Files
ML-py/artifacts/small_metrics.json
T
Noel Sabia dc83825de0 fix: use exact 168-row lag for the seasonal-naive baseline
The baseline now reproduces mission/data.md exactly: MAE 5.40, WAPE 44.7%,
R2 0.462. The model's lag_week remains the previous observed same weekday/hour,
which handles sensor gaps and is documented in the model card.
2026-11-14 05:04:41 +01:00

38 lines
834 B
JSON

{
"model_version": "logit-20261114-040339",
"trained_at": "2026-11-14T04:03:39Z",
"features": [
"hour",
"weekday",
"is_weekend",
"temp_c",
"precip_mm",
"is_holiday"
],
"train_from": "2026-06-12T00:00:00Z",
"train_to": "2026-10-09T01:00:00Z",
"test_from": "2026-10-09T02:00:00Z",
"test_to": "2026-11-07T23:00:00Z",
"thresholds": {
"density-01": 15.23,
"hn-goetzentuem-01": 15.4,
"hn-hagenbuchersee-01": 18.2,
"hn-hagenbuchersee-02": 29.17,
"hn-marahaus-01": 22.23,
"hn-neckarufer-01": 28.35,
"hn-soleo-01": 11.38,
"hn-stadtgalerie-01": 38.41
},
"metrics": {
"accuracy": 0.708,
"precision": 0.36,
"recall": 0.574,
"f1": 0.443,
"roc_auc": 0.726,
"n_train": 18242,
"n_test": 5710,
"positive_rate": 0.202,
"sensors": 8
}
}