code/data_preparing/src/preprocess.py

"""Run satellite/radar and L2 preprocessing from one configuration."""

from __future__ import annotations

import argparse
import json
import subprocess
import sys
from pathlib import Path

from src.config import load_config


def main(argv: list[str] | None = None) -> None:
    parser = argparse.ArgumentParser(description="Preprocess one or more days of satellite, radar, and L2 data.")
    parser.add_argument("--config", required=True, help="YAML configuration path")
    parser.add_argument("--device", default=None, help="Accepted for a common CLI; preprocessing runs on CPU")
    parser.add_argument("--output-dir", default=None, help="Override the configured output directory")
    args = parser.parse_args(argv)

    config = load_config(args.config)
    config.pop("_config_path", None)
    if args.output_dir:
        config["save_dir"] = str(Path(args.output_dir).resolve())
    output_dir = Path(config["save_dir"])
    output_dir.mkdir(parents=True, exist_ok=True)
    runtime_config = output_dir / "preprocess_runtime.json"
    with runtime_config.open("w", encoding="utf-8") as stream:
        json.dump(config, stream, indent=2, ensure_ascii=False)

    try:
        for module in ("src.satellite_radar", "src.l2"):
            subprocess.run([sys.executable, "-m", module, "--config", str(runtime_config)], check=True)
    finally:
        runtime_config.unlink(missing_ok=True)


if __name__ == "__main__":
    main()