Upload 12 files

.env

@@ -0,0 +1,3 @@
+DIABETES_MODEL_URL=https://drive.google.com/uc?export=download&id=14H_wPtW4_W1XPFiiJ3tkmsFFACac_jxS
+SCALER_MODEL_URL=https://drive.google.com/uc?export=download&id=1PnILhtH35yVwG1xfd0bNj7jBquX855bk
+NO_DIABETES_MODEL_URL=https://drive.google.com/uc?export=download&id=1cnjaKDyR7AiCojKsm0rZYtQZSCiJVWW6

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.huggingface.yml

@@ -0,0 +1,2 @@
+sdk: gradio
+app_file: app.py

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Copy dependencies first
+COPY requirements.txt .
+
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy rest of the code
+COPY . .
+
+# Run the app
+CMD ["python", "app.py"]

Procfile

@@ -0,0 +1 @@
+gunicorn -w 4 -k gthread app

README.md

@@ -1,11 +1,11 @@
----
-title: Lolback
-emoji: 🐨
-colorFrom: pink
-colorTo: purple
-sdk: docker
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Lolback
+emoji: 🐨
+colorFrom: pink
+colorTo: purple
+sdk: docker
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,300 @@
+import os
+import requests
+import joblib
+import logging
+import zipfile
+import pandas as pd
+import numpy as np
+import warnings
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+
+# Suppress sklearn warnings
+warnings.filterwarnings('ignore', category=UserWarning, module='sklearn')
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+
+# Get model URLs from environment variables
+DIABETES_MODEL_URL = os.getenv("DIABETES_MODEL_URL")
+SCALER_URL = os.getenv("SCALER_URL")
+MULTI_MODEL_URL = os.getenv("MULTI_MODEL_URL")
+
+# Local paths for downloaded models
+MODEL_PATHS = {
+    "DIABETES_MODEL": "finaliseddiabetes_model.zip",
+    "SCALER": "finalisedscaler.zip",
+    "MULTI_MODEL": "nodiabetes.zip",
+}
+
+# Extracted model names
+EXTRACTED_MODELS = {
+    "DIABETES_MODEL": "finaliseddiabetes_model.joblib",
+    "SCALER": "finalisedscaler.joblib",
+    "MULTI_MODEL": "nodiabetes.joblib",
+}
+
+BASE_DIR = os.getcwd()
+
+# Flask app initialization
+app = Flask(__name__)
+
+# Enable CORS for all routes
+CORS(app, resources={
+    r"/*": {
+        "origins": [
+            "http://localhost:3000",
+            "https://carelog-diabetes-api.onrender.com",
+            "https://carelog-diabetes.vercel.app",
+            "http://localhost:5000"
+        ],
+        "methods": ["GET", "POST", "OPTIONS"],
+        "allow_headers": ["Content-Type", "Authorization"],
+        "supports_credentials": True
+    }
+})
+
+def download_model(url, zip_filename):
+    """Downloads the model zip file from the given URL and saves it locally."""
+    zip_path = os.path.join(BASE_DIR, zip_filename)
+    if not url:
+        logging.error(f"URL for {zip_filename} is missing!")
+        return False
+    try:
+        response = requests.get(url, allow_redirects=True)
+        if response.status_code == 200:
+            with open(zip_path, 'wb') as f:
+                f.write(response.content)
+            logging.info(f"Downloaded {zip_filename} successfully.")
+            return True
+        else:
+            logging.error(f"Failed to download {zip_filename}. HTTP Status: {response.status_code}")
+            return False
+    except Exception as e:
+        logging.error(f"Error downloading {zip_filename}: {e}")
+        return False
+
+def extract_if_needed(zip_filename, extracted_filename):
+    """Extracts model file from zip if not already extracted."""
+    zip_path = os.path.join(BASE_DIR, zip_filename)
+    extracted_path = os.path.join(BASE_DIR, extracted_filename)
+    if os.path.exists(extracted_path):
+        logging.info(f"{extracted_filename} already exists. Skipping extraction.")
+        return True
+    if not os.path.exists(zip_path):
+        logging.error(f"Zip file missing: {zip_path}")
+        return False
+    try:
+        with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+            zip_ref.extractall(BASE_DIR)
+        logging.info(f"Extracted {zip_filename}")
+        return True
+    except Exception as e:
+        logging.error(f"Error extracting {zip_filename}: {e}")
+        return False
+
+def load_model(model_filename):
+    """Loads a model from the given filename."""
+    model_path = os.path.join(BASE_DIR, model_filename)
+    if not os.path.exists(model_path):
+        logging.error(f"Model file not found: {model_path}")
+        return None
+    try:
+        model = joblib.load(model_path)
+        logging.info(f"Loaded {model_filename} successfully.")
+        return model
+    except Exception as e:
+        logging.error(f"Error loading {model_filename}: {e}")
+        return None
+
+def initialize_models():
+    """Handles downloading, extraction, and loading of models."""
+    models = {}
+    for model_key, zip_filename in MODEL_PATHS.items():
+        extracted_filename = EXTRACTED_MODELS[model_key]
+        if not os.path.exists(os.path.join(BASE_DIR, zip_filename)):
+            download_model(globals()[f"{model_key}_URL"], zip_filename)
+        extract_if_needed(zip_filename, extracted_filename)
+        models[model_key] = load_model(extracted_filename)
+    return models
+
+models = initialize_models()
+
+FEATURE_ORDER = [
+    'Pregnancies', 'Glucose', 'BloodPressure', 'Insulin',
+    'BMI', 'DiabetesPedigreeFunction', 'Age'
+]
+
+def validate_input(value, input_type=float, min_value=0, max_value=None):
+    """Enhanced input validation with range checking."""
+    try:
+        value = input_type(value)
+        if value < min_value:
+            return None
+        if max_value is not None and value > max_value:
+            return None
+        return value
+    except (ValueError, TypeError):
+        return None
+
+def validate_blood_pressure(systolic, diastolic):
+    """Validates blood pressure values within realistic ranges."""
+    systolic = validate_input(systolic, float, 0, 300)
+    diastolic = validate_input(diastolic, float, 0, 200)
+    
+    if systolic is None or diastolic is None:
+        return None, None
+    return systolic, diastolic
+
+def validate_gender(gender):
+    """Validates gender input."""
+    if isinstance(gender, str) and gender.lower() in ['male', 'female']:
+        return 1 if gender.lower() == 'male' else 0
+    return None
+
+def calculate_diabetes_pedigree(family_history, first_degree=0, second_degree=0):
+    """Calculates diabetes pedigree function based on family history."""
+    if not family_history:
+        return 0.0
+    genetic_contribution = (first_degree * 0.5) + (second_degree * 0.25)
+    return min(genetic_contribution, 1.0)
+
+def get_multi_condition_predictions(model, df):
+    """Get predictions for multiple health conditions."""
+    try:
+        predictions = model.predict(df)[0]
+        probs_list = model.predict_proba(df)
+        
+        return {
+            'hypertension': bool(predictions[0]),
+            'cardiovascular': float(probs_list[1][0][1]),
+            'stroke': float(probs_list[2][0][1]),
+            'diabetes': float(probs_list[3][0][1])
+        }
+    except Exception as e:
+        logging.error(f"Error in multi-condition prediction: {str(e)}")
+        return None
+
+def get_diabetes_prediction(model, df):
+    """Get diabetes-only prediction."""
+    try:
+        prediction = model.predict(df)[0]
+        probability = float(model.predict_proba(df)[0][1] * 100)
+        return 'Diabetes' if prediction else 'No Diabetes', probability
+    except Exception as e:
+        logging.error(f"Error in diabetes prediction: {str(e)}")
+        return None, 0.0
+
+@app.route('/health', methods=['GET'])
+def health_check():
+    """Health check endpoint."""
+    return jsonify({
+        'status': 'healthy',
+        'message': 'Service is running'
+    })
+
+@app.route('/predict', methods=['POST'])
+def predict_health():
+    """Main prediction endpoint."""
+    try:
+        data = request.get_json()
+        logging.info(f"Received data: {data}")
+        if not data:
+            return jsonify({'status': 'error', 'error': 'Invalid JSON payload'}), 400
+
+        # Validate basic health metrics
+        gender = validate_gender(data.get('gender'))
+        if gender is None:
+            return jsonify({'status': 'error', 'error': 'Invalid gender value. Must be "male" or "female"'}), 400
+
+        systolic, diastolic = validate_blood_pressure(data.get('systolic'), data.get('diastolic'))
+        if systolic is None or diastolic is None:
+            return jsonify({'status': 'error', 'error': 'Invalid blood pressure values'}), 400
+
+        # Validate other common inputs
+        age = validate_input(data.get('age'), float, 0, 120)
+        glucose = validate_input(data.get('glucose'), float, 0, 1000)
+        bmi = validate_input(data.get('bmi'), float, 0, 100)
+
+        if any(v is None for v in [age, glucose, bmi]):
+            return jsonify({'status': 'error', 'error': 'Invalid values for age, glucose, or BMI'}), 400
+
+        # Determine which model to use based on blood pressure
+        use_multi_condition = systolic < 90 or diastolic < 60
+
+        if use_multi_condition:
+            # Multi-condition model input preparation
+            df_multi = pd.DataFrame([{
+                'Age': age,
+                'Gender': gender,
+                'Systolic_bp': systolic,
+                'Diastolic_bp': diastolic,
+                'Glucose': glucose,
+                'BMI': bmi
+            }])
+            
+            results = get_multi_condition_predictions(models['MULTI_MODEL'], df_multi)
+            if results is None:
+                return jsonify({'status': 'error', 'error': 'Error in multi-condition prediction'}), 500
+
+            return jsonify({
+                'status': 'success',
+                'model': 'multi-condition',
+                'predictions': {
+                    'hypertension': results['hypertension'],
+                    'cardiovascular_risk': results['cardiovascular'],
+                    'stroke_risk': results['stroke'],
+                    'diabetes_risk': results['diabetes']
+                }
+            })
+        else:
+            # Diabetes-specific model handling
+            pregnancies = validate_input(data.get('pregnancies', 0 if gender == 1 else None), float, 0, 20)
+            insulin = validate_input(data.get('insulin'), float, 0, 1000)
+            
+            # Family history handling
+            family_history = data.get('family_history', False)
+            first_degree = validate_input(data.get('first_degree_relatives', 0), float, 0, 10)
+            second_degree = validate_input(data.get('second_degree_relatives', 0), float, 0, 20)
+            
+            diabetes_pedigree = calculate_diabetes_pedigree(
+                family_history,
+                first_degree if first_degree is not None else 0,
+                second_degree if second_degree is not None else 0
+            )
+
+            if any(v is None for v in [pregnancies, insulin]):
+                return jsonify({'status': 'error', 'error': 'Invalid values for pregnancies or insulin'}), 400
+
+            df_diabetes = pd.DataFrame([{
+                'Pregnancies': pregnancies,
+                'Glucose': glucose,
+                'BloodPressure': systolic,
+                'Insulin': insulin,
+                'BMI': bmi,
+                'DiabetesPedigreeFunction': diabetes_pedigree,
+                'Age': age
+            }])
+
+            # Ensure correct column order
+            df_diabetes = df_diabetes[FEATURE_ORDER]
+            
+            # Scale the data
+            df_scaled = models['SCALER'].transform(df_diabetes)
+            
+            prediction, probability = get_diabetes_prediction(models['DIABETES_MODEL'], df_scaled)
+            
+            return jsonify({
+                'status': 'success',
+                'model': 'diabetes',
+                'prediction': prediction,
+                'probability': probability,
+                'risk_level': 'HIGH' if probability > 70 else 'MODERATE' if probability > 40 else 'LOW'
+            })
+
+    except Exception as e:
+        logging.error(f"Error: {e}")
+        return jsonify({'status': 'error', 'error': str(e)}), 500
+
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port=7860)

finaliseddiabetes_model.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c17cf84b9c5d2fd57663e1a6344e54aee9a4e513bb80954a3c4ab144d3c0355
+size 283301

finalisedscaler.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26ac692e451befa24ad6e53aa65c95f447e41e6bd5e30aa18fc722989e1ee68
+size 1065

model_loader.py

@@ -0,0 +1,110 @@
+import os
+import requests
+import joblib
+import logging
+import zipfile
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+
+# Get model URLs from environment variables
+DIABETES_MODEL_URL = os.getenv("DIABETES_MODEL_URL")
+SCALER_URL = os.getenv("SCALER_URL")
+MULTI_MODEL_URL = os.getenv("MULTI_MODEL_URL")
+
+# Local paths for downloaded models
+MODEL_PATHS = {
+    "DIABETES_MODEL": "finaliseddiabetes_model.zip",
+    "SCALER": "finalisedscaler.zip",
+    "MULTI_MODEL": "nodiabetes.zip",
+}
+
+# Extracted model names
+EXTRACTED_MODELS = {
+    "DIABETES_MODEL": "finaliseddiabetes_model.joblib",
+    "SCALER": "finalisedscaler.joblib",
+    "MULTI_MODEL": "nodiabetes.joblib",
+}
+
+BASE_DIR = os.getcwd()  # Get current working directory
+
+def download_model(url, zip_filename):
+    """Downloads the model zip file from the given URL and saves it locally."""
+    zip_path = os.path.join(BASE_DIR, zip_filename)
+    if not url:
+        logging.error(f"URL for {zip_filename} is missing!")
+        return False
+
+    try:
+        response = requests.get(url, allow_redirects=True)
+        if response.status_code == 200:
+            with open(zip_path, 'wb') as f:
+                f.write(response.content)
+            logging.info(f"Downloaded {zip_filename} successfully.")
+            return True
+        else:
+            logging.error(f"Failed to download {zip_filename}. HTTP Status: {response.status_code}")
+            return False
+    except Exception as e:
+        logging.error(f"Error downloading {zip_filename}: {e}")
+        return False
+
+def extract_if_needed(zip_filename, extracted_filename):
+    """Extracts model file from zip if not already extracted."""
+    zip_path = os.path.join(BASE_DIR, zip_filename)
+    extracted_path = os.path.join(BASE_DIR, extracted_filename)
+
+    if os.path.exists(extracted_path):
+        logging.info(f"{extracted_filename} already exists. Skipping extraction.")
+        return True
+
+    if not os.path.exists(zip_path):
+        logging.error(f"Zip file missing: {zip_path}")
+        return False
+
+    try:
+        with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+            zip_ref.extractall(BASE_DIR)
+            extracted_files = zip_ref.namelist()
+        logging.info(f"Extracted {zip_filename}, contents: {extracted_files}")
+        return True
+    except Exception as e:
+        logging.error(f"Error extracting {zip_filename}: {e}")
+        return False
+
+def load_model(model_filename):
+    """Loads a model from the given filename."""
+    model_path = os.path.join(BASE_DIR, model_filename)
+    if not os.path.exists(model_path):
+        logging.error(f"Model file not found: {model_path}")
+        return None
+
+    try:
+        model = joblib.load(model_path)
+        logging.info(f"Loaded {model_filename} successfully.")
+        return model
+    except Exception as e:
+        logging.error(f"Error loading {model_filename}: {e}")
+        return None
+
+# **Main Execution**
+for model_key, zip_filename in MODEL_PATHS.items():
+    extracted_filename = EXTRACTED_MODELS[model_key]
+
+    # Step 1: Download model if not present
+    if not os.path.exists(os.path.join(BASE_DIR, zip_filename)):
+        download_model(globals()[f"{model_key}_URL"], zip_filename)
+
+    # Step 2: Extract model file
+    extract_if_needed(zip_filename, extracted_filename)
+
+# Step 3: Load models
+diabetes_model = load_model(EXTRACTED_MODELS["DIABETES_MODEL"])
+scaler = load_model(EXTRACTED_MODELS["SCALER"])
+multi_model = load_model(EXTRACTED_MODELS["MULTI_MODEL"])
+
+# Final check
+if diabetes_model and scaler and multi_model:
+    logging.info("All models loaded successfully! ✅")
+else:
+    logging.error("Some models failed to load. ❌ Check logs for details.")

nodiabetes.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ae3b2c7b5d0bb6172bf0513d5cd187bfd289b457034d0f368a9bd039d2b044
+size 6388514

requirements.txt

@@ -0,0 +1,46 @@
+# Web Framework and WSGI
+Flask==3.0.3
+Flask-Cors==4.0.1
+gunicorn==21.2.0
+Werkzeug==3.0.1
+
+# Machine Learning and Data Processing
+scikit-learn==1.3.0
+pandas==2.2.2
+numpy==1.26.4
+joblib==1.4.2
+waitress==3.0.2
+# Error Handling and Validation
+marshmallow==3.20.2  # For request/response validation
+pydantic==2.6.1     # For data validation
+
+# Security
+python-dotenv==1.0.0
+PyJWT==2.8.0        # For JWT handling if you add authentication
+bcrypt==4.1.2       # For password hashing if needed
+
+# Monitoring and Logging
+prometheus-flask-exporter==0.23.0  # For metrics and monitoring
+python-json-logger==2.0.7          # For structured JSON logging
+sentry-sdk[flask]==1.40.4          # For error tracking
+
+# HTTP and Networking
+requests==2.32.3
+urllib3==2.2.0      # Required by requests
+certifi==2024.2.2   # For SSL certificate verification
+
+# Performance and Caching
+cachetools==5.3.2   # For in-memory caching
+redis==5.0.1        # For distributed caching if needed
+
+# Development and Testing
+pytest==8.0.0       # For unit testing
+pytest-cov==4.1.0   # For test coverage
+black==24.1.1       # For code formatting
+flake8==7.0.0       # For code linting
+
+# Time zone handling
+pytz==2024.1        # For proper timezone handling
+
+# Compression and Performance
+brotli==1.1.0       # For response compression