app.py

import streamlit as st
import tensorflow as tf
from tensorflow.keras.datasets import imdb
from tensorflow.keras.preprocessing.sequence import pad_sequences
import numpy as np

word_index = imdb.get_word_index()
maximo_num_palabras = 20000

def reviwnueva(review, word_index, maximo_num_palabras):
  sequence = []
  for word in review.split():
    index = word_index.get(word.lower(), 0)
    if index < maximo_num_palabras:
      squence.append(index)
    return sequence

model = tf.keras.models.load_model("opiniones.h5")

def predict_sentimiento(review):
    sequence = reviwnueva(review, word_index)
    prediccion = model.predict(sequence)
    if prediccion [0][0]>=0.5 :
        sentimiento = "Positivo"
    else:
        sentimiento = "Negativo"

    return sentimiento

st.title("Ingrese una review para poder calificarla com positiva o negativa")
review = st.text_area("Ingrese reseña aqui", height=200)
if st.button("Predecir sentimiento"):
    if review:
        sentimineto = predict_sentimiento(review)
        st.write(f"El sentimiento es: {sentimineto}")
    else:
        st.write(f'Ingrese una review')