| |
| """ |
| Verify the nesting guarantee of the training fraction files: every smaller fraction must be a |
| subset of every larger one, for every fold. |
| |
| python tools/check_split_fractions.py [--split-root <folder>] [--folds 5] |
| |
| The split root comes from the site config when it is not given (see config.example.yaml). |
| """ |
|
|
| import argparse |
| import sys |
| from pathlib import Path |
|
|
| import pandas as pd |
|
|
| from auto_detect_breast_mri.config import column, resolve_path |
|
|
|
|
| def fraction_of(filename: str) -> float: |
| """0.05 from '..._frac0.05.csv'.""" |
| return float(filename.split("_frac")[-1].rsplit(".csv", 1)[0]) |
|
|
|
|
| def check_fold(fold_dir: Path, id_column: str, expected_files: int) -> bool: |
| """True if every fraction file in fold_dir is nested in all larger ones.""" |
| fraction_files = sorted(fold_dir.glob("*_frac0.*.csv"), key=lambda path: fraction_of(path.name)) |
| if len(fraction_files) != expected_files: |
| print(f"WARNING: {fold_dir.name}: expected {expected_files} fraction files, " |
| f"found {len(fraction_files)}: {[path.name for path in fraction_files]}", file=sys.stderr) |
| ids = {fraction_of(path.name): set(pd.read_csv(path)[id_column]) for path in fraction_files} |
|
|
| ok = True |
| for child, child_ids in sorted(ids.items()): |
| for parent, parent_ids in sorted(ids.items()): |
| if parent <= child: |
| |
| continue |
| missing = child_ids - parent_ids |
| if missing: |
| ok = False |
| print(f"ERROR: {fold_dir.name}: fraction {child} is NOT contained in {parent}: " |
| f"{len(missing)} entries missing from the parent.", file=sys.stderr) |
| else: |
| print(f" {fold_dir.name}: fraction {child} is fully covered by {parent}.") |
| return ok |
|
|
|
|
| def main() -> None: |
| parser = argparse.ArgumentParser(description=__doc__, |
| formatter_class=argparse.RawDescriptionHelpFormatter) |
| parser.add_argument("--split-root", default=None, |
| help="folder holding fold<k>/. Config key: split_root") |
| parser.add_argument("--folds", type=int, default=5, help="number of folds to check. Default: 5") |
| parser.add_argument("--expected-files", type=int, default=4, |
| help="fraction files expected per fold. Default: 4") |
| args = parser.parse_args() |
|
|
| split_root = Path(resolve_path(args.split_root, "split_root", "folder with the split files")) |
| if not split_root.exists(): |
| sys.exit(f"ERROR: directory {split_root} does not exist.") |
|
|
| id_column = column("examination_id") |
| all_ok = True |
| for fold in range(args.folds): |
| fold_dir = split_root / f"fold{fold}" |
| if not fold_dir.exists(): |
| print(f"WARNING: {fold_dir} does not exist, skipping.", file=sys.stderr) |
| continue |
| print(f"Investigating {fold_dir}") |
| all_ok &= check_fold(fold_dir, id_column, args.expected_files) |
|
|
| print("OK: all fractions are nested." if all_ok else "FAIL: nesting is violated, see above.") |
| sys.exit(0 if all_ok else 1) |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
