Sanket758

# Load the csv file
df = pd.read_csv('IMDB_reviews.csv')

# Extract the reviews and sentiments
reviews = np.array(df['review'])
sentiments = np.array(df['sentiment'])

# splitting the data into train and test sets
train_reviews = reviews[:35000]
train_sentiment = reviews[:35000]

Sanket758

# !pip install contractions 
import nltk
nltk.download('stopwords')
nltk.download('punkt')
import contractions
from bs4 import BeautifulSoup
import unicodedata
import re
import nltk
import numpy as np

Sanket758

#!pip install afinn
from afinn import Afinn
afn = Afinn() 

# Predicting sentiment on our reviews
sentiment_polarity = [afn.score(review) for review in test_reviews]
predicted_sentiments = ['positive' if score >= 1.0 else 'negative' for score in sentiment_polarity]

# Evaluation
from sklearn.metrics import accuracy_score, f1_score, precision_score, recall_score, confusion_matrix

Sanket758

from flask import Flask, jsonify, request, json
from flask_pymongo import PyMongo 
from bson.objectid import ObjectId 
from datetime import datetime 
from flask_bcrypt import Bcrypt 
# from flask_cors import CORS
# from flask_jwt_extended import JWTManager

app = Flask(__name__)