示例#1
0
def CrossValidationWithSampling():
	runObj = run_util.run()

	## Load data
	((X_train,Y_train),(X_test)) = loadData(runObj)
	
	## Sample train data 
	RSObj=RS.randomSampling()
	(X_train,Y_train) = RSObj.getRandomSample(X_train,Y_train)
	(X_train,Y_train) = runObj.randomShuffleData(X_train,Y_train)
	print('\n Size of X_train : {0}').format(X_train.shape)
	print('\n Size of Y_train : {0}').format(Y_train.shape)
	X_train.reset_index(drop=True,inplace=True)
	Y_train.reset_index(drop=True,inplace=True)

	## Cross Validation
	kf = KFold(X_train.shape[0], n_folds=5)
	for train_index, test_index in kf:
		X_train_CV, X_test_CV = X_train.ix[train_index], X_train.ix[test_index]
		Y_train_CV, Y_test_CV = Y_train.ix[train_index], Y_train.ix[test_index]
		print('\n Size of X_train_CV : {0}').format(X_train_CV.shape)
		print('\n Size of Y_train_CV : {0}').format(Y_train_CV.shape)
		print('\n Size of X_test_CV : {0}').format(X_test_CV.shape)
		print('\n Size of Y_test_CV : {0}').format(Y_test_CV.shape)

		## Run classifiers
		runObj.runClassifier(X_train_CV,Y_train_CV,X_test_CV,Y_test_CV)
示例#2
0
def RFEWithSampling():
	runObj = run_util.run()

	## Load data
	((X_train,Y_train),(X_test)) = loadData(runObj)
	
	## Sample train data 
	RSObj=RS.randomSampling()
	(X_train,Y_train)=RSObj.getRandomSample(X_train,Y_train)
	(X_train,Y_train) = runObj.randomShuffleData(X_train,Y_train)
	print('\n Size of Sample X_train : {0}').format(X_train.shape)
	print('\n Size of Sample Y_train : {0}').format(Y_train.shape)
	X_train.reset_index(drop=True,inplace=True)
	Y_train.reset_index(drop=True,inplace=True)

	## RFE Feature Selection
	print('\n RFE Feature Selection starts...')
	selected_columns = AF.RFE_featureSelection(X_train,Y_train)
	print('\n RFE Feature Selection ends...')
	X_train = X_train[selected_columns]
	X_test = X_train[selected_columns]

	## Split data into 66% train and 33% test
	((X_train_S,Y_train_S), (X_test_S,Y_test_S)) = runObj.splitDataset(X_train,Y_train)
	print('\n Size of X_train_S : {0}').format(X_train_S.shape)
	print('\n Size of Y_train_S : {0}').format(Y_train_S.shape)
	print('\n Size of X_test_S : {0}').format(X_test_S.shape)
	print('\n Size of Y_test_S : {0}').format(Y_test_S.shape)

	## Run classifiers
	runObj.runClassifier(X_train_S,Y_train_S,X_test_S,Y_test_S)
示例#3
0
def costValuesBasedPrediction():
	runObj = run_util.run()

	## Load data
	((X_train,Y_train),(X_test)) = loadData(runObj)

	## Select feature related to cost
	costFeatures = ['MMRAcquisitionAuctionAveragePrice','VehBCost']
	X_train = X_train[costFeatures]
	print('\n Size of X_train only cost features : {0}').format(X_train.shape)

	## Sample train data 
	RSObj=RS.randomSampling()
	(X_train,Y_train) = RSObj.getRandomSample(X_train,Y_train)
	(X_train,Y_train) = runObj.randomShuffleData(X_train,Y_train)
	print('\n Size of X_train : {0}').format(X_train.shape)
	print('\n Size of Y_train : {0}').format(Y_train.shape)
	X_train.reset_index(drop=True,inplace=True)
	Y_train.reset_index(drop=True,inplace=True)

	## Split data into 66% train and 33% test
	((X_train_S,Y_train_S), (X_test_S,Y_test_S)) = runObj.splitDataset(X_train,Y_train)
	print('\n Size of X_train_S : {0}').format(X_train_S.shape)
	print('\n Size of Y_train_S : {0}').format(Y_train_S.shape)
	print('\n Size of X_test_S : {0}').format(X_test_S.shape)
	print('\n Size of Y_test_S : {0}').format(Y_test_S.shape)

	## Run classifiers
	runObj.runClassifier(X_train_S,Y_train_S,X_test_S,Y_test_S)
示例#4
0
def handpickWithoutSampling():
	runObj = run_util.run()

	## Load data
	((X_train,Y_train),(X_test)) = loadData(runObj)

	## Split data into 66% train and 33% test
	((X_train_S,Y_train_S), (X_test_S,Y_test_S)) = runObj.splitDataset(X_train,Y_train)
	print('\n Size of X_train_S : {0}').format(X_train_S.shape)
	print('\n Size of Y_train_S : {0}').format(Y_train_S.shape)
	print('\n Size of X_test_S : {0}').format(X_test_S.shape)
	print('\n Size of Y_test_S : {0}').format(Y_test_S.shape)

	## Run classifiers
	runObj.runClassifier(X_train_S,Y_train_S,X_test_S,Y_test_S)
示例#5
0
def BoostingWithSampling():
	runObj = run_util.run()

	## Load data
	((X_train,Y_train),(X_test)) = loadData(runObj)
	
	## Sample train data 
	RSObj=RS.randomSampling()
	(X_train,Y_train)=RSObj.getRandomSample(X_train,Y_train)
	(X_train,Y_train) = runObj.randomShuffleData(X_train,Y_train)
	print('\n Size of X_train : {0}').format(X_train.shape)
	print('\n Size of Y_train : {0}').format(Y_train.shape)
	X_train.reset_index(drop=True,inplace=True)
	Y_train.reset_index(drop=True,inplace=True)

	## Boosting Feature Selection
	print('\n Boosting Feature Selection starts...')
	selected_columns_dict = AF.Boosting_featureSelection(X_train,Y_train)
	print('\n Boosting Feature Selection ends...')
	selected_columns=[]
	for col, imp in selected_columns_dict.iteritems():
		if(imp > 0.005):
			selected_columns.append(col)
	print('\n Selected Cols : {0}').format(len(selected_columns))
	
	X_train = X_train[selected_columns]
	X_test = X_train[selected_columns]

	## Split data into 66% train and 33% test
	((X_train_S,Y_train_S), (X_test_S,Y_test_S)) = runObj.splitDataset(X_train,Y_train)
	print('\n Size of X_train_S : {0}').format(X_train_S.shape)
	print('\n Size of Y_train_S : {0}').format(Y_train_S.shape)
	print('\n Size of X_test_S : {0}').format(X_test_S.shape)
	print('\n Size of Y_test_S : {0}').format(Y_test_S.shape)

	## Run classifiers
	runObj.runClassifier(X_train_S,Y_train_S,X_test_S,Y_test_S)
示例#6
0
def handpickWithSampling():
	runObj = run_util.run()

	## Load data
	((X_train,Y_train),(X_test)) = loadData(runObj)
	
	## Sample train data 
	RSObj=RS.randomSampling()
	(X_train,Y_train) = RSObj.getRandomSample(X_train,Y_train)
	(X_train,Y_train) = runObj.randomShuffleData(X_train,Y_train)
	print('\n Size of X_train : {0}').format(X_train.shape)
	print('\n Size of Y_train : {0}').format(Y_train.shape)
	X_train.reset_index(drop=True,inplace=True)
	Y_train.reset_index(drop=True,inplace=True)

	## Split data into 66% train and 33% test
	((X_train_S,Y_train_S), (X_test_S,Y_test_S)) = runObj.splitDataset(X_train,Y_train)
	print('\n Size of X_train_S : {0}').format(X_train_S.shape)
	print('\n Size of Y_train_S : {0}').format(Y_train_S.shape)
	print('\n Size of X_test_S : {0}').format(X_test_S.shape)
	print('\n Size of Y_test_S : {0}').format(Y_test_S.shape)

	## Run classifiers
	runObj.runClassifier(X_train_S,Y_train_S,X_test_S,Y_test_S)
示例#7
0
def visualizePieChart(featureList):
	runObj = run_util.run()
	X = loadData(runObj)
	V_util.visualizePieChart(X,featureList)
示例#8
0
def visualizeCategorial(featureList):
	runObj = run_util.run()
	X = loadData(runObj)
	X = X[featureList]
	V_util.visualizeCategorial(X)
示例#9
0
def visualizeCategoricalClassLabel(featureList):
	runObj = run_util.run()
	X = loadData(runObj)
	V_util.visualizeCategoricalClassLabel(X,featureList)
示例#10
0
def visualizeAll():
	runObj = run_util.run()
	X = loadData(runObj)
	V_util.visualizeAllFeatures(X)
示例#11
0
def visualizePieChart(featureList):
    runObj = run_util.run()
    X = loadData(runObj)
    V_util.visualizePieChart(X, featureList)
示例#12
0
def visualizeCategoricalClassLabel(featureList):
    runObj = run_util.run()
    X = loadData(runObj)
    V_util.visualizeCategoricalClassLabel(X, featureList)
示例#13
0
def visualizeCategorial(featureList):
    runObj = run_util.run()
    X = loadData(runObj)
    X = X[featureList]
    V_util.visualizeCategorial(X)
示例#14
0
def visualizeAll():
    runObj = run_util.run()
    X = loadData(runObj)
    V_util.visualizeAllFeatures(X)