def run_classifier(self, method, classifier):
if method == 'classifier':
self.classifier = Classifier(
self.prepro.severity.keys(), self.prepro.X_train,
self.prepro.y_train, self.prepro.X_test, self.prepro.y_test,
self.prepro.train_size, self.prepro.test_size)
self.classifier.classify(classifier)
if method == 'pipeline':
self.classifier = PipeLineClassifier(
self.prepro.severity.keys(), self.prepro.train_corpus,
self.prepro.y_train, self.prepro.X_test, self.prepro.y_test,
self.prepro.train_size, self.prepro.test_size)
self.classifier.setVariables(classifier)
self.classifier.benchmark()
def run_classifier(self, method, classifier):
if method == 'classifier':
self.classifier = Classifier(
self.prepro.severity.keys(), self.prepro.X_train,
self.prepro.y_train, self.prepro.X_test,
self.prepro.y_test, self.prepro.train_size,
self.prepro.test_size)
self.classifier.classify(classifier)
if method == 'pipeline':
self.classifier = PipeLineClassifier(
self.prepro.severity.keys(), self.prepro.train_corpus,
self.prepro.y_train, self.prepro.X_test,
self.prepro.y_test, self.prepro.train_size,
self.prepro.test_size
)
self.classifier.setVariables(classifier)
self.classifier.benchmark()
class Project:
def __init__(self, num_rows, wrt_feature):
self.db = DB(db='major_2')
data = Data(self.db)
self.data_set = data.getData(num_rows, wrt_feature)
def preprocess(self, new, vector, chi2):
self.prepro = Preprocess(self.data_set, new)
if new == 'True':
if vector == 'hashing':
self.prepro.hashVector()
if vector == 'tfidf':
self.prepro.tfidfVector()
# print self.preprocess.y_train
else:
self.prepro.vectorize(vector)
if chi2:
self.prepro.chisquare()
def run_classifier(self, method, classifier):
if method == 'classifier':
self.classifier = Classifier(
self.prepro.severity.keys(), self.prepro.X_train,
self.prepro.y_train, self.prepro.X_test, self.prepro.y_test,
self.prepro.train_size, self.prepro.test_size)
self.classifier.classify(classifier)
if method == 'pipeline':
self.classifier = PipeLineClassifier(
self.prepro.severity.keys(), self.prepro.train_corpus,
self.prepro.y_train, self.prepro.X_test, self.prepro.y_test,
self.prepro.train_size, self.prepro.test_size)
self.classifier.setVariables(classifier)
self.classifier.benchmark()
class Project:
def __init__(self, num_rows, wrt_feature):
self.db = DB(db='major_2')
data = Data(self.db)
self.data_set = data.getData(num_rows, wrt_feature)
def preprocess(self, new, vector, chi2):
self.prepro = Preprocess(self.data_set, new)
if new == 'True':
if vector == 'hashing':
self.prepro.hashVector()
if vector == 'tfidf':
self.prepro.tfidfVector()
# print self.preprocess.y_train
else:
self.prepro.vectorize(vector)
if chi2:
self.prepro.chisquare()
def run_classifier(self, method, classifier):
if method == 'classifier':
self.classifier = Classifier(
self.prepro.severity.keys(), self.prepro.X_train,
self.prepro.y_train, self.prepro.X_test,
self.prepro.y_test, self.prepro.train_size,
self.prepro.test_size)
self.classifier.classify(classifier)
if method == 'pipeline':
self.classifier = PipeLineClassifier(
self.prepro.severity.keys(), self.prepro.train_corpus,
self.prepro.y_train, self.prepro.X_test,
self.prepro.y_test, self.prepro.train_size,
self.prepro.test_size
)
self.classifier.setVariables(classifier)
self.classifier.benchmark()