import os
import gradio as gr
import nltk
import numpy as np
import tensorflow as tf
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

# Disable GPU usage for TensorFlow
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

# Ensure necessary NLTK resources are downloaded
nltk.download("punkt")

# Initialize stemmer
stemmer = LancasterStemmer()

# Load intents.json and training data for chatbot
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
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")

# Sentiment Analysis Model (Hugging Face)
tokenizer_sentiment = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
model_sentiment = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")

# Emotion Detection Model
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'))

# Process Text Input for Chatbot
def bag_of_words(s, words):
    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)

# Chatbot Functionality
def chatbot(message, history):
    history = history or []
    try:
        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
    except Exception as e:
        response = f"Error: {str(e)} 💥"
    history.append({"role": "user", "content": message})
    history.append({"role": "assistant", "content": response})
    return history, response

# Detect Sentiment
def analyze_sentiment(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]

# Detect Emotion
def detect_emotion(user_input):
    pipe = pipeline("text-classification", model=model_emotion, tokenizer=tokenizer_emotion)
    result = pipe(user_input)
    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 🤔")

# Generate Suggestions for Detected Emotion
def generate_suggestions(emotion):
    resources = {
        "😊 Joy": [
            ["Relaxation Techniques", "Relaxation", '<a href="https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation" target="_blank">Visit</a>'],
            ["Dealing with Stress", "Stress Management", '<a href="https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety" target="_blank">Visit</a>'],
            ["Emotional Wellness Toolkit", "Wellness", '<a href="https://www.nih.gov/health-information/emotional-wellness-toolkit" target="_blank">Visit</a>'],
            ["Relaxation Videos", "Video", '<a href="https://youtu.be/m1vaUGtyo-A" target="_blank">Watch</a>']
        ],
        "😢 Sadness": [
            ["Emotional Wellness Toolkit", "Wellness", '<a href="https://www.nih.gov/health-information/emotional-wellness-toolkit" target="_blank">Visit</a>'],
            ["Dealing with Anxiety", "Anxiety Management", '<a href="https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety" target="_blank">Visit</a>'],
            ["Relaxation Videos", "Video", '<a href="https://youtu.be/-e-4Kx5px_I" target="_blank">Watch</a>']
        ],
        "😨 Fear": [
            ["Mindfulness Practices", "Mindfulness", '<a href="https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation" target="_blank">Visit</a>'],
            ["Coping with Anxiety", "Anxiety Management", '<a href="https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety" target="_blank">Visit</a>'],
            ["Emotional Wellness Toolkit", "Wellness", '<a href="https://www.nih.gov/health-information/emotional-wellness-toolkit" target="_blank">Visit</a>'],
            ["Relaxation Videos", "Video", '<a href="https://youtu.be/yGKKz185M5o" target="_blank">Watch</a>']
        ]
    }
    return resources.get(emotion.split(" ")[1], [["No specific suggestions available", "", ""]])

# Search Professionals and Generate Map
def get_health_professionals_and_map(location, query):
    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
            )["results"]
            map_ = folium.Map(location=(lat, lng), zoom_start=13)
            professionals = []
            for place in places_result:
                professionals.append(f"{place['name']} - {place.get('vicinity', '')}")
                lat, lng = place["geometry"]["location"]["lat"], place["geometry"]["location"]["lng"]
                folium.Marker([lat, lng], popup=place["name"]).add_to(map_)
            return professionals, map_._repr_html_()
        return ["No professionals found"], ""
    except Exception as e:
        return [f"Error: {e}"], ""

# 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)
    professionals_info, map_html = get_health_professionals_and_map(location, query)
    return chatbot_history, sentiment, emotion, suggestions, professionals_info, map_html

# Gradio Interface
with gr.Blocks() as demo:
    gr.Markdown("# 🌟 Well-Being Companion")
    gr.Markdown("Empowering your mental health journey 💚")
    
    with gr.Row():
        user_input = gr.Textbox(label="Your Message")
        location_input = gr.Textbox(label="Your Location")
        query_input = gr.Textbox(label="Search Query")
        submit_button = gr.Button("Submit")

    chatbot_output = gr.Chatbot(label="Chat History", type="messages")
    sentiment_output = gr.Textbox(label="Sentiment Detected")
    emotion_output = gr.Textbox(label="Emotion Detected")
    suggestions_output = gr.DataFrame(label="Suggestions", headers=["Title", "Subject", "Link"])
    professionals_output = gr.Textbox(label="Nearby Professionals", lines=5)
    map_output = gr.HTML(label="Map of Nearby Professionals")

    submit_button.click(
        app_function,
        inputs=[user_input, location_input, query_input, chatbot_output],
        outputs=[
            chatbot_output, sentiment_output, emotion_output,
            suggestions_output, professionals_output, map_output
        ],
    )

demo.launch()