diff --git a/Code/MonoMultiViewClassifiers/ExecClassif.py b/Code/MonoMultiViewClassifiers/ExecClassif.py
index 094dbcdfb7f08f73ad951042d655df6c336b08dd..6585a15c3391cb41e04d48f09791d8b1b10cbbba 100644
--- a/Code/MonoMultiViewClassifiers/ExecClassif.py
+++ b/Code/MonoMultiViewClassifiers/ExecClassif.py
@@ -69,9 +69,15 @@ def initBenchmark(args):
def genViewsDictionnary(DATASET):
datasetsNames = DATASET.keys()
- viewsDictionary = dict((DATASET.get(datasetName).attrs["name"], int(datasetName[4:]))
- for datasetName in datasetsNames
- if datasetName[:4]=="View")
+ viewsDictionary = {}
+ for datasetName in datasetsNames:
+ if datasetName[:4]=="View":
+ viewName = DATASET.get(datasetName).attrs["name"]
+ if type(viewName)!=bytes:
+ viewsDictionary[viewName] = int(datasetName[4:])
+ else:
+ viewsDictionary[viewName.decode("utf-8")] = int(datasetName[4:])
+
return viewsDictionary
@@ -264,8 +270,10 @@ def execOneBenchmarkMonoCore(DATASET=None, LABELS_DICTIONARY=None, directory=Non
logging.debug("Start:\t Monoview benchmark")
for arguments in argumentDictionaries["Monoview"]:
kwargs = arguments["args"]
- views = [DATASET.get("View" + str(viewIndex)).attrs["name"] for viewIndex in
- range(DATASET.get("Metadata").attrs["nbView"])]
+ views = [DATASET.get("View" + str(viewIndex)).attrs["name"]
+ if type(DATASET.get("View" + str(viewIndex)).attrs["name"])!=bytes
+ else DATASET.get("View" + str(viewIndex)).attrs["name"].decode("utf-8")
+ for viewIndex in range(DATASET.get("Metadata").attrs["nbView"])]
neededViewIndex = views.index(kwargs["feat"])
X = DATASET.get("View" + str(neededViewIndex))
Y = labels
@@ -371,7 +379,11 @@ def execClassif(arguments):
viewsDictionary = genViewsDictionnary(DATASET)
nbViews = DATASET.get("Metadata").attrs["nbView"]
- views = [DATASET.get("View"+str(viewIndex)).attrs["name"] for viewIndex in range(nbViews)]
+
+ views = [DATASET.get("View"+str(viewIndex)).attrs["name"]
+ if type(DATASET.get("View"+str(viewIndex)).attrs["name"])!=bytes
+ else DATASET.get("View"+str(viewIndex)).attrs["name"].decode("utf-8")
+ for viewIndex in range(nbViews)]
NB_CLASS = DATASET.get("Metadata").attrs["nbClass"]
metrics = [metric.split(":") for metric in args.CL_metrics]
diff --git a/Code/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py b/Code/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
index ee0005fa04b2547af259e737edc9b6a4798a7cf9..31b5e549f31bc6dd20ac153be5feb86bdf795576 100644
--- a/Code/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
+++ b/Code/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
@@ -187,87 +187,88 @@ def ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFol
if __name__ == '__main__':
+ import argparse
pass
- # parser = argparse.ArgumentParser(
- # description='This methods permits to execute a multiclass classification with one single view. At this point the used classifier is a RandomForest. The GridSearch permits to vary the number of trees and CrossValidation with k-folds. The result will be a plot of the score per class and a CSV with the best classifier found by the GridSearch.',
- # 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('--type', metavar='STRING', action='store', help='Type of Dataset', default=".hdf5")
- # groupStandard.add_argument('--name', metavar='STRING', action='store',
- # help='Name of Database (default: %(default)s)', default='DB')
- # groupStandard.add_argument('--feat', metavar='STRING', action='store',
- # help='Name of Feature for Classification (default: %(default)s)', default='RGB')
- # groupStandard.add_argument('--pathF', metavar='STRING', action='store',
- # help='Path to the views (default: %(default)s)', default='Results-FeatExtr/')
- # groupStandard.add_argument('--fileCL', metavar='STRING', action='store',
- # help='Name of classLabels CSV-file (default: %(default)s)', default='classLabels.csv')
- # groupStandard.add_argument('--fileCLD', metavar='STRING', action='store',
- # help='Name of classLabels-Description CSV-file (default: %(default)s)',
- # default='classLabels-Description.csv')
- # groupStandard.add_argument('--fileFeat', metavar='STRING', action='store',
- # help='Name of feature CSV-file (default: %(default)s)', default='feature.csv')
- #
- # groupClass = parser.add_argument_group('Classification arguments')
- # groupClass.add_argument('--CL_type', metavar='STRING', action='store', help='Classifier to use',
- # default="RandomForest")
- # groupClass.add_argument('--CL_CV', metavar='INT', action='store', help='Number of k-folds for CV', type=int,
- # default=10)
- # groupClass.add_argument('--CL_Cores', metavar='INT', action='store', help='Number of cores, -1 for all', type=int,
- # default=1)
- # groupClass.add_argument('--CL_split', metavar='FLOAT', action='store', help='Split ratio for train and test',
- # type=float, default=0.9)
- # groupClass.add_argument('--CL_metrics', metavar='STRING', action='store',
- # help='Determine which metrics to use, separate with ":" if multiple, if empty, considering all',
- # default='')
- #
- # groupClassifier = parser.add_argument_group('Classifier Config')
- # groupClassifier.add_argument('--CL_config', metavar='STRING', nargs="+", action='store',
- # help='GridSearch: Determine the trees', default=['25:75:125:175'])
- #
- # args = parser.parse_args()
- #
- # classifierKWARGS = dict((key, value) for key, value in enumerate([arg.split(":") for arg in args.CL_config]))
- # ### Main Programm
- #
- #
- # # Configure Logger
- # directory = os.path.dirname(os.path.abspath(__file__)) + "/Results-ClassMonoView/"
- # logfilename = datetime.datetime.now().strftime("%Y_%m_%d") + "-CMV-" + args.name + "-" + args.feat + "-LOG"
- # 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())
- #
- # # Read the features
- # logging.debug("Start:\t Read " + args.type + " Files")
- #
- # if args.type == ".csv":
- # X = np.genfromtxt(args.pathF + args.fileFeat, delimiter=';')
- # Y = np.genfromtxt(args.pathF + args.fileCL, delimiter=';')
- # elif args.type == ".hdf5":
- # dataset = h5py.File(args.pathF + args.name + ".hdf5", "r")
- # viewsDict = dict((dataset.get("View" + str(viewIndex)).attrs["name"], viewIndex) for viewIndex in
- # range(dataset.get("Metadata").attrs["nbView"]))
- # X = dataset["View" + str(viewsDict[args.feat])][...]
- # Y = dataset["Labels"][...]
- #
- # logging.debug("Info:\t Shape of Feature:" + str(X.shape) + ", Length of classLabels vector:" + str(Y.shape))
- # logging.debug("Done:\t Read CSV Files")
- #
- # arguments = {args.CL_type + "KWARGS": classifierKWARGS, "feat": args.feat, "fileFeat": args.fileFeat,
- # "fileCL": args.fileCL, "fileCLD": args.fileCLD, "CL_type": args.CL_type}
- # ExecMonoview(X, Y, args.name, args.CL_split, args.CL_CV, args.CL_Cores, args.type, args.pathF,
- # metrics=args.CL_metrics, **arguments)
+ parser = argparse.ArgumentParser(
+ description='This methods permits to execute a multiclass classification with one single view. At this point the used classifier is a RandomForest. The GridSearch permits to vary the number of trees and CrossValidation with k-folds. The result will be a plot of the score per class and a CSV with the best classifier found by the GridSearch.',
+ 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('--type', metavar='STRING', action='store', help='Type of Dataset', default=".hdf5")
+ groupStandard.add_argument('--name', metavar='STRING', action='store',
+ help='Name of Database (default: %(default)s)', default='DB')
+ groupStandard.add_argument('--feat', metavar='STRING', action='store',
+ help='Name of Feature for Classification (default: %(default)s)', default='RGB')
+ groupStandard.add_argument('--pathF', metavar='STRING', action='store',
+ help='Path to the views (default: %(default)s)', default='Results-FeatExtr/')
+ groupStandard.add_argument('--fileCL', metavar='STRING', action='store',
+ help='Name of classLabels CSV-file (default: %(default)s)', default='classLabels.csv')
+ groupStandard.add_argument('--fileCLD', metavar='STRING', action='store',
+ help='Name of classLabels-Description CSV-file (default: %(default)s)',
+ default='classLabels-Description.csv')
+ groupStandard.add_argument('--fileFeat', metavar='STRING', action='store',
+ help='Name of feature CSV-file (default: %(default)s)', default='feature.csv')
+
+ groupClass = parser.add_argument_group('Classification arguments')
+ groupClass.add_argument('--CL_type', metavar='STRING', action='store', help='Classifier to use',
+ default="RandomForest")
+ groupClass.add_argument('--CL_CV', metavar='INT', action='store', help='Number of k-folds for CV', type=int,
+ default=10)
+ groupClass.add_argument('--CL_Cores', metavar='INT', action='store', help='Number of cores, -1 for all', type=int,
+ default=1)
+ groupClass.add_argument('--CL_split', metavar='FLOAT', action='store', help='Split ratio for train and test',
+ type=float, default=0.9)
+ groupClass.add_argument('--CL_metrics', metavar='STRING', action='store',
+ help='Determine which metrics to use, separate with ":" if multiple, if empty, considering all',
+ default='')
+
+ groupClassifier = parser.add_argument_group('Classifier Config')
+ groupClassifier.add_argument('--CL_config', metavar='STRING', nargs="+", action='store',
+ help='GridSearch: Determine the trees', default=['25:75:125:175'])
+
+ args = parser.parse_args()
+
+ classifierKWARGS = dict((key, value) for key, value in enumerate([arg.split(":") for arg in args.CL_config]))
+ ### Main Programm
+
+
+ # Configure Logger
+ directory = os.path.dirname(os.path.abspath(__file__)) + "/Results-ClassMonoView/"
+ logfilename = datetime.datetime.now().strftime("%Y_%m_%d") + "-CMV-" + args.name + "-" + args.feat + "-LOG"
+ 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())
+
+ # Read the features
+ logging.debug("Start:\t Read " + args.type + " Files")
+
+ if args.type == ".csv":
+ X = np.genfromtxt(args.pathF + args.fileFeat, delimiter=';')
+ Y = np.genfromtxt(args.pathF + args.fileCL, delimiter=';')
+ elif args.type == ".hdf5":
+ dataset = h5py.File(args.pathF + args.name + ".hdf5", "r")
+ viewsDict = dict((dataset.get("View" + str(viewIndex)).attrs["name"], viewIndex) for viewIndex in
+ range(dataset.get("Metadata").attrs["nbView"]))
+ X = dataset["View" + str(viewsDict[args.feat])][...]
+ Y = dataset["Labels"][...]
+
+ logging.debug("Info:\t Shape of Feature:" + str(X.shape) + ", Length of classLabels vector:" + str(Y.shape))
+ logging.debug("Done:\t Read CSV Files")
+
+ arguments = {args.CL_type + "KWARGS": classifierKWARGS, "feat": args.feat, "fileFeat": args.fileFeat,
+ "fileCL": args.fileCL, "fileCLD": args.fileCLD, "CL_type": args.CL_type}
+ ExecMonoview(X, Y, args.name, args.CL_split, args.CL_CV, args.CL_Cores, args.type, args.pathF,
+ metrics=args.CL_metrics, **arguments)
diff --git a/Code/MonoMultiViewClassifiers/MultiviewClassifiers/Mumbo/MumboModule.py b/Code/MonoMultiViewClassifiers/MultiviewClassifiers/Mumbo/MumboModule.py
index 50606d0e3435efc73d1b2b4d9418713bce52e811..fac4de3136af85ceaffb2b76f182fa1fe1adb3ba 100644
--- a/Code/MonoMultiViewClassifiers/MultiviewClassifiers/Mumbo/MumboModule.py
+++ b/Code/MonoMultiViewClassifiers/MultiviewClassifiers/Mumbo/MumboModule.py
@@ -118,6 +118,8 @@ def trainWeakClassifier_hdf5(classifier, classifierName, monoviewDataset, CLASS_
randomState, metric):
weights = computeWeights(DATASET_LENGTH, iterIndex, classifierIndex, CLASS_LABELS, costMatrices)
classifier, classes, isBad, averageScore = classifier.fit_hdf5(monoviewDataset, CLASS_LABELS, weights, metric)
+ if type(viewName) == bytes:
+ viewName = viewName.decode("utf-8")
logging.debug("\t\t\t"+viewName + " : " + str(averageScore))
return classifier, classes, isBad, averageScore
@@ -126,8 +128,7 @@ def gridSearch_hdf5(DATASET, labels, viewIndices, classificationKWARGS, learning
classifiersNames = classificationKWARGS["classifiersNames"]
bestSettings = []
for classifierIndex, classifierName in enumerate(classifiersNames):
- logging.debug("\tStart:\t Random search for " + classifierName + " on " +
- DATASET.get("View" + str(viewIndices[classifierIndex])).attrs["name"])
+ logging.debug("\tStart:\t Random search for " + classifierName + " on View" + str(viewIndices[classifierIndex]))
classifierModule = getattr(Classifiers, classifierName) # Permet d'appeler une fonction avec une string
classifierGridSearch = getattr(classifierModule, "hyperParamSearch")
bestSettings.append(classifierGridSearch(getV(DATASET, viewIndices[classifierIndex], learningIndices),
@@ -252,7 +253,7 @@ class MumboClass:
self.updateCostmatrices(NB_VIEW, trainLength, NB_CLASS, LABELS)
bestView, edge, bestFakeView = self.chooseView(viewsIndices, LABELS, trainLength)
self.bestViews[self.iterIndex] = bestView
- logging.debug("\t\t\t Best view : \t\t" + DATASET.get("View" + str(bestView)).attrs["name"])
+ logging.debug("\t\t\t Best view : \t\t View" + str(bestView))
if areBad.all():
self.generalAlphas[self.iterIndex] = 0.
else:
diff --git a/Code/MonoMultiViewClassifiers/MultiviewClassifiers/Mumbo/analyzeResults.py b/Code/MonoMultiViewClassifiers/MultiviewClassifiers/Mumbo/analyzeResults.py
index 0f00d2ad9f474d710a5132de218a0ee7c800b218..15a2acd899043ea30766d9939940882b3465b4f8 100644
--- a/Code/MonoMultiViewClassifiers/MultiviewClassifiers/Mumbo/analyzeResults.py
+++ b/Code/MonoMultiViewClassifiers/MultiviewClassifiers/Mumbo/analyzeResults.py
@@ -72,7 +72,10 @@ def error(testLabels, computedLabels):
def getDBConfig(DATASET, LEARNING_RATE, nbFolds, databaseName, validationIndices, LABELS_DICTIONARY):
nbView = DATASET.get("Metadata").attrs["nbView"]
- viewNames = [DATASET.get("View" + str(viewIndex)).attrs["name"] for viewIndex in range(nbView)]
+ viewNames = [DATASET.get("View" + str(viewIndex)).attrs["name"]
+ if type(DATASET.get("View" + str(viewIndex)).attrs["name"]) != bytes
+ else DATASET.get("View" + str(viewIndex)).attrs["name"].decode("utf-8")
+ for viewIndex in range(nbView)]
viewShapes = [getShape(DATASET, viewIndex) for viewIndex in range(nbView)]
DBString = "Dataset info :\n\t-Dataset name : " + databaseName
DBString += "\n\t-Labels : " + ', '.join(LABELS_DICTIONARY.values())
diff --git a/Code/MonoMultiViewClassifiers/utils/execution.py b/Code/MonoMultiViewClassifiers/utils/execution.py
index 840f4da70533bfd06456330c04a43c0e36a7dd39..325b05a5478b9bdccfddc6a4fbd8ca94f46e3d91 100644
--- a/Code/MonoMultiViewClassifiers/utils/execution.py
+++ b/Code/MonoMultiViewClassifiers/utils/execution.py
@@ -274,11 +274,19 @@ def initViews(DATASET, args):
NB_VIEW = DATASET.get("Metadata").attrs["nbView"]
if args.views != [""]:
allowedViews = args.views
- allViews = [str(DATASET.get("View" + str(viewIndex)).attrs["name"]) for viewIndex in range(NB_VIEW)]
- views = [str(DATASET.get("View" + str(viewIndex)).attrs["name"]) for viewIndex in range(NB_VIEW) if
- str(DATASET.get("View" + str(viewIndex)).attrs["name"]) in allowedViews]
- viewsIndices = [viewIndex for viewIndex in range(NB_VIEW) if
- str(DATASET.get("View" + str(viewIndex)).attrs["name"]) in allowedViews]
+ allViews = [str(DATASET.get("View" + str(viewIndex)).attrs["name"])
+ if type(DATASET.get("View" + str(viewIndex)).attrs["name"])!=bytes
+ else DATASET.get("View" + str(viewIndex)).attrs["name"].decode("utf-8")
+ for viewIndex in range(NB_VIEW)]
+ views = []
+ viewsIndices = []
+ for viewIndex in range(NB_VIEW):
+ viewName = DATASET.get("View" + str(viewIndex)).attrs["name"]
+ if type(viewName) == bytes:
+ viewName = viewName.decode("utf-8")
+ if viewName in allowedViews:
+ views.append(viewName)
+ viewsIndices.append(viewsIndices)
return views, viewsIndices, allViews
else:
views = [str(DATASET.get("View" + str(viewIndex)).attrs["name"]) for viewIndex in range(NB_VIEW)]