diff --git a/scripts/backfill_event_shape.py b/scripts/backfill_event_shape.py index 9de2f85..975c716 100644 --- a/scripts/backfill_event_shape.py +++ b/scripts/backfill_event_shape.py @@ -11,7 +11,8 @@ from sfm.shape_metrics import shape_from_h5 log = logging.getLogger("backfill_event_shape") def backfill_shape(db: SeismoDb, store: WaveformStore, *, dry_run: bool = False) -> dict: - counts = {"updated": 0, "skipped_no_h5": 0, "skipped_no_samples": 0} + counts = {"updated": 0, "skipped_no_h5": 0, "skipped_no_samples": 0, + "cleared_stale": 0} for row in db.query_events(limit=1_000_000): serial, filename = row.get("serial"), row.get("blastware_filename") if not serial or not filename: @@ -21,6 +22,20 @@ def backfill_shape(db: SeismoDb, store: WaveformStore, *, dry_run: bool = False) counts["skipped_no_h5"] += 1; continue shape = shape_from_h5(h5_path) if shape is None: + # The .h5 can no longer yield a shape (fewer than 2 samples, or a + # flat trace). Clear any previously stored value rather than + # leaving it behind — a stale shape outlives the decode it came + # from and silently feeds the false-trigger detector. Seen after + # a decoder fix shrinks an event: 493 rows in the prod snapshot + # were carrying metrics from a superseded decode (2026-08-25). + if row.get("shape_crest_factor") is not None: + if not dry_run: + with db._connect() as conn: + conn.execute( + "UPDATE events SET shape_crest_factor=NULL, " + "shape_near_peak_count=NULL, shape_sample_count=NULL, " + "shape_axis=NULL WHERE id=?", (row["id"],)) + counts["cleared_stale"] += 1 counts["skipped_no_samples"] += 1; continue if not dry_run: with db._connect() as conn: