diff --git a/Code/MonoMutliViewClassifiers/ExecClassif.py b/Code/MonoMutliViewClassifiers/ExecClassif.py
index 5aaf18c5bf1f444c0c3ebeb9501949ddebe9556e..d79229431aee4ce2feeeb356c5959165d7b9b37b 100644
--- a/Code/MonoMutliViewClassifiers/ExecClassif.py
+++ b/Code/MonoMutliViewClassifiers/ExecClassif.py
@@ -499,6 +499,8 @@ if metrics == [[""]]:
metricsNames = [name for _, name, isPackage
in pkgutil.iter_modules(['Metrics']) if not isPackage and name!="log_loss"]
metrics = [[metricName] for metricName in metricsNames]
+ metrics[0]=metrics[1]
+ metrics[1]=["accuracy_score"]
for metricIndex, metric in enumerate(metrics):
if len(metric)==1:
metrics[metricIndex]=[metric[0], None]
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py
index 02c0560086b4313ed138783e3174f492e9226c6b..86bf631b9f24f511bee5860b4d84dcdf6b3dfec1 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py
@@ -22,7 +22,6 @@ def fit(DATASET, CLASS_LABELS, NB_CORES=1,**kwargs):
def gridSearch(X_train, y_train, nbFolds=4, metric=["accuracy_score", None], nIter=30, nbCores=1):
-
pipeline = Pipeline([('classifier', AdaBoostClassifier())])
param= {"classifier__n_estimators": randint(1, 15),
diff --git a/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py b/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py
index 4e482a3399e57a2613e5120e9b1806026c608e98..25e9a8f9b88a6585a2629b458ee640f7589522d3 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py
@@ -62,8 +62,8 @@ def ExecMultiview(directory, DATASET, name, learningRate, nbFolds, nbCores, data
classifiersIterations = []
classifierPackage = globals()[CL_type] # Permet d'appeler un module avec une string
classifierModule = getattr(classifierPackage, CL_type)
- classifierClass = getattr(classifierModule, CL_type)
- classifierGridSearch = getattr(classifierModule, "gridSearch_hdf5")
+ # classifierClass = getattr(classifierModule, CL_type)
+ # classifierGridSearch = getattr(classifierModule, "gridSearch_hdf5")
analysisModule = getattr(classifierPackage, "analyzeResults")
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py
index 97c0ac4ac70692a7c929e98e2ef97736e37514bf..d0c1fbf2d8718a8f61f303058ec3ea701d48df15 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py
@@ -14,25 +14,25 @@ def genParamsSets(classificationKWARGS, nIter=1):
return paramsSets
-def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
- if type(viewsIndices)==type(None):
- viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
- nbView = len(viewsIndices)
- bestScore = 0.0
- bestConfig = None
- if classificationKWARGS["fusionMethodConfig"][0] is not None:
- for i in range(nIter):
- randomWeightsArray = np.random.random_sample(nbView)
- normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
- classificationKWARGS["fusionMethodConfig"][0] = normalizedArray
- classifier = WeightedLinear(1, **classificationKWARGS)
- classifier.fit_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
- predictedLabels = classifier.predict_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
- accuracy = accuracy_score(DATASET.get("Labels")[trainIndices], predictedLabels)
- if accuracy > bestScore:
- bestScore = accuracy
- bestConfig = normalizedArray
- return [bestConfig]
+# def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
+# if type(viewsIndices)==type(None):
+# viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
+# nbView = len(viewsIndices)
+# bestScore = 0.0
+# bestConfig = None
+# if classificationKWARGS["fusionMethodConfig"][0] is not None:
+# for i in range(nIter):
+# randomWeightsArray = np.random.random_sample(nbView)
+# normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
+# classificationKWARGS["fusionMethodConfig"][0] = normalizedArray
+# classifier = WeightedLinear(1, **classificationKWARGS)
+# classifier.fit_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
+# predictedLabels = classifier.predict_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
+# accuracy = accuracy_score(DATASET.get("Labels")[trainIndices], predictedLabels)
+# if accuracy > bestScore:
+# bestScore = accuracy
+# bestConfig = normalizedArray
+# return [bestConfig]
class WeightedLinear(EarlyFusionClassifier):
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py
index de6b0193eeb06171f543e608d5e82e8b4b7bb681..88628f66e93bf891f543d7ffad51359a3131516e 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py
@@ -13,26 +13,26 @@ def genParamsSets(classificationKWARGS, nIter=1):
normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
paramsSets.append([normalizedArray])
return paramsSets
-
-def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
- if type(viewsIndices)==type(None):
- viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
- nbView = len(viewsIndices)
- bestScore = 0.0
- bestConfig = None
- if classificationKWARGS["fusionMethodConfig"][0] is not None:
- for i in range(nIter):
- randomWeightsArray = np.random.random_sample(nbView)
- normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
- classificationKWARGS["fusionMethodConfig"][0] = normalizedArray
- classifier = BayesianInference(1, **classificationKWARGS)
- classifier.fit_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
- predictedLabels = classifier.predict_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
- accuracy = accuracy_score(DATASET.get("Labels")[trainIndices], predictedLabels)
- if accuracy > bestScore:
- bestScore = accuracy
- bestConfig = normalizedArray
- return [bestConfig]
+#
+# def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
+# if type(viewsIndices)==type(None):
+# viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
+# nbView = len(viewsIndices)
+# bestScore = 0.0
+# bestConfig = None
+# if classificationKWARGS["fusionMethodConfig"][0] is not None:
+# for i in range(nIter):
+# randomWeightsArray = np.random.random_sample(nbView)
+# normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
+# classificationKWARGS["fusionMethodConfig"][0] = normalizedArray
+# classifier = BayesianInference(1, **classificationKWARGS)
+# classifier.fit_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
+# predictedLabels = classifier.predict_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
+# accuracy = accuracy_score(DATASET.get("Labels")[trainIndices], predictedLabels)
+# if accuracy > bestScore:
+# bestScore = accuracy
+# bestConfig = normalizedArray
+# return [bestConfig]
class BayesianInference(LateFusionClassifier):
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/MajorityVoting.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/MajorityVoting.py
index 2ec709517d1011846d38fa2a3194e987b1fd506d..9ea51595c60483f8ace89bc959c9e49debc761e6 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/MajorityVoting.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/MajorityVoting.py
@@ -14,25 +14,25 @@ def genParamsSets(classificationKWARGS, nIter=1):
paramsSets.append([normalizedArray])
return paramsSets
-def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
- if type(viewsIndices)==type(None):
- viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
- nbView = len(viewsIndices)
- bestScore = 0.0
- bestConfig = None
- if classificationKWARGS["fusionMethodConfig"][0] is not None:
- for i in range(nIter):
- randomWeightsArray = np.random.random_sample(nbView)
- normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
- classificationKWARGS["fusionMethodConfig"][0] = normalizedArray
- classifier = MajorityVoting(1, **classificationKWARGS)
- classifier.fit_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
- predictedLabels = classifier.predict_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
- accuracy = accuracy_score(DATASET.get("Labels")[trainIndices], predictedLabels)
- if accuracy > bestScore:
- bestScore = accuracy
- bestConfig = normalizedArray
- return [bestConfig]
+# def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
+# if type(viewsIndices)==type(None):
+# viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
+# nbView = len(viewsIndices)
+# bestScore = 0.0
+# bestConfig = None
+# if classificationKWARGS["fusionMethodConfig"][0] is not None:
+# for i in range(nIter):
+# randomWeightsArray = np.random.random_sample(nbView)
+# normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
+# classificationKWARGS["fusionMethodConfig"][0] = normalizedArray
+# classifier = MajorityVoting(1, **classificationKWARGS)
+# classifier.fit_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
+# predictedLabels = classifier.predict_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
+# accuracy = accuracy_score(DATASET.get("Labels")[trainIndices], predictedLabels)
+# if accuracy > bestScore:
+# bestScore = accuracy
+# bestConfig = normalizedArray
+# return [bestConfig]
class MajorityVoting(LateFusionClassifier):
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py
index 73671d32459bd3734638c3cf214c9d5f821410e8..6af655646d903c356d6ad77f0a406329795d2c73 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py
@@ -26,28 +26,28 @@ def genParamsSets(classificationKWARGS, nIter=1):
return paramsSets
-def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
- if type(viewsIndices)==type(None):
- viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
- nbView = len(viewsIndices)
- bestScore = 0.0
- bestConfig = None
- for i in range(nIter):
- max_attributes = random.randint(1, 20)
- p = random.random()
- model = random.choice(["conjunction", "disjunction"])
- order = random.randint(1,nbView)
- randomWeightsArray = np.random.random_sample(nbView)
- normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
- classificationKWARGS["fusionMethodConfig"][0] = [p, max_attributes, model, order]
- classifier = SCMForLinear(1, **classificationKWARGS)
- classifier.fit_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
- predictedLabels = classifier.predict_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
- accuracy = accuracy_score(DATASET.get("Labels")[trainIndices], predictedLabels)
- if accuracy > bestScore:
- bestScore = accuracy
- bestConfig = [p, max_attributes, model, order]
- return [bestConfig]
+# def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
+# if type(viewsIndices)==type(None):
+# viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
+# nbView = len(viewsIndices)
+# bestScore = 0.0
+# bestConfig = None
+# for i in range(nIter):
+# max_attributes = random.randint(1, 20)
+# p = random.random()
+# model = random.choice(["conjunction", "disjunction"])
+# order = random.randint(1,nbView)
+# randomWeightsArray = np.random.random_sample(nbView)
+# normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
+# classificationKWARGS["fusionMethodConfig"][0] = [p, max_attributes, model, order]
+# classifier = SCMForLinear(1, **classificationKWARGS)
+# classifier.fit_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
+# predictedLabels = classifier.predict_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
+# accuracy = accuracy_score(DATASET.get("Labels")[trainIndices], predictedLabels)
+# if accuracy > bestScore:
+# bestScore = accuracy
+# bestConfig = [p, max_attributes, model, order]
+# return [bestConfig]
class SCMForLinear(LateFusionClassifier):
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SVMForLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SVMForLinear.py
index 066cf3d1470a2c94e16388356417edf7e367d770..894dc7fe7f359a7e1ba1378d8c00e6c2dbe57f9b 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SVMForLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SVMForLinear.py
@@ -13,8 +13,8 @@ def genParamsSets(classificationKWARGS, nIter=1):
paramsSets.append([])
return paramsSets
-def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
- return None
+# def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
+# return None
class SVMForLinear(LateFusionClassifier):
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
index c4a1c60bcfb3a5d512d4e8dce6be6257c303d50b..caf01b88326dfaed6b3540cd2a785866b6bdbcc9 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
@@ -15,25 +15,25 @@ def genParamsSets(classificationKWARGS, nIter=1):
return paramsSets
-def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
- if type(viewsIndices)==type(None):
- viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
- nbView = len(viewsIndices)
- bestScore = 0.0
- bestConfig = None
- if classificationKWARGS["fusionMethodConfig"][0] is not None:
- for i in range(nIter):
- randomWeightsArray = np.random.random_sample(nbView)
- normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
- classificationKWARGS["fusionMethodConfig"][0] = normalizedArray
- classifier = WeightedLinear(1, **classificationKWARGS)
- classifier.fit_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
- predictedLabels = classifier.predict_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
- accuracy = accuracy_score(DATASET.get("Labels")[trainIndices], predictedLabels)
- if accuracy > bestScore:
- bestScore = accuracy
- bestConfig = normalizedArray
- return [bestConfig]
+# def gridSearch(DATASET, classificationKWARGS, trainIndices, nIter=30, viewsIndices=None):
+# if type(viewsIndices)==type(None):
+# viewsIndices = np.arange(DATASET.get("Metadata").attrs["nbView"])
+# nbView = len(viewsIndices)
+# bestScore = 0.0
+# bestConfig = None
+# if classificationKWARGS["fusionMethodConfig"][0] is not None:
+# for i in range(nIter):
+# randomWeightsArray = np.random.random_sample(nbView)
+# normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
+# classificationKWARGS["fusionMethodConfig"][0] = normalizedArray
+# classifier = WeightedLinear(1, **classificationKWARGS)
+# classifier.fit_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
+# predictedLabels = classifier.predict_hdf5(DATASET, trainIndices, viewsIndices=viewsIndices)
+# accuracy = accuracy_score(DATASET.get("Labels")[trainIndices], predictedLabels)
+# if accuracy > bestScore:
+# bestScore = accuracy
+# bestConfig = normalizedArray
+# return [bestConfig]
class WeightedLinear(LateFusionClassifier):
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/DecisionTree.py b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/DecisionTree.py
index fdf6519bf0799e8581274b4bce6761f1ab025be2..0cc9ceaa5543e9f6ca7f4ea07b8668ec4c031791 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/DecisionTree.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/DecisionTree.py
@@ -4,7 +4,9 @@ import numpy as np
from ModifiedMulticlass import OneVsRestClassifier
from SubSampling import subSample
import logging
-# Add weights
+# Add weights
+
+import Metrics
def DecisionTree(data, labels, arg, weights):
depth = int(arg[0])
@@ -37,6 +39,17 @@ def gridSearch(data, labels, metric="accuracy_score"):
bestResults = []
classifier = tree.DecisionTreeClassifier(max_depth=1)
preliminary_accuracies = np.zeros(50)
+ # metricModule = getattr(Metrics, metric[0])
+ # if metric[1]!=None:
+ # metricKWARGS = dict((index, metricConfig) for index, metricConfig in enumerate(metric[1]))
+ # else:
+ # metricKWARGS = {}
+ # if metricModule.getConfig()[-14]=="h":
+ # baseScore = -1000.0
+ # isBetter = "higher"
+ # else:
+ # baseScore = 1000.0
+ # isBetter = "lower"
for i in range(50):
subSampledData, subSampledLabels, subSampledWeights = subSample(data, labels, 0.05)
classifier.fit(subSampledData, subSampledLabels)
@@ -112,7 +125,7 @@ def getBestSetting(bestSettings, bestResults):
diffTo52 = abs(0.55-result)
bestResult = result
bestSettingsIndex = resultIndex
- logging.debug("\t\tInfo:\t Best Reslut : "+str(result))
+ logging.debug("\t\tInfo:\t Best Result : "+str(result))
return map(lambda p: round(p, 4), bestSettings[bestSettingsIndex])
# return map(round(,4), bestSettings[bestSettingsIndex])
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py
index b4c7d5a01c456b768e78293a402cd64167685195..1d12dc86def9631dc977229b323bd19e7a09cc39 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py
@@ -37,8 +37,8 @@ def trainWeakClassifier(classifierName, monoviewDataset, CLASS_LABELS,
def trainWeakClassifier_hdf5(classifierName, monoviewDataset, CLASS_LABELS, DATASET_LENGTH,
- viewIndice, classifier_config, viewName, iterIndex, costMatrices):
- weights = computeWeights(DATASET_LENGTH, iterIndex, viewIndice, CLASS_LABELS, costMatrices)
+ viewIndice, classifier_config, viewName, iterIndex, costMatrices, classifierIndex):
+ weights = computeWeights(DATASET_LENGTH, iterIndex, classifierIndex, CLASS_LABELS, costMatrices)
classifierModule = globals()[classifierName] # Permet d'appeler une fonction avec une string
classifierMethod = getattr(classifierModule, classifierName)
classifier, classes, isBad, averageAccuracy = classifierMethod(monoviewDataset, CLASS_LABELS, classifier_config, weights)
@@ -68,17 +68,23 @@ class Mumbo:
self.classifiersNames = kwargs["classifiersNames"]
self.classifiersConfigs = kwargs["classifiersConfigs"]
nbView = kwargs["nbView"]
+ self.nbCores = NB_CORES
+ self.iterIndex = 0
self.edges = np.zeros((self.maxIter, nbView))
self.alphas = np.zeros((self.maxIter, nbView))
self.generalAlphas = np.zeros(self.maxIter)
- self.nbCores = NB_CORES
- self.iterIndex = 0
self.bestClassifiers = []
- self.bestViews = np.zeros(self.maxIter, dtype=int)
+ self.bestViews = np.zeros(self.maxIter, dtype=int)-1
self.averageAccuracies = np.zeros((self.maxIter, nbView))
self.iterAccuracies = np.zeros(self.maxIter)
def initDataDependant(self, datasetLength, nbView, nbClass, labels):
+ self.edges = np.zeros((self.maxIter, nbView))
+ self.alphas = np.zeros((self.maxIter, nbView))
+ self.generalAlphas = np.zeros(self.maxIter)
+ self.bestClassifiers = []
+ self.bestViews = np.zeros(self.maxIter, dtype=int)-1
+ self.averageAccuracies = np.zeros((self.maxIter, nbView))
self.costMatrices = np.array([
np.array([
np.array([
@@ -160,7 +166,6 @@ class Mumbo:
self.iterIndex += 1
-
def predict_hdf5(self, DATASET, usedIndices=None, viewsIndices=None):
NB_CLASS = DATASET.get("Metadata").attrs["nbClass"]
if usedIndices == None:
@@ -176,8 +181,11 @@ class Mumbo:
for labelIndex, exampleIndex in enumerate(usedIndices):
votes = np.zeros(NB_CLASS)
for classifier, alpha, view in zip(self.bestClassifiers, self.alphas, self.bestViews):
- data = getV(DATASET, int(view), exampleIndex)
- votes[int(classifier.predict(np.array([data])))] += alpha[viewDict[view]]
+ if view != -1:
+ data = getV(DATASET, int(view), exampleIndex)
+ votes[int(classifier.predict(np.array([data])))] += alpha[viewDict[view]]
+ else:
+ pass
predictedLabels[labelIndex] = np.argmax(votes)
else:
predictedLabels = []
@@ -192,7 +200,6 @@ class Mumbo:
predictedProbas = np.zeros((DATASET_LENGTH, NB_CLASS))
for labelIndex, exampleIndex in enumerate(usedIndices):
- votes = np.zeros(NB_CLASS)
for classifier, alpha, view in zip(self.bestClassifiers, self.alphas, self.bestViews):
data = getV(DATASET, int(view), exampleIndex)
predictedProbas[labelIndex, int(classifier.predict(np.array([data])))] += alpha[view]
@@ -242,13 +249,13 @@ class Mumbo:
classifiersNames = self.classifiersNames
iterIndex = self.iterIndex
trainedClassifiersAndLabels = Parallel(n_jobs=NB_JOBS)(
- delayed(trainWeakClassifier_hdf5)(classifiersNames[viewIndex],
+ delayed(trainWeakClassifier_hdf5)(classifiersNames[classifierIndex],
getV(DATASET,viewIndex,trainIndices),
DATASET.get("Labels")[trainIndices],
DATASET_LENGTH,
- viewIndex, classifiersConfigs[viewIndex],
- DATASET.get("View"+str(viewIndex)).attrs["name"], iterIndex, costMatrices)
- for viewIndex in viewIndices)
+ viewIndex, classifiersConfigs[classifierIndex],
+ DATASET.get("View"+str(viewIndex)).attrs["name"], iterIndex, costMatrices, classifierIndex)
+ for classifierIndex, viewIndex in enumerate(viewIndices))
for viewFakeIndex, (classifier, labelsArray, isBad, averageAccuracy) in enumerate(trainedClassifiersAndLabels):
self.averageAccuracies[self.iterIndex, viewFakeIndex] = averageAccuracy
@@ -370,44 +377,44 @@ class Mumbo:
= -1 * np.sum(np.exp(self.generalFs[self.iterIndex, exampleIndice] -
self.generalFs[self.iterIndex, exampleIndice, classe]))
- def fit(self, DATASET, CLASS_LABELS, **kwargs):
- # Initialization
- DATASET_LENGTH = len(CLASS_LABELS)
- NB_VIEW = len(DATASET)
- NB_CLASS = len(set(CLASS_LABELS))
- bestViews = np.zeros(self.maxIter)
- bestClassifiers = []
-
- # Learning
- for i in range(self.maxIter):
- logging.debug('\t\tStart:\t Iteration ' + str(self.iterIndex + 1))
- classifiers, predictedLabels, areBad = self.trainWeakClassifiers(DATASET, CLASS_LABELS, NB_CLASS,
- DATASET_LENGTH, NB_VIEW)
- if areBad.all():
- logging.warning("All bad for iteration " + str(self.iterIndex))
-
- self.predictions[self.iterIndex] = predictedLabels
-
- for viewIndice in range(NB_VIEW):
- self.computeEdge(viewIndice, DATASET_LENGTH, CLASS_LABELS)
- if areBad[viewIndice]:
- self.alphas[self.iterIndex, viewIndice] = 0.
- else:
- self.alphas[self.iterIndex, viewIndice] = self.computeAlpha(self.edges[self.iterIndex,
- viewIndice])
- self.updateDs(CLASS_LABELS, NB_VIEW, DATASET_LENGTH)
- self.updateFs(NB_VIEW, DATASET_LENGTH, NB_CLASS)
-
- self.updateCostmatrices(NB_VIEW, DATASET_LENGTH, NB_CLASS, CLASS_LABELS)
- bestView, edge = self.chooseView(NB_VIEW, CLASS_LABELS, DATASET_LENGTH)
- self.bestViews[self.iterIndex] = bestView
- if areBad.all():
- self.generalAlphas[self.iterIndex] = 0.
- else:
- self.generalAlphas[self.iterIndex] = self.computeAlpha(edge)
- self.bestClassifiers.append(classifiers[bestView])
- self.updateGeneralFs(DATASET_LENGTH, NB_CLASS, bestView)
- self.updateGeneralCostMatrix(DATASET_LENGTH, NB_CLASS, CLASS_LABELS)
+ # def fit(self, DATASET, CLASS_LABELS, **kwargs):
+ # # Initialization
+ # DATASET_LENGTH = len(CLASS_LABELS)
+ # NB_VIEW = len(DATASET)
+ # NB_CLASS = len(set(CLASS_LABELS))
+ # bestViews = np.zeros(self.maxIter)
+ # bestClassifiers = []
+ #
+ # # Learning
+ # for i in range(self.maxIter):
+ # logging.debug('\t\tStart:\t Iteration ' + str(self.iterIndex + 1))
+ # classifiers, predictedLabels, areBad = self.trainWeakClassifiers(DATASET, CLASS_LABELS, NB_CLASS,
+ # DATASET_LENGTH, NB_VIEW)
+ # if areBad.all():
+ # logging.warning("All bad for iteration " + str(self.iterIndex))
+ #
+ # self.predictions[self.iterIndex] = predictedLabels
+ #
+ # for viewIndice in range(NB_VIEW):
+ # self.computeEdge(viewIndice, DATASET_LENGTH, CLASS_LABELS)
+ # if areBad[viewIndice]:
+ # self.alphas[self.iterIndex, viewIndice] = 0.
+ # else:
+ # self.alphas[self.iterIndex, viewIndice] = self.computeAlpha(self.edges[self.iterIndex,
+ # viewIndice])
+ # self.updateDs(CLASS_LABELS, NB_VIEW, DATASET_LENGTH)
+ # self.updateFs(NB_VIEW, DATASET_LENGTH, NB_CLASS)
+ #
+ # self.updateCostmatrices(NB_VIEW, DATASET_LENGTH, NB_CLASS, CLASS_LABELS)
+ # bestView, edge, bestFakeView = self.chooseView(NB_VIEW, CLASS_LABELS, DATASET_LENGTH)
+ # self.bestViews[self.iterIndex] = bestView
+ # if areBad.all():
+ # self.generalAlphas[self.iterIndex] = 0.
+ # else:
+ # self.generalAlphas[self.iterIndex] = self.computeAlpha(edge)
+ # self.bestClassifiers.append(classifiers[bestView])
+ # self.updateGeneralFs(DATASET_LENGTH, NB_CLASS, bestView)
+ # self.updateGeneralCostMatrix(DATASET_LENGTH, NB_CLASS, CLASS_LABELS)
def predict(self, DATASET, NB_CLASS=2):
@@ -439,7 +446,7 @@ class Mumbo:
return np.transpose(predictedLabels)
- def classifyMumbobyIter_hdf5(self, DATASET, usedIndices=None, NB_CLASS=2):
+ def classifyMumbobyIter_hdf5(self, DATASET, fakeViewsIndicesDict, usedIndices=None, NB_CLASS=2):
if usedIndices == None:
usedIndices = range(DATASET.get("Metadata").attrs["datasetLength"])
if usedIndices:
@@ -452,7 +459,7 @@ class Mumbo:
for usedExampleIndex, exampleIndex in enumerate(usedIndices):
data = np.array([np.array(getV(DATASET,int(view), exampleIndex))])
- votesByIter[usedExampleIndex, int(classifier.predict(data))] += alpha[view]
+ votesByIter[usedExampleIndex, int(classifier.predict(data))] += alpha[fakeViewsIndicesDict[view]]
votes[usedExampleIndex] = votes[usedExampleIndex] + np.array(votesByIter[usedExampleIndex])
predictedLabels[usedExampleIndex, iterIndex] = np.argmax(votes[usedExampleIndex])
else:
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/analyzeResults.py b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/analyzeResults.py
index d4811a12d80516f1a503eaaf310db03747f62a79..bb74ecb7e98e972247528f27a2b45f07380922d1 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/analyzeResults.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/analyzeResults.py
@@ -140,6 +140,7 @@ def getReport(classifiersIterations, CLASS_LABELS, iterationValidationIndices, D
DATASET_LENGTH = DATASET.get("Metadata").attrs["datasetLength"]
NB_CLASS = DATASET.get("Metadata").attrs["nbClass"]
metricModule = getattr(Metrics, metric[0])
+ fakeViewsIndicesDict = dict((viewIndex, fakeViewIndex) for viewIndex, fakeViewIndex in zip(viewIndices, range(nbView)))
if metric[1]!=None:
metricKWARGS = dict((index, metricConfig) for index, metricConfig in enumerate(metric[1]))
else:
@@ -165,9 +166,9 @@ def getReport(classifiersIterations, CLASS_LABELS, iterationValidationIndices, D
meanAverageAccuraciesIterations.append(np.mean(mumboClassifier.averageAccuracies, axis=0))
viewsStatsIteration[statIterIndex, :] = np.array([float(list(mumboClassifier.bestViews).count(viewIndex))/
len(mumboClassifier.bestViews)for viewIndex in range(nbView)])
- PredictedTrainLabelsByIter = mumboClassifier.classifyMumbobyIter_hdf5(DATASET, usedIndices=learningIndices,
+ PredictedTrainLabelsByIter = mumboClassifier.classifyMumbobyIter_hdf5(DATASET, fakeViewsIndicesDict, usedIndices=learningIndices,
NB_CLASS=NB_CLASS)
- PredictedTestLabelsByIter = mumboClassifier.classifyMumbobyIter_hdf5(DATASET, usedIndices=validationIndices,
+ PredictedTestLabelsByIter = mumboClassifier.classifyMumbobyIter_hdf5(DATASET, fakeViewsIndicesDict, usedIndices=validationIndices,
NB_CLASS=NB_CLASS)
scoresByIter = np.zeros((len(PredictedTestLabelsByIter),2))
for iterIndex,(iterPredictedTrainLabels, iterPredictedTestLabels) in enumerate(zip(PredictedTrainLabelsByIter, PredictedTestLabelsByIter)):