-
Notifications
You must be signed in to change notification settings - Fork 0
/
review_classifier.py
60 lines (46 loc) · 1.55 KB
/
review_classifier.py
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
53
54
55
56
57
58
59
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Apr 27 12:03:08 2020
@author: shoumik
"""
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset=pd.read_csv('Restaurant_Reviews.tsv',delimiter="\t",quoting=3)
#cleaning the texts
import re
import nltk
#nltk.download('stopwords')
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
corpus=[]
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)
#creating bag of words model
from sklearn.feature_extraction.text import CountVectorizer
cv=CountVectorizer(max_features=1500)
X=cv.fit_transform(corpus).toarray()
y=dataset.iloc[:,1].values
# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
# Fitting classifier to the Training set
from sklearn.naive_bayes import GaussianNB
classifier=GaussianNB()
classifier.fit(X_train,y_train)
# Predicting the Test set results
y_pred = classifier.predict(X_test)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
#pickle the data
import pickle
pickle.dump(classifier,open('nlp_review_classifier.pkl','wb'))
pickle.dump(cv,open('text_transform.pkl','wb'))