Update app.py

app.py

@@ -17,18 +17,18 @@ import torch
 os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
 os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
 
-# Ensure necessary NLTK resources
+# Download necessary NLTK resources
 nltk.download("punkt")
 stemmer = LancasterStemmer()
 
-# Load chatbot intents and training data
+# Load intents.json and chatbot training data
 with open("intents.json") as file:
     intents_data = json.load(file)
 
 with open("data.pickle", "rb") as f:
     words, labels, training, output = pickle.load(f)
 
-# Build chatbot model
+# Build Chatbot Model
 net = tflearn.input_data(shape=[None, len(training[0])])
 net = tflearn.fully_connected(net, 8)
 net = tflearn.fully_connected(net, 8)
@@ -37,18 +37,18 @@ net = tflearn.regression(net)
 chatbot_model = tflearn.DNN(net)
 chatbot_model.load("MentalHealthChatBotmodel.tflearn")
 
-# Hugging Face emotion and sentiment detection models
+# Hugging Face Models for Sentiment and Emotion Detection
 tokenizer_sentiment = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
 model_sentiment = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
 tokenizer_emotion = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 model_emotion = AutoModelForSequenceClassification.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 
-# Initialize Google Maps API client
+# Google Maps API Client
 gmaps = googlemaps.Client(key=os.getenv("GOOGLE_API_KEY"))
 
 # Helper Functions
 def bag_of_words(s, words):
-    """Convert user input into bag-of-words vector."""
+    """Convert user input to bag-of-words vector."""
     bag = [0] * len(words)
     s_words = word_tokenize(s)
     s_words = [stemmer.stem(word.lower()) for word in s_words if word.isalnum()]
@@ -58,87 +58,79 @@ def bag_of_words(s, words):
                 bag[i] = 1
     return np.array(bag)
 
-# Chatbot response logic
 def chatbot(message, history):
-    """Generate chatbot response and update chat history."""
+    """Generate chatbot response and maintain chat history."""
     history = history or []
     try:
         result = chatbot_model.predict([bag_of_words(message, words)])
         tag = labels[np.argmax(result)]
-        response = "I'm sorry, I'm not sure how to respond. 🤔"
+        response = "I'm sorry, I didn't understand that. 🤔"
         for intent in intents_data["intents"]:
             if intent["tag"] == tag:
                 response = random.choice(intent["responses"])
                 break
     except Exception as e:
         response = f"Error: {e}"
-    history.append((message, response))  # Append to the chatbot history
+    history.append((message, response))
     return history, response
 
-# Sentiment detection function
 def analyze_sentiment(user_input):
-    """Analyze sentiment and return emoji-mapped sentiment."""
+    """Analyze sentiment of user input."""
     inputs = tokenizer_sentiment(user_input, return_tensors="pt")
     with torch.no_grad():
         outputs = model_sentiment(**inputs)
     sentiment_class = torch.argmax(outputs.logits, dim=1).item()
     sentiment_map = ["Negative 😔", "Neutral 😐", "Positive 😊"]
-    return sentiment_map[sentiment_class]
+    return f"Sentiment: {sentiment_map[sentiment_class]}"
 
-# Emotion detection function
 def detect_emotion(user_input):
-    """Detect emotion from user input using Hugging Face emotion model."""
+    """Detect emotion from user input."""
     pipe = pipeline("text-classification", model=model_emotion, tokenizer=tokenizer_emotion)
     result = pipe(user_input)
     emotion = result[0]["label"].lower().strip()
     emotion_map = {
-        "joy": "😊 Joy",
-        "anger": "😠 Anger",
-        "sadness": "😢 Sadness",
-        "fear": "😨 Fear",
-        "surprise": "😲 Surprise",
-        "neutral": "😐 Neutral",
+        "joy": "Joy 😊",
+        "anger": "Anger 😠",
+        "sadness": "Sadness 😢",
+        "fear": "Fear 😨",
+        "surprise": "Surprise 😲",
+        "neutral": "Neutral 😐",
     }
-    return emotion_map.get(emotion, "Unknown 🤔")
+    return emotion_map.get(emotion, "Unknown 🤔"), emotion  # Text + clean emotion for matching keys
 
-# Generate suggestions based on emotion
 def generate_suggestions(emotion):
-    """Generate resources and videos to help based on the emotion detected."""
-    emotion_key = emotion.lower()
+    """Generate helpful resources based on emotion."""
     suggestions = {
         "joy": [
-            ["Relaxation Techniques", '<a href="https://www.helpguide.org/mental-health/meditation" target="_blank">Visit</a>'],
-            ["Emotional Toolkit", '<a href="https://www.nih.gov/health-information/emotional-wellness-toolkit" target="_blank">Visit</a>'],
+            ["Relaxation Techniques", '<a href="https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation" target="_blank">Visit</a>'],
+            ["Emotional Toolkit", '<a href="https://www.nih.gov" target="_blank">Visit</a>'],
             ["Stress Management", '<a href="https://www.health.harvard.edu" target="_blank">Visit</a>'],
         ],
         "anger": [
-            ["Calming Techniques", '<a href="https://youtu.be/MIc299Flibs" target="_blank">Watch</a>'],
-            ["Manage Anger", '<a href="https://www.helpguide.org/mental-health/anger-management.htm" target="_blank">Visit</a>'],
+            ["Calm Down Exercises", '<a href="https://youtu.be/MIc299Flibs" target="_blank">Watch</a>'],
+            ["Handle Anger", '<a href="https://www.helpguide.org" target="_blank">Visit</a>']
         ],
         "fear": [
-            ["Coping with Anxiety", '<a href="https://www.helpguide.org/mental-health/anxiety" target="_blank">Visit</a>'],
-            ["Mindfulness Meditation", '<a href="https://youtu.be/yGKKz185M5o" target="_blank">Watch</a>'],
+            ["Overcoming Fear", '<a href="https://youtu.be/yGKKz185M5o" target="_blank">Watch</a>'],
         ],
         "sadness": [
-            ["Overcoming Sadness", '<a href="https://youtu.be/-e-4Kx5px_I" target="_blank">Watch</a>'],
+            ["Overcoming Sadness", '<a href="https://youtu.be/-e-4Kx5px_I" target="_blank">Watch</a>']
         ],
         "surprise": [
             ["Managing Surprises", '<a href="https://www.health.harvard.edu" target="_blank">Visit</a>'],
             ["Relaxation Video", '<a href="https://youtu.be/m1vaUGtyo-A" target="_blank">Watch</a>'],
         ],
         "neutral": [
-            ["General Tips", '<a href="https://www.psychologytoday.com" target="_blank">Read More</a>']
-        ],
+            ["General Wellness Tips", '<a href="https://www.psychologytoday.com" target="_blank">Visit</a>'],
+        ]
     }
-    return suggestions.get(emotion_key, [["No specific suggestions available.", ""]])
+    return suggestions.get(emotion, [["No specific suggestions available.", ""]])
 
-# Google Maps integration
 def get_health_professionals_and_map(location, query):
-    """Search nearby health professionals and generate map."""
+    """Search for healthcare professionals and create an interactive map."""
     try:
         if not location or not query:
-            return ["Please provide a valid location and query."], ""
-
+            return ["Please provide both a location and search query."], ""
         geo_location = gmaps.geocode(location)
         if geo_location:
             lat, lng = geo_location[0]["geometry"]["location"].values()
@@ -147,30 +139,31 @@ def get_health_professionals_and_map(location, query):
             professionals = []
             map_ = folium.Map(location=(lat, lng), zoom_start=13)
             for place in places_result:
-                professionals.append(f"{place['name']} - {place.get('vicinity', 'No address available')}")
+                professionals.append(f"{place['name']} - {place.get('vicinity', 'No address provided')}")
                 folium.Marker(
                     location=[place["geometry"]["location"]["lat"], place["geometry"]["location"]["lng"]],
                     popup=f"{place['name']}"
                 ).add_to(map_)
+
             return professionals, map_._repr_html_()
 
-        return ["No professionals found."], ""
+        return ["No professionals found near this location."], ""
     except Exception as e:
         return [f"Error: {e}"], ""
 
-# Main application logic
-def app_function(user_message, location, query, history):
-    chatbot_history, _ = chatbot(user_message, history)
-    sentiment = analyze_sentiment(user_message)  # Sentiment detection
-    emotion = detect_emotion(user_message)  # Emotion detection
-    suggestions = generate_suggestions(emotion)  # Get emotion-based suggestions
-    professionals, map_html = get_health_professionals_and_map(location, query)  # Google Maps integration
-    return chatbot_history, sentiment, emotion, suggestions, professionals, map_html
+# Main Application
+def app_function(user_input, location, query, history):
+    chatbot_history, _ = chatbot(user_input, history)  # Chatbot response
+    sentiment_output = analyze_sentiment(user_input)  # Sentiment analysis
+    emotion_detected, clean_emotion = detect_emotion(user_input)  # Emotion detection
+    suggestions = generate_suggestions(clean_emotion)  # Emotion-matched suggestions
+    professionals, map_html = get_health_professionals_and_map(location, query)  # Map of professionals
+    return chatbot_history, sentiment_output, emotion_detected, suggestions, professionals, map_html
 
-# Custom CSS
+# Custom CSS for Polished UI
 custom_css = """
 body {
-    background: linear-gradient(135deg, #000, #ff5722);
+    background: linear-gradient(135deg, #000000, #ff5722);
     font-family: 'Roboto', sans-serif;
     color: white;
 }
@@ -178,49 +171,61 @@ h1 {
     font-size: 4.5rem;
     font-weight: bold;
     text-align: center;
-    color: white;
-    text-shadow: 2px 2px 8px rgba(0, 0, 0, 0.4);
+    margin: 20px auto;
 }
 h2 {
     font-size: 2rem;
     text-align: center;
-    font-weight: lighter;
-    color: white;
     margin-bottom: 30px;
+    color: white;
+    font-weight: lighter;
 }
-.button {
-    background: linear-gradient(45deg, #ff5722, #ff9800) !important;
-    border: none !important;
+button {
+    background: linear-gradient(45deg, #ff5722, #ff9800);
+    border: none;
+    color: white;
     padding: 12px 20px;
+    font-size: 16px;
     border-radius: 8px;
-    color: white !important;
     cursor: pointer;
-    font-size: 16px;
+}
+textarea, input {
+    background: black;
+    color: white;
+    border: 1px solid #ff5722;
+    padding: 12px;
+    border-radius: 8px;
+}
+.gr-dataframe {
+    background-color: black !important;
+    color: white !important;
+    overflow: auto;
+    border: 1px solid orange;
 }
 """
 
-# Gradio Application
+# Gradio UI Interface
 with gr.Blocks(css=custom_css) as app:
     gr.HTML("<h1>🌟 Well-Being Companion</h1>")
     gr.HTML("<h2>Empowering Your Mental Health Journey 💚</h2>")
 
     with gr.Row():
-        user_message = gr.Textbox(label="Your Message", placeholder="Enter your message...")
-        location = gr.Textbox(label="Your Location", placeholder="Enter location...")
-        query = gr.Textbox(label="Search Query", placeholder="e.g., therapist")
+        user_message = gr.Textbox(label="Your Message", placeholder="Enter your message here...")
+        location = gr.Textbox(label="Your Location", placeholder="Enter a city...")
+        query = gr.Textbox(label="Search Query", placeholder="e.g., therapist, doctor")
 
-    chatbot_history = gr.Chatbot(label="Chat History")
-    sentiment_output = gr.Textbox(label="Detected Sentiment")
-    emotion_output = gr.Textbox(label="Detected Emotion")
-    suggestions_output = gr.DataFrame(headers=["Title", "Link"], label="Suggestions")
-    professionals_output = gr.Textbox(label="Nearby Professionals", lines=5)
-    map_output = gr.HTML(label="Interactive Map")
+    chatbot = gr.Chatbot(label="Chat History")
+    sentiment = gr.Textbox(label="Detected Sentiment")
+    emotion = gr.Textbox(label="Detected Emotion")
+    suggestions = gr.DataFrame(headers=["Suggestion Title", "Link"], label="Suggestions")
+    professionals = gr.Textbox(label="Nearby Professionals", lines=6)
+    map_html = gr.HTML(label="Interactive Map")
 
     submit_button = gr.Button("Submit")
     submit_button.click(
         app_function,
-        inputs=[user_message, location, query, chatbot_history],
-        outputs=[chatbot_history, sentiment_output, emotion_output, suggestions_output, professionals_output, map_output],
+        inputs=[user_message, location, query, chatbot],
+        outputs=[chatbot, sentiment, emotion, suggestions, professionals, map_html]
     )
 
 app.launch()