Update app.py

app.py

@@ -2,6 +2,7 @@ import streamlit as st
 from functions_preprocess import LinguisticPreprocessor, download_if_non_existent, CNN
 import pickle
 import nltk
+from datasets import load_dataset
 import torch
 nltk.download('stopwords')
 nltk.download('punkt')
@@ -16,7 +17,7 @@ st.title("Movie Reviews: An NLP Sentiment analysis")
 
 #################################################################### Cache the model loading
 
-@st.cache(allow_output_mutation=True)
+@st.cache_data()
 def load_model():
   model_pkl_file = "sentiment_model.pkl"  
   with open(model_pkl_file, 'rb') as file:  
@@ -29,7 +30,7 @@ def load_cnn():
     model.eval()
     return model
 
-def predict_sentiment(text, model, vocab=16236, torch_text = False):
+def predict_sentiment(text, model, vocab, torch_text = False):
     tokenizer = get_tokenizer("basic_english")
     if torch_text == True:
         processor.transform(text)
@@ -53,6 +54,8 @@ def predict_sentiment(text, model, vocab=16236, torch_text = False):
 model_1 = load_model()
 model_2 = load_cnn()
 processor = LinguisticPreprocessor()
+train_data = load_dataset('rotten_tomatoes', split='train')
+vocab, tokenizer = build_vocab(train_data)
 
 
 ############################################################# Text input
@@ -77,10 +80,11 @@ with st.expander("Model 2: CNN Sentiment analysis"):
     user_input = st.text_area("Enter text here...", key='model2_input')
     if st.button('Analyze', key='model2_button'):
         # Displaying output
-        result = predict_sentiment(user_input, model_2, 16236, torch_text=True)
+        result = predict_sentiment(user_input, model_2, vocab, torch_text=True)
         if result >= 0.5:
             st.write('The sentiment is: Positive 😀', key='model2_poswrite')
         else:
             st.write('The sentiment is: Negative 😞', key='model2_negwrite')
 
-st.caption("Por @efeperro.")
+st.caption("Por @efeperro.")
+stop_words = set(stopwords.words('english'))