import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

dataset = pd.read_csv("Restaurant_Reviews.tsv", delimiter="\t", quoting=3)

import re
# import nltk
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
# nltk.download('stopwords')
ps = PorterStemmer()

corpus = []
for i in range(0, 1000):
    review = re.sub('[^a-zA-Z]', ' ', dataset['Review'][i])
    review = review.lower()
    review = review.split()
    review = [ps.stem(word) for word in review if not word in set(stopwords.words('english'))]
    review = ' '.join(review)
    corpus.append(review)

from sklearn.feature_extraction.text import CountVectorizer

cv = CountVectorizer(max_features=1500)

X = cv.fit_transform(corpus).toarray()

Y = dataset.iloc[:, 1].values

from sklearn.model_selection import train_test_split

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.20, random_state = 0)

from sklearn.naive_bayes import GaussianNB

classifier = GaussianNB()

classifier.fit(X_train, Y_train)

Y_pred = classifier.predict(X_test)

print(Y_pred)

print(Y_test)

count = 0
for i in range(0,len(Y_pred)):
    if Y_pred[i] == Y_test[i]:
        count += 1

print(count / len(Y_pred))