Update app.py

app.py

@@ -1,35 +1,38 @@
 import streamlit as st
 import tensorflow as tf
 from tensorflow.keras.datasets import imdb
-from tensorflow.keras.processing.secuence import pad_sequences
+from tensorflow.keras.preprocessing.sequence import pad_sequences
 import numpy as np
 
 word_index = imdb.get_word_index()
-maximo_num_palabras = 20000
+max_words = 20000
 
-def reviewnueva(review, word_index, maximo_num_palabras):
-  sequence = []
+def review_to_sequences(review, word_index, max_words):
+  sequences = []
   for word in review.split():
     index = word_index.get(word.lower(), 0)
-    if index < maximo_num_palabras:
-      sequence.append(index)
-  return sequence
+    if index < max_words:
+      sequences.append(index)
+  return sequences
 
 model = tf.keras.models.load_model("opiniones.h5")
-def predict_sentimiento(review)
-    sequence = reviewnueva(review, word_index)
+def predict_sentimiento(review):
+    sequences = review_to_sequences(review, word_index, max_words)
+    sequences = np.array(sequences)
+    sequences = pad_sequences([sequences], maxlen=1000)
+    prediction = model.predict(sequences)
     if prediction [0] [0]>=0.5 :
         sentimiento = "Positivo"
     else:
         sentimiento = "Negativo"
-    return predict_sentimiento
+    return sentimiento
 
 st.title("Ingrese una review para poder calificarla como positiva o negativa")
 review = st.text_area("Ingrese reseña aqui", height=200)
 
 if st.button("Predicir sentimiento"):
     if review:
-        sentiemiento = predict_sentimiento(review)
+        sentimiento = predict_sentimiento(review)
         st.write(f'El sentimiento es: {sentimiento}')
     else:
         st.write(f'Ingrese una review')