app.py

from tensorflow import keras
import tensorflow as tf
from tensorflow.keras.datasets import imdb
import numpy as np
import gradio as gr

number_of_words = 3000
words_per_view = 200

loaded_model = tf.keras.models.load_model('sentiment_analysis.h5')
word_to_index = imdb.get_word_index()

def get_predict(userInputString, model):
  words = userInputString.split()
  #print(len(words))
  encoded_word = np.zeros(words_per_view).astype(int)
  encoded_word[words_per_view -len(words) - 1] = 1
  for i, word in enumerate(words):
    index = words_per_view - len(words) + i
    encoded_word[index] = word_to_index.get(word, 0) + 3
  encoded_word = np.expand_dims(encoded_word, axis=0)
  prediction = model.predict(encoded_word)
  return prediction

def analyze_sentiment(userInputString):
  result = get_predict(userInputString, loaded_model)[0][0]
  if result > 0.5:
    answer = 'positive review'
  else: answer = 'negative review'  
  return answer
UserInputPage = gr.Interface(
    fn=analyze_sentiment,
    inputs = ["text"],
    outputs=["text"]
)
tabbed_Interface = gr.TabbedInterface([UserInputPage], ["Check user input"])
tabbed_Interface.launch()