fix: evaluate AUC on fixed test EIDs

eval_data.py

@@ -135,6 +135,39 @@ def split_indices(
     )
 
 
+def select_indices_by_eid_file(
+    dataset: Any,
+    eid_file: str | Path,
+) -> Tuple[np.ndarray, Path]:
+    """Return dataset indices whose patient EIDs occur in ``eid_file``."""
+    from train_util import load_eid_file
+
+    path = Path(eid_file)
+    if not path.is_absolute():
+        direct = Path.cwd() / path
+        path = direct if direct.is_file() else Path(__file__).resolve().parent / path
+    if not path.is_file():
+        raise FileNotFoundError(f"EID split file not found: {path}")
+
+    samples = getattr(dataset, "samples", None)
+    if samples is None:
+        raise TypeError("EID-based evaluation requires dataset.samples")
+    selected_eids = load_eid_file(path)
+    indices = np.asarray(
+        [
+            index
+            for index, sample in enumerate(samples)
+            if int(sample["eid"]) in selected_eids
+        ],
+        dtype=np.int64,
+    )
+    if indices.size == 0:
+        raise ValueError(
+            f"No dataset patients matched the EID split file: {path}"
+        )
+    return indices, path.resolve()
+
+
 def build_model_from_dataset(
     args: argparse.Namespace,
     cfg: Dict[str, Any],