Update app.py

app.py

@@ -100,8 +100,8 @@ model_sentiment = AutoModelForSequenceClassification.from_pretrained("cardiffnlp
 sentiment_pipeline = pipeline("sentiment-analysis")
 
 def predict_sentiment(text):
-    result = sentiment_pipeline(text)[0]
-    return result['label']
+    result = sentiment_pipeline(text)
+    return result[0]['label']
 
 # Emotion detection
 tokenizer_emotion = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
@@ -109,8 +109,8 @@ model_emotion = AutoModelForSequenceClassification.from_pretrained("j-hartmann/e
 emotion_pipeline = pipeline("text-classification", model=model_emotion, tokenizer=tokenizer_emotion)
 
 def predict_emotion(text):
-    result = emotion_pipeline(text)[0]
-    return result['label']
+    result = emotion_pipeline(text)
+    return result[0]['label']
 
 # Fetching nearby health professionals
 google_places_url = "https://maps.googleapis.com/maps/api/place/textsearch/json"
@@ -151,9 +151,46 @@ def fetch_nearby_health_professionals(location):
     
     return pd.DataFrame(data, columns=['Name', 'Rating', 'Phone Number'])
 
-# Save results to CSV
-def save_to_csv(data, filename):
-    data.to_csv(filename, index=False)
+# Gradio interface for recommendations
+def generate_recommendations(emotion):
+    if emotion == 'joy':
+        return [
+            {"title": "Mindful Breathing Meditation", "link": "https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation"},
+            {"title": "Dealing with Stress", "link": "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"},
+            {"title": "Emotional Wellness Toolkit", "link": "https://www.nih.gov/health-information/emotional-wellness-toolkit"}
+        ]
+    elif emotion == 'anger':
+        return [
+            {"title": "Emotional Wellness Toolkit", "link": "https://www.nih.gov/health-information/emotional-wellness-toolkit"},
+            {"title": "Stress Management Tips", "link": "https://www.health.harvard.edu/health-a-to-z"},
+            {"title": "Dealing with Anger", "link": "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"}
+        ]
+    elif emotion == 'fear':
+        return [
+            {"title": "Mindfulness Practices", "link": "https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation"},
+            {"title": "Coping with Anxiety", "link": "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"},
+            {"title": "Emotional Wellness Toolkit", "link": "https://www.nih.gov/health-information/emotional-wellness-toolkit"}
+        ]
+    elif emotion == 'sadness':
+        return [
+            {"title": "Emotional Wellness Toolkit", "link": "https://www.nih.gov/health-information/emotional-wellness-toolkit"},
+            {"title": "Dealing with Anxiety", "link": "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"}
+        ]
+    elif emotion == 'surprise':
+        return [
+            {"title": "Managing Stress", "link": "https://www.health.harvard.edu/health-a-to-z"},
+            {"title": "Coping Strategies", "link": "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"}
+        ]
+    else:
+        return []
+
+def recommendations_interface(emotion):
+    recs = generate_recommendations(emotion)
+    html = "<ul>"
+    for rec in recs:
+        html += f"<li><a href='{rec['link']}'>{rec['title']}</a></li>"
+    html += "</ul>"
+    return html
 
 # Gradio interface
 with gr.Blocks() as demo:
@@ -165,8 +202,7 @@ with gr.Blocks() as demo:
 
     # Model prediction for emotion detection
     def predict_emotion(text):
-        result = emotion_pipeline(text)
-        return result[0]['label']
+        return predict_emotion(text)
 
     # Show suggestions based on the detected emotion
     def show_suggestions(emotion):
@@ -197,7 +233,7 @@ with gr.Blocks() as demo:
     message_input = gr.Textbox(lines=1, label="Message")
     submit_chat = gr.Button("Send")
 
-    def chat(message, history):
+    def chat_with_sentiment_and_emotion(message, history):
         history = history or []
         message = message.lower()
         
@@ -220,9 +256,14 @@ with gr.Blocks() as demo:
             response = f"An error occurred: {str(e)}"
         
         history.append((message, response))
-        return history, history
+        
+        # Sentiment analysis
+        sentiment_result = predict_sentiment(message)
+        emotion_result = predict_emotion(message)
+        
+        return history, history, sentiment_result, emotion_result
 
-    submit_chat.click(chat, inputs=[message_input, gr.State()], outputs=[chatbot, gr.State()])
+    submit_chat.click(chat_with_sentiment_and_emotion, inputs=[message_input, gr.State()], outputs=[chatbot, gr.State(), gr.Textbox(), gr.Textbox()])
 
     # Location input for fetching nearby health professionals
     location_input = gr.Textbox(lines=1, label="Enter your location (plain English):")
@@ -236,27 +277,21 @@ with gr.Blocks() as demo:
     nearby_health_professionals_table = gr.Dataframe(headers=["Name", "Rating", "Phone Number"])
     submit_location.click(fetch_nearby_health_professionals, inputs=location_input, outputs=nearby_health_professionals_table)
 
-    # User input for text (sentiment analysis)
-    user_input_sentiment = gr.Textbox(lines=1, label="Enter text to analyze sentiment:")
-    submit_sentiment = gr.Button("Submit")
-
-    # Prediction button for sentiment analysis
-    def predict_sentiment(text):
-        result = sentiment_pipeline(text)
-        return result[0]['label']
-
-    sentiment_output = gr.Textbox(label="Predicted Sentiment")
-    submit_sentiment.click(predict_sentiment, inputs=user_input_sentiment, outputs=sentiment_output)
-
-    # Button to fetch wellness professionals data
-    fetch_button = gr.Button("Fetch Wellness Professionals Data")
-    data_output = gr.Dataframe(headers=["Name", "Rating", "Phone Number"])
-
-    def fetch_data():
-        df = fetch_nearby_health_professionals("Hawaii")
-        return df
-
-    fetch_button.click(fetch_data, inputs=None, outputs=data_output)
+    # Article and video recommendations
+    article_video_recs = gr.HTML("<h2>Article and Video Recommendations</h2><p>No recommendations yet.</p>")
+    recommendations_ui = gr.Interface(
+        fn=recommendations_interface,
+        inputs="text",
+        outputs="html",
+        title="Article and Video Recommendations",
+        description="Get personalized recommendations based on your mood."
+    )
+
+    def update_recommendations(emotion):
+        recs_html = recommendations_interface(emotion)
+        article_video_recs.update(recs_html)
+
+    emotion_output.change(update_recommendations, inputs=emotion_output, outputs=article_video_recs)
 
 # Launch Gradio interface
 demo.launch()