Update app.py

app.py

@@ -12,38 +12,58 @@ download_if_non_existent('corpora/wordnet', 'wordnet')
 #################################################################### Streamlit interface
 st.title("Movie Reviews: An NLP Sentiment analysis")
 
-st.markdown("### NLP Processing utilizing various ML approaches")
-st.markdown("##### This initial approach merges multiple datasets, processed through a TF-IDF vectorizer with 2 n-grams and fed into a Stochastic Gradient Descent model.")
-st.markdown("Give it a go by writing a positive or negative text, and analyze it!")
-
-
 #################################################################### Cache the model loading
+
 @st.cache_data()
-def load_model():
-    model_pkl_file = "sentiment_model.pkl"  
-    with open(model_pkl_file, 'rb') as file:  
-        model = pickle.load(file)
-    return model
+def load_model(model_path):
+  model_pkl_file = "sentiment_model.pkl"  
+  with open(model_pkl_file, 'rb') as file:  
+    model = pickle.load(file)
+  return model
+
+def load_cnn():
+  model.load_state_dict(torch.load('model_cnn.pkl'))
+  model.eval()
+
+  return model
 
-model = load_model()
-processor = LinguisticPreprocessor()
 def predict_sentiment(text, model):
     processor.transform(text)
     prediction = model.predict([text])
     return prediction
 
 
+model_1 = load_model()
+model_2 = load_cnn()
+processor = LinguisticPreprocessor()
+
+
 ############################################################# Text input
-user_input = st.text_area("Enter text here...")
 
-if st.button('Analyze'):
-    # Displaying output
-    result = predict_sentiment(user_input, model)
-    if result >= 0.5:
-        st.write('The sentiment is: Positive 😀')
+with st.expander("Model 1: SGD Classifier"):
+    st.markdown("Give it a go by writing a positive or negative text, and analyze it!")
+
+    # Text input inside the expander
+    user_input = st.text_area("Enter text here...")
+    if st.button('Analyze'):
+        # Displaying output
+        result = predict_sentiment(user_input, model_1)
+        if result >= 0.5:
+            st.write('The sentiment is: Positive 😀')
+        else:
+            st.write('The sentiment is: Negative 😞')
 
-    else:
-        st.write('The sentiment is: Negative 😞')
+with st.expander("Model 2: CNN Sentiment analysis"):
+    st.markdown("Give it a go by writing a positive or negative text, and analyze it!")
 
+    # Text input inside the expander
+    user_input = st.text_area("Enter text here...")
+    if st.button('Analyze'):
+        # Displaying output
+        result = predict_sentiment(user_input, model_2)
+        if result >= 0.5:
+            st.write('The sentiment is: Positive 😀')
+        else:
+            st.write('The sentiment is: Negative 😞')
 
-st.caption("Por @efeperro con ❤️. Credits to 🤗")
+st.caption("Por @efeperro.")