Khalim Conn-Kowlessar e405928516 Re-baseline prediction component-accuracy gate for full-SAP donors (ADR-0037) ... Full-SAP certs mapped property_type=None, so the hard cohort filter silently excluded them as comparables. Correctly typing them admits real lodged EPCs as donors — a ground-truth-method change (cf #1245). Net over the n=36 fixture: 16 components better, 4 worse, 6 unchanged; gains concentrated in the physical characteristics full-SAP certs measure (window_count 3.83->1.69, building_parts, total_window_area, floor_construction, construction_age_band, glazing, walls). The 4 that fell are new-build-vs-old-stock service mismatch on 1-2 targets each (heating/water fuel, cylinder insulation) + floor_area. Tighten 16, loosen 4. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>		2026-06-26 09:34:27 +00:00
..
__init__.py	feat(epc-prediction): Comparable Properties selection ladder (ADR-0029)	2026-06-13 23:44:57 +00:00
test_comparable_properties.py	refactor(epc-prediction): PR review — rename ComparableProperty, relocate PredictionTarget	2026-06-16 13:34:44 +00:00
test_component_accuracy_gate.py	Re-baseline prediction component-accuracy gate for full-SAP donors (ADR-0037)	2026-06-26 09:34:27 +00:00
test_epc_prediction.py	Prefer a MAIN-bearing prediction template so EPC-less dwellings predict 🟩	2026-06-24 13:20:43 +00:00
test_prediction_comparison.py	feat(epc-prediction): roof-insulation +/-1-bucket reporting	2026-06-15 14:04:18 +00:00
test_prediction_target.py	refactor(epc-prediction): PR review — rename ComparableProperty, relocate PredictionTarget	2026-06-16 13:34:44 +00:00
test_validation.py	Prefer a MAIN-bearing prediction template so EPC-less dwellings predict 🟩	2026-06-24 13:20:43 +00:00