def classify(runID, trainingSet, testingSet):
[trainingFile,
testingFile] = arffWriter.writeArffFiles(runID, trainingSet,
testingSet)
return wekaAPI.execute(trainingFile, testingFile,
"weka.classifiers.bayes.NaiveBayesMultinomial",
[])
def classify(runID, trainingSet, testingSet):
[trainingFile,
testingFile] = arffWriter.writeArffFiles(runID, trainingSet,
testingSet)
# deep learning
if config.DEEP_LEARNING_METHOD != -1:
if config.DEEP_LEARNING_METHOD == 1:
logistic_sgd_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 2:
[trainingFile,
testingFile] = dA_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 3:
mlp_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 4:
SdA_2.runDL([trainingFile, testingFile])
if config.NUM_MONITORED_SITES != -1:
[accuracy, debugInfo] = ['NA', []]
return [accuracy, debugInfo]
'''
return wekaAPI.execute( trainingFile,
testingFile,
"weka.Run weka.classifiers.functions.LibSVM",
['-K','2', # RBF kernel
'-G','0.0000019073486328125', # Gamma
'-C','131072'] ) # Cost
'''
if config.CROSS_VALIDATION == 0:
return wekaAPI.execute(
trainingFile,
testingFile,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-K',
'2', # RBF kernel
'-G',
'0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C',
'131072'
]) # Cost
else:
file = Utils.joinTrainingTestingFiles(
trainingFile, testingFile) # join and shuffle
return wekaAPI.executeCrossValidation(
file,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-x',
str(config.CROSS_VALIDATION), # number of folds
'-K',
'2', # RBF kernel
'-G',
'0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C',
'131072'
]) # Cost
def classify( runID, trainingSet, testingSet ):
[trainingFile,testingFile] = arffWriter.writeArffFiles( runID, trainingSet, testingSet )
return wekaAPI.execute( trainingFile,
testingFile,
"weka.Run weka.classifiers.functions.LibSVM",
['-K','2', # RBF kernel
'-G','0.0000019073486328125', # Gamma
'-C','131072'] ) # Cost
def classify(runID, trainingSet, testingSet):
[trainingFile,
testingFile] = arffWriter.writeArffFiles(runID, trainingSet,
testingSet)
# deep learning (AE)
if config.AE != -1:
[trainingFile,
testingFile] = dA_2.calcAE([trainingFile, testingFile])
return wekaAPI.execute(trainingFile, testingFile,
"weka.classifiers.bayes.NaiveBayes", ['-K'])
def classify(runID, trainingSet, testingSet):
[trainingFile,
testingFile] = arffWriter.writeArffFiles(runID, trainingSet,
testingSet)
# return wekaAPI.execute( trainingFile, testingFile, "weka.classifiers.bayes.NaiveBayes", ['-K'] )
if config.CROSS_VALIDATION == 0:
return wekaAPI.execute(trainingFile, testingFile,
"weka.classifiers.bayes.NaiveBayes", ['-K'])
else:
file = Utils.joinTrainingTestingFiles(
trainingFile, testingFile) # join and shuffle
return wekaAPI.executeCrossValidation(
file,
"weka.classifiers.bayes.NaiveBayes",
[
'-x',
str(config.CROSS_VALIDATION), # number of folds
'-K'
])
def classify(runID, trainingSet, testingSet):
[trainingFile,
testingFile] = arffWriter.writeArffFiles(runID, trainingSet,
testingSet)
if config.n_components_PCA != 0:
[trainingFile,
testingFile] = Utils.calcPCA2([trainingFile, testingFile])
if config.n_components_LDA != 0:
[trainingFile,
testingFile] = Utils.calcLDA6([trainingFile, testingFile])
if config.n_components_QDA != 0:
[trainingFile,
testingFile] = Utils.calcQDA([trainingFile, testingFile])
return wekaAPI.execute(trainingFile, testingFile,
"weka.classifiers.bayes.NaiveBayes", ['-K'])
def classify( runID, trainingSet, testingSet ):
[trainingFile,testingFile] = arffWriter.writeArffFiles( runID, trainingSet, testingSet )
if config.n_components_PCA != 0:
[trainingFile,testingFile] = Utils.calcPCA2([trainingFile,testingFile])
if config.n_components_LDA != 0:
[trainingFile,testingFile] = Utils.calcLDA6([trainingFile,testingFile])
if config.n_components_QDA != 0:
[trainingFile,testingFile] = Utils.calcQDA([trainingFile,testingFile])
return wekaAPI.execute( trainingFile,
testingFile,
"weka.Run weka.classifiers.functions.LibSVM",
['-K','2', # RBF kernel
'-G','0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C','131072'] ) # Cost
def classify(runID, trainingSet, testingSet):
[trainingFile,
testingFile] = arffWriter.writeArffFiles(runID, trainingSet,
testingSet)
# return wekaAPI.execute( trainingFile, testingFile, "weka.classifiers.bayes.NaiveBayes", ['-K'] )
# deep learning
if config.DEEP_LEARNING_METHOD != -1:
#DLMethod = Utils.intToDL(config.DEEP_LEARNING_METHOD)
#print 'Deep Learning Method: ' + DLMethod
#[trainingFile, testingFile] = DLMethod.runDL([trainingFile, testingFile])
#[trainingFile, testingFile] = dA_2.calcAE([trainingFile, testingFile])
#SdA_2.calcSdA([trainingFile, testingFile])
#logistic_sgd_2.calcLog_sgd([trainingFile, testingFile])
if config.DEEP_LEARNING_METHOD == 1:
logistic_sgd_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 2:
[trainingFile,
testingFile] = dA_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 3:
mlp_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 4:
SdA_2.runDL([trainingFile, testingFile])
if config.CROSS_VALIDATION == 0:
return wekaAPI.execute(trainingFile, testingFile,
"weka.classifiers.bayes.NaiveBayes", ['-K'])
else:
file = Utils.joinTrainingTestingFiles(
trainingFile, testingFile) # join and shuffle
return wekaAPI.executeCrossValidation(
file,
"weka.classifiers.bayes.NaiveBayes",
[
'-x',
str(config.CROSS_VALIDATION), # number of folds
'-K'
])
def classify(runID, trainingSet, testingSet):
[trainingFile,
testingFile] = arffWriter.writeArffFiles(runID, trainingSet,
testingSet)
# deep learning (AE)
if config.DEEP_LEARNING_METHOD != -1:
#[trainingFile, testingFile] = dA_2.calcAE([trainingFile, testingFile]) # one layer dA
#[trainingFile, testingFile] = dA_2.calcAE([trainingFile, testingFile]) # two layers dA
#[trainingFile, testingFile] = dA_2.calcAE([trainingFile, testingFile])
#SdA_2.calcSdA([trainingFile, testingFile])
if config.DEEP_LEARNING_METHOD == 1:
[trainingFile, testingFile
] = logistic_sgd_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 2:
[trainingFile,
testingFile] = dA_2.runDL([trainingFile, testingFile])
[trainingFile,
testingFile] = dA_2.runDL([trainingFile, testingFile])
#[trainingFile, testingFile] = dA_2.runDL([trainingFile, testingFile])
#[trainingFile, testingFile] = dA_2.runDL([trainingFile, testingFile])
#[trainingFile, testingFile] = dA_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 3:
# DL classifier
return mlp_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 4:
return SdA_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 5:
return mlp_3.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 6:
return SdA_3.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 7:
return LeNetConvPoolLayer_2.runDL([trainingFile, testingFile])
return wekaAPI.execute(trainingFile, testingFile,
"weka.classifiers.bayes.NaiveBayes", ['-K'])
def classify( runID, trainingSet, testingSet ):
[trainingFile,testingFile] = arffWriter.writeArffFiles( runID, trainingSet, testingSet )
return wekaAPI.execute( trainingFile, testingFile, "weka.classifiers.bayes.NaiveBayes", ['-K'] )
def classify(runID, trainingSet, testingSet):
[trainingFile,
testingFile] = arffWriter.writeArffFiles(runID, trainingSet,
testingSet)
[trainingFileOrig, testingFileOrig] = [trainingFile, testingFile]
if config.NUM_MONITORED_SITES != -1: #no need to classify as this is for generating openworld datasets. See the line above (arffWriter)
[accuracy, debugInfo] = ['NA', []]
return [accuracy, debugInfo]
if config.n_components_PCA != 0:
[trainingFile,
testingFile] = Utils.calcPCA2([trainingFile, testingFile])
if config.n_components_LDA != 0:
[trainingFile,
testingFile] = Utils.calcLDA4([trainingFile, testingFile])
if config.n_components_QDA != 0:
[trainingFile,
testingFile] = Utils.calcQDA([trainingFile, testingFile])
if config.lasso != 0:
#[trainingFile,testingFile] = Utils.calcLasso3([trainingFile,testingFile])
#[trainingFile,testingFile] = Utils.calcLogisticRegression([trainingFile,testingFile])
Utils.calcLogisticRegression([trainingFile, testingFile])
# deep learning
if config.DEEP_LEARNING_METHOD != -1:
#[trainingFile, testingFile] = dA_2.calcAE([trainingFile, testingFile]) # one layer dA
#[trainingFile, testingFile] = dA_2.calcAE([trainingFile, testingFile]) # two layers dA
#[trainingFile, testingFile] = dA_2.calcAE([trainingFile, testingFile])
#SdA_2.calcSdA([trainingFile, testingFile])
if config.DEEP_LEARNING_METHOD == 1:
[trainingFile, testingFile
] = logistic_sgd_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 2:
[trainingFile,
testingFile] = dA_2.runDL([trainingFile, testingFile])
[trainingFile,
testingFile] = dA_2.runDL([trainingFile, testingFile])
#[trainingFile, testingFile] = dA_2.runDL([trainingFile, testingFile])
#[trainingFile, testingFile] = dA_2.runDL([trainingFile, testingFile])
#[trainingFile, testingFile] = dA_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 3:
# DL classifier
return mlp_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 4:
return SdA_2.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 5:
return mlp_3.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 6:
return SdA_3.runDL([trainingFile, testingFile])
elif config.DEEP_LEARNING_METHOD == 7:
return LeNetConvPoolLayer_2.runDL([trainingFile, testingFile])
#Utils.plotDensity([trainingFile,testingFile])
#Utils.plot([trainingFile,testingFile])
if config.OC_SVM == 0: # multi-class svm
if config.CROSS_VALIDATION == 0:
#print 'WARNING: NB classifier with Bi-Di. ###########///////////XXXXXX???????? '
#return wekaAPI.execute(trainingFile, testingFile, "weka.classifiers.bayes.NaiveBayes", ['-K'])
return wekaAPI.execute(
trainingFile,
testingFile,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-K',
'2', # RBF kernel
'-G',
'0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C',
'131072', # Cost
#'-S','2', # one-class svm
'-B'
]) # confidence
else:
file = Utils.joinTrainingTestingFiles(
trainingFile, testingFile) # join and shuffle
return wekaAPI.executeCrossValidation(
file,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-x',
str(config.CROSS_VALIDATION), # number of folds
'-K',
'2', # RBF kernel
'-G',
'0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C',
'131072', # Cost
'-B'
]) # confidence
else: # one-class svm
if config.CROSS_VALIDATION == 0:
print str(config.SVM_KERNEL)
print str(config.OC_SVM_Nu)
return wekaAPI.executeOneClassSVM(
trainingFile,
testingFile,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-K',
str(config.SVM_KERNEL),
#'-K','2', # RBF kernel
#'-G','0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
#'-C','131072', # Cost
#'-N','0.001', # nu
'-N',
str(config.OC_SVM_Nu), # nu
'-S',
'2'
]) #, # one-class svm
#'-B'] ) # confidence
else:
file = Utils.joinTrainingTestingFiles(
trainingFile, testingFile) # join and shuffle
return wekaAPI.executeCrossValidation(
file,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-x',
str(config.CROSS_VALIDATION), # number of folds
'-K',
'2', # RBF kernel
'-G',
'0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C',
'131072', # Cost
'-B'
]) # confidence
def classify(runID, trainingSet, testingSet):
[trainingFile,
testingFile] = arffWriter.writeArffFiles(runID, trainingSet,
testingSet)
if config.NUM_MONITORED_SITES != -1: #no need to classify as this is for generating openworld datasets. See the line above (arffWriter)
[accuracy, debugInfo] = ['NA', []]
return [accuracy, debugInfo]
if config.n_components_PCA != 0:
[trainingFile,
testingFile] = Utils.calcPCA2([trainingFile, testingFile])
if config.n_components_LDA != 0:
[trainingFile,
testingFile] = Utils.calcLDA4([trainingFile, testingFile])
if config.n_components_QDA != 0:
[trainingFile,
testingFile] = Utils.calcQDA([trainingFile, testingFile])
if config.lasso != 0:
#[trainingFile,testingFile] = Utils.calcLasso3([trainingFile,testingFile])
#[trainingFile,testingFile] = Utils.calcLogisticRegression([trainingFile,testingFile])
Utils.calcLogisticRegression([trainingFile, testingFile])
#Utils.plotDensity([trainingFile,testingFile])
#Utils.plot([trainingFile,testingFile])
'''
if (config.DATA_SOURCE == 62 or config.DATA_SOURCE == 63 or config.DATA_SOURCE == 64 or config.DATA_SOURCE == 65):
if config.LABEL_NOISE_RATIO != 0:
[trainingFile,testingFile] = Utils.makeLabelNoise([trainingFile,testingFile],config.LABEL_NOISE_RATIO)
'''
if config.CROSS_VALIDATION == 0:
return wekaAPI.execute(
trainingFile,
testingFile,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-K',
'2', # RBF kernel
'-G',
'0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C',
'131072', # Cost
#'-S','2', # one-class svm
'-B'
]) # confidence
else:
file = Utils.joinTrainingTestingFiles(
trainingFile, testingFile) # join and shuffle
return wekaAPI.executeCrossValidation(
file,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-x',
str(config.CROSS_VALIDATION), # number of folds
'-K',
'2', # RBF kernel
'-G',
'0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C',
'131072', # Cost
'-B'
]) # confidence
def classify(runID, trainingSet, testingSet):
[trainingFile,
testingFile] = arffWriter.writeArffFiles(runID, trainingSet,
testingSet)
if config.NUM_MONITORED_SITES != -1: #no need to classify as this is for generating openworld datasets. See the line above (arffWriter)
[accuracy, debugInfo] = ['NA', []]
return [accuracy, debugInfo]
if config.n_components_PCA != 0:
[trainingFile,
testingFile] = Utils.calcPCA2([trainingFile, testingFile])
if config.n_components_LDA != 0:
[trainingFile,
testingFile] = Utils.calcLDA4([trainingFile, testingFile])
if config.n_components_QDA != 0:
[trainingFile,
testingFile] = Utils.calcQDA([trainingFile, testingFile])
if config.lasso != 0:
#[trainingFile,testingFile] = Utils.calcLasso3([trainingFile,testingFile])
#[trainingFile,testingFile] = Utils.calcLogisticRegression([trainingFile,testingFile])
Utils.calcLogisticRegression([trainingFile, testingFile])
#Utils.plotDensity([trainingFile,testingFile])
#Utils.plot([trainingFile,testingFile])
if config.NUM_FEATURES_RF != 0:
[trainingFile,
testingFile] = Utils.calcTreeBaseRF([trainingFile, testingFile],
config.NUM_FEATURES_RF)
if config.OC_SVM == 0: # multi-class svm
if config.CROSS_VALIDATION == 0:
return wekaAPI.execute(
trainingFile,
testingFile,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-K',
'2', # RBF kernel
'-G',
'0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C',
'131072', # Cost
'-B'
]) # confidence
else:
file = Utils.joinTrainingTestingFiles(
trainingFile, testingFile) # join and shuffle
return wekaAPI.executeCrossValidation(
file,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-x',
str(config.CROSS_VALIDATION), # number of folds
'-K',
'2', # RBF kernel
'-G',
'0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C',
'131072', # Cost
'-B'
]) # confidence
else: # one-class svm
if config.CROSS_VALIDATION == 0:
print str(config.SVM_KERNEL)
print str(config.OC_SVM_Nu)
return wekaAPI.executeOneClassSVM(
trainingFile,
testingFile,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-K',
str(config.SVM_KERNEL),
#'-K','0', # kernel
#'-G','0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
#'-C','131072', # Cost
#'-N','0.01', # nu
'-N',
str(config.OC_SVM_Nu), # nu
'-S',
'2'
]) #, # one-class svm
#'-B'] ) # confidence
else:
file = Utils.joinTrainingTestingFiles(
trainingFile, testingFile) # join and shuffle
return wekaAPI.executeCrossValidation(
file,
"weka.Run weka.classifiers.functions.LibSVM",
[
'-x',
str(config.CROSS_VALIDATION), # number of folds
'-K',
'2', # RBF kernel
'-G',
'0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C',
'131072', # Cost
'-B'
]) # confidence
def __applyFeatureSelection(trainingFilename, testingFilename, outputFoldername, featuresFilename):
# if not os.path.exists(outputFoldername):
# os.mkdir(outputFoldername)
# else:
# shutil.rmtree(outputFoldername) # delete and remake folder
# os.mkdir(outputFoldername)
[accuracy,debugInfo] = wekaAPI.execute( trainingFilename,
testingFilename,
"weka.Run weka.classifiers.functions.LibSVM",
['-K','2', # RBF kernel
'-G','0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C','131072'] ) # Cost
print outputFoldername
print 'accuracy before feature selection ' + str(accuracy)
AccAllFeatures = str(accuracy)
trainList = Utils.readFile(trainingFilename)
testList = Utils.readFile(testingFilename)
featuresList = Utils.readFile(featuresFilename)
if len(featuresList) > 0:
featuresList = featuresList[0].split("{")[1].split("}")[0].split(",")
else:
featuresList = [0, 1, 2] # dummy features
featuresList = [int(i) for i in featuresList]
featuresList = sorted(featuresList)
#print featuresList.__contains__(4)
NumSelectedFeatures = len(featuresList)
newTrainList = []
newTestList = []
for i in range(len(trainList)):
if trainList[i].startswith('@'):
if trainList[i].startswith('@ATTRIBUTE'):
if featuresList.__contains__(i-1): # featuresList index startr from 0, arff features(line) starts from 1
#print trainList[i].split(" ")[1]
newTrainList.append(trainList[i])
else:
newTrainList.append(trainList[i])
if trainList[i].startswith('@ATTRIBUTE class'):
newTrainList.append(trainList[i])
else:
newInstance = []
instanceSplit = trainList[i].split(",")
newInstance = [instanceSplit[j] for j in featuresList] # take indecies from featuresList whose index starts from 0
#newInstance = [instanceSplit[j-1] for j in featuresList] # take indecies from featuresList whose index starts from 1
#for j in range(len(instanceSplit)):
# if featuresList.__contains__(j+1):
# newInstance.append(instanceSplit[j])
newInstance.append(instanceSplit[-1])
newTrainList.append(",".join(newInstance))
NumAllFeatures = len(instanceSplit) - 1
for i in range(len(testList)):
if testList[i].startswith('@'):
if testList[i].startswith('@ATTRIBUTE'):
if featuresList.__contains__(i-1): # featuresList index startr from 0, arff features(line) starts from 1
#print testList[i].split(" ")[1]
newTestList.append(testList[i])
else:
newTestList.append(testList[i])
if testList[i].startswith('@ATTRIBUTE class'):
newTestList.append(testList[i])
else:
newInstance = []
instanceSplit = testList[i].split(",")
newInstance = [instanceSplit[j] for j in featuresList] # take indecies from featuresList whose index starts from 0
#newInstance = [instanceSplit[j-1] for j in featuresList] # take indecies from featuresList whose index starts from 1
#for j in range(len(instanceSplit)):
# if featuresList.__contains__(j+1):
# newInstance.append(instanceSplit[j])
newInstance.append(instanceSplit[-1])
newTestList.append(",".join(newInstance))
fnewTrainName = trainingFilename[:-5]+'_Features'+'.arff'
fnewTrain = open(os.path.join(outputFoldername, fnewTrainName), 'w')
for item in newTrainList:
fnewTrain.write(item+'\n')
fnewTrain.close()
# writing the new testing file (with lower dimensions)
fnewTestName = testingFilename[:-5]+'_Features'+'.arff'
fnewTest = open(os.path.join(outputFoldername, fnewTestName), 'w')
for item in newTestList:
fnewTest.write(item+'\n')
fnewTest.close()
[accuracy,debugInfo] = wekaAPI.execute( fnewTrainName,
fnewTestName,
"weka.Run weka.classifiers.functions.LibSVM",
['-K','2', # RBF kernel
'-G','0.0000019073486328125', # Gamma
##May20 '-Z', # normalization 18 May 2015
'-C','131072'] ) # Cost
print 'accuracy after feature selection ' + str(accuracy)
AccSelectedFeatures = str(accuracy)
output = [NumAllFeatures]
output.append(NumSelectedFeatures)
output.append(AccAllFeatures)
output.append(AccSelectedFeatures)
output.append(config.RUN_ID)
writeOutputResultsFile(trainingFilename, output)
print ''
