scripts/report_dataset.py

#!/usr/bin/env python
from __future__ import annotations

import argparse
import sys
from pathlib import Path

PROJECT_ROOT = Path(__file__).resolve().parents[1]
if str(PROJECT_ROOT) not in sys.path:
    sys.path.insert(0, str(PROJECT_ROOT))

from dovla_cil.experiments.reports import generate_dataset_report  # noqa: E402


def main(argv: list[str] | None = None) -> int:
    parser = argparse.ArgumentParser(description="Create analysis reports for a CIL dataset.")
    parser.add_argument("--dataset", type=Path, required=True, help="CIL dataset directory.")
    parser.add_argument("--out", type=Path, required=True, help="Report output directory.")
    parser.add_argument("--sample-groups", type=int, default=3)
    parser.add_argument("--seed", type=int, default=0)
    args = parser.parse_args(argv)

    summary = generate_dataset_report(
        args.dataset,
        args.out,
        sample_groups=args.sample_groups,
        seed=args.seed,
    )
    print(f"report: {args.out}")
    print(f"num records: {summary['num_records']}")
    print(f"num groups: {summary['num_groups']}")
    print(f"success rate: {summary['success_rate']:.3f}")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())