dataset = pd.read_csv('Restaurant_Reviews.tsv', delimiter = 't', quoting = 3)
for i in range(0, 1000):
    review = re.sub('[^a-zA-Z]', ' ', dataset['Review'][i])
    review = review.lower()
    review = review.split()
    ps = PorterStemmer()
    review = [ps.stem(word) for word in review if not word in set(stopwords.words('english'))]
    review = ' '.join(review)
    corpus.append(review)
 cv = CountVectorizer(max_features = 1500)
 X = cv.fit_transform(corpus).toarray()
 y = dataset.iloc[:, 1].values
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state = 0)
 classifier = GaussianNB()
 classifier.fit(X_train, y_train)
 y_pred = classifier.predict(X_test)