app.py

import numpy as np
import string
import streamlit as st
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
import nltk
import json
from tensorflow.keras.models import load_model
import tensorflow as tf

model = load_model("E:\CODES\pythonProject7\_best_model_LSTM.hdf5")

from tensorflow.keras.preprocessing.text import tokenizer_from_json

with open("D:/Analysis_sentiment/tokenizer.json", 'r') as f:
    tokenizer_data = f.read()

tokenizer_config = json.loads(tokenizer_data)
tokenizer = tokenizer_from_json(tokenizer_config)

def predict_sentiment(review):
    sequences = tokenizer.texts_to_sequences([review])
    padded_sequences = pad_sequences(sequences, maxlen=200, padding='post', value=0)
    prediction = model.predict(padded_sequences)[0][0]
    return prediction

st.title('Sentiment Analysis')

review = st.text_input('Enter your review')

if review:
    prediction = predict_sentiment(review)
    if prediction < 0.5:
        st.write('Negative')
    else:
        st.write('Positive')
if __name__ == '__main__':
    app.run()