Khalim Conn-Kowlessar 275a30a825 feat(epc-prediction): complete component coverage — fabric/glazing/renewables/doors (ADR-0030) ... Finish the ADR-0030 Component Accuracy set: roof insulation thickness, floor insulation, room-in-roof presence, modal glazing type, PV presence, solar water heating (categoricals) + door count (residual). Presence flags (room-in-roof, PV, solar) are always-applicable — predicting absence when present is a real miss. Template-copied baseline (40-postcode corpus), newly visible: floor_insulation 94.0% solar_water_heating 99.7% has_pv 98.6% has_room_in_roof 91.9% modal_glazing_type 59.0% <- weak roof_insulation_thickness 30.6% <- weak door_count mean|.| 0.40 compare_prediction now scores 19 categoricals + 5 residuals across every SAP-load-bearing component group. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>		2026-06-14 09:00:30 +00:00
..
__init__.py	feat(epc-prediction): Comparable Properties selection ladder (ADR-0029)	2026-06-13 23:44:57 +00:00
comparable_properties.py	fix(epc-prediction): dedupe re-lodgements + leak-free leave-one-out (ADR-0029)	2026-06-14 00:40:23 +00:00
epc_prediction.py	feat(epc-prediction): cohort-mode the roof/floor/insulation/age categoricals (ADR-0029)	2026-06-14 00:31:16 +00:00
prediction_comparison.py	feat(epc-prediction): complete component coverage — fabric/glazing/renewables/doors (ADR-0030)	2026-06-14 09:00:30 +00:00