feat: RID large-dam daily collector — Mae Ngat storage/inflow/outflow

POST app.rid.go.th/reservoir/api/dams (open, archive >=2009) collected hourly into rid_dams + rid_reservoir_daily; backfill script fetches only missing days so reruns repair holes and are safe alongside the live collector. /api/stats counts the new table via an engine fallback that works when HII collection is disabled. Mae Ngat (DAM_ID 200103) hit 113% usable capacity with ~19 MCM/day inflow in the Oct 2024 flood — candidate features for the next retrain.
2026-08-13 10:29:34 +07:00
parent 811af1625b
commit 6eafb353b1
7 changed files with 712 additions and 19 deletions
@@ -0,0 +1,69 @@
+#!/usr/bin/env python3
+"""Backfill rid_reservoir_daily with RID large-dam history (Mae Ngat et al.).
+
+One request per day against app.rid.go.th/reservoir/api/dams (archive reaches
+back to at least 2009). Days already stored are skipped, so reruns only fetch
+what is missing — safe alongside the hourly live collector, and a rerun
+repairs holes left by transient failures.
+
+Usage:
+    uv run scripts/backfill_rid_reservoir.py                    # missing days since 2018-08-01
+    uv run scripts/backfill_rid_reservoir.py --start 2015-01-01
+    uv run scripts/backfill_rid_reservoir.py --db-url postgresql://...
+"""
+
+import argparse
+import datetime
+import logging
+import os
+import sys
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
+
+from src.config import Config
+from src.rid_reservoir import RidReservoirStore, backfill
+
+DEFAULT_START = datetime.date(2018, 8, 1)  # start of the water_measurements grid
+
+
+def main(argv=None) -> int:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument(
+        "--start", type=datetime.date.fromisoformat, default=DEFAULT_START
+    )
+    parser.add_argument("--end", type=datetime.date.fromisoformat, default=None)
+    parser.add_argument("--db-url", default=None)
+    parser.add_argument("--throttle", type=float, default=0.4)
+    args = parser.parse_args(argv)
+
+    logging.basicConfig(
+        level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s"
+    )
+    if args.db_url:
+        # postgresql+psycopg2://... -> postgresql (driver suffix is not a dialect)
+        connection_string = args.db_url
+        db_type = args.db_url.split(":", 1)[0].split("+", 1)[0]
+    else:
+        cfg = Config.get_database_config()
+        if cfg["type"] not in ("sqlite", "postgresql", "mysql"):
+            print(f"requires a SQL database, got {cfg['type']}", file=sys.stderr)
+            return 1
+        connection_string, db_type = cfg["connection_string"], cfg["type"]
+
+    store = RidReservoirStore(connection_string, db_type)
+    if not store.connect():
+        print(
+            "database connection failed — check the connection string",
+            file=sys.stderr,
+        )
+        return 1
+    end = args.end or datetime.date.today()
+    span_days = (end - args.start).days + 1
+    missing = span_days - len(store.present_dates(args.start, end))
+    saved = backfill(store, args.start, end, throttle_seconds=args.throttle)
+    print(f"backfilled {saved} dam-day rows ({missing} days were missing)")
+    return 0 if saved or missing == 0 else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())