Update app.py

app.py

@@ -17,76 +17,65 @@ import torch
 # Disable GPU usage for TensorFlow
 os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
 
-# Suppress warnings related to missing CUDA libraries
+# Suppress TensorFlow GPU warnings & logs
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
 
-# Ensure necessary NLTK resources are downloaded
-try:
-    nltk.download('punkt')
-except Exception as e:
-    print(f"Error downloading NLTK data: {e}")
+# Download NLTK resources
+nltk.download("punkt")
 
-# Initialize the stemmer
+# Initialize Lancaster Stemmer
 stemmer = LancasterStemmer()
 
-# Load intents.json for Well-Being Chatbot
+# Load intents.json for the chatbot
 with open("intents.json") as file:
-    data = json.load(file)
+    intents_data = json.load(file)
 
 # Load preprocessed data for Well-Being Chatbot
 with open("data.pickle", "rb") as f:
     words, labels, training, output = pickle.load(f)
 
-# Build the model structure for Well-Being Chatbot
-net = tflearn.input_data(shape=[None, len(training[0])], dtype=tf.float32)  # Fix for dtype
+# Build TFlearn Chatbot Model
+net = tflearn.input_data(shape=[None, len(training[0])], dtype=tf.float32)
 net = tflearn.fully_connected(net, 8)
 net = tflearn.fully_connected(net, 8)
 net = tflearn.fully_connected(net, len(output[0]), activation="softmax")
 net = tflearn.regression(net)
 
-# Load the trained model
-model = tflearn.DNN(net)
-model.load("MentalHealthChatBotmodel.tflearn")
+# Load and initialize the trained model
+chatbot_model = tflearn.DNN(net)
+chatbot_model.load("MentalHealthChatBotmodel.tflearn")
 
-# Function to process user input into a bag-of-words format for Chatbot
+# Function to process user input into a bag-of-words format
 def bag_of_words(s, words):
     bag = [0 for _ in range(len(words))]
     s_words = word_tokenize(s)
-    s_words = [stemmer.stem(word.lower()) for word in s_words if word.lower() in words]
+    s_words = [stemmer.stem(word.lower()) for word in s_words if word.isalnum()]
     for se in s_words:
         for i, w in enumerate(words):
             if w == se:
                 bag[i] = 1
     return np.array(bag)
 
-# Chat function for Well-Being Chatbot
+# Chatbot Response Function
 def chatbot(message, history):
     history = history or []
     message = message.lower()
     try:
-        # Predict the tag
-        results = model.predict([bag_of_words(message, words)])
-        results_index = np.argmax(results)
-        tag = labels[results_index]
-
-        # Match tag with intent and choose a random response
-        for tg in data["intents"]:
-            if tg['tag'] == tag:
-                responses = tg['responses']
-                response = random.choice(responses)
+        results = chatbot_model.predict([bag_of_words(message, words)])
+        tag = labels[np.argmax(results)]
+
+        response = "I'm not sure how to respond to that. 🤔"
+        for intent in intents_data["intents"]:
+            if intent["tag"] == tag:
+                response = random.choice(intent["responses"])
                 break
-        else:
-            response = "I'm sorry, I didn't understand that. Could you please rephrase?"
     except Exception as e:
-        response = f"An error occurred: {str(e)}"
-    
-    # Convert the new message and response to the 'messages' format
+        response = f"Error: {str(e)} 💥"
     history.append({"role": "user", "content": message})
     history.append({"role": "assistant", "content": response})
-    
-    return history, history
+    return history, response
 
-# Sentiment Analysis using Hugging Face model
+# Sentiment Analysis Function
 tokenizer_sentiment = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
 model_sentiment = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
 
@@ -94,103 +83,118 @@ def analyze_sentiment(user_input):
     inputs = tokenizer_sentiment(user_input, return_tensors="pt")
     with torch.no_grad():
         outputs = model_sentiment(**inputs)
-    predicted_class = torch.argmax(outputs.logits, dim=1).item()
-    sentiment = ["Negative", "Neutral", "Positive"][predicted_class]  # Assuming 3 classes
-    return f"Predicted Sentiment: {sentiment}"
+    sentiment_class = torch.argmax(outputs.logits, dim=1).item()
+    sentiment_map = ["Negative 😔", "Neutral 😐", "Positive 😊"]
+    return sentiment_map[sentiment_class]
 
-# Emotion Detection using Hugging Face model
+# Emotion Detection Function
 tokenizer_emotion = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 model_emotion = AutoModelForSequenceClassification.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 
 def detect_emotion(user_input):
     pipe = pipeline("text-classification", model=model_emotion, tokenizer=tokenizer_emotion)
     result = pipe(user_input)
-    emotion = result[0]['label']
-    return f"Emotion Detected: {emotion}"
+    emotion = result[0]["label"]
+    emotion_map = {
+        "joy": "😊 Joy",
+        "anger": "😠 Anger",
+        "sadness": "😢 Sadness",
+        "fear": "😨 Fear",
+        "surprise": "😲 Surprise",
+        "neutral": "😐 Neutral",
+    }
+    return emotion_map.get(emotion, "Unknown Emotion 🤔")
 
-# Initialize Google Maps API client securely
+# Health Professionals Search
 gmaps = googlemaps.Client(key=os.getenv('GOOGLE_API_KEY'))
 
-# Function to search for health professionals
-def search_health_professionals(query, location, radius=10000):
-    places_result = gmaps.places_nearby(location, radius=radius, type='doctor', keyword=query)
-    return places_result.get('results', [])
-
-# Function to get directions and display on Gradio UI
-def get_health_professionals_and_map(current_location, health_professional_query):
-    location = gmaps.geocode(current_location)
-    if location:
-        lat = location[0]["geometry"]["location"]["lat"]
-        lng = location[0]["geometry"]["location"]["lng"]
-        location = (lat, lng)
-        
-        professionals = search_health_professionals(health_professional_query, location)
-        
-        # Generate map
-        map_center = location
-        m = folium.Map(location=map_center, zoom_start=13)
-        
-        # Add markers to the map
-        for place in professionals:
-            folium.Marker(
-                location=[place['geometry']['location']['lat'], place['geometry']['location']['lng']],
-                popup=place['name']
-            ).add_to(m)
-        
-        # Convert map to HTML for Gradio display
-        map_html = m._repr_html_()
-        
-        # Route information
-        route_info = "\n".join([f"{place['name']} - {place['vicinity']}" for place in professionals])
-        
-        return route_info, map_html
-    else:
-        return "Unable to find location.", ""
-
-# Function to generate suggestions based on the detected emotion
+def get_health_professionals_and_map(location, query):
+    """Search for health professionals and generate a map."""
+    try:
+        geo_location = gmaps.geocode(location)
+        if geo_location:
+            lat, lng = geo_location[0]["geometry"]["location"].values()
+            places_result = gmaps.places_nearby(
+                location=(lat, lng), radius=10000, type="doctor", keyword=query
+            ).get("results", [])
+
+            # Create map
+            m = folium.Map(location=(lat, lng), zoom_start=13)
+            for place in places_result:
+                folium.Marker(
+                    location=[
+                        place["geometry"]["location"]["lat"],
+                        place["geometry"]["location"]["lng"],
+                    ],
+                    popup=place["name"],
+                ).add_to(m)
+            map_html = m._repr_html_()
+            professionals_info = [
+                f"{place['name']} - {place.get('vicinity', 'No address available')}"
+                for place in places_result
+            ]
+            return "\n".join(professionals_info), map_html
+        return "Unable to find location", ""
+    except Exception as e:
+        return f"Error: {e}", ""
+
+# Suggestions Based on Emotion
 def generate_suggestions(emotion):
     suggestions = {
-        'joy': [
-            {"Title": "Relaxation Techniques 🌿", "Subject": "Relaxation", "Link": '<a href="https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation" target="_blank">Mindful Breathing Meditation</a>'},
-            {"Title": "Dealing with Stress 💆", "Subject": "Stress Management", "Link": '<a href="https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety" target="_blank">Tips for Dealing with Anxiety</a>'},
-            {"Title": "Emotional Wellness Toolkit 💪", "Subject": "Wellness", "Link": '<a href="https://www.nih.gov/health-information/emotional-wellness-toolkit" target="_blank">Emotional Wellness Toolkit</a>'},
-            {"Title": "Relaxation Video 🎥", "Subject": "Video", "Link": '<a href="https://youtu.be/m1vaUGtyo-A" target="_blank">Watch Video</a>'}
+        "😊 Joy": [
+            {"Title": "Meditation 🧘", "Subject": "Relaxation", "Link": "https://example.com/meditation"},
+            {"Title": "Learn a skill 🚀", "Subject": "Growth", "Link": "https://example.com/skills"},
         ],
-        'anger': [
-            {"Title": "Emotional Wellness Toolkit 💡", "Subject": "Wellness", "Link": '<a href="https://www.nih.gov/health-information/emotional-wellness-toolkit" target="_blank">Emotional Wellness Toolkit</a>'},
-            {"Title": "Managing Anger 🌿", "Subject": "Anger Management", "Link": '<a href="https://www.helpguide.org/mental-health/anger-management.htm" target="_blank">HelpGuide on Anger Management</a>'},
-            {"Title": "Relaxation Techniques 💆", "Subject": "Relaxation", "Link": '<a href="https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation" target="_blank">Mindful Breathing Meditation</a>'},
-            {"Title": "Dealing with Stress 💡", "Subject": "Stress Management", "Link": '<a href="https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety" target="_blank">Tips for Dealing with Anxiety</a>'}
+        "😢 Sadness": [
+            {"Title": "Therapist Help 💬", "Subject": "Support", "Link": "https://example.com/therapist"},
+            {"Title": "Stress Management 🌿", "Subject": "Wellness", "Link": "https://example.com/stress"},
         ],
-        'sadness': [
-            {"Title": "Overcoming Sadness 🌈", "Subject": "Well-being", "Link": '<a href="https://www.helpguide.org/mental-health/depression.htm" target="_blank">Overcoming Sadness</a>'},
-            {"Title": "Building Self-Esteem 💪", "Subject": "Confidence", "Link": '<a href="https://www.helpguide.org/mental-health/self-confidence.htm" target="_blank">Self-Confidence Guide</a>'},
-            {"Title": "Breathing Exercises 🧘‍♀️", "Subject": "Breathing", "Link": '<a href="https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation" target="_blank">Mindful Breathing Meditation</a>'},
-            {"Title": "Relaxation Tips 🌿", "Subject": "Relaxation", "Link": '<a href="https://www.helpguide.org/mental-health/stress-relief.htm" target="_blank">Stress Relief Tips</a>'}
-        ]
     }
-    
-    # Return suggestions based on emotion
-    return suggestions.get(emotion.lower(), [])
+    return suggestions.get(emotion.split(" ")[1].lower(), [])
+
+# Main Gradio App Function
+def app_function(message, location, query, history):
+    chatbot_history, _ = chatbot(message, history)
+    sentiment = analyze_sentiment(message)
+    emotion = detect_emotion(message)
+    suggestions = generate_suggestions(emotion)
+    places_info, map_html = get_health_professionals_and_map(location, query)
+    return chatbot_history, sentiment, emotion, suggestions, map_html, places_info
 
 # Gradio Interface
 with gr.Blocks() as demo:
+    gr.Markdown("# 🌟 Well-being Companion")
+    gr.Markdown("Empowering your mental health journey 💚")
+
     with gr.Row():
-        with gr.Column():
-            message_input = gr.Textbox(label="Your Message", placeholder="Type a message here...", lines=4)
-            location_input = gr.Textbox(label="Your Location", placeholder="Enter your location (e.g., Pune, India)...", lines=2)
-            health_query_input = gr.Textbox(label="Health Professional Search", placeholder="Type a health professional type (e.g., therapist, doctor)...", lines=1)
-            history_output = gr.Chatbot(label="Chat History", scale=3)
-            sentiment_output = gr.Textbox(label="Sentiment Analysis")
-            emotion_output = gr.Textbox(label="Emotion Detection")
-            suggestions_output = gr.Dataframe(label="Suggestions", headers=["Title", "Subject", "Link"], interactive=True)
-            map_output = gr.HTML(label="Map")
-            route_info_output = gr.Textbox(label="Nearby Health Professionals Info")
-    
-    message_input.submit(chatbot, [message_input, history_output], [history_output, history_output])
-    message_input.submit(analyze_sentiment, message_input, sentiment_output)
-    message_input.submit(detect_emotion, message_input, emotion_output)
-    message_input.submit(generate_suggestions, emotion_output, suggestions_output)
-    location_input.submit(get_health_professionals_and_map, [location_input, health_query_input], [route_info_output, map_output])
-
-demo.launch()
+        user_input = gr.Textbox(label="Your Message", placeholder="Type your message...", lines=2)
+        location_input = gr.Textbox(label="Your Location", placeholder="Enter location...", lines=2)
+        query_input = gr.Textbox(label="Search Query", placeholder="Enter query (e.g., therapist)...", lines=1)
+        submit_btn = gr.Button("Submit")
+
+    with gr.Row():
+        chatbot_output = gr.Chatbot(label="Chat History", type="messages")
+    with gr.Row():
+        sentiment_output = gr.Textbox(label="Sentiment Analysis")
+        emotion_output = gr.Textbox(label="Emotion Detected")
+    with gr.Row():
+        suggestions_output = gr.DataFrame(label="Suggestions", headers=["Title", "Subject", "Link"])
+    with gr.Row():
+        map_display = gr.HTML(label="Map of Nearby Professionals")
+        health_info_output = gr.Textbox(label="Health Professionals Info", lines=5)
+
+    # Button interaction
+    submit_btn.click(
+        app_function,
+        inputs=[user_input, location_input, query_input, chatbot_output],
+        outputs=[
+            chatbot_output,
+            sentiment_output,
+            emotion_output,
+            suggestions_output,
+            map_display,
+            health_info_output,
+        ],
+    )
+
+demo.launch()