Real Estate Price Predictor
Full-stack ML web application · Python / FastAPI backend · React 18 / Vite frontend · scikit-learn GradientBoostingRegressor
Full-stack ML web app where a React SPA issues debounced POST requests to a FastAPI service, which loads a joblib-serialized scikit-learn GradientBoostingRegressor pipeline to predict property prices with ±15% confidence intervals. The model is trained offline by train.py and deployed as model.pkl.
Generated 4 Jun 2026 · 15 files · 11 components · 5 flows
File Architecture
The full source tree as a layered graph — every file with its role, imports, exports and reverse dependencies.
System Design
Runtime topology across the five zones — client, edge, application, data and external services.
Flow Graph
The five most significant application flows, step by step — startup, auth, write, read and error recovery.
Technology
| Component | Technology | Version | Source of Detection |
|---|---|---|---|
| API framework | FastAPI | >=0.100.0 | backend/requirements.txt |
| ASGI server | uvicorn | >=0.27.0 | requirements.txt; main.py uvicorn.run |
| Validation | pydantic | >=2.0.0 | requirements.txt; main.py BaseModel |
| ML library | scikit-learn | >=1.3.0 | requirements.txt; train.py imports |
| Dataframe | pandas | >=2.0.0 | requirements.txt; main.py / train.py |
| Numerics | numpy | *[unresolved]* | imported in main.py / train.py (transitive) |
| Serialization | joblib | >=1.3.0 | requirements.txt; joblib.load/dump |
| Form parsing | python-multipart | >=0.0.6 | backend/requirements.txt |
| UI framework | React | ^18.2.0 | frontend/package.json |
| Bundler / dev server | Vite | ^5.0.8 | package.json; vite.config.js |
| React plugin | @vitejs/plugin-react | ^4.2.1 | package.json; vite.config.js |
| CSS framework | Tailwind CSS | ^3.4.0 | package.json; tailwind.config.js |
| CSS tooling | PostCSS + autoprefixer | ^8.4.32 / ^10.4.16 | package.json; postcss.config.js |
| ML estimator | GradientBoostingRegressor | n_estimators=200 | train.py; main.py /stats |