junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-07-12 13:29:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
Model/backend/epc_api/json_samples
History
Jun-te Kim c380377948 test(accuracy): ratchet 74.2% -> 75.5% via 'insulated (assumed)' roof Table-18 fix 
RdSAP 10 §5.11.4: a pitched roof lodging thickness "NI" with description
"...insulated (assumed)" was billed at the §5.11.4 observed-retrofit
50 mm row (U 0.68) while the SAME description lodged with "ND" fell
through to the Table 18 age-band default (0.40 for bands A-G). The
ND-vs-NI sentinel is lodging-software noise; "(assumed)" means the
insulation PRESENCE is an age-band assumption, not an observed
retrofit, so Table 18's "thickness cannot be determined" clause
governs both forms. The bare "insulated" description (observed
retrofit, no qualifier) keeps the 50 mm row.

Evidence: the 27-cert loc4+NI corpus cohort was systematically
under-rated (~-1 SAP; zero positive movers among "(assumed)" certs),
vs the 102-cert loc4+ND cohort already on Table 18 at ~0 bias.

Gauge: within-0.5 74.2% -> 75.5%, SAP MAE 0.721 -> 0.708, CO2 MAE
0.09 -> 0.074, PE MAE 3.5 -> 3.2 (floors ratcheted). Unit-pinned in
test_rdsap_uvalues (assumed -> Table 18; bare-insulated -> 0.68
regression guard); integration pin in test_heat_transmission updated;
RealCertExpectation pinned for 10094975827 (66 = lodged, was -1.87).

Ledger: C002 103001004 deferred pending Elmhurst arbitration
(single-immersion off-peak pricing + declared cylinder loss vs
Table-2); C006 quadruplet marked ⚠ (LIG-21.0 software honours lodged
0 extract fans literally vs the Elmhurst-validated 0=unknown->default
convention, worksheet case 46).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-02 19:06:26 +00:00
..
CEPC-7.0 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
CEPC-7.1 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
CEPC-8.0.0 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
RdSAP-Schema-17.0 Map RdSAP-Schema-17.0 certs to EpcPropertyData 🟥 2026-06-12 12:40:04 +00:00
RdSAP-Schema-17.1 Dispatch and map RdSAP-Schema-18.0 certs end-to-end 🟥 2026-06-11 11:12:53 +00:00
RdSAP-Schema-18.0 Dispatch and map RdSAP-Schema-18.0 certs end-to-end 🟥 2026-06-11 11:12:53 +00:00
RdSAP-Schema-19.0 Map RdSAP-Schema-19.0 certs to EpcPropertyData 🟥 2026-06-12 12:19:16 +00:00
RdSAP-Schema-20.0.0 added test for a 1000 examples 2026-06-09 16:02:21 +00:00
RdSAP-Schema-21.0.0 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
RdSAP-Schema-21.0.1 added test for a 1000 examples 2026-06-09 16:02:21 +00:00
real_life_examples test(accuracy): ratchet 74.2% -> 75.5% via 'insulated (assumed)' roof Table-18 fix 2026-07-02 19:06:26 +00:00
SAP-Schema-16.0 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
SAP-Schema-16.1 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
SAP-Schema-16.2 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
SAP-Schema-16.3 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
SAP-Schema-17.0 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
SAP-Schema-17.1 inviestigation with hyde values 2026-06-15 12:13:11 +00:00
SAP-Schema-18.0.0 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
SAP-Schema-19.0.0 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
SAP-Schema-19.1.0 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00
SAP-Schema-19.2.0 adding hacky handling for matching on lmk key or uprn 2026-04-09 14:47:54 +01:00