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 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, response # 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 in plain English and resources in table def detect_emotion(user_input): pipe = pipeline("text-classification", model=model_emotion, tokenizer=tokenizer_emotion) result = pipe(user_input) emotion = result[0]['label'] # Define emotion-specific message and resources if emotion == 'joy': emotion_msg = "You're feeling happy! Keep up the great mood!" resources = [ {"subject": "Relaxation Techniques", "heading": "Mindful Breathing Meditation", "link": "https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation", "video_url": "https://youtu.be/m1vaUGtyo-A"}, {"subject": "Dealing with Stress", "heading": "Tips for Dealing with Anxiety", "link": "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety", "video_url": "https://youtu.be/m1vaUGtyo-A"}, {"subject": "Emotional Wellness Toolkit", "heading": "Emotional Wellness Resources", "link": "https://www.nih.gov/health-information/emotional-wellness-toolkit", "video_url": "https://youtu.be/m1vaUGtyo-A"} ] elif emotion == 'anger': emotion_msg = "You're feeling angry. It's okay to feel this way. Let's try to calm down." resources = [ {"subject": "Emotional Wellness Toolkit", "heading": "Managing Emotions", "link": "https://www.nih.gov/health-information/emotional-wellness-toolkit", "video_url": "https://youtu.be/MIc299Flibs"}, {"subject": "Stress Management Tips", "heading": "Managing Stress Effectively", "link": "https://www.health.harvard.edu/health-a-to-z", "video_url": "https://youtu.be/MIc299Flibs"}, {"subject": "Dealing with Anger", "heading": "Strategies to Calm Anger", "link": "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety", "video_url": "https://youtu.be/MIc299Flibs"} ] elif emotion == 'fear': emotion_msg = "You're feeling fearful. Take a moment to breathe and relax." resources = [ {"subject": "Mindfulness Practices", "heading": "Breathing Techniques", "link": "https://www.helpguide.org/mental-health/meditation/mindful-breathing-meditation", "video_url": "https://youtu.be/yGKKz185M5o"}, {"subject": "Coping with Anxiety", "heading": "Overcoming Fear", "link": "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety", "video_url": "https://youtu.be/yGKKz185M5o"}, {"subject": "Emotional Wellness Toolkit", "heading": "Calming Your Mind", "link": "https://www.nih.gov/health-information/emotional-wellness-toolkit", "video_url": "https://youtu.be/yGKKz185M5o"} ] elif emotion == 'sadness': emotion_msg = "You're feeling sad. It's okay to take a break." resources = [ {"subject": "Emotional Wellness Toolkit", "heading": "Restoring Your Emotional Health", "link": "https://www.nih.gov/health-information/emotional-wellness-toolkit", "video_url": "https://youtu.be/-e-4Kx5px_I"}, {"subject": "Dealing with Anxiety", "heading": "Coping Strategies for Stress", "link": "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety", "video_url": "https://youtu.be/-e-4Kx5px_I"} ] elif emotion == 'surprise': emotion_msg = "You're feeling surprised. It's okay to feel neutral!" resources = [ {"subject": "Managing Stress", "heading": "Relaxation Tips", "link": "https://www.health.harvard.edu/health-a-to-z", "video_url": "https://youtu.be/m1vaUGtyo-A"}, {"subject": "Coping Strategies", "heading": "Dealing with Unexpected Events", "link": "https://www.helpguide.org/mental-health/anxiety/tips-for-dealing-with-anxiety", "video_url": "https://youtu.be/m1vaUGtyo-A"} ] else: emotion_msg = "Could not detect emotion." resources = [] # Create a DataFrame for resources to display in table format resource_df = pd.DataFrame(resources) return emotion_msg, resource_df # 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 # Google Places API setup for wellness professionals url = "https://maps.googleapis.com/maps/api/place/textsearch/json" places_details_url = "https://maps.googleapis.com/maps/api/place/details/json" api_key = os.getenv("GOOGLE_API_KEY") # Use environment variable for security # Function to get places data using Google Places API def get_places_data(query, location, radius, api_key, next_page_token=None): params = { 'query': query, 'location': location, 'radius': radius, 'key': api_key } if next_page_token: params['pagetoken'] = next_page_token response = requests.get(url, params=params) return response.json() # Function to fetch wellness professionals def get_wellness_professionals(location, api_key): lat, lon = get_lat_lon(location, api_key) if lat and lon: places = get_places_data("wellness professional", f"{lat},{lon}", 10000, api_key) if places and 'results' in places: professionals = [] for place in places['results']: name = place.get("name", "No name available") rating = place.get("rating", "No rating available") address = place.get("formatted_address", "No address available") professionals.append({ "Name": name, "Rating": rating, "Address": address }) professionals_df = pd.DataFrame(professionals) return professionals_df else: return "No wellness professionals found nearby." else: return "Location not found. Please check the location." # Gradio interface function to handle actions and outputs def interface_function(message, action, location, history): history = history or [] if action == "Chat": # Use chat function if 'Chat' button is clicked history, response = chat(message, history) elif action == "Detect Emotion": # Use emotion detection if 'Detect Emotion' button is clicked emotion_msg, resource_df = detect_emotion(message) response = emotion_msg # Return the resource DataFrame as a table return history, response, resource_df elif action == "Wellness Resources": # Use location to get wellness professionals if 'Wellness Resources' is clicked if not location.strip(): response = "Please enter a valid location." else: professionals_df = get_wellness_professionals(location, api_key) if isinstance(professionals_df, pd.DataFrame): response = "Found wellness professionals nearby:" return history, response, professionals_df else: response = professionals_df # If error message is returned return history, response, None return history, "Invalid action", None # Gradio Interface with table outputs for emotion and wellness professionals iface = gr.Interface( fn=interface_function, inputs=["text", "radio", "text", "state"], # Include state in the inputs outputs=["text", "dataframe", "state"], # Add state to the outputs live=True, allow_flagging="never" ) iface.launch(share=True)