def fit(self, X, y):
self.vectorizer, self.corpus_matrix, _ = get_tfidf_model(X)
param = {'objective': 'binary:logistic'}
epochs = 100
D_train = xgb.DMatrix(self.corpus_matrix, label=y)
self.clf = xgb.train(param, D_train, epochs)
def fit(self, X, y):
self.vectorizer, self.corpus_matrix, _ = get_tfidf_model(X)
self.clf = SVC(kernel='rbf')
self.clf.fit(self.corpus_matrix, y)
def fit(self, X, y):
self.vectorizer, self.corpus_matrix, _ = get_tfidf_model(X)
self.clf = naive_bayes.MultinomialNB()
self.clf.fit(self.corpus_matrix, y)
def fit(self, X, y):
self.vectorizer, self.X_vectorized, _ = get_tfidf_model(X)
self.clf = KNeighborsClassifier()
self.clf.fit(self.X_vectorized, y)
def fit(self, X, y):
self.x0, self.y0, self.x1, self.y1 = split_binary_classes(X, y)
self.vectorizer0, self.corpus_matrix0, _ = get_tfidf_model(self.x0)
self.vectorizer1, self.corpus_matrix1, _ = get_tfidf_model(self.x1)
def fit(self, X, y):
self.vectorizer, self.X_vectorized, _ = get_tfidf_model(X)
self.clf = RandomForestClassifier()
self.clf.fit(self.X_vectorized, y)