mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-07-12 13:29:04 +00:00
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> |
||
|---|---|---|
| .. | ||
| addresses | ||
| billing | ||
| data_transformation | ||
| epc | ||
| epc_prediction | ||
| fuel_rates | ||
| geospatial | ||
| magicplan | ||
| modelling | ||
| property | ||
| property_baseline | ||
| sap10_calculator | ||
| sap10_ml | ||
| tasks | ||
| building_geometry.py | ||
| postcode.py | ||