From f7290f57db96d86c44be792348e3f99e81fa9aa5 Mon Sep 17 00:00:00 2001
From: Baptiste Bauvin <baptiste.bauvin@lis-lab.fr>
Date: Thu, 14 Feb 2019 07:52:46 -0500
Subject: [PATCH] Test and time
---
.../Monoview/Additions/BoostUtils.py | 2 ++
.../Monoview/Additions/CQBoostUtils.py | 15 ++++++++++++++-
.../Monoview/Additions/QarBoostUtils.py | 2 +-
.../Monoview/MonoviewUtils.py | 1 -
.../MonoviewClassifiers/Adaboost.py | 15 +++++++++++++--
5 files changed, 30 insertions(+), 5 deletions(-)
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
index 90dca128..e7242ee6 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
@@ -760,5 +760,7 @@ def getInterpretBase(classifier, directory, classifier_name, weights,
separator=',', suppress_small=True)
np.savetxt(directory + "voters.csv", classifier.classification_matrix[:, classifier.chosen_columns_], delimiter=',')
np.savetxt(directory + "weights.csv", classifier.weights_, delimiter=',')
+ np.savetxt(directory + "times.csv", np.array([classifier.train_time, classifier.predict_time]), delimiter=',')
+ np.savetxt(directory + "sparsity.csv", np.array([len(weights_sort)]), delimiter=',')
get_accuracy_graph(classifier.train_metrics, classifier_name, directory + 'metrics.png', classifier.plotted_metric, classifier.bounds, "Boosting bound")
return interpretString
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CQBoostUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CQBoostUtils.py
index 18367d71..16821bd7 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CQBoostUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CQBoostUtils.py
@@ -43,6 +43,7 @@ class ColumnGenerationClassifier(BaseEstimator, ClassifierMixin, BaseBoost):
self.chosen_columns_ = []
self.n_total_hypotheses_ = n
self.n_total_examples = m
+ self.train_shape = self.classification_matrix.shape
y_kernel_matrix = np.multiply(y.reshape((len(y), 1)), self.classification_matrix)
@@ -103,14 +104,26 @@ class ColumnGenerationClassifier(BaseEstimator, ClassifierMixin, BaseBoost):
X = np.array(X.todense())
classification_matrix = self._binary_classification_matrix(X)
-
margins = np.squeeze(np.asarray(np.dot(classification_matrix, self.weights_)))
+
signs_array = np.array([int(x) for x in sign(margins)])
signs_array[signs_array == -1] = 0
end = time.time()
self.predict_time = end-start
+ self.step_predict(classification_matrix)
return signs_array
+ def step_predict(self, classification_matrix):
+ if classification_matrix.shape != self.train_shape:
+ self.step_decisions = np.zeros(classification_matrix.shape)
+ self.step_prod = np.zeros(classification_matrix.shape)
+ for weight_index in range(self.weights_.shape[0]-1):
+ margins = np.sum(classification_matrix[:, :weight_index+1]* self.weights_[:weight_index+1], axis=1)
+ signs_array = np.array([int(x) for x in sign(margins)])
+ signs_array[signs_array == -1] = 0
+ self.step_decisions[:, weight_index] = signs_array
+ self.step_prod[:, weight_index] = np.sum(classification_matrix[:, :weight_index+1]* self.weights_[:weight_index+1], axis=1)
+
def initialize(self):
pass
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/QarBoostUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/QarBoostUtils.py
index bc2aac34..50eb7948 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/QarBoostUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/QarBoostUtils.py
@@ -160,12 +160,12 @@ class ColumnGenerationClassifierQar(BaseEstimator, ClassifierMixin, BaseBoost):
logging.warning('Converting sparse matrix to dense matrix.')
X = np.array(X.todense())
classification_matrix = self._binary_classification_matrix(X)
- self.step_predict(classification_matrix)
margins = np.sum(classification_matrix * self.weights_, axis=1)
signs_array = np.array([int(x) for x in sign(margins)])
signs_array[signs_array == -1] = 0
end = time.time()
self.predict_time = end - start
+ self.step_predict(classification_matrix)
return signs_array
def step_predict(self, classification_matrix):
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py
index 0d4c7829..59260507 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py
@@ -31,7 +31,6 @@ def randomizedSearch(X_train, y_train, randomState, outputFileName, classifierMo
nIter = nb_possible_combinations
randomSearch = RandomizedSearchCV(estimator, n_iter=nIter, param_distributions=params_dict, refit=True,
n_jobs=nbCores, scoring=scorer, cv=KFolds, random_state=randomState)
- print(X_train)
detector = randomSearch.fit(X_train, y_train)
bestParams = estimator.genBestParams(detector)
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/Adaboost.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/Adaboost.py
index 4153a0ee..71d6a839 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/Adaboost.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/Adaboost.py
@@ -1,6 +1,7 @@
from sklearn.ensemble import AdaBoostClassifier
from sklearn.tree import DecisionTreeClassifier
import numpy as np
+import time
from sklearn.metrics import accuracy_score
from ..Monoview.MonoviewUtils import CustomRandint, BaseMonoviewClassifier
@@ -32,7 +33,11 @@ class Adaboost(AdaBoostClassifier, BaseMonoviewClassifier):
self.step_predictions = None
def fit(self, X, y, sample_weight=None):
+ begin = time.time()
super(Adaboost, self).fit(X, y, sample_weight=sample_weight)
+ end = time.time()
+ self.train_time = end-begin
+ self.train_shape = X.shape
self.base_predictions = np.array([estim.predict(X) for estim in self.estimators_])
self.metrics = np.array([self.plotted_metric.score(pred, y) for pred in self.staged_predict(X)])
self.bounds = np.array([np.prod(np.sqrt(1-4*np.square(0.5-self.estimator_errors_[:i+1]))) for i in range(self.estimator_errors_.shape[0])])
@@ -42,8 +47,13 @@ class Adaboost(AdaBoostClassifier, BaseMonoviewClassifier):
return True
def predict(self, X):
- super(Adaboost, self).predict(X)
- self.step_predictions = np.array([step_pred for step_pred in self.staged_predict(X)])
+ begin = time.time()
+ pred = super(Adaboost, self).predict(X)
+ end = time.time()
+ self.pred_time = end - begin
+ if X.shape != self.train_shape:
+ self.step_predictions = np.array([step_pred for step_pred in self.staged_predict(X)])
+ return pred
def getInterpret(self, directory, y_test):
interpretString = ""
@@ -56,6 +66,7 @@ class Adaboost(AdaBoostClassifier, BaseMonoviewClassifier):
get_accuracy_graph(self.metrics, "Adaboost", directory+"metrics.png", self.plotted_metric_name, bounds=list(self.bounds))
np.savetxt(directory + "test_metrics.csv", step_test_metrics, delimiter=',')
np.savetxt(directory + "train_metrics.csv", self.metrics, delimiter=',')
+ np.savetxt(directory + "times.csv", np.array([self.train_time, self.pred_time]), delimiter=',')
return interpretString
--
GitLab