def preprocessData(filename):
X, y, csv = pre.loadDataset(filename, ",")
X = pre.fillMissingData(X, 2, 3)
#sex
X = pre.computeCategorization(X)
#embark
X = pre.computeCategorization(X)
XTrain, XTest, yTrain, yTest = pre.splitTrainTestSets(X, y, 0.15)
XTrain = pre.computeScaling(XTrain)
XTest = pre.computeScaling(XTest)
return XTrain, XTest, yTrain, yTest
def runLinearRegressionExample(filename):
start_time = time.time()
X, y = pre.loadDataset(filename)
elapsed_time = time.time() - start_time
print("Load Dataset: %.2f" % elapsed_time, "segundos.")
start_time = time.time()
X = pre.fillMissingData(X, 1, X.shape[1])
elapsed_time = time.time() - start_time
print("Fill Missing Data: %.2f" % elapsed_time, "segundos.")
start_time = time.time()
X = pre.computeCategorization(X, 0)
elapsed_time = time.time() - start_time
print("Compute Categorization: %.2f" % elapsed_time, "segundos.")
start_time = time.time()
XTrain, XTest, yTrain, yTest = pre.splitTrainTestSets(X, y, 0.8)
elapsed_time = time.time() - start_time
print("Split Train Test sets: %.2f" % elapsed_time, "segundos.")
start_time = time.time()
computeLinearRegressionModel(XTrain, yTrain, XTest, yTest)
elapsed_time = time.time() - start_time
print("Compute Linear Regression: %.2f" % elapsed_time, "segundos.")
def runMultipleLinearRegressionExample(filename):
start_time = time.time()
X, y = pre.loadDataset(filename)
elapsed_time = time.time() - start_time
print("Load Dataset: %.2f" % elapsed_time, "segundos.")
start_time = time.time()
X = pre.fillMissingData(X, 0, 2)
elapsed_time = time.time() - start_time
print("Fill Missing Data: %.2f" % elapsed_time, "segundos.")
start_time = time.time()
X = pre.computeCategorization(X, 3)
elapsed_time = time.time() - start_time
print("Compute Categorization: %.2f" % elapsed_time, "segundos.")
start_time = time.time()
XTrain, XTest, yTrain, yTest = pre.splitTrainTestSets(X, y, 0.8)
elapsed_time = time.time() - start_time
print("Split Train Test sets: %.2f" % elapsed_time, "segundos.")
start_time = time.time()
XTrain, XTest = computeAutomaticBackwardElimination(
XTrain, yTrain, XTest, 0.05)
elapsed_time = time.time() - start_time
print("Compute Automatic Backward Elimination: %.2f" % elapsed_time,
"segundos.")
start_time = time.time()
computeMultipleLinearRegressionModel(XTrain, yTrain, XTest, yTest)
elapsed_time = time.time() - start_time
print("Compute Multiple Linear Regression: %.2f" % elapsed_time,
"segundos.")
'''start_time = time.time()
def computeLogisticRegressionExample(filename):
X, y, csv = pre.loadDataset(filename, ",")
X = pre.fillMissingData(X, 2, 3)
#sex
X = pre.computeCategorization(X)
#embark
X = pre.computeCategorization(X)
XTrain, XTest, yTrain, yTest = pre.splitTrainTestSets(X, y, 0.15)
XTrain = pre.computeScaling(XTrain)
XTest = pre.computeScaling(XTest)
classifier = computeLogisticRegressionModel(XTrain, yTrain, XTest)
yPred = predictModel(classifier, XTest)
return evaluateModel(classifier, yPred, yTest)
def preprocessDataCrossValidation(args, use_scaling):
X, y, csv = pre.loadDataset(args.dataset, args.delimiter)
if (args.fill_missing_data_columns is not None):
columns = args.fill_missing_data_columns.split(',')
columns = [int(x) for x in columns]
offset = 0
for n in columns:
X = pre.fillMissingData(X, n + offset)
offset += n
if (args.one_hot_encoding_columns is not None):
columns = args.one_hot_encoding_columns.split(',')
columns = [int(x) for x in columns]
offset = 0
for n in columns:
X, o = pre.computeCategorization(X, n + offset)
offset += o - 1
if (use_scaling == True):
X = pre.computeScaling(X)
if (len(X) == 2):
X = X[0]
return X, y
def preprocessData(args, use_scaling):
X, y, csv = pre.loadDataset(args.dataset, args.delimiter)
if (args.fill_missing_data_columns is not None):
columns = args.fill_missing_data_columns.split(',')
columns = [int(x) for x in columns]
offset = 0
for n in columns:
X = pre.fillMissingData(X, n + offset)
offset += n
if (args.one_hot_encoding_columns is not None):
columns = args.one_hot_encoding_columns.split(',')
columns = [int(x) for x in columns]
offset = 0
for n in columns:
X, o = pre.computeCategorization(X, n + offset)
offset += o - 1
XTrain, XTest, yTrain, yTest = pre.splitTrainTestSets(
X, y, args.test_size)
if (use_scaling == True):
XTrain = pre.computeScaling(XTrain)
XTest = pre.computeScaling(XTest)
if (len(XTrain) == 2):
XTrain = XTrain[0]
if (len(XTest) == 2):
XTest = XTest[0]
return XTrain, XTest, yTrain, yTest
