Download app.py from leo861/heal: direct link, hf CLI and curl.
- Browser
- Download file 3.57 kB
-
https://huggingface.co/leo861/heal/resolve/main/app.py
- Command line
-
hf download hf://leo861/heal/app.py
-
curl -L -o app.py https://huggingface.co/leo861/heal/resolve/main/app.py
3.57 kB
| import os | |
| import logging | |
| from fastapi import FastAPI, HTTPException | |
| from fastapi.middleware.cors import CORSMiddleware | |
| import joblib | |
| import torch | |
| import numpy as np | |
| from huggingface_hub import hf_hub_download | |
| from pydantic import BaseModel | |
| import uvicorn | |
| # Configure logging | |
| logging.basicConfig(level=logging.INFO) | |
| logger = logging.getLogger(__name__) | |
| app = FastAPI(title="Health Monitoring System", | |
| description="A FastAPI application for health monitoring and prediction", | |
| version="1.0.0") | |
| # Add CORS middleware | |
| app.add_middleware( | |
| CORSMiddleware, | |
| allow_origins=["*"], | |
| allow_credentials=True, | |
| allow_methods=["*"], | |
| allow_headers=["*"], | |
| ) | |
| # Load models | |
| def load_models(): | |
| global heart_model, autoencoder | |
| heart_model = None | |
| autoencoder = None | |
| try: | |
| # Download and load heart model | |
| logger.info("Downloading heart model from Hugging Face Hub...") | |
| heart_model_path = hf_hub_download( | |
| repo_id="leo861/app", | |
| filename="heart/models/heart_model.joblib", | |
| cache_dir="models" | |
| ) | |
| heart_model = joblib.load(heart_model_path) | |
| logger.info("Heart model loaded successfully") | |
| except Exception as e: | |
| logger.error(f"Failed to load heart model: {str(e)}") | |
| try: | |
| # Download and load autoencoder | |
| logger.info("Downloading autoencoder from Hugging Face Hub...") | |
| autoencoder_path = hf_hub_download( | |
| repo_id="leo861/app", | |
| filename="models/best_model.pth", | |
| cache_dir="models" | |
| ) | |
| autoencoder = torch.load(autoencoder_path) | |
| autoencoder.eval() | |
| logger.info("Autoencoder model loaded successfully") | |
| except Exception as e: | |
| logger.error(f"Failed to load autoencoder: {str(e)}") | |
| # Load models on startup | |
| async def startup_event(): | |
| logger.info("Loading trained models...") | |
| try: | |
| load_models() | |
| except Exception as e: | |
| logger.error(f"Error loading models: {str(e)}") | |
| # Define request models | |
| class PredictionRequest(BaseModel): | |
| data: dict | |
| # Define response models | |
| class HealthResponse(BaseModel): | |
| status: str | |
| models: dict | |
| class PredictionResponse(BaseModel): | |
| status: str | |
| prediction: str | |
| message: str = None | |
| async def root(): | |
| return {"message": "Welcome to the Health Monitoring System API"} | |
| async def health(): | |
| return { | |
| "status": "healthy", | |
| "models": { | |
| "heart_model": heart_model is not None, | |
| "autoencoder": autoencoder is not None | |
| } | |
| } | |
| async def predict(request: PredictionRequest): | |
| try: | |
| if not request.data: | |
| raise HTTPException(status_code=400, detail="No data provided") | |
| # Add your prediction logic here | |
| logger.info("Processing prediction request") | |
| result = { | |
| "status": "success", | |
| "prediction": "normal", | |
| "message": "Prediction completed successfully" | |
| } | |
| logger.info(f"Prediction completed: {result}") | |
| return result | |
| except Exception as e: | |
| logger.error(f"Error during prediction: {str(e)}") | |
| raise HTTPException(status_code=500, detail=str(e)) | |
| if __name__ == "__main__": | |
| uvicorn.run(app, host="0.0.0.0", port=7860) |