Update app.py

app.py

@@ -2,7 +2,26 @@
 from transformers import pipeline
 import streamlit as st
 
-pipe = pipeline("text-classification", model="mavinsao/mi-roberta-base-finetuned-mental-illness")
+pipe_1 = pipeline("text-classification", model="mavinsao/mi-roberta-base-finetuned-mental-illness")
+pipe_2 = pipeline("text-classification", model="mavinsao/roberta-mental-finetuned")
+
+
+def ensemble_predict(text):
+    results_1 = pipe_1(text)
+    results_2 = pipe_2(text)
+
+    # Implement your chosen ensemble strategy here. 
+    # Example with simple averaging: 
+    ensemble_scores = {}
+    for result in results_1 + results_2:
+        label = result['label']
+        score = result['score']
+        ensemble_scores[label] = ensemble_scores.get(label, 0) + score / 2  
+
+    predicted_label = max(ensemble_scores, key=ensemble_scores.get)
+    confidence = ensemble_scores[predicted_label] 
+
+    return predicted_label, confidence
 
 # Streamlit app
 st.title('Mental Illness Prediction')
@@ -10,7 +29,8 @@ st.title('Mental Illness Prediction')
 # Input text area for user input
 sentence = st.text_area("Enter the long sentence to predict your mental illness state:")
 
-# Prediction button
 if st.button('Predict'):
-    
-    st.write("Predicted labels:", pipe(sentence))
+    # ... (input validation ... )
+    predicted_label, confidence = ensemble_predict(sentence)
+    st.write("Predicted label:", predicted_label)
+    st.write("Confidence:", confidence)