nlp model.py

import pandas as pd

dataset = pd.read_csv('/Users/karanrochlani/Desktop/karan.tsv',delimiter='\t',quoting=3)

import re
import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords 
corpus=[]
for i in range(0,95):
    review=re.sub('[^a-zA-Z]',' ',dataset['Reviews'][i])
    review=review.lower()
    review=review.split()
    review=[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['Rating']

from sklearn.preprocessing import LabelEncoder
labelencoder=LabelEncoder()
y=labelencoder.fit_transform(y)

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)

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)

from sklearn.metrics import accuracy_score
accuracy_score(y_test,y_pred)