Update app.py

app.py

@@ -9,29 +9,27 @@ import pickle
 from nltk.tokenize import word_tokenize
 from nltk.stem.lancaster import LancasterStemmer
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
-import googlemaps
-import folium
 import pandas as pd
 import torch
 
-# Disable GPU usage for TensorFlow for compatibility
+# Disable GPU usage for TensorFlow
 os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
 
-# Download necessary NLTK resources
+# Download required NLTK resources
 nltk.download('punkt')
 
 # Initialize Lancaster Stemmer
 stemmer = LancasterStemmer()
 
-# Load intents.json for Chatbot
+# Load intents.json for the chatbot
 with open("intents.json") as file:
     intents_data = json.load(file)
 
-# Load tokenized data for Chatbot
+# Load tokenized training data
 with open("data.pickle", "rb") as f:
     words, labels, training, output = pickle.load(f)
 
-# Build Chatbot Model
+# Build the TFlearn model
 def build_chatbot_model():
     net = tflearn.input_data(shape=[None, len(training[0])])
     net = tflearn.fully_connected(net, 8)
@@ -44,7 +42,7 @@ def build_chatbot_model():
 
 chatbot_model = build_chatbot_model()
 
-# Bag of Words Function for Chatbot
+# Function: Bag of words
 def bag_of_words(s, words):
     bag = [0 for _ in range(len(words))]
     s_words = word_tokenize(s)
@@ -55,33 +53,31 @@ def bag_of_words(s, words):
                 bag[i] = 1
     return np.array(bag)
 
-# Chatbot Response Function
+# Chatbot response generator
 def chatbot_response(message, history):
-    """Respond to user input and update chat history."""
     history = history or []
     try:
         result = chatbot_model.predict([bag_of_words(message, words)])
-        result_index = np.argmax(result)
-        tag = labels[result_index]
-
-        response = "I didn't understand that. 🤔 Try rephrasing your question."
+        idx = np.argmax(result)
+        tag = labels[idx]
+        response = "I'm not sure how to respond to that 🤔"
         for intent in intents_data["intents"]:
             if intent["tag"] == tag:
-                response = f"🤖 {random.choice(intent['responses'])}"
+                response = random.choice(intent["responses"])
                 break
     except Exception as e:
         response = f"Error generating response: {str(e)} 💥"
 
     history.append({"role": "user", "content": f"💬 {message}"})
-    history.append({"role": "assistant", "content": response})
+    history.append({"role": "assistant", "content": f"🤖 {response}"})
     return history, response
 
-# Emotion Detection with Transformers
+# Hugging Face transformers model for emotion detection
 emotion_tokenizer = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 emotion_model = AutoModelForSequenceClassification.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 
+# Detect emotion
 def detect_emotion(user_input):
-    """Detect emotion using a pre-trained model and return label with an emoji."""
     pipe = pipeline("text-classification", model=emotion_model, tokenizer=emotion_tokenizer)
     try:
         result = pipe(user_input)
@@ -98,7 +94,7 @@ def detect_emotion(user_input):
     except Exception as e:
         return f"Error detecting emotion: {str(e)} 💥"
 
-# Sentiment Analysis
+# Sentiment analysis using Hugging Face
 sentiment_tokenizer = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
 sentiment_model = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
 
@@ -108,82 +104,99 @@ def analyze_sentiment(user_input):
     try:
         with torch.no_grad():
             outputs = sentiment_model(**inputs)
-        sentiment_class = torch.argmax(outputs.logits, dim=1).item()
+        sentiment = torch.argmax(outputs.logits, dim=1).item()
         sentiment_map = ["Negative 😔", "Neutral 😐", "Positive 😊"]
-        return f"Sentiment: {sentiment_map[sentiment_class]}"
+        return sentiment_map[sentiment]
     except Exception as e:
         return f"Error in sentiment analysis: {str(e)} 💥"
 
-# Generate Suggestions Based on Emotion
+# Suggestions based on emotion
 def generate_suggestions(emotion):
     suggestions = {
         "😊 Joy": [
-            {"Title": "Meditation Techniques", "Link": "https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation"},
-            {"Title": "Learn Something New", "Link": "https://www.edx.org/"},
+            {"Title": "Mindful Meditation 🧘‍♂️", "Link": "https://www.helpguide.org/meditation"},
+            {"Title": "Explore a new skill 🚀", "Link": "https://www.skillshare.com/"},
         ],
         "😢 Sadness": [
-            {"Title": "Emotional Wellness Toolkit", "Link": "https://www.nih.gov/health-information/emotional-wellness-toolkit"},
-            {"Title": "Relaxation Videos", "Link": "https://youtu.be/-e-4Kx5px_I"},
+            {"Title": "Improve mental resilience ✨", "Link": "https://www.psychologytoday.com/"},
+            {"Title": "Reach out to a therapist 💬", "Link": "https://www.betterhelp.com/"},
         ],
         "😠 Anger": [
-            {"Title": "Dealing with Anger", "Link": "https://www.helpguide.org/articles/anger/anger-management.htm"},
-            {"Title": "Stress Reducing Tips", "Link": "https://www.webmd.com/stress-management"},
+            {"Title": "Anger Management Guide 🔥", "Link": "https://www.mentalhealth.org.uk/"},
+            {"Title": "Calming Exercises 🌿", "Link": "https://www.calm.com/"},
         ],
     }
-    return suggestions.get(emotion, [{"Title": "General Tips", "Link": "https://www.psychologytoday.com/"}])
+    return suggestions.get(emotion, [{"Title": "General Wellness Resources 🌈", "Link": "https://www.wellness.com/"}])
 
-# Gradio Interface Main Function
-def well_being_app(user_input, location, query, history):
-    """Main app combining chatbot, emotion detection, sentiment, suggestions, and map."""
-    # Chatbot Interaction
+# Main App Function
+def well_being_app(user_input, history):
+    """Main function for chatbot, emotion detection, sentiment analysis, and suggestions."""
+    # Chatbot response
     history, chatbot_reply = chatbot_response(user_input, history)
 
-    # Emotion Detection
+    # Emotion detection
     emotion = detect_emotion(user_input)
 
-    # Sentiment Analysis
+    # Sentiment analysis
     sentiment = analyze_sentiment(user_input)
 
-    # Suggestions Based on Emotion
-    emotion_label = emotion.split(": ")[-1]
-    suggestions = generate_suggestions(emotion_label)
+    # Generating suggestions
+    detected_emotion = emotion.split(": ")[-1]
+    suggestions = generate_suggestions(detected_emotion)
     suggestions_df = pd.DataFrame(suggestions)
 
-    # Return Outputs
-    return (
-        history,
-        sentiment,
-        emotion,
-        suggestions_df
-    )
+    return history, sentiment, emotion, suggestions_df
+
+# Custom CSS for Beautification
+custom_css = """
+body {
+    background: linear-gradient(135deg, #8e44ad, #3498db);
+    font-family: 'Arial', sans-serif;
+    color: white;
+    text-align: center;
+}
+#component-0 span {
+    color: #ffcccc;
+}
+button {
+    background-color: #1abc9c;
+    border: none;
+    color: white;
+    padding: 12px 24px;
+    text-align: center;
+    font-size: 16px;
+    border-radius: 8px;
+    cursor: pointer;
+}
+button:hover {
+    background-color: #16a085;
+}
+"""
+
+# Gradio UI
+with gr.Blocks(css=custom_css) as interface:
+    gr.Markdown("# 🌸 **Mental Health & Well-Being Assistant**")
+    gr.Markdown("### Powered by NLP & AI")
 
-# Gradio Interface UI
-with gr.Blocks() as app:
     with gr.Row():
-        gr.Markdown("# 🌼 Well-Being Support Application")
-
+        user_input = gr.Textbox(lines=2, placeholder="How can I support you today?", label="Your Input")
+        
     with gr.Row():
-        user_input = gr.Textbox(lines=2, placeholder="Type your message here...", label="Your Message")
-        location = gr.Textbox(value="Honolulu, HI", label="Your Location")
-        query = gr.Textbox(value="Counselor", label="Health Professional (Doctor, Therapist, etc.)")
+        submit_button = gr.Button("Submit", elem_id="submit")
     
     with gr.Row():
-        submit_button = gr.Button(value="Submit", label="Submit")
-    
+        chatbot_out = gr.Chatbot(label="Chat History")
+        sentiment_out = gr.Textbox(label="Sentiment")
+        emotion_out = gr.Textbox(label="Detected Emotion")
+        
     with gr.Row():
-        chatbot = gr.Chatbot(label="Chat History")
-        sentiment_output = gr.Textbox(label="Sentiment Analysis")
-        emotion_output = gr.Textbox(label="Emotion Detected")
+        suggestions_out = gr.DataFrame(label="Suggestions", headers=["Title", "Link"])
     
-    with gr.Row():
-        suggestions_output = gr.DataFrame(label="Suggestions Based on Mood")
-
-    # Connect inputs and outputs
     submit_button.click(
         well_being_app,
-        inputs=[user_input, location, query, chatbot],
-        outputs=[chatbot, sentiment_output, emotion_output, suggestions_output],
+        inputs=[user_input, chatbot_out],
+        outputs=[chatbot_out, sentiment_out, emotion_out, suggestions_out],
     )
 
-# Launch the app
-app.launch()
+# Launch App
+interface.launch()