From 38d60f6d8ff92f81fef6e44e3f50baa5897810dd Mon Sep 17 00:00:00 2001
From: bbauvin <baptiste.bauvin@centrale-marseille.fr>
Date: Thu, 5 Oct 2017 10:14:03 -0400
Subject: [PATCH] Replaced all random by sandomstates
---
Code/MonoMutliViewClassifiers/ExecClassif.py | 11 +++----
.../Multiview/ExecMultiview.py | 22 ++++++-------
.../Multiview/Fusion/Fusion.py | 8 ++---
.../Multiview/Fusion/Methods/EarlyFusion.py | 3 +-
.../EarlyFusionPackage/WeightedLinear.py | 8 ++---
.../Multiview/Fusion/Methods/LateFusion.py | 6 ++--
.../LateFusionPackage/BayesianInference.py | 8 ++---
.../LateFusionPackage/MajorityVoting.py | 8 ++---
.../Methods/LateFusionPackage/SCMForLinear.py | 14 ++++----
.../Methods/LateFusionPackage/SVMForLinear.py | 6 ++--
.../LateFusionPackage/WeightedLinear.py | 28 +++-------------
.../Multiview/Fusion/analyzeResults.py | 4 +--
.../Mumbo/Classifiers/DecisionTree.py | 4 +--
.../Mumbo/Classifiers/SubSampling.py | 5 ++-
.../Multiview/Mumbo/Mumbo.py | 6 ++--
.../Multiview/Mumbo/analyzeResults.py | 6 ++--
.../MonoMutliViewClassifiers/utils/Dataset.py | 1 +
.../utils/HyperParameterSearch.py | 33 ++++++++++---------
.../utils/Transformations.py | 1 +
19 files changed, 81 insertions(+), 101 deletions(-)
diff --git a/Code/MonoMutliViewClassifiers/ExecClassif.py b/Code/MonoMutliViewClassifiers/ExecClassif.py
index 5e3ff07f..7553e6b8 100644
--- a/Code/MonoMutliViewClassifiers/ExecClassif.py
+++ b/Code/MonoMutliViewClassifiers/ExecClassif.py
@@ -216,13 +216,13 @@ def lateFusionSetArgs(views, viewsIndices, classes, method,
def initMultiviewArguments(args, benchmark, views, viewsIndices, scores, classifiersConfigs, classifiersNames,
- NB_VIEW, metrics, argumentDictionaries):
+ NB_VIEW, metrics, argumentDictionaries, randomState):
multiviewArguments = []
if "Multiview" in benchmark:
for multiviewAlgoName in benchmark["Multiview"]:
multiviewPackage = getattr(Multiview, multiviewAlgoName)
mutliviewModule = getattr(multiviewPackage, multiviewAlgoName)
- multiviewArguments += mutliviewModule.getArgs(args, benchmark, views, viewsIndices)
+ multiviewArguments += mutliviewModule.getArgs(args, benchmark, views, viewsIndices, randomState)
argumentDictionaries["Multiview"] = multiviewArguments
return argumentDictionaries
@@ -494,7 +494,7 @@ else:
monoviewTime = time.time() - dataBaseTime - start
argumentDictionaries = initMultiviewArguments(args, benchmark, views, viewsIndices, scores, classifiersConfigs,
- classifiersNames, NB_VIEW, metrics[0], argumentDictionaries)
+ classifiersNames, NB_VIEW, metrics[0], argumentDictionaries, randomState)
if nbCores > 1:
resultsMultiview = []
@@ -503,14 +503,14 @@ if nbCores > 1:
resultsMultiview += Parallel(n_jobs=nbCores)(
delayed(ExecMultiview_multicore)(directory, coreIndex, args.name, args.CL_split, args.CL_nbFolds, args.type,
args.pathF,
- LABELS_DICTIONARY, statsIter, hyperParamSearch=hyperParamSearch,
+ LABELS_DICTIONARY, statsIter, randomState, hyperParamSearch=hyperParamSearch,
metrics=metrics, nIter=args.CL_GS_iter,
**argumentDictionaries["Multiview"][stepIndex * nbCores + coreIndex])
for coreIndex in range(min(nbCores, nbExperiments - stepIndex * nbCores)))
else:
resultsMultiview = [
ExecMultiview(directory, DATASET, args.name, args.CL_split, args.CL_nbFolds, 1, args.type, args.pathF,
- LABELS_DICTIONARY, statsIter, hyperParamSearch=hyperParamSearch,
+ LABELS_DICTIONARY, statsIter, randomState, hyperParamSearch=hyperParamSearch,
metrics=metrics, nIter=args.CL_GS_iter, **arguments) for arguments in
argumentDictionaries["Multiview"]]
multiviewTime = time.time() - monoviewTime - dataBaseTime - start
@@ -523,7 +523,6 @@ labels = np.array(
resultsMultiview]).transpose()
trueLabels = DATASET.get("Labels").value
times = [dataBaseTime, monoviewTime, multiviewTime]
-# times=[]
results = (resultsMonoview, resultsMultiview)
analyzeLabels(labels, trueLabels, results, directory)
logging.debug("Start:\t Analyze Global Results")
diff --git a/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py b/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py
index 77e14c20..153b0b6a 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/ExecMultiview.py
@@ -7,27 +7,26 @@ sys.path.append(
from Multiview import *
import GetMultiviewDb as DB
-import argparse
import os
import logging
import time
import h5py
-from utils.Dataset import getShape
-from utils.HyperParameterSearch import searchBestSettings
+from ..utils.Dataset import getShape
+from ..utils.HyperParameterSearch import searchBestSettings
# Author-Info
__author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
-def ExecMultiview_multicore(directory, coreIndex, name, learningRate, nbFolds, databaseType, path, LABELS_DICTIONARY, statsIter,
+def ExecMultiview_multicore(directory, coreIndex, name, learningRate, nbFolds, databaseType, path, LABELS_DICTIONARY, statsIter, randomState,
hyperParamSearch=False, nbCores=1, metrics=None, nIter=30, **arguments):
DATASET = h5py.File(path+name+str(coreIndex)+".hdf5", "r")
- return ExecMultiview(directory, DATASET, name, learningRate, nbFolds, 1, databaseType, path, LABELS_DICTIONARY, statsIter,
+ return ExecMultiview(directory, DATASET, name, learningRate, nbFolds, 1, databaseType, path, LABELS_DICTIONARY, statsIter, randomState,
hyperParamSearch=hyperParamSearch, metrics=metrics, nIter=nIter, **arguments)
-def ExecMultiview(directory, DATASET, name, learningRate, nbFolds, nbCores, databaseType, path, LABELS_DICTIONARY, statsIter,
+def ExecMultiview(directory, DATASET, name, learningRate, nbFolds, nbCores, databaseType, path, LABELS_DICTIONARY, statsIter, randomState,
hyperParamSearch=False, metrics=None, nIter=30, **kwargs):
datasetLength = DATASET.get("Metadata").attrs["datasetLength"]
@@ -36,7 +35,7 @@ def ExecMultiview(directory, DATASET, name, learningRate, nbFolds, nbCores, data
viewsIndices = kwargs["viewsIndices"]
NB_CLASS = DATASET.get("Metadata").attrs["nbClass"]
if not metrics:
- metrics = [["accuracy_score", None]]
+ metrics = [["f1_score", None]]
metric = metrics[0]
CL_type = kwargs["CL_type"]
LABELS_NAMES = kwargs["LABELS_NAMES"]
@@ -63,14 +62,14 @@ def ExecMultiview(directory, DATASET, name, learningRate, nbFolds, nbCores, data
analysisModule = getattr(classifierPackage, "analyzeResults")
logging.info("Start:\t Determine validation split for ratio " + str(learningRate))
- iValidationIndices = [DB.splitDataset(DATASET, learningRate, datasetLength) for iterIndex in range(statsIter)]
+ iValidationIndices = [DB.splitDataset(DATASET, learningRate, datasetLength, randomState) for _ in range(statsIter)]
iLearningIndices = [[index for index in range(datasetLength) if index not in validationIndices] for validationIndices in iValidationIndices]
iClassificationSetLength = [len(learningIndices) for learningIndices in iLearningIndices]
logging.info("Done:\t Determine validation split")
logging.info("Start:\t Determine "+str(nbFolds)+" folds")
if nbFolds != 1:
- iKFolds = [DB.getKFoldIndices(nbFolds, DATASET.get("Labels")[...], NB_CLASS, learningIndices) for learningIndices in iLearningIndices]
+ iKFolds = [DB.getKFoldIndices(nbFolds, DATASET.get("Labels")[...], NB_CLASS, learningIndices, randomState) for learningIndices in iLearningIndices]
else:
iKFolds = [[[], range(classificationSetLength)] for classificationSetLength in iClassificationSetLength]
@@ -84,10 +83,9 @@ def ExecMultiview(directory, DATASET, name, learningRate, nbFolds, nbCores, data
# logging.info("Start:\t Classification")
# Begin Classification
if hyperParamSearch != "None":
- classifier = searchBestSettings(DATASET, CL_type, metrics, iLearningIndices, iKFolds, viewsIndices=viewsIndices, searchingTool=hyperParamSearch, nIter=nIter, **classificationKWARGS)
+ classifier = searchBestSettings(DATASET, CL_type, metrics, iLearningIndices, iKFolds, randomState, viewsIndices=viewsIndices, searchingTool=hyperParamSearch, nIter=nIter, **classificationKWARGS)
else:
classifier = classifierClass(NB_CORES=nbCores, **classificationKWARGS)
- # classifier.setParams(classificationKWARGS)
for _ in range(statsIter):
classifier.fit_hdf5(DATASET, trainIndices=learningIndices, viewsIndices=viewsIndices)
trainLabels = classifier.predict_hdf5(DATASET, usedIndices=learningIndices, viewsIndices=viewsIndices)
@@ -112,7 +110,7 @@ def ExecMultiview(directory, DATASET, name, learningRate, nbFolds, nbCores, data
LABELS_DICTIONARY, views, nbCores, times,
name, nbFolds, ivalidationIndices,
hyperParamSearch, nIter, metrics, statsIter,
- viewsIndices)
+ viewsIndices, randomState)
labelsSet = set(LABELS_DICTIONARY.values())
logging.info(stringAnalysis)
featureString = "-".join(views)
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Fusion.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Fusion.py
index 1f30cb63..11a58af6 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Fusion.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Fusion.py
@@ -95,12 +95,12 @@ def makeMonoviewData_hdf5(DATASET, weights=None, usedIndices=None, viewsIndices=
return monoviewData
-def genParamsSets(classificationKWARGS, nIter=1):
+def genParamsSets(classificationKWARGS, randomState, nIter=1):
fusionTypeName = classificationKWARGS["fusionType"]
fusionTypePackage = globals()[fusionTypeName+"Package"]
fusionMethodModuleName = classificationKWARGS["fusionMethod"]
fusionMethodModule = getattr(fusionTypePackage, fusionMethodModuleName)
- fusionMethodConfig = fusionMethodModule.genParamsSets(classificationKWARGS, nIter=nIter)
+ fusionMethodConfig = fusionMethodModule.genParamsSets(classificationKWARGS, randomState, nIter=nIter)
return fusionMethodConfig
@@ -134,7 +134,7 @@ def gridSearch_hdf5(DATASET, viewsIndices, classificationKWARGS, learningIndices
class Fusion:
- def __init__(self, NB_CORES=1,**kwargs):
+ def __init__(self, randomState, NB_CORES=1, **kwargs):
fusionType = kwargs['fusionType']
fusionMethod = kwargs['fusionMethod']
fusionTypePackage = globals()[fusionType+"Package"]
@@ -142,7 +142,7 @@ class Fusion:
fusionMethodClass = getattr(fusionMethodModule, fusionMethod)
nbCores = NB_CORES
classifierKWARGS = dict((key, value) for key, value in kwargs.iteritems() if key not in ['fusionType', 'fusionMethod'])
- self.classifier = fusionMethodClass(NB_CORES=nbCores, **classifierKWARGS)
+ self.classifier = fusionMethodClass(randomState, NB_CORES=nbCores, **classifierKWARGS)
def setParams(self, paramsSet):
self.classifier.setParams(paramsSet)
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusion.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusion.py
index cb17c4c7..1ba7f1b8 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusion.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusion.py
@@ -6,7 +6,7 @@ from utils.Dataset import getV
class EarlyFusionClassifier(object):
- def __init__(self, monoviewClassifierName, monoviewClassifierConfig, NB_CORES=1):
+ def __init__(self, randomState, monoviewClassifierName, monoviewClassifierConfig, NB_CORES=1):
self.monoviewClassifierName = monoviewClassifierName
if type(monoviewClassifierConfig)==dict:
pass
@@ -18,6 +18,7 @@ class EarlyFusionClassifier(object):
self.monoviewClassifier = None
self.nbCores = NB_CORES
self.monoviewData = None
+ self.randomState = randomState
def makeMonoviewData_hdf5(self, DATASET, weights=None, usedIndices=None, viewsIndices=None):
if type(viewsIndices)==type(None):
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py
index 624ed6f7..ff72555f 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/EarlyFusionPackage/WeightedLinear.py
@@ -4,11 +4,11 @@ import numpy as np
from sklearn.metrics import accuracy_score
-def genParamsSets(classificationKWARGS, nIter=1):
+def genParamsSets(classificationKWARGS, randomState, nIter=1):
nbView = classificationKWARGS["nbView"]
paramsSets = []
for _ in range(nIter):
- randomWeightsArray = np.random.random_sample(nbView)
+ randomWeightsArray = randomState.random_sample(nbView)
normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
paramsSets.append([normalizedArray])
return paramsSets
@@ -57,8 +57,8 @@ def getArgs(args, views, viewsIndices):
class WeightedLinear(EarlyFusionClassifier):
- def __init__(self, NB_CORES=1, **kwargs):
- EarlyFusionClassifier.__init__(self, kwargs['classifiersNames'], kwargs['classifiersConfigs'],
+ def __init__(self, randomState, NB_CORES=1, **kwargs):
+ EarlyFusionClassifier.__init__(self, randomState, kwargs['classifiersNames'], kwargs['classifiersConfigs'],
NB_CORES=NB_CORES)
if kwargs['fusionMethodConfig'][0]==None:
self.weights = np.ones(len(kwargs["classifiersNames"]), dtype=float)
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusion.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusion.py
index 9b616adf..dfebc0c2 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusion.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusion.py
@@ -23,14 +23,13 @@ def fitMonoviewClassifier(classifierName, data, labels, classifierConfig, needPr
def getAccuracies(LateFusionClassifiers):
return ""
+
def Intersect(resMono):
pass
-
-
class LateFusionClassifier(object):
- def __init__(self, monoviewClassifiersNames, monoviewClassifiersConfigs, monoviewSelection, NB_CORES=1):
+ def __init__(self, randomState, monoviewClassifiersNames, monoviewClassifiersConfigs, monoviewSelection, NB_CORES=1):
self.monoviewClassifiersNames = monoviewClassifiersNames
self.monoviewClassifiersConfigs = monoviewClassifiersConfigs
self.monoviewClassifiers = []
@@ -38,6 +37,7 @@ class LateFusionClassifier(object):
self.accuracies = np.zeros(len(monoviewClassifiersNames))
self.needProbas = False
self.monoviewSelection = monoviewSelection
+ self.randomState = randomState
def fit_hdf5(self, DATASET, trainIndices=None, viewsIndices=None):
if type(viewsIndices)==type(None):
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py
index 9b308c51..6ddcfb54 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/BayesianInference.py
@@ -7,11 +7,11 @@ import MonoviewClassifiers
from ...Methods.LateFusion import LateFusionClassifier
-def genParamsSets(classificationKWARGS, nIter=1):
+def genParamsSets(classificationKWARGS, randomState, nIter=1):
nbView = classificationKWARGS["nbView"]
paramsSets = []
for _ in range(nIter):
- randomWeightsArray = np.random.random_sample(nbView)
+ randomWeightsArray = randomState.random_sample(nbView)
normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
paramsSets.append([normalizedArray])
return paramsSets
@@ -78,8 +78,8 @@ def getArgs(args, views, viewsIndices):
class BayesianInference(LateFusionClassifier):
- def __init__(self, NB_CORES=1, **kwargs):
- LateFusionClassifier.__init__(self, kwargs['classifiersNames'], kwargs['classifiersConfigs'], kwargs["monoviewSelection"],
+ def __init__(self, randomState, NB_CORES=1, **kwargs):
+ LateFusionClassifier.__init__(self, randomState, kwargs['classifiersNames'], kwargs['classifiersConfigs'], kwargs["monoviewSelection"],
NB_CORES=NB_CORES)
# self.weights = np.array(map(float, kwargs['fusionMethodConfig'][0]))
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/MajorityVoting.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/MajorityVoting.py
index 086c6405..7f453270 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/MajorityVoting.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/MajorityVoting.py
@@ -5,11 +5,11 @@ from sklearn.metrics import accuracy_score
from utils.Dataset import getV
-def genParamsSets(classificationKWARGS, nIter=1):
+def genParamsSets(classificationKWARGS, randomState, nIter=1):
nbView = classificationKWARGS["nbView"]
paramsSets = []
for _ in range(nIter):
- randomWeightsArray = np.random.random_sample(nbView)
+ randomWeightsArray = randomState.random_sample(nbView)
normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
paramsSets.append([normalizedArray])
return paramsSets
@@ -58,8 +58,8 @@ def getArgs(args, views, viewsIndices):
class MajorityVoting(LateFusionClassifier):
- def __init__(self, NB_CORES=1, **kwargs):
- LateFusionClassifier.__init__(self, kwargs['classifiersNames'], kwargs['classifiersConfigs'], kwargs["monoviewSelection"],
+ def __init__(self, randomState, NB_CORES=1, **kwargs):
+ LateFusionClassifier.__init__(self, randomState, kwargs['classifiersNames'], kwargs['classifiersConfigs'], kwargs["monoviewSelection"],
NB_CORES=NB_CORES)
if kwargs['fusionMethodConfig'][0]==None or kwargs['fusionMethodConfig'][0]==['']:
self.weights = np.ones(len(kwargs["classifiersNames"]), dtype=float)
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py
index e91a87af..f5218f49 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SCMForLinear.py
@@ -14,14 +14,14 @@ from sklearn.metrics import accuracy_score
import itertools
-def genParamsSets(classificationKWARGS, nIter=1):
+def genParamsSets(classificationKWARGS, randomState, nIter=1):
nbView = classificationKWARGS["nbView"]
paramsSets = []
for _ in range(nIter):
- max_attributes = random.randint(1, 20)
- p = random.random()
- model = random.choice(["conjunction", "disjunction"])
- order = random.randint(1,nbView)
+ max_attributes = randomState.randint(1, 20)
+ p = randomState.random()
+ model = randomState.choice(["conjunction", "disjunction"])
+ order = randomState.randint(1,nbView)
paramsSets.append([p, max_attributes, model, order])
return paramsSets
@@ -72,8 +72,8 @@ def getArgs(args, views, viewsIndices):
class SCMForLinear(LateFusionClassifier):
- def __init__(self, NB_CORES=1, **kwargs):
- LateFusionClassifier.__init__(self, kwargs['classifiersNames'], kwargs['classifiersConfigs'], kwargs["monoviewSelection"],
+ def __init__(self, randomState, NB_CORES=1, **kwargs):
+ LateFusionClassifier.__init__(self, randomState, kwargs['classifiersNames'], kwargs['classifiersConfigs'], kwargs["monoviewSelection"],
NB_CORES=NB_CORES)
self.SCMClassifier = None
# self.config = kwargs['fusionMethodConfig'][0]
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SVMForLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SVMForLinear.py
index 1f2f1ad5..fa9ee880 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SVMForLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/SVMForLinear.py
@@ -6,7 +6,7 @@ from sklearn.svm import SVC
from utils.Dataset import getV
-def genParamsSets(classificationKWARGS, nIter=1):
+def genParamsSets(classificationKWARGS, randomState, nIter=1):
nbView = classificationKWARGS["nbView"]
paramsSets = []
for _ in range(nIter):
@@ -38,8 +38,8 @@ def getArgs(args, views, viewsIndices):
return [arguments]
class SVMForLinear(LateFusionClassifier):
- def __init__(self, NB_CORES=1, **kwargs):
- LateFusionClassifier.__init__(self, kwargs['classifiersNames'], kwargs['classifiersConfigs'], kwargs["monoviewSelection"],
+ def __init__(self, randomState, NB_CORES=1, **kwargs):
+ LateFusionClassifier.__init__(self, randomState, kwargs['classifiersNames'], kwargs['classifiersConfigs'], kwargs["monoviewSelection"],
NB_CORES=NB_CORES)
self.SVMClassifier = None
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
index e81ebb84..e880a773 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/Methods/LateFusionPackage/WeightedLinear.py
@@ -5,11 +5,11 @@ from sklearn.metrics import accuracy_score
from utils.Dataset import getV
-def genParamsSets(classificationKWARGS, nIter=1):
+def genParamsSets(classificationKWARGS, randomState, nIter=1):
nbView = classificationKWARGS["nbView"]
paramsSets = []
for _ in range(nIter):
- randomWeightsArray = np.random.random_sample(nbView)
+ randomWeightsArray = randomState.random_sample(nbView)
normalizedArray = randomWeightsArray/np.sum(randomWeightsArray)
paramsSets.append([normalizedArray])
return paramsSets
@@ -36,30 +36,10 @@ def getArgs(args, views, viewsIndices):
"nbView": (len(viewsIndices))}}
return [arguments]
-# 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):
- def __init__(self, NB_CORES=1, **kwargs):
- LateFusionClassifier.__init__(self, kwargs['classifiersNames'], kwargs['classifiersConfigs'], kwargs["monoviewSelection"],
+ def __init__(self, randomState, NB_CORES=1, **kwargs):
+ LateFusionClassifier.__init__(self, randomState, kwargs['classifiersNames'], kwargs['classifiersConfigs'], kwargs["monoviewSelection"],
NB_CORES=NB_CORES)
if kwargs['fusionMethodConfig'][0]==None or kwargs['fusionMethodConfig'][0]==['']:
self.weights = np.ones(len(kwargs["classifiersNames"]), dtype=float)
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Fusion/analyzeResults.py b/Code/MonoMutliViewClassifiers/Multiview/Fusion/analyzeResults.py
index 874452b2..6906723f 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Fusion/analyzeResults.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Fusion/analyzeResults.py
@@ -68,7 +68,7 @@ def getMetricsScores(metrics, trainLabelsIterations, testLabelsIterations,
def execute(classifiersIterations, trainLabelsIterations,testLabelsIterations, DATASET, classificationKWARGS,
learningRate, LABELS_DICTIONARY,views, nbCores, times, name, nbFolds, ivalidationIndices,
- gridSearch, nIter, metrics, statsIter, viewsIndices):
+ gridSearch, nIter, metrics, statsIter, viewsIndices, randomState):
CLASS_LABELS = DATASET.get("Labels").value
@@ -112,7 +112,7 @@ def execute(classifiersIterations, trainLabelsIterations,testLabelsIterations, D
scoreOnTrain = np.mean(np.array([metricModule.score(CLASS_LABELS[learningIndices[statsIterIndex]], trainLabelsIterations[statsIterIndex], **metricKWARGS) for statsIterIndex in range(statsIter)]))
scoreOnTest = np.mean(np.array([metricModule.score(CLASS_LABELS[ivalidationIndices[statsIterIndex]], testLabelsIterations[statsIterIndex], **metricKWARGS) for statsIterIndex in range(statsIter)]))
fusionConfiguration = classifiersIterations[0].classifier.getConfig(fusionMethodConfig,monoviewClassifiersNames, monoviewClassifiersConfigs)
- stringAnalysis = "\t\tResult for Multiview classification with "+ fusionType + \
+ stringAnalysis = "\t\tResult for Multiview classification with "+ fusionType + "and random state : "+str(randomState)+\
"\n\nAverage "+metrics[0][0]+" :\n\t-On Train : " + str(scoreOnTrain) + "\n\t-On Test : " + str(scoreOnTest) + \
"\n\nDataset info :\n\t-Database name : " + name + "\n\t-Labels : " + \
', '.join(LABELS_DICTIONARY.values()) + "\n\t-Views : " + ', '.join(views) + "\n\t-" + str(nbFolds) + \
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/DecisionTree.py b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/DecisionTree.py
index 0cc9ceaa..a2aacd89 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/DecisionTree.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/DecisionTree.py
@@ -33,7 +33,7 @@ def getConfig(classifierConfig):
return 'with depth ' + str(depth) + ', ' + ' sub-sampled at ' + str(subSampling) + ' '
-def gridSearch(data, labels, metric="accuracy_score"):
+def gridSearch(data, labels, randomState, metric="accuracy_score"):
minSubSampling = 1.0/(len(labels)/2)
bestSettings = []
bestResults = []
@@ -51,7 +51,7 @@ def gridSearch(data, labels, metric="accuracy_score"):
# baseScore = 1000.0
# isBetter = "lower"
for i in range(50):
- subSampledData, subSampledLabels, subSampledWeights = subSample(data, labels, 0.05)
+ subSampledData, subSampledLabels, subSampledWeights = subSample(data, labels, 0.05, randomState)
classifier.fit(subSampledData, subSampledLabels)
prediction = classifier.predict(data)
preliminary_accuracies[i] = accuracy_score(labels, prediction)
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/SubSampling.py b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/SubSampling.py
index 4dcd4ffe..b3ffc382 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/SubSampling.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Classifiers/SubSampling.py
@@ -1,5 +1,4 @@
import numpy as np
-import random
def getLabelSupports(CLASS_LABELS):
labels = set(CLASS_LABELS)
@@ -15,7 +14,7 @@ def isUseful(nbTrainingExamples, index, CLASS_LABELS, labelDict):
return False, nbTrainingExamples
-def subSample(data, labels, subSampling, weights=None):
+def subSample(data, labels, subSampling, randomState, weights=None):
if weights is None:
weights = np.ones(len(labels))/len(labels)
nbExamples = len(labels)
@@ -26,7 +25,7 @@ def subSample(data, labels, subSampling, weights=None):
trainingExamplesIndices = []
usedIndices = []
while nbTrainingExamples != [0 for i in range(len(labelSupports))]:
- index = int(random.randint(0, nbExamples - 1))
+ index = int(randomState.randint(0, nbExamples - 1))
isUseFull, nbTrainingExamples = isUseful(nbTrainingExamples, index, labels, labelDict)
if isUseFull and index not in usedIndices:
trainingExamplesIndices.append(index)
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py
index 7763eba3..6e62ad34 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/Mumbo.py
@@ -81,7 +81,7 @@ def trainWeakClassifier_hdf5(classifierName, monoviewDataset, CLASS_LABELS, DATA
return classifier, classes, isBad, averageAccuracy
-def gridSearch_hdf5(DATASET, viewIndices, classificationKWARGS, learningIndices, metric=None, nIter=None):
+def gridSearch_hdf5(DATASET, viewIndices, classificationKWARGS, learningIndices, randomState, metric=None, nIter=None):
classifiersNames = classificationKWARGS["classifiersNames"]
bestSettings = []
for classifierIndex, classifierName in enumerate(classifiersNames):
@@ -96,7 +96,7 @@ def gridSearch_hdf5(DATASET, viewIndices, classificationKWARGS, learningIndices,
class Mumbo:
- def __init__(self, NB_CORES=1, **kwargs):
+ def __init__(self, randomState, NB_CORES=1, **kwargs):
self.maxIter = kwargs["maxIter"]
self.minIter = kwargs["minIter"]
self.threshold = kwargs["threshold"]
@@ -112,6 +112,7 @@ class Mumbo:
self.bestViews = np.zeros(self.maxIter, dtype=int)-1
self.averageAccuracies = np.zeros((self.maxIter, nbView))
self.iterAccuracies = np.zeros(self.maxIter)
+ self.randomState = randomState
def initDataDependant(self, datasetLength, nbView, nbClass, labels):
self.edges = np.zeros((self.maxIter, nbView))
@@ -243,7 +244,6 @@ class Mumbo:
predictedProbas = []
return predictedProbas
-
def trainWeakClassifiers(self, DATASET, CLASS_LABELS, NB_CLASS, DATASET_LENGTH, NB_VIEW):
trainedClassifiers = []
labelsMatrix = []
diff --git a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/analyzeResults.py b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/analyzeResults.py
index 0e343392..fbbfba1a 100644
--- a/Code/MonoMutliViewClassifiers/Multiview/Mumbo/analyzeResults.py
+++ b/Code/MonoMutliViewClassifiers/Multiview/Mumbo/analyzeResults.py
@@ -194,7 +194,6 @@ def getReport(classifiersIterations, CLASS_LABELS, iterationValidationIndices, D
scoresOnTestByIter)
-
def getClassificationReport(kFolds, kFoldClassifier, CLASS_LABELS, validationIndices, DATASET,
kFoldPredictedTrainLabels, kFoldPredictedTestLabels, kFoldPredictedValidationLabels,statsIter, viewIndices):
nbView = len(viewIndices)
@@ -344,6 +343,7 @@ def getClassificationReport(kFolds, kFoldClassifier, CLASS_LABELS, validationInd
kFoldBestViewsStatsM, kFoldAccuracyOnTrainByIterM, kFoldAccuracyOnTestByIterM, kFoldAccuracyOnValidationByIterM,
kFoldBestViewsM)
+
def iterRelevant(iterIndex, kFoldClassifierStats):
relevants = np.zeros(len(kFoldClassifierStats[0]), dtype=bool)
for statsIterIndex, kFoldClassifier in enumerate(kFoldClassifierStats):
@@ -420,7 +420,7 @@ def getMeanIterations(kFoldClassifierStats, foldIndex):
def execute(classifiersIterations, trainLabelsIterations,testLabelsIterations, DATASET,initKWARGS,
LEARNING_RATE,LABELS_DICTIONARY,views, NB_CORES, times,databaseName, nbFolds, validationIndices, gridSearch,
- nIter, metrics, statsIter,viewIndices):
+ nIter, metrics, statsIter,viewIndices, randomState):
CLASS_LABELS = DATASET.get("Labels")[...]
@@ -432,7 +432,7 @@ def execute(classifiersIterations, trainLabelsIterations,testLabelsIterations, D
scoresOnTestByIter) = getReport(classifiersIterations, CLASS_LABELS, validationIndices, DATASET,
trainLabelsIterations, testLabelsIterations, statsIter, viewIndices, metrics[0])
- stringAnalysis = "\t\tResult for Multiview classification with Mumbo" \
+ stringAnalysis = "\t\tResult for Multiview classification with Mumbo with random state : "+str(randomState) + \
"\n\nAverage "+metrics[0][0]+" :\n\t-On Train : " + str(totalScoreOnTrain) + "\n\t-On Test : " + \
str(totalScoreOnTest)
stringAnalysis += dbConfigurationString
diff --git a/Code/MonoMutliViewClassifiers/utils/Dataset.py b/Code/MonoMutliViewClassifiers/utils/Dataset.py
index 6b63b874..23dca4b2 100644
--- a/Code/MonoMutliViewClassifiers/utils/Dataset.py
+++ b/Code/MonoMutliViewClassifiers/utils/Dataset.py
@@ -33,6 +33,7 @@ def getValue(DATASET):
shape=DATASET.attrs["shape"])
return sparse_mat
+
def extractSubset(matrix, usedIndices):
if sparse.issparse(matrix):
newIndptr = np.zeros(len(usedIndices)+1, dtype=int)
diff --git a/Code/MonoMutliViewClassifiers/utils/HyperParameterSearch.py b/Code/MonoMutliViewClassifiers/utils/HyperParameterSearch.py
index dec08581..932aa04e 100644
--- a/Code/MonoMutliViewClassifiers/utils/HyperParameterSearch.py
+++ b/Code/MonoMutliViewClassifiers/utils/HyperParameterSearch.py
@@ -4,12 +4,12 @@ import sys
import Multiview
import Metrics
-def searchBestSettings(dataset, classifierName, metrics, iLearningIndices, iKFolds, viewsIndices=None, searchingTool="hyperParamSearch", nIter=1, **kwargs):
+def searchBestSettings(dataset, classifierName, metrics, iLearningIndices, iKFolds, randomState, viewsIndices=None, searchingTool="hyperParamSearch", nIter=1, **kwargs):
if viewsIndices is None:
viewsIndices = range(dataset.get("Metadata").attrs["nbView"])
thismodule = sys.modules[__name__]
searchingToolMethod = getattr(thismodule, searchingTool)
- bestSettings = searchingToolMethod(dataset, classifierName, metrics, iLearningIndices, iKFolds, viewsIndices=viewsIndices, nIter=nIter, **kwargs)
+ bestSettings = searchingToolMethod(dataset, classifierName, metrics, iLearningIndices, iKFolds, randomState, viewsIndices=viewsIndices, nIter=nIter, **kwargs)
return bestSettings # or well set clasifier ?
@@ -18,7 +18,7 @@ def gridSearch(dataset, classifierName, viewsIndices=None, kFolds=None, nIter=1,
pass
-def randomizedSearch(dataset, classifierName, metrics, iLearningIndices, iKFolds, viewsIndices=None, nIter=1, nbCores=1, **classificationKWARGS):
+def randomizedSearch(dataset, classifierName, metrics, iLearningIndices, iKFolds, randomState, viewsIndices=None, nIter=1, nbCores=1, **classificationKWARGS):
if viewsIndices is None:
viewsIndices = range(dataset.get("Metadata").attrs["nbView"])
metric = metrics[0]
@@ -33,40 +33,41 @@ def randomizedSearch(dataset, classifierName, metrics, iLearningIndices, iKFolds
statsIter = len(iLearningIndices)
if classifierName != "Mumbo":
datasetLength = dataset.get("Metadata").attrs["datasetLength"]
- paramsSets = classifierModule.genParamsSets(classificationKWARGS, nIter=nIter)
+ paramsSets = classifierModule.genParamsSets(classificationKWARGS, randomState, nIter=nIter)
+ if metricModule.getConfig()[-14]=="h":
+ baseScore = -1000.0
+ isBetter = "higher"
+ else:
+ baseScore = 1000.0
+ isBetter = "lower"
+ bestSettings = None
for paramsSet in paramsSets:
- if metricModule.getConfig()[-14]=="h":
- baseScore = -1000.0
- isBetter = "higher"
- else:
- baseScore = 1000.0
- isBetter = "lower"
scores = []
for statsIterIndex in range(statsIter):
for fold in iKFolds[statsIterIndex]:
fold.sort()
trainIndices = [index for index in range(datasetLength) if (index not in fold) and (index in iLearningIndices[statsIterIndex])]
- classifier = classifierClass(NB_CORES=nbCores, **classificationKWARGS)
+ classifier = classifierClass(randomState, NB_CORES=nbCores, **classificationKWARGS)
classifier.setParams(paramsSet)
classifier.fit_hdf5(dataset, trainIndices=trainIndices, viewsIndices=viewsIndices)
- trainLabels = classifier.predict_hdf5(dataset, usedIndices=trainIndices, viewsIndices=viewsIndices)
+ # trainLabels = classifier.predict_hdf5(dataset, usedIndices=trainIndices, viewsIndices=viewsIndices)
testLabels = classifier.predict_hdf5(dataset, usedIndices=fold, viewsIndices=viewsIndices)
- trainScore = metricModule.score(dataset.get("Labels").value[trainIndices], trainLabels)
+ # trainScore = metricModule.score(dataset.get("Labels").value[trainIndices], trainLabels)
testScore = metricModule.score(dataset.get("Labels").value[fold], testLabels)
scores.append(testScore)
crossValScore = np.mean(np.array(scores))
- if isBetter=="higher" and crossValScore>baseScore:
+ if isBetter=="higher" and crossValScore > baseScore:
baseScore = crossValScore
bestSettings = paramsSet
- elif isBetter=="lower" and crossValScore<baseScore:
+ elif isBetter=="lower" and crossValScore < baseScore:
baseScore = crossValScore
bestSettings = paramsSet
classifier = classifierClass(NB_CORES=nbCores, **classificationKWARGS)
classifier.setParams(bestSettings)
else:
- bestConfigs, _ = classifierModule.gridSearch_hdf5(dataset, viewsIndices, classificationKWARGS, iLearningIndices[0], metric=metric, nIter=nIter)
+ bestConfigs, _ = classifierModule.gridSearch_hdf5(dataset, viewsIndices, classificationKWARGS, iLearningIndices[0], randomState, metric=metric, nIter=nIter)
classificationKWARGS["classifiersConfigs"] = bestConfigs
classifier = classifierClass(NB_CORES=nbCores, **classificationKWARGS)
diff --git a/Code/MonoMutliViewClassifiers/utils/Transformations.py b/Code/MonoMutliViewClassifiers/utils/Transformations.py
index a28cccd4..026ff636 100644
--- a/Code/MonoMutliViewClassifiers/utils/Transformations.py
+++ b/Code/MonoMutliViewClassifiers/utils/Transformations.py
@@ -1,5 +1,6 @@
import numpy as np
+
def signLabels(labels):
if set(labels) == (0,1):
return np.array([label if label != 0 else -1 for label in labels])
--
GitLab