File size: 1,607 Bytes
04ae9bb | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | """Data inspection without importing torch."""
from __future__ import annotations
from pathlib import Path
from typing import Any, Dict
from .data.clinical import build_all_data
from .data.splits import fold_summary, make_folds
from .utils import ensure_dir, save_json
def inspect_data(cfg: Dict[str, Any]) -> Dict[str, Any]:
bundle = build_all_data(cfg)
folds = make_folds(bundle.patients, cfg["cv"])
out = {
"n_patients": int(len(bundle.patients)),
"n_train_patients": int((bundle.patients["is_supplemental"] == 0).sum()),
"n_samples_all": int(len(bundle.samples_all)),
"n_samples_eval": int(len(bundle.samples_eval)),
"n_features": int(len(bundle.feature_names)),
"feature_names": list(bundle.feature_names),
"target_cols": list(bundle.target_cols),
"masks": {c: int(bundle.samples_eval[c].sum()) for c in bundle.mask_cols},
"cohorts": bundle.patients["cohort"].value_counts().to_dict(),
"fold_summary": fold_summary(folds).to_dict(orient="records"),
}
out_dir = ensure_dir(Path(cfg["experiment"].get("output_dir", "runs")) / cfg["experiment"].get("name", "ampd_exp") / "inspect")
save_json(out, out_dir / "data_summary.json")
print(f"patients: {out['n_patients']} (train {out['n_train_patients']})")
print(f"samples: all {out['n_samples_all']} | eval {out['n_samples_eval']}")
print(f"features: {out['n_features']}")
print(f"cohorts: {out['cohorts']}")
print(f"masks: {out['masks']}")
print(f"fold summary:\n{fold_summary(folds).to_string(index=False)}")
return out
|