Update app.py

app.py

@@ -1,12 +1,12 @@
 import streamlit as st
 from transformers import pipeline
 
-# Load the emotion classification model
-emotion_analyzer = pipeline("text-classification", model="cardiffnlp/twitter-roberta-base-sentiment")
+# Emotion classifier
+emotion_analyzer = pipeline("text-classification", model="distilbert-base-uncased")
 
-# Enhanced Suggestion Database (Now includes resources)
+# Enhanced Suggestion Database with resources
 suggestion_database = {
-    "sadness": {
+    "NEGATIVE": {
         "suggestions": ["Try a guided meditation", "Take a walk in nature", "Connect with a friend"],
         "articles": [
             {"title": "Overcoming Sadness", "url": "https://example.com/sadness1"},
@@ -17,7 +17,7 @@ suggestion_database = {
             {"title": "Coping with Grief", "url": "https://www.youtube.com/watch?v=sadnessvideo2"},
         ],
     },
-    "joy": {
+    "POSITIVE": {
         "suggestions": ["Practice gratitude", "Engage in a hobby", "Spend time with loved ones"],
         "articles": [
             {"title": "The Benefits of Joy", "url": "https://example.com/joy1"},
@@ -28,7 +28,7 @@ suggestion_database = {
             {"title": "Practicing Gratitude", "url": "https://www.youtube.com/watch?v=joyvideo2"},
         ],
     },
-    "neutral": {
+    "NEUTRAL": {
         "suggestions": ["Take a break", "Engage in a relaxing activity", "Spend time in nature"],
         "articles": [
             {"title": "Importance of Self-Care", "url": "https://example.com/selfcare1"},
@@ -46,9 +46,9 @@ def get_relevant_resources(emotion):
     resources = suggestion_database.get(emotion, {})
     return resources.get("suggestions", []), resources.get("articles", []), resources.get("videos", [])
 
-# Enhanced Suggestion Function
+# Function to suggest activities based on the emotion analysis result
 def suggest_activity(emotion_analysis):
-    max_emotion = max(emotion_analysis, key=emotion_analysis.get) if emotion_analysis else "neutral"
+    max_emotion = max(emotion_analysis, key=emotion_analysis.get) if emotion_analysis else "NEUTRAL"
     suggestions, articles, videos = get_relevant_resources(max_emotion)
     return {
         "suggestions": suggestions,
@@ -56,33 +56,23 @@ def suggest_activity(emotion_analysis):
         "videos": videos,
     }
 
-# Streamlit app interface
-st.title("Emotion Prediction and Well-Being Suggestions")
-
-# Ask 3 questions to the user
-question1 = st.text_input("How are you feeling today?")
-question2 = st.text_input("Have you felt stressed recently?")
-question3 = st.text_input("Do you have enough time for relaxation?")
-
-if st.button("Get Suggestions"):
-    # Combine responses to analyze sentiment
-    user_input = f"{question1} {question2} {question3}"
-    
-    # Perform emotion analysis
-    emotion_analysis = emotion_analyzer(user_input)
+# Streamlit app
+def main():
+    st.title("Emotion Detection and Suggestions")
     
-    # Get suggestions, articles, and videos based on the emotion
-    resources = suggest_activity(emotion_analysis)
+    st.write("Please answer the following questions:")
     
-    # Display suggestions, articles, and videos
-    st.write("Here are some suggestions to help you:")
-    for suggestion in resources["suggestions"]:
-        st.write(f"- {suggestion}")
-    
-    st.write("Articles you may find helpful:")
-    for article in resources["articles"]:
-        st.markdown(f"[{article['title']}]({article['url']})")
-    
-    st.write("Videos you may find helpful:")
-    for video in resources["videos"]:
-        st.markdown(f"[{video['title']}]({video['url']})")
+    # Step 1: Collect answers to three questions
+    question_1 = st.text_input("How are you feeling today? (e.g., happy, sad, stressed)")
+    question_2 = st.text_input("What's something that is currently on your mind?")
+    question_3 = st.text_input("Do you feel overwhelmed or calm right now?")
+
+    if question_1 and question_2 and question_3:
+        # Step 2: Analyze sentiment of responses
+        text_to_analyze = f"{question_1} {question_2} {question_3}"
+        analysis_result = emotion_analyzer(text_to_analyze)
+        emotion = analysis_result[0]['label']  # Get the emotion from the analysis result
+        
+        # Map emotion label from the model to our suggestion database
+        if emotion == "LABEL_0":
+