Khalim Conn-Kowlessar 136f149d46 tooling: widen parity probe sap_score range to (5, 99) ... Previous bound (20, 95) excluded full-SAP new-builds (sap_score 90+, which carry the dramatic wall U-value gap) and deepest-tail heritage certs (sap_score ≤ 20). Widening so the sample reflects the populations where the calculator's biggest spec gaps live. New baseline at 300 certs, seed=7: SAP MAE 5.34 → 4.59 (-0.75) PE MAE 48.99 → 46.78 (-2.21) PE bias 42.07 → 41.78 (-0.29) Note: the v18a parquet only contains ~0.7% certs with age_band=None, while the raw bulk zip has 15% full-SAP "Average thermal transmittance" certs. The parquet is filtering them somewhere upstream — to be chased in separate work. Until then, parity-probe MAE will under-show the true corpus impact of slices that target full-SAP certs. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>		2026-05-18 20:38:22 +00:00
..
src/ml_training_data	tooling: widen parity probe sap_score range to (5, 99)	2026-05-18 20:38:22 +00:00
tests	slice 16i: MAE + RMSE in metrics; sample_weight_fn + low_sap_tail_weight	2026-05-17 14:48:00 +00:00
pyproject.toml	slice 14g: remote_bulk_fetcher extracts ZIP entries via HTTP Range (no full download)	2026-05-16 19:16:52 +00:00