diff --git a/Code/MonoMutliViewClassifiers/ExecClassif.py b/Code/MonoMutliViewClassifiers/ExecClassif.py
index 463439d6409f88babd4f4e961519b4eee368eff1..a4726d985bb200d94d7e007ecbf5e29c721f0e97 100644
--- a/Code/MonoMutliViewClassifiers/ExecClassif.py
+++ b/Code/MonoMutliViewClassifiers/ExecClassif.py
@@ -7,11 +7,12 @@ import operator
import itertools
import sys
import select
+import logging
+import errno
# Import 3rd party modules
from joblib import Parallel, delayed
import numpy as np
-import logging
import matplotlib
matplotlib.use('Agg')
import math
@@ -41,9 +42,17 @@ __status__ = "Prototype" # Production, Development, P
testVersions()
def initLogFile(args):
- directory = os.path.dirname(os.path.abspath(__file__)) + "/Results/"
+ # os.path.dirname(os.path.abspath(__file__)) +
+ directory = "../../Results/"+args.name+"/started_"+time.strftime("%Y_%m_%d-%H_%M")+"/"
logFileName = time.strftime("%Y%m%d-%H%M%S") + "-CMultiV-" + args.CL_type + "-" + "_".join(args.views.split(":")) + "-" + args.name + \
"-LOG"
+ print logFileName
+ if not os.path.exists(os.path.dirname(directory+logFileName)):
+ try:
+ os.makedirs(os.path.dirname(directory+logFileName))
+ except OSError as exc:
+ if exc.errno != errno.EEXIST:
+ raise
logFile = directory + logFileName
if os.path.isfile(logFile + ".log"):
for i in range(1, 20):
@@ -58,6 +67,8 @@ def initLogFile(args):
if args.log:
logging.getLogger().addHandler(logging.StreamHandler())
+ return directory
+
def input(timeout=15):
print "You have " + str(timeout) + " seconds to stop the script by typing n"
@@ -471,7 +482,7 @@ try:
except:
gridSearch = False
-initLogFile(args)
+directory = initLogFile(args)
DATASET, LABELS_DICTIONARY = getDatabase(args.views.split(":"), args.pathF, args.name, args.CL_nb_class, args.CL_classes)
@@ -514,7 +525,7 @@ if nbCores>1:
nbExperiments = len(argumentDictionaries["Monoview"])
for stepIndex in range(int(math.ceil(float(nbExperiments)/nbCores))):
resultsMonoview+=(Parallel(n_jobs=nbCores)(
- delayed(ExecMonoview_multicore)(args.name, labelsNames, args.CL_split, args.CL_nbFolds, coreIndex, args.type, args.pathF, statsIter, gridSearch=gridSearch,
+ delayed(ExecMonoview_multicore)(directory, args.name, labelsNames, args.CL_split, args.CL_nbFolds, coreIndex, args.type, args.pathF, statsIter, gridSearch=gridSearch,
metrics=metrics, nIter=args.CL_GS_iter, **argumentDictionaries["Monoview"][coreIndex + stepIndex * nbCores])
for coreIndex in range(min(nbCores, nbExperiments - stepIndex * nbCores))))
accuracies = [[result[1][1] for result in resultsMonoview if result[0]==viewIndex] for viewIndex in range(NB_VIEW)]
@@ -522,7 +533,7 @@ if nbCores>1:
classifiersConfigs = [[result[1][1][:-1] for result in resultsMonoview if result[0]==viewIndex] for viewIndex in range(NB_VIEW)]
else:
- resultsMonoview+=([ExecMonoview(DATASET.get("View"+str(arguments["viewIndex"])),
+ resultsMonoview+=([ExecMonoview(directory, DATASET.get("View"+str(arguments["viewIndex"])),
DATASET.get("Labels").value, args.name, labelsNames,
args.CL_split, args.CL_nbFolds, 1, args.type, args.pathF, statsIter,
gridSearch=gridSearch, metrics=metrics, nIter=args.CL_GS_iter,
@@ -541,12 +552,12 @@ if nbCores>1:
nbExperiments = len(argumentDictionaries["Multiview"])
for stepIndex in range(int(math.ceil(float(nbExperiments)/nbCores))):
resultsMultiview += Parallel(n_jobs=nbCores)(
- delayed(ExecMultiview_multicore)(coreIndex, args.name, args.CL_split, args.CL_nbFolds, args.type, args.pathF,
+ delayed(ExecMultiview_multicore)(directory, coreIndex, args.name, args.CL_split, args.CL_nbFolds, args.type, args.pathF,
LABELS_DICTIONARY, statsIter, gridSearch=gridSearch,
metrics=metrics, nIter=args.CL_GS_iter, **argumentDictionaries["Multiview"][stepIndex*nbCores+coreIndex])
for coreIndex in range(min(nbCores, nbExperiments - stepIndex * nbCores)))
else:
- resultsMultiview = [ExecMultiview(DATASET, args.name, args.CL_split, args.CL_nbFolds, 1, args.type, args.pathF,
+ resultsMultiview = [ExecMultiview(directory, DATASET, args.name, args.CL_split, args.CL_nbFolds, 1, args.type, args.pathF,
LABELS_DICTIONARY, statsIter, gridSearch=gridSearch,
metrics=metrics, nIter=args.CL_GS_iter, **arguments) for arguments in argumentDictionaries["Multiview"]]
multiviewTime = time.time()-monoviewTime-dataBaseTime-start
@@ -559,8 +570,8 @@ trueLabels = DATASET.get("Labels").value
times = [dataBaseTime, monoviewTime, multiviewTime]
# times=[]
results = (resultsMonoview, resultsMultiview)
-analyzeLabels(labels, trueLabels, results)
+analyzeLabels(labels, trueLabels, results, directory)
logging.debug("Start:\t Analyze Global Results")
-resultAnalysis(benchmark, results, args.name, times, metrics)
+resultAnalysis(benchmark, results, args.name, times, metrics, directory)
logging.debug("Done:\t Analyze Global Results")
diff --git a/Code/MonoMutliViewClassifiers/Monoview/ClassifMonoView.py b/Code/MonoMutliViewClassifiers/Monoview/ClassifMonoView.py
index 798fe9ccefa0d0c79377af68230424e1223441d7..487708e992560c66626ad2523a0de6e2afb8c3a3 100644
--- a/Code/MonoMutliViewClassifiers/Monoview/ClassifMonoView.py
+++ b/Code/MonoMutliViewClassifiers/Monoview/ClassifMonoView.py
@@ -6,9 +6,9 @@
import pandas as pd # For DataFrames
# Import sci-kit learn party modules
-from sklearn.cross_validation import train_test_split # For calculating the train/test split
+#from sklearn.tests import train_test_split # For calculating the train/test split
from sklearn.pipeline import Pipeline # Pipelining in classification
-from sklearn.grid_search import GridSearchCV # GridSearch for parameters of classification
+from sklearn.model_selection import GridSearchCV # GridSearch for parameters of classification
from sklearn.ensemble import RandomForestClassifier # RandomForest-Classifier
import sklearn
import numpy as np
@@ -59,43 +59,43 @@ def extractRandomTrainingSet(CLASS_LABELS, LEARNING_RATE, DATASET_LENGTH, NB_CLA
##### Generating Test and Train Data
-def calcTrainTestOwn(X,y,split):
-
- classLabels = pd.Series(y)
-
-
- data_train = []
- data_test = []
- label_train = []
- label_test = []
-
- # Reminder to store position in array
- reminder = 0
-
- for i in classLabels.unique():
- # Calculate the number of samples per class
- count = (len(classLabels[classLabels==i]))
-
- # Min/Max: To determine the range to read from array
- min_train = reminder
- max_train = int(round(count * split)) +1 +reminder
- min_test = max_train
- max_test = count + reminder
-
- #Extend the respective list with ClassLabels(y)/Features(X)
- label_train.extend(classLabels[min_train:max_train])
- label_test.extend(classLabels[min_test:max_test])
- data_train.extend(X[min_train:max_train])
- data_test.extend(X[min_test:max_test])
-
- reminder = reminder + count
-
- return np.array(data_train), np.array(data_test), np.array(label_train).astype(int), np.array(label_test).astype(int)
-
-def calcTrainTest(X,y,split):
- X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=split)
+# def calcTrainTestOwn(X,y,split):
+#
+# classLabels = pd.Series(y)
+#
+#
+# data_train = []
+# data_test = []
+# label_train = []
+# label_test = []
+#
+# # Reminder to store position in array
+# reminder = 0
+#
+# for i in classLabels.unique():
+# # Calculate the number of samples per class
+# count = (len(classLabels[classLabels==i]))
+#
+# # Min/Max: To determine the range to read from array
+# min_train = reminder
+# max_train = int(round(count * split)) +1 +reminder
+# min_test = max_train
+# max_test = count + reminder
+#
+# #Extend the respective list with ClassLabels(y)/Features(X)
+# label_train.extend(classLabels[min_train:max_train])
+# label_test.extend(classLabels[min_test:max_test])
+# data_train.extend(X[min_train:max_train])
+# data_test.extend(X[min_test:max_test])
+#
+# reminder = reminder + count
+#
+# return np.array(data_train), np.array(data_test), np.array(label_train).astype(int), np.array(label_test).astype(int)
- return (X_train, X_test, y_train, y_test)
+# def calcTrainTest(X,y,split):
+# X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=split)
+#
+# return (X_train, X_test, y_train, y_test)
# Classifiers
diff --git a/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py b/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py
index 07b3b1a1226356e2f75a8c013bd583f52c524a21..949d48f14c0cbcf0e065bac03bc10487a80a0c8f 100644
--- a/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py
+++ b/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py
@@ -29,7 +29,7 @@ __status__ = "Prototype" # Production, Development, Prototype
__date__ = 2016-03-25
-def ExecMonoview_multicore(name, labelsNames, learningRate, nbFolds, datasetFileIndex, databaseType, path, statsIter, gridSearch=True,
+def ExecMonoview_multicore(directory, name, labelsNames, learningRate, nbFolds, datasetFileIndex, databaseType, path, statsIter, gridSearch=True,
metrics=[["accuracy_score", None]], nIter=30, **args):
DATASET = h5py.File(path+name+str(datasetFileIndex)+".hdf5", "r")
kwargs = args["args"]
@@ -37,11 +37,11 @@ def ExecMonoview_multicore(name, labelsNames, learningRate, nbFolds, datasetFile
neededViewIndex = views.index(kwargs["feat"])
X = DATASET.get("View"+str(neededViewIndex))
Y = DATASET.get("Labels").value
- return ExecMonoview(X, Y, name, labelsNames, learningRate, nbFolds, 1, databaseType, path, statsIter, gridSearch=gridSearch,
+ return ExecMonoview(directory, X, Y, name, labelsNames, learningRate, nbFolds, 1, databaseType, path, statsIter, gridSearch=gridSearch,
metrics=metrics, nIter=nIter, **args)
-def ExecMonoview(X, Y, name, labelsNames, learningRate, nbFolds, nbCores, databaseType, path, statsIter, gridSearch=True,
+def ExecMonoview(directory, X, Y, name, labelsNames, learningRate, nbFolds, nbCores, databaseType, path, statsIter, gridSearch=True,
metrics=[["accuracy_score", None]], nIter=30, **args):
logging.debug("Start:\t Loading data")
try:
@@ -63,7 +63,7 @@ def ExecMonoview(X, Y, name, labelsNames, learningRate, nbFolds, nbCores, databa
y_tests = []
y_train_preds = []
y_test_preds = []
- for iterationStat in range(1):
+ for iterationStat in range(statsIter):
# Calculate Train/Test data
logging.debug("Start:\t Determine Train/Test split"+" for iteration "+str(iterationStat+1))
testIndices = ClassifMonoView.splitDataset(Y, nbClass, learningRate, datasetLength)
@@ -116,7 +116,7 @@ def ExecMonoview(X, Y, name, labelsNames, learningRate, nbFolds, nbCores, databa
labelsString = "-".join(labelsNames)
timestr = time.strftime("%Y%m%d-%H%M%S")
CL_type_string = CL_type
- outputFileName = "Results/" + timestr + "Results-" + CL_type_string + "-" + labelsString + \
+ outputFileName = directory + timestr + "Results-" + CL_type_string + "-" + labelsString + \
'-learnRate' + str(learningRate) + '-' + name + "-" + feat
outputTextFile = open(outputFileName + '.txt', 'w')
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py
index 4e9b1c76f2d680c6310167abc7c514113b8f3e0b..02c0560086b4313ed138783e3174f492e9226c6b 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py
@@ -1,6 +1,6 @@
from sklearn.ensemble import AdaBoostClassifier
from sklearn.pipeline import Pipeline
-from sklearn.grid_search import RandomizedSearchCV
+from sklearn.model_selection import RandomizedSearchCV
from sklearn.tree import DecisionTreeClassifier
import Metrics
from scipy.stats import randint
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/DecisionTree.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/DecisionTree.py
index f9cb2679a470bd3977d85d277ab1b90d450dbb3e..8c37293465101abfeda7017b1ec10c80f2741a1c 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/DecisionTree.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/DecisionTree.py
@@ -1,6 +1,6 @@
from sklearn.tree import DecisionTreeClassifier
from sklearn.pipeline import Pipeline # Pipelining in classification
-from sklearn.grid_search import RandomizedSearchCV
+from sklearn.model_selection import RandomizedSearchCV
import Metrics
from scipy.stats import randint
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/KNN.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/KNN.py
index 9105e37c1d5caa97bdfb5588f9e315f427373367..6ed4dd893760cd89480dc715830ee051562388f2 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/KNN.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/KNN.py
@@ -1,6 +1,6 @@
from sklearn.neighbors import KNeighborsClassifier
from sklearn.pipeline import Pipeline # Pipelining in classification
-from sklearn.grid_search import RandomizedSearchCV
+from sklearn.model_selection import RandomizedSearchCV
import Metrics
from scipy.stats import randint
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/RandomForest.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/RandomForest.py
index f0f24ee1b2dcdc87e550e1505d558b3dbb6abbfc..16a4646cdc7f8fd0e0f06edbcf12824b50b81622 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/RandomForest.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/RandomForest.py
@@ -1,6 +1,6 @@
from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline
-from sklearn.grid_search import RandomizedSearchCV
+from sklearn.model_selection import RandomizedSearchCV
import Metrics
from scipy.stats import randint
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SGD.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SGD.py
index 59026a6628b1fff9551316f217daba5835b7a6b4..8912505909feb9370e363c2bd5c41a3d8be73795 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SGD.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SGD.py
@@ -1,6 +1,6 @@
from sklearn.linear_model import SGDClassifier
from sklearn.pipeline import Pipeline # Pipelining in classification
-from sklearn.grid_search import RandomizedSearchCV
+from sklearn.model_selection import RandomizedSearchCV
import Metrics
from scipy.stats import uniform
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMLinear.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMLinear.py
index 4140f7a3b0631534dfb5899539ea04538c757211..c6b7bbe2ee3bf885efab73edd047e17d3e114840 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMLinear.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMLinear.py
@@ -1,6 +1,6 @@
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline # Pipelining in classification
-from sklearn.grid_search import RandomizedSearchCV
+from sklearn.model_selection import RandomizedSearchCV
import Metrics
from scipy.stats import randint
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMPoly.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMPoly.py
index 2beb829592f6b5e9b78c442cc0167b456ba4fc49..1a719a83b4ca38a68b8587913537b696c8dc1d09 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMPoly.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMPoly.py
@@ -1,6 +1,6 @@
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline # Pipelining in classification
-from sklearn.grid_search import RandomizedSearchCV
+from sklearn.model_selection import RandomizedSearchCV
import Metrics
from scipy.stats import randint
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMRBF.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMRBF.py
index 760395b930d641b3f4a826dd3f47fd85a11b8317..ed4ddda7a86f0ea65d35cde3adfec04a10626220 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMRBF.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMRBF.py
@@ -1,6 +1,6 @@
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline # Pipelining in classification
-from sklearn.grid_search import RandomizedSearchCV
+from sklearn.model_selection import RandomizedSearchCV
import Metrics
from scipy.stats import randint
diff --git a/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py b/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py
index 37e02981a723e109dd5bc9b42e919e502247bf20..4e482a3399e57a2613e5120e9b1806026c608e98 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py
@@ -23,14 +23,14 @@ __status__ = "Prototype" # Production, Development, P
-def ExecMultiview_multicore(coreIndex, name, learningRate, nbFolds, databaseType, path, LABELS_DICTIONARY , statsIter,
+def ExecMultiview_multicore(directory, coreIndex, name, learningRate, nbFolds, databaseType, path, LABELS_DICTIONARY , statsIter,
gridSearch=False, nbCores=1, metrics=None, nIter=30, **arguments):
DATASET = h5py.File(path+name+str(coreIndex)+".hdf5", "r")
- return ExecMultiview(DATASET, name, learningRate, nbFolds, 1, databaseType, path, LABELS_DICTIONARY, statsIter,
+ return ExecMultiview(directory, DATASET, name, learningRate, nbFolds, 1, databaseType, path, LABELS_DICTIONARY, statsIter,
gridSearch=gridSearch, metrics=metrics, nIter=nIter, **arguments)
-def ExecMultiview(DATASET, name, learningRate, nbFolds, nbCores, databaseType, path, LABELS_DICTIONARY, statsIter,
+def ExecMultiview(directory, DATASET, name, learningRate, nbFolds, nbCores, databaseType, path, LABELS_DICTIONARY, statsIter,
gridSearch=False, metrics=None, nIter=30, **kwargs):
datasetLength = DATASET.get("Metadata").attrs["datasetLength"]
@@ -126,7 +126,7 @@ def ExecMultiview(DATASET, name, learningRate, nbFolds, nbCores, databaseType, p
CL_type_string += "-"+classificationKWARGS["fusionType"]+"-"+classificationKWARGS["fusionMethod"]+"-"+"-".join(classificationKWARGS["classifiersNames"])
elif CL_type=="Mumbo":
CL_type_string += "-"+"-".join(classificationKWARGS["classifiersNames"])
- outputFileName = "Results/" + timestr + "Results-" + CL_type_string + "-" + featureString + '-' + labelsString + \
+ outputFileName = directory + timestr + "Results-" + CL_type_string + "-" + featureString + '-' + labelsString + \
'-learnRate' + str(learningRate) + '-' + name
outputTextFile = open(outputFileName + '.txt', 'w')
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py
index 439e4d53bc4b1aade3471b28b47590f198101a99..1c97fe0a21e69e2742c12fd22ca9a693e446340c 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py
@@ -96,6 +96,8 @@ class SCMForLinear(LateFusionClassifier):
getV(DATASET, viewIndex, usedIndices))
accus.append(accuracy_score(DATASET.get("Labels").value[usedIndices], monoviewDecision))
monoviewDecisions[:, index] = monoviewDecision
+ print monoviewDecisions
+ exit()
features = self.generateInteractions(monoviewDecisions)
predictedLabels = self.SCMClassifier.predict(features)
else:
@@ -158,10 +160,12 @@ class SCMForLinear(LateFusionClassifier):
def generateInteractions(self, monoViewDecisions):
if type(self.order)==type(None):
order = monoViewDecisions.shape[1]
- genratedIntercations = [monoViewDecisions[:,i] for i in range(monoViewDecisions.shape[1])]
if self.order==1:
+ print monoViewDecisions
return monoViewDecisions
+
else:
+ genratedIntercations = [monoViewDecisions[:,i] for i in range(monoViewDecisions.shape[1])]
for orderIndex in range(self.order-1):
combins = itertools.combinations(range(monoViewDecisions.shape[1]), orderIndex+2)
for combin in combins:
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
index 5dcb33346e6a897c2e3e6b74513bf3739057ba3a..c4a1c60bcfb3a5d512d4e8dce6be6257c303d50b 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
@@ -55,20 +55,15 @@ class WeightedLinear(LateFusionClassifier):
if type(viewsIndices)==type(None):
viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
nbView = len(viewsIndices)
- self.weights = self.weights/float(max(self.weights))
+ self.weights = self.weights/float(sum(self.weights))
if usedIndices == None:
usedIndices = range(DATASET.get("Metadata").attrs["datasetLength"])
if usedIndices:
- predictedLabels = []
viewScores = np.zeros((nbView, len(usedIndices), DATASET.get("Metadata").attrs["nbClass"]))
for index, viewIndex in enumerate(viewsIndices):
- viewScores[index] = self.monoviewClassifiers[index].predict_proba(
- getV(DATASET, viewIndex, usedIndices))
- for currentIndex, usedIndex in enumerate(usedIndices):
- predictedLabel = np.argmax(np.array(
- [max(viewScore) * weight for viewScore, weight in zip(viewScores[:, currentIndex], self.weights)],
- dtype=float))
- predictedLabels.append(predictedLabel)
+ viewScores[index] = np.array(self.monoviewClassifiers[index].predict_proba(
+ getV(DATASET, viewIndex, usedIndices)))*self.weights[index]
+ predictedLabels = np.argmax(np.sum(viewScores, axis=0), axis=1)
else:
predictedLabels = []
diff --git a/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py b/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py
index 34b8a3947f208026622f762b526d853dac03007d..49150a1de5c3a35faf487d61aa8287d57c3f78ee 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py
@@ -183,7 +183,7 @@ def getClassicDBcsv(views, pathF, nameDB, NB_CLASS, LABELS_NAMES):
nbLabelsAvailable+=1
LABELS_NAMES = [line.strip().split(";")[1] for lineIdx, line in enumerate(labelsNamesFile) if lineIdx in np.random.randint(nbLabelsAvailable, size=NB_CLASS)]
fullLabels = np.genfromtxt(pathF + nameDB + '-ClassLabels.csv', delimiter=',').astype(int)
- labelsDictionary = dict((classIndice, labelName) for (classIndice, labelName) in
+ labelsDictionary = dict((classIndex, labelName) for (classIndex, labelName) in
[(int(line.strip().split(";")[0]),line.strip().split(";")[1])for lineIndex, line in enumerate(labelsNamesFile) if line.strip().split(";")[0] in LABELS_NAMES])
if len(set(fullLabels))>NB_CLASS:
usedIndices = getPositions(labelsDictionary.keys(), fullLabels)
@@ -198,12 +198,12 @@ def getClassicDBcsv(views, pathF, nameDB, NB_CLASS, LABELS_NAMES):
viewDset.attrs["binary"] = False
labelsDset = datasetFile.create_dataset("Labels", fullLabels[usedIndices].shape, data=fullLabels[usedIndices])
- #labelsDset.attrs["labelsDictionary"] = labelsDictionary
+ labelsDset.attrs["labels"] = [labelName for index, labelName in labelsDictionary.iteritems()]
+ labelsDset.attrs["labels_indices"] = [labelIndex for labelIndex, labelName in labelsDictionary.iteritems()]
metaDataGrp = datasetFile.create_group("Metadata")
metaDataGrp.attrs["nbView"] = len(views)
metaDataGrp.attrs["nbClass"] = NB_CLASS
- print NB_CLASS
metaDataGrp.attrs["datasetLength"] = len(fullLabels[usedIndices])
datasetFile.close()
datasetFile = h5py.File(pathF+nameDB+".hdf5", "r")
@@ -212,34 +212,38 @@ def getClassicDBcsv(views, pathF, nameDB, NB_CLASS, LABELS_NAMES):
def getClassicDBhdf5(views, pathF, nameDB, NB_CLASS, LABELS_NAMES):
datasetFile = h5py.File(pathF+nameDB+".hdf5", "r")
- fullLabels = datasetFile.get("Labels").value
- fullLabelsDictionary = datasetFile.get("Labels").attrs["labelsDictionary"]
- fullNbClass = datasetFile.get("Metadata").attrs["nbClass"]
- if len(LABELS_NAMES)!=NB_CLASS:
- LABELS_NAMES = [value for index, value in fullLabelsDictionary.iteritems()
- if index in np.random.randint(fullNbClass, size=NB_CLASS)]
- labelsDictionary = dict((classIndice, labelName) for (classIndice, labelName)
- in fullLabelsDictionary.iteritems() if labelName in LABELS_NAMES)
- if len(set(fullLabels))>NB_CLASS:
- usedIndices = getPositions(labelsDictionary.keys(), fullLabels)
- else:
- usedIndices = range(len(fullLabels))
- tempDatasetFile = datasetFile = h5py.File(pathF+nameDB+"_temp.hdf5", "w")
- for viewIndex, view in enumerate(views):
- viewMatrix = datasetFile.get("View"+str(viewIndex)).value[:, usedIndices]
- viewDset = tempDatasetFile.create_dataset("View"+str(viewIndex), viewMatrix.shape, data=viewMatrix)
- viewDset.attrs["name"] = view
-
- labelsDset = tempDatasetFile.create_dataset("Labels", fullLabels[usedIndices].shape, data=fullLabels[usedIndices])
- labelsDset.attrs["labelsDictionary"] = labelsDictionary
-
- metaDataGrp = tempDatasetFile.create_group("Metadata")
- metaDataGrp.attrs["nbView"] = len(views)
- metaDataGrp.attrs["nbClass"] = NB_CLASS
- metaDataGrp.attrs["datasetLength"] = len(fullLabels[usedIndices])
- datasetFile.close()
- tempDatasetFile.close()
- datasetFile = h5py.File(pathF+nameDB+"_temp.hdf5", "r")
+ fullLabels = datasetFile.get("Labels")
+ labelsDictionary = dict((labelIndex, labelName) for labelIndex, labelName in
+ zip(fullLabels.attrs["labels_indices"], fullLabels.attrs["labels"]))
+ # #datasetFile.get("Labels").attrs["labelsDictionary"]
+ #
+ # fullNbClass = datasetFile.get("Metadata").attrs["nbClass"]
+ # if len(LABELS_NAMES)!=NB_CLASS:
+ # LABELS_NAMES = [value for index, value in fullLabelsDictionary.iteritems()
+ # if index in np.random.randint(fullNbClass, size=NB_CLASS)]
+ # usableLabels = [labelName for index, labelName in fullLabelsDictionary.iteritems() if labelName in LABELS_NAMES]
+ # labelsDictionary = dict((classIndex, labelName) for classIndex, labelName
+ # in enumerate(usableLabels))
+ # if len(set(fullLabels))>NB_CLASS:
+ # usedIndices = getPositions(labelsDictionary.keys(), fullLabels)
+ # else:
+ # usedIndices = range(len(fullLabels))
+ # tempDatasetFile = datasetFile = h5py.File(pathF+nameDB+"_temp.hdf5", "w")
+ # for viewIndex, view in enumerate(views):
+ # viewMatrix = datasetFile.get("View"+str(viewIndex)).value[:, usedIndices]
+ # viewDset = tempDatasetFile.create_dataset("View"+str(viewIndex), viewMatrix.shape, data=viewMatrix)
+ # viewDset.attrs["name"] = view
+ #
+ # labelsDset = tempDatasetFile.create_dataset("Labels", fullLabels[usedIndices].shape, data=fullLabels[usedIndices])
+ # labelsDset.attrs["labelsDictionary"] = labelsDictionary
+ #
+ # metaDataGrp = tempDatasetFile.create_group("Metadata")
+ # metaDataGrp.attrs["nbView"] = len(views)
+ # metaDataGrp.attrs["nbClass"] = NB_CLASS
+ # metaDataGrp.attrs["datasetLength"] = len(fullLabels[usedIndices])
+ # datasetFile.close()
+ # tempDatasetFile.close()
+ # datasetFile = h5py.File(pathF+nameDB+"_temp.hdf5", "r")
return datasetFile, labelsDictionary
diff --git a/Code/MonoMutliViewClassifiers/ResultAnalysis.py b/Code/MonoMutliViewClassifiers/ResultAnalysis.py
index 694a63335a23a46e26c9f96653440e482cec99b6..3f9f90285f8e3e0cdb6194862a852917ddd77ec0 100644
--- a/Code/MonoMutliViewClassifiers/ResultAnalysis.py
+++ b/Code/MonoMutliViewClassifiers/ResultAnalysis.py
@@ -36,19 +36,26 @@ def genNamesFromRes(mono, multi):
return names
-def resultAnalysis(benchmark, results, name, times, metrics):
+def resultAnalysis(benchmark, results, name, times, metrics, directory):
mono, multi = results
for metric in metrics:
names = genNamesFromRes(mono, multi)
nbResults = len(mono)+len(multi)
- validationScores = [float(res[1][2][metric[0]][0]) for res in mono]
- validationScores += [float(scores[metric[0]][0]) for a, b, scores, c in multi]
- validationSTD = [float(res[1][2][metric[0]][2]) for res in mono]
- validationSTD += [float(scores[metric[0]][2]) for a, b, scores, c in multi]
- trainScores = [float(res[1][2][metric[0]][1]) for res in mono]
- trainScores += [float(scores[metric[0]][1]) for a, b, scores, c in multi]
- trainSTD = [float(res[1][2][metric[0]][3]) for res in mono]
- trainSTD += [float(scores[metric[0]][3]) for a, b, scores, c in multi]
+ validationScores = [float(res[1][2][metric[0]][1]) for res in mono]
+ validationScores += [float(scores[metric[0]][1]) for a, b, scores, c in multi]
+ validationSTD = [float(res[1][2][metric[0]][3]) for res in mono]
+ validationSTD += [float(scores[metric[0]][3]) for a, b, scores, c in multi]
+ trainScores = [float(res[1][2][metric[0]][0]) for res in mono]
+ trainScores += [float(scores[metric[0]][0]) for a, b, scores, c in multi]
+ trainSTD = [float(res[1][2][metric[0]][2]) for res in mono]
+ trainSTD += [float(scores[metric[0]][2]) for a, b, scores, c in multi]
+
+ validationScores = np.array(validationScores)
+ validationSTD = np.array(validationSTD)
+ trainScores = np.array(trainScores)
+ trainSTD = np.array(trainSTD)
+ names = np.array(names)
+
f = pylab.figure(figsize=(40, 30))
width = 0.35 # the width of the bars
fig = plt.gcf()
@@ -58,20 +65,27 @@ def resultAnalysis(benchmark, results, name, times, metrics):
metricKWARGS = dict((index, metricConfig) for index, metricConfig in enumerate(metric[1]))
else:
metricKWARGS = {}
+ sorted_indices = np.argsort(validationScores)
+ validationScores = validationScores[sorted_indices]
+ validationSTD = validationSTD[sorted_indices]
+ trainScores = trainScores[sorted_indices]
+ trainSTD = trainSTD[sorted_indices]
+ names = names[sorted_indices]
+
ax.set_title(getattr(Metrics, metric[0]).getConfig(**metricKWARGS)+" on validation set for each classifier")
rects = ax.bar(range(nbResults), validationScores, width, color="r", yerr=validationSTD)
rect2 = ax.bar(np.arange(nbResults)+width, trainScores, width, color="0.7", yerr=trainSTD)
autolabel(rects, ax)
autolabel(rect2, ax)
- ax.legend((rects[0], rect2[0]), ('Train', 'Test'))
+ ax.legend((rects[0], rect2[0]), ('Test', 'Train'))
ax.set_xticks(np.arange(nbResults)+width)
ax.set_xticklabels(names, rotation="vertical")
- f.savefig("Results/"+time.strftime("%Y%m%d-%H%M%S")+"-"+name+"-"+metric[0]+".png")
+ f.savefig(directory+time.strftime("%Y%m%d-%H%M%S")+"-"+name+"-"+metric[0]+".png")
logging.info("Extraction time : "+str(times[0])+"s, Monoview time : "+str(times[1])+"s, Multiview Time : "+str(times[2])+"s")
-def analyzeLabels(labelsArrays, realLabels, results):
+def analyzeLabels(labelsArrays, realLabels, results, directory):
mono, multi = results
classifiersNames = genNamesFromRes(mono, multi)
nbClassifiers = len(classifiersNames)
@@ -94,4 +108,4 @@ def analyzeLabels(labelsArrays, realLabels, results):
plt.xticks(ticks, labels, rotation="vertical")
cbar = fig.colorbar(cax, ticks=[0, 1])
cbar.ax.set_yticklabels(['Wrong', ' Right'])
- fig.savefig("Results/"+time.strftime("%Y%m%d-%H%M%S")+"error_analysis.png")
\ No newline at end of file
+ fig.savefig(directory+time.strftime("%Y%m%d-%H%M%S")+"-error_analysis.png")
\ No newline at end of file
diff --git a/Readme.md b/Readme.md
index 901f721319933b09f8436f8c674ddd5db55fdd5a..680b2c6446134035fb454446bff2ba5a167af2a0 100644
--- a/Readme.md
+++ b/Readme.md
@@ -1,4 +1,4 @@
-# Benchmark de classification mono et multi-vue
+# Mono- and Multi-view classification benchmark
This project aims to be an easy-to use solution to run a prior benchmark on a dataset abd evaluate mono- and multi-view algorithms capacity to classify it correctly.
@@ -42,4 +42,4 @@ Results will be stored in multiview-machine-learning-omis/Code/MonoMultiViewClas
## Authors
-* **Baptiste BAUVIN**
+* **Baptiste BAUVIN**