"""Patient-level and cohort-held-out splits.""" from __future__ import annotations from pathlib import Path from typing import Any, Dict, List import numpy as np import pandas as pd from sklearn.model_selection import KFold, StratifiedKFold def make_folds(patients: pd.DataFrame, cfg: Dict[str, Any]) -> pd.DataFrame: scheme = cfg.get("scheme", "patient_kfold") seed = int(cfg.get("seed", 42)) df = patients.copy() train_patients = df[df["is_supplemental"] == 0].reset_index(drop=True) supp_patients = df[df["is_supplemental"] == 1].reset_index(drop=True) if scheme == "patient_kfold": n_splits = int(cfg.get("n_splits", 5)) strat = cfg.get("stratify_by", "cohort") y = train_patients[strat].astype(str).values if strat in train_patients.columns else None counts = pd.Series(y).value_counts() if y is not None else None if y is not None and counts is not None and counts.min() >= n_splits: splitter = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=seed) splits = list(splitter.split(train_patients, y)) else: splitter = KFold(n_splits=n_splits, shuffle=True, random_state=seed) splits = list(splitter.split(train_patients)) train_patients["fold"] = -1 for fold, (_, val_idx) in enumerate(splits): train_patients.loc[val_idx, "fold"] = fold elif scheme == "cohort_heldout": cohorts = sorted(train_patients["cohort"].unique().tolist()) holdout = cfg.get("holdout_cohorts") if holdout: holdout = [c for c in cohorts if c in set(holdout)] else: holdout = cohorts mapping = {c: i for i, c in enumerate(holdout)} train_patients["fold"] = train_patients["cohort"].map(mapping).fillna(-1).astype(int) elif scheme == "single": frac = float(cfg.get("single_val_fraction", 0.2)) rng = np.random.default_rng(seed) idx = np.arange(len(train_patients)) rng.shuffle(idx) n_val = max(1, int(round(len(idx) * frac))) train_patients["fold"] = 1 train_patients.loc[idx[:n_val], "fold"] = 0 else: raise ValueError(f"Unknown cv scheme: {scheme}") out = train_patients[["uid", "patient_id", "cohort", "fold", "is_supplemental"]].copy() if len(supp_patients): supp_patients = supp_patients.copy() supp_patients["fold"] = -2 out = pd.concat( [out, supp_patients[["uid", "patient_id", "cohort", "fold", "is_supplemental"]]], ignore_index=True, ) out = out.sort_values(["is_supplemental", "cohort", "uid"]).reset_index(drop=True) return out def fold_ids(folds: pd.DataFrame) -> List[int]: return sorted(int(x) for x in folds.loc[folds["fold"] >= 0, "fold"].unique()) def save_folds(folds: pd.DataFrame, path: str | Path) -> None: p = Path(path) p.parent.mkdir(parents=True, exist_ok=True) folds.to_csv(p, index=False) def fold_summary(folds: pd.DataFrame) -> pd.DataFrame: rows = [] for fold, g in folds[folds["fold"] >= 0].groupby("fold"): rows.append( { "fold": int(fold), "n_patients": int(len(g)), "n_control": int((g["cohort"] == "control").sum()), "n_frequent": int((g["cohort"] == "frequent").sum()), "n_annual": int((g["cohort"] == "annual").sum()), } ) return pd.DataFrame(rows).sort_values("fold").reset_index(drop=True)