo{u9Q%5?ef#zml$Ktt&fE9n5x1l8q@@p-N`5UbDlWdbzrH@_#s<bsI)@J)WMr5y
zbt<dpBmo(jo~_x}qprI7zP`TRy`sWmUEE%-@bGY-83v4p+juWmp8NOr_ru4JoAdYo
zy_R*qUTZ4XBo)VLsYlPssdzf&<*l0u8sMn1EMT+(m0uHCtG@LoMMg$$*u2>|(>=y>
z(uC>L)7xGi$-c2cF+@wW?&ni+(Avwu#cpo<-6yGlPLEBS;kPFFcpqa!S@^s3{@#t#
zV)xkpeq-!0Y02H#ADhqH8UM1Kq>}jPNN3s%zc~w?+npw<)cpN=Jz!;sgjLCki|;3@
zaGsu~YkasQX|7GB5W|Cq4;OyEF(dta{mhR_A*tK*@3S%N*s<e<joGuCpX1YVWDY}%
z8gt|h%dd_3Xk8UZx8=q0V}^a;k_%c_^#)snt_nHGE??8oZ~rgiJ=2$s$;XpUPt)B|
z_IB0{M^;doYGZ5r@$L5euWawFkGGextC0v_A7}bG<<ZWaJ0<s8Z&dO0@bECW>@uxc
zHY290%8F0MV!_{-!t!$W-DPhBmib6-Y@R78zCb*-sK`hwWCcTXbo9l=9HMe^eg1Yo
zS>EseZ)f-CgY%U&k-`iUX3Xf&-}i$FwA~DJz(MBaWt{V_{Nd4Eqn7c%F7?cs$jxUA
zctNSL9a@U$T$rjI&cLuW`}(!YoHLuB?|;L@#H8RUWR`P-L0Ve+ZE|u_QqmcNxe>qg
zxQt8k=KW>fy7iCI1o5*k!}nH|t_abJ*;&M@>NUmT>#M82zgVl2k`~QW6KQ|1nObA7
zsr}~lGs$cVb4Vcns9e)C|2Qa=f6NOy_I-+xSs%1}flVey2GoZ{meHEi$jqMf|KDHG
zTBlE+K9z_q`2X>^Jm~l)P|**r#;?A4^Y$%h9|w=TUCjHBpbla3@xHC6b|0Q>6m0Lk
z=4IcJdh_aUIiT%Jk&%%<eoq3O{^>Kzgj2r$&&C5U&vbKN=zjL@?(TxZ!h`#2e{Y$+
zG-7qs)~to0tHUDp*X_Oc7<7nN*_#=md2FBdr$ipxTm5}UA)}z6;7r!+W>Beog6ZnI
z*y!it!q-X;_Gy~s-O2c{(e(EAe0hcg=g#>(H?;lw<fJge`TCzf-)!8vyYln0gU7Gw
zn3;(k`279K=Ho0eyGl3@d@la{#*p#!bp3V}PmRDuE$5Px9!ngCG`ja8x4tj-*P^w%
zq3t7kv%bO{nN$Rtb7-bvGTSWk{602bsRhy7^CqZpf`&2o{d^{!b88D{=;|=gAtJ8*
znl4+ju7Wn}9A$mc&M)t_HS6jb8_`Is?AVCBuA7_FA3yH5cRSuEYgqKeW6!r+*$fS!
zZr8_0M?o`jAzGrK12-yyK6mu?x;{SE>)Icv^RaG{|J_}s+-sw^huPfQRhs>8@9Y1n
z>gvUhnUs{2jHK@|&IJdYQ|S6Q+1g)U96dZZW|`$`RmpU3PCF|FTIpW$^3o#rg-Opq
zL;TU(*1Ry(IrsDP^T73SwilBF3_riolX7W22(F=A4}t<{;i81c0g2!|91yqx)OlH<
zal;}c0-UHqM8LuFYrBfNI><N2o}HaNaoRLC2GD%X`+Iv0tH0$~SX*<?3jm#PoBZp`
zO9{gymScUgtM4W}J2h21VnYJsG@Zz%%*)Fnk23u|a>Rwfp;yYZL{9qio1ZQW4_>|M
za_f~!e12{&Yv0LDJofhXb8M@xtuhbw^zd+Sa$*V!4*sgQiI0m*$Y5&fL)i=SAIo0w
zE&u*5He_v-XklSt*w0-vt;_XPJP+0X{~hl!sby#JbE&^_o|8UYbeEr*Xa#B{@{2DJ
z1{JW8E1sR5{rLI(`Zg8M717)EoSdCO6G=OE@9vg6tF$6S3$#}~dV5~L>Z>m<E#=P1
z&2{Zh6^z=F(YUYnw~~ei$5gFQA=|#Ag#`r-`}f;l$uiwl_IB0Y&AnTLSB6x)Ub}rk
z*lIx;nI5gsRUL9CleT1DW~=@E%{3uGK`Ug1LX}MSq3(dGtnBQd&CVabetkNZ@gL<w
z2_kp*R)3!`e}2E$R4vD)L7j5$EAHHh;gK+4km_Zdq>@>m_Vn2^r)jAxu4b)?+<Z){
z%42De<0O@o)YOCL&iVbmF=Njj8)F~!uudV>1wku8!?HrEUJG10h1|~fs(79_dD8H5
z%e2KMFE7n7&zEcCmtXh&2k6+TygL>tDJe55jXr{Q$}lpsfjWr{U+zDQo}{w6!e27^
zEqCYtyjNFN&af<21GRcLCLdpvc6JuSynXXPQ#h^M;z_5bXmarLi(9W?-SDlK`^#S$
z^S1exE-o&v$5~&1+6gXVI*N*n6DLl*u_2N9++1sR&q)^+xpKF(wSgjI{hm)<F9cg}
zZc61gk>V|Tcc*jC9GNNl@p6rgjRC8#W?Wv@`{H9uQDLEDP>@hgZZ2pZY{k{AFE1`K
z_x1HHa^KAHe&26BP&4Muo17`S(PE5@j39m2*Uf!#u|>+h&Suf##S>@D;E<M<uBfbZ
zTpPAHe0^L&QIU}Cynw0N;h@qiV37;wk6*u>)`o$OcH6LhySVMFf;}9eGxzSboo7?o
z#3ibwprOH`sHm86ch}Yz8+F*=oimh%yu0M@V+OFE8DuaCP9}mgAiQ+CoRXGy=;~Eb
zVKtuzvU<FrO<EhXuj_#h3t<S@oaX!E=g)^{&F_oY%>20~ax>c`m4)&9>n5mp{=PBe
z-{0S}6RkF?`Oo9=oCF&4UlF49HaXeu@0Va>pY%x3x|H(r@-;C#gWi91Y-W4->+9=|
z?r!7HDUW{s`0?Pw!^1P|YOQQ+Z9&5Xd(W?q-o9?8`eqydc{T?@?VN`X7go$$<C>QT
z%2%M%fE_2P+_-s@kwMPBjwf>3$9KEmC*9pudglxGogEKuE>l<ao^}OXiwX-020nzg
zfdUOdCmXo9xhYv$Ntx&0bLkXP1#PrhaW!kt=X2Ht1qA}Oi$G^n+}M&SY$C<`?fw1!
zKYwa=?AoQIqQU|S=L-uOUkIM{o0bYXT~?}>EqYsyV^oxs*Ho?6@_Uu+SzD#%T9<F@
ziapI+`Q?S6S^hnqUbkk@kY;6NWkF%##eI2F=6O0*E{S~db|5Lx6ql+h>$h*;tjhB@
z9<wfd^89)7{e86;GE8plD%HMp`SQajPg>^LR)Z3Ob30#H?Qxd4mR0wg+4(mVK6cA6
zk^1xFasPx=Nz<$=4N+^|JUlq!>i?ErRF2{?>#NI|(*znl%I8UbEOG=?CNGwkK5p_x
zIu$Ab>c$~SfRX}42TUUN>8YvU-PjU_PG2;{6z%NpY1Q)y&O8j-m-qU0_kslqJu;R;
zS67F#Gk~_#f_9Dj`0#vtbF<m1^cBavD}Q8UWexN0SlnCrs~(iJ?%tIJP3X7F*J)JA
zbb}7k-YdPdqN0Lh-kG9;$4!TJR)5#aySpnjboN^TLBYSXcQAk}q!kjsJ|36fy1&HV
z*VlDr(9#Qw-TBwV?hgBs;dFO*Ilr`7jzdU@h~FFwM$btX7C17$of|Xn@22CkZ0i0<
zfQI>YG9TAozo)7Eeyunt7H@7^`a-bP+tbsrq{PHTiWj7jVMYA@ecwuhH>dd?6z-Zh
zeR})d-Q~`UFDCr{_V&b?GcG%eo(f1vbWE5auqF3)*q08cCr_S$<UldCx7r+(4Aaxo
zK?g{xsIcVk|GVvlVCy5-6~9zfRTZ_gxB>$ML5K3Hcseb1>jmvHc<>-0WObPDmkzOJ
zP`_@uf>~c8C}u$Y?Y51DUy>isXakMD1Pj2%gX_R;w_h6zeZcJx&5mB^XpFsCU!t;G
z&w-zxpMN~eZ$G2t`m^bCy_PyXKGwSsTxaA=wQv8&3)+<kDjd1R^+4S+P>%yNCAThi
zw@d%0L!qleRvvin<>$v|WMsr3vPU@o<)x*d{bIYz-_I%!;0{<DWeVzgEOzS^vh6xr
zSXSm%QDI^3r8v3paZ`QXvoqiW#Xo)e<kIit;u4}$2<dhN8kW7kXA3%9<My`PW);sr
z?wj`SEPE?uBE<{ZaQA$Ez0=a5hbJeiFFG#dbzjy3bh<*=>W?SY=Xc1RSBlwR7yElx
zXMcaYif6{%U8a1pRw`8{3pZ`rw4wBMn2W0`Xq~``vu8oG^Xp=Ft5umS{Bl=vW!c+X
z9K5`cMwGgYzSGtBpPrt+W!)RQqkvIsDp&69ZJ={&+4y8Ms%*Lsf*Nz+zyueXpuhwV
zdK}w`ly7=KaReHduLHMR+BOz)B|Vk^558XP?+w1N(77G74G}Z|>fFZDID7W&d%dM=
zp7PC@tmX^a&sgyFRcP+%6<0x{!V7Y4Zd!C)+iXXH?@ZIVvmZQopp=^<C@T7uY1zh{
zhYug#*j=s<DjuYzr7u2?n38z7?ct}Vr#rg4g>AcBe>|D&e_?gFzDdRfhc6mpz0%@;
zjIVv!+||+X!u0`c5<^X0ogK8w)kKOnDLHxK<jKveLRW*19*VE|*!tq5&atE2;tMZk
zEV!6a@bgpZjT<*2{<_-MPoFZS<>BG>&x;ILpP!$9{79#8W!*o}DkjjfsYR~c0@Bi_
zKYy|Zt*V=-?EcAgF}uD~=(pGF_dlBKZwFddQki$)n4u^nxqj<~Bv()$<A%lgjrl&{
zVT;A^fCSe-=ZbS=E`vvtG{6H&hCRKXr+6*B^l$sV)<v6iqM!b>tovgD@<vh;=yZ=s
zs@{jrpXbloD)sN*zYUu=3)?PoeSF9?)y90udC<C++FvCnHuW5AW<PxOYUq2X5_@}l
z#><_hUtR>Zw6-oRdU{I2s$|6@H_cutQz3)7KUaomt%=_+r>LmN(6ImCFYc?W!`*Xo
zbZ%|UR<E!+eXy7NpX9$aN=iz<(sNw-9l(u-V^5zySJu<x1C{;T^Nt>F=LZ$g4<00}
zxSCb+;=)3Y-Ea2gyt}irdBqA1Q0e^bcK(D^$^3mk)j;PVv9Pmu%biyOjd4r$vR%A*
zaYym<zHj2ES?=sA_5S?}G=Qvl+Q`PnW<l6$*M7At8<UT35myFnN4R%S&e72^tUhj@
zW$mvm-)u`CAL9kh+3ef5Z_#m~a~E7!u&Ai3Cm(L(y^vu7nlocq;5k{XX}M5yZ?Y7)
z2lDp@s9OywS|pAgtL&;xwt`B4CJ2!vdeJ3H*2e9P`obZ$GWGN{&^9L}C8Z7d_wC-E
z|FSlE`y!v2MxePOCnu)|Z{O-xg(y{VetB`x`S<<z`~UAdXXrU;O_{L(!-p?lSQtRV
zuND;_5*i<0tI2Cv{{R2Yn>WLL|6ji(|NcG>Zf@sxK3QlNP8Qax-XN^*_u`FHZgw{4
z5N%K>zrQE@?c29S?jm}+y1dfnc`a^>4?aBH4%$^$US94q%Y-v)t5oUhYofM`3eLaV
z06J9r^mKh@hFjZmyI)>ju54f+02*AgS!l6x<x0?L4Q`9UD~smO@3$&_mGJ7y%7E2Z
zR|GHbdm-2gI-A>V@xeA;>4Lw%N<AjA<mcyunt89Ta{KxDEpivpQdD&OJr8uD1H*#Q
z)nTCH44ayo0v0;49u)36*d4&@?eBklneS{+UVCtW5wu$D>{(v<`agzF&d%UolkzN4
z>EjmAm_Uu9zFK(Pp+-?3B2u9eQ@*~xAOD3z%y((f!Q;o-?d<GMoIDB2lpyb)IN`A-
zZm*P{p5Bha$89eRJG-V<e}DJz%gf84iI-2GKXc3QgZn@c8#iuT<h~)|^mP60ulDB$
zUn~H34256=ojM_JZ*47nd&`u;zdq6?_m;`(|EVAEgKmKWRfC(;`HPB*KAh5CpYY<s
zLJnSD*VEH<UHjGN?6b}>$+;o0Iqj^IhX=>1@b!9CE{UK*JomO)hKbahySv5v<?Y)x
zZ#H)8li}PN#mmpne^HsM@b9lu7gtwM_4)DR#|f#DpeeEyfr~FJ_m>Y@8RYt<!|Cr|
zKX=fHFDa33e}8@b_;UGtP(vy0?5suZB5mRewW|O80G(3H*z49DySoguiFEy*Ph4$0
zl1&#b1b}vae(7-90BY?>96NTgA5`B$>r_eU<qF?=3t?666j&jp0clG0f$Ls-aHBdg
zXU?JB#n1UBO`aUM+)oxfUT-0`Jmush&>FlqZ{LEp3)xnGd+_b;?M26xw9Mq}>v|NO
z+Z+~Oe4%4gzfItaWOhu$yT^}}t5~{CD?TJ#R1Ppa(#y?tYisuOljrvqJUqlbr=_Fg
z#Z&c@n{>M6nm}Fj4z8-dU$29fP)(R1uw&=WPPyZcpnc5h@9#Kxd0YGY`Ezo29v5S%
zsIJa_zv1DlS6z0szZ}+vElxb#2I`<J^`7n)7A6MTVY%3yAC$9RUEwq{Gh5^??6owA
zk>SqWyMjVOOk1OJL(4xIE-8L~?v}Oe&K)~4-m_fYk{Nt)G3WRF;tN+@&5CRJ^&d3s
zqZ_^L!NbGt8@6wE-=24OLD=exOTEQc|F49MU4usHKmiP@0zmBE#qz(8S%5<jTo*uB
zEP#fhz;!I7=75l`n{#iQfsO>4t{2P1@aFb*{(JZCd3bs{F87;jQ2Hw5%bT0QAEqS9
zT9t4}^|H-2%RLld|Cg1Wo&9Zk&~&|6m;Q7yKR-V;{b!)`Fwdqk$+UbL=txN4y1bwu
zp?CN8W}7~L_8xQ=K4{1;c$tsm>aevB9zSlLsvQnG%Uw`Va7X=ryRdaJkt;s`H1hKB
z0L?NpGMHvxb6Fd;mBrs>n#<Cl#B*~jU)<WN&7h#G%bR;^%R$hgR(mRo_ul{f>-GBC
z#V(ryz=O00ZxroFKmSnnQD;X-S08lruWR9-KQ*8>bm*#(#<_Fnz9?(~twX5#_NMdF
zQtxiLqmM#X1TZ4?A`5l;=FgW0jWR5D=Lel0B6mE=X7}bc(|ae6&nS9&YGL^LxPaAH
zK?iTFJ5+zTJ7DU~Tel9~zAc@#Rcdeb_h;v|g*O)7uxJB~$>dJ~%`bxnXQpf{<m#{e
zECTOIA{fg*+_3ORQa5E|q0jff-|sJW@0SDB3RdOsK<B3(IeHXyOc=w1_wV_orKNLj
zZ}a`I<XQQzFPRx8QlN>IXJ=;ztPBBd>bjC;TJ_~cVrhA&yg`D)!u#H<!`Ih2UXGY%
zmU~O&*Bu$Vnjfsb$vZ)3dM<Qk2TkaIe}CV7sn^sk^UXKuERNk>mT_l?;l5w5v@b5^
z+F1QP@6U7l|C$BQA69*R_3*U*{w=R|FM0mtNy6)EYe7BPj}HzqKY9NAwaj$zxU{gz
z+)CSMmp|p_#kjQ}DkU*B*j9fN`BlB<XK{N+$BX&!=F|(wAmqh&SA2I}x_sHN?oUOJ
zq%qt2z29cNC_MA-<KyFDwFj@;e|&OMSjN6irdQhB?dGOb*ZyR~O`A7^`l_H3d8&4}
zm~G$9r%#?NNI5xa(Q%EkHGh?^ELoxgF3BX0@`2h-eA3G`z}0lloJ9$bHxzPpg9a7b
zdxIh4WM+PW8wzh&fF^_bdJiAd<O1a$KI!8j`TPHxc}>^rWoG9Si4fpoFit;rWK-&C
z(2ntnpwAv29u01b9YaDy&ds;ykDT`L+wFX16BChx2M?|YSvl#2U}u+Zb#-;k*Q?>6
z)m=u$#(}#^GIQ?lll}MaA43CZIo7crNe?eC(Bu(ldb6&sZbi^iF3{SrUteD{Gk_LS
zgDxM?)a2Z_apQ{{8y7$DJgaYLC@5=H0y<|Mbc9P!4-aS<gkR34LFe>}fQ3vlva)NR
zJr4;KyVc&>y0^hoN8VgdK}ks|Fk}%shz707i3>VqWNf@K=cdt}J(a;<G@K-MEqMO!
z?(Pj6H-bh5&RPV1{CGXS9<+RW|DR9YF9LN=HM8@7xL5uDA?WfC+b)4Ny%(N-er<E-
z%JRwCWbA9~>a70$4m98A-X|jnmXGrD^mJSswG}iSXzUkK1IiDDH!L8dmx+%>SfxSX
z|3>=o4GVCrXe2-0P}tQ34gbU(8E~vj0p+D-UH$#;0Ra;peLOW)TiMd`W{+@Z=yE?<
zpSf0|pn;4lD}zC6>;HVY>@Q)OB_clm|Nb*)e7?N8$~|%7M9`?}v70v~SFT*izyP|#
zKs%gITtDuLT>Y09f=0&1uD$9Z6%`h*uCMP09b<QSnXhv|fB<NcIQN#xpO44oSA?&Z
zJ9PN4Yrp1^9fgl4Oq$fB?A`}Dmt{h#B<N^5H#fGlb8|qaw#Zl%IDDCrCM+fv_QL*}
zhM}P#uat?ye7o8WB`<?O>*l4+^FSx^Z76!`m2+>8B&bzzTm>}PIc4n&MsW4BB16Sf
z$hOJ#ajXBSiaegjKQHz_ceRh4HgWds=!Epds;>3Ye?NWtRPgqeX-aBpr`%DcjfFgq
ze|t%u?=_kyooZwL3&elz2C728^%mB|Yd+o?c&vDF&vTGaV$EI1^s-^!d+k&k^HUXh
zQ$F5#as1fDr!QV~xcAFx%K3YE9ME3BC+S${5h>Fwkt<oIHa0dc{Ye{TWMu`##oP5_
zcXh}eRl2jUcDKj<=Z_wJ()UmLX=7spx>Dk8vc0`MXkFNf$jxe>K7R(yQmn3hKi95S
z$~gU;%S@wGE*b6MWjvrt?c`*2?ioINcI>bKjdXz4u7IkR2QSYTv9q)L%&`y@*NZtY
z!!Y^7-|zRi=S|T$dEZ>G;_cS!58k}#>6JELlzMs^c$8W{zHi44i;Ky#u1-?*=K5=^
z?ABAkI9WhYaPJ@3AjgbH`Zqe`c;ZZ!%b({KWsNrn4UaFXm$&bq`teRc;D=J@)}#9r
zs|-OiG0)q&n$}Be>6r0d>^^utIn~BIg-c&wA9S~)gmIcrW3s2GXT-)N)<1v$vihjG
zxwy1^+yDH`%;pOh0zktK4_v0L^qp-6S{2mBBdJs+@^Dr7`nV<MZ|~W&N8F${Rob#h
z1vEf8d2;h4Rd3Kt=!b9L+!7KL7#6toN?E;k%uY&AZ)fM1(~ztG@j>y;n>S}HCO$oJ
z=1j}(-PR1CgBd5OJbZY#{nleph`Gzxs$|(b1fAWUd)rJ!MMc5XbnAip)~cR|=2#Z9
z_^R`n>uJ3B`~Cj)e|wCc-d9)gd<5#sE>Z$hpk;Y0oLado3LY@bGRah`66sD!Pj3gU
z836U9-4`Zxh@X9V{Iiqm!Rx%DV&HOAR1_)D4(>DT>veWL3J#_ak(#>!i5o!69|HnE
zevXhl&pR{e*_oLc7Z<VKtNWeH!p7z_N#)JW&FsIwzdyby^|Zoiqh-FcFWY#%fUN~k
ztMX9<?N{`ithO-s_O=(dx9c-8F+F(lM5Rindqc)Wr5`_jBz$^u5_Ie@xUs8}I88r(
z-DZZ^X{kC<TR^A8yUw?(4cML+%K#d**_e2k?aHc9Ze{mA5z}=6adB}UK7G1mS5{nn
z_-MB{Xra}CW5?KdrOjMUPEuv{)99N%U0h5rrX%m}F3@1?70a?;Uot^k0`J|s*R)Ld
z^wq1P+w<-+F@XAqdU|@GBVMb%z2RioQSgxI&D*!GeHv#LI=2f52sHfu{$9Im{#HGQ
z=f_xoP1T7M`uFc2=p5j`zrMQmJG;1ixil%|-)b4q^v1-a(iQ~@hYlSAtxMZ`+<%@;
z=Th(KpdBTKpHo8aq@<^VZcf>^Z{LcTots`1>iE^w+2!5Y(Wn)=D&nm^)5?NPn>Pze
zN_MV`-Mz?bs@9_88#O>hB4``W5>Mf{l%Mu;wpA_X?f=XC{r$at_Uzd&3R{vMU)bN;
zySS&;*%drW6A13MI{#M#*L$L@(6-5QO*6i~vu}WULLnkKbDBWg13-%v*!g5GL>{=d
zueMqzZqJP@aShPamsBs?#EBC@m$89v7Fio@{^jj$@qPRDZP>U`&~}jl=rFspXOBKU
z-p|OeZQC|hyLMGiqYC%u)32_H+zh&KLB_U91hlHcvh4f2SkNR4=)S`rA0M;&dQ5xq
z>FH@uODHHf_~FZ!EAQ@jaHy5rqUMKzR>+Em<l}t{{pMPM78ihaw1N%;SQ)&Wfnl<`
z|FJteiw!d_D1ZikzrMQ4!OOe#)c)wbACF0U`1*nlTIR`nmfAZvW_w=jimO?m+T_6H
zULGeWr!Czd?f-mm1`T4AzrQDHxh(SN@#D%yMnZvsfuJ=qQs#L)TcdhmV~rIqE-w0_
zdJgKKwXRxhAzGr>*2nixm>{tC_~ONj1%-r~K+`q;X_0>O?Lch_1xriGW_EtJx3{)}
z`Y@}**B?52mKQv~p~C(6?b}{Z4sdSgtLm4xC}5ah_e=BJ`}_INP98aZ;>3Zi+1Dq`
zo5!cF4&EOWvNCAVaUm^ZW8r!8=7CxnZM@QIRWjYeva-G9_bQKPl|Np#DDm-(wqEDf
zgZm77dLiSUe4=8%kCo)eXz`f!CBjCnS8TXpu`Ky9C>KLUwl!aznQ6Qta`Uo#u30Nr
zuG~@c)9BOZ&w;DM)-rXcuf2I+JXcjsZBf$Eu8Qw>%LS#RR_%Cr=5)@121cv$zhRrI
zzGfNwBu8dlS<!fLvHRo0{PtI>Ywqo-1l=__VaAM%XD83Re{yoN>n}Tg{{H&PNsk_0
zTN^#YFqthWIl1uhF<u6L@w2~v{!F~I#4~KS!<SoIvwyr?KL5gEcm63lkwTG?krH+_
z7G}A(Sfr(;K}(=NJ~|q<({j$@#mb<y$QKv8gBte*kC_gG2K{>7ntP?qK?e)x-rCX_
zwbsqSf#KA2ef=sMP%(Hu><a^U80yRUyZdUT`S|!29T#|Za<V#Tt^A_Jixp2Bsdzdq
z_nRBAyDay_rXJ814bTNc28m5C0?$6W9$&Bf<@=tW&t~f<2%Rqf@W7Er&L-kxMNyGa
z-Jg%{#(paIKxZ!&Kl1_Y!TkC2=dJa(Z`=TnYnWsTS(Uz0DR3$TZ4mtWDs-}*-3GVX
zUtb(&8l_&?U7p|4)^_OhY40x{PFu6Ca$R2Te|=wkQE_qMn;V8Ed3SDT)knsJ<j9zv
zyAK+_-ggna<_y%=7MFfLfAhC}j5jR)cY{YY>Oj*Fprs(YZdm-6k#6t(y#I#9vP9^5
zGtCv5mzPCs&zoB|dCLC$Hv#)<D);>TcDqS^ix01q$$>SIn?ZNhfL3;Z_90DD^#<J*
za%EktG-yN5g@w)!-@MVO3fUa7Ij#4FpiY>V7uTlEn??K6)6<nzRgd-vcV1rP+O1Uk
zFY2|L@6}bIhp)%i^D<PF?RWY2hw09pI}e^cTUPt#!Gi|V>}wy2IsD%@{Cjax`C@X!
zl8=v%gYFV?^7G^Knx@m~Ia%%Dv$L~7hbiRb<Oqm}wEX=1yjw0<!r$M&qN?iA>h=2$
zy}P@6;l&Kl&J57Pqi%8iV+$OcUHUy-Tte1BhtDUr-rANcy)F0lvf4d0KZ}kWJt|re
z7ZoM-=+UD!zr>ecUhePi<HPgp{CxiW{CtzFD<0KnE?yLDY;3%-t913%m@AjpL~eHa
zd&zB*%9Cf$_8sWdnZ2;M^yjBk3rowHg;E<q`(FS5`@SD^1=jCxZ!a!zWS*iID<vr@
zX;J-6hfmh3MK5+&!oNR1B}}uXyeMq_@bxQbk(_{-m|B%cckz=Gf}qJXH8r;EYik_0
zW?dB!5^B0|Apkr$U6EG)=m_VX-R1tje;jOP|M2P4p?$T#K|_QEMjyc$_(js=8GW^j
zyI~8K#iiZtzxh7gP*}3D(C7HEi$`G#e7ZrS@5>8rSnPu7lK?dZA3Ol<)q9(qENy+E
z_~y-<pcykIW#x_O=jCqPxB)uGYs2QvhnLT<>#{6<mhkr0R?z0#7lED%{QUf&jX?MB
z%lAr~UxQblXJ?y>o6M~|dhFOMo4QX=K*z@Su=C3$Tv*@;n$Tx>@aN~}AJ1mz2ds;+
zJTt@4`N#^fcJA|2ZL7X;@bU2ltPEM?E|~Z2%}r2)U{~quwl-erF1h223LZ0E2Cb~}
zoo%+G_O}`61|QHOYtV^*wqk;Ufg9CNp5HbFR3s}YbsJ@0)2aD(Go1nCwHr5Y9=sM-
z&ade?DPUEI=AN(DqJMlkt^e^>_WDkVPz!T&^OCo>L_rDX@9*z{D}z*z96g$;&(qz}
z0lERTL{Fi5X6^5{+ui0*o;tPl>FMc@zr4IWLFMGCvY3D0Zs%`({^G&G<`wb#?X<$z
z#XP9Y%*+H;i+}$7*--ntthhh3?D@I5&X14vg8GY~k>!HYQr!=8jvR6M^71k}=myUB
z`~UY<eSO6_BV<kS^K+o<k9}vGxkf}t+_`)A>%E)Hom#n=mTl(QxpODzR9n#Q;J@GR
zD{E_WgW59p_tk=GoK>N#yW}qFK<c9Pdmp#$o9}<E3p@m^XVwSV1Ce>d;@HN*c}b67
z9N(uYW7Y?f05t*nkR*<wOYDl;p4WTjN=VI@i|!iH+jN+im_Qr9E2^rb{_Km}TQxJ&
z>9o>mqi=6-x1TuSk#l#K=*yQcGj45Jx$XbFyC46Yn`;d^=T%5pc;bW!3KdzOD}H=X
z1m%~x*5!|WeSOW)Fv~O>bkJ<_u^vzv$l|YY?B?cl(4kUWwwP?myDPPR-!Coj=3|Sh
zFB+$&YJ+Z*iFlfH5p>Fyo*tijpG@Q8#f#5v?CIgDsH!@2{5bpO^z&jS3xD=V7&1*#
zdANH0z9z4whdKn6d+PdCJR|m0Y?NHK*#@)|2ekUInVnzB+FBZPVdM7gpaTv-_dH%)
z><+qrZqad(N4wwebI!=nm}Qd56doRa<Hn5_pmC3j7cVv~+bnZuheLQ+m>B5n`(C%^
zz180jojb>OcXzqFhX+SZO%2zczK)KL6$KUSCE#?)ZCd!q1=QI&aJhSa*xIP2dw+D6
zsH&<i%)Gp;>$vw6jmDlH9%Db1u>b%5iuON!@+9Hrrqmh6>3pD>kg~V86m4wo)Etfk
zrRllcdoEqR%>AeN&*tuDZM@QLD}$HMs&-KX-A;XJsdw`6K3R?UeS7Xbzp^3_d{oP;
zD=V8twZk5C>+du8JmnFnRm9L>|NoD$RIl5|%4<an=h$uAw(Z0B@9q2d+Z!1fflf|d
z6S<iUG|$|^DSTmHZS|M;_vIZO9l;YudYlK28Oln#i$j+?A2$JyHl}d=UIr;(AR~^;
z5+6$(Kc?t>!=m*ts3d|c^)lp@b`N)PVF9J3j0*}3{`c(#1qC}gIs*R4W#9Vp=>4%i
zS<sQsclK6`gO+h^NIZODeZ2kK>{stsg{=jj9Tva8j!DgQ|LyJhhc90i4qqSVy0_}<
zg<YlD3<p}d#X)BjgYFRc@bGZhX2;9-O>=GtfbLLCpI_T{<3<E%c<I39^N$6U-4g!%
z__!i$?W_lyM<aHZ>8kn7iAeZp$p9+8LFeSWxw(05663FDXJ;=ATDc+NAk&Hvt(<#%
zZoY^;zqXX|SEsN#Xv3pc=qd#b4UhE4%eq9hAKlwq9kHuqWvHIR{e898zrMb1zjG%B
zbSB8LUTM~O$!|)(8a+P7x@%tUDhW~1*4*3MK=ZaAK7Kqn%QXALIqUZ??k?!;=;-Kb
zgAHjm{`pgLQ8{8u*40%HFD>=%I^HjD-*;<k_UuBX(~~DpZeHp=9kk+oNAYvMTif&d
zSFF%j{j2?XdK<rd-^0W0%-|7dLBYm%cXxBo^V*~A-lt$-5b&{SUOK2fec*rtXzfGV
ztTUT@=2~4{RlhJa0<=}Q@{`KBdA8h<(?GK;pf%8-n*T_rFlZvgEcaH2++-H;)U9D(
z?`ILvl<#qqoH>UQA5Tzx1KKMGDQGm3K~2$MiyRrF7Etwc+`{Z!Ft}lIc|&1|Y4$bH
zQJ%-9YKMak$k~#AUv9FRuha29S=auw!mu?Fjq_})7sc<ddvRmq;)~Y<XPf1Mx(>#^
z>eqgJd^~Z=6woa{2hN}Oe;$#OqXRnSF7Xh{+}1_cmSkOB1!{J>^d}Y?85vEOG-*+V
zjisgJ%a<?H=6K9mvP7l1|K-k3Vf9B_ug4wk6juN6;-d1J$jxrgE86*F*L>UjY;nI`
z)9&5in|n=iZUlU>5Nnkd7YSMFCAwtk(u0>T3x9ro-aR2f;nY-Z^(r0Ekd6>^rcIRj
z<;#~I-rmitSFiq-y*>Xv=(ab|-0{7=)rSusc7D*3#LCVNI<K39iwktNM#FRKdF!IL
z^92S5&M-`FJHUAqbfVJr`1;<;&(A;y)_nN%Y166h$|*5>t3tnUh&_IFb+v>=!2-|o
zxp#ILn&sX3(WJh~=UR#Qv_-orJ}N0GD=)m5F=4`lhAvTU(0UtCyv@$v$H@R%IKjp%
z)dIT0*v>BQ!x8;+>tc6r*&lQM%$XJy&yLQ{gP^6@HsO<0dStDy-BIR(&o%den-|~-
z&^gb+YhmDPi9xN8Hc;F?w*>Vqz-wH=eMnFvBk{3FN_KYluF}_w^6u^ewXXmC{d;jw
zW%0%2$T_>q-!BST8Kh=^|Lj@c-^OoKw^x79>yb2GcHmJl188lZ-H!*%Ya%u}9Y~q>
z^xocT4?n-Q-Me?++g%qet*@^SI{rjAdYjINTQ_$WgSuj%`zAB2Hidxp!=}%#1>HuH
zl9ncB5w|wVbam{3ddMB@)4R`qeQ=DG_3zi~@t}5%eEpwB&&g__ZU@_ZeNXT##<G_k
z9UXCc(3S8ZJfL+K;p^j$b_%OAF!0OUxpa%^7JPo@yCOu(#l<Dz`@6dt_xJ6+;m8Ua
z@&a9kJ54uwQQ_lb6I3`KAMbb1%F+@N5(4eY1T_*D9XDD1=1tDqSd~eWCV@&1UTL!f
zmoEo@$q-XDG!*RY?6fL>2b#kEcvL)IL0z34)H~>xvt{wiumjnBb5p8sRo+aa)DIsX
z9u~I|6g3BxojpBA^!NX1nxyKzD0+JyXsE2Fwl*<2dGY5vX=i6WwEzE;pN&^aB_rzd
zg$$Dm875Zo(c5xn-g_SPxb-xH^l=F@KSxjjZocb=#TWmLkYySB4Ew<SM+;C>f$wiH
ztmD`No4i}x-Ru0HEqiBjd7w$o4FPU39f$Al?tYcKzcHB|6nQEtDxk%Opb?2vQ?<3_
z)(0)+lC!N!Io7Fjx=+^HAn_0jX!{%kXcoMpx>{LPm37~~eKV{|S3P?DDs@}NMWu?$
z%7xL}^9qWK53gRokBb3xeE7Q9-EC5)SqT>xxi&2q0kwl9B_%;4@ZYjeo;(?`vq-h5
zs0h5cBkxYcgO*1(Zb`-MEB^iMty8YpC!@;GXUz+Lf6Kj?9HEjI6A%y(Frn<SxssAn
z)kfF=qJ%}!6OKcN4sGebzCOMmbgj~jjmZ^{d(A;ttDKo(csNV{&BpE9kAn`k&foVF
zbd4_P5X*OWcemf#n*Dfjzuln)j?G*#Cf|)_+t=GYJ3G65clrB6w{L^a($0XaF}ws?
zU*FTibL8kz#)@69cTb-#4qE%9uCAVQXNRDnq2Y_GtEWHkjNh|okIm%&iE)!uo;-iP
z|3RnD?Td@uKY~_^9BgK1J=dz@IRmsQ_v8`KIU1m*8t9-r4UH2oT$9euGOb>DUif_s
zX!biXM<zB$=JJO8l8uF2?VxCN7neS60iK%$OMrR{ND|<QbYzLeI;N(gfq{Xbt8ufk
zv{E9kS?YNTg{_TJ&9Ev2MM+N&&(X({l9HessU_7n$*kZ1&uY=4MW9>CZrr^2Ql|RT
z6Hd@trC+btbI<Zy6T7<%bmcqfoFLHYH~#j2L#o##9qj^L#B6@QCV49Nh3so<I*rrM
zC478zw4=B8Xe+n)mUw<{?!z5|$^pAdG7koK8K#^N0PP7`?l+g|!<WxXUAx70l)aT=
zNVvDB^2YA+_2<-Vt}Sxy76UCrbnBOkeGrkBrgm*jWb?M%+gvkz_Ox<~Kbl*9&++rK
zvui&Y9~H=p3AoV4EA7(n;Np^Es`9h`e`+guoL;A|xtSTXMEd)^YJP?XuU~h+d6Oe!
zQz3BRa%|~x|M`8@-`{c0nWWR|wX{jaGvm^dPEYaA9+O%+Iyj7d(kf$OVnB^%(A4XJ
z%kf3NbFD-_e*9QaUf#Zby}pr=5ok31;N*Q3T2r~^T9+ToUcWc(%T96qxFh>&e}ngz
zoYXlTU;noibRGMXlanW;N={PA)Q_tCc7Kve<kOuytG;U8xqH{O-|;AqbUPPlt;)Av
zJu^_d{uF4D_#4m&H;4x*lQlqtJ{t?c<3EXyp#}JjdA8M{u}t@VxrIJ6jWpu-)igf$
zn3OWL{Abw85YR!)^X+QC$o>Ctm>;wq{LcRR`)4M1iVF)jgO&sKN|}OM*jwg1gU0bM
zE%h#Zc1F_0-CbEh!QsP_XU`u#WMpS&2Q@T2JUtsXZ#D+qJ^A)6F9T@h@ihJTysfjv
zC)Al{T{-aJV6$QAs}P0*mzH{iR^<QraF`#o?HDvI+9j%;bbg*KXzcIt@&3iNzrTI>
z_z|?Y-pR=c)Hs`>8O-+i+1bNaSBHZKOfoOId|8q9{NcmKCr?s9`)@(37Gh#!xpN+=
zdJ2K=T5}Zcdi?lt^O`j}GFBxV@M+PbGiT1sxUhh6mRW9>?`*S9xvM#0>tZ?=EKr!D
z8SM5&12h0=3ti>ELP8^aoy??3lNcBxBO@(pei*3v&RSxdmz~{x=8R9^<4Dlm33F_#
z#ZI0)S@HYr_P~WstQVCzl}{Uij!FCT?RLJ~{Oq;jUm5)MFBFuOU9-ElF_|57fXS_`
z*~|=8UthI?w&7f<NZVfiKJLxk-Pe~qpH;=)HT|r+d~J(y`Z<Ti7Z+51eg@i>^X<(|
z=JN9LGxP1`kN3;F=j5z;Vc7b>^>iz!<J!~16S6AA^NWTPXz1uzWnXWy%<p9i;EbLM
zZn|yA=W6c#ECX6b1E~!_L&2?wk0m}9VUq?`?}gwR;Mm4Op5Gr1^9L^V63w}{N0L|C
zOvJXYKu}Qd*7<PHNuWDr=FWe3-lpOM^gcYp?;T>GUTwde?V%P<VNi+i_IbC?>08z{
z(T^V$Gk^}_d_KRP&*A^`yr-w8PMk9*=iNq~dp9?y3rb3Mf||22bL!vUv)!?4SC)MK
z{e9rme|~>^%gFHe_xIyHlEy5)>S3p+>26Fu&c`Ef7xR0jb=nyThKAX*rOV#jNSxYz
zzHzzq(vY=LqM@t9L~Xl{a`N-LgT`t0R+qnht!8H@*V)+#S~)*y(j?G%h6jUZUB9r<
z*)Z#h254X)YpYc3?y^?UVuFpJc7YeXU9ctVDwp>(9ml;@UpG{L&r3;9e>}JR-bK0n
z6(5yWg|1dBaQZk+KfdqeWcBRw$M?49%Y%-AnKY^CSg&+4WPoG+1I@F__V)2#IF7o3
zCgk_O@%HuxwMao{e7*g6=T6L%XV1E%&ae5g%kb>F*xjJcY5D!y@ZXh-gH{GC_mc%(
zpRl*;>!BHj$pWIHsuh>S^B){&Z2c$aIcY=I)m5NLD68UUJV{AO3EA18g~nIb$IGkx
z%{j0la53njA0`G+kLtsR0v<V=h!0zmz%x2F$LEJGOT7Q$(d%O-IiLm~D9V%X&uHuY
zEK?sgv#ob=_j>8e8w%$oKb8Qu5tF6N&K3WOOqDY0)7zKlbNHCyn@>+qgMw6i{(t-Q
z^z=O+k4ZB$WM5ymFluWSYh9Z6q?VwiUJuu9zXvKdTzWDE*?1%xE?fwhV^!+)`)17M
zG+&eKYdqVwU8~-?x4F6bU~e1f$b?T%PlGx=pjCUIRS<4&k3a{gsd#?)@Ik<Knn3F5
zX;<@nCQP2(3_8#MPz&d+$Ex1bjx2WXcj;A+S?)I%bS47m)Gbgm0yMO}yDYb&qQU{R
zBg21&u)1G|+`**6$4yPp4*mQ6|3RnAg2p8T1OyniMy<X32DEJGpX{~Y=1HI~{i384
z&}x-CJB_QpzvF%Ia^2nYb)GY(PY2!p^5fU9E}6g;UteEOzOf<k#l^+!H8nK`H9rd8
zZtN1(2F+-8^z>|*)m?R>1a#@^p;qp|Wj>OiO6BLzpD!*hZvXaUe*M3do3)JtqoQVg
z`@Fs6<t2uOo*tgJAJ5ITjy`+W<J<fD@h^6FM_j(^0V>S4WMAj&m$zqQI5XE;JbHT`
z=wxQlnt^wBcPpEliy!Zkb&iOT0CoD}_EvGuyY&auk}q7LaRW3%3X0}7&~YZ9^ANzh
zjRGMNeC(JZsHl)`?`rA=O&}S*xf&ktT2-~{g`tkye7joEGBSpS>C?qQ)i|H5700|&
zMK^EV0#&=9Yg%6f>bU*>_7-&EO^>YgwgVfVJV^n~jmPdP5j2>Y3c7N`$A?ErS-J4b
zi@+0`c>MkSL8nUm`}Ysjq<bOQ3Yt*_)x2)KQi^6~Vv&)NFYfK#{q4t6@9As)>0O_s
zvM_RUTE?|CGhYO*nDO8k>#kj;uiNtO?ou>17LMMQ)9AMN;H|CMAJ3ZKKXCLYE2uH;
z;n8tb_l&xdQk5XQ$+seSIiFt44)BOb>gj2%vuDr#25Kyb=|;62>y_@74%o1>`1zvj
z>+5dpsWg6ffB*X8Kz;^L8toR-6*7^H+yvT5_ULH$kN5Texvj0OLG$7T<>l-jO2nVN
z-}l>Zcd?EjXqzVZShLHqJLk@w`|<bt{n_uo6~DfwyLzX^_gh=D7rAf9Fitz;aCKEE
z=%B2Sbup68Z9I+z1qM<k84WvjSb$C)Vfb)8zJ6iq>1m)r%(d?hr8e{?^MInK_H+H4
zyX65Q-~S)~c)dwufre57v$R;xU5RKN#>F?1^&2kUQ02<fiLdTHCa_q^tygss<CO)+
z+yV|xb2&OI<I0K~!rV+;T1ut$^&dV@;w`_^R5kx_wQZWw<G1UK-=9>l*?IeKjfVXV
zi~k9apY(y&ow?bY@jYdiZvWKW`<dU&@7)cHU*IM80d*S+K?-;N{`2`fXf@%X%a?;c
ze(q{;Zs+TiJGjCm|DH_ovonsjx8*WAY<>{1x9V%aA{WksmnHi_Gnb%CQzxtWf)bX;
zq?Q#cH2(bgd>+)UH!?N`ZDqTdEESTKrB(L!R_lZb0-$A&o4~7>e*F1-9@KXD@$1*D
zJMX#wZ!LJ}v?cep*j%epCWe|{FPDRdpB1#Vxf2r;e|$L1@7kwv2h>)0e2f>g#bJ}q
zbBp{{yc(yCKnJ#hE^qqw_BI2kAHAsf`MDQ&cW?JJ=R45Ky=CLJZEe%1i|^U92Q+Yy
zb8{2x!i5XL2L*h+9)I}iRndF*?twbHw<mOTXw3h?0Nyzq$e5UzxbW*U(52>Q+fOcg
z_3G+s&`$l*dE2*dcdx10!>BIw`u=LR)ry`%W$*6%Y+GiSx72(3v5Sk{Cr+8dqOGkh
zq8AfUtf#Hb&CVxdFmtZzrAwDSyj(v2(cSX<M^8*tW=y#su=4HM@1QX#(D^$5<CiT8
zT^-iZ(*wFWkb$B0_qW#l`|Z!1JqwzJT<Sgj(BZ?*AEu=6oSS3WY?yrP!QAqDj0|UH
z7&2Rzy#dt^Cg!@#4Rhzpf)*%&rd^~$EzJ7za%5D^`mEkagUB42pzhwqe81JoA)+u6
zEGn&zDmv$mtVIC>A0HoRxyY?;xvuX{{(-Fp;7(6ZpD}y3_PU8GoQ#Z&O=>1{K!f`Z
z->#q8AOHIEr(fG+OG->0J$huae)6PA51u`1J8{Be$L`(SbI$Al?GxVr=M(p_9?9na
zf8W<LY?9Yw1Ko9>@buKwSx19?4yw<uX#$;!e14v-^XqGCH`e?t`ts(cFsN?$`uaL3
z$y`*HVhs-uKXT;AgF8EmL8sdHN|~BGpJ!XmR$pJg=l8qaOzI-fpPilk<HzHEP}_1X
z|2*cK_RD=fGJZ)vKW}03@ji>HFB&?!x}XDk7;f(0+}_giV0QjK$BGJzE>Uf@ilD+B
z1&;6Dym@1gbwvX-QC0u<tGHS2t(FTH0zh})fwH}uTiXl4&W;W)6+6f#{1Atfv@|6P
zi-^};^W);;EbUB8RaL#F99Zn$Uo!9i=kxZU6=uwSD%XB~ejd8^$FE06LB}f2`txc7
z!<Kakd8w(XLDt(qJ5;32axT<l@T9EQ`Sa$cF{q+QJw1(eLha#T4-XErygMDBbJL{4
zXMB7Np7&n4a-~Ml5{|U<^Lo3*^+D@a7&hgf;NamAu~`}c+VSP$(())hw4G1Z=hZQ0
zhK}Ce&^r<@o;+b;0QDRCvQJOf?|<?nrTJ`H&JBxQ8w;o0u&6w|@8q##f$g9<D0OLR
zciC^g?`~Ll<;>ZW_&6o`@ruL8F823M?(JR72TeDA_cj!6+E{oc@$r+qpP!!2vVVVb
zv-@k)WuF*+vCG#mcutxyX;RanR_^S$*Gk~|+O)J~jLS{*cFD1smX^M{0$R*2C@&8>
zMm{Aq_2AK?tf{A_2-?m%n0sRbBWP>jySuwDZc6pO_*lZ!+uPeD^ODN(kB^RaFV4Te
zk4epl4|Gb%&CTf>GcGD^$+;<{>OD=wcG5-A?z%o%>$dg#esS5^*=^Xeg#~oP7U(=9
z(4uwF<zcGc(>Uf``LLtF@t$q<Hy+UPjLGW$3a2-n+@J2~;_^icULZ`EGKGbopC7c3
z!OYAIv=)#-!N^GH_O{%^r>1Ie%)f6Zq8}IYVM$U&MFnW$O~SUSq^}q>5;e;-8+2w5
z<K)i5*Vop@oZnyZkqNx{`OhbBhGm<ZcIuVCyK}IKl^b;1CFrhm>+*LltHag`$jkTd
zEPf8!YU0?;#_Q7m^H}cPU81tqWi8#^-hIWB)qI22eERp~q%f%8rB)g2Ki8@h)XqHn
zdXlO)=mh@G&Q1e!^Y-4}-UBa>{C>0fJgC#SW{u9#LStj&9$9NKaD6!Q;mJ)r#>U2H
zUr(>UR+ikac|Ydlv6HgW?w!4h<$gbt&ygv;VX-s$@gLBxt>2)vYC_WPwr1z-Z&<wA
zP*`;Q*iUw8cYDy@J5Xs;l{2S)12`qT+n<|!ici*xg+U``$A(9yfpMT=z`MIj4_m+A
z!(3fmedG3R?Q{QsKA#UdD#<tP`Fqe>gm(G51EBGiHePAaso=H0zFgc@F;&yD@{<a~
zg2Kngx~~7)v*+Fv(3%v`GLjvIk6rqcO19<Q?V70Up7iI($F9e&T_Oi}6g~zm#A|77
zo%w|MMa&L|x%Ka>{vDUEcbJxHl6Obq@$r81m#zAsKEl+Q|GdEi2Oe88FE4v|W~MO*
z506VsjLf-tw%wqsaUULT2c6~zS|O5od0D4i@Qk0IpMy>f2h~x}&dz4{oU|eHvKnaQ
zkypy3VeMMov~zPbt9%{?1qTZX2r!6?i-SfJ)~#D-QSxGfXZ?kmmzPvcGA=NHwo*Pl
zH5IgqHYFv6f#J>Dx1ix7t+12zv;Y44{T?*_v?}|4{r}oI*5&Vb{X;g~xOHpRA6{F~
zzBW)hOU}0H!H<uRJ$!szl9H7A<n8<7_Ev%Jhfw?Om{3$?1Uen)CqKhHyV_M2pi^vZ
zs=xVsSn>!QYoP3XWM5#?<2_PleA4dHpf&+$iQ<*S#~R>LV0~Nf;bRxudM8_h<F*u3
z0?4SEom-vw_(J{Gyt`4K^S!2}g8bn-%jBZW^{?_5_xsMblimOS-|lmtLHntCB#n72
zCPti|rh9mA_4f_w=jA{%T%h%aN4rEX?kde@VP&29rYRIOg}OQI?1X94mQ}2My?^?1
z--&bQ%D#E?#-%@T3h2(kbJp))*u<|6(>-$hxO9QiV^I4OwCm;Zv0mrJZoLm4JzDhD
zKKKi0W*}-S*V?G9PM~1j|Nk%eIt$Zmv81FV0a@AJi;LY4A3W&zWrd523oGQPBMwm4
zK<QNM&reS;t`65{VPVOzegFD(_uA;~pxGg|d1or_?5!3DrL}W&ttZZz!@~f&1|8I)
zckLEi7_+meNnJ$U)KqkJ*xIK3`|UyJ&hgv*VAz~~-t6UFmAF@Tb{c~&CUbFjcb=qT
zVP&PHrRBA``B0CfF=*NjG*R$jNq*eJL#?2p8Xg&ofMOk6TUq<RUxYy$<%5=bW%jYN
zvL+ts5cKf%6*XK{@c&+~ik=>yb=ez(n|D3_oxOThbltjjH#R1>U;7NoT~AL>FZ}r_
zmDyjdZRX6#K53qm$ZJ)X51xKJbLPx8sq+~dKszm896NTguXgc~V}bp>iy?Vk{<oVf
zxXthu9MfNKSlj}qgJ0l+9ju`jqQSXx>a1B^i(I>t4mPpQFv*<sqOhlF=1fT&Tic5p
z5}g?ie13l3F#DPgkG!4C)m5RV3-_vcs_jhPICG|CQ*$$Do!Hkut3p?UZlYPTWQjzD
z(PPk2s-O`k&<>iE6cr;QBNOYz<u5O}zP^6xcE<gEwG0gW{QO6=Yvbbby+DJsA3hX-
zihyU&o-I0VsAZact);u0``eqFi@(-9KQ|Y&jRv&wifx{cjk>zJ&paE+<YPU8wp|xF
zczLhZy!Z9@2VIf$>)TuI{QUeq-|tl~I<BmwRJB?}$d&=L^iS~R^a&Fhq)fA3*t~!B
zYSqn&heM|7$IBf&c<{uTGe`DTf1faQYHQKcQwI+na{7{SXvwl=Nl#Br{qX(!@n&}Z
z2hX0hot<sIIQ8_jMefE@pv^j<Rmkk@>?$fMPb}gWI<el_TOEENr7e7s3+Itz$F%w)
zBO)Fw?zcNt`1Wu+f8d^qLg(JJ5WU!4Ez@+Pm9(|FeP@{*+?sv8=#AT?IdghSUti;#
zcjZIg-CeBq_V#n1+uGP{D1RRZYFw;|-0adHpa72JCr6H*l>P12396^v&CU9RK#NU!
zt#anf0hi|*uy_pwtug>r_mhR8^?4si(W`4~XD@%P>Un5q@$-8ZOpdMen5d)?yo{$y
zL{q6sWbvm@54YC;1}&<H%l6`5@c-BA^*??-pKrRp{N0_-=<Rt=cjy@!3eGmmb$WYi
zE3d`eLPSekKwP~2>}+$;f_z~$p94oag#-6il}@gR__m*a((FggPqVJBi<P!6d*g7p
zjTba-Y+-GkT`RCR`}#VjWy0A{PE3?A&yxWiLR9$p*utu>uNWG%!`CS&D1hQFVpB@z
z1I?onhDj`-{dtccA8zITH-Gzf^DZ&nF1y-a2X5b%maqGv_#bpI(q6?H=yq#{6;WG3
z-4s@NdHJ=^%irE&6&Dw0_D_|WXJ6l!b#+zZp%zY%t!K`j1uv-5Ss1scqH(HrICxzX
zDAwP->(h<i_90D9chja#3AwpzKi9;>%sE-Zaesj$^P78nqpx;--(CJ5v}=pkVCu)2
zCYhj96hwDV{1d(0Z!V}XaJ=04^u>!Aug_Y6PAP0|Ze~;$>NeL~efZeL-rmW=poUnl
zkhD7_m#Tseu$g^lV_{Jes6`eCCNK7avM8u^W^Lx@2d=rjz@#PU($q;R7n3FSIySQ<
zK0ek9T8_^puBTHa^Dyt;9?dG2#ib7pFrJxd%<k~5`FmnwA_q73<*MATudWIT2qc{N
z*fXuUnHkh>2X#MweSOWr$9HbyfyR{+QbBXIR{O7mW?K&(I;66{9CV1^=jR)fk87Rt
zoWv42P0>@x$k>?Ic2+@MT^(pw(Y}Abvftd=>Rov5%o(1^YQ9bD*RNmj^2nn@td^}U
zE#RE+^}8l$qQ@5A00Zq!0<HB(KHeu`UA88v^?d5-X`sWhPfynuw^=H2?b<caRPNHH
zOJ4-`xPi+54-cKMtdE!14qtcW&Y8)#-zk@sm9<HoUjdr`did~RRQ{~fCr%uAc6Ro~
zEt$cLlO^YE-);_?bbWeydh(YS7p>O+el|NFG~B-?e*e9O%aZ)>+!jT@zqeOVK%l{E
zs#fBe8HO5BTQnFzYeqr0THo55U0l=P^?yg@XEm+xbvji%&B>2n96NRrlmij@@Z4&{
zqsJ2OKk0)+DL7w(qjXL<X#Dn%xU{;uS)UcOe>P_hpS+z;RSOenCGCxk$?REISG77e
zvn>o->a}6hrc;Hnp!r6h^a@e!FcI6Pi?a+8ncVthI3uS8u8Xm(`Fz&ga-W`xr_;qn
zuBQ9F1HL(5FDxwFuz7QHcQ<$1*;%QZx?_L-`lV!KBs5(={#w<(y1&0b*TsnG$K^aY
zd8E6iN5r-%FnULUVoh!B#`^ztclOmvJAC{8y6o*OaOJmLxSd=4$(8-}^>d$3nlxzx
zNXh<sdC=hu?d|Q1-~+jSdu-A<y{H|$#YO2asHf7(Ev{s18(Vni&>^PaWj=;C`E?l*
zetdYiqx7}dxA*t;t3(zjq@^wUx%t-BCf}F5FY3EHIvk##n`>C}qu|Ty>->3nc^sUa
zjm^!>pzZzfbw63z`D7echplz#|8?x-rXD_7D^TlP)~cjo`gHNE>+5=xj&?n~xj7xQ
zAl%8xNkCArk>CE0K=t=`rYEni=oZxm^&Nlw_@SVv$jHaX*U{AlT2sJ~aIlFrVoOHg
zI`fNr*Mdp{z1Ur#gIP2}R!n$ycz^ZxcZ$l&%z1fvpw(XC^8fljKR=)R@K7sgUEZZj
zmt6XlS)`#wuk1H?-ktNu@GB$*fa=qBP?iO?#-ydy>u*@(%(=6na0<9>4Iwr5|NFZ)
zQarf2qW8=0y1!PZrf42!KN|`<;|O#@gQVojpYw87tqNPq<?ru*X0CPk>z_9_r-KSt
z&`Dn(Qe0RsH!`z_#9m+KJKNl*^CM{2aX^58S<VfH>gwvVAA^_sE%ctQ*U{a5*=EN5
zMXua$?(PnMeaPCy#bt@SJapx>!=uNKK_mRu<?k3y#6A3cnBP8RPiI;esLh#pxDAvP
zBn*>U&Q0BQzw)^(<7LTvb1aKLmDIYqu{}FG`+M6m!#dFR{6ByGOqeodN#*0nX{jRm
zaWdNB>&}!Oy|Vpmx41rNRp^@N?R=4ukzK``bPnISBLiA!erc(<?>FC{VQZrf9y`YN
z@Zm$tyjLeroB&k~pnd4`>wbBDS#bz-BC4REVAs_Z)@5%x^kR3-xYL^enw2{>RU6bA
z0If^jTm9Yb`@6f044~yjUtV4Yb=o2#A`V=>EPTKA``ibeM-v}s96tssNsogX#-PnN
z{h-k@&=AU9Sfj`bd{n}(jfMXXg6ho0(vXf4n3R`xpS#?D{-bYiZ&&>JVYub4TCNti
z^`F}lmEA*PukR{-ZEn+9_~Gl<vzNb4Qc+Y;c);uHoZo!oM#L1|=&+3%9V<6&+T@gw
zpwPxAyXxzoTU)b1$NoM)KVQ1S$ViP}-tNrx`^6<CHD@OWI9^#BZ4O$fbUnU4RAznP
zVm8pRL7l?tivkzBaq#oI2LuQ_J2SIc(m0J{*0hd}6$y`-A!h)EJXm?x^<YTYt9$$F
z?Qd<(UjFLVl`A2j^^Ml$?`jSQOKykU9jc_J#ugbFSx{Km*xt^blau4puXf~q{r}#M
z4vv_8HIn}GY#Mued1GQ@FD`Uux3ISEmh;zm=jN2<>h6B{?p;~^xIGtSCaZ9Ei|f0&
zxv{DF&*PDnmIf{KtE;Qih~Bp5K<3E^a03%G+|b#(SX#RMO48#CuMdD?;0doZs1(ct
zk6JmeX9flDWOH!SW!J{SB2eq>;$nBuT{ThrpYMx#aWG_`{N%i}w6s~S_E!v^uAdD(
z(|bqZ<F;$AvMQcVSy`(VyzF5wclhsqb5p8e!U2XKzkg@j+7~`@$+@#baO1{}Z1c{1
zxV1H#-E-21%l`HU@7#$ARra3LQv3UxWP;VkxH|cB+QEP0e7vS=g*Hu}F8=KN{PmV%
zva-F;&dvs1CLgi0Xz8<x<9)J)-`~Z~u`c&J0`6wW!Lv}GjAhe@4+Tf_ROVWh8qE}4
zQ5v~5Yw9ZVCGI^Ei4B=YHgDT@tWVbZOI-%&N*T~}mV2L!;Ysu7!9hU=xwlMq?A!^;
zsEdvpW=+?RcZ-OScz1t4e|UH}=or$Y-Qwc5(+uwPy1e}J^D}4!Ht*h^&Y-1U3;pNY
z{dlps-=$wQ=6Ij1psZ}K?`$*Bm^7%Kvitc&7<7o9rluz7G7!+QeL|{U9dcJSHWY42
z2K5BLB;S9+3kv?lM~+?W0}TndLEDmMpkbdW;C%7+hQ+Img(Xl8kD(f(`{iswlWjkK
z{aTcIdYVS$rX|;2`}|G6zSMiVi2Zp`NpVnEa^BRbqAH$F&(F<$`0{0^-&`wjqdLOv
zdHw(2@}QlrS5^kI>qc$4@H0Q_-kwUfd1rnUuz#rsc^Y(xI%tF^YHOC}x!4^AjAv(?
zgEnGsD17YZC@kgIEvBpBDFj;7?bOPZ8Tb10Y5n~Y3052b{kEQ>b2?&cmMAFK?5q8~
z$gNk3VUzWTcKJHcfWBeU5sn@i%b+VK*bcXHf7!fk8)zd~8;|57OSANIGN3sd(CKui
zr|Fs=pROAXTG09E=H_%IH&rDitq<@f%Y<pu+W!6h4O-wiAysnQwrvazM~=97Olo;|
zcX#sTWxi@(6K~A5E`RXg0fV--_Qk~#bC2~(KR(pT4LX?n*7p4MUuU(nuz=RurJtK~
zaFJ^_=x|(S|4bQBQ?{Xjfk)OV<cr23-S~Ynpg#7-<l_nX`RgtBrJtAk^6D!0%a<=_
zO+B+ZWM$Kf7a2!Om#JA=N`iKHZOy*!Q)ND>`1v`|bc|(L`={^UkEhSCRVy(1=rvUf
z)B-+wR&4*jU)oVyvsynsJ`P#|$F$s74wn6{B;ME9Soo=}7c>Sa4enKx<;dKH)mfE?
zkDWYr4Ac~rmv*-XcPYVx2cY4@jPNxPhChD%cyXun`jxkLb_zc}-hX^;^mdWs+TrVZ
zj&_TKuGL9m6MpdW@^VlpI5|5Pet6&rTHKy~e%^;KUs^!>q(1hvEnch)a^2eK?Ok$5
zUo2g|{PBZ>%^7!gY&^&Q)%Pf90S0LKN58zi+xob@Cj1NIcN8$*-j?fpa*}G{qa&Ol
zYa#+aEJ^YC^Y<_4<Z@77a;f+9usOTy|J#B3-JrpwM@KrF)J$abViv^z{PfhY?oY+h
z>Zsh?+m4>M|KD@uh|AIUFJE6@e|&~vGC0Nq>rT3WK+2b8esi_FC#m?)u?VdD@SyQo
zMNZBdo6Jipk&{#^e|>q$q;6tkY;0_)qT=#J!c9|C(=+eRj*U5)nVSE<T=us-_y6zr
z`$cDGnLc%D<vRKL`g-#}4Q@+PPfy!4fByUzhCNQVx8*+l_V%`R-_qsFPxtlpZQ8nZ
ztBi<<O8kxj$A6zr>x1<rAMX=2(UhG0?(Xi>s$Nqjl)t~HtFEqo`uVxJlch~E6mH+T
zbt*G6bJ20(Q)kZj+}lyO_)$bo&Kl6M-*R$#8Cs7IgWIj((cfMn@VpVIs<Z#riyYNc
z<iYX&Ya^(zcmWwRK5}f~^@9fwI{te$J0CQFbLjBl)Z*geonBM5J{@Z1emd8>{FHV1
zyD8#&F&g13gIvwb&8I6XDS?jbZf56yvebL}sa|RGX{w%+PEXZV@0T|Bvnzcy<;BGo
z?XWd7{=D6Ozf11$3l(*Bkk>yga_x5MPulYC&Q9g;FE6`q+qMm)QPp$O+O=z+?yLQM
z3UmOl?YxUtb$@pJc{)A5OU}82OH}JbeC^k%=RW`Y_phjxOO(e#P;ztG+gm3=_8J=-
zr$$bD`uqF))6=F+E81Q5wkXEB_E*WysI6ITauYi`UaSrD_`>`F6xA+E;xjTd*!W~-
zBu~wAcXzM(`E)vH`P29N_3LlUeVnWQ|NpCRQ-VJ}Itp5f3u-dE_sfCWhE}DoSQt7w
zJ3-TGg3{968#Wk}yuRl9VM~&3>@E>m>oS+Ox3+@z$BAgA?AosuzpI4va2s#1jCIKi
zfk%%XfewJ+k+Be92v{Aa3tE<E|M!dVG@VGLq>#lQzPt<uHPZX#?XUg%yCQUT7}GMN
zJ;v$h4jezuKG(XOjp54LXmRgpI*q$`TkFN`>G<{aHTS##naF90d3ozBzJ1!dbm`KL
zi9JHF3b^!!Ieh3JGz!#T3mPyohjvjwb-*TY(GO}a^?|B!PzO~=T0Q@U#jVQf>c_|B
z>s$K!`(Fh1oZD0R8MFlyG_9`@wPnRK(2WX)RbMi;WL#tdO)~!e_LkL8)9vM@r4OG!
zXScVv2c5#FsHg}U7IJW4*!SZRx6dpS&o3Q^cI@2w@XSo(MaK=Su3ft}AvJR2VLeSt
zYwP6G({xXqIB{Ta^>+q_r>CYG|Ganc`GH2}8J5M%JnQavc6U2RMa??*IWse}qr2Pq
zfeWj9Nr_3_zn|%of9(P-3B7ao?!_gZ!k{tY-{0T6M@2~;>yw@R_?B(;w+DC2?~59!
z3JPAl-N@<>ivJJ>&}wVY@Mq;d&&g^x_Ec_WR98w)Pfl(=al!+17iaqUd7${7GiMIy
zR)i^2L|WS058u5T`(?%<UMUlfw6rwPKt)Y$ZQ#C|pEB|SUXxmipP%ELb)i5=Na(?v
zH)||Fmy|%N4DCM9Irca9)$Ue2ZY;&g$thu5Wdge40CauVO>;@FNlSiwK3$x@dw2PJ
z(9w`x$)IsDozosZJ|ZSlKZ3UCeRyz?`RwcG=jS_5QfX;zefa%;eRzzvr_ixp>GT(Z
zt;vrA;y|;)pyC}e4qS8`G=|jn2{iT(ZUpdw$jR2A(P9fw?*9v}|3NbZudl8a2Q_iN
zy}h0M<HN&(va)j<FYqvc)?^<jNt$b4FUKvW6JS&GFX-YTS5VsanQIk#Amx~<p`oCs
zrzhw_OL+sf4M|72KyzOI{`~`OA_SiqnqpG*<wfJ$+uMr|a@%r=YPDQi>b<z&;h|ac
zLtSo}WL@E4WMl-LLXvfT-CB$9$K~rmLqYHNexJACWzTF)y_gRN+2s=+AM2fATWuD$
zHi|VpJss3BesN)8^P^qO?EH@owQ|p}C|tC_6EvY`2b<7iu&}gz_~GGU3Cp4-*FJ+b
zuS}jixpBErzr4?rbrBnrK-V>a7V*dJtvYz=l8~5~80f}EDbp;KDx1X#>FMpD)|Xqa
z)FOAmbtNw^bxG?mKA0X~*SK}7>8q=&ms`Z`C`c61i@7o3v1D)J;kLx@@9uv1`W1A7
zP~fH%&x^{OQ>RW{T3o(j%^Dp+Wyz@*E(El+wLP==_jddJXBKH)=6cLIGO^&HyeE*M
zTyRhFq^z`h`5WoGPzhM)5;PVF9^FHen7ms|H!9<wjHKku$9pvG7vyJVcDnb=y|nrN
z;-YdyRFqVK(&NIfuR>ee+LA6W^93CqwR*L-Tdx$WzrR2DAdd>R&`l{PWojo+o7Sco
zye#3=6itn=H4%OHwN*TwoSd2zkDG9T_GfemDqmRUD-9YHo~jjkX;*^d-Cd=uKI->=
zetvFP{LBZms_*2<lb}!qox>w9-|uh#S0wpZPhib?H7*_=(7IjFQ4rVGMlX)qn#IsC
zV}^u`Wf9BKZgJ42bryfmV@Gb^mcDoIUf0nX|4!e%EBo^0OSXAE9UU*;9%6?aThG-1
zI>q_gn#c`Xw;tV5_&8u|R;b6MmKif7bYgdjBqk=#Fi!7#VaS{J=ElYuX1TLgWvhA~
z`uh6%{SPk39=^G`x$FAp=jV?fXk`BQ;i0om{63kqv^2|ghDSy3F+TY4@bDsc11Zq*
z$~InU(9*gaH*P$5bhI0EHksY87s?`9OKN^U`1JI&TD9@Re}8|2PKo^S`**k8(Tsv}
zjkn-YxE7{H@OZp6V%{D!Tzd<gD?z1iA9yquG@=A9pUZMUrzh?L*S{+cgL+OY4j(&t
z_t)3guKfvHK;bAL(D3c;?ZuIs)4Ga5i^(>np1!ay*4pv1<h{GQ%Qt3TRs)^D4BBEf
zXU-hZ)}4x~szr5we=RyLyexRRUrd7g(rLQUObmLlyOw-S-=(R){3%lrY%M@V;io5_
zH6ISLLr*{wkdawqnVz5Dzq|Z>($!U=H4Jk_UR_<?4jLBu_vdFvN5_RfyNk-oj)AT#
zPCX?8>Nd(w>bX>3pLcRo&yF1yH*Vg1`ok8qaO;!bq|`_;TNdze{8K$+V`1kuo`c7F
zr4>De&YU^Jkn-M3>9i5(yo%D-*E0KNGZ`BjgNFN_o}M25x4i8Ay}xYgMsjIsX;Jqh
zShwtdn6*m2V&Wyx76MSiaND+RD?(R`ftFJ|KR^HRkB^T*8>L0B@7l5Bz}>sD+1J(x
znyj_x>+1uR88tOEF8xU&pMDj$-_L)s|AvJnxWWT1oq?2+FG4ruZ%GD?^)39903D6J
zusY#!#&J+H*!d@Tq`>)S>E~y@CfV0`3JVJ}?(8tky0U_iVMozZF28v;obK-Kpsh|*
zwL*ogS2WI;J^S#bOG2{NWi88>t4D3kTKfH9wzai2v#&er!CPCiLv7dCr<@RA_DPPp
zwI#E;onIbwvt`A<KbA7GvVx+btmWn93<uua-2CzH_xrQYJo2do9r$r(j^*TBp1b?)
z1N{E%3he6bb%hNe?Q?c<art@tX$*KGl#8LbxR`~NHSy1nkDyBm=USIDFo<f0xg774
z4cwj=dr-IwbZc!zRaKYV;THv=-}jt6bH=5hz~Io~!=Uy03^)I8vnqebqpz<&WA<$B
zc^3>oJKCDr`IG+r`3c&j4_d3sDXjKn$HM0y9v<GXZJXQsdwW@ZwWe*~ZVuX(eecTW
z|2wQj_G+2+mF38QJD2&;;g%!E7KR_(2kKnNBF#cixnc1|3%q<`OY-9tkSS?dGrp(c
zPftxP{P(94bcaDlN5_F_y3q_N_2)l+{(SiVzwh=IR#sf|E)}Fix_NnVf$q$Fdwcup
zU)D7n`v2v=xUg`MyFnBv%l!HIIWaf4cgmD0GSBDEnN#rpUoGS0PEd#7>h*axm7jS1
zf;N0OSX?D~XZh5Qju&4a@<E4M6lTtxsc2y_!~E+7ZBH++ruKGrzqwYd($dl)D}z`a
zzMY-nKhMVT@v&aeP!weSK#C5iLu;6P?7+c;jECF#+c$6Cd~NoADYG1n1S=!8ef#!R
z?uwhF!otF`XJO_Fg~Z1fRwvyDr9=;1Grp(d((Q4g;KsUh*2Y4O{WmPWthxcIr$N&d
zpbczqZf^GQ@^T6boAzjriYI7a`GS`xBF@Y-RzF{#er-);euB_rF)688uPZ$#C1hrT
z4$lE)D={%Kwpl$rk)1-S2IcQ!e*FBY2pKBvlD+W!+}!R12ON$ZJ<2)niouyPXFipH
zX8d+PINB?1E+8V(B5j`c;N#=tmU2qdR5%|#eAu+ic+DQY7|{7clmG7ess9eNgyu`t
zN5&G+Z0sVYCx=?OLCuwd*Vl9zZfb{Y&%ZBM`s#|H^$dnRE8FARFD`a}d^>-?tAhhW
z8?W@Tp9UtjwzApR*R`%+ukY3;(|O>4!@<duHvag|-h3-8dRpquCH6c^>SxTH={QN{
z>T0dozpnF2KbOyusS14~eTv_VZ{^Wrf&HM_(1qbgkAbrAgs2>uui%zVRcMaPDSk7*
zcX{{s@tT{P-`Q2ly=~hz4==B#xpQTOgoP*0oXJ^TT`i&=#$%p$N5EDqu<^sDsf}}X
zpZxcGhl(etqS=yp`O}vRDUQ=;&FYf1E_<@;!O`va>$Eeh3PA@ne)&=&V^?EwocV>O
zrY2}@<Ev|HyWig4-Ys`k;nQd1$lH&M@^|Y-Zv#zSO;TCtHB}2TkkTh_pZDP8kq3uZ
ze~L>>cW+8PttGZkK}l)RAJ|YIt3y_nmRpZRBWQ8#CY|hi31?27YEtn8ZA`zlH9K%e
zLE^#5QhfQZ7G7Ui^YasE8_T)7S)hUb($`^kc9)+&FnQv}TN@IaSG{KAlljr6Zpe2>
z*2`R5Tiat&%elGMpzWM<tx6wt{g2uJnudZU#VO#N_$B#%#_?mY5Y+$|nUFq$^ZKq{
zP@#A-cD`M0!Gi;gE-o$$yryaul$5xHgoxa$|6dEbp!W21efN+M5zy-Fsw?JsA08Z>
zpu)L2e0|%_otA9;a%*0_7u5>k`1b7^==RN9TQWblEf+}#P16}9Fuc0DTD?kS@weOg
z`x8GrIJjZ!R?z8yph0p_x9eb+sP>01FM~mq{>F_PL909Jem)gn6S0v=*{w&w=I8A4
z=jUX%WL{>wzCOOax0iRGZFQTFsuyTM=q8=R=g#q6yLN3y@$<eHfxPctTwGjGUhcl!
zZ|;Tt_4Qxg-WG3cY}5!`#Pa9wU(j_ipi@vBo7on*t11VrjWPu#l!p%=YJ{(w^P;fj
z@gdfq)920WYi8#M?LxB>Hv-L)d<73E2nq%=f(FGwVPR)y2fCOgCMHI~Q)pf6?zYs^
z(?C~UgN`S-wA9<RKg(cy{{6P*X67|(*ShvQvCde!R8>qrjt4xQ8NMc>5p-I^(Qa|J
zc|9u<9=r?KWn248<o5P__lyh;J~<l>X=!QDI=gxE<`ond3){}SnDF=ssH{D@PqC^L
z+Q|piaTiu6Jr>w&1s>J;3tl4dB6MS6N1T0ibv0<I9B5C+V)y=p{QUkCCp^wJUjdz_
zl9Quz=<s1y|6k8SSA}q<rKN#tJslmLfR#b2XZx=11XUkSPE4R8ij`XobdV6+jB6j_
zzHMB+T6@ply`bA-!22O0+|o}>Q2g<F{r(O0|NqH6Pl;@6Z)XRslHQtq9W+l4x{qYi
z<jJ5SpYgI(*#5e|p#5qs?d^-JzP_5psz1v#yA8Aj_v@>xpedg2?(P?Xtv7a;>$~+z
zwcg&I&)o3rdtiEc`kKhiY;SLE6}C~7l-AbP23_%Db$f=#?C0m_FD`m|YKBRsklpV$
z#up!hPP3W{k1dd|{pMP|j5%9#paFDhm_tp?o<?<JxtTL(-q@Zm4>}#_c)$Gf9i4uY
zR6yq`TqsFdlXZO^ue!QAc-H0Tx3{++uiyXg(9v#jUK`24g9q*|ywcg*d-U1a*`Sjz
zL31@ZH#fbwy<H!)*kVPX^2NuTM?uT+oGYO*RSJrf{40szu3Sf)EO@@S3_J-uB|JxF
z(e?AUZb>yZHcA+!a2OdG1uXFp1f3M@-Y>_{0J=2mPzxvI+`GclCr%vLka)P@!vn{&
zhZpD1&c41*QALGiws}5i8?b_>&@9tzw*373FYoS3FZG%#WV<L3v`h2({Q7yXlQfOf
z&VcTlV0iF){r+QLUS6I!X;RV&!`2Pkw;w+-QTgM~=kv2;KO|jP;OODuap2wE-K_pv
zeqmu^ese4uK^AFibL;8pW!&1L$t9|#Qf1P-GHmUvRY&dr`A$-a*;(|I*EeO)z3TV2
zpc`jFhX~kmi5ftgYvTF}N=jAEKFjZc_GWi*ZTRw~#3c7t$n&4i&d#3wg<Wj9|9rRe
z^K3tUzhD3Q&fZq@uM^Bb`OCJ-#H#E~2k2r2*qQ>+rhd?(+)qzWv-*1~@ygjqOj1ew
z`s%8Ix%u%22b;hCll7dmA@8mgvyb|{!|nX0yPdzjyE}Wg^GndKw;w-$9z1`Z|N8oP
z&>;g(&d#8jW6*J%lhu5MY!?~i%(=4>wD{V52^+X;28p^a$&bPHIWM@6{R%t||Kd2L
zT9V3{vu9<%LZ*NJe&;hdEOcrO*jH2O;_jX;=di!zrI3!Uu4`X}f{0cK$KT)I>$BzU
z*c(=bu1>nPCUS;pwiswZ+k^=Mpyh%eK7MSRKVRO)#s;*lbzSW4L#Ix8ec5pcw1!np
z&F%Tm)#2-vl$D)7-@0_^Qp&&Hy?08*8FF%R6g-9I*;FpFyuYWi*k_JK;FSuugJ;h0
zfR=%8PCM(;ujDgX&9}&=;ot52{h$r-E8_NAf!etWyZ^6?+uIejHEUtr-(N~@qVGUw
zJuF|YzN_RV=#cvGFBVRP51aP9yttTsTmJoX;Qrb@0eDv&w5sy{zFN?sEZ06)e}Ct?
zyX-BG&D4*eO=VtQT%cPgrs+l>x^^w>i${pVj~_ok$FfH3C{X<N_V#j%^u)x*na1g_
z{*=2fd-&jBvw^X(b6A+znX_j>gUfs6KRx;CyrAjKv14q^?0iQKG%}0sc3vC3y>GYk
zOVFi8OO~kE)cz9Lq%->quQr3UyF6$q{qMFb;I;LW%Rwt1^HF2164C^PuDJ&(?A^WF
z8g!>d<mNQS6ZaZ_bnEXs@c4ND#HmwTLA5jJ0-y()+-+rVZ_PY&{(Bp*^rFPWZ4p~C
z1o`CcdM;cD0G&-){q2q8#-yVc)<&CGR8}55eAxNR3byMzi@~EAD*_j@fmVMXYUO5T
z09`<rch?G3q3x~yel4c{(GkuaJ9czPU0*O~?p)9W6~j&Y?Wd<|x4(Fi0lK8!;T!YO
zWuFZG)q^fV15FZqeSQ7omzTkyf%mMdt3G`AV6e0OVsmq|==$=vw_5M+E>~7kQab*9
zN=FArMO77OAy}Kt#SD;zWo2a<mzHo!nPfC@iE16Vb0?;-SH<(jrqu2QoV=jL0%sc-
znGKSTaDeJp(6xb}%~bo^gSY3!LasHdnY1SRWGJX5s3i34;$rtM(2@nv$s{o`F`z~C
zi?Xh+0{8wwgE*i`tZg|r7gZKtyb=)=1?pk^c(eJuOTQCqNKK8+qD6~Lw0DHBi4X*>
z`FZp9Evvs<h{50L@)a{?NKC#b%XK2|r@e`Z$ZWG*Cm$c4nAq5dFJE#ZhBl5KJ1K3(
zx0mZ1@5R^Pso|95`%h%0+v8ZJ+h2SI&v$LwSoo>0*Li(Yuk)8*cXk$o&WQodW(6+s
z5ZqJok!i7e|FLbkw-fU6`p(U@PQJM*RU>ZCju(NT-Kqy39qlgs_9jwARn_sf?vt4_
zXELc7+r4}V+SGmkx~_P}%$b^Hzsy8AIXPckSjg-*-;USY+Z%K-3j^pV29Oo+_x;vW
zQc?m{KjQjvpn+b{QCicdPk(Uo{+__aZV#`l47RBKWx|l~>&r{fDzyoU&Y%@+UteE8
zeEYUEc=p?qSKZ7^40Hm)dHerszW(l3@dRz<Ugirru3sU+=_9Bgzb<xn(!D*EQRn?<
zoAH7U$=_N0oX2KnMe3<3fm=_U+gtse$7JHi8(Xu*?f(5p&bhhC_4y%I&`F%r^<r6k
zHKxs+IrG{1Tl?BlBHL6vb7Yj17S%k0c9z^u+`DIYe0Jg{oyYz5{|=m+Yh5hE-Vn7l
zYvz;oScV5ro-Fy=%&oNb&D*yZ*T>smOui8P;L=j>AAi5!fB5pHW|hdo9o8Y=e8oX0
zAusct{o!{0{(~n^a{m4GwR!pS<(}(p&cb7IuV2oboE#amKC?Ho_ar~QusY%Kh1W+w
zb5@CuGY%g+X$^{SGrqlk%kEi-YK1toa*3L(*VWbCSoSswbOpzQkYkCrx8;ITBxo^C
z-QQn{pv8Y*zO?9^zOl1deO2gc(59wNxyu?$mM#U|*8sYj;o;$SMuw%{)5WZ(C@l4w
z>Qqu<0$R0P`}<p_n0MyYRiZXFHWyZh>z{3|pEhlp+Sd(VpPZZwnyLcb3hgmbX@*&@
z6sXu|VP^*|ji~+g<=`Y$Z<qc|14&6q(9yzmzu%hkNEk3Mv++2*y|p!PO@yIM^*0{S
zCf{Sd(x7{k&ds%cd}Cv>W!ZK!*6{UlXG<q4va_?t?5(=mAS~I>&M(&?cQE7Z3`6GR
zV?8H7ez0T!-Cb*EXE(#HcGpR}hJ96Ev-Wn23kV7Z{wrh$ch!`XO{%}WsoAS(mVIrF
zxk2y8=*?-opnX`u%l&4)@p`&s-ty(@ZvAqgIdbL``z+tB-~Z2Prcr7DsOxb#(9yj9
zU(K00mX}q+&pv$@;Pvd;vkhCefQA`BQ^8?tqh9{KnU|iPzToANM9`#i`<0~o7iJ$j
zmiTzjkz*%2YbTdO)(7NEfeuXr&sg}~+gJ$d3h&KacE@7MZns{kgNF_=fhIHM?CW^k
z-Q8VWT|tN8ZqK{xba|QY!}ss|L3?(;tZ+K9sfU@JPr<}Q1T?KYY0{*G<mBdecXxww
z$h&v%x@5yTJv1#WBtR$G@B97Enn%jS<9R7)25^F+vw)0D&ZO?8pkvoS<G@v4G}f$L
zEBbuW<jEiZ{eG`(Ybz_RA17j>D5<QitqnT3vaYT!>b!pJE|K76K8{{qU5)CX0yX%6
z>;-V6rRTz%o10zx0~UZPo}*o&&R183g3`T(we|A|RnV~?(&l~_T2g$>^6&MWn`@n&
z_onj83qh^$bv@ACHuL&cBs_c<u<PWeo+(pAK-I_X?fKzf%Y7cE8GvW*J#;~Z+ELI5
z)nwt{YVU7YED-}0YDu7RtdpI+u)zINb#|_`_#~CYTU#;>jExW9*;x#3_824|<6-tm
zj{z-H1vP4(J$t4RqVfCN$1h(>7#x;*O$Dvk)8GH+(i1rc`^rx$PR`DtyIK^?%*0x`
zL_uRApr-xS?C^-Fs4lsQTpdrIq(nqU&V1v<3fd5Pd6{o<?GG6S&<X|6QT~aEiE2L?
ze$BBgzOX$%9<-4NbT>MzN9Pz2An@+q-frFKZ5;E0_H5Z=VpI8vB{DM7@|>lW71s<8
z9dU7S(2&-R4T(|WdK_F_MkiTWJ3Bf~7(iR^f}$0|YCaeKRQ~+*G-~}rU)w3tk<(oJ
z9YPdBR|Gh2w!ZS^<z>;`&bC!wJYL_gyj|X2b#h91^`h(TprXIlc}hLFlk~-EL*a|i
z4TT+_`ax4+?Q!go!X)tD*?G3olT;EvJvj;54zbEL#OEtxNp^O&h+d2Y18Bpql55w4
ze}8|^`n=S8`mwXK&0Txb3yjmx9a-i(yWsIL-V>X8KnqQd^+>+By?y=3k_~28SA{mu
zoGA&K!*gooS{Su8Yu0_~l8Gvu;p<`yFSHzcy8V9L;T}ojf*&6eLAAv1@9*1p@3wyQ
z_%UdG!;hao7ly75TXfu{<9_{r*=BbBu+rRiKG_d<%kS@f*x3_&ex5DpfN`IBHkQX1
zX>QHFe(cm#?TZ_e-5oD?Zm;`Wr4zSDqW<5{<>%b$Zi}~EZsQhz0Uh9Y02yOCwXvd6
z#q-Cv+xe`%?k+AN8xZ3=FD@?Lxz97LOMViQ!AgF|&W;|=^7c!;=6cV0K}!bs1Sd*>
zgY(tK{F3Cy0)m|fLCJKn9B45eNb>*R$|bqWLr#S)cH@oNRpR-1SKZ%VKmPrG|M2bG
z-ku(wmbSJ<prhE-P1b;RDXv?$ZiaQa-kv>sKt0Zj%95>WzOx)Asho9wt{)%lck$xI
zg5qLl(6Nro{pE9RY;Y_-ckiBDVPRp!)~u-~Z5rg{<@wXo(?hRYSz0RE+5O}7PuXKt
z@}hxH*6P9g{r``>y}g|gG(g%idGh23Cy)GkxBI<8$%_Ec!1#-so7JD4o7)ZAdT{6v
z)4_uWHRAW#xb;XVR{1D`wwZy>3p2~T_2Adn*Bdr&Jh(aiJZOI<s6j9-6*L-t!*X6n
zN5>WTm=0(|*@czC>T_%=g*NFpPf|InHDCXK&MEV6pfwF&I9y!RI?bQIGD|$f0;&zZ
zzPc)G+ZC7$+6L<EqQV9WLD0>Ye?j-dCT#$%*#Qm8^n>n)J+`j;`@4v3Ig+3fT*<X7
z;ntQ+(9)rV>}+n&NfYMG$qBL+nr~Um#w%qaVB2<)laKG*SJS`Ar>1Cv+WDZ<ljqFo
zS+GFi=uflUTN-j+^|x*7|H-&^i3FDBPE>N8Flo}KHg%&qKR-XU{}+Dl*Nxo7l6z~5
zV@iq&C{dQbiz#`1jrZNVcQdR?wWLh5TCQ9PxtPp#xRtwPwn?TCXeY?)_4^l9eSK9>
zQgY<l+USdGB8_!ocZsYHU+)$YGUbIKX#P$I-e~|G-}e0ce9#cbER)P8t<Y5o_xIJV
zh}mfb+C204c)zlelGB$Nhg8+oAD@`0++`jay*;mYk!v^Cyq=!3FE1}o%*^CusQC3o
zQ^oVp`u+d9jvR4Wd;R;1i-#vXo;WdbPsPSp+5K|1zu43b?e-K#Za>;Bo_unWYC&mf
z>-O#DzrMdeKUa850%$%!(e#EnsP}yrHZr#2_%TJ(8y3i7pmA%c*qrdse|{E&4s2Mt
zawX_Qt&@6EMu~@5K=%rN-c|hk9O&qZZTa{4ii?Xu9pJpYJSKIMHFxCf_SgJ0I&|m|
zXowngS@wkmj-bXS<MPE#51yQy3_5FQ&6+hI{`~wb^BlDCkDXtRV}{S1En7_1{@4F^
zdWyUfTf_eU|D?Ia^^SlJOcob!&%M13v{(#u@Iw<T_lJ+i<rmk1W`|66WM5yG_~gVy
z1_o|!Zibuj!3>}i8$r{1jg5^TzJ3)oTWt8?5UZuDtLwwd{`Rh)pPl{q;-WG`gU)Ht
z4w@;N!39rGiT21^i|sCdFJ_}DC>VH9<)r@f#j4<@|KiYXIgy}a>_7_$ot&6tWMl*+
zB|FV>Z!w(M_i};9M5P;BGABRqJj%(#bL7j*%b+!Le|}$=k(QP|Gv8i*v3tLmg{-8o
zvGHb`SbgvU^!pb~LIgf!yP3b^TY7tI_I1$Foo8p8KRz{8dx8q**;%H|+qauneSg;*
zwA8Cp?xF^G6U79nKas9K53UDIsO|#K!mT)bOwshm=B`i8@#ecWLNiccd#`iWhjh`W
z?ECYsNE@YafW|Sn#q}6Y)D^4^T<kXMI%qHG!DjZIpG^~getHVZWqq>NY~U5RcXyXB
zE`NV-R=XS{Xc)AkuP-bn-3v747`i&_;f00Hpo17eXRLu{uKML{oeByJKxeFg@5Q|Q
zz-x*|<Idveht8k(zkDJvFc7qr9el1pV`C%e4lSFNiIAc1(Ceo*<!rKFtrx$q2eh%o
z)>iiY-tTgJayA{HvAXNN&1}3MK-UVsy|uMT-E<G=a6-@pq{eAH3=1+YF5=+eIB;R1
zGb4j`__`zM^J|x7O>EvSD6V(mEMiFM(&fvEnVFqyqqi@r{{D`k;p*z}<VQz3!9z;m
zC_Vyh;c$W0!d+Pv%FPh4Cc=>6ru>IJSJuT^gBAsx$T<d@uK)1)v-9S(v!D}vW|?L)
zF@UyFv9Pg$uEPQaW&<NLi@(<~&~ofW?hBZnJv%!aG+}c`)@wUyV;<n`aEe=Rn1j|c
zz;oz}<Hr=YLgr3jVxR+gVPaoFI~()!^UuD%a3LUOM**Xvq9W)z0?_RxptDzx_sKFX
zS4rNGeO+(IjvX3uTIWxk00mxRUS8kV*Vh+Amgyefl6l#n{$Gtw<R+H~N0RRBF6Unx
zz5UqQ=<NYZy+mVnm+|_~w_|0vaq}kVP!{vNI|nW;^=9?YssP;!v@Q4cgXhnuKfd$%
z`FTMRk(RKvQJgb;dQMJO@0MHW02-t064h>d@gf5>n|SeJVBx;t<$fI8+`=YvBerH;
zJtSZMXJO^t9firD=GEO@rJx~^YwKdWSB0+TniDYRzg|qi&rhjKmM>>!c=Psc;fo83
zHkF@_sEF$^Fr=ragLcI+BqSy_7Ck+sXk``knc>$|?eK)mOwA$}C8b47z19oBm&A%P
z=;`T6*i;xS^PSDc0NOwVI$ERnnGXZ##8%L94;2-a4w>K?zrMaceC?VTJD*I$&Ye3S
z#iXUFf#x=k9B~0%%-y7>qEuyFSiWM<#8gSp;>(N-4bY6;@qYQm5gU_UTw5!>XV0Do
z4<9O4xilkcJJ2d5uQ$@L+U`>uXg$P5P;HkYvu5pD(Drg3IU5NE(3lD+^ws_6u}s*j
zaXvi0w)OY-_uVp=6Lyuoodw<pb#AWp{R<|?j-EUTT8wpgP2^^i<4VfP4<9~kTp7Il
z(dYB_*JZwc`gG{!<>iG>Pl*aH=6d?{X>0B8Z=fs;I*(OGR#tR(jsGkY&>Yx~ijRvP
zc=Epg@$vDG2hIEs9zJA*9F&~&^3qa`xIGs8e!bGZv!_z{c%Q8CP1#P*-9oBf3BSI)
z1npf0Ee?9{V8IXbt!ZbadZf+$Ha?iXGGcQYFQ}Aw@ghS+Gl<2#PsVX~+1m*dCo(b^
zn47ytL`Z;EAsn166?c7I?8oEs^%`P&KfYf-`{m_jK{2tkN%qSb60WQOU)l&7WKj71
zA9TKG8;@kunl(CW;`htlyLa!$yWQ_u{JmUULJVeh$~D}5x?&-0EdY4x_)GTHRiaAD
z%BJgoe|yVaUtbR@i$QY&mzH`zeD+MOz-c4sG~j!CtDo;!$bO>k^Um`3_tbu~X$xMQ
z{iUdU1?ZI1<^J=J-Po86no0ig<Hv%SokgI<J==0_Hcgo#a&fT~t0(wW0n_Yj4-Pi7
zgZ9MStN&li!p^=pc)8!A<HAk7lda7_twivKb&ZXnu{m%P@}x9)vyDASvQQ&xi-wS}
zFk{O5wAvpZ5|17-G&3^;6;r134!*s)nH_YVe8EGee?K1chyI`0)zZRZVQsD52RavF
zl1gToPwmUU-|ruvYhBJ`IqxE93gOS6KcL;$9+Rd#u9>P8`r&$fJ?9LcJ!xlWfrbD;
z$Jp4|+A=aEAMZQ*;9&E_Nt2pvtG|7C__@CF$A^W_9Fu~l&79e}$hG^Gjl8@(KQ}iw
zvtNo0=(yPXb-#ICyF?fnw&dNFdVX&1VNgB%bb9=wH#aw{{rq6b09plOXJ@AoyKBp}
z_eVvw!>+tx$m;@~@zN=*4mwz!0knL)qN+;C!a@SH=@@kHNy<r~gTX?Af}%04F3_9)
ze)Y=R%T1g((Zko*b)u3h=v<?iJr#n+X=fNF)IRo4NLcVd^QdOvB9^?nyOw_b11hEV
zR1_ZObzwdA_V#wroerRbyZYtr+jLHMeO|WZly&Cw*RR2w2%Q`p4oJ^BR$-cRLx5M>
z?8qY5Zjs&2Z*OiszNEbUlA5kAXf(+YG#4dr$HM^f$&H09iQq=-&!hW5&7xNu3a=zT
zPD#EG9t%%;JV6RPr}1hd=;Q(L=<CKp4_>prDv<HBOtV3|Fk^R@J$!k2`HM?SyPy5}
z`ue)>t8`HJ4mAFG<MwUP^yS}QUqS7Dm;O`{ujzWd?EG>XeSbfl)(5Rg*jx2g<T$su
zUeBRcZs{VM#S<q@VsdwPpZnamaQd_Q?AzOPlai7Oo}H0Aa^wi;q!Q44#ho37XU^>K
zf8f1w<3`X~W1y^HZ8m!q8?RKt`+IvoeEfK_5VV$Mwt2qWWHnzFpR_rkF~?W0w5oU>
zg1Q4*p{rWFrfOxzMMp*|YG`mcIyxRo1MP&H?eVGp{zes0+h`G!vZ0|MXs`rygF{yU
z=-e3(500j$CeZqwqdRq@w}DRZhEDUc`g$D8y1dL+!lFRI$jAuP)f7_oda}c9lFFSO
zh0X^`{vW@$xBcpzZ@-!A>$Te_Z9b)_JoU25nG>3>x{oJ(G|_B}<TP$`Ggdpl!MI1M
zUuORCGY03<R!JJUJ=IyJp|bH}*&QLt+~XwzUYcv~%hz2yGs|za>g%}3_t#6$Zk_*i
z@BY~9)#VqfvTN<X`|dh)-~huUm8q34Rx3?XdHD15^YxaYZv$dtdS=X!SQEQjjGbSu
zrLnQ`-n*=I0U8A_E-1RVxFj6!lRa_zv@>WkXwego9%*wvqnSPYiho$G&vC!8Si<>D
zI!N5Q@7ayQe@FTj+kKmDzwz+|wHt*Vv2QG9B_IDOY~A+@EayBc;kaVy#>Xq(e|dRX
z!m30=&aQ@|)u|CQLc0BaUGTc{S64VeCv-hKJDYXcm37MQeF{oSOcN(gtoZUmkd04<
zBR@aCN6OS|{r$u4y;7~*;(8Chyu1uL@(wfz0@{t=%x~wAlCtE~UeGRgA0HmQ*j*|b
zYc2Tr_&}$mf+m?$($f#0IRjb)bV~6NBQqNVL!X?jmXX@a9lyW7UmUtROsl@^%T>_1
z@$cU8+1uNL8p!9)odezG1!_A?m>>YUO~%YjOixd5(c)Kg7Q6Q+ot&h4V}Jer7aCE|
z-@NHr<~uv-`@6fTbz=7Q|71X8!=RP&%<Oy}eXE2&eg2%7lXK?&T>(MCs{(wGIy!Le
z_Xh`=K`V+^u3VXMbCar7$qNPs4{vYKzWob3i_<|RjBeBxfjLu3dZ$hm1@+BNobV`l
zb0e@s=2GCXW1!<xmEC$8V)Tyxe!qYHb!+z3uh%bk2Hl+H>gt+tb(Lt|{e8Mtv%=<D
zm2wFR3jTPz{XVFVA|WZ6_~ODs(8k(3ckc%7udBT%=-CdAzI<@>B_6MAlx>e=wdTug
zl5M|ov~RIw*&Oj3pfMJB9AEwX;2^V#s_H_|$!eg}c0c_(+|Dm3C)d}=%)ZFIUyez*
zD=;Re=kM?D%1TO1)!*N_W@c*MxpPNh`st7T^?#T_U1Zt7)p{{I8shd=flL8SW6m^A
z4+sco5LWkFkbZui*7sXCZaAn-2JM_}y3{2sC)ek1_mk!HG~MRu)5X`UT`MRq&Yqo}
z&BD(9`1$<$W8dE11`SJFtuhE-ALm+CWmQyMeEP12i{5l@kEPKSOuJTX*kIr@-%b`(
zS~@LkQ1N772o4VZ^WiZ6hmRix=LGx)4ePwVzJ77$<z)pWB`p&tPAtm({_bwXrWDRe
zlP4!;Wp%mt%W?W>v6<_wi1PB{Vq#{VIAKD=p+iof=F)_dDJM>yYFfWu|IgpQQ)e#&
z4cdM!fb4blVE_B)^LeS-yFWfY&bIJ;8yFGM@%8m}Wi>T6^Za`(44~z=pc7T5Xa@gC
zkeGV<$`uiiKS8?>G?p9&UFG=VMTU!u3uwh7DDCgrvqxe2>4&dgX<5zld-yV-o{Nj?
z(6zPE6X(t2Yjt9DcXzL-u1-EP!w`J(SH+<Xk3;0G`9j5i^RDccb+3J6QJ-{Nv-_``
z@f(Yf*f$nS^vYzuZhZWwQ+BydnatS@j{{0KKAy1aM&XKOww0e)E?&F{x+TzWo=xY^
z&(D<&3<64Y)_Qw+f$rJ7bouhdb+OiG=2!}Ymj9lz<>cf9kDGs<|3Bfx1jVLFU7|8F
zJ@tQI$4^k<JU`#Qed0vHdG_^uo|6P*WP0-V{d6mFQ3TD>gAUix)LePzU@^m~_cQlB
z=6sQATlYtToloY#*6iy6QBhpd($b&}S%r^}En1v;_3`n3(2(`vc7E;kTQe`SfyUZ4
zZZxc^sVVsM#B;{XnV`{AP>1I7GGA6Tv36<k5FJZP$#v`2fwEgnY^<Q1+`3H<k2Wwe
zCuC-Jc64wY1T99+QitZymkU10y{h`@eRzNPkLlMLKR9zQ%91k45CEMysp>tgqt9vU
zk-xvce|)`uzmk#?)BnHs|M!NijRNgao^bkUK|z6ltiQxOzR+onjf__1?|Aa_^DC;W
z51%^aRiZNYK%euMUmNd(%FI*8`+~)+{UYC(yWBe12P!Z%<w0DF)Qyh?GTFh|aCz4G
z`S!=Zy}d0cFW-OWj1TBomv7&`oj85^@IvQy&?1<Kh=`6pO`pI(!Ef*Gc6W4efbNcG
zV`BrYHjCq57kKs3<;#MiqDzf*UO#=>$|q~p(WiC>)F_%VrKOcy{LsytI}a_4kd~I#
zRljU|^ypF0a7WemcWbvFKCBNqgFkq=U&g&Xl{;TsT3UjZlE}!)Zk^-PBWaxW;CBB0
zqo6Z~Ks}Tlh0L?fazX2~KpW*4Ktq6PeselN_c!=y%bDwG%wN4)yQruLbkFjiKQ%LE
z&t9EV0h%cJ@S$MI^5xuqpmwfxAuQMIwGn-|w4Gl*=}-$NX#FN=vz*^tD@F!Tix$*V
z|M>Vg2R}b(1DeYb)m2;dVs<c?o152szgrHPw|-#}avHRs0n`9<abW>X(N=s+VqszF
z=vx|UBfBa|Q&Y3z`P}kTvAc_&f>$Gg*6|lVKL={?OPOXZdD@b+;jzHpx;N%uR^2GP
zQK)seFIen1@5HhVphbYk6OXUt0Y?=$=GJ$~E?)z3?2QeH7NxI5e0+T;&Y!>DhVk>y
z&(AZiuaiC2FW>LlE!Nq$DipNgqqq0ywYAZplk7x9L>}z@ey=%3542DNbV15R!BVfn
zLPOAy#=E<_U;hn|4?T0_2+QWQvxoLnes*!csL9I8nsI-hE$EVf<YPP+3rqSIE>r~7
zb|;>GD!RTs_cq(kn04l}t0SYM7lXD$?5o}V>DIAcY0&=GxV=@1W@cgf|9Im>^I`&a
zf|^Pf7rB1;{@uN-%<RmWGa+mj%yVzG=<oj{#LCLrG+9Vc@T#BNB4z<WK|#U5$hWt)
z23OkF|ErlXb0&C0gQe%8d-vqx;^II{T=xC_7Twa;mSw$4VBNZP1_lNP4mPtVrlc(S
zlbV>S;(2JHbNiMFeObcQ)zvL6EeUUKYy=%9tD~!%n31ufs9(j?qWs;Q1uaWX%h}a*
z?Ac=jI(&|+mFd{AV~dnC?;dL9zPPhET_<8g!*b`pXFonZZkTpP0#p~dc8i^Q4Voc+
zad9zdXzJ-!&~=fPmXS~QnTuNcJ-t!5LT$tS3#*gh@n#;He0<@o1AWfxyJXvCmm9qS
z<++ev+4d|ZYref&Wpg%xj!lT!Rl>>6FLwlVhEj2H@zYrg7b=1lFa7=f{q<Rfs-Pet
z&{fs7zspk6(?Q2$ftC>1{rPa%eBb#!U32Eh?AWzS%Uu70xu2h3L0OsG|9^i$tE=|f
zZ``GHc9!Yo-)HxnN=`~T^nHm}NNHJ0U|`@(yB})1Yk!-8ET5X~+{VMm;4|ND?&0VE
z=WpIzyi{8J$gyLut{!8pPfrQ?8F6Q>b@`5)e1d`(wI488fg?zFL-BLJmX?+kHdj7R
zYHVb*v9&cUe;31e@<@P&h=#6i=srDNUES~1pTDnH{Iwgj1nJh6%oXwb?Q(K*c2rx2
zzI=6cbw@|X0Z@%HZCV>>4*k`Yl@m@s-LP$&n5_Tnb8{>YUtXvM+Gu*?#*Gy=dxC?4
zn*8nminO)0fo=tEZf5@W_I5ky^lwE)MeuZlnpm@}yQnqaRhDnkmsqU(w94jmZG0Tk
z`*)d6nanCqP@A$$CiIPkX!7xuQs6ulB7CFJL->uw)Z06Y)j=8mU^Bb2we{{ZRiHh!
zVq(kwCNx=CS{}S{LjqKFy35xtxznPdtjsJaDfzVS?C$sbRv&HI<vsuYc4H%>4J9vw
zJSMStP69QpEG#WG|36L()Bo}7SJLTex*tA&zP!3Iu@ux@v$B$^tE*eI_(e<f_PmvU
z&iHzJI|l^?&HN2YjJ?w4kJfI#cPY(gVOMu|Vpi6wqPI`8xw*LoCzc4A>#c~nzpoaw
z6uiFvzfm?TD=P;#_hHbOnF{En8)Il&V1-zKhRBYhr(UhELFYfL=HD+QB&1dAyJVef
zx7fjp7X_=ozkBLz8?x~B_Wb16*VckIGX(_&f$FG@$;X}arh~4+UG$jq=;ei4Wj{Zq
z`pmP5d>U0#V<Tr%(Eu6;JJiC-z+i1{4cevl`}_OryV<8Rmd)7@PU>~euab_hl(6<Y
zdZTdFvASR}P>htx1c`%1w2t)!o0iSl1kNeo2Edi+)2Fw8dwV;4M_f!y&!kC0x@to2
zUtV6`(beTtQc|+?yQT=2$D}3OmoNVp8!CNz&q>g6-LJ3ds;H?cK{gqIP8tLCQ#~fN
zfVPp;|NnQY@e8O-d-{EK_Vsn3+53C7-(x{%OXc3)rd!T%<?h{B2dj-WH8r4NNYK$K
zr>1Cb*tALOyUUlnySq3&me+!2i<_F8r_QzlRfODPIvU0EofbAUHZopY7ptwX)B<#r
zp`&Btr_#DQy9RORtMz;TP3r9Iytb+HNH6yl&=mL%@UDZ{O0PdhyTvC?oY)Aux#-^B
zYS1Zub0&3ktoZf_mYG1?$hKx*KXmF8*ZkUVGe3#1WMyRqU59dQeLUz!tb>}JS@ZYo
zv8kx8{=86b)s^V{y{*5#z6R~c0@Z(PJQ553FxaZAFTb-s^V*u3X3AWk%rkB7+}>@u
zw^zl0HW;dS9y&2mIdt9k_xJaoYOlK&^2Wl&wEu70m7{&ZhOnH{_Tnp~GZoS!yFBTQ
zMQHMI#VXqy;7-@8%^No!ytz4DI|j6s6?B(Uw&BExg$oxhQoa)PYunCq_xIj;k@V)q
zMurA;|9PNAwa5GAkAHl89JCA`G*iuRVMU-a=rrXX?Uw1&r+=#VpKlkN>N`ng@4YJr
zZ{CzV(A~T0)a@0X_xG7EcIyQ#wpkdU0cy_wd_Mp1$&;Q><vb@{Sm4OK=kqyh&>?CI
zmL!3qbh4VSR&ni-4#CuQo|BfCOP?%w%=Go^>+Ag0-`^d*vNCuo^9%iYz39lu#P|31
z-r3UG(eXkQo=-rti=eyjK#j}I>F3>6hplB`D1U#?wXo3e*Z24Rpo3!zyuf#uOq{sz
z)9IhZ&(DGHa_H*n`f$-*9<*F5!Rb;cXoXoTx46r31=-~R8lY9kF7EED{}!y=R}*mR
z@<Oe&#Kgwx@9$Q|SeLz#@bU4vu(!H=>g&?i*Ie)JD%~pSpT6O7NS|!G$wBnoV_GJ2
ziN%_4Wj8oJpheeJNU;TOQ`i1_xg4|%5Ol&l=qexmwyRxTT^kY(GRasJFi4x_2+Rqp
zjw`cSC1-4G3>wMNjov0A>zY1e)~uux6BI$UDQJrQ$BzoofH7!e#A5e;m*c`pW@cd}
zEOWOe9%g&$rupU3{hMWFWejn1-o1VGiYq%i`{2qF&|s;H`-R9mI~G)d7O8F7Vlv0F
zm@P9iQ$ts`wYQfSbR;t~GxNod9UUE6rqD+3Ri<8P^J5d0-9e-1pz}VTot@3l0NN@C
z+Fw{+e*N^_miS+w>%pF!6b9YSzyNCJg@=cO*1hmbo4KT<sDNh4{Qdn8dU{?5jW6Wo
z<$<PN)O=^PJUctPyU)c6)R0`H{6c3QU#KBFJ9|red-AO<nV^0Rs81if-0xvCzg@$`
ziLcf_Sr@aD$=lo8(er51@s%>5wlG?zSe6B;I#5fnRp9<CBxij7{{8q;@9Cff0qSTn
zFzk%!d-En|%9JSwu3z7NCpheDAflzU7}U9V{Gw-f`FkZ}V`0#qrSSFhURYQ?d~~$i
z!^bCNUR~YiXTDcfhx5PR^O+BHpyj{6zq|W1j-2+@Td@XoPeTdI+@s$WLc7KF#bh1R
z3m-SVnykXf$Hxcm5wv!6yy#WZ6ya)pApqLW>at|!qD4w??(LP1-j;K)k(oUpB0|Gz
zlEB*N?QQ$_?=K3!^7Qm{Wep7uas4=#-{0OE=G-u_sr<y^>FL=tdD6Pf8ygh8yuGK^
zm%qBcp5NKod1|$ar&C<qyp9SNtMjK$aRo2)IXK6%c*=E9e);_Tyt27@_*2HazO&5|
zkM&4aeg6LPP%HO~tE<I9H+X^S49j9RR#sN%ZLTYe*7x@ErWi?@<=xTHSo;n#Gyuv6
zUtZlP)H>F;*b+YU(-9{Nu0u?Y_kC7}<co{1C(oDxn&+A-Y+(QAgENnWfkTPO+`|9=
zYC+?w8#iv8a581lV~*|F*Y(cKGUd+9%w$;bXJ1NcDrf`24D)<B8yg#z<yZQY-TNN=
zfE>CAI%3hThJ%}%+rr99>;LPUo7G=kTdQrQ6}WcFv}tV@E(9!Dz8rL(cfI`ci7KFW
zo5&Qu?I~$#iy}9trJA)XYn{KkI$ZltHS3-mQ$XYAtNML=K=g`fff^zfB`*X(qu#RC
zWe+Ycb~i9KzWh3V!qX>DKx-<0R=vNs7c``olas^1FmK*GE&i*5d!Iag%IY}@RJNEG
zKl1^No>zZ=w`lPT8Bpr3uCA7`tC3JtRP^xocfY@{*0A{586$pObrqEZM~<+7W=yAq
zly7)E<tV7*w;wc81})sL9<B?vg9IZ|@gi3?=My4nUw!`M35&YA`bEPMx$_3qpfT?c
zU%t5PuluVo{j_2IznZ5}-D0|+9iT03ZLiKU>{`8A8?-G9bd1Z@RiQ7gub20~%W9Bv
zLcn8E%irJM4_~+-;M~Tu@>BMg$_YDGtl+RNe|O~O=Jbivr?+3a6g0KebJB*ozg3Pe
zk92l)9BAPbPDn@qEy!4qd3o6)<(E2nQx<hei-){9)+;SxUuQFE(j=`nW|LH2{(Z08
z(a~XY6uQ?a>d~2*#y2*la@YO+8V;HPnxvBW=ElY!kGl0QY|oG1TW0}U-wYlX0iDeX
zy0vCgN@vmDB}-UTRaF-~n#jk^%`Gh3nAHfnu?@5-33N<V-W?0jC43t;Z4#38RzEY_
zoPTfCSEqJ9*(uANJtwu?+?+mrXZi6y*{bgg7c5?^3~JN7wAIto+fneaX`0YWHE=CE
zLG1>35DZk5%UJtey^*hV927I)F-%a*6oIQ<NJ#`49J4bwHwRtC{N%($12Z!*S@-8J
zfB*jO4Z0Y#fsq+>qU@VDIa3)+7+zdoKR=H5)UDgMA75JP4QkbadaLg4?x05O#fyS(
zZ*Lcu^`Fty#N;t)iA-M2&snEVoj7q|fn#&Q-(RJm6V&`6JJ%*opU&Ru)R=a5*1;o3
zTuOWtL8H)Xqs>7*elanzMUP+D<W2d+WUja34rs>z+ndNgzwiHV+q~I$zrBl#i)jz^
zSRyOXsh6N)XPRy_=-d>u+*_axPkXDsADdyA3|gdK_xD$4pXQzF_j}u?YKMc)IRf2p
zlbN~l)Va%`^Kfo&%VkwlS#;~otE;O|v1{-D`AiygP|M$6Uk~pnd<?qN#U%e;Oo>Zk
zg_THVm#n+(8w-~&RvRCO^nh#A#dc*fN>y{gB?)NUBT(L&PjIi_8;e)o{{F{z6h2PK
z$^xA+3%a$inT_|+gbY@T8{a`2H8v(4?c%zwtD`ev=FF8xU6STnmxIpsKh`O%UhwBf
zA!u7CXt>|ekr8xw;ENX>|Nj0yeDR{7ZS^;oxmKkv?$^4G9690@e|bI=6BB4zE+`=1
z+yD*mgYI(KU-uWZCM)r98!u=!UpBY{)D}P1BPnASE_{D~{DWhxQ?2X%Sfrhu)ms1W
z^ZZ4NL7P%0s<75qJAg{{C6ht-+JSbCxOR(yPW=PT0$NyFGBSV;zu|+Nls0ePyr#)r
z<^TWHR#a7i_L73mww<OI%T-@r&)^UkD0pj2CiBjizNy;bTz+1=UR+%44(dsP8f;Hr
zs=U3m6?D^&LG7;+ldLNq1x}Y#)6dU4I!!kkv<~;-x3{-J``X(0WV!P5^LOmt{aJ-o
z$#lcx75%d9CP(X>uO97l{*rYge^on(-v{FtBJqQ_{{Q#>|FLIhXMen%zaMm8fNu1*
zmKeQu(2|WWFBGljozu|OJqjB40<BhA0j?*VO!M!_Y)(Ia?95E#iF4=j8XFrQIeOGl
zZ89SR=xnSH9}4d5tBo!QDg>SE_W$Sn{|7%lJ`TF8?(y;d$LHo+gXZ&PWMm4yya>D~
zSn5|)WYi~T+ttv(a4~QTsDA`nXuhG~q0^HmPZqd#i-Au5Sm4;qz#y#d=TcT?_U+A0
zWs8;HzP`IFeYlMmG;8PLez6jCan0(mwIOwKueFntlR+!ygO~e>%DSpYMn!>lYMABD
zdZFRs;*zfdZ3n&7U}k3Cl7C-LJ8aE?-|zSHD=RBMm6Cs>86OuX*VEez+LQZq>vI43
zk6v9}opF1c?kv-6H3Qj~i>%Av9k_W@(md}D=<qzyNCksKR+iSk@Ad!1uU)%lQT9e6
zYHOCNh2~4CR;R|678Vy57X>RTshvA_8km~4wzsqI*}K=U<VC<m!OjvfYrn4>9|x3z
zMlBMKD_-LH-J5o!aD^3QFkT?DP1YSWf-Cz5v=z5-RajJ1*NqzyphZl(%icQG)!Biz
zdVG9*+*xn>;Y*i-N?Z~_t;sWId_XtFIySQ{ddy*-bwy*zvSmuDs;rfjm0HX%zQ4QM
zymzlHXb<Cs3jr4cOAobjix<4PVF)_NU)^s`gNkRxzdt))L|Cb-sIWLXI#&JMYiMYA
z5Olh1<|P#oaq-1<e}92?@PH282eokz)c?I+uc)u@Ul8=xy6TGt==w@o>#_y@^X(Qr
zezE1zqa;ur2|6n7@-ko7<AR_%<X!y#U*e!KgvZDG4_~+tPy$-GZq5hZqtek)a%Glj
zHt0aXB}-IHvaj)g2A-_TbYfy+Cd`|6j=j1gtD(Q2f6?N_8*6`;f$qFX)m2ktTkPHs
zx|iV4;lr$|OKvULu|vYp&=Ay*18v4*W@er;WlBe%>yphk3OnNTze%ssd}HDADtW(R
z)nCv+_=d*<EBj?ZI}na9oOP%#cxyYq{GsdD#cyxVXaA72SX5kG{Lkn4|Bw8BzhB>C
z?zcC$wsLPyJL?n`CB*<*e`_?82XsldO@#sI_-cNB{)3uZ^-WDhYkz-hojO(2tzWM9
zzySwPPX}~3`>(IB7Y1k){Q8m^5gFOpx2n|D)fIH60ci8<j2WP1yH76^?5%Q%^u7vP
z3-I;A>TrDvOG`x+6_<jbyNk~=znE)P+O&PUc~esp14HiZZLKkS$1g4QW@Io<I|Dj{
z6VwiyXt;IJo_hVI%a%PlHB}q5q~l)I>$OJAn<uF#YH4{z3zj-LIx>Qe+-PV3U4GzP
zA~W}JFSpkA<l}sxHPx!Bs-RUbx3=X*zf;(?d-v{!5*HVjt@8t~ZU>JQPUNVotNZZz
z^Wk1;bI^IKpt;4z$9gkvZc>ejjaBp%Qt=d$4ekKlW^kap-AKhVXy3Y1KR!N=PuE%1
z$|qyd@bdEV>6I(k8SdP<^Wo|A_@u|jdYL8#=7Pre-rU_SE+{DI;o-r+02==0bzSlp
zQkR%E{%r#d;RSx(a39oj1F^5Nl*uf5l?d)dfY_ihr>WjPK1V?N{3Ini=gg5Qd3#F~
zbR*$htI`jb{p~?(*6-JR?v0zHu`B(&9O#gS`2BSgPCuPtU%#(tt!uX!Xcw%Lv-8&?
zhP}bd{XBepTK4a^XJTev7@)DC=4TN@Lw7fK*!sA&;fJ5^E_)lqH)r{hC7^W2)yi~s
zwt4&J&BmZpYMwk{VP|K*vNG7cB<7N%(M+D*<?qAz7WmIFU<92pw%ENtAS$Zs!i50P
zs*?h*w-%+ZLU#Vo%euSEbkn9y6Q)iLP4kuiKQ}cgiK*3zF*!N;Vql3=rL?$7?k$nN
zzP>v<7RbcK#hv<ZTl=eIs;TFs1pyigo|EG8IGkKuLWC=rpkszb&(27K^7!p-xrguW
zE>BEMY^?wDSiYdV{5Yrq@ayaA?!FbGY;0^3R5<<T+kyJVi3te-Pp^NN-Vq`vEG(=O
zxrrsd?q}-G*Pz8}*W>GZo0^z()s<tH;h$IbSv%j`<%>Fak`XjQJ7L+4!j3Gl-)HAT
z$Dts6>vKqat@59rQb7e>^!7YgH#fF3XU{55KmG9W<7PSAsug#vQ%{MwxVkD@TSo^(
zy?uFgwYZP3FKF)M&6}JVGiNI5>G2uO<T=oNc^2pn!=4_VgPuoEojrRLI?<G!ojqgb
z%+9_grTX=CTk`M6S?0WZ@&t5EIfq}^?iZgqU)2Bk$PPL~f}fus)ED%hZwDI90FC`Q
zJ3IGC7&3v@$38yR>*}s5`{`!-{D-%;W`mm&t`^?jr?c{16g(&0+t)5{RpPPsHyf|i
zmsyiRO^BHmpl$gsE+O1gr%ikG;o)J>bvmG(cE|hW4<9+g;y=$uP}WyF@7^9xhK%d$
z=AL@JYR{heFP2WXE|Rw_Vkv!nEi_VFPw!X*BQt1*|MGHwZZD5rPp+&C1`X%t@BiEO
z`}_ODCr)rUxATDxV|noI-MVo8aG||=Z!F$ee0g;vf5k3v@mKraoWYv!Do>frD!nq9
zMc2D!+hyCc*g$iL)_zw(X9IDI>n(`eTLoH31v(>-N7ib~p+?XGl|#30OD|ozG|F#P
z?XhFWA~q(mF7ulk^^V~eXphiQ@%RNBHUty|y^Y?G02-IR2s&f?x_<1gmK7^Bo@SoQ
z-}UzP_QNMna;}ZqDkQr!?DBKQ5+z?ygKpoxeH%7xI50&sI3YDP^j+tRySqw-CxEVy
z_Na$W7_FG5t)p`UbP<@KU}Nm=vd%u|kkz2kt>j}pj@$F@K6w7Ty-(Jfi6JOB7<A>*
z9Q%4XP;y@pxR^y<bz)Of(}vR5VM~@TcU~B9;NnHWd-v{vwt&wv%~rFLyC~f)+wNif
z#vC-Vqx3d;zv3ks@Yqkg$L|}39VW;7Kx3<c^SisbLCfu`zGRqWU0HGJH#Zj-=nSa6
zHx!msetrfz+$8PXoXB_JeHEaam~U^-=k{Aw%f`kAitHyvl{;VG-j>@OqxW3FFfM08
z(W4`rCGYRW>ie(%_iFX}EBn5Kc9s=BV)=iE;l%m#?He~1w$5&RG1<EOUC1syPa)8G
zJ<EJ&XK7A+_v7{a{!f1Y!!$%DsC3pZ2laBdz#9J{ub)17^5ELqXwi2CRSyrbMnpxu
zdaD0?Wfti2pI@)nPn<b(<sSx6INZ4-<2_yPXbYz>i@M519v&Xh5ISfk^Y(4&u&}U2
z%7PQ;B^+1u-FSb3)s4aq50NsNOCr{ME1PB8J6sY$5|2R=E7U-H)mN@u>EY?=7#BD1
z6vMB*)!#w;=LD7A6iiG)N<!AI&SI#2du!{DSF6{5`0_FsG!+SIyS=`)R!~}c^_@Kq
z^FzuTqUN`!1_uQRNJw<Fw6KVXi9Py$zrNi^4YZcBrnVNey@-*St)p*cDH|KxQ@-&3
zb2~dZL5J2HIN<Q*<z;v7lSgiE$($T@f41jjwM@m{yobkFSGDm-GI@fJQkIaC0u8-|
z*7d4*T2y>kAa+SmP;hT0G-JAKz1PAiJYm+Xt|w2P6kV5<mA$ysTO4$bew3fvR##6?
zPSBkdv(59F7(nNmva_>GNJ?`0x$RO=Rb_p@=d<6=?C^Cl2fw|&4O$UZ^6rkLu)1H!
zYZF!_rBcwGV#5A~t2R6qn5Y41(yh>XW8tF0WzDyjt4wAUmo?v2&;otXfd^q>VW6|f
zK-W4KKl8b=GMN4K_4Vye3lF@!y!>lgbMs>NekDakMh1iWe>D|VRnvA)Jaf36e`D@#
zvn`pI*_Qjwy;S6Nw-_`MlXcZ=XJzBQizzeiT)6PTROMps$&)7wN=refVm*BIs_Vmt
zf~mgTY&;SS-rn9WE-oB?t7@gq^N!3i%`W)-%op70-nx~QVad{^53k49yZ-+67E}&r
zUtg!Fq{Q^|=g*Gb-m9k*Ykvuw>jgZ0@`S~6l7PHCxIz7Tm5g<n4>xG*<vkl22X*jD
ztElz4x3__|BRo4ZGx*)FM@PFsS@o&2w2RBtkB9l~LH8Dcj#KFt)17kt`<t81prc7{
zZcaayeeK#c4?n-Ko&6mi!O)&2I3&S+P6R8&-^Ygsv}$v6`gtXNeg3DmYHQc43xQ7j
z`}gl(M}L3#&wV>~>`3_f>MCd%+kui>pcM=c9wad6`?;=tQ}}E9{W@v;e?J~e+n!mj
zS8LBW_sZi}uRt?>D(dRW_V)76o;}l=Eylvmu54o?^YZ1(rpa0NC#iaaGCSyE&dAMa
zTG^m;ev66@sn4%zYG_~p-3Dn}{jFu~T3yiD;~Iu9net*lT}h?FZXZynD6RS`XHyaI
zlKlnfyw$X{Wn#h;*I8A4S>YCcJpRP%?RR&VA3k=>?dfwLPft#}zh8nSq@<KgOhowj
z_&}#1?ECplx}~KBG*vG;V@Ah4kvA4g_`XSl@~L3wp+4tV;0z2&cT4!d8MyD)qD6~7
zJZzUgbnYA<Xa(i1t=WpxPlK8^+1K?z+Z5&G<Q64!C8wvi@7Q7S<k_=Fx3*@3#+J8k
zH9d3YjEno_T@4KkpksgnG(<p~_ji@Pe(?0^QqT;qfuW(}-(O!@mtOI;`Q5jw=+zZX
zov1Aw$BrG-(9qD>d~cbr^qt-1{tiYTLD$iO+JKUF?4V1l9$fafKYD7aHt3QUV`F2`
z6vO|Y=j&NiL>EKGt3vXWf}^5VZPN1;y0$)EUt_Mt&6_thbaakv&Axu>&&|jU35;{*
z%=z%<rtzN-hxtKcjG*P?KR-V&e%$n5-_lajy<g7N!Jz@%9o#Ae?QpEP23lkr6cnTt
zV_*ENC$28RD|P3N9S)OJo@Tc?E&Q}g>DMl1yS)XtrsLvlHWa?QWBKO({`h?PSBi^f
z9R-E?ensDnC}GZr92qO}KR!D8;_hy9P@{kL?C!1E*FhH(HTtL>1|6vdIzqSh_qRpK
zTpJS(GJzVW+1J;B4sWRX`fBN>x|f$!K@A`c4UYh)w?<}WZ5uZlGCVleD{WwG+}zpO
z`5<K1`7>ug=jS+_o~G;SesLF{tksII`~HScQc*ND{c5UuDb~$xYX1t*_G(@!lM6vo
zcPCAq+Ir~FA+GD(+}snVPF-4acUS3aBj+3Wt9p8PK!*cgUmx#&xQ!QdyAJ3y$I8me
z01Xk)5~O?o<~%#by8hXPh0YvYT;Q3tiEZ#AbzXZrd)WFo&{;n_cJE%j=IyPm+zS^j
zoMBbEYC*{o??;axhsKGEiYh87FtD<+&M->lvH~6E30j6?mUpKEw0hy@rc|XxllV@a
zJLh(LTW;t&S*sF`Nh+YdGFsPve}CWq;zdU8G37<(5}=CdZ=1={K4+Ij8^9G4xU2w`
zv7j2u<Y?dGeW$1ECx3i&)WF0fgwH`tT%4I<&6+i!wgc!KlRrN`DkXD)Mpr?d=<Mt3
zp011EQz3Zp;K3^6hJWFpBTQr$hV7{Su4iOyoS2>6UG?=<XW!z|+FxHZjT`1on$&c9
zy8hzi<9(;Tf4p)fBxY}wXjxeq=t9em6^FjQy)7OX82I7)cm2&_0RasgHW+{g%^i$B
z%E-uUD0=EuQBm>W?e_a&k-JM?g07cdy2<gxRPAuk7;o-z5hVo$&@H>5%ZZNn$tLFI
z^_@83@#Xb({`<AxWzBMKfbK}VXxRGT7^{nmiwYufgYMx5opD<9!~@jS_}TdKXty{h
z!Ir$d#Cq`H!KUCzdZ1-~r(T0D_5w|e6%`r1y1st>o`0a#eDmx7S%NB9W_G@W4-XFB
z>hrQXa_A7#_jh-Lcb2`mVK`&Pj0M%--)UWceQho1w)-q&Il;XLZxnjSzA;~-Stg?-
z)GFJ41+?}l>A0d&AXvfzB=L3Tj2RmL|L0#?!U@_6zq|as7HH59v^O*GV@Z^sUtiq+
zo0j$eY{J$?wL(hs^=BT;Q}G1dvb~@r36zjF<L`vW?>{@+eD$7td#laAy}8*uV}=Ci
zi04$$ctO!lnQk%NOKC21L9q>)FqSRaDRZDZZVuXnaZt}x?eIfauZrH?Roc9HvvE#t
zE+fPBb+LyxCLh1BA<?<!|KINnaXg~Oj~+dE`Eqbd%G%EE?!(XL*Yml%yFYpIgn>bX
zi?ye>*Rc9q&XQ%zl74-8d1G^W|AQsBj`wnRbaZ&AFkb{6ZUeeJEA;WP-idSO^nfnh
z+_6Jq;>3xdA<M!-LndbC!cR{;O)@XJl=xh71l{i0-`{`A*;aq%j2Q=xA76f^y<<r|
zXj7M*T;K72dFG0b56`X)UT#qGBH-ysPW{-OMXb}NO;bt|x+vWN9-sv^Xdw|I3|S-y
zjwzFakd|)za=*Et67T72&@$ZV@pX=#o}66V+=7CFjoa^4c_%o%wW|7}0lF@Nm0OH~
zVbS8nQ`i6hbsx0R1GMDq-o3bjBtsz~p$ogq^WWUvExtB-yIWP2)ta?yK{r+1*;6UJ
zY}vA^>Zs52Y^xu<eAy|c8wI+$JU~O_)K)Rws0F^W%{X{@MP~%eIdH(iXSUheGaoD&
zcI?~<IsvBm`8m-EK6^kX1-!qvcSp_7O+^f~zrMWu@no_;sBH;4`zPPO{r$zo?C0j&
z_iF|(Q&3iBhTOs8?B>R{%x7j(@$++<`^~?;zJ7dX@$(H8ACnHQ+`4$d0*1G@x3hx|
zSrwS1^6=tf_fw^ylLT$6LPBg7hOLX~T(n3Dw5bxb1J<U}NX>s9Pk4AZ=){ln^K38Q
z2FK@%ua7w)2iARY11)}PYHqHqVhQ!GtJ`;~?|Xgu_jj=(A|e@vf-e_Uetxzve0?0~
z9Evw@-hkG=dmznbOgNds6eM(Uc9(4Xs&4SqsI!X_Xvh$<ezU_v1=529t=9epI;RbE
zea`*=|I9)83A8>(zUBiXXztH*(uDc*`$1Pbl=!Ue?C%fXr|&tb<;9B(7kBsR)$ecT
z@9zy=9hPZ4?;HmgSJT$5rjsU51`Wc@m_0lB+#JgZCsRP<Q+Mv%*--K_=%QgOXx}5~
z(&8UKDpJzZlmGqssr4E(FYxQ@>!U5gpb3MFi;G-aUxQAjs`|Q0O!(zA(E1)-UEcI_
za~z|hq`bVn6O)sh@9nKVe86G<`GB0;+jOt3iBz^~JC}KTn=a^VI0n!VchvU0-X~8|
zdSonx7$(e`74`0z@2>|>kFj=(>mNJV%sz3(3=W2h*K4;Mq@EH19V&H-w=53Qwh9S`
z)j;`E5c9nm7Zx<Wuvqf=UiEuhP_`{7DA3saIXfgoWZ(aPzl+LOtNl&N&+k9n&abSZ
z!t(Ov%NMt|>!+QY(>c$!dexoj6DBYS3k&zi*+vBfDOF7dM+10D$z=&QWT^(Y`*?{J
zlA*xy0@6LxI9)5gU&4@ylasTfudi+4LPgLPn;pA$arvx>Wn^RoO^+=I&;XrjQu_MZ
z!PBR`K}#+Yl9Co}cdlh9`1U3ev>hjKvD=BWXIU9+>i@|wTv+Ze|Kry$B?AM2yu3W6
zWUj)Gk6hP8Y+Q7xl$)D7B`qz>aN@fS8#g*eL`Z;=sj#r{)UAL1)U>p=9=vrcD!}Tl
zf~Sy-jLd@v4-~Apt};P}rrZJo1Q-$ywQz!F_2q1<S}t7*0v%O*XGdXEaM$5p?vUEA
zSHrXJSHHTl^7@RHj*b^+)sZH=UDjt^Ul$8n6mjX&B?bn_B=Ct-rw)Oxw$Hz3Q&CaD
z;pe&Q*|)d1C!9>#QTA3UYHJp2baXVsfv>Nx7d}5H3p(Q!bcW@YEh2NKbaZ?X1&vDl
z<`opY%Jv4loY}=CL>jV&Szw~s-944UX=!PxY^j`}GjgWsMuU#bbyyg%0JMMo<?{It
z-oE8!xUr*9`On|KfdK&u7AwCIoWyv#^5`!WEiEq4xWa6+T+kL>?fb_sU%CXkfgChf
zbbDKFs#)y?b;MHiz<VdUV)Vo(c<o;1GZWO;EPERzAt3=eyBFNojM!hdSM1WuY4-nq
zFsu8|YiVz12j$V_{_~SwU0De_It{e!ut%ct>gsUtDuu<9_zVmTR$Ti#Nk!9qx}uWO
zqE`<gOO^z$R#ks{1G+;5G!3Qb+?D{!e)1K)5{67|ZEZKUW>0^xWJxy{H}}T6zg6&6
z9%XNDCI0yEaE48#QBQ9#tGbGkQY~m+I%&V6l2YukKId7W>KV?e+Uw=z1)4Wh_n)`G
zd%B*1si~-JXUT--X6BgKSkN{<28ZwO?t-o=adC5FVz9BXDfsuNa>?@L-94H|Rs=2v
z^`fUt5qa|T=}Mjj_ji}`fBW_gbTqe<v$LzaDCja2&~n$K-QuC^%HQ4+^`544@WaEy
ztg6DVkHIIHPs!S_e@U0Pa_N!~8ynk>y1!PhuB>GC_V)Ie6!P-A$E22?9v)p)mDnS_
z+^d$IJkRg!eE9kVaGE?0nT=Lj^|k8jE7suP;3LP6Pv8Bx$isu<+WPqO@#lmE1q0U}
z>H{6qny*wQ1KJQIyb*LT!q)o#bvbu;iMqMDfzI^uQ9FEYuJy;G;_(mO-QCU5u&eYn
z=t|g#9R&*?Y<UD4Vp<)x_7LhcI%r1M@#PUtF0MoV_J3PIaqi{@x<uyqart^4X=!P2
zV&7QtG3m@KQ}2SHx8A<KuJ`xVCZ?vgUR><1Y+xV&+U+vesuVOKuOY%U$F5ciG#Im(
ztMv6X-Ko7PI=Z^7>O$Ec9vt-W@;Y>=mHQ!No65B6`=|FOyF5J!89LhPzpGBT;4zbu
zlF}tr*aBa{y{ka?+8*r^6<rq{5uspg9NY~)A|+1Nnh!J@(s`q>qod=6?~y)d7nO63
z%<Q1Er9fj4$BrEX4Pt?=TL*Q`^7sEW1I=tqnj{3exE-{ue0SMfgUU}S7dLLzQ&eO;
z+{Wt+Iuho=gN7+nL{6j_frfLAbP8|SyxIBuJX_b}BA~+S-@kvSCI_nf%wTYKb_N|L
zbK!yj=&*9jq9qTeB$d3n!r9r`30l0Ikf0#K)%s~kg}Au*nz+4D@7vEeiXUF|%dX^K
zIB31wn#j!`&e#77E)iLk8Wco$2<hjoySqwPU%C#O)4g>Bo?v`@d?w7FAOEnbs>*7X
zdH%YiE+Ml){sS#byma~U#M!gCTb&keTDN}p9$~?W6>lt-XnvDcQo581Vu4Z;jI}6y
zd(KTG(6j@n*Ew0u_ruNf`3J9G7YE(KbZ>9<RQ0xLQ>HA)zrQbHd*0kQz6I>8tOsx1
zk~(?vWW~2Pl4s7IHB3Jzb0WnEbTS2Koz<?Al`m#EU0E5t{LJq!pegvgI~EKM9v&RG
zwr00anj|Fnv1Rk-&CW3~GDXG3g>P?}PMJ3C(5+iiX=!PT7IT)rzNQNr#Q*s5W5tID
zjEfd6dhq5=&zdzlpuRb1Vx(Wr*5&w>U1?`$EsWfpwkY|<mdnfimF?_6hb?~i`n7fK
zTHSeewOw1bn1Bv315Ge0XT=s38O6lLUfh)GUGw8%I|o01_`0nb7n%6wY!2)yef=eg
zVXoHoh0g6-{w@ElJts|=HS5<bAy6W_39FsA&Re}&`_SRThPA)G7-fHdclYqIUTM&I
zDvT#RuIt9{lL6h$s-vR=YDV6;eY?94bdA=LKId5p;DQUffI~?s7Rp*BIbARI(3;52
z7nXPmGaQ&6U)RYiZI*CnN1@hXPf(`*_U+i6oyD%MqOacE+|0qp=eF3bcf#!1+zg=8
zo*6*%mY_r96A~2e+_~d&>`G+)eFc|z&`Q*K^X7r}&4SKaj@w(cat&xmDKIdQgNsXO
zO28cL@O7Z6;iE^7f)-qXb}&48l*FLlmiqYdW6&`TIk&cW76iTh{Pinn8vnub=j_hT
z&KC<yKpO$}?A;5RTxfM-1n<OU1J#H6|6&c3kMW$DY3yDQ^mevwwHfFv#V1cvo;-i9
ztfS+TT6<xEqn7i_UmeoodoC>ZpKk;{?{-JcPa}{*@IH#5;9$^E^EYnZeEBp@0kk@#
z6}mbk<aKLH3n=M<9P8FE$Ll!>bSx!ksunuZ2-=8nTt)WF-|zRG)g~wY|Mz!A@bbPF
z7A`I>THrO1<}NNvUV~W{NG#LG2b<Y9Y}gR6&&=GMondNreXO>Q&Xp*$*rb${mNs5#
zCI-;aAy%cYKn2gvyxiR0)6@04yWFj^{{8t0x_tcly4cgP`zt;wH8nSXEn=`$P+(ZL
zY?+6jU)#ck3qPfw_kO?szumU{`+6F4BVu=#9R(H7pfeUOE%D5_y)AcV^NV-y-Z5S3
z6crI^nQL7RIyD`1fXLjrbBoU2xFG>LJ#Jm>?k`0Qf3K_z2Ce1?P51`{1f=ctoo%+G
z{QbO!lt+b+nL=lq=Z979t^S_(=H_O0LqkIetCAI`qI`UKo)lS%=|(L%+W}fqAcE9&
zTkba(bh_cQv$H`(I9Dsv>FN5%7rAzWhQX7M_Z<Xn4)VF=xO3-D(5eynSBgqXbMd8Q
z%X(YZ&+pZfE`bk7_V#A}@TmIA&f@epH#R!&+?RjfZcEP1pb(o?ON)w%0=DPHUNmg6
zD0;&2=g*&n#KgdN=jWEay#-n;!ZfM#`O~MZQ>KW3&Q-X)+`oPLbaBv0l@A{_PE>Z+
z`oG?;tD~a<w72cgpHn$e3=FZmN)CQ~eVtWB`22|#pEjGmzq50(xq8k2yYc3FppDle
zT&+cK*Gr4PSdF7^2D&8R>;YlO*;_AqL6<jRA4XJ`y|%kNf620CU44!&E+LAb4h^U{
zUB!E&a0O_#s$+#&!tsT#l8!5`vINb`ottON&2ZxMX=c!n^g_?cYFgj#?kIGAeY51~
zhlhthUiP<71dZ+(865)kMEmXkNyu82Fff2N3V{}F&Y4tl@Zw_ki4!I)sF9VG?ajWv
zZtBkW4-dEB*p@5(=Iz_9GyKYJ>i_Mzlz3y!8lAm&Q`8`faZCUIt1WqdZ||W}Wo6|j
z&!1--PJ9RI8-R+@_wVD=)-G7UkeHY#VUW<!kn-qn>Eot1Z{8Taj@?z_n3A%jA!XM?
z&{7iAP7$aajD(kiQGtPipu@*NheussAAkJu@qW<dzc+5(O1iNjX<_M9*jj+Z38$Y{
z?Y?akntOJZX+d#ub8|EElcJsAtmy@+gh1g3tAr30)1q0z5)vH;4meEBuB)p{eHW}D
zQdR9#m5`wD=kMRdj0_Hj83u_=JiNT1qR83V`N!|yudj9<(Kpu#0PV_;OBT8-EHB>=
z8Yyp3@$Bg9b1Nw++4+6n-*2};r#hKEe%VuguacdePe$W=`q|IV&x7{PE%Kjl$26(a
zJmZ4GMZuD3OP8iDZQkJN2|C65YLe1j#L!FZ&0hVuJsmwgJUa3FWWK+<tNl4{z5b3u
z$EP_tIiPm;$;s-6j~sDH)wQ>mPfSb%?Nyo5*U_=!+hh^0R;LokwbM$zpcD@3^@1i*
zTb&w@^-3SUazzBRwk|GCPQ??{w=H{ruU9X2S4W?>)r#otc_&VuJP4W*&&uNR_V#|t
z{tnbN2HhFs<>BJ;s{^!I7S#QCsZ}OZCHe+b)~$xF(7D?4;lqcl`m-&Z!g0=%Zt1G1
zuzY@Y*4fju^MyuKVnV`#Z)q(0=6V(X{`}1LTPh8zJe!)BG(@;S-Rir$N<V!16tvTQ
zk_u=9t?uuyrl79v`S<O1?B0F&{CWQ5<9)50HyeXiQO=k>8`K*G^&NYATf4ivU#wW-
z+|<+rTEzyM>^3tq1Dzwc(7FA=t5=|<1fctwyTx>!KqK8NoQ@nj2I^#Z`1^<N%u7ve
z^_^|zs5Y6?OKsZPwYoO8wi|P98X;|>eh*p#1{yWt7T4qO({c+55joZ)*$g^T>v6w*
zSl%O0uVBLl1JIpFx3}eLe~xo=adAQPPQ3i**);CmYind|EGQwtAulh#CG)b|&br^<
za{v7Kd>(X$ENJ^Q=(aS+W;Q0_$$CYFg@Lb~pZ@q!p}Ry;Nh#_0!tmpD&Mq#yK!Gm`
zYLvcIDg&J@Z{f1U+sVmEKtyDTx%0I<I~;7y^Y69HoEbS&IQ3;KVgqnkUI+uI()jVP
zUH-x2$I2E9%XlP>SSG1}sxbo-lOq!pomc&lg4B7sOD^lWy1G{U|NFi0$qB(5w{Jhb
zv$Occ#l`GJMMa=FFdkVek?Qa7bT?~Gv;(aoE`G*y>Cz?Wmenus?n<+<u`OE6dAOH*
zm6)(_bL8eU&~kFE>$}U|cBy(#16{+~G)YiU@M@h5Y!WQ<>Z;HgcC}V~vQ{B4^A5K2
z%O87iuz6$AQ?HtTKcC;?_5d|<7(tCmr7Cc@MDXJ54%zk&kME-5;*XDX3ct9w*ILRv
zPsggy@A7uWl0~yV{rH$HV^IJamJH@Qy=&*rmsiirsH>}cOltY@qe4PbQZqjM>5Yxa
zQ69^yMYvcG9X>25DY?=p<?q9G`J_ijI;(6me4jo(#`<b^>1#1i<^iohkOlWMl$4ZK
z{e>4(mo_9GR`3)`N=mx2OPqmE#^S@SWYD&>y+YWWdv|}mJZRuACr2m6XyywGt6t_8
zArnEjmt0*HYEk`7=hLT80nizpb@BW4H0D}(dU}FR-<)NhANQ`x&yNqZNx<FRT~}Rs
z)m_k$$6vmbJbCtP(Vjr{oiTa}Q!DQ5Xz1wZa4{5;1<@TH9>Sm#I;Y3it-Q9^XeQ77
z`u~5k{am(278V+=i`g0Uu6-$kLBatB#+4l%9`YL>2lys}8<L0moK0J0+dDc+IIa1v
zih!3zJTDQ<B(5WK=;lqy{eM1rw;tZGapT4br=Q-rvQXya$&(gUUo@DQm|Wa1cI_;F
z4pId=AY-vxugmd^k)Y#;etdj9amtjCht=CvJgcl5^gM+?J8C<H)w}u@P0qW!t5wx|
znu4939KW26Lr93ooVjyBCmg$WizWW~@ewqy@L~pNNfvyxKkU@Wla8mS>0aG+{m>yM
zOH0f3mV#H^mM&ciTABcwZfk04;(Gs>y~)L8iS8TFZ5H_*9UkHv!8=|-BLPPs`z1ZB
zL2I`hXKYSCzpD2AT<h|<WT91So0^&ua&ti=a-ba{&z?P-VVusFVk8M#EMsnNt`oZ}
zq{K&Y)vY^=R;=J?Yio=03f?VaRRTJ6qsq8pU&cixk4Y@d%*;1#-aL5nr0381pxdP@
ztUw3e{iuI)x4PiU)4TuwUr(PNEM&sz&g&^6BxNGAXhzE%izoY{IYP8W1ejSa&bqRo
zT=17`H;byS%Z`hVAJm?@v99t=^zw4-Fj^?1vRmfptJoP17958cCRmtH+R*m*@4*@I
zml>K)#O*%$*>JLb+4}S6Y>uCNc<Ezp?C!F+m)_jmJay8fMGqb%T=sM;EI4>pTU$HW
z%d0C!Z+cR4a%fnX+Vs<^o>`Zd^_u0}Simi=_hN4OJ;N9-hKBqk23ZCMh6evt>(+%`
zUgn$s>ZY3StQVi2o-W_Pu`lCTkL0iS|NrHurlx9IT1GB*@4t3trm?7q$daF*pP$~O
zb9R>L=@K=D1%iqF&9{&KV`F&Gd*ktgvW>?X87h>&S?q{?Q^;^W<Ba(N`%fp7&21ar
zm+hARy1{N;?)7!Cv&?d5z1#OYZ?0{1*rosV23|Eadp2#_G-dMS#ap(ROr9xM{N+WU
ztYy)XZ>5!$JLmYN?|pu5uJ!U(ZgDLen>&*$KLoM!$xJx>@WQjRv!9k&O`ShKem7|5
zZ?*A+dt0-^FYi2NA;Y)#%O&rsk4MFQmshaz>FubTtmYeZdYbOm($`@(-<EC7zP|3<
zuLX|HUzXedJsBX&z_72Mv4nwvfx+(eY5o0sRtoRtm$iD*DD`8}(QfhVA0Hl`I)DE9
z%gf7EJ#DMMg=A%|I@Tk(xTS?<ZT$W?&}!k#9U=@DW^6cq@NGgpGsB0lH-!b(Hy$%E
z>=CV&xx@F(;=tVN+j662tx7z;-zn~YDWWW<8<k?kXt&ODvf8fK>vpSnIyyRL-P*F!
zZ?0A7?t3eP)j{Xsgv>j>_xHQqpa9c3Jt;Nv)Y-G4d3kwzpWn&bo?|xq)925;A%|{*
zj^2>9F1xZKaIs3P?Sca@OIB^!62jN+tR1!{ATe>F&gr0lfC)mv!e1Y@%S)~MwkK?D
z)XLD+Vats7u(6BZ+2cFgEc4V9&8++TYTxb;|GWD4yWRfB`(%v+*ccoRA7HQo1<U-Y
zlP52pGiT2Gn!d@q3T@r{<*qLAoUGz`cDDI+mC(>o&q=dPvzG-fc6)i&{Qi|5N#h<<
zCI%__Zx%ab-{dne-0QOC%VV#WVQAQ%)Zcvjpd9;-&3<z%76vc((=;;L^euhOMoHte
zo|h~?cAPljF?ITM?@2nRgQn}nZb>@I)hlBeG-*rP*;#I-2M%9Y=zMjlxA@Mxc}tfs
z&%U#x(96$n-RGXvNG=YJ3(owuOD0SZa9;W$&C$_O%A#Na8=s7ZXVK0WEj_(!Ya%yq
zNj)tlDlRUqXQHgF?aj){dg|P{X?OF?=O)X5LSoh|DOMJinDV`g7CHIOHv5_&$iTqM
z&HMrs0yRSFrH|V$>?+Ov`+5HVDJolYZU&X#uiefkXA|*!=H~SCvpkp?OoHAN7VN%p
zpMhbIV71I0y>Au_4Eaao*td7v@)e}7iP;&XzxPYf+Y33Ko}EF#!J&bH3+4a+I9~Pj
zYWUY5kNc(9vD6$s(8&DtUiEuTeSLq>ZGtVF!X{;JB1+%giM(`Gy6W?%PdwpOekCPa
z7A;<^>N$1l)K}Nn&$lXlm9m3t--<PBeE8a(`P!YAE?sI>@Sx#M+3u=uZ&of@qH?*?
zt>o>k(E6XJ<G*}3%>R03`n<r1h#RKt7v-zp7&4bWD=awp)%ME;=U+b__fMTWH#UFm
zvSn`G)Ad4YYW6f5F)&E6oqk)k+t(cw77Pi8{Of-O-z~i!`|Gj%e+^G5n~Dwp-v9sS
z?>$ZD;#BSMDHA6yoG?MaQikvFQU(SF^Y*{I3=A0^pd8WA)?v%{;qdPdhxtKX)>c$>
zwEub1|I4lH^_h2fm3sO5PA&QR{9NAl?5C%uws|w&e^9iu<l!OKtyx#SrlopLvitFX
zSyWW?WZw4G`S<sMEVe3nk+4H#nePmPhs);Q-B-ICbO!vaS+lGop4jTe?^`q1y8PO`
zn71WXrN6#pf{fwh<n;3K2}w#?^ytx}C(oa!TV0o!eYWhb>FG^R%66wlhAsZNZ|Ahv
zvN0DHyYs86s%D;>W4TPYH)3;IuUz#T!_@Tj>?0k5UY?#8FD>=Hx-Qn*cfMV$w0T~L
zr)TG{Z*Q}$L>U<7AAw|?1s9{XW=$2-k6UB^?_+<~y*)d>y}7yg-rnlhZ*Fcb+I^Rc
zkMG(n)9fp&!}Tw(1O-(qMo@M4_J)FruEfJ^bM0zDx6ZCLZm_HURiYcQ!2xtFbPSgX
z&*kO**H^FKw<>?%&toNBf={15joOki5tKN8fBzjHIc@3I?CVmiKChAH<&XDHmQwll
z`Saw{PlG~2rU(fOXSbi*UGg%?>g?)2U)R^~UHSaqWBY%P`KDK}^Xcs{?H1R+_T%H@
z(vOdh-a5>svNHAbw5s24x0_ad$vE7~!0<zl?E)hxRs0Ztet!P-W4+R;+iy>uF=NGp
z2M=!j*WhJfc+d^X5#Wf2rh@Iq&!6|t-}iIbyy|y5v-uY6|9sB6>fg`jp`oFvJ47-h
zmif<Lw=#IS*(}FL^`Q|FD-4s5ok-ifviSKqE<V0}&x&W8=YK1hDS7{S^?|(Y_Zx-Y
zCvU#_>Q2zy88cQaS)$U~);7zpS^V*Xrs(pIk6dg2d^~<@fBpV-F*_G^bZ{(Px>VD^
z;6jNM1B2b#&X*vUGcfG&Oh{Nz_igk1m!F=Vj@nbPG41@kwY9&$%{<4%!0_W9ru*;T
zkDoeq>h)OriVq8-w&%S)sKmf~^~%cNt9z@<Ma9Ke*Z%&tthgsz=kSyJ$6sDv{<OsE
zX@SL)0*fsL51m58!&f`E^Odq)N={13`>9rG5_9$H)lIkGe){}*^8Wq%nV6WaY)bXM
z92s}=Wr>!Sme<<o?bkLW9)7iUzGbmnYHF&NkB><JJ43_!WN;<UaN$MFzM9C@VQVin
zGP8@w$gG+F@5^#7PR@xcwST`}2S--=IhntY<^Kn`xU@WsVqj=^f9xL{1A~dnn?eQ#
z2j?Sl>^q8oeSN)L)q7gTpC2E;Ui<g4zdqyPq1In7{p+(9@HjXZzqw)PJI7+;!{VCd
z4<01&N||^xv++(+*%_k;+DyFF`6Va`t_)r-A|S9}#|{fsRaH%M^Xmm)=YF3&|BuVG
z)RjASM3n801!eYqpN*%bX1=|(Rc?iGe=~PpoR?P@Xi{<M^5yZxdzUP6dHM3?s+B80
z7DzHM@G?Wn-v+m*KR!Nwb$k1IJ{b#z?YDJ3KYjjuc~$7@D{CT+mo8ua`o_lOuI}#3
zdn!Mhq?`~qd=!+KFg&>#l(ORXR%x1<g&l6=T`e0Dy}xd+m`;Sk_S<X2<7=;$s5P)H
zh~A!ORrsjoCC_@$lG4a&rQY*5>UdXwf4A4!_1@ad%gbI}T|FJNoQYFd&0|v7+Nh;7
zjnlIZxAETEQJB0~!r}j~*XvUw!`{yOar^p?u4eAMd)x0jU;q3z_Y(udgWntP-2ZxA
z43zE~*izoy*!b%~Gyj*@@&BVVH8rhDUQ8$|F21@c)jKpKM8nD|s<N{3)#c^=FGCm@
z8fG6tkF?Ka@9(XR|NAQZ)`mpqxs6Nq)&71}|L=MImjlfF5^I?E++P>FJMY)c^82;n
z`~UxaFa31wruj9WI^B9C7K&<zY1rA_E9nbd?AE)=+~Uv8^!b_R=h^<c*k89~#R?72
zOZWCxZ_U4N=j!gRt)}Moe*gb{oiUGN^rn}+xv}ulr65ZgKFhg&b1jSA^0r5xon;z)
zexB{q0t=t?L+mxx1qY|;MyEuEE&df-18L5=Oqw!h&YJM}+E7qQ_}aGo-5txPPoKU#
z(kTqeoy(0G88QSU9N0ktW1_Wi;X+XT{qKAI|Lx!QE?T6-D{bb}%*K1^)Ku-%%{O_(
zm>3xDNPRPBU|67-)X&VoAf@!pqT%@*+v+gT(GpX&!>_CiR^OU?`&x<61K}LA+rIam
z-jwZ@K6~Nu1V!gpd$*UrkDEGm>dNZx@3{E+*Own&ml~<1rS&Of(RI*}kdcwmmYkbL
zU*F%~f9@9O1dlIYO8!3NufMRk-!5y#h0W*YTC2Ao4zw=VSNz;BG(7zD+cIqp4G&IE
zPA@;du%e<(j~+d`vZu26^2xZ&*VoqmdNSGHB=eHWWlgt&0>{|P%X}|y$-KPp^ZTi{
z-%dN57F<`iZ(i-UNdBvg3>P+-7=l{n3=9qGb8RYv_Evpe_4(fR_4Dg~W&T?($H4HQ
z7`-$q56jD22fC4dUF>cx3yX-28#k6-D}R4)?V?3WzH_av1}HxG3vO>7)Xu%X@9(VU
zK1D^vRV!8mxVpOT-8x(LNq$CAQPGz}-1=9f?WQl;vc&{c#hsd>*_+0&xAgV3N$dCy
zwY9cpet2+jEA#W%-DSC3?yGNqwZ8uE>Sca&Z)LDuu-x(BSR0@0D!tfUC*GE6+uFuH
zKGqvtR8%xKUFUR=gF}N{)eFVemKF&uR)z!L4IB7Ck(?2dm6dg6k!!cr``X`D1_l>g
zgcukO<R;cbV-p&+cOuvC{WeQUS^4VL?CaU<{{MYne|<~lWeErNyo56|43`P-xpZ-{
zyRZ6>p4#8vR{G91yB?c=d)wM?Z*M<8sI+<0rcF~OO<MHiNlI&L>&$bF{SO{ANq6`4
zg_V?SQCYcZQ_$aEUxSzX&E*MaWVm1eb6Ls0KcBqc-rBnQ+t;6;pR0O4efpG(i)+>Q
zKZp74-)uAkm7mRM^>o6yna1g$vgooT!-WN|E-o1#A04gwb~F9y`}gtbYd38Q>K50}
z3u#{T`T2SCxeW404zilRpP4?-a4rLbLvz~ByLsDRa)5$`!RBb%=Gf075!-LazW<wl
zfAz|hA4B9A7!K$rqlL_$51<PXa_{U2ymVFiLOYM-qIY+9U$1_5XJ>KLww#$(B`+4d
zy}iA9hmeDF@t+?brPoDITPmg-rD0)l!`b!T;uR}A{B1tAfRt@aKCWeC6m;q8;WAKD
zCHZ(?=FLs1zkZ&t&)acj&t!FfEfp0PRaI3lUtiO?kFSCX(Url=H<=$ZojQGb_Qgf6
zRuvx>oSSF6x?X<rW*zVB>+4KI*clq~AG3iwRSt_cWn5Ic%*nvOV6X8FHP0U4&p+J8
z3+m!5S$)_Qv}yJ0bNl~4XPvkE@t}E@dHy{0&kQC33l}cDZWHqC{?FgPSNqSmJ9YA8
zU`@>)_ETqm|2$v6j^F-Ifd1YulZuLqU#}^Bdn@$k&!3>uW1-di!?lxkgv!JOgeN90
zJk}$rJp1gjb91fDPc_>!FzlGTgAtO|z~K%i8qV)5c{yp{zhBuq@8)gIzU~JqHecUe
zl^r?l&)>gS7rAmfPi2sr)ygdnn)I=%`LSVM&8L%A+iUb=cZGm@VJ|K&2F=5Ziixe-
zv?)kcRrS@~-P<1)od>On1}&lX-1UCnZxJb}tQ{wI&#|ct`hKr^{k65x*EQHX)qQ3Z
zTt1(7e_w3$ww#A-B_C@)zgJRL7L|}#@#s;~*8KbTO86KUc=^m1FoWHSAU;^u)zyJo
z4=SK8X7256Q}^%R|4@s8_wLKf%R@s$m;U|zeRb&Su+nQq#l=(S%vp1Ky8i38+wWfk
zH5upGR=?VMJ?`?audjJUXA4S6ow{JTF8kaZ%k5wGq(+vnVA=QP#>V7X7KKWOpEEGr
zQ8c>@Ztfv$XJ9C>ez*I*UE6uaiX(r1e*XGq^Z9F_lEf_c)(i3dKU(kA{m%6ay1gy;
z>lx$o8PCtnop;XU*^7&dK}|kUS=qH^Z*OIOes*@!lCCZ;-x&su^}lc5=Mk@JKXAZ7
zH)@N=#ful01@{!}jM@IB^yjD4%O^iL-Q87sxl>r(C!K-eLP8-kxQ~kLp!wgAipOW%
z+f#XKYxeYW^X=Dbhp)R5xn0MbolnLfgnhxn6)RQ*goa)%y}o+Ys*u3Iz~5FXDogIY
zU);88%^Dv~P0ga6F<rgAp^=d@WAvskS$+7Yv{}xDR&Mbx=d9mL=zZOjdwZLvo!!1~
zrQKq>CTV9RnqAXwzAd}VX}5Bte9VXUpys2XGH3~%V`<$!28ILt&5-d0WJlWNK0ekf
zWsuMSnl3z{-2Y<pdAs1OtW~R4tpasaUESSRr=Op<%$U)Hq2K0H$Fp;DS09(JkKwob
zkuZ1b-QDHc_x4nF_4cl<UB70HkE~V6hmvK2c*i;BMsjj;cJ=gJd2w;EY0(pp(pOhb
zmI&1_u!~<YO*t{4>OCtvySAZW;N9Kj;T07Xdk^#KoDK>MoVZ+wks%{MXZ!89X0jM@
ze?R>Fy}h8G?Aqw<uRc9JoppWP+-qy2mtVOOl6!lbZ)RqumWD<^RMf1OAq;l!^6P)k
z1~oLh#r3sRRb3}eoH%L8-{0S}KR-JQ8VA{uc$n?zks~Wst@8T#@gpb?fBN)^XZroh
z#>U23MyXx@?*IQ?Z&mwi3ut5K@7)oT#PniTh{x9i{{Qpbo_BgxTw>xvE-tQ+prA#w
zW=Va0b=4a*boJrk;j61cwJ%r7UENunj@F(#owm8K;NX4^Uf#cP_pROgWOh2cGBB9r
z+=0|mND+2m`P*Aty+M`t-SYcuH>aQXnv|85rQ-SV<Hu8{P6he-@iD(($cy&z>Dl+=
z5%<%lPeDywEnVHIDy{A9+Q!Dg`uqQEI&}E3YV6*%KR%zgH=p@B(A3nFi-TjwyDC@L
z)>&q`uMR4`pEz&cx-VZ!LPJ6_US3+NrK1y4R<`X}zx;YeX10tgD*~(DY&;IGXjYcT
z)YR1MReW^b?zd0%w>KC2>%J(vy1IH!`u6TFs0X5HWff&;Xs8y{`};vNe@H;Ug8Toz
zZLfN}^}5v8gRGNEzPtzo70M=B*!;@M%9?p?P2{OFXQteK8`dqR`{iEs`^+aNCQe#+
zZ`beD@qfMI>;G<j7{rjVBPb{c)awXc9d>m$<KAV<-1zPPY<Rc#dmO0iwJdn=p+;u*
ztb8|pef{u+gax36LQfBms=E5@bDw8~t`5^wR(3u;O*i=ezrU~7)PA|>?&a@)UH;z(
zcH3Vs7PoPo{e8Wedt2V!RcU8uneJ-lW?*P|e$xlsPDF|vh68UqdU`@CD|f1#+@w?b
z@{+4|*qRlw@tf0n-|c)Z7hK73L1WLKPp6|cr}f5FJY=0Zb*kqsD~sKQkKK4B3>-kg
zcUpgc&W=mfKYso^dH;UAZq$|ux8F`njf~n^wDi}Pmy2)QhyV@Bl`H}+jDFE79=F20
zM$a=dGxOBBbJwP52J=j*><5*2KcCN^e)%QHC2^HcMW;@k`m$4f-UZw5cNU*H<1=;I
zv{~oA?09^<|Ne*9M>>VAs=uvy>BGQK6DEwUSY_jrS@Hc|wSQ%0W!9x7ooYTa7HmvD
zzN+~7xk>Bp8O@$PJ$;8zgFYyZQX@~DKR^9!T5ww0v+}xQn{;#|HXL9sy_b4nfn(M8
zyXB^Je=5$-w~wFn<;i4!uSrqca#n&2uKoSZG$P~P(QfgrH9w0)MMN?#FZ11WGsnx@
z`|_2Q!Czl2?mv~bIrC_j=q!uEMaTMNSLfc|Hq&q4W6))aX1TXw%J=5p-gawy{(ScC
zJ-5H|>4EM}|N7xDfA+~qs#PBjviqi2xnyLl&^i6<+;dP3y4+v>>60g*o(FR(1A__A
zwA*jXX7?dSB#7Pc{`Au#&=EjcS679;Rk*}1U$bD*BBh&e%f7z79S*vnsGU!iXFAgd
z(}fEcZn~KR8tj^7mRl9f+&?Y#<%x;Pa#~;P#P#E@9G9<O13C}!)Ku-Rjt)>U#Kg?(
zyIgW}(NiywZ@<2}x@y&`pq!jFMn*;^Nk=%g=H1<O?=!c!-jyANk4t`jN@d<U@9Ng<
zaMRpdpfS~d|NfO;)6&+SI%SH=^wUf4?k<<sGI?LcE}oK-a>aVbgL&2OGDX<MJ;Lk#
zo}Hh+{%|}0>yzs9LsC+fsI1(xCk8a2cDzp(G<Nd#{{HyZ*49;P)_}&1s=mL=-66xk
za34D03JL@$ZeYv(_2ngajPR`a{TY6Y4Q!{u;{vZ{F<+fj^6ZS{)TvW74Gk|IPJMPW
z$E>xrHS@}fz*8qq1cZcK;hlefU+wNspFeNSxTwT0Ix9FNWQqE`3MW~sk_$IBCcowp
z)Q{T}alB9V@}|_&Up~+Of2UyO^TL9Iy?g)tdL6YXrBjBlJ!)%KX!_bki=0lLJX!VY
z<#N-^ODdqHw6AV%Uaq99ytVFcmGe;sh96?kfgq^6L6k`bXjI_J%HYu8;AAUS{$L?*
z*jfMvDV^PS*L}ZVAOG^@%j+@m+j3@Jx_nvs>H9~$(&nr3@9$e?yyqII>oq;D%Cr9e
z@B6R!+~1lV4ssW$URY?f*<#0oV}}kO2BmD!;NPs*o72x<yR);n^vMZ9&r4e}FMl~E
zo&VxcEBCxJEDQ(IO`-iNkh|dcfp^)vJ1cpm&0btt84N1LQ&N`b#qL`2=~I!bi;ISW
z!hw=S$7`?u?SPEX$gTRQ$20$aL{!wQOP4Nz3Q$?Qnutjy_iMjvnwVTEm>K!{`uhD#
z-_PB#!{X@Cqjz^I=m!S|E?l*0)$4WPp`j}mEn4)g)Wf4=UCho$ohA$nQY@HZ#=wx*
zbo%Kf(7AgdAu8K%>z>{;W!ki5Cr)^H2JNr=Yf|{g#dn^~&4QKbGPYG)zLh0<YU%4w
zzx;B|_d7d_pMwUNTHD*Jjn2=wbLUR<zn;{{QzuXEWH#NWY+|zIBLCd~+I)IDHoD7I
zx)eV@clB|<{W^B}nhob}y}P^HH2<E>(PPK1?F$bJTgE4ARbeH}z%V~`=l<6nn(z>V
zGCm}t#B4+V@3Z-Ji_Py<I2S)V6S%+buZXPd+S1q8G)+xICw(~`|1Su1M&Y*H+i5$l
z7%%gky)5(cvXh(ENZUOx+nu`k=9KyK*Qd{~z2;o{>_*Nuu(Nx=y}xpCvHRCwuh(ZE
zZsYy+YW4b%kdP%)rig&5#$!E_pd{|&)ARC-bzd`g-r4*AzJc~c_>1eug?M>+y>(Oo
zjRZV9JG=CHY<cG4Hr}qz&cM*nsgE8%HZ6GI@bu|ZNj-Lk1Lg%-nva{audkb3_wC2W
z$K@MX9Fl_~B37(fqm!DR{`$+y%U`d_S3F?Ujo)|2VWy;WJ74H@z1SyZyQj{Zx32K<
zF-=R$o#%|FrD`fDIPlwknc(E)#51+(+EnduAN3zSn>HCOU9#lF(<0CaRBCE!(axAj
zOU!a_WgKqf-Bs|g>0ae?*~3fA?`5ywTXuSW<{9P}hK7c}9(C(anLd5_*6iz`shvq8
za&qg=oblQF=hJB}e*WnyTQe>?&9DEr^JEMILk*}A0*xaWRdY_c-{#X?^LKTp-<I9~
zvYDYkS>1nLNWYxzy50AdcnXJxg;i}hvF62#3|Dt|?@3zP+E>@d+k;w%1yjpcu3LBQ
z*4FIO|9`))uKxaRS@E88OFSoo1}Jmy?g}m29SiCwZ??<0pz!ylf4x!2^GKPPg4c%*
z9Wtr^S94jCfx*Os2TO;gTTItzF2e#rE?!>H3HR%Ezbmm4m6UvWQ0e{0Gsfp<_<is?
zJInO)hQz~Pu0`h?Hq`OXHp{&<MKk!yzS`=!cD1|i{i^+bcX{&hK1mJZZg8t06PrEB
z$9fDw_JG<Hb1aKZN?ruGy0~~u(m6e;<ZD7t>gj2j$9g2ygnPC0^{+2-?JoK7z!5Yv
znYVrSxm~G|QM=35F0?Y%IUV%;+}zN>z(lK~+E=e!(NIu$u<Ny`s3>U8j=g&iGrRbe
z=`&|)p58QN{(Sw}XP2EhbLRb@p47;w4GE3xuNW9IDxgDKus8wJJ2=<x`P4PXZ~3H2
zldi0dHjkXPH2(ju>sH0jdidn+*8KbXJNwa*&Sl2E8ag^xW*8=?Y`zIvMaRm{KHKk;
z)MR!4YoO_&oErwNuC6oBebfS_H_&aXsp;w0qgSt737Vh~m6y+7a7KquZ^il@J0i?x
z`<j}XZn~MHrKh*fmf=a&zHC_rhM4(J|9yYF1nedhqQEzAd$jj7or|BIo(_$RTc;hq
zPD4q_>2N#$^<aNn)!Ap$tS*8M(qm;~TeV|H#M|53&F4N2{r7tRKX1^<>Y(96P=)>d
ze*OMGfBw9(NsgR$uj;j~bL+D;k(=H6ZNJUfw0W~>(h-iOOO}9IyP(bkXmp`h+I-cL
zB`%=W$=p|kt*x!I3=*5na&H|u$jZQQ;4!waJdpeG^XJR6^Y^WMKCk**N!RtAGo3kg
zP6zq=_OfT~IsfQrH>jeB-BS^mw|)1wYp<s1M!y1efnQu)%qu?YAlP6PY^Cu!&>X*)
zr)Qv(Qxj<3`m$x5ww|6JGaFApUf#NwB0m;%i|fC7+;4yF-{0S*Pfv-0Dh^#;-^Rwq
zWtV#%K4_Y~x%jzX?u`wO%l+mCg@sL1QdTZ~c}aEZ^y%74N=}T7jLU=>89sPord|ey
znD(=2lT#x%-OTCg>kBI?Dta59k+I^X&H9fg)#qm%=@5+CnAG~{@nhfT2iz^@`nkHg
zt}K0h?K*ff@TpU$rp%b};-OK6_4LzACn~$ITCu_-Z+rB#)Rjw?xU5{ca#zXANlwnr
zrqBwdM2msJt`oDH%FyuIqU6N{8NPP2{ChgfFR!$%{&t1Wx~;YKs-(yJTU%GZjOmv&
zO7YnH9n|gEw8^OS{k_<S4<By2{kHU)?rBH|@*(q^vfc18{@R<HQoa2B^S^AbS-kK5
zpJ(P(k9*Bc($C3!eSO{k;>C+m+w<lI1qZ8o?*H>t|0`%<`u4WmHg86T55B&bEq?}v
ziq(Cx)~k|__eq&%O;LGyXJ>Jd)m%`|>+r)1U833{5fK`vH;IUdEID$-rS`|e_O{jU
z_q@Hm{q&|aRqxwdT2?Gt<RmI8`t{nnuQkaZFS^TvXR+7C?k@TFr!w}n-N|DXDSu<X
zXN84_U$;KNFk#7|Lr$rwshZZ-(aZhkuiO6b05gBa&reU;PBAcKNMK8xJ3#aMpk@oM
z3F$9Ai{1NY`F)Udb#;}ptJ$$=@nTT6c>4UgwykY!-u7ti@O2^2&&>tRna)1<WyWIn
z{#Pd^DsNqX`t<3iC03B(blsR80S_NOoOkB4mP|}REoK?d!O+mwiY<nt1H!`8+7BzX
z9|n!=%UTpTl<kfMEp-SAn)K49V&<MbHb;*hUAbjTNc#DCp>=ip=GFbmT)J%8tJC`X
zL)ORby|OXc{qjt?&+m4>&$_iGbCZtuv{X%V^YEQJcYd8$y!-B^n>nY>pEnQ4lw%ja
z6Ooaz;@jKX<#$V$UtW3Qga^MEXxQ5Tqrc6-P#_CBiTd1J>(Hnut@gu;%P+6Iyxbo&
zlI7*$0cyX3<{5YFu=x4&=gf1a&whM-Y#y^+$6GgQOF%)vhW4&K$LHBrPnkYlefQmU
zYQF3GKJAFn^St!;`~CHA-sGH}V;L+dDXC^`oA%<u!dI7;cHha{e(CaM)4V$ts_N?3
zE01l`VP#=?v9Mh($it&!VGy{%2~v=LPKH<3Dnw9FaMHTE`yQ7TxpsqQ3(n3kJe;D$
zz+l&lEr?%p@bFB5Pq~^FKl4#lQ(NUdU2oatJzg0Z8E-#4@BM*3y!rY2_wdbWXCcc&
z?(Ny>H^(Ay_q~0!)v{J4Cqm{O2hGh`Sw&3>iHuxX_xIPz;N^a8tM~A;i{H7Sy?&3<
z^2?yP|I*jje5a+pyuSb6)^l?#7awltUtRzIAE-YE?s-l-3m&9JDfbx~wy#>ZZdz(2
zXiyPlN;3Um6YHycdv`N2Gk*oO>OgI7&@!Z{Q<ok%;BfTFkr%z@_b$vZOny>gb#-@n
ze(k4|>dQ9UDrsqXReyW4vQ}1DcrmEa4?4hV)v8q?5fLjsd?;vceP;9dj4{vrcy>?%
z`TXo`Xi(51(2^e&6_<$<CxV(rixw>cjlN}^on^Y|_S<E~j0_(lr(x|qGBA8_OFutv
z>gAVH4nG8~6zY?;4vCFj%O`84p{eQF+1csk<rU=P)04C9ShfFy*X#GMQ}v#9;$guG
z@EEC<mKJELYWe)SsL5)+m%`&~m(H`T1`UwEzP{c(<c%fB&v$kfgDS*lXJ==BeRcKM
z&GU6?_V)IX)0Un(<+b<wz3Qr0E0_B$mkNxF104_e^1;DoP*?w7?Uj?8bk@f1z7{ao
z($mwk>c_)&P^;TB$jPbc&)>gW%ic!Sem-md>i+)ye)DWrZrWr7T0yZu5wcthHI5#r
zK__2J+b;RfwOZQHz;N{FQB6%v&z(DWE;F{(v$2VJe7yg93#ah9o&Vkne4D83uHp$A
zzmm@1vyfX{ufphZcFw&$k)Toc)a|!TGcG86eSQ6W$t1zn)>bLww4NNZ*;eK6);xId
zAlq(x<>xg1=`)WXWc}(p)5uj*QxlX2@0Q=swPI&zV8fc`Z*R!Dss+kt(c5w+rbez>
zxzcd%lfr-h{(;8w)cohwoc((L@4NC@hRJRF{{71KymY9Q`|G1_{a5q<|5>hXY@7D`
z+uN?5o;Bstf40h4m3V+QHn_R9v7g%GoszPIiJ3VxCT7jIx3_1X`&iZc_W{%FvudX|
zrEI<l>U%tS^5oX~3l{<|S28e|Xke>c@2E^ay;Rn^Yz1Vwl;85;^mB72-hLalIqmF~
z&FTJ@GJKb3%3a@Gp8xjtcK_Gc*I#euw~I&zUA^Pw>kDf2Z^^u@=6UHzr|{OQuUT*J
z?!NBwPBwk}?XUlSzXuiD;Ldq#TidI}{dPg~?P_1yL<a;c=;`Tkt1M`oKY#wcn$Nzr
z-|rMJ3*N&7%CZZc+d)eNDnF-L&h>kHbF(|Rw${|qS#!>z>iW7^-{(vW4=&G|0iHfX
zO$#5wo}ZgL`S8OPvKIGu7B645diB$?-J&8QOIli5ZZ#g?vBSbN|K6RFO@hVG&xP)<
z`+H??b@|dIOEip(f+lUL|6iATZ%<_T-O}lx)|qEeXy{bX5U!$g+YFz5i~s%I=du0v
z+EuGoxml*vDZ|I!D|%a6T4vkrIPkJ0>&=agy;%%<laKeky0LMwTd$Pr%UAEymtT(j
z{k!sLm#CJG&Xm+hE-tR1q@+c5e?B-LzRJMxLk(+lYcXWXQJ@_%<ye|`W2?^Tf`#QB
zot+oO<7*b~*<-Udc6Zp)rAsF*`S772H7)Jc)9LYH6%{*FR=ReJ{rdCyyzjF^-e>07
zMk~AZTv*`PEFv$TZ*|-Pw3vm!x-b@o1Le?3K$P$;kd2It1hoN+iZ&fObjas<#nufQ
z49?ECzhA<(=f>8&z5IN9VM$4gc9p+h_u)gq&9~pIUQbJ1xnjkM;LZ<*pnjf(Op%3*
zmagvAMrQVu?YFOPPWM+;Rh@Z`nc+Y>b{ly@nC<6aZ>88sEk8Y7Kl}MPXd`FB<(F4p
zUS19w<W^Nt$#`>PBWQtBOw61=fByJ@6AiXT$qzYD5i?<ez|<*IG)zsemh`!&rlp<Q
zr1SLo^V4aYHI0owTiYi`P7~9Kc+hC|9(2qhXp8iuC7++4_nvg>^l4EMk&x#*o!j{;
z_ne&qZof3}bK|V#7#K1NusUPjoxJTYS(LlFyHhvc3<(YfP0~Gj^yvMbmAf|HO_>W>
zd1&<>)TyaH_qNP@SH0N|J3hS~`(C}uy7{*3CuF>qk&!X$=BA}Dbr=|=R8HTG`0tA`
zM9lEO40+1!MV`a)Ufsw|Po~)$r=6K$9q{OGpS*qD;nLHat}JrpW@TruUU5Qa_Svxa
z22HPJ13tX{ZE9*d@09U7(9$idxkcb8y|pp9ebwsKR~I_7gO<D)8U}iLdUkboPCT1t
zJeQlH!5_Lt2PHW@s7_#z-C=uOYR5jY`uh5>FE6`WT3UAX_kVYoDJc_EkR78p-R|#~
z%T~@WL45`XhlWRw9!;4tWyzg8F_&jDF#N#UQQ6nNYL%95^fn(**W~xNx4zFSTIX7q
zgBGS(mA;y?Y11YVNy(Mo)Ac|jk%EGPTpSz*b2;=k6+CnTjSRQ*%U_%9ZwG3Tc?MNh
z?wqC<yQ)vtI_t}ei=YJ>T-@BDk&!DWO%nS0?(XdZ%RN_Dg|0R!e&&;VbJNm`cLn$v
z4)9~`J<Q&adwUyO?e9--3wFjxSr#qn>gsv|T4y)S%gbxZtXZHokfw=Ah_Jffl_w`B
z`z}A!y@$lX#}8_H)4i?B-UMW3u9V?xpX0au+#E~g?YGyaot?EZ{rtQl3mI^G!4u2e
zB?H4g1w}<i`(GFPzudn6FN~dE&SdW6&}DveSAlvTpebn3BAfcX`WMfi_dndmd->E<
zZC<fM(x5OqZ}&TA@55s766?B;-SIEpZofZGWoz#3u=6&bd&=J3dHK?(qO<t<xy-Y(
zOn-q!$nNc});2H*(A3nd`uTMF*2>RmM~@zTS-$`GT(jI;pqyn~!^dzSHzNsSPLqM*
zfH>$Hc`Xf%3;FfGqxXKhl?_^m<kl~@_Tl07_~M3bhMGD$Az@+DHf`Qq3K}zh&2RIe
zVVZt?-U6O`YZfhX3Jndt9=m?ksvuWa*SD`HOc03OS#(r5^Mljc=<U-~cHYec4IY1Z
za1gqPWmnl-t<#%$#F-c_6kr)8V>saJ;qQNamT7j$pC5&Lzg~+j+I{!bxpQG29vyP^
ze+qTu_r*-tk2jl}dF13|^{b2B`(Lj!&%ER^b?Q_(ohJQ?CllRG%HPGjy}5b$J*>lz
zMuKrF+S=aoH6I#5!y%xC>w*Oi=WV~w*;V@b*au4n277}%2h41~gEjZomW!Xy+pm8<
zzdnwgPX@FMnv09;%MoFJ4FiJ!(3qW@Tic|`lYN(0`C#-$4vL?dYaI?+81nty-Kmo%
z1^u?&gkD94=R3!5&zsxEBbj6*$p)?nm>3v(*)Zqk85nB(>+0%0eg7WbEv5@e_+jf}
zR@&A6(l9goHp|@F9JJo;*WdT`>)+nqetqBfx4lQY#dI%iN<D2-^(7;?@<R}83~=Vm
zmCEjYpp_+{HHv*QmW$4u@u~gy^Es%%fe!<MrcA>ROM_MqmF<oNwOQvfF*r0QAgwV$
zDUIR_KR$8=MHVY7>#Z%BlXJ{wU%GS&w1(GRzBa^cwy$>BnhQrdg-g%deh2MST{ijs
zj#sa;KuZ8;o8<;=&%2w&-hLj@vxwSTwe?Ne?w279ycbSRRxf?O_j?v(X|L&AW`>6I
z+1S%IXn8a%D=SF%s#U8*q@`C|7C!@xaey?>O>gIuU9~y=eAb;Eg>6~3t1CZ0)6&$u
zI7!ueOU=)s(6F#qhg!M2y1Ih={QBlqz0$myV+JZI85r`IAPWdlyv$$@y2*iyoBMLN
z{=OAGJv^?iu6IBDl(VhMcyeN*+$!Vqn{;fyUI~V@;tzP^sTUa-7-~)z?Y^6LSrF9<
z5bs{z<72&`MT;+a)*Ggt5&<>26crso3&&r|{AjpvA>d|?8K}GMJKHQ2JWaOiVY<%g
zOB0pdZ9+KWLqkKCf<`D0G%#k}-?#Ur3<E=r95(OlNHv@7J1zBO+Gfz4@5z%Vx5h7A
zxNzBL29t!_+j4_zYWBS3VPKHb!P?+bG&lb~4OGz=6&1a6=>2YqKH78QZQ1EfI;}_p
zJ`B7aXVZdHQkH-UAJEWJ@N&OplNlH?0<hKaJJ@EQEjtZbLuqPiTE5`e@443Hetye?
zmo8meWFd2FXYq2--KZ!dG|P-1wi29~QQG5!f4-lA;fD=2FMnt*M&1)J&CPaBe|9mE
zwG(J%CTOfuOGoF*wYAY#*F+kFW{?-V^<GNuw_TQYcGgTk7KQ`rcYg)OfYJae?)51x
z-3nSVs=x2Yp^~m}ZEfw#pew;Zz0HdkFG?Aubb!`Zf)?epipLquW!E<@eHHTeseb*%
zJ(ZugRDaL=``UJPU0t1&S<Z~GbupP61n#Z#ooxnMOY^kE3e+bJkE?V|O--$O)Tv%_
z-uAnOu`wv5!4;q-wti4ed)nDqnKw2h7Fo?*7QE-!)6>(RmROl)U(@;fCfz<5v~K4?
zGykil)8oK>;f=}1v;O}2YE}Pl56GpK#m{E=wM|FVJXhDn?ydsYJbW@12@81koj8Bq
z|KGoVSr-?z-pSjpbNbS$soGbU`^z6ab}Z}sJX`SSrzG}qJ?qn(Km*>PAt5vTK1ww<
zHiFjWbajDx5ozb<tUPkWrS#>cqa{)`*lL*dJ1agenx-GWuBnMB_tq9qv)Q24D6_0e
zSIO0W3A~wOwl-p;6R6d3V`K8x+}mcCPckt4z&;^&=*h{+riq7GK&wy#0|S>8_pDyG
zZra_v^?OS#6cikEqqmvNWtA6_l3G>!`&(@J-Ipa=Mn;#KT|bC|#_b#(8$qXSuUe%A
z^76SkmQsdEEm7O^VxQk!=-mG5&CShH=6Q1#Mlmqd@MFu}=83Pbt<Ac-YwNDEx2yKm
z{(klE_xtJd=f{IqS6+(F-<!JP!e+nucDl<iYeL5GTDiqn?b;P3YgG~u6f{XlSa|A`
zDNAO|kN_2mJ3lzReED*gae5zUAx1|Bhi7<wn@Z-zMXsPlgK1}GBpM0EWqo*X5K%hz
zytffq;@&R@YP_|-Vqo}Ci*wwi%-q-|H*#85R+de`<66AU*bhoquU?fh$(R6Y_~hN)
z_44z1`*0th9;7iUP+b77Nh)Uc!X||o7&10sD`XDHZbS?=WL`P^bBEpb+iO7!+JAm}
z3Yy%RsvRyOD7f(9;r7=nm(Sa^vRR&if#JhpY$GcS+s{5N$~@jD3mHQOb+2X`r#~s%
z4a)3a-`ou5Yd>6~#vngs_UvkKxn^l;S-yacp`i`BjSMx<-`Q0B{M^Zh1y}gyyuY(E
z`0CZGpq(FFT%bXpNs}jo7UaP?=tg@EOwkMmEm>`8VYyrT{qC~j2g*5Sw{`1}ZPK}V
z<;tB#DTe>?)!)UV%VT#G{;_;sa@R^fBP_8=dS%+yHeCmSwC!byI*LslIh?b%J_y`%
zQ6wqljs$1MwilaPXYlB|IVC7A?p4c)aFKp=Mfb0=^Bq=k-olx0r&<`Bi#fds+x2;O
zfH>Qy^f&4IZEwGxI;Z>d+vh6pyC<ibpa01qZpVx~QrN(sSx{gATF+nf;laT<7KKXx
zbEg$<<dM^!>NROe*y_}ekB+7vdlnlT8@Vkf(ranZ!PYZwPm3&<25CMmvh+6mo%WJ}
zfq$;2i(|-iJ=@pSn=>vhTJ)KLp@R{*>3g7kQ}y?EIX5;adQaCoyDD_`rsU&&U%q?+
zS&)#Rkeizuxw|a4?nAS@$XqMss_N>^Syxw;l$L^QcYPk9e(d;hV<V$U3l}cz>FZ0&
z$<f&wrMoof<^F#Y824O0Ia&SlA#VL8Teq5q$Jdr#v}7o7G(u@m{t#HV|KG1OGmX^`
zA3khZ_oqT{_nS>`?(R0vzP9G%ks~fvR#uyGZ*L1(eRWar!aPvFMN(Gw?1v8pZf<U$
zKAqNoKL7upbg!jBvu4lUT=ewRpHI{G>sU>W1iAj+p30m1YODACeVZ>nmzhC)Nzp}=
z#dTj3a&mO;-o3jrL@P5R!()<<udk|SRCM&^+qY-0jovOc(;{2OvPfmBm+JoCci(sU
zB~HuE%R48&|HsikKaSg<`}g<v=U=baKfjqi-`CyUy-(hLUi|-G*Im_(PEYY#x@GIu
zr!Oupc3sYJfOYl47s%<gp~|5C-yah*Gqs=BGs@oG*;)B^>-BSgY9AhIm6Vs)*UG=P
z@@kf=dVqRd?boY4Jv}KYDJr1AsrgZ$HPy@R`_A)AH*enj!X|Cu`}+UCZ|*2ezP3Jo
z{<m-678Nr*Xi7#I=Kr9$W&8H@oSZjjerK=WYqq=W?Ww!v_vdcESEc>;@86xDPHA)N
zwA_4uWo2;X&!^LkZEWUDoH((kukV@s{~zvRIuR2@wZopwtA2O#)Ku-wH9tR@n3{^t
zJ+1TgQMdlGrAt*$Pt!g9>gwvtw{HDf_uhMD$f<8{Z*yz0H2ex%_0tl0NkaqwmlMkU
zPcFL4pIzwOZdCs6j?Mo+pLag)v%YlY%9Nm$Q_Szz82j7(OxgFbH(z9K)DC6$z9*kf
z>z}{3w|aBh*;$K<XSmLqHOt7<bn3Tn-`2$JG|~=RbK=xg?aw#Q*KK=Y^2%dp%)bN1
zOM^5oU%qS{z|0^nhnkoAGcqzXs=vMQTpDyTcl+IGv-5VXe6b`lv8c$%{{PSO#iw<*
zr#w8=>iXQEd&=pjAzD*oiqD$9eDmhasj1qRZ{D2g+AStJmyO}Teo2(M_C4*><Ek{h
zr|Fz*V&%5`@aD&ling}4ptWJ?3v$XV3m!Pw{r`Dhe6FLcMctnYH+OeXR+%_);-8QG
z^=Ckt<D`Gxr!|hhwqB3>y)bVl8^eSD^HFnW^@<R!n_IKPtE#FdsT}W<J-x`a+sMLV
zhIIa(k83v9*4C~JTRn5$JUykY0iaAjP3PqGec!g;DZL*1^UHGk*b<@Aq^vBh`d^pl
zpOaep|L^<y^T+MJZPbb1XES&1+?!i6gD=ixU=SCzXJ$c4q95e$Rlbj38+Q81lP9j0
zM)mgo_J2!m-MY1@^7FGTTemLVyxF+l_FF`staVt4)aE;LEQ>E)yg0E}+C1(1ySqPc
z-~Tr){?8-voxfhK{`~v?e>+guzsoOWnv{&pnX~5i=S-V6&BVlHNzlqYuUQ#tOxRFz
z$DHZ&=FR)_Dt!MbP;Sb(zt47Sl<wZWdv`wS(%w||_7-Rw!?N^M$i<mwoPvXcL8ZaA
z+}lORWy_yj^434QtMv7!cKbhyy}i9JU%b$;ni!b@a?_>h`=%(n_bu7I+j_bG{Bz;^
ze_bspFJHcLr6#CclB@giaFH?Nf;>|Zl=bQdS|2`^|6lQL_xpW!%J0`&*8C{=_51hb
z>({5RuX(Dy^T{OdqUUqVmqo2zwtDsI7a?4qe!X6w4#};Ol9DG+>+hd4S>1nG*y^P_
zcUo$Pt?>vC58t(G*QT1EpU%v+-u@ybZJ}=Twv?Zro=VEeo%{Is_~zu}eKntF-#;_U
zG~39~aAIFyU(KuF`C3-O46ml4Bn*cC??L&Y{@<T7v(5FvWv(VOGjrvmPW7U@rPrUX
zTt4qqXn1UBiJI}6rAt*kgH~VNRPpiAn&|EC&OE5OxhYk1su!zx5dX1b$2O&&o))4t
z)x_jawvxH2=~R`>++5%M{QPZscV}g7jY?5txT1@inZ6qu8cu9x=U4Oen`1Fi#j@l@
zz^vJ`&s&+>+1WkL-F#L$f6v79d6jClwY4|**VmtVT9mi<>ouD{9}e&Q`|WnH-t^CJ
zHlKgi$S!xn_WPa5%<Oz3bI<VnzP5ee)X>#oOINSf?iSbAvud|8g_e_^vu4jWE`N7t
z&$nCI>Hqc>Jaqc6#(bbs<7(E{sEa7Q!p(s@W9qK=p83D??C-h%KG#%LRW19J*4x<F
z_~q-@r$3+1KmX)OO5To#Z6T{c31I%tkH6l^)&Kbjy6Vib^i>GsR)@W>-@G|fdOddf
z{C{7TdrlJ74oms>=V#@^R`E~QqVu0}$NzBZld+r>9$&llK@h_Vf7Ahz3V!SIcRE%J
z_0~jh*XtJ7Klk_h{rOp2XMOwj?YnLLS<~xJ*6n^bYoXPvqZ5_gi;jwhKQZ6`)A!n%
z$lwyb%{M@)_r>D=XA|A!PTtvB{P{sM|Fb^pcOJ#X#a>H;?$vxgYxDETWY=^ihr310
z$hA1b^VIwMY9senm0py*vJ<KB<h@{-?(FP*b91`C)>N;&-EX(uDY@+Hs?O+e7qud0
z;7V^e_q+1t(&?L0PEOK^*zkb)d|!WmdPauE)vQvsQw$FdT@FBQo-i<cO})I#_xYch
zK`W=U%T>Lo4`7br30o5}F?M&^(&fw5J&WGl*r*e=MWea7dFRJt(&w$Lt*mBMzuS47
zL6*Tz2_;D}oIA;1|Ko7+zaB;_`6rXS^-i9fYrVPT<)uZzGg`B@-r9Z7-_I|ts%qB)
zC59aZQ@c@SXcp|7V^{lYPQ2TqJ(nAq+0Rwk=il2?^Y?Z9`9rPT+*(Ww3Wg|cjt4e#
zY$}b;+kTIUt9&|jQSb_5P-T*C_jzW{y*-woE!<t_7#SYi=Yj0Ig%*rIPDn{hZ?60M
ztEaC|Y_8MX%3m*+U%qy2+S%FW%h#^eojZ4K<(rMiL4ICznSntsi`Nxp;4EOj*V3R{
zw{8`Ed2tbBrLC>)%a<=tUR><{dGq|gI)DHEefjq7+4B9r@7^got-JI0yWO9k>epNL
z_V&6iH}dxJ@p<y#V6*2WVRb(hPd-_zDbJog+kCFKzyExNG((Js*Vd@DVI|0AIK$V~
z`}f;Ro9CVR_xJbZd-vi>_)6b=czF2b`}h9w@$n!dy!Cdfl;5jNUv)KW*REY%=N3DF
zTaPc-q;HLS8+-oVKS=grc+m6+vd;(_5)9`~ckAz)F>Ts3o#<^ktHam(WoKv4nl<a3
zRj}67O|`$jHF2#J_x1IiX<uLW?Ck9FG#48Kg9+;MDwM9rmdDPkdbKj9^lGSUdQih$
z>vFNV3=HDDsKa^%ai^YsVxLziZTS9aulc<b#^-G&@7uTU&HerMPm3(K->b@Abu}w*
z|KD#@PCvEz{bqCJgGTmGo&GgSpcAI7BpDtwrJ=Nf7|!g#RRSzuy7X!6b9s~^fPq20
zziko99-xNq^Ser4gG$gl_5c5_3|pO<pI?9f^Yxfw-*>xSuajKG%&?<kC+cpe8HK;U
zy#+Ooy3a8%JdizwmLC4Iv9lL{K5M>w=~7i*Ufz`<TJNh4-j<xt%y7mJJ?-2tdw*{(
zue4dp%S%gNzI%7BPuBX<<;#<!)=q0|Y}~SSYwFuuTV2zGHu%mqoBJ8m9G0tkvGBhm
zF9XB-r6H@YX1PL+6@bQHz<%P}+?oM9W9*)vpW?OD$KU@ye-;Bnh5qw@`^}(6fvJkw
z8#itQRi{BKmn>YU=m~12sURwms1&8mpxa5#|4gmnV=(xPnyoDKKR-Y3pPZaLY01u=
zmc`G{odqq;eD<DOT<^?}9~FU>XPngi=bb4&Z#z9au5#%M5e9~P2O-<C!Im>HG<?2v
z@7}zP8#fxiU%&U;tv9!}YUl6$8m6YMe)<0W`P%FEY&zhSHv8DIV{78~+bv!UYLhd3
z;6rb9l)k=}nvkHN?my3GlFg3?%{RB_$IqHQyZGhO>1i1m8ux$S`_8p4#Y}UmS7vth
z>5GfqyZsm$9>`+Jc;eF*E?oHL=4SP&UaH&gmPP07dbw=T<Qb{Ie*fNF`1lwo6~BG^
z*7Z39!-sq{S8T@Fn(V3iIQM;x`u@Lf^FKeg|8I#k*D*5a`JtQWwRBP}uJZWy_3P8K
zw$6I_@}*MH%%$Kwr#aPYpE(1A@fy@V3&X4P*6&@`T+Ny}XO4;3GiU4CUnLhg85sVE
z%l|QUghm96iV;DLVg?2Vk0jI#DUwo9U|@c~rZ_4p>e7V^6TFswS|`rHV2svPVt94=
z$PpJlIhz?OmW7X8COx^Z&^a?N&+he|A3uKdY&ZP<_TFA=X|tRYmzH{8zI%7BtaaIv
z<;&H#M(Hv$GlSyk*4FIqb1V!yUQEf_8nyNXWCJMFov*xi#`vuav3ec3Hmv&k=I!?L
z=gph9(&p8Huh-+}TNXb{si?3x-Y<VXb$aZyz181AyJKd~nBn2>?!GPe_Oz_6Q6*Xo
z2V9TxqBdVQgUd9Bxzf_or>E&g2dxabbm7DLnU}9z37G`y2k+gx_vWtB)r?jQ2Y7zl
Xn+Pf2jF6c>9pofWS3j3^P6<r_WxH)o
literal 0
HcmV?d00001
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-recall_score-20160908-100037.png b/Code/MonoMutliViewClassifiers/Results/Fake-recall_score-20160908-100037.png
new file mode 100644
index 0000000000000000000000000000000000000000..411634514cd1e5248ea7973287b4b15edb3cb1bf
GIT binary patch
literal 166427
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@u0ZM$osZVp3zI)mmV(GUTajoNG`T0v8ix?>OK
ziLBvt6BhoOmE`FAMlCQ|$+JhOT7N}g;G0;JNjDZNaFsEdirxD8&tUiT((=UeNbh~W
z|IJhPKQz<WI6cj8?wOm;E?@Zl9MqNY0){yaelB>y{|783c#TkEI>7k?uMwjT!3dtw
zs6h`B>W4^`YEn{?!fB&#@9(b{(mQSB<m`MuVAa3vZ*Ons-=vd#X^CgPm8Of^!-o$W
zPfgX{|1xEd(e-t)%{r%FTwfpG+5h$b-?)kIdajBcIeOG_TI!!)uh+YI&9vGU{olGL
z)O~MX-Lj3Bq$DLdBd1NAHtpN3^S)n}#q28KeD>_w4AbmsUKIre1}TyI&xiMf-s83W
z{`$+RQ+pLlFYJ$Xb7NbxW{pAJpC9IPr)=-q_V3zko$0QL{{zbV<!ldaNId-D<x5Uu
zW8)b!W++%%{`6IU-FxZVx=*3ivdQYsncA-_D=TLhBr>fEUCqYL%{^nrjD*k6&brn5
zJHkUWfB*LH{}&0uz+e8!sgY0RgM)*oXa=(>Dk^q#cUNCNdAU=?bArlCU-jm=PiA)F
zM~|;twrrV2^|v+0EV?*_Iy*bpTb6z?tG@l|)9QpZMyuZ&-uvSIwCmgX%a?^MEiI)U
zS5#CSIC6xAm6dh9W$BU+|2Oh1TfY49>h=4auCI#?+?o|SW5x`JX{j-LtG@cGzx}_p
zJ~+-OEQ)vK{rku2WG33#{rwU=MK@YZzV^#RuOG8@`17lGR)xN-mc1T($L0KWTh4n&
zkFv_wd|=%7?^pJc<;(X^EB-gzbJ7>Lx;c*13s2mR%j;dK@-*eiiHSen?S3DyJukNA
z-_PfukU2G7|36pI&-WkIKA*ciD}C$KuaTS65<fjTSx{Pf^u$DE!^A@@S5^c%?>v9I
z$`&4IDKX3Ptr+3lB{Nk#J32cX1(<g3-1+16`u!Uc53{|wy`A6F({qM(`McSEN`FtA
zWL@ESety3D%}uHIOM*f)>|#Wn5}urxcw<}c>}wV-|Gi^kV+;TNsl0LX=H8b}_6SZ=
zQPkDty<hiR*R5A-X`%JRjdN`(g&rU44gSZ_w0E!VrcImfm2B!@Xs|!x{6DLmU;fy(
z+}j4FuR<asBBuPPcz%9<`_!pZ1%tko{WhQe`_Zw2{G=Z9q9-0_W}EX*R`);F#L6A_
zdguS#X*!Wj>i+Zgyi8e98GS!{kCv*Ydi3@@*RQXxZp^%_ro6oCpZ&$KYuoega!E@|
zzqz%QTTM;v)Q3HL_WXbOT?8Hm|FbO^=XOBB3th9kI~G&-_sdu|Em)vX^Z)PnA8$6F
z4_Fzr)O?E3FY`?sHaKj}x_Ym~Xv?agrCeoiZZzKAU9PO7^Tt=b{Y9^_scCI;Y8b~y
zw{y`mnwyzbJP&QjyljwgfWgAbYTrwhi~k$gc%>d3Xk@N<KDRs}H@A1f1c9~M+lBV#
z&6_tb--^?PZMJ>AosW;thkw7{OFym1|GeYajDKgJ?%VP2$?O;TVJiX{&(1bK{^{vy
z!{TQ?H*Vb6^UdT>bjX^BkG*rY@2L5>ZU1$HZIh-<?&;w%$-Q-@W97pC{adDf?djo}
zq8aR#`pNP`+WlYwSf07~T7CaZ7C3j}J1O(L9x2l-2ad)iOH_IbLEgKzHu~_%lbm8=
zVk?4{a=G<NwZ3_i)BExA<;#XSHw;2nhw+Amg=qvY<B>AWYSG{SCrI_)y}i|j85b0;
ztc#T{D=XWuX;aho?dEE}vs#{?pD+D4O4Ka>UeAUN20M1_IB@6?)4Fx*IQaOE@!S7d
zAZBiCEF53+k#*1By@9(*GH=|zefaos_T*zd2QM%84}J9S>-G2-mzVQvg{|QzE-v1&
zYuBRu`};uY_DY|$urPDvw2k%u>vZDx$<)==ZP>Wc@#(3lp^s#(%XkC@1y=+tWIA*9
z?8A5O`uOdBFqr4xyYjP&d;aTGcyT!2>&IN{a)YEJ99LEZGGDuPt)QU5p;yXOKvcB#
z%9W7RJ+;5TIZjLUnPuXc`v1X$gc&ntELgCBA$XaO<JPRJ35kh}<>lo)a<)=CckYzB
zyesFX(UsNV{Gi|oUnleH%gg53=J`q%780A*{D1viGk6(8#YU~Uc7AiMT0eX!n4%rd
zCnhHL;lqam6BL~bUSHGQx?|$Ri4#&KGcz+gdV5{(?kY{p%<TO1^mOuv2L~&Dd{}s_
zc**kRj~DmbHBFx`uA`$9uq`LD<i!O>b^m!+wAXfv>$|zQu<Y5hCm}VJ)!N#cg^exg
z=B8As$IF*2Nw~1UaYfYDRhw$At&J9!ulu2BWNch&^}Lap{ldCf>m56H9z1l2NmMJu
z;qkHFtDg=&Jw4s9>Pv=6#s!9R=gys~wygM&uw?o2)w0_Q>b$(XoK}aeO~}vZcXxMp
zadCNYtXG<$VRiWWMb+Qm6_k~=O`R(0<m^0g&YU%6Hb*ym`uZNd9$()(%QXAYrAtD2
zd3is+T=xI?;-d20b>WFeyF@uSIUAdsnRRq^16POX)_lDhe&XcGi?1!XdZo?VcJAC6
z6?<t*X7GtkJ&nxlt6JiB6fkbmQ8qFPQnj(Sm%m^C-&V>zkH^~DdWv4G)Yn&65C8f3
z`Kp?DhW6(J-Ookk<oMj(-6Nu-l@$~iZg0zVj){>;i9EJ`|G!lqt>)QOHceD^Ulg>|
zYr}>O4p&!&8YUm(nQ9@d?&tFK)Ko=JAu;_pp2%ra|BKk=#l*-kF)=-O^M=RU+k40E
z-HSt4hehnID&6=!SUfB&Ou{@*X49rk28EAY_I``qTV*=SB$KJSx;i2<a$(-xT{Fyb
zXB~U~9#Sp8F3IOIcANYE!$apYb1a1u6B7%Hi<@`uw45_{?!|@9>@v1hA&>2LP0OsE
zYgNi6U;oFjrluxfnU7>dRMeuVtyvO=NiG|;8}je&5@lp$+^}t1+v3H_yGmXz+Gxw#
zu-t!s(yJ>gKYab#x^=5*PEO8)_wW0sYKOm?6PA3X_tuUbJ2ciWU6OZiPp9W(HAMr1
zfSLX=v9T9dhwIO=uaA3d_v=fwiDnG@i_bB6cXzcaI=3CTd^va~|KY=j3twH)+`41u
z&Yd%?%k^GeUk{3ZP@vD7H}A!bjml;3@2&mKtJS9X)cN7Fv$HGy|NS1gF2*t<GV<Zw
z^7}`-M76gZyT1K@jt?s<tJU`Eu3xJ*96Dcfex5BT0jyoC`{vD?3)^y|V|ElczO_)z
z{Omu+qR}k(mWH~@(j`j{oIT6??c2Ag@Kdr@B^oJ_$9{c%-Mv@-*D~Kiey>Y%FN4GS
zWv$sFrwPi*t@~QhmHxBn?n-~VV4K(O{c;a4``foJU#{*oRcq;**Sss^84}LTv0M?m
z+YFTEHYU09$Xbc;%iCR<v0bF+;_|95F9ffxjb^W}uivp_M@H}R^A#@BQd`>ER<+*W
zRmvS07<lT_``53#<Lm#1zK%FCp_uu=(Qa`;NlDJ~^70w8XD_b#`RT>g)#7@wyOxM;
zFR(Aax2F<R{!jV)=ut+M*|9b4UspCW+&%6(Z{EC9)oUf>Pi<N==fsK?+gk)aeE1NM
zSN}80*x1-G?To~gRiWHrVPPA#Z+G9Ec6P#q2@9reJM{J8x3{+ig@izfYwO9$cXyW`
ze|)_E>#J&p_33whZsNE9Bd|$F+0HKR@wdmv`<<tymb|?cDw*bCyQ*_rVQpTXo|^x>
z9<9(-pu%{ncKER!g^#yf<NS3cd{>Wim)7aFea|Czm+69v_e)E?7yHaKdU0_vyOEJm
z$-eMk(>!Be^T(b(dD_XzY0CM$_xJXm`pb3Q(uqSSVgm!Ov{_4UFYlVQYcFm{bk>R3
z;P7}!`O$yd^Y0&PU}O&1nB+QR)~qbq@_jz@%~l+UwP1j*1-LNbdp|2HYs7{GMkZ$F
zsmTXcg|1F|aG-HV(bKMDwO+sOh=#3=YTdBG;Hku^%a?_1tG`|Ob#I%>^<O_eCi~2@
zk-T^B-iFPao7b+@T@|vj>D}GkkH5UUtW{Vl8@?yz+TulvrsRfYWvz<Zr~S&d)h>DO
zqF>W9Gc%9gvxav7t88~LS-~sG{ZnSnoEdfFNT;x2;UgDN>oWKDw${y?jVDc>Y?ysb
z=g+s>`4&Y_I!?8$nyl`>DE0KT6Q@o&O;+<2kdy0E_n-IR&d%Z)7KKX3`eax4Sl9k4
ziP=*j`0wApjN99E=h;@bIk)pEs;RO4{`U6py4c+co|6LCe>^T<e}rAWrh!XTYeDVr
zZyM3tbl%<B+5F^5icZ`f3HiDo3yt!!vb36-n+yN`D!sBkUjE|6iy9gl2bOwI|L}JE
z{YQuS?OS&5wq|&6q*FNK+8W7!|9<Ch$-ghRHS6l3R&MbPB`<?=Zf)V*UH;zf@2{^@
zk55zKoTQR?ZB68jt=ZzYwr00qxDYUvKehhnQ*j<S8woKnv5fosZ13E;Q}FXss!q%f
zfsY?QT9mz+;iui9d2Z?I<^J;z-M=rdsi~Q9Z;$1z?fLwQEbC%-x1F7BzSw)Z-iHq#
zG``JYxUkrrU&f|F;Qik3ayhxV8*^`)ota_CT>k#v(L=4=q2Fd2CbPNq%khG$5m(oP
z*RF|ia&mHTa5T)FJJ+%D;Pva`d#k@6yR_6>P+YuyU+r(P-RGz2MhgfEGBR{@bT};a
znmS?1lot8AAB?lj^N$^DW)EB$q&hWwstTvFd*6|BbFD9~i?!a8b5p4L+na;__J3Qn
z!`CHTUl*(O+@kcANYs{$#x-knK=KbCKHO3MUd}A<PRD@*4mo#r2(FFVdg-Oq;>C*t
zm;1?@<lYhy)e1TA_xE>@ANKtJ_j^al%SoqHZbxs=1D9=&kN02PRhkW|3~z2u_we*Q
zcxkD(VabaC3kwU8%6)HdZ(p2yd)tQ1o1K4ud;9R!t1fnaxd(rKe*W>WUEZMXPetmT
zudlB^J}zJH;^D!;#KaV^DnxURZMB&F|3Ajta&9((5}H#hSJrcjx<3}nd}p^kc#yy&
zWx`Sa=Og>I_3{0i)6Z+Y4?H`|^y2pX_?X>gysxjVb?z3^E%^E>G$Jx`rR{8gyPquV
zd@>H#*Tp90=l9E6mp!<hzyIjLX7<7l4;-gxg|52s`_B4!dr*4I%ggKN=xErx*S1g2
zwyW^*F-1c|K~7H2s{bBNo72t~{P|HRV^P4M8?}Yu!=gW+_SPhomA*PR_Ewv#c!E?+
zNvy1_1f}<~cXv9aOtTh*uaDcXVZ(uWw$%nDF9Kxj>tqTG3y&^)`siqP#+@C8n>KI0
zxGgujqPqI=tE;PD+}UY-ull|1+Nb*F=Hj~1+m4)_Z4L_F8M9_3JwDbeVOwP~&%VB|
z@bNLm3d2N2Yinsx@1v%s=EBBg_otw`l7V4<{Xa`kK%JVZy*PS%-iFPa51*ZFUijz;
z=bG5vVW~nso;;F9ET5m9b<WArY2%e<)7M|0^gVFN*^?(Z_f~yv+Pc-W?)O`BQ1|P`
z&SLelcXv30FaQ6iZ{#_tWS=?Lu~nbX&$sX2n0$Ou=H+D|ugb{COqezelmi}bzh8HF
znr`%zpS%~=`@DX=e16@bW4+QBw`2yJ<lmEFWo7m7@;U@+61}~>{qc>B$r`b{ww$ta
z;#d>Cop1l&Z_-xf?|LRo5cu=&_xp(Ld9vT$-R(Zy&c8V8>Z(&eZr;4f!O3}Wrg3_}
z`Z(J!@9)dAva;UTn9N@F?M-L#^K+us6YoisK7PHa{(l`Pvw?cX9UTo@x0>q3@9Qaj
zeJ%0xv$Ga8KMeNl-8=Q;*O%W#TqmjQo#&mErNzX=1Zs!2w6!ftKR<6r-CwI~Ya*N1
zMsH90`|E4Q-CbLa>hABW-B|S0tD?GkasK^%8@6n5adTtile6iNwJuZ8(K(~>-T(fl
zg%f7Z<gBl+x3I8S5Wm0f#Hmw<UR_;%ado(UN=nLu&FAfcJJ;v`zj@<J=JzdE-%nCe
zw6l|&ZI<iw`r6u$58LG*-Pu`uV^^uR-#i<ThYnu67$|xFg4zEM4-d~UO66*5YPzt$
zzW&bsdiiP7rb(D&2qYyXZAd!G_2vEj_|*C7=jSEf+>}~SSm@Z!C)>4G{@1dz5^pEk
zrEU#e?6x9quhq8P+ihpg_-y_4>`15Zj*5>;yGmYys?yXQ`+oXNQhD;^iGqoV$jq5D
zGj48D&B@K3x;pW7^nM2YUkka#bQ)H#)@I|E>j_%w1rEo$KNg=peKPsBvFGaYTl?$n
zi;9W_BqSnIY-*1w&$_d>TD-2V4iu2H%yPSq^-62kCoHb~{LHm4@QdYlP%SPe*SBYn
z&6e!ze4(pC4)#i$Z>alQm2-EOX!ZAZq2FdU{Qp+m&MV#4%+9~aceYu^<z>CMj%4_n
zEWJ77>jt~h33iVcJv`i={P<Y!jqUmJO3KPplY@?aJ#yqo!r?Yv4?n+S$K~tS=;*he
z_Kk{?0=Z$!784d$)`xq)-#dK2{(rA-^tJ_|tHXYLJT8Crm5k@44QXeka_;Yojg;SK
zGtp2%fq?<k=J=)@bZbvv;c~Uw-``wwa&+qcehuG}ecdnj_oJiTik?D?7A=~R*mmus
z{^f6Zi@c}n-PluU462D2I=3sStFw2D=^m1=|FiI;1*DC!#qf*m`9D8D3(Cv)e|vjd
z*}_8Nc%SUyRiUdV%$d`3zy5#h<K5e*zYJFUy3)QxQ+<|;tE-}l3X7qkA*glqPb2DK
zxihF<=n~a_@a|n-BQv|xB$b>S8yGKMyl7GKLSULs<f5`W?EG>X^%D$jY-Bd+ERNY(
zbo8El?QMtJ`}WVCJp+X$sNTDC_bw<^-ney3$<$O-+C0xCAYj5Ri%SycWh*`=3-AB;
zOMA|oIRbKWeCq1zcXkvqSATos*ehik@@bCRuej{f({u};oDlr+`*-q#1C0izrlIrJ
zdrnsS@bxR}g8MrjJ>7I~Ww3fhRn?=}`TH7GJSFUEELsGPKC^Z{UZwwC|NY(F%P&{U
zBN`#TEU+es;NDUdPoYgZt6SgS-tIqR#taT_ZtlX@*L0`mc6N3;O;Qn*kkF8`t68y0
zS5ME+W0DGJ*eNx_&#&*phYtdqbh@W%hp(EeZEG9*^!=16BE6Zi_H}zEq(-iZ+Z&~7
zqo(F|Vw29dx3`y<<ti#FO7(x;^y}+uZjcr4@7Zq6{r>)b_|M&ikB>P`OEs+hRnl8H
z-@bm`pWSY~QclxSHzpnBnp&|se7)EtmCjkF*{fo^RXh*fx)n9Yve@nIkLh}`LQB1-
z3SC_lDr}yAFXZO588b9|e0*G<pPSpgKVjkDeVmFeSy`(lsCc@#x@sPN^!RbBisvIx
zq0l{l_H1oA`?@uMs^8z+>oiFP)cl%Saq!?lr%5Uw-|c?iwPuY@>W|6l{w`CsLR(g@
zT)Ct6_co(Hudc2>bmolD6zy<7-T7Z$Ty)O<cU8^8BI3j*opmugmDa`Y*VEC}ZJj-P
zcEz_hGmZRGQkG0ejeK)&Z?xpMA0Lw+zIdVG<Li5Lp>umkpJnnf9!1Yd88<gA^{N0V
zRPhX172<hkN1?Oiy!rF>XPIOwr9_IU`^^bxd;at(r@p>^VrHf$pNz$VqBXP4^SQ#q
z!yi6+q*PQ?RI=;Z>hSfeTAx09*0o`SLEx$o&508yF65bSo<DCwYUG*O=Ki_!)&1wK
zxFeryRsK#VB~q;Z&&T##+oqomaC2)r_S(b4LqJVUP07kCN;PKUe3Pk5|NZ^V?K!Ds
z@#4iZtV&m%+IDiXI(Ou>qjz=|haM6=f9&K*&zSvnv8mA&6+0%RM%Mg%I$i6boSfXD
z%a?;yb1p7&1*IH8!G%HZS_P6G9qE)hzn0ro);jBoM(T||S?ei3eWs;OeSUjmvb*Bx
zO<s1h4HBCssCd@=`FMQMf&~teaRC7ezrMfMPl*(pZJr<2maX;Ki9=9IN-HH&Y~#j_
zS`Tk;&kwhoykm#O)ZDIL`*Lq@)2e)aZm#vAd-vijEG#<q?Aeoael4gMyR~T5hoXB%
zEh?Ue&Ytz<P&{&LYj&%Or;?3L%wyB1&!1}_?vt@pQt=d$laqUNZm#vI4}bpDfZB43
zr#D5-yYl^>#O8DLpaGHJQ|Haoi;0PGSsS%A<j_~m%eOMJxi4M16!K~5A^rV-Kt>p+
zoeAKK-&3*CXn*eQZN90u@9ZpYRq<RDxj9YiVeRj4qMLNOBR8k5Y_YHZ7qcbns@IGe
zGgfTbJnK?c&#plE*4rAjclTC@FO?1R@beS9cJ11t(%09t9{&1Ly~Xg!&Mg@iosw^Y
zIs*o#rlP5*r-|18|GQnlspHL?9L3X{GHz^Gc<i%%#RrGwCHs7WYuDxf6nM11_Qkuq
zyH~d?U$%_P-Q7JgFK^wY<yW`=U!%LW%^+;|@``6^X=zF4=h<rAKGq|toDwN!oPI8Z
zQ{Qv;|I7aNE8muXe&(B)mZm0UlCfZ$??t_SX>-57Y8eaiZ}nW1dl?<J+;1)@Mm|43
zAAVci$|~x_CY^10cUSQko6JACNhfMchT=S%%AiLk@)iXSmgh9*wB5NAb8(5Mu%hQB
z?YF_ba<(8H*Vf0cFWkNFv7n+!zxMC1uhml`#gdQp1akWO`H4My_RMM8Q=$G=BV*&%
zy?gf-l$D8z>%|0EUc0$Dy>;u>tt;a9@AKNRXixZ>h`^ZLWxls_FTHqLl)t7b;=a|1
z359`y$<eM-DUsKz{AZcvYWev1T)AhOlAg{jFE5{%n!5DT{opI@YHDgp&(F<ujoaVc
z+^iA4E@on(NZj!qn>DVk4i^^_6H_ua4p#m1^YimV7cT}*(T|T?YM+xKyMATP9-DRX
z+j3@3Q1N78VOep7d*;lUhfbgNKCx*{nBLd5>${}eGrZR?d|&zI&6^`PH>Zbg`}*c)
z@QF=2*VaTXHso!68LY;;*1k(i-Sy(Pf4M(DJv~*mzCil(las=rA}DK5e^;GDO3D(i
zI_*Bi+y(pI%OCHNR95j6lC>@iIsMzx(o(B7JK45ev8AK8S9FpJr@g&BXsByyE-Ndm
z*85y>{kS!SbJm^T`tRd$d8y+^xms@<)E*O^b!wNut>1fYom#Ol**5pDH=<UsezAQI
zJECF;>k4f;)+gJYcX!vq%FoXj8g6b*U%l4Ir2Jis$D|hd`agnZW@cKqe|>q$EH5vw
z6TQtxQcPaHKl}Q+h0g7KFRrbfeQRfIOiakXYumcM9ha}?QDiB5b0hJDs@Ul(S3(}2
zDrgNav?+Zh(kExj6(1kpBW3E99CP%QWjnuo*gCx{d#lT*R>bZqaZE^1(2LvC(ag@j
zN;dt&gM%xgx37!(@%?^%|DHWIHNW3(*NES@=hU_d69l&8-<SLN@#Bx*@AsGP&R~v+
zh*;4&bJna?Yr|Ies(8*YOlEuY=FODEY15{G#!R@lxC%Z!@l5@(DfRS(`Sbf1I=8QS
zIyv+5vX@&X%{LR(4m+YgzozNSmy$E{Y<Hj70ctj;rK#;If6rH6Uq3Z>e%&uk8ylMm
z6DBlBo9C^_nXJMotmf0Odi81}pJ}NsuC9(8jgOD_Yaia8ceiVG`1+(57Zzq|n@!V?
zms{-CduVO+_A6ogueoi^N=;n0Y?*{n3dg5UpRV*Nw_Ny<qpPc%n3os#=BLQ&h)gTD
zhej+6qFNyrcAN^|oOU)~cUkV*R2vNqkF`3QVe7YV-+sLQ-)H%$xwXH(Gzu{7|Nn3I
zu`hL>PO4{VyPuz9DLhH#;q>^ri!<5|Jv%d#+1S`vCuT=L?$tFLlaGTE^isVmQ}^$;
z*U`}lnRjtr?CylLw6;!RbtjI6chp)A?5q79ur(_*)lS&y!S46_oLjj>KYYC&zj}><
zn&%{={o>Qjj=o9*H7FN2HivB6nsYNK^=PT@vvYG-Pb!}?XU>I%&g?1a>5m^B?Y6qp
z`QOOc`0@^|N2e=SFFADh@Wma4$)LtmJHNc1(Yr&f+=`w;$NFTs)z#Hgcj%m+VOwpc
z;(6%2{r@$E@v-lF4PVztOH22DKYjEltDvCZj)I3xUb4&lXI`5=d-m*O&m|=#IisVa
z*Ood&L`Z=8bW=Bg1{6=9=I-q51T~Bs#I@D*qPOw9-}ignEv_p|y`~=e^73+EKtRLO
z)6>OgUz>ETcfI$`O{u2a4&S?XkAs)@=ser%3G?T#-{d>Ju3xXDR`2D@mmVG-4ZC++
zyY<Pe6uN)@Jil$#mjli0{GhfpgZ`%l0#2`2wH%A7jl2J8VM0<;Q|9GmD_cTWg>W8j
z<8{u<TX(8!-mh=-d(TR|o#)gqXDc8hvqs1)<ATE0eY^=3v)?~{+|0<#wxV^qe!QHl
zb(u?0kdWVeyS1Bi&CJBq)YPQDUp_Kn%hWBlm$t9j_y6DT2`Ze0g@sxli;IglW?j{?
zu(s9?Z)EeDc0TR=JYH|_(?ZK5H+p>%kFQxci7hxd*k`U)=;NKeH<t&kafrRL>h!N3
zcaxK6&mKKBRXZ^~y<LCb52w`G+qawl`tmY)O7ZcdM;|^s+}_dI>G<{4)zH4+)nU3k
zG8O{M{pTNR<rcqk?&JLbf7su>d*>SGUf2`K|2mjmvN|SY&XXr8Z|?7xfB5j>i%Uzp
zPnktWNBhjN5IjH6_VBLK*H^y1y|Hoer@NhIPft%jes_2I#L1I`bE3e-EvU`!=f@Ye
zCSsw`zRJ&ODQRho%HQ9c@brJ(ztjxb_1&)BVvdtkd}bQCs`B5ueLMNijzR&a6>pP0
z>OJCBE6;!acwByQ*xD$qL}qrrD?cS6<!jH|>G5@qDxRQGaWCoQ%*@W0mzO(pEG#?|
zvMNOL%pA*L)%~K!Czu7y2M-N`hDj1qQ(NWhemLsBpFMNtLZ6vNQvIQmp7Sw$es;E5
z#j~TgH#G8~Y{f+Vl1SNm6Ux`lI_Ag_a?9XA#bd76DJg4~udVllPXXq$UpAl1054-N
z<y~6hsa5Yisil=$TuZ%NtnAB+z!@`VCVqW&RjPmL<jKvu%ik**8w>OC@mW-T(NOUW
znkf@F1vJzL8bUeND_!{VlB!MB7muHX8&y0#{Qa+ge${n-b+~?ygdx+`tgBAn-`xfE
z{#jU97UbOAr1cS0x-w*3T;#g(IH<5~5TDFq%E`+MYJ(R1`jR=7|Fx>8Q!^W{$-BiC
z|L^UsHmzGx_57UdljqMLUs~$@;p<mjv)*4Bx3*};#Ks!t-ZD{9Rb5#6`Wk5HtiQiM
zPM($7;qR}nR}bB}bBBRp=FFL=42~Xo*wDbR^~bw+?+S{G4{y!B{>7?15j4|wsFfQu
z>A@po5s)gBnYi3<Zj*|q)cmELot(2wGMiMrr#<-c@^aQ>t&+Xhl->In7=nU>K`ryG
zwR-XUcobRA&9`449J#CRuN7#x<;W42B}<n+e0h2Ksa*Z(i@&|S{rK~Fd-swOlWqC;
z`=;qeD=8>Ayj6a==*z3C+|p(_4u{)#FRqO?Z)s^!P*8A46>>@Rp04K_6C-nOj%D+i
zGd@#08E&bSX6>5ZC9n43<Hx|+0?RD6FY|0>xUj@ic&mZGzyFS%I~7e$Mfv6JTGp;z
zd#rZ8U2WHsCn*+|mJes=?+d)G*V3?arzOalh5r}Lm_7UO{rmEu?)A0B)!*JYg6v-r
zs60hGoNssed(c2NXiRa<8l9;p`KRl}9%^Ri4_F&z>NC$KGWnK{u5P#Q>_vY}^X^1E
z{&wJi!&>3`H*emU{Nrd^wkLj0+}^5(pz?Ta)Yc1Iv%^8dhP~3}*M8-AWqo^d^TYS=
z$2$a-yXLg4oAG1C%D5F#TeY;p)^tpnA_7V~sZ1?)-;doW{kPD$-5~v(jErrSNcp=v
zfipRlt`HX~ov|-9O1`qP5;RH<8V)ahehxJ7#mdTh>g}ytmA<KA(^6U3*dD#Qy4s@l
zmkDU(_R$f}C(oZdPg3dqy7JMkZf)jcE2QI>gT`|XHi3tr_EvwNFn#*+J8GUn@9yqi
zK4;FN?EUWIyX?eWXL53JU9xagH8BzKp00QF<>loUcbDhixN&1a?C!D~n^L)JYHC2k
z-3t~dm}Fh?c&u`B(xv4!8lYLRpru|}$GQ0UjveU~4psAbeY?I+)a%ka(Pi29-40GL
z+n;#2E$Y0ytZeVr?CVNqW@6l8It&bdem<XXQT9gS)|Sl0*Ox@sUP@c@&13$iSFc`y
z`c9y^d~v-P(A+G;o*6v99voz@`F1m1>u-Vc=b5dotgo)DOrByQezpGl=g-Y6SH4=V
zeC%ED-Tn3Q4j(5k{(AO!YwVs1LI3%7uAnUCSH{c3bLE$^$*(!l7x{nu{eItcTl#dp
zSf&q)Y=fWhvgSVatd-a;cWo=5(YGBdEV@3Yrl)7y+@EV*KIM7!Oug@shK!%@?XAwT
zU-fO%b;EZ$Ui0m04f5_-965UQ;bDIJkhbGTk2+3L>3!eMv+{9i;jb^5CpN9ws8{*Z
zJ%H=-@_j}wp7%aa`2s2jy@To{CO@(?%e@tn8-011Z(>r?qHoPc2f9yQ`t{A5H<S5m
z<^PI@hgeh6(+{6N@BjAr!7YZzit9f;;XF6bw)@l5)7gI(dd0phUb{8xYEyqdf7qIc
z#w%AsKvTkvjg1xG@0MRxyC+>7v#@(o&)2S3@j|d><i**?krub*8y<B(<Uil;=tO1r
z3+v<UdE{&)rfP)-{oe8Y-{0RS&YusTy(Mmjif6^2ABLbo&Z$#b8LWJxPM<#Q?BT)T
zH^+i8KR>_Z{XJPfKfhD_GRa9vAO8F-W?mn(`{Chs&{_h}6z#LKv)e6;pD|Q?bbNDW
zrtwtyp0w0d$4M%4*Qr`tOHWeCjICYo)XF8`r19QA@s?d$sLu+}f}?AnwchRBc=N`M
z2RAk*gO<U7))LIME_dQ++?0A+$;wJ9`FLOG?0`kR%Q~&PYPst-%$qxxmm$htKtFt4
zOsCp{+c$0`9BSeG@nUhmfUt1$&(F`ZdzO2+2c8#dIF_E7pTAyg*~=)=^JQ;uZH>CT
z`t@dCPfy2YHr@$y=k_jGpa7a1C@U*7Ff??`%F=rD=uyb2iMw}O`^~XvoH0Wp=l(uf
zX|tRL0j9jXJPE@jmNq`ws5h3@rLS6aqqik|dvh~lONL<GpO5YwiUIrUYC%<f>ee@)
z5xaA9EI}ibtHahlc=c-4pM<)Li(F4l)sFx6Nh|t5{rjcMa=SSDK+6jHm+Qt))sL6U
z%*;G-?%Xx2l{&`8!cH7__EvAdvFn0BVq)Tr&FTE#-rQ`ya3NrhT`ed)SU)5MH77m#
z{_gH>MNgqahYn5ot@Y{B)6>(teWD9jr@apPx8>rL_l##N_gjF*&G+otvmxW6lFxiQ
z*~`m(n^&&XjM|>pdvkO8;nSzRpC`XObpAZQpr9aVBpTF5+9tHDN$=~SudlC9oH})>
z5o7H9>f|$4^@rPdUtC(st)r`ZaZhD&MP=o}l9!hzq)LLOUjF_49r}v3_SBYryUN~n
z^-7x`I(?cO)Rg-9>FHGADf@mtlV1C_CNNd($9v<zJKKfT{T>|Y6qfovQDx-~qlBJa
zA4_K%r}MS(%Y&x!K||>8-n|1YGg0xpu_2Lp(&WjZ?^dt-D;N9XR}4?4cli3a-j|n`
zC;$BPw4<{#aGi&|pkQO<=Cp%1Z$>^Z5p%u&Y2kv`TbX}-pC8{kX-hTNB$doH$3=4A
zo&LIeVQyWZ@b0GO=D^KqzH1^jGHp&j@AmT2QbB2HZqG>u6(1fbU5=l$MRGByvB%_)
zlA<CcBqSg%zC6Y;#!&Lh)2Z8d&!)RhRjs`o6Y}42TI$xTiM@B12iY7>KR-`Y(*OF$
z4mH)6$}fxG{r>(wJ63jwf$v|2Sao-?<1@Z)SXVm1@VM))fI0e#ij16`oKfeOue`tD
zbZyulff;&}zr}<4zOD6N9z8nR4I0LNcW-aEtaaIe>(|5IwrlaMeOx+m?p)AJTCaW7
z;<x*xgN{p0(sRE5S>mze%P2KyQIk~_o|2T*v?=xUqjz_AXWiymdH72%^Viz{E6(pe
zd&uk89bVh~#9wi%7xCL<UQ$^TyIX9rdw-h%lbM;>i`(1vm-)?I^@mX`xlg+!aMH$k
z8*jP6+fY@e$g8U24_vw=v~c0Vj{bi4y;WZ?fF`B(R0xWRiJh`2D=QOldT?)VwUun}
z$Bj$%w5R9a+QO;sH^*Ur-QO#AQ}&j=7E4M>D%me#`}N&jY0yaT;dcJQA0HAy-4bqb
zJ(tyCYYQG8Vg=32e*5-K!0APaZrAUU*VlA=Z|C3J!|6H6#Ba`3vx828-ya@smkPgq
zxjkv?kwe-|ni;<$q$)Pv`U08?oL~2g6ST@LDM{(s`T6~xlhqtK78ZV8I4QvA+>YAc
zW?9$PtlakZ+uPf!cE=waY&I-^7xU-O=kpR~IWvw~bp4LIvROywyg*r5*#s5N+2;9f
zv(0jO?D#$;u|7X@#s@Ts_J05WeW$if)ecYk_~>ZX?~wIzvf5#592^}PK`oou-DQdQ
z_Ei3OGT9%rENsP!6-noR->ZHP9-6<r+`sV64a1z9n^-|*Cun;1@^b&hZoN`Fs=w=j
ziqc)BuOEGQczDC6O+l8&K0Q6{UGnx9$knUD)~*s;S8>kO*8iwke0=;Io61WsGP!wq
zTLqYQm%VLL@zl`J2=FuF=j8?UFhEOm<}}1ru-duavMPNQ^5n?eM<ROlvm_S(dFeDs
zg-6<q=WrYE;l0)03qCw>TobcXXm$AdV>^qV7kqmYxi$2LSJta5D{pMc6h77?+1w{<
zoz)Y(BksbMMLRdXVm)9{`fo?!<Al7tz9makLRN?QrbfHDv4PgDZtK@ejf(g5^t`d7
zP&sOgfTg?-Y%M@WWA5#3E7#o7ZaMJf<>jsKR_mVM8<QsbU(T+kV&dfQrHMVeK8Bt?
zfByK9PT|0XPONk6YNK+E9y~nUZu)My_kMTrUv}cPw}Og`i+kkl<sKjJcdx3l`u6^Q
z|Iu#o<d>J0?kIaJ_3iEL<-t<j$sRu$O7@o>t$%$P(nOJ5q>@`#IJwvU#{*{2sAt5s
z97)hJuGG`h4qm+)`rK}cVy1RxbxKC$+bb)DK@-{~FN1t$8nJ$VclYqOx3?cYe$1So
zpFed++cV?b@3$wIh`+P1sHj+xqphI<nmY~+%QGvRzv{!2)8S7`zfKf+44U7+vMx4y
zeJ$@_!6nlrH-lRp&vtl-cYQuL)0iE!iuBxX&q+%z*Y2zTZ|CFdTl%YTBB;^fcYj~)
zRQoE!)KellvAaYnD=V{B&)@&5aPHi>vT`;R4S)XBZ1sFG>s|lC(lv@NjlS6S8@_;)
z0>Odj4ejmazrVYC`Nv|JwkwIhwl)6RSAXUC-DQT7kN33g$=<qo^Wir)Hyc)e%Zb@r
zCHni@ThJ8gzTfYxQ_|Cw_4NECuSY;SRq1QCP3(YyINqH<G~ivVFWWwR`*!R=BXi;7
zW4tw=&zfu9{`2S0gqbrtKR-YJx<tp`-kwA8!|nY2qSD{j@Bi1N;`!pr%E`C3?XCX)
zs$}1!O<T9Rt`1u(AT8Z};)I7y#Rmt=k0;Kb=V#cEe7rBI|MBbB+z!>dgoT9}8NR-{
zdf76!>vQ&Oj-~uZ**{!gA0K{uS+3~9Ls{3>bSgTxB|JYjm!Y9o+I*UYum0z+Ut0y3
z*!kr`Zcm#wZJFWQUq*(82fw_$JaP8y?up9oVl(-C&l}m>%d_*zFf6#gxn|~~ITDX=
z#_cR(Ww@}jIDKnw_4jwWpB6_)PJ8(JHAqL&&reSUoL>9|jSmUR$n->RPJ0OI^7#4n
zZTb_xw@Q?il{Mquo}IT;TBXhN9=y7`x@zuf6%*eXo}QiuzrMcy@ZrP2Ct4epdQW$I
zduwaqw>Ob%?QaAK@k*IAtX->H_WoY)ks~e<k&&9G>mwp0S_E$FD%Iwbx9ize`WiG+
zv@^d~$}}NAzkjiN|EsN+ew?nUsbOGn?~}Q>BX;6@Z?D^{cFvlj8!aYlU3TQuRBb^i
zsV?pCbq~(l|2Ofn;`;pQlT%5FNl;LbLH<3P-oma`kJrcSY?3z5J8=2(<{MXAx|7aW
z{XaETdqwE#X}6w4DY|StziEZh+V%VY{o-Z-EghVC@;O7nn;V8twHD6G(Ao^@kC-`q
z^pP^l;fS2pJI$T(@s-~7r$9Z8sZ&|&>+83k46FbD*W7QeRp^s{u3xK57QQYH{PX+4
z!Ddj&bX(ofP;in;X0CT^Z0yCw?)-0VY-9$FWF2f~pEz^o%3`bTq>P^)-rkpY?0P-V
zwwmG3_gRd8f1h9P<ax{1dCw`c{h(>-O`8t&+yCnbT^**Vt<BBM#&e-EDbVwBng=NF
zZr!i}v<PD2#EFfdLKw6{QoWh!*!lFfB|8fu>u*j}cE3{h=hThbRl7=GJ8?8}i|bAK
z5pfH&M0DD;X&!!l*LECw)yT}=V|4QDjK|E$8kx3hvSm|Fl!{-UuamWV(f-skb<KxB
zv#Vdelw4UG9lrd>`s6#2bI#4R)~^5J#L>88hsBJUGZ(t|%V~X#`?_OY+}<j!znzCf
z-sU8>T?zly<17+)v|7$tG*m6#)zYYC{d#>aE-sU0$@llwo;ZKr{1(?uNR|!h**tmj
z<gNc04z31`jaZewdhqS-ZHwY(J&wmUUhckjYO1!fmKIm__jjOmfM&V3mKer)9v9tJ
zA)0K9sJE>Pke5E4xv?=BG*fkEmMQnmn>SB=czC$onWM3hnO!UVf!3RolhrNC-pu&)
zzU=L-gNF|@&o<9Lc515j)korSM~@#q?EIMhdieUdqc1Klj=z~@ddqG{$eOt2KNjqY
z+gk<d{l4G-zYjF{cC`M(1IBsw^?VE*92^c`UtI+)L0J>M-B0!2t*zN04yd+lY;3ez
z{u#8~b>&LUHh%fO)6?}==bk@%_UezuZEB#!W&%vzV!A;;5B&J`_4N#!%1yWS+LgbP
zd3R^$;xd_|?b}sj=Y~(7XIp*f$`z5%&(0q1l{OFA)+=XwD?{F`{KW-EM@L6cSC&uK
zYRR^}$;bN&N=lA&iE4*@GGhRhSRS69j-Q{M4Gk+cQQ?h?i<@CzzwcV-T=#ytqnp#u
zciB!$+In*O=dXRT)*A{QI&J;2+;8ro!|nW64}GoN#?B{m;fIaL@qj6cuD9amHT?MT
zF&Q+%k{fhswNlH0IhMsCYJ6OZptZ*wiWk<$?@#Lg_;UIDM?XJ5@963ZTB$6$Y11aq
zP*C$F_0vY6ahTK7^^?!eGUedm30b%5)x(F3{QUf9W*W1Dy0sY@D^BfGQ&W?$D$y`9
zG6F5J>8*TrZEf_?x*6}EJp(Nk`t$XAe8h%?##7tg-rk=4{oP%**xRRNWMmXPCmr*g
z1KRo!u6^e0+0b=4Q5A>0!E0o%z5FSf{^!R>(9)Uk_}bRv{qn1G-(O!Z-y-ni(`o(C
zu$!QIEq#71n<5Jvk3_&C6N$~|zJK^|;OXh<SJk|IW*9go$6eU!^V&Q5Z^`p>bCbel
zeSLh6Tw5C*dI;2p(GFh+T4|A&m&d@MuCD&&)m3hF|9MBI$Jeba-1PbC>hOuPW<@>u
z`DLxNt&NSs=}pJ>{L!+swmy976ql!`r<Snd=TD!eXq)c$xegf!Ubk)?Xfaw)aPZZ-
zJ1=f*Ope%?#3~~zJ5@OO-QC^G3!UCCcJKf2<74uSS+f>}tPHYRzFFhfH2&5<e`@|b
zxBuTL;3PS1(xj%H#m^6&Im5HJ`g>U0>)Z8udV7C8Gfm!7{i|wf?!L8abwTTFf|vUx
zzPYi{z|{2W>T_4kbAN4fpCu6#CJI`CA?!F^Cz8q7*!atvo58yC3_s6YnECGVa{d;9
zAFo!g4|#QA&Kw!gsv@cL$!F|B3knPx#Q#1EKYHd2&)r?6&S7C<`~H0Lo|>C}ZqC6;
zs@^?C^H!|TxN-Y-GHAlKUcrZB;dQPjzl_ps*Z9k(oY=9#XQq*WQ^s0x(bey>ZpH1d
zt7TzjP5k@oYs8j}iO2r_|MS@&)K~n$U3;=qSRFKQel7m`v(g^x?!`YYc7OR&0#50E
zexUX%Xg&GViuF}7;-aFgiY)tnJmP+8E%xB3_4M`oetEsEZB_gl8u(Zs7gRjOz6@65
zT?v{eYYXa`d8|ir@h9hC|M_;I`yRi(zkh$=xuyBiE8hQhkDMkbE87biDsASsbMW))
zJN50(otU}d@z<|!NIb02a^S(i=BvllojQ`#kG!s4yK?194^PiP>%K>G(;wRP8y*+k
zWpFK`AJ)d`xMzpDpG96=T)gJPLG~HO>3qxl=l6kD*)upfJA>9O^hg@Bg{}^BeSK~1
z!<R2RkN3+zzO^+Qv{0t0scA#*Z8HXay9@D~(|Dt{<#f)otp*K7)z#Hie0w8#ZmxB^
zZS^+|`#U+;*U5s`vaH|#PwM2!lOMi*J-Rjf`i9ciVOw%<hdpK~OMY=>rSO`yYac#;
zzWk5D=L3z*7KM*kq)ajz($3D(e5@C{OGHso@yDZX{SA3{tytLEojDr4r|TtNUl+Th
z;33nUyLTD)%;34X$d$X~^)+5us}hG^DN|7Q2DDtWtgP(E*X!|Lz0$wFy87|7{{98^
z|Nnv3Ek|w5YR$U3O3~b0JTo)XqTm6;oVjxg-`&}n)PHqDqO(cnCGcXu!)?5v3jg-@
zd}TX3xwTPS53LGa9r8$BMFq5>2ek4IwBaf}Jsq^TWwu#vQ)g%AwX27}239bMe@L3T
z)N``h!*2b32dv-kY0kU5>)^R_e4Lz|C(fKX0ur(R_ha#q=d2B&zV-R@{yU9A5|?^U
zKc>I`Pt&^C-Jo@Gpb>#PckfP|GNom%b@`#AM_qH9*6s80_1#$aw`xn)Rj%AyTN?N8
zx38(G0aanIudjc6q*EBQeDdsU^Tfo&z$Y6QEnd7a<D!y_i;IGi5|f^u-jC1c?KdVL
z=L4;3UMr&;xrt@t#*G|2JT23wi_6H!6g)j8dgS==!-ozr&9C|7x$&jES&qb|%a;WO
z1Q_`F`KM@wf=Uk$AD@=x%hh+4zvpAn2wx|&tNeXm=<2Y8$B(n?Ms0B@D>D-k5=zL-
z<dm0}Zw~)@sa?gBgM*`?zrWuo{_Ty8%<1RmfQE@mPMr@73<NDE-S_`rHE7Ty_4KrY
z^77-&?EDiZO=|l4`}^Yf{dGV7{eI8ul^hWvu`TCj)9&*3N;*0|xwpZSYm;u7F@UxX
zOqx7dP+GeC$B&AZwzfl8uZotxy93&WQTXD5BB+mHnte^ji1+jJ^X?7~44^>Cy=``7
zZL~P3zWw#}^~H_J?m4%%c;<>`*G|=omFkr;Jp|g^vAaA!WOW#?nwr{+3k#X=+_@tl
zA<>}~x@tk)-(M?2RtkX@B)7D%#Ox?w1f{*NudYr#9#m74mlgHtzwXlq4;s$f|Cd?p
z*2~1OwQ6DE<6{!0St4oY=5$(>z5>MuD8BRe|83ixeqKpKgG1S^M<Y<GC-OPJyq%1E
z-48{`FfpI8v9XL*33yl8?{9Af<>l84#a}mCyPl0#N<l$^;q~?PAYU;tGZ+5;mJ3>6
zy&`ZiTTD#MmUp+;#afrVy23fvs?=$!Rw$@S1P!~To}PB}&(F`HkLtePEeCA~GDtkc
zq7%7^rLnOQ6rV;$Mg{-=RL-%f6w(e`6W}-RlFR*FfgFsUlfIm)pEz;isXa?0)|Ovc
z5x8OFMn(qE4BEec|6JvqCxQFCmzVpuZ{KciRq~=?&K#LHH#f7-oH>(&lQVF(#3KLw
z%PoG{OlRd5Q!p?P08JX7n`;eP8la@B%bR_DU2A72r<iWkk~uf#&zr{=A0J;)UA;K(
z?k>=*%i(tZjj5-_?(D0TmaqS_@nYQ{xBH(K25irZm9Z}4`TF|0d$*V_sE=fteNDmI
zTG}}MT+8z1%Z=9U`}=&6#H8yCQ+C`9o)aCue%IOlzP@AU?f>`m^zdxSzrXLquf<C;
ztABl28TWRgTHBORP)j>xWe{ujwKa};d3v|D=dU-D6fwxNGd4NvJImzY0>|bLm;LP*
zmc6}o%1BgRp1-=fddH3(E56G1++4mYcDLE8@b!Incb99Q?y@U6`}p!QU+1JGrL;3M
z8W+3wAG&{EUQ$vrVsjertu2|&z0&5d?z&g~ywlg$7qPoc*Q)#-kG;KpOKU60_z5bU
z*Vo4%pQ!Bq;lV*>o61iv>p#CZbpt%!rTBQ!gb4yCHuYRw?Ebjl{$E3LGc&`3ZvA}>
z9~Qm0DSqa|BVoYs@ZrM^8#gxY-D}&%Bgw=Nv9HGR(4j-1J$7g2T8sBenS%Bh=H1!R
z_~c2-9NTI!_dc1%$&)7=&E556s;qUH!z7iGcXuL}SAVfOHg^|j6szvv&va1TFiB;h
z|9rcw!njh|`-|QA*F<gQ`uOqVis0pZpoqV7Ck8bB#Vc)gWU6*}$Rp{Xcu`ZnmBGvV
zu5FS0ZQH-@i{|9EEAmID3Oj#!aglkpS?-}(rrDrn03~m32u@N-e0;3e!`IjK`@6fm
za^ZV??wf(OIS8xy9QgS7IB4l(*40%Db8l}0ZCi_qk`fXUGRVHB)BAMk5;h)*hGusD
zq?40WK~qFlB`-kDqm+~s1w%u@zrVj9|MBth)Q|D&=6~6H%{cwsg5u}rGA=A&%(}LQ
zQ(RmewCEJHDk3gU?%(J6|1};<6~`>pPVV^%uR~wxs&sU`h=2R>@$sZTKRzxBT^$DM
zNP0|CdGzQ}$vt~*ZEsLh)xy%U^U_l9?g<kF3SV7W89pNk(rLKVs^WR*$Pt&<-)?Wu
z@4mFun_F61y72iq*{Qkhe6m7!ca;jSTet4eojWlW*4Etd@$rU9M>r-<nX;s8&Fkyy
zyA_?=I!;a1<}NNS4&0U#`SAI3^<}=ZmkGT;)+-H~SYDKLwCm8RQ(jkA2D_h`W$OLp
z=~K?gX|5R=E4=>9m?5Efdee>V`SZPYEZcGG$gyKx=jK{->+9=-b`J(F^N|c(A7=~N
zqw(>_$K<U)_~mQ_7Q6S0nPy!Pm^N+Np@Rn<fBgCdTF~CP+<*S6BYR6;PI_^9d4EA+
zp&)3{qMn}KBLDezk1j3s&N_azOjrN+=kxZiAt6&feE1+BCMLGXXQt7i+qa`ZEe_BM
zEvwkg0!}IE>D`XaY@J0<PjPZ{b3c6hRu`1QCeE4#T88!a*Vo`<w)Ow^fVP#oG_&!x
zY~H+i!-fq4^XAQ4lzn~OqZ1RAwLnwu>nEf}`ph!%RJF0Nh{&#s-czx0LTcpW-)&31
zr*~C-eZ}eR?fvl08=YTYUMlC^+oSpF%1UJ!8JUuOaYuiykJ-7Xu=@Nw+g6>^pr`?@
zZOr|Ba<aPX^K)}sH*el-U~VoxRV!4;xs68<v?{Y(T2fNe$H(W$*6iz7wq@?Ncj74g
z{w@}@<>=wtw`+B(LCZH|ca;d9o~|$c^XE^i*w+)4-CZIgW)zf^h-}-oO-Vz;Bj?_p
z$j3YT<?ZzrEneK(-`}qhysT%#rcFYjtHVV9{{AkWetzE7mo?ef)(F~Ge-i;2X=Y}2
z=-fHKit6g_!pFxttG~Znd8GE&mz5IMWouSMZC$lt%NCJ$@7{q{<vcpr%r5oWBk;R-
zaGb7Bu&sckq-IK_n5L%Yqu1;Ai<xF$6PY$`8Ys0qy6kT++An7tWZl=^-o7Gc=cZ%D
zId^x3f|e+Q7KP53J-eGrRI9_SSE}>l<Kx}k;`(Bh_q#qFm#^3O{P^T#_0Vl=BQ`pn
z*rapj>{-)mfn46x^+eCkG8IleHAN7#S~%%w7s$Upv(0?L3qjYf_+9bwk*lDboSuw~
zOv~1-TR(jNE`EDkuJGoxvqGD6x_xJxtvsUtDlT*NW6%oJTif&XPfgR+_VMwVQtFtO
zw{C`I@iNeQ`V}E7CvD=(xU*v;Xa%+_Xemlz8^63>N~Bn4XJ^#=lc!ZYh2Fh;C$-(S
z{$EVUx|qnHGA2{^hprCmT(CePF*{pZM_1Q%u2t!gD=UMKetv%b>LaP5{1$__x$@%T
z>NT~sty{NlEhs7ydie0+qx1IvuT<pKp4wt|>r`G^8fbA-$A>Rpz@g|hRV(Sujg609
zUS2NsKJekU#Mjr>9=d-&J|a4ro1LBg;!<z%!k?c~d!L^_dsg)G^Yh}2jEtaVoe>cc
z9bQwlI@8Y1>fBlU9JH%NWM)|Ht7B)*_#`GJDa|s;Ty%MF-~<)V6Pwn2m5;rD@cHxS
z-TC`|x`Bp0BO)U^K@qdB_IKBoEhfEhC+_<z=gU*8Cn+fjTJ>5{Q32Za`|!yV6|3@h
zYr@X|m9PFTzdAMcf8n3fJcV<OemfksB-9oxKT$VV_<{V(OQOXyFK-C5Je>MpLHl&w
z%*zH+xm%x=C-L1m(7VJ#r_)V4;apbO=B<p;XRdzXzp|+K&Iu8TB_i|R%g0UNxZcP-
zr+EJF4;6nZi{;mSuPna%z4YDTzc$a0ipT4CPt(zq|MP(Tbo9MX(=Oe+7q`r3X3)AF
zkGej6ILtr)LeKG_?-nvA9xtBqKQ_Lqy885=pPx@#KA#h8Wo310P2}cNx3*?y_uEfc
zKfmAf^~pKe?dKYU_rCl3eQT8F@qN$coy-2Wv823wy4&JFv%EVMPT%cs-ejw?U1faX
z_^a&N-?#7E)!0VuudCgE-16$@HzjBGl)SuTRQ&7=$RX#f-|s0pt-F27-QDHW&z(DW
z>F(XyGs$z;tzY?W@ArF`GE7b_^PS!IYxCqv+o12eKFR<8;r{bXx?S)&yWek&^6u=o
zboXv--H*fa)7<4Mmu%U(b!zqdz2B$w$9id=xBH#5^Xar`uki5jmoHvu2&?&M7^k1p
zF~3)ld~-wMVZraV_bRW<zdoOP`RmFbDf61WB!9eKWSV_#%DZ>(Kt><#pL%`Q^Lf>$
ztnYp71G!bI*KMX*?k&OkedX`(eVY5eX8D;}rmIWJ%BB@QJ~s8`<>k{?uiv-J=EDKz
z)cgBt+uv93d44#^3$*okrd4Uy%a<=LAI8cWiLAHoU%q<vY7?p6PtVNv@BC)@uEh5E
zbz3t&8H<2vI*~zXXJ!=s_|4xfrmMAn&!<y{^3&Bn*MxqzdQ$P*I`;l^%X_bHUbmWg
z{E5RndoRm>kC&YLxbJ`2|G(d--`t!&{o~`~U>vzQZR+p$`~NTbx9+jz3DbfF_v>|@
zUj3YNb5rWmN#1&zbLY-|+M8dK{PNW+E%W;|p9Sw{TgCo=xBly6`Tsj&>V7_bx@Pk^
zEm>LF)L&m-rvCf$Gxhei-1hgu-~X6QIREv1{r~EnpU+vJUOGK4O3i;>%&ptEPhVLX
zeA?aa)5J}cpPwoJyVtm9-HPfp*K2hz-Jj?8b*micL?DAdTc#Q{$hY$y*zozy=JRQ{
zwq#bmj=n$Z<>lqix9|U(8@4v8)XDzf&MA|;_4k_G-kyIxcl+IGox<vAKR-RKe7E!Y
zrqb8f&de}O=CEUCU|>j4xw$#r|D5IXIVI)g&-v?rIB!0_u=P&KW#7oXRi$NbZcO}q
z-hThh$6MA&=j~9;zP|2k{QqCqV@fW%o|RMgyma~U<c-P4pLMFw%lM`-C($hD#)Qhx
z&z^?w{}sA!&!<yq{l+SCH6ISveA_(V_Thi^2VX3N&u_J={{HUl6wP3x!beBm+}ODI
z=HmjUd3C>D?s=P=fBNh7`1z*U*LZFfetUCsvZQg^lfUol>#wbkx6e4fviSMj@@Kp6
z|IIVYy)|WL@pHbPA0_4LK6b}Hxs|>C>@3slqQ76Sn^((#0*av_aqY!7j0_g0!OMI+
z<KyE&o_SyUzFP9cdC{LQ{p)9`&#O@4xBHQ>?_+O%%ELpgKhNgZO%7b__H_3BKhG5W
zco`TNw(N@CUG~)e|IhP++y8#w|Nrdt{ePbB`Sa=Y&Ud?B&oYthsaZP3=Kr71?sxy)
zNbY~CZvWF$Z{LqciNf>W-`i^q3Vqq~I~U&sS}@!G`|<eYyLWbvn-kdP7r(8arXN3V
zZ}s<Q#q)p1Y<7QGI<NlU&&B`b3-9l%-TC!e^yO>U%wELrFE1;57JdI$7${(KZ*Swh
zRajMB-M=gM_qVq@-|zbk3c;EO%<>Xjl8yi9#_h2ves)H1J}6!p80IuwJS)f05Nw=w
zX2zV_Z#UJyZhU=h?dhG*=gqGC{7iOV?xiK3KaZ%}O*GBE_T)e#v!rp_nU_+c3=9ks
zj@Q;kPv8A+m$v+`3++awudeL*aEQC|&&T7RuLS!qUA|m>{{KJEXWJ_EM6BQQ$!nS4
z+*#V|b|~f7|GsTp_2q@l&nJ^Bzg%=TE_-uBCwkkOo62(EmYMI>WapE~_$D!D;k$jm
z-=+0m5Mlo5xOI+P`m3E~C*IxNy}9P+r#E+Y8uQzHZ~&EPIx#yo+)Vyx<vm^RtTVsu
zl+*hAZ6>Sx`^Cq{%T>SG2vQmzTN-NjZDT+0FCK0&ofF>rd#CK%x6je~*qX@AMGsrW
zpUr(=lYXpUe*W_LbyoZTJk<~OI(cfU_UAV9J&70k&VIOd{rdFm^?S|a|GsdaZ3{Zp
zoPoi?TVMh6oP*nPZ%>;yZ{Fg(`NrvfVe4XME}vJWB_3Z>D69qw-L~D{dOKC7$CgFb
zecyfm>HPnH(kG?d+L9T$B_l9z_uFkfvew&93Sa8Fb?a8!mx^w2eY=Ip=VqJhzpwkg
zyFFo%FepxRVs;qp|MzwM=jHZ)HGhA5dwPlI<WDF4>x@7d?DM?udzRl+X7V+;a(?OY
zORLVWpEIZa@9X%TkNd1I-McsM=H~S0zwiIAJJv6M|INmVxjT!WKRaLluUM}3%SBLR
zN!nJG?Ao=f==Iv|&${FPJeqLkLWW7v@3-6eUm51@`}yq8pXc`HZ*9%qoPK`ZoYHHN
zKR>kF&skshb@k3Sn@+QRy}^_Jd|q|lyIrr>rS(J3P`_Ywt4qF--ykXH<|ft6>F3Y!
z*L`TdQ}MX>_}=>T^mMzgEB#ZSo|@`@XJ6stV==W~uio5}8T{<rT<eI(ObiSR4#B2U
zy~127;h^H_em?Vq(0TC?gBccV{mJ`+A$`N&-{0jwZ=bkz`}XBiCjI^W-8@kXl#eB(
z*!kshzHu-pPkJ5>5@29p$jD_XX)um(cXyAg`}uTn-v96W|IgjFZCgo6iOlE6Wp8gy
zJv-a{c@wwZioN_$Enw>G=KBBtY(Aec-uda2wsGdAC29T44%~vE7+3S3H|O5HdyDhz
zOKwlm4DS0`INLn`+;aQBFCFKCN&>Kc1_p+P;O~p&|7w`uDRAC=oMAyL#|6f737}%-
z^Y8or|E;+F|HpCrv^zTrU%q-}_3U_T!9iBfxLQU~U42kSu;KBKOVjsFseZR}`ORb=
z@3P?Yd9QBz+U{PNZvOSnvUzu}Y@Yq^raub53aaS;o8@467$2sn{u{)Qy<s=c#{c^?
z{gwD39Z#d&j=o>@p8Jekj^CP?5_o#g{SBe#W~XhK4c7fD-TrG-qWRgKZR+bDe~o&$
zC$r7@`KyI|EDU~A7-S#tT)cjL`t-OeP4T#jM7Lh4sVYBz9JilW`uf__bo<|t>vq4}
zrE+pz?Cwt|l>48|%3gPJhGBBw&+^ie5*5$1b8}|Sn>TOaPZkD?Wt_rl6?*Fu;a&q<
z4)*WM`G2o$hByYyhxz}@`MOs(cjYx7hOGra4I8ilAlHM#DtqtUn5ii%p4D2M4EX!)
z^jc4`t!IAoM!(-9X@v;0xa_xS8tWf+zOLAN%__g`9?X{sED_ssBI9a49tD*oo|_U6
zxBYpWU++Ds<{@{yM|ygC-u}Pe*2L|#I&bsY=bZijKPv0lUVzFXU-P?D)aTb2O;+<g
z_37#9;tvlF>cs8Y5jh|A@_`E~OeGD158my5f3Env?R1sQ?CjIOzP{dE_xG2|$v;0o
zU%q*B=C*CyOr(01?bcn)NO^p$_vfwa`=<SVw_E@B_xI=LSQc-p`uYk~(K`RDge5)*
zeOA?hU4pUf&5go4zt==<)mk04*6P(aPGPl_qg|qr8<UPE^nfm8fG7r$TP6f{i|fbT
zd85dXp}TkQ-pGwfu3|b76HZQ6H?NjyFuu3@-q&?${RTN`X%RKN(IV{c=J{ZGln6vl
zz)^|j?f3ep>v$MVd4F7b)!i>@nQOmGZ#z_ZSqBk6_X_U&eqINTpNDn#Oq%~OH%z`7
z=B0U7j;Y}qsHw8&eeL_x({!URUA}zzO(DoPV7x$8w#q(klj=#28vA?KRPN<-95`Y8
z2^7&kPAvG(@F2x>mMvHz5^=bh0sYPh6{Zp-1t6vthR7rijB6w?L_Cxn*g?7xcmalp
zLMMjxT^J&x4nhPWsI(moA(ZeKO+zTb!7!T3P{U)i96}9`6{96JN`Q>kWhlYHFk0KA
zgh#_@^8+<JMw=ff;W66$Knae~<_B~L2No)$%@0^eKxisAKN|k0-{&iQ?6E+jE6$ZM
zY(ru2X_MC{KW$P!y`|vciiZuAH6~J9wdc**+|<7RA1lNOAaVr@#<hnS9ZxTe+Y>RG
zPNT+v0uzJ}5D_+KuCE3U2^_fE_xOd)`PJz*S3Z9(-hTV-D@l+M|2wTABSr@vbArbg
zek_(fe)06_?C-zVuU>9*<?`k2_wL`f(FYAT&z}ZUdt6`vNZ^CJ_4#7|)Ap;cuYPWG
zBKrI9{&Szd?BHQwV5o_DX8|&vfkECG5~Ek|`=7qQUJjH~57-wS2hj`+6-)HPQAS1?
z7#JRWSHKv=5CU5VF%V1|U<{9FF<OCT5QOrmG0?ym4I5}cFpQ=fSV$}w%~P<T7%eDZ
zAu(D|z(QiQpn!$MXh8uB35L;v0u~gjepP)1u^-&G?pyrXX8pX62ItS8zniyxbvj5G
zivJXXTl^nR${;l<&p?`#F35cWc^_~iasHXgdEMvh!`6qNuWZ=<?z{Zl=bFfkxE~4N
zX5Wu3ajV~l_d_iKQ4i{$oW2Tbk%Bld{KJ-r=5fzx4+I)squnZKKrmo-s}`@l<px^|
zFd9y{!)Y{ZM#F~Y1#11qa(l&~Yy2|D?RWFOl^5YOD-iy6q3g8M6bYRsalsajk1350
zFD)$7XH9g<bv&+d(8$O`xj-{h(5mERNc(~n9Gmnu>c+llG<nE)(MetVckI5m{Po*X
z|4GfC`|Yb$UAo-2&oXU|iTA8wap|Dw!2Y6Wx?b$5$^LdTOJ840EhsPmEzA1-et*61
z^}2sQpWob=?B3SizPak_t2?FFV=YTw1n9-@yYuiW%nUGnphyK|5@@k!T-D2^K7M}B
zo=%VVTYdG^-tYHj_uK#b;lJLx@R7^5oSTzYtuit;o-7_;W4L(n;>tH0k8jGqzfXD#
zc=0XRFc1;p7v;;(@ZeYNx0~sfb$=@2Djv4Jxx3rk)5y|truDlW%KkPVUF?3nSgg9<
zw&q7cRaMoehwbudXJ?suPFlHgWzOAQrkgi!wygN@fOjW&ln7)f7$^Mv!2N<D_RZVv
z_d)Kva^=dSNYI+csuv4uKAlwm`EK|7X?wo4%h!3-*Z)td`L}y(_Vu)cgayg7AtO6r
zLl_tuo_aU%T{yb$&!^KlH#R7)4qLnHQB6`((#MZWL6$#1KmYufFD3i_{dye|I`wcn
z|MR)!_fB5+x4(PwF4P1Fb>P#LtSSbE>+iq3yeugvx9?R=MTN!wzu%($=2~rivNbq3
z_~)zD>x-V8n7HTPuh*WF!d6cWkE>L@eEG8MZP0iW#1s&z6VFuApjY<s(a|qozs8o{
zyMKTGj~_u*)z!vUR<o+#?NtAMzrOz0uU|&y=F{EfYfV6FjnB=sw%#TU(hbKE^H^Rm
z#O5R<DA@n~ayj(*+p_A9AD4pG;DX|Q-_K{WdHDF$JV9#!b8l~ZI?-M3WS^|{rQ5e}
z&wL0n<b(aHRbH{zeb2vGv2fwSo}L~P+h)-tuOX{H85kN~gVJ2m;lqb5OJ7|HeZJg(
zzTc!fWw&#^<9@$dy*};sw%qQIKi`+VyEC))_qV4{PEOwW_uK9NU*5mJyW2eb+M1n@
za=yR2dvkB~_pSFp>mC`FtXkF6+q?Ykz6)Qb^u2m7f9BAkJrUES55a5<o3?Z3&NFAv
z#uk>nyR)<H8pDORU=M;8ggt2H|Ma-uKJDtN(C+8+>waZcRaI>&e0)rGy>0O`pSr(a
zudhB=|L^B>m6Q7W|9qNW|Np_k=9^nGFPG|o(p1C$Rj+rsY&t%v$J}<g^Rvr&?>%F$
zJ4NPktk(tw1Or1v<i8i}tp0N>ChmT}Z}&o1h7w~&D+lr0TeHLYWGp6JkE_=0xBpi$
z>B*&~-ZSUUJ^SqJ?9F+1cd4BGe!qTx@$+-3e}8@5`EuFpNh;E2IVY;$@14Fm{rt0O
z(RrSeV)oTo9`Bbw|LW>$V=Jp$XM914b3;?F`bU2Lhx4D7!Um@g+*fvBe~~0CEDT!C
z{OL-t|I;%wjU)Hh)uyGVe}23D{<9Ys7k8hZJ#*$s>HIwtC#(DG{o^`w=8TV;y1KEU
z;l!6OU-IzqJXyQ_-YN0;nu+Q2Ys(BnK%R&A5JZOYF<LoHul{`2{PP*(^G|MUOt!54
zmh*1U=W~00zuSFtQ|jqQ#Z^^Rmu}y#K3WP|eVn)V>ouG2cZw|w9ypwvZ$E$I#*H$T
zMJoLEe?Ii?LtYBXz>pv*uz<N_=j{A_mY_v@|Nj1-UUTl^V)ykwT)*7Uy}!@)_V)bu
zPi#QWfa3+-U;cd!hI1i|2u^T=9m0W-DuU=^uK^g%YAo|DkO5+d5nytH3%H37W<v;2
zu?k_qNG$VuP8hm`Fa~;CF{&KQ`C~2&U7i?T6#@4yV2%ONnClcYFm#Ou5GbVJcr<|E
zK>=cnrXWx#!0~7ng9inOF-*#!MOVLo7RgRsvuf3q(z{=J`lO_!PMtX6aoLz*hu^)`
zAfG~Tm>8%Sc5q&`>eP)J6}R4U`})6J@$cV39i21WzZrH-_zvD`0an{E)g4syUzo6K
zo%e-uos$)pi>*@Z-hP{RrBwG7^9v^wW97icK0Y=%C##Bu;ScBgP_P+bLfbX}GWyU^
zgxqK`4h|eBF$78}NE(B>7qs`rD>QWF>s>D;Wlc>?rc9hTaalS8!v$5;cwOTW8k(Au
zWApY~>$2q~A@%<g#KfMtzF=U85eB6gglXDAvDa1Y?5Cydd1)zYG{3Cc|J5$B1<VWu
zzGwy(JoYp*wPj*pnAUo48EOlUfnkHqXwwK0rVI?DO(W#cU>I#0p#;YeD0Bv0?*la4
z0}8|!ZlR$|*S%hrUUKEag#b4<w^{Q*U0a9tA3fY4`38F>$i&Hy*;wk@-%WZ93=9YM
zPdL8=q?jQBy1w*5{;JozY7D<eO!~O&dC7^ITW@VwzP>fR7-aOn)|zAB?(%^kXpwk5
z*XHE1W$qvo4*Wlu9s^=9#H`%@5~Li=ff73Wqa7<~P=Kjn(&`)F%%QRtrT+aNhc!oh
z=tmiekPQqC{df4D?Cu+ZdIb`7o!xrff(LV(b}XIEoFwS-Mn|XR4=-m^lDdb~c43yI
zZmu~xxtBVU(zll-9XOR2xyDBEmQS_?hoPB#(|4iuRmF2Q?>-+q?`g9<^I;!D{oVWb
zXKdYN`+dsRTlen0{PDx11+=to4i|FjPtaYKDfRK^*DS;Db4)F>w(h!Q;tQ645Q5^+
z>}@Ob&Vt$*3=R7q+_{6^fW5&3)&x#YPy%!92If9P%+-~|thK{v)L>5Yj5-Gz3k(bl
zSVAYd7<rXr!~ZQYdb5{hzLU(}x_kHSd-v|$F$OJs<cAil5TkOYJT1EU@86=UufE+0
zzLr&8z5MZGWkJv)M`>43&j_N5f#HDL%w?HJo?l;m^iJ`$Co8VL^15sSUdnkx10{`^
zU0Jlt<U0og1A|5IxwGiIQX9^WrUY1sGBgbOe6qpxJIu8=N=`rBlsW6!yp3VIckh1t
z_U&0)Xlc<f6Pyk}3Lp6EOh5hYyZG9$?a$|J3cG#VT2@}Z6TIM;fq~(i1-v)(r!#Yw
zTTR{Gs57?dzI{<^*O~ZEh7GSi=n;mE1s{mt1S_9F#$S6ia*C+BP)$YHT7c0!1B!hx
z9{hP`G_t@E1tLZx3ls`aJlafx1_T2G!w_sluG;ntyeOi;UU&NGWtp?8k43$G_io$v
z?dIQk82&My*JNneeDt?G#E%6+;3}~pIC*ExHnisYiQ{(})O((bFdVq~=r6RrX0a07
zCOfdw(D(9>6~C*t&Zs^&OJ-|SZ00OA`7-7?2J?a$7}C4H+e3_humrNIe)$DRTWbe9
zn)RFJ%&vwgMUb-{k(+ZMaR*gM=N-g`-~^P;0Z1$W>=6(Ph9$sGh4Dai2ucGGB*F%-
z=s`RXo(ikoK^zcn7<CRP7$A5wbRgjXB59X)u3kgx;QsipgPM=OZ$H1&te}49a*!h)
ze1W$?85rgyoPN6L?_bx|SKsbjzUJz;Z+^#*yVq-TmF7P9SL6>GhB|N)sn)kRxGYo3
z@C8cWyIz|EmugY5t4nvf=V)AKd#C?h1Z4S~wC9kr2E>8l18JjK6B-l@45I}XJSZ6G
zT#g>#{C--0e@Q{Xg~$E&_s*U3J8%0vroFwr{^y^E4-@tGd~oWw`<2me^T`8rl-T^*
zZ#SjHq5VXtn`e79@D&`|`{j~%?T?4;v3skw_S^khv3BiR&`L(o$)fh>>pq=S-}~cH
zx9yJy&3k{p+r9Vuy=vS4e?H&cQ~5bQ0yNqMHH(3PA!pXwo$L%B&e#5ayS?_;%jJ9j
z|N9-gyKL>M)#2;ET?zL8dQ3Y1%h&7i_dmbkxBqh?d;Q*Puh;Lt$1Y#<A>SAE;4rfp
z{~P!Unri?3e4d+|`}Ni8_5c3ecILOeqP>34rCw?CU8S$D*`BZa^YQrKU$58i{dz4r
z^zWa~=d<sF$HL)G$}wZKI>7nuZu$MMPbT|+`*4{5|HJR;^J~9--+%vfczo^Equt`a
zKb_XEe$=UMRsXN1-}YNX{=T1S<?rvszRrUi17ai?=bp7?XsCa;e16@lL#^EZzy5CJ
z7T;C<J<tB%kH@y>>;C`!Zu{W?^WHz7PRq*3eED+O|NBw#_%GjX=a)Y}H}_uU^SPyd
z@ae-Jy?cLW_O6b5VDZOyjg_0@guso59xO6A<L1p3bYZT(1ItmiPii9KTDyuA8CUMm
z^@!@-vhGMLclo*_Q}x;#^}aa#ZMN5J73$9`GT$%#qId7T?Bb#{wey>8PEL5Q!}e^B
z@qF+aNP~8k7Yy8QzTdAu4~n=4KN1XX{Qvp(&Ynu+>gwv7w{D%vUcYymO69{=@lUt&
z_djjsw>vRAf8WgC@AvPY4PLbf@;VqFh!I-Atg``hOkDk+kH;Gy=iYwz|IdEgvhs5C
z=jZ0`e){9sF*nev&zkRd%PYU#Oy@5*I4~)DmfF%O`_fCYEM(G5q`rd2DIVO2{8sGu
zd^Tu4!YJZfwngV_@W$cetqigWjke!zB>(()T%KR%|I6j`C#k6W&)f4h*?*qR%+=xR
zpIvm9-~053a=*=_y?gh@?63Qq|No!%`aP3CNoZQKw6yfi8#jK$KV#OJx-8R3&i~T3
z-L?KNuOw`kb~EQynh^uT0YNLi=X1`PGcqtVxR%STd#JMRF$2Q^o82`(i}d36)tufa
zZJzgK3tNM$x&wPe!gBxl=fdM_r_MIdf7Zw@cf<bQS@ZiTsi~^V{pas{n|ywb<z$en
zZf(u3eAKD_tv`NunXb0BcIA(U?f<{M-~a#L@5uQ0{fnP7Y|!!2{HpfJZ<6QzVk;xx
z+j+~TJaPlOC+Z(8EFMMwgNB8{{eQ2xS@-|_c6*Lx@v`Nv3_3=PRtK1>KOPnTe6RZb
z(?hM?m0z!hPgbe__cL8DZqE$R>c@}A<^3o9`Sbbw&cerTesis+f{s!3{PgLx{_|5)
zwSRs%%>VhE^?Mc1Z{NOc+PimdyIj=?PPPN~W}c7c7c($0Twr}Z2Nchr&zph|u@##S
zj*Y)xE?2%>I{niz>HH_t<LgeY3|?OJ@zK#g9}e^1ym#;3|Gn4a>uu$0zXXDApa1*c
z=J%h^=b!I<KJWDI_xonY*Z(#3xBVJo_xsJ}n!jJK?<{!e1UiFt-#jspRd9Skn9=G$
z)9)XT`#*oXou8hbu6})e{CUvIYyEvcl+N3HKJ)MWnl)=uN=v^UNVfm~=kuPg*P?%Z
zx$Iy3^3u|t<BvhhlPy8lRoj85tKjA)_;Fld6uV>l{m$gIYuD!F=HC5QzHR&V{GV=L
z>Z7BhPyhV<y!hXrpL*)x^|Ekn+>ahye~2o?P@sd+_{OpX64Dib8^pkXWeFrkLm$f$
zNQ}Wq2h1gqnC(=|C6JhXJIskF%pL>gEG_2vHkNt*(Evh<cx($H23r7K?c4{dk4~@8
zoHZrr*Sw1>9~R8Gm~rJh4@1Mw2Y;d6X9fla9X(JN^1@1tB2~+YiJ{N-{eQT>6E=eU
z*x)xcD63}6<djR_=k)np-ZoovDaQnchUD|Vp?zis28M_nP)GGahtH%n-))%~8k8R+
zTe#>d*ky2Y85kH0<T3iXqiGO1fUrzL4R8Rxa=DM%+>GG!y}V?~rSCm{yzPg3+!pUk
zXK+YIi`F|Eu_QD0giKJvLh|m8<fT)j=D$~&`Nej*^5rdW)4Vj9N*Jb1Lmk>^a5nMW
zbniO{!vp!Kw-}=^pD~9$Mo=+Zy68Qqy9^D}&r2{00ni!!e8|DR3R}#8^z$M2heNPM
z3}~*C0aS{Bl!F?6jFVMf*FyI5S`@9Wg^s;JWf>R}>@a4aN2^<S=ztiQgMkAaK+xI*
z<TfzAuy$Eykk`v<x8-ez6WtaE-Zy4oNO*{xo){RWMO-$K>{rjceRtpTk}QLW(>Z3M
z3z-=X$f7o+bT$Tg^`0-E<nwFZ<%yZM%8ZwafYQ<(MGy(L3`88*XaLFV3<>Afe#4mU
z{)sd!1X9kxFp?TxRu{pu$3L_&N?=G>FzE2kw`@H8)RdK>zy=&iGpv0tr`XI}l3V_J
z-ldfX6LdG<ymA)SyKZoPV60xSW6v@MhCY38EEF%F5|khH2Dw1agRBo@U|^78f*W1~
zF+3TO|3T%<!XIZiW%Sl-GBi9++lpK+fn9fo9c%@d4JAg~vCx2kP@@ffNH{=9Y=?<b
zD+LJ!9ubGF1wd=MU|szTPVNwAK}f0<)1F00HMopE_Kbbtzb|~M>A=LyS!$0zs^spz
z{e6lbFI)D^v&)pAr_hV_!COuZ%E4YMKmJ4>tAMU7Wk`64sFq(GR5@97Um4=5hW{IG
zfeRQ27eYS6oMs*EqC$cON{;s7p#cG=M#dn=|D^YQj%(LQTlCehmyFYQ69}47)IH&e
zQ?o>eb98io$Q1<<zNfd=wi#t*a>y_p-l#g+q2++(ii}kq9n%D6?=rvAw3%a)IcLpu
zd#8xKPk+btv)j-ASpV+xoco{O+=ujW=sXVrjywc`nW!=QSr~(0qqE(J034lCLxja>
zQbvRY!)VSz1P1MvCSbJKMpxM&f*o_%VKj6`LuYgu2qFzI(0dsOvegU>457JmzQKeN
z%GR!1XExJknQd}x?%iEmj~+dmc^)dcLlNG6Jy04M8=HH5-O_8<>gIl%Qfg|y|H4e;
z<)B^DAjJoC5e>MQ=_gZ+9)0Fty)^TDr26vc=<01JQ()aghCEKttPV&I!-M)QA#Z1X
z18qJ5@&ECg`9K<{ARZK(V~*>LR&mg<VPIewt>O@2fjLV(EJ7z#dO3KYx<NX*v~=sq
z6r;D2ud`lXTdS+5=U0uiBI=9|c>L;sZbE74*4W+CqN0D7-U_~U_0J!t^mB8>79!@^
z4wOR1&hId(O+MLi-hR!rWwz;a=j7$Sy{R@C<sQIwkX=3xrfovbsGyk|wXKP_5GFz*
zVTUDR=m#Q#Wx{cEPargCu<r?k7mhGhn8UW1LuMFjK@MO{WMDb3dDuo)!m-$WH9N1z
zRj++}d;9hc8!qgt{r&67WdDC(Yx(4CZnW`AS3T-fzm}*93u7>Cz|Hc4!T8;QMrP0&
zM%(Xqie+u9w)9Gyf4h;~|MjSN{GZ3wHJ{I#*M2z2o_lXkrR;Rn^*`p;j8+GDe*b#C
z-n#NrN;|*&yAKZ!@BMIy8??;vZu$M%y}w?q{{O@7^y$;G76l7-zu#9admXD0FBbRT
z+EJLy&M&v8YFp;zWuV))L96D@&9nU-|Gx0gkB|HQ|NDKf?)TfTb6`gUg1x|Sh5_t`
zce~$LeK^Q|dsFIZ`E%dj-L3xmd4KW8M@RW&t*%Jt?|FFrJkqo-0|Q8tj&=RNn%moQ
zcRvG>u{(>F7C%4t_wCpGy<fw)xw%2>KVO>)LTrJOGZaB3Q^V`>mzS2B<=!ee`}5DA
zKUdHHKLuL2d2z8jC>XZiulv0#mj$W=LZ!7c$R@Pq-rKYDe%<f4vp#R#x^?yZ|5Kkn
zeJWS^Wa7M<PbW)ngBG1IFqkjCdiAQ><da*{*Q{O}y?xt`9Y5Bu{|sMq3G(ahZMo5)
zrG?M_{Q3Dg^ltV0z4cXh)92S-J1$>;XJzp6sL05buTD+X{`>Fu``BG2E2mDK3c5J@
z-Hyk7`~Uu%9$&Z9`u(2I{OP~Hzt8{w@9*``;B|%!8{UP5hu_|sy>jc;_~o{#v1iZg
zmpnW3vR*W*+8pAG&99Gi3eUADe8itFt`{@ok`zPQT#&!s-rKwTy#4<@-QxP&Qcq7?
z{XD+*YiMzC@!NZQfBUch{c`#IS+i%qUb%eUufsp@+=)p)KkscLyWEQt6O}<rXzPFf
zb?=kOJU`F&|L<n7MF)6|X8O1#{7u|y^49Y8lalQ0^JX)B{)MKzg`S0ZW}W?S$AkI%
z|88rSudDFtW|)!6RMH^%4YauQob~%J_p0B2J*B-qr1a;fr+u>4*Y?%^zO}EmI@JFE
zpJH*nn2hJ==H4y4oooB+#p1bErLSiFmbIza09xE>e!pgOyIj?aHap0a-kk{Vsr8$F
zJ>LU6^K!>j&I^obH}37Nu6{N%z3T7R>%X5)kH59EIQ@8^Y<6nu((m`{|G&B~YgMx1
z@$vrekNfSn?bvanPuBX@#^mFs-=pK=-p#9i_wwU$`TY~27kPud%)szJ@qJ(JZLS6l
zj(6z?imotZCo`^TYP`a9JCQr*;K^o2_9h|e2@hueDA>U!#(uzD(SiNP!+ZDd?~Yqv
zTT}C;YHw9__3MunB|Bs4&dVIX__E|z(e*+Z+2bGe&!evX+h@pVb%4LzZvO7Od3W=+
z`=`JA{##!DqW$L@yZ_HJp^kx22lzjKwT91DLc|#UaT8HqkDd<?4J|DD$VS6vG;CnI
z$6+BcddUVXB(OBvM#~#$;0%$l*{8*G1GW|b>T(c;*{UBc2|?ik!lPjW3Iz}zEeS!P
z0K!8gw}YGt#iOYh8W0SlsTdX#qp27c5~G)9!9!xSpnwI%Xh8uBiP3@r781l16#H-N
zo-L+(+K%Dz@s5<I4kC#@PL7eePAZN|#P3LM<y6va&M^GJm^OK9#^ZCYXAXt2T7@V$
zZkZh>=*;5kc*ALxuf9uP?xX|v&b+uehv&@W$CGDT-uv=f_y6_ExbOe}F|dn|&RM{t
zV{}Fb5flst!*&V<$&;Wn{6{C45CJke{e}n&%(lyD=!}LA*28Xz7`PlwJELi5H0>bL
z0K;el11T`D^od5BU-0l54IOw;FpTWgPl#{;v4}m>*JqD$`nfIj|Noig-@CK*dfe@E
zbFHg?zuo@-%RTG&doI6ulT&`TG+f#|@6ET{`T6(v)y}o4{A84adgEkF=e6};nHc`q
z`rH340iBUnTwI)cbJNn+)>gT?9}lNZo3`uwz3TJTpp`artx8wfR(~rwE?fTPsCazI
ziwg_I#Ko=4-bBnc%iY!UA9ZEa4k3;UjA}R9<?C*Mj)UXY-*e&4otRM2$x-F^Ys*20
z*S+8S{a)q!bLY>O|Nr}a{VdR7bZ>8MT`eA8vyqvd@6Y1hsLK_@=apvfWnd70-)nv^
z<L|GpZ*OnUPu-SyxGgO`z54&(@4vs@&OcxMegEUntJvi#7D(sqSm<y6_lx{ZaZs?r
z@s3TLAct*CKECVoIqTW;=Ea%b-<W*-)aU(=j?34-`SSAe-HOM(({sQVqQG?}6oI|-
z=~I!hvGMaW>1k=d9{1Z@6+Su=Uv>Y_pPK!DzeW4od_1x=3T?@i0#iu?=eN)2?YAc$
zZYzEk9$)+Q)MxIm?{>d0dvKspuKv%*vbVQNPnMysxKabHxN3?mK5Gg(3Gext`kzmy
zPkk=_X!Ciy*B9O8b6;Ou3p$c+dI`EK*TlbOW!O<+Y-|i#=``o(r%y$ppfmsG?|VEu
ze_!VJcXwm!|9;ig)7w_~_!#%UzdLvCT(|q(uF%bUtG{n6e}9j=4ziF7>hb#Xpk-lI
zUtX-b$#4H>gWGKegO@BX7=&|fZ_Cxy)h+$?<>j*F%fp|^*L-jc4i3(}z3uJ)d;kCa
zet&y!b$R;vdAXUHD`)5Jda3{S-=9A<-|rNkcYTX|yx@VQANSj7{P=iWetYfjZ>G06
z8a%h<trcf@@CbBd++5r0ZPVkbGE>W*otY^nCI(ulG}}CX-K!@jCxZ?V1T7KMeqQ(M
z<#M^I7YnCNpI-fX?e<-7x82tJ{SWE^2z6lUQE^bDgH|$aPWJ~Lsd&Hkdu;T!oXo_;
zh3ohK+okN@w`NZDx0~tJPp5|edbN7}uBX$YS5<vFss8)L;{I84=f3^%@v*FZUCq-!
zU%r&|+k85a`X6!d5y+MUw}cij`|Jphuig55e*HesV#eU*ep^dlUlS7--~E2y@33<|
zzP?-Y?(PcxZuj%a<Ymj2S=Ia~Xy=!Y`}*cubiOF+s)_^qCosq+9EvTy8VXw8)y&R6
z@B5jF%I;ycf_q<`*5ChUc{pnJP&>2B-X1j%G91|72;Tt?a^vX805lY!6t4cuf%+TU
zlbIM8Ccf}}0$&Tz;`n<0t>Y3Gkb=EI7<Tmn)If$6EYQ98FaZWX2b3Jez_36FU6Tc)
zEL=I5(cp!y=>dkhS{Rx}9Rm(LhS89Lgu`f>frP_oZi0jZ!)Q4J35d}W7!nSnbrUok
zMr&<IK#aC$AmK3Dgn)*_XcGbw5Ti{9NH~l(A)w(f+Jt}x#Ax>x5)h+J2uL^#d=nz!
z&E47w(^&WZ|H!{Xncp#Zlf|bu7TQ`fl@v2)IZb3)wm59sij@j|L9;9~FZcBO%$lj1
z*?B9W%iFG1vvZkh&}6O|iG5BJxDp*-u396}&GF`a|9#cx6(4R*mb;lfy>@TfkLUOH
z9@n4W7(MOjUdTR6u+JS3=V^fX3=CL~zGDUN_=n1aDa<oZMc_wxfE6%cJ%JMWaAvSF
zESD0DItUyxFk&=>U?Bma14h#jBp{$9mV@<Ito#L)WMFu(e@)CzBVJzK(D@tBUb%KH
z?ZJV@(D{&U`3{_je7!|bJAB<4x#~AlzrMa6T6@au^49F{I<dQ4z_*AqFkEm$oJF>v
zHzOlM<I(3|D%GL2=gc;!yuLnvLR%Z`6ch((#F2^(X6fry4zIF<jPN(`tth^VHm=NY
z!3<-19m~127za&YIWfBlW7Yukj8~NF(7~aEdBupvsDr>E10zO52o@3$nuck}Gbs2g
zBy%!+h+7NKxxQCXb1nme1G^%0vSmSR)Xt*RZ#R<HuZiEk?p5%%mFr@6r@y?U3Oi4k
zfg!3Dnll>8RxVt)u;cve$!|ixTHZb}X-#~+la!PcqVC?p1uGNY-ih;U3$2CE@aBkH
zh1Ws?072$r&P9#pIYjV)W-dodC6w?OEw@pEgJHpF&4v;nqjf(@a4=BV7ztmfbsfGI
z0A_LnHOr)1J9(weo<!gO753}v>*??A?tb3D%y%Nc{`c+wFLw6!_FBH(a(UC|bJok<
z`{jOKS#CGgwOcIraW}M<gE*;Sn^yzhg>!RDE_u$hD$Vk<`FJFz_UqM^D_5S}QTX`N
zi^cuhe(ZVn>{*Yrx!(4>WzpxXUazV7|NH)VZ~eVfCMvr>+xdK6_R`mAX1X-+UFg$|
z*<rB#eqFWR{y(2$>V7`8{CXw$^95)A)C&t7E#L3?998pfZuz~L$K|SZ%<tC}pR@n}
zXHMZUNzlECn-B9@KUvhRm$h_0Bg6ml?P0YJ(rL4cwrQrL5ScS;Pu*NLCl`%~N}G?N
zR5N|{w42LOl-{XY4bh2E&)D#NGK1^_+22R?>n6^cHOps~N#^O~*j*(jk8}!uzLDJj
zRQ~@D_m{=#XJ<`~ExW1eE?@g)+VQOH?BX{Yk3XAN{qE%K{Czup^VuK#eWZUH%~@bB
z!Y&lQpt}v~tJH5Os*ISvOuMmcPA<X_n1ic7om4lj`0(J%i;ItQ`}-vflTP10trN9H
z<8T}A?N=WKmEBVA?kbJkmUHuWwGJfaq2z^UoEI2xZM?cVe7XO8yJ*{c%l+q@n470x
zT^0KN<xbD28a=2&2(_VBXaVz<WM5z3mzS2F4(l&}d#m*H?fa*TXV0D;jiGiGs6TXX
zci!DyPkYVp-FWr!>+9?JmA|Vi^OpO~jjDMUUHEH~s`tIOCmC+9{a@v~N8dAhpWQ#(
zlV`$y<?H%?dKdpcH~5^{)11qjvc7Hf-FfYfT4wzI^*K<nZU3usAn9RR?*H}2w`E3F
z|Ef)eifsLRJ^A*O&Ayhmx8(e;x83G@`qt(5+E9@-Z}-dHh9sQS+y7s0%#HeX?>p#<
z%S#t7e5jKTdG)^je|6fqoU^%;Zr!@|<=x%iv9`z8gG_$@KlCZo{%w0o7v~3Y9N2wz
z<<6ZucfL|)sL1EDezRds)K)FfLc-f}^R3JC-1_C_#{Yd4Zu#fK;rkzVHna1edvLJ1
z`2F7R``&((&fjA=S<UxUu)pop{+cJs?|<BxX`KG7McA*RzD@`d;t(>&`0LlNmj8Y{
zUTw$RP<Eu;fj#4R8=vf~%FoZ9e!U*=-!Eso&Bm_&-=C6KS2Ug5`Eoz*tp9OXep^+|
zzdt`;-rHNv#xEE1>yBaau_gQV+3kL}E4%x?Ch{txhAb0P)6}C~qLRjGK3A7BTsZfG
z?*+r#8;4rCiw`ieKRKnn{*2}GIg?dxZb)?gcCY&Vmv?uqLDvdTdNTk2pL8i{>EQ72
z>9S=v6g`WM%a%Xc@wo3aD0?UOS*m$nx^Q8_!DjaKH#auUv@A|Dwbz9B3Q8_8Vk&7U
zd*>bhD+qKm=$zVbH&?D+ecIRj?iBlfANyxom*??Wy;z`f@}&CwIg-X{DIjNB6eLVa
z`TXpx<&Ou=pU)Vde=__2pEOWbe7p7fvsUrA6Oa4t=iM#8zxUL9)Qd&~8fUHIXL#`c
z*|g}qldR$~6Mp^rwddEX)i=}U*BYgto1^=&auO&M=USK7-TrJ<{%+3i_xtUi&#TT`
zxAWO7P$(Vg5S(e4-1Y-}M=I103=CEp_c4}OsdzsB|2Gz{1j2a1foSzZL>Rzh2@bnA
z*8TmZ6Ti=<TU`I#r>Cbk*Zuvq${*5$XJBY3d)aG#@5Gy%n?GL(_7AP~n!UO3@iCpa
zJr=9O)~@<B#q4F5_PP_3RK30K|C_%5k7{^Kp{sTr%Y~01C;$2Jap&J}w^!S-GHi>U
zJ8Smr*{eZA0~P7Ly}dhMty&F=vy_{gQh&a$uX%rEWpLU3+V3*eZ#G)~ezW=WL;m_5
zhrCx`zH(*C{XfslBe!G(hOLd7x@_69lGoRCYkz+`dtssT=b7hg)b8#sU;pdODN}Rv
z{F}>ym-~gzznqqHYm4T2yWelZ_LseS^=i{$KI@R$xYU1N*VjKisXqTs*7Vx%cg=Ud
z+2noo`Bq73vz!xs*6$*|O6H#W_4W1Us;{qf_viik@^bRJ*xg~ZVsCG3$-G>2H8ec+
z=BCup`IppmqqpgR79;mrKAW-1zwzy%{r~^IH!(9?mVbX==zOLv&L9(Wx8I$n>OF1A
zwrytf|NnWu`SrTpd0*>_pPxJXbb9<ecKMnOU;A^^udRuk{Cs}B-QhOg)xSg-UVISK
zkDK#)-EO_?YimxvxVZT9)b%y0v(0i(ffCJ3<Md@4HyZwazrS8@_nS>`_W%DEIzM{m
z*6izPZ*OhQ|6Q?Z<3_{pcgy3Yq@|5(eth7Ox7%}wJJa7R@6HVHb-BMTw6C&TdNy)j
zO{J8y^ycUDs(;;K{y*{R>hR}B#p8WqV`J?;H1dbk`aPAa{c=(4{=JpK%S+zgGX4Ae
zyZ`%pd!t{jdSz;EzC8Q-x}O*O>!w`xx8M7!_|}wOY4c^#+w*pQI;H*j>-u_-*qn27
zt(WiHXZQGcfBo_8pd%S2?dxjHa&KKZHGQir$aBg4w$sGpYYdZ*_1ygQ-q$Su9!Sr*
z?}0Jf^X~4h^K<{RJ#VtQ|G5@UVK4i#sz;sbMzz1b#8kiCy0#|r_Qt};$JWH|HnXk%
z=Hu(@d-eGiN!#jgXF|hcrw04mZhaNZkg)qo;lC$*3=D72bct#kmAtr6^W6Hr=ly-P
z#rG<or@p$fa_75UuZ>DyU71sUukz*X?fH6pzg&8={eE5K#w6FP>f3i^US77e{{KJA
zS1T45om8C;D#VJPo$;)#t<~H4WRgtnmy0j&@2{`>G<kkVZPx1BTQY<5cD-B%YPHn<
z`r_&9dv@CXns=9%`ycC*ojw2WoAjGI3X`uc4@>&_>8a(<CzCI)4qwkBX{55)z5m>E
zyYD-D<ZP{++jvg;S-+h!+0RPzy#4>0tIM~oV&xV~d2(Xn%j@gokM&AV?-W*lmL2~)
zO3iQ1jE%|1m&Na|v;1<w*|`4SpH=?3rL)cR{c3A#`)od);E^y;Ff}!Od2MZUR#ui#
z!hr^v!Xtt^pH7RmdZOMhEiGOA@u+zEi3y4?FD`a}_3G89i~V&brKP1H?zdan>tjkT
zx`M8IUTwEk=<~C)r=OghT>PMsJ?+8*$D5VU=Ne~RSRhmJpwaSikMXAuhxx;6lV*QA
zrM>>i&gb)1|LQS&ea`y*8S(u;j;=bNF}d#F=lRb!9OeT_yxe{NZ{DtwmqA}8b1z+4
z8El+zpaG;NZ};16J<{guUK!t7l6iSq>W2phL+4*q1D$dTYF4hYTO10C^26=?=QWql
zne@K)eYNHHJH?xi%T+%)#I1kk|DUJ_tHalybLO`Vxw!P|EYs|;HXg}Ivu4c#)f?&a
zD%0XBpH5wSFaO*eOIf3Y-+$lN&wssszuo4vv!`CK-~X@g{pN&&O?;n!ztZL9<(+Ai
z>eXlcZpWO;XEQ6GOmx5Z@o(Dsd3PVi^-tG}oy94v_T&IF{~1AdnTa!v)Av38eYfiM
zTG>zBFKmCkSUl6Nw(8x^=kqSrzxey(aew-!Cnwj|L~b?9xiLY~IPJ;p`~S-7J~Ycu
zsf$Z|cW0;Ur{q=p|Gv$ye9*}L>4>oZlzr!o&)ZBst+#uP==xRX9v$sAPCC*7O8GyZ
z>etT<_On!-9#iBAYP|Z)x3guJDRAJkd@?~NVuQkBx875aj&`rM+j%wj))vj>^Xsar
zzP_5u$jp}Ve((2l@&A8axB2;G^3B}scZ>dfJPvZ$&mYI_=L!4U6t1?H&U+tM^YQ4P
z5AF76TE*jL-2eNoJX&u5!#3%n7Yp0dUR+o>(<C#f{g2FZXMWo$%KbJ*?J`9k%Y0@|
zGQVGA{QBD3(?32wzPz{k`<GW&wLwSGrk$S``*r2ocgtqyowED=W^yAld)lEE&dA+m
zxp7r5m&%k}a0FGl$L+pte6#2CIoVI2_w(}d?)>#?wQ=gHDck?<{BcY=|IBjxzb|>@
z?QGKL6uO12i-~+VHTN*+YHi!^cZ~o3{(gQ#;^9pR2b)y>*B}1-?Y2H>>&8*>u*VOY
z`Om4_|2%m~o?X7Cpp9RC9;o?T{eEwG+Sys5Ur(-mv^M|Wg$ow~zG~+B`TF{@@yX2K
zl{O2h_1e89?d&YRpC5ljgZx(a_t(=8hxyO9a0+j$+4JGkY5nEt=jX}3`v26n>Wc^H
zP}Rrs@_!z%ueRGMbUn5_wmW{tznkgv&wjlgf4@t7E3fx-y|YU^CmUs4SWxovlIqs2
zTVGyU>RooX^!l8-UoZE~sGsCt^GG;yM?vD%bcO?Er>E~_WN0vZC4K*g8>rx3KCep4
zxs6A&cK^|C@$@q@3@x9}DK5GmTfX&C>(yT`{p)9~ulu?hR7e?BetOa)VfZMwp7H;!
z?DeVt{`{P2mKz1?KE2uTxDOO}t>W9~O^>g$Og`3ga{j+B%inCfohNCUb!FOnr$5)q
z)#G*)B!bEn`TswTSAICi4l1HnozF9^|Mz*manX|#Cg$ePx#NF0x%EhFylVIP`T6s)
z<#(sv+?<|%Z%^gT^82-`?W$*2|9IH``R4gLGf><d6_1bEb^5IN{W+kH+rQuM&#wqv
zyvlBO=$=ofv?Z;}azMLFbRT}O{yT4$ak?L<we#oK_5J7ktlx%wy}33C)ao+L3W=+D
z*xDmwY2+?jdL`^OD5Zn;T;%Qh`RvSW^Y^m*xu1Mnv2vwm{J&4rLCsuHZFCdVw5s{>
zVSBD|^0A&f1&4Vh>a3?ReZ*^7`7^SDT}ct_ofK@A3EAw_C4od#IXoewu##y~M}+
z{-1qzcDD5!am7b_tKaQ>{^<ZSe@Ly{>?hqzr$leb2wdhre;#Pt&a2>m^3~sEMXz4n
z#`{Ogfkkj-66+dA5fM?rRz^qGYJrVM5)RJmuyy;maiPQ_C9xh}LD61aw`3O=N2TV5
z2!>|XsY%XDJOW*o%z4ir|LkmwCA0rN^Udzh|E)b5b#Bhwt?TBPw(p#AvwD90-1+n6
zFI~R8vHpKukDRTPe*C^8$9kn7K7ZbR<w}T*eO*lEE;;#$9xWS_k1vYdT{goonXRa}
zcw_ndxIe#MumAD&di=%h`SI5TXa4-~klC$AqVdIxjE{><Y;A3G?(LDhyv%p9#P1&;
zlb7yX$ME3l>hKqLcbgX#6)jl2xOvkiqc^v<a>v*IHU0MPu6AMU-pbEzE9>ObQ&JZA
z&$nB#VnxHwotAlbceQeh>nT`RNT~bIYneE4VnvRxZ*NfUjPDN*v+vlsQ_;vMsK!@P
zLL%YxG~F3Cm79*-Xy=ztdVg=PSMl>T=K1#yoIA%?{{Eim{Mn+~VF@=krGEJOwbemE
zpg(jQZ?Hw*;Wd$)3mzO`{8&8Ky8M{G{oj^GW_GV0Ur*12t3p?ANIJ?@d3=g>e0=<t
zoSQ;Q6FJ=6+-BI-T5Zd_+ocz~>%qUjzaO1<Fg7wuNKR(1udi=uZ8h}MjX!ws;EnD1
z^2_|@as>wmv#_!rJbjvb)v8r9jMMpSY-|GJ;`;vn{{HyFLgx*eHwVwMUTs(Xji>h4
z7st3bIfjJ8ZM;8TE}tI|7S=XZJA6^~_jfB+t~_|Knf>GM_xm3|J3Bk$_BP$eS3XUg
zFrh)wxy`}fpTDiG?Zelvu61>GT3T8YCQWK`?G{_OXOB$!xj6@C7$z$SbtYtIpSIc-
z<Kp6yaBEBEh7B7UT3cE9<n4MseJTnG4|fg@7Pc;b=Tcc|2@?GI`T1h!c0LKK5{=h4
zia!4NS$yNh4Fz*^@dL;2U#$N2#xXKda+-d8U*6qaAZrdDJZMq<O$QWP*VaZG`<*@Z
ze*b^I^78U8udnk9tNR_fwKe<baUNdYi_3haTiV(Vojuzd>*03j@ZpU~N4fS?f9Eq!
zJL9n2Z!QBvznra;hX=<jv)rzyr>8$YIawVPlE-?b+k=<;9lU#YZsDi;`(2{i8!A2~
z^~hR_rKP2<d8{#IXYq4Tq|dM{Rx2qjjXa*HXJ;o@SXlVz`1AAgkAHrC{&kPGp5C#E
z%I+7|Mw?e23zo1he+P1wVfr~49yuF{<YPU8^2P=R4YOxU*Zq7derB%q^hB?pKmYxH
zuln!VGhs=|&M8wwELDD)?5+CBB_$=bCi%qGna1f4UcT)7^r>h|?rkwWJ-v)uTQu+O
ztL@&h#pKQH?fi*}i57K#EZq8JPFm?1J32ZR6c#qlpD+LH%uHryXXk4ZITTwaoafSY
zP;U`%;!t#PjNMtpx^Le;Bk}pn4%gSkZmjs2^yAmBQ<^iAICyxD{P_5|@XZawmB(kB
zX0wTli|^R6BjHdBCkGEt$Sl?u-qUm()6&$Gl$0L4dUeWL&&Wt9zV@r=zTfYxTiV)A
z87fADRJ^{nR!~@2*--NP`n0pNTIK8i2>SW?{dl+geZkL9sg}#9>=)GzJ8<ik)WwSz
zgZ6LOxMfRAcQ^Mmy;!dF^z=0m8<{vcIe8|Xx?g_3w*AYOl0W}`zn8G9v3S4Z!-s;3
zs;Z=ymzHvHa!yQkD$Cd`Ql}lZ=D<?#=^L`I>s3@%dfvVJ?{GUm2QTl@L#^DPsL#2(
zYpP?=&+OaVa+~)hu-o}D<iEIa{^*~dpQUZS9qX0;pCt52v$MZH|3gITZstqp?f>6-
zuyN(em0<COXM;}EzrM4x7?iE{?AgP>uxr;Yi;52lbLP%9%)X|>BW1$z@Zm!*ThH>l
zyGl1~+2Z2l#5Bt!lZnB@+xzg1jmd@u4;*Cd>tvMOdJ^VL>OFA4!NuJ@`RS>tk9c{^
z^6&M`G){kXZEf_8oyE&9l|G7E9lqWzGgEWX;>8c2JZUk{zXvLFZfr<ozI6F=;lDqX
zCi(Z~l=`TJt&8FG_4U28qtJPe#iIuYn`hY9+x`0by8XlnkB>=0she|eo4L5Tftu<<
z*QZRME)L2zZ*Onk+;@T}cg7)o3kwNFMa3B=nUj9p$+^EzcHO#lAHIJ-erc(9q<e~z
zq9SAQvonsX!`3p?{K@(I;o;#KR;8<su+5RRE^C=SUEFVu#X&7C<KN%j9uAMMRlT?8
zz@0lX!fHMTdL)fEBpzn_xZ~g7-^$wB-0gg_L9<w2Y`q_?rlxl2$`z5z%X|;dGR?lQ
zEjRkl&*$?WeP7wq!U76IX|tRI@9yr7bekq^Z*O1n`Wo-Yj~_EGE#aJ|8{H;rUA7?q
z{yq;+Pr>?Wd&=HMmAt<vJKH=zY}Rgp{5v}YzkU0*qw1>`3lrnEoSRKgPft%iF+s7T
zt4pZ=^S5tq-{0NcSo^zdX=KB`yt`H*;o-`9dVI^4Edy0FVQZsW&2n!kn3{&(;dE6J
zjERkX`26{Dli6?n+}&0B`oV(-4Krp)h=_@K={T@A)cyUX`Sfluqk@%{)T>voJbZjy
z9v|yf?K?Z$oWHNHZ%5%{HnZGYEjx>!AG&o*O4>Xxq>J@MXJ@B@fdQx_WaE)&D0_SB
z>dRwHjSias=LLj@x-NF>y|6Lay+_)-@B5uIv(5Vhoqq1B`MGJwa}E|JP`WwZFF)OC
zn{zwgjcvKJZ60g(%(X60`t#%Cjjh?@T-@BRWwvkHbZDw}xP(gb<Ky!6Q!4*lTIvld
zr@g$me0+Q!JbtXaJmpPmd%LoYP0Sw)6O)jn$?Z``j~?yl=x}&{Z|_sd{*~hTaS5lU
zXl7hpCHn3C{eDJfwkwjt!otmx#%TvGUl#uU{(kr^-i|kK-UI{&HkxK%OE^2rG~?2e
z&MV(ng|Ck@^zz_PY^k}G!DyujE@HU6TwPgBO-*^FqJx7Mmk0-L-n?1b=4JMW2M2$=
z-G2YyQ<tvCe|~<B*j2Lf%+coz4_>|MdcW^CU-Y(|iNQuk3;zBp&AGLuv;1SFuClUn
z&F{C{BlgwooHJ?T)LFB--rnAReRuSRWy{o-`Oa=@<rY7sDOvse+}y*LmU^e^*|9e~
zJlvjqa*`@2v@Yp5EI%9cL)N}d#(SF1!8bQIR~}!ndUf)*H#aMOebMBTu~=ZjeL>nh
zkEgh}xJTZ8-@T27hK61nIZwo2)iYSNS30(K%1UOh+b0_RozLHYe(2u4d1hq~9=?3(
zd0nLc7V84ug+ArJtQng{BKQ4x)XmnftEKfze6q&0<^J;*x%bPJ&YN#jX#|RcXV2KG
ztE*ky+>AVyOT4?YvsqL-%;V3yjT<&N1O*A*xqJ8FyLWo~s#k2Xtoov{%x9+3zv`2x
zPH{Q6^Bn~x!q>06@7#%zu`YYF|CQ7H?iVjI&dfIF_w(~(V93qQT@$-ojE|2`!n#c7
z&D*zyFE6Rim^I7DPpkgp$B#42^XDCz`xDegkd~I_kv8KgD=XVk@USV!_te_bCnp4b
zW|?><J$!y*qVmS7uUS8S{(SiK^mL1=FB(#&Sw{?1rMDz<?cZDdJ?YDfixwp>Cj8j>
z^73-fCg+2no}T{r=qUHn7>h~s=j$6*?k!WSI^HMyy2sSmSor?SsF^7#DIPWduCI@`
zXPEHo@0kw|4{yx7Yqc{q`R%Ex+B0mc&2n;b7#Omzt!Z4lR(G0iwAw~bul;p@4N6~y
zxVX4%=+Y`bdGch$rj*Vd(*Co}cxRjEADf~XtYS5P-#)uNd-iOo|6dmt`1IYoySpQ{
zW=;L^KF8eLTqkzdmUHPRU%h(u;menhRrk+cym)bjX|~v}@9+5^JXYi1wrv|I(YdIL
zaJ9}bO6>~z|99rJX>A7%INW=z8?`0i)OQ^Q4sPzlr>1JZ*0E!^t7Cuj@@1!d-4Dju
zX1PN4-#&j%o)Ge{?A;yBf8`}5Tdo+M+Qm?Nagpnz`p>!d7Wi;q5Z90Eku*+gcx*9a
z#ta1w4UW9LJfUP3CdMsWwk%k@_^^g*_05|%BQ~XQzAu!Om0kMl&kX;R6qTCV+QPrT
zN+qPFlh4ny{qX5i(5mw~dH47AK6sG8AisX@j2RMtJ|34BO3qrp^4{L+<l}v^JVBc_
zmcNe+2@QSt>FMc=`}_7@G4%8E+fnn=NJmF!L;n4JR?_b^x*M6<wXT+zwg@<N?77HP
z;=}>Up(0lnI5uxcJuL<*c<=5me=a+H)+{Z#<vu<>J|B+D*Mk~wU;BDHI~zMYJ7t12
z+q$~C*y<-PUA(xNU*7J|=}wXEwl=o7{dIR2Y;<*X{i=83U(Ab_FBOfAH#;U98yQW>
zQp$35Z9O7en{x5;WoK8{qx<K06kbTv{Nv^AE&b<Sa#q%=kaGXGH#e)_+gsh9dV1Pb
z>uuk-LsKs;^OgSc=BDuTb8}ahubDqz{@R*I<@S&+P&4rntH-80`)Z}l^Y2Y@Ryw+1
z>C)DBcXucM`}6Z_pKb9o9>2L(s_h|Nj^W|rw$<N`@Z0|hcz@%<g@BJL;;8|Vk)3?9
zRtF9qTzGGzrl#hO+TYt`f;8D~>9oeXxv@oU&*SCh?yfqXmX>DrBY(YrY`2*1hc`Ek
zR~`oy*)wKH@JJf5l$Diz`0`~+vDMKJ4-d1itdGym&VGETm3xLsrqD9~`F(r#*lfwX
z+~(+1wrSI*C3&B=RejAWd2>VX@-pA%)vL3ce?5Hu?CI(0LGK^Eee<U0#*K&_yLK(A
z|Nn1C#Yd&)k{nSnF|WOg1Fx@(oj73vLwI<&g{9@g>+$ue6Z+PkIpd=fv0=fv&#$ko
zbzbf_*C6>A509*sNc#DCsT2BiZyB`SU+muhDo1I>x^;aMCJ2<gy2APY=lS{x)2Fu|
zZs#}lI?=XopB)z$*OC6KSFV8Sn~d!2>yptiF*;u>Q-gOei17Dcf6h==RyHIo?3A^T
zv8AP@P`Apht=a4hLFUGw%UdqxyyB|)^X}#P`<4<?QcMk3&QHF*HG8>9eK_NR-R18u
zY{?A%`1scQMN7WU3tJoY@a$~!qSMEs{QUT=N?s_`#Z>#2zP`5hT!gl^HmIGbJ?l{B
zr6ruFPMxagPftrbbl`wPU#G}%&|wpL`_7*}efakF{G<I}zkFG+YL!-h#u?Kuzx`6b
zytt@*O;Dt3+qP{xzF)hSJEN)~mW_?A;^!yT_aCjx-)Y=UZ>TT*_{jCguU|@<nw)BC
zYB%;)n=kX7&1P!)H2T)&tgBjUqPB7!IQ~;TF)?w5MWNE;kgkWPrfL_Imp_lKiCYco
zjo4P1ELyZ^N*Uv?kB^T>x+}B@IN4>Nx*o&{$~hcAU2^X367B2jdvSHOcusC^Vs374
z*xIOtg^!P|Sh3>3>FN4~pP%`vsHq(~a>OO`-K?nWgH5a-zI}5mEj8Wu_gnOrcXy+c
zls^Cd{vM<b)Hzl6o8u4=AaHogr>pzx>p^X?ckkY1+}x!4e#dnE_@v`~vKuyUo}6s;
zZQq|y-k=We-QDHKPfS#<JU-XDoR5)_@xzA?6OygU)codjtc~8jsPy%<8Fsb1u2?7S
ztNzaS`}_Oj+j4JDNn<Z&*syi$(LPyggS0ae5|WZ1`>Mab5^ZW~I#RwfkZnsOmpv$M
zT3Qk=E%Cf?<;oM;@9*wfv#_%-PCq}d$mjU9-d^6iUoX|COr7fJ?d|<6qVMsPcYfDu
ze}8NBP|3Owk$US2BZH2v?!slu+V1WyziwT2xQ*9qE5qGex1@IN+{qiI1MZ_oHRL5H
zH@EZ4FUr5a?`vOgSJxzGrK5?NnVhAiU)gkb-QSSd9Ha}bw(mR(Xoal>m^pj4bA0@M
z$8z;M8xonr*2n3#hrIdv@-ln+`FT(8N-Rr1Kd+;^ySclY`_JFMPv`g<f^q;SCugbH
zcSeWBZoLI>ZWz9J`SRfL<I5eTWorDseEm9c{(SwfH?GIm^D;9tS5#CSxOh=8zW(pl
zIhQwHUFIu&uk+pAU8RS&W?z5s=n)e;JA03`x!<{$H;hb8U8ACAT}fUWwYAAZ<<N%2
z!v;x5IC$jkV$Qw1aq05q$q@#>!zZizw>360f_jvU%xoHWO<kpzeaODGW#y5i)%!nv
z{Ma~gqTsVLGn=okk5B&c;$o5C@xInp)=85mAMGzKEv>BAU%qUa*Iwga&)4PN-d6GH
zN#~D^+qRiCH8(HS+jQ>SxoJOtetPZ}9v=Q^-L$N%tbowask<}-D=T-NIUitees;F`
z@zvq$kMv)?dKJ|B_~`Uy|EbfbgIDo3MsLYz6xWaIkk8J@Nci>TWsvxar%#@kRD6DL
z-f?r<*?^cBow}Ia8WFLvd(YkY^r>j+&4g$vb#-+as}he_Zt**J?&RR(JJunnETNKo
z{^Uu{+uL%R=gyUF<B?P<)KOAmy1gy;a04Urk@HKJEjx7OO2|3Q&P9R8`mP70rKOe5
zTfJh%ftQz;2L=W*hKGl*oV`M$IdHLC;`@7hXP9P(&D~w8uBN7>qQY|T-o2hn8-sU$
z`19-QYXehL(fc1`B*o`>2gk+fZN06r8Z`Lw=Eg=|sqEzB#Ub}Y1wq}~eJj=qfvdMg
z3vO-8?Vd74goTy$;g^?}Z|tq!eq^qolxbE=-rZe^cXyS7^5f>Tvl7du?$6)<SM2H2
zrxDxp=2nQGPCGlRQ~bsCd!Aw5-rV;8ekg;o?6ktCpo;|sxLSWa>em18bb9=v^7r?G
z%=InG-^pCLdUfhMKMzJmMh|cA=Gn8QqqgVie*JT2S1GrprR9cg+uR%+7+#+!0*!XP
zd6T0Pv4O#Rx}NKFz1UZCrnB?QJviLXFJW6{^5@T=2={5T4;*mdkuYGGYhB*9d$;v_
z)6!>WBv-6jrFC_Y-7THg`~CL+IK;)pXUv?LcxsB~p7pagY%qB8^r`06>5awD&NMDv
zs%lsBBj7z#Nq&BQ&DX2pMPAD!TAUQu#qI4%KR@r_jT;fqB8rQPckJGMT2r#x%*+hb
zOK#_vmooY3Fw;zb!^VvVr|Cuq#KgqBUy_n~`^Ldz$JnOp#X7~s#qAaTyLIc<saZxd
zdV6{KWUXATPZ0qX8q(6zb8ISwu3o+BRm{Go4b%!vJ2$8E#*GLI3kwg~%R7tHj~qXK
z`07>B^7r?q7CU`w<B@E7dwYBG?{9A}T)eolI7UGr;rqM021Z7QetmsCHEXdfs2pl<
zPyYGoX;44Eq!G(>{diE4d+_+N^7E3Mo40R2zOpj-$HR8{C35DbrboACUpGiOA;7}U
zu6^}&+JOc}i^@+bX8HGYzJA}>*T=VL(ISJgHxY9zi``b9^L=Z2bo)e5V^mO5vNLe8
z+sC-_`P#P(TIaX6vg*a|YB}01?rm#V`>W)|%a;#duix)hQ?qBz<&DPG-*WEkEM9)E
z@aNB;pbGohxw+cyAzeq09dk=kb}TI|^_g!M`|8I1`v0<KW@ewdj?I}lbLNpW&0oKM
z?I~~AU;TYukZ!@2O`8t&N}C_)-@0{crM<kLm)E3SJKh#w-CdrqqNdg*pPiZcF>j8z
zv^2N3w|Av$^0_l-d>-X{GBY#Zvo^cGyWD@}x|REHZ%Aa$$<4jE++V&&)>@3IkzwM*
zi93p(a(#Pum%HzA#qSHx^PZoZD`Akp(8e#%7aSb?@zA559v+*@Pb|ld9edRK_x}F+
z{xfHM?tM3P;`ngZ{Jw&rVc?$3;M7#rH*eldm@|i`@9~25>-%TSkXTx^f7RByzf~@-
zt_KetV$##o6X0M0bv&7vnLz<~Zmu<GBx6nTDPI>C7Emkp@iE>Rvt}jT-&Z@ss#HtY
z=Kt(jv!p~sL>5$je)j13r%#_i?e>t6kOOz`%Gy?aNth9^udBN|F(Ki?f{nj^{nF6X
z{5f4%bKjpoHA|K(S+Hb@OICQ;HeVl3#g+;GwVC{8rX2;1VYLW+;#|FMotvX$;}1QC
zwzf8to6-)MnVNcWdpf2}5!qAoGpMF6YHJp&wzf8pq>;-@vFFSOHm9H8Q1`cLj%6`h
zYinz1-|N?}58u5js~x_srL&W>xh3c7l`9W^e0*$C`^#j~<jEgDJ@pO=30YA1_}HWC
zeeLb+$NJ^hmt2pmsj&eK-QCMRb@(vz-{0TUWrN?%v#Df?kB^^YTOIa@Pk3udNr^$#
zmkdx_<L&M3=@TZ*HP64-Veake?LB!{WLJB8dr;oAqSx1SfBg8Npr*!l_3Bk2;eVEW
z&0SqwbLP(dc$nY*z^z-e5`&!Vc(1RIKmPOcbHn<7HJzR8mq4-DFK>VBKqK?hDSd0_
z%#pdXzh1uf_czze%Y0wUuJ_?~zrU}xJA8fI!6QeOoQpM^66@r|bZ)M7yKA@D)!i2M
z+S=Uw@^&q&SFfIPY2()i2bp7bm+`)P_wK^w%abj)?bspF+S=+>tiIsH2@e^|B9__a
z`EIAD>8AGi`uZL{JKH>S(I$~oU#fS6m6e(K&9P`qJluBG`sKG16O}!DeUCmnI~(LG
zW_G@WV?B}{K0Z@+YP@}ScXvT)>Cw~E^#fyLb&t2aadCA`1dZTvaW(DTYx{o3_Wb)v
zhgvv2e0`tp-TnEwnx-b_zkmNCw&h6X<mOf$4-F4bKG?+S;p;m!LgA++Hz()8Gc%1R
zPMM<eIsdKw|3AX()~&1f`fBQ>nBe_?K5>IepZj&cd&>`tFjV~fw6x-|NUEhdXdw1b
zEBC}{)7tc6cYWyV?(A%wJzM(TzS`9$&)ZIfMMZU8x)ih}_jcH`9ZgM4Z|?3EKX>lj
zi|gy>&$+a5YyN$^JNs&-tG~UOXt{355>P$@wXrVcBvgHU6}n{k^5ko4B8`qeef~W8
z!voM*c-y5riYB_cyf<&&{CaP$mA$?E<>mgzk8}zfCLUt3T$-Hy{oUOiwZF~YH~ooP
zx^$_5nOWQP>EhdRZ>udY>3R<8({4y$OiD^pG2@dlNMHapyk^XvZR~UW+U@Q68?&$L
zxwyGKIyqUL!7lIJ(^s#$^7s8@yLIbUkMJg8LBYlY2OL1oRaI3DGM^iAjj!VSyVy5(
zb_Unv{oA*~UqL{@)^={7Rhd=Un~wGSetGSwtdEG0SmracX~G17FE1`K3#<7wEM2PV
zH{b58g{HKss%pgkI$Kbpx2gRl!f;_%X?BmaIbZg*H4}GvK79@v>|ttT2n!3FVN+Su
zyl;KbGU>HfK7ILeq?w(+;PW$I2KoD&ca^{Id-EoTp`opfO)qwr%ID%k=R3Q)xcX!)
zn>vNnuUUV4adGhso61d>_W9TT_`qnKe(uP5`~Ny0<&GB4IbtK5YHQyj;B?}@epG`W
zxDU&rIDhAI|M}M<J=XMepX2<w|3IP4rcIk(#RR{-wH1_+URRvCn5KD2R9yV=xw+P*
zapu#eP5Y{sr3@aSYN@%Gm6i43*;(m~j0{i~H#$CT+B7A5`}j<=y$Vm}uUNOvt+3D#
z)N5b3P_a0tu+T7WZ`IO}@@aqbH7>VlzQ4Ek@M8D=3(I_^C8VTI$;_TQwe`#ypQSfH
z^h~Ia4h<Fc^76W{CG&FCZUMz5byKHKt@!)Pbe3s0o3F3$wZa+NT3Ux5AMXzg4sHfr
zKDv9OW?<ZM|M|yu6g~#c9B{Ncy}7qnT3FqW<#-`z#O%V(;`ALmcP5^lWx8hZskt61
zP2JtxTefaZ%+2lX7S}&?@uJ|<r%yq{kGsm=a)Ij4*4B-ETIEquQ8zXww^uNqGfY1A
z;N)cWM@Kg^GBR@T@VNN-@tvN*wQ$oWAyZRRuiM}M-QKAJ8kH13HEYHUQ0|S`TV=|S
zaDJZc4C`{eMT-}M+UVlq;u2C)N=8PL3WI(I1O^_Qq8WT)x&QpC<7%p^iaI(zn(^ig
z8**+M<=ouFx;kvF)Bk^eAHI6k_4oJp!zWH~+}@t=o|vcz8e)vwTeY#z3p8vv2|jE%
zpFvnyn4{I{qyP52yAkd|8t(mat&0~Y?=7F9@Z|ly{q^zhT|!c)Oq}RA`6j1gQDRaO
zs9k>J_U+)~6Cb^}xVWI8pkd=i!`B*5gq{Aj$(PDFb=U;#UnyTI^T|Kp_(ONub^#^+
zD}}GzW!wJ<Un%?%cwDjN#N@48O+ih=9Xl*UL`4stIKdGZ7+6qN=2li_mXn*iG4ryT
z&pex%r6D_|4H6iNii<%5H6dYPUUOz=UtgDaq(cxi`4STw8|gmP+S%E8P0UUqZgD-A
z(o$0%Ufz#yx8F}X+{Vk$@b~xk<a>K6HT3n<=S*3<X_FDCQcOKP&1*M<t*!0f{r~c(
z6mGWh_4Nhy3FG487#b1}w>^A&dwWN3FDt{F8ylJH>grCMKAkKXoR{&qsV)2ZI$1V8
znT`n)1VqHd7J;hQ?^=D2AG~<cA!l2qprO%G8sfyE_+;{uV^$2{uB+mbx^?T;b#!+h
z-k5w`L4aey^5yK-*47pl77iLBpeC(XvAR&En(r)@MhAxE<mArQU(cRBTeH|uU4-l5
zix(W#)zvp{-gJzPo?WWax@hrY=Ire3kJ-o0o#WfJYuB1&!|OYX)3;<@^?FqG>fT=K
z*AZL?PoDIw@%{SxI)7AD)EZ??9#9i@iRa`a>u2l5?%L3|I3UaV+<E)|KC<pyuPpwo
zc>G~;-Qj*KKKoY|e=-*G+P|{66bO#KI&frxB2d0m2Ev)xXXW=7q@xd}W5weW+mes-
zwY0Z?z9(Dy;=)1+(=3sFKc7ikst5C2ym*m=lM^&^)z#JY;d}KAPL`(nEdif`%irI#
z{qg&^b7-h&R+jwoYvEyGOh0z4czZj4|IuT;(o>5Vf1RCezOn3W)QcA{7OYso!El6I
z=Ixs|2G!qk*2L@#(iC419T}PU|KDFw9hblVZ`-9yK|K<NPBk{h#=^Q$TM}kWSUY2e
z#E&089y~ic`+)`Dbp80Y&6|z6xVRoXeAt+JdRpR(3k%mIpK3MIQ~R%8Qc`lH`?R)}
zmVmT$_tVqUyZg=a?ntDjrmlH(^6uZ?-y_|Bq&#`{?9jDqVh4`*@-RHOyStphu55PU
z<6{TUpYIo2Ane4U_+Q{I<6Lk%X@b8;U7ekalAw!{;G;*6K$Et!W=UmaWi5)|Uk4g1
zeBI%bl9r}qW+qlxSSZlxQt{=5APW;C4-d}~;TJ7Vifh)cjdY*7`(QJ>vZ0}1YHDgg
zXlU!wrK&AX3oC+VOq?kAy2B^;#s<d1!orUJ{^PUF^A{{y)RcF3SLgZu01cPbVQV9f
zPuacLy}xVy@>}{QB_$;Z>FMfr`nA8l2-g2x=QC%{oC#B=w0!zh1e$(6b;_&8_vY=}
zhYuWRD0N8#RpmQ&SS(q-{IbfG{V(tAG&V9adbP*g(!ydv`uTbPzn;4~Um282z?obA
zt288SKoiQ%756_ZMoJzC&Za<!23TTx=q~HNP0qIJz|EVI(cAN;R@I!GqzY<MPntaW
z>71Uu2M##s#O@MlYioOPc{%@=FJG4QadUG|E;jnc!^^v|?r+t{V=S{~%>oZL`OW2G
zxUsujUraYjCGN~JpOVs2P#JP&mMOQ)anLZ4Ma2gNHNQC=44|I$p;qpxS%DdAL6cyz
zRwDWL_AnkV1SQ;a^K7;4?rqHu2i3>N`(%@6OzM5{A_FuI8N0izwY!^pTh2|TebR;u
zJ9g}Fh>n(C?ms_m&J+zHb8~YQb#>4%az{tU0nl25Cr?s7s=3^+{VscMo^AK>etBa*
zFOlBPPR>1h_kR5Q{XR3pm#<$p7CrUSiQ6N=u%Ym=Th5IQj7yg;)ky|*sORgzs@xOm
zub!Ts&cV;`?%=>6XII0~=%8>fHR9&er%yZ89b$JBINC(6S+%OG)I@F7>eYq6zvX^x
z*#Ih6MMNAF1QrA@_bVtUa40A+cs;}C>Xj=Bs;aJ!WUjtjb$g*RyG_-XjzXuhxczmy
zcKS*aIZmEDxnk9-re(|2?(M5RZ6zlh8XCHz@NwIZJ)rigtE;O32g{2~OSxraWHwZP
z&%0(gbD`&oOQ2cvjT<*U`dsw<oNR#%yRNP-XmJ1^AK#Dj_5TiAEpu7`N)UZ2uPinN
z?w{Ce<rjOUFlBL{vTW&`wuN=d(xoz<5CQ4ZIlERoKH(<oZuQE7*ICxx?3KkNh=AEE
zi_*a353g^@3}#_tOS-luGN_-OogFmk<h7GwW$x{52FAwDE-oxru3n8i9;i`PR`%lR
z>ghkut@!)vtMg<vUja$U&Q+_lcI?{q=<4e5iVqJMA20cIeRp|2kBo)DY_nV@hKQ)B
zLwD}TsQb@jVc4;Ix3Z<BWMpKdPO{PD$&;BUda%UC#)6_<L4bjwtE+26{(U<h8H)f-
zbA?y;_uE_afkv%9{Q8<LAt~vp;}E~U&eqAvX~NvOXU$g3xuVzgH~&gp@u?>Vo7p97
zDh%TGR4_8kur6Qs<9m^>FYm4G`TdT~Y>Fx>EvY_>8bAw4LPJ&Wu^hR4SvY)MjAKB6
zKvq_kLH<3Ph=>RUEv>G?AW$`P*@gQ8Y=qRN>Wha>psR|IqP8}-?`*TywQJW_h}W>Q
zvtKiuS^f3Z)E_cOj~#n--u{2fs#RK5-{1BA_)&4~qli;#sw${G*eh**X~~BDE9b5$
z{Q4?X#-?Jzx%2-k{{7kcW7e*cmqMF1ZCbE!;le4_d%S}~Lt8g&Fxa(h$pX(6pvi^8
zUtcn-?lxHYIR_pGRs1i(WdJB%Aw|Q_j$giqVN#DjEbc>=vhqWhn)83@`t|*-+~P@J
zUtJCAUmv}lud%UFLr-s7vC+3#CYeoZqqir0dvkNmVvRWs4d7ZDw6x^$v0l(rea+9O
z(=S}P(&C`t5E&`SCu5<oPkEP7<kl=vJ~^9?HEVQMtX!#RVj^;Rxqti2nUV|&wzjf$
zb#)ONlUN@wahYh6c?s10I(BDgabQG5$FsAuy>%S!@2|Iic6N6Ar%y%4JfAwdx-NBm
zoMmpnuwcvk$M5g&chAbwDk&{Jx<9?4zka&Ai_3!Y_xE00St)$D<<sFp875}t#H6IA
zjmgKEepJY@@k)iHuUWZL6Et=5zJp6yO^r?6Z_a^lZ*O1RQJ9>Po__e|&B#3`TRS^B
z4;?;yac#8uHb+oT++PH?nB<A@g;k;2Po6$Kc;EoTw{PDBxLO6cT3=jU9o}re<lh`w
zn~DINiO)YiJ`S2KKGLEd9UYyKm9?qwq)%m~rI3)&k>@XdeSKZ={oULjeL_wP1tzQe
zr^!z4+_cH)$noRd=Y4~MgzoLH@7Ignb>QB;xSBd2AD;;KsjJ!f<ve^;YJPpu+_H7+
z#r^g5A5{+7)&A0Wd+vv*sOXNmzq@|?QBhHO@b>ohjO**>{xCJpy=8LEaOMKf6`NAi
z(!A!(Ki)6j{a!;&gsW2Bx%M19V_yo~52_5zz|9d*?iczx`&Z!ciM>{RCE!NL#9naw
zWK-bri7v9s>mY@NEVv>`S=@Ix|Hg(yP=*c)4qmu+t#09(B}-Vs!om!UjSnB~7MD~_
zIezja=ich?;88)1`79GXTH@>fimqC<3beju&YU?B?n#RlEn+%)^k~MtJv(=Nm$j)7
zSnfZ+ZPh9*(8@PS<1_=mlh?k!zAh*y*Qf43kKxA-fs!8|9=^D}UH@^)n-?!%CSF|?
z8nLHh;}zBytHakH+gJO0!tB|nEmqcqgoIqNe)i~SH*9f$ukXaEQ&rnjTqgegbXs4+
zzRpHSNC>pXjN#GilXvdOoSkLL{Go8+uU={Mf=5R<D=I2B^sEV3wQ5zt>ub6zR;@a8
z>5@>dw0W9rr+^d3&lLFdq8+1_mR3MuVB_S;laIKF^78UtyC~As)x{MO8fut!MglYl
zTKnru<E&XypjP6wYhs|%e&x!>*4EY|M;w)vm9KrA5gZ=Qe!OtQrcFZrGlaQX4NOc@
zWP4ZM%Fep6AyLAjK%vD+vFghUM`2FJ8@F#izP2`c#hNuOJ9q9pVtRE~Y4){`GZuNS
z_@m}CgJGga%bhzhFJ8UsI^W;i%v|;L)zT~PBf${|X*!yNTb`hL0o3v&vB_EX_gATf
zmDM8O*=7+t3KstGo1U4Od1G6ybWu@}fUt0L-QQn^ep>bA@9!PGu+UjhK%k-U@v)74
z&L`B@uUf?wyv*m|$H&JH7S5^IyztYfA`TWNpBV;>?fmkf2!FiflX=z^jVDi@fSQh_
zVhhAYMHfbI&nqY@I&^Wdd!&0RX!+H?efxIQ{k7`p?S1(8adYP7WeWoryRBJl`0?Fc
zYtZsALqo$8r%yWv1PH8IyEZT+q$T-yAE?Qhaetrf>lsB4-@WU5^e8E2XOZilIa_#T
z8~SITdGYGiqcby&bryl@|0l-o@S>gN$<wEvZ$8YMHH*vC)bz`%tKK$(2hW}3tE#G6
zv)Jh2)2FRFc37mOq&P%JN7t|mv9q(^xN$?{E8n!OlMmgwd)Kh&i3dlk)0XV(eWg0B
z3)img-L%Q5<kc0=8eLG6&bgg$&0@pUyu7|IUrI8vvJPFl7FH7n8tYu*DSYkYj8%J=
z9qW-~Ha9m18IpT@TB%N}!{mUUSLaFd^YhnyK5Gsdueo$@>eKh&4BZayE#&_|ZtX2u
zTo(-LU!ZjzKsAAE>6~B4N`C|%UwQxO>FI{m-*QsY)14Ir7=BcgU-<U+cJlXkcMA#&
z6X#6mjoVwbaKQow{kT01eSLgAy}hq>dPF%`c9gyrTio(yZ^cKZjT<+fIDPu?48vs5
zqNgiYt}NKGL&D0+%4_F@9bu`dszE_P6Q)mRkB*L(kdWBWcjV5kt=XWJ5*5|epeBWZ
zsVOT1Xxt@wTMnr5y|yN@*);o_fuC0W%9SfOY~JjAex5C8RO!rod-;9)_FcGe;Xt3P
zbwE&1(~>1BGiJ`**mvs8eerqgBQ`R{#l?B;{vZSD#XfxTqNAsWXG`{VzR1W(P)}ga
z+_?t}Wvt5I^#m?<Q#3G`P#Urmv<7s~-n|=ZeinT!uHnA$_wV12m;LP@{`~x0XOR}m
ztvwB(od5j-Y+-?&WB$E8jx{wlE=q!a^X+=u`Q@ElU0J72ow{bR;ndl)yKmfxICAu;
zql(Z&Q0+f!meiWHYZXPf9=?Bn-fGbuRaMna^_HVYk1kxXf@5v;_Gvr1n_630U(Yym
z<;oQWOUuYdGEbjBUz~b++N00O`T6|X+S=CwpRQZ5z@bLB(?v-|UENth0Ms*h^!d@V
zXUD9T-MRYjooJ`aj<UB>Uf$k`Nl8kDzNIfOwU+v*We92QpRDfRb>2HFN=nK!OQkM<
zm975SS*FRd!HNOLLH)~EP>By}B|^*ohwie=6TuCNVDVB=KNQk(1hIYu9?z5jR~lDb
zWkKog=8DH2Amv%>*Z1`BFgP6VlfAe)T>oQJNoq=d{{032>nD1sw3~FbKDN+_+{6M}
z6&o5V%EHuGaWUD`le4F{7nBBcVs=a@4N)t5d#m;8>hQ(j?&tGm3l=bliHY6VQK-Dk
zXXYV`rGH9aTwwhB`}^^U%I-_#zJK}RQd47NWNiF&j*p>=sw!xQMyc7>4VyL{+E@EK
zAvgD|hGew3eq77?_4<=0O-e{gQi`isw`|!lE2-kiYQBeBxy1!!WqY^f-ad5Vgh$fC
zua}m33knK0ZrNgT%=78u!pFyMY|o#6<o)&U@9%?VaX|CvJ-xk0&$qX=J(``r@8Iw6
z?;~AO`^@w~bLanJw=lr^qCR0^VlGO8Ny*8ILY*I8TvTRgfGkUpSRO3%^XJbWf4|?~
zSot|^$@1l(h}^YnR;kXjcXxNI&zk`14vXu@Ir#hc$641;oHwuU#fuEk1mDBM?E)Mu
zD^{&alI`BPX_L_$t5Pm$^SmR6+xZzCUar^dd;H<~{CY2+YiG}%ZC$ufF>Y_wQ7gG(
z6VA|Gpki-#nXgUeJ5cqpY85E0O`1G8@_2HWmEU1-8tBWp0xCaNc3bu3Tq#@v>M4Ak
z-3FpcWp0AY5KvNpL^imm;12FEKsuPq^<G)D{JDQ)OQvv5O$}&R4Aj7HX6K(4@x`L_
zRY*!oipJANf1KO-Kr6T9<m3tp3lFY|+^ll$?2V1dfl*OiCr)@A^L)A<6y)1-r9p!k
zE034Izt`*9EvEUl=|a@an>Rrn_N=U|3mcQ&OI}^+ELBlcQc^m?ecspCH}m06k+!xr
z(8^HIjQLl;`_<px9Nd(8Iv^<Mkj2WH7q4F@e|>e8_tu}3+uL$KeElk#FR~~n<1-Ve
zL4V)1cPexU;lMoG>LbFHMMXsi3T1kFdlf~vKx>9MTAfPX-kMtKvuvJSt(M_KO<P-8
zh6SrvcMB@JIcSI&`JIS!b!Fw^;+imje*d05HX@>;jgKuv#KkxF9lP`U`}>I#CMeYL
z#_q3^1q~|%20Hf3*+v{sR#R4XuJJv3?3j|aHmJ*7`T5y~?KzogsSFGX44y8IA=}es
z`**HdrM0K_w-~6n$;{L|b?VfCLK)vl%>PwFWMyTKoxE}R>ebezOI5qNx&k61I_Aug
zNl8x!jRUV)Z0HDXx4i<#6sYb$;RepJbyo`iiGQ8lwy+OWL0kgY1fX6Yq;>Fl|BA;Z
zJm4B)Vjrvt_z*ODl#-U#Re%1^-6tm}OD<9B(z39Sn5^!9jNkrG!=Xcmtd8$4f8W>9
z!NGR&1~&)CffEyz3qL*a6cG~xbsU9`uU)%#WAbr6x0g4vE-&L<7rXn|Zic_Nwq|GC
z-L-X2@J7%Yj2;<Fp?UM>efadrX?NM%3+rO7uWg*MY3tUbz0&3&9t%5r@~bN=142Vn
zWxXGQ*179OZ+l`Jce{8>>&~5)ixw}I-oo(r)KqN)bMxuWT1Q0$1shqp#SWZ0<@M@!
z#qmDbk8f@ovz-L55@$v<><!A_#mtyJyIXxZN2`;BwDjh_r3OB}zMy6L1v2g1a&J3n
zh$P+HQz^jJx?#hH1lj(T-QxOP>Zy13R0_-6)qqxAB;@Au=I7^gv^w3md2?gm$upmx
zo)(mr?!LV}|MB5={tFi_ILx=J-H>pQiKEr&%lrHCw{G29lYHuK3#agra*qcVd~a`W
zZ{NGucA9=X-@*V6V`JlMf-^h2x`g6`Jv}`u{{OQL2@M4mt7qm|3Og+f$W*tvs1j1g
zFJ~h#UwWcPOZxeFjgKw1<lU8WS}1V8_WRsRes)U{T|Q7#A5>ODx`q?`e);|dXK6^Y
z5HcVMY8HZuf6$;YxH$nDHU@POw)OPzR8&<dX=-+sPn_kT5YWZ?;^W7U3=RMO{`R(6
z=l`}M_0yZ1#xwulkBW-Y(AAxqtaS9_i;Kz?)zzQnu3x`Ceb)_tNzhvM!)?3<CMHJ~
zxppUHWpOc7e0svUE%$aCsFikgRcKG}srboizMvMj&kTdcQjyk)Q>L&mXlQ9Q_4o7F
z)YPQ(iF2@kroU_!X-)y{7P+-GyVPvgim$)l@7KQi%qRJH-_c2`-U5PxjSHRIKlSad
z_^6~8v!kJ*fx&WFu+ElBM#UC^Pw#~azW9NL;{}{L4psmCW%}jo*T~}m5u4M`i}_cq
z`s>tQvt-dCrrg}zFYoWi*YxG&<XqTMm<(#y@7uTU2xwI(KWN3Ml~}QD)fa*J!V3dd
zOxa!ZIWRD=aoRMooZQ@_&yQcbCN^u<tTl@bm#<pIRa{)$d7aPK>92>YD=R}nTAG@j
z`L}Q1K&{fpDR01CE>Ls)54gTX#E6Ic-(`^af{yaRIiTYA>taxRLG*!p_qP`~Hcyx_
zgQLE_o}<<2#mkqTvdek)uMQ0fQ4rt=h>PPZEiL_+Y$tQvQ9)qAu3b@mnxf5}ot(@3
z=6037zP50~27$A)&D}#nMCQz$%gC@f?d+ketHUSGn|ID)<)5uNH-$bwKYzSSRC~$1
z*+;v@A778JcP%S3yS;!XBsBEk<;%jL?L-a=4ZC((F@P3&Jh0$<e7xU1B0}QIl_~G*
z8bQ;p7cLw)Z~y;{RhQEYgT$sY_xE3tu`YWP@3nXbpNvIA<mR-*)6;Yd%FEkVt^{og
zxVW=8{l~9gj}A04gXSHM^~s*LS``DDP(OBzjbF~@z@Ey_AHH6XKYZvAQ?HaMXh`MK
zrAq~0UIf0mvr{-NEe+IHFflQSIG(mBe0|)8EnAK(bZ%d=FPvAxfZ^)Zs{)-aJ(EGr
z{`qQ%VLvr{d-=-BN>JR)GRZt-#TQs`@+4?;cYDPpnTa94Rjm|xOCKNO{qpK6Xamxk
z#TqiRT28$`Gt+p(_U-PUpPh|#56rkyc%r@;RC1a>nGYU?14Yx<#dXgAqCxGf<BI=T
zz>O+Uvl}#JbAJ&yE`O@8czj~n%9Wj>+F=?`W844hSy@Rj7!*8kU~mWt32Cl-ex)y5
zjays~G+o$p<cJGsoWAn&vyQ&Lw#k!)L2Eh$mE9ive!stc{(Sk@D~ilZUxmc%trFGL
z)LgM@)uf0k<^TWH-nelCv;h9b&SLe~E6%8>sw&#p$oS8<WBpLr+?{y1?clLvZG}c<
z^K2@cK<mp7G%(IEPUpL|Jzu|cvB<0TC-1}7MzPk{*RNQyV!^6aT(4feTCrvg3&WbY
zy;9lN)+Eje*cZ3As+Ch%?ZK<7s~>$YFf}y|2@PfZ@#A|-fX0!JkB?tm6{<ZgaOR@3
z+@Nx}UK~*lgGQ2c;`hmXe}A8yA!c8V<hgU_G&D30Oi*;*Q1vydN6NIT&}-Yd`Szd%
z8=#Sx<Hy-!cb6TVZJs}2!i0u<d#ewFN7J93I(2Hn%9Wn+kN)_gbUUin{^`GSC#J(i
z38ee%S>D`RTO3PEO;4RV1zOcvCHwGk-{DuUUYR()$<Gkd`k5bae5E|NCS2M53p7jf
z71AEM6mTV9str6X18D?<x>KOaGE)OQgbErhc?FJC(9Dg8k(t@COG~{$3mdKlo={)1
zWC;r&AK!^nr<wvZjvVb4H>~)O0IK3SIXPe4+^n9IoIG`t{{D)OOlD?g0imHsr^nZI
z#_lcyEreRJa^=C3lhqSbQd*?V^DeOYxqwC+SeP2moGk-2sRiFY2dxu-acymM^Kt#S
zJra$LjsKIBj(&S_QTflO)A|*Eei%aAP!$yw3%sZ6tyydc+W+wR`T55Oo7pvVbz8S>
zGuu`2vPn?ct>gWtwQpdpB<K12K&#I{3sQCzJY>3a=ME^$K$C#=cim52xFF!>=4Mgw
zfZ=dU&fePJVt#&ppwa!Nrlt>{&)X}Tn~O6nSh%oJGk96T?{9B=f;UZ`Gp9#T*=<4Q
z<z*KxUOXsY|A&!5Lqp@h48vprY3b8u3dy_6-a4%gTbq!b-3{ufnVO0oIR5$arc`ek
ztCEgFC$oM3|5byQ;QaaV5!CX#bonwP1E`ra+bmZ=MC6EtqILPZJD{}>B_$=GMbtB9
zNHEC98-og_m>8MIEpO)7*UO2CiGh}&?ka!ZcjSl*gZ%m4ty@jc&9y#mp=f=6zJ2@l
z?dH2mU$;FwJKI@Bi19~7o|t}I&y*=5$2e~;09UZ!#&I2@-2Sk*FIXHlmIliCkY*KB
zK`CTN7OV-J>p@*~(E3Pa_r3+7Zh%PZ<42E_>ehM`e|;6YW5<pYh7%uMxOmYqDM<<B
z-#rx{nWUtoc2s@U>gw*^n08jG!$oOnObs7H?yW5c*G6xD@a9d=;dcJ!#}+a+kO8&!
zc6K3Q;i+{We|C%O7d$w?xF&KlTlTdzju{ymMMXss$CI-D{rL$BK{1^Og@51g*FQTu
z`?%GzI~LZ~kKf(h{k8A01s|wG{j>b=@9*z7=HItFa{Tz>;^*f+eEjI>;lbhL><pSz
zSsGWv$KdDZcVkm3_o2gw6@@wr9v)(4VPm`W==1)F{dKnQ?(gT1kB_gYtbDk7{l2F4
z>-FE=+w0wZ9yHMU-yhL=I&f=ic4B&Z`;j9qE9DQ|zIjv8(sHJw(a{HwA2+|gzW(u-
zmzOKPy_tFB$a1${se^|PGe18+KYhl8xkrw;fSOjI5vU!7k6-z4oj!m5_&nQc3AL2h
z7Zy5y`1TDn9r^9u-RS3kI9i?l{P}#IM|cxxq^hBT0W?%6t{*qWLVwq;T?OUk$6sDv
zE~%EHuBpihT7_Nv+w9JrJFoVn#qFtBxaGQtuhY}-4-PVemhijx$vD2gw)W$%uh}2{
zPPetSb#!(fJU7=`a(PNKxHI(w)WQZ&(<4{m=IB*8G=*G(q!74LP`mBsz8{acL&C!s
zyZ6g+@bDa28NB?%>-GDu{S0&q3=D)U3%_$G#>L(JwBf|0i&w53IW<*#;-pDUn>HCu
znLb@vSC@Bn`1-bG%hX<1_<(A2c78dR!a~EiJr#}V=jSclu|uMrUmmplDe`#oEBpUH
z`9YH-lE!HXe}8=iMIC6>f7#nxiBC^WUGvxwwB;`6?yjx(<Wm<eT*#Q7p1x%1(vN*B
z*Q_}*!!Wtv#RbJPGYp;kUWzogwXr=rKmY!M)?X|dnwke!1~1=`e4Nk4&23ZPVgp#o
z;)ob^Te5U%;-4QM85kNJ0-jfNi|J07K3)BN1Q#gIKYaUk?8U{!3zsbmd%k1lOvz1~
zH$Rp4VFb-LckAyvu($gAhRn-qotzxtI`iY)+$n($4h(L6GM$sv{gb}DxLDd39UXo8
z57Ucc&@v~VStgvb&2pXI-`o3I=Ka0B)^c_=Cln;B?d<Gc+}NlrXH(Ij8@=ty&Sh-8
zQY|elEN(AvEb?6O2b2j-a&L*eeEHI%>`lbn>t{baJbbkLQjpmd(EJ)C5<#6U#3U?<
z1FdFte=1be)gRy6TMgPrYEbv5qN1Y0<4=#Q^|Vr-v?Y7{ub(<`!r}5V-={O$YO+|E
z7^AjkfwuNJgoaKnm3db7<_2SZeLZN`1ZYI`>{-{mJiVl(B!iqA20woPRt7DY@YxC4
zlmOb?Xw~Kfx_WZK%9Wjs%<Q14sx`%b?(Qy^Fw2oRH_x^kG;RO>-d>)dP1n~(o7+@>
z>nY`FEqrxFlSkf8hLx37==}X1h0JMbX)_EGnZ)#BIzVj*$SR$lNm|oRo$`9}{JFBe
z{`zzLptTwQX6~9_2Aa8V5pWXe15JAFtv+6Dqpi(dRaI5wvm_#Je_ijnxz?ZMo?GyV
zii#HbEU}n0Y0`(o{PrLAwcXm1*?i|t4BJT&(3+$NZ{MD+j){+#Z*6TY@>wD=&#ty>
zsrU3xa{0HmXnJ{hJ(=NA7_+}lR@yAbVX~U<lDf*v+j664mh=6XvvlcFMFj;024APY
zyH|&=PkMT4YR1Jytyk`AE?c&&;^QOMX6m)fqkVjMUUP7%>gez!CMG^Q{_o#E4qo21
z#_M+MkT`krWI<`^)O4HHqW}MDTiV)`jE#j|U0qAf$^|%BysF!OOqwJ#$D+{b+0MXY
ztebb2zdyDi@$iS+`TIR>@>5b++}+)KBn+8$m%W{|>*e+5FaG}izGB_FG+AfGt@-!m
z!q>;OPM$10XYO1<S=ruqcXu;`CQ%JaUIc&!%N`%=HTr%2dEVV!r8A6Dxng2s67uuU
zTk#dU_sh9@dUEpc@~Y1J{^g5{qa!0I)kj1}E8Ez}fQk+W2Zpe<QAag&qvh>t8ustE
z2hF-po*ewVc9q!QKBX1`r+<=&Ms>o021d|cvqi4muVhZ2KJ8pkV9>@VdrDzu5~!j5
z?#|A`)qhS+)qZhlX}659CSPXx%^$1h%#q2+%si>t`{?4;t5Yotpa1*&JLBf2r82^r
zY|6^YHueAJe6J`fGV1B=eLBOV@XGedyN%+5O*p5<mzHilbKTX^kr6c3dEBLoYK5?j
ztZbxvfX33LOCRk%$;HA1T8*@6Q&3WmgF?f!X=0!<a%=W=Baf4D5fKu5_UyT^B2an8
z%$c5V57l(vv?~t`43scV<GHt|l37<*_r<GM*Cds5gSAs9Or6^L^Yio1a`JXHJFfim
znKF6hO3i;i9`k=x`m$n$#+HnWOwDY(PE}P_P0h`QwZBTP8P2pSc_F~V%L`hpR9sxV
zCI7zMtXZ?b+wVYmT4Q0&(j`kCyk5V5T7{mWp<ut9?V&d}H$Qy;o}U5agref&kEiwb
zYrJLpQu+BAXi1NRQ3?lW2f)(5KHUON96z_O*uduiS$(*2{`~p!pzgrF+TWlp3rvj+
zfq{V$yUTQSbaew`W7lqpXJI;UWo7Wj`u}w;?d{$3g*jMOtXtQ%f4}{?xz_EVi9DYZ
zeQVe1`pvh~{d!|}`TK$o4;(ElEKXQXeFU-?wAtgH;=_M`e}fi^K(<_*K6{oIbTC3$
zS=roV&}@80hK7xe%@cVa#v3<oJUBDcIH-T>^y!a3JUlGG)mr4YR3b}#q1SE09c4nV
z9vp0zR7qZ+etzDLijRw~BwxLH71V?L_3f?p^N_Aa>eR_|+E%Vu;o#)NRQLO>xrm6!
zhQ7mR?(8fs{Qs}^&i;D&wb9#;t&81#q(8g<-QC^o(&l-f1%_U`Umm@+HT&Y`bbp)b
zZ#<fsnjM{;6Mrr45z~!gadvjTv#XRl|K6U1o72y~`eRf3Yf7n)8V@h;#A(xxRom$5
zu01!m+rIqNE=fn{nKNd9I#?GjUp{=Gkr^~GoRX6A;7F&i*Zv<e3`xn!fk8n`%F4<j
zVq%Y;ot-Vv=~7xZ#WgNY4zx+_V@yhl3JVjXn%^9akAEg8I!~B5QSp2Q*V8L2gF%bg
zK?h0H{46>%&o=rMq|{dI1CNjjeDd5;{G9Lkix($2S(rNI7Y3YIx^(HrzT+XKrKaYI
zhgkd+1PazhZ-2(Z#CUyQZM9!?^lV`cmOD#4Cr7xasM*=g3l0x|4m!U<*1D_*B=ha<
z?VT4c1gy)xzHZL4Wopys%sFGFW_*6W{qv~pd1oc1rHk*~yEmt+i|hH*r$>Ef8ns@&
za^;DSukX%1du*;5K3%tBMaSk18y?Iu%|6yEW!e=S82GS_SNfQxl~s|Jme!o9Q$@dj
zdmDYtaArq$_v0&9ukO6K*u7ZYf8G-oCdTc>&;9gtbb2;#+4981#AL_q?fIMgP9E7?
z{oO)VR(4(a`+Ike^-5ccii(~)e!M+;a~f}YO3IO!uU{9>oH=t%vJt4i>gVd(`uW?p
zXOA8|vS@TTFxR56sk^iDAsesMk(Db~78)8Fu1Pj>h7G&^08hGuT6D1H-CsAz3_PN>
z0Pik<#^J$DN0{zc+iQQ9`T6_zgM1kh60+mPi;TX<7JByf^NkG*9ymEUNvNxIxj8#G
z-`<)n{#t@-W#Qvvclu<lBaR1ne13NJaY$(B&b86oi=IAx`sn%n{q^Vn+JAdzqqXYS
z|HnUG^K~>RWWDQXh|*h`BDrowLf4~7GZhS0Jl&U)HSKrQyR@#~VR|PO9?k3GTA8^h
za@x)*+8TKcD^{%GI`f{tuJ7#hoyN>hYuKKDwOC#(^S<ERZp+O!sqdZ_i|a-$*|u$4
zSigj!(}R{}s-Ba6t=)bvsQk^1i!1*B`SZu6Kga0h%a>9AV|SH!zJ2y=*|zQ5!{6W8
zx%t4yFJDS7Do>VN5w&&IFHmdu*Y5B4s{M15lNX;mapJ<S-|zSR_KRH=q8Z$m9yVvr
zoGaSl>qKnX1O+c@dk3w)nsu@JL1#xtN5_c@&_39rr(B;teG1r|=G%R@F={$!k?QMf
zYoq%89UK_I&QJ>}DKTl|k!;$r!(#3J^5Wvdx3*?KeEe8B!|3yb88bQxA0JCR-X{wh
zwPaWjvNGt$gJyn%{ChUtwY{k+DGB%XRL;6SC2Fl(uav2PfI!2><l~D%Rt7C{7fJj7
z?=PsB%e%9KQK4Que`^%4xVSi|6ZZD@c5$197N9--A08eq{PH4j?f(3mn^eQrL^PV;
zuL-`8@@Q@RemQ0Lz9W;>{TGC-Hr>77+QK5?<)x)BuCAW`fb(eb;}gk`UmQC&@%X-p
z$B)6$#s1pG^3v|+W_>oOs4hq5?+uGx8w;Pn(c0+ke4yo82?+|IMn9;OS5tHQY$q%r
z&;UBM$fhFT!;(j!^BJnYzq@Kv9}^pUab>XjmW+!|A5tEHmhQa0z5O`oaEvOE&B6QY
zYBi>M^~l@DebGpJesZ!ps4bn8oSc}R&Mq!4&T!!DZ1agTXLgF|Mk#1%aq;o-HL08O
zwmLO>P1O>8_5b^+soMI5N}m@7XmG{I{`)B;7aQI?U4_%q(o$_^@0scA*Xsub2Nym%
z!l@y`1=@Rh_pa>PsI7+@nc26zv#$J<;^N}+;M3F7P0K{JRa96&yZHF|#cjDjiK3JH
z0ysT%=rlyFJ@)eQ@~wUqpT2x)aat%~JL_h^>Z_nbF5=?kw8Gc%XlrX<RGuh#`t<3;
zD}$GBi3|3fZPvPV>(&<+&oKErU408WM`wS%{kpilt15G>%HD9OtE*pJEGQZc3SaY(
z2oMDd=8k{WU?z5vyRWXV@4p^jFKb=)=D^?I-vbvqv94u(QT+Ve(MLzSLCXpcPM&pd
zbNYD!AtBHLET^?$hc8|fbg298F^Q$VzCP#HmXk{Josaj+x9{I?4?0BY+1c6Ma>v(z
z_SP!9^&I&4_;}#ns?v*(XUyHR#|Cst%Kd${9v&VH6ZWrco<Co{>dTA7z`2V9G(bHk
z7IyY-xub7DyFZ^h71ySnpZ9mtGQ;})e?E1e>kXP^lBrZ-blIxt2}ey$&4+W=??LBf
zfEt4_F*4uY+-&ZXwa&V`J#ewxis0paNA(WutNg468aWZujY_z%z;Q*~-d*SF{cqmB
z%{`;9qhrO7$4n(kAYi;CXeEQgXYZfSxAQ*K|Jd2labnKK!j6uP7omsuDJm%~3Kx`a
z@95~#j*gB7t=nW~=ex3#q4w-7Q_w=9O`A5c_-9ptmY4KM8XFWn@#vAWl{$Cs97BV3
z`MZRJO{@_+3KZ4+=k>h2yqtU9l`p%>-gaq+uY2(6>FE{W>*t+o&7P!^czs=LlbXo$
z&FAe7PgHg<`1r`R<i!O>Jv}`u`Pr=8VjQz3oM9DTaC!gK$&;JyYJVkses(rs_0<iV
zH#0M&q@_7cQUNWGe0;1|Y-`}<Wxlfwa&MV{wgMhK%KG?N@8Jgro439zesMwZ$FE;W
zhue6?e*X&A5SgIDnYA^lY%{y(qzRKJCqFvb(a{md8`I$D;^N|x(l+mZkdCpju$h^e
z+uIIpPobjXVqb%~6}(a=4NeO|drLt(BHDPRrT$2IP6AE*&PuS_n3SB%=&)J)`{&zj
z5vTO-ZB9Geq~ba2ZfpA4S*ah=RXh*<`1sh@V6Fu-J70^6CusSd2p20GpG*c=a#iSR
zAA`9O%l+muF;rAlW!*J<^7C(estsr8y}8!q3=E;G!>;biJ@NVX{!=$BenAV6d_+mI
zv9Kihz67W+LX<?1BI#mpZ?c56yBq>7FVG5K*W+*hS43FN=fX~g+AAvpZ){9vUl+e$
zuPlHu>&gm7eSQ6$8yg&-f4sN1`tgm8$sPUu<{wiY?cBLja*x$U70-_DZsUtC&zfa3
zZcJA9FZl5x@$B!e-Mg)$w&(R;TI$^`d*;XvhP^K)O`aUMF2*t<I=WlVbw%doWe-p5
z??0kGzozNpVt3GPO$N~5F)O!N!pTXhpw`bazqwi!L6<LY-!N;z&+k(eH>aOBJ80tK
z;<8>&&p{oOWR0A!uZv}7xUwcP`1Ll$^Y8z!dVO&*yNc(bXJ=<8rlv04nd^~~vV?P)
zu=jP(#9wl=pYLC=ZHhi~<)t}!S678LJ1so0HT!zNA{Wk()nR8>=-&_)67n%wXi?*P
z^6_iWxWxJ9=OYg#A3k=mzgM~c{qavf>U2P?^_rD6z9&J&{XWAU95TnyWmX<~d3(D)
zpR84jar!w0bMx?Q#$T=6;un^93V(TfTfAFbU(9yZ$(y%sB|SXUDq)n;aqcnbkf{}c
zi*-J|`k-?D#&;p_T}mJA&(1Vv2OTPwmZtV^r^?}T=lDS9khO3Mv-qV)#Wcj3czSxS
zh}x>PXz^mx*-Il<NttGWHbUOmk~#U@V?{;9j^5s_C(b(jn;y0H*xu^zI|>;E1qEla
zWH*CrXr8N}pzP-Kwn{uM5xqU{YW3|&uI}#43^_SDTk?YUrJtY2Sn=`c^Ut@Zy}PzH
zx+*_<(~1=u4Ek}w=ktXNo}LnA(3hM2d^;y-Cy$D!Q>T#XmONqU;{uS%?^`c&EtvO4
z`tS{lPZ(&|#zG!&b$S9uik$0_GzNv#mG$xRvAaqdRXjn*Q-MwZ%elRcH*{49XjhO+
zzh=wk&BlGQ)@r*M{@&P_Tu@eK_Aw;oola@uPD9YpE@(1j@ArF$K|S|l()kPwps5<r
zxXPy|Cj&G@B+T>XJn-~Y*3#mVlapI?Tw_{=?a7+$`S;!OC;vJFTMN)Frkm2gJ>z22
z|98LYPo6w^XGcRvM~6>aI5bHHUtJXnTKd-1+<b9Gpfae)|N8nmXuz<bpg_QuOVqeu
z&bDdt<jF4#&zw8jEgrbsPxfMRfZ^vqT2d~p2SJI=+4Uf(6|rzp!sCF%jrlyuj{^cX
zfLaPGG;UacYOupMEJ8$bWGZuHeys;By+72#d1GI#bx?3HBST+b-;WQ6`9bHug{+AP
z{Lqr*Gv7`Yv={KgLTAIQD;j6njIXbYJ-o=Zdqd67BA>ZdSCzzGsH><jFsuq+zpnK5
zgy-MYnHa>y#Z7W<2vmQ6r(58&Htg{E^Zd`x&E5RMH}uh?M*`yF?d|;XuVPYU1q2il
zv_2owUa<dw_5x{rO-;_wRUwW(K0U5>`OnVIX7`-*;pg-D&XZKm%r-y&;JnAA7X5uc
z4zXMo6cpTBwS!?UINAA_W?o|1|L>Q!il@`tTU!N%gqjvCP}s41cemVG9Ssq#8#iw*
z^q#I4pfwfLidnOEt!sa(80aXyxV=@N;UiJ45CPl1n;SQ8c7A?t?!pi)P{Zi#)Lfmp
zP74oMzu&{WG^q2y0f&%vF_B+9(iW$lp7!GEYVkjR|AGpni;riB&TG-qH!u*`TlLkc
zolmwRwc$TFB9uYdy%tRNLdeC^zmFL}QZp)<mm`Cgnq5IlHJ&_uy3nbWD?meJ(Q!d7
zb#-?6+Ao43TB0hRmuk|UK6&D>Hq3ctNYdY5U&SsubG0%}Qc*MpS2nY5w>^3G3{;nR
zP0?U%bpox0nxYZNr0O-r;KvP*NiA>Q<Ous_*vZJq7}Wo(0c|;c{t<Kx*_j!J9^T%@
zA5$LP-BHL4vaV0gmdoM0=ss1?O&!;#C{Eiq;m3T?*2|g3=}A96Jd`la5{Ze8Wqe{k
zUraZu<!HBf@~0;!XPD*Ay5V@XVQGHMg4e}&1ok}_5EK-Z6<;7M2r4i(?$}|`(%PE%
z`PtbYzu)gy^b`U`$Ak$2EG#S!wqB1Dwq0akUG}EIYw4kTd#fkTo!h%9_4J|p_vO8o
z3h72~6S18a5V|_dH7QAH&DymW*Tq_EO!X>xeU10qw{MHwjk#^Bza5!pTRmawR91C$
zb<l<sucbn3qqmFM&I(9A-skG#!U9@2oSMp-pPvuX`u?75Utiy%<HD<gmU`_de=p}X
zMWc~V*2-aJ$fE4)>o#oNDr!5cz=kt)-rBXg^K7fzik_YVrJREY4`y6k)cRuM88&#G
z_}dMsesq`n?PiY})$l^B4x9xmVdUeKl#~OIrp9AYy|3V<WuR@mI|`XW2aa*s+uQH?
z`|Wm<y7Anvudh2#Qu*@kuJk08%slB!%l+kreblcl@tmyS2|C$_uhnVc&fF8>@wKT<
zFVA@2-j)kmG`ltX`YW4z>*MY3>?mY5G&EG3=VKEeA1`BF#sgZ=KYhCRscE{aKi6%|
zzHat0<=OL_o6{{yUI^IO+NR2@drzD^xp~3_0nk3lNh+XY78pK!c^SOoY8Ghj<bM5s
zTl2q6=6V(TUV5IKq`Eav`qQ6(E-o%17SNVZh!1ERdtzcDXp_&{=<T3t6ExoCwN&W+
z{{MDw-n?<?*Kmo7lG>Jgn{BFBt8+V_qP{-Ao}L~DAD>%6fx)Zm>-DQ#CI_#+3UXA4
zmT1|V8;w`4giO&2<pP;7#Y^?p_WXRo-P2xAo;R=W?d|Q(OM@OBm#=rp%hOvGwsuwJ
zy^4y84!OV?$;bN~mj)%?-j?g(>Djn;?b>Tsqjf%d$y8QWg6818mL57c*ZSj=lfo8O
zR*#zb?HYnsy4>EDtNW{q(}pv2yL-P};_GW`16GEBjw4+VwmNWcRjI~QFVM*|aeJ#4
zxtmDm$lSeQ!Md^VOY;2}$B$`t^g?@ag*VJUK_woeNq}lHunwq1@*c0LT8Xc&tdy`S
zS@9z9%%Pv3pX+`q?l>W`E@o#FpRARFf&#<gHeTngSyvetw&&eF1X}bcDcQ-)&bJ_J
zZB&!Gscm(2b&sTRTllJf@{*F0pvkZqhRFt1UotK}p0PG~x!=n>8b>c*4*rnxtXW!I
z#4jjFDDVEh+`!py1q22EPKTDRD<posTt43<ewTgC4}qm#Q=PWw-34vAy11CL^!+{X
zfwm7HJ_Ma$q2lTE_t#g`@S@6psr{;zzrJXGdv|wrDQn;LxN2V8>TfOu1qQQBv(>6x
z9tH&k2?z=@PW5V?tnSam@ao#y)s^>l?ApaOFQDhnotQWG_seTd<=S2T-p$R8?bH-a
z&>^y*@C{uZw#Z#X$=X_aclrA^uce3n{r&y%%gf-9H4%c1jg6pj$KCJuX;--{tPon2
z*V)+#+WS>eVF4Q4^O)4q#w!gP`fO}$EGR1zvt4vE0o3UR#}7Eynw$02f#dF2;{6lJ
zk427vs#E3u-o?_=?)GMVc{wtV!4)Z25-64?9zS-mw|DXV3k#hKKR$B(^W$;9TkO`K
zq00j_9z1-=2&pu>|H%B(2OSXFEv9>DsrPi3{-iR{A)39?=Abht7P(ix)CyS<@Ss-J
z+FCj@Gn0WUuJiiAgN)m@ZS(N*GJ3lp4YbD()cyGI@UUxtQkhoRnvTrN%L*5Z7)hDy
z{rC>ra;O=+4Adt4qT%A=a#RRf$clm%eS=07LA&ogCLM{N^!M=B*Vh*YtrU=x>)ZeD
z7dKZc)A@O}!nV@_cC9<`@YyrAr9qwg`~L)esYrWxtXF#0^RqucKUee=irSLV2-*-S
z=ey#}86VKH98ioGJYXm)DthqfQPb<|>$~NAHDbfvRz+@Bb8>PrNIfNT@iFJ|$pNLi
ztG=#!=9N5MFSf~Pp~LF1wV*!mzS`eia_4gpVF_xlfWi_o*pc`~`Y$Y-K*mKbg5%)0
z0VsavG{Jf;CCQIPO1``Z1Wl1WJw5$+10(Z;XU~=uC(C;8WO{a_Qy8=~_sH?%*->sQ
zLqO*n78Df;*~V==*qZ%G=jBFD9v+=b$HX2!e5ju&_1P@<mI-L8{dk{j^VF$RUlg7>
z_26JLXg}AHBS$*qj_QCmN4>bW*BV?9iEKXB%l%K*`_~#JC8a7!SYDZN^4vMlLQ00I
zUac!uXr!d4FZP<M1)Az@V&!(}PdC$x-^Vl6i*>43>+10JhfbY3^~nF#&*evsxbR3C
zwWznA1fA4!tY7~8@#pfNK79hs@`Ltq1_lP!#QXytp9Pxyvr8{|;JM;c-T%MkAUECE
zTWu~cy`iw@C?vJkLQ^Zao;k<;M*1<RAc77sf%_t$#>i(T>EjjPF^x~)fut|VkDml<
zh|IEo9i_1<Y_;yEkCugxSVFW!m6Vky&Y9CQN!9z%`Sbi<ONHiIm$&uy_P!82D<!_}
z<l|)LU7)T1pc*7<ts7|j{G&&UiWPUwpFh9h<q@m8KNg^gS5RU0;6URh>7^z)Hv$fn
zEL#pAtYBsU&CzCEU8Sg{#RaOQZRY-baE$dopZ)5Nj*fq_*%z4wK#hipiJ$_yv$GLe
zK>zrdY++@kWMClRwNxng_BP#1db`)p+Fkx$$;L)TYbsa$pO5TUvP|#Q{m!lVeAb+U
zheyPAUL@#nf(1b<L8}XQm%q>27oqmx+uPf-o}Zsz|BrKP6tBO(zs6Lri;Fo$rKML}
zN-C<VvTob9je~<@!;j-ncN(Xk%ZLj$&%fu=DWrN~p)>o%WX|R9RYI61O`Z%&Y%4;v
zK+CxqK3t2==bY!oW7b!A!=eq`p#~*nNP!_QtuFujSOvJn2N}Zq0_qKdVsCPPZ?cV9
zUm~~=`UFnrTh>Nz_xr+;wlZ>aTE?|Cl1|Rfg0iw}fBM|tS*-3gU9Xql{*S=Hg9kr+
z{3vLvCAgPqSLy3zKR>I_uUS;;GfAcUE)NR>_!Qv!zhA}sWGsUo>`=8gbNKhaJ}hk7
z(SQF>zr4Cy927;{a&H$sW>Qj8GO~pAkCWB?=Uutgdh6CLDOsx$P(65kU2I}@wl=5;
z4-Vc~`Z{byh!&^;v2*86Q2lbGQ+Q#BR^aZk+>6Rw-~Vt)KYaKQw8n*DLFno*&<Wvx
z{{DUV<cUg!Q=yz)O~;879xFn$KnplP8-CVCZ3Pt^8dJTltP1u1(%}SJ*P}I+3v`fX
zue7;>r%+8z&4LiEi+iifEv&4%<N{ah*kN%t`_-eP-3$%S&dyH$^W!522ZzJXqNgnW
z8f^YfSKosM__pOrhiHj{&hNf+CkAvV1?X^SPEN<UR;4ce8A0H9z>K5ktlxTJkq6E^
zu*iGPiilOH#Kh~%{pBwz&oFIuVvLWE|MBY=w2E@8sIWM6=+FkxDZXo?M9uT>iP)+I
zZY+9#&lc1i0&TsFi;HV~%*e>dv`k1_OUvsEM_TsRS69XUzR%T?%8PMuadA;9WV8Zj
zfSI7;bzS^^K863MAFT{t9`$GX(f?agPm6&f!J>cxw7CB5*6X09hAk~E3nDkCEjljj
zcU{y>$|R%V=H_%|3k!*>t3pAI>zOlWf=)#Og^Qd`2k7|Mq@!J+wE|PTRBdc+UHdhT
z^h%q9DvA#u3PACYwN<KD%Jk5Ohld44L|RTw)$W!HTu~qQ^2PP|`qrqmZg+Q;e!LnU
z@3=DL(ABG<UpfwbPzkB@pKo_`o^ADlpp_f)@7txMras(yJq~o-8mJNgk8uWafQod;
zV0Qi!SV0A@dqJZk&~}pzSP{6T3@ZKG!0N!m<)BOxTv7i1o@-H&QP$N}twBq@I^~YP
znW7UZba!`o``Wd-M#jd44-PQi*;(xVCBo(CvCGT-4HFJ9tO(Is+xq;xc#~avC-;Tg
z+FIBCgl)gRzt^u~(Q4aK=;-+S+gsyb`=;x~R&`Dm5ER_|OJ!@+S}|J|P*ezthOCdX
zZE0x%9l@WMm$&G+p*2@46KLb~t*zQlPEHSAzvj-)ez%d8!OqTZmUhmL9XmjWt9mUJ
z;*~NHu$>iIP*C8ImZtXR?c0lMqs=v@dVw}Jg@uJJau@bm7{I`A=k8rW85y3XL79Q!
zpDr%1{rzp0wruFysL*276>hy!opQcA{@Zeft_=C4a^?T^?fLPb12_8R?c3I_)!kL{
zl4)sBXP>Nf)Su^~;HC?xG9Z8aWL@lT(1~O*JBwHu1Y~7-<>lo;hh2fLJ}^q<vitFX
z`CxEY>6aIQD?+qDLn{1oHVt#<&V6RPGWmGlqT|M#?(Xi3#XsBD{t`Jq&vx?+?bG}I
ze!J~<-`vnp(9_dX?DLI3mv3xL-k5NZ$!DI8<k{Kg?d#X;Ut1U3-6g86WMU%n{r&yp
zx3*?;f34Wp_2|)~g2%^r85&lv*3P=JLa{>0NS&*dsrdOhSMX8!D_5=rtpo&3gPUYt
za(RCK%Ifg*Q<Nvo4AKA%*0xPMY`dR-y@0=qOGpW<bHelV>C=axJvA{qjdF5wT>6!d
ze7|4c&u{mGfsc=Gk-MSw(^FHO`{isw#m}zN?2C_Q$lBZ6gK}B)_Ph<-w~O2M-K?lf
z<@Me(sb4Ym)D*|>@9r)P(R%p!@!{Ck|BdPkPi@||t*yVGe~Oo?-JcK6b#aoNy@!uo
zZ0}X>M;Rdqu6Q%M2G%76r+CmfO=ZrUL&=Yyz(%wnLt7H>+vV#Vw&&fwuqM(N)R(%v
z%-7k+ho`2dh5>va-_)t1Wp8h(Rs>zPE`G)Xs>_v>K<n}~M7Thy&1<R9-Cd=dcdR~A
z|K*~4Yn|@e=<V-ReUsy&w&g^=IR5O$#$^3Wsn1WJJ!{*Rd;1aSfD!2A#@XM!QES~^
zUt9a|;loB%?`a)!p&g)`8#bS}(=K@W(5m#+gW37}HojQBBt1Pn`T4oIpw294FTs<i
zPcvnwt8lIkTPtKTH`6xW<&Xb)aqiO(m6DhmnA!P6ex>XDtZnb;cya#$WL{xWk_Ko{
zXm!}tH&=Xbfz~f<Og^6U<ix~^$Gzq*{mDiC^X<025Z?E%H~sv)hetYvKYaMm02&@E
zJmVG?Cbli-Cg_~AkX0d`Uo6z7&z;*lN!7bcZt;zcUnU0#3kwJCEK0qYEMg6A3FXXL
zlmKe?Zz$|)>OFi+Q|DW6VvdZNA7u3GhK1|FV~LMN#H5cKnDI$3*8mSa=Ex-P{rzrt
zK|#TRhlks_bvRfXKm#LJSA}|bcnH|6%mnQoTp9#goekQ-7Pa=+?)Uq;K_eY(Y>S*)
zxfZ#rXl(->+mmuq2y~F5q@*Ostao>JgBH#+8~`miPCmw?qNc_*@5&d@A^Xptx1XA-
zy}17WzZKEj^%x$!-~a#Et*zM;XUynWu|i|d_j}b%>ZW^JT3A4rFI-<2+q`(O@}*0c
z9z1!{;@&UkxHfEY%+8_>+qZ9@aen0@oh|Yv85g`~9QjiSuKR^t6{{FPW8+F%Qtwn%
z^_7*GSBI@Vv^ILXOTSXfKH)0R{=3vvQ1^Uh!J<c?wZ@?Jd@nCAckNFKle4XA>9_wU
zA+8rAVB00|%kPD!pI=*VFK?fWWzw$3uFmT3?+)I*D{KG%&*m3_Ef>l!6?u7aWnEd(
zD6H-`qhQgaW>C}g@G(s;P+0{DV{oLrI1UPVR?rwrdvCA^G*Z4KKL$sYa)0mPV}{p$
zets?}AfQmaCupgcho7I>Lzkqht3tU!b4r`j&x4v4pvCB*6W7}K<<A{`{vYJKySvNX
zBO+$J2wX8^WyD4$&><lVpgjOHjZzDKeo8$Hn!Qd*N$HUCUjf>woOgE@Xw@`myG26-
z0}BgF!mBGQK_aiNtORXk?vxAeFibwCpsLDh|NoEiy4c-pTcdi{MsHWr)#Wu#Ki9H&
zu`-{$olcd{WJ!~ZfQA1zyKr)Hu87}n*VNRsq3EgCn#j#;(cANmZogmGy*2xK((i9?
zJG#1rY}G&`o{QGF@`G9gE-tRho|9e(o{{penRNWPo4uXgu8)Nmeb<I5tE(?RaPH8Q
z{`1mzp+`TZq@{Jq9o5-b_~r3yFFASX%9@-fA2)(~Tl3Aq?azE3Tr!0iGH37IlY9B{
z<)-70A3geTD|`LS0;P?hQyZ5Car*oFUtByxx4OFe$dMxpKqbGsA$R$^JDQiyhpvtK
zYCrGDpUSE#B{Q?I;@juX^MmfViHVJ!IDLA1E4O&mn{3ebiy4;1YF^XzVjo1jytMS<
z_WXFzaqkCG9vwY$B;m$}#Eg4;Eahw}7!>|*zH{yz-{a%`$Cr9fHz<1I@#n)~{w8(R
z;!o#$x$jjx<^_!iL~qY?-JEuIL&ilV(7pykL&HVKO;$cVJze})dK;hYFCjHWC8esb
z(B@U3;Zgk?opF5gOqNT_i)(S&<*(4VVd3)McAxy|$H~sF2cPqbiv4bT@$|v(jW%{>
zAtE*R0unbCcEs^P6dVI(gf?DjgQ6!Vn2rkx3xig5m%O_Zc_1aJrL8UNpH2C@n3k57
z12=C*K5%)qGWGN{i^4}NY&;SQRU!{pg{}@;^8NOmJ9nlV^j1on<wz(gDNTTsS4qcu
zBtLxo*tmbcJ;Q>kudkxkJ9;N2CpWwI%bk>~|MSBzCnv|pV&cyeCr&i%-fhhQIv9A8
z%EOP3kI#AxI$BpezD6<2=HaHzn?XYXM~)tS`0#K$>%Y62o<h&g&DGAZDg?E6=GT1c
zeD?X&jQjo`la8>yaB*>Qg-|XoM+0^iJuUe0A#u;wYtf6`4ZY3G%s@9?%$YOCrQhkO
zfd8z^z5U#xtn*=0<{=?9_S23ZZ|iD0FRjG`E=IMqAi)F<M>cR7Dk^%v|LMn#ipgi@
zSPJ{jHaoie{XXvc`g)H^EzInE4=yZpj@X(ddL_#gG?iE7qp0RLr=wF?eNpJ@Fwg*e
z)t48H?(XgvlV`Rr^`3s{`gL*8X5a@0n*-NInO;=p++6iFYc1=GtgTYs)Ad|yYHXUC
zngVv0<uV*N+AR+1tzB6W$b7hsSJ-r2z`c9-K79Lj?M_*7@!_YZr-M#qiHM9`=-AAr
z5xHr}0nVczzkNIQ=xF!FrQYJ8QP`;C=jK>8AMF-DeEhikg_5M5J9a$y_VzYIgOIA%
zf~>2nK;vPcb`b;Uo|lB|Z0#bK#6CIOE;-vO(CtW@?xwHgzOb{fF;CTdn#=QZa|LB&
zdUln*?vex5eN$Ce{*1N+m%^JtO*<Yb6As^5CKoIJTv-_$v9m}OG<7BH?{?HTEKE#E
zNeR>uh176q>iYWppzi6@Q&V-nbvtOyS+ho`rL}co@N&NuF*`SbMm0d|5TvEMx8JMk
zR*(GG|K&?b&EK!rLFYu>xpT**Us*)D{hxM@OywJCEiUNDwV&NL-oMkq^&NELs4{0x
zO^(bjeemotD4(##?kHdctyOq<xP7bGhOL>G*-lT>-F$=9YkU6vHm{{l5fPwu$lTV}
z)+H}5u|lUx5>iuDt6UOgWMx6a%gg=eGcl}LyOw(ozxSji-@DGOUv+bHdh*>}rJ!|x
zS|KYIl<H_|a_UBJbNT=8uVLAn2uI;bmb<FHYRxjuZfob4KXm%E_vXTbOTDLqj?bQ=
z9nQCL<Hi-CtEWBi^vyppK@oH_*T>uW`xzP3d}p;(etxzven04ly2HClUkeBcB~ARl
zt?Khx^N$}MI<JY^>h(S?ZrY8LTeGjX1+6?XMKhS;Nq&lejLe$I9{Z{<89BGMaC&-r
zDjhdj`T6;IWgQ(JP-nODvzm>K&4LguK?w<t^z`(Lk3j`@5Nv=*B0xg~w7t5ixw%xX
zzoP?mxD;qffX&QG%i?D|pib(OCn;av-<LPdzUGparuOLZ<A=|lfiB~?s61)r$B!Qm
z9_bXmxGgt&?s0y3yPoy?esQ()$r^o3d9-xt(ucpkz6LF9l981K4fuomLf$Jt`#vix
z6Av^nO4w9vcu{!9&&7r1Uj6^t?z_FSyV`n_Wz6_Q*+BCYevaUFP)G!L&}fALcmM)2
z*tzgf(qoDKUT4S@W3Yhq@&%jI&x87U&y}{e^UFVab#*nU6W=Rk%B3@JYs&waEmJ2<
zX!!K>H0U^X(A`IO3!a63yXY>T8T&Q*+^*8sJ_fy&E93TBfli6JxY+$Q=w9O*(9r^%
zoSbU&&V2EkYZba={^u`W{`9MB%7N~dkTgyMEjBXGzsE9Rf5x@*=RucfZMng^2z2DE
z{{BCpQ`{D&oSbyx%$Xyg&1Si`%|MyB`1!erZ8<Yt^Z3&9^ZP+5>PUwms7-%ohr@p8
zWWeidYb$<yP>kA^!?`r5Q_i+(LC(!hi;gQRDQSI!SGxZ}>nA{`!Bz1jf+m6NYJVvx
zDKTYjm71ioFm`v@ipb4sSF%i_w&iphCLc?<v!ig4yJ_eB`u}?`*nj?ZJAZ$R=b8JU
zySDb%*WY}6^5jX-1cHyn#0t=v_h)7rgZ5d2TFC$IojSz@D!4&Wy)M?eQMfBPKfnLS
zkBY^9b{kwA9UV1dcbR~?5iKn(2X5bv{^H?entxB`@^b&{d*X_UiUg#kx%v6|yZ>z3
zvEqhB&Yb$B#}e(}aX~q7Z_v!_-2U{Jwagm||A|W<w?H0k+F1C{){Ia3dHu%1p2MK=
zZRP&n;DE($y&wL5zn^X9`SbZPzSPsxKt;87h12Jd{dKix=GjVbPCtKaWAbrORSVks
zcY3<M``KBh7okUliE4+5*sk(i6Td(13rCu^sw!(_WaOsfn>THmFlkcKq0S?jx3*+X
zyjQPVI#~^RpBBT1KUJN7{($zUfyQ)q=BB5&e|>%Zb1lcua0h>Xe{tKkNGa<w9nc}K
zpkdaOlaoNlI^^Bm)#^Lj?BJ<WT#Ss2paX7R7`A@=^r>n3bn$6AkxhSpe|KIQlz3%D
zAZXPQ=%%K+zrQ-=CU$hJh=8wT+M0b`@6D~P-o@2lUtR6!?9?pSf8|QZkt0VUzKAcs
zyxiYCB}GL{FNQ;2ULG`>S$yW+J-L7X{(&yUIy&dd<sF5OooX|cJ%x&jisBx*JoCMu
zT>AA@sD+i)tOBW{r*`~<tp(T!+Glaz{=ZCESXjp8WxTJhujglHXJ4{(>BBoai!G|Y
zXn+p9ZRHjR&9g2#F1pCMoe#7%kBwJKrAlP;XV8W`9UY#D6DNZ9_JFnr$jJ0em>_Uv
zeSG|v3bpc2PdxAJF843~eQ~in=mhza5|f&m8Wuk_Iq=wTZjQ|3jrm((>m@QkgOK|)
zWz71_%=$jwu($;txqPy*a0_Vs^05e?w7WD+-{Bh;w?Id4Pn@`LXKqF^dzGTLHn(;8
zJC}$E2|gJM25oKaE&2E5%*@Pwyjr~;v@t*D&JIEOnh%XH0zDP{{ry|o+7^L!o_+Xm
z!K&=p8A;HJFyC1wf+lk_U0q!>@78^LBMB;_-TUQ0W%P>J-DV6A9v$rl?W74<<|7H(
zm~>=CT08gor%RVF2d!h_YIXXeaR{`&1yr|8*NeTdz>yg=IiDAkAd{V)4Z5kY{N0^{
zTeGi&_FO%BcX#)q<4U0Xt@8D=?o!Y~f{qhwz-c+{EE5B0GWOUpwrkgJReN|&Y6)8E
z^>A+ay@TfWYnsjPRX876acJkxouFzJbn5fF`}_O3M70#u)ZB`bA~G^G($36SSju#B
zb<W{7Ubgp>XU^=rx;p&vnVH5DR8B4`i@CQUvH6)HXbs-0YiqkfOD1>3XJu)fn`g^y
zZ*TwR-rn0+l4sqyU;m$%pPzrv?{~Xz?5Q-4iHYI5qpqmP=;-JO8pQ@J7F*;u*NRC^
z^!5Aw|3T~YLC3;6HnSbPdpGv^)Y?;1wbc`>K2MlDx%uz!@1P3G{?7+yBV*%>3mln2
zJD(38Jh&ogY1a!uU#Eou3741o&eG0%@vCN22q<BIqW#H6(3o7$VbF4<$)G8i-^&WX
z2?Mh1=2+rmiDSo3f(J%}EplXXVdEB$HxzE!nsJedU*7JBczg{bbP`_Kt*2r7^y&BJ
zzrMG3cc+?(e%4mdeR`lhCD0jHldLNqm+Q~3uc-U}E|!IrRZ&q9bWms0a<ks!{qo5V
z54GOdU9JyWfy+=(TI%}z++4$=CmvJuVxvB^B+aod=eu|Bo`<imE9f?yU$56QGk_*b
zA0O{u>@(BIqUOg2S3NOV<20V6q$JR8*2DMi#l4P*ijvy1XU~Jzue&XapK;8(P}0UH
z%jG#~L&`}Z4G}ILS*t7HbtkE(r_D^T`urJm+t8;cCoPJeaBSMN3A6<QbSAp0Dr++v
z@1YJsWzg|*7n8X*rk)mSX=!<|cKbch(Z_4ntl84%J*lOmgTwLiO#Zx>1-iz@!n@1f
zHhC>Qbg-E{F*&(;UF>cp3k!*T`}VQUa|h3z?_q)t{7Tu^*&OSa=U4duWO@GnzhT9n
zgfqQ;d|Vd0^``Vs*9c_F%*<4q<FUrB_SXry)920|TNSz*l<V&7triDuVc3#+*~fg2
z<cSj}E?6CWeR8roYn|f%KTCEVY-UeBHAQooTwq7&>ac?c4>E!_YuwzFT6%AJ)z?>`
zD+>Zvhv}|~+|0%;repAN%A>tMpUq}y0L>n1P4)U#H?3&V9KCDTuD!Uk)7Yx~T@UDn
z#~T}&UteE;e1>7NLEasUEt!|uYJYukbZ`Kz0(0s2X4+8LbNtvv(E38qw4Wg#xG(VX
zFs$eS4OPNM*gfRU{2p$ABt_5)CQy|mCM5-GMlXopU&rt%-hSc2g&e%RQ~yeO-}>@s
zzFV(UYexr%imK{Duc=y~(;}<Bzgt`B_cwT|R_KNO_4Qxg-Hkr5WLf$1bFvkcm5O$D
za;2}XIChKaGB8Zni#@a@^YVtm$8Iv#WoMGiGJY**<CS`FXJ;|!O0GqV7J&|xWBB?0
zIOv+Q8yk}!zImfl;bmx+cc<gy<KyBHHGH7a!XGad_Zy_2lj)9V*jM|zOhbfACu$1^
zS1Z%)?fK>vSBt%48|pqi@vNw>UR?C_6bA>#g<CsT*8KbgT6Pk)E+%s#_l5HJ_j>Q`
ztyWf7X9wNWd3Lrr_nqSxKEDb**2}%c_I`+=jg8FivbTper=JI<+pn*$KmPmu{`H-X
zpw%^^ys!yi=E};-MeYXK=gytmQS`Ly%|~H%zXfS$XQ|CO@h2rcJ^AUWsWZ&;<=)-f
z+ijM6OTotG&Z4@Hf9_0BbOv2d!2s$@IypOE+?pMJFu3#k=kxZ5@86IA)-vz;sj1rR
z_4W0CzFhWKn{{T7&rGAEi}qj8S_9gBer07a_?nR{Q_zse@9*yym%qOUI;!u`;lmd<
zrFvgXp5y>-WwvcB`~)jsG-b^AULFRG_$Nz9tIJEf%Ym9Da}Fgwo?r)?pZNstYk*R~
zwH<}YpaT)EuZwjK3K9bCChQbef3)}eJz?8fHzPNv@q)Tupye^|_kN#u@Oj|rX}X}p
zsf2yiuie;~3>qo3t^Ri4{CWS^5g{QWfByb8%)4W;wsq08C0<jtA~vOTzA!xF7ZoKH
z6cm)wudc5C_~c}DwK*PhjvR5>yZvSB$H&JX_nO~3aB{Lb=v=3-udipz=HK47_UOLr
zH6M?PgC@eJ=|&^!pMZd;r>0JvHH%AMUtcF?hrqvo|1^S^^}N^!S}N=bAA`23{KT?y
z<;sG>!i#_I&b2NF4F`b^0XocY-?Du9@&lYlxp;VvfR=d(2r!tNn=|N_+5G+Y`#tDj
zMM>i{jyVBy-n_{Htu^@k{QU8|yUQQGeVaQ`{qu>={(f=Wrkfr8{qFbo)%NaM-`>u?
zE${BHN$N)a(@I3AE!tJ{)9BElL!fz4aq;#~PfvqpiuP82KXyBRKQ9BQvbnH6-kwL!
zM&kMT`QkPoPjAk@Z+CY3Ye`AT2`ZcuCr-2|e&*Bo+iOxw;9|F#RW1*~9S87=Vo>`6
zQh|JCl6JQT4+TJmwL#5~4TU_(kM|q^&Eh1(7Zyu{<Gu-W_}}ib+$-y1r9tJ#^K)}A
zF7Xt;m^^dtk|iorv_en4_`Q4Q&P=<@aiyU4^NESd+&Xsb4SllKk1qS$ADv~I&Ek_5
z2impu<Vnho-Me4!d9{5hs2jh?wfn-F$jwaW=kBfk4w_xKckf=)GUejZS64JaryiG;
zm7O?oLZjf$&6_uq#6R5MRmu(8b@QlL7Box(n%n5@<prHc(<!W;^yo-u)q8zUp-Gb_
z`IyKG3SL~@3f-U3)!4|)u4HE?rw%$4*QV}|1Zaq3ZS?j90U82QQlKN|7yHgOOJWyI
z`Sj#uM{h4^tO~Sn#B&m8vc;z6hd^Or;fIeO4?dq?uUF+W`P8XXmttI%3=IYE-Ma^B
z5$xHs$E80lOh`y*!h{J6N}tXH-7Uc_rsGgnX4cfybYX3@d86>GbB~YrKYa2e<w~vh
zbUjcty8lV%iXEK1ysi-u5}-5hCaHQa@}902u_Z&$s^kTz?Y8!}S>7Fq`L*99e|>$e
zo)L99U}Z?a%8;n~?O9i~=6>ILM0h%*S)XFgoF-5k5fsHQ?k7Q(%hV=INH13aPhscg
z$o$$4TgM@B473gk6v@)k?f<x^6&-!IDC5EcM$nqUb+Nl&+3ZU{FIV&H<?@d1ZqVw(
zrOTHu4qEE9>9}_Ix}GmzN`(DV;y~LI3LhVP_<sL?HU<}W_ru4JvukQ<zPPZEd6~~l
zrQdt1rs~G-61jKp-iu31x$oS$^8wxlczu2S;;OH&B6gLme4u&s#F;aorDmWJg`c~h
zJV^mvNO|+-P0;EN8yg!IKaIYvTmL-;9Xp|UB~5Ytr0w_Xq|4vk5wvZKd~}SJm6e4h
z!>m?WNompaZg^zRum306%*K1^&b=*}!k`;7Z`_F3^Ya<_R_e4fGZHtdf4gz()}!O{
z^+(F@*S4>X-hSxpS>EsO?mC~HW%}``cs!^=WA&R=Jykbmhrs9O=iP&XKoi~ql9HfZ
zHXU-Ob!vaTT<+oR4VvR=_!E17@7}$jwNDmSR!Og~t?lUParyr4F022qPfwpcllt3T
z={ae_^y%LxsT<`V@0UORe*gbI_kKCi3LO>CLr+dlX7yD&w<2)yg+;F1pu;~H85!C9
zg|hGL_^AEY;^QgPV~L<8P8W|IGvxd2CM~_Z034Cv&H`v}09XRlAwZS@wFXfnK7l6r
zKYS>F4mk#_z8ZC0)$`Ey`*ol}$93`h`?hQ`x%oIVGZS=DHmACg{MT1kohvFV*!bmm
zq@|_Tf=&eo@n2nCt)5}E@!Q+m?V!803m+ewVUj7d@7F8svl~G}3`s}3Ks^JUBF0^-
zS8GG}yMxw~OxKIO^ylva$7axOX$uPrj(I^njLdA{uEg8z_Zgn--w!$k;QIP_b_URS
zl<fR+S8lZ&4+05-t_JH6ROXU7ed5G{UteE?PP}29+_}BtW73}g|9*oG2zK4K{Kes3
zZmwH<DmT9n?C9vwX<PE|{{1zO1uLKx#fL%Hj($8Y&&*&|@}gnQ8XeFbH4gvQ?E)>S
z-dp{h#n1DZ)4~9UNh+YRRkyikls$!<oSl6QX8v3mwH17XF6i*%6aOb=pPHg+QUA~8
z&fU8g7dnG_iHc@sVIP+0&v#nr@cY}_kH@6*CHB03dU`r&m-wAKF~UA+aiFC&esirJ
zURfC&u=?r*70=>Jr#{<zPfD5C?^{y?GRw8!@hFdUJ6CgWvdp($GjPl66KI|I8)+>a
zFz?n4i(`qPl@6fc?iCxryo}_>679W<?>92DUs&wUzhwFH#U(E<X+&?!Y5eUmDP>~#
z&oB)U4sLGefPe|-9xrz9KlbbE>%#y4YK8sP;!;vns=mGHY~z(qdU0XltnUlGr|Ts?
zJvG&$`kM}DICHT(|G~+#<}F{Y{^re_510MzL91{?wZmLslbfKsR$g6Qty}h)>C)P&
zudiO*-*3OnXC@N^XmGTRSGo;!e>bm`2`E?s_tjL&SQI#XShB4A(GgBib9CRneb7av
zpwj2kQg6_moS@n<Cr9UA)ob00i)YPQzFd9M<jIAfpZV_jb}PG}uuyYD=X4d%A5W*p
zv-oQCtzWMXT37JpMIdOGu&7qZg+1cwDJcu;{{G6ivO*AaFHTj+<jCD+x=c(=0lP{v
zFD?eHA^23m3f?WXC~1MuOd}5;9~RKYqenM3CeN@aT=Z<m)~%*SMn*2Z>1IVmMFsEf
zSb`3axLbbTb!X92mwuI=sI|xB>;E*`|NC+HL9OoBC2|V?S$exfwX^cx-`vc;HhR0;
z*;%HH44?}aTR4SXdee*8`Q?rrY-aD>wSHsxf{Lr4_6aDML$pLer-4hEW<5C2$P8++
z9BSnT?Z<O*b?uZ3=9sr7#$x8onV{09l}ps6Ur7X9DT{;4d#)r<PM>)E7^vCydzrxv
z3w>}!E^-9aQ3MSbS%7Bf5;qjaC4f|FcJzV@{{0shyMvm%H}=(9OPORSRLMMaa&|U-
zzkZTR;*%2-qvk(6Z(H?+W97<~9DICcUpvwc-oG#Z^5shj^E??gez`T3^?|Fe&eE=l
ze)OoA0hAN={ri>8u<L%gcIc{>Cr?s>`%}MxcB*gKV9?Uu9{uFeAJBB;(W9=#)!*OU
z&A7OT_12b5W(LqmciNd5iWycLLBqzj)!!0MOi-Nl{mw*XcP55AckXORKQGrEQ^WTp
ze@f6&FVT>dL9Smk($a5j$pj73>?(V^s`B0(`+7M}PR<$j^>#wS!iJTfQVs^sx^|$E
z*|6qE0q816&_X$@(k9SCIkaY;N&Y<<(D>L~t5VR_VxUzqpvJq*{+gdgbLP%v_0zcb
z>gsC4%u6a~^X^={coB3ukCzvhjg1YcR{=W0_`{TC6Q@sCuWCtJ?9|FNOaFIJa4=}>
z@XSnO_hK7$b#_Zj%SFeGHSO|yKn*n>DH9Ic>Tg%}+}9A{y0R*i`}8zj=kM>pha0!F
zw{y??^7QrX?fDDq-6pAk?yd%{hAjE^Cep>t4Rk3uBO~LA=<Rxb^K3dF9&Ug9{eC?=
zL&(Y?R?upL|Ns87`fGz{bIx)9Sz`pME9RRYO9Zv)410PP%l|%Rkuyj9M`S8!SjjHG
z=kT%0MsQ-V2Nx~+A2y!?4II?m1D7UOSBHa6*V425UoWa1c4T(`K28SE@o#hH&gHI2
z^F|EATv+Jr+LI|}_v?i+sFS_@e%<9g=DT<8T2%P>*oJM}?p%KR_RX6wc_t$A^8K4q
zPtPh)`ds??neU1at(Ml-hlg6ZC#Z1Fn>TOKaiK#ePkL@PbSx_~>yxwXDtvq_vv0ai
zq|nQkFBcsXUKhK&Y)8>kE>J5;JA9pjzCOQc_O+Jf%hg4=T3>u@v8?>G<b~iFF>^hQ
zjO*)SK}*6Pw#$Q##+jlQD`i{tr6FkLm7Fq17Z;cRyr=()8-msj1sWQazl#A4kIC2l
zP;B@UyL*1U=Zx92yHA|(D0y+g@kxhM?yW7H&FuVc+w<;%`ge-XZ5e%2_2cEv&N6k5
zh?sG7&K2il)$jLy-%#-}31k!K=%TndInc^K%YWD7>oeb;@|iMg)~d??r3D2H3`>?S
z&FtHrfB#<6I=7-17Zy6j#~zuq&h67_{rw9{Utg>E^+l5bwDB2qnB1=N_k8Z|?j>(;
ziCS7(cJ%fhUEtUpur9{3<o&(a4_B5Q2es8fJB&cvi(oBx(54nXQC8{puBKjaGauak
zgKjed%_7yU-~Z2Qo=v4v70+ft5s{V!3lta{wr@8F4e@Quz0Ec6R83@b^y19R%Q9|l
zS@|OHjN5FpT+oPf@|6{VtbMBL>d9wknZCHOadE@RGlvhi^Mmg4+pxg^w4FI?t5jTE
z9Oxhm&;SINs8)wuV8=4w*-1Y?J<YhWL2=QdMH6Pu>|7VSJF72#XVK9|>x*<fg`~{$
zdXDu<cgwYQapuJ=SnEAq57cNhGBN^1A7~xZogIRpD@ay_t?gQ{K!JswJ^Id}8c>_B
z5#HvD+M4z7(o*jquh;K?@Z<@Lxw-k-jXga)pe4I<a&nK@L~`!!sRUhSur2?7-|z45
zv*%u6X6ThR2OT5F>g)b2=iD4i&`H*I|Nj(&j>CApet+BU-PR3%VrOj6xw+`3<unck
zko}+&&3^7K3SSc;SpV<m@@HB0+w<>ln=!d~ef)mCDwfS=$;Ws=S+e^3JJ+RNQw<Uh
zFtD((EvozbtE02iab?g_1_pjP8;8wlXFr@ZzaMd@^E3l!R~?@y>+d$CC<E`P15NO0
zahaXthIP`R`^P|&e80}lFa*t*Iu{gdxb|F>v7KLD%(f{q^WGjy(5We9Z*MU+q#ah|
z=jXSuwB($3uI9`PLuOE-1>GScAi&@`NkCY*d9izc($Ox_6KBsJ-I96Pr9U(1=FOX+
zRm_JD9RihzE3RgNa))u+nFB4H!XI8PpC5H+zxcoFb1aKNr^kXyR|e2JXp@{90t^$T
zPj5eQ!UMGIMaf;{-KVFgLH9)+Zs%VZwwhaJ`xUm3)mK3$nSFbAw_DmgkAVTS?;Ug`
z<?r9oC65{I>~IjTuCCUY>ZLK&%ckN3gP@>bz{-$_4GD~5IuQ+4rLPoJR9GAx9dn$O
zlolyHf-Oo~<kBf*<$tfRq~uD?%$${a@%wrb54W9^(~sY06BHEWV=*z}{~gmC5|B;F
zpk-8HD}z))$rZGHZ|+>#oSYn!<DWi#`tZ2lKI+U=RnVbFiHF<3gUk;OHZwk%AF%TE
z^!Mx5t+S~8wdLC5R87$7P%mC&_{^~oWVo<7-T%yNbN;ZfuoI_GgEr$mc>P+t!pn#q
zbSc}1hlc~#$JsI*cye;`#^UFGpxs@?my8%d6QZ@hza2d@)7Z6FO9nK`0vgh{cq0wz
zi=T)9ZE(o{lKdFjyz2$e4N7){DA3Lbh_Wq^siF6vy)~^|q5<3UVz*>p=hM^E+puZV
zrCt3ho*cZqq9zMp%Gg$kIQ%PqHh(*BW!?YqyC)~B7rwt|d-kn+zudvwx1}MKo1n$a
z%9YXE_4;J3+dxNE-q}&e@JU>p*#R_alXR5p>@&@24<7g1AM2B~o-l1%+qJdP$uBQ0
z1?^G{+?Epwx?M+D%}2m?QRIr?<$Rz4Ur;v~v<C0(t*xfVFI~C>I^JQ==X2If>LTiP
zc5<NGEOK(zoNImV@bCE)RXqoPZ*R~p`aXGkzUb)a9lLfho%nBF9T6b`njhL*{r%9v
zgN`4TJSuq11Ui(sUD3G>)MD6C`C0AI;lm4qRvKhpQUR@71Xa84DoRRP(_quRGeC)a
zneXh9cOO=UXmQtMW_iw;Gv~vDgUmM{*Z==(t`)i}<xuAltLkrS0<HI@rKT!sYMy*l
z-p;z9n7!EA+PZsJ(&;u{=?#g8+0ITs=J4;_q0G$8jQjg+SB0!(QuyDpe8UEVoI5)N
z|Nj0iZo19@)MH<?crj?d+$2@+q+44uK}(a={O9o~{BP+|^`6EtFKEq=9~CaHu9>xA
zrEhLrT;ylN(6D5Q%35LO)uF4|7z)bD^a|oZC&4XWK0C*(_%LV-_{C$#G-bZ|+JUQV
z@UUHB&*6QbJsG{d!4}|^0FS{9z$cJifjq2Z_!Hb$c(J|YWzgCA-{0I^{Ml~WCWgJf
zv&|-`aL$}LbHm1s7w=449JX4~6TC6rVrk{XXr8Q>p!Lei?tP$DRG>41;^O48uC3_=
zFFHQ^#4P6qLwR{QXu;2iPoIQr`yw}Q-Re47&6n#>Eojlu=5&8X;hF8AQ_#NOuRnf0
zzMfZKUw?{jbl4Y<wB$=mJVBM(pP!!%OI`%rxOIz(0kkfr=4TP8X*|QG(nw4%Mx!F=
z^5bKyt<$GXYdhXA|M=tM;{mI$iv73dR#IA2-wZGRLFxGVb#c(vQyE#=z{PI73=SnF
zCZN-hMYY2~Eo+U~U0WV_9{uq3E9k(Wk0;gVi&&KX{FDkBQQuqjRmfnb#P#*@*TE;J
zffm}`*;&jOagOg<k&uv(LH0Er8M_+L;bNe*+MxVDWr_%B%g2u&kNd&9gOm4_L~qY)
zoj+eb>)M*g2RCLICT}UL1T6{LmUA;{qWV{pj0+6BQYIJf=tXbSNlHqZFl!c<wzjr~
zl@-?<zdaWhyDOWRh*VZqM%Awm&;YHY0<8sUQZu&Q8pR9RMELj5`CWc*Ha?lGeG_z4
z04VDp-v?^K$$*w*&w=y@cpwEvKd9~p%_jeabqFMmfyVg_<)oo&=70Uoza6pZa63PA
zN4T))u{DvKLE}_cR)_OHJw4t1=clJz`~Ls^e*ebC<o2U6KYvg5w>t<LOnvtM#_sPM
z=Da`N|9JiR*p~}Dw3aJ9y>N`D*lbOXlcjw5^pB}2wVG!hW}oYcG;T@c6F%MRTI|)4
zB3(4^@r2LMCb)P`;+ub8zV6n$yWeBWAJ*O98Q=f<R_WT`p9^ExXNRv|zRQ08d3N~)
ziHF-j`-JcA-hOR%_{>Sl?tKglvrIA<eJf0io0IRwCu7k7Izi^iiHVDrOUwoB;(7tT
zxNpj>*VCp=ldvpO0o4U3PIye-!!Xxe@4|We`Bin#&Pblv)T8D*E8)tDK(*S(pky?C
zsm31>@ERYX+(Rv#pcO8l>EI_%Qs!6`GJ$S20-c1IaZw4hy#ido1<#mioDRA}bw&7k
zxwJDg7(FL}HWq*e%|Ih*Z{EHI^+PTix1K(A3bfn?)MLoHqES&*1=?w*_P6`l=jZ1a
zJ2tc3*pSG)DttX?I7m@lot@#qix(aD>wf#b)%%&h33MTJ?yW5sU*DOg8~y0Y%HZ{t
zfhUvl^YcIDzxes>cD`Z$J)4sE_hj4oWSz3Iv_M^t7Z(&kn?OH5J8Qf%o+T|M<-x&b
z_MiV59IC2z-O2`?@%;FBKdZiIdv7pk2iFaYS2xUG-LTMa2d#i^>kT&e<_j7zPJFx~
z8HD!8n1SY+&HN7DuxL$w{Gz>gaUTeMF1lgyB|rDpmXrVMy{4stlD6+`v$OTF*X>>Y
zn-o5B`Sb7hd#nEWcC}KI)qIT}C~X8);kUQvC;$HTc17%NGtluNSyxvr^qp<S!Ow4g
zQ##Bv`x*~up~dF(^H=PyeLdg(c-e`A2N^+YzSAX^{{H^{@!Re9uT}2xn`^bB{{KEk
zamjvWcD{r+H#UM|TFNwwg`b~)?f)5z*!krWUS3+7ad(#~C}jWteP0h+g)&7m7<A?k
z=(0R%Gaf%bzeUT11O=x?Owu{M>4l)i^^NBl7$A29fKCf>3E7|(x(ak12nRR!<tiHs
z3klH05N~g9=iPIr0(7VtXdmD--RKDuCo(dCu4<pI7YphXhOCQ;{NPl$Y15_+B`<?o
z+S(qSn``|8bg)tBtB}ccvyO1r)z$rY+;2Z&!UP7-NuaZ3ZL7aMv3E?ov;=$>0_cL<
zikGj$SA}STmT&z1{r!BsuC=u^=s=s_@AvnAdV2c#emOb0z5@pwQc_bpXK3BApYJwl
z&YYgJv(0C}x$N=p<mJo4^XARFv8QtLwa2l$%Z|2ki-XRMW!4vVUKo(E=b*#1)V29m
z6(6he^42YUCdq5&_Yl1CY)kU}70HiZ^!F~7m3EhvUS9A<`tOFqlH|u3$BzXbKXy@G
z+TGf$&kC&kS0ZS?=0$L7SZr^`CmI?SCgwF=uQzgYTH>1<8y7v7U~P2*?YwN`m1bf9
ztriCzRD5EB;)=-4%Z~k=q%!k~aJMKItCEt^f)K5(a`C%LG(jheo;l;gtZ&TcKhNgi
zdHer7Q@vVm+=zJc<jE6z$-TkL{i5ur-*eer_Lhm^$B!Q?YGY=IKc77bv>M6EN{XFN
zreWsHnJ+Beo`U9jK~pRF_t$;hF@L^1xGnPU$KeB~j}#Xc9^6s**r4V|!NuU7Hm{|p
z{@<ECcP?*wdis}_m)RK^88hze*!ZH-#l<CGr1&B;csas~0??7)vAegOdpvL6yr2G0
z3_?MtBe=M*fR^_D{+0_m9-!#ysSO)82-y10ShGe4w0vse!i77kzw7PUvu8uy->NNH
zSG~TNEdF>}e}BTKCnpPvik!T>x{iHZ6}tM-wYAYq(<I|=Zc3dvWy+FovsznOca^+c
zRQPUh^>@%B3uj+rt>@?GyRQyg3u<OB^PT<Z)6>&Z{>mp$oH%f5sy3^>>7Liu*DI^2
zxI8bEmzRHYXXoXH?jy5|QoCMosxnD0FUXPc&6(4*G5^ZO!Y|;}M2q`+gDt-G*4?m}
zb;E)coZUhBTN)DeIWm7Y6q;--<T?h9dVXp5;JsB}yGr({cv_Ucx{@80JV!@YH*jN;
zYeZC3*Sw^VxR^cP{O{NQ-+Qgt_a)Pp`*pv0_y76i{qK16ww!}sUtc#p=k4ozbXVzX
zP$QLjow1&onc0W$-$BPLO`1FzbP?u?5G~M2L&?W_9M?u|^?8(Zvp(J<uS<N|>(zO8
zcY$VEq|9<UK#MA_UJZTS`eLqix!4B3H4B~FL7Na>Tw5y*N<UFsvltol;`VfG*kEwv
z$PrLyx+%O%P(q?(YxZ>|4UG<Sy&v_AjEowwyG*LSzw2#iV5s@=u>DWIvy01@Ss$Ri
z3ZVsVy;3)Jm1;LNHEof*zpGT+#>R$c&nXMg%%ExZwIeSsE(Wc4m@#waLC_{EorR!Y
zgR1v5&~A%^kO{wDUTL!rXKkWDC!-%b=Jx#KlP4*Yf2!6rv+-`oy=}JlUB&*~+h$kR
z$KPjI-E;oN#^l8O{Po{VCe?rX`t@iVuQbbA;nO#7?mS@r8nlto&(Du7Mn&xYjy3XT
zpzY7Tpcq1rP2Ypy*!%@9zma2ePSZwEY<@Wmi_OW+&CDvELbiurfDZ4^zP9FI`uy59
z&@#n&%6GPAUw830h^qen4%97Vu-X5?&d5k;;>3wj=hud=7CUt45Rc{g3`<MPM9`@d
zb~P5D?A6i1(JL)8gDY~{#JO|Ve$GC-IsJS>Vq)T?_}$fCUQGP|UfHcDz*@~yC?&E@
z#q-43v!-869y&QW6+AyD3mWUXv8#0TEyGr)#*N9xl`JeGE?8}>c+BLReSMwlbiG)v
zKfgsl%QvO=Ku#K2!NS4Cb!bE4VbJ9@pgVKl^34a$x8>yMfNoE%SSn#=W>)d-jpUj&
zYh3&drLL|HKMu-E`|E0TA~&i0KWoEkTYKc-!Gi&xd%O;}@q#vTe)TQ3w6p{*-~#Q9
zPnh|Tm4yX#(kf^=u8miE+2=j)_x<Jr4dbo~UCp!OT*Ze>m0e$7UFA+pOe`oaJ`C#Y
z?JCJ+aBy>D0}W@3YKLX~VVe4{?CmYnko9q~UwE293%ib8JaX(J|8F;0X?J_@dO!W+
zBGT=(pbA;dtgjAKCtE;@*GkJA8MAZy(V{N6re@CzPSr!!@AovHoo&9@Z?2VuK>}#F
zG$A*4ZDAZ}>S>Mfo~)~@I_D*9aqE}sUFh8IG%Yn`U5w=Y+V69ZJ#SU<)QH_x^6$Rt
zi=VF7K_})G6g0HAvoG_RnY77#Hy0nDTTYISUd)aKUn~Cp`g(C+ZS|SC*4Gc5KGNOW
zD{6ai#o2kb(gzP71dSAcRscQtdHr?S+gl5Zo}OyD-g#JBJmc4o$Ni;p-rnAa-`(9^
z`23vgm36Vwc6N4bF>Wp{U!F}&iJa!zuK;RuEjr{o*GhDA`gymqvTe6si;0Oz*w^hj
z`R@`FLmQ7IXhS<_^ZcUapz37e|M$P{>E4)9$MDzR(9rP1=g)^HC^}!*o*!RPS(*6u
z*4BceqC;yUH-lD{CB4757jzNMi<Rr=>YN5mOeQ5KgJx@f{QkW-@9wS*Telv4e7wK#
z+nY$xoTH(kA*dS*>Z4EIBfWL)T3yiYUJ;R&DN{r&EG-ky&$IpT?Hd~dXjZ!T*%{3b
zz9spq)cxmyZl=AlJzxIJ*|VSPf0l!4f+tT7oIcHcdt2_~yY2s<etCI$hHbSOXk|+J
z`FWl5lv%*12wH(+8r1ZH#I&YdaK6kpQ1*Rw0~Gn7dbk~Q*unA&(5lg<4TX?$8&nPR
zOSgBuo*zHE)NpI}^%Vu6ZrRZ;(aME8<t9y<6tJ@>^~kYf&+2{6LQS)-Gz6_Y^5x~_
zt#b3NO0`0?MD=2Kr94P=QN4U`Z}nHJ^|`mVt*`9-2%500sIUlIAIIzNe*Dk%emUDN
zzqwY5mX?<P5B>Rmzh2(D{N0tR$FiVBdNTTu^O3Y1L2K=9+=u{O+H>HubxqxmhwWMR
zF2=6ye6oi?YyWo^rLwTGz1kD}{dWF--GsRheP^4k^?3gL$rI2W@#`~tKmPuBTpn~r
z(3UM*{>a;$-qd51dMe@MBvsaXhF^U@e|Z_)BVov-9lp*bE^gi}!^mlgX=!bZ%<M`3
z{`^$??fmoF+UUdQ&hcHmcu^|<)yb159S^thK7913N!GfoW1iNTX}Zw@!orKo%wP4%
zS}zJ-?x*(MZA0<%bBQM*H#DD`s@)E{gD-k}9z%n$x?jShBb_(4W{d0S=qw1)`goY%
zo+D0&Pa4wb>H7z6DYqs+7U}E#3_70T258F;C|ba+BTX4lB|B$7QuVsn9^P8=^!GpB
zD{cPa!$aqc>e*XX-nsE`{<rt{*I%#9y|tzCtap!dK|#U9bJJBg6B85HXY%gl1jXgb
zAl0q2n`UTbXJ>;JtIV(awelM1Ffq_l^?5dxNe@y}eBRyN9lpl?`I|R?x~2zsUfG%*
z4w?qr|M%PMTd%ifUq3cgJKP}cjD$(n6^@G+FLLnnAK#LB88l4dnBCdY;bj&FIUdhN
zb>2SzK!d5)rSI?Um416`>*d#X)~wO_^6sv5^tPPJv#Wce-Q3uclEF)M_Uy5#sHiw_
z{5X4AS=plHoFA{p*DI>2v5D)&99Zn$pOBu;?(gqk^5O#Hx^?RoJ?A{SeBy+CLPA0h
z-oEW!?mz$8el_rRm+m=pWO}5{`O3=5ICywmJUlqGLRYC2=t^pX!|mdRd=v0`*9rS>
zSbWg}XMwJ^-o>4ue9`{p=&^<2jiAm*unDMb13u@)+tc&lhQ!05vlrLK7suauaWG_`
z+~hp2R;B;T<bN4FJwJP@b~xy0@*P!QS6!QJ<uR#c%^DrY*FEg>8~$zgnyLj_;mX0w
zd$kHQUK+7Ejd#+dNj!Vbe7LnWo85B~Xgqqx%$YB*o`4J{vPGz0>t27@HFZ^dx98m1
zv!y}nmx`aA`Ey-JNC-5Y4?4u~<RsOf>&xHV5CokJvod(Oi;t?3lGeux$WHP=&Q10I
z>s;L3SKIa;xqkh6$~%X(r!Ot_{`#x2Bq3n|<F$_T<YZ7WFaFCLbpJN!l877o>-T&9
zE3h**78X|XX_!7;+^Y1IN>yLr?t+I*O3KQh@)p$9JkY=hUfdLU=tHK;E6~gdsDW~8
zYqm!GJ{wTmM=y3)$2`@T<9)IdCroGnU0M{nI&4STTd9Aa=l=&y%!4{k9fHaRiHBIg
zqc$On4;+KE`GYOK`CbG^$(4<TTR^>rTF_w^pk71HoJHXF#|m)A0n}?S2gm2b8y2pR
z_Q%@l@9#kOoPthPTNSE3MLXQ@b>*^udtd+g`8n(U`TKRha}Rd&oWFHTYLd!9$Wa&j
z_U!|=txv!B^S=K7VbJ2=@_Uu+@Av=Tckcgk(5j9HsmI#=9sb{LU}OfZD1H3kU^D34
z%v&2br=MTs+Aa3t)>iFnYa*317Cr>68JM8L`TN`3=AAn${~d4r`Sp4{?*_j$_5WqP
zrlo==4M3&pe7jokCZ+S%AC}Lra{?VhD<RRb(7C;9R*u1*LdS<WIXN2&9y;+znP~jq
znt6Fy;;%0+L6g_3!`6O^kKd5M2)bm#rtVL~kq{-NMMC}1)qqnO&d;+wd|bXB)May?
zmU`p%ZDxj`;9x~hp<Sh~+e%+wn|Ve5aNfN=oa*Z8pi>s-C6$1th&QL7SJKkrdV72O
z^(sFvFD}sGvX77VC!d>RDPfv5r7>Kp{nAozWgQ(JP)YGZ^N?=T77lJPodXA(*&n`m
zG2{O)(Cy5d)BRJ@)1TizdFSq3Sx!#QtmiXl_4M$7P7ax_A8+<@`9x52^XzQ%>lIcZ
z85tU&8Ii`*N3`Sj*)%mZUAdP7+P1T>^z}8+abwTU%v3Iz`!V5hMiRI`2yWIa&$wZ6
z9-MPU`f5RaNpNXt@d_OOm3^S>3+j)&1$R0jO;SxMv%WIW=^k8MmwsM}4c?x5TC7LP
zl<WHX`0(nzRbOAturAlLDu1VwHiO~i%a<KpT}@s~onm5S-n@BpVX-^E##FD0%F51p
z=_YgL&b_#+G&|?cj=(P>i>J?>+q+|j1$g&)>#t>?%NSf9AL|8eEBf;0rtyEJFPqcP
zCtY6Vs}a6V2DIfT>*^}bIIm+WCMF`Mr|BMUWM&Uo=)}4;8MIy<)cpqaHqOj2Y!Z{=
z%Z~}zp%uCcG?0{KfBDyo#r+>n>+e@EH4T0H{v~Jx@x#Nzm7rW6Sa=dVrjYUllpZ1{
zsZ^esVfg9p?()y^{$5^_j`zuGdrwmFpJNgD!0B+XhRCN|TeDry8+c`AW)@9W^G(s#
z)~-C>Co6UQ|F75jKi6)*H|gxzvrj`;he_5g5X`)~YO0KokWy7!AZWSklW%WtuiiUt
z?p$4KYwOcyW@bed6+3Fay@~t@I=ddEPf*#7Bg*U8lIZPuMK?F4KFz(o?WCln<foOv
z%b&3EN}c%j?c1l#>E~U}gHAs<k$r7VV70EMrsp&j&%VAsu`Q>5fcu3dpwXb(#eKcb
zM-PJbrhvMVW#HB<r1KF_2p%~Q=>rcYz!Sh1EelJ_lb}}U3rROkE2}6oW8=wp@7{fS
zb94IX=xsR@x98kcIzP`gx~#l>`q?vQp3ImbanZPSNA>r0Hue8%c6v@$+oa-I^z_u!
zrxTUkPk~lZ+4@>UM@Rqs{eHi=?co<GDJdt;ojdnwj%BfnzhRVl{=F%nlMip-xN%~V
z%E?J8CqY3n->&w_>+9>g=cRAqleJQ*|NHg&qI8bHty!TzXXo#`SZQNo60$C8>ncX^
ziH6zN*Ui1N#8cSP+&p|*YUIA+=Y2V;sjAzvulqf|(<!We$~60$$rl$TrA6j#J6~`^
z4#-|npf#22@9*!|cX)5#yxADEIzmNN6?6nzNVV1R*?#~2@4h{G8K|*yex7Z{^>wnK
z%aVGf%|SaS89>8S{dT`NJUu-@4YTX(Vp-RVX8-&1^Tmyg%Aj2ejLd8Y?%XN)Kda{7
zpGqD%n~1ktYkz-Jw6v6ruldOO>-&3t2GIPA-(0I!S?e-T4_IlLRO^>7C7{#h_~q@c
z{QA10^z}8SFv)u#A0HPK5n-{nw`XwJTlEz*JyTI#{rJw#;uZ1x_dRHRbYc^av9a;i
z>v1(8UnflpOrlCwXJlmj@$>n7K@ky^s;-MO4U^ekU0vM{y3Ty5_w;l1dyAi+108_^
z+8XCG+l&`<toM$f9?-@P6%`gmMMcn3fNSewxu<%yZrET@^Yv=Dgmu}P7oCSdS0VlQ
z_;^vegsil*^odPtzO}>#J%9D8i&xrAL0z4Fd;WbkhLCkJH=k55Hvn~TpPZcR`{}h`
zQIXL++v;VXe{4=aKVi<CoCB_^?x3p(em)hS{A-V-eVxsoy?ZZi$qWV^&kedX1hkJm
z=?F(}@%H@teV|j+4|svn05kVI(16hj7SO5wv&?c=eXh8?%ojAg!K|m0oSvTEe&a^O
zj~_o4xcAH5*ion)6BF~`@#E$*XM8}bC_x*@d>*p#NHDZIH6A$N06J*RYpRyieuXJ2
zoXh>@3T?Si5EK;j;MJ>D-)`O8TMel(mVK)_Jxy0oR5bNOrJJ&<D(m4k-owj$XHS?t
zoBP4f**vPALBGF?AHP=uYJo)O?_K)sR&@Se*2rlSXU)>enEDZPO7OdTduRXuI9c6a
z!Ba>{S^4Ad_xo4R)%Fx}>yycR(RpZN;ffWYAz<(TA$Sxx*Z?#tY#t($Gw0AoMDIjX
zLV9^Zj*J!`c$5&*nGso&etzDK{q^>s3QN(s?ZDNmp^x2+87^!{bY^^g#H#j}N!r<2
zOUpj~<X-AM{TQeMKPn#25s?-X6dXKp+O)PWUrOQ<coIH7Itt1wPR`DTDJKMO+`ipC
zFU16ub5^X-xc6a^z_Vx1Rs<|$@|vnO_5a>3kJ)a$Qi?h{JaetfL1*Gz?VD>^%$As#
z2pZm7P<rgFNPf(RgY5DNXJ?s$4k@0d7t0kM9$xePZuyG~3!86M78VwQ)@L2-kyOsm
z6ch|Rc^o?1<OMoY^~mw#$uBM}jOu@Xf4{t*o*rAAs$9Kcph0wWG^i?ldwaY4`FXa9
zsi~~o+}uZw9tGX3zUa9mD?2;;6#aO)t=ZSbY+ZM7iE6Fbdr*j>?(f%d(6WQO<@ZCY
z_lB$t(g<BOMe(_0FKAoH?QOZBMRKdd)`C`lT%6o;>h$T$KTB5Z*<&L(xu?r(X_ME|
zOBH{Azu$ko;;hL19XuNfOA;T8^nix*d%+z|P~FR#{8*$1)JR*NkOLYH0`*+L%`s?{
zfzC+;DFHR97t5RZ9lTfn|L>pr{@&iJ7I~+{UqnYnK0MgWZq;vJ@qr;MEQ~EC#YQi7
z7t2(y*3#G46b%gp=gph<<IU#t3qrIWzI&%vHP3OXcDUc-e9->PkB^Uoj)dB<b?en1
z)vYR?9-f|tPka`G*0O_^N95k#20G9G&Ye43?rm5Qx3`MvT4(vMFPWgJ+~42cI=i{C
zmA${mo1dQ#>fC^a^g)ZewywYF!Y!`XGJU!@=-79&+*_b66$}kWj<~$Jzh6G})Rcow
ztlTW?Rg#4S1VERTZk=uTclP$}=9@Ne=H1iN(edK!Ay|}xu3iQ0zuB;T`|%SKl|d7T
z9+O&*9B~0HMV&Zt;taFgSubX?nI|3L@R?!YxV~7`^Uzf7@VL)Pk3m~ew)Ur=o74I4
z?{Cl@Q=su85w6x_mdh&I%NaUAOa2dLfI48S!`C1C@bEC`Cbr_|=N_Jzs0>=@a^~#S
z`Wnyx{p4EXhwtw028}DWw6%53OEURUqVaZJ>~6Ixr%p)28#HG0M!FO<_6Hiz+XCv1
zg5ng^M}?0ZWh8+{>@{V;0}W+hwUEfxys;{DHE3k--o1OE6`{Ysy}h`nvUqE9JHPy~
zCRXkX>td}PU-P`bwl+Fqd!FpIwbAX9)%_10J<3}9`&(<!N|(RCzPg?lK6d^3bn_b*
zgI9;GWng%Ie*X1ews)uGR}?-uAz1U_AbUYciOcnMv4Vnv6YI}hya?|1Tw3Z~$!N8*
z^84L#(1w1{DFcRvhClzu@7%R3>BIy@(5{r2*w~|eDvQ6oe;>U`N7>R+l8=v1sva~-
zv}n;}qyeL*r_Y`xU0C1<>Yk~1HaRV1`0!_?$|fDqIV=%7i&Fo+Ugoec0JQ!Sw59G|
zecJ79x$6rjehknMiK^egmGQrE^~!&Ty03tWgI;O#w!M38LHlDKAMXckE&&~BdawGu
z?bc#j8yirE_37#9+)>(nn>QPSjv868K;dF=k5l0O_a9#K{*{(?7Y2ngpC~(cFt0R6
zrb_aSG^Ay_!U8swbK!IXC`K;!LRw4U0UXdh&G+_LPMSO!w3h-jJjMVzB_FgV`P{j4
zAXnVEbLR-3serMuF=*>_^6|a^t*IGzca<&_kF&P0kjRjo%Ay^%=ECcwzmCmpk_o+q
znYXv;f;L$kZs!O2q@b+q*gV_n2XEi<GJp!Wx<4P?C-1Zj4g`h%WOe^EY3J|v<voP$
z^RK9?s)7dZI(mE0{@>*cI=b@s?VaG2(^DDJ($YYq1}g#=gKl=8ZJy7>uqt$Q8)!%+
zZf{kSc$Z<-mkiKBea1a}?_b54?A*DtqoV^f`3@Nx{2yIcR|gvDpE+~pgVwf>=d9l=
z=;`r+77kxs9e#05q;Zd&ZPa64+m9bVZrHfdaedrg7F|(o1qBAsu`TzneE$EVM58J)
zN9OGfi(4BDzZ~E96Lbb>jtn%g??Q!-Aq#_BqF~i9VXbwquC4}MdiUei>h++tPrTA*
z3>E)O)m2nj{{O!J{{d(R+0ut6HuZq&Vpms1EiJG0_J_HDznE|L_e=0a;ht*`54Rf@
zKl8b9<A#E<aq#0E-QC>p?(9@fm?^Q?t@qOJJId~Tdyc89a_ieHpMLQ979l~wy;e1l
zeS?BiJ-Aw#1O)|ag8BDO*|Nn1bjRL{i;FjG-rNjYX7)V)Sk0Fgf}mbr?C!FKJ~NG)
zrcc^vQSm_mbfSy8x;l@f5zD%D>!R-exeBf|Pt0IpXBU52<2gw{OzhjNYXP2zjxC&i
zbl<{936DYJB_T06GN3@y;xprW+1=}W^e9OB7)V;=-OJ0%K_?&h&9ML-M*ZaJ)0MK*
zRX9PHy=>|00S)<g{YhWuGxL+wGzs&mUZD>PJtrlkrm~8Qi-XQ>7ZVd>i*h@*Cg<iR
z&^dxmPEHdhO=414SKq3>z<<7-EVsCxOHt9L2TR))255k1jMS<Rcdrg#4>}Dpe0|)}
z!|nX0dP>t&I4@qj*mO-YEHFO?bi?7~zk7a~+cD1V=y-AU5i97_6BifN6E`=fZ%jVU
z2fB6cz-Q}_?fLiR-tYO`cO#MMgRkuuEgoqz9?+4;hYlSwsQB>UPkdWidV2EFE>X|{
zv=<gSZ!CD|bkO@`#GlXN&9~ld(>cA#^S{xAf6D?i6g(&0D-SjMdS2S>-2EFCUpCzU
zHD+WkiA%fJgNs<C;De0h@$J<y1LgGP3FdisK*KKU;`j4aS644ty7b_|gN!Rzt~_z}
zZ0q91$~n2Ypwmh(26uY3h_B_zu=D*kf4%o4mg?$ipBV-VJ;Z&dl|)8H-q=%F+-Sb%
z$G_k2S=S0bU)*o!R90s8=<#DyJ%{sW&Kv;^@K=3(1xkruLYg(seNV|XpI&)6_r?ZB
zMn=X7DxB}$z0(L^H|N@CK3S`j2dPOPj<Ft{K4nUa*Ho>QcYic>baZqf#vCFeBSEL1
z_S^sCh@AGh{=kgs)7d>IJ$V1VUsO8`bp1}#bSb|3SDe>7f%a!^PWPYdznYVe@7S?k
zY0$kX%=*g7TdTfi?LGJU{{H{jaY-^iN;K}SS-V!zQ|Qm1KcGtg_3P8t|FRDryLbeY
z*1$;-G>#2gvh>@{+6)$a?y{gF6Ex?1Yh&Sy)QyFpf|B+1-QDJ(m4P#6NbK0X`|!=1
zlA!&spoM1%2bn<IHbLC8vrJw6Yu~c*$#8g1+K_Y8XvWN$i4P7mR{gasE-tpPvRagT
zdt1isZEv&VG|#=bxcK7wcze*M?M2Hawt}v#d~l!<bfQ#1fB@(^3<eJ$pCgZsc7t{f
z{`~x0SyPh}bTqI-ffg@pEx`Ky|GJKLiz^!#1bp~({r$7E;7vs9Vs<iFTU&!RlBJ%W
z<{A|xl@i(3+{~PllT+~dneWA5-ggHYnL)Rsu3xWj_wPqCXkr<ZEpBc~6_k?dI&#DX
zbiOUGl!<`t)E<wsvrH4Sv%6os$N;S#_#*SL;&IcX)922)#l*;f7QB3RV{>tFSz-?z
zstsWRjf#UNy8;3PK*a+;KflMMmebSqlMgnrMr=yq1l?*^|F7m^Fz>Ttz0w6mMc~En
znjuY*k&%h-?(F2?;<{8-^YPJ9&=Af%yV@+!lmPR5zNOJsRaT1@ErRSmWVg1q{_^4?
zv)59gxVX4Q&n0=y`qV(N_>K4CY4AjrrVKn@;Ub{na&SyvT>bpTi;nYlzj;8*N1NIC
zL2FxX+_>?FdnG%cOvjQXDlYEs+;P8t?cBN3abW;xxN*aV4GptrNB<LE%{^)M?CvR3
zL~Lq*iGXfS-%<FOXT!A*abGqrU#`x?#Ps3garwh%&-#ARS!|qfLE+EO=kssut=@jj
zFml?%$B&y=g{}s#YdwA1`Sdj1i4!L_US96c9g!UYT64KBb~mUdi`ts?^!|rMm7kx1
zwhn;S7lL-89zN{+B}B38-JMR5%gyudFf{zx-@j|uF7O)W>+9w|Xidpkvv%#rx7+W(
z%1Ktr1+8p&b#-;}n;RQ{{P}#|^*rbxE9H-{d1TN5Q2X}nvwEKfI_~|*kt3iphuGrM
zY>JADK}SG=HqU~(<Q2kmRXk^yWKLR8nzH8AwYA*h;^J@a><oVW@!Q+mkI&oxKeDs<
zInSP+6)6ucFZ?oj%9Iw+$@5Et9=^D^ctyxcp<iEKGA|A4bnBJsoTn}Vnu?Io(t<`*
zd+%b|-){CfGFn<@eBg)ziGUj{V3F0JA!g9o78e#co;Z23ap_W3C1qvM*{%!+K0Q4R
zs^6C^UCJ4kb*HGP$e`jw!jYp#pT^t#TDG(1rxECANYJk5M@PFSsBnUAymxS5sQUV<
z_0!YS-SaX;WMpJMJe?jdR<U`C=VUd|_92E3Z@1qE?bbYT=8VY`A4M5iS<nJN&}zD<
z{0h*4pi7o4Nw~c&w`qFU<muDfLCu*@PfwpXeY&~5oqd*RHd}FV@x{wL%hJxys=E8<
z@q87}Lr1&C<1Z^czPh6@`NywcNw2P~T(mrZ^YNQEJu8Eke|pC1;^MNt^W_z5@Tz~#
zX>;fHrk$Pj(&pYGSMJIGT90l_J`Ng1{PXpCyw&`Bhs?iDFmrTt1dTvgmA&Zz-Kib6
zHj1I4TU<ZsU=u57)#4)8ZkF{b6ERAn)_;<olQtAR^<rKl{QlnF>Yx7Yudc2ZpU=0{
zxs^*4blB>I2?C(gJF~B^YlWP}1ll{-BWoS@#U&BE5F?;)L%xSRxQ_-}snJ&(Yyqxz
z+P@q;rYQlAwzr_Z_+!u*8%W_I(Dt-{zh3JzH0<1IxhiC3Q%g(BAMOk1=iBpZYimyw
z_GT$AF0T3W@p%55qt6)v7Q6BK%rs&JoyONGtiGY_Z4_wxI0qM(lZOZBDk@N&aBi;k
z;aj(&zQiOJ6&FvOF=NH&A4|QbPnbM;^8bxfr%pZj$Nt-+mAe^0Q$3!OKD@ZN_|IeA
zs4bwY#$C=Db8)pYfl|WfXJ=jg1(#)BUM3~JV7^VI5NHX@+NiCNQT5;NFD>;34OG3l
zzFt3RRl)t5&%9H-RIN&1wSdM`zQ`=Bc-*w;<-NVuixw>cPnTTGhWFPPK#N>%ZRMU{
z`)%g6$Ds30c9*^7*>kD_bX0}0vG8p3d^gZd=lS{iRYFq*9334&oBGqv&+CodUA9to
z^M(zeCE2C_>fM(q>gn-uwK7#!RvH)^JIBPtEZqM@^Ob(1ml3D{e1Bj5@9*#7)mB$d
zP1XKcq9KbIlQ^*{=Td$I;|+_}L{MD7BCQKFKL}n&7b24*bBP@^ATnoB^5Z|CCAx^1
zl*-S~&$+pYHF%j1<A*<-N8)S0ih?$2?%87lI=}wMlga)p>vbe=ZOu+Mx_@8VET;ps
zOYhtq%Z~p3cCV#QAt55$^6&FSM@NHpi2VEa?*r)A>8lU^{Q2|YZu$L%Wp8guSQIFD
zP1Ry$04;<FTNl%Lv|D^}`1-h?&*klEBtTc=Jd>KTdbM`m-Ce8?etv&@YO1!fq9Wtn
zU8T$){xl^8@09p|AGFN!?(Xu(r>1Iq`1`ldohu8fI_2f%C-0W9RZ?<#`*>~i_N3d}
zayvRZFaDS%BrFUnhaxwpNfs@-7_q0qP)0@ubgeyTjbP~Nu-2I~XWp`$q>^~JjTbtI
zZUVb2Z(D9RXmsf8S>M;^3qbo!6J$ZdF6t+D<?ZwWkDwp2srcaV_VJS^DPP{*m6nr}
z`|-a1f47ur76XHju<*yb<@X=n+M0c1L!$FPesSO4sZ&KkXY!x7{~z;3L~9{vz8bXH
z?*75OQCqV>)BO)$ywIqS3_SVe{BmbiHMLn^E-!3&Uj8q9WeBMMD<mxZ@a0R+r9mK6
zUS59jGf!79Xtoj5$6FNM4;m@?Ec1KWiyIbSjBZ%Ctd|3=oqBF*=64a)u-Q=95jS_X
zdH$mp7Z-o{{JDAQQrOml#LLTk4UCPO=g*f1t&22DJ=HN!3$&&3*}1vh!s>nsy1Kl#
z?m5kyJzG0r=Esxg&bj&c@PN)tirro2xG-Ra?aSLCpi_TAhY*#$kyx{4O~6twQHBF+
zqql=@0@?HZUUf%jXXE0<%Jb}ML0e`(=a2sT_pfRC{yNaYbkP2)<l}ve44`BDE?fuz
zZA+`Htc=*2B?_ur!4uzE7M`A-FK%zw2OaCQHa=d(6LfIXwYAag>gwu@+()aw-z^87
ziwZja=k-TUVYP(c-`-l3zM9fFy)%4clIz~QO~t>z<udCU$$<{h1l<nCD{b~-PvOB?
zrr8%(2CF-A9}UtF`T2j{+hUJtsUDM#98*+M(ozF=06IEOa9CPdW&JVmnU)GVo;!M5
z&czB@hF4csCQsV`h6ywPw|4&yg-g>HFIEQKLR-bQm+{<u`+m@pS+Au*UqlxEC|U75
ze-|hkF@`ZrURwKaF6?USb=GgLbzUzd{oK+Fw9NIJFErj>geE<<0iAQ2arl^~l^Ne&
z9y7kZUd!%Tgsu*Ay}By&v;DSBn+|n}YHvt7%GJ2K2Q=7vVRw1{m6gHlpccj?Rqq8M
zT8gKQw&mPxnq`{3DEs=lMd?zl>F4Jq{{HqhU}Z>0e?L1z$cg~RHyVzort9~&w6K6S
z59}^`duo5A7w9<O$B&!m*;YS`|B;@Wni?b?-7js<2f9%{EKE#CSJyD{5DTcb>gecb
zm^o9j>ifIi%FoX_=VcmLT3UjZxSyP?4r=^<d3~L~^!2sYwQF_d?CW|!lU-+LnSyl9
zpD)iRXS3pCNp^6-%S%g{@{OK6dD7xNT~D%L;z!VY%L`7o>`O~LCG2W;96S1)0d%q<
z3oC2lqa&Sa)r`M3rJm;6TM4>yOjLe8WC=k^%QC;YQETM8d}kUxHC<y^cY3=1@i~^o
z1z%nSPTm`A`O<%7ND}De(2I*$8=mL){r-I3K5%1_>lCd}uMbvQFF{%L<Ye{PPhyLI
zmS~iwrKN4yw8`mspDgGas9mM6o%U}Bk9*9u0M9T_*muMH%dU-u;1%vB8}qyRdYykI
zJ-+bz7-ZAq#UtRj19g7a&(<{O6I~Oy*lojx4F~e~|7`=EPzdQ_G;ZH+4%+^nc6OGc
ziHXSknopfCRyv*7)U&txyVKI3htKENyG2Dwf#w<4Mw_#+uz*f^d&{}nWr?1W64U&e
zPn>l>9<uXD7&tty1Wo!aaBLP36il3C?hV>Wqobn(x;f&;jT<XuPoFpe+DHT15>ov9
z9A}iru@kp$Nr6^Ad3bbOdki`$<j2Ry6KBrMe2@ydu#oEq3wVdJlCnwZtB{MrUQ@n&
zDY<d$)*`oFsTa4m>&L{#n!cL^8Kc+CP?Vhf_4W0`=g;f^@3jSOG5h-Js-UzqcYc2U
z!PgyLVs^4#=8@At7lp1^q2c1{`tobK&%?6`@St>AFD4DT-c${o3q0a;WEO>YgQjZT
zg{7CjxM8tG-;D3#YSY?ZB_5MnIEB?576v5z`tlOo-T^HqVP0db2Rb1qJieCI*w}c+
zZ2S7(6=h{+3<u7h<prIS_3QO|-*-%3l->IrmIgfpO{fP237t867SvvEXkaLLcSjO*
z=(>6k=oAyi?Ck8xdjk(1>y^F;Iv_;fj=kakpXc_VBfgZBm3==keaXDMY@z>ryNcIq
zw||)b{|~!q))fW@6*V=`C<ADs1GIv2y~z8Uo6{@4yb%2K>61yHrL{G8gvzw`cJ@Pu
z4;xl|NLXvG2U>o9QkqLhP;g=*boHl_)<?H~xw-$}cZ=y>s^YtU#hG<tYUCG|MM5jH
zuCDs&-#*KtaM7*H3*~Go7JNOw=cRvp)xjzAzqzdElWvb=``xzU2Y6=tMQFlf(8!;F
zDEKZFzP((a(ZL*<MUQ4%m1?PY9@<g(IAB$X=H9$TNvp&c+`e%G)C*@|sIIP#h>8NO
z8~=G+J7h&e_Vsn0v(gJDtNS0@Rr<Q%>#NWcn?ToFCtO<M`Qq~O{*xse%uKVdwKy$2
zu(SAiLSA0qEYs{~|MxnIdrkrkDKhJt=&Ae9JF>)cvVgpN|8oENN#Eby1s#$5_xE?u
z!q^ED1h(Yejr!u#{NwNU`-TM%9QK}jdto6nXhGNYJtr)_zPQK?I)PzF;bW7$SwY+L
zVnK_WWv$CZw)pJ{T^$DMQi7JWmzaH;UFU3(Tk*K*P-<#w;^${)LC5M|x^&4TFHXTz
z2z2GW<LeHjRYxIBG8P334#-cM`AFZBamE#W$Igx(&iQ;xrSI>EF#!+xxws^OXOds^
zgT}erJ3M&6%U}P3*B1x~c7A;S-u>3RDPHHVu8Wm^et!P>|2yjb{`vu0SSBFQFlUa;
ziV&@kwNarDoDTo`bXx!6%a@%mFE2lQ|GqrvvH*3-)@8o4ohB{$(|s<!#%C62k<!zr
ztzDwpi^|{Mi`ZLL`p?ka-5qo_-^)u&)ruK^{r&y@;j34xuJ6>-)7w%1|6g`o${x^p
z5`3~&57zJhcc@p|oPhy!CuMhc_k+}=zaI|s|M+s*|KmY+dC;66XvD0ISDKBRo7=_3
zWdY<$8WG!Ij(a;6B!G^Ky}d2B@aZYh8#ix0{P_5|M)WqFOP4MwoHmk?kujMk<L~0)
z^6N2daO?o6SN-~RHz-ems?aI*)6a|l&pVa>W@XsgSuZ$UT+}-A&t1*^^5Wu)>+9w3
z)qan?7~CTTYLLn(DH(!ODcA9RnljR`a0SifaUBQM#L3s!Mw{zIY+xvUb_UcVRP&k9
zpclLAz`c8NlT;Lyl@BkO=TY<LN1;i^1&1#@i-iRR10Nj!vi;-Z<BP-AMtOL6fL6gC
zI(+zQ-}c<wVQ&|GF~2)m-9I5SbLI7&)22;3app|T+3ueC-QC?M<4gYee|~n>`S!M4
zL22pk-{0RS|N8P0v|eY=-o4=SSOOQjoj7$$$TnEw-VTTD8<USe`uF!Y=rE*!)nU38
z*4D|7kM(BU+hh6c{QQ2<HIV1$*)B>4Z|{IF7nU$i<MEqs$2-*v6yt~P-j&^5_SWg^
ztE-0j_iSXWN;p7gQm1oGpE$Ac@9*!c|4!KIJKGGrXDl@(r%%?JO<P+Vw2j6}#q$uT
z2Dx%2WbO0v_xJ8j_<Z8TnYq^C?~D0mEIvq0myq9A7`c6C@$;m6dn!MC`QqZ>zyKNp
zva@vL1}*xuSi=8}S5y>S*ye#IPxHSVKc-l_0X)OH3!JP$t0wHt_+B>mI=db{R%r>^
z4Dsvh>xomRw)V+d&wAtQ?A9;WdvUS*^ZGZ>pSS-2ZzDW-<_yoiefvNg@pfF;z_shg
zpF^$O9X&lq=319Oc=@uEk(q6Q&rBn>7<bi!6P4XTTiPO`qd^k|QpZ<^tZdp{{+=sB
z?cC<{^IQIH|6v}yuS0?X)TsoW!w8y#D=IQF%e~bSwl?bFzrVjh$FSM`d?E}!;L@jg
zcg;^D&|!TH8#ZiU`0%HgiviTC0d3EGc&L?wk56pdMTrl`SZ9IG4f_A@`+m?75TMh;
z878DkUb}V;H2niwvoEOZ2I=^N;?8H%pGRd|!0rB&En1<gz~|W)KR@T{<;68;&Kv=0
z>F#a0x0x#bEo1if_Ffac-S0zCA!y?k=mfHlkB|R&9$)<C%^QQ_XFfdAW<C$BjMTVV
z7kNDQp44*Z&YkO9+Ps+R&b>Ic-1#MV8({2iG0<6gN4v#AcOaVQ_cb&ye0g=18+1sy
z?M00Zg`j*<`=MG?l-)ibwEP7!u4xbI;_VL)Ed21<%^XxTfwIt-!^ae1O23$ATu=aQ
z9!x(!kM+Z!LtEW?rJmNuY|Du}a`foOlh<2ZyTuX@HnD;R`(<QhKgZwSmMdNL_0`n+
zi^>c;cJEeJRCIi66a4AN$7G$@T_V4~y*&)tj#lw8$t3TN1gNHWabfxM=g$Msoa?fK
zQ+1=oE-&|Y_wewjQwAMHa_`<fhK84ymxGRM^zic&+jGT0go{<h^U~{>$Z5Xcs;`1B
zuU!?YosyouxbX3@j_z*foSdA0&wZQOct6~$exG=>OSEaaR9q{Us6pW)7an;#83xcX
zDxl*VF8kZFGJq<B`St&H#+h4I2!A}ry6fhR8wsGhZ%r};Hf`RVn3~$!D{a0Ayvi1o
zIU)C23h$ZH(Xk@skuc;6aj%9eS3*GTXNH9AZ0-j?^(*2)bN!$NQ;N5HKz#<#*vYfA
zvq9&f<?sC}#_*uu{@;N^t=xh_LQR`ePcMq!U)MB!lHrZ*`SV|Jh8&97UFQ3RW%1GF
z&M(6jyOA>B0Um?_wJt&3_q)i2Bxud)Bk)Ca7r}jb&=@wTT?Cr_s|V!~2M33L$F-(%
zrJtV%-emf2_j}M~XEV%lrOfj0=@h6+Hm{A|e(3OF=eLVK&6y(u+AwHfY<zfC=;{kA
z0+n6d-IEWsaDq<We|C1Zdcj5s(4Doj&2kI={wm$Ed-vl{PfvUJ`?E7xSXh8Uct_P&
zt!L-w>sPFN2--e3+bq|~!=vNaMs@#r3N|(}pc}k4`1BM$KGr!eK&eO8T5Q|4Z5|#T
zpdQ1VxpS}f{r>e!$;c?^g4IUQ1gLTPxhM6YrA|80+jwGkm$}Bp$%U<nXp}O|;)u~W
zw?97yG)bM3p3cl5BP+Wx|Gu3~)t3`0`7sO(>(;H?QTkep;lQCoOjEVP-JG19{;|FQ
z-Lf%t>eLgRE-o&rQqW#P2vbExMZ$vvjWY}qnHUx%9qj^b<aly&G9v@%%y`gn{G>@r
zMavAnzP{eRcdzZYcXzo#E0B_R?%bJidz)@ha4=|b3U`!;%a^oAmlt-qO-ns;{J8Vd
zAkZOG{PK1!YuD=TDtpUSUtj;@$B&MA83o{>w2qD=36Dj1rQKzJFDuA_RDY1=sNm}F
zgvE^;Hxe!`as`c<Ff7QvzHUeDZ?irbOQr`ueJl6<d?tNoXR-SepXQf$b{2ydYJ-+V
z`)2oacXxBM@yqpS1}}TEUrbt>TV7rsw14@>r_=hM<G+9Zetcu{aZoc%Fu3*8_wUEo
z#qQpaf8Q=-RS4&~bLX=Bf67^x=`32jxbWQ_%Y)v$?=LKL25lF7@c1z^c;KP)=jZ33
zGgE&&o1I_q_LixPO~r+j`5r#EKp7o$WAqHeWZ3-M|K-#4<NGEmyRW+Y;dBUS`(U@Y
zzMGR1la8+L#`^ztTe7e7Sz1~$Fc=#fySTZ5j+z7I?C0m^7Ct*8xm8;H&*#r+kB)S9
z^z@jVd>_p4;b!`L&;YYV*&B(5=l^X%D{nF`C_H)kH1X=HP!0}`1N`=X6e_@rW0nZm
zg04^Q=-|4(t27(D1>w$efBBZSwxnlgX3j87W_xyiKEJ-cek1qMT@@dds=mHj`ms&!
z!B77A)n8wwZn95MRjQgBXCwOxl&?1?A2&!k!f|IuA+w{S<BFJ_MxYZ#Kx?>+jf200
zELQLo0`01+`B?-yR~0na2U-CoC<waq>*D8@1kmaiXBQPV>E#)q{WRvS$&UpDI}aWM
ztuuveV03Xgwy@;oB@bU;)(?L&uYLUZG0VIUbnkFf)T|YiY};#pm%X{UnH`jqXBww}
z`E?vL;sRQ^^mZ$#XE<reAN6JXE^JEmzO$$D@`TSl$Ii{Q1{Fo1Rmqc7GG)rk%a6~m
z|EHNSv*PS*^W)#%-Y)$2r&4387sCP2it2&~4k>AApgTqO{P-jP?(XjC^@<xcPoF*O
z`ts7!Qn~&0|Lt^iba-~0sNj*akx=)a*Rph}D#HTb*=81{uSC+$&T3u1|DTk)-yDOJ
z-RBt-{{Q<68ozDj65Ud#yDn^P)IZ?^z868;9MjH7q@<=YGN}2?U|1T|+0ns~b7KP|
z=tRjqm7iJGgU(3UdB&9=x)-Nc%9Ly4#*HUVooZUTR28(~0kmJ@(h^UGdHX-6KRndh
z6y6mKI_hD6UF`FZudlBMCCxTz7u8d}(&ihgzGgw^Gg@>`XC3!_srP<KEXu})-j7)~
zHYkGj@mUr>TVX4k_50gfwZA1Axu8WtZ^0MED%#n}F@P4`Zd}X)Ud7~m^yofN`v^1`
zE-(Gu5;C+J1FCnygW-QS7S02$g8@%+gB4!ikmw9b{c&+|H+Ge3U%Gtx;>zIVe;$Xg
zi!ogJ{%Po{kb`TZw?BCCf@5h==f2wCi;|9ZElQVc<r39;@b2#Jto46?y<Wdz<Hm!#
z-|t)ft!ib^(tuSVn$G8prDo2YSx{DXt@4h@{7ZlQL3c6>2@4ng`B4b!c<Sr(%gM=s
zZsQQ)vQz)ix@3t8XwTKgjT?XZ=a_}^N|_u0B@z*lC51ZX=HjofuXn$^%$HTi*l*sv
zc^|%f5wUf)0CfZM^70Cbi%<W*aqE`U!-o$!`1!@Rb#`>T@Krkb|6ix7AP7vASh;c~
zXbf@g+_^6_op_~8II^#=bFHYb`1S4W>N3!2*Pu;dfByd6m~@oOk^5xC+UV_ke}8{>
z_w(a>^Y$(1ypG;t70*LgSBJB%QBGb6o)AAadtb>!70#VIcdoAtJvm|S+};^8BtZ2$
z=y+tOg$6fw&pM5FWMp=}(+_sDbH$()fZupucJ~I?<be0YfLCp_cQu2@Xhh_tpXcYu
z{M}gi?-+PV0%*m;FYB^55;Zk76K2igikx<FbGkohR^sRJ?Ca}#kM&9`D=9fW@H%{J
zf4zN(mMCaD73e^6-`Qp#zJCX;wDbK{U2%S%EvO&^ZPPC+D+8T<3tAVZ7rQIr@v+{l
z=Y4XvQig_x7Ul2eEZF)8v>*%AkN_=<S+Zowfs-dWtG~TDxxZsa>Fa9@4e@n9U7z?E
z6?uAkt_WE<>DKeUm0f*(ZlDW7L_}IZi6(S)7-+BHoVjyBt3r+(Kdx+MCI&uOeWly;
z>G5?3-`v~`TDovCm}gz+>M+m>^KE%|SAE=SVQwzYD{bbo)NAU7;^%%BgL|Fa+}PHv
zUHfyhw35=I@D_2%-Q0nl)91|TG0VLLnj2jau~8}O+8R#qq%~-R>C2a$e}8{JeDPx7
zhae-fyu3V(;AK3ZaEaQQ)j7}E?G)Pf3ANhi3AKMezYMr|@#2Y7r<|60O)YqRP50tu
zo>wO(DuWKpdbxc5geg-%b45RX{7_I(V3=!N-UhmWwKL_&4T}(&H`15HrI%NL7x%wN
z-B1Xcw_l=f=J#;}C<B6qI>0kh@i}uAdHVSs1D&OvpWknmd+W*md9!A9U0of%*mt%W
zXkqbz)})m5^yK4xvH>eYK!?zM`t%7jzzDhk{M8lCY15`HQkS|i(>VRYj>6;{w{L^?
zID(F408O?!xAQ&R`~6<9_4UJtneW}Z7qPEq=Yp+|*2L|VVrJ)a$;i;C`tpLYyu2J#
ze7}454%GO%wkEO}bf(w)d$C_a67^ztwX6<b|LEc2_NaW3MIl<OYmD@2n0D>@@Sy-S
zwf^$u%L%EHlT;WPa#{?gaKhFC<mPV7xTy5y^>zObPKT|lzv+N>y%s$^wa~R&%)s3I
zy#2P)*I}UE5+^4oXm{aa_kI>V(Pnc!jXNhNtAkFFJ97N^W6;{0z18M>_U<kG|F4#X
zjZH~KMdkl8P0%UhCeYsM368aqo0mn@znkoDS9#Rit8cmg{71jv?|1j{;Q=kGVptKj
zRthvTsp#DHp*L~KRQPs9l`1aDjbFZ$xVXAHE)4?BY=JI9yttTsikB+rjN0?YS~XTz
z?t_kBD1CkH;j62wC!|X1Mr~=>zuz7-h0M;*e(`fl;$sn6>GrO!TF`*%i~iov=4O3r
z-+Vtp`lw6v&HDb`u&7UdoRRcc1hkl~3!JMjtp4`nW3r2@YvRjGOD$@C7=Wq|&&g_?
z^HK{yn`Y0<GzP7T30WP+3p$0eUA}HbnO{wfO&h;_U;h5TVsCG472XoE2DFdnSP$ql
z<DENq8kn2A=jG|Ccpd`nT1z~{a#6Syv_T2f^^~!x2zcH4oZ-{|*)y%|7-NI0s;od0
z_ot`pD?^H6(5}x@({#0~W;rfhzI<`@_jeuL-KXo<dQH^=t$7ArSie5r9@IDU^Ya7U
zLIJv#XkCnDWB1XAz1$_<9v+}oK3ZXGIP~@P*Tn6OdfO(xHhOzocQ<#4*3<_}LG4;$
z=ypgWr(5@~e0|j3_TTS^_<H6C`nnxmD?qDJ?(8s3J3mjiifgKXr>7^V#0b$61<k;K
zwww9Sw*#%}yRu^9i^@YEUIxq(;bOJ1wSD;hJ%4?D{f?bGJLjc{fTot@f46ltgZEMh
zOS=pIZaZNB%8}p^vRU9g-!5$j!9}Tvp1HaB#EBC@n^HlG0bgET{&;TrJ;$ghDbVto
zX}ZziyYAAtCQqH(3aN1uLHSTaBw|;|O3(NmZmqkkzG|7}-da+&F{fY7Hehp_@5Re4
zKVK~F2OY5wnx@aVx@zjV?j&2#miRM2Qqt3v_4N3BXPFq@>~4<-^<%THuj~Ev^mMlE
zzXu1IV|ElU>PBrb_+Vsc_uu~8J8P|1*75Q`KBqdcZd};Fs?4-4p?5_?LP8JgV<8t`
zo*SFoI+r9|;l9YB6~5u^ESKwfEbp|Ag@(Lg6Io=kSL=F}Ba8C&E|I{4Oh)_d|5(oE
z%w?H#{(#N;Vw>4B&rdI&_f*5i;B#I5^D_te?f*1@Hd35BcWy`FW43KMH<_ZNqd_Z(
z88(3Kx14Jw+AD1?HYdzRPjAJH)vL8Xef~Ug(xj$Ei<D-}oVikG4`})lbobZPsj3#B
zM(*DujF1s|-7mk^ajdtk`5_Rz%m;L2{fDpD;}?T_xLdZEfKC+Zm$!Fwabc<Y{!Uj(
zFK}<^%S);|cJ2i206DUw@UhGBg;i?C#=^I^=YwuA0UdQ$@-pbh@88{hO9S^<hdd1m
z4!*cPem~dwOP4Nf$iA)zYUP5C61}oA7_?%SS6!r8w*AH1<oye8B^^&ZzLLw@ukww#
z%dCTa&RdW69qtPjEt~V{Mq!6Zvut}-x9svg?fmkfQxYtSpYinc_6CN8EZM{S?DTZ~
ziz|cGL9476E?l^1aaKrVq-0W35@?^}o7>y@j~+b=?u$Hq+G?15Y(eJbWs8)vrcRn9
zq@u3A*nhsAmHid>sm4Y|P7V$XptG8+y23Q|^gwmw!}ss|EsLLZ^erw;F_QfE^L+iG
z)2CM-`aIXV9CR~O`n2lE$jF8D|Nq_Cnmzr~&a<=4K_^Hvv++3i`1JVw;fa&g(_0aB
zd6}=EloXe}y*=m*g)3J=QW<JbPtyf;g#uz?bRcoEMBfT@RGgsT)axsQ)u$fs7SnB7
zxl$9fqJFBiCujsG`FP*a4-XH6HuNg!==fX?Y%M4)ZJjqy4m7M+TU+~7pL?~Er%<1~
z{kq1Ikoh1jii(P${^=~UTrO^I?h`3SQ?pe(54CcOv#6@%e*5sySwu|i5$G%`4G{wq
z6A@X@$DrxicXxLyTUg8}Z~ry<$Pt&CPbbwqyu6%do8?Y9FK<!60J<ZuTU>w2`L%I-
zr8G4)wXU0nys-#PKE80*fjZ=P%U^Z8&$+Y_9Chuo%eCHEJl*&>q+hoE6_YjJRWWP7
zO3-nLpz0_2c;CYK{dES$#=-MWrWk>C)3)==Uz^GJ1+>1(%`NHrx>(S{nZ0{Kowtu4
zkIS3?unU&{`SWK%X=$jQ{smJ%KR?hy;RgqsK@%c#_a~R8`uO;i)XfZc?dj?HVY`y+
z>RszkKR-Wz`YXY??Dx0an(ueZwa)W`hJiq1h<x+^*PlCgE>uqsv;bh`QP%op>*K#h
z+?i`#z9Xl-qhp1b1!Q_Kgddco6crV<@?TZ@`up?Gn>R0FLqcOiN|J^M*OaMKHRY#I
zof`UM=g-f_1^(XLRr(s7sXQmEZP>Q$*|(xq*S2O~2OYsJYh9+Gtjr9`4rgW>KYaR>
zRa;y8;zyHrcXk%<u?|uF_WnM9c6Rnu^Y>GxO?&kDynVZmnsY>i#G5y7K+8;P{{Q{X
z!O00K9TW^UO1!aHb)#^F-iG@Dz8fB|NIJe!#@g@ejr>#KSm|>%J=nLnOLlqD8;h&S
z$2DP5z+&xp_1oLq?Vvu`;Wl39xVX5TpFx*~*x1B;KFCs7RMfO^p(5x841fE-Av;?%
ztgWSQ-n=PVcc%LN-sJ~dZh24NpAWi__2;Lj6I3`SsVuDi{;r^?DCplqqt)RxH8mS*
zf0zCE_3PD@0~@StY;8BDpO^db>sMFbBGJ6NyOw@3HCI+<_Vo08x~}@i2Su~|dp+g%
zD%~f4Y|+xxY}~kU<Ei5H^0Q~p?(SGJb;phcS>L{W1MQfcKR<rw=0}f`TH4!_PfSo`
znj|PFXv!l4+0MU;U4)DE(xppUw)?BTuJYUaLsVWq{%NvOX=_{Cp^Fy<+4<$3%&uAy
zv_1bm==eWS5wT?1vO|XsF$qKVAcLmit>y)QO0RWsd%Ip<UcTB!TwJ^zbRN^cKR;&}
zrE)PGxOPnpv`PHo;r7yZy{8$h&&}WXI3PA*zhdde$02>taNZ9K=at=Hk*UeYSIU73
zIExVR8-*URZ!BJE>*%;VKQ~v~R$o)oF*9=|n{em%FE4{ZjgRy5Y(wLggS#{5?%94l
zzbabi@`Tj%^vBoMMuVm$oSc{@O`7!K^LhK^%gcNxsBpf$z5V!ugUwT!U)KKma`EK(
z@bmL*L8DusWfY*sqgC0Ph=&X-cJJQZP?F?3%Y@U;&Q8LrL<4m0m$&z6uJ;}Hc9-Wf
zzBGCNe11LXX2Pl7vQ5p+f-*8O@2py#7;SBB*TnCSbMPvR+f&i_=uy(s$BPyzF|2P}
z_5a78Y&SPIsncpg;^HgvFD`N|C@gH;y?gg3y^quN<K4>2%s{Jls=vQeG%yG#0Btb)
z)y)i98T}P>V8^xf@%-N2-k|ZOQ}Ij0#Kn{U{`v~qR<>vFUe@I*tLnM9xgWlLd)EAG
zz|?z{&t*ZI*A~0=9%^FcHb^-k@Ra+-&!0a<>v}pnJJpoA4)1mj)zjDKm$fbnseJe2
z<Kqb`oXN*}0xRo2JUDoD-^=9-la4E{s(xd>M6YblDM*A>y)k#mXSe1<i7LK}w-5F?
zze+kDIDhL_({uCf<6r&+t)wl#UmM=sd4!9bTUd7Cy-Qo4TGfB6x_GpOQ<#Clf1ZtF
zP>_(2urTOS5a)Kj#Ov!~!FS0oUa-I+B}VaBpX};C?;|&-t(@aIX~|`8**SCPGVX~A
z3B9;TE%x^vP|<gHcX_+hLQtD+-=9z37M7MPW0XCGW|`%7)&2dou=e-2rb%6fxwlMw
zW}B_O^Lep*zuxybDxOxGJ=(gtuRMS7prM(aA2eEZit)?!`02X3x`iJeIO^ppDJiXD
z<%9Iet}@&I{UV%qXGbG+h6glC%>WuT(9qO8_~2mk$H)ElTz;B<Wo2fYHg68Cv#fu3
zi1p9k_w~m=KR^HR<?{KU(cc88OJVQ#|F;7j_GQJEY1!)32%45XKhHL6|IU!`IE|-w
z7iy*F<@Hs6f49=6{M8jr2}w!NY`4~V^Q<czy;7!^Qf$^9><cz6lUc?2O*%;2+VAO&
zLapO{!M5LKzuNd1RG3ZJ1rf0<oAU}%ePlJswqH5gw|L)q`~NbGjEn_^g$FMzbY|Qm
z6;}Q4k7ZMHbK#d4fjPIfcouk_t-Sm3#n~CNW<5IAE1hwB+u9czQHO8bkT~4VfBeJ4
z!-e19#U43&H1X}NtsZ`U#}>QyyBrr*Qd4s)VOhI1^Rn90MIu#Si?^*^tJ@G>{=KZU
zv~}v#sSiSKDJm#9l(4KldXzOk?Z$@06DLl9Caot-oY=T&lTk!;bn=4(jTbIo7MAVr
z=vWc=m;rq2QlKs9Foi$gZs&LO^&Ok2><(IG&2ZqvL}kOQD;l5+MV^>Fybc<q1s%_{
zapOjYhTq@cAHI53R6lMH=&aoh)!*~p+}g@LZ{ED7$&<E4?ys{2oi3hqlnb=G6f{mQ
z+qvb!p;m5J_X|;=670>JHv)o!jiB=V>@3s6Q?<hjo}H1b`Et?y!u9aKQ)8l{q;zz2
zSX4#3WtV5Yu?P`H&lFdak1w2+a2%yv1C?TYS6RTB#l5z!t`4+|6|}hobRinUgQrhh
z_w2EmGHu$S<HwgD+P&u0B1B6o<Km*$7Zy>E-`(8}TA|z9%PVD`r(@L@wxi~!k&uwk
zlydw1m7mo>M=96+{gnth5dd_-WQWt9xFW}=wf}xTU!<I&TgM-?wd7^cMZqm%;^KQO
zJtu*dZ(3VhUkvQ%=#UceTo|C?(heC3oK^YnkL9=b_xs=8-v0Q-#l;oh-pqXA;RHGj
zxUR15)Y=u=;p<!i0t7%uES{Tdo&4m)M9_7YlO|1KQCH2qye85ZRHOfY3o3DpX8Jsp
z@|+Y95uu?ZH}Tr$EnANCNE#c||Eqag+|15@>}a=mU_iivPi%K}qqilTn`3G9`TfgF
zOT9q@SW(+@IHRMZK^KZ0J$lr`&(H1uzrUgDwr<<j7Nd9k+1c5wORw6!u~@$Wl;rOV
zT$KZ7gsi^5&+gwST%mTOup_G<T#1+-@B5q&jwuV5e19h=rn2|<))uj!0bP>q+{Pm)
z>zfVg8G!a}`uOlXDcbqM;*hJmyRw1;gQTP+!-7A1o;-U7TD}yqqd*aKHOcZTJ)lF*
zIy*Z-wThP)7wE!j$Swq}|DbC_d!<Z;WT&o(J9XlOLqvqcrcIjy0s<QB`#*b3YDqrc
z$LX~^wy3BmAt@;+&r&APbzSW4u$TL_A6yLr9g9>|oRb8e`uy7CwD7>k$HzB<2Bh!q
z76%<#ymIAAzyD1-_V)5=X=$g9gF4s0-|q)CdKem(FJFFY_N$IKY3ni_6;C1A<}G*b
z>?{V2K74t3*}X($EvS@V7rs6Yv@`>>cW3HU*6M1|`A*yK%%1l6@#Dmll$MW=k8^vi
zvb|9VY6i_hsh;!O{w_;`gd?IFcz$-n<B%TNc4z_f`PrN~a~?c-qGHu{?Xm5dILm?u
z44_`^g9i+tdzYfNcvN0n<|_?4ASN*}(aN~t-K$qz%*@O^^7eAs*VZ&PH#5KA#hviu
z!@~(GobCMbZ9Zy;KRi6V`maQ+oJt)iVZOcH{`vX&#TzyVq^727J)fkK`1n|F)1^*f
zNy$#l;AIZ}{`|4KN*q^*t#xs~6csaNQCBy&R{7&&ygu`6Bt1Pnr<O^3PAd8LUChPB
z#q=noSGTC@(Vd;eH}=(9gO)tr*<H>*NhR@63+InltJf#w=dZt<?`L3Ydi3mUb4CV!
zc{>*`FRp32(aUV~b#+}cGgq#tSaS5x;lr-(3#t;Xt_lTR*mhxWbvfve==pWOG<9@!
zU5{Vl;uhCC(!j`kVX3$H)4K~*JP+-u{Cp~QclrCcxz&LeE?yLD=aXIaNlIK?JZ4vk
zr*r2PVQ_+8p>`u5)bIf{g`~g@)K$m8jZ;u93u>}ny-~R8IJ7<}lL->H?)!D;&K=Og
ztR6{YwzjsmMUOLVWB>pA8&yzX(8eR#v}1<_XyX^p0_KM1=4L<MQ{P@)<qlsLbFfd=
zy5Qv{RSPStLnlvi_Vx9>xU+Nfi;6=c;^NMeRGt<*etkS7uB^<gjZe1g%o!h(>}x!r
zy1QFUHy|Q{qt%H~SXfv>QnIs86I4EcRwf>9=RbVsPE3i++T*U8>kA4Uucn=u(FnSs
zEWiG@^qjeKfBsZdQd*S^ZHZn=ij0f|MFZ%l_MRRdP%^o9?;dDk4m9l3BWo=NIu$gT
z>pN)o_SaWeK`TEVJ$@V*7Pf3t<*!#)SA$NcKhWY5GCy{AneWeIr{3@XFUKvW)6m?^
z3|jFDTBB0>`r0CJizm=`<Kq?Wvh5xB)WD6J0N)MwSM;OsAH(=EUqQ>79v$g4Ff%(g
z!!Q{Xygag2Q=At~eUNZpd%Au+=(ayCTXS=BcR#;AHsQ|Fhlf}}+k{S@Jn7-%<C2u5
z1UixU(W4~L!GRYq3O2Lzw}F<het*x;%*=doqN$Ri;=)tMzvTb>_wU5nv#w4~OrW_;
zV`F2`rgA<$KG4FZjhUC#jvPDI)u(yn?d|P`>E~ql=CAI&zd!!rqo!4=YHCUf3Jmw_
zey@F@;o{=LJ88*-e16cG1RYx@H8(S#n`7B*mU}DV&W=LRx}=9sp0F^0E@7Ik7YnK-
zE2^rv{Iu?YRyn<V+4<y23TT-8^mP69`Sax&9{l|L95ki|ntH4Hnsw0AQyO$li2a`r
z%zUy|OZHfMF87;jQ1vAPbV}OU+2-PNCTuzR^Ye31+4bjj{QpC5Z*NabNN5mLb~|wU
zw)DGq@Agb)nkaRn@XGN%XVar~&iP%k?JLS|<lp15=DR9l&9_&xOlHxo#N(C5Z!AKB
z-&lNEcB63B_xu0<-Ul5Y^zZBXdeEu4xwp5qPM<CgI-p^De*DFcTihZeCI7wu|BpZS
z_BPkY$9i3l3$7}CeGPQO9%zO2o;@}*X3bJEGZQP?DZ>D&hg@7-9(;RyyJ>RQ=TA?)
z|D6B-hac1soie56$Pt%2JB!&t`-JDtmGzrvqiMD1ny07d!IP8KAHILDZ`E~dYvyG(
z(7_v^5r98`YPMuvW-~N21oaRY5?)<ddE)fx!;Q@BEb3SHG%~Y;24O(!VPsuj-`!s?
z|Mu3_;Gb1%R`c-kZp^x>b!LubaEZv;l*GhF(7BYLb4eBp2nw2dz_LbARaF(}g2%A6
zQLX&;e*}L0`gO{9-^S%ht*xyFCMKX;D5spat^Fkex{&X9pKM}Ml9GXJ=3?vecL#3X
zlr+z~<M936UGUZ(hpH;8f8Xo>i-(1Uf#wu%ZOvA<(9D!>b!r4HC~|X4IzP`=Lqnrs
z<3>Xp$W~}UWw(w#k0o1g6yB4u=G)8pO?nk?narYDiThVdmdR8Jzp)6Beq-Tcdblsx
z_>ILEwHt*i%x)B}3J(iwn=wNo=k_+<ix)3yXlXh1%h?)KeoCpRtUP$=kW-0EBIx47
zIdf!g+_(WAWqQnEo_EJ$$@1mOrlz8;t*u(jFF@CGt&iIaN?k3jt(|?VKxf&t1TXgk
zt*G|!^J`P_toZq9>5GUc(2ib5M@OrlI}MGD4$U&nHpsnYGG)q?1)h`DZtSf#Kh`73
z%mCW|`tPy*Kjzlf)~3l>_dp}`iHBI;+}$nS%*HDu>%MyGlqnC6bP9utov5u@s#bjg
zF);yK|NlAv|Hwk;_6aj)aLn{kv*HsJ3~W9OsX&x;x8~ioa&dE0($wTsQ&W?$F4F-`
zyNZj8r=+HS?6q|%1+Ce<u{oW;?Cq`Az{PGW=g3+Xv4F;fZfr~z6ckj{P`t{ns;UaQ
z()8N;_<qop*#7?fOP4NPlq{I3TPCw;d-vbAS6tS76Mx;v@3?1ICbLTWjfKmr<l~A}
zzi$+-ShwME$oq$f+dq8#cyL|pZiYQkTOK`n)C3w{m#_P=@IlEeVOiPUh6aX|loSSr
zq@*N;>8B^op52{zxGnMFq1F!{J_yVS`h4l~<;47aP|p%nBR4iS&af`m<Kf}iQ25wQ
zLxgLNZM7I^ie_=vozKtDgZA^QsHi9?Dl%$nYMxs7@K~>O@_`1%f}$eOYLo{{Zn;lq
zzp%UXHCujuJ_{==BZF1h8_<9{Xoi*nbY?OrVSImoUtBU+S?gD&rmd}PW@hG#ySvTr
zRX(3v#JqWu3TO*#u;5mw!a_r<@^?J-_4Q|F8oQUstUY{`HT3rGa(z(VyL2fC)S8#I
zE?ZL|aQE)rSO+U5rA5E|_y6(+7k?fs@$vCLe*FS<Xh7AAlCtu~%Fk(_y%Foytpg9k
zboOZ;ssDSup0VQVG9J%KQ~FmMSAKf3U9$Vt!o}|WN!QjyKD~E^nISJP4>Sh3q4IMY
z<H;5KDn349<&(4NIB~+`$noRM3}?=sJ=&&pspyTxRPZQL9e6D7#n}z_LwccOc&ueI
zi_8y0>TB*d;Bk#r(<V%4$i2NS@%y{GC(fS-&1r%T5topVNO*m1E$CjT@AvE13zv)7
z;%`k^Hr!hqZLXrCa^U=V{>H|}01c6dokgk)2aX<P&Az_w>dJ?oU%be8dZ02ZOUuj4
zYe9g<g<YlD7S`5>PoCuT^Ya63NpEaye6eFm>ysi-7ht`N!+fJuF3?gS(3I<%H9U!l
ziJ(ie9!!~4`0UI~uKK*J`}=H*ii;=Co*n(pN4)-=k&#i8)53;@3m3l7h+4SlDC^p&
ztxby;D~pSVB)qw?@zno$rrFa@%~bIW&=8rR;;Am)Bp@hwmGvHI^LIzb3OUR2cQT;b
zf39^o=yqrWbMxcz|2~O>mOwT0+c`{D^L25*!eMJ`>oKWix&Qn{fs5TPT)w>eTk;QY
zmsK4TCkleLbLQ{+x$Mwq&~4AV-|urSEZo>Od7@dch6rdP5fu03@8d+o#1=(vP6MqC
zRr8y}u`_1fwd<-%zs$?#gu?~}H$E1)s{3trJvb&owN#&T$o3nB|6nmGV(oWzUEJO-
zP|O|glRa_nT-(f<l6&^-0W}W3yuBU%^p>P?nu3-VS7l{o)1|C)4UEhQIXOL$_SeBH
zS41{$+&JO%Q--*^Ybzfg>pgMqoY<U@HBC)Spe^sIsi_+_ZE9M%a^(vTsqepDyFWiS
zck1D1etv#0E-r3=kn*)#?>^&S(B%p*FE4-i@L}VzUTM%2BWMZPqD6}oCZ7Zqn4kkr
zb)&Wj$WGmILOi~v5p+_tnORtg$U_|+oqH96jVhj2zit2g`1m+0*1Y7!h3#`%IyzP)
zK7#eWL&Cz^K<8uL-j;h~ce%cteI1Xova(I(CzleFUeM(m44`9Bwfa|o{#CW;dR+dK
ze{Z+nzpx@udFtj#lY~G=7l6vN>Thcnv@G!jH9$_B@Bp_5{{H^HaQ*sz(6Y}*M>-42
z%df9A4;R|2`^MspMM(7<b5MQXaZfMyy*Yz5-&Ni+nX2G77B2bX)_e%=)z`PT>+8kt
zY5{qDalhT6CnqNxCLQVUV*gbB<_2Sae*ToHQ!_1AK9iJ^O1io#bcSVdS}XGl(6Q9v
z@wK2mIh=m0Di0n!2wJOqex9wi&HkdNT#FVhno?ez_oD3WEmn1P^)1=g{Ys`(`A%oQ
z(3u6g_tVbK4wNc;B#jd?Gb10$UId*orXUMC^yD2p+`hlLY3$<eu54r^bn)WFMUMrp
zYVR(4dkC}_>fYY!!`H8i$L=m;WmvL&dGg^l-W?Sml|b{Cg^!PM`gtj_va*6E=0Hnv
zoEA1LUaY)l?_SWY6$g$SaVfD`#MUj_z9J3MD{z^0yv{kK_>IL9y)qf4v&qL5S6M<k
z0WmQ#po9o2$Is3-U;pjbqen@gO?2vFEnD*LN_~EI_VAsZ#o96s^X=>Hl$4YTet*k7
z=xOTj@6UgGTW<68>EW%<t;^qm&e&n^{FvqFRa9j3>&wf<lgro7v#s8C>-s#)Vz!ef
zPyVT9Ua(>XM_XIlR6XX4s^#zQto#%+Nd?sXUmLacQh?IikH`1Ri{AYk4ZdOV-)vAP
z_mTm0R4s7t^!fAqqqpaU?t1v;(o*jY8#Y`x8GkPL>!HJkLA&}C)z#g9GPOA^1T9?z
zt#Q)~UdG|)vFPQ?m!Oez&`$g9+s#2;EO#X(*@K{LTIc*K;kcqw;Elo+%Wf2U$iA^~
zQQ?BLDpxkkw!Z@HzL+p?Uf-1~AtGX8t9TaN-(AkXx9aPm7Z(=`iixRNtvVKJ-mtIk
zZxv`t-+#W{)rqVwYOu8c1x9a+|NpB64Tl&S8lHN}y6cHA`-;-a2s2Yt(Z<Hcj{g4R
zo72yO4kC8ao33nbE^cRM2R*OY<@gl~Tid-{?W_NvIdOsmG!Dqb%xsu(L4j9AIRErC
z-K^TYWxlhQHJaRN?dA>v&9qEXdHCVs;Rz>GB<yM`w#qAe3iZiaFKa9TweR`aAuDKC
z+?#Eb%5~}T<%yFf1wGukc(HQTmluum>;FX_KDlC_hOX|>o14=MKR@$ja9Hj)7c}xy
zTU&eZq=)p9Wy?T|XGP~NUAh!B=n6Wr9(1bK%HZXzO3hi7lu9=|4#?ebKcMtRVTXrE
znGC4Ww~Ei2Pq6b)pYzs(ea=@Ck1yOcVctB@VHgonQAvM(eB|KaIdW%bF{riQD{bzy
zFyO(Po13jRKX~xu<Ye&XH_(v|^XAPH)tglL<AWk7-Sf#>JvcMdSjul@Eoi4^+1p#1
z)5TxRn#D8ubjqgf6I^yLU9#lB)vKbQ=Kku{+Db}FA=AV_g^QS&SVvEf$efVRpqUWR
zx`t<GXM;L7iOI>#44@%K{r!KM&ds$3T{*L(?yr@SvT|TZNXv{F5_4s)Ew6w4h$+<1
z&u@YXXJKLCh3nVD?be-J8NA$NLSIM6iiZy&rJ&%|YFX>DBWGqB8`l5(!*zbTUM%QL
zIgR^U99_Ps{rlKopYZk7RqXS9k&%&#s;aI}t&|qcN;<B%XnUt@dxuLRI_vpa(CI&*
zO=LemKM#zE=;*qqwsv*7%D$qfTz~%j5fB$&{t0v{*}+>|vo9`o=Wl#zlKt_~QP3=P
zLwLFC+E;JCyx;d*ukPQ^=WMoTmg~jtXSP~-{OVQFpFe+kczQYp1`3`zb0%b(m`>at
z2|+<Y(3XlhA)i5YWk&~xikjM?BS&1G>X@60`}z6(cpd*Aw1yUR6W8D0-`jh8dHv>C
zC~6pHGVAGq#t0|wP?`*GSH0TH&Mz18ld0<UwY3u`PhNb`WyxB<c{Y)Y`ycB+DZTyg
z@9)Ii+_j%dmu=Z1GQa+xWr~sHp+kof($m{POL;)cT0A^BK%3|qJ3Ch_1dW-3CgV0f
z7MQ5<#$pLynanE9G8rYIR@wF|;GEsJc;AW@8ldg$pj9?4oWdLG{#I2~Ryr;WP_VL+
zirrPx*xug$V#c8xw{C$td919gph!P;>Qq8%Dr<0X@WqQJ=kDK^2W_|(;bJ{=<_zdk
zryg1BFwiJvLP|=Dn(r(Qua$Ev-dnFaH`6#>KuU_s+1Xh{TztCq`wI)1-`(A<t}wIW
z^|iH!*F<hU#XFzb0dz;+&*$@#zrMQq;rsXYl`A!u`Oa?J|NrlMrb%5N|NJa|b9=l0
zPM2kC*7!V)nWU0)XGdUwRUzoou{Sr3WA@kWy>ox=g9ix~mX;5Xc8mWwZvU^bm0NsK
z{r`WU!^FhJ|I}-0YFbo&Qu*`uud6#~v}C#kWLnkbYuxU#w-aW~ihB8TXYuorPprXO
z=Z_v`our~EuPwqg_4w3_S9yPYIR(1VvG!NV)aQ>LJp$c&1v=LZy!HGQuQY5*?whZz
z3#f79A^XN0)ZGS`n4r=!s|%W7K}7**z$E|WrKO;rk&uv3KtMpl*Voq{udn~B{iMjU
z?*HF%(2A|%=jRqBa|z1G@c8@te|d9Lcx}|yLk*0~A?Mb|>}*=GLW6~smD6iQWLsOC
zfr$wV18Ax5vSrH*jEsclc>SJ<JntZNeW|zj)_wW^C#raQ`1{v;cW#-!ukNa{R{6U-
zj+dADnoe=s{p8uRM>jX8Pn~C9{f%em&Yh=@zrDR(-@N5+Kx%qA=%7B(7zgOqy(cGy
zw`5#oYHe)|&=4^&G`x6o{pFaL0PExZ^6miv0^q_ls{=a87V^Hbq9OrwuzYcG^X}cd
zPeqoLn1GHNDt_kU_|jwck)uaf+JFWm|NQ+M7!%VYX`HqIwhAQY-X2NNHRD~P+Ac1t
zx|60)Z|{?}US(7M=SQK(q!z>EV=HXzD?TK=xw+YW^2d%9jLF9pO9`g@)#2-tUS3){
z;bh7w#uJk!2{AM*U8-7BTf4F5XOYi5o5&O&MKRqd7HMheFK=#cKJ@wYbp7OykB(Xy
zH~e#-YgH;FyD$z^zJmsylarf4*Dm%gE^KDw)iQ4Yt<hT@z8<t$`PBQzFJHa{EwswX
z&AqriKVC4fb@TS^?ja!}fByVAHCI$zT-nA(1~hIy!N<nh+8VU_PEJm);``n5&~u=L
z38vZCR_JhedV4#!^U0dX26NQc*FSmoOi59ZF?M%Z>&%&wpacEb+1Wv79e_IHNy*8s
z$3>dDxjQ;KJXGNAg6$a>m5v-cmUL!@A!x7TC)UfSr|UmH)XM$h;$n6&{Wu*9)y(Ga
z_v_=IetdItGw3F+B}<loditlH|Nk_7|AW)|`;UOm?FDt;Zfr=L)#nv;<jx(L@9*vg
zSH8QlGT6Y#$Z5V^ZOFX*D=P%0OtY4ptZ=!~u<`K(s~h>Ch6A|53u1>f9KaRctAyhV
zXC)mEoIi2m#83b0PfydmxT7%n&fe<q%DlY1K56s3j;`fbKYjjO`s@9<qut^g)6PoG
zv9FhFZEbzZ_Fcu(DJ^Z;f|4YpxrK%qGbBztEkd7PsQJAu_x7?+761SJwJ3PN&?jTr
zB&h7R0z7087Z(RQraZ-EEoe>RjvYG=+`TIs7Z=A6_w~`6H#uu!b_#(8OcD|nJeZOM
zikx-p*1fp9+kDR4x!_6>R3L)RhfO;>3$zuN=|k2E3o|pZdGqEeDQElS<miAWP_3+#
z?Cs?l76fP{WMp(yetxECYb(1s?d&1Qc$N*cBKYFM4yq88lvb@3(~SaM6~`^6<KXGZ
zS@!;3@7>+yi<c~6X>4q?sQqOUwJk@}N-cBY+uPegl`&{3$k`JoI3}z4YJFEydMRgZ
zZ4DZW`}p`cL)_kq;%8?hL3evpK5w~x>C&Zy#6(3UH9=Dc@bm*{78+75KxZACT^4Ns
z%>q3JO?+MfZC{MpTNV0qNB;eNKc3tF@4R#=$fo)m&%}unE1u6SXHmPdX0p1!l7)rD
z!Gi}G8f>e-X~_TocpkK9H|3-d=yKnJB*RCKAA|P8f=+7!%?yQwiLF_)=EA<(YS5(z
z$BrGds^0#LnVs*z<;%jkx3(NS)XKduKx0aJ?yW73?R>HVVq$6r3oRNO8-M(Iz5X=s
zeCCGPv!y|~HQ^u=<H;k%1qBBVHnW3PMLuQtwI*`&hwJ<QiTcmCJ9@C0z4Y6=54FF)
z9X;ADZkT+GCnY^y*~UiZ;lqa~&Ye5fBWVoUjPvyQGSA6spqmA!>BVYUY)ump7YCgX
z&(M%|c9!EL6`QIr9+mH2yy%#$?%&m=e&yBG)u74<ba=+Pb?ZQTQJ4A8=L-)H|MK!O
zyMElB3pbB~j>`G+?IRy#mBAGSliXV(-QxPs?kd0N6%iF(nX~8r=H2D*7wy;)(cI}F
ztsApLfSHZQVY*&yLUwj{@$++zlT^;kHeY{dYxVbctucDy6DD;?X@Prg&=~8KZNDc1
zo&;_0a7jA8(EKQ5t-$>mhRL8U1b^P<*E>Hx*8B1A_xq1QhoYUHrmN^F)Ya9sq4agw
zMMG0HJw3mlwVsnyKr4K!zr9)c;a2(mTJh{_Yc8hPtOcECtgWrRWXX~TN4v#AyQ}{E
z{H!?rG-#Y^$IhLJKR-Q%R7^dJ&TR^MdVHXhFScY%JhijAnb|Dwj)vNt1kmW|Y_nV~
zTXR#>qg%7Do6PXo4LWH~Qc@DMs@%xPC?G71Ejv4#N5(>+s%lp)|It2K>!iE8N*5((
z%<Yr4e)R3_Z3YHrW@b<iK~qyx!Z?kGLBZB`@1di<yB>Uf)U?!lI_R!(4-XFp2GE6=
zpbawne!sJR+BEk%xD4!g#Raa5IyzQ3?yUZ<2Q9Ie`Ofa@bB=n~%x`zV-~KO)we{|z
z+3|}PEdpK69=c=gtP=0_aeF~WlD4$8C}?YQfBW_gG<x^z`}_4pu{AX|Jv}`Jb$==x
zJv&z@f@++N_d(gE!$W!lINyLKnOv6eLYCQpx|3he&b1aVets_0PR_Q<<k92D8`ICr
zok%ePU7A!-S}HmtVDq29e?MLgk9S-caNx`t9%-|j12;A%hpwBb!s+JbW@UYa9dt<O
z@kd9yK}#1!L_`=E;`Y^WGDw(Y2-MWn2uMh9n46nVG;9UUWrwYe3VpeA=T6I_q9T(S
z9@P=i(V%31dAWc4#EBD6MFs{69y)wDF*Q|HV{X|570$A<vJIOz3(K~?V%!<i_xJaA
zWep7u27}a7B5NWxGWE;ZIz>i;nwy}liw8B2K77O!x;g!P*za4$>F4$wRRMLN<}V4*
z5Lx65KJHTRYFJ5$2@?|&_+B^AAu2I?pasZnywYv0+~T0M8wFmM%(my>2TebJeSQ7n
zx>)NQH*PR6fbO7weohv&rS?dtFzBv=Ia4}1N<=}E7~iColveTID170&@v(qlVC{iE
z@JvUC$;)SFXB(KB>Y8hKJAjV5OFGJRW`-d%S1Xh6ER%!R)<!=B9o~6kPo?pnKYzeW
z9#=lwis-gaoIagBI5_yov13kp)0r7SyPrEcIG)CKmwJYTh=3-`KyzpFYroC>^t-~%
zjqT9k!-c=U<-WPIbMu``?6E~}Z<(f~rY>BtfI+l(O+{rTr^nJr<FqpkDxRQa%3r>G
zF-ShvlV$G)X|OWC+;aN;{{MZKm-`<+e3%(@dGh7u{-C`Npw;GTlM}zZxCpxYIciIW
zqLo%Aqpj^;^IdV1RGt<|Dk&*d8AInV7FE3m9gg?m186!9wD#MzTWsZ?2c}hDGESrz
zxwyM?`+41ZadUGzXdM%%(gPnk3OW@kaIqWch6T`q%Q+JuVS82NH?N>zrZKdWpmZq>
zGEwA`AD)@1X=G&d;mJwiFE1`KA3Jtzk@7^bO`A72uU@Skwl0PfeEa;al9x?)cb79W
z*x1;BHtB(G)a%g%Ez!k4HXs1H=i9-7K`(yanol*L1!Flkje4X^y#kCjf))pzoUE>_
zsk!pd!D5H<Hb-3@odwI6x1TxVBOxIH+9NqhCG@A^Bo#$#>u6_APwB!!$FEtRzB;Q-
z-rEXJlJc;ue^1&VfuX0jS5RC${Nb^u6DA1c+}Sa4{~UECrA1Y(vhARC8%kv|N=iyu
z9XAR)I*wS?{4gkcbAz$Aw$^8s31`txncv^u9tI6`?Jj@M#2{sw)nZxv40Oj%)8($>
zkB?l}L~dpS9m|!NsCeqssgQH3&<4sQ7FO28*Vop9j)VY>(RFli)O@>{zG2%oHU`kn
zwU?Kca&T}6%n2cSwt%bj^)=n8u0~>FVok!Gra3nZR8&<HPfk)TC@XVY9ky0$&%3Yt
z4HtEZh>9M(aN$Gm`;xl?1%;p^W-^6qFEWDrnjKlMKRrDiu{A4n>GNmLo}D;(@?rvL
zBx%vD<l~A;N{iY$kiw)8w95YCV)w%b4luN}wSlG#x8>dK%DlYn;ob84M}K^L92gbV
zm3+Jpv|#~sH~2FD`Fd8{jvYOI9JHP#<LWBWH*em6_9N|#=}SL94|Kx*wr$&9+~2?d
z#SAAFHnv0O&-+)VUjZ#RP@4?eerhz6r>?F}!Z@wx!IY$u*VlMCIXORk{_LEPpdiB4
z`pNI3o}OOB?y|M#_~$dPZ*wiJeetJXNLW}<K%gOi|KG3@kyYtI!NH(2Iez@805w)X
z_t`!vvMeete)#w?v%S4N=mP1IGuz)?TN@o}r>3N&bP3T`PESc`S+r=8*ZIwxHi5?U
zdDRyEdU9i9GU%jz(Afb^O-vdhTvLl<?|$-gad`w<CARUtfZ#+k&|0M=Q26D778M-r
za}KH24qM{@+D`T9i6>}v5@>$2rltmT*EeX}Mdk4emo5d}xP2QmZfRxNASWWiLb%RN
zOh^cL_xsC{PGQ5sM=lHw9v&Q^Y<=lckl@Fb&0Dv+=H%#badCk*J5QN9_28*fT+5a%
zTeO(7{Pi_m(4OSN!orFV4;U9MS_HZ_^Uj?Z(B{%lPfotLy?y<Q8B*y<Nle1R!WRv<
z+`73rT~J)Sea;-2A3uH^IChN9f4-e7WRKOwEt$a=1x@u-Raw`qTL;=v3_6^_#l=PA
z{H-mS&7jq)hue6q3>*AHUte14y|ujMzp>|}3G?Rtn<fNWFPj4|#?D{8Dk>-_IKwnM
zZ0F|c@9#k8ok-YLZD~kZ@)opg6LeYJvuDph-Q=pTuT-r-N6ZLW^Ic^D7g^Szm3yF^
zd#McEoV9Q%1)Z_R!NCEl2^bkbr{RIlTj&&4U&W*T^7ZS(w{J^xi|Gi6hOYSh{5+^r
z2U_>Q#l^+IpdY`Fg#mPkmz|v*2M<rn?AfzV%!qn@p4+L!wV=Sj#@6=Y=5+rpSy#E3
z*?0mhq2t>EA|fgp3oSA;GeH^9)02~pN1|cN7SL2FLxri1w77V?d%s-b>1n!6le6aa
z_w#Sdzt0yRAAcgn=wjg(FHcX-J$v^Gii)zfIx%`qdhqNSo3ykv!}_{)GmO*uK-<zS
zRz5pB+nhgkcNyr&hOVwI0XeyKMRp}G0;Vo3i9K?Zbv=)i$%;D+RaseDpedAfvAZFs
z1bq2Y0=i3l+qP|1J9$7;5$g&dxBhj!+B;za=;VLU1fzs~osEj;p^eGMLCqb|@mXB0
zOx)snBC?aWTmZF=cE<F9mYy6q;7|f8Aw|LAZ0_Q+<Sle*Sck`LP$t;$Sm0_eJHOn4
zJ9lD!-Z*oHhaqI%@5eVcr=K^O<~#ev>(`4TH>WW)Ow)}%bl?DkrKRPmVr^}0Q0F4V
z=2B3%m~K;VFK^YiH<1s2K0Q5sW5vg$xiSvlzkhGvxX~~uC`e)Q$tm&Galbzt=HHlo
zUC;65kykf2tAm!0f4^7Fe|ed&Gw22w8JF_%a`6d%YZfd}04<aUt%F*<T018<cWQcD
zTN}u;ixw{~En@h4W~MO*FK_F@g^FF>-KXc4zqr8o{oP&R2|hM@dI4K=Z<|d${`>p;
z<BiPh1y4>0g8ENS-<+7J{Nd9lr;LmhYRW=_f~Fc(i<n^zp6z*eCrp^oaBXe0vVnmB
zS1b6!HPAM?udiBzm-`*ObSbFB=aLgEE31Tgp3MC#&Mq!douIW|f7?1bw#b4~v^Afg
zU?wz0FWU9_`0j*%Kl^5U>FVv}H8L_{*z-%K^!+{A>hJGD=gC`@aOB?JCMw$hYUQ6l
zH6~eCJW6;J>wdpA|MBbBp*wf>99nNZ*Qyk>RD@MUIRDL!jUK+fN0)j}2W>V0t^JXc
zll$=D1L&m5DgRe@D=903O2+v3`$gW|44@NsPMkR-GQr2D_V23qYb&3hlbyTs@b~$D
z3kwfU)ec_(>YUZb#4K3N#LWEh>-G5Q(st|&=H?)~K_`1cm&EU31}{4mH09W~ZCgig
zudAaY<GT3$eV`?(k&y?lTnQ;Lxs=4r&gW89wd;k1i;K%ta6hKb*~R56BdEm(%GmH0
z-_^PI>;KC>KR=(HK}1Z9iNVOo2()p0>g&8aI~IP-xs`NfMIdOOGUx`1+S*#sd;{o|
zzFj3RnLtZ(j$B&m&AMDAx8Tzg&m+f=Ys-U9^|-!1UcdbA;dXw|jfJ4jYV*r2$4^h!
zUoF#i_UzfKH&u;6=h-M{to{A{J!q@W)OoL8zh1mzg-3Je7SOQ@phEQd^YC|TcI=RN
z`0$~GQA$Tc%A>!9g^u98405(r3E$t{Wtx=Po_&2C=$huK^JdSQ_2|~tY$+cX7nds=
z;5l;Z^YinQZ*R-}@%4H<=y<W?{qmsvvSH)KgC`~`KYaRh>E_$hR)PkHn`h6Ke)Hzd
zgQrhbLF*<af(k=i?YB~O0|SA^#zw94KY#t2w%c!Ez>7DsmzbHEA3lH1KGTPd0koeW
z#Yhq|$@$><^X0+iDs_7|ILMa2yHnZixy3&wMn+6Oj)!4_3TR*N!FjgTT6?~M>it=!
z*(Q?y*<W5?=XdXyTl*pV?CI(H;9GewEO2C+)M;MwBH*InmT9f6u2Y*gczSwn*tqdx
zg3?>WNK5R^Uj6ueJ&1u8?eBZz!a)n$)~sDCC@0qkI$`R>36H01R;=K7`0(L|O`C+K
zfF=|EO%~y5bt>TiHCdDv&Dv4&QpoPt3uVw?0#_@OZqydgVjIvV*F%S#JSKsvRM15h
zwpCvQWT$Tlcz<v2#QF34cbC6EbmNAEn3&ip@jLO8RXD}<Vg#mu8pMLud{^1PwTm`n
zmPSeGQW$hmPN}kz(xYDcv{O?w^A$b+iU|odfkv3OYzZk5>Ai6Ia&Wce!PiGw_2c)|
zoL;%*@a5(HfiW>Wtxk-_#>P1}HZUe1?+e}OHc17v5Z!aKT2oM0`HKsRprg94Ul#{$
z0olCS7_@G3#>|<DDk>}=KYj%Dp1QlcU#wW-+SJta;c>q`Xf*!XwQHbNlph}-fB5QE
z*M<!SKJ)El7cN}*;rn-S+0c#|GbGN;u@sJsjMO?G9Tk;ydYbNp(@&cwb*3gKGyD7d
zgL-w9m6Zmjrmi_TYd(E``1WmYx48bJOG~|*CU*&ninjXO{bZ4~Dmjoozjj&7Bhbq7
z4<8Ed?5mZwE`O)<eQ!@kN5>V|f}K^<L4h5&w+gh3tg*3ihDoN7RmqD5Hv4OToBeye
z{~x#aG#$s?Wp6=)Ehf3QLK2cLx#{WYW$j%dBQCzY(Zt2Y1u|3Z;<BXoM&XKWphmcd
z^v1^lxu6LQGfqxU$AEwd=XfHE3mdCISGolUUoI-2vNRlY0$uhs9h<s85j$5ffZF&U
z`|JNOPge64niF8$#xKw3IjP{shr|;pMm+L%dv5hlRN*|{Cwtk!>g}gLKZ`-#?;oI9
z_SNC~F*^zvYkz-pt*f)kySJxPP}%LlgM-aarwP3jYISNXetu3-S(!OCHFd+bZO0BY
zGA~@dT-|DxK}<}*US;<_&_3_!`tf0v`_j+P10ApD)+?o|At@*r`1d$;S<|ZNp#9U4
zo6{ct`1m+9kK3;B5euk8e06pB<J0>4uf#YgDJd<I0!_D~wZPwo2L&~OPHTO6nH{_U
z!F~11TMSl#v6X**7=l{oudlDyZcn{?=T6D1?7qp9g;hL3m%4rV`gLmm>f%>dG<la?
zw&Ma{oB%rB`_zQ5pj-1+1}}g0Wr1mEPdE1!P}>lceHbpR3|5bbh~V%8ZKVER2x~7a
zov7^YG)YCqvdCp^HsgaA7Z>MSiwOz}2Cm)kSU^xP(D_Io=)MbHL2Ew2iQjhD|F;8O
zQUn>0y;!(Kiv7Y$BXRw>BeP7i3;zA71T7eW&f%n_rEz(w`vnDoFYUXwHafgw-u(If
zTeg^3SXpIRNCy4|-TMpgUt3jz`q!#*;^G2=f)h1<!Ry~6OTDLmIBR}?Md{iYz2pA&
zf4@u<4y+9e3ToQ2WeZol4r_y=a~p?;tBcF74%zlsT;TjI3|;u;vcwm%>Puj6>>hvd
zz_Y~lT`a7vAJ6~)Cw=MR4WN5;KYe->)XoJOF?(`yGB_i;DvRkvFr=raTUb~usQmnF
z(c_G@(&l*ypProb@bX&qrFy%Hr<HYso~O_<zqws2gO_*pEt;BlcUNob>1m){=b&S$
zLPA95%$*BbU3TF@0BGHH?eA}*vXepkI-n~g1h0Dk{P`2Kxg_fPtl6`b?d|{TsxSJr
zV$B*J(82`JW#KU~F)vGN94B;in6!fSLxS5JpmI(O+~!a&lUbz;TJtbL#j}JZ@!Wj-
z_20HaYJe5{xVX5QrcM<N3JUu0=qNYns(^ogeoi?36f_Wh=gyrCH9w0k8n&*;+j;c!
z^Ye<6Pnt|wR%coF$D*mJsU(fT*2F|)l8U3hKmWFE+rWGCHg4D;AnTtE8lm}@YPATq
z765eW<^6x(%q^^~7l*D6Tcpf+^eF2qZ*TAB&6|zAyu1t&4lpcPx^&@^B`gdVmibB_
zIePTr#l`M7Hl=nySmNU1@>Lkt+mEaI_s5clhv&+!u=sd+{kT09r#n~Jaq;pVJvCJu
z)XY&=R|oa#Pfyo(2MrhH-38rXDykjU(dX&nV%35#fG#|>UU2*7&6Tzd>jN}Osv_oV
zmHqou37QE8oz(5<$k<S??<R>hBxm~U+S=$7=gx)MojY;DAt)$l=WEar)n{j$gZ7kP
zOtHBXG;`)m&@~DxgO^X3GNt9~>+9OP<Bs>qhO%9%{`N-GYMnu6XD8^SpzZhTw5__r
z9z0_D`t$ei!#8e7XliOsIGF<4x@!3!-Zt*&=y+uhpZ)m?x`u4)#^1+!rKLQazXn!R
zSb%zKYvT9IRaRCqfG%xv)|(Exx2d3@;6SIaI_N?#4nHp!mtCO1Xa=ViQBbW2PA$+{
zanbhkSFVVF*23Q2mh0*+sHCIgQ^K<9`IoO>LD$hRfI48Hg$r}$$UNOSb*kvPxV>6h
z^N#)f^Z7hzu3g2mNyQU%Ay+{`!OqtrT&!Qdd;v{CGirL?E_ruHa;|mxu_K+rjC-O2
zKta;d!lI(42D*;Aqo=1u#WUmPCRG_(*}?}07!R&AJ%8i~i<+9+qT~!-J-vYY`TPI2
zv2u%ndm_bG<x5{(;oP2oUu;4TXg$^g21v8?YII{`BL@%9nr~Klua=#<v#XT*-@kth
z4aa(=nHlEUR<ki=Tv;Kg<~OG!baj}biAhL=o08HcTW~`F)csitS(n?<;Smk0s5U$n
z*c)5^{+_F!A74&R&XoVhO3qHv40dr}P<8IuF*eZd7Y5HspuG&B)v@<L$H_Uj^S!*%
z)L!`b*uv`X?*cSLK79IgXnK4dr@Fd2Xs5K(<z>DX*T>s$$-f^L5OgU`H+tKV6@iNl
zvaV<_fF_1OH*Jb)hbdTEO1AUMi_Hn(k(ZaxxxY_#-@bhlPNpn+%yIlE>#ORYpHyd=
z<wm`%%*z8UKQ)=r0SX5Af(-9FSA0tsmcG6Q+Ihrq;KmIJP*M&Hn|8{Sm6cU#k)Ytj
zzNF&|Zzb(lR8q=40^S<$?Ba5(1C&o>+h4rx=<9QHaA+vXFjG@wE7~cubLURbng3#X
zF&zB-{0B8VU$ukA9A95s8?mcI^UK$-hSlG4K%-zUE-mG52rqvTyQ^g7gDJC;v$MIQ
zqoWxd0s{qOVq-z0(-xvv-7_;Yp^N^7goGx{oXI)Ur|sY0-^m{y99;C66VxRKb@blv
z{VoSuEYK%w9cIz-?%g{*g}D_mF#$X4{{8|TzV+ejSKab&pPqXE`E*)e!X#rtLkeir
zx*2)YTCfwe%n!5`!@BGZ0|RKw$8^0|Cl?o%Q>RXWR$7CmAv!xdn<j(CFjlsM@<oRf
z(!k-XdyUNO4<0^bWM^jwo$%K!rt6fGqw}Q5vLXEcJ5W1&@nTkW)m8FdUS1zwTvVPh
zV}`>d6@~-ba&HTWin7l1VG|b@2U#m?RU$BFipy-|wP6)MKRu21Sz-&?{<=B+yw>}e
zxl^XJ?Ac>8W5$dF2M;p#_4O5$lpHzG$efswp<%VopsK2B>O9X$EZ~8Kl4tLIUA3ZP
zE-d$#=aI9Ku>bdC@rw>8(2<?*-n|2zb=|@#{NT--p7^?-tf0%PI5{0_YHX5{k{&#I
zq-3QfC>XdGc5Z{xrO4mk-@8{-Sd_iF0bVQl>gsCH&2wB_T%d)pt3tIw=6?J3ZP8+I
zNVP&jYSI7W_wKTX#y<c5zkbj8z$b^8_UNz#9Xxu7`xL`YucyZIzh>P&6>1!E<<^E3
zcG<h`Z!_JRa{bIPDg9qBer*i8o{$n&WO`U8M!%_ekJ9Z~Qynk*94|3EvRd_^@Vxu-
zf0L#iJ$>r475lsGlK(88f3-9Ip4s<f)ytn%8;>(GFq{>vmU*yTTwZ?tw%prUx3}e5
z)&AOIRrcma21D(+IhIk|a%T3)TBq$0$&h<?X6EAQ@pX})%^xpCl(n?9wj>?ps{MFW
zoVULIzxC-&TPi=NIhW2WUHkB%cBW_Z5k^MFqMb2aot=S2MMZ}%RGyz_>$|*i>i)lP
z^Uc590j-3-`$*{hfrG5(=}%8hon@5Tr5Cf~LP12M%GTW5VflN%PCM2wpT9$Zf#Lp9
z1}g>-`2XzA&f;79YInaW+dXOWWKk)pTOZ_?GBPmK2>zC4V7MTI@YHcm4vq`6^Y^V>
zKELi)7xRn!{eQR3tNj*v_1ZNlJ=R(6mc`F9uC0mGO`GuJ{?n&VGY_?JZn~NC>f+*d
zCuisNKVk|CH@2TX^F#4I<L<k4++KV7&!%OUc$XFxZ3+qs5|NY3v*L~GY39zm*UBya
z<)XX%%L@ygch&sdv}n;Hladz!tnBQw{g@dJEZ=G*3vxL_gE=Q3-!*4`+a=!9^)f*o
zwy)pECufsk#m&I*fIYdMnSo)J@;3_xh6R>M{mg$r6T7QcuH5<Rmw0^5!f$VHS8w2O
zC^pT$rt|gXW%t(B)>n6SZhk5AIO>$aPkzw!qvc#bOBp^(89v?keKDn_rLQh6^<Lcg
zWyg*kv-f$*oehtTo%^P2Hxm<+h=jz71q&3m=H9+mGA+EwYAz^>et&ywnssG`+Uu)V
zuWIS*hZhxXYP4ctsF7!W0djtW*z-$Ey>D$uZ03`<TXW$;z~4vW`vW2(W~jUbU1|%u
z_mh=d?8W^5f0i#=w20?A69YqxJbIK|lQhYg5VkgIsb=splgQuC?f<WQdV2b6@%=wq
z8;uywo(+$$U7C4$nPE-eYc5{is~;X7Hm&(l;5q5^(@W~}Yc3f~u}eQEGuNur%hA!%
z%flnU%d4xXsE8;0ewF?IpXXB}r*Uy}r*6Of_4EAye|F8^sN+4`JpY@++)A04g2$IG
zUD{IhH7hkGC8luiiWMG`l9H>|um4^k$-r=y8Ro~QM>>V2ED9Fz$=m5{zpd-Z#ldl*
zjaT}~^XJQZdU$HTUJdv1@VM~kXt!z75st%085kI@AN$9~z+mG3rjUWbq4<a#`;M)k
zeDd$_Z*4ofxW#V0SrQ?)ca^T5rW>uc{r1}F@pU&#)Ed$jl)t}cRrzVjOP=+ht6?Ii
zl?H>{%g!gW!`1cP+S1q8UftinA2hAHGI+VyB(t0wpmuWR?QOZY_SIH*OE~<0HakBh
zGVJiYAHT2v;A0oRv*Z1K=kU*eb3ZXKJZRr|=lbv4V&Hg7OS!bfv+Dic?_X};{}+~-
znQ2w@q@$>)=*qU-=+MwmO*6Bw;^*hCHZU^#EN5b1xFhh*9GU_l$??G2?e+ib{ysC`
ze{oyxZ7E(AUKxvk|G)SDU%mVNzS{}15B`38d%OJb`F)?yS^v5`|KAm*{HcF`JnlD5
zJ0r0+db?j|XXmow9x3y@n8^np`rH2vNli`tb@P1PvKccZJTEmevzL5$;CS@dF)ckk
zzt!RE%_e5gIsNp~y}i|;K|xCGhZUD!Uis=(*3P?mKY#vQ8Na`-$U<hB@k8c)_B#@u
zpPRc$XSM5JJ-fO;JNjg;)jYj?eXpL@-@oSnzxV(1KHa&wIo-7UUCdmY%Aj^W*-s^E
z3=C(PU~#Q#V-s_@jra2ZzxV%}?g<YFSP;0_E%V2Rhf(|M_U4$)KIp{2&@lTjTJ(OH
zW1N2O1vIPgDu2HYbY!w0Q%%#^wA~M*JMQL{cS}~u7$&(){>~?3vEb9EB2aFfIB}wH
z-i@s~-mI*w^Sr)DNt@*aq@^wU^!c-C#fJxO*|W`ZgWTNO{{4Aw|N0=iyh+H5$n^8`
zrXGHnAz`7fs~Z{{JNHiBb|)vNDO08_xpF0B>9S>7ii(c8x3(D0eKWP}?X9K#_WvUE
z_k3u2DWYt#W5LFoo71zuy}5b)@9$G@%TA|l&U|@kY1OBb>b4>53=W?!ohkvP4F-mJ
zA(4?Q|NZ@KUiJR>^?v(*7XO3!85llTzR8ECW=PU*h}KqDcUN}n30NPuS42u`)sG)P
z++P3w{yyB%u`%uJtke|(AL_Kj))>rvF!kG;o5e>Rk8jvu5E>e~a@DF;CvWxgeKI#U
zPCs|0_`L1)lpisZ+W2Hwy?K*!c81~NqdW_?=iiUJRNlNnP*AYy$wYT4wsX~AUtLYw
zuWtT2zy9~^w6n9WCb3<x-0|R+Tc6CzdA8N3-j-=AD?6XJ`P>r}94u{{961ftsd~Tn
zyOxg5nE*`&hJF2vU>`bk2gS$h*Vq4ddtdwC%EID?ix30Df&N2ik-B4RT;)?yS9kZ-
z;p^kVWBwnv|F`hw=5*r*zL>);oWefp6-yr<@1O1WK@zkUwVh9P-L88Zlig))DlRm;
zruojZiOkH*^z!u$b#ZBVDf5GaPjAPz8#f}39y{hWDJv_>B;$fY>HB+k3q%<h&I-fQ
z-*eF5#=hF$QgQRG%l#&W1O_ggFkyn)`TOPfYvr<;85n*j-nh@e(D1ComXCoUqwmIJ
zhG!w+;iu1^KVQPeV3Hje7#Ov)Xz9F~PoAu7Y-UlbSFXHxYN~ehl?5**se1dUA7C#m
zIM`eLs8iiXoq^%Pn#jEEw{xwSz!C4i@n%lA4ePbHW#*Ote}8}V`nBy;b_Rxm%jh=R
z?*%2S+uQS}f4R&10+a&g+ttppDgX8+^6B&EtG%b|-P)Yq->%JQVy^BtXUDT$sga+)
ze-F>dSkd0K$KBDfQLgq&VCl<Cu9MY#gGx%aEP2m&J91~y(tW>PX+M4b{B`*LUsE3j
zeb&;}78Mg)wrG*k(&fu%pZl0q{Ok<qW`-NmkGqiC8CJ#5dj1vroZF<6dvDLp09gix
zeZA5b7(rgrJ=G<u4e}_%pCy={$i2NS^V^%7llDpLRsH|_{p-Kq@8dt-tbVuCy<1%W
zTZ&vmnwE{tpRV>(f0iFO;J_<k;9#77E+i>w5&Nk#zpt*ZTgq?u!(spLyYHt=o_slD
zZTR}Qs9hy1+jynZR-F4?FkdB4j9uJh+VttmIfd0uq-|d5-Y=*7=>b0jL!N4$13Sol
zNccgqUfiA)`TKsl<!z6iYgKw_{=YBF)waKinzr=70f(Qze@m}oxo}4(eqW6DG@XkV
z7rTGGk=$>(>uL4bS*EY9t(|?WUw*xFJD;Y$zQ3udsg{=3C1!q`gdKM_gN~S5?B4G+
z>D{i^dadp4(t4ltrcRx@>+?D5t*NJ{iCKEsl)kzmT~~H~p6#uj#p>n@y5FCz@9OId
zD=65&#m#+nXL0&vO9loL>pKm6NDc-u4?JgKVbM@faF|r`<b+`9n;U_Rjg4)q8BEHT
z`_B){&0P!Hq6-?5iaLGrWMEd-D!tfUOSa#u^48z~XVb5*ua}3%Rk}uR&od3lajU4X
zaDKjH6)U&cohzTGrQTg6^kdWdeZRaeFY`_QA;ZuReIyOi+5=e(!*xBo-|gytSj-@|
zG3BI??awEZecR5fu5@na`}K8w{aTP!ldfz`cDMa_L|98#_iM>A!{hz(*EgTHTYck3
zMCq$5o=1-!owQ`tDlOl+R-yI(f8Xa7uWEnrAYpC9MyHJ%H!chADcBif{<Zk!CDqF(
zKRE5J{(kM`WOd(k28Ihch0GWZn*aUh^ZB3!^0&6<&p$WUdim+;`sPvFb-dg8<;_Ca
z7wlZIYE@8f?%UAo+1c5lp`lklSn24jIr)C^vsHWc#AIe>f||zt{o$3BJ7e^wFL~eg
zd3)~dWuKp)fBkm*eY2QXmAlK|hb1K?9nP+=ulJo{a4=zFWZCY!B~AWWFWJTaEdTlW
zIcTg%%C4qjv3)!P!-M4qp>1SXh%qoQ%->e~yNp-T$YtTeg}eU$`~CIh^7&e}wy|5c
zZoRd$czIHC^40b6_LpZe%xe7oet$gZMv}w)_G_x&?OcBG*1x~Mw^n>iI(q!L`JV8&
zxOIB5yDF?McZkPTIOg8oc6D9s?v(AfudWPU?)Lg{JO6di7CPtBG*wkqO)IOY$H)7x
z-`JRZb#Ha~WzP?cGBFo!bO<WX+9NI{wd%=}6j-ImXTAYiDY7suh}?K5Z~N^M79<aV
znSTQKZ9X)tTD59R_I173T_v8NOfyY4ddj?c>+bF@&wg=X;i<D{uU=T_?7N)lLm?<`
zO*1Yi#O^3?%*@Q}>g$`PB5PIRarEfXU2nJD-jaLU?C8;>E4OV6>+I~5GRv9q?A+Y!
z9e=KI^YLBlku?7D|KI)pmtS69esyE=@wWR%CvB<uS!DbF&*xv)_y0@Xapm);PoJjD
zp1pd}BBiU>udlBE|4+)kZjW2P+}g6Yw`QLEyh6^l>cplsvw!uZMp_j-IH0TbDb8$m
zZ!`Bl--?PK{J-AGSeLyK6J=z$um@YR+LnLc?(96<=<WCGcAuMLsqDFG{rc%Ds%mOk
zpPrnYWm&Ao{DPrw%Z?oupkr5NS(mRf%fGi~(j+0zpp=v)n>KCw@~B&1%g89`Qu%h#
z`foSW)rxIb?b{dU=;#<8yMEQGpx4*d+D1IFH8L`qGI8R<RjahtMs9YitgJkB?%cI0
zn!zS1Cj@$>&HeWOd8+^P`SWzEuhYDJd~%Fj{=8g1f7O~bKK8$Fo)-}oR`#?ic+dd4
z;|WyJ9X&eJ!}J~K+|<0hb^kuJ+rO9^9+!EMUEJf+$H&KgLG{m~0xWq*Oh{<a_4xYO
z$jHc|-FH8I|9%~GCi2GQ<6ghsUAue#&olF1&t~WIOlNZVJayW%Wfv|4<lfk@@Feex
zuV26JdcW^?$@978uNL>)8O?nq$|rAkr@*+%)wQ*$x!JVniAQQ$nwF{Q)slI~b8c*K
zoH=vmsq^QrKRDPdy*BsO7Eeh@$zPx6|6ju{UvnW~Vdek20??M`C(oZ>f5fN9z`!ss
z-5Anu11CW!VeeK_vPDZvOT}|q>dN%<^P;xr#UB0zI&0MW-HyW{atvEI^!NQ(WcTNT
zv+egg#ajCM)4$w(@aEgw+omZe1g1`%`tqoFyh+SUTSzZVqrSd==iR)>X-mJpzMg%c
zfw8N<KRhyW=1Z6U8J5M%=2gGjsdo7JBv5xUH9bB1SdS#zsXgxPe6nBOY(9VLWyz{V
zi=6cLewlRY^y#lJ7WcpEvwjy47B<bx%gZOd>Q1My`nsRRpPqQmwJbhXqQ<~rw|eSJ
zs7Dag55qQI>1Cj^vp~x*SBI?yT?gem%f!>R>dS;LcXc-xKR;(0!+AhFH8u6*CLP__
zT_I+(eIp|yum9~yjRcJku)o@K`oqJ+U(Z>;&p0(jGip;xr^?HX$K@u2yYcV${a(k$
zCzG+^!X9pMy^OcFwu16%pR9Gt=9?goot<Us&2RT(L5|t%YipyIXI@^Gd1;B~t-aOT
zUp|R`_uydjs|yPchhDcXd$XdMoxf_siQTbpA2fjur2Brid_Jf%S^aM3@sefkE$!{6
zH?4VXCoUnef{~dm<Jp;+UOqlw96%ks=BH)5?=DkD_!`1`&|b7N#;X3`o?Bb9uN!oH
zxmW#u<$?tcWxHdU+4-(0_uDMei`^xm$NC`q(BZ?Wn{Sr<_>j0Y@9wWQHaXqXmo_FJ
zw+VSss~59lLBHKEk9I!UOHWTv7Znv<y3n~@%fjMD$t=Uy*Vl*V<*hTzyR+ift*E2N
zk82wn2PYrv3H<%-?QEO<ppxbD8RK0gFDErdoqu(8_4KIidAjX~7allpz%AR<)YQw<
zbK>czm;U|z%_};qd}}kek+Jb?nV5p(vgKPknz@&}|2Ib`a+8aDzueX2e%oa)USxO%
zxw^JqTNAlB@9wV5KR-TNmAshn>C>l>;NZoJ7Ae_&IKbR?nvvlHFV6yINFcz;jBB8t
zD`JF)A!FMdzvW3uN$V^EbUhKn0_~^IY`&S()zNWbN8#fsGiR=xF=Ixy-Tw6Ra-hVa
z9k%8}z(Pw_R@SO77u~Ne^%nP?WwP?3z{gWlwZC2skJq%fkKh06>Uy5(RdVd&F}JhV
z?_CzUI_%`bf)%m5%X+V^TD5A*tXZp$%h$(%`ZN3f{mTCO`nvzcix+S0DqX!WiGiVp
z8`6Y^JDh=mVb)gYaL%gr>&@pfF`S)tH}CqZtE;C@oLG4D>z_Y0sVOO2PTW6wdwc%%
z1C7kS=@n~zXPdn&-~W5=zmNU(CRO{x*T+@8-Fn?5=Z1lEYFc5z!L6=tZds?MXwI@K
zeI<JR`T6<lUAx6z-q@HtY01sa>92du?_K!$`MK>(PKJi_S*aN90|tfz)2B?E1|Cu?
zeKkeRf8LrGFEV2HR0N8OigtB%1qB35c<Iu=``+J<($dmRx8KUG`l!b<KmPWGh0dlW
zF9Kxk>tfvd<)*6KExjJg#m{dZlXmUe+UWdOyC+YWu%M--C0hJR>Z(<%LZYLquYSFC
zD=IWJ)N~IYH}~bIr>EOaWMgpHd;qgSz;J-KU}ub!b=ev&F0LnKyHg{lfjVQLbaQEe
zW3x%_Efe4Qc6SR_rpwsZ?Ri+1=(%deiV2rr=72lXTWfw6xw^Sk8J(XoXU?42|9Vm*
zXIU0M(_QgV_Tj^ax^*x9+y@2R-TME3qqbyBl&kxZc(?exZSS>j@9(ca+AXeaXSeU+
z-cO&3N?%?&dU+-T!w;R)wR@G9A;%<$eW3m9Ok?-WX=j6KYxlksVX%AmegFTx_bMLq
z>PBpEXlCOL%E?)?E$8N<FJDSLF9rMCE(HxN>@I(A7V}DSbNcyfZ*Fc*jl5<$zj*iE
zO*eBuZFNvLiT~=%<jptpei=_o-FjpHa!_;mdR(>d?QOZ2ugBM~ZE9j#x^(HvRja(#
z@B6jN$k<p^Ts+<C^R&kgnr46gzW;x0GaK)vR&Mbr)23Z35IC{WxjiH%X3g!q-5?W!
zV`AoHWoJ*FF=IvI;kL|ocXmRu8Mc=6o7>ypx6QXLd~`%thw;LsCr_VdetL2eQ~|%d
zynObW`?cTiM(r+J+h}A=T!(jMdhEWMn<Y)>HT3nvqoQWT=uLn0_;F}loZj@)s-CYd
zENljC^?^4nt6uN@bV}R&@62g74RYe*%Rv{If`)*eot+IDbMfrz=?Mu7n-*8|(bd(>
z&1=%1zkk2pOrJmV3@gKd=LT4M26yWJ|GmDq@OyRM_TO#uSsSufu2~aue_!qTUH4Xn
zYG1u_rDDU0HK1k!dVhFo`O4L+FF!jw`|8&0@UJf~A1~><Uiq+995god_SRPKvfZ(B
ztxB`D*wy?f`1@49-Z12Oq)be~XC)=2Eh#63E=w{nn0R9rWFIWSV-XAsSh@K5uODn?
zU%%^JiIu3V?AwD%?>`<9_MhSR!K<#WPRcZEikM!^35H*yZ*FXKHcmSe@ci7|(qCU*
zs=Y41TRI)oNo59=1&j;~2EC9G1yJ&YVY~E0Eu71Q8MZh`N=im;NN5B_*NPPyo|94|
zC+)MAP`0;^2PLJGE{oARv3K&y7ni~Y%+n&KEtRvaTCr-?sgkbnRqNM>2LxOQy}o+Y
zsw=xnv-!m;+4=M`w6wLor=^01aW>t|Id$sPu6OA=r!Q?vJ#7;J8qqn7HLF*=Tsr+p
ziPh9elNR0ETYY+y&fjm__lK62Ztat^U3IXTJ^R*{%w@*CCr+Qf+`=iGviatf#qRvA
zZEdssK1p3(?tlHt%3#y1D;h_S9GP+Mqt^F()$2j)iBi+k%_CQ@Uw?g;Y4(&EGcp#O
z(c#m}ShZn8fZ1%{uV24zx|yS;qmyI7@FZ*9c0LA%b?1uyKQ9b|g&Kn1p|t(>+R)Wu
znQw1xUA1Dx1!(Pgaj|>$qa&T0Zssf#?(IP9oyI+_|M$H9%l7?$ecActt{iA&2BjTV
z78aALW1DnzV|H8!SZE14jHd4A>3A(`>u6AA8x=JRR3rM$waPp<#}YJs(ACvtQt-gx
z@=Ces)2A<A8N58}c%Q6H3<Cp$O&?}NGcf$oU}R*h`h3>>>zB*^v;96=nHOm^rbdEB
zkR5uzgGMx#`OI9zEv|RsZJGI<sJq*8qxXKj77gkdJajU)*ulWSFyjceI0^;ba0?ne
z^76X$cKiK2tK-?KDk>Q#CMcdddD3t$ll+YLGe5xA0+c*F#9I61qC2Qg2ki}5u|k7a
z)+*%S!Gp^#_dI;iBpn<TwJP`awwG5{2G6po+yq+E`SFo!Xh?{LmKJExe3>vK!v{|u
zjH;i3A*S_g+T_&8O*eD8dV52&va$~QS5)kHX|o=5sxzpg8MQrcu8^>>@ACuh7IXcM
z9yzk2_V>5&nDy({g;iGWoHTi|Z46uf^P-(5Wp5%xMMO@#EjztQM^sc))7CatTt6<P
zqGAW=*a1)p=f}!$K;00dAYouA5Owd9nRxhNKw;s=IeyDeojN7eCabKZB*nYr`>U&`
zOV%ClkuY3zvYMSwCZMu%C+MVz6DK@wzWwI*dRpqr1q%)YcYa_j+a0?)e0`Xk+cDAW
zpFe+|I&tE~NBKY9f<fD*zaEp$&p6n`DrJ%}At^a|YwBsSrOTIlPnuWtO0)LY%jKYE
z=ffZdhMHjQ%Z!MG3S-?{6}>$VJOtA#t?p@6{cX)0zvW(DUQY@vw&dNldiwO~$xS+~
zEiD?BmXV;VIv&1?&OblTc9YKPlfM%a6IZQT6%-m8I(e(M?foFoIjEpBWWK$<y}bDO
zxtCtwJ+~cEeEs_F>d5f$>rWJz9VUTp6|MY~lA50W`pe79zSrLG`<=HocK0=KlNLH>
z0dpFJHrG&5aRCi#Z%90>;;A>?yS25o>hIU<TZ^CjiHeCy>3!*e4rH>jvP#)jZAnT_
z1`X7M8g7!3l101kf(E~<zPwo2E?;+}WZ7{U`?{FpeX`jVv4Me#%P-%2vU79#`K+Ix
zo_6*0d`X!X{_sK5>eU#fJqJU>vsNtGs9|<MT%2C}Va4{t3nxtylC`UeDBB(T_t)28
zFR!kbHWf2>7C#4#YpbfNf`<C0>BWNEfiGXa1YNFqb$@+*>FaA}OO_o6?P;53TfI%^
z^rY0tQzuUb`uX`yetsu!dyd)cX?n3)3ohA!#$Z2uD3G<O_^|4=-}2y#7ca``FflBs
zOk}|9*FDhEi`}*4(xsrOQ>L7FSa9NH$*V6fFK1m}H+RycNhX<>R8-Z~wG|Z|85tRu
z757>eK00E0UH9~){rmSjIXl~iJh44>>Xb?OyO^7A%eH2Hy{plG`spN<(zmxlZ{EB)
z%RGOck+HFFTGg2o6P2%SPWRt=H!n3M<;BeOd4XA3S&P$kPJ<eQ@AiI=Yi(_n)H3aE
z=3b|(tnAD!rgP!ML}gJ?QPr2b-}kD3Myh`P{8{z&YPhc&6T^ec5*TBP3=BKE9z00c
z8KZaf$PrL7{QT@}a8c2ws&8*Ht<J7)X>T{@sgLtcNLaweBe7tnak`eF;YH@uXRK^&
zr_P`EpClqAw8$*?){7@6C-c6ZYh8YAqO!Zs)5@5foHa?w$*P{Frlz30v#b1l-i}kh
z3knWy-TUQ|cahaxFHg_F_xJXuMoz2yef$2ZUAv+{eUb+Un@w|XnOp`p^=4ysJ{cJD
zL&L+>Pj3<t5Lj^FfCDQl>&o2Q+m>zKb8b`W=_||q<yqO;U$0y~@6w;2pH1uk)quv@
z4<0<&)!ltrI)BeX&~WR^l2?uFau<%v*XLN>R!&Mv3JD9l_Q47=opf#c{kqk+ZbdzP
z`c%`%=u*N$OMjb>EQg<mA3Vr<9dt^lsHkY>&reUexVeK%O17MvZ@+%V42ivezuo@z
z;V^&d_S?ScObib;>ukUM)=U<&M0n5(8lqW#Srd|`_f~&jwQikX?5>hPFR!jilP7~}
z-W@wEZszEIpLYP%)?6L7cGBU80lUlIO05OWzL}ba_S^s45m)h$wf67V>#we_pTB7F
z;;p5x!<>)KGp_$vqZ_rwLsV2W>+-T*P$#louF8Xvk#Uobx2dUV)%UyQriG7OF0XV8
z2?@zK+9mqyQMZ1{von%^pRbsl8hL9^<>rM}#X&(qCHHH;XMTKibkdR~OH^3d*s?x9
zJNxU~?R?XU4+)`RVXOA+xl^DCnq<J5q8#<6d(W@=<hgj^m*C}oni?7&oSdAX2>0{r
zd+F2P-P3agG;&n>>WcQddi$2zH#ZDDFTJ_B8C2T7`1AAgyfa^<jvhT)_5bhp)a|!H
zQ@XrTCMQZJ3078C&N4`B$}yV_DsnDdxS(wp9uxECq0wiH9Sc@U8mDRK>iT+mdhYuB
z?Y8f8&?E-7TH}K<Xng1Mv$L1a&9zRAoc8MVYhU%sn1qA{X=i3Ee0h0!eBs~z`ag@~
zYQKioem-kHY01;m(_jC5KL7gue_!?e(?Cb?REx;U-hE>BL))_GNk><A_tcp)Up5-O
z7m}4-``|%>sF>KQ;^*g<74M1jw%>6eZS%=ZIyZC7K(m&nrduDX+t}PGkz-&u%Z1r7
zWneHr@w6!O{k^?fnwk?2Kb&y+Wk_l1);oFI|NQxLWqrK8r3~NYnR4F`F!R57aIhKF
z$9=c+`8>C5(Ck`O)vl^<Z&u1$mw8MARi3@l=C2MkGOHEkTkgKQ?&|7r&@|Yjkl5I@
zA3hX-2DO;kcrw1^<mIh1GB%EWa*!3Z(ZVGYQ;>^Z!$LZNN{C8UkAcB%EtY{I28R67
zZ*L+kW%}A0KVP~OboJ`hlW)tkRa9I&Jw17u`#Cu|L8<g*in5q))Dp*Lww3<#?Yz9b
zLHSArv^YXbPw!gp_Pfhkxy8LEWo2iBYTsT7!$T>bbidC3?z-!4-qmZ@ww+M?oc;3d
z?(Kf_Y%;A5XRD~H-u-Zp)o*$5WHsNcK;{>Bca;Wj&%0}qcgMo>{@=PXtGT@U=U-nN
zy?oCeo5*QPCrl7fRabxA%x`B9!^_Z+pM<rvzqLJI|K)DRM;#p;wx3QY_k!kTPZumK
z@96Hn{Cs}>x}C+(L0JS8Wh$<2ZlK0DXk1T8Sy|Qd-@kvq-fTYa^X!oKnfdnd$;Wyw
zet39z>Wmo~R>v*)^mbS(DuS+{o6*KAt>#&@Ge%2C=gRB#``692E?>1_!-WDx28Mmz
z*eb`>Gi)k1UAlA$H2l%g!ExC#PFG3E$$OfP;ao=jvZc}Qot>Sh&Y82uuJ)IPkx@|D
z?!6axrABILXnY7!s`06;+$qD?F2mRE<>dt$r@HyJ3^Z<{sj0c_GXukiNUV)MR_3b*
z{L`^FQTnHWPRZ8N)eZIZ?3CeapX0aOZ@wL9kXutz(-SnGS5&k~NJvOTKp??NoPlBf
zF>LKy{(#8Hl^Zq~Kw5%#OZwdLjUyhO9$&Yz_V+i>N$2KTtAoZK0z5oC7C-Nkv3&H=
zEVxhJKF^BLPRGI`LT|dap`oFdpWn4Tm7k}~nX_h|ZS^caW`+efvDWYGMZ51V6YkN_
z(V22KEx5K8G{Mis&Aq-lxYT?1$*N~(X3nxKPFwta)8@^yZJw9yj=p0r9V5#w9utdo
z)r=Se!`Vqs^H%;}hCYbK!0<siBrNRJIqUaVrs+mU-Qj()V_WFzu)AN<)qG|YaC_~!
z4H}o-nHM?j&)>hIQc|xLDs9d&i=KR#V_liU!SC;{U%y_hb$*9&`neM?OHMs3IPtI`
z<Ndw8t5&ZLo~{==WzwWYPoAVKU9v<&PtVV6_Sq6pcE!>+WoVFZU@UoXeCMSDU#GIL
zv1J`-V4P)Hyi7<~*ft=Ija~eX%=FVs{q24(xft+kW$<zl5s@V=Ei52|)zy!KM~geL
zB~tkX+qQ-M{P|PLD5b-y{9TUKac#n*Ton_ao}Qk4a+0c5)t41=)o%=4-QB$>f%?R0
zXQfJCU-Jdc7A<scpE7;=@>#Q_L`6kkHnPhZ#PH>BO+3tYcDA{{b@{uTLh~cc3?G8A
z=4iGz_xA3Nyua^H@{Sn2URmofR#w)c-FG+Xc)Pl~dincbKiVxWDkrxNG`#%l%gbfK
z4_)J`-<qzC+UmvE?)>)F*6b}|p`lB!TnVxL_v3NZ!&dPxU$4inj^AI`)z=3acjFa3
zJbOos-rKvo!&OyPi!5Y{tmdv-w{F_)x6|g&pa1LYYxVZSiB`f44D(a4%o{K~;GQ&T
z(wEKi|N7MbI4u9=sCfL0b04)fr=7hN|NmFGZrq-T-{0R~-+zC)gn$5e9m?NdU)i`H
z_D<7@T%<m~X4A<JJ5@?wTyWg~@9X-n*P`=1Cs~!fS)o3!!fEN!rSs0UOt+~1wgxoq
z@b};M{nwfKZ5BLukg#;=QqX)uNMYedAt9kJ$L;?GT9>`Ku(SBNgdID>1NRK9qn6@(
zzTc|`jnT{h`@jwwDFUrT0?j#JT<jiS*sx9Y<muCwpPZaLb?)4?mzVpSNACaqZui!*
zw^7WgAJRfYLszX`yZ2R9ZtmJut5!+HwYRpu{PgtnJdbAato!@+s(`8tB_*eRn@=4<
z!NF5!%~}<=x9a33ox`mR3?}lJqh$;X1<Xc9MqeJb%fC9(DIB$<VBwv-?VC1l2CWxp
zm#>S+zP|42Qt#<L=~97_kt_Gr{*Ei%8@f7d)ykD069j7x{{4O*G;X_c&6+hQvCe23
z3C5*-dUCSr{od~-UtR>t+E#_^+_|&r*URNscbDh4oo8hD(TQcAj^Tjsiwg^zK?@3P
zf4|vmRr6y5bY9S1z82IYm$EEcVq|PQb=IsbtE<U}4j(T4@ZjL;b=GtJT;1KPH*oAr
zxVXp_)RqSIVz+GB()J#CM3GxuZ_1auxuA0-FLnqj`=}jWpz1wsh93jNf};=Ez-wC|
zJw7PeAP<_GZ)|M*^!@wv+i$0(MuIwWpf>)GA3wD3y}2U;>T&qj|C;>m&CSan?tM2G
zS|72|36zoT>-Ma)saOe}Q9O0(6lh{&OVLxWwJ|$`j`zt1hlNeE`~AlF=+UE|u(3e!
z_~z<|y;|DZsoQUZnyZ&J85m5sr`>*AHoFh%CM4>EsJLFtg<D&*r_P?eTGqPkMB3&|
z(5&s5Ggq4V?KEbeT~_+~TIQ`SnY$kMS#PQSo_G1=_L$h%xo!ON>twCVR+PWL$J>1P
z>eZ{D0)&lUZcVSW`Ki3^v;9~v@Pr~t+bQ$r<yo;aFwDOWTi}G`28IUxi2ZeYi;9c4
z7Cv^ndhME)on0KLi#5YA`O3c9-)`soWGsWy&&|1LeBLH`#kI}1wq$~)Oh9Es_Vsn4
zzP`QC?!nnPmchd6epAk-8PDZpU|@K_hB+z<O1E;APXt|ETweTqK0iDyZ5e1L<!8<P
zeYK`#ZzA}w&P<P-rsg+iMW?X(EWgI-r%s)klo|;ds?IT+y=l{?b-yJ~Z`zV`(}@2H
zBLl;OYMen^hM3dnMQ<`6U<b{LrEPxs;o;$|ySui6rm-Tgnc62uPV1Akezwr*$0|_g
z==t;P6B866>q!|HYUHprV|Qel&Gwy^dNOS@XvyHpl`DDeA3l7z>@$N&GGwK~qL(}j
z46}6EAnS3E1D;`>g1Y+iWguJA&dsUh&f0T+qO$vw0*jEC7@g&pS8m#51epcx=;&}`
zez~{mtI=HU1(F+Y=70*{A0Hos0t~c(szeA^BRf0+I<UWT-@bohS1R^zP6tnrE?MHj
z*Y3P@>C#;l9~bGI4)XBmm^69v*MscxGtRY$Yw7A<-Ija1<kb~TP{;D(#fu<iT3T8n
zqM}O|EKs=I`N0S@HGcMNXkg&PSFc}#h9G+7?c)}^_lNB+d+YO@k>SB-Y<;E!{^y<+
zt=zC7VEz7oyUO0(xw)wQb7899bZ^i`M@PrTJ9*o6P6q`BPP}yaa_PrMuC49upuyN#
zcD1`+hE%LXOv~Tenmzr`pFbGW@`4Nu^GiOv7c!y*G>EgsptQ8~)`rApyZ?WRFKfoF
z-Log={hrT#a`k@-j~+Xgb)-Y^*6#B4pfx$q=T)C8k=t`-P2}b;*Z2Pm?H1R+_V4fS
zukXL-u(7aYTv-taDn$-DRqW=IwR&+geg4$TFGE~iTjQ!;s!p9g{q;q6`Kz+!cNVT$
zqce5Nlo{t(uuc##Fcio_N89K4Eq^JpzVPKGRm-`4d;k4<UG-vNJ80DoXqxEP-S>6N
z*YE!qHCfH~(zUhGrSI-og6dmtF&%@sJo=NTPhWm=vbwglHE7XP)~34ecgtUYczBrY
z)Prt9)9DNhHE!5P^v-S4`TF9bb7*Mjvfw>#1qB;o^rj~zC4pL$m7kw!T3SZhR(~^@
z%O;Plb~)S1Exx7fZPe3e&p_kHn{MVvS(U6vJ3DJByL=63H2n3owU@VKUIvXIy}h^h
zc8L)KgIy!GW|g!-?XMEh!lcD+y+J-cJuhV*zk2m5W&3UEJXt<2uAtl7a(&Yewzssm
zzkYDAIXt%9YHn9w-?s$8nxntIz6O=5z0&5Zwrvah`0*oXCgNC+<l=8{Z<|+@JvlKE
zG?q56@|mRbRtAP2a@aCx-hp+oyRYo41ueYvW@hILxxOw|R6yXu3s4zU@X*P*bzbSO
zFPT_Yn0E&S1%U!<$`p~KM~|LN+dT7JtN5uCCoVLxa+?%A@o;r@_5Ahj`~=j&t3%$P
zZWm|@`SW@E^=HnUc`e6vX?uQrudMYo=TZiSA9knTmhJX+2c>6JT(MhPa?v&&@2_9K
z%B}clhj(P6V&bk{R=o0dG1g^o0^Z--3!25!)YJ3BQjfGwzqzk=H)x%L6*EIa8n*r!
z!yO@Mvz!ZiDnD;2etu5Oc2585;@x+nwq{Mewk~#cR~J|8zM9Cuz(CNjs+!-N3TJkE
zP~ET`wsir;A9W_vPcH=x7eNXrzvaPKuU-W$f%*J7cz@mBCj}Nh=}aFSEiEn0|4N?T
zWK#U>OmqM<gTv?JSUOn@d7vXno)%b0v7Phw_6CipZNI%1)Du=!)igB?UAb~4Xtn%o
zvs@qb!`$c-4(xV^(l+1y0vd&^t^KRJf{|gt&tz=9W;W0W1ImzfvZQY6gNu3Fy(itt
z+YTB+XgeDm9DH?kxPIic)Exr%P9TkxnEkrf(%wG%95Vw$1GW-#hazG~dg`=k%a(di
z*HTt?&f6XhT0_w<XZz*DVgA=or^lPkeI<DF=1tJZLRQu)B_$=F=Lg(DJ8=2hosS+p
zT4Xg>OIv#~xD6C;bAsWAKd3m|Q@MFp+1piiwZCSZV`NwmiM<m6n#crIlb|m2von&Q
zMT61XassQWc7YBo{QCZWJg7Ja4dyOqvU~jI=4Oy(;9;GB%*>T~aeFjQZvu^=K6#Q-
z`{5w_GUJD?pn;yhf43Gqbh7<=C3sme14G8N94x&?h8oAn$eG7_B$apHT^F`C%5zeT
z-gK3f+1J;B=7slEe)dtT>OFPJ>*m|C+`GH3mT>Kf@$l#XE!_!^uMGt?>u+vO2VD>W
za%K9tIf03Z3tzfaNS@vVn$rsn4V~%7$gtoh_Js=KERf;fOXbd+b8l_AcyhA3^fl}9
zcWad0`(~W_Yz11C$5i8jZ;0VR>oWiO>p&A}S5^deb#@xgWoB^LjD1?Nqq8$GGBWb;
z>m55R*2e9PdVH++GH9H3&mJ3BH#aFAmOb~EdQT6Didr>kk`QQ1%Ur*?cC}HU+f0Ij
zCaL+(TJq#cimHl=hJwO@61_cFFw3slHSs#9FCA*-<`rdPcyL?C{J1A(MHzGb&(F_W
zGcGEHhJ>u}oo#k&N8w_*suzl^EG#EB>0G^X<;C6d`&W;23i~dX3XhCjY5jgrFf=*5
zl&P55(7=EgX7}{;^z!oy1MhG;*nT5t+iSaI@JOUBIM-qg2Y%4<f$#V0<I8r(f)-FN
zaBTKbuWUtckW~oIKC8C-?z(-ozqM3VT~D4o2^x9@P0pDxFfjc2k2N!OfexIsvI2$K
z?suEr`(y$O3pW}W8`}mviv?XxcI1f5WyueW>F4H5y!>*?;fE6rKfD0ia}gfCTrYN)
ziIhiwclYjv(d!r)7(QIaS{i7*Dcc>kK5lJK507V1X(^~_3A&k&SHfVy#m%52a?hLz
zsjc1H8L~LXZ1$qXi%skPRDe3>cXyYY&t;K+ShVxYN%i?AQeO6@uckCLHBFf?VZoFs
zB2S+@0ktC-G6F5wI8cgA1_p)?|F@RcFO0nYSN?eX_0qF1%N`X>6_w<UYVP5>IAg~N
zmX$B&H*ebdh|8KY%;l!1fUAn4m-@9v$0;qjB@3<|l9*ViZG4)8-)e$Kj`b>*iz-bk
z&%S^EVBdR>zoGV@ukYLa<zvJ9gI{;vi?5LD**N*T-2r)vzxVbp(l9bKEOgYH`G02l
zy-M}DbLU2GPV=?0w%(j_a?+lEzg}C`{3y7Y=~HZ+cE+Q;ygY1u+}yR%+n*hmuRp^s
zUo+wL`u%qQe_h}I>C<Wb>2pt*m>L;PdU|^L^1XX)eSLjbUd>9kVK{I<nGtzbs-gJO
z{rmI#?S5(8um4|bmUCmmA`K%0g9)eg_uFWPtvNAGH@fK0kB^&-XSVsxv6y&wcX|5X
zUtf2AzgJ!S@u>Ln?c2@g*Z-@WHGB5uyLV&DlrCSmwl=!>dTjaA2M3#9zJ7iB<Ye{F
z51RRxtzWONtE;>7->=u74{_^Hnajz*yL#mtlwd!{FCJSGIIrSSr_IMB!j=UO9NOC2
zj4Ui>u*+2_Y)(IauJ-%g=~a8@&6_uGQ?TYqfBU~v&fERg*<JSbRQmkdY3uj>(mLKJ
z>m4YPnVo(5(b4Y9moHDAH*emZlFPm`EsN7`p7e3fzP|3Pule06vAfHjo|ve7b4Ova
zT<w>OI?>y79zTBk^4+_0q2aNiWois2I^5vRXfOx<*`J-6>6x9KopyHC)I}OWD?^NI
zZ04BXuQBEp(>ZZFfB)R<^?SFy@mUs8U0pqCiAL9%+2;Ct_wL=VJ14&UZt2PpEmiSL
z9N*sFp1w8v`m(UqOIN<UuU(|>H^*aANl8gcLW08UYiqst#_1aiGe}KiMecSt*c;l}
z&D&f3UCpyk&UTi{&HeTDw{G3?n<*_VJ^RzPm(QNhuRk|UHyRXDbFIslMXi0-XZ`L3
zxBi|9yWj7#zM5tFe*gcvd6my*u8G>J1=`GRJyY}BjpY8P&t~WQ`TP4nJ3BkPjE{HK
z)~%*z&z|+1v~AnAGddG5Ix{eEob_~Z44GqTZ2#xO;r#pO=UQKXpTc0lK6Q~s*Cv!T
zj>{HjZLK=id*=V%v%gFJ+s>aeXU?iUnaLFu7R}AgH@D?RtEs7N%DA}b%ImLRzJC2%
z_W0}jy&sQBSN{2Uy!g+Lk3w0EZrf8%PST0kps;@Lx2Q=eA0Hjf%*{P}T)uuzeEnb3
z?RU$f`Q&V7fEoo)f*3M<P&YgLU<RFXYQ0eL%eQZ7_x4m){(8AQc>VRuSFe6u{@MIa
zfwNrIi-nr276;1MR2WQ;udB5C`DC(A^tLr`WR`8bckkYwU$0hIKAjqFRQ&9W&G$RS
zp!9wD+O=t3ODDzG{Z!50`!($5Ooj^^P)CgpSl-;2>^@B|HmZz`7qozM=bKHZH`V?w
z<9;z`>&1%~LBm@suV(H1e9pS~_1f*z=CUyGo@PQ>zZYP|{o>C|{r!K8!sBa8pPiZc
zdHUw$<YY-%S>L^J^P7wqEdHBJMb57b4#|}-mrg(TYp&PQNzdok|C3+AsK?SRu7B>?
z+1Z!x-=D7nDkRqJc+}O?)AM9nbe?5u+4pyMBe!NvWi4U&F<S>^MMgnbT+PR$o9m7<
zS=Fb0dvo*VmdxO1=jX?laa|4w6iKg{H)F<$Cr?s5T^S1gt(u1B4$I0<Pa^H7xmezv
zXIt&}(<b}c8k<iilxJF(=Xts^FsO*3^v^BWkN3%*ZkMl{0czR25s^Cc=xBHGS<~w&
zXJ?uIe7F1ksdJ1B5A0Fh_hGxKx%u;dzu%vKcX#(`zl8@u)A29gyg4(=H2c!cn=@6t
zr#<<4J^uW|!|kX2m>G5~FhvWj$E!lLK<XDdx1aJ`c<{^j@5}e^w{Pc@J+=G&zS#>G
zF680id9rf(yi;$t-=EhmUuW_CPO<;2*|SgkrOuL&mp^}RZ}nsq_kKCwNpJ4&x6jSZ
zU4Evwx7W8)nqiK=mTRC$DoV%U!j87KwoO%EU%k1r(>OLZHud?11AH<T6F~Ox@umI$
z_jjgkb=kY!@ArZ7!Iv*n=DK&Tx|*dm^^|71Yv7#1Z@)jEJb7~EDdvXHUC`Y|&;rOp
zJ-+6n>#f_ji|>|RPkni5>B|={JiNV6YZ_1WQk6E#(O5ab?c$|NldfI6c4n68>+PzK
z9zJ}y=jXH8ksA^m@74W&8&myuYifE>lkaS^sdE_^#Cgn76N2BWtFPkE?dY9h|LOC2
z`}EV(bR}hE&YYWT9lSQI__%EOlDPHH-|c?yw>9eQ@Av!Xr_ZZYn;usM+UgWsX2fuy
z@+@k)Hh9|B-fnDRF(dc(w$!8~rEW1@uf1{p@$vDuZr?sXqyBNP`KKR``=9^#_*nG{
z6GM!}tW&7_fb?wk?%g}nJU?z;-LIEdUVkkqE&coQ53l*13GH%K8C|a!81!OL%K(OD
zclu<lH<i4+w8@x(!NPYdYV9I*|HKK8Y5MW=zJ2><VrsfHZ1voa2i`~8u`|q=hi3VL
zjk$MsnQDixJM-t~=gZfxPw$mBU$%e0y=!1fMTG^ZTHcuCdUNKKH%q6-S-mdTn(8&L
z{@>5~1#Aor_CcCmi!`hud*2{&*KllW!NWsmW*91iYO0CK?nNh6r>Fe>_BL``PUNxU
z$1mT#JNN7B>&xTTPoL}6x$5ex$o;`9LyRmffAU{pVEEvE?%#Sdh)EFg$K2ZA-<Gal
zufH`)*VotAbCR&SpNglIl@+MkE`5D%>dX@+1)rXr++3$KpP9kO7PTUqGx^%JYbNIA
z>Ylf5-2xSNe?A=M-(PEA{_ajsZ|~Hp$4yG!+}H>@mFefN*XvLFF)}<bLCeVMv9Yl?
zx98u_pP#?y<FTB3do1_=`<1Pxre<VfGDUm+o=r!bmd$?l>=~$!b8~NX`Atm*hB?Pj
z)5r5A+qat^K781+>`la^Cp(|dJKZO1ed*e@Y2Et!EEX?bT>0&0y7#&itCdLE7vvPo
zn#W>)Pha1&z2EP7uMImrxBTAB=={A~->58`xp3jaHF0~btjpi|golUUv}9oT(~eTH
zGMu|LJ-%+{>h=4qil3eNdHUwYjT?LV`j*A5_ji=+eRNWN{+Z?T>t^Ne|7+$wUC-Cu
z-90KQ%5Ub%5UraV5}iF;85qRX&;oaB)Y@rhXPbk{7|)^~A0EaO9u<|8lsu`s{Z7%T
zHxC{py!u+DrmlY4BX!oQu+{aJ!7D@l++kqw*|=;I%Jg1_&GP%55hAW?YHB*%pX<v$
zJvq5an1SI({GYG;Igt|=sNdg|fYPF4U|?uKD|;Iz_4M?l{QUGZGe6%yI5;?K>n%xs
z28Lkt7MRrKA3rL-y}LVG#j@&4#-x=0|NdrXXIrP{<>cg?x;^9Hw!FKurfP?${rmG1
z)V4d;D-Eh~7HNRmLg&t%TNANy(HkFz25!Hl8eNOtpfswbythXAE)BALx<;eR_*`AR
zou#E^Xr)O*E4O&su^!2rTeHLaWGp9n>+Mvzy*>Z@rqt6$c6RgLy?eJNe!tz<s=aSQ
z7#g_I3q{awW-aSRw(a@%_pOQDZ3fN}|Kp0S3Lm*lTC#YtGBY!C<o3L|tR)N$n&0dz
WB@F&@%gMKb@{y;jpUXO@geCxM<w%eK
literal 0
HcmV?d00001
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-roc_auc_score-20160908-100040.png b/Code/MonoMutliViewClassifiers/Results/Fake-roc_auc_score-20160908-100040.png
new file mode 100644
index 0000000000000000000000000000000000000000..2c537de54fb1cc489785394aef906011f1fa86fc
GIT binary patch
literal 167357
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@u0ZM$pX)?9}D=^5Vd7btOji`%H=wb4A}O+>(A
zHMOiBwTmvi-~Qb)-Nw<$THP;uG;VQ{$YQsRNlR}kaXkNh_)Xm!Ywq0+NuTz8f4^&w
z((^epErb0e4;#04yzu97P*=hW7zn9YWN*kYw*xO=Fd(Gj-w}oqyv|T!IzULpFJa~j
zop{~B!9YmGXn>#v;BXF*7x9WVHZq%Z9-o_QEx$|4<)@gmG<W1Q!@N5?_+zK;_i=Gy
zNr^o6@NoO*t@Ho4W=|E)&(9apkNe{s-pnB>DX9^<N+fD)*3zl-rf-uI5MYQr_kX>%
zNQnLC@Sm%n=>-M`PDqus|Mw%g@!j|N>$0w{%DAxLVEejb_I*01Ik>nkdHtU7*2vuJ
zt7>ZT^K-7PT%rl7sjQLH49nl$;g4O)|H}C+Xa4<typhu`F880m|Lcyn6D!xQkKD|5
zb#-|A+_|zTk;la2YZx1fy%G7wNCr85|KmQnY0cN;SFVVhJ9mzQhsPx(BxK#~_xJb9
z&$TXh+n97TAv2TH-QE4ls!;C7$9kQ;yuA8ub17~}Jj~Y8)^_OhY3^y$rft}`(edY}
zr-lg!7-a10Z2X^_6h3k}`!i;LU2MK(=>mU0M$6>meP=(4U!Oc_l0n^{iXT6J9=v*0
z^x3m#1%-u<&1}2|m7h{<>i$^xKX>@4>?x$;`Rl^f3yb*NCZtN1zP@%f+HYEFMP=pR
zUQ^{?AM8?Q|6R_$RO<2k8{aSfUuIeS?7_3Mvu9WoE()uPn-}OgiA&|e*ZKGC{+;^u
z_v-Vx(F>lpb2Q1D=gIWR*>?HPHv5}<{Ll7N*}HW*o@;G?aIL;-x30&}O!bQwFaG%R
z`Fvt#X6HiZb|obxrqWkeesX7d{!jaL>+;FT>KFG`m+z_g$i&Rf=i=hRGRri3+G8^p
z1bA=!_kySbJfIitZ&UH?=;&w=V3L%S+)?<L%`E?3&y5=qbF9n#3cqgo@}=a<+uP!+
z!`3!UohmxZJiqVKQt!t{yTv;?I~`qISe~7q-`^{3e(3)F`1IfI{c?&XCL+iC<w4OZ
zWuDg~r0V6s(I{=6mvDDiX~ec1$!BM0w>L7gOO@K4p03}nb6UVD;pL^JGt6>l-TQ3z
zWctdlQ*UleX5Ur*zVG?@`HNFdPRh8y&-TupI}>Kj>e`%sKIzMgi!*F0jq>j7U^F*3
zUwp3dQ~IeXni7^pDmFGYb|s-D9+O%wFZWNryQ}oYm6ey<*YRDnKeWKH`NG!h>-?WS
zw*FssVAhNoGx%d!mG)G9<(jPK>oi%-H(;sP)SCD2m(Q;|v^sn}*MhYFIsc#R^mhEQ
z`}a+=+*=D`b{75kc02##zS`gWzux$7CSS#K&a<Y*X3d&4|CZgVsi@3Vw=RFzqT+dD
zXR-R7yLY*Fgnha16d!$mXR&%i`QzNTx3+HmWU*ZZ9_&ia$TiK2{Wo4*T)ef;uJ94d
zpTB=M7Cdy~kv8Kw+9i7V)c+rk`!{A?)%x-4SJLTex*9=CI>P=PYUMVp_>izA>nhiB
z|M_k+jZ#f2*T?U7yS&V|@Z}}dlGoRGxy5uE_U_$#?c4gey@$@sG@dwXR@RluH#ax4
zb8>RNxVziD?Cq`A6)QA+W|?p<TUPl$Jx{U4FDfTT=hpUoeq&=}7dN*>?)`FBsq5nQ
zb{%YHf81~X@5JYgn)!F`-u=Jvpm<zdoQIFk5%c>s&EMYMe*XHV%CG!~PoA)-t1ss-
z%2{gn@BXRd$DccgH*%~FTkDjSrFH1=VeXWA*KRT034i}w{yX`(-p-S2<^Kl!%~>C}
z*P!T$$B`pP6f`tmG+%jm|ABMg!JV41yS}uqJ9J;o{_T^4&Fl;x*1vUr@qXd@wfFbe
z%QFP*C`g=Zb50jgO`Zt&)V_{E5Dxy<zPh%ydsFIZCyvJA=jSq?%37E4Oq@8eps46j
zpR9FB(|N{(2L~E|d^)ZF@z2j<9yyx`?f3TofAT+i^eA9|UG18fok8k9WEj@0Sz}Q3
zC4)!a?#_xT{n%Y1lT;SQ@2}(F=01FRx&Ow>&uNRlO_Ww-VdIf#ICIA5%v|em!yhsX
zr>5z4@2&nWwPn)NZgG83c@nZJg!9|CZyPpmc0M^t_2N=*@j3SOam)YAG)}*;vp8Ku
zH%dfnDwk`Qh~wpDz8mZQR?Xe?`r2COW;Wgj4<0aRYiozBi;)ao=HpmZwaYIOQi98z
zpKpI0RC>zG%g>lSJNeFz!dXT$XU>e+QK0zh+FI`F>gtH-=*3lEUqx(4Xbfx=ewD1*
z+0oIUbK0Wj$A++96P4XB>?+N!sH$>W8nm$B;h`1L+t-EtWl(@uC$qNP-k$F~E%nRG
z%k10p@4HRci+%9w6_>ZS_mwq~!J9wb{(b4vr4K)!&p&+mvhcKN(=@`@$)uf~)f&A$
zFY{YEkH5b^kBo(YdH%g4dn!Nk-1FmTe82y{+}5nCO>5Wc=H%oAtPazy`TzHO*Y((G
zsVuCl4{vTxe{p}meV2$P(^Rk4E>UeIBcq`Ah2P%XY!=gvI&k%>sMb_2Rqts>!sBaG
zuN+qp5*9YhyJK->eY|`tw|HA?E31u-jewX~+m9a=M{~F3-fnyFAi>wx*2YFaK%l|3
zTTHU#OivHbnYq^Drdd}SCQlY#vv%#n$B&!0<=%dDppiK$b$iauCOO-x1wJ#4Hf-G3
z*xSonQ(J48f6wM<_R6|>dH47A{`~xWu~RG8hAmrK`uq9S{O7IF++O#$>dLxUX)`mk
zg7Wg?3mlt8>>U>FGw<x|d~tCx`<=UY6H`-J<KyGkL~cH|;B%<ApWm?)6O{w^)l^1A
zMjkwPkg-?F^w7TA-#xebZ*9%Ku5fyj-~MS6CNM-!Q#@_dCu_ZI>i4hL<DI9a%2<_n
zX#f59_xF!Co6iR<a^YMNqP1hk4h0nzmh|)Uu3E0!XU4yWJ8f;;UaK{0);xIku5X@g
zwUVKsAR{B=gw((Pxj#QT+MRK8ld6oYY+`P1Z$ksa9E(Dy)jj?F{mcFby!W4$I%CF+
zj8isse<TjK^Sj^Nl$w~F%<S&&K1DZLY;W~<Hz%j2dyl1+epiBO@qPRDZP>Q0t-YPS
zjaPcv%jL;QNdgiQ9M#p;7M7L^)6dWI@bbEJGv4p-t6N*M1!ZJ-($mw=e!jgn+I+2{
zot75YCY{H}<?D~UySrOZLV|;xoqg?VMh1318HdejXCJ(I!!y;Z)hP8;!jlsdJ-oe*
zf84oz>5@V1uM!q^c2J5F6B8>aE_U|t;P9JgvvNo8!sG@!NlD2W_VspA+j2Pb^Yd4P
zXjxcWFD`t1?8e^e?O`{~^Y0xvc#yG`OVlYWY}%uLc0Zp8pV-thzy4pO_TTOI>zpep
zEcWc#laQF$=+w%ksH4MkeO>J3o9(;mJv}@Q?5X@5u+&R5A~G_wDYbWHaar}ZH;wb>
z%je|eJb3e_r|j*m%vWFk{a8`<>WXH`iwlmI^Q$W>A3pB4cS}l2T6f)S_tVqU58t^X
zqo}B8Iqmj_MCPpP>v*%Xvq4VGzP@gj!l^f3wtoHcrNqU>CF9qOM@PGpzr48U;qQO_
z%jTc9W(hI&*%{J7i{9URQeJZ=@A<j8vz{M1d6HAsy6i}=w7JOXeRY4OCae3qZOyux
zketjM9UXmTbvXaUix;DwR(*fhyI_HW$D}1MFJJll;^E<TK?#W!GqqQq51c#yZ%psZ
z__X<#WB1p|&b2OY+r4}Dvl&^jyGj}bm`+dEH-BYiTk}I;e%&w4nwlDu+Te@~jk=#t
z#piCi`Tpm@W_D22SzBA*xP5zZ=<2W?RbN**9*@~wrkfIZY(wH<k<XVeUw-)F1qVMr
zzwi7h)9XS!{gMkxN=&k@tXOEwrfs-ve^+nsRh#!WpG&+yzn1I&iC6~cT7a)xpKjS=
z(j#LjlzMtv>(ZsFbLPysuqM)Yu4VkU<X&m>a|?Dl=JjMwZu=(Rwr%qFURi6gO*)Ss
z9BdYF(m0pQ@c7u<h6aWiGiE3#D>H+dhBr5*E(}`9Q}^63jb~5YUn{pBiN;x`*@w=a
z<<*+Xb?@Fi34??NHI1l~_x4s_+*O*rWA|?7r9lTzpY|?1w?0hZyR5-G**yy9OtrMQ
z>gwtWii?|<E>+#LXAj6tYofRNt-iC=d-{c~+2KEa{BT$rbnxt1Uel~A2QDmho;Y*n
zO3m+e(c$0YCr+Fw;B?^j?daz_PiN-sOgk&Z!p3&!;zdDF`5C{@M$K=|iXZQJUTypH
z;-YfRmy7NiQCl>8e0@JY?zewd^%l{wd2zq-biM$h%Ih~WHop9;^5i7d2`Zd_e}8YE
zJ$v@OxBLG6%04sCR{Hn%_s8Gf-fp^j#p>oG_v1_NPDp<K<m2PxH}=(9pPHiCY*qT|
zz_n{)#_8vdOj7l}urb-a`TOMAH*Q44>@MSV?G`hAA^wq<(<<xM7EQl77L8S3Ux6w@
z15?wZd#k?}e0bn!l5v6I>Z;JoQ(||OXtMFia0CYjZ^^vOw$y9tp~uJj3%|XI)QQ^S
z@j7Pz&u7v;GmTi+ty{;z&E4GF%L{6b<nQ~*R{j0m(R+KVw}w5Kro#F1<x37OE~la*
zqgiITT-MgsXHTW)-{0rDI&AHR^7nC|;wUjOF<@ngMa2gNHeM-E(@$AT>(qkR8lFLY
zmG7UwzqeO<ZPeDLy?bqMZOLTj=jT^ZRaLaJlj|1KJv75Gx#&)uuA(C2)~u^eokFT6
zj&riFuXDY<Eq7!6|2mVL8v()J&dxUH;Ndy)^Yin-y;Y?p@9)X3T)A?FNv2SrjOC=q
zmQPa7%rNZe={a(wQ~2WU@_Y*mizmB$zrVY?G3~5WMP(%@fF`JL&Nk0KcA$~D@XZaw
zKVL5UTisr=WXXZ^=lR9N#9rLksC;ivW%Jk9*BATGw=*y_yvS)JXI-XqtWTCZJv|-N
z$ji&i>*(%2+#_kcA^W=C9E(CGGc&WD*S>yuczA|ct`rk9^TmbE>^E-Qc<}4%>l-@?
zl|i-M<Kz8{gO+;D`s6)L=iqVq`kq6r+>3o@n-vrm9(;VfUr=1U{lp26nolRycgk%J
zUmw@e*XOp>YwCs7;rbC#QI8Hbvs+Ys(EwGup!)OXL}m9wM~<+RzPi%b-p(Er94sg-
z+^p!__TbIU%~t0({Hl~P%aKS*P6lNfliXV(x3}dU-hRJsH7A#}Ws%CQt=a8tyiy7G
z_ti#hNMPKwY14*;gG_UOsi~_kj@w&RP*UPD->!DTq)APsudjj1Tz)y53(^hK?#{I?
zzpx?E`OeN__J9BWW!&3i8Mm*dQ`Wj{LFDGNh)pS+zrMYl{km?GcI++_8ygz|Vd2G7
z*YUlWsKUw4C(|&0{(LokH8r+r)26KmUq4Un?ezFM$H{8GAd8my&Q>xp5%HgIcXXO=
zG^oXwb8{2x*;%HScOH8`+bmbgtw(}UU0walySvh5Wo0+E=ga^3^CuxcfBkmed6va&
z!OQ)wepy-m?#{tBUg--f0+nNS6fiFJn##n$BWooRy)DNvCr9Vd;lmH#zFoVL|AQXG
z=D598J4#=RfjUNJxwjlR8gFmUPrkh^_r;Bki_>QB37G%=&d%bE)!*~B<lYu*Y;3%-
zyIddClv=VxrKP21f%kO1jH|0eLG8@P$NQ6?o|;<m?aj<{?Z#hX`#*dr`19j&e?e)f
zYet4fOl+)avd_&;sey~#c-PjhiQg}`yZpUdx0vpSlj`#`SoiD3?U7(+=WFTh<+Un%
z!(nc2E@M@~5xm^*XrHWg!J8X~H*Vg1TJ`SZ$Bz=GSt3$qIUQkZqYhrYC<yZIw%psG
zWccRBMrPkxCKsoer}11+*VN>kU;oeY&!0aRmUs&9*tHAP;JCd#-@RK*cSFuiqq95m
z5)&KsVt0Z1dpEXbi$`tCS-ExnmoFu2qPO$4a*JQ9npXb)Uhjnq0efnHi>-~`?sjsL
zYT^5PwmG-9a9WqYJF?KZJz#5A=-Su1o<eN=ay^UP`xm92o|bWQ)6%qe2|jbLE?T@;
zP)v-?+uOV3-5tqRF403DA0H3go);UkGRXC#<<E!h@&*Y97*>R6fy$(L^XBcS`)f5#
zKfdqn?d^}RtPEyb>oRZJw6@~s=N5*ojS5&9QgvE4Vgm!n6SK{7L5;`Y<$j58Z*2wT
z#a3?dEzjzI{c8XA_V(lF^XuJSURr9HaX}#^B}G9?i)*@m{JD*N$7HPa|K{Z7ddM&R
ztkdyPu;RPm>|SZ}r0eTqLH$}LX6C|&hgfs&>=10{lLfif^sf@bl4Z-33=9Os_2XQ=
zzPfsGdwzUMYHH&7dA2XEt(9IEvvbkU56-*G-YR$sDJd%p3J5ebG%%d~Sy5fRxcvRS
zf|8OW*VaZ~+?E@C_Org{q_lsNum617D{UUIyDWE#W-!~`-Q~w$UthoVm%P5denmw^
z!vBAN*<#fn+_kxQ{yaawyq!xxfWWTO*KNDY-zWY3^%c~kHOsx#BBmRak*n+}v@QRB
z-`eQyS?_*M)ehfK{M>JjZM9hVx|oxttsl4L-ad5ip4{s2^~b)vyj*IxYeVX3u_eov
zEvo<jZ<bB+@4(tGTQ^2-PD{M8ArX}0D=IABynVYd{k+_j)#3ghnUjuv3BPymUPnjA
zfi;nv6+DI7_+(f8yx{Q7F32-0OY7Cu)$Oap*Dp#tI|~$g^XzK7N?%`F=s8*K$G_k2
zFRqWbpZk_)uJn^5Gt4r5{wI1^2MS3@aClDIkaUy_RDK8w3JN%7-1SdBp8Iv%!i5Vh
zs=w)gMl{Oa-g^4u-ukpR5<4<4tLa2;Vrgt_{P6j6^Uj@?dhz>uQcq7yJl-d3QT=Vr
zxm9=W*M65h)-TT=9UTqIrt{{_tN8GMu}|K<FLZTS=GmW(O*`K=6uy7p)ngm}wYuix
zqoWsh7N_61eOuYkP%!=69B^r|GFYAAebf2u>+3+HV#|D`fBg8NpsUMko_FWKBG+z%
z!bdI<k&%oSa$kq84s&&JVF8WG?AT$!BWdLFdC$uKtMl`2F87yradSI#`LeLARY^m0
zGqc}3o6d`i-IdkU*nWR|d->(@Ns}g-{Pz=<lH!V-_VC@iybE6uBjk(f866R$LjOxu
zJcTytyk2tr*fB0)Vc~^AD~}v*=imCtYl?<qN~GBD@9)o-{;#X6bDEY48jVnF5h#Cu
zPjr$BXK``y$7g3}H(7St`_8k8^q8cw%x~^0&(B}KimIupJ^FsX{<@~ToSa@tq*!2J
zVAXd?K|w_oPod=FeOH(C%G<|zOj4=(@*+^->%NkglP0KmwzRcrJzKtHNyfjrr>8^{
z)6&%D%$@66Q?tkK=I`(Cv;WmSI>M>wIqAc<Z({xO_ScrAr=@jWTN}+CIqm3^lase@
z`~K~l*e0EBHQ!ks;p^jGzWKlV{XXGIDxHeXZ5?aY==fHJg-v^Ld;9tcsgXIix1C+^
z`P;W|Vs>_RU6q1@f=<&?1*N4|duHF?w|7EnWX!G-&*gtMr=Q<a7k2;l?d|#5mxP3b
zOwRxQ@$vE2Q}1tXcK4X10xHL*+U4D`Q1qO{!OeZyYk&Fsc?G4VqMLNO@9nLYF4_0$
z@$cWixfNSx7$&z(Q1RrEHuG6MN5%8d<;%g^xnEyhb(*B|@b&A}rSWllt5j=hYg=_r
zC!L*TYV~_!YUG#q_v2s3#qKO}oiS@x7ni73#?=1KPQghkoxi@m?%uM+WbK|6D>M{6
zC;fQTt<Ph1UEP0Phq!*+izUa89_5slmcF>im3!?MDbp;Dsa~q{>}pqSKKuK7m}gej
zstKu)S5}338`^7XdcJ->+dN-u+Uu*Ur%y<YoMTrTrEP0t6XP*SrKYCFB`Il<nysp;
z>y8~eII^>|A3l4gR`>g@xo=!m)h><reR~2{hCDhsSv~4^@cr3(vAZ&ss;j7QsH>|d
zCMGK8-QBg+)4t@z1V4L~76D#qGZ8g4wWPbdO0BLh&bqql(5X{itKUkmN<Tl(X<BOG
z(^I0pQP<bSw$7eCdqv#dT^Sb^G^*KJT1L*8F{9&HuXOgMd;4m&L1|J)SNG^dW%n)L
z=FXU*VPj+CGEvFZrK)O|TI|ZR_xDr=&zL!rv%I`~?LOaF`K2GdYuBbkirN4Bu{iAB
zqodueDxQxn``cgj3b)#J>)YGgqPJHHIHjbdXxKeJ7SM0V$Hy0S{`_q7e3w=((U#86
z&Vs_ii#z*zrOiPpt6N+@YpM3v)vrFU3trw=@$b*hu(+_WY1bs=B_%agJcU61dw*}Q
z)z`hXzqf7JutDJ4w{MSbZOx9VWM=0RnWWOm$jl~D@-8zov+M2ee}8{3@|dW!sOIOV
zsF%lj7=P`l{OtBTGU)o!q@!JjZr+Ui^YOU+tdg%5w>Bob&&|EIHd<Z9Qz*Xf=TbFY
zOUp<L3ky))UHJ7?=-N-y_2b3N%*+<K^-4v(eD!Z>#>GWZ$zgG?|NQw`{P4j8g%GW&
z=e9~&7A;v;n__=$Yxeb)ojZ4G#O~S>Ca->E_r`-qj<{^ezaO`p&#UbHJzW(~p=Nge
zuruNIpd9k()6>&Ym3McQ3UAWs{`&fQ_EL5hmKR&T%Gdu1^q8c=#Kh#{=GLZWYib%g
zMK?O^#3mgkX6DbeImy3o-nkXvH|3e$Pg(iR*FC4De*ApiKKtp}xz^zxlT@TkvzAO<
zC&!<DX2!y)|DK(dzPKjRI58<{(bfMiq?d2HuDINC`^L|w-xTi(T<rF=;@{g_TZK32
zXrG%s)g<$hOJQHlqa&P&Sy@^!F)>F@PuJgi&UcausL0@xvstnA?1_oWpse)k%S$%d
z>H`gopt7s@x!>G9V!BZrk<*T@-~Vrwr|~v<(MNY>Tvq1pvFB4$QQ;^qE`Iptjn2C}
zI~RxAnV5tW@|bPgFQoMRJ7ewFxA*t&pP=FiYBNW@G|#&Oid(0pL77_@?>WQ!#c-ML
zv!(w}yuBMDzqBr>V^8mGMn*=bNh*O$y+r3)miT=#VzaCG;E-*%Vq5-wyTqg<B{n{p
z6;s#MrE5oST5_&JwdLFH0>^vh$@dOk{d@WM`;KGtR&U<C`NNklS2B&AGVHStxAB6)
z|LyJVucw^;_nyP)#r)4&z4lpNxg|%tM4cw7fO-LQ>n}@Mm#vwQ8VMSS)Q+vyKXmx8
zYg*c}bA`zLM*nlRE=Y5o|JGj7mhYD`<(g|<?)LatFC&9-`nfBSQ?(2Y1sNW^d^z)V
z-PKe%n~DWn*KXcyeCF&~?lu1yK<&D@p>q!(K0I;i)Yhfm)5UHS3JD7<dQNiGZj^Gq
z@3rt|xJ1m30!1TZW5cvF5}>59JZGYkt4V$Qz8Xsv&qFH$7e9FQYL(~oR7vCXb1f>K
z5!-TRJ~B){H;2>P+k35vB6xz~P%HOi`~N@tuVrOSQb~MvW+p>J=;|=Zf^Elw<^5k;
zJ>9k{rR->zD7d>Z_1Y3o;fl)2hhJV^j(Qmw7-(Q<cyNj5<SmzMZEQfpl-XffXSyAm
z*$&>mEzK>a<KX1v)R$WS;~~4pq!!KKWf^zHy}iAC=30q5aU8AAOif+7^Lp0PQ&XGg
z&zFDn`0>YASG9eA-Pu{J=qWT!Cz2^TI(qHjFK=!NhprAY{c&&CjvWVX-HKA*8?@Am
zgNy6X!De<)w|{DSR@SP>kLK3S@7Ah#3OK!Z8!RI$yS47y$B%(J<`o|jI21RepO-tD
z+#_ks*2*P%Y01j)q`JSqOxgHkIxa2s&i-`f%o)%a@sj1smF?`}((BdK)Mgl^c7;W4
zOgd^%@gV_JdacWt9~%=R!zXXobKye3Tv742Z{8S`y@>#oAvbmuCindg6q1qQQEW-O
zTKwRy)^kTkM-D!|V=IG~fB5w^o8bV+u~VnEE?A)8dvmUJ`J-oNXG@r52)w$!e*M<>
zPOV%ISFhi92-GV0wm#+Rs?ZZ>&Kz0b*u3SJ83V{Ek3KI7+h13^b|XW@_MpWpSFZH4
zHg5^qpPZGo>c^btM<*ycZ<!}wTwGl8?v7++WMszGRa4KEzPY#8n&H8tquo2-Ro~lF
zIYEW9TU@`bx3@QJo{DFew*R)=+hNB1C*CceU+3iJ#>U1gwPbVBizA)FiP_n!H783)
zM@Jw17Q4hlu;j%B#_;uVpn-@juehG%^B9<$U$2~YrS#?H<@}Q-PcD3RM$)%xu2pHk
zu9D20`}<@yH8rDdySTbKPEz^u=4P<AuC6YxprD{e@Uot;pP!zdUL3!_&Z7RG&APa~
ztEQ@Z3W3H@Dk>|V?mid2J<l~OOA9nd)g`K(mHYYa_WN4vmh3Kg=(MNyx7g<N^VeQI
zZYW><dRyjYw%gnDkDs2dU%IV!e$~?V-^16`-k+f89I&sZa_yG7zrP$g5(A_|<NtFC
zs~xy<C1i45dV2fC#qQ57?4+yS{Q0u^*R6oKC+Rh3^eikS&dxT!?)Cf2W&glME}Tb>
z9C`5W?rw&AYXf#eXNPWVNQ`=V_Uu{1(pMp%9>dpHSKa1yZu)aZ|L)zphG}PJ$b4U4
zw~RNk_20k0zd^m(J$v?icse~k>*>{%!R)cS%Upwkgv@epE!muVeO;{S>iw&~zQ2F}
zLAn$})z??7iY@1|-uKJd9=f-;8Z;6TvLe87a$b&oR?k%J@JDZNZ<nyC*l^Bz{w1!r
z4Ilr8#-*gBBwSq;x?$_qt25_M*9c^4X6JXSs<Nv4^U-~7E_YU5g2(JX+RrnOop`-t
z?YsE<^PQio=qD#UJk*+)mbPs3dbeJwg-)$pR>ehM=cGM5Gt=s^D8td`>lNPZHhll!
zmqhit1G~R-E)_j7_14}?e>8sYR~A`fS^Vt4nKL}6r|Vy@{4ZsiB{FBu9FgBS#l^*Y
z|FXl!$OQlXp7|`U1yL6MTYIcmdimGQDxMMhYAmb1zWUmjl`@B!oewl&n{jW?&aex?
z+w<-k<lHcDadS&L)WT`Wrc<Z!^z?N1tE)mm<2))VDxksludlDSuV26Zoc_xBR;64F
z7uG~>j`?2w?@uMe`=;af!dHc8f~I)3=iNQ@`T6;+OnsqRQ~fSTF@OfwJUu-%Vt1Jw
z>z7|YS-+)W>C&Z18*&{%Q%uj!&JJ81rVGk7&|XP<dwbyTl~G$)J<|VFT~+ny$;rvH
z=FhjU@0)F&f9UjSZ$pg_e;WdlXU?9Td})a%sM81<<9zWVV{hvD`S$#g(=KjEbe_AX
zjaT~6ks~g}`!{QcuA1U^K=Z?Y`8E$fzqYAUMHwDEIXT(D*!b|S($^xdC(N7Ir|v&b
z!P4^Pf`loclHvFJ{l|9}KmYLMW$>Qb-(i#0J%vDROU@czZtlY$9v%iwYLvXZ#L6pe
z)-r#-d`wJCkuBc`y$vf%UthbiF`0c;*xIfO7Xp6#{=K;D?JX<$AclLa*L`Q3@$N2r
zd+6+J^Q}!<s-B1b{{Al7AH3L&cdkk40ne|mu9kkfa(-FRhw0O&i+71?FPkhUAkeTe
z`MB1-^Kbm-STHhp`1&5bu`#*yle~Q$kD|-GTZ^q`{5jCb{Nv5$^B-QX-~Z_2<KrBB
zd~O#Pxf&)P<B_qek?@^ucC?Y1UBPow7{jhzd7PY_U8TG0{_a|qXZbZ%TrY-!;m6OP
zFP~IaRvx^3S$KQ?{jfV>FXLv;nsw;zUD=Z-Pg>5|yA2eQhYvFcFY`ILv-tUiMXuaG
ze*RpTb#)c1n2oY$(7buNiZ1IKTR{`CPft$|ToIrcvM%Q41FNfRB7+TWmlqyAc#!ex
zs?fs|mE8-zz6uRl6{30lv5a*YPw}%e2Tx8`|M=r$@{;Atvp-$Q4g9-tdXp6Mx|p3!
znU|M6JTXxjGzlwT|7T(GnKxBmU$q7<c2l&nl9I3gW7tss)?1cmR_&gUenoM;n1GsZ
z>tlDbF?96zU*}A?Tz<B9?dPALpDTJ!O4_|~+cvkWt3pA2pQ-ECeP8I@F4Fu_&c3ea
z%o!h0@&t|PM*A~Ve0w9Q;(4lY&V}!1(&c9t6+b-0dSX-0uF}`9o;)?NlP(4oS(bPG
zlb@8=oLT4C%x0CjNoR50-(Nc_KdYUaZ_n@V??1<~m~H0FnG;kzKkm8ucFTfi)jwy(
zhph~9HC$k9UAo}e<>mgxYrA*#fBybGye1t~hn||MUHI=$<=J+JE1!P*Fgx7cRcb1~
z*TdKMDog*mn4LnAk&zty{MT<Dn^AW~;#Ky-FL!?Y_;KL!<zT}V_ixx;i`f77n{?dX
zs@7j$Uu)L|C~IhN2&?%7%yAbza_7JWv!CJTF855FUwHdQozD8?2dAcL3yO-ic8lvP
zSz1QERt^;t6N~z7QTj?m#nb8XGGE?x;f{AeEwtjKGdtT_TND5N`Kb}V&&I0sRZAPM
z^rF1GyEbgzd|B)I&f@elGmY656%}7xSja48n#E#oZ!e-BXA@s~_4(J=*E_nqn^&*a
zPCGkmDJaLcwzfXn{PykJxywIxBNa`u5)FRvUiz1KpTDQiuaDn<tW#M1!g7Ck9ti^m
z&?14zv+DyEI(c|_9Jsr?d}~-v=%P5^Kv|FFe0=ra-bh}$e3?5(^oy$ZG>1tla~mq%
z-QBn3-IbbcmU{>^QnatO+IOB+g@LxV_xrldn>K;6!h*zyhgua|PLwmaeyftPsStR4
ztoLvmue3qZ5e^Q;gzW6@xV=@0pPrnY6<T&xdxMlv!Sq?PR;^q=3Di=1cXzjkr{_g3
zhw|d$V4eSOZW=SZZ*sr?Kf$rAZOw#P;%{$lJ=`a2ZBYEoXHCRLChuuFjRH)dIg%$Q
zCtq9<sNDQ*vB(;xJ=`uQ{^=}Px|Ffu(W?WNOQjckPuH7ank{y1eSE+Ez8_3mv#ti|
zOrJH2OI=-kZD`z8A0M9wj~+Ft`_Fsv<Y~z|hAmBU^K7fz&YU?T^M0+0XT`@yuIm_I
zfU?wuh0YJ3JZU-BD}DI%Y3{JFFvtMCTTG11y*-tSHSJ4Y1nk(gE9v2()*0sca?j4p
zWPT9);r*AFmqnS~?`_Y!YXxc^t`1-C=HkNAA`q}L1Qf+-XJ#y{To)W1{P6Yb?%Uh*
z7l*BldU192^k=u0Em@NA?aj@o($jvKqK;p;p3(HrG|i|z-(O|wUi$m0`(3&3Z*RBP
z{{E&pZK8^%|J#ij7Z-t6WF;jhn`$rgp48&jD+QWIN=r+#D0tAI#&GxCIX`U=&)Ds}
z(q=Dg+kQo!>ii}3<O<tY)&<YMyh*QrSDc)k-5tE#@8RzE`woMKYs=rqaVUa<r;(XG
z>B@@0uD6#We$A8joYYgdZIf}@nG=4Qp@9cB6srC%EZ$W4Ij!W)4bWUv#+@C8UQ;v}
zv$M0$&ZzkDA#v@t2!Z4SCnu{5%E*8U2NrgAWfc{cva+%XsgmM)F$b=#jV`@ae}0~=
zVbzxm7gyIzrVHWgVmi;9@tJFRd~^DFg_Z-GQcoAHX}`32{rg$c(do{&&i=lVTXw8R
zvg&n?$81&xZ*Ol7#Vt*KQ#G~*F5T!U|8>WTFNz&^j-@;I&z)ZvcK@$Qm}5_WR$HI-
ztIu}D&wB1%UG>>&pT^1ae=bdU{Rh;L4fvyQ_V=e-$2})4`4O|S`9`l~`KJ0WNe3Dj
z8Sbss$xTaZTNk@KYpUrsc~iH%TF-?}ttCtsK3_WiY-?PlWII<<UP1=6X>$In(YIK2
z{p1H17CIZIpOX>M3}QJu%e1+@y?xo*brBn#o=bXrdNwXzyx4C;nIG4qea}nnrq12?
z+^YIp&J>M6Chf2_2d=CPHcUMwGGo@PMXudqGc1eMKq30zZaWibrB|o0deY-#y%9T$
zR9gfzf|v2^`~A+k<mDyR^QB>v=FH(yWSM7EIq7xv<KJ9aIVwspu&7>*ZGkYnP4kz3
z!<H>B0RaM_(b-p5S1%4<ANS+!_WKKhR+^-~y1u@@rG@3q{r&O>4<4-gK6TQhrsC)4
z7=Qd1&FL1?<<i&Jzq7Ymyq#a(%p$`=9W)<uZEZB;9_|;Rzf`k5Cv8YMDYTZMq%>f@
zm4n0meT;A8W5U<3seExkkwa0We&?--Z{NOwyp?utPUmd%d?hn8v2JnwV}E{ro;Yh(
z*NPPyYpd?;ueZPcp#JMm&>XUzot@Rs&d$!Lr&qqr?cWu%yX<WdkB;dSozqp#>R(y)
z&GPTboSkhB8l^6Lbwv|2&A=_L=kog6T2M7GS2Xpr^WI%|7Q6S0eEzyrI{R3UWX6pR
zif#PzeTUomwWn>|zTG`2NXW?8xHRm^nKNgOTwd;98g|%t+TOjkEdp$71!he?bH=Af
z)>^EUTm0D1&(BNkG7A3uC_MUhSNZ$CcXxLy>+13z@0UOR?Ck7~H9w0?vaj)kua9fp
zyt%mV_|^>@4$Lr2Hb^@oac6(Md^^9qTS|&b*t(cb(CA>;pV(a`E7MZnU0m#*{r2&b
zlapuIR+rhGyI1gQ-u!lcd8Pn9k8^%=?bFZ6)O@>{&KhmGC)%;(<Rn##;%7WbNl5`~
zA`C04tC<<HuC8kR`};d+#28e2-P)45_-g)*+qa!3spQ<=#;Y5>?M$)krtJrdo}PO7
zL_9?LjPFDx*9|2vgLGndiG2L{v7@u|U=u61LEaq;4n>jhpMRF0uuGHhnzSV5cw;-i
zyw*M8+Q(g!E-rRIeCQC<^K)}AOP&Yy?Qh6GE9aSEkjV7!$76obgwVf#|Dq~`m-$>g
zqq^zyhYt<`0Rnt777f|g*DWl0d8w+|@#^`ym>3zYkQEbNo1XByZ)(2nT&3jhE8n$s
zb$ve{oV_RL`%lZWYq^@{&Xt`sY0`wLQ<n<2#0Atk$Nj!J2h_DGuL&_OxfA%m{KbWZ
zmUUAWEO?S$mwBQz%)a}V-G(J0;$KaD{bTYNplbmt=Ns0>#C?5n(fRYmZboLd2Y-Hk
z{_*vC{Ka*#)@QTcWmUd(=Ur;&UYoq(lIbaL`PtX2YEM+Bc+CE@`gvxX)``N~6Otv3
z+3YGmv3!1Z*7@nFsfB-j6oOWAJY65RH!5A4ot<4pRrTT7+2(Gn3!hIneE-1fQ_;Ff
zDv2K+9F(xBFaXUsEOzf#va*tTeQoXGsoLQMKR>0;m^qV?A?y0O-rU>U6qS{kpP!q1
z_}$&zp!Gs6t*xMf+tJan(jq(cRr=DXty!RHguvTkPi}a?D|VOvHoNBYA&t%dkD96#
z>a@S^Z^8R}wr6IUdTYO5+;4YjP2RFCuQuKK^78V>XJ@5N^6p50YX2qQ-`|&a;_#Va
zpm@D%$@1mTqtuLygkHXUxgu~eo87M$%17<>^z?4*uit+yYiH=HkVXL}b-y_mcITJI
zP1OoD$>fzbbD3$B3bJZV#73p#yEqj;e0zI4=DgzWM@PFslS&pPF9dROa<(*?zPhrK
znc>FP?C^EJSB9;XYAA2~^#1qX@ApCTbU%LlkdWCCvn>ZSED7pBxUGG%qJQyXWjWib
zB|G$Mwewa*Mnx$pC@>hOojCwnIQZpDN%Oi+!<^jQz&#a(clOuEr@LA)SQI_+Xp}jA
z|GvDUqM}9F8wpUKG-6rQ)~pk!P6hF(boKUvhO+`!FVI>Uyqs^+<jI2a^7GgKwW<9j
zqN%9~n&<V~aQ*aj{g0>h_dnUOckW!-S*F=-N4v$9ZER#bJw4sn11c*j7Gz&vcVlxp
zzt=RKPEe#;T1p<+ogP0)Wo>`p3eBxk_n(?;T`n?zbu&9Z(~tk(R`>7H*I4oVL+z{n
z?l<@LO1JaNU;A~#qoBax(W6Hj%HBpXT;R+Cxu-?oCsz&gy;x>NmOeS#Rg=q~pOd|_
zx7s}Zcers{>#d@vrygGRw?BGsZ#5%B^tK$$308kX*Q{9+urbNirs@laxPIK3@BglR
zcUif1$+BgS4z+RztPJUL%mW8As9!bLK~K?T-TBhE;|=%g|I7OM`B^nibU63c-o{48
ziNnR!_2HwV-8)KN3Po+nSSb7>I^cX=-K#mlyDNWwQq_yuv0(DLcm7<9?oHJWXJd%j
zTV;Cx_o>dRn2=v9JRQGw*O%I7uldv0|B8QO%JivImsW;ddF;0~YOBKOO@YtnM%!m4
zB{3<sB-J^d*S}x>^;PJJO+8*ywVp<W)$)RBvo&jU=Kh&6L&9TH%d4xa#Vc&Dc8TeB
zEm)v1$EuX;`uceHkPuKidVSp9l2gx?%b)fA`s%7;OF&H?Xqv!+?fKGvQ$s_;SNo=G
z2D62Qh3%;LsC4PlrIJs{Nl7MO|F3>}MeXyY`X^WXKCMzX{`QW9HQT*CmBOIGq&qt{
z`Z;_9twQ<y%y;kc8+)tE_r1>MNxpY*>XWB2n~Mtz9dB>T6_k|)Er9y-@ArF9u~B+z
z=FFK3{pMPMCLHHj7Av%9OyIXqNzcvg<r39;@agI4Dtjq+q+B{1r8RD!c4bANfw}qd
z9!cW~vu3UG{QmvBd%v9Rhc`Ekx8&RmDoni!TIqOsnQ!ylxpU8T9dd5xbDgRcTJYqA
z;FlK{owM&}>BsK_Ez(XqH)m$H?R4E}HqS{LGA=6VL~e5Vc)o#=dBW7Gt*NJ{Wp2y9
zzD^c2RhoO-%y)xR8K_;+$}JwSDaG^bs^<rGPu(r1AIBpsEX*Ti0$OhywC4KL)6*~R
zC``7g_@Hq7m%56|gKKM}tzN#mdUw<RNx#(R*DwhS3-`#|#~B7#{NDTG^74MQ3--TP
zU5kv2lrYPYXc74FVsU@bn&`4upKCunU<9qLvH$nOdHI>c?fkra3F|^vi{0B-yIS~&
zyrkqx^94Sd3eJ0(9{t{bCSIWG+Z#}OuSdo*Nc-=*ySrx?r~5UoePmYpDrClt83{)^
z1iOB|s<te8;<2ahZ`9;}zrJSoNEk9rQdyXPf8Wnlhc7I2R%~(DU-#E!wPM=$S68*?
zSe0sB|GQ)7&V#2;ae+$L)6?}$U*_N6cXiE!?{>A0p0BP(74P2eKi@8t=TODJKbCQO
zDj0)<gJ;a1&CIZ8?_N>n!gKTO`!$1?{mIq-oSK&Q==J*jZ30e{%U)m8Ju}x@JS{El
z#l5}NeYdZ#2xR{E@869rnUnAFC;s{Mdc9?xii&z;V<SUDE4R3kuCA{(gRO=JM`UE=
ztk+-b7^*xxIJ~B4G_rDwz2LoKS@~&6lKiCD?Rj?-va-4=KR<hTZ*O%}rLtR(#s&u6
z^z?KNMG<?Bf~TiMZR-9+sK?%Yzh{3`iGu?}N~GQeh9`fdY$^;|1VAg${5H%JaC)z`
z$!k~ndp=`h<1@3(`S<_-w>#|KionGarcG;;v#rVqdvd08`*!nn@%z^m|9QXfw_l-*
zW{2T{+qb1XJw2`d9{u$6w5hykz@>e))i-Y5OniE3YDZ5`i;5?xyR3N~vRWzO&5ey+
z@<A8H&qPir<>TaR+`HE{Y;9EQjvW?j_k4VOT$`=C_S?;L&?2u33!Mx9{wkgOr>BSK
zXhWH*s8&eB>ebqQ^K3E$e(rg7bF+Gj0BE_0k&%(fOVBDQgG8ssFHb>bO2?nR{+maS
z97%Y7Zf;cOt8FqOA}s#?{tO`fhYlSo`1U5!XNG~Jp}_BFXJ>nOcwG3i=AT4!ko~M^
zP*Jnl+u#2<D7~+ZGHtfo@#Nvd#$&zG%8H7P&zWPE`^`Nx%QXAJlP4`@Z*NJ)iYKr5
zJw5gGG|(`Jo}M0Pd5E87^6$Xpme$tHU%%hTe-Ls?`0?Rk*Ll~tUlHl)={A+0Sn}`f
zF<cRsmX^lB&Fvf&CFRyHw|46H-|zP)zq_;3z}y^^uX%3G-^i0Yx$>obQMP+!;DpCz
zc|Eesd-v{Td{Ot|;n8mK7uVO%f8>6LjaQ0Ak)@4SdfAV@xwos!<0L=xtvhm~*w^1b
zyhi@qi4zAlr=Mr|^M7;Mqa&Pq|E7H_Vtv`Izwf|o^ZX0D%kz)cpZ4_hJoxkTbM8Mo
z5QWc|^J%{pYC9kV>enl|c0G99Z+~o#WwAl&s}P@ACZ3bGr<@c@NlOFGAA@=mpydrg
zOT8XGJv|+?M6T}d*KknJ_VKY^jp%J_uGQ)4>VlSEfJV<jt2Vy9y$vcfrf38*IdR<C
zQOL~BCv)KQ^Ye!F|Nh9lu6S`l5i}YUx+>&kA?u5MwZD@d9qEkNn8XTNsunpdF+Cl$
zqO9cYEm7ZDCXSoa&Iar(N=->id-Uby<&NIo*2RmJ!`4PE6+Urgfg^Lyy*-k)RbL$X
z<!nKV<5^f(Kufz<u3TwR{Y}Sjt`%!^baX^i)Uygc&`Ox!-`)mpPV=3j9nR<4C30}G
zy8njK*I}UX_W1h0TbJeREPA@3;Gq*}W^P5;S}7+dr+`%<nl{znc+$_!0i|g^84Cu6
z717)E_WgRL?K9s_R#ZF8rJYYUAvd=-c6ZssPft&O`2PL)hlhuY*WCW?)-Tt)V~2%K
z+#U(g@}GbJ0UH~e4?jL8$Lz0@J>DmKc!}p^o+#J+3kw`U{<r)0BN^1c0<9@3c*q1=
zh;eOgbn@{&*{G-N{Bk|NzrR0x{yhJ^d-p)~#m?gA0>Z+~^78T}FE1TkQEUiW$=<3P
zy-mT&N-BJPoGWyJ+Sk|D7bhNWyRoOzIK}e+{SUgayG(w4f8XEAEw1&f{Ov8#=<Rt&
ze|>!&xX_6ev=n8MO5*8hx*i@L4%78wKh^$obab3yRjTFIC({|U)N7$@x7de|9}jkm
z>lgg~mV4ybu|xOo%iI6|Q{4A^q6%j-JO8mOD}w`92C25Rv?$ox%ChszxfB%{F)=fj
zHkIGnn$0dPEq!HWu)DBA-IEi7pm99Y>}xKI-Fk~`p8fs(J#cN5X~?P&&Z*krZOfOd
zU%GT@L-KJxP?N^Fjprf@*Y`I!g)cAnKR!XxSwL908I&qPixoE}vpYFE3(CsQUH|&W
zzBi1|ZicRlkzDRK*Qr;^6tt8~MO{7l@2{_*vE45(FF$<zc=GFg;p^jiA3R6^t&E*v
zU9JaOLe0+3erI<%e_>(aj+&oFpyA-~@bJa2-@bX%b84#g<3~rktsI|~zP{Evb*iYG
zeI1Xvxp~N%h`{XV;NW1;3bV7bOr1|p(+yl7XB)CMN)*)ksQ#{ZZjNPh^!7YOLqkEW
zsb2ZAUE=zEg^!Otyq&)vRF#9K<Zj%)oqT^^t%skV8>n)Bc}aEg`M0%=jg1phC6(QJ
z4lMPa{@}$64hGN$qK*0Y?P`8LoeoNeUeon>&CSh0j*i}**V@_1x$n;>@3pm@iVB`W
zKEB+~>es%iuIu@D(Ov%Gi;IhYyj(sXl%!i)T0r@PU(UwC$A{<Fx3}Gf$;Tv0&Lkb}
zO8oZb<`2-80MJ6!S64XKty|a8+k3QASRFLq<TKOg=z=O<Su2tGHJ>=4Bk(h3&U|=d
zV{%7-zx!;n+zqwA%hrBkHDs&#_wzZZZ46q?w=!7$#_ijW-`v~`YKvQyz3KS+`nq=B
z@}QL$HYU64#P5^g7T0UpyxADk-V8o>@+7CUS&joJzb^NaWnpIr?UR_G!dd?Q9>^sV
zrc7xGUmqt~()%eWJvusCCt?GGZS^;oy;WZ?tPEBc(TkBd-Y@SS6C=aK#3Udsz1p;F
zs%9{o{htraAir{nYJt{$YQ*j`F)}hLcz#Y+#<GYdFE4LL(bF!+(!A^IWT)xHcK!JA
zgDEmJ-1GcATTq+Nw))$Gq@!IKmzVJx85wOTeC!6=D7gRcx9G;6^OY~txfk7C^%OK@
zUHbZ3#`Sfwpv9__RJ|Yl`T6<A-fHuhm>AGv)wP>GKR<uGSK9o;-SYbnK{Jwne|>%U
z?p+@{znp@dom~3)c}HiNW}7%pO+7UQv_^K(;>C$sSzSp-yC9Q{!t>_Mn^l<n?aj@K
zUtcu2M73BR#O~g<b*t`$pQ&Y_+*Va(WmWPb;e*-z`v10|VVm{)esNWQf7iNxz5cs9
zJDYi>%?=zn!lE6v=EBb(9**~lAKb0ozIE%-H#av=oH(&j(YY-nZ07lMH|nl{I);a*
zXa*b9{3r-n9p-Dy_WtH(_LVDFu87&W>72xz>2_uo782>_=eb^9=6i90BXdMV!~(CW
zTA*3kd%JvR8nL?f$sGLi^K;>^FPSWCY@qc$5&P?G<Mvd5+Byp&HYQcteV-$7S*`c2
zeNnbLygIyl_wL1|-r{RwcZ-2mu7OIjS+lxoe}6l8>5@?B>ae3nyT!Nmfhw6EIa?`V
zH6MqaMNcnm%Z;w6s(N&BvAadp7Y)$1E%~}13mwj>TZ3Bg64mQKo7?{W`Wm<?#q-LF
zKxWWnzkL0l#@gTC9=^J|nuC+mai&o!1H<KIzRo^AJb(WFefan>v$V8y%)T1Q-DPi^
zHg7im_5FSPgX^H~?2o6@<3W`LsG9SgZPq${y7;6?lL}s6(*?~4)&BZ&@pqm#qN4r3
zltobR@9MpkpWSM{UJVDW*Ew|QQqYxkvC(gCZ`Z&6mWhd}Ma8qL{><64|J!CkN98WY
zdrndTEoCwPe{r$<p<B12Zrr-nb-Z8x^^^CvxBHj8y5d<;RmC;cOI1cjre*#5^%CZJ
zb3FX~&VBtMZI&ajaN$DG`ml(oD6Z`6?7(#~mKXQe*B5?zax!K+KQ}jM8OYDi&!0za
z^PH>(TGx_#T5Ro?)6@04?P`B@JUZH){VHHvPNZSV34y}r=jO_MpE+fUiki<1g+G7(
zv~+iO8<?AmpF4N%(E0QJpk{+j<tLTvRd;un``7$_yM0mJ-(QOg9v*U98pP@E?|*Sq
zsyC>Sa5UF%o{gqe$qR)$cki~gwzhuw@Im10Y;$pG^SmpXyUX52J$(OO|IM2>ElZa!
zT@kTy(F~i)O%<P?^@8`R1@5W%81s5h(Nizb7(Zx*jgF3v%f&^mt^4=y2dy92QT{$|
z-R;$~)@44RmG=?R(V)$1pw;A{EscVLf}nMX8#iv8wdwWs_2QtVNT3BL+qP{xbnjkV
z$f^*}9y!}6o7!I?+4~<pd<dG_ytA)1dh)ah6BJS+#cF?j30&jt;Lwm1?cwVy>fFX7
zC?_Z9v^1!*=;^7>$jxb;mzVo<drmrXVWBgxRruGB(k2-TX8eD0QW&&!DkV}ZE-tPs
zRZKTZCF|N6%{6P+wr<_J^~2Y%qTOP;K|0!}H*s)r1)T}rWtVllPgZ!Yb-9?FoZO*9
zhn#lo+}W9RbyerX!|mP0&(BGgteZJ=X417ak&B#Kxj@U`MD$`JzP!5XeP?H}`^OvI
z;`(B5Z*Lb@^_n7Z?b<ca60nf<aj|D+7&`B%_^5RK@zNzrIzB!=-u>V~Lg1E+z=c68
z!Asu~5*9@4E?evO^T&@0K_MX}P!#p{_JUk!|K~&Vy>yl3ua|yVv&z-YjVp4RYe>kH
zuw5#iN(Kf2Dr#z7a<)|*<>lpxnVFh3wY9D#C0owb@yS}Lq(q86KGu8rWc9~Kt)SQh
z83zjSQ>VN{^y6Z-WL@>riQeY3r|PTL_1DYKZ%91cqH}st&{8j}O5fRLpcRnoVt2o~
z`|spr^`s{!CW2&U6)q`xd1+Dd@xG+5udXT?8wUrQEq}eE=&2WIRRPEackbMAIX}<V
zH7RKkC>0fylw8r8eR->pQ@#B5tgBj}c1B`qs%lE)wJ)q6KYmQQu^|z(B>2$Tv%V`r
zv>rZwtZY^KO2u!E#lp?<>FMd9g!e!B{lDb3>$vUv_Mc;Ydav|!_o)_-9YO&-nH;>#
z*Pe+9X9qDC@w!T<9hO|S;i;bXk*8TZb8^?pH*Y(_aC&V_u~AZlWqr<>nT|URv$eNO
zDCsaPbqTMo|Nr9g-?G;851nH8#O3?X)}OQeKJR<w-Re4p>Z0Fwx2O3%dA|JS-<)qU
zb@yw(Pd%--dre7c>D0cyKBL4#Ek$p)UY~aV@4Is5U1$GqtNs1WsQ%xdqIWx=Py6=m
zn^ESaC6_K=4(5}yv6!&??(=)q?{%lg6nVaU^G0W}Td!8PxW3+bo6l$d|B<?IW}0sF
zsW&$_pRT_5d7e?xlM_WpMZ>2Ym#cm=<NM!_$K~~Nb90xjUAy*9(P>@Z{Kq?=&(k))
zUsF8Orn2beix(Qt=M?+RG)nc_`EJ+iQ_cK#H{S0$J1_p<bmRY@rtjA&etu5(ebx2d
zr*=M{7cHh26EUy$+s&e<Q^Tii+qP|S-THZz&t`7Qxw+}m-Mg{3Zr?s#`Fw8pGT+%@
zd3!z{`!xIhpJgv=|K;y4d#ly!w)o4JFESrDrrCckJ%6xt{rPr&dA;oG>vV<Hd|p)N
ztc%>d?9JWX+fAf;Hx)cQ^#A8JZ_9npZ#LSs^`#la$=|PArW?I&ie>S$Dd*0e1N-u7
zX!un7zc2mW|L(bW@7|}q?`zkenQOfr6vUtqto!rBDF5D`PjlbbESIq;SaARA{Hj+g
zK|+_VUJY&Il`cDS?e?}@?c!%=G~d^K-~C(8JOBSq`4_)WC+}TeeR`6rw^w!b?}mH*
z|F?_BRV=(ya@lw3?%lh4Bn%hzNSUtEiQ2Nl=IfPU_n7Yy_dln-KR#>c!#3$(asBh^
ze!aZ)TK4?sjJuVyY|ZL^U7kN}rg6I5N2!?aJ8bSfUwu8kelN(hr-!)pb<*dShGk}F
zYoDH`n_YD;=-=mmdzLR>?laG3=a%i;r%zONpZ4?f^XcvKbw4^@&wEkbyx8*I@h2bm
z`AeU8{3PSmKKXphdDq`2*RD;roOk_zb35PE^)*kmQ!g#?T)KGi;vQ-9b$4n$pM83u
zk=ghB#?sf<K7H)3-!rHDUggrgd-sB*LEgBZef8v@efv`t>e<#;*ICW`ee3q^=zTxW
z=1=plc_f_r=f}s|{{1&Mr%(U-`ug;H_wMa`op*oV-kAEoUsGRQS-Eue>eVG>Wz+cU
zJ~ThQ7M*YV=zr=J+iSD;if3-S3`&|!tlYo8Nf@X3?EG@c`}EuG_v1imsP4M$#ph1o
zlWf}h+%(mH&d+6gFePeJil<z~gT^&6JB@_Z{m!)UN`HDX+5g!@ce#^uEQ_=3--qx2
z6&hFb@o3%jz5jl_j@(yMxo*#=Q#L;yG&k3lfQ++v`{zTu{h3csPjAk<yQ}8k=lS_x
z3niRx-MUqDGj;mY>-+zeuI@KV+579&>YWdoxQkAzPJhy=J}={I;Uty)|Np)>uKo4p
z&jWV*6Q7=*j;@ulI0O;|4X*FqyZ7eq^7jkwT@wwDnP~s#A^*?M^Z(BgRCeQemAm)u
zx3{;A>;L^(6SvnY{`alxelK&2e^tC(I=$$kt9a_mOG_iS=f$q>X9hWufgyd%!?kt{
z4C?Prs?R_3_xt_%`L(a3BX<_1PI_`Hd;Qs?;_-8C=k3<*xBpl1_Icf#WO?gHo6gQQ
zSNB}E^VzI}mIfeG=BRypdwaTJ^06<w-~4<&|NPwYdowqmv(n}k)5*Aa^1+$y_5c5s
zl$NIc`0)S#>Qm<TYm8Titv&VdaQo(ri;KkOt=sP|Uu&}1z5m>%)YDP5BKIEh$=S@<
zeBRDlR#x_}-u}<$tUv$xeEvCi{EtHm=0AM5`~A5dN#jp{-`DSd|9+|8w#9qx_W${G
z`sK@)o{KM@IMm9`{<KU|YTv)F>(hUHc=+>G`2Jh37K7Z$z;Hm)zk$!7<?owx`_msD
z9{&ATZJD65+mqt?zhn0Od8(iO{@z|m>#{cu`|mwFJNxp@n=}3EK22^ei~;Gk$kmD4
zW3hMd-kFxgX}fmq+LV5Np3RpF&Xy%F0``6E%}@FA;^JC6r8yhx{(YYR{M+sP^Lr{k
z7d>nhe|Dgex$?_J_s_@e{~3a&xVuEPqiT=XX@{+`SbOfU_4Phk>rXS!*Qia8udCd(
zd-vyC+3Qn}_sQPeS)6{XUw;19?CX5LB=z?Fc=YFmyZx!v>-Sk@Y~Pr5b=8|&TS0}!
z$rXW%KW*RtS2ucl-dXMSdnQTe?=h7B_o1Er?KaE5y|UJ3(&l+*SjA&5pasL*J3Eah
ztNZ(<r>E~foql%K)$bo0*<OHlSRCfJpQGwMP3GfmW02P$_!QqQy`K8`Sa0QnM)sl)
z4-S@;m8E@qb2D;dlB?a<mHu0QRq#0Wx+(X%J)Uy+-n!V`pSt7!BspBS6-|8gamSZS
z-k&e_*O~O&ev62!`}tJmq^o%B6w~Z$Pqy98JKZ6u9983F@wesyv;2uBR_;$ng#A-q
zUt3%GxYzvCzVCbWx8JME4qG2L_w#xC|5N59zr3`x`PWx*{kS>P<Ek|IZNCKk``BN<
zWba<v;N^a2dCl)kNIgA`_f>B3uiuxZ@4NC!8RP>7h6C1ai>Cxd)p9WSo!OFk*{JHv
zi=6xW_TGQGyZrsRD=ULRd9-f7?B1E6B6#Q1Y0;ZXUtf!<`}q_a{S1DSs^9N5zaC%z
z*Kqyy43kgCr1R%A3BykBE?Ab4{gsiyqOhG$*6LM$Q)Yht``<qt?v~%Ll{C!?d3JVo
z`K5F0Ag3I7@Z(Lo{cQ95HJ@kv?>rAPz#{H&bS(peUyQrEJD<E=&5@`7|2((<ZD%J?
z|MPVGrsU&&H6Od<eWGt~{GU7N@9*#Fx3}fKeD_Z7LoUcr7%q4vV^yM2{q4=kKR-Vg
z|NHrT`!5Ry9z~{-2F08+GYl&qwu<-dsJXwd)^pPLec$&o|FW8Gp6|E#;)$!_@wN+I
z=ilC@>pfjh_J<?PSs;TmI(=uGJ)M=kF7vA)gM<^y3kK&KUtV7Rd_uYZ$=2&}-s$P-
z_n%sqz42Il@x+&xm)XCR)_s~h|H<F?_4R3IXPGW|U0z<U{`0)N!!n<lMR%UFJ$M2t
zVD|leo4@^+#B$Z!S2p|Fq7ud5R;JIc+J;7Cp0oR!6MWtbjW~OA`Mlg$H<zIimcOCq
zp1t_?-d=0(>3VNpJ1`_H06TxV{oj{&YQNu&++SB4wl-?2%FpZj|4rqUHhZEh|I_1G
zpX_XvpTF<_pV!RJpZ4fTr=(d<#Qyagi=Ur+b8oLTXb$AV+p>}p70+cpGbc$Jr_EVX
z&3vHK;`y9n8}aKK(0yZj+a!HHhHqA;&wlm>(>GspF3+jO^v%57S)2W#p=9zsjGc*r
zS=E7E;!xVzSyNZ9+oiQSeEqp@{e3e!h1JszxA9iK+xficyzTcdvFn#FSGWK7v43;=
z`FWsv_Wt!7TQY;CdfnFT`}HcgwgwczaQwhT*@0c+ky+lI8K&9SQZ6s^t$aE){L@1I
zT8-#!IVbPzEdIUja)!yJYuCz-Jf9X+^#AYo^k-*g&NRuqw9>{5ZVZS~ASJYbnWr#)
zer?&iU9Z>ODZL)M_4>}|^QwRSb^8KpT>bgFzFzjsW8{R!z~FphgY~-|kNd*pnHm<R
z-rrXXilAxw@$(Fmk8Sy7!SKG~@-pA-uY!Kj=!t{;;Dja<NUR}Jp7Kk328+PnAg|1?
ziVPA_pw`rxIhMxz|Gv#P=45zp3R?@1e5@x-9-Om5-ezE6XxM(So}pmTt*Bb40G#sU
zX9Bkj-~tQ`lQ=Lg0KgFOP;x*vpMim40fvY|Cj<Ir16>#*Dj3#lVTg=62q|_L7#K!F
z2qiokM$-^#c#P&Ul<*iWhfsoJw4_F@-x)^hGSu|3VzjnL36Rm|2TE{^Ha}2<W3>5!
z79OL`50n5IZGNBx2UVLN5B}fSJzrquYqq|}^Y3oEWA@uQ_ox=H?4n#npEBnbK3N-<
zSSN!bN6xN1M~;c2svKP$fA_OEt-0FfF|p!9+66@&rtNvBC$-Os@cq@wvTSn7<)^=O
zI?mhuTJbnPy>@Tk{h9ioXWl;Z@GL*77cgrC4Hon(@>B#DK*zITdIN~5R|U{@O>jZK
zpwB@Oz3+`Bi8*2D5@NK1xdckL644vy!qDZ3;Z+eLdhDYC1PycuHJXAT;Q%EET?)Dw
z{vG7B2mi0<m<5N1-Zi#LD=0ANbzA&S5+n}A*JZ)Eqhw~<=9v#4PTUf;{Pny`hJXJu
z&zw0^Y#~zik4Xk+krzgxp;Ld<7@hRETWpnJwf0(DNT@1uX5MiOoVhM+b(_?4&6Wvj
z4QK$*b;<U3X#Exj9Uic$2vyj|?nW~na`<2w+#C&{(Ex&lz)-E*7QCKoTWvPmJpbIM
zr>Bh#3?^J%9sc~m!RF~T{~sJ|j@+E)3!1^WQ+7KSJnQ@O`TX(%Lzt(*^o9V=3yiz&
zY(8%{`}@6WebDqQyL`=ref##={CqOmvgE}D*Y|!tKA_bACw$HCPLZ`Pd$M->y;G0-
z?dQeU{d_8=gE}7|Hf!H5c7}qV`~Ls?{pRj&^ZfmP%gl0bO;NeIqcB;n?#IJDpH6B2
zd^S7(+1~0eFD~x+@u<7<<<jY&&RM^YS$z`hBp7jk=^5t>hS)dV`ujZM<KyEh9=7h>
ztm-}O320(}`~AAvH*emod|&tDVf)YL^Xox#q$(%p*Z;fuaWBjSFn!>VngjcbB+ykI
zay1_g>csB)vgdQ?>aeqW?dGrF_e%>jZObQPG2!>S-Qf9M&=gV5%}uIr%XTl`jZ*YB
zw60wLj*%f|-{a%`=@}U>nm#XFxNytuw=&jcIrnzk|NRo2x8q@(&G$RSH}_N)hpma2
zsK5V@(d})yr*{@V-&Fhio1Y(AU@0(KIfz>qKl7QU6IpbyvcCTRo!6f&OJ9ZDdRtcZ
z?#|5V@pYD-o66qa0&UN#{Qvj+=U=baKc5zz_wq~u*mE!<!SU7FY6gbs@1M=iKNnyB
zxAb7;>Z`M=|JL92o%Hqf_4(y?c6RfO)6YF=m#^E=<&EmCya%9g&dJEoINm3_`@x?d
zA0K;8N<BU8Y<2m~O{t(wN$>W4zxVmv`<>6{ZMpq+j!osKMf3M(US4*m?)Tg0b9?*y
z(`#z}1U*Bl_!tUA-`w1+Uj6Nj<@-1N_WxF7@-p1@Yv8+ZG;CeW%=P>KSuOXQd+O3s
z@8{?C|9-do%a<=HPftz#d{0(d`t(F)cOz@-*}vcKuYXrlR%T{vYr7K^Ilq3s-}gJu
z&E0+d3u~CaL3BatzuU~L%a<)PGBXRiti-S@GXE|!!;YHQ*VdlCU;lq@?C!F&b3yq8
zG`;@n>gvrkKR>CQT)+R{teG=s&ap1fdslnj=CjYOw`F#}UM$|Zxor2`&d$y|mCxt?
zO8}V<#|KJJ2wz~_bz@cN>Q7%T`#;}$J??a;u==M1%={_e-`%yW`jVlhruOXK_gAae
zKb!1tck;ab|2b}pC#qDwTDg2v+SyreZfsQE|My$8T;-FApk=b{e6pw3#qKV8+-rXA
z>sGiuAV$M14p6>aKEG}jXqC$3$&)QBKc#@u6f-;Dla0saW>@?B`}<c_SL^TCUH|{z
zo{z_*Z|*M7xBK_wF%Lig^Ude&PXGG)di~RIkZA}k)-kVa_uX~XEDU#3v$C|3lanoL
zeiXR5yT6{t%usOm=lS;=pA<|w`lC8WtMmSBxV{3_FY*jA>$v6Hx#419#(`4L(H;jl
zBp}3SmkbgPP;w;oStotDY76x?0|SHA(wjNUR;}8VUUKEZg9NEwx4Yo=OAHYz;HExA
zp^n$tG~>gEl{2^cUAJAj_}6cCBV%J-CvYwCU=`Aszy^)b(9lPpPpT-Fo_{&v<(4Sv
zpwOw1ZhXUPc%T1b>6bIGwEzqZ2b9bwrEGa82)62iXw_>uFbhE(IHZ8w2?0qAm*fkH
ziU(EKVBNSZEZw*Rs^Ad5vgBq?T1AD*+G{U&EiVbF|L>5Nw#*fIT;~ESIL=I0u3B~E
z`D9PGSMx3_Ue4TVwq%tSxFZM(IS?*k1aTeSqW9t$6!w;)4J9!oB!VpmX@lX>As<*s
zfawLa3!q6$Kn*#tEes3{F`$0@s#UM%T?}k)Zq783Dm@RDYH;;O)NL1z&N`dc*6w~O
zYwo&gFZZwC`BT!;qFVUCDrMCW8R<n5QfEH}rL*6_CyW^8)8SI~bbBoaX^NHXytfOS
z>%qoBhz$m#1BZ~1fRMOHRv*NFd#B)X>et7|Khn1^UFN#wutd(KD~?fYPC4A%tr{I2
ze5IZq22M)5(%Mfn%dX*by0q3=e65&DM_$>==Jo{~Q}Rx`x!6t+t8rwxInU<F{|n*=
z<5PFlA5TyF{&m;SH*emgKWt1-E4v4YY>;cPWL1;_9grF<WvLe;J%Lm(FgRe2&O(cI
zh&+hIHqitsXFzgrjM;+?A!3kd1-M*;8^XZApyHXf3sO(SX3tVvI%QpYPsslJ=MxNG
zRIwq{CHsLra$wgr6W?dg+cR%ZUAMd^WWD+9r%zP{k%pVYA%T(*tG)Efj~c_18(v!~
zZ<@00?(87s$)bkULf~xSFlqmz&#mj+5%xGNU$z_K8id$^3S!Cyh{Xt93|L|#YuRf^
z?qgtJSflTIdC8PZUwbCL`u<yzhb<OT1TZwbMr7>=%Q9!Feg1rS%UiGO!EURr&p!L<
z(<BbaTDOKyWq1+rV3{T^?;<N(z<gMRJGLL{#(&34t|ND#K*AD4Ez-k`L(D0Nvn9}`
z$+hlfnL%DJtB!em{r#7Rt$AHK$RaS_-~~-FJ2+=8JNf62LGJELU#Cob^)+qto;@m%
zMhQsai~zVgFHKXscpsxTRp&Z%mgat6HU()hAVS&7Hczo#(1H$R!2gV0h=2zPFfcIm
zu+uI{V+IE&`btMEYe67s66!n<HGK2@U<;s0DbSpGM+SSY1Vu+fCnS$Yu;Wdw3=N@>
zm|VlWbc)n`eKpB4+jN&{m$p?0dm;P#fEFZCT$`FW38f5TNX{BfuAl%%-~q0pkfROk
zD9{)tm;on7^D{gsK#V~bKv#Vrm0jKvoYfHnL-qu44>!UXe+FmBvjEo}8`7o(W!3DP
zk#ghf9KlGh+wXieUBS&1PzW$EFx)8s*INm^QfiSes#u_+3=9khj?8>lh2TP1j~$Wq
zg2c#dtF4;34$`uJygGB%l%QSn41@mG**70t@EU1KF&S#xpT)~EjqL4xZm%n`O<hv8
z_oj}%ekW381+8EIxoR#w_PpD(E%v<R#HCx_-kTDH+zNnZkpG!8QWn03^#4H~V7S9_
zIToWIYC}vf15$*74S^6tp)xdvc{T%AOZGr0q|j$*@H6$D{PSnxt+J)BHI=WvKAToq
z=?U%Jfm$b~;1tHdaA9STSMPc8$vnH~87p~b-rlRZ6cKz48)0q5V@C{5I$eiu_hMjR
zxVH5rG!Z~T4@4TsAx9ZVgaJzr2kJhsG?>6rvdwx4NxcVDvaoqn`H`t!*x^cW<1%|b
zI7=}+u)_53NoieBbNHIV`ofJ;=cGZlMaV<lczxxRp!*3sk@MEk**Z9tuQv19bm1!p
z$cP{HAEd-rKimUS+pslfv?>J!3IdN-rHHT?)ZJmIGyh{N#0yxV#REi9^3u#%XU_9q
z-liSvFS#-<-|X~hZza%ft7FK$UWSH^L0&6A{!E&bc)i#yMKgD|`BD+EImsy1)`1!D
z`f82#h$_Fq)ioqYAtdJNDJ%mR(8>>@14L4-@nd@VE66+;esIgwcXE)|bz`?x_ur=*
zNR-$zGcY8?f~!j9=lpRnbp^>L7<J3Z>LSn_0eJk~?Uei;nA!)&G?!la{zwP8m-4Z0
zj`RukP6h^s>s}3f1`qY(_RIin1}!W!e12~3>20~UKYhEM|GZOu-i}w_Ykxd!zqvjC
z{{23GU*D&1Zf@TB`JA=8sboXxF@!A%BH$kR!Ilq>N(>AKz6va0_SqpGUt>7G_FLq)
z_xI<ojo$w3#>V8zUoV#ze|mEA&7GZ}SKYTZHJ!TsUX}Lud)4nnkH6pXxKB`zE#dDc
zc72%Z8}xoC2r@7{sN%T5sCEN1MelF-Q^mbc=H$P>zbC8c@A=^LZvX#(d;a};{qxo8
z_5VKG&8vE~Qb(tQ5mY-sOi6hA8SJR~*`PMr>hCX?&reHBQ`6u7=hM^V?RU$f<EmaR
zt@-=)`p>7+<JY~c(~H?L0d!znh%v$p(84KBMF;j73HNKi$G+SBeqYXw4G+5>TbI4r
z@#pL6oh2`W<f`9n%(=6}aP#KPmEUfre?H7_-;)FP2-qnG_dr8o2VQ}uj*E+n>#gm~
z&8K@$*L!+qrt$w@dpB?1d~<t#yj=aCk066U^Vt)X-8W@lUpL3D)+%~ij^tBNo(CHR
zCK7l!LBaBV|NnWn^LD?@KVH4}-qZE}XW!jjp8oya-Rb}To-scE1a$bp;(ohX<@YMp
z-|zqbuUDQ2tQ$u3m@--&VA=im+wITC<?H{vt+>5y`u;lGvbVRUw#(O9fYxO2-eli!
z&jd@_yc_xYyru1Z7KR5=Yrh^p)_MFm!{jriU00)CKkxg@*042eZTw;3>xB#v=UHAb
z2<PPG>7}2W^Yiw{&FSaWJVEOsUhg}<`~5!a`}P0-n%*t@|L^b3Et!`^kAHh}bFyvq
zx0vteS!a~^UQVg2o3SnSWz{K<uT`5P<KjLgfl`_87P)!FRr@#@4s4C!@9!1v?`Kq-
z`dVc5R=IPs&v_ZLFIMenQ(yOZ^0OZwA6wS_`5}7z+<g1{7o`}~<}%18H09pkXRGc%
z?@TMV_@>0eZKsd#|M_gTkFRg)?{9Cf*Ukqm?=Z{1SL3_A_Wj=Pn>K7HxNFaxpsTg?
zint(3bFD%VltR^_enUgz)|$W2kT?wriQkZr$b1V5iH|2g`^#%o{QB||be4v!E>prJ
za1<7wx1C;ozt&v7=7VEg_1mo~Cy#cE7r(i&(dN?$<(r#Qy(c}n9$$a<=jZ2}OJ83D
zoiXG2uj<h4_utp=*ni&szYQp@tX{vbs<>XT!8CQok@|Ct3=9V}D$a2-Fw}p%A<<Cy
z%<5>CWjRBF(attzhV03p0C;<2qcUg(LnAZ$r`!4aQ(s?OYgzUtqVC_%=Q6fcUp~FP
zSMj(Pbo$@Vm&@nt{Xd^<UH<M2Gr!G*cDX8z*=D(?Rt7IG`tsu9o#OMhmIV(S!uJco
z(iE7!pvY)-pyl_E$Nj}09vsxs(|dMjXYtK#xzT=eEGEY8E{olF_R5uzWy_bZ|FQ4+
z{CYcezd0ww<7*~PojUc**|SflhR2<poxgA9+1cjz-^7C(n_y!>gak8FNdss3>$TgT
zeRz1-vgXH!{r8@|xVSjHMyYBN=#+qVK3S=+HXx;NoY3U+|GO`Q3tH}-Eb2bVglqBi
zMLjNMw_bLYe6^{v*&D26{^q_|<~rdG#$Whu-wnRGaMHPt+<J+uj&)iPtqcqgWDzZN
zs2G+uG}6QjL=lz_jyimV7or5)m@;Hw94Zf@u=E<|LfYUUSqN@WIr;nry!cwbV(YY3
zQnrr+KHH>6PP+)1HfCthSAkpqBWdl{Ip?##{WYvQwQ$+XDZgulp{q_0a3iX}nvJVo
zef+6=(yHp5<F+@yP2o#U8^odANCpN5i!-yH7{NNj2mF6aK*xz84g(dW&%u=xoX@~O
zoVO=EDgFZ2^k9Ef_R3Wkjrokv7f(x-1XYwEqw5hyH>h8XI{kA`+I{)O%VpAL`R%-K
z4xLCiFd1B<g3UTGdBrNZ`S&NSS^Qik;q<=v;818Ap+Oxo7zk3;uza)H&K~G^^8x8!
zRPz$%Tn(0(ggOZ15D2ycx9K2k2#GmYQ-Yxjv#Ij}+7*MC0U|NGix&{x#S1IXNFvq(
zfRtm~@Q9i0Res8#CIPq1wM$pIowvARb3Srf>K7gchJBo<Udms&b=v33v-|Ab{4KAT
z%q`lV4{Gh!p)__G8n%ao+S=_`jdVY6d16}a{$;B`{`muG@q(QPBJ%TmizGn{pywSr
zj>r)p83qOh8}|Q<kl7Z9Kn3U8tsz%mNVd;<Zh3lB&pbv3hCK!-PW$k7>$M`g^*6sC
zf1%kvYgzES@4lc;y^I^m*iKD#=+(!cqbHSqnbVwe^LzFx@H8EoqCFE#Po{q1U|?v-
zf1Qj-*$|g7%xlKX(-?6|R7#k?7&2M}HJIW2a`e(*9%{fc{Fr?$>fCeF-~S|Rp9Wkm
zIrVoRXvF9rd{qd<q(8o)Uw{0WmLhBWTp{|~-&w0bx#|zvR*)a;*^^Gc5M*HZ<A~<^
zeJ<I$p{7;G7Cx&yw@GJlI>UiPQ2as629tlXu@p)lHesm34C@1@L2dyX0wF%MUQ?NV
zQJJCP{ue{Y&;~>tOrD1hm4P{6g190U%|i?fL`4UNE{ZcI*vSmUWk$?BKs2m_FuXb%
zK+w1XQ^=L{huzTn%oMpkV_;}7hwagN5S_L5X-(Yb_x%@x`AmJ6-+4b9I#bNR&|nYC
zn+LEKieT#){s_V%WZzC`(F2jF;FL!zBN!My$e`sj1}uY#NVNmRq|rnO4F@PiQ~>>k
z*N;D{FzO$$K_B3Q@gI_+vMuLdfAc%}%M@qd%bMSRtHI~de>lP7x55y!OavRm!0@3J
z7Ox*RLCQp^#1A(+H}s+W2bM#ir3>>k)E}e8Fgzf@3@nR%MvGx^$Uupa9YC;N)sJ}0
z3g|)n$3AGk`$H7C*sz(4-ZK1I0h)CDv2D*|XmIY412>rcm#_NeetNsg>lc>nH#fb%
z9x|1GIwPp9d)gYh=<UF3aL@9?5qL55V?V-_uKtTqtD)vHFjVkiWOXvzPPKhVYrsDE
zVEUY)0$!Gax|Qp&bw?N&9<U=hsA1izs+v0QO?~r<C+PmJ^My_XHpn9vp>-SJ9mx;J
zYkQDf0rusAVq#XJVYb*jKUqRswd<FnHSQbiPsl>s{|)8Pw#0+eThKc(3s@QQ4<Qsn
zyYmlDhlKKP&hxx>v6ydD>izXAwF<=;_HdTVfL+VLa1VMgTLbeNPrb$N3=B1fAi0M7
z7o)sGd*>CdsGRqAfj9#L!v`a9@_}kQpoqN^i)%ve^H{iG>0dA~=%cjOWpbe1JBEh&
zABbw&!xB6wUhP*RhgSSQ>vUL}gGE}ycBD~+EYK*z_IR$fb9tdYnE+R39u#W3VINXw
zv`%wV8SK<R2WWUQFx<NY8XY+@xd<lp;oNAo3k^&tMdGjoRM+4efkP@AAZ{F>YPaG4
zhVuV<(buyXj^E!NxlF>*`Qwt1786&GMvkppSzR4@`5p$GzZJ}z8shA{KtQ5TcNVJ>
ziyyC}Yp|=!mMtbO{0py%G$nXGh}2`*DF3{q@9Npgy~kevtF!<9^)K^1=oy;}&^p`<
z3<k(K9vlFe>xbKr^E*gQ19+eW#Dd`i7$qX+?3)BeP^0dm0GZ{CGC;$?z~F!w-vh}r
zFfb&*GBcFVz<@a!$OEq2;0hQR7%=DCp`|QB(P-en!=hm{aNuDvnsVSlF`BL5K{5Es
zoDE+<^QNEA+uz@od;8X=RPWv8@8A9Xe*b^}`N-JV+{10WwqGtdhbMT${QzPlNOD|Y
zoOb8l-s<YVU$0mH`FPyA<VAqAdET2wcDWai`|ba2KmX&;=kwK{&zj%fQ~6o+jtEE_
z9RFA@yntC}<9WN^YaSo(2OYEj?fw1xll|>(vdh<8SiAk+t>W{x-}C2h-nQ-9y}i}D
zKOU1_|6m(jJBV?>9yHP0x%cxq>)bm#HeS7YwR^MgY_qRNg#EvqRG(k+>B&iZo5wFM
zF0TE0H5_zRL3mLpNFN+0aDx1BV|skuP1*807q6|2)}Q(Q*4EdL-tT|@=H}+Nx3{ks
zkFUA-_BmV!h|$0xn=o^(UG1)^Q>UJOrmd|VyQ5%X@N&Pu?|!e}^T{iETh7au%jfS4
z(ndO#g@J*=JLU2Hy$lTX_jVRPzqKXva_Z;o^?ScPdcXha>-GEJU0CQWYhSl#_4<9k
zy554<!GWv-V;z2TP)MDfZT|i9dHZ;?|DfsGfB&MdUAwmH{l4E-KOVNPzflKP3L_2_
z6*5~L5Q>hBe0gPM@bt6(^X+1<o;AP!XZ3r~dXK%|?^VyWC|vaQ>(^C!F*`2k@BedY
zXYuo>`1tp2(s?g-y<YeG?*IB{Gt+nd`}JCX=G&W_m)ll<`!f@M;5*2k2mTgiZz4bk
z0Hl;XJ2P{CrZmGeaD2SIvvYI5-LDm!)6Z`!eSNL_v%me{Ek~0so||i3|8?*CeZSWo
zO}ePuZ&P%#W@7{>lJfTd{l+I}b0gT__UrEd^&cJ_e7EoSyZ`^3LDs<VkIQv$oet{n
z`?09{-OlIvw>TP7)g0I(lKSm_Wvt)(Eh>M{N4N8KzjH#LpP&E!#6;z{_xA42y}d2;
z>)-G9%b%T@S@!0}#nABBtAD@WzuzgWu4kQJTDtXi-tM*2<EmC#zu)s&|F0O#E-?Mz
zy*kMJ-DPiIZ9Fdbx>Y>xMZ0`m#_>K`S<9j&U%!3@opk?kXYKEArC(lL-1qm}?Yx~&
zr)|r>fA8Dd+xph|xw&g+=j~d_E?@Iu{U6jN84u*08u&ImxmWdiE$B{xdv(9x*8TZ-
z9JFBKUhVh0pu-co&+CYFo8{d2(4MX<)-Be3bZQK!qXl*unE1gC%0D}^*X>-!%+6Qx
z;6UU38qj3<^gA8@qWArLHv9k6EU-ctabVKV$FB?Elg1F?ANvtAst^%|(bfz!AQ%`%
zTQl&W7;Oh5f@1i$W~?h?uc53380}3VqJOlj2@i|WemFcRMh7Y2K`}al0}qOkFue6Y
z>HWLd&pNjm`2I&FXD?A`;@UXL@rb9_%7AEAb-`B)y187tJOobOSXj5P-hs`~!ouRl
z0;jDnUOYIiprOV0=uv>W^^FLZo{%eUOWzj>-V0LQvc-&F?)aC2d-CTi|1;X_fkG3r
zq`_Q3g*muLOyicAQ9&XGAV-}8iY5pijVwqwfJn@vS4Tq!6fO`v8aj}00FhWm21m;s
zP{4rkXy|~00Zd??^E4Vd;D7-WqoD&11~7qTFmJTI0}dGwF&a9cP=MeAqitnKK!6qw
z5!sXQ*>m;kRnU%9(5U~_@c6s)Y^#5LILv>&_TA%t`*)4(av5c1+g`qWnU<DzYkPkD
z{JLK+_ir$T+XG^35CrWIytBC9?$)D6N$h+wFP2V^%gV}H_50oK{JRtW%+BBUvP*ki
zMqS;$>G5?to!j|JKRr45Zr|^B_v-)ut<S6m83M-%$}@M};btg!xbMfKZt(m<#lu!U
zIh%;9jm+%3-fp{H_35Pg?<bS}|9!l<bLY-y&z_x|b@u%E^3P|@x9`|-12i$@Sq@!K
z1~t@7PJIEh&xY;y>vpePxe~N{b?eP*Yolk+p8b0BdArx3?Vant`}+Hr|NVM>`=(7r
z8^c+lIw6!AXuhloGzE9J>h;>(+uPo*`T6ed?(6H;Kfkgv`0tO${j%0&YtrY}Zd<?q
z-!9PP&ZIY}X9nlw1W&JKWYD|w=~I!hvGMaW>1k<J#m{`y{pLh`m*uzrQ}BN8_qb5d
z#9OEOycav4&)fZCH|pe@^n78^R@(gif3ICz8-0FeeCgHD?CaMzZ`g1FG~Kv*{k~iG
z_Ety7#=h;h|F;8&?k`_Tmiy1QOaJ%#{r>f_@#p(wt*_PDe>$Q3_SV+b$K|TmEOzgY
z+vAEd#nRBJ0NPe;Y-~K&qVUn2pPxPzg__^1cwD*n{VDDBZ~py$pP!hx@bYs1|8HNu
z`v3mH!RFZFv!>~1L6f2X{{BAyx*plM9R==vGA~a|R8Bt&+QxZ$3opZDzXm>ogJtjT
z+;o?(y#kua+m?I#+Ozrf|0-vj<z_uUH~0Bp&;j3DjnmJSyt=Zol=+Kze9gw#-DPvX
z*F$0mLKb}dbGNZ6zV2u0_WO0eQ*UuJcy9Yyq|b1mwfe(B_TQh++gCrG8h$Np_3G8S
zy1HA_&(GVIe?RW(_xtttHzptd^?LpOYwvzPY?nV*dH>WYulIXC`)%I5Ikx<6>GXfF
zRd*1J8hDR#f_4jke|Hx&v26SKjPYEX%1zOEJC`n9y0lN;{@%mG?bqK`|9ZK+`t8>1
zzrNkhpFMZ(+N}HgYVVd@_PtwpT=s6kVP4R5>C&Z3r%j)3UG?R~(_bnO)1l-8BO%Zp
z_3QEVd!Ns*-)DZWV)6XCUn^y;%f7tZ{l4saZ28)|n=>yj18o7mR$N?My!Yp`*}8gq
z+cs^wwDo%2?R$HxLG#(=_bQ+7{|j0I3pE#X`VSi@N(-X5<zyx%E^KXWt>5$f!^6Yr
zb35Wp?d|XX`SWLK9O_E@849zn??=rQ3=RL8h*)ccvKSKN1S|vb#H^qqVzCz6sB=I8
z491vC*+xSL957&Fh=<O<<NIWVLA#Q9qW)j8JJtYQrL7J=QWWe#2ob=Ee55l-Y!2ok
zLv&3AOh~7hg7h#<Mb~ry!`u)IO{0zhhaJOc$UwqjG|fQ5VKg^E!-0O~j9AkCNZ49{
z(E<<>{G(L^Bpet<>nTV;jMh_-a2TzpAmK1tPeH?he)ZI7-2@5p(Ygr|4x@DwG#p0j
zCP+Yx)=iLb7}9l9^837~Ejqs$dgPTSO=S*jG2~=T-O4$UWnx@G`W3Z~B|M9cK472W
zdu>s#wYVX7wCIa~MwW|tQLa3KBCLtrE6w%_SZ?!Vsy1GnUTkF0-|wIHtm5+f?SJB*
zSKj^qn^`6X5=5hmxgg;HA_sc8QUfPw`wnP6<k{KTyT9GazP+<JJ%9h-Z}aa}Kc8DZ
zYwp~)>vq4(dVH++Zr$&<Z*Om3KUv*Bu5B&yya_{t_QhXY;}{zDKYzJ={=2j0_jB^{
z*6BuX+p=N9g~R;zcP?ED0-aJ@`Tp(w{riKL`+=r6KsVunrqTFht*$(JlytmLHv952
z-{~LYL7{@c;Y^_OReygt%n#lO_pnub*6i7<U#(m|@725A@88W#pZ9X__j}gw@BaMx
z6Lgqu=w^2LnhmkL%f3G9)-QW-ps~KB9AO#*1H*$;oAcI+Gdy^-_v10?wekD+)&Bmr
z_KaE1jSFwy<h<YizwUnB@3)oj|CQIoeLcX;Uvik&{L9Pb^ZzOTMxFBtHv>7$y6jCv
z`Mt{Y%a<>&eg@)H{tN%}<8eP|1DkaIo{y8zcANR|fpkU3#pR`?J)86M%o(5hKOf!I
z{pS4eem{Hu{P)}M*S!Xv92|nSy-nB!G!F%ul`_k@QE=|htJUk{D(e=4_A~LxSX_AA
zZ+~xH>~6iAeJFlC@C0;}@CMK>ruh25U+4VP-~VURr$0_L-)^Sc{(7-E_wKH()8p%Y
zPI`yBC(ftuYxZ6S2J!r~v}MBTeshfD<Kou6dNw=%-{ta}&u7iw-rKwT_4@t$jvhT~
zmUpM(;C_2^^XsM8W4C8*D}R6Q+q=8f2j3$*<iUH;WvuS~a<QhMIjn0L(y&uxZ*N<>
zbm>yR`F3}|eED+fPcy$=Mpo9U+}qp!-v52S{(miKv*eqbn{{<{OE3GH|6O{2{`~px
z=T*Pkx#BKz3fy7x?>alH{l6cNx8>j8=O)c)aPr#PuS^Uvdq5M1o72yKyX39E_RP6C
zmX{A5a<VRem-G4A*-+5D*m?W^dq5UFz2k5H_lh&W?UhfTit_h<4cmUV>~`vXd1P-e
z?AY{!$?5>h?TyLq)!*K{-1&SSXo5ET^fX;v9i1;<ug8}^IWci+F=(S4Xs=>??bp!l
zcZ$42{q26H$k%=e+`M_StbN^{$H)8E&zV1O-n)tJay#GrN1YIkhz1?b3c9oQ+n>+p
zzu(GUU;66G%58afK@-^D@0Q;`HFM?4mDkorZ+~@9eSXcQD_26=`Q_hzczAgAJkS&{
z+M>1};^3LO)$4YxYG&sz`|#l4=XsVzPfo1TUld;Z^Xc^eU(oikwM2e@j&$W0*#AGw
zM`yvn0RbXL=LkWe0KpBTGpLY&0Fjs{5{!lpC|n?TG;|>003t`HyFsA<!9#qy8|;bE
zVh|h*5Mnf=L&5<>j%IXFC_wONMu&t0h?E#zF$M=%_Op)A&^b4&x(l`zfPo=lw9f@k
zBba@zAN<wd->)jY%U1BGR-W%BzvlJH4@7(wCn+{Xo0wjIpul%g{y~u2l`BGmZi~B<
z8d)s2S$4R2Iq$I8arME)who0~ipOiFy|&~pnpdTC;qlqeRR{OR+<)KxzVtt1zTNOY
zf&v_}n4vm)h#xp$K*VU^fI<O+N6+MdgaZQu1Lk=BXyA+n4wg0y+BocJ%7Ld628I!R
znv2fP+uQTMKbxJut@`^r(1tJ2;e0<oKmY%HXY}^G(my{w#?^d0I<Mx_$*{1nT@@c6
zG2f6t3OfddiU>~7*^n0(yZ?T%xZkSiiHCgspTgCvSMUAv=`?63SbgQYUteF>emKa!
zcK!P8<?ru_bsuHEg>J~&yzfj5e~RPl|CWO8nUt^lk$AjMcJ-?h6P0bh-zf%7kAWr#
z>Z`uN4(GeRE_SYU`MT57_3c+|MV@|PXlS1zeSvY>jpy_0@4b4JwSND<U(a%m_sQ=4
zb}Kt}U(HTw^SnPVZ>rC$SQNXv%(lZ6RkNxh=qSMO^>J@+rq9oPes1pfGyF0Z8-BtL
zN{9IV!FwUlL5;J`^S5o=wk>tvwr$t$?k<mxkH6ox7NP=5Hl(V8%-jF(SGIN8n;S;;
zUoN_v&qv)Q^(U68q(SxDjpY8Xzu)iApZOoO4GQG|Mh1p|>#n|yV`!+)%gtT;_3KyN
z&$G?*!@hpG?0^6IdwJ`!HOuE!y_$FP;o)}cnjar(|AG%vfjWWVf8n<`H_y$ptv>%|
z`TV+D%W@ea%0M=Prl&w>LY}w(f9Kp>YxC#f>tZrDMr_Hyzwh_2zryN%U;cbPfB$+u
z%p4H?;rhSZtxfl9KKuUu{{H^5UWSM??b~}982;bUUccwkv14xP{`2n4xx24+_vPjO
z<sTj#EPH=1_UhW`?Yrv!R+YcIb8}rNT6jNTD``*#O^(LZe!U9X$GGqRzu)sJpUnhK
z#FgK#y}mMdx!HZ|x<3`^=jOb;oxeZ#{5;#)pTFO$UVk*{;@0fzyQ;tEfut@i^$y+p
z_uFm$KmS24Mc~`spd%RVem<Feuk!g^yT4y9gN|VQ_U`U&(2<`Do!iasN9u^JU9%>~
z^7p&l@3%$hnBD(bzGYv84qD&uLw!beFUNtP$|n=utN#D}zPs?T+x|bFyu;VUyj(gx
zZrAg<p!wvD8w=0BeI5#$O9grO)9o8KDkh-p?PFl5@E~SyHWAyj6yX>DLH&zmqcfT>
z7#J`|KSq!5h6dkg;J^c7^x$`-pcu_o@W2>7Dit0SqerD8f?{->3LX}SBYOTPy{~gx
zv+lob-~Ke2B9m4o-mMzqj|D_bJGuh8IlMQ8vblYmerbi6YT!1{TP_`(QH?t_Pr0qD
z=lUi8<#^PTF43+T#{x7<q)#{5WSq0;owxhvpFQSps^6`zdph&t@#M;5`g@<Z7H{};
z64t0%fH6>u<+5UoMuP(M_8+(p7#d*L5W<D9+@y(iLns3SmJ7JJFd8wKSKNwV^iL;Y
zG><eeS}~Yc+y-Fi!g80)XaK>Zlz{=;EsvuCG#WtA5E#v3(13tYqh$~z9H8WAAq@=(
z2sK)ZLBat_j#l%~fPhd#xgFHJCFufUEdazn3=E@<Mp#IIX@}8PH8>og#Avqz8W0d_
zv|k1Z2Pioh`(+J@`3VUMpi8FC+5i93BWG)6oPO>M=u)SA+vwF-i_Y7Af3oNExzjTY
zlZ(Dy4Nw35?d|^$N1+~qPzM539oQwFfwq&aiP>qi{cc$_XeMLJ)~%`M=2+g`Q(1iY
z`Kzy0&(6%8T>ARj(?)i=6T$wrQ|H(H(hQF+4F%oh6kK8pF$+o>OyRh|*tRkE_O{f&
zzrIH9D#@It7dwlUTkOeUe)}`7;;~bXc8i<Wls!JydvjB&cU;xWr8eJgB=3B`@As#R
z?((TeIs_~Kd_3-dv7F&R{k#3MY7Ypc&Cc4k5|zk2V|O(t_^cTk(R*|GtlU*Mm!T1c
zze6_rn%+huOw#5<&1G!ZKbb)`K>~D&;H7KVrnPd5&#TCNa$@4n-|u#BPCY%X=KtUC
zQ_t`F^=kD@gG8si9S_@t*Y`@B>wSK9_VnxZ`{#kSy~*#DZP?%aKOzjnRabK^+8
z)vR2p&Hfm!3fb(N{0+^wU@pST%nbGFj8+E>wk03$D=8~WJ2S&@e|7D#9!d3majCz*
zy`5=Q`pR?t`5A`F?tL<z{{H9hSL;Ay2SOP<;RMCe-{0TUA06pb-)mR+=*X4VU%!0&
z_HSwWWRn`y+r}(x!K(M|+t(vw`Dw}Z+qZA~*Zf^?6TSYrv>obkm~-acnpMldP=9wt
z;Nqe$FD_1wd;k8u{l~BSKjnCPdmm2!FS`8w&CSox&*Le$_3QrkBjuCkocezJzu%^B
zB7Zl3Q~UY({eMVIXRfjQePh|Jm3P!6<LtwsVmUAN%io5??Z(Uh|K2d`<y}5s8xpN1
zW?%02=Ymtj<r^>m*X7JU)^_>)R7hfwlK%DnIMk3gU+V3*`6eHJ`TP_l_4M-o{hkal
zgh%)Pu8Zv=Odry>UU~hsYI8rsgY`SV-O9dv`}XYE-DQ8@ef6DfmU?YXWaa0x=EZ-%
zUjP4a^W3>}U%q*BCOUub*WK6SD;~D$#OyGzE`N7Mb$ZOF_Vepvcbjd$SM~b-XJ1Iz
zL&y*PFW<d8r@Q^mr8mY55^gn2RtF5OUA;QB-~OLPJHPz78HUMzd-j#SzP4q{mL;oK
zuYS0Be$A(op6m1P?lN8M-tU*5p8j<6=JfM^<>lpS{`2m9n0yH~q6V@cqi^57eQ$1W
z*Wa9eKJS|*1COyCqill2?QOZyY3Jt5e0qBN^M&nlUXyruc%EGH)<65><KxdSm(N%8
zto!k>{Yuu>l9G~?BOQXClX#`go;;hKf9_bXv~l^nJ1Qs7+y9?)?%cVU^1G#xyUTKm
z_i2LcgX0C6EH4-i-|;oSJLP&@wQjeVu9v&JJ7`Y6=HJifH@9R4uiNpcOXcL;@_RE)
zv#+Jx-&ecy!y)d;D#!cf&rc1Ho2kG5j}hqD)MLHU(?eH>J>C6&-|6)EwbL|%mzjLN
zjk=3;)`GP+*%>~}ul)IR`sS3AlS<0VpHGjkJDEB?b{goQP?wr{D!RJ5nYp=t?-s9J
zySDQC-SW>Tl>49DOrP%?A0MA~X2wL*>}wsUQ`Zl8o(f+;4ouLf)1)o`{_kgjdlSrP
zFmA-SL|6qhGALp8>-X=?<?rvkxwqH4`ujWI`uh6K{xG*UB))ucadGA2Uh_@G&(EdJ
zH+sUu$Cvi~-QAaO-{yYPbiTAH_4KCn^Yc!vum5^AJaSvkP0c+V56)b^etr7S&(G8U
z{`z{>j+MbLTK8+!-g|G985kPu!&YD2lytN!=f(y_TU*<o`|E4+Gc!+4(F``qzqdyx
zYKzA6dDVHs`nmJ=?c2BK|G(ci_tjQcRab+I3|#D%dTEL0%U7>XnO={Xd~vb6`R_B!
zR$qUuzAZB|GxM9J^RbP|$3K0&9zXv}_437wm6hFkGQL&%etz6<pLV=YR{d?!&!^MV
z54CWfwaY&tAt7-hGJWpVH^yyK{{8#+=KlWwN8Zow6joohckkYt>4rU^#SxJklU%E+
zs%F)mnsDXv<;k(T%TnLn*?HEE)sGvr>>z7vl$!6XD{q1u5;GDK6kcCjdwQO2wNc)k
z9d{}o_s+Db{N%Ym@A5L=$Xz9w_p0CT4X%G;Q261&!J6N1x6iaH&D!kG*kF9`-QC@r
ztG>RHv8gcFoObrq+wJ$~B_HogJvm7glx(xMMlJK7KTmyrjnU=h{`uc_`WC;quu#UT
z<VE>^yU5j7Kb^CFza(sR>a8uAGtF|Ng!NM_BxPjIJUrZ9e9rQ@$?qwO>F@9DU3oQY
z=Z{C-fA_Qh)BXMZ{rN^__DdHpPTYLnZuiaSCU>8moh@Crcj;2qw{PF>e9**gRQKmc
za7pOrtFOOq*}fgL+xy(!@Aq!MDQ=r`@ZiB7DO0V})Ai3c^V{8cQ`|P^+O=yX<>l%B
z{`{=}@%8KL>mZh8*_#`h`*L1bRD4L-mUD9wGdo|(w>LM{|Lr^Z@$vD?x2m4i^gWuW
z?EdeIar&eCrMv(C`(1oJwmkIT?#trwH4~rDueVzrw$|$CbY9u!=4Q*17XiomWM^;N
zwk>VGaY~P@wV8I<niEZ|+_P%A80JhnH^+V_Gs6Lc&H4BDm6Vn~?Npz4Vu|PEO%)#>
zff@^|!`GiXHC21_kNO+C->+D)Zg1^_^9(^EE?q85Bbzl8w1foM7<o0ODI|4nOw^B9
zWY{Gh7?6|`VX#QyTiym&mk^bvOF9h)o4f)SE4g+lDW%rc|1f&5dPdTtE<de*-uraj
z>!%97#lGH|es*SMTH5>Cx<7(%Z*6r>NKmNy_NMdBotSGAQ}t9-SlHOu3d+md_wTpo
zle6hKal%8!rb6J~zkd>TH5NQPJReT$@88g;RcvZ%dSiFF{+&B_E^Nz<*3i`K++UM-
zdz&sBuT+a|^|uAPcFigcQ7bAcGRVB7^5Vsd1<~8{Bn%Q5+IS?J7@65X+zZ#P9Xrw~
zJaO*avsSBoRMpiFU%V*z>({S>;^M<oG=m?!ecP)Uye#3u0>=y2ue<NB`#WLElp|KF
z&Ro5A?a_mS%@Srg5<I-T3zsZmF*P;S(9}G5;evp3JKxbpX7-Aoj|($1HN)1$bmraN
z<ro_)JJ-6rZRbu)tMYd|rKP1aX3a`E+9j%?r<W!>wex=cf7#9H=iAn<)$Qr+UATNX
zdvbE}ja#>puC0me=<Q9F4P3Xk?ypp2WaOIU6KjRl{Suy>n7AhS#L~m<{D+SoZ7t>5
zxh3ta)QS}=HuNb@H_N}r<LvBw&G5;ki;LYKK6`e|sx5|#lk*^`EVXKjv8w-Pv&?_~
zIjc6GJ(Zu?!otEneEM|g*4FHe6(5sk%$RZD{CWQRyWD@Co}S*(*_k+H%G!<&j*{2c
zc)h&5GVbm&eRghc_x1Jh<`UwPk|$5I<`fnd-q=~JuB4>&;oIBj&g4mxCs!87Ue(mm
zadB{9*!TBa^qINV;@8*5Pq%pY=H})-)wbu(oH_F3<mANc?Cyom?T;=jbQU@;YgyDX
zUHXNpii(1bjZFHvIS=Q&sC|5l_sl%o=wl~u{QB^a`P=*Z{PObhId^tU{9N9u9lq|v
zC*!M=)%^uzWqYHy=N0zttp2W7_v@v)<g%pa_x4tA*tYH1x3{+oUtQ6xsH{AA|Gxab
zefv20`P+MYd1Yi|Cd`?`qpq%gXLosjY0AviD_0&oGt+qC;>FC)&dxJt&U|=rvAc)2
zxAXBn*^hV2?<anHbMwcm)$0xF{`_FO`=NOH{Q3P07AXAq`SanctE(UFZ*OZ`6u-Z2
z!<H>awq#ze_$i(4<HOU&E6v8v&d$QZvS8IJuJ`x$9=@?L`Qo0+Vo-wgo~~z6{Y~ff
z3Zw1i@8cpOA`YB5!7*9g|JZEv{D6P}25W2Ul6Q9`_f~&zn>SBRzy80jj?R&5Yoi4P
z1OnEJzrVLv`tR@W?Ng_Urk$PDy4-)hk&mYQxjB~2>tc5wI&gqtZ`D_)q9UV){^uLg
z&(E`{{blmFCFjQN+s+yyMgKN$-wx7wYfC1xv9Ym>i_3;S9pO^*dJP?&6j|4Ipu~LQ
z1c$s`O@i#x$ss{Ohfbe=T*}16v|#=E{)5fz$)BE_d~}}M)z$UFg$oa^R`1-k%gV&W
zWY(Ycsi&u{Q8wO~e4KBk^kw_HKN8mE@1`Uw{hTm!W@qN*We0EEkkHc7x^VSsYgZT7
zt?l{!GmX<PrTt_0_3dr<lqn+D3^^2ACY%?`t#;;6Y!PtknDgu3@ArYRvAx#i??8EW
z&f|A?ce96whwH@b5K#A@Hzm<&+o3~;4ARfZ?AX0K`P-YD8@6p*_noySGE#EVq)7ro
zLQR#QpE*WGN?u;(n>-_;tgEZ*!K+tYx3}jnPCnjOP*fyzzjepEcSkfeHD?&5a&61K
z-PSFx@8s^@UYax0)8D^+@nU5cB|#fo+r-@5yAS@TsH#4Ea&j^#=IZ|cE&uZ3Vsq)6
z`q-Qt9X3804rXTNH8DFUectot_ICchzP^sGuBOS8g<sz=`uOW>Hjk7Ehk4!|0ezWi
zCBCk1Zb}vw65@I>4coSvy}n^IarSI(b#--{>Tf)KeSHPx<@p79lO|6Vl#uAC{r&CX
z_xttJE5uKn4|H{9J=P=HT>Si;qpvTon3&jxO`BGg=Y4yBzyHF8fE_z`KK$|VaX@fz
zvTU?k+@6YyPd28erv6V7`eb?f<jIF`AMHDK<=VARWx`6I&ZnlPDq301D&^VfGJ9!(
zx38~jMTLcvvvZ{T&+BXB_Dap1IrGNWZ1FaJ`M&A;@kwuQZH?GlWqRrI<-#v70`HaB
z>V5q9QNprF1r(7hgO@Am>+@TezdLervU=gCC!RH5uZFKtHv0VVFguT=5sRUr;Um|~
zsHmuj{dKl#{_|q;-#k9vUs)W>cwlw-`U|_u^Y>JIWSTW=mWICm@o#T$gLB>Ub92A0
zTWy|y@58IF7TVg}wZFbNrlzX;`1%&UzNS0JzFsadG0~##kHwcSUydYaXJ=P#O}y96
zFaO}(yS^7MGCrCvUA(xtSK2)3Pz&eRV|Fz^1gy*7Jvlpf^SwQl%+}V{clK6?*W^vp
zjc!x*o_65=eR-xv2b*d6(#twrlzisf$?h(HFZO?}_jJ7<Pp8LU*kAv@D*5uIOB-r_
z7U@K9^SNf2dhY&x`P^Gu9BXQ9zI^#&ka|ia=hha^*xhAE|Nj1d^nPPnYU;sTx1_SK
ztvT4p%r3Ef+S&~p3|iXSk}fUrG%z!BD=0A7vuDqO6)QSs8mAw+d|6mjR1_5E-`?J4
zx3;#vcPH}e&CTgAE-&Z*^!YO*Lt|qj$Rz=BaeVRd@evUb3$|?&tN#A(X#W1cZL`hu
z4;?trP?&Yo!^h{yfkx(qOP8|7#>W2m{d@6(1q@TCPWABiKK%WDeScRM*Bq--E@ihK
zhngCjoSdA9<I_4<tkCe8XCs-GmS$jVeE8qr-+_UFjk9J+tysA-@%Fad6)RR8`1kj>
zVg5avk~cR5o7s4iWTVyo{rT)45go0pug`zr`1KdE)@2L!?2+-FuIKvw-Cd9Y8#Wls
zv8$EZo_E)2ciCHs<!O(%->++KZ)eZR%{4506R{>{XHbn#c)0klU%zf_PUpXK_wLQs
z6cr;Qq0`fJ5AQC2Z&3Ow1XK_*e0XtDxuw0`IW|_-d%E6HP{}VP)fKqd?ctG5;SV1^
zB+U79e|yeNBT&(x?B3VX*~$6Zq6jqd0ji&t`Oa<&TN|~p?{JKh6Vtlb-D-6;@9tRs
z`T2Z4@3E;<raX9Xu=&Nky}NZDpX|-Oy)E(Ssi`w8i`Dl1`<2}zVdzxj<L=J>?%lf|
zU$4g-rk|5((@cGST)uwI_nEW3OG->GUAmMq;l<@IudZsZShZ?XpJMQGzqyBY6h00J
z3}j?xX5O)5heK?vZ2tXyu5NB@PR`DS4-PQO*j9-+xAUdSPM`VULBft5I}*OWx(c$i
zq_i~BU8zOD$xeF<!(0I;P+4eM`t+3OkKez&V{7;r?(Ql*e5jTC;rsXci&H)+YG`mQ
zcJDtnQQ2KZF8}5x)tH!=2ag^#873c7(9q~G=e{7W8`bjWO^%DJ>%ps6rxwSQl$d}j
z=06_}^WWH<-p?bvX=}zsr7hXl`8ICc_*L!kzwIwCFMs@eetp~I$-;F%9<s;mD)Bs~
znVNrdQ|g9Io1A=ndXC8FoH={;;iE@QN4v!j-@GY#dYZ0tQj${hl1<+a^V=&J8w>CM
z`%RjSU+#>ho{^Ez<72&tA06!$l#|mt-16o^n&ur)uIm=pPx}4s?T1gFChge$x1C>p
zL;86+ornz#pvYh5J6l3!sx32fv)bPSd^K|z?p@h9zq|7DGt<g9z0&6Yj;cHfo-|>?
zg(n+pb~9gkc({GGjhU_O-*_J<JJl_bTt9c8n`he%%2uaOb2D666{`K_?r!mO=g!Tr
ztF>a|k!Uz^!XwWA5-$fw!_J+SLc+qJnwi1D&5g~iPp0$V-`|g4TwE++l)~|NN)8Jv
ztD>43+rEAK9`W*ATOZ$_d3o8xYipx#Y|E8?Z&fI3Z*M<k>Qs;tKR>^U&(C<x^6qpT
zIN*?ymiFk*&SFrz>GcesAHRM%`TFvL>wrE`^Yz);+3eBL(Jt=p-Qtr!oPBn7wxFzR
z?^5sS*LE-4vu97i>ub6>H#fDGx};?s7RgIYOyuC_KmOz6<D<{hPEXS<C@noY%QSmK
z#mA&;f-^yR{>)6{i`#Oe8RYjz-``(vujV@|B%k@5-(0JMr%!Vq?~_dyojUWvg#b|B
z>d{$lA75X?v@;SubFD-h8yg=L*8cwH>gUJz?d|R3vsqu1?vGYeRRz`9phiiTsCGg^
zLWBLkAI^X5rp}nr!N|;}U|=AisHmu;eEQ6*tE(^Wtu9wlQCU#=`B}uK6wYmVce~c_
z`^A-+nfd7br0{hyoZQ^pYvT9MGcQ+++g+yn=Iz_UudhNmSeSC|><|QH=mU++g+D)~
zezeHX&yR?RNH{%BcTZ%4oPa>XtXWbqyUTcw9XmF|s#I&5emq}oZS9if%e$=;Yiev_
zVq-T}ea*U;v*~j<BO_x$L4iX~j!sus*DGBIc82Ka=(u~fq6|q%NekAj=~=QwWyOjW
zSFFv--^F}+eVyMt@6Lf;rLRE^h=|C@#J9J$?ulraH)RTotgP&enKKVwyeRng_V)Y>
zy{t@(`u6@BT3U-DH>bV0vQpTsSL$eG-m`OaPirj9iQQG=d8e3#iLp=4wrjC_zn2W?
zV5FRTdm^WOd~$4C?rnprFBv)a_sP1ty7Kl#M@2n4HC3Bu(#DUU&)a+3)_r{B`s4R+
zWnEofH#fHrA3shEH2S8btSl%gsadxt{rtSD*)~@+H8mYWLPV;*ztcTk;bU9>PexeX
z&*k>E+>P1S^(?Hc%p`=RrMp)KFHgF&qi{$4f4h8hg-x3`JEx|qhOLQc6x9w}Q2F_p
z(EZhMd#jFWC@QuHe9BzR`l1C~yqwTvWo5l`?V4F;PHwL5d$mQ+o;@?Gymb9~e0{HR
z`nf-+JD(iiS^ON7)K+$%XFPEAs;K>+56otHcQil+kfo*M>uYNt$JE5R`}^~6PCtL_
z(o*l#DLreyd@0GfxoPReyG>WGTrsHpl%f-{!NKk14eRP}I%4{9I;9^i8F=JuB)Y|P
z4?R0OyK*zbTr=;7WnW$d>O^hfFit!3KxXlpH9eBXX%AjrUVdY5wRyhSg4HWl9Jq2t
zWU+gHUP(?)j*h+=<Int3?w(ig+^$R5l{$DzTNY%#`uRKN#_ijekMYSI>y>uDF4De>
zb%F1}<-3<LZHeqM0o^_``M8+4`2TLtC#Nqj_rJK<y`QaqzCj{WPfyQ-cklSBtE*ky
z-Hkoe<=@@e*_?WM+STf}hQ`LuUS3=_HZ~6)K2+RSt#Mz*s)R#W-A|-GZqt@6M;16X
z3kV1>)YsQPdHVF>iHXYftGR3Sl9G}P%HPFUSXweNn3$MsD0=E;VPOI4#BJEV{rJ&t
z@x+{*GZrh~sH&(Wyt}jW>$@}NnU_=|qN5L=J<D5GR%TKE&t|>a(`%L$9~6%D%g5(G
ze12h}^TX%Q+pn$;fBf|Hbc>P~0<%oBj~S>+Z%O3ZKG(WD>BonMH@4@`|B)ZO%;(^m
z$juu{UIy9J|C=+N+ntMx>y>ZZ`sj{(D}$G_CHwmL94X)RZ1S2lYpU-5zj^BxQ^S$_
z>1_ORJq-;EGgFh_o|>vX!!Vg`&Dyn$4BBC98hU$qr|Con<xdugj*j-3Wx^R47`SH9
zshF%REiv6Fm3PNL<;AbBuMG<y9jTh@9~~_n7Z(R=)2v=$RQ~;4tWNyCm_L@c@7|T|
z7T3@F5W8v9CZl7$(#Ka{e>P)=1gO<j`}-T~hr-G1($dm8aeH>esf%#6&afy{T5n&U
zmXZRh(?0(YkFPm+`nwK;MZp7xn%Y`v9Xocre{42+cP##Vx$GaYJ#X%hkFTz-mQ<O#
zH~03o&i~eGYHp7t_USqN|M&a-(f?<+Rx-~QTc97aLm+s$U#o{o)5M8_P0h^@-@S{=
z?{QFY=oZsmuyW-|4b|$MJ9kEG$q;;A=<DknS6hEZ)yhih-@ktzetvBW7b=#$xxuKf
zuOC;NUikZ4ZcA$`<By8BM~)qP^!<MQdh=!PX1%(*+k9Kz-BSvx($?kgTuMt#^<sCm
z@X1<v$UJ`Xq{Vx>-oZ0xcor^P$ZK}*VfVkkzdyg)Zso+G=yENC(F)WF;!rHgI?%v)
zV@IJf8;=A7H#hgW!j~^!J}Rt9N=az}4IWHZ_lM+!o}QkR30`&~VPR%J+jV?>eQSPv
zco^@e5+4#8`tjG-*J{1GdU|;!j^Ca;d3$r;ym`}CYWCErM^|^Qm^yXp*LN?Jd#6nk
z)6&-d|J3DEvzhn9u&}UePrl0~Cnv|<wFRA2Sn>Ux>@=OoOD}Hhk`MXm5+5&bTm9|G
z&CTi3vb(FkX03_X=)|`2iTm+B*`wSOmh7zkZI*X$k7l#Wr-iQFVjDJWIIySkvy^Q0
zt1FswEDAwNomYpgy|6jm9~5c5eRnsf_g75fmJbOHT?p!)6%=HY<U~bD<=x+>+Z^(#
z(ad`e>w&$nwEz#NO`Y0W_V(7nGiTOZ+z9f`zc*i3{(jW0|KZI|<IdwUva*8G(%p^B
z?1#>s<9mFpcXFZC&kqj|vv<y4Z)##v@b6D$kG#EH@G>9Ax;ncrU%yJKq^PT_yFXIP
zudAyAmGNr+^LWC;ud97MeE#g|>H4boj^4g`Q?jtIu%NWm_5Qxv!iR@g*<Rkz($bn#
z;l4QU?k+_`L&0_H))f>L9XdH#U2;jXwzakN=jZ41KYVX!U;s5^gO~dqUEtVU@asz^
z+shk^c!PJ?R()A<P_60IsZ$*M{O-@s&HXt4{~z|BKY!lXUvIy-B_|_0d+~-10e>Pq
zJvrxEl{U4txixQ8RaF)Gf6ly=yKC!~EmAU<uUv5n4V}71+3@qDquo{Ape`9dgOIuL
z)(smToL#o=!14R@{{1#*kByCGnDC>v==Zm`m7jNVG2Gi*&0bns`tk9u`-@b*&fAuI
z`_b9i=0>NF-Rc(Czpydc{o~_Z*{iC*zvDd?6&00qexB{7F17Mm=J|b}J{6sNeDmhb
z3l}d=OjP>$@!Q+zmEG?@fBp<&eN5KX)z#3_I;A94?E81`<bFBZsv}lSF&8gf5cqy?
z*KXcm{yYzNcXs{weNSxao}ZJwSIhq6zFy1@P|>+$$r8{|h@zt644X=$DN}xI-;)0G
z)6<B3HI@zipZ)n{EE+Z@A2;$-m0uULlZl_7|J>2%rB-EcIvyTwfBfm`={>Oxbzfct
zUK0e5B}n~`(t_lo`5nHq%@)S*uX}NIwRlcWPC{yG>$cq6POh%3Q>RX?`1wgS@7|uy
zB}-H!BqcvSTeq_G+4=eW`T6-*u3Sm@_U7h`ySvNxcAj~EfB*5bv&}cw{w|ZTF5@|P
z@F36SQ(^b_)ox5ZEml!cvA}n>*__95`)WGZMsGiK?wnuS%NxI+&CcIY_qPhvs(Eo?
z;he{yhAFSK*@4TKgWF!-khCt-G0VNxQug*%;;AW`Lhn0%zPoGv=GIp3+2;Ar&hkBD
zNJvg@UK_nV=}3p*h0B*8%Y1)zRhxyKz59L9VfHPNT;|^1-YxCz$$x%)3<wT>Ec5-{
zUF(+C)`jWk=Nb7NpSE?YY2DAK;!~ziU+mf~7IeJJMd{w%lfPE4-{(|QQ#1M4r_5k>
z1_N{R_DPe3oSdAbWThn}PON5q5f&D9;`Hh4OG!76_sf6IV%)WLtErq_O~?9uzgAt`
zI9)$}nxoRs#JoJd)YPYHy1V#!c%EEkD!HZ8I(y|x%`IEE&MqlGbl`x)kDotJDu`Cs
z{`zw8<>lp;=4~%;ZdP9xyPHj1TzpOBX18N6pEy51H+SNU88;FN<rz$}ukpC|$uv%z
zCRS5ZGi%GigU?-}qor9{S%vy*zuzstaPeZ}^5yEkzP@gMzwfu-v6nY4UBCW(&Wn3{
ztIK2d*U9SX=@k?d99R*!IAu<sZgO&RN=k}{&9!a0(MOIS2i2&~Z9E4b9BfXV)2FMe
zyS9ou?f>l-PT>WM7dHnkb~||S;>7anBDpgT`NqcXy_dB5|Fg%BnQd)t&&;tDULU{z
z*oTLQQ|I)_8XFrgS+=Z8etXu{uFs{Gwzjd4=3cZfXJccl`1GXn$HulcwnK*wspxGw
zclPYmUw=P6UlzJL?CZO%l}nbexVpM_&K3#{3Gw*L_qF))uF~v1RbRdSL_|hP{{8)3
zT;Jt?{?DI3_uLZr(XGGlz~|@ZkM@U#h8m`x66xf=61S(~;*+z@_UyXR+gv<7JAV}3
zU6hcT`jjnMTT82A^TBN@etv$Ss{csuzE7V%35bccDLS_qcpRHId9pBQY}ne`nn%WB
z!@Z3wR%qnh+auZ6*Y{}u(&ft!-?$NROtW*(!{p=HTEfDU+3HuXS>xj3!lI?E{qWT*
ztwLc@JJ6VS*}FTPFE1}Q-!Z#9C`jng;lmH#zCEiUYhB8He)8nWi8(ns`yN}$i_h~8
z3Jg@-c>BZE!|nWrMNdws^={p^?b+4*P*96=qHfk|5Utp9LX(-9dCAhHiWU|Uf`Wn^
zoSZAm(_7Nc&RSUg{T&AfN5l5*=26>nP8zIzb9SDsw5X^k2M341`y|k6gO5yqcUhm@
zmT{5E{{J82wDa@M8m;rmy|snYX`w)T-A~nhKc7i|d3QJZ(KFWc^YdCaZ8CcQu4PN&
zVYZZ%lmmC~%D%m|b#g^r-rZfT;`(t1PMzYCHp@wnjZ_O;AJ=>5PRyD4_VV50`fk_P
z#Y)ea&dx9Q;BY%XXdWVLecV~AO=nnGSwa1S*j*)!?d|N(O-o;0(bUk=`jizYpF8c)
zTTu78yPMm`$H$=Xk;}Q~XB(N>C(NIJeziPv`nfrr#l^)nKRztH$ok^my?Z~t-Of*)
z;$z3r>J+oLO7#3Z+vbG}7hc)8Y}v98A3jV7H2St??b?m$=jA|JJSX%2*izZJb*m|;
zmpN(DBsX={&$-F$+1c4KdnyEf{`}eN_vJchWH!YhJ3IT$?d|>RG&wUii{xFqb`3OG
zmX(!NQOv$(8EEVdG%m7ZhlPcOg@?@LrQYHyDk`AXefj%)QwyEGvGK`t=tge?^~Ek+
zxsp>5qadK5qQX*DRTZ%{OLV>2t&Ll@xTK`0Ow)_i`uGFXgL`>N6*SssXJ=>RcYNC3
zy|#XHEE?z6{qlTNn4Fvp%Am~bd@d0Y66@!g_x1IGoO5k`y#B|p5y8R2)Ai$zotUUx
z`09#g+}zo_vb(aCXC7>3SGKZ}I^4$lc+We#@GXg4=ElaxAdhm3>rJVsIW<M|!lg@x
z%J0{<x3sWGE>BKB)+4#2__^QW$6Q=o1rHCgo|$Rv&bIPN_tveYdwW@?PMr$QO3C%V
z-<n56N1xV`Dppfd`)cNW@!GX#dzk;+-CbU}^}xkTmxMqab^B`<E<E^CXQ8U<`smTN
z^P%tW?VUJfib~y`MXucEdOtsU^e7=OPj7X`nVB<YT=}iDa`EEBmB*h|e}DJ!)vRBu
z4;*l~apT4U|M_;Hux4RmT(o#`;nP#1Z|>|AR+`wcnZNekw%prn?(XiOUeK{)#~!sF
zjf{+}`1FL6hnM%L^zZ%k|K)DpygBE6c8fs5wKb6*US2}^w?aZgS*@+Dmn>W6q$1=P
z9WA|a<HkKz`&Vtwx~dhkuLd-RS5R2k=%8@m+uPfMA|fp>USyQKyu`Y1-@Y};r+h*}
zME?B!Tln}GuY|O;vWbbvWHsMKt<UQNqocbI9dg=|cQ@+K_CJ4WKvmGxsZ&3E_~6hl
zXDgvLW$mO%LN8vtFv(oAZJU{ww>PMrxPHL`hRn=N4PD)-H>UpF)~N~VS=PHMJi5F_
z0z7i%WS0n<Ak)zixzFkl9zI>Inps0z`*16__=IWG+NSHrcb)gYy)8E}Gqbainf+5<
zp&bKg5PWsm+CwXYmj{G|TzRl#+cq;$r|b1=Ze?X<HqM)?)~-Ezak0CgpkU*bD<OMo
zehN*UIyE3LP|&{I#@5!b>PyDG*mO=#PS9|j<$6tjfB!FUZ%;4vnOXhm2`9+!zrMVz
zDxa}p@yeB*4-dB||NQjy#f62;%`I>CRDO2b6Y1sV)^_A<kd3Wv<<7`cYooV6c>K8e
z#*K(8SFT){{Xt)-bHRcI4C(3Vpl0iaO`DQtOqt;CTvTLqZmxBE<>zNtXIChkoUHEu
z;m611FYoWiyS=<o_3;twyZih5L1QAXUcKt=dw%)Q#qIg`A6;D?ZeV1TRWO}*pSO<>
zs4e~R@Av!WyDaS0)!F&w?OIl^UfpwP<JSiVnL)WnPEPK^rAw2nwm~YAJv)U1N=i&X
zbERKjUtjDy+brn#vgOMkKRY|yBruZ6ZZF^UlV{H!-I#p*!Lw)AUM#uY%+9Z5Yb*Qu
z`ugdCR@=(n-|Gd9+-qujzFM?pclrB6SFeid$M19T_3h;m-c<baQ>sqf9*Kho4{q4L
z{khEdZ*QY}B#qf#zI-{Sy!_vtB}<khoSkJFu_=W!Cnv|^_|+>{68`=9>EZ9ce!Ih`
zVlg?nzRb(Z6jfDSU!}jb|M!D=-MV!ZUtfvluUi>k|5x<#GT*~9jngg6eHa@+>A>9Q
z;pv?>x8+KU=|nX2^zf9ty*0HsCMQSd&fUA9X63y((n_(Bk&>rQok~bZP$-Q_OjIm;
zcZV}QJ^jY5Tc<Q+qZck*xTE&BS=pN#ils4`nVLMjyr9f}FDIeu>#NX|w6vsOUtR_s
z7ZnkC@Ou6JV^>xNR~ENl=;`5k^6Z&eRr#x?CMKVmMy$!l`;N{qOir27w|2q=fjj$Z
zXBRux&E2%gNJ2{L(CO2lcG<K*tDnW+-^GF|3DBUa8DB|B$r1hif0%-UL5;eq-`{k%
z<=+R*LfBM(VmWa9?B1BzSi|gVIvE)m27V{}LPA8EnwkoJf6JXRZJO7el1b}jKfJrU
z`^L81*+1_5DGi+Opx}^}rnb1`P06b(ocHT~udVp}kC~k>;n9&!P)DI(&ekC9jKqxD
zvz3*UnhJwJ`Eg^`Rjoh2UaznC^+l6mLG11_3DYc*ur(2ig_BR6pW4*K#KOd=qpNF}
zc&J6~Z`{%4(rd3sn&-*L*;F*lHqU4J@nc?UVq)W+J24Cmt5#|0#qH7fT7BqzXHyds
zD1mKEK5l09?ZQIm83u_=`S+LG)%<7xje~x8c=+qR#V$&Ldn>JKZ0%bFoKF1Lk81D(
z4O=^LD9+!x+<(4VgvXiVuFqTk#0zw~oH%(hv%q(2{(U(vF0M6?4c%ui^#}_JYO*eW
zXHs!*#_ZYVyH@mq$E5^5RjyvU_ULT$e9#Q4sHo`5<kP241q1{fnC+|2@l!o3D=Q!<
zs7XvW${{o~^wo_?lZ5tEeeDV_pZ3@K$CkuXyUX8$rVU=ae(f9{9{%daoH;Tn>FJ--
z4jViD%e{K_s)nv^>#ki@i(@+kF6~&gN^4KuUn$+_Z7s8ANxil>BPuTb_~YZ_E7q=c
zJ>DlPefP$c58*B@EN;D0t?%yccGeJ4Qc+<^KHk^rp>k-Zar%X&-r}HH$fI4NYZjl1
z0S!&Y#4K32kWpJ(J7z}#<KJIjon2j7^X}|u%)7hm;H67K?0hl_vZ2qSwq!J}jo#j6
z{y@esiDjNmrBa;D?!?1vEUc^#k9LdeB%f+swMq*#ZMW_H-@7|im>L_VbEo$9^nm6@
ze*FB&$WZp?Mx$l%GX*s@wr9_tfy(}M>+}{aUM#6Tm6w&3)n|@{VC}CjnI$=1UR-=K
z76(p0=Vj1|+{7Yno_FNa)6*BX=g05ZwJYiRy4VYsFCU(!8yyf5(h|G7Y+?BNxHXG~
zK(VL-i_sJ6pzfK|!hk>PtG~ZnqkM9zb35O{`2BUg_Y#{X?63O&uXeF;;7<*0?QXTr
z!cHlNPMqN2<Kx?~ef#o0<%0{I+aEl5zyMmI5O_kp<rlB{D~lF^$OUzmEnZnXnZKa#
zaIY1gqKnvy$0mJNd_UD!JT6$==gcutRa;vd)HS%iF4noQ(D2KbF9kn8rCL~9E1R2(
zo0*wKY|oQb^O<qLYSkG_D=W}c<jIpKSFBpKsyuI9{Qf>g=e7qgE-o%8ElrgTeO6Lh
z`tbGZZdPuw1<RJP?b@|#hHbSO6Eia-!|t-Thwkhw4h#%DXrUSX^yyO#9UYh1X1Nu+
z8ElP>Kj;6?|FI)--mF<t+w$-8>Fet=G|ZkYeQ#fF_l_MF3<s{QjRp-xKY9LqbC0I+
zmO{tNphW)n_jmV-3X86;t_!<Lvp-f(^-yuzU-$RIVt0NPcJ|GEUL1-oHIt@9uq!~C
z#3tviUKPE*F81(5Wp@Pujs;7Xf+~9p3kwGgkwxY2@9o(s+^O>Tcz?TtLc_v^iF;dr
zEnBv1&0<4!5w45t<Lz(UzJ2)IIX)>VsWr+cMSXpJBO)U^=Np%mm1SIACHgwzOzF!@
zthu+htu42WjELCKrz$>Y&YUCHr>tG88?`0lpw*;13(f}Z=#{sR`?Kfet*zRxEsB<|
zdn{vDGsCKn<x1g>z~c|y{<cY%%H&-s+;P!KI`2xM%3^Tz-2q1yC<4u2SwJ|-lBIKw
zfpo~WLv;impP2Xh+S-nuo+o>(UoCKKHpsbQaAuaN_py^toPB(F4jn!`aqisSM~{;J
ze3eUMYJ4ECJLS)nySvNzv#+gbT(n4O$`m`lwd+@{V){@Rc>B%G%^S<!M#bql?63T+
z7Pc;i)7RHmL|mM?p`vl|+_|!8XJ#<Q$H&L%Ic(pu<;c3&-Jscj<MeY2)~w-iZsQS@
zKY#ArG0<3|fnxN=jT=9F{CM!}Y;#4S&VrYhR4uHn7jM`gFmK*GPz}e%D|N(bna_tp
z!=LsGSFY5Ii;0Vj?A)=#LML`tNKK5ZE9=vzPuDy;dFSu%?~(35Ql310dhpmWwgbm|
zc^Dqt-CfRLS2jCvv0LKTS63mkdOzD=@IlAlYn-^axCG?o`+xkXh}m7no0*xpV(r@2
zS+k^aa&rq`UQ)d#IP=80b8ay)GV5Y@xBd80VN>;mgQ=0h%F5~yXNl87fv~W!HH%N(
z0S(wMS)wv!`gG^OK*49vo(XWZKJrYgs;XL}Y$Pfn(UE<9ouZ;5WB$E8jZIBVyUO3|
z+1WcS6aX#omJNQ!Cu^m$Z{DlA3m2|jX_-5B?vFiRUS4+p^VoX6g{7sUsw%6fs3@qw
zUAlDXk6D|xZ*TAG<9pq4#%Hz}FDPTCrK$Nk{q5F^-KC(dz4~DF<mP7Ps&8+8ZZBW=
zPbTpA#2za?aLTw}uo#@r!JNk)?(pP<o>Kat8bE~rG+kZ#`r;z<xpU`kY{{H_<S}UC
zV5)Zbgjut+9;duvWo1qL_~__`t5;p;+tn^ux>U9BP9rmW%A6kC*x1-LQCq$C7&gwD
zCFSJg1X>ryaNyirYfx*eTYU3J&(&dTH{{*50u4YbP2|wh(gMxU9qW_jX5irFKHS90
zU9nYTi(gWb5@?N?dHy{I6`{l%8xk#Qe{K0uu|4lDC_l?s7PTaLnI$D985BHlD0zL2
zS5Hsx#*V_pKk|++Jb3hoiI<nx#l^+I&+AF&?%mcw!NH)lGA^#J52wf1Ic8<8st{fz
zU-yG?x&QoQkB|3Ds;hoFcH#sFsE7FRxI81nty{M~eEoX#P%AehL-zG`t_cYWr%s)U
zIHuAf;A9sGNmhz26a257o~|z_DcQ*@ZT8^d;dTKImPfH|KlSYG<82sU{rUO%(aEH%
zSFf&FY#10E+<bd`ez!WPwC8PYZ57~Pd2wf_v5bt2fSA}ZE4ARQTeo_6d#^6<dsTMz
z?TwAfprJeqMeFtP`^Dx@|M8<@$+BgOcI}b^^(lXU(|ujx6A~W&_*k#>qt8Wuf0c@e
zi#sa_EXcmT4m2<4;lc5G#+eH$At&SZR<-WfVezqYXYq4B7bU@{Eg6i_(a{zb77y(I
z|Kxu?qo@%a^<M*zPwe~ETXLmPYEhrEY^lu26^~7Lze>Mc@%W0nth?1Ki%WsWGdryM
zN<gJh-({04g-aIq1<RMpyj=0v!(Dc{;wy_gSFT<Kb%I`AUhZupCnnbB+Aa36h;dS5
zBcqRxkASEsYierhwZbP|bLYxdeSM|6&v@0^wYs1|&KEB-Lc+rjU%e{2K5p-!W_ErF
z^{IRB?X6y1|NkGT!eKaY=Z?&>Wy>t;{#Y;^IDD9S<;s;OPM%DZoIF!pKTg5UPHt_~
z)~4=mZWbm+h6OuzNGx2q@WuW8_WI@uuWoPGcTo}q)lJve$2<G`ufNCiC3JO|qK%Er
z&Ye4RnooJ$U36pr;&-ziPX-M=fSRkHpPy%BD1LTEaKGO5Yu6SzxATFPG#)y9IP#cE
z(TU5Kg|A+{`pDPeSg&-ucKA943k!*@Ter@zF4sGA<_xH|Jm$#>N*uzv4(i~V=85pf
z7Z;U3x=j7?qvFYvC!iGyW@cuOVn4{r$V41Zd3SYn_@iPGaq)Ig)4i*!>&4yO=0ZY3
z5yvNUhlYk)RD4jlwl3Ct@}Yl=@-`j2x;lJg`TIC4`~Q#6+y57d4;I&tbMf=z3keOa
z+<ADn%GIk^L31^+!9o{QLh@2mQ#(337Ch%&@z_KZTt!Um0k;J%!HR%6{VVR9$U>#S
zX#rX4F^1I7_*=JbMQli5{PX9JiX1-&heJSsfR~q7%AB6P&(6+HzP!vAG>!FIqbU7w
z8}E%>rP^|~RV<>SqI0av`R><z=Dl*|ih=+~KwMnk-QDHg?>o+^pPsIN{NCQ`iIXQY
ztE#HLxw)A=c$rUQXD25EXnDix@b$+wrJj~hSN*gEH0iy+&i2`vnazt9DQ(HSyXzj)
zm)PB9iSO?0T(M$B!kiE@5fPDDChPK;nHl!f%Gdw@XM5@L<%_FAwLiY*`S7v05;C>h
zdv30^v5$te(nJnNM@IuAqeCYqDl^vD@H4aVWEfn#aYI7gZ_b2Lmz|)AjpXBfiKnOO
z1_TB==H=<lnLGFB>=+42Nkt<gp}V`w)1{{fIC1=RxyV!k?S?bv-rnX~S7%pJQj(CL
z&%ZE$V_`r?+}<kFpWd&|-@LcC`lxWFoPAx-v$M0W&;F2-oXl)$YI@CZ=E@Z-9Fme2
z{g6>rSATqWcljf0FOF6xpBV;?r9Nt>PM@AQVS<94xu&LO#s7b{yUN~jRaaMk{Ap-p
zlq4IvOwOhvAYbX><>meh7cOkvSNpq5UGUq>%kA5(ABTs9DOp-Z*3=0J3xm3MTk`M6
z{h2e<rqby344(@sAul&=-u!y*{Nw%d-S0KjM7S)~oomm5b2TX6PYT@s&<$Jy+yRR%
zw|iyYyBJnR6hK&cu;KvJ2$|St)t3Tpz)S?yE9U0rHWeQjUcP*J;lhO#<!iQV5t%k^
znt`F=!B%c@3DuP2Cr@(jt^R(jjaNFt{in*2<HsLAIXO8XB;?40gUt`0JUL<|Bs_KM
zR1Hl{$Jf`^9^IS&{@&h>j*f;!i<H`UB%4+SFE{c#8CFzeq@=9;@ySVH26^!&J~<nS
z_}Z_ck5k@cWM(FUrZsjHEIh*cqOPuvgO}GeE>7<8l1+h;kvCt=;1<^dtw_tv%mghI
z^YiQDnIu^G?e+ToNnc)E^ziX%*}Bz~p<}&zaB%RJoSQ-ij<>!7t!4mq^<Ta`X|yS3
z<+^pp)<$n%uwn&Aad9ztd9VwpsksS0u{fWBm6cUPL*u~7lPmAJh=zuSUc30Dsi}!c
zL{!u;=?Dj?b6flCOXH+TLa!r=K&_dTD_4RVCNpP7?(J*_wJIJPE?={TXQBs-x3~Al
z7R!YJ9I>&n*DlUjwR;(8arXZDdX82n&@xFiAtumt_uA;~0imI+!NHfSu7~U{dmC{)
zxl3(fk+g9d&!fkWCr+Q<9=0~B^L#(3<?!{@(bwN~z(xE+H`#XSub{Rjxcv!kO`cqF
zAJj*HG$K%26mGK13&AlB)(38?F7fvBbK76{7qo_zm0PUieaXy;6C2OYHh+AyTfC#U
zw{`7W-N#Edm4AO13tFftZI%O?Lx?!8_+)Z;Y;13*u==AH7Z(e3x;#4DrlqB&Aix3Y
ze!scDU%soWt7r15dm9oDe|U71`_7)q%?FvjJbIK=^8TKzpPwIScK-E>Gp_FLhwtB)
zKY8+`fr&{=e?PyP|Gb{Gv$Hn#9XqnS{JnsbRM(9g5l@~!SGKT_2n!3-(9;90=rYK-
zpiuJSLSw1V%nu(vICy$;u8Y~J^l$bOUfG8J*=M$7UFBNtH#bReDyY9a-xASDQ?R$+
ze~<6|%a<<$f`XjZ$L&2LEcoWln*~dk9<|aEj*E-iQTA49)22-e7A{oW$K2W6%)Dmp
z+RDAnsdtwc@bmNY$XbawEfjcrdwaU9cV0$D254R1T<dbNcyB&Fz85z(D!<O~nK^5g
zlCiOHR#w)AjT;5$i%UyOo8;e{Q);v9)w-2}%5I=RcBh2`Y;0_6l25YEYB{y`-JOc6
zD$v6A4O_Q9eH$D3uM1ptgCiBS73gjR&d<<RAEY+{<xC1Zo+$&4RIol!VwiI*c2^0f
zaoQP&ygWS?CdP*Ta`v|u7BV|IIX!sv=#Yh?G-yF|Vxr<a`+7cKUtb9+DYFO(Z2=C@
z8Y?%>o7MmRSU!66Xu|yY{UCQAIKZ%V>sAd-&BkTR)bz!LuCH9R$|)*J>eJ`XiOI>#
zva+(*CeDc7S)|Iu#01(X;My$)S}Dcw;mgb5oI5)N4<0-iu`!7?Y)!;Li<NIcvn%J$
z@qwnwXBZ|M<lnRT@%y)PXsBrP_B_|jOwFL6poFBPLsnYG^|2NEa&8(`R91d0duYk<
z<mppT$NI#nQ%=9Xy`4CDax-YTz|EVIN)tI^ca<F6ka$=?MC6FoDjx|6i37K9OM6e(
z6aC+t&G>7UX*Ou9#Dnwp|5F4*^)5VPZ4q!fvA<nxfiSo>_{3TD`5CW}kPxWT(b2(S
zQ}aWBi;HW;s#Qs{y({<Zu{m<|=)+rEvpf3xkIUEpVN_LBjfjkN)DTHJJIi#9@~Idv
zudWKG8(Xul2gJnml)b%mb$55u%$bs}XPmim?V6IQ>DGIeS{fP-v(0jkJU@Q#p4_x)
z(?EkFiHQq;M0NG|yJux-u`n@KeS4#6r~mHVyEVzDV(w<=*VNd6T123cHc82=yO-@M
zdwa@CP1uBU>g|t@j~{)ms;ta>c9yB|e)FqyryFg!2ww{@O*eW|pQiYV#~yBwHs6Z-
z9`3U4MzDV9Ws@uUJHRbPP!Hr1QeWh;2`@M)NiFI-+zU>ODvSFro0MJ;4+|4xSP;D2
z@5R;C(<>aU<Zs@-ZT|9qeND|Co=YdhCwjEFc8h^m#;#k}=Aa;;U!|j~+q!U}A`=tS
zhJ=Gm*8*qW*jH=)=g*&jm>3?0N5#Pr5gf+G#%p4CiwUdyrOXNX2AZ|rSNj{ZokXa=
zU)r3HlauqrxpUJBjebs;G^xq5_?gL#D~B#!5?Z)$;f76{lBV>mh1Lq1nwkbiMnd{F
z;Xy%3vb{S$K0f~V&(F^tot=%1jf`Kue0in2C2miJ;i5&0CQO`o&|+oIiWMsqOiZ@i
zd;R+N_xGU5>K<8Zv9`9hNBiI3+|0f??d+l7-`_{Nr1qKVgT^8L#UgqWK7M|Dj~+i3
z6c=xY_B<IDtX<oC=#bN~mrvXs9U1F>zcpVIzh7?V%$WilET9F$vfVqYzrX8LR{^D?
zpP!#!xO8dJ^K<nl&zy1b@!@G|ZvOb;p)&^yQ%HFD=Dwpbm6evDd7`b^*B?DR+|F>|
zcea;`(8GTFe=E!*&Gq&9ckS8*8aIAjaps~*$Vo3RuY$k7N<S_Eof5oo*Dk5Fv@{Q2
z-&EOt%~uw_&fsXj1a2OHn*Wf<?n}9nKMT?TSOV^R`Z<H!2Fj9<J_V#};o%N0OxjjF
z7Wh=3e0NtVXh2|+s`rKc_4PG>zh3_;X6rZ0gflWSa!<^h{rUIpKs!q=Ul!KW)0<&e
zTeY{?xaf%oXeFqX)vUsxo56vB2cMmtZJ2#cr}Mb8lhcR4-|v4ebIh1~=S~c$1HX0a
zR?spNtMYeetb~LE0|OtmK0kKs*p?45OtG=CXJ(u8*VWYtz5lW|`8XeFxNhmvr9G2R
zwQbvG_UF%^SzCUde0Fv=Xc6!|jh6h3&rD7nicjvl_JXT|mI?j``edz-2v^4KsbHMw
z!Q$-f%+cxuS{&`PP~h&a(q!4mE0_Dvzc%~Bl$kR*89-x0Z9I}p3j<DAC{}~oH99&j
zj*g6<K7S63iQ$>((K2b0(6x&*s{jA96%rOcdVb-PCn=y|21iFm+o~@Kvi&pHtkL;s
zDk?7CK4*?hhYP3`EcNZ%w>6IqLG>qSs^jcza}8~6=gLY;7bQX8NzC6>LVSIFkDa`c
zeRY-SnX_jDV`6$1Em8vQ1K7E9=Z@m%e6KTn0zhRwxcSzD)<O91`gd6-c$^TqSqIMX
zfAql#0n`Xk0mn9|f4JlB?sEQ{H*Y?=K6C#pgG8q05SO^t*4D&BEu24IE}svXX=-g{
zU9@PCgi3P$;Wl0gs}hYqdHcRai<Erk+wHwqsI9G?b9dL&K&x$EzJ4wI`>XUE>x=8_
z<K1_cy-k_ZwYU8Jy~Gz67D|}s$?Vy)=fb|)>Mi;A=auR#%gM<pczld^Oa6V(hJ_g>
znL;9>qLIfZS--!x*Lk*Cu0{X#uQK}#Oif*Ve0(O0Er{P)#JX(RG9wSw`HL1UGN}Jo
z6A=~VRU`lY%1YsRw$;ZJBtf%ml?!0&H*1)loteoT931@diO9kL4$$c8#wTqXHyVQ0
z=Xba$Nk~XIXow`eyR%b(tJT2RI9axTCAYX<hkELrJ(a@pb~O&0)6OQOrn2Ve=X10=
z-MD#kW8cX$mzH{i^8D@X`Hv5`^9O{6f<{$9jsZ34-rg1m4KXI4x--Kt`AE5kK&K06
z3hm9?w;M}d2641H&6qJ`L*I!rPft%jdOgI;i|gM0dVW_|*DtTGa$jEN+Z>?r<ZX-k
ztd>)64>q$uDi)TP?@vEJ&rwBaVeIZQ0j|~`58LG{tbb0i0!JOFS4c_wK<4G9O`8nz
z?pQ2YvZO#SNSK2Kw9a?J1O|o|x3}l-J>I)g`n>x2dA5^({on1{EvBKZJsGsB>BU9m
zit6fOx$D=iP1|v!pC8n<K5)R{#j973e!t(}zHy@=!-JEP)o<*nH13nJY<hZny0M>T
z_1W3x$Ja)02el8c1wL`}^5Oz_{_X7SKx=!g;uHiPTwNW$sY5M%SJ~UH*VosZ-*~a;
zT>k#Q$5x-630i#a+AXH2rN!0E#`{R7{NW*1&_)+&vz!TuRzIC)i-THv|MeO>?t!}V
z0!|zgtJlZx2NephC5p0-^+-PA^e?r4F`-{XL}UT9&vky{)~%)?At4d&leur*y7l#(
z?|i%33u_{cuWg+1`r_jDA9FZbo#Nh|I_v7_$fz5&rJ=XC_s5?bH*Pri`u3KZJQEQW
zP0Y%QdcV_oa)5nMKmY^7j2SaJ&iC%!Yim{V;(&!@HMlT^w9m}Z8f*K}8*AW^V{jGh
z_jm=;&>pBGXP$6?K}A(H@$4*90j^fiRHsEB|N5(-;ZY8j6)RRWY}&NxhoSgH50*v;
z(86%ZWmEXw+}uD}iiwFSAS9&a+S+K)GO&WOGByU#U|#t8IM=i^wZ}^~U0>!a4JuSm
zPt%=Tkte1X(=l1yU&-8jdTs#Qs@1Cv^X^#4*w@K0H8Pw!b&8>ZU*66^MJVyhi;JLv
ziz!onl<#-o=jUIsYSp6;4-c<de4^Db`ItxT->FYdOjQ0KB=vJ^_4hoGjnd|ME$!{>
zJ-xkx!otmZvAaP1xZUONk6m2sZdmlh<62<qqD`BGu3fuU@!<g@XhY@ueZTqA($X@n
zt&v={YSn~^6C0h|`9N(814Bc{q9UV^(9p=^X^X<w#~GNLAKzE|TV-FkrIpp9Wy{z;
ze*D-o89YOyhG_gRTd;uP=g*&@3^~g@|C|-y#Nw4JSH8HoxV_?%%*yre+)JEhy*kz_
z{o?9saZpL*KG7P~##$M?JRv{7|JvH<&3#JOS3I7uzZo?0Vh)>^F@I&zySUEzpB}i7
zolxHdk_C<QgZg1VcZ1{7`5)&ii%Tn4u1vhSDRs}D*B|1K9y!9m@ay|~euf=2KZ_>E
z6~8+6`D7C-cfpSji7Kk9j={mgYooWj`S|e6nKP&0<0Dtl0uuXwKa|1iY*wA|on^ua
zio~cWsa302zt(-VyZ*o3nzd^U3m>`U+}_q(8j=<i6eJ)i*}2?*KGTmK2U};)mR_@V
zt)zPL^OKX+C2T4TWMpLxi=X+Fytv@_$W8MK|H*jW_<b^<35BL6rd6v~FI=;xXVoe#
zhKBj`<-v{ig*khxzH%iW>p6IJb@<Wu552s+R;*jc_Tl5_mH>?-7Z<yO_E}5|oVn;M
zH)xq*y*Oe_t?=C)OP$zVBH!QNXJ?4nRl<4h+&K*$9nglXhtHq4CmwDy^gDTNXYq3Z
zY3c4ie`<dG_yOA52--CQ+Jv&ZJpaXu7aRIcfEq<tu3UNHK4<?5<lcw#`KkXw{p24%
zDxN%le)#TP*<ZhYtysCzv9i+g%GIkcD_i=l`LwmQFSBgizrb_FllKeyKyz!oi~BAM
zfP2tV?%)>El9em&oA81M*fKl75eXVTkt~(D6mq3-R+|+lZ<@G(+e60!kFPv`;etT7
zxc;#{m7gQr73WX5bScQf!a_k^o!x1nfVf`F0npUL_Wb)whK7Q+)!$rVVr2AxfBO9V
zd}3}cudAyo=(223dsxkHPRFfVQJ{=gRaLd4@G)EN1D98U0RasT3KMqS>;tu=7yZ3+
zcW<@$-QDH+pMJD*iz{hpyomQvxi4p1)dE^L&@XTAmYb_<Rr-p>-`^j!OrX>xEh#w}
z6!f4moz&FS3l}apTwfP!m~ukkW9+`4uvV?@m$%Z;<)96ppPvVX-m6!yKx69l@0FLX
zUd?T5Yy0Nj-r0#x+wSeF1#QUWkv0RZ^0cV=VeskGCkBR9t5$*5qHoK&dB{T5dgaQM
z5=JQ;SFT=NxN;?UCpSYtL_~+6vYUdQUSF=mG0+--ZMnA(9XrN$xQ*Ajs>-UN|M_y?
z*=9Gk=gU8C$pPJvZeV71?8U{!psjT&X=zLhpv{T3wY4nl?8bg4&ds$h2kl4j_4VD7
zagk}`#*GYicIj^Ya=qEt*BSbqIJdL-c|uxRn_2Fy1BVVVd3t&>*v*sH*4Cb5TRpAN
zsSMNtsHm=9T>bqWXdBX_$B!9nY|OdE^<1K&q#n2A1RMvAi<N*zOF#o^?eJ;3%#L5a
zkHJH02r<ZT%A7Vxs|&2@I7Cb)&p7?uk%P_bfx*Ftt-9_M78VNHhpX(Y`l=NZ6O%H-
zqb?&WOG#6c6O^$*o$%1mP|#90P{(p(66>SKk1KcnkYNBdt6pEzwXn8M{{Qc<K&K06
z5=Kc$>A}mFpryI@^zG{Z{jmfsTM^X`OE}sk3feOmx2NKum00lSXJ-%Zsr(FTpnR<V
z|MmWzoyC#Ir%0x!r{CFIz5QaL(nOB9xVSxk?tJ+7x4NaRO-WIa5wv)(zn}lm;lrTS
zbw7Un`c(DNlEK2#GV$@T-j1Fgmzo-zbMx&%d%dG-{>6u_jcWb<{r%zl_vPc_;y|nR
z9=?Cyzq|bXrANh}*7tv;v31Zsj~h2{Dr#zaJ`(>>R#xWW>zg{k$L`0E9}1S1l7fPQ
z72n=O?(OtHJIl0r`EvDhbFGgXC|Y}ZdcL^5UH{#^z1@L}-AreQgargN$Xb^f_?)=5
zulDzYw{LmV)6?JF*}3`PPeHC$P`W(al9O{|10!h2>d(*5g%1z4Ry|)Dx;hLrVC3S$
za=7IUXifF8V{F^=@3-yVUETcr%;)FlE317ks)Xe6%h@=bpJ!Y6;ejJ)10ZN#=lzy7
zt5<j5xDf#=T?@U;kP-o?6Ag=S(2NU7^S<v+>+g5*_2sSl@}hCU0);sig-q)H^Kw4)
z_v^*)>zS?}UnF<_^l4`wpB^6Jlj5ePraylDQqtAsefsq2iWMtBJM;eh`LkfzvSU_q
z!MV4#9K5%;Ixr}x>G}Ejk8f^H2klz__xJb3WxmqaKF;`czW!e`pR85Ft1Bx(YZXB;
zry0C#LGABvAHIG~mF=H-cD6ZaQlR(WWAJQ-wY9Rca&xgyXsD=Lk3?hb?{A5(uB<fj
zQ3vftFwDQVM@{#Nx<h8BCa9yjHhQ}fXy>%dPDf~aj1N)yDkv*6FLv)|W8h$EVmrS7
z$0P11&!3;Rnsx^?I=p?mc^khxpQ`Fow&T7&J`-lo*8ZJPbl~`LcF>B|cXxNUm%hGs
zb#?;-!{6WE#qZy2>o?1}(Xi0D{n3w)k0tDCDw-dMg@pyxGyIBaZEH*V^W!6EBC6{9
zySoo|w6?O!+0~p-kgT?|vjcT3K?{3&rOnNDECcO#JaWXv?d6R{o-6Lu{rTv=V)bfe
zV`E|WKAFr9dn9ctHvI65s&SSD4XuOQZ*`Ey9H@2&4W>(eosB+^4^0Q489C5+I=D>$
z8HVjES?u2LmX)Oi@(*Y}bFq7W+w$e<d+U|m`%+{lOM1S4TnZX{T(?f|u*s8PWdRP*
zF&?00I)Q-`OJ$ycb`P3nUrV^Kz_FvZ7c?vmTFWdg&24UOz9w=r+rfheK?@l_KRa9a
z=7u5Ytc&;i|MQuentpkIUmkSzN%Q0P_x3i=o-OS+->z5Hds@Qtb8~ruHeKIaU2aqT
zt*4Y{XW^qGoS;RQt*xzJ|J6M{#yexijD#~Y3?nuqFoH&|*T>t3goGG)X~nNvwJIPW
zpyAJ-KWzU&YnnctH~F(|HmDWeBA`@$<;s;0@9tWkdu(ZG32Lq;D*gQQ>uYw&%S)}F
zcX+5crKT?B5kA>JWr_%BvEZEZinX=1Po6$C^iY!rO+e-6=bw9g>((s|Ev-q3N<TpZ
zh&pk5W_;eUYnPRmw|D9ck2)1~b!7tsfwQyCr~i1|+t}E6#hSh5oRN{yhQz~c3?`gk
z*RPA)%M~9VU-R*(xKMm>PjBzXKR=7vPTqh|g6sf~h9JuEi9O)59THoh5ixL-g9pG;
zt`tgvM?s*ibkHQrt{XQZt_eOl)yT|V@ZbRB$H$<!IX}-9ymMN?)Kqlcx^<g+)Wbmw
z9Br$=DOg)eA3b`M*Q{KCgJsWN=bFq+%|2OcwXb(R6dug+@Zh*}=T5=1Gc&8|uV23G
zyua?RLCOh%ocsG?A1#ZYzxez6`-_(?Yb)j1d1aw9JE)HE^YbexD+4tUb#!zX7>*u2
zDq)f#5cE&Jx?D~)^zV+sKRcO~7Ie&7v`Ayc(rIne8l|;%G-T^JoOm!vT5smBwJ|}0
z+{LR!f{T5FB~|VO7b=>5KXYnIk^50zL1)%TksbT(|5%zCma}O*H?}zcTIM|G`-*dy
zWhCyMx>MaRe|$~kW}a{7yWdUrw{!ge@9)Kp$?jXSu6liudAMlNqJsbbYC~3qcs~E`
z?Bq0I)~v3=$Hx|CUS0-j>41uy^Y;H`f|vOSZV6lC-Y=JUtVa?wE}VC7PvnE&SAuJL
zm6VjU<mNT_xwyEvgfMN%y)6bhD&WS(WNsO6PtSv!Qcqu48LZBD`V2TN&$U`wQS<)Z
z-WBot_i>8P<gYEi`D6EN^ZZ3VGmX@ulIu=Q*U$gZYn^^>j^ou;p}sp#*jQLvKK%9d
zb=PswYUdq0cFZW4_|u?FwcPvPtVgp0rapc8RPxUr4_{x`l|f5=cATi$P{@<~SObLa
zgGmVc@r&d84EuT)_h2A->Ejk=eMU$qG56LMLED3CY$`rDRGUY7PAd5RF4m^*PsDS>
zNh%9{W*ULw?$F`GtZPK_&(1Qf_<pxMa8-!rmDS<?`P|xb&wN|d-QVvHT4p_OUY}9w
zsRcDZKe5U!e!nPe+JjF|Pgnf^`(3oZ{N*LreEZ3%t3p?ceS3d@y)CD$ot<3hsu0KD
z-`;{+fjZIKc$(RGg=~XY<nRA0HdQOsX|`GJg$0hxJ9h3oc<!7Z$Tf;;YHk;tE?ZT8
zQn`|~_1t?|>oOj3y%>j#3=Pn_AqLQV_oT^_H`e{F>b7O9y|N+@v<d0YpFajkM>x9w
zn(HblEqd;%TE!p;0+Ql_f{m-g*Mm-R&<<PEpyJul-w#^&C1sk`vS*J?_g_Z^1|A6m
z2GF$fx3{;q?pOB|`t<3OLGm%4oV&Y3o7wrrb_C2xJ3A}!a2sz`e`;D<($!U=8FzPW
z?F^sEZ*Ol8I&<Q^tPtpwm(<hK7G_^x$26_;>SA|(&>G$FbupR+Iq&c7jo4YF`seRo
zU;8sW6%`c;mzVig^{1w$g4P{<`1Hx>qt@pSUwl{mS|{=6i|-0qs}g|?K6})BXMsw{
zs{W@>pC*EaJ->W0`Ka~zz%fH;l-Hufz5MTEXt54S0d+Ytk8fC<LPD*RCr@r(?B1Vr
zdYZ0>udk@B`;3Xo?vKvQG`1*y#xrN`+>IF*mEIorumAh=`TQS0pU(%KLe#zYg=<BH
z#VnJ|rtItMK<BN1HniM}pO*3F#>N#PD}_MYnU*YH{`l6`Y}PteRn^XUnl4MdrcRhJ
zVL^qBqT<2>bGze9rd1g>9a<H+Sq)U%g{%l*e0yuFbGMi-Xl2)tBS#|soP5pzD$VZf
zub21p^V?DVT@O^XgQDR_s%B77P{8i8+`0E}Z_O50@pLLE*l_Os@1H*(URvtCY)*Pu
zQgX6k!U2Yy`}<^t)qET>GFIG+2jyWOBT!lpoXWA>Z|<bqTQZfsCoTDW`t)gUKMxN9
zTmKb%_SjfzXn0Ih@hmGVo2KeH>F%97DeUa*k&{$*=HK79NS&+r$qB)m$BwzZyS8?=
zjI6A#_aqf}H@8#T;p?Wv*M1GXdG4Iwzqi}(yPOw!_Ur5GO`A7we)H&&(*E!FsyBHp
zopitUd+g5o|Nl14ojW&Xb(pTDs;cW3pUK|d-jk)xax|uEhx@&|w|DoNpp{R~&9y$A
zduz+YP_3zVb`&OCDl0pG@lgaV0lR(U#tGZ%Z&UXFerFvyNu}~&6YHm0rrA&2dZkWo
z+qUh~`u+d3s+I}V|NFW8&5IWr`+q*0{b^0)=9H;ks{V5<0_Rzku6pz2iAwmIh(JFd
z9}(N&j@;YZPHIi{s(Zip`xEDOzLS$wP8u2-e%e?2`^mSrw@+WYb`8XKIWN)%FJe%W
zTu*JXgtWUP7IfSIsq`^2>nof%abi&`mng_Jt3$MYw#(N|NR6EK{?1P2{a-G5f9ev|
zX3<wEPR`EO){ola@r7q|$gYyi%71@;E=r%VG;pyS=(532cXk#(U9(2#?fdlf^wXc8
zot?aP?b@do7rS%EWJFC;IoT_1KFzxHRmh5X(4464%@jGiniZd4-`QEbY4z&WIr;he
z`S<qhJn*rdU%qRePuhW-HzWW3`Fy^#Zhh_VZ<~61d*{rYx$^Vx`!%0?W0v_y2A?z5
z?(6IO^yp}}>v;twrK&{FO**F+`8TO6DJdx}I^^x^dla-`V*dPotI}5yZ$wvoy}7ek
z{o4BY^`HN+u(2&FetvGza?Y*k=jC|h?PNMTJFWJ=fAy;C>FMc*j~{oxVDx#yoH;$5
z!fK%6z{B64oneY*FdJw>^3Bc7y5F*OjE#jir=P!8=X-Kf&#kT5p!UY&<NfY4jZ$6w
zMbe(1n+w|a1ZrkHI2pPpHL|U{n;Ud~N1v=USDePVmzS3tW?j*cu_$nO{ylnYR_prx
z|D@LM{Wfbs>Z7$$TS4O}j#X7wDUsLW{_f4Wxe3(9`t|LtcE!Sq9GTP{nZKYC!yLKX
zXxo_2ll=I_@neC<P>^9yFDM<@BSrb9soLR57Zx~jaB(>u?~^qwc;Im4`0?!cbS7rz
z!uR(;-TCMbL4|zsc0F%zZ_l=`&$_y*RWEkeg4EN~nx=O?e)+PqPuBX;Wq*57+oNwx
za&8D@ZIuG;>9;-lX36s9i-VW@Srk3tc=P5BXaOGsblUvFrd01EM~^Pdxw)xn`m8pu
zrA|||Lc6~FuYP!__4$qyH7i0^F_pL1S8?_4+kMP?Qp=q?F_UwYKR<o_y1V-OyN53>
zE)G~30@_19d$x4c_PpNM-DNLr%1%wu?C9(~`1A8~*0rMADk?0Mm6aWRePXt)9UU)P
zj|gAr>;M6s2A$JCo=%T1x%c78!-tGhy;Q4a-JFmrdGh4R6X(ynUtJZNn3}3uB{Xy6
zpFcG+_H{AOvsXoKPTR0;o0#ocoe#b%el1<TJo)*#xjQO8F8a3f<&~AfGP1I+{>oY#
zZ&<W#%wMqrL=}EXek}0!JD7=G<d<pA4FUcAe~dueS9h1cUsUw;l$H8|^RrC3KR-Wz
zyjR+sMc;Jq@qT$_6&04(*Vnh}oGvIRVEC}4TE)}J!GYo0y4dWA^PSuI<=sHM_3`~;
zx=|hTlEXk7+b%A4fBfO$;T4gam%Xq|Q@6L5-?(w(jg86dlO|1Ku-Ul+v}yF=`}g^Q
za~B7#+)(y53bZ43UQ(Hw&x{4%U5cI4&dm5Y=h}?@pv`CRTS0qySoMw9{{8*^@bTm9
z`TKsV+1S`@sQ#X(qNbK~dt2^{D=R0TOP+0#+4Sq{>*zO}H$V$o`{isw5#7?(wkYlF
ztg8QZsrmW(39^EMfhUhcBjd~jx5bPMZ|zUn|GgpcPuWgTP;jQP8K0n_;NFZI<}NNS
zUzCy_3kU{!re<e%|NQ(s`Nf5WRsIg~+j1m98wuXL$vNoltFNQOBPb{+VVuTe_u~O`
z$oe>0hJw$}d_gVx8P?@`%Y0@wWnNy!8JAUccX#>mR&H_7?)5#tUahY3kD08(8NDq>
za7)0P|9{`tgLaLdn`g^yZ*RY2$Bq}ZdHa4m;&$Xd8S{aq<k$A1;^K?@>+9D<Z|B>j
z16n4|Fk$LcR?kTSA|fqUSBFPmX`OX#U2OM<4+Sy%Y9v9^ng)qXZM@RUKF`=&{r%AO
z>*AoDC`ar5t_;!gn8Xq}O;rDzf~QbXak1~7o{o+eM-RY)<-+B9k<+J6HTCxTE?n24
z4Q}fAZ1CIT)+^<>Gzhfb6|{pfuKsW7;(E79Du4d{ey<jxer=+%JA*@Y=)2|e(#e|P
zAOF4Cd|ttG(zjQK=GT6kdC^|kQ%KEkPDWGdBhUhsNh%LtuixM1we--*lsl(j=K@?<
z=-m5H(sR;=l#@cjYlL6_`1qKCfuEm$Zhvp(uOH%)_ghxId3JU-184&mOiUV9i+t;a
zG-V)U-5Y7N1`VW;`n9pJ2h>Q0Hjg!uAB*^2T^0KA-|zR2ANSi|t7iIjV`K8h%*$#q
zJBwW31Tbb@U&pJjuMawTr>g(^>+AgN{BlR0o}TWz$Hyi-JbZDv`ZN{J&dyG?s1&;!
zjmJRQ^ZvftTh~R+&CR!DUS@lGYO1jHnIjcURUelwS+XGMXcss$yRP`~p`hl|N%e~N
zd%u4;$S%JiY;6=n!;&Q`pp*kXu(0%1h|gTB&<{bEjZ2bD9e;n<PEI>BBeBWU#l=Nm
z4%+odY150{#lo;6czNHs<Hu}j|8#>6Hk+gZY71`IwCPe^j!#a`8qRB-OW*q@w#}Qp
z{J%r4rajM-+0VYL4qVI@q9qDC)FNo9*FsR5{>4}w6f~(*tn2W4&D1|tL19<U&t9(c
zaA)FU2~cT%Jvp_;HVni9NzV#8cI;w*ZL*BCyJUR-)Q?{yK$ZOdWm7(8dr3;W+ne<j
z=E#6GTu)BTkxBhCOKVmmGkenedwVS^KdF5B^r^(p;s4`)d(aReNCH%mFP}AM?OI*X
z%*w;V?XPYBeZ3x^{N~0+vC8s_ps*X)g}iquf4qNoj-{}mpx}v9rw-lsKe=J^=EF-o
zCx7^OT%J27J<5i0Z$;kyec-XSo15LMH;Q<N?k>v(4Z&t#Uw5_IMn#3iy-#N2iSEWf
zlXXsmCad*h99&#n)DGTK09D#X&ZV!eT>N>kMRjlDa)WE@<MTfxdv8lWFUJ6yTswFC
z%aO;&`x$M1KYV_<U-$0U*VlRLa!x*a^oYUc_pGX4hK%BRF$^Ex?5zA{$ml&?uT{lU
zBXrf2bH|SyGlVvgP}@huH_2Uv1qB)X{ry2T-Q8WK%_^Rtam<fr&F?21ZsT1MwpQxU
zp+hd`MHW?kePvPcVZkHL7wr6UE?-|=_1)8TX718?5pfd6>F16dm#^>n_V#x2lM@pw
zo=y#CV0eCRF6dM;(1yDeAzD5&3>-fMUGC`aZr;6n_X|l?q4(-PkMv5Lg9_B6k9DKB
zJ-NU8U%ZzW7c|@sTQ2}bhv3YWQl?p;Ewdbad~TD~d|l2PTCWaU+q8eb{i$iX+ErXr
z4Zgp>-@bV9;un%>&)?kK4C)QPkPJCwv$vZqFc92>4Jh1@KV@U#3X2;SAtB&A93lg5
zX=w48@rjCpI<0)7?4ZVE`#)_>P0b%a9`|o7eC&2-cR4@9g9i^9?(MBkes*Ri=zz#Q
z0X><QmnGiXk||-B#B!`pcJ<x^XO?<T2d(1*ol*q4bhktJ%j8Lu7#K{muU+|hW5)7+
zbtVRJaq&I>e!af2ueQ1|d6UlK;^*fqYJY8UjSo>ZG!*RY?DX*VzFa-2G$CO@L+G>C
za)<i1atHlAx3}jnj@p{l(ci!Q#QE7bH>W#KQmOgzuzi9G=jQbDX1~%^JP*0c*QPX;
zqGaG@Hnz5))1;gysa#nd&abGb_~P<%{yTT>xcD1$Yfa@UD=T|(ZLRc`EK|^|Np^Pj
z#m#4&Hm9AvusuH>)PO8{dTP=08M4;a)+KLmiDqq;irrOm@!rj2msW;o?fLm^cEIYZ
zpa#~}RiUo_M$&7ewmRM4S1TwW(9k8S-8C;c?1x%Ns-vSLXz2RSpFb7p4fP3-+<q+Z
z*goV&94xPc0w1M456$V|XaZ&QoH>tn7eD6%EkM~>l)55B>tb=ssk3K~HZU?TxR?Q|
z6sp7W^7K+7+oIMUTNS!mXHk2ImZ*xSQ&^Z-PEO7idFjd1r>8fSCQa1}<<gqUB`GPX
z5xPpmYpPc2mz@(;I4vzL)uJ-&PEFJ8wk&>@@Z-b7s($^bEgX-J^*Xz`wRKMKEdTl{
z6x3m7=aXSr@SpGgB$db`*QXdxt5f=TAGC1f*O!+PrdcA#`eeJKwq`L_eEMmUf6oTA
zXcly)Ohv_x8w=A8T+)wO@c#D>!<w^-N=jOGumbm(kg%|zsAy~H>uV3s%ru^$!g+R<
zsk4U%2NN^%$4lP&o%1x#Ec2bc;9|yx+TUeQo;+FL)XD`q4<Tx;+v>2jF6V_$-Mk5E
z@NL+(&8?kJc0t(ci;La)Z`{7!Jugk{UgdMyoZH)YZ{ECFP*T#ef4}{eEYn+CGL@@l
z1%TT1K0Z8?CQX7a_*ii@3$!SMkB@KBbI#DEUZQt)7PBw)n%XpfzWkLe(_Q87`J$tv
zFJ5kWJUd|O&0Dt~f%Zg3Y*b=mW)_r@>6xY*-8C=O4Ag{&bp25p@~3W?w{0w(f(`MY
z)u4W9X=*VsF$Rf;SnfT%)Bu|3vo3pc;OgpdMux3fSDl`poBQ#YbUsI1niZ%#Q1N_m
zeZ9PjC#Z7z|L?Ew2ER2YC#yS8QUUEo(wge^d!ym}x?d|fug#neIwa`qS>Dsr^{-dg
zTv*_^qw1^HqsNaym2Z4}yo^nS0BA+Z^y%VSAuASqFZ}xIs_{po&!2yMOa>hpC?_Y^
zb$;^F6KBu5dU$Z``~A+^V-kzBv^2wk#qRwIr;R{?y(V&VoA_TQ{g@A57O8^{@Pm{B
zN=l0sJ>-1h0s^X_gHb_IK4XRiXeakluc@H^%EGYKAHUtsKYZ?--xn7}=%{Xni4@4@
zpFe*V6c#!b6c{u$H(%V4=zLMw*Kb-XNJ^@gZMIqNp}p1L1D5$n?)m%ecEIYZFK%pH
z>>9K6&V+V;`J~6kdM{*{fR@orm_D67Jw5&H^IlL%+<6G(VX0m=X|o)MtSqgZ+}zT4
z_mVoxADuXV{`frGYEYW1{G7IA`SQaD4>H<Te`|?a>$bb>t<JAL&KluWb>H9LKmP0M
z>xCCHK0NNXcbb-ZWlf}T)>f&52M<<!y&CT7Zz2uu(y?wV<Vn6SaqO682ei}X_Yhnx
zb0vX_2E(4-U;%Kut1f5Gp+rzqO5_M=z$sZmdbxs`-^0+AL9C$Tk~##HUHlEXIXOAS
ze%5xJ5CNSNWN&ZJ!p4^L<ix}kfs5G~9{l?H8q}#wN=^nHhj(Rdbohs$%bT}vKfa^z
zamDgi^(W4pX_-A+8nk|g-|mOQ7n#kae|{A175Do1;e)`QGc_L$vAP!j{+4@ZN8#Z`
zdfS{`T)xCVf<@c~&_cw&3#+4|q)tuIY?iaF0-e;kXgO!;^K-JGru4;&7cI)(NT_%^
z9d6^@T3%H7>#&^nrxzEML4(@Q`DFC>eh~tt5*Bv$#g(6*EmG&2K5JIjj2RLcCQ_hN
zgcv{rlW(8<u8rEtqAvnEOx3#lU5ne|gV)wZPn<ck^V8GQ$_fe$2M-<ujRwBxbb9jS
zNy6)EYcFJ&fX+4r%_FF*tAh@yw6KuK-}`mii%zGHzAJvIs;h&}&Hy>D@DYoO=b_i@
z_xDYhAi%=Py0Gf&t3~Rwc+L9ia^^IF`gouU^Gh-)W-j*k23x$5PK8Q<axanusDOs(
zfJvAo9pRW`TP<e)=Y#XYcenm53SJpfP+s01wbm^lV1jF%{4agb;>j82`EuvxTB}!e
z-HhCxCkr}dMb^5kW8SAbq3dFH9(e8L=f`JcWW*q{M;LU_XkvDD_wDWZv&&XUu87-f
zrRFoEA#kx<=e(q{IdkR+$jP1KUK+6Q<001n_rAQmEGQ<{wr7vc#o&&P4lfmGAsf<k
zcV{s>=uGx$y3q=rLjNbe$p@Vo)$7*$;zb7N=+}UiAr*gqY<v;v^l~?I`|8!&SF%j)
zem)Vt`1#DCtE<De&Nt`e<eZ?wsT;lRNFy`5i@&gzwl-+{zgtO(N!i<5t#|Ik?AWp6
z!Kta*i<WaPeSglQ^wkwd4-XD-6H2%*-|6c6M@PGFS@+JhF6Yyl$^}~J;^D!;#wVju
zHScBuJkf(2bMnyKAoCbpXhO0{AgFl^%|D=~@ZlR4;EV;*`r`O8%@+q6nL!N`t<Y61
ziq35Zu3im&-&(5klyAmlHQz(KN?#ZJ{FIt|dd1bOAHRPezIZY4%O0U-^>vz?mpoU~
z&{z>6zOAFLuZ}PKOmszs1!!WunVtX8sZ(BGWHuY++%SmQQz7{A<HtqIXSDj;{bT{H
zqCecm>*{Zqy{F*d{$$Vlt2;V6=CQ*<{LqspPac4l#<?wajERvcDk=(C8)XXG$lk5L
zPr&wk4rnQxR4<!UFPpf2T+7s{Q;+Un`TYH)$&(FheiZD}^f`EQb2?~YkDYz}<oWaa
zL3^kUHnDbecR&98iQhc`-jNd%m48|;W(RfRuE*CORi9tev^IMCr=5(_%Qt|Map9DW
z`H<8KX?0Y#)dpAO$Q%aOPrpD#5-8*}k{{a~KBj47)|UuM&!7>gwvC1J0#=6H`hTr_
z(F&c@Vn6@L*j9;1^|Ec;xY5JY)A8k{r5AS=r?0r01!^IgnVBt8pJh64$FiRDye~JG
zz77LbJDYTpKRh^CP*`}eTB+*!xw))sgkOJnco?*`XR21HLCK4NqufhDtwN@2Gv|3N
zJ#=epwxEm*55tew>-PsNcH;$&DEZDdYq~y@KW@i^`wzcsDJd<gKOXgk0o0{XGSaiR
zm;d<jBPieRsWg_esbBz|FVD*AxHfDt=+Nn1r`~lxyS6sEqpz>cZSleU{eRgar-3TX
z2cW6<fPe`vD$_v6C11!e0gW@Qjo!Y+K0@umv0mw0=jVft65OP7`0!!otgTUBOcwUZ
zST3qHc7jw9f)WxLAJ3l-R`;KGrOr2YcNs6Fg)sj`<RQr_VJ${YO-;~Dw22gNpS(RE
zL&lvQ8y|!wZ7Aew?@gAGcDDz2tP{Z%11O{u?u*EQn&EwQ;P5|u!vYdFHV476QV3Rf
z3LK#&Yh!i>ePP*rWlv?XN&Y>Vi4!M+PA&dc{p;D;*@5d~EWf<FD}C_b!4Drl3ffNX
zh-0v=`f}ml_v-h1mlyj?Qt93+!NE{bS;@!%S_<>#{{H<33cc&{8r1*)zj^bf*zf=A
zm*n5y2a2NIWp67UGASu38CgQpbIP$kS?guRqFLG5**|{%1O;>T_jen%ZWXl++)@4g
zUE<$gUoT{sfVM(@`t<3+vuACdlhr_~;`UZ8Qs?^qg-`n8#fv*CJ}NORD1CixhFPu@
zXvfHl7aA1{EiyARLHmx}79U*b+z#4#va9s9l8z2f)>f&~*VjaC13Ow;STancKs8MG
z`nXmV&kr9zHb$*=TOYUg!Gi}1Rf_^TJ3DW!U%5H`JQD-x5Q$D<btMA>0a5KRkv#!C
z`#7&|03E=3V*{g9FWc{LZ=K`f<YHoDKYlz89+3O``ntI7#U(c^j)6xrUK|It(?JtH
z;Bx4k@tfI)5+6$(KX$PnG$s!nc1_HglYYaZ_3$y!e4sq25f2(U+4S%4@9udC*Fv;J
zYiesjXDiH^BLkY$x_I$oM_1ROQ&Y7czIoG=eSKZ$JkO9tpa!P8|GXoAe}A7ie}4Rf
z3UD7N>FCj;o%0g5P1B3bx>$dI*`tT8+#MYq9<bs(W!bAME1R{$*D+LlI{av5@baiX
z{N4ZG?S8+n*=_N`b+NlAOrG34J+6w=xt$NxQk!L-uU9p%;Mcni7gq!-pP6CEeDL7G
z6@iP}UUVKxNlgXqodjj1z18N>3baSYQYdSyl$@O0B6Tj%>BKJX?x6Y;R0pI=`pz-|
z>AtYsUp{1QROlC%h5zc7FP>ljPjZvaV#j8-A73u}FAQ59xH?StqHycO*#T2+tG;mD
z-j)k;U7xJ=gt>Ej!LDoL0o4#uTQU@@772h$rnZfRUy?x+uHf+z(15pQ2WUhD6twXC
z0U3E>1;>>HxKdaQ9t>ap0(64elqn)t)<%n`o|+<Pd;HB5y;!NeRbQLduGQVNY14-6
z>w0(gR0e<1StRuM;$nBuiZv6d-gBML{ry>LPYL-ueE<4Y)b?NwubfT97Z$C?iib^2
zWp8c-zBoS5y8NA`o}!Xc)kpA*gu4J}dMnUz{k~sXPEJk&GBP~j;o%pH&-8gMZJIk*
zc31g(Py^$~uV065&ANVri9udo{;jN8OiT<Y+*Vx8GReB)@x^3wz_y&ol+@IN_wLEr
zR()xRS_|sKB!C93X9Z|Y<zfJ3r3ViZR$R^M-Zi;jQP#Tb%DtB-Zr+TnR$rm!JF8=!
z+8z7*Evv#-|5Us3-@M>~1L)X&emR?lwQF^EmA+=%8rADJ*DCVQcWpCh37-mT(10cz
zz<o=Zzc<W}Ve6EDst(jy2hCZ!(c2RK{P?(|;2{%3!uff&A3lC`%*xWTDtXbcVS~Y!
zH#dVncx~j9v0&(RYX<GOU%&rf)7-gpznQKKUhcQ(`OKE)X6J?e&#J$?5R|j8%P}mU
zR{OZuoa^t6Cr?uD?5n+<G;j8PY5O`G&`2%l_#xe>Ee-3}>w^xuR##VdadUh0?(Xi0
zeKnO6=baZ1OiEG$O~f#)2wg3fb$y*~h2Tu#sa~y-o6{D0PuF8;sQ&(LVd&~G&^iMf
zTidVyW`@VtUY#O*(g!kRo4ow6Z7t7x0e=^lkQy7txuE%k6)dODpFjTf_4UB5S)n&>
z+~}C6d}NksHt1m1DZ0^NUqm(sZ%hImQSH1o40OiSqUST_o||h88r28I-rl`?Us$F+
zemU1v=cAw9u_^lTa-hT)wYIIlpMSm9AM+aFRYsr^^v4f}wPB0P-{1RF7wVBCW7emb
zBZC?*a~37vw>b#P0g&1oPHI}2of8IE6_EH#&6#uP_rKroL7iSur66lv=2B5%@#yj6
zhmRjKGrYL9ReQ~vH5*b-iyid#egEX-WN4N5_4W0IK`SpTbY=&2dtY2U{OFyKeZqkT
zrFz}9F*`q5t~JzO8?{yIQ*rT!2M3>TIaafC*RDmeyUReq30jkPYN~d2e11x#+ibI3
z&@B_|_x<wv5&}AgsuMK&&ic+KW`A96&CjRP#cHR20hNOH_DJsk_e=ZT{r&xa{?yEU
zJV_<-<RsOmYcsE1p4{>O-OH1QyefnY84s+B-QD#kUFT<Mdq>BM`w!rqkGHqCKYa6M
z&E6pMmtOw<$A5f$Y?yXNV$Y{j+KZmgxU<;3U*{KZ{D07K5uj^1cI@5_Zsf^q2A!e;
zT35br-@X+=OS@iJs!g9fx%tvk@9uelk0O4}4wyW7GAO<;8hgorGl`iWWYp}2#nFSu
z5+93*f@b;oq?cQOn@%}%9wj{9P}tQ4s?OVcgJr;xVdj^(_v^K2jp%JU-`?I1f6x-Z
zFvG6aYMM@D(~>1B2fclj4GjgQdf7l-km_$bDUrvb^Y^wwyC9%3Cv~Bz5!<$H0}oZF
zoDfJ!OIwt4a}#KL{;smOTnwO2osyE$ggJ9`DptOHdvi1UT<dbTtE)l{D?TKcWL#ii
zD0p^8QYU_&%*m4{JG#4_e}8++s&Be?$r2UNYR2h$u}#g*%tl5=4_>_J`2GF8^R(2E
zH4%c}zI_w>T)WCb{Z@Nhn_au=vwm?s(5P)-$Rc(~3HR|sRM06SW8;k}Cxv46*TsGj
zQRLaX@cFm5w>NCsbm-pRYTq3zo`9NdpzWXWbw6Fdh-@zU|F3q>?{~X@Jnpx5@fSRF
zLAoj^C<t_T>)+qsXXgcQ7Ct{G3%a4@!b0ao%Q+HX_?`ysr;goi)+cA1b;wl}G9uX<
zECVj9K=Dxsii~}RJ-vsIY4U+4Jt6S{jtq%opjd+GiQweq<lx~6v58yiCAwtEk{JaP
zBT8RibB&0Q0B!0A-NRvDFK7Sv3;5*v$>;yar=_V?eSOusVui-V;1w-}MMa<;t_%n6
z-IIHIdiwF7pPz3%E^k-UapsIq;O7=Det!36Hr@}%<?9n(U0KP&!{d^Wps>tuZWriq
zh_A1&yH`}~crnwdN7|fk<;s<yP0yeyg~(~3)iWt6DG9&6yeudvIIyqwx665xnHMfx
zQ2M{g#naO><HiQXUteA}AMF-TzPTwCbURGgnux}yr>7@_mf&`G3)@ca=;(+GxCW0J
zk4Y+3O_7hK=TG^#)3E1!e_c)7m&vJ;J9qA6U8m#Y|KYRS{ylqaVs;j>Mn*<1T0TS7
ztS|A;uApPj-6ZErr`F_w%J^gFr6IG<$3DLHf(TFfxbtFvZ?c3vsQ;jm{8-}ndhOJj
zyeS`d1|ECvW^dM~S6y9gQ}ZL>V?|PuQe4$bRbf4$>?<n*16E)C@Zp1i?a`c@w{I)k
z*~!hdDiyLlssq{z9#Mbp=FOk>aY_GdY-|dioDh6_e6Dr*vFG#a`=YjHDcal17e7C@
z^~U<Wlhyq}htp|<uZw9+etK%^;RB7#hLxXE7*8MR?(aW-VxscJMXua`zFv=Km{+5}
zee>qSM>>T;OPxRm^4+ihzxTn?6u*CU51Yc{Dp~#f{6GOY%RIlY^7FIAmzS1y^!JO~
zUS1-m8x``z-Z<$<$MX#>p!qu3G^UrvzlOOlem<D}?91cNPDc-(mj(@$U##z6fBe*s
zI{}3sKDTvs)jEHv`S3MDa=x?{U){Zcz>S3+^Z574X+JJ@ZhiRnZ7*o4Rr0YO%>o@u
zOYnst*Vo0e>If?v83p~mzd7x!lZOY#s_^xC1rsZ?uC5a8le6tobZ+aIrxepGW!m+%
zYWDQ$-({}N*gjF&T}e%i&C=3RBX*YwX!-Z!$IT553=9ruXPK7nW7F;I?d5%UfB*W5
zKL?xHH*DN!_)zKd#F;ZW&CSgj8k(D#RXjnbwQM;ay(Ocu-|m;k6`O}eMMa?6Kt)YW
zNmqC6f&12~o`=>%Zf034+%B%C@nY}ydzb6>Yn|Ee?=cB7&)(Ik4w;ac>L98ec4S}e
z?+ZH$lP?CJnbh0MYh!Es@Wl&_Dz2#xHJ9hq)x@o^_)+QXdK5H%<$UxgXo@QjB6JY6
zat=)h)Odyq87%Xk-<NiF*2A^i?|~-8RXh)^i`~7U{C%8G<R+F)I?1oDtX!1NWte$M
z1$5dzXawQ@zS@WH-}AGxvtQhN=1>zW_k-83yH8G5Prk7s5!}G_Jfsu5E95y#N#wMR
z2?v=#bGfy@zBul!`pUqNetzE3U8S!<tDAacEQ7AZEZnnq@58rm*Z#e6^{VLe^Yf4E
z@BhQ3t*vd6b%kT8_jIux0W$gd`JiF#ySqvcOXu%dSp4S6$;mV9>+Nc4YFO3^pFVn&
z)jaPG1H%-pP_A?5&Vk0ls=mG9WUwfICzF$#>*^=+>_8*)hwtBy-`!m<y8C>Pzr*uZ
z?l0Q0yG%ek;2t~x73B_JWR#Q^iBD7c9RC#5DCszJ??5B7pp+DszrR0d5rKW*(Qfg_
zv-9^Eel*g`+_ZVKps+Bry}f<N${^P-GMhoe1=-ivEzG*QO6+&DgVrp_jW?i1(Tb?8
zt6o^9J^lFjIA|${lzHA6^T>aP54ZDw{P}!7=ro^#(o#`dcMUVXzu}<T&Kx>jl$tX~
z{f7CM_$1JnK|tXK(1_QRjfL|P9$%>M1oeuXj~+ax`J&(c-+>nw7jMkJZ#P%?#;t9+
z-L2f>QExcC%=7LvxGe_V+u=9Y3UrDa=t!vA-``s2&zE1bW{r!#$gzV58F%j7S@GqC
zAj5%Mw{{(Py+Os3?fr{Ci)I-nvw?09JlxK|7__e9c;5Yey<uyk5<fgRC}Cf>XF+R9
zpI+Raj%R0QE9>g=#>K_m;uZ%TW&@h7JK7~$_~e8jbRbmPuEwJ7-_LZ=ihBlw%1<e0
z=GjU&v++9B)!Bipm@q-0`_JyH+3WYVZP{X?6S?WggQI(NHcozhbv66esNM}53>f_N
zQUqjV*4Rq^Z|1i<aBFKe=(>Z6#=csLij0AQfgOE)$F^o)2W?c@8r8dCfkMdoxY#c?
zpa|vicL1+q(qatJ5(O<Tc<>-$@A2fMBmo(jo;`bPg!PT}L7l;UwZA7!n$&c#nSHU}
zTr1G5?9<cJAHI48I!@-I@X0eje*8$dw8S&x`ntLI9{>LK_VDugbzOU_zt5_eSs^JY
zxufVQ*QLvsA3k{SoH6}6Y%KtTxw-ii&0x1LItz`AjUPUJ+N$W>mT+T3BB%*FV}=B1
z;9RWQG*3&;%<tib!W9}wBX0{AC4mMh+Pj*1Aw$xjo`jZ`ncu^WAcYof8w<IT9*dN`
zx}teyRjBuS&#cVMOi*7RG-b8B>@Ab}`KV3%=Wm%hWlD?JRIP_|%kMdQcyv5sO^-`q
zX5+cA^Y!*gQ?<iqCG=LVjNGi|)-Tr!8k>Iq(X#m21JLR0ph@)UGw*$Te7yVXa~m6*
ze~(pF5BEx&3kV7}?$}`gIw<bI<jHB)<?nhtC#yxi;an8HF6N-W{ofWj+o}a6FE4=t
z@x#Nz8xs$+MMOq|7K}#hC|KwkCv)!JJvrmFGoVE4>ThVhr=T&BonH<#;{5CD>xt8*
zfv(DOTpM=y{(X5-tq=j*{*I0nM>dPuHh?qczrC}~^ADXn=l6vt5!AN$_xHE5ni|_C
z9p_0ZB`+>8mcF{usB;>$qZ~Be&MB<cF)vGK|G!_^6aSx)&foJ<X4;JXe}8`m4V85r
z4-N_fO(V=Im{<Y2JnqZO%Y|=l7(RLaJiGq>sZ(6KQCkiy@th25us3oa-MD@G@u#P!
zbANrt?0sdqzx)*KaK63O-`zYsIQHz_>*_DG%C%c;hFR{cZ?9F&&Ba0I$nW00+x6du
z9XoDV<jmQh{8)tVH>fH%0=IZ$bLP~azx10e;qf0~>E#9BF{mlvA;K3)kN;HX$e5k8
z-&n}i-n$q)(y@F2Xr1iYS*EwTm;CvAh)+~2<Un-(Ue$_)m0347D5jm6(I{!0_Ta(6
zX3$W#m~Is4gouTHbFDxVRc(B-T<YrT7lVC4t9loy&sclqN=Qn2y0+Z;bLZT$vQ}}5
zcV1o-xjAX?zo=KPvsQ(#?*px(WBBl;uJg}7)*ZWc9lClo^!LWOb7jNUMjgGbXtR^~
z*Wq@4*YgJ6kB|2s2SxjwIWnN0|711aLtkHC2OW$U5gDmyU?5QZ{G6z5u!O$8enn;F
z!`18e9XdDHdf~+kgR(afJyNDz+~Rtm%WGWxRg{#pE><vEfqMB9XWrVB%DpY;=Ayq9
zkQRjg2hgCGqMhBnMfC+%xwlM?96JWuR1P{N;r06c>ul5V^ZOeb7;^6IxtVnD%H=JY
zmzDlraGRv^<k>U3<F3!nUMMd8_{i15!eT~2Z$$C)b4T0d>o~NvwLuHtd8N%<Zf;7Q
zIB{a*<>mg54>U4^wy=QKaDa#XwOi)Tmj?~GU$_u(G5E~6h0g5)qN1%gZbYn!+RAlx
zb+~&$fq|2g(*@8p*=L`3H#R2kD1P4e?eXvL?+@R;EnWTXO=Ew5|AEv;8w<Jmdlz^2
z23Ne1j)kpQ-UW*M{H`{LM2-xqL?ODwt~YPqOqe-y<=-1OT4i6%eDfv;be4W#U?AwC
zn>B0JfbPz?apT5=%l`I9LD%n8ea!-m6MP8~I&t_g^Tdf0K^@dPckh<=&9$i%`uzNS
z`|{<>7nCj&6&GLr`Qzi`{h+2FXk{{}l!jN^=J#uwL32S$N=`>YHXjx~Kh?J8hd^0b
zS-{GWMawzNi=X*?d3#&@?ygej#csVW=MA;@6gWPNh>l(yx;kt}<!3d}Djm>>)%Lu*
zLblzYOg;I@^668+gUd>rjgpV?)O@>{&d_k?jL(f5HxAs2`Ysg&S+!sB`K<ZJr_<vf
zO%0C|Gz_%}4-YSSd5IO2aPICd58PRldgS==?E4a8l9HVr9UODbC+s}|x?^r}|H)IQ
z4qaO64Z0H2V^T_Bc+9_VxAV82zX;l^wZM@%WM$CO1E6a?+k=<;Ei8V1?#8at)hp9y
z-I-~e4(ecUzgNZm`r6v&?r!hK<0`7E3;pNYSrk5E0bRd&Wqo}7fuN0`1@R3H3?`YE
zSQai^SWsMixjKD*m#8*ZM7ms2aq-6D=YF6g7Jt9r?;aK=23n54ulBc+g@we`RiVPR
z7gZqj((1jB+xETppVrk2nlFfjj!b}NCMAv^t8D6BEdP61#tn;Ip!NZ1q8l;>`k4i^
zM#=BuhQboqa1yAzSe<%$8tAq~cllZtcX#(6zkerxd2tc6{{F}Fs;{q77qvcfotFCM
z=4N(Kn%PrneChJ#i%UF(bN}1!ef)E6^mfp2nTo2aqM>2nhpfx6ed2F#Z-4yi>S~6D
zsI6HGv#+lMEf_pCRa?Dcp~Q0k`EA>`n}c>-P1B8j^mKYW8w2RnVbJ2rpP!zB+9usL
zktKI_6oSt5S?JuJke|Q4SVvizIW8^^v;p?aOk-AElevP*ZVr=FK$mw0tPGJbOlkoy
zx)alj$!IEl_I&&OI?(0F8|weprKG1Pe}8uuIvD2U>}*)|C1Xq8-KZ}<iu-=Qvu<f=
zSy1@+80awKsZ*z(EA*TsAS|q$G56<#R_+qehJ@48bfM#~IXO8O_Ewj(u(Kb&etr9a
z=b+L@l=nSkTTIF_(3as&VRfd8PtTT%YKLXq|KqZ2(&WjY@H+Y!G>z`&*2XE`d3Aq%
z{n2DgOUsB&DV(5Naih2AE%cpj#=*~Te%HbnlwCiwt^e}n3)6pv|6hEILHltdB4(^q
z=K^)|r|3qD-QJe#+{z{T#co;J*;zk8SI=(Giv?{ZiLd$C+8N&U{Z{sR$TUKRiPX{K
zk*B1ee%ZKf8|a3Ji(9k9LEYTT%X}lYW{E;8z6H6rx4pQ(-=2w?IWaj|xk``o0C;*s
z&#cb~G$8_NbMz!Xo}l<<_M*hcFTl-A&|*S9(9{T@<e_7lQf7T1#h|V~NO6g)o7<uL
z_vM?}c$q#td97|_Bs6j2#IE{dlk}=SmM0(YbM^7z0W}n}uC7YFu_5ur_4V_=6~B7F
zDs*)lsAUzuzm93ztb1o?n}gayr>E;LuKW8d<K`w+h6i_c7K5%Ae06m-XfJ5@PKV3)
zO|!0WfQ}+fpI_UyV}}K3KJ38c>yHJM-4g!%__!i&@2&?^lh(xT1ud7>Dfnc`018BA
zHl71#W*X~0V)@c5ZSJ%*DDmE&%7B$2H+B>*zPNi{^efI6$NOZPw{JIJ6}GnPzyXK3
z+~%RHLO9Fc-8uN^Xt(YsmM?3gw}Wm|2CcY&T-F)(!0?#e`nZ%m1&!;Li--2~^&Ok0
z8~x$O$K)Tseu3)Kir;Uye~nuJS{~ii4(qppjzCzXK4a^vtE(R$YUS=a-Y;j{WmWnL
zv<d3u$&(=446DE8+}Tyi4LTaJq-2Zh-@~7S54ZCl|M2iIBST(Z9%u{j_jh+$*9*PB
zu+W)<gCn5E`Fyabc9@HU0|RJdiLkD*eqv&x*k9(gi@ZEM4t#ukyztkT%oCe>etmrn
zD%L=CKPUmec##3#Hs&J)UJY^F!t9(dXqX37z=-flxAP?4mpBgU7=lU^NpNe#_3$x8
zXV~-%WK>jB#;kAMGT+&c9v$u8QSwp<6xG{uZ-cIr&A7jB?~BZ|^qZSfU)<abz98q@
z+uPEAZ9rY^uyrw+i%OGv<?ZE8o;(S<w$iHn-I`(@Jv}}~M#dQiiB0D^7fo9dwKWSg
z66bQ>z*<sL(!<v`)MnnKNljnAlnCnysasm!d~p2BnIoOTA5Uqoe{f@Ca>b7iieYP`
zmKN`c-CZX3JL>aAclm>7&+^`{{VpqInx#_J7x}Q2n`>3nR?t>Zc71()&}HC^jEoxb
z`}Vwu1g&6$&F+LSfp+xV+glBqJ^cqtp`fimpoLH6@9%+zS9S!fS+GC>bUA2aV`D*S
zDeH$fUCXntt#K?V0Sytb=!vMStFy<~|1||2!x_Cj@8Ip*x0UXnS^VVF)6<L8XY`()
zuAltiKx1pwn%%ptudR>&KSz9~y7w+_@4~tE^>TrMffq7NJbZjWJBdJDle)jZ9`>5w
zV_*RFnwr^o4{b<1JYm8Fg^G`#HzyzGd&_^_*w|RnQwVhKz^5lCnfj-ya3&w`GyUrF
z5Ik)OUh|Y+0&YJh%Sb<$H0w)zgIG?y3pR`PnFl=W4_f649#V}3uZ9sx$<6Jp`ub{N
z+}<is2?81o_4oI`xcSVvx3{+kF7uh`WPcCTAhdn!y1n?hUyr2mvI8fdGk~@W?)m@k
zcf_`wnGLDWo}Qa)?cwR!ID7W&d%NqRr9d6|+2;IbXPfJP*txm(cbSWu+o9XHqc2z)
zg&*&iKb}6nmd)DQIwdVl%pz`YRcW_v<Nse@UxUs^_qV&=3>ql`&2IGe^8Wkrm>)DA
zF<H&m=tqU;B+yL;!fTb4l&Us<U?~B$C>9ANytuG%N6k;8K3Quv22dR~%QU;~_4W16
zOM^hClv<a+16^QwlutC})D%rn&wQ47K3{oxxyPiIkB^UodbORMouI~LyL_ES)iTf2
z^z`iaN)zYI;mOa>2ThB{#l<aJK6C1lB`PYasxR;CeE$7@{c-X5n#MVEWWKz-%x+ut
zMPSE;63|4syZdn`+ifvBiz+@mI9MF#qUxKHqOxewBG55;puW<JYip%J_p#dB+ebu3
zzO>nvd3o87`~Uy7J2ta%MrBKZ7cICw|2|D8a?$sV(|#OFZRkzr0j*T(D+ISAe{F}Z
z%mC$M(2^$^X?Jny_J6u&evaT-zGLA2B4|SO=&^<Wo0i_$xZ48M7^(dHY+?2HcUArQ
zx3}@W-~ZoENLbi+kI$ZVe)&aSQ?<H|uMS(=)y^+Jt6*Z~&272Tpp`Jj>E{?2zP-80
zEH5v=WZAMq=g;#eCMI^x57*zs$}M)__HAj<(%#jpwd3l3rZOA=Z5ViZN))tEi(5=b
zU{6rbnl(BpDJctzo}RjOAGFi-)6>(S^9AGfRvo;1H}-*3;hMF)^Y;~hes)$VR_BT9
zr(@Fj51yT!y(oQ#YTS+m3l1D`c<Xw<qod=+Pxvya1E40kl+>!f6>o2C1+_LoM<QL1
ztL6o5ymN7BIl6D-@oU$_Ko^JZ`}s^7bYR@Nb?ZPYr$O_&{dT`Nn%Q`@J}lcQe)G=G
zV$dziclOmv+u7NHwt%0Wrt5m%$Qu+qMn*;g^78x-PKMs!yLa!$7Z;U5*J=L!^%bOU
zecWCa{n~$@K7Hc)%l~<jilV*!e@lI%{C0l%W9#?->-zouy?BM5iszvzn!zl(!s%~r
zYy?$*V)}7C2M#za&KJtQwdE!EUz?BTOhFC29&mra0u;e>79~CwIdbgc(PM^vpvhTx
zad08M>xPBvVbBt{#oeHpk>eJi3L9KiZv^)mbaZujFJ8O|Dp;bTq*5ZUS?YNTg{_HD
z%$REtzAnbm&8_Xx$DSUZn7vh3Te{C2U%h@`*NYb!Jkn-7W@ctq$3Y$J7cVkEdp(-2
zb#6^Q&iCcTMP}dGW=Ef#oc!_S^7&c)pxV>V&+o^x+4(x3SiVGU&3brcWpKof0>wv<
z9u>U1WBK-dds`dm_Bf5`ZEGG(O#&UT0~!YG6jo=jsjSVswnlPY%uXhT8OG^+W$*8;
zEf$pXzPKjRIOoO&#>MXadIg~UVXMQ|I=#NOmQ_bM|KFdVpbGcl%a@rG*K4+YIK;}j
zHhR0?7ZxQYrEbNO|Nl%E1r-2FM%HCzWuVJ5@6~>fWdI$nvuX3@jrITQ82s0*vd+C_
za%X3;`vWf{ajmIblT;QKK0el3W!$gg+0oNua?t4W<2P@5E-rQl-D}4%@6QBn9UUG{
zPR@ej;^z7D<&BJtK*Q+=z31Cc^=bv};F=m9XZY*J=jZ2>&(E_xar(6JL8H%~uE*Dd
zMgT49{#c|$wyAjDGGA-+H{WxT&ZnI_YknGm7D%68Ak^0D?0WE+rp&iqJ@7aXXzlol
z8|EP);IjBd(qj=m&{Bu?uC88Z*Q3WkwJ<~>4`_SnpTB=Uet75%8jKLt3eor=0Wx0i
zzSdN(z`(#4mzVe7dn{k`ff2MHe0TYK(0J9xjT<YT&n^G(>-GBNBOQXbu7f&0prh+8
zN?(a2B_%z0|6adh<;%*7iUa4)@qvy^2?`E=_~c2;j~^93e*9oy0F4<h^`0K}<|wzv
z{#mBkNgo~@<lyFJW&mvkR(9_@!f*el!L3&cbd4rx$86c#TdEZ+U&`86iR9ki*1CSZ
zep7QZX!S0r@QK-31d4gkAsou?eV|7BqUE#Zw70Vd1qBtny=A)R%O&rE!a~ggL4D6j
zA1?dbb4F?OtzWOdY11a~2HL&V;#0N5uk8~{PfJ^rc(^U&(h^RyoEr*Nt4`{~?~`e4
zY}5!}H|K>WsJgeg2b*%%h~H;3Y4T)7hRDcB&;lAY-&sp+^Kx^0!4pnr-174DK!-O>
znIf|1>$T_=5gQl1@H}*4Q_uan-@N<(ew%&qc+{)eRSoL-7Yd4sF4gVHy=?~CDO39D
z3L^t(J+plMpN%Uj)wWlE&wF!k@9uzp-8ZrtaVGM$Uj#vevAu50{{H?~*2PNiE_>TF
zd$u%aq+zjpzmlGw-xnXnAIqLDI(h1plbaixR`@!ds;&TVQm{D;%Ke~qs}|rU`Na)|
zH_TlR9;<8vW&Y&~kliXdpt52^VOLWxsB*UeR{)Q1ShUrCILN*tYO5A#dz)LYROdY9
zn3R+y-@b-UQt6R2c6(m^BN()}c5n4}0U4Q`SDk5!3JMJT@^(jBIE6viWW0Udt#kU8
zbxri6lg}9@OqkGc-u}N#!@uiywL(`ZsHz^lviZ!tmzS4=78$>Ik<o2q`TyKpYfyWt
zZcpj!FwiN{xwp5mGJp=r5EK+_y4HDhPh~M^o%rE){_Fdm^+_7DF@P?}$i2NS^2y2P
z2PShb4Otz=3+^T#ebdt3z8KV>xwm)sx6f*dij1C~o}hFCTD+HfO5~unZ#L-gL(?pg
zT_rD>wnp`WPCh$!%<YQ~Xc$-sJ`4<6spQ%%wy^H+uNymy)i-V43|au4-9O*HUheAZ
zaPb`hdzN}nPx|!a<gL|(pu<V+?Cd;zeOq_$woW@Yr*mKJZ?3pZsh>Z8E>fQ&0ZMrP
zHoU*Lw;D9-kalj)O51s}XLsMZ6BGE^r)$1>E2yp3($@B9Zuz~7`|hm>(E=@#;TG3(
zSs%C8AnlBVi@Q5_+^;{pG8P+7fHtD7iP-qaa*d(?a=*DwIXOCO)~*$lkmz9Jl>)VQ
zLCgK?{(cQ-aM+r4RX|Rz?_e`KcbqmGsJnK~_)lCYsHXU{M^nb^oH2N0scmCES9|Yg
zp8esXeA4dX_7EOOd0!$lLA?)cJ$&rq(evQdR%IU_xt^J6+^#<VzrDJ;`krsMvKbn*
z!`CgS`ud7>U%L0C7NgWt56+t3Khhzn>~hA0o0*Nr!NY^YZ;r*n+T3-atHoxS<#J_b
zpRV1#ckbM|2f2A;_ti*>YK0g)RQg={_Lgaei4<roq~HEugNo+|(5$65hr7G`+g8q^
zq9Rak2JPFa-c$1OQpJxC3s+PgDt&Q*QCu(Pfd2kJP2A#o3ikH$pz+=IcJ>ghsV^!I
z$yk^9d|}yqlv`Y6OX_K{3=^rE|9`*V*pexHYN|GSeSQ6kt66W4>VcXH`xAH8E31KO
z1}#TW|GZDu8g!ox!@QWSzhClme*W}HKw28KadDz>Yt-&C-8Nq7HaXj>1J|#MgA%CR
z>X4N}pefB2D>S+*gZV|{et&ywSpTmERPg@({@%T=&aUdqi-orTp3kp;6*F}v=uXgE
z*Y9siJ<Y^mWMs7ExOLf^48wBeo4d>NC%)H9@+?>W`EvRE3(I_^L8q}Y7*u})5995v
z`U+Y#09wm*=T3}_Wf5ptX+^|FCD82<6<c3|M~FdNj6nN~&Tjx6nIQo_AOkcTwD3^^
zXlW^Eqp}Pro<aMJ+Pj*2lW&~X-{14)OUXs!Gj5>M7nl3XGk|Wl1f2t3_VyNMT<X3x
zYuAFRU6br<K3_yOgN~R39d?s^yid14M^%;e^fX=P<$iNnbd32SYX@CJLPYrF?RX-m
zfqL^#PfuT*eSO`En4OzmbUK-2U*iGYjsjZpy<>+(N@^;ok$LN}xL(YLAG>3`C$%i|
zoxLdY^0GzC12_+Ii@$hvZLRdK(${Tg&iH^9Q%Uu*fo?c3zhA?go}LbBOdmXWP^>)3
zPEhdTXV@-JuZCTvuOHpnS^VSkdHaViUT}nmhriu;=8O-hoA&PAyGLwXX4T(vKqH0H
z=6Of%?k+FAcZHb&)Ou-R<z`u{Tx?eS%m=h4SibIuVopxZho8^qA3l4Q_rT=U2KC?X
zmfzAoF2vZdd9yL7rm)$mwSDqrVbI9m+q-pncXlKi=AYYJ^t9^*XPT~(64TXHp@+Y{
zy&bsJOBB??addP9EiQQU_;KJeA4!G-@%4XOpPilk__Y51Ej!Hhm~&*3Z&-xLyaCO0
zgR<*kP**#@C;2gGq7ON0LA`QV)Jlj63O0h~r!6cZp8pnQ{Qd2%u<gM$pnZXtm-#xk
z^T{$eR3B6<FE6*Svf_$Mw^LG5y0E9RxT2~Gv@~;)ilUvJ96O&3__(}1du&?T+q>sw
z23cBK-q=;Dy=c**4aLv>PHgJwleJb-Qeu*?|6_Qs{(o)v@85^)K^qojtx6oG>%}rK
zDF5%@`<t)p(ZBx||86;p2#5%7XyoNSCS-c;h>(F`^&3_LsogG)y-&0AFG?hZ99gmP
zh!Bfl_LK!lzKfE4O|nAXbh0wCicZ|M-~LBs+F@Cp72hrQTu)XrzW2`R^E{qIlXu@e
z|NQg$z~z3j44`}H4jnr5;i9{Ir%d1u?eKM={T84p%aq7-W%oj)1E!^dlFY-04|kNl
z7Gqf8)XD`qda~-vi^NO4%mojbV%Mx$^Wf=IR(*Yao0=a23l}cr;Nv^C{eE3HXvx63
zb?ZKS`v%GsH`-iWTz(#5hwO9b0^M6M*ZlpB8#glSeau2Zvs=&S*RT7&XYXFyM~@!y
zSWJxgA7>iD>p5vd^6@@%liot@&{ZO!ZpV=$E)h{tiwYhdx>Y=L=FA)W>-V30qcd^V
ztS(TM`F`(rxi(&DHig%1Ua|T6!dC=<Zrlm`^WR8RH)@MRN{R~T=5Gej>6m~1{!L6v
z17!-(UOzcGxu)eR$)MZ2L5oG-@A=HfknrltO3-mXZT#}<_GU^lym|A+AmIQ5=+@CI
zD-MBHc0ShFSa>DzKA3zwAu30v^oF@*GDH+gLPRalM4#mR|M$0`punM5$`rIQ_3+J`
zl4)saUD@F6^9>6)d7n>@uVb9>)%5fG>pLq8|K8Tq(&E~<apSG)ot>Qp#l_AkDJpmF
z-evVmi^;mOq7k&E3e-6K|L?m!LnOaAGw9gg4LLWB-agV?_F(gQyTjXZZ-4mmG8oiU
z@SdjQxIOP~z#<n;&`jfGHD4jyMS-B3&r3>7Ks(H%qoYByyw&esUS1BG+pm7VSG~Zg
zFz?QeMt}RiBJTZiSARaRoba{yl!&}T{jV>Yx3*@tE4%lBjwuw?3SpS=)%tfEuk?qz
z<@Z6i-dwwOtw~+9om>3LnRDm(po4H9zu&J1Ei*iL@Zb!iR4&kZBTx~lEF>r>>QTc0
zS-seB;=~DufPe|-MD6zO*|VuOBg?BxT)(fKU;dTte^3V?WMvTB9FH}{&(E!l`uO$d
z=jR=rorXWJCNjQ=Ie6#NrAtf7aw50q$zEF<z5MS5i4#$gKVDv54mvII)D%r-h1YG%
zd8N$~{{H$ZVUjUnMPaL?aT<@3vhu`9lbV!VyAnY6%@#alTIM&GOW}1Js2h1OxU2N>
zF<uuJ7md2Gt+}_aEy=TCXqYiW;%IN9pPwH?L($Vysk=dg5guM%MmKVfwSi|CJ9{Ua
zznQHAN*@+GlOLxfK3;Kn-$_YncaTKR98`&8=n|IEn^HQzo!?#d_EKf<N}Gm%58LIP
zCaI{Xt1kv+gX_OeY~t~pG-2Yz!~>eW-TT@dePiF=+FJPHg5r^*M-{ECq-M^X3EFM;
z^3qb*{<MPE*VZ~O^_mJQj!g3J#eA`FJA3F5Q?Io7xw1VG8<RkX;x}~m9G;-)3|fH)
zS{-tBwz+$!kg7|6iV5hvg2nFrk7noZYwYjm2Orx7+90s2L=!YJzA|`u(!)coP3opL
zdNC8q{pZ^qeSEzC<ByNYCpP7LdLJnuD7cr)t^sl?7K4hK+M&aTnbrO0we<G#YK5=k
zVd&`TIWkQ*8kBTFb0|l<M1^fuO32B{fyUn5dL$;ky)#uid_&RGzZYEsVQT@rzP!C1
zejp|3&Ynu+<DbvZw?F><etkb^lC|OGnuK-d-`?JCSpF^sv^$Pp&IWXP`h`WV+((Wc
zO}w@y^2eLa=L6Qq*<MWES2)`|AG9Ct!J|i$-ro7~@v-RYJ@$2fBxalC8l9Y7m34hx
z@2#!b+40jg0+~Ro?wy>N&YU@ukesYsVD%BS#+QYKMZwrOxG-k%#e^#>0%zFQ?^|$^
z$A4OChKbbM*W&fpN|XCF@5h{kM)6{~-_KOd`mA#1%-L8Nm-P5aU+rXTvpykdcU!Y_
z-r&??nf!Rqkz*%irPa%GWK_-is&eK`zhUueLt)Xk``Zjt+4<#I7)119B0kR2&<FK%
z&ds%cJh%K_<KDftZ{EHYeg6N~YyF(t+s>wx{gX3HVlm6T)xvN8N8s!0>+Q>zt5<z{
zv$FW3R&ddyBb*Eli`{xf))#+%R25wG<b<Hl3<J;*ftYRA#hZI7jX_N|!{lQced3xy
zEQ{UyLDxbFiixF7;$Kkwkg4?F-q%0p*Z<>;oCaEw-y>;!Y>D_j1tq1b&{=o%6+taS
zrHg9*^Lj2X_Xiz8vvK1_&@oY<`8{@ixrCFGR6+e?HUD`!RX&NJQQq|P^FZ_KGi<BP
zR6Iee%h-6OTB^RjI(Y4x*yUxu!nVr_G&MCjI5--*ySb0`NHT|qhs)ShTv%eCv9IEz
z(yObh+b>)Q2w4@v2|7}?s>%wy{1Mc<Oq%*<`%U@!KaJCLqgU<v23quTb94Ir4=$|T
zYuBzldH=%ax7+W75;15Zw@=o(t)+!UMMVYFNqBK@uQh1CtVo_kO;z>b!^7>j{)3MR
z?@9*s<t{JxXZ6?OlU7d$N1fLjX;rgxs}mn@C@e{Q{G<mQw^ra-6q0^^bwl9|i(MNE
zi;jU}*IgDI?VY`!vu;>?iPw$ZcIDsfNvV=wUtM*6e5`lt@vnc~zvKrm^EoJA|7YR%
zKRb(`8<f5ZVfItG_ULGL;rDm3pevoPt`0xGCG&E?LMK*GIiG!fo#{>1)u7Y1mif+B
zGBpkT7<Ip1|J-aPYisKpH*a>z9o9H{^eAZg%Ejt^X=i73baxv+a5?t)#6)EY`#KxY
zx)nBFsRKukx<0R8_Tu5;cF-wlpiUlW(M$dR-}0aiV(qUI&~6GXEiPrZo`&Y;<`;pT
z9UWXcp3_nzzX*W#$GS|}T=eu5sFBLS!EvGT-u3I^v(595-Q8WzYcumBXqXT*@F{Cu
zrl6_G$&iql+39chljZaC^X@k{rLy{K_<4D8ftJkI*Vlu#@q-$apo1<h?e^RQT0H_<
zIoZ+G)uiHCP*MU~&9}u`!)LCQ=)#2ycN9JCdf<6~&!JZC<fo^mg6GU4qN1cgOQuY+
zukomQPrD))59*Nc$#zYdA|kk$>-+n=9-z&pwZF?I-|c;JKPEQz;j33&Z*OmZZF7HT
zaXRSS=jnQ}Mjuj=GE8RWm`j}4wC3}&X7S_3Mn*iQ^DZVle$v+qT2*5Htrwh;`|?0h
z?)UD7`Kt|}gLhsWI~JJqc*XH!7khgbgR?d$^6PSB?%uHQ%8~hc!(vLfrlzJw)D{g;
zh6b$>k~^-EVIoygRkf(@?=Oai^z-u)K|9oqQaDzHt)2C@%5#!W(eb2Sx8?;46e_B!
zUfJxg`B~H>XDfB`<Vm)9XDmRsZi8k(3knQCwcEUT>+VYKO+MadwSU?@x9V?i7#S)m
zDm3DrKRfz$S<1IJH$k(76P4W)K<kKQ76&bM<K3}iN5b`Wu~z5HUtC}W-C!DD|2Or)
z$s@%@MTbB`7)4J!E-seneefXR?e}|IwwPF0SuF}*9|vmufi@NPySuo23DZ=mg6wuX
z6<bqdvnqW3y6<~duU=i|&KDfIF2)kH%T-yKx%~Y-(5ddHrs;AQ7Z+b#%sF||q^8u<
z(+=LhFAq8%V)krl&?w8Zv$MP9&Sw1ibXp&@`ASAcMnGPE{@a?LpPqsiV>3>cjQjZL
zsGzX$VvDrAygq-spDMSv^2^ycY)m@JV>&BvXT?V)P?z(}86T6pI}+jR<IZlA_6!OV
z3R@qiTM=}4cjafbKY#vwnfLv}hXe2K?&h_a7;$;IzqqYa;{i~PRkt?tJ9op}3!K$|
zZ7iH}!(wOh{S}9go$TwKYz)rLvY;)vGOA{N@4zMYrsT&@dO%Sg*xoxicCJ<Fr;@!Y
zo)*>L-bl|nW+AE>#In?Ty4yr0SC{^zkT{z?-||6=f6rz6zGVCY9vb`esr%d4K3VI6
z&(F^0Tvt_5QBYA~*_w6L=t0S`qo+=Bfu{REeFBYbfCA{jg9Ok;FrY&Zwq{-Rd6anb
zznw>37yq=?p{v7mLC4#DeSQ7-fktM~9)!=1U;O4;anA5tlX$odbTIylOG~*y`9JIG
zDn<s-_+di>gNutx0;qCdE&@90=*EUb=9-$C9R&yffByE(?cyTWi<{H^E2^s>FYdQ{
z^j}&@X_0vgKV+e;C`0I~5YYNH7I}I3xzFo=y;R?^V~0eA*5eOvZW@QIjS>Z2%>Clx
z;>5Hxw)FJ$i^-f{|NJZlP0)ib@OyWEKYw|7c}rW{r!+ZPBV*&l)YPTlYjSedoUGx9
zUms`t=FZOGt6kqg(@uAHmGT-){U~W)XOokgE4q8)pXlG;-U>=dX=PY#l#!J!-V+Hr
zTBM+$z~F&P(#K<|rJ(geg`1K=O)^l%JPh6z2g;bg)zWk3yaC7E6fpS(+_Wz`4ywM@
ztw9wxs7kiVne*n&n>PxclU^A1#Qp#G7ql=QbXZ#}x44*XUx9hv9Rb^>i?{aI+ozqI
z!>RE4;O`9^3|d-SU+&o!wKa=_gTvrSh1=<a2N^*v_!ASA3*X)XZLCd=esCb<#HOAt
zTTJ%e&khO>PRz^8n{<Eo?$X!G{(fE&xLD-5if5C~=?N;Fl9G~ba=sS!_V%Cx@_yZK
z-MU{d)sI^Cx;1}%eEjhB>){tlk_sO-y#XCL>~Hr|<@o*OpmCe8511iG7_c_<_w$2J
zM=pDNEAh&Tz%Efcas9ZS6DK@$A~(5wn34oqZf0sKDkdhj$lXwCs#Yjy8Fm0<5rt2+
zvA^H${u?)MN@m$C4%%N=+tS|tdQYaFt*xxId7jH;HD4B=w2FK8?t$hzK|4qUmEB(K
z1?}%Ud~vb+#<a6i%zo)MJES}7Y^%OFI5;q9g{|qBsO-Kd<KiOlnMa`Y(yPPPp8Ce9
zwYTK)F<#KYtY0M9z&jWx%SyY;g3DTPew!1X+|>(iTqDPj%-<Up>)Uz{AN#3q=2r&J
zvyhy7Q`V});|m9?)7x8HH`e|x15Kp;{r%njXqRYWX6DSdyVk|-=9+QtgI352g({ZC
zre$v;KodBdbQb5_-1Ot!?)RH&V?8FdEOPD6s-M1KP5Zj!<mANkbaruZai95icT>c7
zfBO2>H6=wwFLu|G&oy^<m0n!tE3Ff;;lP2(o#K*`npG@|&GPTrfL1%azqc3E%Whcn
z{yJzaIJojt=M&dEvCe<KUDbJ2H8s%LNIS~k%dHAu&&SWt&+O;s;_~I&#FWTsuKbSR
zs&?mW!(_H+XJ@x>*<y0Eu(-I`XO6|i6#Fd<4WNs%pPik3V|V%b7lA!ZZi_Gei+r1P
zaM>5OFZ*3xToyRD^MSSxR(*fRYi@21njqri<C|e!t_K<x1>J_H8?{Bi_La2yX(P}&
z=o2SAKx_Nr;^J0>t`=LfcJ0S6FM~njJ<?`54lXV%cE4UIzqz;fwo3ToZQHiB?cZ--
zQ&R()-D78Ge{*{~|GRhZ7#emKKTrDi=cna8m+#xEzP*tIU7OX+&c7&Nq0=q?|Dau2
zU%r&=*ts+D`MJ3<wLk37&9!a^ZF~6q?5qdq%+Wpp@NQyoR3eJvPsguFx7Q*HVIgTq
z4Lj!#s4Z4>2weXjhLQ{a{QCYqt=8x5L(@}tLARdmD#^6VSm)&9!*gnyZuf~39&f*=
z1cxs55{2GxXLbHOWWy<_anY!*tTh94PVK8*VQZuIKJ@HykBE=}t%WXqeeK}AdvVo&
zo}8Qvx>PSIIe9DpGxO|gJiE)^U)%WsbdKE9K3MsvP*_+9>iWFBy`3>-?T4Qi-Q_j!
zxfp|Pr$7AQU~}NMoJby7tC06zci->%+}H4uC;!=*nU%ZjY;9#Xr=PELzAUj{zW$G3
zU0t1rkI$8TA9YR}b%|=XrJkPlbVt&w+s}S}ehwPp2A#}s=8Vr#%gAY<u@6ROwuFm|
zT-AOrtLYZg1#M^g@Zm#_`B%{4h;@H|6%-X6I&c49rz#{7bPat+2glK@D{pUYbw1uF
z>-)}a1Gl(d!p%*oJIdZlc}>x11T9Sl?^85RKbLT7iYDj)|1)RLK79GIQ@-wp<A)=U
zHWZeCOVBIHpdk}bIVvmt9Ml1N1KP3!Y5aKQ%(=6%u;}=)%Ff=!e4r(Gkp57g5V#9e
zI?txEDSCU}!;6dEFO<&SvQp>G2hbF7SZVC(X}b46s2n?Z{kpmTb?-?n4Gj(ECcJxj
zlai7^C#f7=q_FJNrAtDMjg6q*{<+Vfqh{8x*Pmxwo%Z15i5WH(9~9#2&tJUw(bV6G
zHSqblxq{;2?f2_``xfr0`uYmwOHdD&jaN#+#zrRl`nscMW*Qroz6x=?3>ve@fsR>p
zaM^6#tuf=2*WK#x?_6JBTN@fXd(xz)dA8L_$NOaSE3_U@n=+;4#0d{jquJP4SWi#y
z!-o%`lfzzIZ29qgem!Unxc79uhaVpw->`9G<LcGgx3=YSgDS<xoJa3^c&uHqLSx77
z-H(5Mets)?l1k#iCRPuB|Kly3!k`FT=-dukG632wY@sWu4Qhv|=ie~D2_CHijYU<-
zf|{9g_9Q+|0T-XnSsM#qlqP^it3I{$f(lc6Grx0>9zO<M6Pj~#lk4;Ecf`4EXPo+;
ze93?D#SHPk0f(pT&jY2TtE<Bw|N8pcO1yM}3a6%~X45ibxjT%1ml~y>T9AK#--qwt
zuUFRH*-;4Eu#}XP#A7q_;nuvnQj=63KA&ITHgo38Rc_N%IIF+CF+5O`wD*VIobYA8
z_Rg516}E;0w4P|Dv3s?SmKGOiWk4IBY**^(X_@`ov#;}&zq@nr=H_(Q9xoS{kOv<b
zOF-SrMNCgX=P~f}hre;Vw6C^$a%5xF{HLd<udZ^gdU0VP+YC1wZEfwG`}=IK^XtyD
ztL^feYxVHM!^3JnpVbr<8G(ic&CShA-rNZMV&V4o(o%2G-Qatxzk_DY{{8*EIAUYc
zqT@nsyC-UZ4*WPhO&7FYKVVae=a)A(h3D6N>U^=WCHwk1*+q*M2?z-_frg`x^-6;V
z7eL2!sHm$ag9Zd_Dvi3t_4TSk79W7O|9`9HgQ5h~l*j|M|IJ~o$;VH4K_f(qkARiR
zLGyxoc@8M{G&UA~d3|fEcG<f-obmDTCi(YdRK2ELsGPg<|C?PE9~V7({?q#X9_0$9
z!<)BkX;JY64cpq-+FsmOTRmg;>~6W!FaEr*|9{y0eogbOt=WqsH>Xwo_dPq$_V$6v
zlJf5w{sn;=GP$?SKuZHnv#*8Bv9AAT0~)X{d3Q(h_4W1QCJP^ex=@o;9zHnOtP!$e
z!ne{qP*uU~qkgTvzI{@vB<MKot=ZQvtPa-)oqOpJ#-4X;3n!>0cwwQlVa^SMKxJtj
zalI3Br%n}RVrB-N@A`J*OyhLWEut1BF9c?p=dZKfSMf0kv>M5OzMZI{mY`r@<8jy^
za>JD?AzxlzX1~2Xzg_3_hOJv!8B|nM944uNW+fCA71h2b-T>{feei(6+uQr%Vu`tK
zy;2YV{QP`lSE=@`Et!iy&-(GB0yMP@S_=8+=V#FNTW0@EnJzKiu7(B%9w`%#FB*q*
zBR8>t?#H>f*gY{nf4%L#?CW|Z@9)WGW@g@+dPX~ZUC)XY8b?c)scC9*R)2qY^y=zx
z-zxJ-o72yOCSh)twSW5l9kg^wvB2n~*EAhYd3pJxXT|pa{U#0SN*g90OZfNaC)09c
zIdEh17i>fslp9+?JxTTQH_~^(jnpfNuxtvI0CyU}I-nAZXK&qVT2oW=<=w9ASD-@M
zF!>m0bx+r0P?N2Rl^e8*%&?jB!;_Q3Id^x79z1vubOjb@neN(X^NOmfLub$WeyMOf
zeDR_nXoJSHv$I|MlfGQKbO|(rXp(is<9+k5WslzP|L=CVjTf{+r{w*;*xv%betv!q
zx_WYoMj+GietGv+E>RYLuVY8<-<Q`8TXSHdvU|X)5Y3~Yt0NaiZcdXh%aJ(NE3Ka4
zbok*R)}7kn>tv4gNG`7MfBm@M{upRNvZaOP==+zTBlAy8RQ}0eB`6qJcM{yfN%^AY
zJ4?lTl1jg{x!=C}|NFjG`1thL)cvUd9cX=OiYAk~iA}GYa{i4Cj$b6)Gz|>{^RBFz
zn3I^O`2Wx6^Ec1^|9sxQs8`DLiBl`r$?R)u4F5E^EvfwcY}5St^IsVD96Byvud_Y#
zvRk2!uC8xcNy(J8Yt}s3ntlD$^YinkgEqVD3|Q#&X+_{-7GJMpOT4G+6@7ek^yysd
z@>8Cko}X@RPJdeU_0`F3+qM;DWvzPgvE@>R$){gmUyB}3N=i!cob=?whXTi7NqKNP
z^e?Dikw4{z#T0pPOJ-;C{TGlEAoxI8-}&c3P;Ue@D3}M9f3*SB(fnd%VPSFNe(m?U
zFARHvDk^s5q@}5auZxMCXP!TAPx5iT%Hw^qpY~LKesXH6_UW{=v?3RmmKTPtJL>=M
z+mmroX=mVKw@oUZMK?F4f=<3Zt?oZh#CBG}wQJWteZOC?U&XU{@{}nm)>c-hK0iM%
zZrgQnSMBd@cQ&W{-#m57YnqDZG!@Tnn>J0V{`yMwKIrs`3b)rcHYS5s<mguMD4v?G
zuV4T9ta;V>-@kvKetLSk`2&}fGf~^~bj`D_c$_<N0(@xq-QDWZ5fLZWMsGh?_I8S9
z@RL=ctEH-3l#~{2cT>E`e?S<tR6Ot<=y<gC@%wXDmsnd_J$k)<Kj^Xu(DK})?_~0=
zfBp~OzWfcSrBnO++rrY<*Fa--X8HF($5%2lELyx6d?JdP8e3vw;)^>wH$TWc8nq=u
z5Hwu@T4!JX|DQ(4iIRF>(2yY;zuX#&vJVd&L0exgE%5{`?`2q!c6OFU^*0^RfRRqj
zj({U8+#a5stPX0X%h^^f`TRSuTTGY5C$$2!NWZ_I->T#V1H+2o<$Pj#F&yRP<)C%?
zpd(*w7Ful5Ieg}fPvM)R+1%XRg36Mrs0pC*@UfGJAd&s87df(#B+Ni#N#G;{N(GgN
zk6k=_`?fUbAd>$6{uhBg=ic1h44T*b^Xv6`ji@avzEv#un+v+q08~&Lr=N3~ZI;X8
zr|GsbXz7FJ&)Mzm?LqTDpay$EfdLZ}(}%0!@ri$ad|c!%a_sC`-sS%D#cbOyZrrq~
zN#}HzY?<fDn>QsFE?fv|Zrt5n&d88@dYb9adneES`}^B4_m;`zKl_BGrMs_O3EBHR
zI5=2PS~~kcCs*H!6&j#X8nv&b#)XeucI@80xbX3@j4LYyzrDK)QrshDs&#wo?y|Rs
zK=VuqUZ5nv%smgZA#DW%sJA0!p10<E&EsRe8w(%1G5fh3J9q3D+r)_zLAM}n&%3*!
z@^hMnrRBlHhnY{FJjub&-wrwq&#?9N{r&bPQoNw;S@H4lQ?$eNZnL*cQhE61=H@0f
zlQ}<rR9IMBYxljqzh8cm3TP==7kDw(w!FJpCqDML)zsL4I>frs+Z2?QnH{eAwoOve
z{P*Y4o!jru&9w$?#(fmgD`l#1+DJ%9h{ZS629!qb?5~gi{p;rD^a(1QiHV7z^8!S!
zdrfM&xY%8~3bcH9N;s%}3(E13tZWGy6siT~^OLfm91m*pc7g_w{LX<31yExcGWbw*
zZEtnCj9raH?yW5cCn!2Uc=KjX?m|fh&>^V}FOOK2zms`(Ztm)eAAedGxpptA|Nn1>
zN#>-6lRe%}PE10=!l0Y#?GktrUS3)XngILr_b=!QwHvo?b;+H~03Cc4y*=+~llV@J
zkQD-6Q?*(TwQ^_IhY7yCw7`*>g@pxlU-F93)zco`nP2~}6SOHO=SIMVl4EB@#PxoB
zILr?k^Z=d2b9%ad`{vEY`+mQ(-jaJetne=AYMFn3Dtn~O{VptVadBalmxpc}WtcN(
zPQi-{iagS0KF@z1Zs$LI^5n?_!JWtX)r!(`b9?tze_!M~+YB`7uA`%qkeAoT%+9yK
zv6*erabvEsvNDaxO)8*G=T#yPy{2j{-EmNe0n`AAh>U!AxBPynjDE}x11@pBoD&~=
zjy*Wo4B9R9<JYf6m7kw!1TJcMF|p;;nKM^*TZg2jE$f)r;{`d4akK3If4|>vmNh;q
zJ)P04&kj5{Q*>+}WN0Wb2{eW`+4x&;9aI9^jf6>nhWtRYIYp3B-owXEMs7|!yQRLb
zr{_%By(#h+wr|*Q;BY(t*Ln3nJ}Bzw=<rxf{0Q3N3R<-%B-HfcMaGU@yOMr<c=+MV
z7ni4}rn>g02dH{YIdRQ=<;s;aEDDv>{N`|EXTQ$bAMP;;v}(|~FH_{#x3}F3o!b|M
zt_}nB;kClntSCO%WL5f#V}{?J;^*f;XWW8T;!T<~X+!z@xE;H9E9>d;&9DDw>DDK+
z^2a=15eW$nb8~ah3M$>`Z7x?=g)%aLPWGtzVE`&!k9Lc5&zscKxqZ9&p1pfTyAA(N
z-@V)V(xpp0Hj;vZ7jL)1`mqdue|<gt<>h725q}pKyD#>dsx?7{^Ww#e5nD0@4;?yW
zQ2fm2VzSho6@iNlDnF%!g7QZ8^>uq6cJ>^eX`C*y{`r}i&7k%92b<YJn|(~Ae79x$
z6t<Q#Sd_e&@ItW1t(lE?L*890&?LQ?nHlKh9?;z$pb3LkF3tOPJ4#+oI(g4$NBR3W
z&;a<qfB!(^Rd-~)wo9Amb;vDrNO%mYV0(KP^Zj-M_b@@jM0wy$`6U@77uXIPqm`9*
zHwO>i{@MuYxUPT=8JxU1%QV}iKVi$AyLUkc<(lQ*T9A2pSywS=o&BSu-4}P2W;<S%
zyf@dn9Mlz<FhKxx26{nJk<<HodqLgdU8S$P<osuRdwaXMQFbb5X*>hyy#90ZUoPA8
z;Ap3?`iF<@@`vu-lLH-z5)d%q+nl|7ZQtG5+5GhM^v{eXL7=O3KnFyenQ6=}C@6TV
zKK$IdbD)R^rH%CT^o`Dw0)M?fuNyf{P+FSX+In}+es=*u!N7aqlb+f^=b<Pqnv<H6
zlJMX_BdB+#;@RZ3m~p~Z?M|K3pn5NCecW2xJT4O{-dESwb{9Q8wep{}b@{uRW?@PG
zUbn@cdqW+*ORrn@t5IANbiE5`F-}fyZs6uL-#K=*Qs?K{9^ROI{KLKK_nPZU3kw@}
z@3szG7o(XGRS3GSGx-?Lj~_oe<c?}Q`TCr1|NRT~8$rXbFODBu_$T2pB$O|#PJlLq
zKt&@YN*0D61b2kwrQ1I>gT@BhKfONIE1hv`i)K=CGHBWn)XQK1b+<qpJNo+iKnn-8
z!q#Y%1uz>L8#lMMvfkR7&F=5-za`_M(slOrZ{NJ(F_9HzSsk`E=<9}m2O61q4SEYR
zudWgW-LLlect7a&Iq0MkXahXM48vqLP~&5A<Qz?X&@^S{<z*Xt7ykdweyT6t+{@6=
zP$PPqj*_zS*8Alh9UU6~cg*1iw__MV7ddXtzMgbuh9PKn1vJjXAgUGOu)FMSz;Zv?
zgTh^gWp5%Xs;au=4!<Y}{l4cUc;$n@p~Hs@UtiN@i2T0|)V9#q*Pk(SCg;2h2B67k
zW_G@Wb8{?r)cv&rP4aC_KAyIF;qwa%oi}XS<kT-`%i^mwZToifZMnCP&93?<U*5hb
z{3tjGrKR0%znz85Fni_5REdHIV0LXRypjx>Zbl04{@%qP#jxq<De<6w#LnX9pr(SN
zk`mLxg$o%r?R);?=g)_r2|*cISyul{i%mMpmX?yy+w+cITN@qvSJv)^`+u{H3knyN
zCDuMZ-k*GKjwQ&6MMXv1K7(%PDStn&;p7ns<FuYv+5U4ZKC-E6M*MhSxtHtRWiJ<(
zFTV=d!F_xstqCSlyiH9_6~X*_CmlKBQc+Ry;K|9!JpREKU~2(3Y~1Mh^wd<wl)F7Y
ze|$^^9d%Lt?TzEcq@$n?$)gt+7fV<csmRF4fUYL9u(p1^=jZCWzrUE4DJMUA{d)HD
z*Q%fkEDlJ|YU2_z<J+tCjrS?Lbo-U0#{qR43txn8EYz^SVX;I^y8Tmkuk-q@UQqfx
zdH3`4^BYr7i_NhtX6x+iJaOhs$eigaoU6mvi<!tucF#0UfA;ge&wRVTygo^Hnwp!7
zZS*~bbaZqcJbBWxtMv7uJ9q9lOrB_{9k<6K?d&X8dwcsM$B!RAc+hbp^RG3Ln*}5!
zI&R#EI5=6V&290?%U>s{%zV=%etmuXanNxMe}9$QRDIF7?R;dCilU88%!QJ+sn=V%
z`(&-tHpQF&KPn4aa}}o#TXoR@8l<)V|HnA*-X2bc?ABMH;;ZcKtt58g2J^2MUW3|;
zpoN|s92^H89Bkey-?nV&(!{H)LP1+eHzXbwkdV-*2r?4;|1Tlnde-SpI<vpDH-4Gq
zwzyHnb5(e#+1K^b;M7tT`bPQ`zZu`kqsIdKYZo6mwlMrCIERBqp}vAgJgP!-WKQv$
z`JKzVyNlJ_-2Bd-O5ttWwt4vYw9K6=D<mW|Vd6x_>gwu<=xESD(;|0OErGZ#MiXky
zZ`R9CSK-{YZQBf+%A$F4vvghr1qE%W{rycwd=F@QC#$deInXioTeg_USe0npW`1$<
z<jEDWyUjowQr1Rq?~=Q!@aeO0<n>2J`MWP%2&ky8cAlgXvMxpvJcx34WAbqxo0$?Z
zI~4xIh7S*kySTVasfP~ptzhu*^gMWBq4USb;FFTyO83m1Idg&vXIxwyXsHU9xSmc$
z(BX%^wqLBKXovIN-CcftcXaRi_4=Uh$?o#^QWZu<VXv>P4K9t{U-$Rk2bE)uyPaRA
zXJ&GGP6EwpgJyece}9Yl7|#ywC_sY~G#F|Rs+7!kA(EpPxNo=<Tz$bp`N^8}^Yd=(
zueVoHQVQ5vlxksRm2`h!?T-h|{2MAhCV^&DKucJzt_pSS|8<O4!hm6tO5)KjQ3GS+
z!wrngA%FKewQ?Q2cTWy<BK+#Gwf8<uc?6nIto{A%=<fIXw5voGfBXG@fAWC_#tmDy
zw)Xe)uL@bo!~i-j<kC`aP-7Fctj^HT5LAtWnq@k%yF{GZ`9y7g&MyD`Eq6=SRj%vn
zVw-z=c|oIbkB)YO4itl2T@n@+wxjm<wikiC?@mlqE+{W||NZUl#pV9;pw<7NO$Tv%
zEdKocD<~`5yV$*d5$H%xcU9$}ty!TF(b38_HZrNFr-|D36@a1-dFaB4&BeuKi5$HB
z>DDXNdbC>{bZv~XdtXa;H@Au>=yYJv{zTB+<Gy|SBDQ2qd=bd|?AqGsf`WpEsZ*!E
z2wcIidBcVSpu>3{KVJO#&!wf_pn)Ts`hRy0OcoU7xg+bfU)_Hm=on|vTF6FbcF@3V
z-rZdXFJBhU%gbAI+*m3HG_Uw&)eUo(_2AV4&@rAbt8Q4pMZkkQ5Rv(N_u97c%lF;f
zoc{RX;r0#Nx4VP37dXCRWM)%PQ)7Gh@L`jB?Pt))X|G%J>FN51@7$3Q)egJzE@JNF
zo*tef$B%=?i$SwFYCba(8Zvp`yUOq0wd>IB+tQ%pgN}BIy7s4*u<^-s?En8yy88RO
zvt@qMQY$Jd7S#Ow1WM0F#>O8Hvde>3XgohRSJ+@};@5X~K}Rn*R#aH53SGS{_5*0N
z3)IX59r9KC``f{zM_s?HaC&oZuQX`M-`eQy3=Y44uh_iV7<4erwYAaQ^CtB4E?ug+
z@9($hy}3S1PH#>>AFwh=wMX7w4zw-%MPWxr$2~82h6DNf_qVrS*QMRto)5Z`O+ioZ
z+=0oG{XIQAptWM4@^G<x|E9Yx>YhT&{N`$9SQ&+F&AQq&d9pBQ@6+d+*=D&PzTdBZ
ze5jS1ZC=lcga_{eUL84dB;oO~UQkS(oU9I7PYg<A^XARVxUit{#m5%Vs;pk;%A@-f
zt4hK1hPyWAUrBr%5Vx_gBMvn62=0`Zf>v$h$Sk^k{?sWh&<uk`fx@NBmjjo02)4Ag
zf;RLsG=OfidUIo=hmVhl&B{V=fB)kT4mKA)IKcS!@Z$X0tHakP9d6^jv7=B~FMc17
z=cEf;GJ`?aJG=MGX+&;X@<Ol|bPVUdKc7y^h<nepDg~W$&&U9p>jkaJd-5d3xlgkN
zlumf1+w}MU33}cn{`dEH_nI1;vUhhhD}oA*jExKb{3rz7y9r$oI9bg%U`2r9#l@07
zS679G>i+wfKS|}`r>Cd$Gn5`*-H_<KCI3F?G#LR~E>VNNzCKX%M_eDYs>|7D`908<
z><+FCTeg^(WL|Q4|MUC(`uj`lH-Hv$?J9lUR{!s(`}=pgdseoWeEj(FV27acg>|vk
zpfgFXt_o#l0G(XbEw1mDlA<zACsL`xODOX|1LFi0PS6dDGiOS&@kmT~eSadj5;Z$e
z^2oO0gTrp?kbXJa9oAFimU@9NG5GW6Pr=(;rl85ng9i_SYOL`1+E(zAnLr6MNEiBz
zbWk&>L)~Wu%24JzlOG4vZ7B5M1xvr$0BYGk=>u2eil#R#DuegcRQ~yV-kzbssg-MC
z%+8{YuC7aV4Rs$Mxkf}pbjWOU0CkXmeR=u$nq3VacwNJnmzND|f0ckLf6z_M%Y0`)
zc>EZ2epN+9#evhOx#wDyHZ5Jc^hIGSs8Lr^vgO`q(Eh-xs$Ji<wzjsO{3Bhx@wFbq
zjT<){CaHif)U5vZ_xpX&0rxJw=^`dlytB-5yO#OR?vitzajaK5y_(@KXgBQ9Zt=ji
zQKq0quS3}X*queJrrFnA?(Qme?a{geTHO!2LH*4Q!S{Q=&wEkW^5_t2<>jr};W>AA
zO$B$?_A1sum)SCW`0(MtJlkr6njZyopO?SC*L!Vkv~-0Q=)}$DCr?sx?(dU5JKMZ{
z?b@|3Ca!1z?b~f;=LcPr^5*7d_rh~`?#NtT=6m_~`#zt;jm+!|E@n)aIg``a*jUD*
zK;b%n<)>eY0gh?O$)KLy!ub7lU3V9Tt&cl<ci|Tg4-bc=B&B&al}wS-e1ElxHuO%G
zHsgEB{=4l;0=TPP4qEVt7HgH@*}=)yAcfNHAceiVcUyyoyI)>j&V1rl;}6h5IE&r;
zC(NAL37QuLT^I2{le_KO+UVJ5&VT>)^)={pgc<hrc6_o{Ee{?ffX2c>yT!I{HMJ^#
z#{)V}r=p@m?&<^3QLyj#{pJHLt!rRp4%ktU$N;)q0W|-$)O-3O_kOusulwcg`NYM=
z10PFG*}U2K-JPAx3a_7+-Q1K4+OMS-yNlsO)q)!#a>xF!S9b4908R6ky_Ev_Sz1~;
zWMvSmoSdB6cY~^cfC-Pjf=>IHYh4bS(z^Y9N=F9=XxjPRot<qm7c)RrXjxfV#+@C8
zpaqVfo}LB|DfX&(a`5tsnk;-+@UUsm%iG)aLDOZR1I12EPy}tSJNLcd)s>aX306u<
zi<<l=ebwFR1s+O21U~c7%FIm6w)z{W`m_80rx@fQ1_4>wUXZuV^X@ogWUTmh)-^ae
zF|iSJepR>rK2UiOP*_-aV|)JmGS=^0qFN6Y_uDn?-Mja}$que%_3!yaWo2_O?RI92
z)c()T&JJ4VeevSOg3{8~<;&G=Y;8fO%3ORbDI%?&f5YO77N{DO2aSGBZmpeM4(gA9
ziqd{iKm6pOV<)Z6`1W#{@m+iky2oLTO{EZMtHeYl*AIVw7WYUPGDUC8X`DGz5)@TO
zyT!pXb?%^Ts!ZHsItOMNr%#wMgClnPg!GgYju~fuELpk~)NujL;LQVHi6LTLJG%=s
z5tMsdY`Ndurq)*0Q&Y9s89)mY=h@fyeZN=DFDNLuVf*&upP!$9`1o;i*xIOrr%!u-
zc#?nb!^6XcpPqQmu`1<aFi1Tm0y+=o!GXpTXU>4m*##XTDi50bUeYEkEZlr=Z}sEp
z@pTt}{&k(CvSa5?MHLkmK0ZDsHIess%kR5_25YOo<;;Dq?mw?5c6S+Qq>^o(&z?(5
zy;n!2Jb!n0H`}Ze6`;$ee|)*@FDNCos{CQo*Voq<Cm-)?QWNoBd@<wyn%CJL(^5Sq
z9XY0`q;yLC9b~C>O3RzKZ#VCiR6A|-@6TudH#asa-!5cW5xIGpXWb1}20uSPEBhS^
zL8tHCliOSUUCfqkFDvK(I{SY=nCH!#x5!<vYqxXi-4a0|p{5DwqZyf(wEZ_1eroG=
zUf)#fyk1yZom;xScQN;GwfEq-wfJJSv2YV~wd<!okg{Iq^^;ec`~Cd%G;m){<y+8z
zIOwRS)nRLeET$IT*p$j$_3cgPEYs{o<?ruBY|D|fv9(n^Z3N2Tt3p>VDt>-$(Qy;5
zl`B_*&SYw8ZU!xNXK+{<wDbs{s>jJms-SEKx&;3GJlk7GgQB)%F!J;BgD0vU%x`UN
z^|Z~gO+3URV_zo&T4))xgafoPx&Gfzc1K4?17l<7^Yd&s7Cdyim@MT}Rb_Q+dw&1@
z`v0=EzrVTO-&YGd1{~BOd3kxcMg2dUYwP3t7c5W!osQ<-FL!p^?yZ_Tik^D)b@NzS
zSb(mNV4HKI0yHfAg~KiT)s>YJmPIMs+RrmC$i2M{RFF>54EFiP_(fDZ?8&YQMnOTr
zr}E{H@lhiu<Fqp;uFp=oyxhN@`Le`*Py^!MpPv?$pO&0l7vlG-vZ@NS^&50?GGoeJ
zneX54*Do%4c}XK?$A$+lS1g!qoX)q*cXryO)z6B`HB^m_jUyr=7R2r@1C1<pi|H2q
zy_uJup1$Dakwnl;bNiK~`xj;(JC^u(&w*nn`@k77sJquWUrM^Y_cN0;Xu;#XjfEb%
zW_)`ym))_LvKh2C_|6>}&`c)ioOO41cj&?%&=CQ%Ofs43>+5TNy<EP?UDRn>DrgDO
z!Gi}uCzJ>Y3nwNgH-mPO-o7pU?%lgC*|1IzO$`l>`E|cE>wY|B|MLER{QFYS^dIP?
zND+~gN!?4YtP16R_UxHO(G!j}Yu1Q7pEPL_=wdttU0q&ry%+%#MM-6EZ|^g+&H3x<
z>a5P|M{VH{R`+u$D%#YjuB@b_6np^O6Yl8fxzHnN?9v~wz^3vO%e8CQRs=2Os`~zp
zH$DA%&gv(S(R%J#6M9Y_>y^H^(3$;huPwj49r*MRNlDJ~^74b11x0o4$a>jFPMbJq
zPS4ut?Mbh%tzGr6PxB7Xv12EtL7m=xidB2TleU|Z?>~_Rk01!_jRSYoZf-0D<%29x
z3vzwr<}}AiDn9dUB&B-UHm99E_4U2Sq?VPz%cT;m9v6Ll<O({l36v-oIz?{pU%qrH
zBWQIThrGOe&EK!r)xI<Q>J(N7ooeDc+e}eSjjfeSw5h$Feb3gq+WgPJUI6S+E;
zEK!MwikkJtiFLMlKIrbXqM9Ev40gZY7_W)g$ds6vsP>cL*O{5d7gvYtUs(~zJiqpv
z<SJNy4m8N{{G4n{TN~HBpgmWvgxJ*mk(fDi=FM}KR#sdyJaojx#n;5{7HekbzqYgB
z;H|CMzD16XN=iybJkUW07uI_>HYRVakK2^ec`mymnE$EEwA72r0-_#IPfx%8j?Xmp
zl*rL{0sQiISALe?`*wF>oWaw(^Im*Sd<+^06nH8RTKmAamk(Ms`~hDeyYPA=q%fIM
zZ=80fLB(^1K_U~ExZav9LDAq^hP$UuakX-bvoYMbb!(BwM5P_&@8^B1SsApn;PElu
zz{iqzwq#xg4bOs3Et!@II$33gRjC%}2rnbqHQrZOg)Y39QSk5(tB6(zN9gLXtN-pT
z=vVRFQS)<Cqne4{{{R21L3@^*+xZ^;{QUgJ?s9$5Xt20=J9GsOc(vRz$3GvB%S#v}
zG_1<Ly)Cy}zV63EUjLLip!V@x>++;SEu1&Sd{>6976aY63)(9>%Wscq_O*nAO{}0J
zsK1zfy1h?fj$X_Tg>p?zP0(gE(3XiKM~>uli+fCJdB6XE+=UX*q>41GQ|r(tV>#*Z
z?386c6g3$p{}PzeabiY6xyIj$$3^$Rja>o3PVl7iVmZ)xiF|?+CBTXD6?lb^fMDmx
z`}5s*m3b}I0X2D!c8hOa|N7e6Zcr=g-o1Ms{{EoT_&`&<1x|;5eLAiG@YSoX$jxa7
zPoL%n-A-XUDG<~=QSrQFSMu+XX{xxWC}?D7ie9V~=u+ZcrLVU<fAjXOptN-N)6>&u
zpJ9GcSXfw4Ru)#ecJgH5M~@!e``~hHb?)tL8Mn9T{`>h{9(0BiL%>2ORtrl@&Urp-
z<m-Mgg3jz|m#^!{ySodtgGa(JiRH}Mvw|WbEk#dHCBC?@aM5v*CT{U3Z@#^~4LYoH
zUF>c)X=!Pj+Fv3^yT#p;l9W;++vd)V-8T1eXGe#JEi{#eFo3o&zP-Kuc&D(s!f7KF
z&r9n*{d{zOSxvHkE0?HCzk^H4q>AEob)eI@?(eJp_-^<6F1e#CHi9;BC@KjxLsx6e
zzO%8gqvJ@z;}^%lE5*xmWR#SQ%3^nwfDfjs|5qcT8N@PK-T#>S{2Hd{=xC2gElZZD
zOujYo$CsCvSA?&h_rkEpFCZYGZ~e=qox<viK(_{VbvXqE30+$kyV~OZs!;8t&M)(K
zgEq-{OjKI6PB&-?$E3-V?|*PPcK+nalTYNW{%>#P76;7-b@cSO#Kg#ec4eQNYkm0c
zUD?TMzD~_-yb~r(QmXPv+)>b22f8>eCPt?2_giz&sQ`U_eK+=08iRTruH9mwK_O5>
z?}Z_FTL(O>dZf+yo}ZiRTu@*jWuDh_YN|HqbPmvw6k>WY9m&W06qS^mzRWnJs;UZF
zXVqmM8NDs1bCGK|*Swydvnzv_CnP2^GE{te!l~kUD1ZN7&_0{F*UR7Dx;o+U#EFp`
z5*lA+_sdv*VpBJ?+fx|1pOsq-wE7&>h}^#2{MVP4hvy2HfaePoO>dY_2?wX*UmFXH
zj_(WX?{&`FP^hsUTmXMb25-rb1NRg_{r0%Co72y4D17X;WXTdxeW<oO<HU`P$)ExF
zx3BqRtsY!h=nPsSbmq*N3;SxTckJBBIp@NLqN*RDp&ra-VQh2yxSE93{Sw~Y*|}lM
zmLr?f&u^NmAHGiJ-TnRg2}XrM!NH~f_W#fiuIrFs03~Tq6~)dk=aQ47vn}T)XsH-z
zHV$-XCg|W>@Z`|t2kYYYb|oHeV`MmU_AFyctuLd)$w{i98Cw=MwnNvihu`Qq*1#>E
zvOWL4UCqCr&q0j<&`~7}4LYYmjsP7Y{_|5RsJm@l{!YY3Q&2GQpvp=8X^T}sT??hf
zq04+EL5ruj#dI8MYHUFJCnP01!`4PIp4jzrfyYE84o*%%o0S%gjg6rFnV>Pc`v0?%
zlarf4cPbv~5M)}eoV@5_26z+0i4!L(oG%AB9#}8=cZc<qy72XJN85O%L17H)=TA~u
zn0a{_XfsH^oNd6S6wiywQmmjsOp7IK^<jZ^A6|n_Zmk1P!d*#xJVEMDr0dUv>p_b`
z!4Y~au)Wtg>qENeQ}+FNSEMZp6#C@t`#wKE&wQe)V69^_+pX(IyTy+;GPCdaYzn%A
zA!1L3VV|5W=z!t3ALm+^gS%<%a*PX#o}TLH>I#ZU_X2t7>FMc@9~^83onJLgFSe_V
zSNhSz!|kBkFx&ZL19ldrUQCvX`S|FlVfHnhA3uL)N>|?BS6fhC&dzXVmMM2*V`E2e
zuc*z+#0(QDk4Z~jMMX~Y{g!@psrPiyzVIbWmo7{^+y+`+1)30wH~;$T>f!45d)q@-
zhjGrk@&Po*t{J>6;mL`K3=NB1yOk6a7@FC5nHWGLkD&3dRjz#Z++ub(*lTNRgRaDT
zaG=q{+Z!~C1sXyIbt@S_Lv4kRkAcsU1kbGtL)(s83_?Oe0h`l&85*{3HEmeKUl9kI
z^arh+N-;~`Q1`d$$IqYONcsBJwO7iNfua8IS8*n0=7-Opw?8`Cy*U5=z9x0m<bn?m
z94{&dFcv>P#(Pm&LiZitQqT;LLG7;+pZRvO>F4Gg1jTdaWwjqaejGS|o?lK*?!%`~
zPRsq~CS+!6R>dUV0BwDq5CxtK09^_77rajfG~$v4nM?Tvu6UmG^@95ID<M+^E6P7S
zaIC1V&W>kiXMYS@v9}?S8FbW8$?I#p#_8vde0zJF)z9<TgXQz<n!3BYA1(a!<x2^V
zlnF;#T3W>BG+rr_jD`;%3P8=O;%8?L9%|)g_0s|EIJ>wh)f+U;FjYGow1W{ePR-CT
zcdjhxO8LLPN_C>PczjsWc72JbaL&z5taWvDH_zEtf8)u%zRtB9w9-fISPQ4HOMid@
zXq58WwQHb_XESF?%E-!!KEJ&^zkkC91INpqp_|iuLATJ|y51{gdZ<fO`@+uR^pvzT
z(1C`aD?1Kw9{u_L5bJckSf{8cDe%@rc78d~y}`ak51AMW%F2$-wJv91c=qfWXhLz(
zqD5Qy7sT(YkrWdXQ*s9#<$GZVGx#XqK*k4;9yNg$a({YqlA+<!Qg6^`_T^>1%nYDC
zaNg7PTx)9foG@%%8NFRECpQ;#M$?R$Gd0hprlc$gT^;7(;c-B|{*PjYlhUH?!sYF!
zq$8(+x>GFd?8&dMtpyzg06M#3XK{K(W#z%chn>H4uz~l#w0C&$nEBlUtw#fm&VXAL
zC#AvbjluQZ<Al`IR#oq52?rV&85+*bwFVuT2s+-iVU24g=#;QKyUYEb%wW5`GI+U7
ztiGpE*_#_5+m;#X`T6-t*i?Yd&R=IMCMn6u&ksJ0F23&P(r-JaPZ#%_Yt?#sx_-Ar
zsD{42K4{<<RF=*(N`3I+#flqGtN;A?2%2GS<rZi0&#E}yCwmxl6fr+PKWKI1<;%j|
zV!BQnla78kYknVeJ(@+;mlY@9dHC!S)sK?_ZLr)?_!zoP;pqOApf1;!7Z<x&_xl_@
zHC20K$;%)YSJ#Ce6O}A#ei%e;&+Gm2rG%kj=1j>$hYo!>sXm`$-jxqlrLS7-|NjZz
zSa5Lv{yfm=?1l{nlmA$<GJpocPfk`Ze04>WA@aXHXbn!m0|!vTI6KSq!?$n8`0f8F
zR0M&BX*`wTo8`L2bOj_OSJvKL9j*@=UpP0%60|Q?OgD<f+}ylTxU2N%r_?VmE-K&V
zwRN~Q`@C({7lWJT5uF|PmWc0m{`>WMJZMZ7G}!?<JMs8&_SDnUK!XheQc_({o}^q{
zEXC?M33M;hRPFFb|Nj04H8Vk%)q^gRto{9M(Q)A>&;Tm9sR&tmoL_YO7`VYR*&MpL
z(Za>$*usp9i#$9$7$$6;{dJ*py9oF38#it!7#ap%sbJfleO(XKI|SWAFu(ra%2)Qm
zg7WhG>FMc5H~#(o-FcGA+rE|hH6ISLgJymdj~h$vE`Q%Pf4+Ry^>w_SlQzv=AG6cw
z-@o7ajFUUBZ^;Y>ZFdFTGq`-YIs<5{wS++e!=%ZRL3f1O)%?@vm$SKG=aF;D$jB&Q
zOGe<{=Z_yfO32I0JJ8t!8g>8p`~CjK9ut)q8m8$+KYDX>GiYXH-@jkkb1aLGsmR;0
zHym!~2W6zCUQ;jq+`Gf6mFt%50pE+Dt&VwjES4-;!oUDpG4Aj058Ab8Vj==++#YJ>
zX7%@UaS1696|!Xj&HD>J%{w#05Yz<o^5W_e(QE>pB7Ufq8`RTiSR-A}#LUd<uj%*k
z(b2-s&wTej&%d{)GwEoTWS)XnK;GS5;5&qWeSHneg(;C?bIg~9-t#n%kG~JjFicEL
z_b!+m1I=Eqh~IDb?EL)oH)OM}uZvaNYdu8|`{)P<cysb8{cpT04}xmd#d6Z>+`rYz
zb7W5GoADuufj3*g#MamS{S~pZNcGO0JD@|tKr0|Y7t((Fvo-s=&#UyxokdRzo}ZJw
zar^e+%a?`sR)2Q`A2pB)x{|r|_xJbOeSd$wUJtrnXZQPkt1aSo6eNo1#oU<iShDxY
zlN1Xpt5>%9UAs;G-v&+DzIc%VT10a3;>8nZ&VU9brA)I}dfR@p>=O_cZr+r7TFJ;L
zXm|4Fm8-(n%ay&q$15*CKj%5<dfmduZYFt851;=8TMKX};y}u=lUJ{bu3NWm(Q$!3
zZt*8;l8$zPhD5(@UAj~iv`=Si_I0k=ogE!7a+Oa0uRT5qwCu2htEZ)fWyZ{z2SJBi
zX*lu9SO|bd_HS*?zPP(Q|LD#O7XrS#zb_A&>z%rQ^JGM8OUr`z{dFGx{_Shm>UN3i
z&wDH7IjP|9uTsX#6E|MSFqxpDdD}Psm&c@*o}M0ao6v(3rcG<>=->d=_SN6sG`cM|
zycv2nHS*ZMzrR7px8>g6rf6s=Xl7;x+KLIf$m89+bF&5hwf0VK1<h9MQ`~yP;wN|@
zd@=YK0Y2zDg(vdhJvESn0zk`(gSvYc-&+~H{K3PAjV&!KCpPuGySqF2@-p9BpRcYC
zcR$?5D<~qOQs8yis^$miI^vC$pVL4+e9+aX|2LLDPYj%1{r|xIcrno<bC0qLGj12y
z>JrStdWQA0K+`hbMbk7rCFgx<G;#dc@!B$M)^64*Ny{GWW98CR`nAGl9e+pCryY$t
zi<%Tp{Q39c`IRGPJr>^|?1{hrv~<?{zfX7FYxkaMZv1&?zP!AAkDP7P^7)6|`{jDO
z#q}SZnQ06<Zw|EiG;VLzL(r5+pRDzicXLg%#rWiGI!;g5=l0U>Yi?!+b*DjxpYPnc
z6Esp16Ei2NqvFAVMuvvu<9(eyo>6+*+T6Lfwgmp#y?FJv_xJhv`T0Qw>75;*t|w@{
zIa6_QaZ78fqM{<>#*G^b3JV2gLtld~@b#Xia}abttouca^z?MlVL;X2-mLtv`Nz%8
z>7bJmLA&{6tV%peLe>UEL~tl8EAK0Fc5w-Dw}6bix_rI&_xE?hj0*~&_F(DjYoMd=
z85C@7Wxv0>>wJA(ET||teC0|=LC__$u&^-DYNoO`HyY2)weIe7jyiSX1ji(m#3v^v
zPB@uT@qX|3lB(wkp?|-YtoZx;`{E@_SU`(G-`?Kt>VA0z=x7BkEiTZNWScf^N=Qg(
z0PW@d^W!6Eo$O+_UKe*2-D7>uuM+kvhHiYkqFwg6WtmKs<Qt16d}T60qSk#?Hwxz^
zA742AAV|@1kfJN+Ko>bqnbPv??Cj(V3mm&%gLY7-q^Pj*O0~r8t>X02aLdfp<dd;z
zSg}F_RK7ob`V@3Qu#ehd`+pz#O>%Aol(_Wns`#h`x(Vvp+1ZEBo#RVCKhHHVP|$Cl
zP3OJ6)!KKnlarZ2TMqB+2n>iSR8m$3t=a}%8TH}Yx3;ZYO&>jal#rX-d*MO=XzUwQ
zJMG!C$HiUr*{iFoPn<a6P*+#CRJ!#<iV@?=E!_SN;bMY<;OiPLE_R=A`soA}PKJb}
zq^9@#|I6*$x35V!>)ulD>7bkmip{>hJ_7@TfHj~C$Ux`f6criy`1pMI@X)!@^XP+P
ztft<co{j|t20}tY0WmS)BMS5K@=lyQ**Jf`JQEX>$n0gHm340mAX8}`+<(7Z_Rp%l
z+rlaQ%EI$+U`$NU*VorUy$sNxC<AzxrC}1wGQYW}_}c=P`uO;Ojyn1A`*(MrQ`DP_
zi`_dqI~_wpMEc}xyVQJVfzEq1n#ltyzaD3b&g1*Ke8L0)&}5aQq~wItPeE6}_xJOI
z?x_b|*50SiW9|2L<KuwbjrS+4x=|Q%yzjGm*_^H$`Bx72Id47M=e#QEc%ZEHx%oE=
zwUUkp@>}y=6|?4B*(KZl>el1q{er^6&84reJ-o6qc!qtwT~l+j>+wrFmMl>LWesIz
zW?8F}18X8Te|We1z1H2y6DBmgyuAFe{r{i*ZG5s?8Y?3fE?oHI`u=~co|8b^x+Nqe
z9za$?gT#NmUhnEI^5|HvG-#M^(xgdRvNr4se$0DmHLoG=;$ruH&`My?a`dN9pMv(i
z?cQxY%QRcfYL*-5vdy@-I8a0FQPl3Tx1gOU5|WY!uU{7jP1nqvDY?vlK3{!({g#Z2
zP6<hcI|?1IPMSO!G%$5-ZS>)*S4AgIoaiMT$0K7QFm2kjj;=1DIa4}1R@6NLZ7UHJ
zoG7;HjdQGioXMZ+*7`zOhWlF-RxJe`sqR1DE@D$k=L?Mx|CH3!htuQhKr!?0_x}IV
zplo+zW3uAplc4)rt>zin$gWbdwY3GUqqeiN16}6|S}NiZ)hOHk;%f4K#nKIrL;7Tw
zD}iI9!=zcZ{mQ|<U`r4e6cvh>c*<mg*scA}&a<s<dwYAkvYnmW&6_ttx8%Kf`!+Bj
zpaC>>2wH5jVS|8d@Qg{5gh1IXFfb6*!Tj>&%Z9wWR&(WI7SBpeNl~z}ipq?*cKfz8
z=)N*p-x-R|ZJ?DK+~RsIn>QCvb>3)ZW+vsgtk%ohyYS14K+y3y>Fw?D9$sEf)AeF6
ztO{N2b^Y_FPZMU%;&OL)=T#R@es*Ri=oH!y|9-y*omFL?cjv$|-`NT2>FsOQ=r9}r
z9qXHUNd=VO3!*;mD0F-p6B|2m`t<fEPf|q0#17rL6O(zk`@)3)7dJO0Wo73AP#gDG
zCv^9D)Qh7lIrMERJ}`g=>^G;K1@$jWUS48lm@sQrSLo_6&~8sqE2>}4*5!!ms_lAl
zdqBG@YJR`nE@4}><%LDa`I!B6veDaeKrwXb^5u;cACp+v*t+_b2HME3%F@)-ta!b4
zyH>2XukX=sZ*PMROaVm|XejLRGGEg<0X$_gi^BW=w#A8A^I7|qg7U|HaHLd4zOi^?
zaW(Py$`09f591q!FH$!?4*BxnATy7=oeXH(M`tG|7dN-4dV*c`Hy%(HY2g&!ka1Dz
zVxZ}&J$qy}ZrlhOOe%YOt98*LCD1K`6HcapHseZ}=jm823e(ipJ$iDo`o+!Z{&VGD
zEnX!lEv>Af!SVUoSz%e%)gq#zpp#xXczBMSnQ82L{G!#bU%!6*d_G@s@=2}O``dD*
zQ;cSw%XycYo7;PDZ*}tTZ*RM@rOop|cdCGj+#5F{=Khe~qjqP<f~sC=^J9x#y9ERU
z8t&YQ0rdiT7v$gC!Wm!lk+rL<i$z^kNom!59v61V0^u&Jk{1iURQ&t%6SO8QfB)ZQ
zC6ho4O!n;EYgqCkpyu;ga}Iv~>m?zIF|n}=moIMzwV4kbaQK*%SgPWAXri*a$%MXF
z!qwH)Ev>DIcXkwl28MNXbr-H*zrLhj#nYnx-<}06OU{DU+BP*Y*;IYuDB3CG=H|9Y
zIrGk;R&LP63px=S8kRf%J=-a)Zcz3nLPb^e;FT*Og|+YR?FHSCG0(1c)sAgNPrX#s
z)wS<_-<5QHrJOb2Rn~9PNYVCpS=t+m5OGM%ZFn5g4$g+NHa-rBO*p=A`q94Ni=b5_
zr>E;b{_yZHD4ita<*kdjeEs_I7Z(?U7U;~Cbny4`ata9%*_MC5@6Mf=FR!ojgN|Ti
zm#_J7>-)^<6Q@sS4-XGN`iyngv6Ck`L94M15*XNcBo=&D4+~$KdU~4G{+Z#aJ-xj@
z=Y;gmI@hP8sk!n3dwlx#{QJkk<7=0e<i5DDkfA}+IIZBvpZ~>WW$VfwH-X~r){Y17
zd3aXIckeEK&S!obbYCy03}k+A6+0+RZP;M2l>h6V1<RL158)4YFfx2nWO?fJY0>`E
zr%!ADz4zyDcE`WGv$IS=7kGkN)6&w?@8bMScU67W0-Z}(`Z^4><2(EMx*2A<QYl7~
zYu2uHJ$`w|=JfNQN>*rry4YrBW?u65G_|!4gNCeYYinED+YcW+$oTvF`{UQ+>p>TZ
zfzkt$aQDH!#XYj^ub6)Gu56Zdm$de~dZRGwSY5CnC|<y2T%S?doK+hiU+DqGgUl*!
za06t{tGBnda$jEVe|&<X^Mu*6qZ9WQKR?&e(Q%>1z;Vu;ISDB#ErQB!4-WI&hvYa-
znK`rb%$YM@`=7nte*ap6)7zz|&)=Rob7sV@5=|A)CKb;Yx3+4}nKMVEe#gwK#dURc
zpgH9~fB%+dB}9nE#l>}Wb~f(czyF0s)Wd6QqrL2lFJHbqamtjChx<UMQ9VA^Tk*Kp
z+(goU#idI@GiJ=th^_v3<Io`|7nQX~dbw9!UmtG|+P$ryu;5TsV4$Fql9EBe0|&;F
zpxZ3@;j#0i$TBE6cy-MFqNiPcdw))yFd^V=vQnsS)E17uzP=mV^X2WYIEU`4{cW}_
z?{3%H=<Q0Xs;twdO_MOslSwg>1RY6gH7@{Ee1VQfoT3>#W!=%^#~=Uu`+J6QIv;4M
zKf{L2n-Bl|{2ZJ{e?Krf(D%6<oYeC@Lf=?~CLdoZW$kzNM!r_k@rAn%fNOt{2slRi
z;4va<-S>)%i|fM1<l|b`y}i8y!@`ywba`Z3`H2N|$#-Yx%5Qc%WB5ELm3;ehW&i5T
z<eAqa)6&#H{nH~yTtL?@YHD(V&VDz`xxwH$>B6?$XdVdz2g3>XKt<Z0y3+UeWI?;T
zZs+gsJvmu@aqaJKQ~4UIDk?ZU)Tgaqum9)IAA^by383Msu&}VH^E&P=cIRh&Y4W~Z
zz7DkbBq_KZH1>b6iB<I7<kL?tT)uqx*4Av+B_hvXUS6)Dr4?kOr=!F2p=QOe_1EJK
z%*?Jum`&VK*!b$%`T6|f;^LsAjr=<Im%J1*GB(~=^RozaM9RT~2b+S01O>0g%fK>|
zjjb*8Uag0h{p~~dOo$2zX#p+S|NHAJ=mPpVlUDrG)X)GOlwyCy`D)eUUh@kp0+m4v
zP(VZX2O610^A|jS`ZV;HDd_mF6qm#btB|Wj#l@g4*GseA`(zqbJS9xCrd;~U$jo--
z$HMv7MXmV)?<Rwr;~~AW%d_5Cm?rO6tTMe(h!TH=9dW#n7W%84oScGpcXn!BumAnl
ze9zBkv!#4g!a(=4a(tb(E_dDMa(%O1p!CD=;N#=t9$sFDI)&8>9v$HXO}^jWp3lx;
zl6y<!=g*%?kGVh>L;iR#X`H69)^pO5%d@R4tgV?V_63HfN}ImC^*!y&i;JLK^rXl#
z#Yhq~Q*2>rsd-n~QwTKM1G>8@_x3i?DIq;4C#xradU8^9UB8UwrbDKllS<N*CG%ny
z?E3fjck=yxwV+Gek{JFTJ)f$rt^MZq_Ws#sf`Wp3S@<AF16^eXT`2-OS~7BTTH?1i
zH#06T<7Ig8?(S|4UEQM%jLaY2Zokjvr|FlLre<VpJT-2Pef>Y1f1l_7U$A5ei+tS=
zMH^dNRyCDe(~JuWF?%WkOL#67744MqpJ(If<I{6WUhnEubFWIPkgGa6ItB0V*)GjK
z-Y?(2aibyV@Vk<|j?HYKm7Z#kGkMGAyxRD9g4GSQ+>-_FG=cj=@K`#&Qqr1lWwUI1
z$kD#VyFj~-9334C3JVWDIM~c+BOj)%sd=!8l^fKi&AG9`vB2wW<;9OH%FdiQ1Dbu_
zl6N<%L}YDZQc}}G=k}x*7Z&cQ{;v1v@#BqEU$a09ocQJKL}dLzYyK|^Zn@URD=i|u
z^up)+o8P{9!(d~7_x9DRqM$=HgEQL~EKs;8xJArdZ^c|tBhS`W7Sy|{s<JwD`ZQ>b
z#lG6#PM~#wpbHzTdZF#Dub|UGKY&(me}8uuv@b00-X2Z{3A-8#w;l=5TA8_be1Ej+
z@B6{jFK_P_6C=Z*psmflZr!?yUtcsqJ56M*%MyNnd;8(jC!sl0ww%4SHT&VacYUd+
zrzL)Rax&xUs;MtLmVi#=Rkv!o_UL6mXmLRS=<HR{+4gF_vmShUdfKA)mkH=J0SO6>
z{VLOE&EoR*_IC6<3aP+XHver4IocO&3au!>HTV)pFBMdutUA^gY+N>H7C5%Rd1Vzh
z2giY@r>B2>*e(y+;K#r))2HpuotP<8rye|ie*LB3u+qTHOifUibDnMWqR7o@iymk6
z?k<0?WNj_IZQHht8ygnBu!wqiX{on|k59;)y1LKLd`)t02;}emDh4{6oROKWqfg^V
zx3AucMgDd_T}oKi9(}Hm+AXdxChM48__*oTWED<6KE8s20s-09j*b^wl}<h_+W7)<
z0N#>$p!WLB&Fs<Jat<zZZV!lw(XpB&kb8TZtAj&BQuvjpr>BD!$$=&Wj`ztL*8C^{
zjlg(%dNxg-v@P?}5>8Nc{=W=VdDqs~F0EGabaHfT?5J>w0xdWWUha2vj%BgPbv7P}
z2FOv~@h_Qo%{I$DbY`Y;>9hNnk9LcL*3W}Zi6|>8v#9>2)78~g@ac)?mv?ugU&cvG
zOYhjZGx71U-lj`g@?~?L-zfBuePiyT-w!U8UM27UDGW*PFP?6E9MUW6Ui-$PKIu59
zTO+X7s<X56#>V9KOPn+0Yd$ct@yTdd&AN8t)G4Ri+j2oW(9F%vFBZ1k-dk<n)YLR#
z-aI~ruJ_)4etc~_l1-JLpB=n>Ik>><?2o_S?-xEg!U?KTEG;GZ<!l;STUljfWku_&
zzQ5~b<CW^@^9s>lx_mikiNB<z<cag=kKaFDsp5I);o)}HrI+<?-n^M{b5m;T*@qok
z#a~}t)%qXHc-|Z|;koEmvM^{3kkYF3Cq<T^bA)xHw<SD3Hy3oz(U~)6N`A3!+Ox-I
z#_ZYJa_?_%=Wk}?ZR+jiWjJv9wD(KrQWt&529b+~9;eUFGUeX4Z{LfXo0q@Ph-zQ%
z9D4TNJvsM&InagNMn*;#*2mkQnPs~AQ2R7tA)$nvoF2pEV;o+qY(aerP>6xM=Aa~O
zS~lla;{KH~kdQ@6@O;*OPr)%@u|%tE&aL92qNd4{C%=%0>QA3xyS@B<Tt#K&!utRJ
zCY($G9Wk18_R19z(78Mn6+6!HEC8+Rzi>ey`B=}vRiUdd?60q%w~HHeVb25=PIf+-
zhJE|&+W2In9$$a)NukiwlM~d6EPj4&;erJWPoF;ZdOb-c@$av%O_w@_MMYaXh1H$>
z{rTrwl{$5c>AJXIin^oWDrv5_;#RM;xk2I~78O<1(3`m`o|k@J*X`)&xN;PF97`2w
zSRK^ts{8p=98~2_QUUb=e*F1-{^I(0`?>!Lnr6<F1Q$G@`B%``eacCpqg9cSlBZ6c
zayhE3D<&wYXvK7u8FYXI=$MjqvAdK0{P+mkY@C>ys%kYY40IVMsFUM2*Gki`eUb|2
z=JfOH3f`ZaYhC)z*AcWH?f(A#x2j`eVhTP!a^+RM<OgmQDVA=4$AK-V7`Y$P5AKhH
zhDSgRq_3bRYhSP}xVZ`%9&s;y_wF5N|I>=V#R(}XDpq~hE`NRgUR+EkqM?zQUCGW)
zZs*ROUd%5TK*2p%YRcB_;Ok5`mc9;)*;66d*Vk82RMfP1v9eX!8x5;@2ClBI6I476
z@BDaV7z%349&Ba@?QjB(cY>~kNjp0W6dgr7WptyrwQStD@x=@$(5-v!{c@o0zK)KL
z%khg<cQl?_=EVf;T^YO_d{X=O{r`E>)6?tfJ32aENkC6Y*%IOA#s*qu0NTiIYb*Qq
z*4F0!etyu7;f=}158b{k{rC5GaoOM<<@amFwZqrBTwdloal(X#PoIjG&RxDfW@pp4
zx3{@{JY2rsyt+DERDKQUZ~?>ecQK#=aM1OnGYpe2tP0h>DA@Y&Wxx`>GMTFz9t&Jt
zeFRi|%LK9i?tOKmu;WE&5~wi>sxsY6-&nYO(c1WUg`To9^W)?F?VX*RZoN{h@$vCI
zayB!Z7ll4ZxL-V7FBUX$x+-S-h7As7W!u<<J4^rlsRZ>BL3av6+cluOIbB^{4b08k
z7cW+3<B?!+cX$8t?yhuOTiYV#Y?q{@q^<og{Tmw_Pn<mIn3SYsRsN2rxVZSujg8EI
ze}6v?I;fmi+Dt)D&#%NsG4KAq-kHYfML%L(YyQ>sNsEWPKhi18!NqmR{{K(^i-Dl_
zz4xR!>*WMMlRKG9|NZ^__{+=72BxM*UtC-as(TKdJjuxb8e1%Rb%oQq>`lY;>C+!9
zd6b%(3R)ng?my23w12teWe^Js3j>3fmltSH#EBH6H8DGb3W6@V@ypvC0j2f7zrSny
zslU9iklC$Irc=^54Ya|yNqCZ(W%)Z9P;AE6{}tVyf4^<vLPgMd=koIM6%`d9R9KZn
zH#}a^C)<AIXdQUK?@Q5*{H%5mA2I;=rRYW>5<htJ|9|iQAA5Fo_Q%)j_k$|Kwb9$#
zeAGZmr0VM{RjYZ|H1ze4|Nndc|H9JO*C5rT)7Gr3T$|I+A6pZ-dBW`3+{VVnM~)r^
z-44fKkbX|a#m()}x3{;OCU<>)bJO_G`Tu|TL0hz!EKvb%%PoI*$MJ9*@52WVz=QLB
zD@rF#o(#Ge7(86FsBqb`WuVo~p!K&;o<2Qz<%-D0jT<FwDhwDvcSN5!d-mwPz16Jh
zSNH6z{SDeCAF&~!@r6c|K5T@)a?R?Vo}LX!N4b1voB5WAtWC+x>|C%w!Dqf*Y>9}H
z(xU4^u$(bv-aI+biF2abVGs6xzt`N@*qGES|7K;3qa$NaPtSz~j?725s{7A-@apR7
zjQjg+qqgN}8pviYwl05n;O0$9(AxOx>taE}6buegQBwcD*Z&v4cI_JIMxt9=GL<bf
zGo^RN^tH6GxVXB4mS+C^`P0DAuyOfv^_rR*gPa=%7X>@Fh(SkeH{8E)I^not5dZJq
zsvCtX%s|5x8y*X+Y?pPnePa<K{l?;p(T&2au(-Is8#f|A>3(<ld$+_yMbP92r?8rX
z+T??mE(MjiB!Z63d-Epe#;se63LhU^^q9lE>PrS_)w`-HD=RCj7xRnn@9sA5-D?X<
zS|2_XTnyZL=xDci;h!IcpfwMm)3{YUE55y%`641pT}OvUQBl$A=UziIvtz45R~uA*
zN|`ck+M>Y4ZZ|e2vxD+21L!2sf3Nrd<7Q=LZJL~QZ)5UtgS<NyZ|>|A2Ax*-!Xj$z
zmMx%D<6ZCXtG&3$mHT30%cEngSASpM|F8A$@9&R~bP8X%eqCI)9n@|*45>hrbhoCR
zl>&vFrY0w-6x_bu{8+CvySTV`N=nLyW?Pri1J|#M8yXsdCIsAiBo=M~9p2I-Y0P%-
z-o1{V9+4>%UNv936a+f;8+2OR!^7>ML8?ugj4p2M*dk`lcX9R6I_J_>*>;c8H|8$u
zK?6skWim=vH$E2FTlK~wB>YBU*0%=-nScEJnfUwLTZVc0TOK`n)KvfP^L)@u49oJ%
zbMEdg2aVOeeEE{0;l_;!(2{<2b#~`Ao`ZWTKR<Z+QqyATv!zRyg7&<CW<O^bCWBV$
zf|g5OxFGQQ`ug@5z2h^D(-T0|*{Wkxr%ZWpWo0nvLb0SIrAd<~i#i_$-JLw&t`@XW
zc*6#RgPvRa_4pT*zr4h1XJ^O3$;rq7+M;DNlgE3y9xKC{IhMkp^}S(X(@xBg3cUH=
zJ2NxW!`IifU(WW!G3opei5XMDr!maxS|Qri)djlC7__qJ*_oM(9%smc>JreZ)Q5*!
zHMF%4KRG%1;=bD7UhEfbZERSUC@U$g`p=WKuN6E)>hj_H_xAn!?Li$kP|c#H#RWR*
z^Yyj04`03F@|*-Z4RwYSXugJFUcH9%B$cC&XZg%9co=$YQPqnJ3!P^eCcCxre`RRc
zz1tdea(d349f1x;tMoz3vTA>SQ`FMp;^gFHVBqHF-ng)1iwt-iX@%Z~`=CKP#Z|K3
zX1{_C;DH7<Lag6dTup`ya+Eg8F0TT$NcU74gJ#n9?6E0%e@|9e&8K1ELPgN-ebBD)
z*X#FR>lAkV{_ZZfzP>)FE;E|R^ZEJt@HI1M%~}+@y9_k6d6MyqUhFOfLqkDEMn(=k
zzP1>><DZ_MW@OOQ(~H<!wbhSz{`-4-qYVq@O`6nn=~B>%r$wM`t>@021J(AECkxBS
z$RuQBXjtiGDw>;{zqz^D-LS!~@R18>(igO(yt2~r(BZ>|b$==jYMO$olBxghUD=i!
z{p86L1$Fi1hi2*ho0poC!?QDnPgz;{V&E31RB7=o85f!Q`ugtdSRi!o-o38>^9+;Q
zF3nQ$1kZJOs++SYDk-hvwt?QpC1+Xv4ZO@S_x84j@9ys2uwlai(9|3#5I~zwz!QU4
zIBacgJtnoN`_BWNuX5q?<<%dve<&%19=mZv0yG6G9$ypq^4F=U+8?im$1hy5!sGBs
zkJ%@m7J;tN0o`-FvsfK8gtWv{7_{OLRH@INJ=@EEddCa@Hx}o?F|}W@bmL=ztGeH2
z+k^SXq5QHrNc@oZr>1Iy7N3HK#Lk@YnK65|v)W|PRL|b3uR*)YUtL+*(bwmem$z=g
zmRXmV`^(RmF+%~;`hv{-%G|kghrz~vZROuzUrz`fjK2<B3vlL)$efThfBw|K=9so^
z106y5!b9r&qv!6&`(#BAKlAhRdvR^;><1}dyY=Qb{5vjR56X|A?GlIEct1WlDeN=b
zjQ8Tjix;k6KYn7OGN`u>y3wa3<dPC-<HEYw-Jr{KF9x=3-m+!QS2vbPDlgv@|Cp%k
z9<nR{!-IqCEjR@QFTRG&dVCG2th5Bp^MSUifVv`IUI_N|_JS@;xOmaz(X+F&85;Ox
ztu$=co$UVI8CS7U`TP6*|NGc@r8L$~oi;7$!GT855XnsAbQV>W+@fD!GC}u0U5~GK
z4GR<F;o$+*FrZaxa&mH3Umtoc3U8Hdmu-)e`^^iQ^t-rv>Fd923C9=iItXnUWNm!B
z;c>v-gyRcuB^_TGxjt?$sMQSW1i#<^-wt#{d*b1?P|FGXOJ9fm`0-=Go;@*#Jx$M_
zIKcsGp>N5&tR?Gke@mt?XcL);xHz}ps!DD#ordYt#dnpzk9+y+>FMc$va)L}&i*Xj
zUi-Vu!qO6Shx4MvSF(56H25v)6IS;FtsoQ=69X-eS+i!1maX7k_kKC1OQ6=)OFh_t
zQSs5EM{n${HU|w|SAWmDSlIDu>f77fli%Ff_~PPX_CJ6BUffxn4z7}~t&MI6ol<&x
zTP|px=)n?|AP)}?P}=J0;W_cN$im9%(DCE!p!M9KYbcK^SLJR5)w$r|2j?Y~Z_Hg@
zC4)zP1Ty8U`6m8?jLfYnE-Y+Zzh3`Xk7V;Q-`UqH>H`A>-`(H8URb&XQ~*HRMq08C
z^NrK_l$4bVe}Bt8=xOTj@6SKmJipCHZFNcQ?QOXePNvAH9Q({01Ra-n_2lJM&^otM
z-{;xYN~!zLdvafzp|!Quz{qG-k+DE*(erb2v#zUpIxTkVy|BoYn^*OcT>anQfj3{?
zFWM<HN#)~x5kW!0iEV|D$>@$(d-v?IxwETu^(k3D{kT0G-rnAGYYOLOfhNe;@B77d
z^XAPibAu;EmS@hM1ubp!nPU-H;3VYh@6R8*y9~6azow=JTsa8|zT_yA2@?O!yRu2P
zy~8CDoO>r|-6-tv5CKV8^MNE@9eQzb@x*D<+NMkq5fKs5;9YQkcRByJZ{I*?ZX7y%
z*wy{&j#+FMuCI&j*5Cg}$bX*A#R8+Zlc!E?-IjY>$;>QlV`Zb>%C`(#_4rROTe3vK
z!a{<RlT$-a?^yo+zij5_=1-nH0i_W}Mn(yXf(0*TNG)H!Jp5(B*ZY#v(x3$jpl#gN
z@AoWjOnH=hYm4X7_h+A+oNPM5ZFj+Arc~#4zE%}aPzUPE*RO^pFD^*!cblXlV^<Tw
z{1Vi(w}*}eFRIFabfnY6+uOOQsA%cyzP`Q}*Vamdwk7eZFaEV?%^Duiy4SO_%^4YF
ztx6i2o0)ldcv#exb0<ui)U^Fx)#^)IuUrWMZJGt0Wq*BLtYPLQm8pKg3Q9q&)_i+;
zzDcj*wB{4+Jk;l`-z?jnb*RtTWzmMmp!VOwSsNY)#Dc8eU-uWZg3>Vg7$_7rr=4wD
zxKQ!h`gs1GF@47A=U$v)V?W*}>+Iyj#E|gs&(9B^KCLQIo(Y=1xV<em<N7*Tzxj4+
zA5OWY4s96c#4X6aBB^%$`t^EN&n?kKMMg2Pv7nQRcI?^(T2YmGxv7zv{m`XLLV<yS
zpjO<mUTM(D+;{d=3WG*jb8>ST8D748`Qz#Icu>3H$FE<HZf(u(=<0GxOjJxtPA)Bq
znE&rcFZUEnOH0Q|Dxd>QK$C$x)Q<PdUv~g)J-yBkZF#S_mwkVq?K0olZI;E)LUw_U
z_*@gc-S6W<UZq91K*x7%1WoB-o9j!<%>^wPTlyO`($MGZvR()pkf<!bx1d%Zs94%r
z{5&8apy8CA+S=9XLh<`*BpDeQJNo;>f9(U^Y4G*cRZxk4pk$V)lvLM+3jqx0{ax3-
zd;BGT-%qu=9}nBFSIzJb-BrhAwer~2tD=>al^%Y6pjP*pvuCH8>2mP$g3k6fGBRRO
zzq&`&dzylgk&wFI9Ea1>bf;b`Dk=iC+xqSQNi;S#?x_E7SM~iJZ*+9DjBQm&K++|)
zJ3AUWIyzh)iOmFW#|?RZcYpo<Tjm#{w`R4zd6UDdrj%Ry=7!<ceSP{TUT?Fl{&wKl
zF}Ih`eIg?z?S4KHe)0M>Xe5k}kMG9*dVA3F#g^9AhqLqd3C@_&5hwn}VhPtb=^$}v
z2(3y0=UIV?8XyU9p6z=DIwJ8PyFBPF(#OYoLGvn#lTRv4KfST~dmg9@3)=me%$1y;
z-o9gp#gpgHAK%)Vt)Z{qzIChVnKNfx+%NAqaKNGF-_Pe0PCqp;H$T3s^!0<cZ`XpR
zcMZ(U+!nj_vMjygXY;!+3sgUWP6TmtbJNh$TD9Tcx>)NwyUYC@j6Pml6WJ_joE9Qs
z$IcKO99;A1q&jG|Armt*=#c7@lhr|MO!^y^Bu$wz1#}BVmv73c)2F9iQ}sOb>+5UQ
zrNZjw=Hf?>9^Fy)HmY^MHK@{=JXsjjk_4^!`TXpx^ZR>yLDvc9#eDd$s;>U{#>Qk0
z9v%_UIPHo!=qeDwtJS%;wm5ouc};ztetzE7ljc4vmBhuxJti%w(3yUEs$95hc=>_l
z&)3E5Y|;!~rV-oS-+vsmv@89bjL#ek!2_T9b3iBSu=B}WxXJ%jAn<O|amCOL_b2Rv
zm65F0d@H-5g=gr7#~_K2?G+!BzP!CH4mvdG{CUuEKA^QvhtHnnt^f0p{nyvm?R~P=
zU45EInpn9XJbl{w?(XizuH9mwt7k7kE7aZz69gPNO;4XV!QtlS#?T;bo_FBP8J=Uu
zjx_~m+8Y}i-`P>fyf%8fn5^q#tI}6XE`9zM?>VVu%a$$SQ#`6AB|_{M6+J&EYm#>-
z!Z~vbXjrzZyL)wvzMh_&pI_gj!rR+&wRsZvuQM_>HmvxN09t3^JImzY<Kz9H8x2K7
zL>%;{F9ywU|1O>-Exu=tvU{I`ib@N3sv!#zxbx=Ci`ZLbdgt!lhYuev+_J6udtOU>
zd-AO<nN61_nsxT~hgZb}1vMQw;2<I@n)vF<O3<=L1_e`7QBc1EbogV=O(VfT&+aGB
zo-L~V{mtuopNu7w=OlxyD;i5*GqdqH`1tgwJr=x}-6Pu`a<I<%Rnl=qrNA479-?n7
zK*Lf>LaiW)K9EG<-KpB)8!A2~y?Fgvn@z#n+nbRgEG!Ik*BR(Em&8LX6AfEIOQ3Rc
zb1&|#{_b^MKXzBkg$n_5B^~~+=99JR=nK%lv$tCO=FOWMwr+I=-EngK;*RormCFw?
zRC#%Efl|r2xz^hAj$giXso?9Y&>J^zE(~8Er?iL*=j`#3;(~$$r>1IyPKYzVUlW}9
z_S4hT5nHpSUSd;RxpHO3^>uTXC3Au9ES)n)Mnz2xv=17T=lW!=L8FeK#W0|r_@hUU
zT#k!0Ns9{z3QqJuRB8YI{OsuNKD;7u@rBLl{zs*kfkxPVetv#&ZL~RPYp0**t%M5;
z9KHJY|M}!?l5v6I<jIp6S5{1X^b6EosQGp?UBV<o0CZl0qH|k@l~$%8H#avZ2fw`a
z@$vD*oSdF{w$)m(`4<*2N||IVI9cKHMGDk*B9sNvb8^=F_<w&-WihC!S^oZB=$hz=
z2+-2}MUOJK?%88A_uuZ~hlf}}JH$cz%^V#aTMybo*48?{JaP+ZR-vP}w{`Yx>7t?{
z(BWR7ZC3N<&1(wYS2f!_Kdfp``gyrGcXx}k^UEFCka&2?H9k2Tj+s7fuH9mpMvJb2
zqB|xg=E1{<j5B@M9#ra|J9Fm9r>Cb2-`}%kVQ1&|(>w->oL8^9<ZP=z<3HQBZDVN2
zzP|3^kB^T*1GoErzq4jI-`@53(W3`XpQ;*dI(Fpf(TAJQ+chs<to-TICk6({@)pqA
z{Y#fF86+R$d2@GnctOzF$H!P*TwGKp&3nNBt_WQ8S4VD6^YHUKc4udCU{q8WXuj=u
zpR9(iu4_So0cZ!rv$M0i`#hsEPEXVQ@bzoxuYmL1$BrHQ@b&B34{Ay;<=ENTLBntt
z7rQge+h1Ay>q{n&w3$y~(IM`YD_3sVvPDF2az~sqXywH>=^#;P4e=@g($odl5Rlon
zzE`_SUN&imuhWqG{^}~X{r^A4r%s&$t%O{$LSxUzW715*S=TluAK#F0kVz+E0|SGA
zu<+uFKiBQ!>wc<&&cLm%u0Gg#6m-nT{e86?^Y7bj$-ONmDJi*O+cvk`+j0v(Kl7b2
zW5$a&nP;oNziXX7UEIgl*D(K{&55T)M`x{E3BFnI!-s-K&ZC@se8;}LysXVLpBXf0
z0NOiI{w{{`<Pp$0uixI@ZU?!N?LzvQ8I7PC*MFYP!F{#AOTLx-h}&EB@DOCty^*o8
zprBx5M+ZkrT3XVpD=R^ZkRDZEUJ<AaD!f6{d2^zSp+h4K4wKb<6+DIH>}pm-l$Vqo
z*_eFX<*0Dh(^FG5G&LRj<!m3kdesHm!*yzkCg}Ra^Yd&$w_wb@3$EAWZ0AAO0IzR7
z)+?=SVlrj9d%#)|F)^*T75~f2-`{f$44lX&Jke~HdA=NU9^>FS@cP(R70(&A)n%>K
z<?rrrnwy(5YIeRTJqqfm)qy4{6qP34C|t1((i?G65rVJdbT3`()_dsGRPB%N>;Fsh
zN}C-4t<L#=zh3_AZ1Z*%PYoTNBmMUOG^~~#J97NE_PpsTo}im9l9H0N_I?LlKD;V)
zwTYyEc1ugkfm^qvPM$mon({q!_N-z0Ihh?hcY>CN7L=DCzqHib^|(mV!6sG-ivop5
zj~`E*J-hqo=jYmMzrVjP4>}%R*l)w?@b!nTT-kD})Y#ZKW^Yw!bLW=Rpw&I|=Jjn(
zKd)qKD+^ic>3Dx%?ZV~DZ>MW)%fBy|eQk}Ptn+KoxYqXk`)mvnQc{a@Z*K$Th82N}
z85lA%GpFX=S;8Hc69X#2W$bDsIy*ZV8qDuiFoPySLCdLbBs@O~&QmU>t>B8t#pO%X
z&g$=an>KF-9Zh<yR~ods`rX~~`$x;~*Rr#-w{uzVcXM}t4BDVjvOVjP?zeB>EULa}
z96EGp!o-P<b$@?>b{fC9yL<bkT24+*12eN@GYpeiR8<#U2dxC?g7g?&ZZ&|H1VG{_
z7qa9=5wzMm@7kKk8K&9O9(_D9Q5iJ9GGm6si`TCogT|d#uU>tiWtOOfL<i^!)1sX+
z&z?Pt*q$f5XYbyr?<T5n9y@l-%K8dB1E}=N$j|`o%l-4GhT*{G^z#f1pqonn{P`mw
zBg0c(UOv&Vbw|ldp|CX(flqg}wz6*8yxDYyM>S|4j*=2n@G_sqjT<*!ib_lbUCEb_
zo2#oaw`>B^#Pusi$T$_dqM{;0L#MEM(#=h&pgGc0r%wyY$@P7Fe4N`)lh0f);M>#b
z@vCayzr4IWK2ZoXtUh05`st^OoWWBgf_v8x9vW56oPB$HKB%p8eO;{cY_r^i>}+m^
z9d&=LKqu%(OH0exR*6iTHmzy0kl@61NuXhg{fbJ9el^IpXMx&L9j}<nWLD{x$tYb~
zGTS`=(3vx94lU4OJUiR`_@>m;2Boh;PCP9Fo&RY6?}u_tO$`GBs3qaxzyMzBcy$lx
zfShk{Zq6{x7Aq<)1~oNz?6BCeb0;GM=w#0mCp?a>Ji1H8%1R0}Jg~d$E$Eh9&3VT!
zU%m_~LT+!*Prkh^SJbTbf@=8sI9E3}wojiw2i`o<<)bD%!E5s}zqwqVlQxvSje7C&
zC8#}PTGy-M8L_`^FWaTe>7bKUK#P}`FISf`%jp0e7k6t*W=CIN+rE8vpmF)DtHT$A
zRw*o=BnBFdyZU#Mil*6gMJ1(0w;n>4Eel?)1{Imhm#hE!{=Ofyj^y8;pI-SDy)u?U
zzkdC?vA25rgC$FPySlqUM>B)^L+1JSSQtPDl_<OQ9GIdRoRE^DVxcG~_)-hh8~DvD
zD41ysVp;PcSQl4^hK03#`BGw2_ebLHuF~et&Q8$c4jCC4P~rFV^mJwh&|xipbFC7O
z_sKFa`1|{V4n3EYlvGOQG9)zf&}vcfL7}Osso>=$)upfR?k+z*N!1&40;S{0BfAP8
zvw=pPmMmG~#eSagt|Z&mEn8aV&68Ufzn{<9**PLA%4yP)EKnalB`qyWLori1FDAga
zw65;O>(~36R9swK*4sk|jRN;xhYuF+yCggP@S#JXO|bhc{9RmJzH)(lEV#Gt2I$1O
z7o|t~oLy9|H8QhrD199!At7<#`gQTVyu2G*v&BJUTcCCy188yxG~CWDt|u}lYz}CU
z>FTObi}H6eTwGiMadGRm=y?jQi{G!OG1o#-QSrye<MJPm%hw+`aDZXr#ECy%EbdQ8
zPG$zDb}{|9o&^gO4tkpE>+16U{q?nZ>QqtC(9(kk37~z(ZEbC!GkTvCS)Q9?$*ird
zeKD|gSLy3%m)wj%xkI?qH06YVimGbj!$YkFWo2&NV!B#;-yhv?xabsU>Gg>dE3T=>
z?&sT42s&LRQ<(W8V+R<-U0doseM8dGF0JdjIyw{P&Ru&D-1^Y(mu&|Phq%A7aB*?@
zVg+hP3xQ6R1r6fx@bV_6q_mu!ZT|SUeEpFpCntY=HakD*%nU=&l)=Np?Vy#{pfnb|
z%tuf*`mvCZ5a?7f(3mwJAD@S(XXEVI(p}x%phJ^DZQ}Cx_ZB5{fi^rfG%y@Jxk6ao
zuVvppyG4r^FI>OAzoCJlN6OTzz{?QS3^{Vdg@uI$G#pa2Go~<TPj@#r=%C`yho2w#
zoER7@Z}oq*u)3duh6cy~KhN!5-4|A=sj9LbJa`b){3t9m1f6dHoua9$s{@@Dcc78k
z^?1$Gyt}(X-zJ0h#rq;UEXR%=)6mgbQ)H{G%)B;g>!k#xRsMYPc0Hg2C?JbZ+GF&>
zqpn|#z1P{{VFSuIII_^`=xsTYpgZT2kM}LC{QL|wzX{rBt?1mAaDQKIm$38cQ>QMh
zkGBU6f~d1!aCUM6?RR<dBn5P0#j|J6K<hp4+__Wm>Wb!$-Mf=tURt^+nJY0PBjRCY
z)t?_9CG6{L7!-7LK#R{EA|q#ZR2;f_^QNMn9^cQOKX;V9l>)5=%gyCAHa5O^v1NDZ
zYq4oMkxf5-fQ}`S2c64RR_5mC$0w#6)xs&Pwjg|c+@j>HnA6jAL7Sy78g98Y(>Pr~
zUcUd$o17m%e}Zmc1ud?ts<O(-$+@tjF!`dOsh*{!<hph1GVbm&1??PladXqU=Hu&I
z`2Sxm*i&p5R#wfmDqZ!_<;VWXDx8^_nd>zK1qCm@hAl}8dA}1p4kcuqc4ozfviJ9F
zbMEXARCezZnb5Q4?x&}xK@$%L4;^Bv{r#<V@7}#HJX~B{xF8K!C8bMcAXb?Sg0*N@
z;m=R0pdGB0pPw-_fY!2scJTf9_;_mDWF8)#2ag{&?<{`a)unZ1XYq5;PFT<tsrL5r
z44|zm3<s>=?*X0Q$HLBj`0m}<6rZ(Uzw<hk93|8ZKkDi0+q!wPv6r_uXuZ{vWy=<A
z*&=e_bK=b(KPo_{i_A956`B+B`Olv}8&Xe;{rLUcIX*tVL}qPJR1}xIyu6FMyR+VO
z=SeC%cJDrX?V8wu&-b-K%g-!}pK<uDs@$A@-tGChxu8RbK+BO`Tr}45%h^O^YQ%~c
zK5lw`uk!g^F6I}SnxG@7xU9<G^?*+a03Cq}>4Ls|lBVF|f@l<lyl-u71<g*rxV)VI
zSdS#L=cIxk9}+<oFLZWtPvvKq<0`se?v~#_c=jwWJD*I$!i5W8fJz20@De3+7ndb(
z!7K|TRw-zi@`eo?0&L98&Dj~2X4l7R>*-yKFw0F!NN7;=oyEW~%RC=cil?NfYhPQt
zc5UI)Q=)+%J-pA(x0m0xZQF}`d#jhe2Caw7$XMaWw}73E?a+}UEGJK%ym0+`_@6hG
z5BGk*cNlaGz*6DW)!*NN3g>%uzjHx5{@>o-zP?1@?%~7E4ptkToSZgfU)KZm9@ni~
zw_)?<;5Cwxl8I+#7=mg@KfVR??P{gE#dMn{P896w>e5=XJ^MP}_jh-NC-~Up#VpAA
z{Oqh(|MxdHoA*|KfArvBvxHgBj7zr;HnS^EKDi;|qLQzhijq>*+83RC4&c)B%O+@1
z1)2yrc<|ta(@!Jz)mVZyYgboSgU%ca3kzG6JW1@-`SYOt1wR+cDJfm@0;S(?(unkn
zU@hA9`FgOy|2ic#+w|=0ZqR=7^ZVUncb6SKH`iM9_3!WR-Cti@>w0u?m6pCfKd+RD
zfUI)|=)AIj|Nd>*uwliQ=YH*cvIW1t<uaZ;0=lWw%Zm$ixSOPL8fbUfym|9JeED(&
zbe-h?)!mC0Edt#PQeXd{Yql7J!}h$p1%H2)GM+qQY_Q^A&ROg7cQ4Lx-mm|Dy_Z`r
zejm@ym~|1qUms)LrDb6uae2A_dV?B12GCNe@86H#*;&l0qO7D;W&42za(Z`_?hTy9
zl1KN~x3|SJGcy+@3kV8^c7ob?f7?0`Z9Jt_{E#kB$E$Oo+nbA@pJQa;;^JZe4N7O+
z+q3ght$E&^3l(O$po`1?{CM0Sv8Te2hll6G)9LY#7WdmZE%%$tz;Jzi{P9OeyIGg3
z<QBZSVW^^_q9J$u$dL!Pwq}dItN!qSaa-<fw(9C?-es5N&d;-5T_$0suI`?0KC`p8
zS5($9J2f?RVfy)bq3fh2Bo=Jg5YXJY#eIL>U(k7p4Gj%k*{-gx9UUD94m2{estCVd
zFD?G$*|V^S_t(}+m%X{6s4%l^N7Yv?A79_qG3Lg`hp(;<H=O~#i1QG1)x)amUS3`s
zDnF<F`F1-W)E1Vrt!e>n1iW@l>~K4OyN}xCn|G(JOv}Eu26U{xjEs!J<dZJP6_u2N
zz~j631q3IWB|}Df5v;3oA3R84VQ1Hl{rvs=`hxi}de?6XUute{78DR*sI9GKIB=v>
z7*yfDc##1bRaQ`NSnj7%w=uC%>)oB5pSdPy%>VJDqNS~ki2+B4anILl(H12y0+!lm
zgLbgR*ZpJ#t^H_7dBiJc6H&slHZ?Od@~uKnP>@hgZZ4=#0=igUPY-nYT|miW@9BDq
z#>T>@r|TczTm4<j=K5={yqEx6X=!QDrL(7|Xd0NAg+*!W=(xDJu&i0TmUSt3IfBa0
z7(H>>CUA4cLsncr?#S==`}=2`=R4_52Q{A!3=Kg8m4N{P44#ufb*gRkw*}GL^A<gx
zB=+j!V)jp;J{5d_7dvCdj02Z01$}J$%{@s4bU|2?kdWX+y(G|H*g9tyms?%3?Qv|N
zMq;KmWXr5esj`vLrfc!Wg^!MePgqjN&CPvyPvz%;urM{NF1HsiU#{FEd9b^ed!B9e
zx31vKcF@H7iWQ*!O_+T<&>-7_DUU$+(8$TjfyN+r6h40N=1mVM5T8AJ#=*@En&wGL
zPJa04k&=~G=EMmT1VE#G9o^la<Fi4F%AcGN1kK~v*np3)0B!P;kkGJNC9rYhM$n!f
zBO{|J>!Kqg6E83GEhsJ)p5mhu9UWa!S($iqQ|gJcXIp2^lzjB)k;r|1d3kwI^Icp&
zPGn9<&x;ospfkVU-r9QDUA}h7jU$S-wz7hPf;&K)R&sBLJ>1#T(a{kCTe7oix}1F-
zPjz*5N_x7og@wevefvP8mPvoVy}kY8<?{I(3LZLvu3LM4e!lzTW4)|uYPnAyJz8{W
z_Nk8_KT3HxySN<bbJp(%<@+sy)_i+)z%{zt8;dWSK!fPBLEBJOR9w>A*6b{7%mS?)
zH8$SNrGDyCv7n&f48vqL(49;-RxmJtw($P_e*f_G>){1XXC<skG*m=u!fwOX0(c$*
zol?7gJ*d}o?T6_k70>}yQXb1=y}Z0Yw^ls-e!sqb?_S$;^X>cN_EstC>+_rE-vbRA
zZpgpCk88HjOQD@HSjRBbt!5eA*|8uEbR<bYfPh}?t|cXVtG~aC*p$NQ)+3>)At@*r
z`1d$0vri9O8`TOr6XL`~<*V<+YQDS(<dHOD(GFjCBz=DEvYic}DkUocl)V>S7X&3h
zXfI_;JjQBv(^zQ-^;O#aa<+#SI=2_Ry=8iI!<yZ@cl-T4Q&?2gq~h7p-{0QY*!ZZ>
zw@==FU1P~DcfIM#Mn*!`Wp4tcHvN0h%x{o+NoB6wmSv|3A2VIOyQ`EN-eUxJGz0|&
zuhzo{lrw*PcnDfi%r6)6G7fY-%Z1f_uAmM>5K=eF#bv!RC=%aJp9-7f6$2fC{y4*w
zZ$WUVUd)aL(Du$dJBu|mG#n}`cV611;<=;l@2&+Uk5p7uLANqxTwN8q^fhSa&DXbe
z@#4j8lLfElBloyhOa}M3ZSrD3HSi*d4roohqz`n8K)3$BfR}OR=H@lu@0PE(5WJec
zbm>wLU*EM~&IU1nCXpLLTwIoP-zZ$MZUeaROgz4D7idP-<yMPq`ztQ+I<ewi9apAL
zn9%U>a64%FrJ$g|!OM&5&Ye4;k<iKN{)f(;;{zR>DjUp^o}T{a&*$@@e20%6JLaS|
zxiGjLv^x<#=j5vV?A%=L^z`&E@9)d|&NdU3b<e)LqmWrx&Bq}qC}`^WyP#Dg47*f3
zXP9IPfevi4>I&OMRGS^NpUE2@Kbrdb{A;7PhrNvB=H`C#^y%J5E+O($r%zA*_U2~9
z<}}`}uC7&k`tv!21Sc-r@c6>%r2UFYO1Yp62p(L4XTY-)R6I*q63@-GUjAus`MW!n
zt)46PadC1sZry4+Y4T*yfai?avy;!wu`DPqJ`6f%;@!KxrQXxK`ZQg9XGc$&GQ}Z2
zKHfR=)pW?rkV`t-1##Ud7SBnbJ&V@X)}Vbw|01HIy84!zF7un)Rs8(i!~6gLna`O!
z7ra<-B51MTDsOBJYleiZtgatOEo<a`-GW!WRaI3DOiV&v#xXN9+tmL0BC5XVSH{If
zuAmm#pFe*dJbA(rA0H1oRv9#EG|Mzw!Bc3OZnT<}nxNoIfijt@$Ty(&Z7*ms=EldM
zsuffx9PM-d-@mt-zi-#R@Am(Gy({u=QhB&av6E?`qp(7k%9CTN&$rxJCCb&o*p%U$
zbs@M#Zi`32C8b9TnjbV41vF*_&6pG<u*gS4d~)o%q^}}s0(yrEG$r2ks;qhV`}bkP
z{mU3xCjNb+cK*1}zZ-vR%AZ-D6SA|~XD?sj?!1rj??HC?Jr5acZf}$RvcYa$-t~2{
zv+QbjMQzDgxH<j2*RTKVi$RSVZEbH$OG_z>f(0ji)>~G6S<xqB8T5JAnl(Oo+jpNU
zetvH5<wdUDB9f9X&)WQ0!OYHg;%U*!9XlfOwnuY|>8!Z<+SSG7ij+rxZ?Eax?4Hw4
zFMU35zyA5W>T@Ms{tq5BNt;)GN-@p97ZbfbZ|dcjA-A{XW`nyT^}jC9=ef$r@Zi6M
z13Lo)!-MVnemv@yw%Yjn!b0b`6^-^$n^HPKt2J4<#a?`Qd3n+jIom1?U0vVg<9(q?
zNsG*KZY=o!=lp+@7%qkkj~kC4gl*W*$nZn!o5c>%H-!ug`?_rT@>r{79(>EbysVc`
z)@q6M`#qOSx&*t$_08ro*k4}}sC>8Zxa_1Q6DA0l=G}={?l*T;<og>N7k_(mGg<5W
z>wA^YWqs${#ZF5-xk=~gvu9f7=G)H|Z_7RXupr}L6Dyn6!)(yLXFgf0j4v-PPTFU=
z;K19m)k~JR=uP+54qq2iSGP~+bdZNf$D~P<z8qwimst00-!$FmRjH?^Ei<lRV;8@(
z<Lqqn>{nM-f{x-jyFdKz>fP`6MIY~zH4b27aQJ(G!HR)_fnopD$&(k)nKS2oP2c2Q
zg}Uzja#x?6oUH2UJKJokN@!S^*Q8k{nTswic7NS#e(!?z`aMZ&1Q{-T*l_&d+Jt&$
zh7X}{3JbJvJZ5015v`WF!}ZPLz}wPCM>ywNm3jpR2Ab9%lbW?L`S>iqhWXuHT|tqN
zGgVG*(kXp;$yGai-IW!Ai&Z?cudmAuV7CFy3&rj#nV5Uq%isSxsDC_ZQqXJ3)0;#@
zM3(%1zdt@PF|p0-;b|u)CzFf|3cOM#9+RGYtO$vSSaChB+BbSzPGDl<!iP@An>KBl
zGJX2;H*az*=lWf?JXTn6uy^&kbzuPk7fi38K7IP?j>2SpF-C@f{RRzu3=9kh^b3Q`
z>o`C|E1=c&o<X0VoxQrqm0Q-PV#77#^z-vfC$ceQEC3~eji4l;^vz;NC^!jp*z)Cx
zf|5YQ)~u=X>i_+mweaSmMM_JTE?v22PmKM)kNsaSdF#KN=q_g%!}+7#v6=1V-SYca
z&&)Kwx*|~7caBBi<72(S&(F<Otu1zbe`cmJZ+Mlzk55lhQj&_NsHo_x>+9!RmA%Q>
z!S!#&mMtNA)4lbkgNhQXf(H$A{FYaJd9m=xla$MqZbyzCd!=9hvs<p>0i*5DCzHE6
zI(EEL_;r}yK4-x>8$P`q+du&*U;Aa^rp=pQuL%tg&%U`S)yu=f0Gt#OZf?t+-3Lky
z3<p}~|NF9h*W*6xFURfw1x_+aIU(@({{O%8r|HG60!?fwD?2A9CKm0CY4c`eV94Y7
zEzQ6XAiwcABLl-%!D^WY?cWcw%fFcDE*F@Tw5aaW<oPe2PLIF#>+9>O)26AtoNZt3
zw>)@t*jl3)t{?3E#}{*p>#ayVJ#CYY_oOfXe!pM6V1a|*^5ELv->yzjbiT5$w)*f=
zgWN|)I?exp&QRT&dRi<rJpBGKrTd^!mA7|xZhrPGYy0iBmzVpmPCY%%%f}}qC}`58
zNs~n6<<~bfFkIew%tEFwdtKx-)!W-rBg2}1-itZAl~3=*y}i39O`dF;eop3cr`wv?
z-C_Lpe>Q+7DT<zWEM2xN>*l7^tlQhxrk$AqS{t}>#R`ww-``B<axpZ-Co#x^g6cxT
z+PJ+@-qUn0%K!i2Zkl^5r25;N!1wp|mVSE^d2`#^3l{>`#_kT=TlLjwE*Aqsf%A>~
z3=9pwI&AqE7*_P(c+6nGXP#~Ks>;vLZtW;s3|b^*mV4`pl*4?(<Tf$Am=((IeG+=C
zui7Pz(_So{9(U<_e0{Ff(T+`<jCAAnM6mPAt@-);cYNfurKPX0Nv`_5?lmueysxvA
z3Lgi@gyW9`OG>s(nlve^?cDB?mq}J<m;d>?zJBk*=l>qt|9fmU{RbPL-VRHU<6Ag|
zOFlk2I_of(%F4>m&#GRp-ENY0M&fWQ1H%t}whN3Pul^8!et!P-WxlhYlvqujGG)ny
z3m0bn*WhJfc+ijTsqJbC3J&>uKDN!P`}J})--7*rzum5SHZwgWGBR_A$O?H-fM#A^
zW;(<1QT^2U^Ve@oK7Q(9!HVMN=eT%z_r3xxsf^Pze*C+JeU9JrT#b*meC>;`>0b5p
z^z`!c18p#VY4XE>Pj5%1xPIIfP*>pZ@9(cqP1SyNW#wcxKA9B{9wc1OWMKHQ)omFw
z$mt9pR1Y3J`0M8Rx@D)Q>t~;wq&myCdfT_Rx6`e-85kZ^C)YDGFuYR!X2HO)z%Hqu
z`Od5Z2OL5}LSl;lJ~-H%b#>KL@ot7I;g^^B25-;13o2~N-rkyd&T!pAp2_v{%l+q1
zyZv_B>8F!UKfScbwL2s<bm_OZx35ci^mljfemVO|V0~z4=*gEQS_%pdjg5_5TwI{i
z#W($@%J$o9U%bfJnswFda6A9{&2`VtNKTzLO-obrq=PI2!@qvU5|Hy9nu~vaN(Ch}
zc0QSajEog^zb?<$($Vpm^yO-J{L8i5?_HW>S^TBH{*Uuqt5TyFZU%-AcQN9`e}CQI
zEhR65d}kOeJa-GUib6MPi--N+m;Ss{7+2)?$yzV-oUCS8)AwFPN@~@?X7=n44-QUJ
z=|8^M-|pv<G>zJ0J(5<XuckCLHG%TglP4)ppFNXWx9=|~f1lW-BPu3#>Sf6*b^D(u
z%j=G9(gEG2%U${mRPcKH`d+PmzjyhUFJD%#6BiZLw6%@Bdi83Y9y7y&x&&xWS|DRz
z7X!-kjm+#Rx3{TiDkwOt4qqQOS<QFKym{-AkN0WX*~NW+cJ}gxh0eU<%nS@M^62Hx
zw^@eCZB<`iEuCjuo%Q3xL(}FgX|tRQhg!K)Z*PmMdZ~JOCc~@7b+Nl&9qANaW?bX+
z{M_8s$ZNi}$2RG_y}SFnndr}L$9kn#hp&%&b#?W0HNQC;o>6<Nwx*q(wX|2-JnQl@
zU*05!zpK~po0J-9TKy<L{;{-7Ou^%QfB9lhZ{L2BnW5qR@lE?*=SPF$jp5bA!pFy6
z{{4Rc`uh66*-Mu#dv#%<^Qp6ELq9(|8yXk4ZpI9WvvVwiYkz$)#9lgVzyI#;?ysxk
z|9VNA=dCfFaAkXb{NMBc|Mb7x`#r9?wBh~jt=ZRk?SG%Me*fb8{{OYjdqTfG?zg{o
zVxscaqNiS}Dk?M18D@QXaj}%G-Tv>F;I}t7yW9V|*e@b0tLu4dclr8nZ*MQ3F+<|$
z(W5W-e!pitF?-JO#~1r#twVx>l%}6n-F|zmar(Iv+j31aFS*!OeVK6jsnJ|c`wwpq
zvPN&qnV1^M`>Ooo#l`NWPfiGW26=gPfx`IjkK^|1KHu3{{M@AYna^B{LZ{!~-+wPt
zV_^8o#QXvjFb!;~Ha0QMY`m91`@OF12@eQZ@bGXuD8WT-&6+C1*M886fuUjc;eTul
z3|HJi)vQD95jpk`^ERiS&-(xG@2;Y!T~=jpR+#19n&HRvr|Iy+9S@^Ba&PAuIQKiZ
z^R4}S@7~_((5R?Yd3Sed8X0Xm$Gdx4>dFNR4n%j_C4YT&_0)+I7d|~beRY5R|EO&F
zx*rQKUB3La-TsdwzwMU^3!UCumA{)4qZfYmz|V7YtwTdYRc~(-6%tx><cQ1CB}+6^
zRb4-R{FrrX%gUE2^S6|~4y*n1@%Sv8%1tjtlr45F*!J@B^6Xz<Uf%!teQNIQA`6+Q
z4GE3&s$Oa8Uj?-{OpL%a2SbDTT${?Ey;WaVeZ9AR{rrkYod1@~F)%zR$H=+id3o#F
z_+(ezxDnCX*0w7B{JgE#%HQ8x+tkG5JKOARfZ~JSV)}78RtME{@9+D&s<|&QF;Poj
zKfJQCa_&}X*(dAsi;9ZAyxDyInxx(IC5_DNTGrOl!OQ(}4VYi7joLct%UOjS7nhbc
z9?2l%0y$~v+X?&C&0nvt|GOHroIHW;g5{0}zuI`Em+8gsI<YNx>GI{-e|~)Q^7LH!
zwI?-_i;L^h-|zR=Z`feqyp)0Ahds2u;Pomk-8#!OJM8t|{CIYD_Sqgx3=BI|-{dne
zfFlzUvkkXjKb;;Q77{WgDLHxlu7BV6|Bt=A+&`T`c1It$$@sz3y<g6B?gMjBQoXh|
zI=*<X?`*SM+w<p(cb_?R>Qqox)~cYOAQ3^qL@V~Xre^MS`f6%!hK7cdmUMM-eSLl1
zU)H+JB!-p2;qMVhV|T&9pO3orw`5;mH|zTI^Yf>xOr1JaQ$=OTxzGGI9~!RTVqjp{
z$N$Y7S{Fbnh6c;@b8`YGtNHq*GdS$MwlY{<H*%AUzwOs4Ow7#LYePdqGEPoX<;@Bx
z`S<7NGT{g97CRms12w{y2{SOPxUO@1Tkd5+P||0p=sx^#$1BYZ+j6g0{=fZw)#}xI
zr?N9J6kJA+cKbd3_WvSgo8?aWa+ddnb30$?_Po2VY|7u=vDA&<7xVV^_Uqr?-rgI-
zxnQ4V-Jc(&*L6<^ZB9EYA|>@|snY$xfPe+=^0gr#WjhKVi-?M<zMOryY?@BwqU7U!
znLj^0{q^&Fecp~MdnT*<gX$7jS644@Z{xX-FGFkRjpoNfr%s)k`SH<FtBMZ`&dsx3
zT`xa*vyS)cYio@|*clq?AG1NLr%e?flP+^IFfiC_poQB3{`|+sdO=;nCHZaL|NcC;
ze|^6G-{;Wzd*AQ-ZIXY_CjS}Zisgq6A6{Rz;>><-9-ff-cC}L`PhQ;8!lFNA=J(I@
z|HsJJd}y3k|F81tvuD?$x_f)CHnDPp8vo9v``Ul26mAA(xj%nudS$J{_}ZQ4T9@Zd
zV6SIjD6lSM26t}2!44(%7r(ruTKn~C_@><G+}qo(zOVoP+iLr(sA)?N9B?qrzIG-+
zwc%IV#YL{O?CbaO$=j_tE?2$gn(qD6({zK|`D8(jqPO?=$N&8KbJdC!0fB)NtG>U>
z-En7kpPcQg!|nXuliuz7o!8plF0J=TSKWW!mDuvTOTWIpZhpe?QKzu_y$_pjZ_mFz
zO*eW6V{A?Szu1tFDNW7Ip%D=)zzqsUh6VQ?LIM@)UNBXsuAtz+$jCTpiE}&OO5fRL
zTs%A`F{}&rS=avBqNT09wf=wI)|{K0u0`eLtqTeYD*5>-b??_}(N!;(PQS9)oqzA2
zPp5BfNNir1WPIrGVM(jwre|jwKVLR)yUuH~sR!oET9^4uR`X5zA;Zvc`$!^2m@(uX
zy<2|&><3GR^)u}2_sy$%wbJVF^GR2Bm1h5aB)<PbbpBpd&#cSKdgs-A@_c(|=jGco
zkAc>dpSSr8>coI{kco<mdrvxb`m|}`BbUE#^XrXcUPw1JH*c-@m~`~Wkr{r5haP{t
zbLITg)6;#`53`rPy%nnNH^*QuBZI@<qrBiM0~`=g;?KS3^Xu1DetwpDeO;_o{l7iy
zVs-{)-`%7mYf*3@K(^u6qCI<JrcRxDJ!buyH6fLim1kdX*s#HBfB&o1mo5b@UAFAh
z<Bu!S&(G7+)t!3$@x(7@3;rGJl`egFh;{GZZ@1gL_vYW;mh0u=v7++snn>ebS?g;F
z6C?eWUoL5i&w9Zw{%7~i&FR@sPE3@tsVG=$AJ4$>p#31EXn{HqOzq#6d0CBD!oXqS
z!i7~I4zhoJxqQBsuCDLYsZ(!lO6^WcN&>|VxIw}$UlUOL{M=RLew#(V-|b$1?bf@y
zyG`@&*?fI-bMv#kmo5cu&A)%|_DnaQc{Y(}XPaNYwl?}{iPhC@xwoTUgYG$*|L=>s
zb7`8YnwplDmRItzo{K927hl<!?0(tv1G7v_!0ihQonP+}my%kwWQj`Y>ubIfCr&Ko
zGvA=&&C1Gp&x?g&LEOfi+uMBI!7fK44t&45yF7pD^y%5JudUrx^K;X!ZMmzzzP_%l
ztLqCY(+)H;Pn|w}c_TCXEI-x<&;NbfzJF!>{<>Wi9~T7$2aAe|s(RkqU%$VrySwzb
zY<b4xW4&G7-NC7;ONE4lKzaD=9LviEKi`VW$gEizy!_Sv|G)Q_{`!)+HS_YaXXP7J
zKrPhsw%_Oc`+2@zO7H8wKYwbTK79)6h+VyU71TmI)+4!CP}yw-XuRX|o>j%q&u!9q
zz058-a@x0dcdKW2)l5J9@WF$odO<n4e|z^?yZ6cL^mS!mxRQSd-0Mg3DZ_#FZ*Oh&
zzP#K&yjx7S<lCD_&!E!Mtty&|ijI+yk*7|cOk|KfpxfQueHoPcW*Vnw-Q88HrKvel
z#nsJC%h)(rf6s>|C1qvR+T!Ss>GNyTjIOU<wR*Lvh)BuVub(~@ndaTO(e1iV+157p
z<;#~^`uf*5rJkNLfByP6Z*qKR7&tPs@mzRuaq-s=hxu1~PF7nMoWHxJrNzqm2<W=F
zZ*OicmjC<0y{oTpn#$X|yTgBfdmHTI)AQ)jBcCNw-~au7udT1|zyI&s{I8!*>zlu5
z=2m(6;^JaZ?UNC(gAvl=K=`&Ho|}{NV)pvI%g&tfxw&m^+Sys)K?%@MOl|S&ckAoE
zYJ*D2HgCoS|Ga#CLo+f~gsqQ@ea`mf)vGMq4+ofcy<WHb%SCtjnSNhE$9SyRDY<ve
z8lQs)4@#Nk%m7XBOq!Hrbv_%kBBrN@M>l?7%-`SN*Khsyuw7ou);6~O$6@&|7o7Pe
zwM^c}^XuK%Rl0hXN#>;oe0mHF4ELTJpgWj>VY`x+mRD+O>LiuZo31SN7GE2)b5mOF
z+gn?AeLiRH`;^h4`NJV@{fxJ_wpM++nI0MyrS)?5!JEFb%|I79-rAhrA6M~^_3+ev
z%8*W2*0nV=b8b&djf~owHTBn*my1C?hV%1mmkIAxQdf6BZ}&TA?!#hF(2yl)K%n$h
z2y^Pb#ig&Wf%>se%65l_g)IYZLtVObY1NmD?xoM?mV?rOs;cTT<Gt^Ge0+TUuVvw*
zmUHuLv#o>~81`R10j?_%QNX~!aHk9JV9@C|;K3lK5AHK(&fKKq%`K)g;qb$Nw6tg7
z{*`XbjtktS`%*tVI9T<3Zn;U~A(pfA?c*nXxslxOIcb)8{<`w}wc(%vi-?SSpqq1&
zj&ePH`ZV+Nv$I7OG9ZsF^PRn{U9QT5uiY6m4!6W}vPs?@i`?7W&X#=21zqK_HSg}P
zS+8?%Z2|4P-V^cU_PWx7gP;v<>~a+j-qZE2)_%X6ZgpAv(BZ?Wk=M%Y#3dwF*wy~h
zP*->7<m8Og0Cn#+;3!v~eyk{Yc!(8LZ>0%<`bgo9j*WBtmjC+pcD15&+lt!X-`czx
zf6V^yp}<mxPu8Nqp;y{`-@-=s)0;}3oDkF({WY&!T>sVLe!ENm{{Aj~dP=nP)fG=>
zcD|5;f(<WClEc<UE#0%nW^LqVx2aR7zPh=2xsj2PNzoIJtyx!Bo%`G^rhDnf$H$<v
z>Y2CR6P1=;eXLjd^wT0u1A`6MqFh~DCrzIG^kc=A>hF2Zt<Pd#KWOUd>9JxLzf<{q
zF7KlUOfP5KtABoe{`$ki?O$&s_iJitc})rl3tN_YdfH0oc0MWNw4QJ8@2~&!rzSKc
zWW|aV9($|5o5k=kG}J@;yGSX)VXs;8F`m6&E_wg@^?JSUat4RJPs?_T%F5PWZOrnt
zDt^}E<?TIn%9JNhjXulpwJRwpnN)qrNKHx6u(JBK>wNzGeX-nPIu{-t?cN)b;pgbs
zC|CO>aBKekxW~tOSDU)*NjWJ5s^d>j*S~(g{$KIorT2~>WWE0V)#~+GFE1@E+8F~H
z=vuoKbjHe(B`-SF=UsSma`M-w)8kjU_sey4bzN%XmF5v;W_S<}8AV5OIzzzvvoj2x
zK_erjrCVQ$Fs#@<$8Y()>i4!wmoJYmt^N7wsh7Wh{)GMA=DD|)?5q7f>)eM(P=^cD
zp!@sxef|2cbvZd};%dK!@=BSU2$&fu6H`z-apJ^T28m5-ese0Weg##w@9ylhDtgkP
zlKJb)%c{R$uY>C9{4^$p2iv7)f<|wVUBtk^@Il?W{M{8$o&M^IW@>6GD0Zgn#exQ&
zL3@rCEKs=I8TUQ*yK)$KT&8N}vF!#mb+ydwd{+)MGM9dN5h!a{6EUge``vPF8=E@?
zGb5$Va(1kI?^jc^=h5TG`SBC_HTCtwQ&XRsUf0&v4vmY8`)sA7;}gCv=A)YwqMwWE
zEb{}8KW1E65vZl1F(LQ%CLM23VhstIq5`ThXPIP9TIMq|X~z}oJ~`W{;@ulS-I9}U
z%dS_xyR)-6YD>mMC1vHkGt+(Y^4|H@AKRq!^vRPuZBqXQ<>c-?Xg~K~lwCaLelx$_
zik-#JUrltEyIA}EZg_U?_jh+^ndi@|`t~OBb6jTT%3Is>-@o-?VE8jFwf?$bFscg~
z7#<vlw*FV{+I6dhi^2Z;?E8P**6;tf>)Dx^pj%2c)zsWxUtb>{6*Wuc<@Ei3mfHRO
z5)3Lb3Raeb4mG*F+<$s%<n`Kf+j1>s_;e#SIDk4y(_ft_w2(3XD|vd8)SLUkp!tQ>
z>-Vkdl{SBMT7Q3tqhn)Ga4={@Bs{LtRZ>#2tGnBHZsqO5f`ey&-oF2DS>4}XFCQK4
z_VV>zYsr!F|KDFNJ-utP<#!hLN}Frx>G@5aI@Qa=<H7>RX3&ts;in7?KiKoYGd{>3
zd{AEY_EzcP^K$lef6S&aWO#h~{CVossY~Cy$(d_cyX)Mqz2EPx7S#@u&@fKEu_5u*
zrKR0Dx5KKcb{*@NUq5Bal&JF&)0Qq+pm4YT|6eX{ZsU+wvEl1t4Cg*D2j$OMv$Xn;
zgQ}5LTegJA^}B-`$hmiR1d8j$T)3UTKX=EMZ`D7aPS5{k%v;G|tEcBTzy9COv~zQO
z%b1TbFeos1x;TccEPZ`#<&q^XlSCvXSDrcJv-iUx?yjDmDJrJf*L>#Jew%qRhJoP^
zA7mH>*>8W&HS^p3m}~y7?)0{|(sg1C>z+S3Ir-JSy}wPbOPgka`oj8RGew1k7tfd>
z;Th!W+WPD3>*am2)>7*}>4t`eMs3fV`)=oRxzg9y&X)9@pJ`LM2~>rwjoyChWyz}C
z+uOEY1C2J@|9$D-_G(XeGk0E`i%ZM1^Yinqm>C+XIw2#K$S$f&|M=+WGGPW2hldXz
z-rAmj-}L(3yzPq?E!q?D#2VC9xXfv{(sQz!lwHk^do`bZ*)FV4`uyzdEUVI0x3*?4
zzr5W4dgT7!?{<UsoHD1T6&5fuFc|b=v**o?jbM9TzI-{$IK2-vQsFn(%5##==}BMC
z9+Uu;d!Q*Rql+sL<K|axZcb0VUADIL^rkI&cdeXD(;}uVJvY~S^`1R<O1k`4VN4bM
zWaHCYp>1p&JS{czU=wSRh0LilXa1Z6C5cvU@v4P<3=O~9F<r;dApPM{xBjWOW!jdO
zk+HkWrlv;z`ntXzG_LmI!^6X`?(g5P<~u9J>T(B4A2uu_W5r9A`G%>dL_kwShuitX
zOG>u9l$l@j|L^zLi~H?@%F4>-ZhiGCOE-F(4<{!l+o>~;9yIOZ;^ux@U=b1<tJ{8f
z;h{r^W-&Xgd%F7?Bg28Mk>B>qtFt0U5t!YudQ)yRs50*o)dtmI+TrU~1TXiKGE8cb
ztN&AIDZ_WU)6K=zRnx*EqP4X(>-xI6FJ<O`ivRyL{@3gH|Ep?$e_NS<f8Va>^QuJz
z1Oh;lbzh#%&X>|MNe4B?emrcSI(P2ciOTL;rlz5we)R2axu(g-ctAViU0q#Y-QK?b
zWyt!|=g(h1(kZ;P@^c!v4H$PEvq#0ikmu>(&~UHfF|Y04FPE1E*PQE>@k)rC1{y>O
zcw7w{+~5>ed-3RK_om$4&#t|Cc6Rn_(CGLK!(<-uSqBfYGB6xaVY>jH&H(!zMyvyE
zi2${8ladxiZOKTqI-Y*?`0?xm4UDJGo;97zWMA^}k!$Uji|(M#%(|GJi~QzVWj;92
z$i>HJHaCrjUHs0Bxz^=bkB{|&M#wj9+9V<>y3~8R-pVy=eCAq}1_cC6c<I8x@J9$U
z<1#Q@e^6kN5;;wVuRSR#Y09KYL7#=?<npY}r`P=XcwEY|Xi3<*n3XLpESD`m2<L5&
zzIgFs*40&4L$9BoW4ZX!r65&R)ykbb`_7?NE|Bq@%S*kdi^$2X^PH@fd1{L0vS3Dr
z58gZrAhRMc--GCw!wa3;pA_v3iHXtKetWHL^|vcL)^3Pd_t&Oa##Mv-mT$hcD>YI}
zL*ql3(w~OQFR#Fd`Ss)X#k_p^lK0=V{3~CHu0%8$82+uC_!8tIG#r0*p)-5wiwlm6
z-TSAh%(X7}%iA8Us;XMFGbU<h(b7+!Kc_}cb8>Q;GG)pVe!CwB3ckJto$C=fE%f={
z4I2!mPM^Md&z?Q!Ze5+1uVMG+gY({x$E0s<&7OX4zWw^uchzqSw6EF!I_~VMRjaJn
zB^f4xI%aFu=%l8nzy9*_a_P1Ad%wr6jo5g|L6U*tD>JreG}lm3aRH5KFK}#D@s#U#
zZ*6U@db{=dmekW?qGDoFdSCh$yZ6uX`ykEA$_mO|Nl8hd_9&>1eEIU_rrhY&VQYh)
zpPT#jgmV9kb6;jHcJF_6VxqF?`qQUQJt^D$8Zz`3wZ&uN#EJLLeAbkSDacj#pBM7|
z-QD#&@2v<_4h;#Z*vP@q@T(PDIW#*UDoShmY1Qecmrj}_1Zq(GEf2P>`Vvr7wCSbI
zj~O$K)3xmE;#5^tt*XDR5z~oSpgym{DKj(k*Q0LzE33oxOJ7_#ShDQ;p3mp3K?8a^
zrzfRGo;rIrG%qi2?(>}6(+)qp(8S8k6EX|bx)hg_TUY!0TWs;&w`JN|TBo`}y>5N%
zDevj&>067R`%RrP<;2sXlW)sFA)a+}(^4T}Vbi=j7OJYMpqU>=M#g2uy;z1iH>RJL
z15Km&Ef4OMsx?0K_+y2N=l46s{hKy#HqE}KlbVt;<II;?iHF-(dQaEelpFo><x461
zx;;TbL0PuRk<*%*no9ov{jRN}b0%OVxc!M%k^FjAt?bz?u7B;*)6-v1X|JE*!@_W2
zy&=X30s}(<@4<ryKULUt_4S1X1x*4?8-WH~US2v{GRvQnpMSmNzdiE~9B}yh^0K?7
zrKOjL#|NjGm5q&!S(lb{s%WaHxcJUCyV@zNo^|c^*6iiZ?R+y&eclC{pgD5HW0IDZ
z)|K_~_N8xbTr8OS{^5hB*VP}7ia#yeJ$25UHS1z`pW3AJ_t*9P*Jc{0m;CsU`1Sq$
z_{nO%MsqnC8txa(z}8L<4Gj(5q~p!V$jHUR6A}<GVU~G*p4I8+Ix#x}?(QlLE-2Vg
z_w#go*0(n|K{KYHf=xzd&5j)wd;k4<EoEJ{=1$)Bs_*aC_S^rvQL-)E#oayo{5)IJ
z^^YGt`f{)O{ma+u_lKpXf-<M5q-5rX3v<-x*Gzi&Is3tbrq|iGwyf;x>e`ZVQK_}H
z71Tr**NX`#DcJ&AI1idM2aUL?F)-Af-jsXWOct}ye$ahxo~`!w+q#fMEo)u2V$~|I
zx3{;47Zq)qG-=Y5IdecxwUpugKJP$yd~K-rbiJvkp9Y<trklNX>h$T_s;aL3HXmEm
z{O7IF-~T5FlovumrkLg2NLX>BI_><twL6QSuUfOl2NWl>OtZgip8wZ}k&$tej<=|&
zXw~<-<zIh1?w{>vx@gTBA5ii**vt-^_W%2P#pKjTP=jirRq>?BlfNEd=Fhmdr*hJg
zBS&0V+1NniMxc(~)&2GLpedlGOP98JGlC{XuvB>mct2Ix{CYCkKZ|$ie5+C~M@Pr5
z{(g`Ti;9bV)2m`rQkJOs%vjJVtR7eT_qO62W%oXhNz44_ue%;!A1kgG^C4~7c?~_i
zYxDpANw=Kq$17(O@%PtP<GCp=b#?oW^~q|tA6^JL8^FZm%c}FD;^Ngi&)D$ktpF_<
zLaq?m85*jvG`<)bqBm51%{n{F)EhD(xN6-xv$;=78yg!z4Y_4LGmEZ%z5n-JdDYXY
z;h@=S&q-psQA?iBtM&u!irPE#rRnYM`QafUA#-m(SpV$8LT4>Ky)ZYoHt|z6-e{xa
zA1itPK45A;tay6UlL8A7Vd2G7rc9YN|HFrZ%asfaSG2JeE_W3Ak1qzL49JqHyzSBH
z=jKezy$#B5RbO5xPCuP$b@??Y3D^GqmU+01ch~!Uzq8i9y|*_yGcyy^12D_Kr{f9g
zon2cKxp;5&_gN?QzD0C#y(gWUW4ZXlhl1K458Gc|Uhcm({qv_!QzlNlsKBqs!NGAs
zI)Bf?<@4)qK^CgLwk~-wAx3X{S9kZ*vfW$L&&%E1rh9smh@fC#wt}sh*|icq28Oz|
z*ek%&cXupz#;lvw_<62%`Knc`ytd_PtEjkic6ORF_roV7K?^!Tm$0pj-kt}FKu`xW
z6RF1pI?G{FNMz*7udlCXzqqhaZF2tV`u+Nsw&jL~g_)gD{QUamt*xv5=2#?J9ZpwK
zQ@i)!AZy<C=*P!;vjdo4$Xb;IfaXD}zGQgb|5I1C`>yH!`QhtgR{r@@6FF_^gb4zw
zs;V!W`Rxp1co`b%p{rz2s`3X?QCqWAU(RNH)X~AgD`~Xk8fbD>Qtu0IVPWB~KcCN=
z7C-Y@8@=66RaJG;k`pI9Qq$62wTj0Dq@*lSSsA%G?bn;l=Y5_Xaz8WAHd@)e@5+ON
z%~K~#NU%C?0b0(YsHiAqk}-jeS4ze6Q-zI|j?NX(IHzv(wiO#TTqsavVEEUKt$NHp
zfjXCXe7UQOO9p5*&-lUNb!D$>Gcs08nl$Ok+GulEH@8zSORhz2hYp{&%-7V_oeEz6
z5#;IF$tPo>u>A5$&`Lr}%bO)~3=DPHZA@4o_2XgA{e7|1Qm<Cp>*)AAefm^OUw{4P
zvaQcA8pQ6aiL@?%7vkyJ8KXD-PTqFV>Y!=5(OQOv;1y#*L6aUmek>{=kYFXwz_9-q
zw!-6k!KWvlt*xz~5%bK<%w@%UK!cPxdNAkAYd#(o2epY*UjF&{dD4<in~YjpTCP;R
z11*-!H+~8pP=0W{sk!;-#|jZy*|kfSsDN_5r>7?<r@S;_V0a~qt$Dpq{q{Crb&0@;
z2#xl`3tzp;vXtQy6%(s_?t7K@t=j83b7Y=Ad2*#n-`aXNXz`=@j(W2lW}pRYt5#`Q
z&h=wuVbL%!2yk?C%(}N{=Sv+1hF7Ym^H%(aF7822T?O2J^K4e`ez(i}_4W1n1?CGL
z|C**3TXlK9q;=VwT#b*p$NS~?zuT1>2^#-(a(3Puk}~b^!xhC62e<NR{P_0w)vK)h
zr;_F0-bC)ao3}GYZ)c3&+Z!95LqkKe?(f?>Y4T*y%BLq!QjQ)ydh%hxjB~6w8Ui0|
z4I23F%v#MG6YralumCi`JZFxKs)|a*!ZSReWGdJ1KELLZ=h}r|f|vVgYG`<T{P+>H
zxG67h-AmB$4A!2)edpBFrPK7|*D*4)t%%)Swye13(7CzRTMHk%ftFfEMn-~0>y~;?
z2leAX$53l%oG4MMIkCvK+ob+qjjUZwM8EB~8H*MzQt?bpO^w=?GZVDB)G+y2#{YkR
zPn|y>?&{jw)zx)ncX|HdryoLBhp)f3CUWzZ)YH@0%AIW(80@k3p7IWC%f0>T>)X@Y
z4-wZ1dFTup@Y9Xm1zOFh8@+AK*08v^byKE@*nT`B3|dIB@6RXiuP-h-2L=X0CN6&n
z5iZ9;!|YG6%p5R0;1?1W{<>KHuLo#?r1ZlB$IF&>skgRd{yH814|G0%=J$7Ze_j7A
z#LUEGQuCu=ZPeCN35qor|NQ*?^-8e+RnV%5Yipxli|_x@davrWu4m9}v)nJBI{Epz
zx%bYs^jnm_n*+KF{r;b4=CAJV-rm&QJayKrRpN0Kjz^Ck?dtEp{=V+Jb?&`Ak<ZW1
zPY2DjMqj`(AHdLH54t!TG@*9?-?!~mKc7y&x;k9HSJK!`*{x^CD~4R>N%QBg$KEZe
ziL9*Lsim#GerH@{<jPN<KFzwGn3xD!C}V!<K{Kex_1u&jEhs1`Wt7qp6cjXN(xgQ<
zZbU>*OWh&B(D18S8cVl0&!MVn7sz9ekN3YmYkq%9?(I|O&V@xp%#f>mBDgkUqtkT#
zc(b{gM@~*wzq+^jd-gi>tScU(qM~s+P4*QZ4zin;zl(W$bMx|ZSSK`RcYaWejEt=M
z|Mz?8j}M8U<XKr+S@rAX@~d03!`sd?GW=-7GKbG_z&GRWuC4PbpGn$&K4T182MZd=
zn?8LxXu$*86x7x1Lx&G<&A-1dd)@B4d9JRml^Z$!CA_<{6SS;$SLy3zSFT){_5Q@a
zzrRCcV%Au{+u@wQ@8_~5`FYOq`|I|$@yTWxNwS@tZ-2jpiGhKa%^XYDxyB#be%_pR
zHs$s<ozs_Ag|5D`++Y6do133knOk3XfBEv|FVI*wXfei~?{9mLfLe>6o}M;MJ0lTX
z`5_Qm@lBmMbEUF-A7~{>)TWfqJ{ikJXU_Q4e!H38)!jWAJ_ML{ZcgS7seLb=oSa-_
zH5ZgWUWza<ykb4QE%$Z_3vy`)W;g8LQSot6*qVrid-m9X(jZ^EGic=5&8<zY>V=}E
z4By(Aok5e;d@s!{zqc~?_O_XR``)fvwaTR8Ljp*7?C!F)k}`J1&w4=XA^!dSoqcwe
zX_3|3Wx<SBoRQWzXzS{pE#YHes9TS<`BJ|j>#7!L{^{&2(^YHMgn;@9>E~p6Wh{f%
zMr~d7_05LF!=PE$UU~a_0c*=aOKDwQU88oDtOPl|tBWgkM}gzTix*FwJbCePzr9}j
z;Y85H8p8oz%n20+h6ijsl146qf`V1=c0QjnapJ-kFJ8R1yT7-(yjRNfly~W~$Z1QD
z%h$*B+yC3~Qsl>qGiQ7vr!8gW7CZ5<K*QMhv$cJ4<TNq8m=~>}<q$PEyCAR4;L{qC
z!OQ(Zv$9qR2@8W3j$gL?!2Iyx!y*eAPy&@Q&s+21LqX)U(z~D$LuL2Aij@NYR&Cl8
z1R9-eU}V0sF4p?8B?H3`TWl3*!DSh~cAe9c4nGX=@#z6|T<Z=UKJ5FPamDd%xwn^r
z28SdW7_LO~U`d`auBbBx_lsX#P}~`#Cn_#}`fVAgzqTnidRnTclG37U4plihYhK1M
zeC;^=Fd!sk3TS#gaIxFU<l}wICNnUs2*;cNVqn<8)qc3}^8AfD-dC?)-M;YHca*`I
zTRV%F>&5O;IlW0lNNCZLB`UQa4ze#Ze%M_0?#@ck1i+P*!JuVaAt6&h`_ndUG6K!x
zIXXHn6MmQs&DV<-DTRiIuMS@y2bxy{?bn#58$IhBGsA)R*m~g&@^g+q2JHigtA1;m
zdvnuLNB-xJU)jj@yY)&fZE9iyx4A<?LY8dVViLQn#Pi|9hoA;NX!^xU)Na+DJ)qMD
zg6rz`ZOgm6O3imx#(@S#Dch<oa&<ovO*1bYDN$lzsC)UW{}B^7gCP?c39DAE+EVp3
ztM=c|=gWd?qB1jAg7$cTDz>i9&WjfoI&V!r&IhX7&fEQ70~&Y9yu9osXxaX=v$L1q
z-Ch1V{{2lJ4vq^S9v<GBbycgm^+V~}=<U~x&)X<(zrA+TCZoMS9(8N!>Rw&kZ@0?&
z{hr{NGiPdPY8rxj`H7IVw8$=EcwlXkdCBE)JOA|CZ_VaDGS-XV2O8l6ZI`hBee?X4
zWxmpP%kS4#{rmYGH0PIfXGbBZOaYCH$y%3XoSS30Y%(M!AX6n<b8l~hOqDRR^GRql
z+jDVn1SBLZm}Q!+23lS}4K(v=SNjXJ!Ui<&{t`6s>85-cvjfkt@7yMx(sy?vpFVxM
zEV#z4pkRZIT>qlQi$RU7$jxb*nwp-myGjh_ve|<U=qP=E@9(VFy;7#2*$eUR2l;w&
zdsc{QhiT~R`_DGd2aP`+Xk<3cy=7wi<$^P4-Q~`rrE0#jmJ~idmU(+y?y|{@3?I0$
zWsy4#n!(F59v$ff%|$F)yx8}-M0jYZ>hjBx#jgusqaxgODmFGTzrVfR{cP9mx1be^
z;@uDQL7qjOW(G}^O;mPY6}mcX>pWSroEhil*{=Th__*{cR)z!rA-hdbB8Z`Y8I;h%
z)<$WXnT3H?K-+%5v$&z50X*Mie!u2&z{2vmcC}G?+oK`7Kf1+qgF-{6-rAnO{>hUR
z(D<08Wn^JtVUdN*vf_u$mo8rh?P=hZHUkYlPx^9pzM^N;o{Ej2mScEa<<S(Snky3&
zokau%7lJzCl9H15D>Xd6zq@OibwvZTNcF*gqy>v8Zr%6Jt!;(wY0%0T@vNHu<Bu<@
z&#wu}*7$p6WiS^PS5QsO9#A8B_UvpcVY?-(R(XL|Cp|km8&sh~E3(T-!&BMU)=a$o
z(qt}|{N~KdYG2>pzFxw{!0=TJ+xY4ZUC?5Z$jxb)r>E)iR$0hjPrJQsnqKTGQSGo5
zYu11!Ujvu>%{56n!eRUG$7A!751>)*x(I9${$N_AjU1?94;er%+I<%^%bs%^wAdW9
zDr;wq-sPDLe*#cTP6mcou*Iz?fl_e!++1t*>8C@D3-%R1_X92V-<I3j(xPE#7^tbK
z>E-DeSW~lSmRW9=m84z5t1Bx({c_k$1AE<}hXr@Or0akJ^=s}5Mur9dlCfoDHqa0Q
z=$^MN+1K^v+SkX0OP|irVD9%@9y}@K_BJIYrL4BI!9hVH($d<eH}Qxc61SA$i=3v~
zet6-G88f2p&xQ_^FbJTB?t}kZ%j-9WUT>E^KEK#cb4u)m3!0Z3UyAM0OS)o_((3eM
z@`RUjCaXQ#_2}HQylo+yefC7Am2{^l3*;Aw&yY}MyPd=N;MJWD$=eEljSJ6l>q{9Q
zy0zL;j7=grY{k<*dfOx~Y8utO-p(Gk{z=T7_dn-6sl6zWH}5ke!vp1;yUX+6?RvdV
zCvua@>aew^&ds&HeEIU^sI}7?8ymN5-I{v1jrZq4{<?sYS6g1ZeS3CQ=;}>HPfzJY
zZCUX`=GBoKHzL~F+l?(OW=xzov8S(ZS=j2OAzFWr%NsR(x2pYB5?ArCb<4JG&wjmL
zuW!Z9py$bkvY1f*;H9PB#@W}_@bL0JeR6X0&QGVbiys_lTob)r@A2cuFJHVk@$K#H
z;I(1heyzI-UtL+*)6<iZk)d(;@ZrjzPp5zGum7XGG)VL8*|U)wlU(aQcE^j%J;@Wa
z`l?a-xjAocY*Yp{<Gar>Hh2f^M6tM`%D~EM*1LD_LbRrun3$+|s;R3_R$04t?aQ}s
z&u+`T-Q_dKuus-{n%B}vAR}Ct8yq$@H-Fw8|0k*L&trMe@kf@WuR`Y4e!E#xQu5@<
z$;m&juCEI%Q8M;f8R8Wk9o;8yA6LS~5VJ|D3uWAQ1$*)HbH2&R$&>2)($de*n|nRJ
z{_ouL;yMu%Hg4Rw=u_I9sI_4wOr?*uUXMHd;X?r^bWKdAEOzf-7PRt7@%-O0R@T<t
z=aSie{rkRu{@K~)>5q@~X6EOEL)Q{5bRDa!tKHn)?^o78?ln*Q{_gJ1-|u#R{&qWm
z`TqU(*JFx(8(R%N&$TR8)8GH6sI9Hd$i`;Q#EBFC{C!`4{?E_Pn`?f4x>J1K78JJA
zbfc#&TefUb@yvyBH6M>|*|O!yuGi~M&oa%vbnDiyefy^et(+ojT_zI3!SHo$$mil9
z<P7@!>x;$x&o&;HJ3Ud^-KhH88=L=sKJR?oXMO3)l_^0hr)<AhrR{I~HDuq%-h7d{
zQ9F{4_dQ*;dfll;X7){acXur+p5Zua)+{4S%bDN4eOnW;QR(z_{qtR-+MjNouiN&*
z<dw(H7`yi~gH}#ixpHOZ3dRQSenwEM5$1#g^_c|)2EV_(^<EluGI#skX<M_ei_JAr
z_VMv~l5YPyGH>V8X*v-b7QB#2oA5Tc?i&LGPd;cZK+(=QUP~uQ=j~9OJ9jQ95Ui}N
zHy1oSwCFMe!w+$0<n?3?{2wlP>!*HvbabYD{lCideZ9S@1qB9Ivr45-rA<5B&j0-L
z{Qor<C9gD2R`*X!Nl`g`_^_m$+&TGwAKK^G)mqK}^F;l;<dXXpk9*}`PRnLs`1fBD
zr72m{;I(wp-QDHOmoHcMEP8aLQzvGJ!SC<y&%e65`n=`s>({4eZJo7p<w~U>?ohqy
zn=3v(s(G6oe|nkk>`yQK>vz3Sd3EH;lazlyj@!>O_WFPO{=aGcwQrImx8+1ySzCWT
zq1-Prmy@9&@}sc>EYv`>{DZyU|6R@6>f_@RGfnw3|K~Ht=a;Nqs~f#7$1^%Q8l?5d
z<NoJII)z=A8y-G8%T!xdR`%we%HnVD?#|x-@9X-XKhM|Cd%b?Y-TvQq-+x*x|98a;
zmo(62_33|qea+0w^mKN1)|z_icO1ik`r{~tZbSE_%a<p||NAuk=jr%=lVq*SmV~Wd
zx_!HOczkWCS<a0Kw$<OBfbKv}H)8hn^8<zH?d|#JWy|kO)LyqkDK<9t=im4B^N$@n
zR#H+TGWP_}mh$)aYF>KBpW2vw{L<aKb2q1-f3`aQZ`Q8eyDwk4G6m#Fe)~TK7iTgA
zY)8wq4=#Q9*k5n+{cd^uyWQ{i$=Ftz{Qdj)<?Gj{!}oofdS<q{e)+x1^i@~0!q&w^
zmT0kpiUw%LefaR<o<E;XTh{(6$=Vt<YxZnVrdkuT(?~mf-I-0Pr$M=4(d3zp+w$(t
zN<BR-H6ueq-GAPhb91dfpUtl`etm82=^sBTtgNg)t@N*5^}>f?MKo$A|Fb_kE9=yq
zoyErK=jL3=+B(H+DGv|NlauQ6&-j|(ow9s>oz?ZY>fDPneKt><HciEIZP@8WuHBce
zUj2IR!Jl2P*LklD(b_QqTpX^A-o7ko<&uRD=L_#VdGe%+XLfdWRdw~|+}qniR$o;z
zW?YbmmMA+ue*C!S(<yDwN#^$|ls$`{oS0~0Za%*_FDEDG*6p-e=J#uitG~VRjE|4!
zleL;sv~x~${$5j1Fz4<6`)$hUr#8ReY_5FJ$X;~b_WP3$4-dPl8=u|xb!~p?)m5R9
zJBw1qbfZE__)4?h-PxI$ljAeV#N0gn+nbw}f4^S8|Fh;`6YD=;wubJ2RadjNE>Z@i
zSQt)QRJ8NYKIxhNYiED2{`>pql`B_Do}QIpW@ZLO+voH4^E*2`@6>!gyE1I`%XjbU
zo*#Q%Uj3+3z3Bbk@6XQ6G-kcR^mX0l&Bo?;OM*fB>r_0a>BrC8S^WH2t9aar+xh$F
z>eoEvwk&%S5m)_oYm+zQ0=u0kt9&0Yzqz$_^^2BW7p`8N>e?;#^xyCI{#&DbtE+#v
z&)fg7O?p%2<z<<x7RSk0m+64gblu<A@#%MWmAXDRXf7=+eF`cr7x&xEy16<1`9XI1
zGoY0H?Afy^UQ0oT>r}p4xxDKfOT(_GsM{6vP91D!-<)=K)*|B-#mD<(PltxbPGx52
zlUPuEkd2*vbN>B(AzD-Kl-<sa++CJ?(UT!yJI@8=o<YMQ$pxPi<EmaR)rs3<@%j0A
z`}a3DZrsSj$G0qMt)H_bLrfJ~?pUzT=F<sf@jr8eR!(V`t9nr%z#PK|3N4()m9>%4
zr0RD&K^gv^H)?W@nE)yh#sA1Mmz+z#x2N*v*6i?UI*~yoT*d)w!>aH9?(FRJ@%0rA
zVPTlQuIM7N%Nedr-<*Cv?!#%1Dc`MXetfWe|NP9%$?NO?zK-0G;OOYez@UO=SIgz)
z{?B(lpLcro`h8I)T%~D0KRx|<Cf#nbZuGV%pp}{zEg2a8bfZ)z4F9(tJ9aGR&JIIm
zWo6gp0qOH9pUng{lul36&CJgBPESvltN-(Hjz!_37bXl1r=y(F9JxMd<&<sPw#nGn
z?Rg>c%E#Z|zpARL=+BRjf4(fY_pPt5ud1&8eD{5w`Sv?S-tYGPepmDJbi7}3a`MHM
zX9ONUeq8x<YWO6T{5>DtCOtVZQ8_a&&+hr18#iuj+0J-i>5`DuSF>DEb`b>Z|MmO#
z=E~2{WUNXw-oAb7`aIxxpPcQifB*h{`TF(giHXWH&GX~l?fHBzWcAfGF*`TCu;B{P
zn;xt+^;~7x>Z|v@zqxyU`LbopwD}qIG*Q>|Jy^8o$D{7d%*>Oe*JG!fW?x&fb*rhb
zukZ6Ynp3@QZcKJ}Y`xOGY}v9ibFIybpPi{pcd;=rn4mtt#t4+HKzoy8s^4yPO%G~_
z-CZU+mw{nAuQ^JsR}gsW>8Hx`J9=mEe|k1MKkfWHTTu30=-eKpH@*1v+U?7t);{}o
zJKuk2%(>0y?PjyfRVd8=aYVi7$A^cDCNnbVWunITfi2P!5+3pK@t|V@K-K@V+4+83
zqkPND%cG*A?v?-RRG)WZ@ArGNjnmJG1aLDH{LIimZb>jO?D$hsTAF%sk?YR?|9%Ir
z4ZD2r-oJ&<^LIRK%el2BbJi;c2EBOHKw?;S7oH^<7%KYF6Yc)LzrUl`h9B~dJ!fDr
z4n|Kq+xJ#~f3|M-yHk@?y+L)@T<h{>%a^NfjnZXiX3oscKHbJE-F0qBLch(Y6Rh>i
zL$sbQY?u2be}#eJgQM40P|Ff!c=BuZ%S%gVnr4T!wY3#}dU7(R^66B|f(H)Q)<#eN
z`0-;&NlD7@Z*NzIt#(}=w4i8b&B6PcQ@v)+ngumc?@xU$th@!$AM_S4Ui|XiJHMqt
zpn82$N>P!K=cQY>X5G7YFX#5QwI^KC8X!6JhYUl)FVwoEAn@6_xwDTQJEr1UTwI)X
z9;0PEqtS1^-Q4H%s`b|I`;~Q3lYwDRJ8I4pU%Gd%?c&9Y-|yM~@tE}H>hJIN{QY)&
z=8PF0_4W1Zc0QZM#62@pN?Lkz;p1aHJv}0GnHUaKOQ0pVUAuM}85m5syxd>iQ?BO2
zK^dD0gR^JP?tIjxZDe6F<9+S>YSwV0$y2<RZrQr^>5q?(U6(U3e2`ljwKh!K3VA%L
z!Ta=s2MOQa-k$EYbkgm--MZP=*XdeyN-o>K-+s1v{<($D?U(M|ivx|={!c<#%5s3U
z`sLE;n<_p&Iy2w?|DN>Y$Bu!l&f03ln|h`Dea&<0pJ(&yCWDrOMs7~?jf#%GeC0~X
zIZy)_+5|7CG(uT?`=BXQYwDYOd#!D4Z9OLmtNW!qJk)w~e|>$}`ncM2H}~z^7qa>)
zs92qNiYHWW`uXZ*AzD9oGcwFb<8=ic+X9MRFb=4{SFN73Hth6~BP|;Z<Zs^GoZjun
z!0^D{;{SOTl){*Sp&-%##Ssh)3<{m7F%~cZOX6o>@LAus2sCy8wh~0F@W)&58Ge3y
zcei=@-BM6hG3njAcW>_OG`6+1U3oQ2QbNKbIy%}c=SDz@8pDCq<yZ>H_)|}dyp~?F
zJfF4o*6(?Hp^b$=_Gx;tvm!UA!P;a~!{cT$v-73g-Bl_nFYoW}?!GPm{=BTMQ6*Xo
z2U5|t$;E5{7ikW2rDbK$URxU-yfWm{g%9UvUVic<WfG{E+`D%#=)4a`D~1CmzwHY}
Vm2G3@7fk|r*3;F`Wt~$(69C(DI)MNH
literal 0
HcmV?d00001
diff --git a/Code/MonoMutliViewClassifiers/Results/Fake-zero_one_loss-20160908-100043.png b/Code/MonoMutliViewClassifiers/Results/Fake-zero_one_loss-20160908-100043.png
new file mode 100644
index 0000000000000000000000000000000000000000..8378bf5f9d08d4cf686e321ef86c811adb4da78b
GIT binary patch
literal 164993
zcmeAS@N?(olHy`uVBq!ia0y~y;9tPNz`cWmje&vT>sI&Y3=9k`#ZI0f92^`RH5@4&
z3=9mM1s;*b3=I5<Ak4VJet9MXg93x6i(^Q|oHw@}1sfa~j%;YEKYu*k_5e?3lhljS
zbC!$@DBwf&_uFVf3^mP+vM7oe8csFvp^6-kxPYc@1<wmqB@8{I#y~@4G;E*&!7!R`
zU?DM@r(hv5T2R14Vzi)u1;uDV0Sk%If&vy2qXh*#Bt{DgSWt`>6tIvOEhu0iF<MZ-
zLt?a`fCa^9K>-Vi(SiaN5<{+_IB@vh-1h4wZ~rsbzn}XurLRRnvDu|*0jH^|6Pt5Z
zhh|fd^OS8X7l!<HU7f_^C2AU)$zyt5Ao+|6hv9Zp?ZB)q7pIAZfB#)5uCqL6dD7Cb
z<@Wd2mG6q@uiN_VUUvPrTiNTs+&drX;_^R<$x09}U`!yS;%_(S3m3eArGb!&FZyZ=
zgz>sVkb#hji~DCZ_~CVj3j;wFqXB{zg2OpL{zrC;>$mBgj@XpqnOXj{S3q3+c*TYP
zB9YSsg@l4`-K|Ld_WnM9<TS&wH#fxXuFsZP-7T(v=*$_O;N^ay+WcHxO*;R#|5JZI
zV}`_uO+C!)e0#2Z-gjo>7qiUk>tt<gZ6{8j9)2sfa`BFxI~RIQ)yhg$ja2^f?ymGE
zoyWhvzSiH}oweob^exdFlUQF}S;;IdEq!8B&qC++X=T&BLbI~8QX<_#Lat=*|2F&A
zUENo)_ctc9|M~kjaG8(fiA_CyveryL^6UCLJK*3S_mBMlNPMr(-Mg(*BCox+Upi6b
zW4xkgP-gkVUPaGK(vtk<=H@3h@kmQc-`QR6pDmsG==A*he?MncyNB%ZdcC)HF6U|I
zc0Sjen^FxE4lr!}WL|o%YU;gb)p~jtH=9g)aJ)~pdv*Bwq-SSlu75i#pE);qjY{(S
z)ZXilCPm+W_We+R{-=2=>gtQ#`{gRWybxTpc(I_caPx)@8^SMmSIvG|H9sgg_~O3W
z>LtsTEy};YucNcm@%p;h(BlS-bK$<}cv0V9m|5O{B(Oj0#015P4-Xp8{W{(+pL}ae
zriO-w!`i5=amnXj>|d39yf5R*3PG)~H4(RB0~h<W{CqyY-k|DB#+jMM?&;Et{!e1#
zm3nYzXR$`~ww%oJr&BFUUI=W<yW4f+Mudh)*QIxUE2S+86n2%qW)l~me(Bw*|1IVB
zD%leg6K5DCGA&xX*z#Ccz^v?+NBcfje|uBeySK7B_vR*6h7BbzgG@3mESOU5oUax8
z{@1$L-4o`{?R~%RH(%_olEBr`yGk_W?Cbtm?e;{<T<aNyFCa(O$pwzhU2FP#dR*%2
z?39$14O31`xPC?Zm;UB$+uF8nEzK-<R`>V!|MTUtzl2SN!JfT)y?0x?EcII$aNzXm
z)gkM2TPk#~&$O*J>*?wFaFAVo&$QQjU%q+!HZeax{?=WMiI0w*c`X%u{`J+>;@fg>
zw>>>Q{q>!>bML(|ZQ8xNI<x%Y*2;<BpFBG|o8iN;zZV4dMwaY-?b<uvYpT}XPjyHo
z^TpTd)63Wqk<#IDc}3vj4P|emuB?p~FDxvS`ug+d&l$$)d{U-aEYZ=?5m8Z#{N`HC
zu&v(amgEIX)*^bbyIS;OcP*&-`N_b@=ujgwd&pb8_<cR|Y^xUqE%h=mHg4X$*|_TK
ztJc%g^`-Cpzq&envFBv94VyPNx3;ooU0>JhIay6nUEO{0+S#+ESB0!>I^Hk;xLbc;
z!|K)AB3!Ji!q#?a1}}TD=h#GLcL71c#x7B9P}bGc)BEw`aev|KYr4(9SD)<^R==<^
zSbd6qyc}06Q(j))k1v<~3x9vh?cG-X{@&3IiH8H$Mwv!LMlST3X|y72t<<kCFPpQk
zuUok_c29*N6BE;e7cV%9i;H*c*rA}K!?QYk{k7Hcd#k^<>73qC_ji}u-G6_7E1otw
z)+f6<tnTZp&@b=r%ZIKGYi(_1m64GN*j<)e^Xa7ei4!LRUe5*>M4h)js@A$0r=4l&
z@8>^r_H5wFAXOe23xUYU$W@;uwam=KDl030d^)YqYnAu?-CYiD?&juZW)UvdJ$v^W
zCLQ5ONlne%!pp_gG;yLJ7Z;a7;Ukxd%1XzD0SAsAWj)-^@1B>p?pk)tjsixIE4#b7
z&zw0Eu+WLM<o!Kaas9X}yXWuRx%0=vcKHjtO0#$D+zHZo@F3&a+2+T;y}i9v?(^;Z
z{R^YF=M|Kfw>vFtSiD&I)wQ+Viq35c_V)4XUmrVuT-n4##Lv$!KtrUUtjsMSK;YTA
zxvQ_eJJKl(O1Cw&wGSUWU??swuBfa`ys;q>l%J1Pa`!KvYhAtw6vNxLwJlz(ylBy)
z2{UJMGFVi8Qn|G)m%F;UIwCrHaqR9g4`1J_7V|&deDdVUgV*c#yG_*!T@ax0;N{EC
zjmgJf)tKFqFlv8w`s7K@soLS!G|Ed$TXjy)Fi32Q`uXkcZN<|@Nl8gpPR+NeY`SqH
z;>XXQ2Tz^ix_0f_hwtBypPH&|dT#COx$F&7rig6GxX5H?X0~DLR@cwZ&Q6>&rw3fj
zuQB^CUiSZA?U(oW<4xtVuB}=5QTEm4<@`=gP70orUe#>USzQ}mR9tLW{LBZGBffq6
zwqeVbmfgFpZ*9--zq`9!T-0l7JHPy+>+$ui`}f<=nKS2$6<fu$1(x~uY_6=2m%n!H
z+J;S=oc{j$YM6h|ruTXDt@FC7s;q0Hx3@JnGxzlLY&rL~^<`CEXJ==|?QObR;p=!>
zoj|F3QQ%^?sN-&hlO|8TxF*v0#?6}tj~!!6OiZ+>`?KTPwqN_alaKW{PSpxk@DzIV
z=+Tv9XC|q7e~}9I(hghWP*7lSYKkUvadGjL6@kpcYCacs9h;CUsi>&9qxd<W-JcK6
zA*(_-j~zRfb$@5s+gpwc0}>t{YGpgBsjbbe?AGJ3HS20ZULId{b#+T?Yo_e|*7-kQ
zUS582S84VX&0w}^)24B7aUFVixc%#{XA_m(6;2yjmA+cC+4t+KtBHAe>t;>&{*-&s
z?Yb0W#Wv%jgam~(Yt}q?@SuTD*6P8bR&J~FqT=H19UUAM6%_{#9b($HZCl2j9foy3
zpNelSJ7xN&k(phgC7_r4X>sVKt?N#lJb7@5=VVaciinCjbnTj$?<|vpvrMy1Zi&U|
zFJHE7QTFw98sY0?K)GvuobA<j4}TdwnR})DpTQGbO`o4{9zA-b(9$q__Uu<X4i)z)
zX2(CR`f_V)_6*Z(v3r%zWg{XYR@hEobZ1YcFf$uZLwh^B2p8+AX}aBIZ*M)ku`yXH
zH~;Rg){V)>7ZpA}wyJdh=FP^t%HQ`DKR@?!kDHel*RGP6O<q&AKpE@gNlxA9ZC8H%
zVcaw2IiF3mu$!yv%4=y)PfvHBtmbQwe{WAxzwXJsuXguozr4?U>Zi7v8k-Xb3oC18
zk9F!yGfqy<jH|0ePfgWc9<{yp=hNw{N)r-KmH&KrxLv}kMB~ogyNOv@QH$~=k;?DA
z7VnT-$zR$cHzu*F`OIKYS64rB{J8VNfE8DtKYhB;cedG$jmhk*LRYuFySv+YVL-zB
zdwV4;3KaU}Y`czji)YXI{^{xIj0+1G_w3z!aj`qUP30#RGcz-Wd8!#E+1Ggf|M|>+
z=<wmd#csTF?Ca%DPt!eotXFzt_4m9hYoo*0|Ld2r6q>B&>$J1z>4m-3<q?sQiMO}q
zN>~=Dl)bspC~IAI;Kq;t|NTWKsVJJ8i|a;jJF+%<`-N4Z+7i;z$%or`CG2V}Hf`Q)
zm~};CYqn0*77qE^FM=XmtROpg7Ny4QD&gc7*E_PzcXq*(6BEU6b>@G5cDAFVgMq=t
z#pS@&tD?vI<&WRlSu7|o-@jyu%8p&Tm@1~3JbC}Ve|7l!MU|hQaq#oE3oxx*xw50b
z-~IWyxeuQ`TP8MJD|FQY@9BCQwr)MTHhTMnNt2qkW?xq_GTL-wpXVeN&q-hQO~1W8
z|MA`O`$reM_k-N);^Ok)<>lo&s=jJX(~WLxWM*IFGt(&R`Smhi=lOvpB__|#&Sp<f
zPp|oM(cQq*)U~F@1{B15_SnprHS1L^zt`K_+d-*eL*?hRH~06;`_4Ag{Wjz0=jX~+
zR{OZ;>B80mNQH%ky|}Z}SVmTMWBz?RpLsTtv(5959c*R~eed}2_xo#Wr6*0A^x<Ch
zdr+|uy*=;f6wTm*_xEgjRgS*By?t@;a=#O&Pdne<mizGK%T8(Yyo9^EN^fjR<^J~e
zHhX;h{iNTs=FRInZ}*#rk&!Xu;v&{lQ?=Wpx925ZUgir*g>}DPs&BnpS^xX3xk<(a
zhD|!kHa0Tv-n~0<>eQj9r>7g1zl-siVZbORCgvLV`M7-jk>m39Jzb*ON;Wn!si&tM
zy}P@-@Yxy3BS()uoa}EGxHWb|0;5^ZjfQ2uvq90Jp`mf$<KyEW@0Q<B{Qd2%MbQ%u
z9bMh4=kz^=%<}GZoSkjHIQRCpA5SLx7reNjc;x6&MN?BzVRb*3j0}xgCYeqA_J0KS
z|NSOymV2vZb@=*6XJ#5pJ!fh-al%8!x{OCqP|(28@ZhmtX;4G;@$vrT$H#h)9^1L3
zIHS<X*?D8l&!U(;6@go|e@@j7|8PCN-f@!3n|phu<7>Z8UG;Ze>}~~5p;@Nc%d}3P
zIpb1LVBk03uGgyc)q?!{`#?=pCnu(R_5W+<*j9(FS6Rc%&bJ`-^fZvfa=*C&OT9$@
ze7l{`!N(V-s-N}w!9ivg7M25N&hX5&E_W*{GrP7XvU$Y{jjgdKtV>=j@KWL9;&KWI
znD9#G)X#O{>*FGJ7O7@kUDX=5x9Z@XJ2LhE|C&#lG-<+w2@Mx61nhmMtgg=9D{Zc~
zEjQ7&>dS#HQSAqh9yQhd{pC1GWlj8kxr-MsT2y>cn5GxIDl2-{`L`DqI?u2uRAORg
zzPLR<e#z3MqSoeFzu9u`?~~2FwWV?GTHQm34?leKrsvC-k~!Ape8tbt9W}pSv$*`t
zq{)*F3m>_d<lmEFX5%^V^z`(Nd3UW?*w~VupPS3U!4a_4^hqoiAD>%Vn%chq|Ehod
z`n9O`_qSD_fBgD&=-jz=Hw;-B0s{j(y1Sj9o|-BsD9C7SZLOlNo_u9R;Em1c{AKU%
ztenU)bKbnZHeTsNw{A(zwJL4WIjs@DZ_lcGXU_1HzP@&JqO$vk4-cL9mi;_;=1j}}
z{r2bP+xJ&}eYG(8c%O&2_u*GpS6^J@%6(?GIse~ZUoTtesj9M0R`+k)zu*4X*VpZ@
zudh#jduwaPwKbA{bFEreg{~H>jD2dA_xjpeP!sKUo%Z?qhlf~8-rbQbD=S;|+x*Gx
zAd%eS<F~eEU)-7<K4a$0h1u8Ftq54iG-=YL3o8PZudIuWeqFg}@#4VEX}%`8w?ss>
z!;bv@{e5HU>#&*+2ibR2d{jEtBgxFLVe@8ZA0M8&e?QY>_SeNuW#C@X&z<}C)Y-GH
z-D0{04-PPftdElgh3n(v{Ts{PMwPt0#Jb#n{;?k)ADi~=E_*BW>iT+qet!NhZ*B^|
zeEBkBYnCXe!4bQ=?B&*P22bXir2M;({_g6r^XK^u4Gkmq*V&$%W7&MLnSJ%K_D}nH
zBY$fp>v;;X@k+HUS)#Hf@2(W6!7*`S;Kq-Zg^yUGwq!K2^UHyf?Tafbg)d#Yv?1{@
zn@Qds32Cz&hlq$7tNu1Jvm2zI5@BIyS5{JD3JVL{QSwr#?(f&|Bgc<FzOc}FMd<2j
zw@k%!A{t)2$dHhh1{DvXtHZ$g{>=@;GjpxQ=USJCW&bytXU&jva}(>ti4#wpJn0w_
zApy!eHWeQjK>po+zplIA{@;!hk9qfo*IqBw|Mb0K_H5~-q@)e`_w7Ih<ld^ULA~Zr
z>tFx+opNS|p@eZ7kBp4Wg=N0d7FJe|&dfBPVO6RH>H-~Z=RbVvl-Ju`mX?+roScqs
zZfsH8ayX@>rFZP!{aUnM2?453vLM%?hJ7-YN@vcVZEbCB_3-q(cq{G8i;GT^R17OV
zBm@QoEYQ-|&=9Eo{Y`X}PWO)=6`?=3W?yen@pPJ&`tj@a_-xzstyx!FbWSH7?Gnv;
zx;lKl*d&$CS65fRzWV=gJ3qJQq?XyUXYZ)~zHXI`y?y+a+}mL%Ht8fKCtvL=EG`z_
zq|<Gdd#hu)|NK>_-rw7+{pQUZmzhSXE^%@5R{eQ&wENJND<Kt?m7USs^H$EyK0nX)
z(1{ZsC2wv7uK#!J=uytdX-6L&?G8=tm$Mc6_U+rD8#f|kY$^iQ{+*&3+@j*SDE0KT
zRhxWgn{j$hI`Vve{kp<`ckaY|d~s3vs=c*^MaQYB+N<v_zx4O__ph&t-{0HYs&iV&
z)HHN)-u->Gpb$tqBN2LYP2^^f_pYsplzJ;~U$^F(c<x7mLm$$o%$Tu4${f^{`E=(_
z%*7?1!it`g3d+l`zpmqsx3{;CU$SHgN8~iuy;WbY++ty61vz%Ac6dnY%9Se*ojK!k
z<JPUNZgKrpTl@R^Kw;Kz_siq4%_No1^82;nHWeQnbi?M&n+NjJot?$*q4OqARDAR1
zP0QlNi!JK^?YXt{-;c-qiK(foudc0KeZ4j<J-vIjd4ATE^wiYOS*F=s?Ck7Yf7Ji`
z`P^w*>c-5=YQ4!^-}h>izP={P)#|il>C((Aw)Sf4<M*#Kd#<4ywZ+3@lFBllnTx{Y
z#KqNBJcZQM)RYVj1J|yr{QS&mlFGve4;C1{&zOC@<;VZ?$8O(_PDx8!b!zkG&8~~x
zdO^W+b5m;8agRwVP0h_$Pw~uk{<^g1@EptHkkrr5&xfCt<Z5-Ysr=*;`uzEGbsb$@
z*Sx%StJZ|Ck8_%qYFPRzWNUGHdV2SU4F-uRDJp*R?bd2t|8`DXM1;fN-(T_cCJzsf
z0PFru_M3FN|Nj2I`l{yX-{0S_7n{C0{XAE4a`MB+j~8EyyS;U)k+E^B&gn&Ue}6?K
zPn|b!-PS*qhuitZH|cbjzP^^ZHhkarR^9l0F<<%Y>;6Q9{`>JU`Qy9Y@3U%Ndwt${
za+8jjPQ-$6oheC4Nhb5+kN3&8>YRSG{eIo$jP>ugFD;nQb=-+V@zLYQtty^}PM`K(
zyJyMkiFUQWL~gR@CVO!xf{Hsu&q*B}9RfFR-pndZKGq|+NvC_Jar&yM+V5AEzrUws
zZy*2sFTbRb%ZW`o+j4I&+w7b8_xE@4Nh+QGc0XO#{`vIu^r36l!Zbv<w!SZU_(Lyp
zlgnF)rxm}yT=xIEt1KsH&4kp*GxKbt7wcJBMS;x7xw%No_{(jjBb(p9`+Wc9qH8|O
zmMwd9q*FNSZ9AXrs$I{YU)QPs_j9>heNl0-YevQj15;Dc`u~5oN6p<<zIVqzzd06x
z9+OmVZOL5x?alkUyO&3W%h=UKgvM3uwaL3<v9(xLMTNt2lFRFBYfHZ^G;qFma=PLB
z*WTBqE?wBV{!`2(l}@jzTA8tvUrm}mUERjUre){OoyTrHxVAR>(9N5X7M7NsbLPl|
z{@h#r{mQk=Ug_uN2!@4)Eec&7mi09K{5(-LHMK(r4?51VF86!9<IwxVr)%D2W@a8b
zcFb+Y%$b>YZhyWm>hxRc=!NR5<+9(6{>feV_BZg-x4w5bH@kaGQjs#xTl4LEgMgDx
z+@1)JNh)o8va7<@)tE<b$yoS}S6vAX7F|*lpT7usIDP%$UTO0S`)aFG($kY49%`-l
zez)B87Kh@8!~FIOl8$!$c(?ogm9klrRX8s%^JQlE^Xas{)bVNh@o}&9R<!fU9%|(l
zfAIc&|GL=StFD&5yCc~vZGNnkTYSQlDIsrcbz*i1Oj3CW>dx;hdK&U{lMZNfZ-NS^
z{ogN>uO+9So5N{rY<$&zx^_6<+gn?m)6&%RVs<Rhns1!W_vzE84}ZVkU+mP%mGzv1
zkI${5!UELF14ZJEe_5LgAG@Wbq%6q3zV5^K@8PSZK|P~8cQzD1_q(&B(0T2<pL1U^
z9=LHMBH2AdSXg+iHOsBrx2Lbz|4YCr<1J_~B<f7};`hc~-QCS9o<Cl#UVo)*lBt=Q
zTTV_6=le%9%kS5U$L=aQ`0?@ajWs_%Dc#nK-6gVf=S~TWf(6IcZ4y@VY1q1T>nh*G
zNh*n_rf6>1x;1p_%-ORSSATy8YSL~@J|6P4TU_5QEKDpZDe1x6w`<GhNttFXh~Hla
z8u~al-#-4$-kGyz9Xff^bMc*9x1<6C15cbd;o#-f<+gWQdi0L>M-9!)uI);G`8j!0
z(bH2=$MfFb+nbo2+}zT_vi5oX|G(c&%Ql3)TN1lEOt-gkdHVTz0!|OEtPGZVK1qf1
ze$D6JTkF0qTehsDx3^V*sas6<QsMOTdrrti$vo}5x4Zm(*wnZ8_DYLtg&bJm*gRqG
z+_kgZFJHb~`0Gn13mY4#qz(OcT7UloP=^OpTa@Jm2M2@t9;~daNBe#|xAQ$bHB}o_
zyLOA|UU~KF>+9vWo<>V^b8}yfSsSvqs+5I=1vDgE@#n`zxrr5G-ij^f?(Ug?e{1CQ
z*VorGGiZgaSrJ~%5V0jgP{s4m63@vAd3o!!%+1Y@KRG#Bu_fR)-_&QtpTB-R+Ad$W
z;``p0i)!L-J!5j-uRCwvyj8NrQ*Uj{?Ox_P`_ZSTr#*apSUzOkSB*_OGlNlBSXd`!
zM?i8;?ccB0H*DX2y~;K?IJoBb+wD@;i^Z44_-h=G2`nlu{&-q{|AAY#q=eP|LRNqN
z@BthOlP5Q;dQZ!cxxJ$>`RbqLBBG+K$;rtwwpCkhWHX<C=I=QvWcO+Dch^^iu72?1
z#foj!C7%0re+8_YxvTs=pS`{P)?F7DyTAS;mU;W^jT<*4=GXnw{PgM5m3zl0MQzCt
zOo=>Je!q74w>PJ!>2?P$cFR1&>a}j&I&jiE6}2UUQCwVn@BE4T-ak1#>wA2N=k<M)
zR385S_x}HbM~@bL-?}a5W|RH@Kf=uHd{-i*LskSZ#@GE+&AY#Etr^>?X}YU7&SRUm
zR?*4HX+!z@xF^q_uRits%*^ILe`;zzpEX|*wszLB!dv&+r+>Wj_|YR!TiV6lJ^Rk=
zb+7HtU#MpN5`TQ}n*HowOpBlScuZ=Mum2PH_C4c+n^EVlUk`t7o^)$VX4d@zcqyW!
zq$PW7>0L%70j7C2l}(_Ll5=ydB`k}UxH&DmbhKN1;=Fl$`uh4k(&m1P<2V?Li;F=e
z+~Rk0%kMRIc6Pe`>=agKu<^ckO-)6Gg`HpS$jQm-Th)R^%04~uocnxL)K)F6&{g1$
z-NVD}S)Cl)wrz`=JP|ZF#sF%$PgPY{XJ+{J_V#j9#V7CX?mlt;{PCmR;--@pekpu(
zgwtcvlCN?-Jv|qecna&p?h;Y=pXajFYwCq9nZXv;*2$Nacv{r`v54B5)!NX&@Z;C7
zES24*@9)Xl|M|e2b!A24i4z{6wtcUZX^{7_+M9<CA2uv{;^E@%p8WgU+l-r=RGFBV
z0v5aRHlIsAVH~8!$Iil%u_gb;hJ{*%o0lXdCvU9#TUGP*YIsLS$Ay_sqOMeI*}S=V
z{(N~MVd27me=4u63iV#QFYoRyspBH1a{hCzS`CwrWylnNeB{b-U}y33EozRo@88_q
zJi{oJ3#8@sHC>z9Um>CDo<e!|_N@H%TrYN4!m%F7jO*)Um6Vh&tcf&cVPRR|HC5|q
zocqe^@9!kcawI_hSQoo{QRd}k92^`DH#eo4-g@@*Y2v*-l@VLBM9<B$?LKqHM?^$q
z#VhXbYYlQYhNvZ8T^a1Y_}tB#k_;w7cc;uU$y^k8ZAW3Ugrwxkc{}y=joQVIA3e$%
zx+>)0zS`d*slUIyb?z3^1qCu_5a;{5yP%HNw>LML6<coI@bUC?tgEwA@w{X;t*EGo
zVZn`kn#l{^{++DC`S0Jq9VIU(T}xgaww6m<Tf6tuq2&9A4lO$In)$p?^zCiA-DhW;
zAHIHFe6CfgQ$m7*lu1THfYZ&tzrQoSn7@I~W_Nw$w2NCZgL`)^^PQd5Gx<_Y-q+XH
zum9fHb!l&PIj9%>_4Rf4>3XpOGBQ044GdRzr*s@R;IQ_oqobom!2<@rc{ZH~4jc&o
zrI-2n$w}ckmc?vOPfb1i<>lqAap%vR@p=9A&Ye43&SkdVynWl5qjAfYElIzN9v)(~
zsrw_*D{bC3ckW!bS`QD7WBu~$OYJV1$xBH~FRuCdDeL~UMHbf9paJvUWp5At{QNxh
z{<I%IDwZr?{`m8G`|A<)5}$GnTZ+yu$&K5#abx59_4<4=77GHuUyrX(ytKp<)GJ;W
zzrRo2f8L%c|1@l?zHo%Ei*a1)HPxi9fvw_O4?{+++rEAKqUv*&7Ck++D!;DqORakR
zwLSkA@x=ZX3tJy&+q|yy$A?6Q16#ANZ@Kq*srPh+7EqG9Qs<F)dYbMG^L)8JdHcRC
zTTGrjeY*0Mil<Xll+>x|`uq%_0T_lAvhj1Kf4tK#W69(>iD%b3v$i{{_r2aR{p<Gz
z#YvMVCnhB|U0ofXz4rXclLz-!f1faM;=*rp!!<-!L~eej{aPHUOZBoJWr;w3!#vyS
zM^8>pesN>t;%hE?s;NfzmU>S&D0>qz_wAOq|Nj2Td+0TD=FAByp3nI<i)x3p2r%)>
z*=W2H3wa(SxA=8T{ok+RayAtUrZue7ZRBpy3f%d@ul|&T&s?j}bbA%gLyO(}yWXxh
z`*nwzA=GBg+O>sGP6+nM*-Cx<_z^Vh*&?73y-jD);>Do;+Uj?Yf4|?~-rmj*YOjJS
zx5;Y0O&d2Ff(nGp%gYWPKD^kaR<EnOn>#2dNI+P)`R(oP$$x)+6>wTm^z;-ccd_xw
zthipuQ|Wd}LThp|*W^@5K0dy-du>wT;o+d!o#5quM|&iVKO7a0&&W-Gv02CGc0bb#
zss3GMfx15PKhBslr{}_jfG5wNgVM^|TU(oZdwEkLkF5+|z5&#{Nl#yW>-y?&eos$N
z&{QR;*R2!1jmL?jqPjZy%ZrOv^(Pi>P;_ov5VNxgG&PrYc2=vTaT-I#v=zVKZoj`u
z)!WU@E$MI@?}rZ`9DaX$8@SMk^=jYD%gg=4U(cST;u%$bAoSR#6}z67FAKk9wyvkA
zCtzDn<elB+>recyooE>%zi{EgA1{~BFL-o>Q$kw$@x8s(9K5`(Q>Ti)y1IJ#t&64K
z-`$;{;<@#A*~5KHmn?a4r#E8KlBD0u=3L%-l=Fg|y{hxQ&yUu`?UkCW?tkpl)6;^&
z!i#TJnkp$V1uyq&UA#DX<MRNu)#85Bbp6uO)ZV;(yY=6N)^&wJQRjWHm){JKwJJIA
z?CfmA+*>Ap{(L_F<KuC8#TJLVyGjM6rMuJ4&U#s^7yB60J``|T@$72&Up-rWWo2e3
z4zLGaXL>7KRX=x%C8M@Z;i2n3UDv(IZF@j-c*oAowcc3qG3m&$V@wQU`f)s-lP+vd
z_usm$tuC4;@XB|&3v$0fgT--st4^Fb<C2h|02)4sj*ga)lzez=Yj(t*io(v{pKJEV
zeKXejvsl~p;`g~Vk)Qu{S52&twCdM<U-|adR;$}K`}^h_CbPBiNHSGdSA&Mn^z`&L
zY}nAC;t3t5S!|Xz<*&&TcZ;}V#rh{p=cm5_O$k&-*7Hj|`uF$uiSy_6%g)t(c`-4H
zX_wt=W~AD-$`)nCOUS8xKc7ke`Sp7Jhp%6cURvtiowM5K+M5dtohNom-^%bl6*MoH
zqw)6k{Oq;+OJ7errxFzVcX#dYZP)H@%D=m7>9ut#Q;w&lrXIX>Y15JCn(zL&9$j2u
z{orQaIc_nX15K>l1@G=yzPY)XeRKNxV>dP?E4Bo@{h$FERdQ@*Q`FVv_4M=v4OoV)
zkL%r>e*RIv{l5#lylWFr#rkr;Z(FhCwL8<Ey?Zw%9pw@c5qa?C<>eb&v&BKF6*TS)
z8sNUX+}|+Ju*azK_qn;&1;xd|tF<*W4*dQ7-L&k2$(8W<+E&+YF-0>ovB1E<sM{iS
z)2^-#zrLbA@^RoK6;QctXJ@Bs$Is9sZ!hOR-|pzX+TSK+it|h|L4(LE3VoW{cm?F;
z`|sR|k+H9nxxGFA_?pPgp!o?4E2~vymAYR2a<&&1yYr`{raru|&>0jzVtO$h8#Wk#
zCOP={_(1Ih(5SVTZdAhSYiqN1zvfajsQmOqd{?<MXiOsc4=5As>iWLsXBYXVRJ_6t
z)DlZL$n@scR&F&lwFxSoUwNFIoD4EAsidT&Bz%8&7u03A%@}ucyP|WO$WLbJqZ>DF
zY!qNBe|P6%)cVzbQjLv`51ZewY0lsGlg&K;-jPOTb^&qm_SDnUKttfazrWZ2CUZ)~
zB=yiDyPVwIiSy?5{rOV^s-v&Ilu}>%^-f9cbni!dzu!At{eEw|y8pZfCnhT2*i&iz
z?99yOZMnBWrSPiQP2G#LYwql;jn38mu<HKO=bG!EKY!kye7sMxWQ|?nzWV>5id*~R
zMwQns)7Lt;^KIC;@!+P^)1c|+B}<orM(jU){pz|lYU`C-)1KU3r2o`b%rtMFdG0Nf
zl#~<&Jv~18nh%XpcTY{#78Dl`fAr7h{`yNbZol?S*3Z6IAE+;+@BG~G=`Kw>JGr&d
z+x529*45b^>yd2k64eH|PwM@Ph0g6JeSvC|@9(J;j*E+9`}*EhWM7`=wHDQ#;ST#t
zWj_4+FBkBycjmNdX%`ChKi~F1T8g3Xrniq1sWRHDr5(QR$d8YYLFM3)<HyB!e@+8U
zaHglXKY5bUTy{#QYyNzBhJ^e3YNK9%e{++WA&awI)$;mO?eK!f$9Q+_-Yq^`C2C3=
zuQU?_pNvJoqhgVx=g;#yajgA5VgCI7BS%~qc0CT<TUA=~>*aD#b;FQwxQ#dJ_Eg<y
zvA4IkgXW<Hg@l^4!`D6de!pISTm30nrvJZQ>-X-OGG&U=WV4jWw)ykr_x*UptrNdb
z#))I@-)g~Ag%hSsSrS<O<3r-wlb_o*ZQXiwMd0EIGiR>!`f&Xkf9!c9V`Jgvesi0g
z7G9V&XWjZXUTG(ek3q*CPt^`j$j@ItQGw${o&8iFAD;^w5}l76IRa`i3OGs33CT!K
zZr-rL;LLn``MuTO-Kwf~z1pW2zmJC@<My_-QJ*XsWGstZwpM?5y+F6n($G-w=g*%<
z&jqhf;?vbpQDK>+lKB1I-5Z<J`B#OkWD*w_XE<MWQ%^(Vz$8`gf}fvKSy)+D?p^=&
z_4Rh0)2l3(E$OQI-y&coe1m7H&%0~tedo@ddvR^8w2+VxXo7#q5>TcPsg8MjYpY_*
zfuEnBe|<N7{(N~ZF0L*6Cjb8a-o37FUzU5sQuBv9_v$=*_6#)Zd}U=Ys5$=R$&-ZJ
z+j6Vq*XQ10IB;)oHRGTEA44aVuiRl69I|)mQq`K8nh(e2>tFoYI8}V1O!B^c`;Kn=
z`t4g=Ybz^gI%mxqo!%<vYrd*W12hCAB|G>3|0fM<wdwEw)3j%g&6ihKy%)dju8Hmn
zUhXH$p}6JT>Bz`Pi_%w9uKi<hINm3_^_%-`D>qBC7J;g-r%#>Yl9Q9$QTch<tEyJb
z`4>MIA6y-9#X54*&%+aThR5sg`exd)@b$7STTDRX-v9pnlj6Jyno;$eW3lk76a&w!
z-*IeD_fGw?OLgb<LtRnFMZfL(Czo+!gQAg<QNg=AJEzy>;i(0@Kog8BR%pzaIWzI@
zuF|Tv9JwheEsf0VkKXV9f9yab^T#hQgL}=k=ifJb@&ARqfB-{&e!hyT>ci{t^`Wby
zcbDl-nl$Ob+qb>PdZopy*R5Eg!J%kS_org(-FIAETpxZupYP1k$Z!8A;QhW#<AehY
zpw|A035uXLyjyKv-nw%vR<&F5@5_Dr_AO##5^JA~<)Se2+FvCxd#gmx&NdIXUB5Z~
z{G)ewcS}7Fe5bVX&Qe=-b@%K?>3MnUvdZJRxx15ohwrbe<xt#^aFA*1r~7rkd5zQ0
zUCF3_bcAy)XVLlZ?^9ph+^pUr09y8OYin^)kwMXu6VuD)zIc%lvNDME^Yin^w`N~A
zc~$-81!yGT%q&xHWyZI!*Y5`n!`S_J(4160SKn*CU2Q^odb?rrF$Gms*Tr$+N%PF|
z^71_V{jdK}Y-;5eUsZQu!G^=_{IBOQGyFX^dEFD|r+M2>6>F4ls^9nb?(TBKgaZvp
z>pySeP&5FI46<B#^CqW9!jNf_is<g@=c{Kpb8CmMlc}kxnJ{Ha%aJ24Ep2V9Uj6y|
zH!&@(?Z%CWt+Ly=<!|q;E(gs}K0e;>?&#Qf?C1YKpZ(V+@7>VQz)(?90h*P+v9ES_
z)ZITnKNo&{bX4f>?ax!JSH<nGi(RY-u4l4rYJLdx%h`fjtUkWJ-Frc6au^gWEhFF8
zY3_GccIyfFo!Fx8KQH0OhldkXIBS1@3$=dcTal;l^plzAym5+Nz^;;)LTTsctqt2&
z_}ERxqJSZEby%pX;q)i5TEWYBKwY-9hDFCk7<go@L~h=^`Qq|&ej{UJ(^v8~6%CWs
z{a=+YKJV%0=XP^b>epLaZyY(oa(8#Rdsvv5Td&m8u=1y;M9<8z6kfJ$nbhv;{W+j@
zNdipW;`+xfE%gR<A-><Qk6%1@;e9dZE!o%kQcq1e`045C!aqL>!Q&{|wSK$ysdI92
zM(ik9c<r@_x!IP^t}Z7>M@CQqx%In|t}gH6W4)JO&khXwwQsWOOnWb(?ne^4zSRo8
zy|uNuy`3H8Gvh#OOUp>p<rY>}hYlTL0xb@(|Nm!k*5v8a+Z~(PGVjLzp6qYeIB}xj
zv0mxrU#sgrKRYYFk3YBS>nm1iY3Va_t;1jUbBUDSodoUyUHVa-aAJa@fD>pOZ%66t
zX>NZXAMZCkCXHOnMD}>^W=5)p{=4?e**g9H_IBdjxxH0iUnwdoGIDZqTHW5gbLYyk
ztum%rBA_|DpP!#6UtZ?R!O7XUd9(4mdwaXRr|Ug@Fv-s3F>Ecs!R8qjg^L__Tj|H`
zk<g9W;xJt=_QJYY>yXu9ywA_iKYpxNIx#!DTh)8oi_&>+y;2WP>+e4TnpvA=nysXy
z#58T%v>V%Ur9smrp!wSy8xpI&drRl%=j%jm;i&!nt+l_O|IndB51u}4y>llfW`CV*
zXJ=<YNy(9$o72Bq-T%BhGb$=7>Ea^Sj-DQu%gcN(?krB<v17-BA0Hoss=GOJ<{0GP
zvkCn@*Sh>sxBfnd#csV1o<3!DcXz+DqmWtJJg;TqL_tvWF`S<yFKwR3<L~beT1>TW
z-MWfjUo^|!-Rb=N{5)te*oSZ5^tSB>4GCXe6$)xM{`q=69<(Y2)GzLpHV4fxM{LcS
z8ufdr_w=NHe|~}%4%yh)1T6EBjM-VlI@>I_$!Xz%2M3$Gd)z%uGB2_G{r&xT6D#+F
z$B&!+=2{&*a)bq>X6{_sIdkTilwH*06c!dfa_pFrk&)2Kl`ExoFWa?i*Q4L>_aARy
zWDZ#FC+p(owkT$2(T)A}_I&boJyNDw373|5vc-P>`Qygz+o0*?7dJL4OPS?#T(}VM
z<Hrw&Nh%;WTh#n8xODmQ#~&XbC!PO$GkrcN_8A!&J9>Ir)~?m<leKPZX6Ij2{QO+R
z=Ct0Z-<rY863)-F<>27~tu0%#W(}zB0#$GY1qBZO|NZUWo7T=Jn~<8?3YslHdzROU
zLq$zZNmZ5g>#M8Io72uRFn|~i4h+}UMz=RKFn}g=%irBOxGnc~z}hHN3rowFqU*&~
zJ%v_<ujiAOmj^AIIdX(W+C1;b{Q7^LX1TW(RDXYWbl&68GYeZ=+u9y|zh8g+@^b&H
zLNk4ReFX&s8t(2ccb=rO)oQ7H-4Dj;`tiqJTwJ^nv{p9nj>OZ`(~sY;|KD5u{2XY_
zRK&)lR;|Y1@E*`Al0Dz=Rdew3yD#^f`{3cjM&tBz3D?)fg4UR9%f0>W(EA13x0}zI
zJ9lHzQ!fc=>BCpAicV5ln0|hqhrfUO{Q2^r#Spi)W-l&!dJ44m<k{KTh0o8)^2pgl
ztWPnQmzM|iiNC+QE8vuISMq1&-Cd=JK?{@8&Px6G@nb>l?{5=SIHk>U4s6Z7eqn2N
zc*)yap^tZ5s>{<)y0E};N9AWV(4x<0&)9;4gF$_S>ThovckkYP?e|qx9UY#-ZM=uK
z<=*~q&ieg>OG~{${ev@S&u+}PsI+xk+dl7U)24yarjW2OXvI`TW#z#WCpaEHe7GWX
zb=bt@RYgxvy|}!b-*1jZqh;~41BVYY>qc*D>F(yfbop}O*H@vSk~c6gaE5VupX0~f
z6(5yAiM-$bU&Q-lHQ!mF8syK1!~7OiUo@JUn+xCHvt1LpnXO;W_RyP~n;*V<l@(ym
z^Ys0Det&;|ki^cNJ3*lg9_f?(m8;pc&Gd4={lAWNvAdNF3<P3#l{g;l5}i0@N{ju!
zAI!e9OfGsH>Fw(~cHaJfPe%s_C_S7!$+`dkKWiZ&AyA8Gs&;r*jJb)4NcOcgj_rK1
z7gmL8&zL<M6hXFCUoPAXe`;}WN1-xk4c(Tkt6cr^_Qz(KW*5A_XZz>=|G)Bo{{H>C
zuiRPUlb@7Ty~y`@Q(6{g-xp8J$>}M5eN9nEhX=GGVgG*nn%dgL#Kgw^|9)|6YHIGN
z`l^+8cNc4`6Qk!OgNzFbpz)clSy!EQm%W`Zd2;jK>hDU*%FG839+dLDadmb0@i~^o
zA5N;zKXCrM|JE{4$0aBzC?Pw$`|j@Y{ZoExo;i4s@$__k(26fX8JV8%_p14~W?u)j
z3qWPBw0T~}ABCVq)t#WV2TMPGckuAwQ1hSHBdF}QAnWQXP$Io^_bzC<e95w9N&o--
z<>28ta&2vN{EsN4lKx8<hmum&>eTe~ZvFj#f-Ed8Ig5*nFD`Io-dOzHZ*QM%*_#;|
zcXw@F5wNgn!=_C_TeGi=8K<8U`T6tb`W@F{29><MWvY03)4l(ke0<j|j&Djm?Xo%T
zY)f-<vw^X(@Kmi(p~l9>q)SUYA06wJmb%{6)upw`UtB*<#J2hyXoW6lp#W&Uah`28
zXjWaSrhawUT96*_Y~t+M-Lp)yL2KhD&YipV;<dA9eM43TxxTJUN=gFFUjP61SE_XX
z|9`t*TwdN^P+Tm`)#_wnVbKw_HLDYpCg0rM9lpK}vEsn=RiCW2npN2w4H;S4)|oSB
z7L=BX&aeBm5>!1#?Jj<PuJgS8|ClSQ!~HF+thid86z|-<>zb0X#G>ZMhE=h7dFy_B
zyPfa4I&5vr>eZ_a%+1C7`uad?ULPHouLsSzReg=*P|UltLvdHxTP+zGnU>bp))n#l
z_ubf#*nDGq{`?84kv+23VOPJsxVTu!$|~x|uV1Tfg|CeY{qpv9_@9r*<*SY^UUL4$
z@Avz~udWUk2YJWZy1S8?y=%=Hoy6Q+-9LZ+eAyRoZf>5KlCtFU{a7{@7LLeitrI6s
z+)?zj%kA&Exz?_yr|Gut-McqHLu66b)m2G9K0H)1HV$5#8xSzTz{u!Q)!aqLytA@a
zfo2CkeEKBx?AbHW>~+ZcxY#dmZU!GYe*AUq`si&rg1u6vLS|-WprwLJIyycoYHC?~
zzkw_W37PWY<43`=va&;`PI-l_4)d+~b~F9audlDGV)Os~`MD_hc;BJJhn*v$qCo2z
z0+;*Af>sNFQsmZcl9G~-F8kYyzI*rX(49Lm6;)MT>-YbQ0xdImEupCuck9@yN$V`N
zH8ea<Y|<$zDmt<vaIwo&t<V;yg#vPNa!Ge~6e_8!yFZTEq|-fNg23AE>)y*`tpF_+
ziJaEDapT4v<?rW3#X=_CK^2INow<29X!f0jg@wb~+InGt1}O3}uC19l!?JjphrfUL
zR$Z+=_kKB1-KZ@BW@cufq_-vGqLYfcdN(688%N}{qc1Nnzj{ktboITx)!fR;$`fbJ
zS`}9J=7!<LHIc@N>FMe{Jv|}C2b<aXkL)OX?2?hOVnxWxNdX!npczvZcJ}Vj)nTI2
zhYzKlnW2~xDRz5%{`D2wuWIL7m#<q9zJA_@En7sUO`G=UZux!D;^*hCR?anlx>MBs
z_MF{mXQe*=`~99<Utb>-`#HI}pz#ZEkVHkzihHhmXZe#SDHr!t7AIzBYv<(TxI{$E
z0Ijt?m&{u^eO=5>r9+1ggSOCwCNKLSvoPC7bX)3av5VVsqXYNVR3@gSscD6+(U3C9
zPyh|e6+S$~x^<gtZ}w6_WjBzwXBww}>6#jpmbOg7u4V@)v2e9IP0<W?+mdrL=*_LI
z-ivb!&+l3BJ|_?~t?=vL+W7r(>DJEsba(v<zA|TD_H{i$2?-4yU2uAQabaQej)I3x
z=XO5+@bIvbiAl(f+qb!;rKLe?9zA|sdQ8*aJ{~j&1xh<JX3ff4(_4B}-`YC*$gyKx
zQCqV(xw*L$larM}lRTwzT6ue8uGD<CalY^A{ET1mOSS)&i(hTH=7-PUy58=&*15ga
z-;Z<%D!Z(W+S;;o>Cz3`wu!~X#eo_xNk2b5&C1^Q=TD7c?XQxDj~^@R=;*i{?Gkle
zAGi0&*Vos(-?$eQZR+Ug2skTx?%X-hz?AU*f4^3*I(xe2ofl{Y#NMi}LZHGeEiG-4
zQ!AH}hK2`dQ%u&|Eoc4P?t$kYK7Mxy%>K9NQOSn~ju)4Di$8qxM(50#GoXb)A3lE;
zKHSE8`Ny^?C3-4|PV%B~XQ4-``PL3DF6%?L=iS|qch`zX(uif=ym=kn-G?tOcHfwP
zf1gtQ*8fL3g+F}%-adW0_^)qoxw*Nyb8c_r1+^F+9BekM{q^N~g*dE)cKH%t`0|o!
zMRoP!=<Rtwo=%VV+HL(sjFXS=SR*t0g!%L1Z^c%wW@TYfP*r7}Idi6gxw-z^cOtJJ
z9&Z2e;e!LHakf4_{?^@v{|zlIEms6B<pOmUCrk*qbypGLbR{LFs$>c9uACK5KwbOL
z)nSRZwq!~erEoAjXy&(bI6KSq<J0N!N}8IU&o_R4cD7l?)5FIH)UIRzbx=6CxSV2Q
zWRUhFy=c9&vzWcFuWy2iXXv*dACp0a%mfuqS?e;LqxS^==2w4u!dX;Q6!QOHyr!NW
zUpv3N+v{s<?{_^ZX4tT8+p!sj$p#4r80Oei3f0xsExoJyOWr8`oD9g&+uQT?->wrt
z>Iex6?hOPDQ-2Wy4K4Ka_Fh~cZy!2y=1j?7-`;kw-}j5lJpW$H=FOY0CCl5@aI`ut
z{8(?dI$$A_UfiA^UcY_eq5c0iXkF==h>c8+j*crLHY(-a-`9J0clqOIXJ><IW~<Uy
zA-7^xe$6la`>XWF&z}n`KR^5M<%>&PoE&J1Z^;rBPz(Llm6c2Hx;BH>W1l#4=E&RI
z+r4*df3ZJy=Z*}wxSq?|S*G5*wc&Px8Tle=3xoyt9`&1R#j3Bb9}yY3a_aT<@$sSS
zwHa+SG&oj=uXp?Z@2_FWi-3rT2++XrjSY#1qrcbND8r(0k-7ipXJ<hxpx@lt30lEv
zU}n}feY&{a?>ELgayC1*>~_!B^qdrTd#jPLF(~isU3YW2zx<9JJNC52y<A@N^V5rq
zi`l=uzu#Z``<tS*HE79(!~K1=prNlFyLV476X#VrZPdmuA9w5Sg8z>4wO;}=%NvpQ
zadmXO=vCoVbjd7l>ge!V7PdADw2l?D=r*kG-5tvxKYk?q`|~qv_hRv|fPe<jc>L$*
z=iT%2^cW7@xFG?W3jg)}{r^+Hk=6`-QS<ioZQZ?lcO2)7>hJGdC#(6!Ij={tv!kOU
z&h}k{pUW39P?9=x=8VZHQLffiapIBF9zJ~7xM72Vi<=v0<Cb>VnggIN)<P%NmiG4j
zo9dAE3-5gy6B`>C5D;+dt^zDTp>)+-NYXMkH+L^9+vfK3@^b&sue*F^nQ(4SJ9}uU
z_w<CsL`H^=jt)>$&hGD*;4PV#**589+nVX>@^W%=78Dn2f06=6GZrGm3bdXf`}(?t
zpcUQVeTD5E9ru)c9MqMnx<l7Q2!fW5x&2%ly`6!<&(F`Qf39`8o|BVP$jRqk4<A1K
z@#pjT!ne0f!A+};oSd95E-pUK{bde%Ai?-?pmF_$)!*MOz00elRMidIG5JFG+3VNc
zwZFeTytvqX!=_C^Q`ObgohPaM`1R|R4XDv@;{5sR8t2cRWo3Bs^yy2RYiG~$9@uQ}
zuqu3g+@X8If)`I4q?{1&nQymu%kGbENjW9SSWwroA1{vGz=}kAKVIzJh!tr{JzgxG
zj1>i&9CJ56<_1Ba=HEj1ez{dP0!m6swT6syJ6`CD2?{o@3|<au-yONI(3z3J($cb{
zyW9D28}Gw6Z+IAX)c!UzGB$qr@+GITvNA)%^y%WDk%68b9?+g6hJb*8hS1ev2XEby
zl9Q9OTA!Vl$H%ZDZm-p=D=R;1<xlMB=t|7aKD{%79p(y%TVUj}jGq3yo?dLo_o9US
zT?uJyX!asQyIqE6SdnXT4LoeSmYrc%R8qPm4k~r;C4GH;9n|G8Ogh2=DkLGbj&oL)
z7HG;jboax<?a3!6sqQFyD-{zH6Ot-l^MUcz_4WP#{{B9E=Z?(j>H5b{PF6QeJj4>Z
z2;YYOzvYkwv%TbHP>+-;*Xe1x&TejOpzV~p(c2Uh6dbO)O;S0rX-(Ok-|zSL7d<@%
znoA2_?&lg7CI;GJSpTo4=EuYK^}o$vDH4f(@qc6a_8nmni4v{h^-i<0c-XuJBqR>c
zb+x^G;GSlJ!Cbx@%f3mSxyai$Yx|;HvrLZ@52ro97+q8O_Y~;(%O6}E7Z~5|WapPF
zsjj~L_U+q`XJ?z||NEx=D?TqTZ`aP9KPNp$J&p4F3I6qQd#g&{Dl_bezqh~s{_E@O
ztABn1t!>`*&645%p7itcVt==+pO$+rr#Nl4@$ES`pPeyF-)6b_?DCt>p{$uml9%70
zDFaD<&irP%`7DTqEcw&qH`KJB=6~54=D*(EFK=JB=bIqI9sT$B_P##aExxz*_qONf
z=g0q+fgeP{z`*d&@jv5%=fD2lVn-HbU|{%ADzJbVRV;uL{rpV{Mk`b$3{x4<kMR^7
zH3k|+qhSLL2!_#g0}F}KJOvAhhS7oo78Iie1uP^+3kq0Bj20BIkQgl}U?DNu+Jc9~
zXh8uBia}RUTz-^L30n(*+G84R2f`waVbI0ekdLXKA5r_X|L@+t8$12<(_85^f&B7z
zZ$3Uge%+3lf#Jby6$hlwZ$tH?ckkAz`_KFK@UZ-KyQkg1UM`>i`|tPrE}*L>!WGce
z7VXrr`@glS>TU793HN_}csN~edN-&G{D6xEq#hQ(1@CRv&Wr!e0qSwL@7w<kEp!=b
zWKooZw1qI0fG8yFhJGQ2gDSFXKq?bPjR6G%0|Uc|3Y!n=)!*OGO25gL@WV&rnAd@m
ziefQq{FIJ5X;^hOJy77_+U6+ZGH3G-<}ds&6yE9a-jd*c^z7Qg=7hotd5@MTZR2X<
z=!(+$JMFdh6pi@X>$lZ@v`{$x)#m))xaeh*rJ*4TqE=v}FCHR>fE3Y_=>j42K_LSS
zgE7;88z^IeTmi!kUg$aE05OAB7#T|o!w=5r24hK19O$EAqk#j97={Gm0_Q-Jb^X7Z
z_4|Hh{r>j$b)WUS7Z(;f&$X%iRA2Y~#p3>Ld-nX9UazgKZJtmJHyXrv5VrYwnm)sU
z|Ib^+<6bQ8x63Ln-u(CX_w8G^UY+c3cXMU%@~R&X+y8&tZGNv}@$|T=mz!>`-~aE{
zY5o0og#B$k`mg5&83V_6npj>iaKG7n-tP60PT{>@uSMtP<%NCy^ZESu1I+wiPHC_I
za#DT%pSRolZNJ@Eck|n~vQTMh>HlXA!A$@$4(R6o1i5PK?+=IhZ*NXNpK3mH{hBpj
z9(C(~d%1l6x4Y%{W3N`;zI}V`x^>^K1pCLn4@Id58dwz^*dr3s&&_%H@Av!s($cS+
ze*XIPYw7dwSI6b+-#j@v+4k?3%Wv=Q{=VxSC&)rL)?s6`I>2OI{w^jvJA3!D?Ck8=
zJrx@_r=O4e7%5-#!BJc<CL=ldan(9d1q9c{pd$d%_WSMj`%#gRH%<5d{dQa5c7M?O
z{r~IA@0N!5+yDDfdYd1io`HcOLWilOffaNd;lCe``(r=fumAt|(r4|DSHt5=e|>p5
zuln82Y198^qv&a<Uu|n%&B(Cs?yXx<>F4L&HMK8)7ZX~3zxKQ6+|7IU-o11w$h}Wy
z=c@bn@7#HF&iehHoU$Ju9`ecC)r5kspn@A#@V2b1?AFbjJ9EB$K5u`2NiIV~3CKBR
z4-Pc?&9%C!zyHsrSFc_z1)cU59ToNJKqGT_$+>gq{J!6-&VT*-b@<oc`TPHt@!Nj6
z5L$~oxP9R3*Kl#Jx_>{P%i2_YP|IaGpcK9DCO1RD+j*7GX8!y0`TV`g=X1R`e|~-*
zl*AS~x8K^HA0K+Z{(o(J-Op5Uy_g%N$7UL*|9aG|f9uAL9f{S*rZX^XS2JJ0th3?k
z*RS(xzuk<h|NFJ>$HVq-@9*Egb}j6F&1c`^eX_g1+{<3S_uB6F`)*&4ufJ>i{Z8>s
z$>aU<`I(t3mEHU9y!eWmSfYCvWD^eV{eG`{@6TtmW$o+sfYvXu%hzlGok-&@SNY_U
zwYRsouD<^JU*8@b?Vf8<xTu+(zwCbP_q!*yqM0=TWY*oX+qtr~Ra+Lj_y2oq4RX>O
zw=e&rqM}~i&fou6{W_|j#7?|>U4UW?1H+GSjDj6Y!*;a%g{A1xz=4GX!)VP74~o%d
z4Lm3qM%#Swuo!I+!-Hb9w*U`{(XJFcC>lolneec{oI)H8oYBA;9if1y0U}2z;OZfa
z5tOYO{%<I^R}8vdFLOM8cka%ae-~~`nmUc|;x+-b-HJ}_d~!{Cf+9O7u()nlXgSfv
z)#TLlFP=&9+9?6eF1~v_RxPdzN++xGTW*Z9P;7jva`TVg`}<8lK8LS;TbF+4_~Rcl
ze{NbY`9n_Z*-3Fo&_c;c7$Zj-82!ajHPFBUQ={Pn4hASOnl_*T0j5UN1~?d?#Aw=p
z1_YQIh_s<Gx3&Ye769xBFhOj*{JOU?c=@K%*VooWZdTI{Uw5XBS9(+V`+NIq|K8hM
zy}9u5v6#}Up*tUSX&3!|yZ!lLe*2gsN5MA02#57T3z)y`Y?rIj$lvqP%`E@kobC6j
zw4I%ucm962dvpH%ef#&6rKPEXhQIZ8KADtrdz<e1J)gYZ?fHBTw4K>|1Ip@Yh8L#J
zzWfXc5BL51_4>`dz1E<qjBPnLC#l@rQ(2t1_v<yApHC+LeAKOfuJY}}!|k7MB=<l4
zcwGK`_WHfsLMEe(o;Jum<9xwT`(|;!-Kh%~0_1AHT>J?-Ozz1<ce#_(<LhSb+_|$j
z?)SIb`OnYW|3Aa6zh{EV&#%|x#cTCpz5~-2ZnJ=lxt+iN>{;{sb3#{#%`Mzl_xIP&
z>*t?tK5utgcl(`5w$<OBv`Ockcsf0PUiP}3YUl0$*X+9cZqYl?%6G6SV4~`Bz-4BJ
zh#iaF`_oEFzO4Ct@#4jj-FIayi=NE6UibZO`OX)Mx<7q5%%A@H+S<t7Wx00$emvgu
z<59O|?XQx!s+UWT&fx<a1S7sEFj_gtTUUNc30o6Uc<twh4<G)#eqQwGNN36JyL<k8
zI$imwQ+<*OXt*9U7{BM|v)Pr;W~LY2Or5TKt^j5Vm|mdHYi7&P(7OA}CGXF_-|wGa
zdhcb)v-tn@*VRrg^PPRpV*b2&=T1&m|9sZ`{-17d)S#|=01E1yk`fd5J{il`e_mW%
z>^bS`>hSrWZ(Us-{`|s1=bit4y*_WT|J|<Fm)@2Y|M~H8|DWH{+j34$4UellcJs@Z
zl4Z-6|36m)b_$gE$GW@h?WuLKyU$ttemXr~DvH@*zwiR)FB?l=Uwiuby#4u3Vf9T}
zS6BV~ynf#=EoNrs$nAM|E!WSTHS5$u=XN7=^Xbz0dkX*6<mKrxGc)h}b}Re;r}z8+
z{dzrf&K#Td=b^TMsRKWM#`BBV6g+SMol_FU;$SbGQ^ml*4VqGU+He2w#J9J%pP%=e
zYc*BYx-8{z8*k+1G~Y>2j?34ddGjX6Z@!)F|9$Lo6$*Fr%-@4jcI5WkXV0ARS-0<3
z*8c>s4KU(>(Gze`{r&ZI=l_4dKYzLG|9tuUx>LU9cc;i&mp%FL@bJu;GiTP{5B9g6
z`u$$DK4?zl*s)`iRKDLS_BYGBGb8u*wx>5XChvT^?e?dW>hn|X@2kDJueMrm-;YPj
z?8IR9fawbYj8+cwtN;J~{`pSv`PAp<=33VMskpW-b~Y%%_F2E1QGfox0S7jA_Vc^G
zUG}#>yZOA`?7O?mpWiLNfA+_Z3eaIWIk&cCYT7e_&4Upal-YLO&D;J`km1X8W_G@m
ztSqhH-`}5q@+9Rl(!Aod-v9sljBn0=;`CScd810*YA%N7-v1d7IL-ZQ5d$*{N>5Y8
zm@@Xnn86kqRRaw!5H%V;piqF}(X;^z2@pMO)5fHQ%b;t^4mfR%TD#@;+hyrGt0qpI
z*wfo<Y73iCZAf*3t~YUr&)OO#DL>z1`RC}%!D3fGd^mOHoSeu)n92<*uu|sB(z4yL
zAAg=x5%xVFsltBwrOk}8-Ma9FHVK}ve)NlCVNbQ$a_|aJyyYOwO`xC$;|tO-W5HYy
zp@O*`V^j?&V4!%IgiqTnIjDy=Oo>_>cI$1~Wn;0cCr)@AJ9g~f$I^YU#a|B41j?Wz
zy*5ny@nhkaC3V?Vrxr=c#m&5Vv-!WqmTz~V1~GKP)@en!-FjQbdd+&WkBM#iL>Zsu
zpA&Aq{bt{_rq&#))<FrDVy7+bRGIAC{~{1>WyCqQ*)YdJl`}ZxV=VBR-~w|RToFdn
z9aRGh8xZX<6vIa{s|w_H5WcV<J*Cc?chIP4;r;M;njm?GhI?wTWW^x1<Z4!GO^wpr
zbNRmhks*f<Ya3fv2N;~56v6j>YBd*F{etcAovjV5ncHuRo_yzHbn(j^*CK<t=bAIO
z-%g60cBHjFe&=$qa)zq8uoTW<;SVWY#U;LrLL|>hfSTeEHjLcsh>=ExFdB!hgFwxn
z_Py2|6F1fUvG`XQTNLGD-P7(n%gW=lLrZSrB7xG*7Xi~-Sd^6(WtXk6xpMG@g34X1
zl8af6O)t`>+f;CLIlSDK<8p;L^QgGfgxpUP_8<QL`}_1Cn@wt~($eDfKRnoM{5bu&
z!TB?9_Qb-1hJk?ra|#nne#KbotN<@&U`AoCn{dDkWy}$L6^!v^%=Ms{4HV4Tc+61@
z%;^>^wFW%t!Mx$21W&wBAu<EV)9ChBkO@EHXD##8T>4sa?W^y<C3)Cl&oea4K354E
z$!PF=ZmS1Ulb|aMT9Ru}Hf!0*Lx&6&U(C859Ch{e+0@k3o9xvLGqlb<1}XEgdS3``
zNo0ewK*Pphua)vIBE5{>RQY*NGnRVmt$DP)3a4^IGoMX2zH%@;kS~-2wTluiRrYg(
z%#E0xwhO(iKTttTSwEUCK;Z|&!zJUS?S`j@$Llg@O$pjH@8YVu{qqkdT=>cZ^{f@V
zkZ;(3!NgZgtWB~vZ1=oNtK#zYw6#wwLAOsdnEJsB*7}80f*yZfs&aVU^DQZsi!bh*
z5(ID5X3v2a>g!G#oJ_i|47F!LsBtXnB3K571RGfM8mfqafoj>7uI1XKo9jRs5$21_
ztFZ)j!)#dh1gvb!qRd%3Iy}ZwYs+kxhVH!=6Bahj6|~vqKnO~PU8}M5%8we&lN(-J
z>PDW+*rLA_(&;r2g@-w4pT_AnPqE$L?#Thu886|LJlHA*28PGPRGlNJP^W9^K#nMI
zgbaaNZ#00wF$E<s_pK1sZkm*`?KQZbhZ@6h;78^xwWU+mrEghv|9!fFM2RgkL&6%=
zLa^bqiSOjr)<n0(SJy4yvg-Qm)2B{t;*e!{;E$S)4y1Z%n%c!9HyS`~-w*1j4Y3DW
z(30W6{)}a)u3=zc=wZibKzpJUW(;?Dd@nDVa_MVN*w^2GdDxoQr8C4#J)XocqXxyM
zgh!^B?*1Ss;VswAm|%tC$A->uuayTM2Te-6UL3V)&c%#)FU>{n2|ATJYz;3__69O6
zI{~Rgu37XSWiU87(%Lt|?+&$cSAM-3zPa@EwKHeWf=BZUA04?L_x|tq`{&P`IU`zs
zZGHUw_`07@<0DX~iF#&(YNdi?&}NC6PbbxH?ys-kmV0~JV)y=MpxLvNlhrq8UthO>
z&%0fvuRlGTo&Rjz?svQ1{K(yY_u8W*Sds<P2{D`(7}ais$Jb8nxBI2h&M$xN-{0Sp
zRnFUd_IbDS`Mf=!PHF%A^ZES$Z)S4UZ#L@a>20%xcI3eN85m|TfU5ro^MC(%+;41c
zJzG4k;^C!@ywYY*em<XnUOc{LqI~_IkF)Zg|M~g(=i`3+TeDF2=J;?hS{-2d{p<Dm
z;_r9M(;pw}oi2NSWAgE(>;F&f7T16FuwDM#GT+&t`5*Q9HAeUAe&=RaqvXAYk7l5T
z{J))>)6b{X)&1*w{Q2|eofRLG&dsqbzWVyy*|Se~KA(45x!-1z?`*TDS5^jF*8C_a
zdw*~4<>mgMskvM~<T{>#;TUMUN7LVLxASjqNIWchyn64wrR(F*&a<uFlzx7mcYXb%
zPW4YO7WY3}*e-V}I)Cp}(7e(!e$>gqW3w1!6PoT;y<YqC@Av!bE$pOv^=kiCfo4JZ
z?S3Tq&9Nv9hU{~_Fn3vIkk`v9x7EM?*0D7^UN?pYEyJ=dkQryspMQR4rg6B8ef77T
zNl(7r&fov;_MXRm)}PLr-;cSR`u+X=`DbUF$Cu^2zqj}1?(+Ag|968;xMSmcIVCZ1
z#>I@SuQk`c`uc3srcF9d5WgmzwJv)T(I;zNc5`F#^K+$J*cv?59oT0i+}@sl{^Vr!
z;(vdB=G@uw@zO{A{eO&JUt4?n+uPggf1B<9{cd;8%}q~d>HR)u{XV6z@Z+xkkj-MZ
zLcLag{E3qFVa3R`J^#OQv-;1soBR9y{{4$x8GMXDkzW03<?>IU3EREj@0~uazkiO(
z&Vq+deR8(5=31Ahy}q{Aa}wyf#pmbdp5B&wdsE%tUn>8<KRjHwzy9Xi+Fvi1Tb8~G
z0ZpUUf0qU)hy|*LRsJalg8k0Gz_4yEDD>Xm*r;6n?aj$XX7*2?&)cWp-j-`w^(6ze
z!3Z=_d+BLh_1mqW>%D*e`~6=3uh@*(-DOYr{eE|vncrr@+1cjLLFuLFi3ezkTgIYb
z!Rma}^!oyoSPs?xc-UU~_v`h|TeeJzum5WbnxgHKx1V=+cX|A-GrLM(8yOoH-~2kS
z?$=8h`#PKXwcjGc!o!X2?dOZf*BFB4+PCH0{FGl08&70lVEAr1g8^wRzyS$?1<XD>
zqVsmDw)4q?rbO3O%~W>pi}@yfaq^P~2b(P`J|x`!4D&pgZs0Wf{9POzHef!ONYF)T
zhJwU~OScHM9%W!)Aagun)?3te_S-Cs%AG-N9=tyU3c`dgER`gOECWN{1T=M1gR*M&
zO-Z@&b<Q-Mbdy`tgStQp(3Sa0s71c1Vqst~ct*>rF$>&|G0;UF0l8jl`<<78;Xv=q
zZ`VWPf*B3gF8eDp&!V51;m^$H^&s#1aD$o`cUUkBn3`C7pR)T53=DT>Z2hq7RJInw
zvWrm`?dqTblK<yF+k<p312;nRnu5IkDt<yKF|L1YPJvqe4`TJ)W&fd8PlsA947NJt
zuu6AqzeMmmX$FP{>Bps_3_fbl3m6)<9);MUcHakWM;-%%1V5}q0=WW=2i>R?IB395
zgAzkw*v=DaKmzRSSj^^d1E(U&z+HlG)+{w{?!!H9t7H8$L)V*6pE@;F(29ZKI_iwY
zfmtC~E0%SrA=O}-HzQ@^Ye5DE12J0W7>qsjBYO}PH4+#Y7)VL3KlrP^^Gl`wJy7^(
zvcy}{5EjcRH;TGM4mWyq25{}#$=TJ!*XqT7HtUL`_Nxa9TNFa9c5S)lpvf^;hDB6e
zRIqTO0Q<)NEulY}M7*lS7Vdxeed&ex|35eHv?<?tJ-cR7jGg(N;_{e#mEa@^CWz|Y
z4U<vvS((*fKSPN>>p{)T%<5wSrMvHbsoJ|Ooq>Vj0Low!L(i0DnMU^a&nFb@d#mYu
z_2rqg(o)wJJ_d#Z9*{{fAC7QH`;j4U>UrsguR)-!Sv0Bcc5z#ZYV*N)Q-bD{GcYhn
zXo3sc2F?esAhsV^`>B%oLSNma)@|+}Yh9qmF(4ZUQkq}{=}@Y5t%gqOZ$I@M+`!y0
z(RaHoNC^^dxQN=R1T~l_N|6Y&8;0$?$1n+?vs=KaAwk#FcXE)|ZR568x8E+i{(7q|
zv)a7RpcJ#l{{8X9+)5vC`?o+BoFWqrXUtOj{P`~r+w<G=j6&v~%Lxk)|8r1g%ZZ<$
z?%TEb-yd(-X0r^O40gzY8X6265~l>cl0T)Z{&Kr*x<{Ci#2Zh|qw=R6yXWLHFfb(i
zt+eOMKAjAnDQ$QSN!HQ<_9vZgD>rmLr~xJ7*XMs1Mnua6gH4Ue-1QdhA}|j^^ss?#
zf^Z<@kepE)CMk<{Q;x(0(4>@QkOXqz1-RR>EuANH`)%L#*R!kHd~BXeGc=rh^i>{`
zN_zAl38%o<_i{?zzWE0q)Z7kkTXlKn*;lW+G#H|u)G#v`MDF<qN`(vz4HwlQEwFVf
zrvxQ8JXQI-?K#g$FSce|&7~Yn3tZ2cGcZg(`WoCsXJC-X1?L!s2Wr1O#cs(l`mmtc
zz3AmOXk7qt3<Cp$ffTj6U>FBw48A_<q?suG_gMw4UoVuv>emCaZofGHu=9B#!;BP2
zU_wHwLCnN=^3R`jY|Wo@{UvAlrJJo@t^LT9!EB0W1)sl7Kl1?<@N_doH3P$z1yh0!
zZ-vCyL1=tkXSfky_OH0&QKbxn+H6o45~g}V=wB7?+<pdzfBEwcGdA=Nn*zu5@;8Vd
zXNZ6YuD|sxd{wsl<=3iQ#Om({@z9iWzzR!A4?d(0Vn#BoA^&;-XwnlBxUkHCIJ)ZC
z6ll<13k8?y5X}q>3=d{4yA7X&g^C`?7#&)H1_hWJnsdGwMHo@DdTF;1so}s{aQ7Fv
z<OYXFP6eVAXfV8H;`{9RZ%LkW+ig=<Sk1k;X5G3DNWx1vf#indHMr6ziZW>@MEYzn
zG`|bYDqwrTgj+K-C4+e&Vzh}13IzlnLDS@(MzFFJ<b8>0(5ef$YskQ`!4c9I11Vv+
zF=5uSlYeULn-Binwwxz)x$*3)S4Ba?H4F?4*+>f@4zz)XYf$=x(A2z!6Vh4%n<pKE
zNUsSxKBHYbaHzltGMBUw)4n8fbfaNo`Nu~`_k27ieREf7c3OHmXiBl>-_Pg&zrWSd
z(@U$Wvhuh8`$ZrObuZClhXy`_XW!o4oy~9eLqUJf2PZyRt0^;Q&IIrD`}KPL|Btyf
z|Nnmf`C@VZrpnLH6!lnPeg@NSph=sa+V6MEL3^9Ny}v*I@9*!=mrjp61)56y{eHjw
z`u+cY+3%aXbm`JJcXykAzf*i(;5w=s7W*~u8630w`DF5$GiN|kRG&72CjO3!$Dc93
zUo$y)x!>I{W}s;%(CpItz2EN{EJrmU8RUs$b$>n{xA}6x`R1n7)1t@A-`%PF`P#hb
z-JP9pZg1Dm-}`mi>iLj%HQ3<{3=B*q4TWXT&dfY>_H1k^XrJ12z1UMPFE7vk@%jC}
z-+5{2>7P$&ujk2Df@uKL25z9L<G}v%hlg5oZf$wF>hWB^=bx^xfBt-a{ketC?L~in
ze7sZl`>peB)YA!j_!+GZNZj62S^V$U>-DSq_}Q9I$M2uFbm>x?e?K0B_64?W<7e2h
z6C-Qinef>VY%`enGo3*;q37(`vroUgyc{lTU;NBx(vy9^-|c>OzV_$S=|A6WJ`dV}
zILD^a$g}9>rKNxVe!mZzrt_O;GjsR*eb(joDxdS#|6jd+->lv5cD?RO-d+Cw+`GHG
z|DV0f*wA?yOC2ZIIPqx>Y?T^A&+g>oeV`q1;WF0M-*UXO86?V?N*WBeB_Hnt-EnAH
z{w`))&ds8qKepemo4s=7$~QMQKAvU&{dWHT)T}J6^LD@Ah#p_QY+2E(D=Te&JOEFF
z#nt_MD*f+YGdq7;V&cPV?>QKJRs?zV%1)pB<@P*d6>UkLZ%d{qRj{~CLxhCEyLF|G
z2j%O2DE8a^%JA-HkVpqP<J+C$^G`uD^6m0<Gp@%~>v|S_d~{UCvPcEAoAKJ(=*cSk
z|NpB#H_vwV+uPfpZ@Zm$TG-!aqOiJOOlfs@cX#E3Mt1NV=figSxa+@}7$&csf5g6&
zF=IZ$Y6b?53yjBZoSSR?`OoL`&(E6QKO<lNXClbF6BCs!D?g=x&U*a$``g>w(?N6m
z*W>Gb*Ix(EiRRwkwmL6AGgA{Z;W)4A)yl7XkfsnpBW)c53z&O$_S^rnc)#bf-?Zt|
zKR=&e{|vNgcKQ6eS;yt7-+cP+<LjGRRrPDxc2iT+sVi5mOgx8{DQ7UqCY-rjcwE-9
z;DH05j77oS_m(w3K8S|9?4JiZ;Zb)v>X1hAvuD!}qng2xpoCPLfRo-3T@whc%^+R?
zkwmo*(RCfDzp*{}_A(}hu0`P;N{h<oniZY4={fEf7<GNWn_lKUCXsW;3(m2WH*!y9
zM87l25VRH<WHSs0NJ1KpFg^o=1T)6fQ=`T}gJ<Z4jjVF`X4qPQ(a48JBg1IMfQ7`+
zOVOjL7#4S<sTdX#!yy%4y}lXLDQK`S-+kAr@9~?S_MI_$d-v^|Hy5de^x-}@`5&0P
z^KRbWy|KIR*Uz2%$v|KK{;wYu=J3tT3=9l4M&N4PX69oHv-$tmtV@4xbD;YB@BY5W
z2FOhSn6kCmU;n;A?j`(Fj6a9Ec9enP!TSWrEC4Ln85kBAA)5vgH(-Nq4*_w&SPSeD
zFcV57j~W9FiP5lu1_Z-sx`BnnXr6+F1jA@S0Sk)Jf&vy2qXh*lBt{DgSV)W(6!4J1
zEGRzD-n+Z}?B*P1i$B@DYbQ2wXdUrl6I9n+>Xa)w$7Myco|cHFlA}s;`>)o2jFLwl
zJa~}M%yo6q;%52g1uHB%x}E2~Nk|qn3<{K<y6?1Wh4<78mu}fq$Xq^LS#R_FFZ-Vz
z=mS&?n8R9_%akyu%rN((Vr)TAz?db+a?!^?J4fx_t5;e6wqHYTZ_j`KYW4cO^Yd&$
zyF6aoegAk|9(3=KiM93ZFJDTGjg8;l-o73*84`a(3Lb+X#*Ge^7YxGhF1pL-78Y(~
zX6O5I$y?vl)bwiY_q*HkJpP?Ezh81xG~C4A{{CtG{dX2Rw_8<yN-4izTmF9k|9|@-
z3*0~kf$@fkKC$mu8Fm!J*L-x%-}^NTG`qsiFSiDCkq_u{8rz>wCf9yCss8`Rn>%-6
zii?ZW&pvzpeD}|1v!i2T-rTExzjw)QQ0D|}8kmso7Y1$rx}CrO?v*Pc{r3NU+{$@<
zZSC2!XTRP|pa1o4`Te=qe=l3UeD}X!ucIR)civcyI#D7FnkYHA@7Jr<pu-%u<=!s4
zR`dPc-R$evi(g$?37SCZleNCK`Me$c&K}QisKdf$+g6_5%fKL>S6R7p=FFMJ&y0<Y
z=UNso6IS<I^SiHIzHZ0&d)4b#=|*q+azxnw%bnu$v0q}5x>5`b4ZY_%UoZ&2*?zw+
z`}MW8&(Eyi^=j4D*RLZZB3?A}+r79N9-sUE-d@n9Qpe@%W3cPasjAv_dAa|5<NtrZ
z-@m?Yefse}+3fxDl}{#?y}flcx!?BM#l`OW_ZERe4MrSr0d2|IFmvWi&~C1CHI<b+
zS4rpZ`MBp^`O~T4W&i(v-@akPg_oC?|NmC<^?&(?2M5>fd^T%y+VAi0^Z)<*`~2&E
zm`NZyW{0wSU&)gb6E~;X|Nrwj^%iVLmUa0%(5aWNrpMQ1-rkm*{rSB8|2@95&9)Xl
zKli!r`TG6;Zp}1Kw<>*gWf$YGZvA~XKxZuehOXiQnasejqvGE?hlBe2|7-$XRb-UQ
zazN#F%}#NK2ZwBbJZS#=^ZER}pH69KZ@zl<>a=OoZf#EYzr8(w{j1;a_rJffG5PP;
z>+#v&|9&{k|9nq=YU<MRdzH&?-n<FgROtO5B`z2av^`=eY2e&e{r#O>)r*Co>!JMS
z+1%9Ke&^DqOF_r`<==mJcsTnz=%TK@-)?2s{(igt?74GcTl4Sl%iHyG*}EN&`|@@?
zZ0nP^zjx_U(CO2sWo@gz6x9krya6Q(Bte@N@4Q~W{~qX`E9v|_7ya%3Ug?vyuKIqr
zeD~{hyRW^wxg|4rwt2qY>zzAy?z~s?`K*|@cywgs%Ujv&L8(F3s$_-r`#qoU|AS9N
zfelY!21V%(-RNywHf*?X=+Ghid&NIKJlyQ(vVPY5`T2Eq|AN+|E_(BsaQ5|m)Lg-E
zpuQ1ftp#kk5!f0KaR6iKGUlYO0mhUG=9wuxh&3f3V;LA2FwbYfT>3HU9B5!MFffdU
z4k9c@(+(mmMspS-EJn*6L|BZL%80NSt+NneF<PS|!UA&};ArSjCv^5daM=!93xF_@
zfnl_SMuf&_35^Jg(GnUF7NcblA}r`wLjRDjF2B4e^(K45ABl-;WIB|3JT){{`*x^w
zd}*>?Z04wvDxk||e;{X*Sni#j9g#OyIka=Bbd+7zO6pjk!4d7T^=0dcjlM!RW=q=6
zp4?bjQ)6U&e0JUbr~j?azy5b${=oyL(QXSOVn@3zh_D!~6cJ%DS}7vJVu)6X!tc+_
zG=6)3|NgVH&CB0zy}qsZ`MG;_zu(&L{eI5+J!nEAw*2nZW4+S5|9-oDdwYJoy8paA
zJkh9w{^5(hX76QSs6T(%-~R6G{Czj?+=+?amXn#7xDYhnzI5r*cYD9z`+V>A{`&gm
zesi<V&$9(B{jU9ZR2(#Hdi3Z~(4hV@-`RSPQ3kLX7}l{cl{9dEd)O}j?bqw|-w$!?
zo0yx2Uk&!Ry?VF&{$1nqHkYg4?=8Q#`}60|ckBQEU7ZFx3T=1U+gC@$<KG-;Wd8r+
z9U_iEtJkNd-;L5|IB>N3aj$vQ{<_-V-`+;g%)PN;;mw;j@74eRyYKI}+n?|Keg9+6
zt44OY7j4pcFE0Dr|8+;3WmuO3a#-1$8yi8#cr9DLJp63=n;RQH{aOFx<8gWG+FvE+
z_bMK%-WEi$eTEE3*S0--?wmPu#`5#bnKS?Wc--$d$KvDkd*=4`_w)Dvy(a8$Q@ApW
z1x24)2k79jzkfcT&%LqX;hdjW!{hgU`s1|s_q*M)76l8A%h&IT-CY*DNfu@7yy2uG
z==`<oF~z?7|NVMx`5CmZ{^`%wA8$6FuljP){r0ZXZ2kRzKB?YCcjfErRg4UJ_s*R0
zQTLl;k-l%wo|vnkYn_(A|M6^g{;j>$<=5luYrDI<bMNf<*i>Jim$&Zqy4`tKLFdK2
zy}SE+(|u%z9JpWn<;BH5Ion-X-wyNJueoT(;9~_kuI=`=+-Pra@40rhyI#J0IrS&I
ze9eU`S3+)Y%l*Co`~Ls`ewV$!clYMz^ysLlSIcJS{qo*#Z*PC!_WPaUK$K~xg3Leb
z`ME%oL%H|&)%Kb(B}`fy{hF0wM@7Hww}|xf^WH9<9v3weGz-+)+FJJR&dq0MXRij$
zjLonAR|&G{)Xw>JzgD)(RjqjX^y$5-*K6~3zuk6vAIg*mLqY0CR?t*L^6|cJZ*E>L
zK5u)y{C@5AX}Zx-5fLw5uiyXf#6)H7=b%Fr<0_v{1y5q_d^&B_yqZrZ?S8#joR*$$
zUH7Nrc)xtSrM<1~UFCk8qMQFwPdeVP4LrejH9Y?9&*$^sZ@nJ(`pU}S+`GHB9zA;W
z-R}4MrWywa2d|CZo_BSxzunIzD_5@MlefF`@Nj#$?e4GFqFF)b0wdDS2YnR>_8A4?
zv8AEx{Bmy|9Bh7WTm0n2#L#$`^}jxy*8l(VDnc>ntR2qH@6Pw52r)2x$RC|pfCmX3
z8@Z#?F7QxiU>I$KA_8Ny4T=bh(KaX|EQV+s6yX67Yc!*SLIHwDGdd(3K;&pf2ZaIz
zk7jg8IDp8(IRg8Gzxw<8Ri$^?3jWl}^WEgvygvDXh_B)##inQz)9Viu_%6yn2y(k}
zMM%(Xad%Q9i{&=U4mU679Tq#TKDgM{q3}!bc+Iremi$HYs+2A~KKr@q;NF<~@7v#(
z{%6d$19=;YF_%=f5wTE+nB|g0ECO<d-}3@>4d&$s3B;^7LOR3)Vi4vcP(_TbLC{l~
zAR0iV0TBy4M*{~GQeZrqa=^g=B1TgVC=|dLOU*KxtzcjT1kUcA-*i#d0`QC$&amjm
z(i$HP91;U3;pN?ZwY$yl*KEGKyZrl)$Niv1?C0j&|F=JXcUS4^$H)7>KkC;1_GGgE
zwoRKZ9qksEKX43Y1(-f?*sFnW!;?Na+gtAPwO1x8yZ`#}xIa2J_U+T@@$Xiz-}mcu
z@%8ob@0<DUGHPr0?ydg5EkZ}`0=gktrMtx$9?S>b67&1b=JUTk9OegIUlQuxC-ZXW
z^Lej(&F{T9t-t@z<;|cy5%zyRID;k??(8g%-B<I|aV;;{Eil4n$(;ti4M*($|M?si
z9$x+T>vi*V>#{d5K%=*xo}RwDqwul+dApBCgx}uU`r2^~>UAGFoQzfngmzbb%{p)Q
zJIA{G-JbNi2L~F@K8KkOq3c1XDs|r7Q@MHT)~&jqw{G3~?%v+pzkdBP%R$}$prZ{k
z@Aud1@wYc7AD{MfalhTJpP;KJA?AR{2k(UzFzakQE?2$ge*OR2(|@+#ue)7?x~=;|
z`P#hiObmaDv$M0;u3w)&^ZuU7&8wErulu#H?*EOA$+lmw1b;sR9eaNNx*U1H|40Ak
z^z&uk-rTHCv;X_$vRN+kflb078*6`mD}8vVweH`~=VkBi?6llp^wg{S=%U)+-|k+2
zKi{Ho(ewHB|Mt}(&n`9W|8`$b<PT`tVSoL9vs{(~M$tFlu`>L44jN-OGc&WQ{Pg76
zn{RJ#gQgLh+4(^`1y<$V-F5Zr>+8FVpPwsR3qDC1<Zm$6VKfIh1+;hO)#~-%u0`j6
z{rmm?_cO-lOMZQM2|B0BZ?4tWpZ7jKK5kw7%m;KmQ1!PrH|OmCey>_rtb1MT?rV2<
zmxH9H>&32m^>+LHx(EMJSMcA6V=8G-{eDt?{+Dys@4viUKL6X}e*10Z@9*vV@u-_m
z)@sYob4eRBQd3h;-z>jhyZva=#-Hc*FaCNo39Xsi@ZUK)+l67;Ddm2fOTXXmzuzlu
z{_E-V_+3R$z4Z5fxn%o(j#cTZ-rnBoJp1*(9{1btDt>-$+Wlk4jy3-QU-Jp}F^D+e
zjC7(NNPvN1w6P8e2M{^hlL3VS7-KGc84Vn8z<`L+zyXB<7)y)}5P-vhfq?<bX4BEY
z84VoF9dW4RZvT_spKIQ#!?CR~{)A+tleeRr*wMlXA}0d`4Sg5#G+jDqyD`Q==7@>w
z(xf{DTQsg0u^whsEDRUv<=JxQfa=9SACZG51^vRW1X<2~KmNO9-*oZ!pQq)|`z>?s
zz4>AJd*^HUukUPo{w?P^=ngjrA!dvNczDpy`144@7}0CR=;C-{Xj@@`K02q+iJ?uD
z4RvV(1A~eoy0!&}Fa|GGFtmk8pr0)?;RuE{E)3sJ!q66wh~eAOKtd1O(LfqaNyz;%
z1_p-F>^52^p>}u~Mhk9?Br#gMjWz+02gMi|7)IMk7)fHZF^SOz9c^)6V4SrhbamL%
z<M#gwca^-Hv@Q4cviSXVKM%|Q`=B2i9UD9Mai6uGtaX{s?y|R^dh=_P&)a-H^L&m3
ztj`IiGuH5c3|ic0r8PaSDzolGv;33m`~Q`$TD8h3<-`P=Z#R;^#)U^m&sKD9OZoNX
zrRB>dlZy_ria(iKe$Vs&zrUL^E-qs8LS3G1qQ>@u!S{x+zs<zi`THz|)qGC0a0(Z_
z*?2td+nbv&udR(f)+ZbNe(UyoRoQa&e?HzRILvGLxW~BY&&T7>53<YqoSvpz{OxAC
z`2}}|1OM;(rm|-oDGBy5KZ;6xz3gvzSLCuU8u9lFrqZJ&!S;VKl^Wi?;%^T%m6_qc
zC)nA!+wV?WwQ5z5jOC_x5v#-28YLa+0A20y^Y;CJVHI!RZofZIcl#Y9c9{Z)yBqmr
zt)5(P=06KMvdQ1>=ab^Id<W{g@~4SnI1AY>6bF*&4PJ&n>XHkXO%gvpKkwf!XM1T~
z?C#RO?{9B!fA>-8yv=8yvYV;Xzk&qJ<!iqLis{Atn9qwk+-*_?_VA|E)0b8TFaO$C
z{_2Y6)~#D3ca^+M-(}{x7wvuzX*K4O2DLTImZ`0c+8Xt~;`Oz)ujT&hT)%eh+O=w3
zaB6}P8xmJ(Su-%qkDYCnyQ%2usjq$Ye?A^B?XRDf9la$Z@cq{RGRyb>c+~wrFQtL^
z+W-CP_ogpVeBYn1GV_{4{q;vG|Ns4sheY>R?d9@!MY2!iO<MMK&m~A)|CRdxHv%es
z`@{R=yH>^rSH-<tHY2a=<+8fo|8;9-C+*T)Hv3oZkMGHMudLU!T@Ot;`;XPzUxONA
z_UHG;yjRz!%nJvpP1?0G{_%eK*APPrf2O<T2XP$OzuGl7H#hgDBEydyHa?jdOTDK*
z`}ur+{PQ1kEQ>e2-}n33yy|x+%lCbr>%VuKd%xVvi;LYsyLd|b;;Y|om9#8MnOFU8
z=bIgm`{q}@-I96v)8F^?|Ls3J!omqef7m(Gsx+(5;!($@WQGeZ73`ouE`NWo^2NgT
zPY2oMm&EQaD?R@F+}zn>x=~BY-{1Qh_xpr$|C;iecXxJzPNu5*@*=R}?E=SUqtaJb
zayFke`?@a}<radcD^{*NIZ4&qDC5F{O^X>W90A+$rc-^M$Nsv%MGsrW)6UE=^qdsB
zI&5k9`na1(-MXJ%EbdqH1RdZM5+1(1`un@go10Q6J((7rck*Go{JiM=y{7DP6$z7`
z+%3QF+b?HpRPo_~&up``bNEr`ku-W4tsI2QZzQ%qUAOz)sgvsS=e)bS`}wce>(2-K
z+fKDCewK3H_Pfs{nc6QGXBwq?P1A{-w08SFE6+`3Z*RTXdOfc4VXJu2t<2?1o!j|#
zembT7`Pb|9&rhn)KT~!)H~d*U>a5<B1*_gLF#NfHr{Zz1<>xcT#-*>W{Q3L7{=A>{
z+bJ`R)35cOpS;AiTkK}W;@)dJ^A`7-o%;Lz{`|}S_O{bw%ObO~vMz1Uzwa~C=;#mB
zxxiVP?=fniNhyo}{}o{n+bp*XWi0?GPQiE<Gxkog!{m=2kIScjd~`H&LxQ82e%zdX
z`+qy$cz`uAFfd$DSsSy{$T;oHiQ@CN;bl|Y(!ajC3Q{^vFE*-dirdTS`~RfI)qFg9
z==lFn)Av6CahcVaGU~FjvW#+WY`9bN`E05?V*_tk_pMvEZf$aAU|^WPZr3iW=`lr~
zc{`s@(}~$(@c-}S?_#=9DWDxZ3)|&pP4>65oSnNZveWZ)aB%QscDV`#P$4o+FLu_f
zS+lleURIlHUGDe(-rmn^^J}$pZ*SAJPJ5Y^o&9=O=EX&>Hw&eDO|!2(nHnA!`ToA&
z_jh+MZ%RGA>G9NOYq#G!_2=j3>#v`#j{lpr?M~6@O^;2bR)?)Ubxb-xrmV;9>EnL;
zbDL66zxsE#<kc0;wb9%4ti^n9goejX_14>|!Y!_+W9_wgOToiKHvj*8w)}8_`E(zX
zbPK=zAA_q`ufDvqv-oCUgIdPbRiQKOYO6rOQu5-0BD-u!z_y!dv%j93ZJh3><}+i$
z{r~^I^U81PjM!IG8CU!D>YGic^+2JNmVdB`b?2{Ft2fvD{Pbq``+b(5PAG3qJ3DJm
z<+GVH&2pnwtzNzPcHZu%>Gr=P%Wmgx-}HD|+R-l2$c;%yt>XQ|!o#2M`~A+lw6yfs
zmzR_6YJW|cF=1KC*H>46K4|9uv{b)#<r|IObB~U82gk<FeY^esz4LNErt3s+)5+ie
zw`^DW`+52`54ls1Yu-)nw+(y$ST|~m$LnirFK^Ahp0n|&81Ix-HCwlC&Ahv-wC?Nb
z_|z*a0#lD?hJ>w;n`@SP>&YQ*{WJY_UlwnAY+@yyyCra$-`rV=hudmjJvP5zQ{2WY
zJ<T-xnn}T?W63{1J+1un@%ZO&xAW64EO0E{pAX7mIa>lhSIQslxBK<t{=Q|F|JL1p
zadEM6&5sX<*3X?+_v@w4JR8gKxXM&!^=uoEoub-dDU*H8JVQf6K~e5&c2fnEsQPTb
z-Pp94;Q-sppEb|;7#MudOj7l}w7dNMobr2>peQ=lCp+6)f3Hb+d~K=T-Y=JWWUbBS
zT9=>u`F#HTx#jmPy{GADS{F6%ezj`#rLEc5d1S3j9v|;Ne`RH`aq+V=K69;1L0m?5
znF;G+cR%aWUZ-K5)f~M!&3E1Yf4_Jnja24Zm3oDShTb)wZ(aIo%E4y#=eu67JN@eF
z>eGEuT}QjcpTAh#@Av!L+sm8N&x0cQ=ezR#vunTKHMgz)cIMga{CS`T(E5G9vTg=S
zU)fXn`O^OS|0ORksXDjuoa_)({&ZOWpMkPl&xr>In=dc*p8jU@dApg`<#{&)rSII@
znhh#v-t7PX?`GEOwLzhwQ_XU3Em^fnD>`>;=(pSX`$5Ig*-!1quU@@s`Fu|CrOoN*
zw`5<}ySuymeE7akQ%m08vweGO>uEmgHxo9Wx3jMQ|NB13+3j*w8jIcg&&gH4nV5HX
z*V5$UeW13}w;Rd*GWCBxR(?3he!B0*ioO5;{f^v{5qQ&3YAvW-ZkH+YxM?W0^!~qZ
z+a)au5<u+v|NlJCyt*nB#0JF!$Ymh*%gf8tPfSouJ)SXT-L6-wzPz}&_>DyGrP}Xz
zr$6qqUiU_VH|c1X=*!E?{rfDR&G_?3eE*4;%jeJ2um5@4^7Wd{pX}qgYi@2zooQQL
z=IMF5^!MBC%hS)#Te)i0DY59BiNgLihM*HQtDc{oW4Sq!@5a9`%k5Ji9qHT&+CF-a
zUB2d(<>zN-v(3)0t_K|<Sp071^JgCp^PlfjpEtu@zV=J-`PqiaZku<@@BebiThgwk
z0_1nliIX$Ua&Il4SAN;o-1M~gh3YpOj~i8fdUB`s``y<4FaAE6?4S1K#YNsZYhpkJ
z%@obxPnYNaGZBw134C~7^x2u2mv#0pt9rZjx>5GEH8y|0TyA~7=fffHpEu9fU29l*
zYIDNDrY~=An}ZTQXy2+#@fkx&`?{KQ7LR*C8RGA+ucz--zn@$A`C00L21ZcHd~>4o
zomr;YMp;)@Y{|cG2MXS*udk*~kFT@*{QUg+ZMXAgEB9F_fnxLB?)UTL|2$xSU7NRK
zVfF8~+lxOQ6@R{F^SM*<|9>3c^?0(H?<u?AZzkW{Tb=&o#Kg0o(&ubWKY#Au@Avcf
ze!pk^d|q`P=!&(PFBjb<&2l1cZOfhg?d|P!P&wWsX?&{h)&o$Uc(diQ-_5GmYe9K=
zO~ghe&?Qu$JGDS*ZTGuf*;Zw5Zs^qi`~7bB`)8o${yE$4cS`N__kFvS{rPNuopJ52
zFDE}9m!H4?-`Dl3%W`Di?fd;MXaC=CFK=zl1~n|t%r@6QSzo&2^EvD1>vq4>vP`u6
zb}M^*&EMDY`hPZGkE>qlKi}?V(P`bwtHalWu2D;M&lC7x^SK?glH-j=uU}|r=(c-R
zuh&FvUG+x8_tK}Qr)NLC{`h~%yPeOMc~95-d9Hll<cEjbuh;JVaIgA(>SSND%&`CZ
z`PbLQn%zv9T>ta@ve|i2Wlw@)YQJ9ny3gRR_WC`OI)&BE5*8hM2)efJ#6;!GYooVs
z$-1f~YgOX0I&AHxvu3wbuB-@*J7a(H`o3>lZ9X0mPCd@hz&maFUPgunw^vhw{Z78R
zy882-;`2+>&(CXpt{bsIp_z^M)C|MqqT{mVCJBd%VvEn3T0U$MHY#~>p-0Zvs`mG{
z*yqw8{{J{`Z&d#7PE6_5P*4wP)5l}dpx9GY%d>dD_j?>0uhbO#|3A;)EW4d+oN%CF
zSGnT9=evdNKOPa5G)!{Q+yCd&pMT%?`~Uv-_H^If1kmQ#FYoW$Z{51p^2dYb%iHts
zfBgk2Z$Jlio|$2&%y0W8VBfE+>!->7F8=<Yng7}C`~S*zmA#!+e9m(DhUwCII~4!^
z{(c_RxM5^wn<Bg0anJvMza?!d3P9UzcRl>D+;(}|xj8dW>+ROr|NHLyO+TN_o-VuF
zQ73Yf3NsteiP!7*&-?fHclwJ93tyKS=il2ir~cp1oe$fjKV5L<uYI-KA+IAVE9=wV
z_qF<<8_;fT$(%g5?3QNjuP>3yXKMy8OS!bfQ_?8K1Jv5sl6iUAn;X1IFE1_q|7j;E
zr0kBX<eU)GkGqp|y!QX>t=ZSjZi_2E+6?L$q@A4=TGr!svU{mW^|P7jpj_=U%Vgyn
zjrqGjpR?B2-}@z~?(^*XPa2r{PHaj&{i!?tkJ9tG<#C`8^O<kA_h!wy@Fx%3<<BX$
z%S_7Mc2n)RTy+kp8S690!m#{Kp*tu9-|YMSF4bM<?5fb!pYFb|GvAzkex3Bv+-*10
zc0Oq0HmdpYq4Zqs)2ZRJ&VJVN1nqNvv+MP`$Xz9w`+gkNe|DJP{>;?yxS5~~4Z3gc
zdF9rmqg`pG_HkP>0znOgH8DGltlw;K234SU%J0|id^Rh)=(O(kCCSJ8N}sQb-MuYx
zZ^FG*p{qfO=*%qB)$c5??yLPBQ*zN2)b_Y;3A&PSrbS`W=E~=5KsD}p+wW(%_4fo^
zKf9yw@u$b~|1BOL@AvN((|vU=H&1^?P;~TcP*?wYTy^f<jc>Qz)(ej*blvy!Z2r39
zcYl6<E`ByMJ?+kpLSEU;2Yco1?V|H`rpnd*cv$l0h9Rg<Q=J|&>FxIWcKZ8%B;Eb)
zAg&uVWnb;@XV2~bSLW^ccx+Oz`I_u?JJmo1(?xgrxp{YYJ>7I#@3i4@naR_1qtmXe
z2m~ckP^<C&pJ(QvRI=&$ylS)A<zcmdzg`Eoo!)N0?>7mYh8}fke|p$1|E$OO+zC*t
zd~5dgXQ1AI?e{yAm(Q!xirrnNYgu}@0@PM{n_q7YYLi-(yqNIu@$u(#%kP~$HC5ZV
z{@<TDMW-}Zu3UL?Zuz~L&3slG{Puqeetmr%UiOBq@c-ZM=|4U^e0g<sIH(ZT3|_Wm
z*)p~4Yim4bo8=b$d^&ykvSn()%Y06Hs?VL0yZx?NGdsVYby;)8<6d)6`+v{RXR|&3
zy_T!}dNuqxD7O9UK1~Mo;XoFeUXPi)``s>WfBU~BR^{(vie44nDL!utYL{+4E?1p$
zV?!dSj(;Wh`ocnI(6G$wb-VSP+xc|$Q#?UAuJG}(r;GdTPHj9cH~Zb)-Rhp8OA|r0
z3aAADvS`n@TiG*BGK2VRzg)Oe^?EJHWN*KJKc&s{VvhAlPIl(AREhuhY5M8D%PZy-
z9O48e6t_N^nfkRay;C90$Z76!l}q032VJoVx=8f(-0d|#KY<!i*6(&CJ0Ht70hKp%
ziqBa}nr4OU`?@y&>4IjyRn=>1e}9v-D#-xt>Ia#ux-7>c`FLOK^Xzv@o72vo`t$R%
zv_jzJFV~{;mzKW1mU=uRp!{BC`o8~v--ALlc6Zs?1C7j=*TwFx`EZcE^54(r#+jFv
zfEqubmN}>)wCVA*XP~5Wppm)wUgdL8Yxd=Zh0Zr8G9)yEC)Ine%&{yss{8Y!>iBa{
zP&=td(pc^B@&5b;DZPh}ipS46%xA4*ez)ZEa=U#mm(5OlaG(*?#M$?K@B62Zy7lwS
zn7;)3+nRzJa_{#4|HmU`vf{&@$jxa_L9L3+<#VUKUblN4qwuuXSAzY0pP!ri`9U-P
zy3eO~{0E)1F`ZLbE#*K1qvhKzmp>g~<~J!g)n=Y|XUCV9m(@3?pZ|A7{zlDH?f8=*
z*Z+FC{JHe~A8yBbrN95bvHSgs73=oaJ~+?QA;Q_zAu7=8sHCB##Kqji#?tF}q=;AS
zN=8q_B15lrdylM6a!z*E*|>d%L}0)K4y~h15;`3srb<CeIy<I({(X3Q<@=VK%qQQU
zeRJ_=-L<5(XXeb^DtCU?VVg5=_VPb^^vFUbbYK3ypKO_#nLoZ>k2kFNknn8Bh7ATk
ze*R3nx2KYWmp3%YsV-x)$hP<Ue)Eaz#T?j{d;7ur_xk1Kzs>XSCA`14cZO}X*}mWJ
ztaI+{nCKkzH2eO(+Qs`4*zfr<<iEM`{pgvQ#?rRmetmuYKSAh|-p;bOQHzhSx-B~a
zw2Jk`Mompku=v8WK_}u%pPiAc`T2DEhwtCn8BFr;$^8EIwt4n!>194Mn;Mzfm2`A`
z)~dhMi{B?>W@gsW-QB!yogRaNsi~;4ThD<8M&^PqF9LZajarJm?96g*G^|*mp%b$s
zU{~Y8U8S!-92Jj$@a*jD8@ozZ-zt4%)h({?mYJ!!XwjkvuU>U++GMmQe!tx6u(eK6
zQBvpT*>+FUjsDbk^5~&f?uCmNH^08V-do)L&F$^{#_8u=?(eG=6ckj9^;wi>mV2wE
zqk}^yVuQo8S)aatKYn($`Nqo6Y4-$oF60fq;pF5bASKncG5NUH`LoZ?&VKmtVdK@+
z;mP;*RPIqO5)>D2*Wdp~DEHPD#t+{%f0eKQBPguqGvQ{#=HTUiAHIJ-zA^cDh3nI_
z>+52FT;Kms_3oYnr%rJ#cJDv-<mBXySy#1Q?x_3wOHo^!`}g<v;j>v^l-`d%cKrC^
zJ9lJ+)%}i4QuV&DueSQnzu)gKeP6j_hXs#}g}~~twTHgFy<O=RHfySO_@eCV>vojA
zl`1JMHLU+v!@|zK*nhsAho9fHx@mh#UIvxCzQ+6d+S=gRy9L%qZf5iI^V?DL)5t|h
z@Y?$LepYU=gbNECJ9>Ji^l@`=IBd_myP@)P+SbU1eKkLeu3WkD;M7!Y19S7^AlGJG
zRN9h#oljF!^OB#0v@|zAKmVGTok6)~H-Bz^dV2cdn>QsdUc9KGqcbJ4fsdi~_qWi~
zyO%RLgoKD}*|J4IUcP^s@9a}DvkjBkVq#(n{{AXm6T4gN@^b(7xpQT&t%+PL#(m-O
z<Hr{lxpGHDM=!4b|L?_xh0c5Pbc8yue0tBx%gbw$d5LANRq3G<6P0H^PdnBlIY&tA
z`q6IjrMB)WLJwbDTx?PGWyPJ1vesosmif+}BI%!+b9a~MVz=Hy+j4IQL_|cq-?4VB
zu3qe}BZ`vp|9_sZ7m?dv@Q`VmZgks|Cn+;#&Qvro2=F}lgPWV%IU-`lmyh@MR;QX(
zt_Y5a>G}Np{NnKSai@BYU%kBC->~ja#g@#=Y`e?fyZ!(7_jPY)Umqw&A3lHHUj6;u
z%C~GTeSLi^)~o@=;D(fwLN8vuI#s*A>fayB<t;4&PA7KviY*X!;!tc6ShVO!l3`YM
zwzTQCZQH`$sx3-OPdBf+bX|RZO;dc`&!_T!ORPZ2x$^Tf&6pZK201x7&}lLo>i$-#
zss{6Na&kuOF4HakSSc$kEL`*TYIwwkgvLpeK2Du9sp;%&bMqb18~XbA)codj+}xb5
zttnZbes0deJ(ZtD^z7Ih4mPtVzq_;Z#+J;<w{#qqpAEXvCuiHWv-o+^t1Bzd7)C`!
z&9ExflC!Vtv912L;w;mbWxlfyffBG=Z&pE0Ny(O|9HvkAUx`Uvz1zD^@zoW^r@2oK
zT)Of3`@VvrqD8&35`X^uc`++#MKr@LiB~1pLmJGy1D`DJx6Ar+W6`2T^#+|;m4AL1
z?kayD_x@+$<6{TUoZ-25?_NPsk&}xHOMA(xhu_}b{_$@2`;@xx5z*1ghK7Q6c6J{=
zew=vEHsr31RSC!A<NeeB?M=zf=JxmZ*NNXJb9$Ptb6%capN!?F>ANocR?^bqGEO_w
zuzIyNgF}40y!Ujy*3FxZ-FhS#)z#Hwb`&r^d-iP3WUc#Kv#%Q@ALE&6{n>Yh0pquC
z-#&c$)U<f9^0~Rz%fluYy_T`55J*1WH#PFd&zH;RCw+W$G-79w>O9-(Hs^M}g`Shu
zWP(3AN-x{+_Rdb>!)?5W|NZ^F^t|sZ6VA)ad=EFVa)0>pGI(o@#iaT3^^Gg{<|$S!
z_nZ5wck7ldQ|`Ttnwyf6a-!zn_3iob3=@9;J@epT^TwK=MN3m3zrD278x#d^-o9mI
z@SdjA*xbzg?EHNF&7NNO_thFE9%7keUq3HAWU058*P%N*i<jQ5cyy#QVtbzKv3_~|
z%RhU1dLF!g-+y;^`RA@xCFSq#99-nuy`(<9y1E)vgnhO1zIN$S)BO4KqyFagb#)z@
zq8WT)eY`zGzIkOqLBWANm7i0r7P=@M{PFSe)nD(=U%3*Jb7Mne<(|;hVOc-tu`;mp
z$s9P;%Kci`j{RO8`<v&_+u!g1FPD9N-Bi1{okgncOHOSseI53)-rd#pr0n8#+!yx$
z`<4B&ezRGAz;f0X#m~+hd~$NKA_vo%GiNrWo))X9u0Gu(*y(cN^5y2nM#kk+{-ma-
zgHq_3$82nDSzmt|db_x=fHG`L3(JgIvyzVY$$t3$J$&_foxHodS|>~pV8~xT_r;5h
zKi_WW8zsM5w=!;Tm7;~k3}-L9vUhhnU%kqT*;64XCMH&Ne8;X`j~*TE-mq=kv30S#
zU*+yutjES9u^{aJRY4~X#ZzwF7dRDL1e`bm1DV<Rj{N%i+OXh(L&@uFy_R~as;*Xk
zb7#z)`EdLFy2D30g{5VrWo3Ddjg3{81o2LtI<@zo(&+;S81nD!`PnYKQY<$&cTdH~
zMS;oPU0qT!6aMZqFfnmSOG{gPEG;Ev#Z{Lpr%rjzwEm@$l#$VK>eQ)vi;1rmoDI6+
z<?Su~_g->d-ny`I|F;(xv&ZeNYW?~7xw*x*cif?+m)6Bve|d3{IsM$6%z`(krfP3Y
zIVq&NBuG})x@?M`L(r3JYom7*K5i2dTFGW>YYVCfjMLBM6ufzPd3oWZBb*?&o}F#(
z-Y;kS;qUkR<`!k|@9n+hsrPEZs#RRF)@3c5Hy1Z2Po6xv@bxuakm4<oT+wcBY`3=M
za%X41W;>pimS*-Ve|>rE>aevRo}3ikdHmP+_x&$kWbjCtaP;-{efa!2xX9}2hi7M{
zch<+he*OCKot?!J)@3?szO!2P?6KLBeZ9}wsczGzO;7SZZL9d0RPyQyr?9$TOMAQf
z;$IJcKfAd(z3Ba;x6hun&6pukQBkoVet#VYKmYRyed`Y$a@tvL0@}nRC@#*<&(9Bv
z&gJv#9!=<5f98zOnOUZ*?|nW!UH^Eyd|k)M$?AtMUlz9i|Hrt!q~>CqX3oo(FTa`z
zUb%G1DI-I}?#~D3Kfmw)cZ-XYtNZiO-H-F9fsv7uqhsTjjmws)S(UzGsjdB6mE7Ik
z{nT!K-YYQ?X(_2|)@ca|4XajZrMf>-Q&)FSo9NQcC(GdQE^XP}U8TXZePbK9-?#ny
zy`1mZv11Gh-#<U$leJoL_I@bChgVm%O|q}~{Mzwuw?^gO<-W7cG_<vYqs;CV6%}3B
znC$-Y@viJu+1J;7J$CEXt)%z&_MYlmR#Z}28W<OM&Su`snVn*~Q5uF5Use44wDi!?
z@0FF6Al8?S3l}Pyn3zlv?A?8=?*7WYOP4QKx(8_f`t|G5z3B4oiLVZR-I{Tc>HIv~
zWV!vdzqj40W&3ge(BZ=yb8Z@`sHq(~bB5>k_Wa{VI)xXmTv_K`Ev6gQ;@U07SYiGD
z$$>^@3F9=L=OL>eURvt?;p4|dJ-hXnHzvFDNSpCYoH#LSH^bi-7Z>kQ7I5NFd~f<S
zdnG9AD7NfTHp{!iAucZd<;_iDK0dw;n>RbpHp{)RB{MiAEbP(E&FMP|AG1Ar{5UZ!
zZJAlQ?^@&RYdS0}EDM$`V~el-Dq8jRm8$W?pI={J2dUeZd%G?9cwge_X}U6(wZiw;
z{ROpFe*E~cp!D^%Gll2p**X^#7|6)VPMy)W|GeFAp4ZpbI&aUr`{CvC`9{a*S{Ac8
zIy!#%`ZYAks_s~iWOJ{y`J&w0+h&+#PP${Aw6E$b*Y5K7$CmldzLLgX%urBJ;80Lt
z(8e#%CoC-dY{&ES^OH|c)4jC&&I;yRI<04~T@zcla3Lr?mz0#ucnr#%6DA0Jd2!LX
z^W~3C+qWO*xBt`d=~K~*moGJCv^kn?-95R>f4*HuZ*T6Eh|*hE7#VVMau%#y+4=VN
zc5{oetE)n@wlds3caCr8&YitcI=??Wblw`(ke8p|&(1Hmz<<6SZ(nauPl%J!)x_jv
zW?kL2Zo0eTw`NU^(goMtYu2nuNJ+V}Vz=<RsI6Sx;`(7uTK}rPzw4b}|8M3_L!W**
z+k&U3M0f1oo&5FHRWHBgQlNBy<ml0>(RbJxd}o;)oT%)ckde`G;J^X5+=35whDJtC
zb#?phB+sw^XBo96gE2lne#ed-4?dr_4==LXcWZ0*@i{N<ZOsmk*;^(0?%lhBva(|*
zCMr*z)2CltT)br2vQxI#mibB_Id<&O>C@cKZ9E4b9Bc;3Iy*bhWZnEf_s)*OjEjp{
z-TGuY|NZ^F`mU*~^s)`6+1Gs1HeRjg=HY4S?Bv|{=acuIijPc(+jxVEtm@XRT|05g
z6qVXLdn${cy?;7oipb7#xBB~A^Y6>`%h^t{yLSD$yN5@|9oK6&Z{FmxkFUFLl7BDe
z*}7@7X3e^A;lhO7nt`sat%uGB+&9;a-ge~k^Ycslw{F>DkZ^$ErPG)H)22^f9wyDS
zJ?ko$|9rctcGs?5JGR7g@)Ny)(<e`6etC8fv_bL*!_lKhFC8!KZrZwK%d6hCD^>)|
z=H2$Ru(b5(zrVkq=6#tudv^DP2?C&wjI+_dnAq5jnU~cptgMnQEO0bBer~>fzwd0b
zh4ugcU3wlA6qJycx9-Ulm#Zt1k7w(6d!Md49~u_+=*r6A6>HYCw70k4@eR3h@WMjp
zjm6LXd}bOgy?1xd<HwH$rKGwV8W{Xu{#Y4ZF>k^IhT`Jlm$K)t7Czi*BPuFdw7Yj#
z)rSX+ZaoqgS8V+D?OWE@SW!@QHl_QP7Kr9h)LK>h`<sWK-?3@B(FL!rXy)AC7yIlS
zhwm&C$Ls52H`e?tVqsx<(9Cc5U`E)_eZO95hlGSA{QUIvQml^sj|a>znf~swKKbh9
z%ZK*=fAWLm=M_%PdVH*Rf``hF7mNEp+)SUpFnoPnk-5G_@iU$+Tee(z=jY+*=;-0=
z+q!+b`K@ia+TZ`&*;6TOX=w>676JkU-k<Q=SoG8@B|Sa)+M382=J|5FN?r!N-*abw
zy?p+?JqI@=9^O#&)a%~FscDDXcwgM#Z*Nupjz?Zz{+Vg%uP>Py85t|CF0#9&)A|<V
zraO1<CT3=Ketdk~INqF{PsSlGZeCQa<d3J*;}0D>#+H9?Pi6sQm4gGrzpv}-H8p2u
zP4G|w^^NA)R5Aqz2e&4#U9;xF<Hw7ar2M&g`*!mCdwVNBKl5FzCconHGuCh4zD4Y>
zv+e5cmYy?ZO`f#%joY^$A8O@3ar$(2!J_^9_U()EW!t=c`|*E&f4`hHsoBgs5yboW
z_;_G&@M5#_16e(S%5D$3_4hgW`0&h`JNIed%R4)b*TwE;<LBqUv$NR!B<D|QlMDf~
z{ChoTXPX~BaA3i`!igR&Z*OlueB=m=cG#ML)xBjoxw(R3Vr{J4Vkd0vGA<~9S~t#Z
zJdOzo3npFu`1Hw>7GZV22fyF%pI&|E&K;TX^>IfRI5rCi2`vg+Kl|U`-;aNMd>pYo
zZ|<G@$JyA}I(mAJbO<UJ{Q8o))yll|x=6P2%!AGB%1TO1&h31uapmu|ZyB_ny>&|p
zG>$OGviOPIe3MKe9$wy$KcCNkd~0jAm)~*FBwgX}Z*SR-KYjjO*~UiZ@^b%hC#|bV
z`T6>rCoY&aO-#*qmP+}X_51&ERaaN1x;{R4=~7VIW)Wp&<!7=F-rw1|IE-5+H#fKN
z@2}FA$+fk$&z>Ld?CdNO-@bQ!)z??8KYmoaOt!VPeRizU(9m$h#*KktChv4~byNRM
z%elCS^>g3Z^7r>bS7*OEAGS7%m7Sga%e%YM%5FUk9x6^QE-ZSnyISU2mpcitq{&y^
z&%L`#^zZNQ#~&PQPRz^Gi;b8wablx;zudtqS3-7e{Qvs;`iV1Vo~(&iZeh5*%-6Z5
zW>3lGWvf<cSy)*qX=-vdDI7R)g5%=Fi&<amLer0SiFWk#v~1mKdgtz4MWN0O@6B0m
z!PWxg-Zsm*v4K%gQ1Hc_oyKB%F(<5-U7BNGFL!#H?%}VmuP5f^^~LTkOFY!Vx#hzj
z|E%onz<_{;X}Zx~^G}~XefZto-GPyjobvMWCGYReO?G;!rKjiCEv74FdhNss4pmjv
z{{>1{r_Z0?|Kv%^lqpkAygl`5Tc@UCi@>LPSCti)*GPbSn@;x<O-)TTG&CmMV?A)=
z#tgM;W({3k*NO^@Ns}jkd~?(I<<HE^%Xo8ga}6^tC~S?M!_VM9&*os4s5U53h=_?@
zv(8INVUd@Y*NNF7kd~GvBlIaWI=XwYdq1ei^6>IHv^o8JKxAa+GT+%=@z(qH?UOLg
znsO^P{rbAt!zU-J&%8cm{d)ahUtb@$UUtd0>I(<R_vh{Z>lC+lTCuUQNtoqGi0MYL
zaC39>asJfQ)}EX<ZPKh+TIHKX;^X7D-qCsb?Cfj~9v+vH5|gZ~tQ56B+)WG{BY4cs
z&1?Su{k~!I=EpOpOelADa$*AYnr9lPpYpMp@ciOp_lh4M6hRIAB_%aapFDYRZ*TRB
z%ggy^nPy*mP*ECX@$1u5Z=3pmGHGdPU*Bz7`0ml8M+KnKtiNBc^Xi>Df9lksW_JDu
z4<9aEQc`nwf4zM8`ncBqetsTaUeP{XJw3O?#D%x+aB3(iF|qT@9obd-`ogZ#?AGMq
zprC@s$9QM0&}p~&E4Oa)+_}BU$NLVRKE3*&=XQ2}ITtT4u4`+fmoF))d3$p+`($;0
zx0;$ghg>tu-`#0!Z)XSfFlWt@QdN7RZe%3%`PtdS({!UBJb7|N=KH6o-aT@*Qkt5Y
zXLeif&leIF-dOcD>&$$6c|JbAGliz6rZY^l#e#x@Qp7y=op*9}{&-Y8Uct~X@ZtSi
z`~Uy5wz0AK@aJdo)}71z=Gk=W@B6{D|Ia7x;=>{g72n>>EIBMvYH1$5J@4q7o0})j
zn$@KjyUXCXtGoN*+qb3l<M)NkE_N2t*41^*%+$QKJ%4>cjH4rC*}FTO=H}*K-rf%P
zeEH+n)@*T5w@lW$OhYC-C<s)l`ph!%%r!IETl3TC(xpoVsi#C*AAkD%`Qu6T`3aw%
zoXje22c2b`lAdl}QU2=BpBkT8CY;H~dJew0xOnQ6zV&Z!Z-0DkZS)z|pQT>j-icXR
zT=n(!Ik&cWdcF)fKi9h4Ap4q*i@W>j9GM&Y>+An~ILyCc)22r=`qod^k59V2Ew`hi
z<G^C~euh1F@0>n-nECQD-{yV$?4Gy$0cAvKvz!BKqqheH1u2zZ_AGtd0O~JaTN}Of
z`Lpxgzg(0AFI~E1vGnos;N^bM!My*VcCme(jgzzU#l6+#py)6&GqWgtCGvbp&6Fuq
z5{`C>T2y{gk+ZMkVaT|>O&8SGQT3j7;_i}9wW?y>ib9<U+1cHNkB^zY`mI&E>!O#e
zy}doCx--wa!|>so?ds_5c_+@DV`Iq3&IVO4T=wcU^E-|vfrlfG^<);jS?Jtukax#o
zYwi51&(C=G{dmMJV^<UL%+^bQWoD(-tExH<#g+;G<F_!(1vSlE1f1>__siR_+dd&e
zR(!7Tr+P;LmXy@gtGkz3mAqis7;(m0u6#>mSIyC*M|afzF57#(x3|}~x%(Ceq|xwx
z`>k71Q>IRJjE<J}ooyCsv2Dv1k)J<*W^I1Ss#x#t>&x5K-Mw)6a`xQZ+*VMB=_4qG
z?b`e%exaZAvOQH_xn90}nQ?ucY)@~mXy4gWr<~H#mfgy!a64hYcGoT`RaMoDYilB#
zV><*cZCJHR3)J$Hulc}OQc_ZJ{NcJ4D>(S&?ObwmbwShB4~{K!shw+8%BAey=W=~r
ztl~tE4Yj|^dL)h6niL*PkFRrles1o=w{Lq@y{CQXTUD}g<HmyW^7eiE?B2Y2BOoWo
zCoV1?5)$&@*VorSemw3^%+Bs+X6FN`tg5Qw;NzQ?cfhjdM}bY%7mr;PW*QnC(q=gh
zetvxCXJ{>4wTf%&)~#8$zyEs`BQ()t$u#cNvuDm2RDMd)iQ6N=up#+4pU-?d*}%ZS
z4I4K$?%r+P)7vX3D0t9vWl_h`q#k*DxxLlj^9pj3l9c#lEEY^#FU>H+zTOTrChOWQ
zwlIEw-G>h!4!pa&J25E<G>o@+!v+D+VB`6Dww3Oxpjh;T#ps0chM6-ZRfIafEYH5a
zZjbWHDbDSD2ag_IdeGWO;8Xhg`2BeWN~^3+oj9@J<eL_Or3S{v&6_tH&zUo4#p4r&
zFD@urSX&>ya%D=n$S1yqb%)(#+XWW!T*;SmlWqSad!_KkipK&@QyQ)O4zGATVSlp~
zpLD5=Q-{&bn>RtDUOS4Oa&>ieB_t&^ojBpKW9LpqYinsfKE8<EWxB_DrH@;$y7cw^
zefga`cY1huIE02yJ+pIX)mN=H9?7P~?)`@jA8sxWS!!%%cI;3qw_)|SoGVwZ9Jp~q
z0@U>bRo)CY_Ewvxote?t)x~wr^QV@+zPqC%W7PJ%wcEHaT)uSa->3hJ`({6V`Qk;w
z?QOXqK(h`Nm6Z>lo}S*(*~!Sj!p@%j^wiW7r%ykY49?7W+;r^qg@w#)JQ58TE(C~(
zi7iS!J?+wWEk}U|j~+F>ySp3Iz1y=`2-JmD@x8|gP4m2;KYTbaRXe=k$qB&@7bOWP
zsY4ep3Z6T6Zi0u(i>s@r-@4Q3GH+w@aVHfaP^%$r;l8O;Mc-%K@l+Aov17-9lP5X*
z`uZ+hzy4g-bE$-c#DR0?{C>?UEGcpM{OoMy@ki^5pP$RPysY=k*DGtI&F^gtX<EH{
z^_N+%Zg1EB^5si~dywRoNUqyAHYP7!KU*($*N48vL9eXNJv`jL^6?2r+4f#5KIyO0
zX0I%At`y$LSja0~D)V#2eUlz=L_vjDJl+s^JaKWKvV7^BHZThm%^;nnGDn-5n+3(h
zj_t8twS2jH8=q`f=H+FYmNT<Dy1GDvBSyx?fgvF+_V*9_s0jUC+dAp}uHEJDlfJ&X
zdf~!_hGoxgulyPs8p?1_FYEWK)$2E;ot4@e(@^*L7_Uz3E)h01HVrK;CWe<x?(XjH
zK69-^xyAKDPP4w)wrv|IYC%=dY5n~Rwrmk`ZsVCKcmB*7m(^iwE!3W9TUkjpHa3EK
z{Va|Lj&_SbeD<uZsfp>wuU|?3{`~y#<;xS<V9hIqhClBoCL}1t#>7QNcFvd~0h-6D
z+LL*CnTEdpb5Z}7@9yqCZhgpF+1y;5kB^VxUS0|V!}_?rOdq!0?vb$+(hgs@g!Khz
zME<@@xq~`*(Bg^gr1|svZ`_DDa_rcnQ&Y7){QTT<b9GBfN-k{AkB`|?F|pi5&&b$V
zP*}KGJA9pjnVHzjmoEi6T{12%YAs=!>!Q>+cdqRF6<(mDOcd<w<eol#3JR;<US1WU
z&XS-Rot>QTJ7U&GZRHAI7jtlH_Vs|UFt&{mJ?mn3d!6rhQF5GZmRoT=WS4V0pXd7J
zyYx+Xcz7PXc%fmdzqk7Pw7Q?`{9<BbC(fAB(bdJ3k(G7m+O@DMUrS5Ng|6LVdz6bl
zgC@#A?)LUx?75=;($3=al$4Y!)%itbWp4d)w*NkzyZT=FmBlA$O8DCbNePg|BC;4<
z1|SRF0H>co%p?`KruzH4g5u)C$9koo%FVYf*8?@Kmn>0HRezj+xQ!RogX`(-y|}wP
zUqVXilx+Ef1B|NbkI&z@A)y_%W<s9Ng2juQ-`?Jye5i$!p<%9d`J>nC_fOMH3syfn
z+x+;gt=WdDr$jiK8kYIaPP)IZ7Bm9IprE3{vN`>H*lO2>rH>vxdhqgP=cY|Y98C=i
zo!cKhpI<*s?*EU+{h-=d#<Hj-*~@OxqD2N77Zhs#d^}!IUVi-7*VjwSmDw1|%gbN9
ze*O5$%HTPZg+d>_ecQWaiOQQB8=0S<pAR0nS+YdsrJBqAn$Ns-|9+<1)clxG9JDCw
z%$YL+0s;;B`~QkDB&4LYv~r6lottCH&|sQ<E#c~_Pz_z(r;?KeoH#1eFEW)t+uVVm
zk*SCXiKeEe4-XD9cep6M)I0o2Pha2Pit*K*oyC_<CSARHb<g6$z~JEK=<Ru)>MgN5
zi&$A%Sp_;>etbC0|M1P5o(U5K?iub}wRWv*QPHL|maA@uZcjem=i%@Fe9naV;`(tO
z=e=`sbS6!j6c8KBD=RCzr{?FRavQx>t5<_NQk9@`x2vm5L8$Y>Qg3k!YwP6S-`?&?
zE^?k6@U;5hAIqeqq$SUvetUacfQ7NDs_Mn<?fP@(&i(kl{{QT9pQ#R@lBQ4Rl|@(J
z{=gn9zuGH>B9H>**uuKS5~VVcV1dOFrE`9*c&y<j>u&eTqSsm0-SCygCWwIHD~qpz
z#}l)!t&s#x?rH`vJ7Fs)B-FIC`1z`*OiRAKy?yx7C86i%=eJLrCidP!>*&Rcg0|J)
zrreVRT}yo7>Qz@47nW74SA(WtpP!%q_}|~(b0%xWuaDac8opT*yIYJQAvu{@TU%Sk
zzD|bW!Q;oxOO~jlq^5rCIqB=?$Cs3xd~r`@@s8cQomGSw8M?Z<He_Gd<B>3M&^1?h
zb$z`&i{pW-tHVD&I?6p`#*7m>4)Gh4Se=}mC(fOF)_ldJE4p2OwO_5XEG_!~ueRpX
zN%e|fUo;sKetmg)>Hg`hTeoi5u;IXgMrJ`NsZ+*kfsXt3?OU;K-LyQWN6(+Pdr#K`
z4O*^PyY^_0q;W!SZtsZ`9_Ktc6<a2h3+uwmor&}2>CIgsBrV;&W{r+X_B9?pKE6w_
zALh=TTY3D+yPuz*Un&+67H+;@|6f*0O6tYc)#B@7cOSE!=e1(hszV2x**B)0m6|2;
zO}%uosb2iPp4#8vF8=%}U;pQ0`<Gd}3LY|T+O%oG+O=z^S?@U=92?uq%+7bgRF&P=
zDOFon_vp&t<u6K^Us?3J$}Ug5QuqX14uGN$RI#jhyvOzLvX3hsoAg-q)qq<C8g8H@
z!6#ihXZwoBCUW4KWnw?L+Bv%7@gIF<W#u#TY^A%!^`}+W{QUIv#)d@ZuI}!sb9(G!
zV`Fpf><|oI?)OyI^(hN0tD=R41gK$nYl|kR*9IE8wX(7j=ycK0*FQebwt7jqOSpQs
znC_u{wZA7!oyzL#>-*;JZt=-#zD-M)sxm0(>hfxbuRBtHzxKGLW}xb>UAsV2V9WgH
z_Z>Rqv?b?eP#WW}cXxLiCLiMo2?;6iTP2gUaYx|eS7rtb3%0#~ygq)vo0k{YEc1N5
zzqZVK{_g(s=jUfo@PbB2`#7h%3$TE??rCXh5{5}E4cnh5J~+_$_1LW0vmYPn6h76r
z!f4Ur#f5Kf80OsDBk4Qa%(bk{?9QD#OJ>J_CY5z`cw%>#J(ZpUDiz!jr2=E_tu2mm
zadJ^xGC-4&9x6f}Dnei0+}wOoK4|~>Z*Om_&pq+^!$W7#+_6tZQ9(gNUmxH58FxZL
zLKO7${HpqdgoHqI2`^<;RfIUftt~b2r%#{mD0@5W%N-RpwMSoHUw?6FDfgT?bCx_m
ze&$S1dC1aT_5b&saXECnU*0)BUjFZ|uao_h-rU{2{nopl_{hl4mKK(mKRdg-51*c{
ze{rER`^)UKM@KsMBo{eO4iG(k=FAjJdwzMlDfa?>lqMReJMTRY&)S~?_a`py1C<13
zphDvKMAyH|62WDHvV5rwL=37R@=BqU8@ObER6$@(`uh5yevhW6=7sCmr(1>v1u;cO
zM@K|ODcRV}33jTBiH*IuI$WQHmGxuaC%=x~-lP8Ze_42Wd3oe)B-X84w@0}!Ffy|9
z(W4|#eBb*0?d|RM;N^af&d$uBq30(jCtEImqOGXNn3$MY@#TeJ!**^*c7C}YyV_p`
ze#iP3E>slLjcTzhes&_ZVPD0^q&K&=a_`)^bIxQf_tezX=49AJiMl#yaYkfhq?d<V
z$jy_J)eW<*XdF3u^x(aFatuqZPo6qe)b7UvW`=z6Rq^}lWRLgBHm_f=fBuBl(p|fx
z%=7QHw6(G2<m7;6K<-Th_07t~5CwpOShu2B_rq7Ow2T8?qoZe+n@m*@>t48UVdKNY
z?VvHy7k77?o0ytb9uMN=<Ky%2@^Z?})m^i8ZK@jItQj*t^c|l&ZJHR1W5e3DYfBEz
zaZzgAxY6)^M$FaN;JCOr34;U%6(P=D<?sE3IT<Z1EgwERJA1{dRZUZ;PCa9Kbz5%q
zy^lK<d9KJ=?B4H|lcQ5qTns8OU;ZpCD|0(P&-Uss+it7AByjHE0FG`%Gm^A6r;v~k
zsL5US_EzGzH#aX?$1Yp8Ea~zx-xDWKI+m1}{QCCxwB^cAcXt-E&zm=ogNqBa<fHPq
z;*+`Iv9Y}$A0L1G;^JZf7ROyT16*BMU6cgf`sI2-Yj32aq(GDT7Zy5CoIJT%+C1+{
zbVFQ7NXxp|-G{DT6>aB}eIz?|H)y#}^fn$&PEG?;Q`dw91<>jUHQ!ku`i>o49ljn^
zE4aA3E9>j?M{mmkwdK0Hx<HNpimIwZhYmHB`z-zN@uOp5p`l*vE|prpdu@CNZu_Rq
zGSBb3yxjkDhZiVTzsn$Eb;9)N>YEQ&dwFr0n3`VPobLb9g~i?7T|!FgQ{So9{rm0L
z#q4bA>EU_t`nC6ahevPT@Kje<Z@qVLQ(n-F{(gSDzh8nqRD?=iTxcxUnYwWO`u<O!
zifVp5Y`>I!^5#uRS?jVVvc1~c+S*H&E_HNwX9rappC3JVzz`c7d++0pRlApgrm*t!
z^F36Aw&dTRSFSVFVRFFDSLb@yuh(DZJG*UP?eA4@V<Z3dP$P2Zw8ieJ02S?^LeND?
zuwi>S`_>H`4t#ri`{BEH=PVWFZL7bzI65-Uv#aG|W@er-Yu2@B32mXyg3r%<{WyPC
z|N5etl$11K`t<gPhuas|{{FUN?ONBuLPH)No-0L)g>zS}(o#`Z2gME_A0KG`=)K1s
z-Pm0sr>E<?J2)^rJ2#iRxVV_%z~kfn8|(g7<=ouF>OD>8;3QRV3-!=_Q>KVmSXnJ{
z@0XLXtujeFH>Wf8^fb_D#=(OJH8eFHlaiElbagA;pFTU!eSZJ%ch*0C|6cv}P%*=a
zvu9hoySa^wj4mv6W=}~?efa2TcR_J+vjPWbJQvh);*~c0(6>tD?d|O#hluG!DAe|C
zWvKo7>gtb&?eZUv%h!MCSS6J4naPPm@yUE=*aCw}_Nh~+KD@Ox8&s&R3|<ayA|6c&
z2@U<&cPun7PcJDc2{dyD>W+NBU*EoLncAB-ZxkkaY^eI0bx&}ro}po&mExOIQ?)g;
zw482l%T0Z^C?PlZthJi?)~#DTyu2n^y8rz7Gvn^AtzZ6FSXv&uc5PaD$Wm<$jR|qy
z8#iwB@bYT%P;u&)vt9E1=<VCH%YBxv{(V<kTDp66`1(a#wuq#qr5RlhnXVUGar{Y>
z+QLn;_H{8;aY4bs7ngVnzpM_vTM63QRB=3n6Vz<z3kH|>=3Rluq0Ip^P)iWh%K)_+
zZ$N4cJ4lCh#bXmbaP0tU8A7U$pDP}l_}%?Fb>c)uh8I^>3Riu5qZvD4UEiEJbELk$
z@9*smb&|TO#KH9J+}!T9(c2g8+9jnl(PP((jZ2oWEL*lLVqcAA+WC2Bt+m8&Z_7RW
z=xBFfNC*qVrQ+a#0EX=B>@|^_*&ZM7e?BMZr&ZaTj=I0U9zHnOT-5*j=TA@^oH%nP
zq{!&%gc&nBUS3{){q~hZ*RF}}E_>TFcdqR6l$zG|_T-zJQayZpT4v6iS@Lk_vSn)T
zGw$@tT8lkDH`h5NMC8`?e12hJ;hC-1K!deEKR=&1Yt|{tl|?4Gw?uZAy`A*)@2_89
zvvcn4kxV|;)3|cw$}d0nR)0^rwI#FS?=RE-6?ZN^V+Hj`?Ym(s#6I<%Jax(`Cr2kK
zDM>(Dy8FwQ5{8C}69u`rxGa_j%l`cN6SVMiW8PgWPywJKv~bz7wsM_!@9yo@o;yK6
zSh#t)|NKK2E=-8C{;#U5%NrONcw<v4x13D{!$gmkSFf_}ZQP-)uYbH#SRK@Rx2gER
zz;NZ?EFl)g{r~^%K9h3y&Yc(uY3av5KR@5|xX^uaz*B8Ky<=BbhcBJ{EbrbP(3%?1
z+AK}Y&T^Y|kof!wiep%WL%IpzK?ym~*aWC^(B6yGgOCBmIJy+a&;1+A-bS&ov4Oh#
zpqk6>=M&+XuKmJlJ`QefZBcsX?(eU+|MU0n!`H95%gf7sW*WIZyVE0K$h36n(vFUf
z2XjJx&N9pG@||s#cxy{$QGfpZeX{ZOf4AP!<5&wChX3-V<jS>ci$H_99}e?Zx<7jK
z=jZ23t<Rr5d$#363}13`@|ii7!r<oX^7pdVWeNZO{M69Yd^jh>vZtqKL&e8OZn<@v
zGB2y?L~rxi71*(B;aP4_$zLyK8V2q6F<O_snc(;2<jIqb3LFNermZeY2j^H8D@^qG
z@bS3(=f0CyA0O{eRkK;TbSWbPsQyrNZgWtYSm1XeJ~dU9i;HW*{Q3QR_SlGsiaH9g
zh=_}S?mKq(_4W0F;^OMHys9cH3-;`hN!loJcX#=7+5Xu*Jv=W>MTLc%*R0XuXlj_I
z8-3{H$<A_{cdJ&f{`l#s_mrtq7jD@i^7QFb0hUI!la02VR}UO$C^q^x%RHY?T3T8}
zRCM8n4FZ;ymM6}gJNEYW_Dc81P2hn)6L70PACh;$Lr$f0{=5ENR*1br@ZVK-Ifm5R
zcXxN6ICEyozj;457d}2#=;0a?>fyn0tXCSmW~{Zf^=n`G>ubEv&(D88p=bYs1qwC4
zUM{z&`(wey%?%m|nEAM@tc-(?@7a{T^<{5wJ$!X_^%>R|;p^jEZ*R+;I;U%Y`1-hq
zm;LQq=g*h_^Y<^P`3k8s*U8ApfYzIqytu%qsHix@Ad$($#H8YQkmdTgy-u&Mt(|%N
zbyeT44VyMOg@lAG7F!U%tAsNwEX>Pe=`7G}edOk}gV(Nwz589U+;8rOCntsZPJ$x(
zJ2Rq+H>mwp5)m2cslMDpMQFyXS)clr8l5?N_TzE+dItfPE&2E5ggRM33lUwE8n<pW
zeP0pN+TQN1o_c3TA#?t{J&u#rd=t{s+Z!4fJXC}%tgJruojlvb$_>iB(cAMLo}F!e
z;o3E~_xJW1W?$0*brW7+=l}KV*PdjpyDu&-URv%Uz``gdCRR{Xbf}4yTVbL{LT2Vk
zYbEoE6DMBE)-p5{Tpz!`t*wo%>f0OeOpj2fORl=jMU{|kzrVltKJS~8qXU}ub`-d<
zEjQXjMX2WUS@SIGpHryOB9J+1WMuT<`SbQ8M_isMnNIXrBF24Tee7;Fh8Ne@&p-3H
z?MiRBy8k?zz#s3gUB2v`nYmI(cxB(0FC{E2EC&73l9DH5-z?|*^XJcotgBj}lIZpN
z{cSsUS~5JixY+&1mQ3M38OtWuZm~kYl{LF|?b=cKS<S6q?yPm!DGwhX76uVfQAGm-
zfyTy0uH)S<N;dWXVk9qycum)fE%^HCYL#^Cm7ia)$6w7VUM8sQmhkS*PK)|~Ha51l
zGany1e7Nx49ZMEgR!zgXS+MLq&0|4%5F~?#-0K$CPe@5QV%>IXmR0Ghl0(6F#jT#`
zZj9imt*!m?`nrEr-<!8@FK)>UzIQRCY2w6*XLi24yW4!0N#-GIvGTjS%csv1?sQo+
zZFkY;j-yF0UcNkd@StN=os5jkg2jsuTT7KoNl9(kv}sc1+Y2gJwjW6{WH@l?QczXi
zoH=t65)%(vO4fsWSm0*(FVN60WDM`dipMA1!QC&&&|Tu<KClvS=Nwepq7CI~m=!#5
zICA_rXkpL<4;2FwlPT7IvUTCzN0T~SltMy69K5}~f6Z_eVCisCx^m@;hT+mI17qXE
zEu6v|YJL_$N76x4-?L{+GbEgvqPYVyzXxh@U0WNS{Ort3&@$d9^JZHXKYOrzew|ZU
znc4jXG9lsNhtHqqKi)6j?xE5&ZJHRvgR`^E1y~qCi?$n?*%z!_S@)g$%g2w6+qRkU
z$=jW=?(&kbt=e+v{{BxgmPJqGy%z8K_U2}@X7I9vzrVhI`1rAL=T6H-ixyqjS)8sD
zy^W{(+na+I7rPrK9pShaICascO+w$kecMt0-wrgXaNhpE%(ZLRGA=FQT(xS|gjut?
zoZI;lUte3hVapa5Cnu&YTensof3_(7{JaetHy-@=_xIC%;h@<JQ&ZE9-rlEkz#V#X
zM2Ft+=g*%fPM>aWZDlPfEv-DRsHLZ=$q9;OzgfzgbQ*&;z}5o1+UKIaWaGN{{eAOn
ztDT&ko6AL}I!_L`={MhwS6y9wOU}(n<swr-Gccl{-qwBC#EaQ03*N<b&i}N)t)~<B
zq2vGHu@}X9QE*G@$@>L;i)Zxp@qxB<Y~Azv!+cj)S4IXl9tj49j-H;JEAQv*`uHm4
z+nbvfH9rhMOYagAKy`(ZmKN8#b?bH%JY)h*&wxfawZqpvkqv#R<};(=^mKh?OH0YC
zSFaj%gN9PrtE;O)(^%2l^Pb91oqgnpOG|6(!;g=TGu+E7c=+@wYjt(?xsyLCzq}A+
z<Cp9C_xJbX)B5{cT3cK1^aibvpJX4sB||W5eH`z`h@MxkvNAF=L33&h8!A2~=|pa7
zDRz2V_3w`*s9$$_y1w`Q!=|RDfw8f?58mDv7V2bi@0W804U)S(?K0C>Xc2Jw7m1h-
zJ92Y#`o@HVOm}vd^D`8DeB`=g=gx%-7BDok@g90~wA--cMZh`DpH|i1bQUdMJaPK;
z_5%kTK%>JN+S<-BF*2YfCStl#ANo$jR#sY;l$5;io@2jq)hef=BBM{AK0SEwz+wH=
z{}X4=?!Iv&;>pve2XEh&etT=Hv#&4jsne$~u8B0Rl70BL?{HL9l!@aT{|q6mpV})x
z<7S{4v@7o5X3=3#29<3$5&Js(*uuWc2Cu*)ql>|;Pl3l3L1S=`3KZI8235d1!NI|2
zW}AaHuso4%-Q(=#<@Mmro1QgmKovqud;8<b{&ojXPuCX|7jKudtx`}^bJP9(>GE>_
z#Qc1IUS8gsZ#UC#Y|E8C)-T_G>sAzKkW@`gZAaZ-tK0`JDIMUv-a7kjhl|onrCZ<c
z&b2PTur>R-TmO9HbUw438z1=9f^uKJd}&enNkz`CrsLMFsFGJ#IQQ+_2O48~pK-^<
z-Tm>Ko0~zo%gfsv)KArm-IZ`+g5ss!HLI;}?P(Bj;`sUe!t(qU@J#d`=5uqc+4J-B
zK?9xK;(ABw-z%r)<nRa!3%|L!xjorwU);VL&hYSX9$71q=xsR%A0BR>ID0lX!-Z?t
zj{W%fcw^<~v~!w2J-xgRO;B{cuqM)2LPFxf_WO0r3?d>T2|qqO?C9)#C_Q0w?(J<0
zeP^42*0X~K1}05ndhqsV=G|SU-`?LpZ>cDMzwWp0nX_j><2axeUuI?|L&K&`Mxebe
z(c5w!&Y3X(_V#?xss}bUwhNapJC~H0G;Ci#GjOrn!&6hW=Lml){`Mvkv}L9A^|cq*
z)=EEm{Frf%t$A5l8EE0#^Oiq<J|36n;NWn$zApCSrd01E$Br>oROdZAGqd^0lazCu
zKNo<9&5nX*SwLfG@S=LouN9z)JotzUXbKM^2}%{vAvDP7ENFi3_ovhPg&!U`Ub%AR
zL*JsJJ9qCcT`yXx7r&3Eyu4ghEl3u$!mGdk`1bpC-OK&wJ4HuJPuGukD=ajerW4t8
z<3_|*(EgIQx3(TWJKG#I-3A&_X;MhIzpoawqM@d?R#0Ak{kQJ(^X+Q8Y^%Q|oSdW@
zu_=Y~+q=8nbLPn0+qh$vWw9ElOC7m6&GY~7^Y+GRXCBA~XWqGUr{MXyxopQdn;7cr
z>$m>d{qXDS>o>M$gNCo$&ds$}HZTxaxNzZ(-R1gXdNC`mb)RQEaP_L_>+9>?BO)Y{
zl9NHzFlgg}*!=&~MYY2~i+3Wn<w*Yd`}gDe`oG+uHAHi*%QHS&g4R3z?}Yc9_#$?d
zXv)aS3d+mte`l_6cXwA&RW0;bCdI_eJaNK=hT!FX4^K{3Hxiyd%OsO2K0bbqZS}Nd
zr@BXvA75M_Z+~ZJF}t#R-x_mG9eaCu>#{cwW=vTB_xE>Y1qFt@yu2Gbi_`ahR-Wil
z@Z&>bALmaFE-t5l0D-i#vsyoVD46;A(w@rVA3uIPxUw=>M)=d@88bN8+1c;xD&@X+
z@7~uqWB>Vfp|`WU)D~_6ttYar`f}i4GyBDDxzT$nK058XylLY`!$pf1Z!CQsc1{zT
zM!?lOs2L85Z*ZmVZuiQZ7tDe*%RwWpkR)-!9XyVY+yZdl*l+iX!_?ID#l5}Opg9;}
zbw5yTyz2YnJ|$&k(E6`uAMf0WadCCkG@O`q@#4jUhg!KO&Y9Em=~EGC*xA%nv|C)i
z4Kxm25wkV#uGH^uZ=DMZ4d>a_cB%W%Td-q?g#EuC%2C_%&RWZb|Nr-We_~={<H^bD
z$w#|HBQ_?nf>!?X$yy~mJk+}9apC67%W64yc5FN-U%GJZT3&N=^Cioc866J^4Nd&<
z;o*(__4aE1^VS?GSp^!P0qtG5;#A8tWy+KXM>>T$`1sshTv*;)Xf;Et07*m@;E<K2
z<<=|3${^6`^0g1NoVT*F@>JhaBfq&;tqlzfpjGR$X3hHA7abL)WNjV&^I(WWLV|+b
zuNTU9_Ew97_OHxrU|?Wo<C$>prkgA)D=VmDarEQk<AymmHdGyd`{s>E9pe|!8ffuj
zeX`wKv#&1-UmpkQ!0^l2Jebh4|G)tUQ2F@%{e94!<LlU9W_CW8m>8MmB{iUScmDpr
zVrOTWI!8rG^~qQUy)QMc_>k~&?v^XOr83~6;CLc<1_lwWp91%1N`R|)NCYFN0Sojr
z(A6tt%H`?lxug2K-oBsDq<f@Hx%TbbXJoJJ*7HDivUKJ9$EBdLtTmCws>>ALOHK4>
zG0VNRAa-}zg$oxR$hPl(@E~DL++L}9^X7H*^||Hc=@k_h3(Cs!>g(%+#6cyaY;a~t
zX(?#l<DOy2rTqPW*<@v9c_a)N_W%D^z4!6@xV=r&r;CGTPeF^)tjpg$nJ{Vpy4c;1
zPEJ<elf0rwSlut-!-Inw8X6NS|NZ*<dc&42M_yc93|a?LQCWHL=uuWtQPDY*R!v*A
zO6$q<=gRu}>+kV{)*=0y_iKI`Wc!>`NMBzcU)<iRqc-!VPGxm=c2-pj($$aK<M904
z+?mH&9UW3rmxB5eM~=9F76_iX9<aOY?S$F0Pb<#M^6>WujnsYK0UAx==AJsk!_=nk
zkHqI^XOrdfudR{v^75K8!=qG1MFljqd*SNUslT84{{Hq>^q%E|+G(?9buCz+z+l4p
z^*m^{t(9ARQRwQhqWa}CX3u{7^73+-Ngv(8vmD^)x(|=8_Fm8w8hC+CFStbx&efoW
zHXFc0W}tQgisGb;7ccHnUNME4o$tYcM&?V$SBI}Zc5iR>>t1a=J-47BAsZW;DU$w6
zK@Fbj@9$jG($u=Tx?bhJQxNLB@{RAKs;a6**_#=MiWm2Br)|%_&!?}i|L4<beWUZU
zXUsTo^e8K6f@E9n?I(G^zS>p&{bib!l~r*(z*9_2Y)8#cqnOxOP;Ibcg$8H~5ko*o
z2#deJzlxe#(%D(2T))r%&inc4sf2x<&7He<A3k|<#G0?Xoln-u)04BOw>Nd(_s^f5
z9UU3>{rwhw<K|689UUG}p%D-uAf_92L{m3D|K6U1udc2Zl#=S2GiOfK`{2?S<szVR
z{QCv?1Ue&ViEbk^`-iXB<F8v!n?AjL!UTbes;VN7Wl}miIt9PK<v#o9Jza01_jElk
zpCwjL?xsH8|MbZd2Y-Km&&&}2&(F?^`rX-C{$38WcIb%9s)I+4u+;zg$o{z^C`ic1
z*LUg+k5ZE@lXqLi2b*wCUAt_V+r!t37Ayd5iwI0oy6Q-sc+}I=+oQZ<%B4#|FYl(f
zDhYCNa|ecosv5hg2s!%u^G{auJ#=ZQx8;&2?+-LGfB6309W*SEnW?#*d$ZW)z3-Kj
zl?`it6o8iB`TO&qoo&9}-0j}7uvZG&+T6zJ=ThY4Z7Me0`R8+G^3I)>b-&-5zf}5i
z;)KVRtgBq0vL`A^%E`&eAoG&SJ;R;1_Sf6@^!7e{^oU7YTRS2m!ol6$J*~$><<Q3D
z;})tR>z+JGsrmQwxzYKf$B!%9+R6qm_dELP>S{)Y!|nX;d3kz%^K4db<Gzr7W=7-P
z-Q~#_7C8QRwR-)PZ^pXd(QTz?vY_^!VvE3~4O6wlA6;DR4q9&O<m{{{)F~h-*}2qv
zI%pNXsi|q!Z&w8dpBV;>papKAeYchqJz8eXk^&Vopv|hFsXMhN#}6K4T<$k_QuUjw
ztHW<>&zGMwcka|VUZp%zCLD^2ibd}y6uiG@+tShkYH`X;`uOzi+g@4gG6iev-S;+v
z=HK7n+Y8$IQ)eKWke}awdAa{-+pxgEMo=S1sMF=-$`I$fDj}8DY}b9A{yv%PZ=v#d
zy?ehL2S5Mx>NU%jv4OfA^X+P<%<(b}I1XP6V-C*S@a0usXQMB#g5>QdkfuGd;>#9O
zr%vtY?mn!)|4&m>6VtuI9W(7}t=`?;4cbAxF!%Ph8{2Yce<{3s{_gH_&<c(>H#R!w
zn(qa*XsW)vXjJ!~r(kIb+HqY}f92x!_<G*t<YdrxiqzE9ice2G_s&1w4;o@@-MG;(
zC^&fL@!;U#*LQdRs9nBpwxG$hnKLEz;`i}5J3E64?7zRhI=i{C^~qW<`__G)Q9(_O
zO;uIZz|hb!F;Ow^&W^?#H*Qqfzf#iI=a;oEn^LK#q{O5&kt6w7&&0~Q3kw`ioH!AX
zW;3<u(GgBiL?$LCMr=r6T;?}d>w7z>v0p#g0kW8`QvJ@p+USD9LO~a$iD&v<lmvr<
zgDa0eUbSqQ8>nNiAk^8iE%!E;(nOC98#V}h`TCW0qK8V4to5{Vm%MecyVWu>Gdbti
z{aOi{k8@NJ;+$=sFZS)-UG17bACEWn_4Q4dGUbT1nmK6A1867<v>=azgG1m*(nipk
z2R-ukaThLL6g+eGZ0nvqHunstu3NFfW5c#>VxT$O#1|J9Hbv-&?b)-3MO<9mQAdn>
z+qP|oPEXgbJpKf<60B+3v}p!8Hw+&B`1rWVLq%v?-d!yjivouY8#fAW*}AngdVAi-
zzLQ7q?k;C#W@ZNMemOMDG@E5(gboWE8<+Pq9YG%-9~Nb0WkqA-$>lzJ=jPdJcN|Sp
zR8Vl(QS=nFG^Zu`cpvA*ix&?aXk-Sha!|CgnpN(T2kII?TK}N#BWMXGBwgKDaUZ@6
z1JUw>R36}2b?`U=qzRaL<JsBSpb8S?ucVC;9bH{QERF)7K7Vc%(~aU-xNzYdVWH5)
zYuD=L+}_q(&NKDOmds$#-q~`VsV2$CcpRObop0<YTpSP>s95{&>+9=>mif+R@%8mh
zytXD%Mp$dQhl)^6ZZ508|9Q8+6_u4A`_`B|efreMJ~K1Zshv-jB{nwp;q&?R>&o}+
z*)yj+Wf2o-3lIw{>q#5)f(H(c-rn97Utdi<^SS!l8^JGMzJO{p2?+@fP_tXM8MJmH
zzmvsLphCY1vP`eVB+k*1@zUkXfzi?3esir>zU8~}3DgaKa&ofK^YkYtCVu$z>5**j
z>TYrUq+44uL1WLA`<&bPZtSf#zjNn~g=#SG&Ye3!3Ds}DUGJt%Mhp$}=E=43O1Evz
zzP{?M>9<!`wb#V%4y*FzY-;F}wN83+V&V+@dOPr{%qMD~oh{3J4?|XyAB`3O?MGHp
zQDJ%a?%f>WPoICk-=BP}N3x@{b7JMalP5WEZ_jtXzAn~M^>P0FeYG=etIbZGI;FtT
zRPz0M+Sys4Q6~xOGM(owf55BqAZsR2N|(hFU!{*i#tqP#4WQLlhKTii;AJ_t@9nKN
z%)F!mT9W?m-MbkUg-S}w%1igBgI1tFdXyBiqoA=ksBT@{-mVQB3|_uIe&>!%Gdq9V
z;>F6(Q~rE;d71s)yLX@#`+E(o<F{@}f%X70F*8@X2U@14rhfSH<;d3T>kAeyW)2Px
zW;ife-9I2OkkQ@U9kh=A>@3sAb3!bSBpF6+&H6h1-`<xmU;a-}x~eGF{rax#zC6zU
zJ-d%}yC{W(hij`!2gb_D$!X~6xy8iD97!@PDlSe;Ok_+?Pj_)~InfilB}1@J*1C<I
zU#`IG^z`}j<+HM~K$-tuAb1R32sQ@aB4Db(!IXDzkEZd%llSh)C2gEhZZcJogQ=*v
z7?eV;t&MgD4Ya8&I+T^2J#oeijbdL*3k!$f;K}7Cpb7D(+S=OA6%`h8b~PHd=JV#w
zGcYiCAlo~kT&z^)=!*Lj_IH5?!=Ehfb3XCk7QDs<JmdzAlL`N;!DF%D!MRV7(b0>G
zpP#d+{bj<%%?;}H&t!d(eQk|nL4m<MyV_HhD?f#Xh8{eBo?qR6UW)?9h3nVZKWzKn
z;i3eZ!D8o^3psuL!qwH`hDk>_=GasU{r&azv8?;jKVL5UgEn=ni`&a(Y;1h5FvKr6
zSJ!WjMPu>vbI{SZR}Y>(Wd-e(d1aZjQ3A9XWrksLg?peSx0ud^-4|jeUR@pj-#IfR
z-pQ%yPH)h!FE0;U&Mf--?RI`aak2CIxV@n2ky~6(!Pr<Bbn4mi<;&09kh85?;5}V0
zYd6F1latjyeESAUD9iljf?Tn)-v8yRS4AG~9EvS_erGURftu(Xidru|JUq;x@Hb%J
zyF%v|&NZMR^A$#~EI^|_mG=YogH)aP-C@NCS_C(B+cvYN=4Q||&ra?O&Q4CC!x;9|
z{hd`D^fY=;g<;sbn9iG<!AAjrb`LNpsH?NTzP|qWv0mwo85jR2zdyG)dDnmYzWwi1
zlpJ+5H@eJn*)mOO>5+XZUOEd`2~OgS`W>Vjo1?gBnpSAi{acHS1Q$+IGSSRhzbI>^
z?Z(q?O*&4Ke*T>}KXKMh<H=vL?Swy9&AD9c^X|!<^5<thrM!Dyte*Vp%E~5n)4lKR
z?tc8~>FFIMFNI!RTf4gW;VczT(3vy~IFJ5(v-$jn{QGvGb0y|ll{RhOy!qVmw0C!Q
zHmRu;A7p*;CI0D?CkyKT{{w9uypm=5=FJ-hhRDds2`ZemzrGy2wKZEeYw@zu*VhzH
zOhi6@{0Q1n`{Uzd!<-uiYk$AFxtZP0&MsneTJO<)|3tW0RXm%b)=s<o#&MF$lP6DR
zR2V5KEedBAUmz?fC@45{VfufKX;Y`NN=r*GE;}++g>&c5ooX}u_Wb(#+Ie9Bs0Y1a
z+cvjmHeQ~8eJY+me!t)EYcMyWonM}f;q1CQ=kuhKG<R2=pJORJNhPyPe4b_TvV-?0
zs&ERc`4}85dBh`W#4<@G@#UqZ0U9C_MkyU&$<x#I%@39&$y%53Fg$qqa%Ji53F+VK
zr+!oksVskYhmj#<b(rt#ZHnjL{ntu<{Nnhri6FEOOhVYlF80<YOGvxRVIXs}zQi1v
zN(7p7Xl2k+F3_Z~&m4=u=S*J=laD2Qes&hL`t61z>x#g|Y*E|udQG#hy|B5rKHgr&
zqJZJ!$B%0Bd~CwQ!<)m^r>Srj78a__I#IKMnYa4O3&C&i?yjzkFDx#0zP&9sa9d8~
z#^#w4;tRxMgMx%)WMmR@b9Jjk7J~LsT@8<a__*Kx*z@`IpiLwU2YRK=4a(oefcC@%
zFY`G#MKhSiKdb7OSeUR${eGh-uh;K4J80tK;<8>&&p};DNlD4bIedK_E5nZ6yR+|_
zJ-PWezO=5cZh{Ku>+9>=r%s*vY@1?WV4&IzKb=_h)|b^e^Zqh#U0Ne~V)C<+)p2{R
zM7UT%1-Fo@*Mh3AuiR=6g4Wv$`)csT2Y>oeH7WeY^Rvd&KHS()_$B%AiO0V;+U%1*
z4Ps?`$;AhMx?!<vV?Gavk4>f!U1n7QXv2hU^*7Ks)`_!cuSPZ0y}M%xTF=1D#&e*F
zmD{C1t7zM{Z8OaC<=Xh=*M0tRX{oni+8K%NJytd+jlb<ZGHIR1pGA?I(-MDud3oa0
zsYBh~MxZS?GBQ1#!s=Xe&TZMjus1_USU7NPl<AQpM>5R3H-?yIU2*6Z)7_AF*J|$Z
z=B6gl7+d!po+tOOWSLHyJb7m!XeZ@Nmh9$^j*gBKJUe&q&aO2~^i+Q%k^J~rZ&iNu
zrWrFN7#ezed#~l5`u^o*FvI!%e`?BZU%I=i)cbv|x0tLf?}MM&uWsftff~XOekOl@
zW5%c*wx&VFQzLLu%eCC3#}bDi$&&0O3Tn}V79mu9eYG%pd)@>U&g^Sz4uZ}F0PO(J
zy1I&klT*-knSh_4pGCoghBr)KnA!OboIH8*Nbtm+o3FG!Jq9Z6LCe$1@7IbeyZ0TL
zoxhKhVMoPBB{BWDo|BW+ofifq{Q2>*N!_&f#fyxJii!@o#SxFbs(ik?uU1+&dfOD+
zdz(_d|LuMKUsYAL@G%o8?McQl&IN~>Pw4tMSw==i(0<CpZM?4i$z`A^8GC#CDVo7<
zUo=9_fL4P%JvCL>w(aK5f`?35*VpM*@o1&Zi*;>YVQ|CZ*T%vX8aK>8-LMD|$&u00
z`PQ45BcsJ-)@NhJC(0__&eh$UEFs<A)zqup-|PHe+tbq%)Di&=2`vGwd3f{o?Z<=c
z@(I`0L>82kh}bNY0Ch93tPBR#dp(lIZkrFD0o8)_|7vt1H?agS^V!(J`U|u-j$zNg
zU$3LK^H!GCD=`$5m4QmK4avv*n2uk`GTl}3vdK98T*Q}UT7`v$9o^l|Sy`*jxnBGC
z?;q1LBmF&0zl!%T?fM8xaa*%Oj~qJ|_2hHfw>LK@sBp&Dd}LMeJoM(~W?pc)`02F1
zuYs(f;KkML+!s1Qp>`(Z@-p9#&*#@WO;WkCDwNyN(UF6Lqha>!*)J}hX>wZFFn6x(
zuF}_ROM^Pk&9y#!>sHj4h_r=~o6|rm>i_)x8@Mt^_2T0hvewqtKYsmkS{bq^`}(?B
z+P5RDTAdop?^UvUEfuQ$^~G_jR;WvVidodwtk!+Czd^%`1qB5HwtbNgJy(4C_2p$V
zNHlo4-yWj_`yn|!`SFS5`zJu;V+i@;*gnG^P|z#)qmYZGrH>ncBB{>?O8Q+?g{-NY
zsukMgv{1mdFTm2$614STVbDqi&q>dWwbj+xv$jfkEfrcFzJ6PWT#$yy1QpK6$jA*F
zH(tDBrebb>o#k?8=pq+R4H2#-%a<>9=@bIxql3rYCaI*Pr_auC`W(2-NAk=}WA?-C
z{MRdMPEJw<HF+;xzU*r=v*P;tc<@;*e}8{xzEInm?>R~5k!fnjQhk-WKo1WN(0py+
zVz<OIGYks~3mGT;ubE|EZzrY`(QtCIy0VE$$eRUe2QHcGUHEF5$8o>7qobp%4;En&
zF)=cr<-2u%t3b`uNh+Y&;NaqF+P~jEuKKO%MP;tdm7mjAglK{Gf84xzb49>HrmC;6
zSeFKMhOLe2l=EMab#;}Zq9Wt9Yu8>}SjarZOBK`w4_fNgDR)-q%e%YMpo3E$AMX!b
z7i0P3=TFC#A)s?b7P$*&-PutH+Ew2xZJv;t%BruguQAmNbQa3DZ{HRj7hYBL^puC6
zpIfJp>V=iT>KaqMO5Wd--L`GpB6s0F^@XQ4Z{2$I@^b%&4<3LfPFUF3Ks(kJ9XFDO
z*Mo1QE8*-MnaVfPe{WcP!iIirEPR55dM3}D$(f#>-Xm{6FMP+9$4^d9zOl1deO>&1
zK8AwALdWTPu@_bZDj%FY^W3Yes}((ketmt-?m5Y1JMYW;`}cD$6VAT0#B+iQXYg{r
zR;Ps*?wF<A+LEa@<J=z5T9>@Myojw?Q_npHot*Ub^>smM>Fh@*k9_|4@n9n}yFuxz
zkS%$4r9`ztE>!N1+L|@9!szqoFE4{ZEu4At=56YqycDz$I3Pg4EawJ;=cI(>WM+nn
zPfs|nWSN2wG^zX5IlHb=THNOLmnA7DCqat=B_%BxX!WY41{&!9@S(uP&F#^(wb2@Z
zi&(76-f%1p>imAMn!l{9Y>~T&lC7=mY_r@Zuce3P*;Y@OKAk;1J)MP(P07GO;Onca
z!nTV}uDqHBa+KCouG!}KZc$NEUeon@K_+-D6_T|s+tLwx`s>LPCk~vq|IahktMz`}
zZ%~(VMcCR|&nh23e5hFElE^1x!7$aU)pxd;qN*zEwr$&@!t*y8i<FcwFeos1x;Ta$
z(Jp-Q^r@nn8k^QsF3>#ZV)uSf6a4%AdU>y<LT_(x-~K{d?So3lT{)YIhF)oNr=>v;
zLF+)H)*gGkem~#Rpw0sa9ImX54*$}T*4(>TT6(#HSzjGEC9rM;H3426J7&oD+f5E4
zkt6f>h6R!YsHp|k0h8zn-&vIEGt-Dw*{w&wwky)2`r8`UIzGXfhn}9EesN{6`j6kg
zlb@WJxFT+^6~lvTYojB!WC$)=v}i;1_q;1>B7;9HSr)!3L=!Y<6Ta%-^fPCCcI@1l
z_~ypOAAdfdckNH!)+cMdta!1AzrX*%$us%$Vgf8WJ3DvO{@&)AyUp3f<;(sftS?+Z
z;OK?-`~R=|dCAt)RCKBLbkOFt4P|emE-vPrI%iJL*VorUCsVlh%eAU_t_WX0@0pk0
z`F(FTs(?-`=##bHvhKjgTiNRumcPFTs^C69JL}r75#!~>rKGI9Flc4LmluHy4s)$a
zP0mY;i;Eu=?gGu}$L=n3TpE;kdt2^_GiO|WetHVtbil^8$al6GD9u<~OW)p>+w8UU
z(7M>&ptWG2)x`eu?Lan6R`Ye~*AVe{x~i+F2x^{ycAI~Ed|c5}NXjImVZj0gP`}#G
z&u@{tiFA(4U1&6bitHE1j$P~r#ociWP>!C{1g=}3Y%DARH<T~-_9n}KifTVca4dn_
zaD`u_4U<^(Vs<p#uls#=#cH$tuSB?5ZES27glJt{?l0f{N9I?2#I6#}XXoelcZ=(H
z$sK(IIwLdt`nsd%=32Y<f4UU9DrDt>-(F>9W|uBsW)#^Ylt0rb6|^J$$Pt&zd|7OB
z=FBmu`%}>)W$N`sBklObi-HRmF1(}B+H<Uz``>O!<1_^o6_%YlcP?^QR8rEKwu1rO
zu2>=A?dNxFf}-<=($`@glaAD@RD*UoE(lsFASl>a|L-R|S1XhMd^=IwX#u;|9eDWa
z71z?B&h`6#d3~u!d-&_?>simw-rSt7=qVJnEvNJE@9*7mzAM(O(E%;x78Dc&jo%a%
z6@k`1WM5y`Dd(#Z8}3$AUhW<cAmHTW<kGJ$<L`9!?Ww8Sv$T6bi_y7SnLt}@0s;is
zcqA06Y&IVRHS07xdKb%sa)rCOSzjGEI@&hoe@T8Uas(6?%HZg5w>Rs{%aJ(@jt;IQ
zXs6|3Z*TC0e}8|2S}7rGA_PGLC#zSlKG$2S^OS4G!Gi}u{kunxADikf4$%Ug30d^?
zRHxkf8xIbdR!;kJ<IBs-%RQu{U0huDv}B%%&dAWH`};K<)IkXg3tM#DP#biB;8g8!
z0cmONDv`|}u7<}iOg}#ll*C^Io{=)w`;o8na&uQl$BWblOeLW1#G)iMYinuH@eLtb
zqM%hRbLaN13SGU(f4<!e>+*FkKAt(Y)O-4Zpp^@PR)Ut2M?^+O{_(Wc_ww*K@ZsU%
z%AgrN+~Rr(hgvvmYT`gk??FTQ7Z<s9^z}V^{7D~l4#J6v%0K5^Y*b%(%DVEC3h2Ba
z&@f>??+uG%&|ukjvA1`zJg7Kvmy>>O`K|XOIMm>Y7}C$H?CVXo0S9;`ILv=-Ec~P?
z!gY3jsjf)q>Z@Wuf5=!Cv1m=@3JeSc?Qc0bN%i7VZ*h&OUO#^QI&|!q+n0{CUheBp
zK5kTu-Ija1ZDsIsr?p|A`G<nCvTHj9_Igj(V_GH*I&E3PszgI8d|i*CbK8l$DVG*F
zGBaMDInQa~fnBAq1tcUm7(h!^R)w$cd+{P;OYZHk4<*l<rN#f4|5>A?r1UF)jVr$c
zs1$N(d;0XLqM4Z(w0u6?&Yzf{-)~p@%VA~6qT1izTyLd*4=w)wF4o1x#bIgC!}a_B
zHASs;TkO{R;cof;h5qyH79BU{1}$>)TI!UNqVn$E-qk;oW;Wd3o}WF>zW)DT^D9}V
zHnz44L$qA`)vi1|+-|C_ykyCe1J|yJ{rmS%?Eem%;#XHR&t|`Rc6K(nDl2`ZQl<0o
z%iI<(hoB&#YwP3rr+T#}AMayixL5Z(_h4}6!DEJe;5J?!s5k+Y_`ASW!IR|s68)ey
zIVjOXqTwz$mOgDP>^XkSum@BIfx6%JW_{b_>;D9P;YeFq`T1GKy*-wP4jmE@7GC_*
z=l-Tt?o-oryZP;YFf=wce)#rH%vMWqFH_Z*7Yl!WJ}zIsrqpMWO7~qJ7KW(pdAtli
zp3kq}kbi$4({bIO8yP?S|1WP}m$UKz|Ds>t-gYl^ZU=?oogEDw9UVUKHrtJhi`}=D
zE!?(ko7-}~xu6nlZ*}>NTerI80(WfLVglMes5O-fbgENcp5C21cLZc)c$NlrMs3aN
zlndOE9)1H<_D<CfXJE*^wdLTImBFBLe2R9s--nh*OO`ED($eAr>F1YoiHnoVy0)fs
z!UO@0sa~M^>r02z9NTJ8Y=cIazP`S$=qa>k@7{$WS{FB```@^IyIU@B#f}{oXR}`&
zYUO5V5YvqU<(v=SzqdCxH$UJ!`oMF=FVN98(8k5Rz15&~OX1<+K65Mt9UUE4#O~hq
zLeRGh6c3<wI9eRp9N!0vJaE(QFQ~%~s>f}P!($aD@#)w1_xe>Vo0kP>Jb3(=SzcZq
zba)ozpc99R3JcJ2h9RrNc+K<giP)+IZk#k{P7i3&%fV*$6Q@sW7u>mjKmI^SlB>IW
zx7@*;wGkT+E&9LD*Y$8OcSlEuhYGYgWfc7G-MbxSZ>1Xk=yxyonVIx4UTlBH;WplY
zl_8+gc+=+1pqe)E!~{jq8W?a*t3GF)cFvXc@$&KYe@&T~nFIG$m0nclnml!C>)Pn;
zpf=3)`1+%h)%_p5c+oLY+1+Vn$f3)ZgTHh*#q6(>6%-T%Mc~cN=?lYFU)+%B3|hay
z$jG=NXld6A!PcseUheh(eyU%|GJSPrWpn1`WsWOD4jnz}`laL02bGXYPz&JO+uI9+
zR&FSM?gyIFU%&U86lfvhf&~g&GA=rO>2Lz~nO+<R4LO0zdRW1=TmjsPg#`K&aHfHD
zrbLc_vxmGiJnPIkw7dGd9%#q)<}}|ada+SoEYg;zoSgLH=4SPr+}w#%r?%eRUH<so
zT<b;0m9)&}*;F<iY-V>}8kDJPQ@>5%i==l<!@I|im8)1bn`T^4xTqXpc%+w`>(<WV
z<rly2t@!xJdrnJ7$BV1#E3am4eWBO^0xK5mDt)b_p~2DE*jP|nDr(zzGf+bWbbi|R
zcXtIvL|EkI<s+ht`*j&UeEW7SCJ}ThGb1BofY#I%@%#6^xOm2CrcvsIsZ(2nmU=C8
z@0SbEnhNUCtXZ?hrC)7|(?SLY&><cM1_EA7FD+X4WU>G8K3UUnt5u*TtyciAw3&$Q
ztb+e`oS`d2KB-*!Z=P^~0koHeU*4`|?OI(#zc>2Nb5Utf?Fs5(e(MF1p!N%>!<qL+
z`Y^U0%C3#zu_vVdtH`-)YoiVG?pVa^tC3_75Ef?6&(B}7WXS^Oc0LYH&V#?-@7J&J
z+W77LeNg%5JKOBxzrVjXY~Fl%k9z65JCR>1)DrXa^S>nRQ}>_u;N|7zV#TR9-Fl@Y
zYwx$Tu&Ai1MV(3hyr}T;vBY<GcFwS=G>Y1i!6+{;zb0xcS6^Qr2RHZOz1810WL;h5
zWIJ#Dq8&RdKuMDUv~y9)G>c<i$C*y2g$K;<*EFw--Oa>s>C&YOt3tIwt4uO(ZCQEl
z{>td>>ona}jF$#zD0m9-=(bmv$;T<q>*!eV0^U+Ob^7#S(3wL^y+m)^xX~f!-Z8)K
z7w7x^|Lsmq(NwMy+5Gsy0|tA0dyT1HpehQK!n~*JfpS^DoNd6W5Y3B^XY{6rU)yj*
z`=><EzM9G}Z*B^EEfu<V@7|rzAFMW<q4TzGHH8#kprMuzpHF$@$e8unfjf&xeaAV6
zlJ7r33VTSRKau=cL{3^AmO0$P1GC2~KrIbW5BS;H*^85p_i^y@y5{8Q?Ag1QkzwDy
zeH%7yI&^JqG^>AB)pEbNO^`}2@9r+vR;NZjSu0Sj>E16VRzCFyzx|&L7uGKYZBbYC
zO^%D&nicxu__G6z%=(#9pP#;Z)%ES|?Z?00??1k``g_32Al0+Kd!yF6-QJc9Is>4U
zTf9pyv?F$R*~87}?X(M?g7$Ac-u-^x<`=7%q^GBYPIIvUEmpOuXxOvIX6@riDv3Wo
zJ#AWMyf(eNBmPUy#tkxhN@}1pX37`VAD?u;yrZMzA2+nj(`o|^53P+dJ?nRO$=i#I
z-6hQPWI*eY&F|L)f3Z;e{^X=^x81|n`$5M5^vPH<@$>V8>X$DTX^%fXJ`URLUQ<&O
zu(K%j;^P@HWo2ew({wbedXkP`@^|v}@NfVR?*zU9mqHr~yP9g1`+E-`)8sPalU}~z
zhI!k@!W$N@;D&1AV-Z&A_TJzKa62?-&Y}d+@Xm(9o~uhdg{No+vsHh8r@KKxgaI^0
z^7Qod$H#i5LF0itc37+k(Q<Kdd2pzeJ7D!y&^q^~rlt$a{pCYeg?N7Ha5*|{?OI(i
zy_k-J&Fsp?#=@zmrW^#_4)FRlHv_0s2iid2(!z3Z@~k)?A0E)CnpWtlgbNECR|GHT
zV|eiA=jVv6S)xKhLISd~z2*07!#^xpR{r=HFK7$^bUxbNy|$qF*>y3NpmD^ktx|k^
zd>WyvrW~#D6HQ(C_rgNw_(Lks`lZDM1O+E*a9v~;08L#4UM$epteiP>CTJ^P-rZfQ
zRU(RC=3W4;pVZdYesgp4@fKlG`S0)Vw@;rg?l;Fmu}Wm~rw0d_K{p^-l)szvBCzE`
zxs!iTkWfxe&W8N^c9(fWd{orc51&2D%g!$+V%sI~%P-2$)6=n6$`mw}DC`$fvjH?Z
z0t#`^ST8KZMZleCM2L4aL81uMT`=<tgz7m4T1x)s@88t^@O3ego}Qj+b3E3}GR+1}
z2K&#qbM^4x03C~B|L+I$Vz=H$k3RpOK67U0Jlkp|8=Dx=AS>uBK~qyv22ggMq8~3e
zT`%^M%=r^19MaO3t@zl&#mnnD*Q&JO-5pC%ul(P?e;>YoKR!h>7$kCKU99xNg$oxQ
z7fE_^W21+s=fQ)`?1f)ng|4`o1!^R{eED*QVKUpBw{JI=zmL0^JnPJbh0ff6=d122
ze9ZRh>T1xIBhW?((D4b!dZj=9{eD0B>Z;HmKcCMRl$F)3@=;P!s&b9&mIF1<Iy$=C
zCaGLho?$xghf05cZ(U7I$>Yb1W=E}c^Yim-oZG4?Ki_=U(`U~f-P)Rc;?yZ2+pb7Z
z=ivHO8#}X4KW?0OoV-|C+TGqRzXVj$+?P0pL*_AtO!Ug2r4uGjRIIkq)8kve_uDK^
zb)oDlD*^+wrhfSHMZ~u2rdH@G5zrAIJB!mVE}qe9UH(qw<@Z>H0ULJMyQps_M~)
zhlgj~j@?yqaQpo_ZgFw(Cr_Uy-rG|t_WPD~=_?UX=Gl~bTFfGBTTUcsP0VC9Um=5;
z6&p8hl&~yPiQ1CU`1|{N<`e&Qwr}1H+W7+7Spb?{-~Z=R_XE$9bN1{gJO~<{cXxLO
z1^n6B=Ewj1{Jb&gDA$o=$GYS$FPWwj8T8`5q+!w#?-}5F{WxrxLu7w~dX;6xr8#*u
zF)K8F>{+-d;jzHq_aFa8$jM7<aoOds*l@$#MW6kC|I?2f7cP46xs9v4*ZE7)2e1O8
zw&~NwL8qo&T<k7xF>S(xhN;@&hpt}_Kai5t(%PE&@6TED`wAKw9DaU&OzKAdYooRv
znyBn<Q1Kz*;$n{Qy;Wb8_TGQ??AgAS%rm!7OjH(>l<a)-CTEIHq!8$KhV9$UtG>Qs
zWvKZ3_4?Mh=4nTc9b@B{vzcJ~@54jq8#ivuC{X%5app`;b8~ZshP``jRXh(JZs#{W
z9=#=_QGfrRpeq%JQq$9uUte1b8Hmqn++XfBsU?5kPqzytj|v_)HQD|9k$m>~RKx#v
zik?E?`AbnjFeNA`>deQ-cVl<CKB!-Faq$dQX=!QD%oBJ{f=krdCezQ{PA^2H=3YP|
zxUCith!koD;Bs`uiXU}4{r$Y6tn<x7B*2AeNJx$SwByIydO#<Ffc77NPQ6_pw^zYa
zsO<f{UeMz9pP!xvtiC$KD7EW_VJm2{aY2E>tu2|LQTIdV&+~)FZ;iOS#dMqc`}x&;
zXSF0AZd+LO_0=MGp|qo2qEXxzu4b8v=|;8u_)!5m&^l~w6hi~3ll}MCSJ337Tc3<(
zR?NaZd-gnd`gG~ex36Axc~94Sc%)Mpv=8y`udjidQal@lyB<G%+RDl;wjg?YUdELb
z6R&LyUhbE8u!$Aa>oS=eaqir?9ksvB7#6s63atoRE7d1w+XWgq1aEu+^_OG<XZ-#B
z9kk2p`@6f7-`aV{Hk|9_F42zMqyk#eFCo!kRr;z!uDzq<#Z=XmKi3z5yS!=n2O1bb
z{pVR`xvM_^*qD5LL(WYj(0Ph#^Ln~wAMck}HZl^LYgOv>^wd<)ywRsmpFkV<LskYI
zP1?_~<WS|GABKkxAHKLXJ3M4%kn0zVw5KmGFSn@qVE~HBc_}~jB_$<)e7l{0aesaN
zj$OOD<lHsP`2Ma3m8tnFG+^z+pEu0E>^}k;t^wr<NSowI^5YBtg+SvBpoyj63p<OS
ze|Wike$xAUd!x8-+}fJmezaRW`VG_4+uQS<mj)@?*vKsRpWg<VmH{1h0NV4rVbdld
z+eHT7zI{7!^5ntE>i!H2*REY-z1Obld8yj<dHB`q@%7*%B|uAAmwHXz(x<AXwkULU
zn1o4&z_DIw^$aH?_waQwj-Q{M1)Yw0ZEbY6nI33j4m9A)&dx4lS0iDXeNDt><x5_9
zI~h=KrBB|Tk70&Mrcm1XdA*?PaP;;0LCfWvnwoSzy${RZ`&BF`I2d&D^4{5%kxA;;
zSA}wWEfrE!RAl&MZp6XEb4BOa|39D4Z_K-ErJ|<RC3ATR=(HTrFt>{f=xUq~A3ih$
zt#p}hSNq_}6O}3((1HLiSWaT*YGneQhn|qI;N0Vh6DNX3Ec5c#b*dZdFZY{!2-HiR
zGNr|_neE`+yRwmyksba0?W<R7drj3+t#UCkzIX2)C>Q+x_O?{+{_b+{!4bCA-)2-8
zeY|w}a^c%srZ!byIKF-R23ke(^3qb*e$|k)G&Rs1Jm{8@8ygZA9XGU|IB{ad`@P?F
z%FOe$q|EvXZ&-v#fGb&6NbXJCnBQ~!*up~zppiE42%R)|5)m|?$Oh_9_&MgxX##DN
z6Bies+kGV{IJofXDbXiSpDuLkm0}e;AGJwbJooO7LS|9zFqilD_6mxKsO)}tX7!uH
z{PtINz1luUzW&cemdi7yUyrYsonQA$)9(MD;<?A4pPAX*$}RrrSg*9&yfa_=WUa%N
z-2eRL%O83FAe%e;YNanP_jfNTG0D5Phf|^cV$O8ESOFQCoQ>Qr>tlDffvR@fsxJ;F
zC#ixueW0^iE-&-luxV4%`t|x^`f)iEXCI!b70Lzb3fukt5`1y-4B5Px1@}Qa9D`PF
zD17X;WZ5!M;sVuXpFcada*4Y1ySuoAyn$D||8`rKzXKf|_(kH7P3<p{zrVk`r=+M{
z$ud>(1g)-n@a`So)~MdFwNapvb_x5sJud=%A3Zrax%J;%w_d5eEuLrY@2mX{ItlIO
zV^2@dAAi5!_qCW<vAgW;p&m(N&|vtJr%yBM@={Y<#dM<-EG#5stx5ze7FsOzn(9<j
zvnNnpK4MWr1H%;EXfgSk4~$JsO%I+vRjpE42&x)a1~1Qw)3>y=1m$oW8ylTZryng!
zdc2`9?#MCF+=Dr|^H-N6lbbW=|G7)Q*%BWAk(NGg0UiSU1RjCfva#@=wHcrE^ZPd}
zjwL>RaSW8}HCH4aZu{|a`FxYvOZM#82nv}COFV@S3eQ?z_4U=m*X#Em17%cZc0SPd
ze9&&BX*!Wi<>lpHUSH>TZsTcOym;}8Kwr>tg^Sz`qBS)&EB^f0_~s+108>>x+9KR}
zc}?VIrM>^7Ua9%|`T0fcD$!(kaPzCs&!4P2cI`TJ^=fGG?Q`e&R)?>D_FLf7`i6NE
zCn{F)Y&OZeV*%RMb>iGPx091p1!ZJ<qPOQI-rZFSiuL{b?Vp{UtzPAm2ul8-4X_Un
zwcgm8EgqsJ3c7ayG?Dr7(NPJDf(0)GJ3BhMOrf0)qhQd1yVur6n{E$Z69HOv%k<sb
z+uJ!OXN_xpp;hUt5EoZhP^0C;w{M^sZ<FI*Q?**-_Ev#T7ZWQE@_&4+m;39|UKP(1
zCr?&(3ePmJ?Y}xzJ3JvjKmSnXky+;Xa{GQf;*N-nTo}8%Y(@Bbxl>a#o4<T1nPXYZ
z_WS#L_vh#48s^`#=>ZM+?{EU`Ujf~SaABddYkyK1pPWqxsIYN$P5k=mD(IG;gan1A
zrlx@Pakdv9&%ASSvHQe1bJpzq``{pRMP(&uO6%Uedra!W{oo;AGqb*rH_UI{uxJC%
zLv8_0Zrm5)lXjPuK3)Mz8K7bIPd6-XfycYJ+ItuG!t^EP$mEulm7O?q=E@zjEgP9_
zzyJ7{44Mvj`0(M4z18Mx)~o?toN?pEjf7iUGQsyFmA#GH^Z(!PMeeGNHnz5cVq$FZ
z@$nTE6&bRi)*fi$c$x2Pu36`{ELyyHYo2}WFA>o4`(}22gMtSRpm}|Uf`^A#K{cL6
z{63py{`2*cLN*_6eg4VF$S5H_oxRmbu}b72Xs;J&9zJ?|9(a7E@C=u^o<ZN%t)`%P
zd+YLd4_;ke{p0g_`@-+<VlO5O3JQu=Px^IpS`fIFO$pog?^iZx(;>rznKL=1rKKaH
zv)?PKdJ2K&89{3S?$>^oy;t+uS8y@c^H;CB*2V5l`uOPRj`H_%TA{02Zrq4C+nJb{
zm^j0(cGoq|l=YiTv#&|)@ed0V3tJP>2s-|1l1lfj!pgI=OlKX>xWBI!)N#`aUl;SB
zE;BO|v^o*gsmr~+ZDy6vWb68WHa0dkp!~Hae!twgbLUv!6+b@43%Um2$H&J%e!t%z
zxVtQuadKDbzdw~<UR~wpl{PzaVWIQGXU~>>K4r(p$H%nHnBUUU5|q>r9X|Z=wElk3
z-h{8Oue*b8T$7OKSQWauOYWkI2p22p(CeL#+SZ*{_da^eP!5y|+~q*iF`z=>@C}Qf
zpj40#Nd?N_<qM!0u*94>HQ+L%_3*Ka;1XgYcu>?m`t&qiP(2K~jqT~Fsm=4}%Y#bV
zEqQmN-oO9)=H_J=;aTEaqk3n|kZ5Ud2MrB?4gr%g%USVqe|osh{_5{~OiWA#kB{*l
zIeL_H-YpY3yPA&5&(9K%_sN2`$TEQT$$(BXx2-ZcHBDE$!pZR597|?>ef=d%mo7{_
zJ+0z#uQ>z5bp7~a3!U2o_SICrxx4$il6ZHYthLz2jT<d0J}7ui)mmDrV{0qBHhOzo
ze?NcP*;%R?PM0MOlUP(d4}mVK3(zn~I>OPsU)fU#RBbf9Jaaz2{%<R21Ks_7wH1GU
z7=mVsDyplMRaIG?+xd<zpI_HymV2v1F1UkN+6>gl&)@&oY|h-diK(eeOJgRfxVX7-
z%{o_8@R%t#GBWbUu2Ss~Em4pmH*VZmQ2qTK2M<q6f4_g@b5PG)ly7~5A1Gy}ECcQN
z<`h<AIAQ<u<?r|Vuh048a!W`^=)#6X=bMjJy{0%+Rqf(b7g}Ba|KFzLn>KF-wOT-j
zMu7I4-P)Ghec?jDW!`i)BV*&Oejlp7ya;TppHN?R>CT44!vaD=Nv{N3LA`rW>GSsX
z_Qg)ETvqQt|9ZXtG3eOlv$IS$7CrSkGuQh1k>IZH*P`<o8UFozF25o~>*nvsQ=LV-
zBBG-YU%xKCZ{I!-fB)mp&dvs%eBL8#E%x|$zx(d8w-@%;*Z=ta`!Hy_Xom^|tbC~i
zPli0+02*hUVE1PBp~S}-ppGbLJVm0t7qnFAOX6clkpvy;vdEFiO-xMu@cHxM1C7j#
zPxjY=ra{ES)P7q}+w$^gH>fy2al%7IO>I%u)m5O=>wkTHy}Z(IFKEdKsIB<x>udFd
zpv$|9pYwq#gC9RCKwWm-=xr<vpvxK-F8rif91B|uun=@^GM|h^f}ym@-W7F!e}Q%o
zr=6SA`Qk+eXj;tS-|vqdg36!+zbz~+Ip+oSY|Xx&bf|@sRct=9!%U;p4-ebrldi3a
z6x+z~_xb$#Hm8LL{`~yBFhJwO=kxZ`dtU8as^?%|^+jXPo;?9ey+nWf{+*qBCuC!i
ztBSfh=wKtUoeZ_Nx8=ULzFxklsHouEo5(wRDmNdf<*{8KmwIQ1!|lz!qRL828%ke?
zfm$J;^{9KROz%~{x1B3(A}A;rc(H)d3Y3%r4MC@#Rk3V-_T)*+>FN5X<?M@|aNN0j
z*Vkg=&y(lQ9ov+8+MxPd4rse2X!pE}ON;B@!=H^0xAPzW@bEArXn!pSH@EZmcXwI+
zRqugz#;y+6zbRZbudtxNVSU`*55M2<pPga!Sx87I>0*3_=(U@h(+l6+Fa*_PSzD#H
zW?w(HxB5HiGBePQ6hT43jH|1rzA*Gu0M9*w3mDM4wPWD;ZvT>aU*Z^Oe19^msPTKa
zq0mDfyy_IJ7__S9SmNW1>^nOQLFcut4qvZiXebDBdqIK0z1r`w7Z=Z*3)<@R_xpYK
z{dIpoyxaX=szz>W)>SV1e?Jy?E)&kav!l?%!{flWx3@u4nro9UUc3l8W%5|R{Q9i{
zS0;t5jRKvIEMnVs)6?JI-OH=%&BrB6RBWogoM;j5oIGK|g70Rw=81<`Ko`<lRDIDf
zGBN_40k-xrXpzW`@3TOKA823lhD7F9*VpS;$!tE<%gwbaXek$HY<gE|_L<q{{Clgu
zI{p0g)V1H$#pR3FBiIBo=r9!zZ|~;Kn>Rm82Tk~HN<BSc?%ZC`B;UMw^O)2{R{PJl
z1C0uT&Rlx+itEA8zUB6RzX&TSDS=MEX%y}PovO6ddphVmTu?EvXU`s;PbqSiA3uIv
z<ZdAS@#9AcgM@~_?_WQBIB=|2I{uT(vy+q79SQ=SEap^EVG*Jw`smT4fQ?D6poLEH
z`|C2UtPo^)@Z;lS35x;+(7ue#>F2rT{djtFXYul9r@x*#<Kr=@WyK1OIaZ~s4%Di8
z9-3j8>|?vA0JcQp6S%c;Eb+0#v165epxORo@KtYS;Lb<e#=?2v1s3pSa-cScjG3R~
zwQJW_gsv9Ly1J_M-{0S$!p3*DnW*iwo1Q*CE-x=F?cKM3_3G8njNgWC&%UnLBWJto
zz@uV@7k73VgO(((iP;%+Amy2=r6p)Qu%Nj3a^=;0Z%|kM=jZ2(D?dMDoo8)b_QoM1
zLISke$k+YZs~a1WXIK`4PIj9xb7tg&9g`<dKC1U%f9Y#6&}n8zpId=OO5WYy&o3=4
zJ;%D7@8H3M9DID&s_Q)`O_(twW6{fwj*d9p7)bdY!UI~M{qf^RP%2?~@bGYZ#<ew)
z&>{E@8w}pu+RFX*)>dKb6$+Ep{f|97+zvYEv7(~FVUkLZv^n3(l`A{CyPLOfHwQHr
zFDB2r^7weaY4}7B503`WVAJ~e{%dQayXDTV0Ucmuo_FWMuA=kz>;L!eEPk$JZ7t2n
z$oS&o;`RfazRw>XZr2E3Hz)ABZuB-CIlG!4lhhYIQq$4ldHC?5Md2eBuW34+d3Sdu
z{`>P2blTgRHEXuKyS<|@x#ru=bWj6%L8h<s(jdpBL79JZetvpt^**~(U5`0O#u>bN
zh9~)cM)Kne^+%6^JBz=M8JK~V$Q-@_YDIpD-&hD)vtiiN8!P~x4>vR8`>P*uN_2Pk
zqPoAoK-+nCmA_y2`Ny}nw?TJMDCp^(J2JU*`oxKir>1J3mRldRl*`D-$j4%0<;{Jy
z)}W&^K0iOt%#f6n^x*B=-YHW=Ky742Ma50$SBKwR<l6n<>C@J{ySolvy(*f&=OY`#
z1JG81vbR!k^?yrsqPBQ^n39x|nyP4PD?3#y^wJ+4O-)YFowa3UW>w$baPsr>Hwt$p
z=dP{)d2X(CIoH<66RVd5E_T~d{Jigl;Ta)wJ&hCh@5gU`DJ>`{xHkqK+o0<poZI=X
z-ih0uC;RTs&gR4I{EydezvuM(+grohUnSkP8;@VRCbs|YH|e?`57|NElk3*4^YHU)
z+r8Twbj22rjKzinp2h1oftoz$=2(IbxZA$n9CVV-rd02X$upPw+x=vD`SN8)Z!hbF
z{jYaVpDqqMFsiz`8e~{tVBm|Jo0mWEjNf<XPR!!}iE)!uo;-cJ_etlO+Y6oB3qC#Z
zw5j;8;6SpXr;wWeJe>@qLQusyO*cB}=BCsS-@ltzOp17XtT+DU@y_sdhJ2u&ejhlC
zg8B=shrzMi+nX!_ieQKYD1wnBppgq2QMh%(qV@2xiPLAz>gwp=ICAu;qN%B9*4C)k
zJ5)S>{QLc$)mQ!8*6iyO=FQWqwz0L9y}mx){GrRU#d&vkf##eyBpyykPF`FJx+bxs
zqr>6uu2NQC^=s$mT3=l3&To=;M*`GQ*phkK<hWMY8V+}NcTgumY$wCrqeoen`_Di2
z=xDc~tZZ+$xPDfhUCE08(2kzeQ&R+OmP$0U^B-&F7BBeoqmbd}d;PPsOb>6(zRth^
zx(IXq{(q~sa`rC;<y6q6#Qyeww;b4b=8O+$A8hWeErJF!E4amU4phJ2+rG?qcGQ#V
zF1tHB7A*Ms`g*rqV@Jn{B#&41|4(y)YG1*bpykD&CDZb?Uj!Kz1TXgkH6Fjcz0Iyr
zAAWab@Ny+f%g6^)QuM(4NDkf3-=BNsq|GE1MID_pER$!>&$_w_eB!~5!p96x>Q9Oa
z2{mm_KY!@#SzgeXUsaVApS+z;#ii-~3j-D;AMdO9eAb-z-uFvOy*oNP9rN<majF^X
ze}8`;wBrp_DX+Mi<uPfAW#-eH^Hn`Joj9&$XD64Jm$&Hnf~2-y=T^{amEUfV@qkM3
zI&xl7G4SX>ZjQ`j(2!u^iVZg`LL$JtEgK7a4j;Ri|NY(F51&7S_N{^zqi~68iR|cC
z@f53^n&0Zw_~AnV3k%B&n}0u_&j%fAwWIv~yiRpteJw4nz181AeP>Wh`|R%vN4v#0
z=G-)zV^=FRapJ@epFa!RtbAEnRdwjxIX=)WIYB`|pcM)?ZbVd6S2Kg>*hIC%BHlb>
zU2^;N`u%;5&1{M)Dl813@lnu?0-!wh>iYWrK3VHUNk_YG?5*DZz|;5riHXV?*VoC`
z)YJ$_NOT-H;BaQXy?pBFX-DT+7K83a24&c{+wY6nt~yy+RRy|Q$~^zxk?i$*+0xUW
zGtI8>oYZ3f?}zh+mPbE+`~Y>Tet&-tpB1exOiNP(P3E-mN+(@j=DWz<bY|%4u!HyS
zgRBs><q{OUsNEk9*?OYIc51qQe@hDsgF{%D7@v$q!-EG2XA85lvs2R2x}?tMJbCiu
z!I_!Hpv6~{)qEd3c%V?Fl6WP{^xv=7`hUJ&k7s+Iy;A)v!%y`L3oEOvJkYs{xwp5q
z?%r+9ups^XycrgSi&lK}c?VkFv3~!*tShy>dzp@|es)@a|B;uMmoE%jd0|Ut@Rb#T
z%)86qx6Pg{{p{@Qc4hZI1uLtlFEgAzEO~n9<f&6mRaI76p{rD?L>7XFgFtIvdTODC
zxQ!X8b#}wN^&qHTPnG~LY)u5MiJ5aK@$rU2uIAp)GN2LxS{MAP{rB_vilC)jpp6Gt
z*2l+xu{hM)+M0PUUe)u^i;Ii5+8v%>`QZWMrAwCtBqTCk37&OYAGdeH#EFd`A0JP?
zu_1BRck!)JYj+;nt_r#}d2{;tN4N9$vo82uyB)NE+sn)7Yed@nGc%1j`1##IEm^&D
z{(gRKpr+KfZMnBEY)bV8ohHNp>X!J-w~M_{l4P2HPv-Xad{A50^!?7o?)_{GJ9h0#
z`u**#*v=m^C+=%3&APg3Mby?+F9Of_Wn^f8hPB__-JLzpJpKH<qrKAR2I=QyKnGKN
zdUCR9xyf2Z=eC3^D*|8K+NwRpOLbS-TP|s7Y4Cu<-bp)P%Q8Wy<$})oxwSPr`TDw8
zP>}#?x}OCdopA8vNzVr@kJd(PWSXqzd+E(FS@?2`1BVYYZ%#YwbbnthtAD0cWo6|e
zcMUVG&{a!*ZqnD)<#q3uJGv%vv&r$|qM`|tCo5;!On&tFn1yxuJJ9F===O)Rzk8h)
zI)M6h6(5s8D-=K{OuM+WfGP||W;T&u<tm<szTdC^FSN|if4TpBw~!E#HEY*CeE+`R
zs`S-^7Z(>xm}ZIi&9mWTSP`{V%gNapbUoR@%UuUSZT8PH_N#ji@4I;Hd2itji}T=R
zBrm{=sGeKag-L=2lFmy%-T-RqNr2bcCd-(eEB>>_2sHLI-yAg9SpM{s=$V<u?cL}9
z&tJS)`Cip)U4{c&v#&pR@+9Pear7jWDSEL|@ArJ>bL){%O!C<b>Suvg;T-RmzrM$O
z_l_M43LhWaux;C&%WvPldGjUDL_}V`pG#B=G&xrK`I+yE5G~Nw<U2cyC#Z1Fn>TOK
zaiK*qJBw!Za)SEK_5bTYJJXBzq@0{|;=~C7(|HB5RwW0Xo}OO#=m;lh@k?c8CFt&=
z<;&GYxLRL)Y_Y8Rvf_o{88LG`jf~gV)&{H$0bOgjq4IMYXneM=t}Z}p>a4SR9UUDn
z>JJzFck==D>O*=!J@gkhHY$U5yEFXUU1tA#l7YFoIH>x*vU2hX!Pcnld9t9Eww!I%
zf#b))8#QEBM{HD@WuD*n;X^^U<;wP+@9%cMPdeDdsu8_S=iA%c?R)mve0g!vx%kig
z`hOR1O`WNstLyvuU-U8`Ne0j;!Ly3veX_dGvQ(<Sz0v$~)m7(ZmI~<T4bUioy8k=|
z2GDGXZuB-#*|A~!cK7e^?t%{QKHScq{NlpGf`S5v^Yd(3{d23p&H50LH_}>MX6K5*
zyf*Mgwt&D5plwK?nE#RtYU~^K^g6p9JO-LFdhz|3bUvtWv*@@1s9DOv!NI^#QCXRI
zX^CgX{e62MtUNP)>sHfQrrB+2XJ>WF9nAsdR8YU>SdV1zgNUFYA<*8_b91e^XPmKt
zt{en4T}xgFT*)#8b?HGR?e**8Q?){cY!?ZD>hwvf-WL`)GJ_5g*Vg8~ySx0l%>J66
zn~ugmjhdtaYC-f$n~T|Ui3;D@;Sjw&@9u@Q(dH>>X-S`-oefwS60y5X7t~4vt=ofa
z&f2o0^{0!Ai#}{~rzo>&_O&BNyTw1AxBtH&W@k}BY3Ws&(`U{c0kuFMK2*$eI0y<=
z&{;dr=huTe!dv`aF*Y3Ql}^66$hB#ia<N(VHJzAUCE)!|IXO8W-fq7Ss@)y_>79`_
z%enAI#+!xV>Z(xCJ$em)Vt2~Q%6|NQzdn22x8mR5a=R@pzu(%Ly~y1l8#FI+byeub
z<l}rH>tZCE+4<e(+tq?bgpV9Mwy5OgC5DFI-`|6}JfH(0b>1CGZRkzr0Bs4Y1w|3K
zTPA(n0KDc-iwnGK?75{GXo1CH@IWzWDiE}{>@R37%0y*%B?E(i*Ppu@_EvxIk~_F&
zOU6Z};N^a<;H#H6Kb+9s&VFjDwt9utXHc`(B>$d_?`$*B5$h_Rpc9n8y}#eT)O)&;
zxw$xa(S*s$H*a!sZg1lSjU#W(7Qd2Z3OW?}<>lqckB)Tycrw{v=iPhm|DeDE9UdFI
zyNs0qRLS#7nJ_Sbc5P^BalPO7d)*1a*4-s9g&sY6G-1{(uB}nA4|XgyTM)JOSR1eO
zhUDXXuytdgBgVeGx_Ww%H2Z^Nth=UYg>rc<74ljt1Zpd#q^N{wi9S0ww|i&t^F?KE
zZ-G{MIXE!fp3u>;q61cl&j4+zIybre&D*!8@oLelyr=6WJ~=UQ({b&vH62r?hzR?s
zT<hM=Cha^)CFkz0ud2Su_dsi)o!j{y9&Bdcuz7QHZ*T9j2+&p6zu%g7@7#1`vbw)P
z(G!n7pU+u?#;+Rw2y2!8eZ0H7o7-=W#lo)@k)RPq(2*bq4<2M_xVN`D`P-YDph@bu
zIJsx%=kv?U%O4D$WC`lbx%Eo5?kauF#GvLsuSYj}Tf&bI4`)rD#(3c1K}OJK(H==-
zmtHLy(A+I()ZgNbG^Bxd0^G6#Exyl4ek=hhuzQnb%=jd`K@=!4K$JmSe($&6uXA4N
zH8o(lpKQsC3ykN^o!hW!)1_VgDxMtN+`=XcU%t7&U*6$g@w211+iZ6KU;XaI#l;?e
ze%J2QeR#mQXU`r1NY&OjdFFIb^>Uz*8C1O->zC(Os4p~R*phXX%X_-s)tq@roS-AY
zKnol}x0Br7rVE<T2aSk`YK0uQx;osj@R7?!<yoz_wq`&6^z<}%h<sm7<&{;T-o>DS
z-p%Rfk6FLpqg>!r2t85`bUEMiL&XaJi%$uOFIc{O`C{+sdKM)w1afk7L5J}u{D1%E
z;lqa!dnyde-rQ(3N<GCfFGMCUX2JaCX6812`M!sT+aEtWJG-N!qrq$Gp(UP^4JtpS
zJbCh@LvCV6$BGE}cn&CyzrMEi^3KD{gI4N%Sh`YGGkl%QyZig~t3kJ$tccmUiBnzZ
z^_Q2I-QNEA_2XkQXg%bgcN-W=-X-Lvr>6&o=R|H!<Gr>fa`Deg5-09QTG-lxZkBhs
zx+;|M$@~u@a&mp3!N&^=92XrEeYW|$owJV*&!)|rLF*P;+S(r7*;x!)Q`zuG*how-
zMx(-O<D<uq1!ZN|evQ1kvpBum>LUY#kg)JpKb|$9jYJ1do?LmLcJ7=x6DCef+;sB{
zFEo)XFSud;6Wj!pICktLXt4jco4r||8Mp}uTD5){)C8E^k4Pz?HsBLTGP=LWwcDir
z-oD!1=YB_=V)|0{_Lk!$m6X)fgU61!6-W0)t!-2BJaP7{>BA|{T=NW9EL|PH-wsr#
zO_?HssCM1KYxUBKvahXaoIP8*?&ni+(7eJIi!{(3;J&lXbU%FFlzMtm`TKiJYDS=G
z$Ac#)tABjE{r;lT*Vk4AENpr)@eJr5>4G0063@&uW><FWX;`~fmqEeWS{igW!SwjL
zPS6<ty*-sp>ZZ1NF##1XU%ssP@j+3}u7+c4RPM+BX^t)~U*h3|s~;X5WCk5Ac;5bh
z%ig`VSyxstGIVry9$e--dqc^~pf~sSN~fNlCTg=%0yIRsHA~d)-;c*k$3g4RrfP>T
z0xiZ@6MlSaYj#z?ecd04)6?~jo8PZtK2TI<Fda1K1DcZp9VHeN1UlpfTmY!5vc}hb
z6$NDolbjm?UuNjvJ=QA?8pzzSd$+iSS=pP2wXyf)?P@?X5fM*3Z9&sMe}8>7-L4(7
zqT$Akh$Tyx9z1o5>)W?)Ov{Dee?D&yI^6Nor%zkz)&*!7RDH>)`Tcf#lbW&Z)+pXq
zr-eKJzB#|k@6E<1leKSxHX4I6|M7jG?ISXv`eDv<Q2hYf#||no`oRr;3vi<V(f|at
z^p1fhmO#}>;SGyle|P8V+`PB9nvucG%q(hqCl}~c;ujYev%k8ww!2GI8`N8iI(~k>
zegE0n=Fw-S?zjK<BN=q<4`_&Yv0E=_$4GsB{oL8%k(0n%Eo^LUx8_NIdh>7ElM4%-
zLCZsr^+<x2>~1c6?8YN)#xuY6+std{y{GAP8YUlmaB8Y{M_1RT6Ra=p>^NYdANTdo
znVH4`tFMC2Qc0g*n|4t;UO-UrZ#dWCaz)Ud9;J&-&CQ_pALvwplP6Dtma>8_YF)BK
zMJH+t$MJr7_kw~AFAQ5}8YYA0SuQScWcHbD#yd$xQAvrZnT^-!a2s#nzM9IGmX;2=
z;2m$?<g~Q5f);noul**Ob$wm$-s<mBU&PP;|MQt&$}Fb?a)IN+hlkrwoIJ_M0NU8Z
z&M$Z6mg@h|vR79$x8&Zww&M4;oSQ=R|NnmXp0}bxGk)Kmqw_Bqm%obv4J_MMe>*Z!
z*?q#aX>D7!n8;WbvDDSo%`nfOceGY;#>9!B<#XBpm>b;t<ud=i`S<s?hrhqL%}Pj|
zfkxKBLwSG9L93JXKoJRA0}JZt9|O(w{mj2%ks}ieUMau>$=to53F6Q9Hx$0Oe`{Or
z>Pp|0SF=oVZV33!HoN*K=AHc_ao<@coXh>@PO`20^(E71p3Th`;m)m~lYw^@v)|sH
z@4hx_tALOYleoC}mfYK7pnc6Zcvpj(g3r#*etdGWderu(|EkOG2w7TK95{H;@ry*7
zrm8Ay>FaA#ZU0@1&Q}DlAeh+?IyL&ujg6q|>7>l_c*@Jm=l+je^!xjJ(2PpP<z>8g
z?%V-wqf1FmO@y9}-6v<;)o=e#0^DfS5)=&FsEV}6-@{&AUH!+;pNcv<KF>dbM&6{&
z^N!55F88sS`Ey6@Z!^%L`D>%MD=8~8GbE&^w}ZB%f{w9W6}noj!l@9{r^vZ!1iF5!
z{QW)G-DPhDq@=PghEJ|IcKy2e^YinMUtH|2=qUs`8C6<(_0Fb4Pfkt-E&KDHuE#m=
z%hSypHy%7SRU5Q4>+E^Z*`9N)%NK>N4y$;(^}30D{N5^4&~+zo-sA`_=KB8Vs>h_s
zlQ*WG7VF+Cb+Q|jut5FG)6;aV`oF)p$PBtFyp>zr$7ZGkSL>n!oNQTJqn>-RpRb!Y
zdv^A!k7w9G9d+ow08lj#S{4ABmXkOJ+6DufhBF5h_kABh6T*dCz`Z+(cF=xy&{|T+
z+5xRKpaqM1u~NqA=Z@UinC#l0EGELm%EZikaYdjqgF{-H+A^P+O^VKK4|>h-X%y6Z
zPSW|*brg9;6zB}u8HULdrcO<Lbn=XITAG?!{ym<lUad1`NIZG+Bx7CAy|vNibI&gg
zzxeL%Zbk+>J3Gj}V{fC}TPAOAY-DcdlWm$hb?S@4GhTD8N*}y?*Z21J_SZJ=UcUxi
zqyoBKLT#SUo>x~_C*Rpo2)Y&fMc|n>ucepve7CFpCDPZ|_u}qu^QNXI&;<O&$Dje;
zpf&I<Xm@v)^KZ?%I>|O}cUkUPQOke*dw=tFeTunbS7$4t*`&l|7Qn*&^JZ`C#RkqB
z)v+67dV3cyI3|>Aeo!JQN5XVkM^`tSs+o(cV6aH_8h6)?Dq=1oO%V<i_v~v_Z@$sf
zSx~Ki^R;ntT1xrcozHk0*KaugS7NnR=qd#p8yQPWOVEmgqT=GfokgiLX3y@Pr*`J_
zbbZhyZA(kbgM-cNA3l9L1iF~|<x9<~SqFc-Tt43*`<f19VRPu)pQ}PwKYDj}H`BD2
z@i#Z6f)<H<nz3`IC1~jV+pTtf`9(f6jegBa3jm$O;qUMN<k_=Dm7kyOsQbI?)?E)H
zV`I>Yw}aka-(OoB&B4WW>DQk1>-E3Ay}kUnYtq?yw$Wc&gc^H;4b1wi%>4e{Fkf}U
zVprnhjN``wj~>&M`0Zw%BU73)=g-E%kd1{UhmT$C>s{OhR-Sjm;?)g{pUIC`Bt3r7
z*1LFJ-QQoWReM!DEy~~Bv5rcfp`)V%nvaTzi0GJ?6mTzQ&$sgXwcqC+yDoK^^#y1X
zMBT5K%lGt`zq`{Jy*+Q`UOio1UO_>@717(*$z7Ke%g)aJ@$)C>lqXG1P0*z)Q@m6`
zOGQskR$m;pHp;DV;~RT@74u`<r%OY(=f#2&QLnW5u@4UqKYa9P(MP8*d3SelMyOwV
zadEL>;vp8$zzOL3leJM>85qLX#~r=2)EjgO>CtX+?l{e3D*_jT1^`%CSUx;x`hWiZ
zeR<HH>HT$oAH09x&u{-{!vFgMf`WUM_dth(SU}5A%ii7s9f;d|{{5}3-0$AKtBOmN
z0N*)onw@lMiRTQ1L?$0!--nMLDOF7i(2v`5;M7#@k6*9HKL$nmw{OR;t&RSfCdXS;
zT%4GjyY}nPDN{ri|5UA6?A8m~4nEg!&;7mC=AdO3?V)Yyr>1Cb*t|J-r}WADrSI-Y
zMsLp(-QuUCuD-nH{+i-<cPuTetX>sPjHr3MDes2Gt&N3OK=HLN@aVCNywdL0W_?;_
zeg|)ugW@Y09A90%i>1x_%5r2vbLKQ{Ec|r*Sm1H6T2X0tP^5qR_HBZS=NF!4^O6?<
zpm~bqV?B;5gO<9S7ku~Z?CeGA5^F$Z_q#hg8RFtA<Rv9LPn_`RUB5PTwb(Sh*j48%
z*-l@)DERnT@8KPVk3nlgTH4!J%N8W)q(r)vm2JDW-ZU~Y(!ku@{M7opd#k^n`~CUH
z$H$@bCaZ96(s2f#%JiaoR)M3VBWR;3=oH>Jx3+pewG<W>1})@oY;0`0)_Js<`%3P;
zJ(72Km!JP$YFC^CTMKYM*u}-=OW6nL1g(&Qf&xSG@jln(ese*U$y8yx>AKNvH*Q4e
z#P5sw;AOaG?b?Y`r?Pr`dtVIZar^q}>c<Zcok8`XcKEt8)yDpH<?<W1Z@+%sruov2
z!ekeB_w1U>cR<&jrJfc8ZHYTz^!M}k@5e7JbOx>E=#jM!d;J=8Xse8EmB{Ps>#sky
zI(%^V#Ek3P^W$}5cZsZ9w+__g@tUs3%W&e%nIoT`o(5gmvo(IfrTDyidpciTUEMuz
zVR??sTW}`Zm3SYT$z-LMSM+Qw#1@Zp9)U)0|8@2*?gPiHmRTPti#~e%*wtS{5H!Fo
zYhAX$Z>|++WpYexENGF-w_S02t2iT;*I!)~Dr|c&0aWKNcJFV~IlUrgrxC~lThDWQ
zP72sn@^VkT_l4Kp>w<%V67uu;%gf8p%(K0n!M~e}hsPx+M`vBk&P5-8w(&|Ya&G5~
z*pe}E-t<m!&=%|_$LI|Sj7-eTg%1uef);}wc)k9*ot@o^n4Oy*ls@|KfT@(3o$t!8
z7|^_kj0JeWqwMXi4`07teGEF3t6tu7T59AM4sfeZ>&6_*;tdH0nNrfzSKH*}<@IG=
zUMBfgUzZ`_$%%<ON?(J9<Q1yA91RQ&PyXJ#ZaJ&;W&Q>K_0-hZKzkQXOjI^ZH~=2O
z`uyx{K}pGxKR-Wz{CwX2@r8xX8Mn8seX;WW9G%mkK|auCh>gkaKYspPn0I#<=n9L=
z%l!*KK5_;1XAKPvL8rTH%)f89*rxZ^v14qCii)5^>a()6WMpLvKRj>*&v$^%4rt{T
zfA(8#SN-br^Ya#FUtb4W<9X)HnNM{;%irI#-Bb0ID=sb$v<%N*{$Km&=jW3THnD;(
z8rZaHlgoL*rryP}((a%f`9?Z4N9OK^!Y#><MS3@y^Ziz<2W4H55WHj#Hp!7O^Q*gI
z0V%{GX~x<0>-Y6%Z%N!fnjNx1+B|PT($TIx7h>2?o;(SP<fP=}&->J*S4){@IV=oF
zxVNWLYCh=Ff+=3A>tc5=d!Fi|dU>I9dr4L7?{9DKe-t_lYU*s*U;t{|^YQUj_RqJe
z6pGzl=IZ6;b+7d&Xv6Tn+TSK}dz@WdTv#7NcWJ1eSnS>px_`^M{2fC@?V;!G@^vdd
zIh!Pxyt!f6BVouiRXZG125*^n<!}A}@AXXAUf#d6vzYtqFVMY2pU>OZyJz#<U*<bo
zKt!bF%a<>E<ZVuG>M=?^mGJb`)SvTa{L26Q=qNYnP7Tm1?Yz8or;0b}9KLcz1aum}
zBvtR8Z|$Ez^DJxE>MmNm`0BkYpI=?o1`Q^jJ9qBJ?(+37RvvnDXQ!~Cp`q6D!17mD
zIAeF0neH-girrPh3EJJ$D{UUIF2?f9+uP!{)!$ecKnrDz)6N|D_xE>VULIeoQ{(&n
z|KmO+72dFz1*s~JgNj~F3F+ktIdk@JC@eX=4^nk5h84vYtjUl6w1TrLxDb}P3)aYW
z?AS$LH#fGt`}=y;{pUGczP+UPX+ryc>!K$ee(STZue)m<mn6Z&%*_3@%5&0&l9!jt
zx3vA^oiurJ;L0G?sm_i)Q>RW91s$~Z@wj|;P2JmDTRC`mj%-dp|7A}P&&k8>{M}!^
z&zUpl-X|fgPS7?)_kOvD)8p#`EBBPWy#=~595no-<~vKl%1SCRF>!`<xnA12Ihq-|
zf`Wl3k3o+GT5;s^S3Ry{MM2*inb{vae!Tc{cKp7Y&bq(95}%)&`@Ujo;^{MIK;?pv
zurO%<c6oU@=mdgm*TTM-DE|BLnE%L;BcM(lXmw{|b~ZOZKYz)a8-jXzdW)WO9^E~0
z!aC3`mv7(pitEQcu~qXF0*xJoua8T7b!Fv-ty_<-2wV(G30_mRIAgrqy1;D`i#O7x
z;1Y9*wi(}EUQq6sb13ogieyl0Mlp6{;fve^P-6wOL`@b{CHnmf3Jx|bdlQj!e_!n5
z>vzoAZ6!`$Prh{S$PtzI7x-f(K0iOZtMoPK6g3r9)l8c!j+0dO)cg#(V0HMQ^@9IP
zgO+-M7O6QoIhokmSAI$XRgx!9o~(*nR&Qr#H$jE7`un@ql`B{J_3C&EeS3d@eS2xr
z-k(-65yyUQoe{Eg*Dlarn1croR`!E#BLi)ZFwGJPTNg9)JLs;gg75EQ=UA8f9SKoV
zS|rpj4mp}|s)Bo;jAKd3mQ!~<tjgczn5YM2Z_c`^HMdT|HtULp?Ha-Jw{A&Um%Y*W
zFkK9^fo^-=UC=hY#eW|D`TYDmXkfRZvJzAfEqX4o1#|<ukr8MBwY|Na9n>!|N<Gyv
zPnGAr+oD&0etwSFS)>Z8k3Ky;y*Pe<-HUsBcfW`{RQl=)CnqN-XcTSva&?gW|3A;|
zcT|1VnrC0%2b%T!_2s2T^tLrGR<bqrE|vrpV9OK0D+X62fnp%z*s+VUzun+Dq4hAR
zwFzpf^z?%A2RJ`~8YNuqpqO18yFP9&s71uW#&+oPW#Ol%re6MGmHhu+>CaE8Q{O-T
z|Goaddd0+lk&%&(lT=DxUSj2HWtwYU-nMh+&KHqv&oBGi9|bLR2OT8mJKHSk|Lk9X
zKA-=(=gfx>d@t%Htx7aNJN-dbb?K`sftBwb9qrDzx=Iw3IeMkdxuRCs=ib`VsNxAL
zy6yB%oVWkKroA-j@8|mgn{+^X{y-V$*Z24Rx3*?8SKMv1|MP)4>&lA8z{PHfUtU~X
zr1qMZUr%Gk)~%+X>9?96ANCvvja65Eex_(=CpT~2yvlz4=xv}u56O9UwOUD_UTx=b
zXlC<jShGflN5(?Hy6jDZ&gl)CH#0MUZY!Lm0&3I>3JSV?J-q?6!{OpZLC_&6%O&Qd
zot*``VzZ;G3$(w%WS^R;sVHbx?B(U<8w(yfflhrqug&ZH^3u|cB`<?O=RYr6&au7b
zXAx*SBj`||=4R)6kE_4Eahz{gJ7MnJx#g2~&YmqTBqS6Pm!4x}Yz(T+WA@kGUGd(n
z=-nO5Ejc%X-o6V^R8$0w`?Kf?udn&}iGzb9pmOt3&>7v^a&IR+I?@@jqhR5I(za%B
z8%0*y-5gY_fimfyW1yZzu)(+9G;kK)l?X~FB7D-%O+jr`P+Bkn=VMS~R#bX<!3~R9
zH*effP*8Aq9b4Xe_uO1-&~WmdU8UYnKZ1IR7Z<s{xVCooj6|lCloSOmEiSL6LWPBe
z8@6tBeSdH7!T=5M{)>4BK@0J3Z_C}7d)w?{Fi%`rnc1U9k3jd~tQCJH-F?6QzpU?U
zv!j#M{Vy!{pTDR3f_~hdj<>hBFOJz+WKs9W0z77*DLHAv1Od=Wll}jGX={b7Sn%o2
z-{0RaF7uTJ?Qxu}?k~0_puVEO@!+bEl}(+(>Z|_vyk6XIcgWxVZ_Ab~CR6K|uaDm^
z_xM;Zq`Guf1)oAX@!;<_o6o0sPI_{3vifO$IhzyJHkOu=^NdovbUY{7Bp>5x<o<g8
z$Pt%&dnz}-kYv-ewT;cYwq|BdW~S!*ySu~R{sb+0sC&Qndy28Kapm7%Uw_GGIM~?Q
zK3%Xt;i56mA$R#&mGT!C9G`A{^Csu!$&;Sjwr!hs_|Tyz-QxPE;%mQ7%}GmB>zB8W
zyAWig0=i88^fX=V_xJWjpF4AA%K5q0>gHKjJhpA#Jb5#yts;C1<dhwSi%%t=Jb7}H
zif2(t$(9A7ZS5$L4L;zo4AkSuH$jR}&}Ov7vY^UR<}A4PQUWd#7H&Uy@nYb=Z@2SZ
z&l`ALym)cb%9ShMJbR|5AF;vV-p=CXdy1d?RUT|&-86gl?3}DDt>Z_Ibj;H{(#+2P
zMAduRiL<jzC#!l+(hgsz<3Gc|(XR5-k{6kWZr-?Y0@M?IA<3q0Y#dxxR5VFkFGi!P
z>)@{9=Y4n9$J^h$bt`I`isv*HaFG1|{$Bt7u2SzWHqE7PZW#Vty?&pNtutsj{wdI%
znAe^=J2^dB6}tLWp`fIZyuAF*$jxa*etvyAr#IF7|5tnS(xsqpA3p|GzwMDUelp86
z`&G4)py0**Z8KkRKLDSKxFW%8sgQFUPoVYE+b2(Qf<}r#qe7XN)u!$){&V}}|NkY`
zLE+1MBtc8n?Ck77>s~>}_nez+%?z3b_;}G>UeVH0a^l2^pp}CUwkGLDZejr~HoCj3
z)Uf15z>Jxa@9ih+$M5SARCZfoQ}*LS;*upx9&A2ucX)!LGXq2Et1Ab07C+xm{yt78
zZcoIKkY>>OjoaJvK?8YG`{lOg-VQsU_1C)gmkARS(}ktp;tURde|_Cp@iD2Qy87{@
zrQR7gHY|M5`sl<ap5Wl%smJftfKp-7B*!FZ{d<x3w;LqiuHOi5!}ipIDh6wCCuJ3Q
z(OG3LsIj{|AqOQ1Xv&!NrTzQ&@5jgE@`3^a3RPVPfByM=K5&0s?VmrN&uhf)D!KRg
z?yl0qH#R1Na@?7@*5aVeS381wxJ0!;i~2!b$il~Lpb@F1L7=M>9)VWVOwkN>@fSIE
z`ZV`)|M_CJhaW^lM>|hToofANl9sr*c+TBjqU+=K9@<;|oq=JhcDUKEdzvQ}I=6#H
zW)}b1HF?scrZsDH)}BvKO;uD?b?xu=>T79X0Ua^z_O;SD_m)XTbv0<>HsjhFNzgK(
zHEVQ0s}$aDt^W1~eDp?wDku#wbI$`GOu_={<jykBU-$Lrv$L~7J1nYVT-wfEy9V0+
z@ZsxMP@x4Xqb#hg4`077ety0^XhYqey?b5Hi{!nyu+YHJ@F1v7Bq7nE6}oE0-==^`
zDxk*01*gBBzP_#9-QA~>K|^dRo}i_Mryj43-tHC>GR5w>WY3i=A)v+opdnp9KfZ?R
z`9@PzJfEJ=pZ9w^=!6!~8kecZLF9=|JzKVzIIiY7es6E}#|H<S_w>)Vt!DF_1iF#p
ze%){1r&}kfBpzzv{54NQ2E6kSRGve+p{u|nMNj&{^VXUYpcVmWkRcR2vh?XVc(s8@
z54f_IHuL-U>&we#W%oYNQ6-@L<1sNYSNLXur{K9G)UW;g{M@kqU(M9+^Y=AkcbR~i
zE$8ii`y4PjJZajrwl7~wQc_YrFeNi+hplPo@8<{I+fnqy<HpUKo%2!*KsVH_SfL?T
z5y)U{Y#g#8fN`nU)KkCXT$gxGR`UhT|CGGG##{ROT4?3FL#^DPJ#Dkha<ww%CK?}W
z<_4|(05$VKYYtb1t_GcE0=kPx*19aDGBzegMlWtp$H~d++)-XGE+L;j!iFCX+`K9I
z@#9C(B@M@(_sdu^rKhLct{3XxKjXyw-d<i%0^yUjTHrt5Zo`%>EjxEwf-0dUp28PD
z^EB<<YkO+CKB!^QJx?j7l}j|_UIHhB{r^A4Yu2s>&09=8?mbltbR^Bo;&}%p43k(u
zyRZ)&aHy!N0xgqSq|P~Y_UzSP-v#X4xl>6^Qe<fm=hC2+-+q+euU-CahT*<K$%Mxl
zhmW0<msYO_)yL2-<)`DvPRfHCX@38}kq7BbF7E1`Y!4bJ1Pw8Pl|bWi&Y!KBm(|{%
z-?(vO)_LjAtiPsBn^y7X$Hr^V<?ZWuyuH0`^^9b$uZwLCTIu5A!XhLr3_6CyF!`9n
z!hi#3&-#9`*{c=4ZcfyF&_MsKEtxaSa;0)|a<2S~RrC}J3J(5id07E;UCCm%Uhu-)
zq9-0ZcJ0ct*|4DQ?=Plno#p@jRGyh-%H7T{@0OOP2HHrRpPvufR{Q_&`+CqhI8)c(
zbXmA?;fGJ3K$ANc*Tq_2SraMDFk!}w4p3V2nQ0WUEobI~sVN?yMf&gGuP>6gY+qSj
zt!!-_ef~7)c$3%)M#%mQPJ@&a0-za!va&MJC?9AF5xkVVL)Cklf{~F>@$++{w!!Z~
zOP*g|UjF(^l;@;^$H#ih_na`8V_EF>^znlS37}Qx{PK37!JovWq($GPl5HN!GJwZx
z3?zJKnH+56l?H8AxpC{(qf1M@K}!U7mA~gRHoht^AG5RQXvTe?iU$W6K|3@Q6%`jP
zm*BZ4>$Q2dd4AWt0HqCupz8J5F-W-!%4?<Ia+Njte#Y@*7ePmrfrbRZLqy;{E2!Vu
z2X3sJgL+P&MDS^Q-QTK<!aUQqZ#SQ&7uy9&qN%5+X`Pp~uah}FO}DwfzkfmLuX4!Y
zZ3;?COzG$6wQk;Q47x6})v2+KSGsGSy3g}-b1M(@_1W0kGJ>{vUHf5scLx6+kas}2
z$-=^7fjjuBnDf==4jyDIe}C`js?gOHj8-c%E-YXKT_OD7LBf$EN1psGfBNWA(?n%=
z(1jEQg@uCFlXx!K@6SKEsb|U*ksG&ful{S@)X~ww<v%GkQp^^_?CAJ3ee&dH(4OMQ
z$9gBIaH^@PF~r@U>M|`A6#B2Ptvy|RM`Ff|84D5*w}FnwI#-|m{oUR71rr|{7#d#u
z(H!dVnLnoYt9aa!SBF};Gj46seDmfFXz2uK$?N%fwud(+AOG<0_xsg*uHC&Wd+*-8
zh|Oue3${M8u(V7(H^-8LgG0dfsDjA1-+cS;U9bla%5F)191sW^5CHXg7CuV259$r|
zf!AC?8n^9T&ER;j1~2FVMV;2F+2;A6(`!9EJsmfvoekJsmdgNILIIlLw6L^%cw=L7
zL20R|b%?)@uWw>zW~bj=E60Ta3vzF7V~wlG&Cg%Iyfj2;P3-Ql<=tP~`Q_KOo3<^j
z{rwFzOWr4M-<N)V-ocY6IobK;TDEUDXGl0V$MVLO%*hvJ&V@)EJa`avj`nSdTmSz$
zy!uhOSj*B<a;kQ?TTV{Sz3Z|{N=jN*a?hQ>Yvh<_%$lX7qr)St?&nfcV)E|JPG$zs
z!3tKTuUdY6ea#)G0h-BQ5TN05-oV1<>fVB)q9Oq~InWt`kfFi<+jf<_WU{xnpD}9|
zSKJEuudl9xt`%)+Zk{-0N{g6oRKleto>}=XI{W+Ew{A84_3f>8#>xn2^Wf*QdH?&%
z+ZR1bdJGCvP+#)f*?91L#)_oJ0fig#w<LpQWTl_$g9p<>HWse10Jk?yk{`e5>-{Va
zZjXe7TwNW0{O9NAAD>Q-S5i}Bi{75c`r%i$UqFBWXk#R3`&isc`%OBad)+~OtdNi?
ze)a9*-!9&-{qylSXlVTL@qT3s3yEvju2uZ|v-8$x&`}fh|MxYdCV~21&#%w3D10QV
zrx{uC&{CBB{ber~moMKw@Ig*)4N;moV}^o_&7AyK3zIzk{oB{C*9R@%jE;`pv2!P5
z#ox3u_W%C~gBHvE`}-SoF7!d~lL4Uq>*Hg+&5IW+yY<O%ii?Z)=KssOvtwgJX^IEh
zc#)To8K0>5@3yX{Ugup&j{^cX7OvO<Ifwj`sC0W*SFiKYqmWAZ&Czc08~bXl&&{y}
z?R9?g?Aa<CeNUllYopaOWF@<H7C#sJ_5RE}+uyP}hB;nKjqX2J^=w+YRCUhWxfeGi
zI?tFr`*o(I<fcujr<3mOsRXUc$^s9PhQ4dC%fDyS($=P=s_Ob7=&ymHq2`s>s-8x-
znDr-3nj|15)&|<YRr$%~tx}TbBmr4j-Hf?)qTe1gB_HpTeEa;Y{YP+k<%{b>*Je9{
zYTv!p-$92KGsMjgxVzAq{mSZa|2GDVKbFZ=NrNsMe82BEpZ9dVqaA|EpXwxM&7Ir3
zHTyc~&|=V{+Kh}950<8A{QKAK=(}9^^roCE`+1h^pD|;G!z7it{-I{y&P$t}i@#wJ
z5(8dG$@j9Wcd_-iUM)~yf>z~$1M@{6s2KwbzbEg%y}b>Z;9DEL9W>ee<x9zp+qac<
zb$Kl<Eei??8hU$qCrz5<;;*VDcyEi*f;#h?`|b5Sh2Fe*V^I6+i&Lyg<fXkeKZUHz
z-kkV;p!@y4-+mXY3PI~gQqt3v?d;;-GJSb|e*WUPy;UpX_uDO6w8+K(YWJcV|7#^X
z&g{Q?ZEf_!_wV^VCp~!ftgYzjsmz+Y8<UTJ+2g|_7ZXqd8UhYkIqB3vaTgbtkP`UZ
zR>jXxs-V?qzO&67r#;;xZ}9BdGp9)^KYsp9e0ysv=n$$0OMe|U|9aszXdmR4mzUjN
z-_2rTW(KuT@9Zx3KY#i}K<<qVj?1s}N*X<p)i>nXV?CuTEG%q-3TN!Dl18V6pbG{o
zAMIxYO)ko4>3!oBWd*k*tih91vk=KK6g(Wj3eL9+AAyqUhQd$RL03{(m2emu8Wt26
zH&31{4BA}}Ix67irc}_@SP*xXX?EAVU*~wG&3GoMfcD%Qn3^8lka)P{S9Mxi8fa<k
z?{9A}?yLP>z9(po=VZ0S3kw`GE-Yw#p~?34&CSiA)qJ3P76b$uq)fBGtF1uC5v8Q0
zfUa)!@bf$N>FH_E+yUrzP6^YjDG#2$zX!VZcVBHaXkXX1ZQDSHo1L1b+x_KB$%#!o
z)z#Gz(b3=o4VS;VyMF&auKfJ`l6Q9`nc4YV{{Q<6y2Ec%>S-kv6_(D<PSD;nDbp;K
zDlN$gvrMx=x4m7wcyUF{&P^{Y4}E;lwCMD?bD&FqW|?L$`>MdKq@;977M2efLCucT
z)6*0c6c|7y!tUMHDxQbFzP`RO=cdt`n4Ln6jg1kTQaWF(tO6}awXm`}1UhJ6MC+iA
zuI|Q+i%KjkEEzR*N4rEp_YK7DsaW_t)kT&0J>Sw;H#fFLixw>i(GnCFXOE7K1|8qd
z)yfnX7q{rSBoAl~8C<Tc_yI0dxsL6-*aI#~6t(P-#&H4)Hx_o>vtwsx?~ycS1Ko}!
zXJ5y|&dz@1*s*7^9=16*3{=$Bm94CzK3pn4fAy*;=&I$auUco$o_+Z0)vWU4ul_uF
z@<hSZR1`F+`se3o!_rqFwrj5LH?Mv3@F8P;eLZNjY~8wbi_#_MfY$tdzh8g6k(vF<
zyveDO`}XYvErY+dF1Gv5otQ0occo^|oM}=2Z%@P4U#1BM7(mM(K|vk5I_zGfxNh{e
zBa>9UK|4i3o$q(=-Yr_r1)BH)xqN&6eYS=@_5Hhc>_|8}%k;y?kAiz9@bpfdDhisf
zT$}5&<mBe`^8tISN<mYW^J_kJzOZz0ary5B&uO4!`25`5t@G0CGA<~92E{KfcCU&{
zvnVPm+ED+$PDNGq;mOJBS^0}5t8f~ppA*^A#}j&YSLwqyZ+dEff6J@^-N^+yj->GA
zB~@E}Wi82ya*ey7{m7@M=>}*`1+9Am9d_{V?{DXY0Si1QtAWPXk7-JP`e(JyA)xaB
zKuyK_FF;#~jvfQYQy#cMSaSH-!b3@q1@_inyLOF(m-pz0hlfADx~d%!5dmu9?ydUD
z#IPoEGuvb}U#F_7T@RMFy}i0R9Mu1K^ytwiJ-NTzch>#2GRwaQTFd(2)z#G#R5*2`
zx3%owZ~yDt+wM<KPj}DD5CC0baa271Np-}jGc%1R&YH!=06KvJbc2yi{lA#`#;u^M
zr(axL{PC!Ge1^@3q!$+!dieSteRp>^tG=kZxw-i9e);2HUtfpLGJw`Jr=_JWTK>}a
z>@3q#t3Qw5t9Tx|x;p&+MWw@6w`2x`a$NDVGlI6QUJ~l+>Y#lK?c(66{bRxJL5&y}
z)rhh(v#2c@3%~vhTN@?$RbK~m9{#<()sOq_|6Qp1F1BxFy9p-;#{tlY!^&WF(5%ze
ztgB26F?*{-Pfycz&dJf4rXR0Yq1tJZbHl)6Qp?rV;n2A#?GNugCbg8lzV<S4ZUw)*
z-I?9iA@}#yR+ek%YK5$5Sg=5Wg_ZT;v0mvLdn%2mc&Sd)i|qn!Ob%Y=BWN2a0q%H#
zR`FkAl~%6@H(^YY?~6cI>?_7@0L|iq8j;4JVibI>$R$?k<prz4)^>r8*<naXOKStI
zOHou*e9!dd^mP5hmo5c8IU;oM%o!eLcD_H?<7)UAOtY>Wcyn{JVfD8h&@|U<^Za9=
zOII2i7+6?Y4_?16URPHKx~dy=?CE(?HFb6N&d$!L`TIc|HTPCc{l0PO(xn&wn16e=
zZZ|_hb~d-?qz}*M*FUqpzbaJQXP!;u6`SUSq@<>4y3wE}?V{xzm-kc_Z{@ylex7aj
z>FN5Q#T_eRcbhd_|6Bg{mg$w1!R(-uQw>9Rtl$4nimR0=c6ZrP(BY+3eE~K*78F1`
z^l_lgyI=aCGyV+hwo74a0Tu}zxPD#y_xJb5XBZ}%*zM21Z};QJj~A6wA98ST9QgeF
zJZSxW1$fh%-xn1vMJ6Vu4<8;n>qKl|`2GETc;&e}cVsrFoxSwyzN}>XjvW>=X3S79
zHy2;FY*|NlxAuqWHm!eE13c5Rv%5k2h)zsU)GBWWZ3TJHx70N%O6t<(%M&L~WQ?5F
z`-@kbL3+7Dj*J%9H{O>`;EwdejfMXX?E~dUa9b?l@ss}E;0o}RA=fc*3v7bk4U5*t
zZ{POLwJuNk_U0x--2KKMpb@Oe>i!dE&+hh}ZI<}q!NI2RX*_mzc5a{l?k#+LEaT1&
zL(tijKYmnbO!WetdvkuC?S_pT9sA{MA3T4~9v>fnG5G5`@9BD=W5fb?m*s-iTrTyR
z%ESQbf8X6z8nH2n_1Cwzv%mj(e7yhg-Mg_@V)hml79PC2yPR>)zkRVgi&9loR6zSq
z7~<jsa&*KW|G&I`|GzHKJ-f$xrB9qV0a~RC>KMnz$1mP3VQXU(^Yn4-?y|)1@9uVV
zb_V{QB_u4&-0IZ$^Yio9#fuJtEPV6!Eod*bN!AsP(A8m}xwBK*DxTo;P<5}!%f$p(
zG_&y@S`oPT!oJ#S&|ZRd>()utw*~L7t7UxM(b3^$=XtH{i57SlC+FuMACsr{2L}a#
z&N0}rd-vo0|NrWP9K_(^<8uUbk^5}({G`{{)>hibn3zqQHjRUi@0j}h8l@_(sR8|R
zwucTjvw!w0SRb}l%I?nxXA27pjySgvqrZRO1$1_Hy499zJotL@zt>VBK|w(eAD@=?
zc6JdiRuL}NJ9qB5oWHCMUSz$(;)c0PzC5UL^W5~C??Xt311@6b2NyX%*Sfsm(-Tk7
z{FRuPSjERjte^(#+uPegWd~^a!lu;I0n2<OF9x@EbaozG<l0^E?2P1+<;$HfN1rGz
zDq_(wwz+xpCP?noRPBxR|LbPVn6cu{%i9s41G18j_kk{=*U{AtT<RstaNzFl@{f;>
za)XZf>FDfiY;I<b+f&il(7*sXf3&Wyu4(%I>f~cRpvBmQudZk^9O#iW77!9@dU&{9
z+1y+lbl2AY{r3C*|EoUe{Z-x4QWCU9!QcMxl8>*uRXjn1EG{lAGP1I)IwI>Go7q4G
z2I#b~-t+$R?PNiNpgW77f7#=+r%P1(Rmq8Sd#k^H*>a))w70&QogcI^YO7of=y0!+
zx3@wsIBoRt@%i*`&C6nsX{jEQjvNEsn4olzaV}`^^aO*Yg~f`$20qhLL3hVlm%j_C
zmSK2xWo7b|{co5U($mv>_wP`+G_|>znGJM>0oz}0(DL;Cf4@nKaJ9bBbo%%%VEz3P
zK|#UBjt-7Fw$)<i&YhDmNMI1*Y7LxkbM}~~j2WLO`|q}UYG&uMK`U(4-poFf4C+u8
zzQ|2_yyqBb0q&t=nxJ#m*rnU=sU_#n0bL-Fb#+yxd~{S)(%V~GBX*aqJrLTK`1{*i
z(D@*sgSQ!(*+8oo0yIP>q)J+szjHY|%k<)6cm9jUyiQ?ZV&C4}WL_H7`Qt|ggF`Eq
z=#f65B{e@kfsVk~mV0|c{r`V^4hP-ZmdhO<AOGd$W%c)m?7h9c7w@`J_3Fw>(9~4i
zz8X$$Zf>9XcCw%yV}}kOPRz>c0?p8Wd~|eC`m3|6!`ENfS)2~?Feq0oaBL3Po)>%L
z#*GIrFE0lj#%Gpy2Xtf=C_%dS%Z2XVz146>+1sdn?L3xNR-jW#t71|t<ZLPws+tbY
zvMg3R)+@cd?4u<EXeOVLk#UA$a@)nYhJ96EUor9PD<~-~TJ%^Jat##Eg*leRU0<9x
z-rStNzuB}c|LiQ&h#dure)DWHx2R8@{7!@mocP1mMln|WeYOKM4=1V}=CU$qDa-oB
zlk_YsBsQm=H98esTv@IWx@_694O_OjfR4Hk(73QI_cqi1?YD2=ew{hjB4^H_#K#lX
z-7x>M4s<4P{)WOU8}qsP!5y^=yFn4R=OAd^8z}BxcJ(^HpJiyy_jJAIWHkeG^W&hI
zOLhNw2M|Led3Se#Pk2*NVQFUP7qboJh@4jV;)0^aRIfij9`}3r`?s%Mt6TN$4QG9Q
zeMNQk>N|;3J3?C9+mk;$I0)K551NfxyFPk<oh@iT%7+gHi*0n4=H1-|vJTWI$j;85
z`rOFa_~Ne8?3DC$(9}wk*d)bGn>HP4V&xVP5n1x_r>gff&`DjOfrWX~1qB5s8a_Y{
zR~LVcK+ri`$;r)9rdbIG8W;--3j?iH!zZcu%rJ1g;AEr{y)6fHNztc!H$a7C$oe?h
zjT<+D4#nKlw<6`?-Gy5wr%Hn67(zls7A;y-^2_?zhcp9ldFB!RMtafq?q1NcB-!7~
zKHRVXt+u#$`zUDsc5xr5?veowA-s4CIxkJd^U#-<mlKncnkqj(6a4|&sCs6m@z)LK
zHh^+qeBDn~(0Enaw_k4`-@JK~fgwCR9CTpT>h=4Kc5z?upJTzeG^kU)?g!(^lP3*~
zjhol6*Z=eP@5Qyz<`Gd*UGqFtUDDFj)~s36^KC&>?(J<0UAx78f|@Y@f1a=3Q1vy-
z#m!CXDeH^k=jUAi|NHy#UiJHj_WytK!zuxnhzN;y_x5(Ljo!``rx_O(Cid^oXV3!L
zRkqKcJW)xQ81e4iJJ3ny9fHaxaxns8Vrf&@xr77-C)PpR8A@6o)qH17`TqRr>FL=u
zy!Wp-|D2c_`GsYX&`MD5FK?e^nA~>i?m{{Hx-}o)|GE91?`xak{kNU><RC@LiWlIH
z5@=;gK;eeMj;=mX$hO~O14&D_uXyq7%uHs_Nd~2_LZ)bidM$Sj>G{f3lAWCm+WiJv
zz0S_f&3$Koz5V;2T%uYJK<hG}y}Y|7ax>_%m?cY8PHgG{ooe{(%*+?}_wT=0vO&!>
z`&vt9C#PQQE*4{B<11?-jo;trz2z~fWp()aSD6bFEvvujfDTRi@uOl-#YZM~KADE?
z+s)-{t6BmVyD4gDaOB?JCTbh3U-$d1IghlN&+_YKZ*B<QumAtoIxb}f=!U7gyURh>
zeP*>UyRtS~TswRnC}*;)70&<r>nrF8oPXc<|If^QQvbWLVAh8RO-<0@jRP}{(<jWE
zx2~+BQN{DeyWQ_u)+#G0Y2Ad6xqo`Se*d%I&PK_9R5ckE|5DWuoTvy&tB<9pbGL&=
zOxrs=ctE{OnY$Z7BYgsbod?0G(i$wNq-6N-=U<P@bAw)Pg>E^klsC`0Au!u47kru7
z-YV9mL7l5YS98UzhzDI|XJcbykblnxv<ms^)zB|0%@_7m7JE#ZQhxF0?0(N!CnqM*
zNl+V;T)(`&&M$42a{@eot*NOAy1(mUOvAqy7nOJH*zw{^RC;>4P1Tndvie3bvesoT
z$NOYI9+$6w@a^qwhK8)Gs}A108Tr9zBd9X1`SbDkj|a{C7j~EDgZ70aAMb13xzqB{
z;lrS6y9ac%ppRljf#W~WK_#FA-jDT4gBC<xUhW^bEhiGx8km*}8VkQ`37T0fL98J;
z-Y*ZnRk!dFOG;#$if85WnteYv8}8q@JZfv!B6R^lN!5Lp;k!{sLV7`sR6fCp63}57
za9_hkg$=xX>fjB~8a4sJi3?xf+^jxLH@dBrTl~<WLrj;K`-65OC#I*fdrq1#b7p2p
zxr$xwFB9;9M%zJ7e*W{{lYgDwl6g5`b(pS-ii(1<v2bEyqSpEC`S;_VF8Wfx8#E$)
z=#bO$>roLA4}N}r{=Q=3!{V|svtQlk{^xysbTs4sKHH?^<c}{dDuaT_w(1KgncDq+
zV{DRniA6ttpNMU+gj~#myHhlSKfJi8{O8kYebAXibLPz1kbB!~OU_Lp(B`pMS672p
zYhE<&?C9{)0rw$XTtb+9=GjO-KR>@cXr;^NXJ;Qid)D^%_xHtBUtfW?7WT<nx6PO#
zanZOHv}t&vvU^C~iCgPptwEPqd@wRHS?)I%Gyuw=psdV1Nd>gF&M_)#*0Jl~UtRT{
z|M|oL&`CDWumAh?dj0!?&W8`Br*Dnkk|8LjAIHPb&;R51@8kyu8ut`8v4OjH9^!AL
zwRFG<_$?^7@4x8lb>5ZmI3N)`jh=BF)R%WJ&yl&r3hL7L2HSvUC8p^{fB5v&yX4iC
zlNtQHGfgsuz@=0n=;T#-`Ti9vG-k}2wW#>{xeuQ{3GE2j|7rJ+KcFpEJv~SM{{9Y{
zm;>D`<1^E!D#l&)V5hLULH)m)h{(u?H#eteoey6b#L6#cBe20|&YCqkz5nC?Og4;n
z;b8zZGeBoU9&YDXR#j!ay*<Bu`Eqqo(ed;1b5I2cS|spdW>xv$U!|ahF$@WLd3+DP
zJ{MsC9o(+$-sh5$p~1w=+?s2`Vza~H?!jjEkN5xo69=8S{rGr4Bf}=0!>3MhU0&vU
z7_@z~?oY*=dwZil1Su&kn&dg@zKpv!xc|<!I%ugE=+rCFn!zhqLO>fS%*@2z-rmms
z;g>JFn3z~cM~A?kkU1AF1e}>+$m~Dg?&$shGn2EkyB|DA0Il7AU}dDDrltno%>X(J
z)IEEJ%7f=UWuQ^a>+9peXXd4z76bM7C#itWFZ}TRJLr%`(1x*#!n{o2bu5=y_lE}t
ze)tSp<_1~tQgZm1V(f=%QBhWVQ27LnJ9ALnL6w#tZs$M#@$vD(kB?j#*6YV)Us~dM
z?|ACzX|6FbGVg1AL1UZKbfeoAyZ0YDcu?{E$Gf}B7w6yKS1E4G)Bs<f<pbJv6uLU>
z;fIHZK{GsIYa$w#`Obdy@$qpEet!4qda)0lJyWY%c5kX~wAkloXPpBA0^*eAZ7Kxr
z-Mh!o09ur0Vj`lcso6CBReNVAr;6vLms>aKNWcBQN;`brfy<YLZ{EC_achg_qeqVf
zq@`znue`h>P#M&d0JU--Ed3R}(1{fkvX77TGBbb<e*lfRAD6G^VE`>CwEOu)crKsi
z5A#O{S#L!~M=P6{h#YR`cP}e51C2lC-Zld*YhwV_-=KW>^5x5>=|X~nQ+@U@LuX$>
zyX34&UokM`<m52y`Nw)*+Ro1I$D7UPTXKw9q|NhO0s;i0w&iplIN-47`@L$02GA5R
z=$?&$00Gc|tYb49XPj5tgAWf6FH#TSEdKn=_o6V57-)dASIQK0vL0w|H~rk4gU`;+
z{&<+*9<+VH(b4h4*RQSf=gaRZea)t=t$ne$H4)TZcixqBA2g%41-za~Q{wlsgdA`i
zs0*@s8$6~BDk&$dgG{m9m9?vp`1kK$rM&i3FVH!Lv(58Chw6aK{JGZR)@5%5c1+?q
zxGr}0gLm)N6$SoW9lrj<$K&##j^OL->)j`-`3lI&_P)Hl95lz&Ev_%NBciAJ`#aFN
zw4g=sckbLN`1`9gB_)M{;mzB(f>KglOO~kUL~e5V5cD_u;v&{<`S<%4EKu0`9JE_y
z!v=#bp!GdQhRgisYE?OP8l;{QxpCu$f}$ehvSrH(ii(0N_Z2@s*U{4>vc+!=Xw&zh
zR_;o9^XzLptHalWE*1ohLu}2yzR0atib=fd^Z91(bul}e-n_|SXlQO`=99PUvH$<)
zvIf5%1B1A@_?^Ag;-I|WcWSD(GGr)fb@=*2prI%i&|25ta_EE(<DI*ALHBoq`Y;Tj
zy+kZ5ETHRd85(99rzail67}%)6}1eW(Z(wcI&lcJz-8sim8Xg=EiFOy!=+1?KHSdV
z&l%<6^5y-J-Oi$YI;TMga|f+-2?-IIXH&@}EiL`!#YN`2y1EZvzlz!hz6Y;#05=>!
z>yEU(`5wGs;o_3Cp%AhXHQ2z6PjF)5hHcx9eR_Ht<TM6{emUEM_xEh)SQIiHc<o#X
zI+XU#{`&YQK6_tYTN}MFPTy0g?A@K8eb*$!Kv#xJ7&2{6KYy-T$IMJ@-@bjIRQmxm
z0BZa0`SbSR<$e!eU0toTjO*$1=k0%ge}DYp;o%h_D~0CFnG^EvlWpoL5f^uNaHnAU
ztNWn2=Y#C>pwTU^Rwk}iChuuFj-YcaL0gQTot<q_^<~AydlP4vXh(0;0bS8>a<aOz
zsi|mRU!T^0-?fpO*@V@60xUnAj#v}9nN2%vjf0aDla7uKXuU9KfArPW;S3DH!ND$W
zZi}kFziXQQDju|&_~9Yesm<K~{#6<$AL9YHu)k|Efc9^KHrNI)_hYR1``_Keg9FsT
zxpOB5bQ~^df);dmn7*o#lGaQg7k&lMc8*0&TXS!N7C2SPe}8{p9<+yokMG#?`SpFO
z-qQ}8KJER$Y2&)My<Piif3MoRkiFvX;ph8me@ngPkLc{Ux7576{n!2f|3G1u_~*w*
z(9TXKCZ>R$MX4pPuknJ8g8uycysN({$0U`5r%!W(?v8F|=La1q0UGmv`0(M2J3BYO
zsB{7knkp&@HTMQv<j91+nccLpu%qKh!eh`naZzwluB3E0U{^`zlBG)-D{9SO|M*cc
zwK*AdN!7f0dRg=Cy}h}aot<9}bf!q*!$Yid|E22$1qXw6p?$is(79c~Gw7ad@coRt
zyG-BR*}3?9C0p|SeYK#O(7jb(6+9>1`ka@S2O7g?)e&BwdV1Q8&FTE0y?m`sj0_U?
zbvA9h(rwSr&rd!-&vws`KlyTYH8aW;HyWNkdD8LarKMZ#{=c}W44P&wocItl`hISn
zEjKqeH-p3OvbUg1PC#d6fmRfrn`4<gMSMQ<fr-lQ0s;aJT%uYTf1+a6Ms3|=-5|Yq
zW$^N(Pft#Qrv4ZbetmfvpdrG+&wu>d+USex<L!0g_C$Q}0#&r9eZDY&B2P){#*t28
zL22pk>H6`YMjvQN)Kc&12F1^O7}nqaAuJ`ORk73pbV}FS=<QqV>R(^e1zn6?-@L+Q
zXYFq@vz!|ZkojGfO**S>@_m-?nVi<x*a)t4BX*U%w2n&NA!VM|13Gu*;h|Qo^7dPs
z)B6MO%X&>-vqlGWv#i%rp^qOwGJt&2A*;#(9ue2l0uQZ%wzj>yVX=N=K6n&0=`m;&
zbyp&Ij$aBKr&?NOd@q}N7w-m{51PFB^a*q;DQMl}y4c;%Z0jE%<6ZnKE^eupD5$*R
z<Kqj^5CM$}X@#xPsG8;oy5?BUreeXT8=(7Zv$L~JGA=kg{Rp}lEM#TSuQ}-k^X%*S
z)YaA3o|k?cJL~_u#r<|pNl8k6^X+<%9C3N_?Af8acV*AcGHveUd@uaNt*FQdbkxX=
z8#ne?n@O*B>y=6br4kN~fNDK;b#_pX{qwW4tUAU%a&mGXK70_cb+(X;nP49t9=>DO
zu4lD5sj00SHW;+DwsPJE?S0EvI{E)krz&_TbgD#VW~PCuY3tgxYhP$O@ygrDfU2B`
z2njYGi3OkTTw5Cr8kd01?>31|TG-XmabSX?^M_YgwQt<KxiIJErmXc7RX9C8J(;de
z1g$n~RPoHp|8>a?yisq@<4{%SvNE%zq@)c+PrX1hXliO|Zq=)H>YN50&oRYI6|};B
z$@1lguU!+ft^Nj@1lqHA?@zUs{fVIQvxSQi?t^Ma*W<^2a!b3HznQ%saw^dhZ8N`%
zpds>O7a@x_K*!vGrrmc3FZTn@MPz1XPDquk{q+TOG5mz@HE(Ziy|^VaxTU?FJ7#6P
zd!I~W(8?p*a&LpCAQr{$E(0BUH{Y(d=T~*be7joEDdlslO1ZXe+qR?RrI3_aPRF~u
zyOVEk%hg&x*CbOYDJiMo<t0_e?4y~NmT-a=LFU}r!ntzgO3>ah(D1OHQr_)tx(pAN
z*oXisgip9`XOFr#PUbATNV$eVZsLDFfzz9010JO*V$&(h)a;D?QmCejRR{=D>
zSjqN$`TRQ2=niQ4?Zx0P=O9}g4zG*dePy56^CwRh6h1x%ssz5hy{%rg%JIaRGc8l6
ziq@BbuKS&a7>Ec83c9c^)*93*1&x)Ron^|%(An8p@!<iZjg1YcPzMiTd$k?AdQ~(P
za$6Os|8=qWghM3S)(Nv$lbcJwe&6lv>hAvd>FMbp>)+kmt6eoKZmvZklh;xq`#&F;
zCrzH5n3l#CA0PkY_wU8g+w(ST*&<>)kw*fw7@`)mvP6Uzw1S^clpQ1j9(BVa;^*bX
z)hB1mWo>P}CHuPG`;VYIDsOCH1f3mmxQ&-pPej?;S{k&OCTQi6dA8M{)<&PKwbR0Y
z1=-ivZP>6uz&3EbUd)b$WxlgP?Euhf=9ib3e|&S(SjM`H=l%Zw`%Y!wy?giJ+qb=@
z+1EItw9kQ-*5%wVXlZF#Q2zd2L2>cngU#%qe%{XF=Sh!`^>+01xU7%c>*6o^?AF$7
z4==AnlhyrA<U|$)Xt1m?(%HkjYt@Dg2B4WgNlD2Gsgjda7(tEE4K+WDc%)1`J~;i|
zUGY&V@6L|KqNk@8hOQ1XFg8A2op*g*Y{Z5HMj;`ggyiIA`~QD}9|ReKHU^xVXWKo~
zI9<ukPEJ2=&jHY;s<&@@-TUPdudE2<;Nm)EZPE%_+SU%;1|+!vbPCqX_q=j8KXmmq
zEkR@VprtK_hK8VukYPd8)-2G8ux@=aC(YX?x|x}oad2`vIyf}E&`ddCWMm{DDhe9y
z*s;Un#;seR!&d?{L_nQE+w%)PybGwGX__sjq@*-q$`qE!X%|<8YJ)aH*8l&vVf%J*
zTYm}2w8e%S=1a8A`rh5Js84*nBKf`uFSrW|ig)N*Dl0R;iyOelPl84X_vV5&B!z^C
zgsqKgeSEw>`P>}K8J5M%UPM-ve|Zte!p^R&smXbDRp{X*o|8X3Y?oiP2XxjYXbUmu
zd=+_lc}MS~v#iVYKobcblUnA?k(n`brlPt!`y`b_&@F^^wYy$)I^Ee*DGZuJxVYHe
zG_HbA;r)N(<m1*0R-Zm`;=sPz-=LN;wDbjy#oXMK>gs=abx#k^mseN03kwS?`$Ja-
zv4T?D)TyFuyizTo`7g*$W@iTn2G9vv1sg4Fb~x;AX<-5FrAj*51zO<K#w#7dw<qKF
zHr+XM=PnG<Vudtzpu<-a883ZVw$9w%<WKsc{gpBd^_h+#9&c}NcfY*McVogqri;NV
zT0o0Rrs+m62+=D1^u#k{RS4(b-{0Gv7CM0L#y&6HR^A?zo|FW-D-Sdzb^bg*XoZ8i
zB#Rl}#ofpEfeviTI0hQb4m`e3@e)5|^`J3mO-7%U8Q;V@NQue{YB!{$sDK*f?fmkf
zMOmP$EI`-LyttqUY8r`Zg$URN&zP<spLBknZGhHP&=pcXK0X_=u4*mbSJ2BfZOW9E
zx3{;ij?uZjyFCBOn#kZUCW)XWNuVWY;DIw++pTdTuiw2}_dK;t-P&5Zu&^-W+M1ac
z<81yMySUgLG~YNyKR)j9=YDznV^g)mL03Q8>I*-f>~DAQ(b4XUd#lSUs;VA6J3BjK
zcbP6|vgFB=6z~+3LCK4Nh=>S|IBhw8y$fefpXTnDw|8@LVlpx|e)#0clA;Gk@9Zqz
zn0S~?MOBqE4zvv02)YbgiTTU3bsYIimM%>^F+mY@03YZi5YUD#22gM1!i50P;-158
zyr9b{I(E9KUTftRzpydc9ds0I?XNF_w(VXsq|NgZKqt*<O$ALNg3cb&3|`hTZ)rGa
zY#{yoJlDl;y(V^`6A@k9+#db=`}@O(4+kzRbOx=`v(*=A?sfk1Zeu=Zv0cubKj7Jj
zjxWvNB{GSRpMbZ@I4_aUk<rpK>)W+uiwWq2E_J^-4ZXd*M#jdU-!;sfJh?gR>MGET
z?+p9;eJ@s4O`Scv`^Jq37Z;a=<9)If-`+@qW-B#BxW2r(DZJEsx|r?71)!OP8yk~B
z%bPC7UvUTZx<Ny<Gi<B3z0hQPdUJC+=stSTDIflJKV81aG$&_eb%9oYEey!0sRNyn
zs3GE3ykq+8+0ysw|JS;>xjnPpmUdPObg``OY%|xKoHc=er1vP;>`<s*>OK9~pP!!v
zMMPR4gD<OM8updFjbdSAdvtSiI<zmJwul{kU*W`ESyxxBtg%TyCu3n{_2@t&vsU>e
zP=c)b{*G5(US20|j|6A~{r3>XJ$v?m)(wCz<T`Uk=Y4zY&xtCW?R>JA4qIt?g7&wA
z)>KOvFf8?+-nMzOv5&8BXq>XA(7AZ)DjC>XfVtM{8H$pdwrnw3vV6I+vNAJxNXhGq
z%HH3Py7eDCeArm|`Ps*J0slX|UcY}){r`WUbyzYoGN0r?M=^lbt*lwIX3ufZ7)(nG
z%hc<CqroR9EZp8$3tI69jl)_{KM}M8RZGu|Pg>m`w90Kx6J!G_XzkOL+Fvi1gBl#5
zBlX;Rr4F7vsrlYAI5_yr%ggN5-`|<e;=a%?XA8R6{lp0m(Cn>iw;1TS?O$JCe_#K8
z<|EMIqkH!3`NXGhV3vDpOXKq8>Y&3EudR)i{wuqB>&ETd&3_%<W3qAEwrAg$)QFV4
zKQUcDe%03p`)`7#eP1r0zsly><HyY4?uEYH|Nl0&wx4ZxD43aDTfwLIL*01uAN}s#
z<?rSAZ-XXU+2G@%phGqe9z3X(|Eluvks~a7tG<HnKVs1lcAl2{<k_=lwR2|AUj6a^
z?D~JQi|V5`Cb1stm1g($_TI63_vbG~S{JrvUk9xn6BKMba>S*gq9WnU48s5ok%Ho4
zVO#(Ae)H|l?sm@Hn0;Mu$L`&$_f$T=x;p&FkH`I>iOa9AuP^qTtk%)jckIi{%b+`h
zKqq&^=&*sN*4yu~p)DbNb;II|8KlHp1)gHz0vC-7w>N@UTA#e%Cu?nxcgLdU%SCq&
zU*FK`ePL^(IJmhl|2J^FwI!2TTU#4+I5{&r-x=$c7w6_$|EPa+w?5|V_y6|)Zf_3O
z_$jDmZ?ux<^m^YFQ?457?1@@*)+<MUai+adO_tBX?@2dKXD81vy!!g-@o!4g?uT7j
zVe<ar+vmHN_~hGP?r#n9dj7k8{pVYip;mKC<jz}dfBp2)r(2f&>C;cYy{bBQw$=CF
z#^&bRkM&nRof`gSM!-IvpQYC3=HjQP>$j_TPEg^j{q?1B_Uzfe_@_tOf^yp0=<P}t
z7B?2KwQYU)`gM2g?lMISi-;1DNYF7b$G+cLvqoph(xsuh-}T%71Kl6+@esHE3*&hK
zqN1V(=H}Nc-n~rD&dwH`n9|wJJ@4$zo05fvg&drmE6c*7qPk|xkm!*xbaDV4$MCF?
z8L~*(x4~<vlbf5{+UL{tVvSbB*Qu(j+kZBkxNVwVELV7V_?z3?`}1Edi~?OJ20E+v
z+uPfP&(27KZW;RY<m89%-;XbFY<4*=+*RJb>Mp3?n0$<<_xYqrlR*2PL2GX=FY{$)
z0F?=EZf>?Hc+hZgZ=qzu@t^*0EWX%mxIbarjl!(seZkgcb9QaKA9B3U`8=~VUuL)L
z^0GG;Ta%Bkl(zOO1uK0FQo1EPCZ=beZS}RPxWK^1Q>VOa)r8(ZJlx*V-3@AI&#Rp4
zwX{jaldbyumH#2vlV(2CF*g^#zCPaF%Zn>0C<rv*_<sL?Ina$lDxOZ)*Tovv{3!V9
z@asS$Gw-L*SJ%hegSLKEJe?YDQ2VQ-<o&(9#~1_h^Ya;B9swPY5fC8Y)+f_B(>VRm
zwQJjsSuf(3FmQ0N`uqFe@An&1P6~YuYCmzp!^O=lY`5Ripo1q)aJ;_0UVK8(9QS^?
zg<H0S{N1r+3Cn@W3t!pW|DQ5*=FEGWI*%M>y%oKu!qCRX=E2*yYxjBoY2_9NwTwZx
zXncEnn}eTUe9okfjukH-F+he*g&#bA-2C<R^~2Y$iGkY0zt~qUUAi=4f1NF;FW%6=
za8R>z*1SiLl0b*x_}YH)(ckldDQat0>&E2cNe>UTN*E@!{1SiB+S+Pb=hMz7`$aNP
z;-2iPGFDbr(8lm%#h~7nisuZ2#HM4P54ZEL|LkjjR@9pB;^*Ua&bN||uavd+dwZks
z)v-F~D;75jJ)$8IC2Q?>_eNod6gxQj+^fHR`({!5t7PqS&=#k-s+X#^YC_spR#7D_
zYNszud;Mqm@@_pf|9LzNppMO@OP40hn$>mXN(iXaX<hb)fdO<HnX9X-(qk^rj^MBL
z=jYi*KlYiV(j4~+bkEy^lZ#f(5;K*&^*rs;63-Wxm-B~ciT?Tf_akT|?d)0K$5Nh?
zF6=7J-t*_v=@+-Qu3oSt2{in8dAa}kZ-0J#e7xFL-E-1Gok<TLF}>ZnV@JaMeYG=8
zv!_)t{C)X7H99&Pl<vJjCrnB;z;em~(B|{i;p;(dEl?>A+Ty?f8mHCL(lV&|QBd>s
zYIsv{*W}r=K`T;w<<HHxtrn~QefxeuTwLGw`*onvZ6@JKF?)Z#S`AvL`a(jbSZgX5
zzr5X%b+Nm*)D^E>_-E0S^7d78w{A7fyT5Pk$2%V%A5Tn6Yind?&$79{$d!9b#zm+3
zA5)rTpWnPu=pp{be2H$^oLd_oU+I%wp7+MQH2Jt<>;`a7foH16S9)dJOAhvdqVD27
z(82i|HW+})>?bECGR)&yJ$3qY&^4Cre6oki@7JnZEd6Kmwj#uS+O%n)lK`yB-|1L&
z<;<8pJNe6tixRd~CZMGgOO~jtiQO%x?l<Sa-s<lz$Ay&?6&*`hZvJ|=`~8*fpcg0i
zZ<dvnWwhD3d;9X`>Tlk>VOc(@eZvNWi-IZL-Q2IzudE0>aq85emBGtFx3I5TrFG->
zZO}o-21Z6gvi%($D?A^=5<93X44U-o=<h#%u$jH^?JZM=1FzTb@7tJs{Lt;&w-vT?
z+JF6cT>kOFW_AxB9~Oo?JB!)p&6`*8<%Qs_Et$=r)pp1GWI^M?bEZ5=`}^xFsFB|#
zstwNIZ*ByZs7wN_H|XqBh~8rz@^;RgIiT}R`t5#kfX+ZU+AR)h#P9idOxnQg+MkIr
zZf<NjIXNt<qTS@iK^*8V<hVT@pcDa`%whm_x)&^9m^yVT2N&0>k9w=yRxDb?1Pa^(
zjm)6^Z5Inu9$#A<ed6@#=H_PRsBJl#R((34HBy?Iny+@xkKbL!3tHcNT7Q4f&f@1u
zKR!HMq|EiP<Rok8_j}dvK|ZVDy|g9grV%v!{U@ndSXzP(J1-GYQd*Se8niM*>!KoP
z5mtwX`O~LQK|`0@^6qvyxAQGrv&N@HMR8Zz+pY-{1ipq{nW`PGq@=_ot``G3llmj*
zzA8}AdwUDdnet?r?`*Rbt5ya5zngh=m8b|;>oL<wDhqe)h;Xq{y19Al)}v=;8iTq?
zUyDIAWIKzW2ZV$y`N(z`wD|Geot<o-zrXzR^Rt9e3dgPO`TXwg?x0bfrAwDu6h2~M
z<Cj}gxOVSe+bLeEW_fosG}ivv@Yv>HpYyJS{fb!@;C%3+@9(qw;GALM!V9ieWbST!
z{72fF?`4y0`-+cCmMlqler~Q*`2o-=;D$*@I4)jH0j=c+of$7AB(xwz%k{XRo}Has
zVq)TnQ>U01zCKsAx0he+)_Vwatn}l@$`(uOK<UxL*Vom{i|f+m%b+Cy2X5VxTDNZ9
zD|^t{&)s6WF7B#XlQwPI1e)HNGe<^5RP>?!@k$lXLk|zPvo4)Hea{}7k{1^i-YT+K
zG%IFb&CYB4!w*be3Yzu|sn1CQ(JsC{UQ0n&6mKYf9R@ne^!vNJ%}bXqb^PD3X2S-7
zu&}UK$A5o&dwBKweO%Sm)eH^m*RMY|`&GxhSr&y#DxN~J%_(`HjXFF$M-DVHySh)5
z1(orCe}4xZdnhO>+B#>BjD@vz^1VHkSMP0^GiMHuv9a-wpFcUhwB+AdT-^v7Y0XC}
z+y8F3f29XrkihDIcG=}=Z!DH@m&sfbv-bPDbLY;3XV3bU@Z5ZCduAS}zgbgT3p&xa
zzP=tb^jv#wWw1JESpVY1i)_XX?_R#-6c!f#@$+Zm*;%Fqg@q4e%Ncv*Y^5ftJUr0I
z3>v7ltty!-pM0YE$kV4!K_}`J{Q8n9A}+po)he&YF_TnsZftN2uqp&?qR+g%3{>In
zt@_&3+S>ZUW7APr%~?BkEGPpV5_e@~@Wg4;!m_tdR5|&eKF`s`Wr;Q)<RlhTLD0>w
z*VaaZCI}yVdwY9=3Mc43pmzB>j`Z~O=DK3gDu8vdyV)3iJnpxjFmGO;{=OehwQ-S=
zou^KD1%C86mXws_;=VvF0d!~h@B9Dz>}r1{oSLFp@%!!e#O!Qst7$r*!%CgocpTTq
z?Y&aoK1qf1^YioT%ig}byPNmj^rm&|*4@}&|KE81#}6M4{QUg<>lBZ9;ARmxY3G8A
zcTj=<>R8?997J%xy-_%?7gX+BoIeK21;-V0H$KidfBH0cV`C#|JFAbcuj}!Nw$Al`
z>$HrFgp}QS9D;&`xVX4X*e)<0IC}Kx0=CrO-{1Fli|d0fU9hPCXA=_}`|#N_w(#)q
zFK=!Jm)InFd3!5*PO94R@n!NVJ#%w$(DZ&;nHi{PW#^Y$5WBlfLr<^GYboe_l7zH0
zHLGQy{vc?89kg{fJ3ISgVM>2@(7Xqan$l-m7OR2A%|R>S-@SYH=Z}D(pl!O0gF0v;
zV$#Mrb7Vl<^`p1vxrT*_?J9lU*3iJfBWop+zxS({n%^7_adGjBhOO0aw_XQLDuWsb
zpq)>vR$aPbQ~UCgYRUV1u?bE}S*P^k_pPZ*ewseNwhgqB<>*n?;AK9I^XJQ3mA%oh
zT4b=tTI6Myth@Ca3zsW1-~oM6&YDlqR1I8?OwhYgxaD}CvrBKMtb4VkrR5BxRIW2;
z&w@@MWMN}VdU9f-jL=$E_TTe%6g*@KTN@Sndgs=yrk_52`ZB{~4d`x+e}8|23ay~v
z;EA(lb%Bod-?Bv{EG(>`v=p=h<Ke4UT?d=l4<9+=Qj)UQ!_%|!S@NcK-mdHx)<
z=t6(r52ZD0)@&$#?zdydjt8sP?*rA&?MIHdTr_OmQTUkc*}1u=9~SF={Q8?yPp@Lz
zl`A1Ft*s9y``Zc1wsv%^h@2Gi=OrU()?lK}&K)}*JUKZTG>!;5co9_Z<mKftG`x9}
z0~#x{E`Qgue*O9fOCH_bS<Jp~-#(DLqqbx;K0Q5MSw)3~0n~f}UFUTFzWnO&^<s0T
zJb7_%Z}ksQO8@)&`|9_8mlnJ8gT_!dr=NGby)BnjUB%L}_Lm8$2C4u1Iv(U)A0Hos
zv@;ScEG!3Z-=19_q;QGJy6@YKLXYq_<{|NKEL?aG*9F_Zu~?#ACbLSvOlDDA;_;R8
zWippUt@*BsTl?Mp_j~_;>F8}a2lxN`st>yA7_{o;`*(K-2L?7?DHW@EIU%8;5C8vr
z{~xp%7IcnHiOfRKIrgA6EBE$PYG`OQEM2N9BrLozM2nGuTTI6xCr2mm&JIP3l@_4k
ztN(w_{|9YF%FN6JZA>{k+x+6DRB!06+(pW#{Hm&~Kud-$TnM-r_+?%2a=(iIf4_hH
z`F#H34I2dJT9rCEIWd8DY%)|lpIaUf5CA%!pUZDmy>mO?QBZ^B#0ig!fhq6L&9#1U
zX=(Sd@5#=oSy^47tHTnnt%+Q;_{5~%Ufx584t==jF5lVb<l=Hgr;q`>Fxq2TPfyQ<
z&FTJYqPB89KGxg3apT5cJ^61|Miv$t`uO@@T;$6AwHVZle0q91Xw0qT#RbO%t4WJz
zo9BZjr^46Axz4w%y|CP09()Syzwh<`#mmadK&y*)mAq84&^+1ewbZGo$Ou%9#_ld#
zxMBszvuDpfeEjI>;J^Sn(Ai39V$R0LSLChvuCo8;HD$5po0xYazvOVA^VfrY&b$Zv
zoR>(K$=u!WIG}dJ;{fLkkFTs<wTg?Alk>)=RPINQ9|r~nHSMeYo%HI;$`9YaxA*q;
zzUVk~XICjV=uVG<0*BYv*18@S%)7M26LgH?Oyl%`n3y$&4Ryc2<$ig8U;gp&e)p1+
zEiYDVD){%OQpUbcCVG3`(N1A?1y3P4`#K$~X>VLyT@{s-4k_51r=_JuY)<0^-IdVQ
z#RWRY9&`yy3#Tvx1E}Bk@BaVa^%{D5Vsk?NgW?l(=J@w_cO}enX1uW26c!lRxY)fP
zv^@zlAtCFo0m@zff35$2=-=PppnXlPPKs81f`WmY4>Oj4$}OdtpiLs6klO+o=Mz@<
zJM!e@WYFrXIdf$8ZESyG2|BrLUF>eqq%~+=(&IM|4mN-I{P{3s=2crm(UetGR1|bQ
z>b3Rp{fFE651%-}F?H(HMahCE#jN=PA1Cc!_`FrN-J|-Axl3=qZ2LU%G8v_}8y^dp
z+Lg&v#oZ`;_3gNPJ?NAaP~Yi8%Ehksc6QJLogQg(zXGejo&Ejp5fKubHf>^H;N;{C
z(3*PU{Q2Xc!%{OYD*gEJgTrrS{mhv&3(Csc)~?n4^XCs}H+SXdX9tfQVUae=0iCj+
zzyB{=baeE^z_07}?2!STkOb;bPny*9<x9!e3k9dA=^Cb-5ZJMEr=pgYS3%HE!zYYi
z?(MBsR#0FN6cl7=cz1XA;rsXHPfyopXE-z0S{#&@=USJ$9J|sz>)+lfGiP@8^ziUV
z7%=GX`QWs*G17CAfVlYb^&Oi6Kud&etCdVlL_o(e$hw#9*zw>d=x~hl_Wxz3PMtc#
zuGVT-`TMxX3cI#%-`-H-;^N{vzwqvKP(>s-kppr`;IXT#!#9?`4g+0u0a{x0{M_7!
zFJE$cPEzok^kRn7pU3k589qGmm7JuqQvQ1Ct1ByeCA(*V4lYUj_U7i*dsmnl;^N{!
zgIF62AG<N0T(J_=!2q3-pL=^7=*%95gxp+RGm(jBz_oSzJoazWRdP29J6^T_eRlIk
z;fu<I;|rfR%C@hl1J~N^^VrK|KnmvRs;aVr!s6Uq>%fSJ4$#8>S65aV7#e~WErF)G
z&fEPyqwr1x<U`Qedq<D5{`>bYVo$}!Uu%Mw`++uOELyynw}@eH`TKhwo}P{#9vp`b
zA6^)=5;TX)(9qt_er;WBcEI81A3uJ4)%e*s{oH~@i<q>ga>-hkwd~$)edo@d2hX0d
zsjI8cm@%WH&)aB8h}OpR^KxGqer?ITydmi**PY$v{Gp+tpfS5Cn!zl~uk=q=_rLbz
z{jznjyOr$i<$wPCdG#F6$NQ0KX=wo~LkvKNl(~v!Ma3i}CNhSHhwJIBIC!K}`09V#
z>Tfx{#-5WF1g%u?oaCs-qNt=)C0D@?&Pa>Yo?KZO47#1S?$1YeP~mXx+O;32<Nq<`
z=jZSFb}Jivd1*&gVoC~&=Oob9t}PiCncUpmO6z#)J3LGcjg1eB$JaFW+yC2f?DN&t
z;g2u-+q-6FuADb{;+&NsTA;(&Z*R*z{O<1Vz?hgGv)o$=hgvv675fygrD6A{cf7cN
zqi`NLn*O$x9PM-dQnT?ssOw<M52=?HJ@1x%ejgH-im@9X+uUC2J$*y!X|bI9`($_S
z+zGw)oQatkbTLzJcKW$FojZ0|h=_=Ac&)Z~ZsTd(xzlpeq)7n*0Sw;W-YRNpPAfy0
zDvGv0<CQj3FgFh`2-?`y)m8BHlxRq3=)rU6_@+&pwn+Kq-OKOgZL7b9@Xy}8bLYbR
z`}>+Eo9edJuzvw<rvPQdnwlEW^;$MHKLj?Xopp+dkpb<y=$G#Yt>uc{UAAcPq#n?+
zz8ytRxrBs;UEKxG9Xqz{UN?t|r_qh;AC%quGD`2Bn5Zmm$tfrp`1uH=U|XcNV$~`x
z(7jgEbfZDX_TAZEFQ1l{R`KCM<BN<ca8DexYRW|J`qP(RUHonDp7?uOfByp4ZZWBJ
zQBhIQA{H$zE%4GUFOQ<4Pft8SneYFv>-!6ypOcl4mQFr1!w?kyd-m?-eRX!KOK+=e
zyKK8u-`}=Z-LmZ~3MH%dGu|kC@iXE0!e2?p6|-XASiG_LQUj`GHa@<RdtreisL2Xi
zA!vTDf;o7(-_aR{$yu@|?(eI$2CX3q4PE+t$**)oEo;iRAph1DPWieYil<JUVo|@k
z|HKK8AHRMrir-&nIxl`tg<xS};j7)2=H=F9Z$Jw%LDi#`*W|Pl%r9Jafx3JF0Rn5*
zt~D%v=5yoLt!owTUl^I$I6T~4TwGFiSb(-Jy0~09GIi=yMLRpW+uL%TYijnquyFA`
z)hBEH;aYTl;(-Q64nDqP-TM1Dz$XTSwyzaGKlkvseEpFno|9SBRVOMbDQ&3zUH0V3
z6NjZipgS}f85t{HuibuOp)>o%j~%mg%Vd=9LPkzIzV!cX^C*8~u>>UeH~F~YC0Xe3
zo1B~+=vwRf^W|@C%Z+~ib?MTjJF360bJXE@d1Iq8=tSGf&(E$}H0(<_$aLh`u}8;x
zrJE+dnm=)(;I^EbO!f8urOwy?`RM-R_wV8f68>UKK<na|+4)RP><&La)7brWw*Nev
zPGNPw53kuAJUuyme0{TH*^)f+?(O+`rr2{5XeKZsBI1SS#F{@pUoT#^yMA?umdB(c
z`#}dfyHp*6Br&C|Ph8yGg@1p2jWVAz&%R#H%*>4K=i$m#(LO#rpc6WtJbk*dzHwpD
z%7oO^)~BbZC*RtV*(5wE!_Cd@#pUJvOiWAy0s;)6YH4D}35N}!EkgMo(r+wWRJg49
zUUtd0Z#mfK?6L?fQ3#UwV&gN*gcGz=y!aVUS9iB5+lBo5`+EQV{hj>h$H$JoJ~7$Q
z_phWJ;`i6tK07nBxt(ABmF3Jopg|?j;kZstO;weRiYwnUY*pkxJ<qb3?cu|R9)5mq
zk&%+1d-XJ?dVw178X6pmii)6t))zCX(o<4G9v6JAH!?N`_13#Sd?)~IxZpo|<o1@#
z$zk(ngH9Gw?A=pP*tqQCVt40BDl!%Y3|y^Di{1OzeNKi98hoA5*U_=!=R?S_n4oFp
z<z>F0^Z74bzMO4SURvsUe_!p#zu)h_wv;p#ojP^ukGI?J7l6jfKsofmlP4_6$;k&#
zdhmgc|Ck<MxAWNMo*tezH#RbF&%5h1->&w<IqUZsrRJ<kO1a<$-2H&q8-*PnB4sjJ
z9Az@AxUKmFI}brxdZmfS7d}@sHWmh5Ika^vXeI5T!-oy?@7c_lF(ct{8!zZ0wzu2w
z^Q0X-xH0+oggJ9~7$Wvm7}nI*X2+;}25p!)E?@5gT7vlLiKp%IDf6w%-!1T-uJ`IG
zYn$8j#G+QGiyWR$bZu>A=gpf3x=q-|)>cqjdiBOF2}e2vH*DN^a9i$eQ0DEGHcz^{
zt8_=%Td8|>zjG}tEEpIzZQAtVFuy%$Lo2A&HB~ztv`=8llqm{|iU$?izrMV`V~4}!
z*|VipJe`7qgnD{=ulBz#`tzgEc8Ri*QdS)_6TA4veSde?F#DR0PQ-=<$3CZ?p7!u|
z{{GPYnav$5>_Eo?fX<1`%*=doW#!~wKlfIDKXm>)f4`h<kbQc3di$3zCB3gZIzY7u
zs0-QN;gWb<anZ3Oki;kun4ENc<@{!L{-mp`LM>{4nRIn`2VTCtg!gOT5pn%E7Y`4P
zNs}g-*y+p3$$@6hLFeNb%&pUn+{EHNO^5NrlXWZ3S6Tn{*5BI#ngNL9|D1XH!utll
zTOYrCaY;;6yma|;U{DZ~wzhWfQdaM2I*vIxIz>fApfJ<l_k(HU#*Lt|tesER<lLvv
zpF!(o_W%339&|Xs-QDGe6(15TEG!<pxVX4UXtGQ}A*dVKc|>$3cv$Mnle>GXzt7z7
z@cza|WpIDD;|b{AW~*A6dWHNOpxutu)z!W4ji*kXTJe7G_XPnO0<yBa>gwvCk^T9#
z-y|0;TJ+)j{{OKFNlICIH$b`49MtPm5^9BH*Ih}+6_o<P65#IO+oMO1K0IrFzh&`a
zWi|hKJ)o(N`}gIwrgDA!_z`r3Vognr%W;uo7cUBSc6MrLX&suX9Uc%G%4%(G4ccDT
zx2$~O!iAuNzM<s^=%hDcb-yb++$O2am^l-)tfwjHl<@mn_fpHsPb$;&V!48YgQrZJ
z7H0ka+FI$n`}=eiW>&nuw)XIwo10hj&S!R5?l<?tz3TU%(?~dYd0Uq*RR#4n_WymG
z&orqkFfOide%&w6y)Mg8N2$2DxB|k$+O)&hh5WwN+0)Z9d$u%aS4IB5pKRS?x`!Sd
zYzCdgsHgYi|I+2lAK%!R%)!em3hvH(LMML&O)Eh=h-Vt7XW819zMA6r@6eQ0pFezP
zQ1N_qTx+V=<HB5?Qf50_&@mEcW*9m@-nnFn3TWLUx0ud>Et!`YY$^{Q16>mT-~eND
zZ7{!}ZTuUHCA{CHLH%rS4!@Of9MrZEn5Y4g0C&LqzJcb+7dp2qsj9NNy1Ig<n*RN|
zzTatO$fNJ~>)SVPHm>^iM$>AU0O<1AuU}pF*ZoaMOl(wiZp)YhtyDo<HKqjY_wn^j
z%*x_o08K6E=;|h>rKwp={Sz4#_2|{r)!>D^8dcX<hwHD6+y38Yl1fTinpu$2Pb0Is
zZyl#VJ@Q?p*|tk3PXF`NfSD1t7T{0Kl&Mp%R>g&dwf*^1^Y!t%*xg~$hw|1H6&D*8
zJ@H6MPhadi+YB_zbZcvN`=dumD?+qNUR*esu;0J9(D5*+Stuwd2p)yHB*+fg*t+86
z=Z_x`-rAb|@aa?5{QUgh%|CurxVXC~Ut1H|bZO!o@Hx_Y`ugq}85&;R-k|mX=m-@C
z(6ZBBY4b&;udhXHOls{|p`wgyTJ89{*xg?w`#WYCmdRXV`^^igt-!@ZE~K^s7rvL+
zz}1+0^>n@1Lz_}hF9^`M!aPA#RFnZ!>9Mf0C;$BPbcR*wsuMGuKuaw6`1oF2UmxH5
z9CYE#Bvo&oG={(DtG>KYv~rqU@cNqWlc!G)9z4jX8@)|L*8P1OuXI>0!{0MAjX{eT
z;%Yv+etlh$mZk<;we0Th4q5@{67q1)+_{3{;_VYAOvp-Kx^!trXXn8VL1h*d;qxa?
za;^?v-`3yHA6NBKwRbaU9P#WdQz>pIBO@cweU7!qML^xQpFe+kczPZLHF~tQwcp&?
zDXgcb_v6*-^&jq*-&Zs=3@q_c+_9sfqoczGk<Pot_1%(^l+=7?G&C}^uc}Y1dU%Kx
zw8^>l_qU^yRJ~c2t5{Ziy&7&RcYdZZyKdALhpH;8sI6H`>;CE2{{)}#xCb=RR`No?
ztygO4`xPq6*REaLQTuz_vEt+X^6fKcO0x0EtoT^dEv9>6kt=uYG37;RJ)k0}&KbQ3
zLN1#w&YL-N=CA+tpi_r7rFw&oDz44T&Fx(szP_tVJ-fBFmF@3V&_y0=A~&;vu5m3a
zEZlm~)^pN?xpQ?j=0<${_>qH~+c_*ui~+PW!)vL~&!0a*SMQ1GMzMgd5!95vKTS8<
zMDG2~&7egjM-Mi$8>XF+=-u4R&VT6seR=QcdRNn3Zi1>*$fPlEeSJNHe^p^#o*w9$
z&fDAbm2GTd3cL)%*2nSs`}>1B)$iWDD<~*nV2IgS#0t7KYqnYLhp*S;nJbJ!=FFJE
z5g#8vapG4sLqkFNnh%UIv9W;>5gZJVzTDA2KR-{LIkWTT=Je$E_x3hTekCt1E+8m4
z(Zg*KGq{f}Xd1G+>@8?yyp>yg(V|66paB<9e>N}>bO-gHU$57Lt{HtXL&X_1xSNo$
z;MnY{c}B*@&It(#TjP}`JuECL0$ok{?*4xM2PgIOK|2r(laH-<Kj%XTWWvqmh{~e0
z4$%Aqcn%s;L5M>ezMz@|Hp3bB{@z|t>G$=qV>8>s`Tzf@YiVl-hK04|-rn}GRXk2$
zM!<g1un%OOo{6FC?X9JCf1cZemc4_vEd2ZXo7+#vt*FQdbRKE#?{A<p)=!)~**JHu
z?5?u6UD?;y9lUerPQv?Zd&=L(f%*=?%l$yxVMDa0B6rAH)kM^7Y-HqXzXWc5Sj+%A
zNTHy>0CWkU!psUiJ-r*-^X2tocP)`~m~UHc1}aV;Jv`igV|)JmgZE_XKwX>icQT+2
zym#)z9653XboJ!UojYe(7OS0`XS@2}9niQI=oaKnsi#?%U+cegDG0PqjN!sEUulm?
zE!E%Otvnwa8w<L3Jn&;n)ZQx7Q>RZGCLCa>sH#dj)+0H?FqzH9*4D7#frCxemlFx#
z7!7<3+t|M%GUM(p(`h=9hjzOM?42@YN=D9}|Nfx1VrJ$_IpK*ix=~v=pc5LPo56#Z
z`#DZhIWymW|E;Z{8?A#@icFZ)F-sdXnEOrok{GD@c%;wy>rwDDw4&0)8-*+OLDml3
znr)EC6t+ID7c?sXn#KeT+k^UZZ*OmJSMk)))C3KLxE{YUd&v@&udgSmc;48WEnfEa
zR_Noc`g^|!U0V~m_<Y4CK|w)AYisKz%a=dCxY&IIWS{+l5Ur1|*Y7`c`ZV|H>H6Zb
z!JzxydL#^)JUu-%G&Bx8I@)b|E;c4+L*ijJ!-p)pYknG8mA(pjy>sbORnR2DahFd<
zSywbtQd1vZSs8rd)G4RXP|-JU--1@zOGrw7vlZE0{=TpD^|j7EMeDn}%a8X;n=>$|
zsi}dc6E9u944N(g4Y{WEcF*QHc=;$R=z^_>hubGkn#9CV@vv1Kw9BIA*UROvSgrlR
zQ6Olm53Y$o)3Q&I=6tv3>00rfypz3tZyV_N96vw5t7iL;9X<N+_4@tm3ZqRWr~Ui;
z`|*p5i#xiyoc#Rw=FFW7YLWBE*+e|v_2fy)jF~eJo<Hv&5TulK4jk^Fl>;(LlbFFX
zcc29~?Hx}VWZSnuV(8+%J(Zsg^6%Mvef;t9ab-(O$=zjdo17LN*ircS!ONGL1`F$2
z+u9x-=C^P0TG|9UDC_UHXwZp>pk)^cX=!O2oNF0Cb9JCKm$|pMxdsLbGCcVB_&7sD
z;^8*X_Vb4iAA;5?O9ppvi|c`A&bH2rj*eE=*Z1%5d~*2SJvl=|Lr@|;bLNc6IWI3S
z&~>HO*4B<MpEx4TUS}~)@lyTv=4Nw82L}VFfrD+hN~FD;+vF^)(|WVRv!kP9mc8fF
zpp`D|3Q8c5wc^K*ik8+^MQv?vh6xiUFf0w~{PU*<v@Eh)Ot-1OzyHA$6?5~vI}JfA
zkAT*>F7+0N^foqcF8ut=_r~qpps?StaiidzDIFa=;7N<$yn=$JtZyv9(;F^VL?FW!
z0u$|GcbD-_n>Ot#TPi1Ldt2C=h{l=5=}t?7KrPW5dn%2Yn3xzCK!cPX9voiY-mL0Z
zK}A;5zdt``nCHuJad9PNW_BJq;-WFti{Sw1I0<R#)%&tHDt2~vACAu7+nRTG*TcKz
z_e1yhrKhGUs;RM==iNEbZ~reM_hqx<&YGV_MMXscAt5cZ+`|6+{mZ)K(t42nlT<)k
zyxiQ}W>^-d&6QX76f(=Xv7o)=)2H9>_dmWKU*Fo_&kq`G0WCMawkEQpySv$G;ej6?
zA8#ys8?`0-x?f4iBt~WB#Z|HTo|CF}@(2nFUgd{3sBZ5r*RQFm0Ufn`aj|>y$45t{
z_J5GFud@;1Vtw@ZF{`?&rIxn#;Wl3Bf)5WIV|JJEGF$-7E6G}m8K<3TSh;fLgBBN;
zlogOUBNrEybjYZjlF}q&a5I%J@bRiOYh1#@#N=!$8ur!xK6K|!Oo_@QMRj#`P^tIy
z)KmsgQ({s0`nVfAi`5xGmwP`yH`m$EukXYRC&J?b9nI|gpi@!B^<pkm?2F%D_v2Bw
zzCqcW2*;C0c2#}VTIM&mYs;1`Qtam$4@<Ib-MF!F;zYqsn>QyWB{4}$OM6WEa;ATx
z3g^z9JFC1rijEv*Exr8oce~TVj20Ca7nig0@Su`5O5r$j_UyzdQ$ijed%9wUM$U~5
zjrMcYm6R5#waT`GlCN@^jFOU4R^JWK9yhCk2MpWt@AD-mC$q4zftux@oha?{bsf>$
z^B5UGb9p<9pFjG1-d=o8*qq|$=Rni#ux@8)=+Z(xPoYhlH?uAkR##GDnr)tc?EU`#
zAk#ntLwC#Xx9;6*3%;inbShdz#Eb_^eodb_lQTU%{l=|ZpnmVehYvw16STNI@i5zp
z5UoGoZs%{<x>Zy*bj9oI>$7zxZ3JZvk2RpPCv<gr=hy$UymR+%Vq#+8<5K_seS%k)
zELp;`Y}vA}`!1IjA2`bD;^LyBehl8cxYEikz9H-Cs;Kj8*RGv7efsj_;Jzp?Xol9s
z<*cAJpP-<isrwrX7neseRwW#dkN3BCc7g__Kvy#6+}k60dAa{_Z~eV2_V)H6VPTIx
zJUkq+Ek_b`HHf5fT1Vg7@{=b|R{Z^XJuxwnQC(dfbYPm-QlZq;RM2FojI1oEQ+&~|
z6}0c#!=vNZxfPd}`8GQ(bbyStIypHRBpzZpsCo3o-QDIvK|!DsmOgwaSP`Q2b?zfu
z8=DPfZ=;&!?bzq>bW8oZ@N@psWy?S*34D~G#+4%=>j(}c^}hS{_4WB0&@J{${9%=Z
z+W9kQcvMwYx6T7?FiJk&SLNg4d-CDocF<suvbs9EtE+3k$`GmNZM&Y%?dUiHS|GOZ
zzJTDwIU7NPWrZCb9-#Ul95e&FJ?SXdm)F<%kN3$s|Ni#&<G<hUl{GXtKx<$2)&9Ox
z&a-ySnwHI*jY0Q`HOn~kcXTw&ohu7k0rTRbaztcg;=v}?0IjJ%zFv=i`1C1gxURcT
zv!%1sbL;h&n!(FJOClH=R;<wY^5P=%)TvXI9&tW@@uK6%5f{+%m{U`=SFBpqG<UA7
zj;^k&yD-SJp!_vq%9NJf<?ogB^!VPrdk31ey0p|AbWS9wcT(cB_w|K^%vL2Y6s+3T
z{QY)2-^0txDK1W~sj2C~g9i=m{PIfL+T7p1eapDJYwL@Ss_FCQ@%j7vgANbO-}h53
zDLMIS`dq8hL!jl<Z@1r<I>KOO8@)bm@2fq^f9fZxfCdVCr*w35tf+)8NE0-zoHuV?
zM{n;@&{)9SyZdUTrOoq>{P_5oRYiGc^v)tx(6D7hbTnu=8|bW-7alGyE?J;O8{edr
zlqOl1$y{OuCD)U(*5EZsFMfiKXgYN05a=j0h6Bgt>w7>OfP$C#T$J!LGBa~?a9{wn
z8nsphEcc&(Y?7+?g>AXfBBG*<44}g{89?WoHZ?T~$jR~P>+4T6Onq%H-XhV37}wsg
zVFPFjpvgJVl_xuPSh%>jaCm9>xw*03xqCM-Fc8#D2OV(%>Qv6-IjyFu`taV~YS6LK
z50?BA7ZGV$3tp2f!PV+iA``iC#R>-p2Zl$F9)ag@g!b&&^Web)h6gA2Yd<?Tx0{t)
zjKgnL{paWBk9X_u>-h4e1T^xdrsnpz=E;ePQqC{iI=Z>%NtoqCY-RjnoPO@XrKR2#
zACHP(++CgzYAC_Fp3O0APA)EA_7p&7z&mE`S+PO`v|Q=L1jP@ZKQ}`z@c~^R%PVc>
zurw&~;v&~Y$&+|$|9-s=Ixe%|0fUc^kIQjIC8bLTKx<?6D=I1N1SS3rj|BuL-T^Of
zD(slozq|ZB=+M-^H%^`6VlbKa`*UPu<ji}UPIhkGXn1Q&CNl%5hW7FCnJ|6&a=Y!D
zHy>W=J>BJ~^313`6^1f0G8fjz@0U8SAG4!D)q9%66Najc3=L4pJ#QXgtJA`N_dZ|Q
zQTTX6@^L=Lmq%V*UoT(x>!tdhPp7oer!13PU0gt$4-d^U&3^FmC8xW)``4K(S89T0
zV&&!YCosQI_n&v<(o*lltgNm}mo8;J2VIr%_V#vG72*DFZj;=bn_M4%oM&4N+IuKt
zQz4LitmmSIb;SpTKY#y%t_G@gQ&CdN3hQxUhqZV>bF-?dtf0M96%`gCTB4x7<5KVG
z;N22+e=Krxb6t<CNNQ<mfi778u}n@$X_6`^^@7?pu+-bp@uUybDeH6o^5@S_y&3;2
z-F>PK9X!Yw85zkiuci-l0mR+i<*Uzse}BLK++6GKE_dIM#6-oYEg6bdZ33X%Lz|kL
z6LWK8AAg@KXIu5)Sg$nGq)zj~M=qc;@%j1r$KTxC3|avE<HrwBeGS^_{(rsVt!=r|
zpj0m-6O)_C$nfRuZSk8oZ!%5lOwalAraJrHp32J!?>_vU|8LKZ2ak?+2doTvwb@=@
z&miRC!-qd!Ebd>$JD<5>`gHN8=4Q}6N{lB#bt*gbAi9oOtnTjaDr#zrR;=I%Ul-#D
zYV^N(laQIIX(e^?#)XB>6KBrUv|<w!3|tHD$K-c(tk8r`QYkH3)*#ysn!kGS^XK31
z_X~f0$z*USEHq?L(AMUDdwcu!9q(RUU0rovO+5K{-_d7hXM;}j1x<#Xn`2q={cici
z)#3UK4rOI#({!WNEL2ZI$I#c*?a98b7qhcy>8(=G0WF|8(l77t$M?T{0&1e4muWkD
z{=E4ORbx(0&PB>6uFbVBHz;^;AnJT?Z*O2w(4ylmpFoGr?$}|`($W%Qt*xu;>f^)X
z)+3>)FtegQE+!x#AmHtu{QLWE>?~g1kn*YE=cm+?S65bEEB5yGj@efe*$=wnW|lZ~
z)m-4@u(-HB-RNx(p3kp$D=Ra5cYlAsS?;X^2M;o?-~Z3*&)>hiWw(v4=HA^^`r*^3
zrpc3q|NQ;y3d)c{plpbv4m$5&QDJfD@L|(=+<biN%I114HM(KFq`kczv=E7_m5IS1
z_m+u<2-lILM;#XiD5$6$S@6!|Pf22<S>C-pH#<C^sB3C+f`-T$JSMe(4ynApF4i>e
z_a$$AP?P6ZkGiz}{y#>1vQ{CFzt1|}FaNk*zV5(=#KSBq!ud~5OkAXVVp?zSS!4FZ
z%a<-ac<^AsahFe^A=!$GiUYTAN8jxQ<#f<l2r)Z_w&&kp_bn=41GE?cbU25waI>Uw
z+JQ4?d>*e^vV_IZ&~U@%&B9aqKuh;0hiFapD&YWiHI$TM=h)ZF<?s2(23k`%)vLAa
z?X81%?#S@V**Fvy8mf4L>OfGJW?${^u0C%glY|2dB4T2XuC0wWFgFJ+o%tpH&fjxV
z%jWd+TwWe7E^QsM?NUvD+d4X)bb(l)1|p30;%7&1@7nLjeP)}j6`W*}8yFY}8mrLK
z)^>Hj$gQlbymq>vO>E4EA0HpP`Kj{r%iFnRW@?6LiLP0*=EK|V_d%C^NnQ7t1Uh4E
zOV(Ad0I!eV-rwiX&(8;qJ$`y}vY@>DIKTZL25oI^&<Y$&OG!>n&JQ0x2*^%NQBhK2
z0-abOBrKempU>~@?F|}h1y!GYeaCtvjW?9M3~Fg>>*~{TadKixJ3Fg&&K#NE=efDL
z8#6DfX-xHUJb9$3prB#>dVNqIsi}!6A}UJB&@k}tPtb|4JByze{QFaR(DNv0_Xl#n
zN52r%Rrm4X0d3rsum7|0R<@*|pkQV@Gi1-p6&2fx4-9{Qe|L|IlRI?yu%LuQN8a6C
zE6?ZO+0j`4=dt{cKcCNET<R?j8g5)0y<Kd^j3*}!A9h|HucfZ4`ce^ey|Fc)sSLOz
z6tw0u6#>`iFxE-WkPs0iB_*D;6SKOxw-mp<Wf~C`6}Ee^jxFe>;+vb(AOHLN`;{vz
z`0y0a=s)NdT;W&8UtC<Q=qUtRH`(gccyY1&^`C~5R6wWyRC%cDKYjWXbk}U%&!^&F
z-rtu8js1X*dW?wZ$iBWV@yrav8{6~aw=Q*Qb6FaMb+n?hPmM=h{L0%02b(##xevE;
zi<``Qe|^3Dz8{acL93DiK>LE0^~1vmbg;<g^z+9iD!b3ysr%!_#l@geO3+9Rzugaq
zdPY!rP;#ITbU!Fc3;a`fU|^%Lx?jSB1C1Hi*Uf!lu_-Ns`Gw2*(|><|FMM%9F=l6x
ztF6xKr%zJ@?ib&=b4S5bXwsxf2{}1y>SCrpKHmRYaqgcLAzDX{9ZLeO)pouHYO39<
zd@kE8w`JL^!otRH>*DwKWnW*%$WZm=1*5dI^g)nYX4%2ZrZ2x<uLsSe+EfIr&SrdY
zVWD%cY&WPG=LqUAb*!)iO))7gde$M^-r)g0f(^8iMNyH_YiUr4Oypw*tE<oM>?{T?
zBLl5hee@_PBs4U0j`yUNH*azrUmo%F_I7@MZ|}v8$;YM6b8~Zp4h9Yn54TlU&bp-+
zzprNwc**y|Wr6DT_4SM^k34?Fq@<)IbTpy_a^?o43;?Cfu<Ke=y=wk`z1};gW7ejw
zF0Pc6lq)|@2Qh#qj~hZ<Tv9qf3r-S2?H5bX#4EV}_oM}~1Z>f<qrXc8U+P&}N`eYq
z9UYwqPoA_Gr=N3J8M0{28Xk4OISq>!E3@&-=~yijc=ztzkLULPBVQZjI5{!>`TKY0
zm4$3CU%s>`dn4iG?Ck1(u^Y5p_U>I-Jv}|}HM$m?O257e^_goWnwgoobzhnHq?8TJ
zFD9uxoLheHp!NGb%2r)EvHR;}<7+;$LbrS!IePTq-Mg|sfBpnrxdiGGJ2ta*_IbLv
zTv36pXY81@<j^6fl6Q9^S7)zXyEZT);>L;26`HG7tvdAQ=jV-icde#On|7^AwqDW0
z#pM@h*7<0ivx`g7kv?bMqoDK#V=a-Nq|(`^aOUOZ<y-fCdv<nq?~ImNt2#P3Zrr@7
zXlpCmFJ}uHn-bHB01fEG*Z&obi;IicSF`iQ45uqw?=0H0M~17_$v<<}G-dZb1tq0J
z32Yap>&0?;PD)5gVR3hN-?4M&%KtZR-00|2mo`p6cLa1A!PDvSphcBpVq%MwIgcJ?
zy><G;iH6;~t+lkY3{p-Aq@<*PmRB)cSQ)GiI`tjimIkd#6NYv1J+<`p+dDfu!>&t7
zOM?b1LD9cxsrU4xr>8)>K$>RHmIhtKQ1i2BOa6Vi*VooIt9XKDlwQnmaY=EwQMh8^
zjr@)dk3KL9)Qf|$z8s$LzTw@ICriFE?DJY`^dhl#)lJZCktrvIKntc_U0oUe?UhKq
zu^|z3a!o~r#hyKTT#j9t{rdWPWpnfJzZTls+?kn~SJ(Z1+;6|3@Uh#T4~Mva^|%{N
zojbSp%9Rk%;>*m;%!vJUdw0DqeSa@DSz&Md{<=kvxhBt=)wN-RLCvR=>WdbiU=kP4
z&^Iv=dG_oX=rmQQg$+}uPCfP$-W&!sxDXlk>+kpbv$t;i4Qd&AIQs_r`0(7T`RofC
zkYZ(JWoS6q%<jB01bSi6!HbLCKi<k-&*|so;?mXvs`Iedek(qr%q%*&xVv}vIrz@O
z+qS>F8?-~vdzwxoc!%c1i4!||de(rNB25z~3SL_uudkqb()av4+l!mi{XzEu9GJ|?
z3R*Pm>FJo2r3G4-n0tGh<0KVO#DP}!?=D~e;L5M-3!T|P>vBtYZa#R#^!D$k)B2#3
za@VX~d-eaiUz_D%ZC}tp20y%auWe%^^YG!r(zxTkcSFE&WMU%1aA8xbH-kfDq$C4q
zvDFNtR4&j-3`@PIbDajY2S976aI^<j6yAj|x()a*Yix3PnXj;H<17nycJ`FiR7M6B
zPta<R4b|WCSXfvX7{0x~pC7<22U<36SNjXJ9_jvldC(NmojZ3-)=gC5TpPXp7--+o
zy4c-ZUS37lK<9bOT8kwg?_*^M2?=>{pphALAh_Qgi$-R4J`O((w}1cv(8BNs4-zy)
zxGom9JbuLV*0%1C#M<cX>%Q99+smt|sa1gnIj$gje=2#emOWpXe7p}di_37}&K()h
zn6jT=-!W6r7Qsb=f)g8)jxTIW0vD5D7O16Z31wx;KqlRS`Om7Us5q<)0WDet4Qs%*
z^r!}2294u^28vEk({0|k(Gaxur~H1cIOuwW4^Q~^o}Q*FJSV7LMppLWix(UW8k(A*
z&Dw9?ykS|sXqkqxGV{unD?w{2yu7$JZQi^vK*ONoLjsSyT}+9M;;*l-+vnH);#|My
z6BlTmz`MJ<uUmAyd;3;bVQxiCOu+8x@pY2ze6mgj1qE9-qqItum6WpNRHk|@6_SPA
zgVo{D^6~L;(1bSVG9L!e3P#WxxTNIdz|hdvmBGswWnW(hI!+BV4&C8l{l?tI#pR03
z#>WDJf`P?HK>f70cXx~1+1V8o79M<YaWSZQ3tNf!>AT;;00ld{xPqWX%N8zL#Pt2$
zUFUW_Sp`oahJ@48bRi?YpcSQ{S=qe1yEy&47QqMBJB8K#9(;U!ymy9&9cWnt=qkb5
z=dZSGF%c0F0j;DhC@gGTy;?gaHWoC0GGo@Pu0HLai4z0YrcY9FTpHv!Nu~Mcu9cp-
z-P~+^G93>Ow?78m&?y_(0Xiz+_HAj<4OTXlMtAPs{dkz){=lhIT!Dds9)3}Jd?#UR
z0sKHmNZ8oexVWn-DP>K9E#`4y%RWEP7BqAH?d@&Qvi_J|C7ht`FoA)BAzGq3IyxKb
z|JPYqTX*+)xwyD25e1FaC_zS7A+3d~e{DRHOvS~;Dypgr7c5|yHf@>|^NYa1z#AJ9
znTv{xS=Cju<Q6Sjv?1f7Qb<@>SDzASAbQc_#S<q_UR?M0pRwnpf*&6e9bbNV9eMb$
zso@gGq~PG-kdP4YxizJwq5N~dzr5^TViIXt^rR!~dasP-riqhJFpG;{@%QoJNjpEU
z_xJbrtEY=HH0<1I30i-|!p6qs=i%aVr36;3cD(TK>h7L6XAV!R6KL6OL`1}jdJSJt
z0uTZ9w;%}sG}J6;%@=rh#;jSO<wrA2v%`9sU(7bkJp>vt-n7Z+pl9c-_7y8MTwGiv
z&M17GpL=^7FKD=P;zYr!udi6Sxx1y-Ti5;BF>i9`!qe9qzysKyl2cNa6i&|y4-e;&
zx05k5Gh4KHVozbA<KMgc>*Yb4OQDN$s;jF(hpohdR;3CG3YuoZM|lNLdhRZJ`{9^$
z{)3B)-9eExJ-)8<^mP61K37nr7-K|AmV~jf@suf3u2jvNJh{0~*7}v9prC2Epr9bi
z{-YM-DTzg~A|fIRy1KlOe0ua)uXJEsTwmVZU70*f_@zu%+$*27{Ml-7i-2j_vSkLw
z#?G&=txe3!)3chUvvldwh2`(>y|}Sa`Olv}tLBP}i76>7Gp}2>j_DG}6SdF+TS=+;
z^NWkhZ*Fd8zj^Z}Xyon3$Hy19W`{F4WM*oDVhyxM7<97Fo40RSm#Zo%DXo$Q^&+5y
z*N~iQD(CO-4{H5_R-T^&T_6uy==SHwN2W=FfyKp-kMW+FYd!t&^AL4zZtfmwb3X9-
zoS@S7%F5tZ3%{&bp#j<;Q~LUvgjI<K==i=9Cp-?Wl)jIze<3F>o^k%}U0Ki-;1A!w
zkAGYVX(N98@iEy}9b66}a?{giXJ>!-@BuVR5uzo^aNx=nk?L=69J|GIAH09x4?0`r
z#f60to6~q}YHL~5)s&Q!s?0EBFD5WBu%N8$*aSuA2hX1`mkY73`l4Z$bAw^3SF3Bc
z7^u;B*5UuZzlE=_>0UHUSs1=PZi33nIMB?Lk+HF~=EOZSXUqUy$$9SFxf#akd<+Ta
z=h;T=s{yUCo-k)ljsWwErAwDiQ1QImIp1!X`i>nA)&Be2vOa&w`vgi)(w?E$SL+Ib
zL7?%cce~#wot~x(n#Z_v_io|WSD`L$ZinvNk@@-aC+L{4O{u3py!wCq-dy(Z*n5Bf
z*VmqFoWSaPLv+#!At@EcMIKIO)6SIK$XgxYz#|}*oy2@E^u_fk7LhedJXSjQ7MO=F
zn87nsNb`gebE=_byKYjcmzt13qQJWZkBC{53V7z<m;aX{#mu4g+)BODF74CtpE1{G
zR{E(Q^G~md5C8vfSui65LmuaQa|VV5ijQR385m4l_B>`NzxVKP``6v~|N8ANd%Mbb
z0%)+{@A?0K`rqyUU)NmP@ZP%Q#Rc8>wa@34f4LT&Z+a>^)&AED<z7i+x7XL#hdVhn
zy_8vetXDcbzu?DYf4jiK!i{wwyW=&itfD4;`T2bQ>k|`|yE;1qV`Ao9TN9bAblsx=
z_~K@E{#6?`1n5oo&f6X>Dk{1uH=2==@zvek+hg>mzx4Uh_?}Pi#_sa<I;XQj>bw2t
zS}mQd?(a1zC@AR5qi+3I)A#>L-CO(o{QT>CDnFMzJ0mG;TXp63Oa=xM4xR<f3=9km
zQd2*CDBzW~3i<zg|NrW@k#%+Z+<K*!CLV6fJlw`xWFf=G4GIl@^w78$92vQCv3vik
zS65fRy0dfhtu2|!R-7NW`Pv^(%U9f%yZa)KZJ&hUqI;Xq+y9SIRaJd;bMtZ~W#!j*
zH)Kan`}Fzq-l;E)&GPQ7=;`5k`t)h$g$0hK*S6)|UG?Ql$=|2?^%oEG+vlvfu>0J6
zd;RIBOLHIWS+T;y)YNoSZggT|qL+_Ph?iGaP*9MFy!`sKv$JOUee?YN?d@fE`PwDV
z=T)C8=@OKQ3AjGTve+d3+#LBo->2r@F0zn`+E=r4Ud<;@{i}=&7dDs}%7TJ`p}~CW
z)Tt};@9!&}SNpy4)02~b+-(^c4!r+R$IQSWrF5^5fx*G~h&5k9`q{bG;mU430XaEq
zK(`&))&9B?X<zeW!>7-mO{>4<IJY*ukKS3d^d-yuk_QJGU-MaQ10Bx&^r@D<{`&1@
ztDFDuo?R2U`OBBf{@11LrY})+Zqu-~jy6s|mt(^GVr|scNnhS7<hZ!BwDHT=<vy@6
zGuw9Y-@H5P_W%F;ewJ-@*<wkD=MS1@OIsE#*;V>l?e?~*^X9G73|^+8s=D-?-04js
zLPCq!<tiNB-rjB=!o|?=KbZmS!wV~}T)U=aV6frb=J$5(ZEdqWm>3v-cvkFZWMJSG
zd~X3w=sPyYRlQVob#>J=GyAsdHK=$pO+P2YcA;@L=!6Q8uU=izyv$km_{2ozth>9u
z@?O8aC3CT|dtb%I6KmG2(OJ4|nU<=mtDvCZvf>Bo7CRn1OG-)-5f)bVT(xS|r2~!3
zS9cbt9}Z<;F!6yUzq$JR{{*%3$?p30^H3}Iq$QUw1+})eUcLSQK{J2VT3!Z*2ge`$
zWrJoxhK9C|a+w2jy1KYnSy*PAV`yMo>pfjBYHQY1P^_}DvtN%~y=v8^RiUe;t}b}7
zDfP6E`T_pJf`e<TA9bqxs53BJSP;1__x3VnaJ+vIYd>6gH#i~p_PXzXcBgOMy7k^E
zW(I~GxqI$2K&)b5xFGPckNM9Z&{17)@9mAgwB39`zl5QaZS}V`+u#5B`T5l8)4}b0
zvLz1=FzSahWn}oxx2wHedU}(Hgv1Il-KdI{C(55ZfBt&oaXFAOlgvvhuCA`0zrJml
z8@f8|<?8kOg5u)l)%|@PFRf>~e$5&m(5Usdx3{NGo0evEeEHr_r?h9;R-3&)wqxC;
zOF?U6b_T`Qd~DUy*8cj}(DL-AExEVNoJ$!PewgPuu!H<$qNN?a&SWkF1H*^SkI=&H
z!Sn6e*Y!Yc$V=M~yMh)o->d)s_w~EC_xA3drWgC_tPKNiNJYhuQvRtw_dR%!@b&%u
z_|0i&gPfe2#7~|1{dIl)TJUJpkHhjN<?rrTWpCWL5tO0Y_++zIocmrdUnNhRUHr<_
z*|S%33ag!XSg<1d`nujv5BM1v-l;&{2XZ46KPU$+`>Fr``~Iff=-k`eu14qY4SgRL
zdwP?IjLez?2OONIGDyu5)eg(Jxhd7E@KK9g{hyCk+iTXx?hc!4ReI^i$H%2#UIadU
z_H5OvRbIEZ=ZEjF`^z)E`ufV?<t2}faC%;<{eE}(hYtmZUH2_rv&QH9z3TO4Z*E-F
zVDDV+JG<<3HNT9-g1yz>i<o!)*!y$eiWM5IZEabnr|D*0UpM!q3<HCd3^qqMH8qKd
zh^Tm4)&1FVYfI+h2M-bshcZa*Dt>-$<*r>(pj%%~Pt$$922@mNYHIE(dfEl*Uhn<!
zs2fylgL2s0J3B82Y?OTX@FCCK$8BP|Q6<s8bx-edR{fA3U;B0HGXMGKK3Fm^ly@91
zfrb@=`XloFZn^y7=L~z2Zf;7g`gBtLHSc`ypx4*dew}^)k6Zq}pUYHM`p!11deo^N
z5)$&{txvMwT&txkgO_Wmsk!Ce-WKZU*r>8{&z_je%X}}}|NF>)xOJbRiAe}(skDzz
z&r1<y8@cnje`9tQ9W61c0bS|@sy8l6GBB7#+-cxLxCG2P@V@rj&Ge{UB`f)4t(I_$
z>%Dk&b#>`A-P4ygCLiay%9x>X>h$T**x1^`Uthh-nmT=Y{O>#aYJXSN_e-ssG)ZXb
zvSp_pe_Y`|-%d+YbK>#G6TiGI__r>0cge>`u77`?uQ!W%RSUXM%*pA{*7J>xjk63A
zn+_^%p5wRtCCmORH~95_>}%x~&pI>1P|7SPVs8CD28ILYn;9{JtuFWbySq|06&paM
zcDr1a$NZX4otG|M3W<$fySMr~C}{Rpe>a=Uxqz|a#lrS2DJO+&f4x}z>fYY!xmypn
z^Jl-jwDi^G<>$AigKDx13!Aqa_g1{y`TWYB%Hp@TxBL4o56->4ZS7{eoErvzzpk%0
z4M`76N?NpN(IS(&KNY>Q)?st4%gyGp*dI8^TG|V)7R7X<G&D6mL7UA|Qd0IF=G8eJ
zR9CleyAUHoMu5)kZMl~P!6A%9d`SNK`nvzqr%!Kf&!4|8X6K@9xwo^9_sM#Bdtd(d
z_qS=v34y0io@AVuptvlU@yAZk=(?0e!2;0I$17JtK;_P)J~`V}O-)R9ORvY?+L}H6
z(W6J8AZTe}0W|?WKRat2Q}-N{4W6Bu`K$i_`~NTR>@3c@yzK1O{YNKlNjl19`}@u2
zU)T5lOWkqhcTsWi)X9?<gN`-awk@po_qVG*K0Y?B`jW9V=jNr7dEupRZ-q`vy?d=(
z=k%rL^Xu!{yK1H%e)!-)(|-Xuxqpl6%KhfqRJM09Fl5}=!3eIWko?*ZZ(Z_Y!m~3o
z7w>+*FM8_Ksgsu6x)tRKDvUO5+GLV_O^59Q<DZnm!opu~HlH`izh{$sdz)`-YwM&X
zCr)^zrlr05`FwtOO3IQY`T5%azFhYAeO48ko4eM@$tiC~TwL6`WxlhkHl8S7vV6I=
zt!?bnr%$7Hm#qbPY3|&$>GLYxn%ViU?I?WwWp(^tFGfbjWx?-vw6wHTIUfNfov!Zg
zuif!~oGxCxIBCgw`~NZSeKLVQK0S{fJ@Q#11v&{vQ(fI%fB&CNaaAvuy44mms?4=2
zJypWQz|hNO4rzHIdG<qgVq#*{hJ;2VW8>7@+nAV{zrNf3KI_emjg$86E&X1;|M%Q~
zf8W<j>#;VpX`7mc>PBt3aI9DQ_1%WJ=;+n#@-+e9?^Uk{ond%+r5)&I>+5-L`ntNI
z85t|w`eau2^zbZQvSh}&&$D`^&9#)3ohvIVrA#sc=5AdZy<N-JHn#rf>G&@n4)aTE
znY_2>*8{DLWnyBIx_gk7f#JY!nPuRXB9eO<9xU(Z>I%xtT&Z$$lTPXDYre0quiw9I
zU*+etyT#{imwjSb5Lof==ku+VpVMsrez^?F++W^4c=PV=Zqten38LcSuYW$DZyxi~
z8dRD>O8cAJbWd;El6aU6RPEIM`T}YnzjRp-Iw)#h-LIEbho4U}NjV{qnx3Bh?95EI
zQ#J0dudOvLeHF6vZr;>s(_XcT#|3zLcFI-1F$B5c)R{9OiHQqe`mDFE{q@DS{@fhP
z#iverU7pFn@MEnSHXlh?m8`f|`#tvTY;%9#Stb{^WL^eU*Pv8<Y5Vpw=VqIqFHmKu
zpE7f%=IKpaYJL`3%J8M8rTu#VO5eBh_rGnmx^I+o!(i{{bJkVQW~PG<0rI@`xZhsS
zGwa@-ogkxmB@7NEEUcWa7kg<}>FX(zCoi_G{&wPF0VvDPvaQ}GSN9{)QigAB{QkJh
z%l)q}@tnM+{(s%&ljV0ND!X6VRr*?b-S*7OZti_DACo5L@4k4D_5GgDeR4G)9M{I}
zjk>$L+<fj!(T5KoZqj+p{+*SbeRci+f3r-prwIuO?FnFGa5$WBb6f80KIE7Lu^Z%1
zKmPdQ(b4X#o130)bzJiOUbX+vpFfMN=1LhPG_>){uj7-olF(y)kbmg#;im-_C2wvR
zn&#g6GL216_w=QclhyZzyr>41GW_;`0^IxMu3lXoes!t0IIpCU%ff{VmtF3;xgoK+
zsHkX5=4G|e@bK0C^X*QZIB{WyVe*w#p{uKYhp&lPs2RNM#i^;<Y*~A?&CJ4lXPZqu
z{WPecpkVISRjagA)zv{x{P6H_8`oKoza=Flzw+trcs{RM>gYk%OWXg?(TU#XqwY87
z!sCAXbt_hAc!E;rwRN$p{pMO_{`v9Is_M&%qT=Gv(9orz0xN!hUE66!h7bJEb|@$q
zpg7|~T;)?yP<{RD+3b9u<qQtZPs?_T%F5Q>ZOrmqwPHnpr)TG+Nt5=(q|H10Fu=v7
z1$2p9PY;i)yZil;|BcM-pv18@X6GgE)@P_~za>`AM^=Zey%Zi_yL8VUo4>!V?+4Xz
zGBE|k>-T<}6}CQ3clzn2({!V+MQZEohkJQ-srk=a^L$>lUwr-FtySOOtzEG~1KfHr
zWMKH$idoO`-qK#bXVJ~g>8rPGyH>)*U=rcCJUIK>n!u{6U!~VSfBH0K-n@Gn|Ha<l
z+Z)Zy#$zz|;bu^u%l^+p{$HT!s^^tCIcwso-<tBuT3rd483}UP#EBC@$=M|L)|S`n
z^ka4ecu&*0cyhA3s%P=DGZ$a4-@mR~T))a#n1Nyc)gu@+F9Sn^y{4AdB~YdQ?M-BA
zYO1D|me+Ls_^`~(mAgt_E}Aew;Bsf&cjxcQ*REVS@v@|9<+1GsHFd?#Z9EqzC_0zC
zx}rJPqR?ql$^F{znl?6f3T8%Hm%rPy_Ws--KPrwMKYo9wf_!jX+`3n<UP-SD4-a3x
zXV0Ho&%eFB{rc6_)%QG@85TGuKzc#Y_=Qjp#42p$Ko#@PpFcO{Mo&x4JTXDBtE+30
z3a^Ys04VqMNE-7@uR6Xmc=@`!dODs<mo6>ZefR6Px%TyO+F@$~Qc{+ff9{!SUH&e&
z{`e-Hv$ITJ^IiGT|KY<2H~W%*^Ff^-xvCe6x{;e)`t5$L039ii{`SMe!=Sd(uP-l)
z-$r_Rc3PFZc<|PTf#J`z)c+R*gCR~skPnW7lH%EUw$WR+Ze144@MEX_zmNS@f4^Se
znsHGH<WNIH!&@7Z+b><Zq~hss`*jNF9E!L1_unsAS$<}wv3v2eGZRxI&F`k)-X_D>
zK21M<o%;NmOWvi=EM)p_|LaSQ?EQ8>c)8!)OWEu9E{ok=_VV@m{b6-=`+|alL*wGs
zg~!*1N=iz0b$1)jtvp^>aPaNV<M#g+HZrrny0p~W%hz{rnZSvQi`_#50v7Ckx66BX
z+1sF)m^rIfubw(#!h(g)?OFHsR6_C@wx*+uRmqEK-{;xY{^Fa)kl_QWe5X!b`sPi}
zT<h|6_kR8Tet&)G>uZu4#>r1kOnh~1?d+V}VO3STmif$FG-b*Zt7@IoK^`6*aup94
zx8~o!7qGHCc5l_ylBW9_nwo)GS*vX1`hR_Sxp>kfp-LM$Pf!ziYxZ@$*gX}2_5VK4
z=be79Qh)E4OS$#S4fz)wKYH}#=JR%!_f&oc^{GU~#JnacDJxH%IdkRn`So!VCr+HS
z<iG)k+Fvi1s}(ace6YqWH$GVN+kUyge{aWc+1uOlEA<)f_(Vp|tor(@^zc_T-&reG
ztvc21ns)Ta5e+ppw@D$Pp-Vw~t%{$YYg=98?d#hM>X-J(TCYk!KW|xa&AH<9w#%QL
zot=GuUu}`q+^pN%a_4?cJlytjef{6n3$5NideC%RTu=~nlhVv{3=9h#lQ0r_!~IC`
zSOi0FKt;ulJ{ilR!=>AAgNhJ+v7deF^C}LNH2HIJa9mgsxOhv&$0W83>p>T0%(5(A
zc57?)^5W;`u14>Fzwh^#tKspI8phqt+zbp2nb<rotmb1dmtldRm%sn@MXuc@MNd3R
zUtV&ZloB~@Nk0Fv6Q@sKUcG)_meIu(sGZo<+huc0VZGS2h-pjL#qM6UXV0CIF8@_)
z*M@p{oZ!8F`t)hg9n|__KiT;7R_GfW2Tx1Q{Q2o=k%i2uGiUxBd>=7w>Gu0|x4BCh
z7))$1UB|$1r%61n!ZB}q^vRPaUtL_>u5<d*`}+UYp&=nJj&ur3nPf~@=088r>T<`O
zJ2Ad93>^8|onv>Gg?5YS`l$cxku*-rxV0ry$~0@rqQ#4SpZ}Nw8ex&I`>}A-=FP9y
zUcGiL>+P+rULGC>0cm3F;#an(o))u|;k$b6+Np;H8K<Y|Ugu-jIZ-}}oq@qT?dE-Z
zKQ2W6hOw@v-rg3rK5lL4>uW2wYzYZp9~U}ZFV>{$ONQ?pi$K2i!zGIZ0|NuOczLf*
z(~Z8eF4p?8rQOs0|9|iQ3fkT4-Y0Xhfsy&j#$<O^R@SRGlOv~z>Br@)xG?AJZ1dOQ
z`+rT{w0W~>+8K$Z%a(y0n{|8JT2R3P8qm1CJ^y+GBeT!)s@S|dP@{O6ZS}W;0!9Xg
z4_0g!7-24i(;p_Yu(H1FHNSTuzy5dhWlg*1VSK6^biB82-5R&zqb;a*Gd^##*n7I(
z$!%}5w}+YM--`itN{{u+=kK_{!>7l<z@TP`(T`+cC}1{DKNpgfwMs}>xb*wo^4aG;
zMt=PGQOc%b!?Sa9v#nU`UR+x0{p-VFeo(JJc5hW^?5+|}4Iv^Wm1T8Sf=_P;Xo3>d
zs{!rWTC+yS)z$Uor>Cd2bag?YDIz44WF^SJu>S~y72G#4#sOXn8NSGAs_lmt&X^&w
zbjgyK-<<sX=5wDLg9d(3hH!syZoj?u#fyxsSyx}}dMzp{s->wJ7!)*V`soL+ZRGlo
z^~tXO^QQ*Vnyvj^wsh%IkR!PG`LBO@dD%4i7|-RE3=BV1v4w5kgC8Fs7wwGE($JW2
z`)ycZ;m56s$2&SYte9VJ+_-UB@!qr}9fDuy)&BeW9AxSFdA6dGlA6meN2cH1r1SLo
z^J;Cux&tpuvd+#j_44=M|E?-7Zr-KKm!<#e-e2*)zy8nSxca}Px=~v^nA!P4e0+M!
z-rQKYWs8aDrC@*CrJz&He}8{(9>c}ZP@k2A8Ac2T!b@LW@dORM>?nM!;`#ji{OPyf
zh9xF0jM1BZZGHUuJ9lCtr!C#E!9Z12^<^`^ok2|Pb6JZ5hiR!-tMBcrt)4o4`szJ<
z_T0Pm^_#g^^!B`~()oK9I=Az^Jk-j)>t5}o-og{V+TUGWvvTFi@(GLzo;!E$Jay_+
zP+8fwb91f3^Z)+){r>u{($_pw7#S`Y7+_06-G>exGAVfx0P4(6dh)SiOX_Jc-G~hi
z)!*NNG7gV8xH|Vy|Iz#BPff3!ZIq#*p_Fl252#}N@}=bFwza&{W}s24sxKGaebcMX
zf`*blJvo^@-`m^!Y1!`AZ>{V9?Fm~GvGBwRkNjspMfmh~Y}~ZT=<BPiuiIYx&N2xM
z4V^09&A^ZmApseWgC#I9y@OX(Rkdhm3@D0qbgpbnKK`V{>gw+Dd{uSz+2@-3XPW2F
zd-V8mXhg({Q>VOi<M+i(R`(B!ikh|W&nNG%Z*PaswJJ55`_lCNp3i;H&dgLky(uMf
z+Ou<WSMMx-e(g5Aj?Y_g$%apF$IcHQ3S=#dp0vHr+a4Vl7#OF+#IPVS5u=)5V0gd=
z8cbNUNJ&&o?9|hulW)sjgS!1UH!T$s7B<biq@t>-s%d8z=jiCTthm<_)StSpdpal~
zVL{ZEjE75=?gz%itf~C`?BvUmRi2ac-79V6`c+mYAMZPL?%cIMKR-{MI5E-aayF<d
zns;~C$!)nymoLvgHAU0Q({ttK<C}C^TUuT;vdabh{`Qu4>a3#&S<R=<o43xjTPzb)
z?_XNly(GUrUnTSDsi~)6H3=vqAH$lFTiV)AJ^l!qRq^!noMm6XZ_=bmSJp<GU(U2s
zwXykg>%;T2ENDHWw77zT4NOc-DxQgniCNdy%se;8vN(5d?CvtqAm2)x_1&GFpx(X8
z%2lhpKzZl+xw*XIKjlDyOjOkZY8yW_Kp)~@U|@K#Ix8zHC2|_H8$4lxfNB1{J0;W3
zSN?vx{p#j)|JJs)S1Xs#yL70Pduzc%Cs6a*#3ZD!un^P;G)+9jvh!{pXi!ML_RGYV
zIqN(6`oP7;`NG1&sLg4;`+h!?4h;|2Ha8ESIB_By_u0xvo$3;H`x!w_Pdhs+^Y^#6
zQ5%z5Z*9+CzhZ?3sBLud;>BN|=l@@GcDDKHmnE~#u`nFSM;bE+CuA^jGs^oSY%Kr-
z14B(<YU<KEd7ycz7`^FyayBbw&5|m8al!HA$&+4QUO`1gn;t!S^rXP#UNuvE^;=U=
zk5zBFw{G;dHJiiY;?_->BH}yGCi1-P_c@^Z;J&`Q3re)Nb`~#RnDjn!N5R5rI+2Sm
zT?#VIzUDLAEccRfzs;fr3lt)!EnT%rYwz!OyJuMxE_xZF?B(sfwdko=?Z>0ytJbW!
z^4)!|&go0ra&PloojG~VoHd}q67T7HQ&m*e)U+%tB0vLe=J#tBJ2tbeT(ibURaLdk
zn-MhKgDr9CeyXtf_2Y5>Yo4X^ZL7l+6&1Vs`@@ThHi2uX%deG`mA{@bJ`ZXyT#x;q
z$MO5g$;p$JSQbBf@%4KA^`qV5duP5h=HlY|^6&Ti(=SW1Zfr;d4bZ(*Q7$Sj2F0eO
z3?FE`K{sm4j(7W-nwa#b&pdvR_3PO=mcc7muJrQpxpKGsey$ZeLjzkcX77)oVSd8n
zW4)k6|Lxsf?bDk=qNB5|PQGqxZZ<7`=5uz2;p1Je>wjII|K-){^{?*#|F>Nw^Jtf7
z)wi4JU)R_FJw1D7T=9bgjIOS(S9kONtLl@tU)R*cl$w%KvGB}x7gtwJ6O)kWZ8?Fv
z%ij7t|FP#-T|wjFhZ9mGi!5Y76PI3Ir?$@j@S)&xB?E(r2G*9C65%P$^{=n5pWi2A
zxoEC+`Ks#g?@F)n$=j{jvc&{6%vAmD%|sR7`F63O6!3h0eV)?yzGADnprn53@?}*|
zQBhG)O?z!^^ws_K|E;Qvi;AX9oOn@#Uyp-}>k_EGx&QCm_GQ5}Ozh%!Kqr1bE!r6p
z5TLOA_S#2}lE9U=h@fC#x`M5l*|icq28Oz|oiD+u9hHbL{r9JGXUw{6=I5@iuB%qA
zoS1u?i<>(*De2MH#^XPJRG4O8J5#br5Y$x$O?z!l_Xo|5X=!;)D*5svP*g<Z#k$?^
zE<HNht?GI8>Qzt|&aFox(dcL2uYa`@x8<(hwQE-(-^}|y{c^UD;deV_L&J~L`1J~Q
z-<@TW8MIi+;r*4BldVc$Eh&6_%=6c`_nU9O-S_Q#<=<alPn|tGH8m3CoS>jdc0V34
zAHK@K@IxJIi(^6P>aa=sWEJ{4Ixc*8c=+`l(Cq9(r~9Du0MFa~_WAtm?B#8_w?iT#
zG(5X{dP36Dmd&gGSLy2J<~0d4O!;#8{8?vO`y+M~EIigDxj6A~o2H`T!IHj0nV5oV
zLbWjy!-M@;>&Zs6xx|_%7nhc4y3uJ?%yw_8w%^;HanZ@s)AJQ%O8IGt)$29U)0Y1E
zQ<JZH==_u^Q%*cBI{CC{<%SIb$NOX_Uw#?#{@&iHbLQk&@iQ>&KZ-49^BM&3{;A=U
zu~0a@>6LB%{e62u^A>S&artkneqXeR-C5-7>guYcqci37(@D4AUfWsx{K}?OZ&fw5
ztV>HgLFHRb&7P*FCZFd_3=ghj^VAQ)Q>RW{*;iYgdw*YSW@hHH;yqe;Iy3top4Q)g
zWubGsil?|<%mkIG)23<Z=&U)n@A2{e>b+;D1TXiS>DM67&C5IW_~XEmk}Z=aO){zf
zSEH(`x-xou-m=RK3>gJj-7zuew%Oc-Bhz%FpA=YxL`Q44A6}>%z3tBf->bcE)m}$#
zPRqQuCbD#1YI^$h+v&H<7XQA_W`67-t9e*(u=4WDD;F$KU}b05R#9;|JKNlRE-QmW
zbIQ%$um7>+lRqq}sj0iZ->cr5e7w)CoY^Wb@9V3p+yBnx6jr;_D0IK<*O!;G*F{fT
zdf<S=){KjXyj{~QW%{bx1@F9QXnH^I`n79S+UIwiI_0(VZr;uqy`3?7vNja~rlzK^
zE-Y-GG<ovWDN~j_d6IJU=+To83uc^SWjL@NTi4=)vOxpiACv3SJNC`PnAd#ppy~GG
zj}>1&9+$r^>1AL2ZH<$Y6KGYzlP4)>=UQJcQDb1J>%>;r$}iltD+)A}Zd0-0*4FHF
ztK;e-qN17C*Tq^@e_OL@(<Tv7(WR%S>#yFjB_wuNNuY;E$4i$V6HsR~3&GPeph~Ok
zZ4{_|{rGtQ^^1$$L9?i<R%w9}%imvLjbr%Yw-!EjJ3HS#zWV#S+!FI6%nTojG5h=s
z3=hQK+~2?7@&3L)!RRAgzrVc&O%**oJzZ2zZr#hv%d?O5NG=P0=p094ef&d+a5>Jv
z@MqFttiypGK0a6U>ppVt{qyPcuSebbKF@zlxw$$0b$<Qt+0*o5R~>HWe{KKXn}>_*
z5@=*1@i1F+>j&4<({wLS_P2}7{}D4OYJ1+=`+uI9SA9NfuIib4Ys*Dpf18Di7AfVY
zA99~#UmrKyJpY>f{~zw4rqRNM3%z`OuYNvnzrLx7>FDv}ul?(PP5$=g=3;JfJ%buP
zh6DZ=j$m~t=u9opApP|Cx=8)KUnc$f_ICBh$H%k3ytsH>c0n%g0jp+x(C}?(=~v$C
zt5>fMjf<;$Tm1Xm+tRPELi3j#WZ#-~)oW79?QKd*N+vZw3YIQeqM@qlx^d&iO**Fw
z6d4$J*)gYxK*JbczLezN+Y`CmfBv;cN4ryRZ`-ta^VNN|)u5@$sO@=k*Tw8ivbx-{
z38O>ufFCv#dGzSfuiy%GsrU3%{`2jw&zm}B$_nRpzI#3`{3lPHx>Wss?{Z;vKhVg?
zsgox!f;#zMUtDZ{Sj@msmxeir$G}h^4T_DG!OOE=U0G>W_GSiX7;p0A#mD8UeHJcU
zC}ml+#K_2K%A`q2R#&qR9X?$8<itejb-VB8xw^VmZshovaB`9=s1a24?aj(7SFU95
zR|ZX?J32PL+x1#cH*QbFrS01nzQ3{2S=p_}U?xv9xEf$&XmD$m#xgunw**=|85jg?
z%RRkGC-=q%$G^Y7htIdGU01!i*m=sldF!^{tMX>&liBg@&2H(=@O3dO_w2FhmAAha
zB3Ba<6Enx|_Zwr-1mcsElR+y>!q!HC7FB@?>-lxRRz7<4NX4_UvGLcJ%l@YM_iPSd
z{otCKnp$Kv7t~gLDZ;=Y#d3OE?(Gs5)FuN114G099VIU(U0WNye9j!1w>LMt^R+uW
zxA6qJxwWCq{MdfKv-t1t@3Z~(J<iI?GRe7N08(yS^<{^dMNDAeLSc2kj0+1uw=PWv
z&4q_B@CHOi&V0A`d)(U_8=b+m3j@Q4YF{7lq7YPv{AlKtHq%g7cb{#R8&q1l6*NW)
z>T8{uVVHGwRp{Kk%I<w3si{ks`OHjOac%c3)9ht$Z*R~3`sykujjdX>3N$(I>h7L>
zZA~Po%`L;%{?Z3z#r6hlrDQbdx)xU#mlrqF=ZCtvwJln_IDgmv@bz(0)@5s^zdEy7
z#~XA&+>uUU-{l9~Q`6E;ZPEdCefip*XU?2y|3milrZ3-a=T|QTEj_ruG3WL+Uw4pg
zsQAaOySvM?4>T|?Gp;#yW~TAfS+iChIpT7+_WRvs#Shp~=B+>*Q#a|nUUq+@j<>r1
zye~nDe?m)3w|@Hc$)w^#!q)8T=Suh(80z}5_=e$*S^Htd)0>_YScnJ<FP<`GO1AyO
zhYy#1W-v*BtW#)u$-}@P1)7{@KnLrR-`&}{{jcn4(Dd~h>ww4Aee(8t(@!sLYGT@X
zH&0Yt{Pecm$Z1QFMtm4e6!_Ym0|Nu4?CbV`hL+CFwVv(A#IV2-Yd_vfhVM9dHsb2F
zYxf$Z?w5mFsdw`r-TIX)R(MR;kDrFpG`u|XgQKgfD}hlnJ2i9ja7#<eTl;EvXJuz!
z-JT!cD{mjS*u6jO^fX=H=Zp*wzGG`^95{dO@kh`YC}?i`+q=8BSG0dFtd;9`Pd?rk
zT35F(=k~PJNRXkIE?p}5`6;!vy*>NamzT2)liOZ~{8;hnQ_<Sk-C;X-?!2`<e?Aiv
z6DWRqrOo~J|GK(fL_i<`Jf2tb+r1EToYKU|)YSCWj>5&D+<aNnZtapKE}(G}(1hBI
z84|q`hEDAKa-fFc*Dsg-XM;vxY^%5Z`?h_5=F3Y<t!jR3`1g6<*#!#}dZkRgq|I^+
zA~@o&?<&pqoof}Ew>^64(xp`oTg5{_yM5)VeZJo*?l&?v4vmP&umW}V4`XX%@^e7O
z+Mkr|_Fev?M>~AoiMM6h2b)-{o=kMVvdmW+w8f|X$6@&|U$4h!Us~b`Dp2%db}VRS
z=g+#h$aUG|hsmJA6*5P%HTU*5$Q()X@jgk7W_vC!t{~7j1~YT&?QJ@zFSYSXU)f(@
z|Mlf%_oGLTE)!;C_#lnFK(IQ!>B`pZ@Tt?M&-VK$xp3jaPZc&@eSKj;L6e@HpTB;|
z5|z@|*Upwm{c*vZ(D-0Z@@zH(!w*)hosok*lEx;vw@g4me(~bPWyL+KSFW6R`Q@In
z*99IP9ka~y^Q^e*RBUWO%Pn?3+;#hHSV+he@$Luupwn~a%#q2xwFT6jdUbhuznE^+
z640?`p{v76zxByj22Gthb(T?T*TN_UhClqwFVHh51H*REy;NCOS4~YyPBu+Az)<?;
zMxdjkW9heuX-kiGi%V;LSy%l0+{w3Pr@_4oP|tbQ%9Vlbe6myK%vrN!iHfSay0)I4
zA85E<uO^_XY8S{26P4Xpc~94ywC``a$D}YwT?4w5N=^9TV$jTbM+XOJP0gtjCw?4s
zcC7mPYU#%0<5es97#RMiW1XyLVE9nF-N+?3a#~h)_TGTU)i!edcK?1nwsL-%etur4
zheyYw$B(DZnX_hR@$*^dTKHG4TzPRr;^8gn=jFb>xabV6!a}fAB0pxp%TNY}j15>b
zv@GaI_OsAd=#|4icNpH@wzcYO*4pUpeoL1w-BtB<6=+iT;$rvgM@KrhmwW&%9jS}M
zHW=_g{d0wlRmFz|T-@AGi*`OK+Z`GhsCavusDQwNdwZ)-KP{Shj^#o7vvYH+Z-a{J
z&1q+MF`F_lnABi3Z5wD}R&V<2TL&rw11Exp)oyP)bm-8O88cQ)nIZyeW7*loot<TB
zJeNlvbQBn<KW=CkSbo2D`%9T0ob87T!M1GOy0v@(8$&}Iw&K4bdQ0i+u)QCTNn4e?
zm;lO}uX|HXrZu`RzpUxGDK}bBQ1E)&+2Eic5ou}d)0=q24~bhM<`rgG?Kg*177Ppu
zSTlepX!Ui!+*;5a#Ij{sKR-S7^7o&fd;8Xg#O7UPZ&$g?*M{it`?2U{$odoK&V^-V
ztpcrp78FdhVy}CIHg~WQT)1AhJ;Cr}->g|upw&^b)@32*=h^x`XJELXfUToczzu3A
zn&#dLX>Dy?wPsDo?QOYRlaKR(CNWOy?+>}ZuXby~LC}cM3_sRC$9{f({<Lg&Xhej@
z^wUchEmDfzR}(ocRZ~aD$J5jE*Mnw$pY%iRH@2-kaKHi7kOR$6gV$B6v}5TjGSq|b
zp-4V<0z8VWHc6%bxU%P~8ygpcCa>!M)lBZRTfAnCkKgiO>+*LdbD8AD#l)5^bZ&oj
zH9Y?6JlpD$e}5`LD`#qde+x}bUAisjW|Ebl-LXwNpb@pFPoFLe2Bqp*GeGSKwA}xJ
z{ouiaTpSz|zP!DVvpMZ-$+I&vvtPfxwe|AH$H#r2{*<}B%~$<^Ki-iAyNqK!lC#Wm
zXSwxCEq(DK<FX|KgNX&Uq<W|6#fuD4aq;-yGUDRPO|!3M+}TkGT5B?8_UzRsPIxr8
zHoV_m^t7w1s|z&lGX1pb_S<Vg%S%&FPXi4BF7cc^Wy+K#KYmoOva-%R*V+%N9YLpY
z-nbFLD`DUuYhAYH`|l*^B%lBT!~e9KGU}{oer90!&@84GvqIH-+KMe(Le9=Iy}ZnK
z_LmdN{Tdn?9@A1mW8Lrf{a&Z$Hz&jD>W)pDjP6#y-wPV4x^(H1&+`NAEUc_2;REfU
z1^GcilXjK9PP5{zJMysL&jUH|_~YwVDFy~9Ic&+jZb?%U)87C8euEYondQu2<CDp-
zI;kEK9<Hsg@88VM9|j(1JkV|-!)H0y@9V3p-iWc}Lx&IhE@xz5c<}!?wz`&A#-hL>
zFfb6bqKW^VZQY+8TwGjJCQf|VYIJ{7{r@^u6_pw18st~3Su^GK+i9ntPCEVc(!pl-
z(BR<3e6m(oBt81OyLT^*UI&^7{R~}2j}m|n*yi{x2c3ub<x7cYkgIF!p~Hu_mc9=A
z`u_g@bNA-Vkx5NSS+Q-~HJ4R^SXyvR^FQDlNfu^cSP=M7LIK4_5T`-<$G^Sxi1EQQ
zpzhkb*xj$5PLB_}zAhG2?t^+aqN1Y9E<boY%Pe=*zS`eex3*-SI)DE9|G)SDzXbKN
zL47UIYLBVmafWj_<U#KK`)T_Akkw&puPpHtww!ye${w`x9$O=m!QQi~YL{95y)~DY
z`)7ZAbaYd0^v#<$v+nQPD_8p^5L6L_uZuC9%PIflW5tuQ-Jk-)_R|UFtjo)KK@}co
zxvheNL+$TxrgJ&ur_7(f9(3bNP-Nsx&;a7<@b#}iBQY}!lSM>CmdvxQ&ieM|<}zbO
zh7ZwL8!rnILB~xk^P9VBW$^M>H#R1pI(s(M&#w=(4iL1E^~s5er%s#*@bc<<86r^x
zY7fWgiGruOK<!~uJR3^d_-7F{AIHhia39-141@jd1(2aK<i6;8^aXpI`q@`kO;tI$
zE!Wk>CF943hu7K8B_}7RMoxR^^rQLFqa@IJM8D<1zO!nqm7agBQ1Jv6<7H*rKuxor
z9-hgd6^**s@>kxY)A)uEugB~v@qB%4ZLptT-?uk6mD>+51f3%N?aj@q9}nA~7FcYl
z`&$JXYoDy<d+Fcb-@fXHPjA|^Y09iwtENm5admN-ajtPb7aw1kgF}M~sL%%$Av2BB
z*R9>2eZ6o0Nd|^LEYostZ+poBO1Y>w{z-wwtGg%u+|9jr|NGs~w{At{KmFN**)Q$s
z;pvq$es-((`hQS+3)FxE4RS0HYuNAY=Xb4{-)_ZH@9AEXgoK4fWn|WXY@40G@8SZ-
z=8&+kWs@ce9bO6=`o>(x&%m&wajJIsEWZ!jhuitXkNm%WPqw8j_J5&FeQo`I%emt1
z%4;v&I2hl|(_;|8HK!@S<EcXGnIEp#Stpipx^URGTso@97O0%F*jZ|FLc5rSnzC)h
zhYij_w{=+pRhnkz?*ISrzxu3yr~m)EwD0%M<IMZo->1LVx8b*b^XXpt<6|;56$W3c
zY-3|%>#g^vo}MOSQIIh4RfgF0b+M-(_uJ3Q-~ZQaciCGl>vq*O%a^NzPPVoC^WpHC
zn4L!L{PO2kuirQ8+qZ8bt`p<y|C-LP{T6w1Cc}j-sKYY{m@Vu7)$H26`}Da5Cu4V)
z>Gs=xi*R#y*IlqV;ql|gmet>KR$T?<uE}$)%csp{Vemc8gfi<NV8#97&s^{6da0L}
z`9|(8ds~~neAzN1JG*&Rd-rjqGJN=uscDTIuMN+NzPz}|S|2Rp+9zZAiT?`2>4V?i
z-Y)+2<>i;JUsXNx?(CSzD{YpNlA>Z=_GX5;wV~le^ZPZInXDN8%-2C#6}>^>{r>;|
zn)YvOIQMr=<YqNyX6BoFDvNJw>NxhgJ)ZY{=FFLA&YhbU!otA6-s>hx_s?Yd&Ye41
z?WeiyynVD={Q2JXQCqe0_k47_wmv>SNRWY{lNDvKPwv3m+uMuZ-Ps8`@9B-mtTW%<
z-v0b#vj4Li8<T&&Tt5HQIYx#D_NcD=P@kQfdv;&#ZzDs)z%nl1XWjbyJl2Mt-k5wm
zX!X@ke?Fgo{<z=%T(7kGDL-b0h-*=&P#PTzDn(r<My;Lp`uh6mbDbu?eEr%xK0bb3
z{Qi0R`~Mg@J3GI8|Ngx7`#qDz<7*7p@Bdd7SNU}6mTlXn%{?V#Xlpz7^mKi7&%C?4
zrmF0$`kHm?_U-3qeSLj(tE3rhe7f8gU(~Q>LW-7#XQn15Q=HrRQgd>2Vq;@dpI<mq
z_vhnr9$wzmf&zo^^`KU9_NQCf>zBr@f8Ht{r(xYM6sk2<#MSWqnu{5CioZSoeDmhb
zqo<e~+PhH4+$t3A*Z;4zva<U0<+A_s-Mg*l&Yhc?ojuz;Sj5$Do=s$s;@L%O*Xphg
zUw>{@=<0tFN^){?=a$c}o0UGl)@*+Lzsh-4uU2j{);xINfWu8rh7CEW`v4l)gI0#T
zvwm!r^zW4Z{y&q}@B5|I+}tcFE$zKD=%ly)-YHdk=S`2Vvz+Rs8ejjn^j_`vyEeaG
zEZ$l1G3n+>1_pjpZj^rBfko1Ca_1gANZ9xD+3YiC&OF)qe4h8-IRE_od@C!fcQgM#
zne6}RT6F%??f2`n7m6_?{LDa2;0zIURaI4+3UOs%28L<+<|yfyq5IvRpPyg8d#7j3
z%+Rnq1T7)_?Ct4E`Tp+i%NH*^yuH0wU43QC|7YgYVupsLE0?}OibMv6S+{2zr*EqN
z|1am>9?QLZ_ga>|3i<Wx*QE>-BO9AJQER8|t^Pi3uII@<Ion+i^1BwDn5gXjuThGD
z;h)#V3=^qTltHr#d$#4>1?{bRa;TMiXXWR#YipyYU%Ytn&8@B4moHzwxh*%^Z;r*p
zs=aY#TB@r;w7CB*)95;L?%Y362kg((*8f-8kR4ZlXP5SM1_owhPZ!4!BTLJf_wL;b
zS$%cOmMtot@9ylJtn%{B8=w06`aXI4xHKj219$G+X_7zvoPnYHJZh1{pYrw9)y&*n
z-$`4xZ%==EYU<CQ&*%UD@$=W$*T$x%p<!~~7f^C51H-!{l&vET?3b=yoqF=*N&9>A
zE1%7rV^?dn|Np=0w6ruM6O$?G^C}h{ahf*k+O=zMZg1BY78Xuj&cIM0j+#ttCd`{R
zkB6Thw20Vq(&2Xg=YM{F&dkq0uiS4l>Ep+bd%oYRRt?`YMFf$FnHUblV##^!r+@sY
zI5*FBcGlKew$<NKo}ZhWs=o0E4=?Z23k#h=={P(*{H7%X!=HB4LP_k+rKR3Cw`2xi
zTNhh>|K`e-D|`C;m&dKwcal8&=<W9V=gRNbPM5Fyp?LT1T~OFYN8jEvbCE{Trza;T
zaWOJXQ%CiYPQ=!zvo9|%zkL1rbd{ZjkKN32ZcLasapIdB8<X$7dGH|N)z_-D^z_pn
zshz7rw7$>P>^k(Gm*Id?Hfr*3cvk#<Zbz@1vazx8wAP>V&z?OybuI(Lf%?M#^}=Yw
z-3K-$phOI4_*+E`WyHQ=QV(Y8XJF`Fjh^x^fB90P7r$?g%Ffc)VUwP`y1F_uKYzZt
zxvA;a7r8pM>F4I0{P*|w=E~2{zI^-k?8?euP>H(u;)xF*3bM9FeS3E|x=fAXz@}gm
zsb066D7&gmrh6@&v`FLGTvMsu>T~~U?5wSKM^u_Lu8rQFcC<@$XTd|KynB0QmcG80
zT2f-NyX@_$FJDTw<=&nqtnRlYZvFJRTnro5pcPuI(h?FH){ScBmX<U5?S3d+%`(;1
z{U2AntN6L!q$Qg-8~^?L*Rt-<4%QNe2G?);tkY(*GMoDU1LY@AS3j3^P6<r_bAZpv
literal 0
HcmV?d00001
--
GitLab