How itsharshvb/health_impact_project works
Project type and purpose
• This is a backend‐only, data‐driven microservice that scrapes air‐quality data, stores it in a local database, and exposes an API for predicting health impacts using a trained ML model.
• The README confirms it’s an “air pollutant health impact” project using machine learning.
File structure
• Top-level directories:
• backend/: all application code
• backend/data & data_files/: raw and derived data files (city lists, SQLite DB)
• backend/models/: serialized ML model & scaler
• backend/scrape_mod/: standalone scraper scripts & config
• backend/src/: core application
• Inside backend/src:
• api/routes.py – HTTP endpoints (likely FastAPI)
• core/ – configuration loader, logging setup, city‐loader utility
• db/ – ORM models and session management (SQLite)
• schemas/ – Pydantic schemas for request/response validation
• services/ – business logic (air‐quality fetcher, scraper orchestrator, health‐impact predictor)
• utils/ – supportive modules (city mapping)
• Supporting files:
• requirements.txt – Python dependencies
• backend_setup_guide.md – deployment instructions
Extract insights from the README
• Single responsibility: ingest data, store it, serve predictions.
• Stacks: Python, FastAPI (implied by route structure), SQLite, Keras (model), Pandas/CSV for scrapers.
Detailed capture of essential elements
• Environment variables or config file (core/config.py) flowing into components