Update app.py

app.py

@@ -1,116 +1,51 @@
 import gradio as gr
-import nltk
-import numpy as np
-import tflearn
 import random
-import json
-import pickle
-import torch
-from nltk.tokenize import word_tokenize
-from nltk.stem.lancaster import LancasterStemmer
-from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 import requests
-import geocoder  # Use geocoder to get latitude/longitude from city
-
-# 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.")
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 
-# 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)
+# Replace with your Google Maps API and Places API Key
+GOOGLE_API_KEY = "GOOGLE_API_KEY"
 
-# Chat function
-def chat(message, history, state):
-    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?"
+# Load pre-trained models for sentiment and emotion detection
+tokenizer = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
+sentiment_model = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
+emotion_tokenizer = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
+emotion_model = AutoModelForSequenceClassification.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 
-        # Add emoticons to the response
-        emoticon_dict = {
-            "joy": "😊",
-            "anger": "😡",
-            "fear": "😨",
-            "sadness": "😔",
-            "surprise": "😲",
-            "neutral": "😐"
-        }
+# Function to get latitude and longitude from city using Google Maps Geocoding API
+def get_lat_lng_from_city(city):
+    geocode_url = f"https://maps.googleapis.com/maps/api/geocode/json?address={city}&key={GOOGLE_API_KEY}"
+    response = requests.get(geocode_url)
+    data = response.json()
+    if data["status"] == "OK":
+        lat_lng = data["results"][0]["geometry"]["location"]
+        return lat_lng["lat"], lat_lng["lng"]
+    else:
+        return None, None
 
-        # Add the emotion-related emoticon to the response
-        for tg in data["intents"]:
-            if tg['tag'] == tag:
-                emotion = tg.get('emotion', 'neutral')  # Default to neutral if no emotion is defined
-                response = f"{response} {emoticon_dict.get(emotion, '😐')}"
-                break
+# Function to get wellness professionals using Google Places API
+def get_wellness_professionals(location):
+    lat, lng = get_lat_lng_from_city(location)
+    if lat and lng:
+        places_url = f"https://maps.googleapis.com/maps/api/place/nearbysearch/json?location={lat},{lng}&radius=5000&type=health&key={GOOGLE_API_KEY}"
+        response = requests.get(places_url)
+        data = response.json()
+        professionals = []
+        if 'results' in data:
+            for place in data['results']:
+                name = place['name']
+                address = place.get('vicinity', 'No address available')
+                url = place.get('website', '#')
+                professionals.append(f"**{name}** - {address} - [Visit Website]({url})")
         
-        history.append((message, response))
-
-        # Transition to the next feature (sentiment analysis)
-        state['step'] = 2  # Move to sentiment analysis
-    except Exception as e:
-        response = f"An error occurred: {str(e)}"
-
-    return history, history, state
-
-# Load pre-trained model and tokenizer for sentiment analysis
-tokenizer = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
-sentiment_model = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
+        if not professionals:
+            professionals.append("No wellness professionals found nearby.")
+        return "\n".join(professionals)
+    else:
+        return "Couldn't fetch your location. Please make sure you entered a valid location."
 
 # Function for sentiment analysis
 def analyze_sentiment(text, state):
-    if state is None:
-        state = {'step': 1}
-        
     inputs = tokenizer(text, return_tensors="pt")
     with torch.no_grad():
         outputs = sentiment_model(**inputs)
@@ -129,10 +64,6 @@ def analyze_sentiment(text, state):
     state['step'] = 3  # Move to emotion detection and suggestions
     return sentiment_with_emoji, state
 
-# Load pre-trained model and tokenizer for emotion detection
-emotion_tokenizer = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
-emotion_model = AutoModelForSequenceClassification.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
-
 # Function for emotion detection and suggestions
 def detect_emotion(text, state):
     pipe = pipeline("text-classification", model=emotion_model, tokenizer=emotion_tokenizer)
@@ -194,32 +125,6 @@ def provide_suggestions(emotion):
     # Ensure we return a message even if no articles/videos are found
     return resources.get(emotion, {'message': "Stay calm. 🙂", 'articles': ["[General Wellbeing Tips](https://www.helpguide.org)"], 'videos': []})
 
-# Function to fetch wellness professionals based on location
-def get_wellness_professionals(location):
-    # Use Geocoder to get latitude/longitude from city
-    g = geocoder.osm(location)
-    if g.ok:
-        latitude, longitude = g.latlng
-        google_api_url = f"https://maps.googleapis.com/maps/api/place/nearbysearch/json?location={latitude},{longitude}&radius=5000&type=health&key=YOUR_GOOGLE_API_KEY"
-        
-        response = requests.get(google_api_url)
-        data = response.json()
-        
-        professionals = []
-        if 'results' in data:
-            for place in data['results']:
-                name = place['name']
-                address = place.get('vicinity', 'No address available')
-                url = place.get('website', '#')
-                professionals.append(f"**{name}** - {address} - [Visit Website]({url})")
-        
-        if not professionals:
-            professionals.append("No wellness professionals found nearby.")
-        
-        return "\n".join(professionals)
-    else:
-        return "Couldn't fetch your location. Please make sure you entered a valid location."
-
 # Function to ask for location and provide wellness professionals
 def search_wellness_professionals(location, state):
     professionals = get_wellness_professionals(location)
@@ -246,4 +151,4 @@ def create_ui():
 
 # Launch Gradio interface
 demo = create_ui()
-demo.launch(debug=True)
+demo.launch(debug=True)