Initial import NDC_1C

scripts/run_features.py

@@ -0,0 +1,82 @@
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+import sys
+
+PROJECT_ROOT = Path(__file__).resolve().parents[1]
+if str(PROJECT_ROOT) not in sys.path:
+    sys.path.insert(0, str(PROJECT_ROOT))
+
+from canonical_layer.features import FeatureService
+from config.settings import LOGS_DIR
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        description="Run feature/anomaly engine over canonical store",
+    )
+    parser.add_argument(
+        "--baseline-window-hours",
+        type=int,
+        default=None,
+        help="Baseline window in hours used for drift context",
+    )
+    parser.add_argument(
+        "--stale-refresh-threshold-hours",
+        type=int,
+        default=None,
+        help="Trigger stale_refresh anomaly when latest refresh is older than this threshold",
+    )
+    parser.add_argument(
+        "--top-account-tokens",
+        type=int,
+        default=20,
+        help="How many account-like tokens to keep in feature metrics",
+    )
+    parser.add_argument(
+        "--entity-limit",
+        type=int,
+        default=None,
+        help="How many canonical entities to scan",
+    )
+    parser.add_argument(
+        "--output",
+        default=str(LOGS_DIR / "features_last_run.json"),
+        help="Where to write run summary json",
+    )
+    parser.add_argument(
+        "--strict",
+        action="store_true",
+        help="Exit with code 1 if feature run status is not success",
+    )
+    return parser.parse_args()
+
+
+def main() -> int:
+    args = parse_args()
+    service = FeatureService.build()
+    result = service.run_feature_engine(
+        baseline_window_hours=args.baseline_window_hours,
+        stale_refresh_threshold_hours=args.stale_refresh_threshold_hours,
+        top_account_tokens=args.top_account_tokens,
+        entity_limit=args.entity_limit,
+    )
+    payload = result.to_dict()
+    payload["feature_store_stats"] = service.stats()
+    payload["feature_runs"] = service.list_recent_runs(limit=5)
+    payload["active_anomalies"] = service.list_anomalies(limit=100, active_only=True)
+
+    output_path = Path(args.output)
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+    output_path.write_text(json.dumps(payload, ensure_ascii=False, indent=2), encoding="utf-8")
+    print(json.dumps(payload, ensure_ascii=False, indent=2))
+
+    if args.strict and result.status != "success":
+        return 1
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())