Update virtualhealth.py

virtualhealth.py

@@ -1,108 +1,22 @@
-# -*- coding: utf-8 -*-
-"""VirtualHealth.ipynb
-
-Automatically generated by Colab.
-
-Original file is located at
-    https://colab.research.google.com/drive/1yVSYiPz-WUlO7U0uAKe9LmfMXHd5eyAA
-"""
-!pip install streamlit
-
 import xgboost as xgb
 import pickle
 import numpy as np
 import pandas as pd
-
-# Load the trained model
-model = xgb.XGBClassifier()
-model.load_model("symptom_disease_model.json")
-
-# Load the label encoder
-label_encoder = pickle.load(open("label_encoder.pkl", "rb"))
-
-# Load symptom names (from preprocessed training data)
-X_train = pd.read_csv("X_train.csv")  # Get feature names
-symptom_list = X_train.columns.tolist()
-
-# Function to Predict Disease
-def predict_disease(user_symptoms):
-    # Convert user symptoms into one-hot encoded format
-    input_vector = np.zeros(len(symptom_list))
-
-    for symptom in user_symptoms:
-        if symptom in symptom_list:
-            input_vector[symptom_list.index(symptom)] = 1
-
-    input_vector = input_vector.reshape(1, -1)  # Reshape for model
-
-    # Predict disease (returns a numerical class)
-    predicted_class = model.predict(input_vector)[0]
-
-    # Convert number to disease name
-    predicted_disease = label_encoder.inverse_transform([predicted_class])[0]
-
-    return predicted_disease
-
-# Example Usage
-user_symptoms = ["itching", "skin_rash", "nodal_skin_eruptions"]
-predicted_disease = predict_disease(user_symptoms)
-print(f"Predicted Disease: {predicted_disease}")
-
-!pip install zipfile36
-import sys
-if sys.version_info >= (3, 6):
-    import zipfile
-else:
-    import zipfile36 as zipfile
-import os
-
-zip_file_path = '/content/disease symptom.zip'  # Update with your path
-extracted_dir = '/content'  # Where to extract the files
-
-with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:
-    zip_ref.extractall(extracted_dir)
-
-# Load the precaution dataset
-precaution_df = pd.read_csv("Disease precaution.csv")
-
-# Convert to dictionary for fast lookup
-precaution_dict = {}
-for _, row in precaution_df.iterrows():
-    disease = row["Disease"].strip().lower()
-    precautions = [row[f"Precaution_{i}"] for i in range(1, 5) if pd.notna(row[f"Precaution_{i}"])]
-    precaution_dict[disease] = precautions
-
-# Function to Get Precautions
-def get_precautions(disease_name):
-    disease_name = disease_name.strip().lower()
-    return precaution_dict.get(disease_name, ["No precautions found"])
-
-# Example Usage
-precautions = get_precautions(predicted_disease)
-print(f"Precautions for {predicted_disease}: {precautions}")
-
-!pip install nltk
-
-import re
+import torch
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering
 import nltk
-from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+import re
 
-# Download stopwords if not already downloaded
+# 🔹 Download stopwords only when needed
 nltk.download("stopwords")
 nltk.download("punkt")
+nltk.download('punkt_tab')
 
 # Load English stopwords
 stop_words = set(stopwords.words("english"))
-nltk.download('punkt_tab')
-
-import xgboost as xgb
-import pickle
-import numpy as np
-import pandas as pd
-import torch
-from transformers import AutoTokenizer, AutoModelForQuestionAnswering
-import re  # Import regex module for better input processing
 
 # ============================
 # 🔹 1. Load Pretrained Medical Q&A Model
@@ -112,18 +26,12 @@ tokenizer = AutoTokenizer.from_pretrained(qa_model_name)
 qa_model = AutoModelForQuestionAnswering.from_pretrained(qa_model_name)
 
 # ============================
-# 🔹 2. Load Symptom Checker Model & Label Encoder (Fixed)
+# 🔹 2. Load Symptom Checker Model
 # ============================
-# Load trained XGBoost model from JSON
 model = xgb.XGBClassifier()
-model.load_model("symptom_disease_model.json")
-common_symptoms = ["fever", "cough", "headache", "pain", "vomiting", "fatigue", "nausea", "rash", "chills", "dizziness", "sore throat", "diarrhea"]
-
-# Load Corrected Label Encoder
-label_encoder = pickle.load(open("label_encoder.pkl", "rb"))
-
-# Load symptom names from training data
-X_train = pd.read_csv("X_train.csv")  # Get feature names
+model.load_model("symptom_disease_model.json")  # Load trained model
+label_encoder = pickle.load(open("label_encoder.pkl", "rb"))  # Load label encoder
+X_train = pd.read_csv("X_train.csv")  # Load symptoms
 symptom_list = X_train.columns.tolist()
 
 # ============================
@@ -145,34 +53,27 @@ def load_medical_context():
 medical_context = load_medical_context()
 
 # ============================
-# 🔹 5. Doctor Database (For Appointments)
+# 🔹 5. Doctor Database
 # ============================
 doctor_database = {
     "malaria": [{"name": "Dr. Rajesh Kumar", "specialty": "Infectious Diseases", "location": "Apollo Hospital", "contact": "9876543210"}],
     "diabetes": [{"name": "Dr. Anil Mehta", "specialty": "Endocrinologist", "location": "AIIMS Delhi", "contact": "9876543233"}],
     "heart attack": [{"name": "Dr. Vikram Singh", "specialty": "Cardiologist", "location": "Medanta Hospital", "contact": "9876543255"}],
-    "hepatitis e": [{"name": "Dr. Sunil Agarwal", "specialty": "Hepatologist", "location": "Fortis Hospital", "contact": "9876543266"}],
-    "pneumonia": [{"name": "Dr. Priya Sharma", "specialty": "Pulmonologist", "location": "Max Healthcare", "contact": "9876543277"}],
-    "heartattack": [{"name": "Dr. Vikram Singh", "specialty": "Cardiologist", "location": "Medanta Hospital", "contact": "9876543255"}],
 }
 
 # ============================
-# 🔹 6. Predict Disease from Symptoms (Fully Fixed)
+# 🔹 6. Predict Disease from Symptoms
 # ============================
 def predict_disease(user_symptoms):
-    """Predicts the disease based on user symptoms using the trained XGBoost model."""
+    """Predicts disease based on user symptoms using the trained XGBoost model."""
     input_vector = np.zeros(len(symptom_list))
 
     for symptom in user_symptoms:
         if symptom in symptom_list:
-            input_vector[symptom_list.index(symptom)] = 1  # One-hot encoding
+            input_vector[symptom_list.index(symptom)] = 1
 
     input_vector = input_vector.reshape(1, -1)  # Reshape for model input
-
-    # Predict disease (returns a numerical class)
-    predicted_class = model.predict(input_vector)[0]
-
-    # Convert number to disease name
+    predicted_class = model.predict(input_vector)[0]  # Predict disease
     predicted_disease = label_encoder.inverse_transform([predicted_class])[0]
 
     return predicted_disease
@@ -218,237 +119,30 @@ def book_appointment(disease):
 # ============================
 # 🔹 10. Handle User Queries
 # ============================
-def extract_treatment_from_context(disease):
-    """Extracts treatment details for a given disease from `medical_context.txt`."""
-    with open("medical_context.txt", "r", encoding="utf-8") as file:
-        lines = file.readlines()
-
-    treatment_section = []
-    found_disease = False
-    found_treatment = False
-
-    for line in lines:
-        line = line.strip()
-
-        #  Check if we found the disease name
-        if f"## {disease.lower()}" in line.lower():
-            found_disease = True
-
-        #  If we found the disease, now look for "Treatment"
-        if found_disease and "**Treatment**" in line:
-            found_treatment = True
-            continue  # Skip the "**Treatment**:" line itself
-
-        #  If found, keep extracting treatment details
-        if found_treatment:
-            # Stop at blank line or the next section (## New Disease Name)
-            if line == "" or line.startswith("## "):
-                break
-            treatment_section.append(line)
-
-    return "\n".join(treatment_section) if treatment_section else None
-
-
-def extract_disease_name(user_query):
-    """Extracts the disease name by removing unnecessary words, but keeps medical terms."""
-    user_query_cleaned = re.sub(r"[^\w\s]", "", user_query.lower())  # Remove punctuation
-    words = word_tokenize(user_query_cleaned)
-
-    #  Remove stopwords but keep diseases/symptoms
-    filtered_words = [word for word in words if word not in stop_words or word in common_symptoms]
-
-    return " ".join(filtered_words).strip()
-
-def find_best_match(query, database):
-    """Finds the best matching disease from the database based on query words."""
-    query_words = query.split()  # Split query into words
-
-    # Check for exact match first
-    if query in database:
-        return query  # Exact match found
-
-    # Check if any word in query exists in database keys
-    for disease in database:
-        for word in query_words:
-            if word in disease:  # Partial match found
-                return disease
-
-    return None  # No match found
-
-
 def handle_user_query(user_query):
     """Handles user queries related to symptoms, diseases, and doctor appointments."""
-
     user_query = user_query.lower().strip()
 
-    #  Skip Cleaning for "I have..." and "experiencing..." Cases
-    if "i have" in user_query or "experiencing" in user_query:
-        symptoms = user_query.replace("I have", "").replace("experiencing", "").strip()
-        disease = predict_disease(symptoms.split(", "))  # Convert to list
-        precautions = get_precautions(disease)
-        return f"**Predicted Disease:** {disease}\n**Precautions:** {', '.join(precautions)}\n{book_appointment(disease)}"
-
-    #  Extract Disease Name for Queries
-    user_query_cleaned = extract_disease_name(user_query)
-
-    #  Handle "Who should I see for..." Queries (Improved with Partial Matching)
-    if "who should i see " in user_query:
-        disease_query = user_query.replace("who should i see", "").strip()
-        disease = find_best_match(disease_query, doctor_database)  # Get best match
-
-        if disease:
-            doctor = doctor_database[disease][0]
-            return f"You should see a **{doctor['specialty']}** for {disease}.\nExample: {doctor['name']} at {doctor['location']}."
-        else:
-            return "I'm not sure. Please consult a general physician for more guidance."
-
-    #  Book Appointment (Improved with Partial Matching)
-    elif "book appointment" in user_query_cleaned:
-        disease_query = user_query_cleaned.replace("book appointment", "").strip()
-        disease = find_best_match(disease_query, doctor_database)
-        return book_appointment(disease) if disease else "Sorry, no matching doctor found."
-
-    #  Symptoms Query
-    elif "symptoms" in user_query_cleaned or "signs" in user_query_cleaned:
-        disease = user_query_cleaned.replace("symptoms", "").replace("signs", "").strip()
+    # Check if query is about symptoms
+    if "symptoms" in user_query or "signs" in user_query:
+        disease = user_query.replace("symptoms", "").replace("signs", "").strip()
         return get_medical_answer(f"What are the symptoms of {disease}?")
 
-    #  Precautions Query
-    elif "precautions" in user_query_cleaned or "prevent" in user_query_cleaned:
-        disease = user_query_cleaned.replace("precautions", "").replace("prevent", "").strip()
-        return ", ".join(get_precautions(disease))
-
-    #  Treatment Query
-    if "treatment" in user_query_cleaned or "treat" in user_query_cleaned:
-        disease = user_query_cleaned.replace("treatment", "").replace("treat", "").strip()
+    # Check if query is about treatment
+    elif "treatment" in user_query or "treat" in user_query:
+        disease = user_query.replace("treatment", "").replace("treat", "").strip()
+        return get_medical_answer(f"What is the treatment for {disease}?")
 
-        # 🔹 First, try to extract treatment from `medical_context.txt`
-        treatment_answer = extract_treatment_from_context(disease)
-        if treatment_answer:
-            return treatment_answer  #  Use direct extraction first
+    # Check for doctor recommendation
+    elif "who should i see" in user_query:
+        disease = user_query.replace("who should i see for", "").strip()
+        return book_appointment(disease)
 
-        # 🔹 If no treatment info found, use the Q&A Model
-        model_answer = get_medical_answer(f"What is the treatment for {disease}?")
-        if model_answer in ["<s>", "", "No reliable answer found."]:
-            return f"I'm not sure, but common treatments for {disease} include medication, therapy, or consulting a specialist."
-        return model_answer
+    # Check for appointment booking
+    elif "book appointment" in user_query:
+        disease = user_query.replace("book appointment for", "").strip()
+        return book_appointment(disease)
 
-    #  General Medical Questions (Fallback)
+    # Default case: general medical question
     else:
-        response = get_medical_answer(user_query)
-        if response in ["<s>", "", "No reliable answer found."]:
-            return "I'm not sure, but you may consult a specialist for better guidance."
-        return response
-
-# ============================
-# 🔹 11. Test Cases (Run Examples)
-# ============================
-print(handle_user_query("I have fever, chills, and muscle aches"))  # Should predict disease & precautions
-print(handle_user_query("What are the symptoms of pneumonia?"))  # Should return pneumonia symptoms
-print(handle_user_query("Book an appointment for diabetes"))  # Should book a diabetes specialist
-print(handle_user_query("Who should I see for  heart attack"))  # Should return "Cardiologist"
-print(handle_user_query("what is the treatment for tuberculosis"))  # Should return correct treatment
-
-print(handle_user_query("What is the treatment for tuberculosis?"))  # Should return correct treatment
-print(handle_user_query("What is the treatment for malaria?"))  # Should also work
-print(handle_user_query("What is the treatment for cancer?"))  # Should return something useful
-
-print(handle_user_query("What is the treatment for tuberculosis?"))  # Should return correct treatment
-print(handle_user_query("What is the treatment for malaria?"))  # Should also work
-print(handle_user_query("What is the treatment for cancer?"))  # Should return something useful
-print(handle_user_query("How to treat diabetes?"))  # Should return proper treatment
-print(handle_user_query("Tell me the cure for pneumonia?"))  # Should return treatment
-print(handle_user_query("Treatment for typhoid?"))  # Should extract treatment
-
-print(handle_user_query("What are the symptoms of pneumonia?"))  # Should return correct symptoms
-print(handle_user_query("Signs of heart attack?"))  # Should return expected symptoms
-print(handle_user_query("How do I know if I have typhoid?"))  # Should return typhoid symptoms
-print(handle_user_query("What symptoms should I check for tuberculosis?"))  # Should work
-print(handle_user_query("Symptoms of dengue?"))  # Should return symptoms of dengue
-
-print(handle_user_query("Who should I see for a heart attack?"))  # Should return "Cardiologist"
-print(handle_user_query("Which doctor should I visit for diabetes?"))  # Should return "Endocrinologist"
-print(handle_user_query("Who should I consult for a skin rash?"))  # Should return "Dermatologist"
-print(handle_user_query("What kind of doctor treats pneumonia?"))  # Should return "Pulmonologist"
-print(handle_user_query("Who specializes in treating migraines?"))  # Should return "Neurologist"
-
-print(handle_user_query("Book an appointment for malaria"))  # Should book doctor for malaria
-print(handle_user_query("I need a doctor for high blood pressure"))  # Should book doctor for hypertension
-print(handle_user_query("Schedule a consultation for fever"))  # Should book general physician
-print(handle_user_query("Find a doctor for diabetes treatment"))  # Should book endocrinologist
-print(handle_user_query("Book an appointment for pneumonia treatment"))  # Should book pulmonologist
-
-print(handle_user_query("I have fever, cough, and chills"))  # Should predict disease correctly
-print(handle_user_query("Experiencing blurry vision and excessive thirst"))  # Should return "Diabetes"
-print(handle_user_query("I am experiencing severe chest pain and difficulty breathing"))  # Should return "Heart Attack"
-print(handle_user_query("Feeling tired, cold, and gaining weight"))  # Should return "Hypothyroidism"
-print(handle_user_query("I have rash, joint pain, and headache"))  # Should return "Dengue"
-
-print(handle_user_query("What does a doctor do?"))  # Should return general doctor description
-print(handle_user_query("What are antibiotics?"))  # Should explain antibiotics
-print(handle_user_query("How does the immune system work?"))  # Should explain immunity
-print(handle_user_query("What is the function of the liver?"))  # Should explain liver function
-print(handle_user_query("Explain how blood pressure works?"))  # Should provide useful explanation
-
-
-
-
-# Commented out IPython magic to ensure Python compatibility.
-# %%writefile app.py
-# import streamlit as st
-# import requests
-# 
-# st.set_page_config(page_title="AI Health Assistant", page_icon="🤖")
-# 
-# st.title("🩺 AI Health Assistant")
-# st.write("Ask any medical-related questions:")
-# 
-# # User Input
-# user_input = st.text_input("Your Question:")
-# 
-# # Button to Send Query
-# if st.button("Ask"):
-#     response = requests.post("https://b7da-35-232-247-117.ngrok-free.app/query/", json={"user_input": user_input})
-#     bot_response = response.json().get("response", "Error fetching response")
-# 
-#     st.markdown(f"**🤖 Bot:** {bot_response}")
-#
-
-"""✅ Steps to Deploy on Hugging Face Spaces
-📌 Step 1: Create a Hugging Face Space
-1️⃣ Go to Hugging Face Spaces
-2️⃣ Click "New Space"
-3️⃣ Name the Space (e.g., AI-Health-Assistant)
-4️⃣ Select "Streamlit" as the SDK
-5️⃣ Click "Create Space" ✅
-
-📌 Step 2: Clone the Repository Locally
-After creating the Space, clone it to your local machine or Google Colab:
-
-```bash
-git clone https://huggingface.co/spaces/YOUR_USERNAME/AI-Health-Assistant
-cd AI-Health-Assistant
-```
-Replace YOUR_USERNAME with your Hugging Face username!
-
-📌 Step 3: Add app.py (Your Streamlit Chatbot)
-Inside the cloned folder, create app.py and paste the following:
-
-📌 Step 4: Create requirements.txt
-Create a new file requirements.txt inside the same folder and add:
-```bash
-streamlit
-requests
-```
-
-📌 Step 5: Push Your Code to Hugging Face
-Run these commands to push the code:
-
-```bash
-git add .
-git commit -m "Initial commit"
-git push
-```
-🚀 Your Space will automatically start building!
-"""
-
+        return get_medical_answer(user_query)