first_nlp.py

#NAtural language processing
import pandas as pd
import numpy as np

#importing he tsv files
dataset= pd.read_csv('Restaurant_Reviews.tsv', delimiter='\t', quoting=3)

#cleaning process
#importing the libraries for datapreprocessing
import re
import nltk
#downloading the nltk(Natural Language toolkit) stopwords
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)
    
    
#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 = 0.20, random_state = 0)

############Naive Bayes Classifier############
# Fitting Naive Bayes 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)