app.py

import os
import gradio as gr
import nltk
import numpy as np
import tflearn
import random
import json
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 torch
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score

# Suppress TensorFlow warnings
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"

# Download necessary NLTK resources
nltk.download("punkt")
stemmer = LancasterStemmer()

# Load intents 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 the chatbot model
net = tflearn.input_data(shape=[None, len(training[0])])
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)
chatbot_model = tflearn.DNN(net)
chatbot_model.load("MentalHealthChatBotmodel.tflearn")

# Hugging Face sentiment and emotion models
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")

# Google Maps API Client
gmaps = googlemaps.Client(key=os.getenv("GOOGLE_API_KEY"))

# Load the disease dataset
df_train = pd.read_csv("Training.csv")  # Change the file path as necessary
df_test = pd.read_csv("Testing.csv")  # Change the file path as necessary

# Encode diseases
disease_dict = {
    'Fungal infection': 0, 'Allergy': 1, 'GERD': 2, 'Chronic cholestasis': 3, 'Drug Reaction': 4,
    'Peptic ulcer disease': 5, 'AIDS': 6, 'Diabetes ': 7, 'Gastroenteritis': 8, 'Bronchial Asthma': 9,
    'Hypertension ': 10, 'Migraine': 11, 'Cervical spondylosis': 12, 'Paralysis (brain hemorrhage)': 13,
    'Jaundice': 14, 'Malaria': 15, 'Chicken pox': 16, 'Dengue': 17, 'Typhoid': 18, 'hepatitis A': 19,
    'Hepatitis B': 20, 'Hepatitis C': 21, 'Hepatitis D': 22, 'Hepatitis E': 23, 'Alcoholic hepatitis': 24,
    'Tuberculosis': 25, 'Common Cold': 26, 'Pneumonia': 27, 'Dimorphic hemorrhoids(piles)': 28,
    'Heart attack': 29, 'Varicose veins': 30, 'Hypothyroidism': 31, 'Hyperthyroidism': 32,
    'Hypoglycemia': 33, 'Osteoarthritis': 34, 'Arthritis': 35,
    '(vertigo) Paroxysmal Positional Vertigo': 36, 'Acne': 37, 'Urinary tract infection': 38,
    'Psoriasis': 39, 'Impetigo': 40
}

# Function to prepare data
def prepare_data(df):
    """Prepares data for training/testing."""
    X = df.iloc[:, :-1]  # Features
    y = df.iloc[:, -1]   # Target
    label_encoder = LabelEncoder()
    y_encoded = label_encoder.fit_transform(y)
    return X, y_encoded, label_encoder

# Preparing training and testing data
X_train, y_train, label_encoder_train = prepare_data(df_train)
X_test, y_test, label_encoder_test = prepare_data(df_test)

# Define the models
models = {
    "Decision Tree": DecisionTreeClassifier(),
    "Random Forest": RandomForestClassifier(),
    "Naive Bayes": GaussianNB()
}

# Train and evaluate models
trained_models = {}
for model_name, model_obj in models.items():
    model_obj.fit(X_train, y_train)  # Fit the model
    y_pred = model_obj.predict(X_test)  # Make predictions
    acc = accuracy_score(y_test, y_pred)  # Calculate accuracy
    trained_models[model_name] = {'model': model_obj, 'accuracy': acc}

# Helper Functions for Chatbot
def bag_of_words(s, words):
    """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()]
    for se in s_words:
        for i, w in enumerate(words):
            if w == se:
                bag[i] = 1
    return np.array(bag)

def generate_chatbot_response(message, history):
    """Generate chatbot response and maintain conversation history."""
    history = history or []
    try:
        result = chatbot_model.predict([bag_of_words(message, words)])
        tag = labels[np.argmax(result)]
        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))
    return history, response

def analyze_sentiment(user_input):
    """Analyze sentiment and map to emojis."""
    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 f"Sentiment: {sentiment_map[sentiment_class]}"

def detect_emotion(user_input):
    """Detect emotions based on 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 😐",
    }
    return emotion_map.get(emotion, "Unknown 🤔"), emotion

def generate_suggestions(emotion):
    """Return relevant suggestions based on detected emotions."""
    emotion_key = emotion.lower()
    suggestions = {
        "joy": [
            ("Mindfulness Practices", "https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation"),
            ("Coping with Anxiety", "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"),
            ("Emotional Wellness Toolkit", "https://www.nih.gov/health-information/emotional-wellness-toolkit"),
            ("Relaxation Video", "https://youtu.be/yGKKz185M5o"),
        ],
        "anger": [
            ("Emotional Wellness Toolkit", "https://www.nih.gov/health-information/emotional-wellness-toolkit"),
            ("Stress Management Tips", "https://www.health.harvard.edu/health-a-to-z"),
            ("Dealing with Anger", "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"),
            ("Relaxation Video", "https://youtu.be/MIc299Flibs"),
        ],
        "fear": [
            ("Mindfulness Practices", "https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation"),
            ("Coping with Anxiety", "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"),
            ("Emotional Wellness Toolkit", "https://www.nih.gov/health-information/emotional-wellness-toolkit"),
            ("Relaxation Video", "https://youtu.be/yGKKz185M5o"),
        ],
        "sadness": [
            ("Emotional Wellness Toolkit", "https://www.nih.gov/health-information/emotional-wellness-toolkit"),
            ("Dealing with Anxiety", "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"),
            ("Relaxation Video", "https://youtu.be/-e-4Kx5px_I"),
        ],
        "surprise": [
            ("Managing Stress", "https://www.health.harvard.edu/health-a-to-z"),
            ("Coping Strategies", "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"),
            ("Relaxation Video", "https://youtu.be/m1vaUGtyo-A"),
        ],
    }
    
    # Create a markdown string for clickable suggestions in a table format
    formatted_suggestions = ["### Suggestions"]
    formatted_suggestions.append(f"Since you’re feeling {emotion}, you might find these links particularly helpful. Don’t hesitate to explore:")
    formatted_suggestions.append("| Title | Link |")
    formatted_suggestions.append("|-------|------|")  # Table headers
    formatted_suggestions += [
        f"| {title} | [{link}]({link}) |" for title, link in suggestions.get(emotion_key, [("No specific suggestions available.", "#")])
    ]

    return "\n".join(formatted_suggestions)

def get_health_professionals_and_map(location, query):
    """Search nearby healthcare professionals using Google Maps API."""
    try:
        if not location or not query:
            return [], ""  # Return empty list if inputs are missing

        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, keyword=query)["results"]
            professionals = []
            map_ = folium.Map(location=(lat, lng), zoom_start=13)
            for place in places_result:
                professionals.append([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 [], ""  # Return empty list if no professionals found
    except Exception as e:
        return [], ""  # Return empty list on exception

# Main Application Logic for Chatbot
def app_function_chatbot(user_input, location, query, history):
    chatbot_history, _ = generate_chatbot_response(user_input, history)
    sentiment_result = analyze_sentiment(user_input)
    emotion_result, cleaned_emotion = detect_emotion(user_input)
    suggestions = generate_suggestions(cleaned_emotion)
    professionals, map_html = get_health_professionals_and_map(location, query)
    return chatbot_history, sentiment_result, emotion_result, suggestions, professionals, map_html

# Disease Prediction Logic
def predict_disease(symptoms):
    """Predict disease based on input symptoms."""
    input_test = np.zeros(len(X_train.columns))  # Create an array for feature input
    for symptom in symptoms:
        if symptom in X_train.columns:
            input_test[X_train.columns.get_loc(symptom)] = 1
    predictions = {}
    for model_name, info in trained_models.items():
        prediction = info['model'].predict([input_test])[0]
        predicted_disease = label_encoder_train.inverse_transform([prediction])[0]
        predictions[model_name] = predicted_disease

    # Create a Markdown table for displaying predictions
    markdown_output = ["### Predicted Diseases"]
    markdown_output.append("| Model | Predicted Disease |")
    markdown_output.append("|-------|------------------|")  # Table headers
    for model_name, disease in predictions.items():
        markdown_output.append(f"| {model_name} | {disease} |")
    
    return "\n".join(markdown_output)

from gradio.components import HTML

# Custom CSS for styling
custom_css = """
body {
    font-family: 'Arial', sans-serif;
    background-color: #f0f4f7; /* Light background for better contrast */
    margin: 0;
    padding: 0;
}

h1 {
    background: linear-gradient(135deg, #3c6487, #355f7a); /* Gradient using your color */
    color: #ffffff;
    border-radius: 12px;
    padding: 15px;
    text-align: center;
    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2); /* Shadow effect */
}

textarea, input {
    background: white; /* Input background */
    color: black;
    border: 2px solid #3c6487; /* Matching border color */
    padding: 10px;
    font-size: 1rem;
    border-radius: 10px;
    box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1); /* Light shadow for inputs */
}

.gr-button {
    background-color: #ae1c93; /* Set the button color */
    color: white;
    border-radius: 8px;
    box-shadow: 0 4px 6px rgba(0, 0, 0, 0.2); /* Shadow on button */
    display: flex;
    align-items: center;
    justify-content: center;
}

.gr-button:hover {
    background-color: #8f167b; /* Darker shade on hover */
}

.gr-button:active {
    background-color: #7f156b; /* Even darker shade on active */
}

.gr-button .fa {
    margin-right: 10px;
}

.df-container {
    background: white;
    color: black;
    border: 2px solid #3c6487; /* Matching border color for data frames */
    border-radius: 10px;
    padding: 10px;
    font-size: 14px;
    max-height: 400px;
    height: auto;
    overflow-y: auto;
    box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1); /* Light shadow for data frame */
}

@media (max-width: 768px) {
    h1 {
        font-size: 1.5rem;
        padding: 10px;
    }

    .gr-button {
        font-size: 0.9rem;
        padding: 10px;
    }

    .gr-row {
        flex-direction: column;
        align-items: center;
    }

    textarea, input {
        width: 100%;
        margin-bottom: 10px;
    }

    .gr-chatbot {
        max-height: 300px;
        overflow-y: auto;
    }
}
"""

# Gradio Application Interface
with gr.Blocks(css=custom_css) as app:
    gr.HTML("<h1>🌟 Well-Being For All </h1>")
    
    with gr.Tab("Well-Being Chatbot"):
        with gr.Row():
            user_input = gr.Textbox(label="Please Enter Your Message Here", placeholder="Type your message here...", max_lines=3)
            location = gr.Textbox(label="Please Enter Your Current Location Here", placeholder="E.g., New York", max_lines=1)
            query = gr.Textbox(label="Please Enter Which Health Professional You Want To Search Nearby", placeholder="E.g., therapist", max_lines=1)
        
        submit_chatbot = gr.Button(value="Submit Your Message", variant="primary", elem_id="submit-chatbot", icon="fa-paper-plane")
        
        # Adding the loading prop for the chatbot button
        chatbot = gr.Chatbot(label="Chat History", elem_id="chat-history", show_label=True)
        sentiment = gr.Textbox(label="Detected Sentiment")
        emotion = gr.Textbox(label="Detected Emotion")
        
        suggestions_markdown = gr.Markdown(label="Suggestions")  # Markdown for displaying suggestions
        professionals = gr.DataFrame(label="Nearby Health Professionals", headers=["Name", "Address"])
        map_html = gr.HTML(label="Interactive Map")

        submit_chatbot.click(
            app_function_chatbot,
            inputs=[user_input, location, query, chatbot],
            outputs=[chatbot, sentiment, emotion, suggestions_markdown, professionals, map_html],
            loading=True  # Enable loading spinner on button click
        )
        
    with gr.Tab("Disease Prediction"):
        symptom1 = gr.Dropdown(X_train.columns.tolist(), label="Select Symptom 1")
        symptom2 = gr.Dropdown(X_train.columns.tolist(), label="Select Symptom 2")
        symptom3 = gr.Dropdown(X_train.columns.tolist(), label="Select Symptom 3")
        symptom4 = gr.Dropdown(X_train.columns.tolist(), label="Select Symptom 4")
        symptom5 = gr.Dropdown(X_train.columns.tolist(), label="Select Symptom 5")
        
        submit_disease = gr.Button(value="Predict Disease", variant="primary", icon="fa-stethoscope")
        
        # Adding the loading prop for the disease prediction button
        disease_prediction_result = gr.Markdown(label="Predicted Diseases")  # Use Markdown for predictions

        submit_disease.click(
            lambda symptom1, symptom2, symptom3, symptom4, symptom5: predict_disease(
                [symptom1, symptom2, symptom3, symptom4, symptom5]),
            inputs=[symptom1, symptom2, symptom3, symptom4, symptom5],
            outputs=disease_prediction_result,
            loading=True  # Enable loading spinner on button click
        )

# Launch the Gradio application
app.launch()