ReviewClassification/classification.py at master · arpitjadiya/ReviewClassification · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
# -*- coding: utf-8 -*-
"""
Created on Tue Jan  1 09:28:22 2019

@author: arpit
"""

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
nltk.download('stopwords')
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer


corpus = []

for i in range(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)

from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer()
X = cv.fit_transform(corpus).toarray()
y = dataset.iloc[:,1].values

from sklearn.cross_validation import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.2 ,random_state = 0 )

from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
classifier.fit(X_train,y_train)

y_pred = classifier.predict(X_test)

from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test,y_pred)