3 Commits

Include renames

Author	SHA1	Message	Date
grabowski	0e30ddbcb6	fix(notify): no "gauge feed stale" for RID's nightly pause on a quiet river ... ping-status sent "gauge feed stale" around midnight and "feed recovered" around 07:00 on each of the last three nights (ntfy and, since phase 3, the Matrix room). RID publishes no hourly report overnight: the 21:00 reading is the last until the 22:00..06:00 hours arrive together (06:35, 06:55, 07:22 on 2026-10-17/18/19). The ThaiWater overlay was meant to bridge that, but ThaiWater's copies of the RID gauges come from the same feed with the same delay (P.1's mirror still has no value for 22:00-00:00 this morning), so it does not. Between 21:00 and FEED_NIGHT_UNTIL_HOUR (default 9, 0 = off) the feed of a quiet river is no longer reported stale; one still without new readings at 09:00 is. While a station is at warning/danger or the P.1 outlook is on, the 3 h rule holds all night. A feed already stale stays stale through the night (no false "recovered"), and a real recovery is announced at any hour. The replay of the Python notifier runs with the window off. Docs no longer claim that ThaiWater keeps the feed current at night.	2026-10-19 09:35:10 +07:00
grabowski	6ae67dec63	feat(collector): forecast and ntfy in ping-collector; ThaiWater keeps alerts current at night ... Phase 2b/2c of docs/RUST_REWRITE.md. With FORECAST_IN_COLLECTOR=true (shared .env) ping-collector, after each cycle that brought newer RID or HII readings and at least hourly: loads the last 336 h (RID + HII mirror fill), fetches the rain forecast, runs every exported model (rust/forecast), stores forecast_history and forecast_current, and sends the ntfy notifications. The Python API then serves forecast_current as /forecast (computing in-process only when it is older than FORECAST_MAX_AGE_SECONDS) and neither forecasts nor notifies. ntfy (collector/src/notify.rs): a port of src/notify.py with the same topics, texts, hysteresis, capacity guard and notification_state keys, checked word for word on 751 messages generated by Python (testdata/gen_notify_cases.py). The change: for stations whose ThaiWater twin is the same sensor, a reading newer than RID's drives the level alerts (marked as ThaiWater telemetry), and the feed counts as stale only when neither source has a reading for 3 h. RID alone lagging is reported once after RID_STALE_ALERT_HOURS (18). This ends the nightly "gauge feed stale" / "recovered" pairs caused by RID's late reports. Commands: `forecast [--json] [--save] [--now] [--rain-file]`, `notify --dry-run`. scripts/forecast_parity.py compares Python and the collector on the live database (same moment, same rain); locally 48/48 rows identical. install_collector.sh: models export + that check on every install, --cutover-forecast (refuses on a failed check) and --rollback-forecast. Trees are packed into 24-byte nodes: 70 MB peak with all 15 models (was 140). Forecast values are written to NUMERIC as shortest round-trip text, so they round as psycopg2's do. DB test schemas get a counter (parallel tests collided on Windows' coarse clock).	2026-10-18 14:43:39 +07:00
grabowski	5c4f464383	feat(forecast): Rust forecast crate, bit-for-bit with the Python serving path ... Phase 2a of docs/RUST_REWRITE.md. rust/forecast (ping-forecast) ports the serving half of src/ml: the HII mirror gap fill, the hourly grid, every feature (pandas' Kahan rolling sums included), the Mae Ngat dam frame, HistGradientBoosting tree inference, the heuristic fallback, stale-threshold handling and the P.1 flood-stage probabilities. Hand-over from Python (src/ml/export.py): - models/flood_<station>.json.gz next to each joblib bundle; train_all() writes it, retrain.sh promotes it, `python -m src.ml.export` exports existing ones. - rust/forecast/flood_config.json: thresholds, stages, leads and notify constants, compiled in. tests/test_model_export.py fails while it differs from the Python source. Parity (rust/forecast/tests/parity.rs, fixtures from testdata/gen_forecast_fixtures.py on the production code path): four scenarios incl. the 2024 flood with RID lagging behind HII. Merged readings, all features and all levels identical; with all 15 local models 377/384 probabilities bit-identical, the rest within 2 ulp (exp). Python refactor without behaviour change: predict.forecasts_from_long, and get_latest_forecasts/load_latest/serving_frame take now/rain for reproducible comparisons; the HII query orders its rows.	2026-10-18 14:21:56 +07:00