Update app.py

app.py

@@ -12,24 +12,24 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipe
 import pandas as pd
 import torch
 
-# Disable GPU usage for TensorFlow compatibility
+# Disable TensorFlow GPU warnings (safe since we are using CPU)
 os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
 
 # Download necessary NLTK resources
 nltk.download("punkt")
 
-# Initialize Lancaster Stemmer
+# Initialize Lancaster Stemmer for text preprocessing
 stemmer = LancasterStemmer()
 
 # Load intents.json for the chatbot
 with open("intents.json") as file:
     intents_data = json.load(file)
 
-# Load tokenized training data
+# Load tokenized training data for chatbot
 with open("data.pickle", "rb") as f:
     words, labels, training, output = pickle.load(f)
 
-# Build the TFlearn model
+# Build TFlearn Chatbot Model
 def build_chatbot_model():
     net = tflearn.input_data(shape=[None, len(training[0])])
     net = tflearn.fully_connected(net, 8)
@@ -42,7 +42,7 @@ def build_chatbot_model():
 
 chatbot_model = build_chatbot_model()
 
-# Function: Bag of words
+# Function: Bag of Words
 def bag_of_words(s, words):
     bag = [0 for _ in range(len(words))]
     s_words = word_tokenize(s)
@@ -53,15 +53,15 @@ def bag_of_words(s, words):
                 bag[i] = 1
     return np.array(bag)
 
-# Chatbot response generator
+# Chatbot Response Function
 def chatbot_response(message, history):
-    """Generates a response from the chatbot and appends it to the history."""
+    """Generates a chatbot response."""
     history = history or []
     try:
         result = chatbot_model.predict([bag_of_words(message, words)])
         idx = np.argmax(result)
         tag = labels[idx]
-        response = "I'm not sure how to respond to that. 🤔"
+        response = "I didn't understand that. 🤔"
         for intent in intents_data["intents"]:
             if intent["tag"] == tag:
                 response = random.choice(intent["responses"])
@@ -69,11 +69,11 @@ def chatbot_response(message, history):
     except Exception as e:
         response = f"Error generating response: {str(e)} 💥"
 
-    # Format output as tuples for Gradio Chatbot compatibility
-    history.append((message, response))
+    history.append({"role": "user", "content": message})
+    history.append({"role": "assistant", "content": response})
     return history, response
 
-# Emotion detection transformer model
+# Emotion Detection Function
 emotion_tokenizer = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 emotion_model = AutoModelForSequenceClassification.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 
@@ -94,12 +94,12 @@ def detect_emotion(user_input):
     except Exception as e:
         return f"Error detecting emotion: {str(e)} 💥"
 
-# Sentiment analysis model
+# Sentiment Analysis Function
 sentiment_tokenizer = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
 sentiment_model = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
 
 def analyze_sentiment(user_input):
-    """Analyze sentiment of user input."""
+    """Analyze sentiment based on input."""
     inputs = sentiment_tokenizer(user_input, return_tensors="pt")
     try:
         with torch.no_grad():
@@ -110,37 +110,40 @@ def analyze_sentiment(user_input):
     except Exception as e:
         return f"Error in sentiment analysis: {str(e)} 💥"
 
-# Suggestions based on emotion
+# Suggestions Based on Emotion
 def generate_suggestions(emotion):
-    suggestions = {
+    suggestions_map = {
         "😊 Joy": [
             {"Title": "Mindful Meditation 🧘", "Link": "https://www.helpguide.org/meditation"},
-            {"Title": "Learn a new skill ✨", "Link": "https://www.skillshare.com/"},
+            {"Title": "Learn a New Skill ✨", "Link": "https://www.skillshare.com/"},
         ],
         "😢 Sadness": [
-            {"Title": "Talk to a professional 💬", "Link": "https://www.betterhelp.com/"},
-            {"Title": "Mental health toolkit 🛠️", "Link": "https://www.psychologytoday.com/"},
+            {"Title": "Talk to a Professional 💬", "Link": "https://www.betterhelp.com/"},
+            {"Title": "Mental Health Toolkit 🛠️", "Link": "https://www.psychologytoday.com/"},
         ],
         "😠 Anger": [
             {"Title": "Anger Management Tips 🔥", "Link": "https://www.mentalhealth.org.uk"},
             {"Title": "Stress Relieving Exercises 🌿", "Link": "https://www.calm.com/"},
         ],
     }
-    return suggestions.get(emotion, [{"Title": "Wellness Resources 🌈", "Link": "https://www.helpguide.org/wellness"}])
+    return suggestions_map.get(emotion, [{"Title": "General Wellness Resources 🌈", "Link": "https://www.helpguide.org/wellness"}])
 
-# Dummy Function for Location Query Simulation (replace this with actual map/search integration)
+# Dummy Nearby Professionals Function
 def search_nearby_professionals(location, query):
-    """Simulate searching for nearby professionals and returning results."""
-    return [
-        {"Name": "Wellness Center One", "Address": "123 Wellness Way"},
-        {"Name": "Mental Health Clinic", "Address": "456 Recovery Road"},
-        {"Name": "Therapists Hub", "Address": "789 Peace Avenue"},
-    ] if location and query else []
-
+    """Simulates the search for nearby professionals."""
+    if location and query:
+        return [
+            {"Name": "Wellness Center", "Address": "123 Wellness Way"},
+            {"Name": "Mental Health Clinic", "Address": "456 Recovery Road"},
+            {"Name": "Therapy Hub", "Address": "789 Peace Avenue"},
+        ]
+    return []
+
+# Main App Logic
 def well_being_app(user_input, location, query, history):
-    """Main function for chatbot, emotion detection, sentiment, suggestions, and location query."""
-    # Chatbot response
-    history, chatbot_reply = chatbot_response(user_input, history)
+    """Handles chatbot interaction, emotion detection, sentiment analysis, and professional search results."""
+    # Chatbot Response
+    history, _ = chatbot_response(user_input, history)
 
     # Emotion Detection
     emotion = detect_emotion(user_input)
@@ -148,83 +151,52 @@ def well_being_app(user_input, location, query, history):
     # Sentiment Analysis
     sentiment = analyze_sentiment(user_input)
 
-    # Suggestions
-    detected_emotion = emotion.split(": ")[-1]
-    suggestions = generate_suggestions(detected_emotion)
+    # Emotion-based Suggestions
+    emotion_name = emotion.split(": ")[-1]
+    suggestions = generate_suggestions(emotion_name)
     suggestions_df = pd.DataFrame(suggestions)
 
-    # Nearby Professionals (Location Query)
+    # Nearby Professionals Lookup
     professionals = search_nearby_professionals(location, query)
 
     return history, sentiment, emotion, suggestions_df, professionals
 
-# Custom CSS for beautification
-custom_css = """
-body {
-    background: linear-gradient(135deg, #28a745, #218838);
-    font-family: Arial, sans-serif;
-    color: black;
-}
-button {
-    background-color: #1abc9c;
-    color: white;
-    padding: 10px 20px;
-    font-size: 16px;
-    border-radius: 8px;
-    cursor: pointer;
-}
-button:hover {
-    background-color: #16a085;
-}
-textarea, input[type="text"] {
-    background: #ffffff;
-    color: #000000;
-    font-size: 14px;
-    border: 1px solid #ced4da;
-    padding: 10px;
-    border-radius: 5px;
-}
-"""
-
-# Gradio UI
-with gr.Blocks(css=custom_css) as interface:
-    gr.Markdown("# 🌱 **Well-being Companion**")
-    gr.Markdown("### Empowering Your Mental Health Journey with AI 💚")
-
-    # Input Section
+# Gradio Interface
+with gr.Blocks() as interface:
+    gr.Markdown("## 🌱 Well-being Companion")
+    gr.Markdown("> Empowering Your Health! 💚")
+
     with gr.Row():
-        gr.Textbox(label="Your Message", lines=2, placeholder="How can I support you today?", elem_id="message_input")
-        gr.Textbox(label="Location", placeholder="Enter your location (e.g., New York City)")
-        gr.Textbox(label="Search Query", placeholder="Professionals nearby? (e.g., doctors, therapists)")
-        submit_button = gr.Button("Submit")
+        user_input = gr.Textbox(label="Your Message", placeholder="How are you feeling today? (e.g. I feel happy)")
+        location_input = gr.Textbox(label="Location", placeholder="Enter your city (e.g., New York)")
+        query_input = gr.Textbox(label="Search Query", placeholder="What are you searching for? (e.g., therapists)")
+        submit_button = gr.Button("Submit", variant="primary")
 
     # Chatbot Section
-    with gr.Row():
-        chatbot_title = "### Chatbot Response"
-        chatbot_output = gr.Chatbot(label=None)
+    chatbot_output = gr.Chatbot(label="Chatbot Interaction", type="messages", value=[])
 
-    # Sentiment and Emotion Section
-    with gr.Row():
-        gr.Markdown("### Sentiment Analysis")
-        sentiment_output = gr.Textbox(label=None)
-        gr.Markdown("### Detected Emotion")
-        emotion_output = gr.Textbox(label=None)
+    # Sentiment and Emotion Outputs
+    sentiment_output = gr.Textbox(label="Sentiment Analysis")
+    emotion_output = gr.Textbox(label="Emotion Detected")
 
-    # Suggestions Section
-    with gr.Row():
-        gr.Markdown("### Suggestions")
-        suggestions_output = gr.DataFrame(headers=["Title", "Link"], interactive=False, max_height=300)
+    # Suggestions Table
+    suggestions_output = gr.DataFrame(label="Suggestions", value=[], headers=["Title", "Link"])
 
-    # Location Search Results Section
-    with gr.Row():
-        gr.Markdown("### Nearby Professionals")
-        location_output = gr.DataFrame(headers=["Name", "Address"], interactive=False, max_height=300)
+    # Professionals Table
+    nearby_professionals_output = gr.DataFrame(label="Nearby Professionals", value=[], headers=["Name", "Address"])
 
+    # Connect Inputs to Outputs
     submit_button.click(
         well_being_app,
-        inputs=["message_input", "Location", "Search Query", chatbot_output],
-        outputs=[chatbot_output, sentiment_output, emotion_output, suggestions_output, location_output],
+        inputs=[user_input, location_input, query_input, chatbot_output],
+        outputs=[
+            chatbot_output,
+            sentiment_output,
+            emotion_output,
+            suggestions_output,
+            nearby_professionals_output,
+        ],
     )
 
-# Launch the app
+# Run Gradio Application
 interface.launch()