def computeExample(filename, kernel):
XTrain, XTest, yTrain, yTest = ClassificationModel.preprocessData(
filename)
classifier = SVM.computeModel(XTrain, yTrain, kernel)
yPred = ClassificationModel.predictModel(classifier, XTest)
return ClassificationModel.evaluateModel(yPred, yTest)
def computeExample(filename):
XTrain, XTest, yTrain, yTest = ClassificationModel.preprocessData(
filename)
classifier = LogisticRegression.computeModel(XTrain, yTrain)
yPred = ClassificationModel.predictModel(classifier, XTest)
return ClassificationModel.evaluateModel(yPred, yTest)
def computeExample(filename):
XTrain, XTest, yTrain, yTest = ClassificationModel.preprocessData(
filename, True)
classifier = KNN.computeModel(XTrain, yTrain)
yPred = ClassificationModel.predictModel(classifier, XTest, False)
return ClassificationModel.evaluateModel(yPred, yTest)
def compute(self):
import timeit
start = timeit.default_timer()
XTrain, XTest, yTrain, yTest = ClassificationModel.preprocessData(self.args, False)
classifier = RandomForest.computeModel(XTrain, yTrain, self.args.n_estimators, self.args.criterion)
yPred = ClassificationModel.predictModel(classifier, XTest)
confusionMatrix = ClassificationModel.evaluateModel(yPred, yTest)
if(self.args.print_accuracy):
print(confusionMatrix, ClassificationModel.getAccuracy(confusionMatrix))
stop = timeit.default_timer()
return confusionMatrix, ClassificationModel.getAccuracy(confusionMatrix), stop - start
def compute(self):
import timeit
start = timeit.default_timer()
XTrain, XTest, yTrain, yTest = ClassificationModel.preprocessData(self.args, True)
classifier = LogisticRegression.computeModel(XTrain, yTrain, self.args.solver)
yPred = ClassificationModel.predictModel(classifier, XTest)
confusionMatrix = ClassificationModel.evaluateModel(yPred, yTest)
if(self.args.print_accuracy):
print(confusionMatrix, ClassificationModel.getAccuracy(confusionMatrix))
stop = timeit.default_timer()
return confusionMatrix, ClassificationModel.getAccuracy(confusionMatrix), stop - start
def compute(self):
import timeit
start = timeit.default_timer()
XTrain, XTest, yTrain, yTest = ClassificationModel.preprocessData(self.args, True)
classifier = KNN.computeModel(XTrain, yTrain, self.args.n_neighbors, self.args.power_parameter_minkowski_metric)
yPred = ClassificationModel.predictModel(classifier, XTest)
confusionMatrix = ClassificationModel.evaluateModel(yPred, yTest)
if(self.args.print_accuracy):
print(confusionMatrix, ClassificationModel.getAccuracy(confusionMatrix))
stop = timeit.default_timer()
return confusionMatrix, ClassificationModel.getAccuracy(confusionMatrix), stop - start
def computeCrossValidation(self):
from sklearn.model_selection import cross_validate
X, y = ClassificationModel.preprocessDataCrossValidation(self.args, False)
classifier = RandomForest.computeModel(X, y, self.args.n_estimators, self.args.criterion)
cv_results = cross_validate(classifier, X, y, cv=self.args.k_fold_cross_validation)
if(self.args.print_accuracy):
print(cv_results)
return cv_results
def computeCrossValidation(self):
from sklearn.model_selection import cross_validate
X, y = ClassificationModel.preprocessDataCrossValidation(self.args, True)
classifier = LogisticRegression.computeModel(X, y, self.args.solver)
cv_results = cross_validate(classifier, X, y, cv=self.args.k_fold_cross_validation)
if(self.args.print_accuracy):
print(cv_results)
return cv_results
def computeCrossValidation(self):
from sklearn.model_selection import cross_validate
X, y = ClassificationModel.preprocessDataCrossValidation(self.args, True)
classifier = KNN.computeModel(X, y, self.args.n_neighbors, self.args.power_parameter_minkowski_metric)
cv_results = cross_validate(classifier, X, y, cv=self.args.k_fold_cross_validation)
if(self.args.print_accuracy):
print(cv_results)
return cv_results
def compute(self):
import timeit
start = timeit.default_timer()
XTrain, XTest, yTrain, yTest = ClassificationModel.preprocessData(self.args, False)
classifier = DecisionTree.computeModel(XTrain, yTrain, self.args.criterion)
yPred = ClassificationModel.predictModel(classifier, XTest)
confusionMatrix = ClassificationModel.getConfusionMatrix(yPred, yTest)
rocCurve = ClassificationModel.getRocCurve(yPred, yTest)
if(self.args.print_accuracy):
print(confusionMatrix, ClassificationModel.getAccuracy(confusionMatrix))
stop = timeit.default_timer()
return confusionMatrix, rocCurve, ClassificationModel.getAccuracy(confusionMatrix), stop - start, classifier
