Files
grabowski 6eafb353b1 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

49 lines
1.5 KiB
Python

#!/usr/bin/env python3
"""Backfill the openmeteo_rain table with the full 2021+ catchment history.
Usage:
uv run scripts/backfill_rain_db.py # DB from Config/.env
uv run scripts/backfill_rain_db.py --db-url postgresql://...
"""
import argparse
import logging
import os
import sys
sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
from src.config import Config
from src.ml.rain import backfill_db
def main(argv=None) -> int:
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--db-url", default=None)
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"]
from sqlalchemy import create_engine
engine = create_engine(connection_string, pool_pre_ping=True)
saved = backfill_db(engine, db_type)
print(f"backfilled {saved} hourly rows into openmeteo_rain")
return 0 if saved else 1
if __name__ == "__main__":
sys.exit(main())