From 8f1c9a3e596501458d3bcdf32f519e24163f2933 Mon Sep 17 00:00:00 2001
From: Baptiste Bauvin <baptiste.bauvin.1@ulaval.ca>
Date: Tue, 24 Oct 2017 18:25:57 -0400
Subject: [PATCH] Refactored
---
.../Monoview/ExecClassifMonoView.py | 325 ++++++++++--------
Code/Versions.py | 58 +---
2 files changed, 189 insertions(+), 194 deletions(-)
diff --git a/Code/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py b/Code/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
index 661b44cd..4d1925da 100644
--- a/Code/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
+++ b/Code/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
@@ -24,29 +24,10 @@ __author__ = "Nikolas Huelsmann, Baptiste BAUVIN"
__status__ = "Prototype" # Production, Development, Prototype
# __date__ = 2016 - 03 - 25
-
-def ExecMonoview_multicore(directory, name, labelsNames, classificationIndices, KFolds, datasetFileIndex, databaseType,
- path, randomState, hyperParamSearch="randomizedSearch",
- metrics=[["accuracy_score", None]], nIter=30, **args):
- DATASET = h5py.File(path + name + str(datasetFileIndex) + ".hdf5", "r")
- kwargs = args["args"]
- views = [DATASET.get("View" + str(viewIndex)).attrs["name"] for viewIndex in
- range(DATASET.get("Metadata").attrs["nbView"])]
- neededViewIndex = views.index(kwargs["feat"])
- X = DATASET.get("View" + str(neededViewIndex))
- Y = DATASET.get("Labels").value
- return ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFolds, 1, databaseType, path,
- randomState, hyperParamSearch=hyperParamSearch,
- metrics=metrics, nIter=nIter, **args)
-
-
-def ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFolds, nbCores, databaseType, path,
- randomState, hyperParamSearch="randomizedSearch",
- metrics=[["accuracy_score", None]], nIter=30, **args):
- logging.debug("Start:\t Loading data")
+def initConstants(args, X, classificationIndices, labelsNames, name, directory):
try:
kwargs = args["args"]
- except:
+ except KeyError:
kwargs = args
t_start = time.time()
feat = X.attrs["name"]
@@ -56,6 +37,7 @@ def ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFol
labelsString = "-".join(labelsNames)
timestr = time.strftime("%Y%m%d-%H%M%S")
CL_type_string = CL_type
+
outputFileName = directory + "/" + CL_type_string + "/" + "/" + feat + "/" + timestr + "Results-" + CL_type_string + "-" + labelsString + \
'-learnRate' + str(learningRate) + '-' + name + "-" + feat + "-"
if not os.path.exists(os.path.dirname(outputFileName)):
@@ -64,26 +46,18 @@ def ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFol
except OSError as exc:
if exc.errno != errno.EEXIST:
raise
- logging.debug("Done:\t Loading data")
- # Determine the Database to extract features
- logging.debug("Info:\t Classification - Database:" + str(name) + " Feature:" + str(feat) + " train ratio:"
- + str(learningRate) + ", CrossValidation k-folds: " + str(KFolds.n_splits) + ", cores:"
- + str(nbCores) + ", algorithm : " + CL_type)
+ return kwargs, t_start, feat, CL_type, X, learningRate, labelsString, timestr, outputFileName
+def initTrainTest(X, Y, classificationIndices):
trainIndices, testIndices = classificationIndices
- # Calculate Train/Test data
- logging.debug("Start:\t Determine Train/Test split")
X_train = extractSubset(X, trainIndices)
X_test = extractSubset(X, testIndices)
y_train = Y[trainIndices]
y_test = Y[testIndices]
+ return X_train, y_train, X_test, y_test
- logging.debug("Info:\t Shape X_train:" + str(X_train.shape) + ", Length of y_train:" + str(len(y_train)))
- logging.debug("Info:\t Shape X_test:" + str(X_test.shape) + ", Length of y_test:" + str(len(y_test)))
- logging.debug("Done:\t Determine Train/Test split")
-
- classifierModule = getattr(MonoviewClassifiers, CL_type)
-
+def getKWARGS(classifierModule, hyperParamSearch, nIter, CL_type, X_train, y_train, randomState,
+ outputFileName, KFolds, nbCores, metrics, kwargs):
if hyperParamSearch != "None":
classifierHPSearch = getattr(classifierModule, hyperParamSearch)
logging.debug("Start:\t RandomSearch best settings with " + str(nIter) + " iterations for " + CL_type)
@@ -92,42 +66,15 @@ def ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFol
clKWARGS = dict((str(index), desc) for index, desc in enumerate(cl_desc))
logging.debug("Done:\t RandomSearch best settings")
else:
- clKWARGS = kwargs[kwargs["CL_type"] + "KWARGS"]
- logging.debug("Start:\t Training")
- cl_res = classifierModule.fit(X_train, y_train, randomState, NB_CORES=nbCores, **clKWARGS)
- logging.debug("Done:\t Training")
-
- logging.debug("Start:\t Predicting")
- # Stats Result
- y_train_pred = cl_res.predict(X_train)
- y_test_pred = cl_res.predict(X_test)
-
- full_labels = cl_res.predict(X)
- logging.debug("Done:\t Predicting")
- t_end = time.time() - t_start
- logging.debug("Info:\t Time for training and predicting: " + str(t_end) + "[s]")
-
- logging.debug("Start:\t Getting Results")
+ clKWARGS = kwargs[CL_type + "KWARGS"]
+ return clKWARGS
- stringAnalysis, imagesAnalysis, metricsScores = execute(name, classificationIndices, KFolds, nbCores,
- hyperParamSearch, metrics, nIter, feat, CL_type,
- clKWARGS, labelsNames, X.shape,
- y_train, y_train_pred, y_test, y_test_pred, t_end,
- randomState, cl_res, outputFileName)
- cl_desc = [value for key, value in sorted(clKWARGS.items())]
- logging.debug("Done:\t Getting Results")
+def saveResults(stringAnalysis, outputFileName, full_labels_pred, y_train_pred, y_train, imagesAnalysis):
logging.info(stringAnalysis)
- # labelsString = "-".join(labelsNames)
- # timestr = time.strftime("%Y%m%d-%H%M%S")
- # CL_type_string = CL_type
- # outputFileName = directory + "/"+CL_type_string+"/"+"/"+feat+"/"+timestr +"Results-" + CL_type_string + "-" + labelsString + \
- # '-learnRate' + str(learningRate) + '-' + name + "-" + feat + "-"
-
-
outputTextFile = open(outputFileName + '.txt', 'w')
outputTextFile.write(stringAnalysis)
outputTextFile.close()
- np.savetxt(outputFileName + "full_pred.csv", full_labels.astype(np.int16), delimiter=",")
+ np.savetxt(outputFileName + "full_pred.csv", full_labels_pred.astype(np.int16), delimiter=",")
np.savetxt(outputFileName + "train_pred.csv", y_train_pred.astype(np.int16), delimiter=",")
np.savetxt(outputFileName + "train_labels.csv", y_train.astype(np.int16), delimiter=",")
@@ -142,92 +89,170 @@ def ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFol
imagesAnalysis[imageName].savefig(outputFileName + imageName + '.png')
- logging.info("Done:\t Result Analysis")
+
+def ExecMonoview_multicore(directory, name, labelsNames, classificationIndices, KFolds, datasetFileIndex, databaseType,
+ path, randomState, hyperParamSearch="randomizedSearch",
+ metrics=[["accuracy_score", None]], nIter=30, **args):
+ DATASET = h5py.File(path + name + str(datasetFileIndex) + ".hdf5", "r")
+ kwargs = args["args"]
+ views = [DATASET.get("View" + str(viewIndex)).attrs["name"] for viewIndex in
+ range(DATASET.get("Metadata").attrs["nbView"])]
+ neededViewIndex = views.index(kwargs["feat"])
+ X = DATASET.get("View" + str(neededViewIndex))
+ Y = DATASET.get("Labels").value
+ return ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFolds, 1, databaseType, path,
+ randomState, hyperParamSearch=hyperParamSearch,
+ metrics=metrics, nIter=nIter, **args)
+
+
+def ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFolds, nbCores, databaseType, path,
+ randomState, hyperParamSearch="randomizedSearch",
+ metrics=[["accuracy_score", None]], nIter=30, **args):
+
+ logging.debug("Start:\t Loading data")
+ kwargs, \
+ t_start, \
+ feat, \
+ CL_type, \
+ X, \
+ learningRate, \
+ labelsString, \
+ timestr, \
+ outputFileName = initConstants(args, X, classificationIndices, labelsNames, name, directory)
+ logging.debug("Done:\t Loading data")
+
+ logging.debug("Info:\t Classification - Database:" + str(name) + " Feature:" + str(feat) + " train ratio:"
+ + str(learningRate) + ", CrossValidation k-folds: " + str(KFolds.n_splits) + ", cores:"
+ + str(nbCores) + ", algorithm : " + CL_type)
+
+ logging.debug("Start:\t Determine Train/Test split")
+ X_train, y_train, X_test, y_test = initTrainTest(X, Y, classificationIndices)
+ logging.debug("Info:\t Shape X_train:" + str(X_train.shape) + ", Length of y_train:" + str(len(y_train)))
+ logging.debug("Info:\t Shape X_test:" + str(X_test.shape) + ", Length of y_test:" + str(len(y_test)))
+ logging.debug("Done:\t Determine Train/Test split")
+
+ logging.debug("Start:\t Generate classifier args")
+ classifierModule = getattr(MonoviewClassifiers, CL_type)
+ clKWARGS = getKWARGS(classifierModule, hyperParamSearch,
+ nIter, CL_type, X_train, y_train,
+ randomState, outputFileName,
+ KFolds, nbCores, metrics, kwargs)
+ logging.debug("Done:\t Generate classifier args")
+
+ logging.debug("Start:\t Training")
+ cl_res = classifierModule.fit(X_train, y_train, randomState, NB_CORES=nbCores, **clKWARGS)
+ logging.debug("Done:\t Training")
+
+ logging.debug("Start:\t Predicting")
+ full_labels_pred = cl_res.predict(X)
+ y_train_pred = full_labels_pred[classificationIndices[0]]
+ y_test_pred = full_labels_pred[classificationIndices[1]]
+ logging.debug("Done:\t Predicting")
+
+ t_end = time.time() - t_start
+ logging.debug("Info:\t Time for training and predicting: " + str(t_end) + "[s]")
+
+ logging.debug("Start:\t Getting Results")
+ stringAnalysis, \
+ imagesAnalysis, \
+ metricsScores = execute(name, classificationIndices, KFolds, nbCores,
+ hyperParamSearch, metrics, nIter, feat, CL_type,
+ clKWARGS, labelsNames, X.shape,
+ y_train, y_train_pred, y_test, y_test_pred, t_end,
+ randomState, cl_res, outputFileName)
+ cl_desc = [value for key, value in sorted(clKWARGS.items())]
+ logging.debug("Done:\t Getting Results")
+
+ logging.debug("Start:\t Saving results")
+ saveResults(stringAnalysis, outputFileName, full_labels_pred, y_train_pred, y_train, imagesAnalysis)
+ logging.info("Done:\t Saving Results")
+
viewIndex = args["viewIndex"]
- return viewIndex, [CL_type, cl_desc + [feat], metricsScores, full_labels, clKWARGS]
+ return viewIndex, [CL_type, cl_desc + [feat], metricsScores, full_labels_pred, clKWARGS]
if __name__ == '__main__':
- 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)
+ 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)
diff --git a/Code/Versions.py b/Code/Versions.py
index 0da83a60..e7a8c3d3 100644
--- a/Code/Versions.py
+++ b/Code/Versions.py
@@ -1,110 +1,80 @@
-#!/usr/bin/env python
-
-""" Script to render versions of modules used """
-
-# Import built-in modules
-
-# Import 3rd party modules
-
-# Import own modules
-
-
# Author-Info
__author__ = "Baptiste Bauvin"
__status__ = "Prototype" # Production, Development, Prototype
-# __date__ = 2016 - 03 - 25
def testVersions():
isUpToDate = True
toInstall = []
+
try:
import sys
- # print("Python-V.: " + sys.version)
- except:
- # print "Please install Python 2.7"
+ except ImportError:
raise
try:
import pyscm
- except:
- # print "Please install pyscm"
+ except ImportError:
isUpToDate = False
toInstall.append("pyscm")
try:
import numpy
- # print("Numpy-V.: " + numpy.version.version)
- except:
- # print "Please install numpy module"
+ except ImportError:
isUpToDate = False
toInstall.append("numpy")
try:
import scipy
- # print("Scipy-V.: " + scipy.__version__)
- except:
- # print "Please install scipy module"
+ except ImportError:
isUpToDate = False
toInstall.append("scipy")
try:
import matplotlib
- # print("Matplotlib-V.: " + matplotlib.__version__)
- except:
- # print "Please install matplotlib module"
+ except ImportError:
isUpToDate = False
toInstall.append("matplotlib")
try:
import sklearn
- # print("Sklearn-V.: " + sklearn.__version__)
- except:
- # print "Please install sklearn module"
+ except ImportError:
isUpToDate = False
toInstall.append("sklearn")
try:
- import logging # To create Log-Files
- # print("Logging: " + logging.__version__)
- except:
- # print "Please install logging module"
+ import logging
+ except ImportError:
isUpToDate = False
toInstall.append("logging")
try:
import joblib
- # print("joblib: " + joblib.__version__)
- except:
- # print "Pease install joblib module"
+ except ImportError:
isUpToDate = False
toInstall.append("joblib")
try:
import argparse
- # print("argparse: " + argparse.__version__)
- except:
- # print "Pease install argparse module"
+ except ImportError:
isUpToDate = False
toInstall.append("argparse")
try:
import h5py #
- # print("h5py: " + h5py.__version__)
- except:
- # print "Pease install h5py module"
+ except ImportError:
isUpToDate = False
toInstall.append("h5py")
try:
import graphviz #
- except:
+ except ImportError:
isUpToDate = False
toInstall.append("graphviz")
try:
import pickle #
- except:
+ except ImportError:
isUpToDate = False
toInstall.append("pickle")
--
GitLab