Add src/ml/ package predicting, per station and per 6/12/24 h horizon,
the probability of exceeding warning (3.0 m) and danger (4.5 m) levels
plus expected peak level, trained on the 592k-row PostgreSQL history:
- features.py: hourly grid with coverage gating and no future leakage;
upstream stations enter at empirically measured travel-time lags
(P.20 +17h ... P.103 +1h vs P.1); hour-of-day deliberately excluded
(it encodes the scrape schedule, not hydrology)
- train.py: HistGradientBoosting regression + warn/danger classifier
heads per station x horizon, >=30-positives gate with calibrated
sigmoid-on-regression fallback, strict temporal splits, per-event
lead-time evaluation; guards against sklearn 1.9.0 crash on
degenerate feature columns
- predict.py: bundle loading with feature-name checks, heuristic
fallback tier, get_latest_forecasts() for the API; raises when no
models are trained so the endpoint 503s instead of serving
persistence output as forecasts
- data.py: Postgres-first loader (FLOOD_ML_DB_URL override), HTTP API
fallback (flagged: that path backfills synthetic discharge), csv.gz
cache
- /forecast endpoint (15-min TTL cache) + dashboard flood-risk panel
(hidden until models exist)
- docs/FLOOD_FORECASTING.md: full system doc with measured deployment
numbers (~335 MB RSS, CPU negligible, ~6 min full retrain) and
retraining policy
Validation: out-of-sample backtest of the record 2024 flood season
(train <= Aug 2024) alerted 24-48 h ahead of the Oct 5 peak; 2025-26
test split: P.1 6h PR-AUC 0.974, recall 98.3% at 1% false-alarm rate.
Also: fix P.81 station coordinates (was Ban Pong/Ratchaburi, 493 km
out of basin; now 18.6936 N 99.0819 E per RID station page), pin
scikit-learn==1.9.0 and numpy<2, gitignore model artifacts (~100 MB,
train on the server via scripts/train_flood_model.py).
Station CRUD via the API previously mutated the scraper's in-memory
station_mapping only, so changes were lost on restart (and the systemd
service auto-restarts).
- Extract the 130-line hardcoded station_mapping into bundled defaults at
src/data/stations.json; the scraper loads from a runtime-writable config
file (STATION_CONFIG_PATH, default stations.json) and falls back to the
bundled defaults to seed it.
- Add scraper.save_stations() with an atomic temp-file + os.replace write.
- create/update/delete station endpoints now persist and roll back the
in-memory change if the write fails; re-raise HTTPException so persistence
errors surface as real 500s instead of being swallowed.
- Backend-agnostic (works for the VictoriaMetrics deployment, which has no
relational stations table). Runtime stations.json is gitignored.
Also clears pre-existing flake8 debt in water_scraper_v3.py (unused imports,
long lines, duplicate logging import) and dedupes the User-Agent to
Config.USER_AGENT.
Features:
- Real-time water level monitoring for Ping River Basin (16 stations)
- Coverage from Chiang Dao to Nakhon Sawan in Northern Thailand
- FastAPI web interface with interactive dashboard and station management
- Multi-database support (SQLite, MySQL, PostgreSQL, InfluxDB, VictoriaMetrics)
- Comprehensive monitoring with health checks and metrics collection
- Docker deployment with Grafana integration
- Production-ready architecture with enterprise-grade observability
CI/CD & Automation:
- Complete Gitea Actions workflows for CI/CD, security, and releases
- Multi-Python version testing (3.9-3.12)
- Multi-architecture Docker builds (amd64, arm64)
- Daily security scanning and dependency monitoring
- Automated documentation generation
- Performance testing and validation
Production Ready:
- Type safety with Pydantic models and comprehensive type hints
- Data validation layer with range checking and error handling
- Rate limiting and request tracking for API protection
- Enhanced logging with rotation, colors, and performance metrics
- Station management API for dynamic CRUD operations
- Comprehensive documentation and deployment guides
Technical Stack:
- Python 3.9+ with FastAPI and Pydantic
- Multi-database architecture with adapter pattern
- Docker containerization with multi-stage builds
- Grafana dashboards for visualization
- Gitea Actions for CI/CD automation
- Enterprise monitoring and alerting
Ready for deployment to B4L infrastructure!
grabowski