diff --git a/config_files/config.ini b/config_files/config.ini
index 29b0823c8a3aead18d720d3f8c086bb8979e7915..027ca27a52ab8706682e1dd4770a103aa8cce11f 100644
--- a/config_files/config.ini
+++ b/config_files/config.ini
@@ -27,7 +27,7 @@ type = list_str ; Monoview Multiview
algos_monoview = list_str ; all
algos_multiview = list_str ; all
statsiter = int ; 2
-metrics = list_str ; all
+metrics = list_str ; accuracy_score f1_score
metric_princ = str ; f1_score
HPS_type = str ; randomizedSearch
HPS_iter = int ; 2
@@ -62,6 +62,11 @@ n_estimators = list_int ; 50
base_estimator = list_str ; DecisionTreeClassifier
n_stumps = list_int ; 1
+[AdaboostPregen10]
+n_estimators = list_int ; 50
+base_estimator = list_str ; DecisionTreeClassifier
+n_stumps = list_int ; 1
+
[AdaboostGraalpy]
n_iterations = list_int ; 50
n_stumps = list_int ; 1
@@ -108,6 +113,30 @@ n_stumps = list_int ; 1
n_max_iterations = list_int ; 10
n_stumps = list_int ; 1
+[CGDesc10]
+n_max_iterations = list_int ; 10
+n_stumps = list_int ; 1
+
+[CGreed]
+n_max_iterations = list_int ; 10
+n_stumps = list_int ; 1
+
+[QarBoost]
+n_max_iterations = list_int ; 10
+n_stumps = list_int ; 1
+
+[QarBoostNC3]
+n_max_iterations = list_int ; 10
+n_stumps = list_int ; 1
+
+[QarBoostv2]
+n_max_iterations = list_int ; 10
+n_stumps = list_int ; 1
+
+[QarBoostv3]
+n_max_iterations = list_int ; 10
+n_stumps = list_int ; 1
+
[CBBoost]
n_max_iterations = list_int ; 10
n_stumps = list_int ; 1
diff --git a/multiview_platform/MonoMultiViewClassifiers/ExecClassif.py b/multiview_platform/MonoMultiViewClassifiers/ExecClassif.py
index 25b3e5acc143f602b86313651a97649838828eb9..4559834641ffd30f1e6931d031159481e63d4b23 100644
--- a/multiview_platform/MonoMultiViewClassifiers/ExecClassif.py
+++ b/multiview_platform/MonoMultiViewClassifiers/ExecClassif.py
@@ -232,14 +232,16 @@ def initMonoviewKWARGS(args, classifiersNames):
monoviewKWARGS = {}
for classifiersName in classifiersNames:
try:
- classifierModule = getattr(MonoviewClassifiers, classifiersName)
+ getattr(MonoviewClassifiers, classifiersName)
except AttributeError:
raise AttributeError(
classifiersName + " is not implemented in MonoviewClassifiers, "
"please specify the name of the file in MonoviewClassifiers")
- monoviewKWARGS[
- classifiersName + "KWARGSInit"] = classifierModule.formatCmdArgs(
- args)
+ try:
+ monoviewKWARGS[
+ classifiersName + "KWARGSInit"] = args[classifiersName]
+ except KeyError:
+ raise KeyError("No configuration was provided for "+classifiersName+", please add it's configuration to the .ini file")
logging.debug("Done:\t Initializing Monoview classifiers arguments")
return monoviewKWARGS
@@ -336,13 +338,13 @@ def execOneBenchmark(coreIndex=-1, LABELS_DICTIONARY=None, directory=None,
logging.debug("Start:\t Monoview benchmark")
resultsMonoview += [
- ExecMonoview_multicore(directory, args.name, labelsNames,
+ ExecMonoview_multicore(directory, args["Base"]["name"], labelsNames,
classificationIndices, kFolds,
- coreIndex, args.type, args.pathF, randomState,
+ coreIndex, args["Base"]["type"], args["Base"]["pathf"], randomState,
labels,
hyperParamSearch=hyperParamSearch,
metrics=metrics,
- nIter=args.CL_HPS_iter, **argument)
+ nIter=args["Classification"]["hps_iter"], **argument)
for argument in argumentDictionaries["Monoview"]]
logging.debug("Done:\t Monoview benchmark")
@@ -357,11 +359,11 @@ def execOneBenchmark(coreIndex=-1, LABELS_DICTIONARY=None, directory=None,
logging.debug("Start:\t Multiview benchmark")
resultsMultiview = [
- ExecMultiview_multicore(directory, coreIndex, args.name,
- classificationIndices, kFolds, args.type,
- args.pathF, LABELS_DICTIONARY, randomState,
+ ExecMultiview_multicore(directory, coreIndex, args["Base"]["name"],
+ classificationIndices, kFolds, args["Base"]["type"],
+ args["Base"]["pathf"], LABELS_DICTIONARY, randomState,
labels, hyperParamSearch=hyperParamSearch,
- metrics=metrics, nIter=args.CL_HPS_iter,
+ metrics=metrics, nIter=args["Classification"]["hps_iter"],
**arguments)
for arguments in argumentDictionaries["Multiview"]]
logging.debug("Done:\t Multiview benchmark")
@@ -392,13 +394,13 @@ def execOneBenchmark_multicore(nbCores=-1, LABELS_DICTIONARY=None,
nbMulticoreToDo = int(math.ceil(float(nbExperiments) / nbCores))
for stepIndex in range(nbMulticoreToDo):
resultsMonoview += (Parallel(n_jobs=nbCores)(
- delayed(ExecMonoview_multicore)(directory, args.name, labelsNames,
+ delayed(ExecMonoview_multicore)(directory, args["Base"]["name"], labelsNames,
classificationIndices, kFolds,
- coreIndex, args.type, args.pathF,
+ coreIndex, args["Base"]["type"], args["Base"]["pathf"],
randomState, labels,
hyperParamSearch=hyperParamSearch,
metrics=metrics,
- nIter=args.CL_HPS_iter,
+ nIter=args["Classification"]["hps_iter"],
**argumentDictionaries["Monoview"][
coreIndex + stepIndex * nbCores])
for coreIndex in
@@ -420,14 +422,14 @@ def execOneBenchmark_multicore(nbCores=-1, LABELS_DICTIONARY=None,
nbMulticoreToDo = int(math.ceil(float(nbExperiments) / nbCores))
for stepIndex in range(nbMulticoreToDo):
resultsMultiview += Parallel(n_jobs=nbCores)(
- delayed(ExecMultiview_multicore)(directory, coreIndex, args.name,
+ delayed(ExecMultiview_multicore)(directory, coreIndex, args["Base"]["name"],
classificationIndices, kFolds,
- args.type, args.pathF,
+ args["Base"]["type"], args["Base"]["pathf"],
LABELS_DICTIONARY, randomState,
labels,
hyperParamSearch=hyperParamSearch,
metrics=metrics,
- nIter=args.CL_HPS_iter,
+ nIter=args["Classification"]["hps_iter"],
**
argumentDictionaries["Multiview"][
stepIndex * nbCores + coreIndex])
@@ -457,11 +459,11 @@ def execOneBenchmarkMonoCore(DATASET=None, LABELS_DICTIONARY=None,
X = DATASET.get("View" + str(arguments["viewIndex"]))
Y = labels
resultsMonoview += [
- ExecMonoview(directory, X, Y, args.name, labelsNames,
+ ExecMonoview(directory, X, Y, args["Base"]["name"], labelsNames,
classificationIndices, kFolds,
- 1, args.type, args.pathF, randomState,
+ 1, args["Base"]["type"], args["Base"]["pathf"], randomState,
hyperParamSearch=hyperParamSearch, metrics=metrics,
- nIter=args.CL_HPS_iter, **arguments)]
+ nIter=args["Classification"]["hps_iter"], **arguments)]
logging.debug("Done:\t Monoview benchmark")
logging.debug("Start:\t Multiview arguments initialization")
@@ -478,11 +480,11 @@ def execOneBenchmarkMonoCore(DATASET=None, LABELS_DICTIONARY=None,
resultsMultiview = []
for arguments in argumentDictionaries["Multiview"]:
resultsMultiview += [
- ExecMultiview(directory, DATASET, args.name, classificationIndices,
- kFolds, 1, args.type,
- args.pathF, LABELS_DICTIONARY, randomState, labels,
+ ExecMultiview(directory, DATASET, args["Base"]["name"], classificationIndices,
+ kFolds, 1, args["Base"]["type"],
+ args["Base"]["pathf"], LABELS_DICTIONARY, randomState, labels,
hyperParamSearch=hyperParamSearch,
- metrics=metrics, nIter=args.CL_HPS_iter, **arguments)]
+ metrics=metrics, nIter=args["Classification"]["hps_iter"], **arguments)]
logging.debug("Done:\t Multiview benchmark")
return [flag, resultsMonoview + resultsMultiview]
@@ -633,11 +635,12 @@ def execClassif(arguments):
views, viewsIndices, allViews = execution.initViews(DATASET, args["Base"]["views"])
viewsDictionary = genViewsDictionnary(DATASET, views)
+ print(viewsDictionary)
nbViews = len(views)
NB_CLASS = DATASET.get("Metadata").attrs["nbClass"]
metrics = [metric.split(":") for metric in args["Classification"]["metrics"]]
- if metrics == [[""]]:
+ if metrics == [["all"]]:
metricsNames = [name for _, name, isPackage
in pkgutil.iter_modules(
['./MonoMultiViewClassifiers/Metrics']) if
@@ -664,7 +667,6 @@ def execClassif(arguments):
argumentDictionaries, benchmark, nbViews,
views, viewsIndices)
nbMulticlass = len(labelsCombinations)
-
results_mean_stds = execBenchmark(nbCores, statsIter, nbMulticlass,
benchmarkArgumentDictionaries, splits, directories,
directory, multiclassLabels, metrics, LABELS_DICTIONARY,
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
index 0e6890857c8e9b56801acf2d759f1f9ccb00bb32..27f9d69d23e22c2ccef05fdbda05c18031e13a37 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
@@ -228,132 +228,132 @@ def saveResults(stringAnalysis, outputFileName, full_labels_pred, y_train_pred,
imagesAnalysis[imageName].savefig(
outputFileName + imageName + '.png', transparent=True)
-
-if __name__ == '__main__':
- """The goal of this part of the module is to be able to execute a monoview experimentation
- on a node of a cluster independently.
- So one need to fill in all the ExecMonoview function arguments with the parse arg function
- It could be a good idea to use pickle to store all the 'simple' args in order to reload them easily"""
- import argparse
- import pickle
-
- from ..utils import Dataset
-
- parser = argparse.ArgumentParser(
- description='This methods is used to execute a multiclass classification with one single view. ',
- formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-
- 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='Plausible')
- groupStandard.add_argument('--cl_name', metavar='STRING', action='store',
- help='THe name of the monoview classifier to use',
- default='DecisionTree')
- groupStandard.add_argument('--view', metavar='STRING', action='store',
- help='Name of the view used', default='View0')
- groupStandard.add_argument('--pathF', metavar='STRING', action='store',
- help='Path to the database hdf5 file',
- default='../../../Data/Plausible')
- groupStandard.add_argument('--directory', metavar='STRING', action='store',
- help='Path of the output directory', default='')
- groupStandard.add_argument('--labelsNames', metavar='STRING',
- action='store', nargs='+',
- help='Name of the labels used for classification',
- default=['Yes', 'No'])
- groupStandard.add_argument('--classificationIndices', metavar='STRING',
- action='store',
- help='Path to the classificationIndices pickle file',
- default='')
- groupStandard.add_argument('--KFolds', metavar='STRING', action='store',
- help='Path to the kFolds pickle file',
- default='')
- groupStandard.add_argument('--nbCores', metavar='INT', action='store',
- help='Number of cores, -1 for all',
- type=int, default=1)
- groupStandard.add_argument('--randomState', metavar='INT', action='store',
- help='Seed for the random state or pickable randomstate file',
- default=42)
- groupStandard.add_argument('--hyperParamSearch', metavar='STRING',
- action='store',
- help='The type of method used to search the best set of hyper parameters',
- default='randomizedSearch')
- groupStandard.add_argument('--metrics', metavar='STRING', action='store',
- help='Path to the pickle file describing the metricsused to analyze the performance',
- default='')
- groupStandard.add_argument('--kwargs', metavar='STRING', action='store',
- help='Path to the pickle file containing the key-words arguments used for classification',
- default='')
- groupStandard.add_argument('--nIter', metavar='INT', action='store',
- help='Number of itetarion in hyper parameter search',
- type=int,
- default=10)
-
- args = parser.parse_args()
-
- directory = args.directory
- name = args.name
- classifierName = args.cl_name
- labelsNames = args.labelsNames
- viewName = args.view
- with open(args.classificationIndices, 'rb') as handle:
- classificationIndices = pickle.load(handle)
- with open(args.KFolds, 'rb') as handle:
- KFolds = pickle.load(handle)
- nbCores = args.nbCores
- path = args.pathF
- with open(args.randomState, 'rb') as handle:
- randomState = pickle.load(handle)
- hyperParamSearch = args.hyperParamSearch
- with open(args.metrics, 'rb') as handle:
- metrics = pickle.load(handle)
- nIter = args.nIter
- with open(args.kwargs, 'rb') as handle:
- kwargs = pickle.load(handle)
-
- databaseType = None
-
- # Extract the data using MPI
- X, Y = Dataset.getMonoviewShared(path, name, viewName)
-
- # Init log
- logFileName = time.strftime(
- "%Y_%m_%d-%H_%M_%S") + "-" + name + "-" + viewName + "-" + classifierName + '-LOG'
- 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):
- testFileName = logFileName + "-" + str(i) + ".log"
- if not (os.path.isfile(directory + testFileName)):
- logFile = directory + testFileName
- break
- else:
- logFile += ".log"
- logging.basicConfig(format='%(asctime)s %(levelname)s: %(message)s',
- filename=logFile, level=logging.DEBUG,
- filemode='w')
- if args.log:
- logging.getLogger().addHandler(logging.StreamHandler())
-
- # Computing on multiple cores
- res = ExecMonoview(directory, X, Y, name, labelsNames,
- classificationIndices, KFolds, nbCores, databaseType,
- path,
- randomState, hyperParamSearch=hyperParamSearch,
- metrics=metrics, nIter=nIter, **kwargs)
-
- with open(directory + "res.pickle", "wb") as handle:
- pickle.dump(res, handle)
-
- # Pickle the res in a file to be reused.
- # Go put a token in the token files without breaking everything.
-
- # Need to write a function to be able to know the timeu sed
- # for a monoview experimentation approximately and the ressource it uses to write automatically the file in the shell
- # it will have to be a not-too close approx as the taskswont be long and Ram-o-phage
+#
+# if __name__ == '__main__':
+# """The goal of this part of the module is to be able to execute a monoview experimentation
+# on a node of a cluster independently.
+# So one need to fill in all the ExecMonoview function arguments with the parse arg function
+# It could be a good idea to use pickle to store all the 'simple' args in order to reload them easily"""
+# import argparse
+# import pickle
+#
+# from ..utils import Dataset
+#
+# parser = argparse.ArgumentParser(
+# description='This methods is used to execute a multiclass classification with one single view. ',
+# formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+#
+# 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='Plausible')
+# groupStandard.add_argument('--cl_name', metavar='STRING', action='store',
+# help='THe name of the monoview classifier to use',
+# default='DecisionTree')
+# groupStandard.add_argument('--view', metavar='STRING', action='store',
+# help='Name of the view used', default='View0')
+# groupStandard.add_argument('--pathF', metavar='STRING', action='store',
+# help='Path to the database hdf5 file',
+# default='../../../Data/Plausible')
+# groupStandard.add_argument('--directory', metavar='STRING', action='store',
+# help='Path of the output directory', default='')
+# groupStandard.add_argument('--labelsNames', metavar='STRING',
+# action='store', nargs='+',
+# help='Name of the labels used for classification',
+# default=['Yes', 'No'])
+# groupStandard.add_argument('--classificationIndices', metavar='STRING',
+# action='store',
+# help='Path to the classificationIndices pickle file',
+# default='')
+# groupStandard.add_argument('--KFolds', metavar='STRING', action='store',
+# help='Path to the kFolds pickle file',
+# default='')
+# groupStandard.add_argument('--nbCores', metavar='INT', action='store',
+# help='Number of cores, -1 for all',
+# type=int, default=1)
+# groupStandard.add_argument('--randomState', metavar='INT', action='store',
+# help='Seed for the random state or pickable randomstate file',
+# default=42)
+# groupStandard.add_argument('--hyperParamSearch', metavar='STRING',
+# action='store',
+# help='The type of method used to search the best set of hyper parameters',
+# default='randomizedSearch')
+# groupStandard.add_argument('--metrics', metavar='STRING', action='store',
+# help='Path to the pickle file describing the metricsused to analyze the performance',
+# default='')
+# groupStandard.add_argument('--kwargs', metavar='STRING', action='store',
+# help='Path to the pickle file containing the key-words arguments used for classification',
+# default='')
+# groupStandard.add_argument('--nIter', metavar='INT', action='store',
+# help='Number of itetarion in hyper parameter search',
+# type=int,
+# default=10)
+#
+# args = parser.parse_args()
+#
+# directory = args.directory
+# name = args.name
+# classifierName = args.cl_name
+# labelsNames = args.labelsNames
+# viewName = args.view
+# with open(args.classificationIndices, 'rb') as handle:
+# classificationIndices = pickle.load(handle)
+# with open(args.KFolds, 'rb') as handle:
+# KFolds = pickle.load(handle)
+# nbCores = args.nbCores
+# path = args.pathF
+# with open(args.randomState, 'rb') as handle:
+# randomState = pickle.load(handle)
+# hyperParamSearch = args.hyperParamSearch
+# with open(args.metrics, 'rb') as handle:
+# metrics = pickle.load(handle)
+# nIter = args.nIter
+# with open(args.kwargs, 'rb') as handle:
+# kwargs = pickle.load(handle)
+#
+# databaseType = None
+#
+# # Extract the data using MPI
+# X, Y = Dataset.getMonoviewShared(path, name, viewName)
+#
+# # Init log
+# logFileName = time.strftime(
+# "%Y_%m_%d-%H_%M_%S") + "-" + name + "-" + viewName + "-" + classifierName + '-LOG'
+# 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):
+# testFileName = logFileName + "-" + str(i) + ".log"
+# if not (os.path.isfile(directory + testFileName)):
+# logFile = directory + testFileName
+# break
+# else:
+# logFile += ".log"
+# logging.basicConfig(format='%(asctime)s %(levelname)s: %(message)s',
+# filename=logFile, level=logging.DEBUG,
+# filemode='w')
+# if args.log:
+# logging.getLogger().addHandler(logging.StreamHandler())
+#
+# # Computing on multiple cores
+# res = ExecMonoview(directory, X, Y, name, labelsNames,
+# classificationIndices, KFolds, nbCores, databaseType,
+# path,
+# randomState, hyperParamSearch=hyperParamSearch,
+# metrics=metrics, nIter=nIter, **kwargs)
+#
+# with open(directory + "res.pickle", "wb") as handle:
+# pickle.dump(res, handle)
+#
+# # Pickle the res in a file to be reused.
+# # Go put a token in the token files without breaking everything.
+#
+# # Need to write a function to be able to know the timeu sed
+# # for a monoview experimentation approximately and the ressource it uses to write automatically the file in the shell
+# # it will have to be a not-too close approx as the taskswont be long and Ram-o-phage
diff --git a/multiview_platform/MonoMultiViewClassifiers/utils/GetMultiviewDb.py b/multiview_platform/MonoMultiViewClassifiers/utils/GetMultiviewDb.py
index 668ff11bf85654f458e998ef66f9ed2c28ad2ef4..5821bf0261b618ba2d945c3e20a20e70bce25202 100644
--- a/multiview_platform/MonoMultiViewClassifiers/utils/GetMultiviewDb.py
+++ b/multiview_platform/MonoMultiViewClassifiers/utils/GetMultiviewDb.py
@@ -68,7 +68,7 @@ def deleteHDF5(benchmarkArgumentsDictionaries, nbCores, DATASET):
logging.debug("Start:\t Deleting datasets for multiprocessing")
for coreIndex in range(nbCores):
- os.remove(args.pathF + args.name + str(coreIndex) + ".hdf5")
+ os.remove(args["Base"]["pathf"] + args["Base"]["name"] + str(coreIndex) + ".hdf5")
filename = DATASET.filename
DATASET.close()
if "_temp_" in filename:
diff --git a/multiview_platform/MonoMultiViewClassifiers/utils/execution.py b/multiview_platform/MonoMultiViewClassifiers/utils/execution.py
index 06305d19c4c67016be62f16b0b34b64332fa7381..d297a232a1d6091734a8c90818cde9978b6b86b0 100644
--- a/multiview_platform/MonoMultiViewClassifiers/utils/execution.py
+++ b/multiview_platform/MonoMultiViewClassifiers/utils/execution.py
@@ -911,8 +911,7 @@ def initViews(DATASET, argViews):
Names of all the available views in the dataset.
"""
NB_VIEW = DATASET.get("Metadata").attrs["nbView"]
- print(NB_VIEW)
- if argViews != [""]:
+ if argViews != ["all"]:
allowedViews = argViews
allViews = [str(DATASET.get("View" + str(viewIndex)).attrs["name"])
if type(