3 commits

Author	SHA1	Message	Date
Khalim Conn-Kowlessar	700ff4640c	slice 16g: LightGBM objective=mape for sap_score + peui_ucl ... Per ADR-0008: the v15 baseline reports MAPE but optimises MSE, which under-weights tail rows. Switching to objective='mape' applies gradient proportional to 1/|y| and lets the model focus where MAPE penalises. Targets co2_emissions, space_heating_kwh, hot_water_kwh, and peui_raw retain the default 'regression' objective (some rows have ~zero CO2 from heavy PV; MAPE objective destabilises near zero). Sample weights deferred to slice 16i if slice 16h's per-decile residuals still show tail bias after the objective switch.	2026-05-17 12:06:13 +00:00
Khalim Conn-Kowlessar	fd8d71eb05	slice 15e: per-decile residuals reporting in train_baseline ... Adds `_per_decile_residuals` and writes `residuals_<target>.json` next to metrics.json. Buckets test-set rows by deciles of the true target value; each bucket carries count + MAPE + MAE + mean residual + true_min/max. Lets us tell whether errors concentrate in the tails of the true distribution (e.g. SAP<40 / SAP>85) vs the mid-band — which the global MAPE alone hides. Baseline for slice 16's MAPE-improvement ablations.	2026-05-17 11:18:40 +00:00
Khalim Conn-Kowlessar	b676e05d49	slice 14f: train_baseline fits LightGBM per target, emits MAPE/R^2 + importance ... Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>	2026-05-16 18:47:49 +00:00