Remove legacy event and mixed distribution paths

prepare_data.py

@@ -4,7 +4,7 @@ This script converts raw UK Biobank CSV exports into the artefacts consumed by
 DeepHealth:
 
 * ``ukb_event_data.npy``: ``(N, 3)`` uint32 array of ``(eid, days, label)``
-  disease/death/checkup events sorted by patient then time.
+  disease/death events sorted by patient then time.
 * ``ukb_basic_info.csv``: basic patient table indexed by ``eid`` with ``sex``.
 * ``ukb_other_info.npy``: ``(M, 5)`` float64 array of
   ``(eid, type, value, value_kind, time)`` rows. ``type=0`` is reserved for
@@ -219,7 +219,8 @@ with open(labels_file, encoding="utf-8") as f:  # Open labels file
     for idx, line in enumerate(f):  # Enumerate to assign incremental label IDs
         parts = line.strip().split(" ")  # Split by space
         if parts and parts[0]:  # Guard against empty lines
-            # Start labels from 1 to reserve 0 for padding, 1 for checkup
+            # Keep raw disease ids at 2+ so existing prepared data and model
+            # vocabulary indices remain stable; raw id 1 is unused.
             label_dict[parts[0]] = idx + 2
 
 # Pre-build lookup: ICD/Death column name -> integer label for fast per-column extraction
@@ -327,19 +328,6 @@ for ukb_chunk in tqdm.tqdm(ukb_iterator, desc="Processing UK Biobank data"):
     if cancer_frames:
         event_list.append(np.vstack(cancer_frames))
 
-    # Add checkup events with label=1 using date_of_assessment (already in days from dob)
-    if "date_of_assessment" in ukb_chunk.columns:
-        doa_series = ukb_chunk["date_of_assessment"].dropna()
-        if not doa_series.empty:
-            checkup_data = np.column_stack(
-                (
-                    doa_series.index.values,
-                    doa_series.values.astype(int),
-                    np.ones(len(doa_series), dtype=int),
-                )
-            )
-            event_list.append(checkup_data)
-
 # Combine tabular chunks
 final_tabular = pd.concat(tabular_list, axis=0, ignore_index=False)
 final_tabular.index.name = "eid"  # Ensure index named consistently