From dcffa946dc96db5cab6f7d00e862eb01487141d9 Mon Sep 17 00:00:00 2001
From: Baptiste Bauvin <baptiste.bauvin@centrale-marseille.fr>
Date: Tue, 4 Oct 2016 19:41:31 -0400
Subject: [PATCH] Debugged everything
---
Code/MonoMutliViewClassifiers/ExecClassif.py | 49 +++++++++----------
.../Monoview/ExecClassifMonoView.py | 2 +-
.../MonoviewClassifiers/Adaboost.py | 3 ++
.../MonoviewClassifiers/DecisionTree.py | 3 ++
.../MonoviewClassifiers/KNN.py | 3 ++
.../MonoviewClassifiers/RandomForest.py | 3 ++
.../MonoviewClassifiers/SCM.py | 5 +-
.../MonoviewClassifiers/SGD.py | 2 +
.../MonoviewClassifiers/SVMLinear.py | 2 +
.../MonoviewClassifiers/SVMPoly.py | 2 +
.../MonoviewClassifiers/SVMRBF.py | 2 +
.../Multiview/Fusion/Methods/LateFusion.py | 7 ++-
.../LateFusionPackage/BayesianInference.py | 2 +-
.../LateFusionPackage/WeightedLinear.py | 1 +
.../Multiview/GetMultiviewDb.py | 1 -
.../MonoMutliViewClassifiers/utils/Dataset.py | 2 -
multiview-machine-learning-omis.iml | 2 +-
17 files changed, 56 insertions(+), 35 deletions(-)
diff --git a/Code/MonoMutliViewClassifiers/ExecClassif.py b/Code/MonoMutliViewClassifiers/ExecClassif.py
index 5cf3ce2f..9557a7c0 100644
--- a/Code/MonoMutliViewClassifiers/ExecClassif.py
+++ b/Code/MonoMutliViewClassifiers/ExecClassif.py
@@ -40,7 +40,7 @@ parser = argparse.ArgumentParser(
groupStandard = parser.add_argument_group('Standard arguments')
groupStandard.add_argument('-log', action='store_true', help='Use option to activate Logging to Console')
groupStandard.add_argument('--name', metavar='STRING', action='store', help='Name of Database (default: %(default)s)',
- default='MultiOmic')
+ default='Plausible')
groupStandard.add_argument('--type', metavar='STRING', action='store', help='Type of database : .hdf5 or .csv',
default='.hdf5')
groupStandard.add_argument('--views', metavar='STRING', action='store',help='Name of the views selected for learning',
@@ -55,7 +55,7 @@ groupClass.add_argument('--CL_split', metavar='FLOAT', action='store',
help='Determine the learning rate if > 1.0, number of fold for cross validation', type=float,
default=0.7)
groupClass.add_argument('--CL_nbFolds', metavar='INT', action='store', help='Number of folds in cross validation',
- type=int, default=5 )
+ type=int, default=2 )
groupClass.add_argument('--CL_nb_class', metavar='INT', action='store', help='Number of classes, -1 for all', type=int,
default=2)
groupClass.add_argument('--CL_classes', metavar='STRING', action='store',
@@ -73,12 +73,12 @@ groupClass.add_argument('--CL_algos_multiview', metavar='STRING', action='store'
groupClass.add_argument('--CL_cores', metavar='INT', action='store', help='Number of cores, -1 for all', type=int,
default=1)
groupClass.add_argument('--CL_statsiter', metavar='INT', action='store', help='Number of iteration for each algorithm to mean results', type=int,
- default=1)
+ default=2)
groupClass.add_argument('--CL_metrics', metavar='STRING', action='store', nargs="+",
help='Determine which metrics to use, separate metric and configuration with ":". If multiple, separate with space. If no metric is specified, considering all with accuracy for classification '
'first one will be used for classification', default=[''])
groupClass.add_argument('--CL_GS_iter', metavar='INT', action='store',
- help='Determine how many Randomized grid search tests to do', type=int, default=30)
+ help='Determine how many Randomized grid search tests to do', type=int, default=2)
groupClass.add_argument('--CL_GS_type', metavar='STRING', action='store',
help='Determine which hyperparamter search function use', default="randomizedSearch")
@@ -241,7 +241,7 @@ if args.CL_type.split(":")==["Benchmark"]:
for fusionModulesName, fusionClasse in zip(fusionModulesNames, fusionClasses))
allMonoviewAlgos = [name for _, name, isPackage in
pkgutil.iter_modules(['MonoviewClassifiers'])
- if (not isPackage) and (name!="SGD") and (name[:3]!="SVM") and (name!="SCM")]
+ if (not isPackage) and (name!="SGD") and (name[:3]!="SVM")]
fusionMonoviewClassifiers = allMonoviewAlgos
allFusionAlgos = {"Methods": fusionMethods, "Classifiers": fusionMonoviewClassifiers}
allMumboAlgos = [name for _, name, isPackage in
@@ -335,7 +335,7 @@ if nbCores>1:
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)]
classifiersNames = [[result[1][0] for result in resultsMonoview if result[0]==viewIndex] for viewIndex in range(NB_VIEW)]
- classifiersConfigs = [[result[1][2] for result in resultsMonoview if result[0]==viewIndex] for viewIndex in range(NB_VIEW)]
+ 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"])),
DATASET.get("Labels").value, args.name, labelsNames,
@@ -348,27 +348,8 @@ else:
classifiersNames = [[result[1][0] for result in resultsMonoview if result[0]==viewIndex] for viewIndex in viewsIndices]
classifiersConfigs = [[result[1][1][:-1] for result in resultsMonoview if result[0]==viewIndex] for viewIndex in viewsIndices]
monoviewTime = time.time()-dataBaseTime-start
-print classifiersConfigs
if True:
if benchmark["Multiview"]:
- try:
- if benchmark["Multiview"]["Mumbo"]:
- for combination in itertools.combinations_with_replacement(range(len(benchmark["Multiview"]["Mumbo"])), NB_VIEW):
- mumboClassifiersNames = [benchmark["Multiview"]["Mumbo"][index] for index in combination]
- arguments = {"CL_type": "Mumbo",
- "views": views,
- "NB_VIEW": len(views),
- "viewsIndices": viewsIndices,
- "NB_CLASS": len(args.CL_classes.split(":")),
- "LABELS_NAMES": args.CL_classes.split(":"),
- "MumboKWARGS": {"classifiersNames": mumboClassifiersNames,
- "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], "nbView":(len(viewsIndices))}}
- argumentDictionaries["Multiview"].append(arguments)
- except:
- pass
-
try:
if benchmark["Multiview"]["Fusion"]:
if args.FU_cl_names.split(':') !=['']:
@@ -456,9 +437,25 @@ if True:
pass
except:
pass
+ try:
+ if benchmark["Multiview"]["Mumbo"]:
+ for combination in itertools.combinations_with_replacement(range(len(benchmark["Multiview"]["Mumbo"])), NB_VIEW):
+ mumboClassifiersNames = [benchmark["Multiview"]["Mumbo"][index] for index in combination]
+ arguments = {"CL_type": "Mumbo",
+ "views": views,
+ "NB_VIEW": len(views),
+ "viewsIndices": viewsIndices,
+ "NB_CLASS": len(args.CL_classes.split(":")),
+ "LABELS_NAMES": args.CL_classes.split(":"),
+ "MumboKWARGS": {"classifiersNames": mumboClassifiersNames,
+ "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], "nbView":(len(viewsIndices))}}
+ argumentDictionaries["Multiview"].append(arguments)
+ except:
+ pass
else:
pass
-# resultsMultiview = []
if nbCores>1:
resultsMultiview = []
nbExperiments = len(argumentDictionaries["Multiview"])
diff --git a/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py b/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py
index 9919fbd6..84934343 100644
--- a/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py
+++ b/Code/MonoMutliViewClassifiers/Monoview/ExecClassifMonoView.py
@@ -38,7 +38,7 @@ 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, learningRate, nbFolds, 1, databaseType, path, statsIter, gridSearch=gridSearch,
+ return ExecMonoview(X, Y, name, labelsNames, learningRate, nbFolds, 1, databaseType, path, statsIter, gridSearch=gridSearch,
metrics=metrics, nIter=nIter, **args)
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py
index 430a71cc..e1d2e0de 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/Adaboost.py
@@ -10,6 +10,9 @@ __author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
+def canProbas():
+ return True
+
def fit(DATASET, CLASS_LABELS, NB_CORES=1,**kwargs):
num_estimators = int(kwargs['0'])
base_estimators = DecisionTreeClassifier()#kwargs['1']
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/DecisionTree.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/DecisionTree.py
index 626099e1..f9cb2679 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/DecisionTree.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/DecisionTree.py
@@ -10,6 +10,9 @@ __author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
+def canProbas():
+ return True
+
def fit(DATASET, CLASS_LABELS, NB_CORES=1, **kwargs):
maxDepth = int(kwargs['0'])
classifier = DecisionTreeClassifier(max_depth=maxDepth)
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/KNN.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/KNN.py
index 323c4e7c..9105e37c 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/KNN.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/KNN.py
@@ -10,6 +10,9 @@ __author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
+def canProbas():
+ return True
+
def fit(DATASET, CLASS_LABELS, NB_CORES=1,**kwargs):
nNeighbors = int(kwargs['0'])
classifier = KNeighborsClassifier(n_neighbors=nNeighbors)
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/RandomForest.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/RandomForest.py
index 7037d6b6..f0f24ee1 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/RandomForest.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/RandomForest.py
@@ -10,6 +10,9 @@ __author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
+def canProbas():
+ return True
+
def fit(DATASET, CLASS_LABELS, NB_CORES=1,**kwargs):
num_estimators = int(kwargs['0'])
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SCM.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SCM.py
index 2b28f22e..423d7f84 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SCM.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SCM.py
@@ -18,6 +18,10 @@ __author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
+
+def canProbas():
+ return False
+
def fit(DATASET, CLASS_LABELS, NB_CORES=1,**kwargs):
max_attrtibutes = kwargs['0']
try:
@@ -33,7 +37,6 @@ def fit(DATASET, CLASS_LABELS, NB_CORES=1,**kwargs):
binaryAttributes = kwargs["binaryAttributes"]
except:
attributeClassification, binaryAttributes, dsetFile, name = transformData(DATASET)
- print kwargs
classifier = pyscm.scm.SetCoveringMachine(p=p, max_attributes=max_attrtibutes, model_type=model_type, verbose=False)
classifier.fit(binaryAttributes, CLASS_LABELS, X=None, attribute_classifications=attributeClassification, iteration_callback=None)
try:
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SGD.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SGD.py
index ef0d7b3b..59026a66 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SGD.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SGD.py
@@ -10,6 +10,8 @@ __author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
+def canProbas():
+ return True
def fit(DATASET, CLASS_LABELS, NB_CORES=1,**kwargs):
loss = kwargs['0']
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMLinear.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMLinear.py
index 60ed82c2..4140f7a3 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMLinear.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMLinear.py
@@ -10,6 +10,8 @@ __author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
+def canProbas():
+ return True
def fit(DATASET, CLASS_LABELS, NB_CORES=1,**kwargs):
C = int(kwargs['0'])
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMPoly.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMPoly.py
index c78492b3..7f48d225 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMPoly.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMPoly.py
@@ -10,6 +10,8 @@ __author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
+def canProbas():
+ return True
def fit(DATASET, CLASS_LABELS, NB_CORES=1,**kwargs):
C = int(kwargs['0'])
diff --git a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMRBF.py b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMRBF.py
index f5153ebb..9234a3a5 100644
--- a/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMRBF.py
+++ b/Code/MonoMutliViewClassifiers/MonoviewClassifiers/SVMRBF.py
@@ -10,6 +10,8 @@ __author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
+def canProbas():
+ return True
def fit(DATASET, CLASS_LABELS, NB_CORES=1,**kwargs):
C = int(kwargs['0'])
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusion.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusion.py
index 63341c29..63d870cf 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusion.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusion.py
@@ -10,8 +10,10 @@ import MonoviewClassifiers
from utils.Dataset import getV
-def fitMonoviewClassifier(classifierName, data, labels, classifierConfig):
+def fitMonoviewClassifier(classifierName, data, labels, classifierConfig, needProbas):
monoviewClassifier = getattr(MonoviewClassifiers, classifierName)
+ if needProbas and not monoviewClassifier.canProbas():
+ monoviewClassifier = getattr(MonoviewClassifiers, "DecisionTree")
classifier = monoviewClassifier.fit(data,labels,**dict((str(configIndex), config) for configIndex, config in
enumerate(classifierConfig
)))
@@ -28,6 +30,7 @@ class LateFusionClassifier(object):
self.monoviewClassifiers = []
self.nbCores = NB_CORES
self.accuracies = np.zeros(len(monoviewClassifiersNames))
+ self.needProbas = False
def fit_hdf5(self, DATASET, trainIndices=None, viewsIndices=None):
if type(viewsIndices)==type(None):
@@ -38,5 +41,5 @@ class LateFusionClassifier(object):
delayed(fitMonoviewClassifier)(self.monoviewClassifiersNames[index],
getV(DATASET, viewIndex, trainIndices),
DATASET.get("Labels")[trainIndices],
- self.monoviewClassifiersConfigs[index])
+ self.monoviewClassifiersConfigs[index], self.needProbas)
for index, viewIndex in enumerate(viewsIndices))
\ No newline at end of file
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py
index 36cf0015..de6b0193 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py
@@ -6,7 +6,6 @@ from utils.Dataset import getV
def genParamsSets(classificationKWARGS, nIter=1):
- print classificationKWARGS
nbView = classificationKWARGS["nbView"]
paramsSets = []
for _ in range(nIter):
@@ -43,6 +42,7 @@ class BayesianInference(LateFusionClassifier):
# self.weights = np.array(map(float, kwargs['fusionMethodConfig'][0]))
self.weights = None #A modifier !!
+ self.needProbas = True
def setParams(self, paramsSet):
self.weights = paramsSet[0]
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
index 6937fd10..5dcb3334 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
@@ -46,6 +46,7 @@ class WeightedLinear(LateFusionClassifier):
pass
else:
self.weights = np.array(map(float, kwargs['fusionMethodConfig'][0]))
+ self.needProbas = True
def setParams(self, paramsSet):
self.weights = paramsSet[0]
diff --git a/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py b/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py
index 76b2af6a..546a1bf4 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/GetMultiviewDb.py
@@ -480,7 +480,6 @@ def getAdjacenceMatrix(RNASeqRanking, sotredRNASeq, k=2):
nbGenes = RNASeqRanking.shape[1]
pointer = 0
for patientIndex in range(RNASeqRanking.shape[0]):
- print patientIndex
for i in range(nbGenes):
for j in range(k/2):
try:
diff --git a/Code/MonoMutliViewClassifiers/utils/Dataset.py b/Code/MonoMutliViewClassifiers/utils/Dataset.py
index 98db8952..6b63b874 100644
--- a/Code/MonoMutliViewClassifiers/utils/Dataset.py
+++ b/Code/MonoMutliViewClassifiers/utils/Dataset.py
@@ -37,10 +37,8 @@ def extractSubset(matrix, usedIndices):
if sparse.issparse(matrix):
newIndptr = np.zeros(len(usedIndices)+1, dtype=int)
oldindptr = matrix.indptr
- print oldindptr
for exampleIndexIndex, exampleIndex in enumerate(usedIndices):
newIndptr[exampleIndexIndex+1] = newIndptr[exampleIndexIndex]+(oldindptr[exampleIndex+1]-oldindptr[exampleIndex])
- print newIndptr
newData = np.ones(newIndptr[-1], dtype=bool)
newIndices = np.zeros(newIndptr[-1], dtype=int)
oldIndices = matrix.indices
diff --git a/multiview-machine-learning-omis.iml b/multiview-machine-learning-omis.iml
index ad3c0a36..8021953e 100644
--- a/multiview-machine-learning-omis.iml
+++ b/multiview-machine-learning-omis.iml
@@ -1,5 +1,5 @@
<?xml version="1.0" encoding="UTF-8"?>
-<module type="PYTHON_MODULE" version="4">
+<module type="WEB_MODULE" version="4">
<component name="NewModuleRootManager" inherit-compiler-output="true">
<exclude-output />
<content url="file://$MODULE_DIR$" />
--
GitLab