import json
import pickle
import random
import nltk
import numpy as np
import tflearn
import gradio as gr
import requests
import torch
import pandas as pd
import folium
from bs4 import BeautifulSoup
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
from nltk.tokenize import word_tokenize
from nltk.stem.lancaster import LancasterStemmer
import os

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

# Initialize the stemmer
stemmer = LancasterStemmer()

# Load intents.json
try:
    with open("intents.json") as file:
        data = json.load(file)
except FileNotFoundError:
    raise FileNotFoundError("Error: 'intents.json' file not found. Ensure it exists in the current directory.")

# Load preprocessed data from pickle
try:
    with open("data.pickle", "rb") as f:
        words, labels, training, output = pickle.load(f)
except FileNotFoundError:
    raise FileNotFoundError("Error: 'data.pickle' file not found. Ensure it exists and matches the model.")

# Build the model structure
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)

# Load the trained model
model = tflearn.DNN(net)
try:
    model.load("MentalHealthChatBotmodel.tflearn")
except FileNotFoundError:
    raise FileNotFoundError("Error: Trained model file 'MentalHealthChatBotmodel.tflearn' not found.")

# Function to process user input into a bag-of-words format
def bag_of_words(s, words):
    bag = [0 for _ in range(len(words))]
    s_words = word_tokenize(s)
    s_words = [stemmer.stem(word.lower()) for word in s_words if word.lower() in words]
    for se in s_words:
        for i, w in enumerate(words):
            if w == se:
                bag[i] = 1
    return np.array(bag)

# Chat function
def chat(message, history):
    history = history or []
    message = message.lower()
    
    try:
        # Predict the tag
        results = model.predict([bag_of_words(message, words)])
        results_index = np.argmax(results)
        tag = labels[results_index]

        # Match tag with intent and choose a random response
        for tg in data["intents"]:
            if tg['tag'] == tag:
                responses = tg['responses']
                response = random.choice(responses)
                break
        else:
            response = "I'm sorry, I didn't understand that. Could you please rephrase?"

    except Exception as e:
        response = f"An error occurred: {str(e)}"
    
    history.append((message, response))
    return history, history


# Sentiment analysis setup
tokenizer_sentiment = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
model_sentiment = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")

# Emotion detection setup
def load_emotion_model():
    tokenizer = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
    model = AutoModelForSequenceClassification.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
    return tokenizer, model

tokenizer_emotion, model_emotion = load_emotion_model()

# Emotion detection function with suggestions
def detect_emotion(user_input):
    pipe = pipeline("text-classification", model=model_emotion, tokenizer=tokenizer_emotion)
    result = pipe(user_input)
    emotion = result[0]['label']
    
    suggestions = []
    video_link = ""
    
    # Provide suggestions based on the detected emotion
    if emotion == 'joy':
        suggestions = [
            ("Relaxation Techniques", "https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation"),
            ("Dealing with Stress", "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety"),
            ("Emotional Wellness Toolkit", "https://www.nih.gov/health-information/emotional-wellness-toolkit")
        ]
        video_link = "Watch on YouTube: https://youtu.be/m1vaUGtyo-A"
    elif emotion == 'anger':
        suggestions = [
            ("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")
        ]
        video_link = "Watch on YouTube: https://youtu.be/MIc299Flibs"
    elif emotion == 'fear':
        suggestions = [
            ("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")
        ]
        video_link = "Watch on YouTube: https://youtu.be/yGKKz185M5o"
    elif emotion == 'sadness':
        suggestions = [
            ("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")
        ]
        video_link = "Watch on YouTube: https://youtu.be/-e-4Kx5px_I"
    elif emotion == 'surprise':
        suggestions = [
            ("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")
        ]
        video_link = "Watch on YouTube: https://youtu.be/m1vaUGtyo-A"
    
    return emotion, suggestions, video_link

# Google Geocoding API setup to convert city name to latitude/longitude
geocode_url = "https://maps.googleapis.com/maps/api/geocode/json"

def get_lat_lon(location, api_key):
    params = {
        "address": location,
        "key": api_key
    }
    response = requests.get(geocode_url, params=params)
    if response.status_code == 200:
        result = response.json()
        if result['status'] == 'OK':
            # Return the first result's latitude and longitude
            location = result['results'][0]['geometry']['location']
            return location['lat'], location['lng']
    return None, None

# Get wellness professionals
def get_wellness_professionals(location, api_key):
    query = "therapist OR counselor OR mental health professional OR marriage and family therapist OR psychotherapist OR psychiatrist OR psychologist OR nutritionist OR wellness doctor OR holistic practitioner OR integrative medicine OR chiropractor OR naturopath"
    radius = 50000  # 50 km radius

    # Get the latitude and longitude from the location input
    lat, lon = get_lat_lon(location, api_key)
    
    if lat is None or lon is None:
        return "Unable to find coordinates for the given location."

    # Using Google Places API to fetch wellness professionals
    data = get_places_data(query, f"{lat},{lon}", radius, api_key)

    if data:
        results = data.get('results', [])
        wellness_data = []
        for place in results:
            name = place.get("name")
            address = place.get("formatted_address")
            latitude = place.get("geometry", {}).get("location", {}).get("lat")
            longitude = place.get("geometry", {}).get("location", {}).get("lng")
            wellness_data.append([name, address, latitude, longitude])
        return wellness_data

    return []

# Function to generate a map with wellness professionals
def generate_map(wellness_data):
    map_center = [23.685, 90.3563]  # Default center for Bangladesh (you can adjust this)
    m = folium.Map(location=map_center, zoom_start=12)

    for place in wellness_data:
        name, address, lat, lon = place
        folium.Marker(
            location=[lat, lon],
            popup=f"<b>{name}</b><br>{address}",
            icon=folium.Icon(color='blue', icon='info-sign')
        ).add_to(m)

    # Save map as an HTML file
    map_file = "wellness_map.html"
    m.save(map_file)
    
    # Return the HTML file path to be embedded in Gradio
    return map_file

# Gradio interface setup for user interaction
def user_interface(message, location, history, api_key):
    history, history = chat(message, history)
    
    # Sentiment analysis
    inputs = tokenizer_sentiment(message, return_tensors="pt")
    outputs = model_sentiment(**inputs)
    sentiment = ["Negative", "Neutral", "Positive"][torch.argmax(outputs.logits, dim=1).item()]
    
    # Emotion detection
    emotion, resources, video_link = detect_emotion(message)
    
    # Get wellness professionals
    wellness_data = get_wellness_professionals(location, api_key)
    
    # Generate the map
    map_file = generate_map(wellness_data)
    
    # Create a DataFrame for the suggestions
    suggestions_df = pd.DataFrame(resources, columns=["Subject", "Article URL"])
    suggestions_df["Video URL"] = video_link  # Add video URL column
    
    return history, history, sentiment, emotion, resources, video_link, map_file, suggestions_df.to_html(escape=False)

# Gradio chatbot interface
chatbot = gr.Chatbot(label="Mental Health Chatbot")
location_input = gr.Textbox(label="Enter your location (latitude,longitude)", placeholder="e.g., 21.3,-157.8")

# Gradio interface definition
demo = gr.Interface(
    user_interface,
    [gr.Textbox(label="Message"), location_input, "state", "text"],
    [chatbot, "state", "text", "text", "json", "text", "html", "html"],  # Added additional output for the map
    allow_flagging="never",
    title="Mental Health & Well-being Assistant"
)

# Launch Gradio interface
if __name__ == "__main__":
    demo.launch()