grabowski
5c4f464383
CI / Test suite (push) Successful in 1m2s
CI / Format & lint (push) Successful in 22s
Rust / fmt, clippy, test, build (push) Successful in 9m53s
Security / Dependency vulnerabilities (push) Successful in 1m52s
Security / Static analysis (push) Successful in 20s
Security / License report (push) Successful in 1m41s
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.
107 lines
3.2 KiB
Rust
107 lines
3.2 KiB
Rust
//! Constants shared with Python, generated from it: `flood_config.json` is
|
|
//! written by `uv run python -m src.ml.export --config`, and
|
|
//! tests/test_model_export.py fails while it differs from the Python source.
|
|
|
|
use serde::Deserialize;
|
|
use std::collections::BTreeMap;
|
|
use std::sync::OnceLock;
|
|
|
|
#[derive(Debug, Deserialize)]
|
|
pub struct Stage {
|
|
pub stage: u32,
|
|
pub level: f64,
|
|
pub discharge_cms: f64,
|
|
}
|
|
|
|
#[derive(Debug, Deserialize)]
|
|
pub struct DamConfig {
|
|
pub dam_id: String,
|
|
pub report_hour: u32,
|
|
pub ffill_limit_h: usize,
|
|
pub serving_days: i64,
|
|
}
|
|
|
|
#[derive(Debug, Deserialize)]
|
|
pub struct NotifyConfig {
|
|
pub clear_margin_m: f64,
|
|
pub capacity_guard_min_pct: f64,
|
|
pub capacity_guard_exempt: Vec<String>,
|
|
pub outlook_on: f64,
|
|
pub outlook_off: f64,
|
|
pub outlook_horizon: u32,
|
|
pub feed_stale_after_h: f64,
|
|
pub station_names: BTreeMap<String, String>,
|
|
}
|
|
|
|
#[derive(Debug, Deserialize)]
|
|
pub struct FloodConfig {
|
|
thresholds: BTreeMap<String, (f64, f64)>,
|
|
pub flood_stages: BTreeMap<String, Vec<Stage>>,
|
|
upstream_leads: BTreeMap<String, Vec<(String, i64)>>,
|
|
pub dam_stations: Vec<String>,
|
|
pub monsoon_months: Vec<u32>,
|
|
pub ffill_limit_h: usize,
|
|
pub basin_anchor: String,
|
|
pub forward_rain_h: usize,
|
|
pub horizons: Vec<u32>,
|
|
pub stale_after_h: f64,
|
|
pub heuristic_sigma: f64,
|
|
pub heuristic_version: String,
|
|
pub latest_window_h: i64,
|
|
pub hii_fill_stations: Vec<String>,
|
|
pub hii_exact_mirrors: Vec<String>,
|
|
pub hii_min_overlap_hours: usize,
|
|
pub dam: DamConfig,
|
|
pub notify: NotifyConfig,
|
|
}
|
|
|
|
impl FloodConfig {
|
|
/// (warning, danger) for a station, or the "*" default.
|
|
pub fn thresholds(&self, station: &str) -> (f64, f64) {
|
|
self.thresholds
|
|
.get(station)
|
|
.or_else(|| self.thresholds.get("*"))
|
|
.copied()
|
|
.unwrap_or((f64::INFINITY, f64::INFINITY))
|
|
}
|
|
|
|
/// (upstream station, lead hours) pairs, in Python's order.
|
|
pub fn upstream_leads(&self, station: &str) -> &[(String, i64)] {
|
|
self.upstream_leads.get(station).map_or(&[], Vec::as_slice)
|
|
}
|
|
|
|
/// The stations the models are built for (Python's `UPSTREAM_LEADS` keys).
|
|
pub fn forecast_stations(&self) -> impl Iterator<Item = &str> {
|
|
self.upstream_leads.keys().map(String::as_str)
|
|
}
|
|
|
|
pub fn is_dam_station(&self, station: &str) -> bool {
|
|
self.dam_stations.iter().any(|s| s == station)
|
|
}
|
|
}
|
|
|
|
pub fn config() -> &'static FloodConfig {
|
|
static CONFIG: OnceLock<FloodConfig> = OnceLock::new();
|
|
CONFIG.get_or_init(|| {
|
|
serde_json::from_str(include_str!("../flood_config.json"))
|
|
.expect("flood_config.json is generated by src/ml/export.py and must parse")
|
|
})
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::*;
|
|
|
|
#[test]
|
|
fn generated_config_parses_and_has_the_basin() {
|
|
let c = config();
|
|
assert_eq!(c.thresholds("P.1"), (3.7, 4.2));
|
|
assert_eq!(c.thresholds("P.999"), (3.0, 4.5));
|
|
assert_eq!(c.upstream_leads("P.1")[0], ("P.103".to_string(), 1));
|
|
assert!(c.upstream_leads("P.82").is_empty());
|
|
assert_eq!(c.forecast_stations().count(), 16);
|
|
assert_eq!(c.horizons, vec![6, 12, 24]);
|
|
assert!(c.is_dam_station("P.1") && !c.is_dam_station("P.20"));
|
|
}
|
|
}
|