Template (the comparable whose structure/geometry is copied wholesale)
was members[0] — an arbitrary draw from the API search order. With floor
area varying widely within a property_type cohort (NG71AA houses span
51-340 m2), this made the copied geometry noisy and systematically large.
Pick the member whose floor area is closest to the cohort median instead,
implementing ADR-0029 decision 4's unimplemented "closest on size"
criterion while keeping the structure coherent (it is still one real
property, so floor dims / windows / parts stay internally consistent for
the calculator).
Smoke corpus (29 leave-one-out predictions):
floor_area mean|.| 68.0 -> 37.9 m2 (bias +46.8 -> -3.9)
window_area mean|.| 11.1 -> 7.3 m2
parts mean|.| 1.00 -> 0.38
SAP |pred-calc - calc(actual)| MAE 7.19 -> 4.86
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Pure compare_prediction (TDD): wall-construction classification hit + signed
residuals on floor area, window count, total window area, building-parts count.
Plus validate_epc_prediction.py (IO plumbing): drops each cert from its postcode
cohort, predicts from the rest on guaranteed inputs only, aggregates the metrics,
and reports SAP three ways (pred-calc vs lodged / vs calc-on-actual / vs the
neighbour-mean baseline). Smoke run: wall 90.9%, floor-area mean|·| 42.6 m2 (a
real signal — template-copied floor area is noisy), SAP pred-calc edges baseline.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
predict() copies a representative template comparable's structure (coherent for
the calculator), overrides the homogeneous categorical with the cohort mode
(robust to an atypical template), then applies known Landlord Overrides on top
(a known value wins over the estimate). Proven on wall construction; roof/floor/
insulation/age extend on the same mode+override mechanism, driven next by the
validation harness metrics.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Pure-domain select_comparables: property type is an always-hard filter; built
form and known Landlord Overrides (e.g. solid brick) are conditioning filters on
the filter-then-relax ladder — applied while >= minimum_cohort survive, relaxed
otherwise (the mixed-street border case degrades gracefully). PredictionTarget
(known inputs) + Comparable (epc + register metadata) + ComparableProperties
(selected cohort). Weighting (recency x similarity) follows in the synthesis slice.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adds a committed integration test driving the full API path — raw gov-EPC
response → from_api_response → cert_to_inputs → calculate_sap_from_inputs —
across all 1000 certs in the in-repo RdSAP-21.0.1 corpus, and pins the
aggregate accuracy of our continuous SAP (plus CO2 and primary energy)
against each cert's lodged figures. Mirrors scripts/eval_api_sap_accuracy.py
but runs in CI off the committed corpus (~2s, no /tmp sample needed).
Scoped to RdSAP-21.0.1 — the SAP 10.2-era schema whose lodged rating uses the
same methodology we compute (a fair target). Pre-SAP10 schemas (17.x-20.0.0)
lodge SAP 2012 ratings and are out of scope (guarded for mapping only by
test_mapper_corpus.py).
Current: SAP within-0.5 = 65.0%, MAE = 1.174 (tight floor/ceiling — the
optimised gauge). CO2 MAE = 0.27 t/yr (bias +0.17) and PE MAE = 14.6
kWh/m2/yr (bias +8.9) are reported + loosely guarded: cost is well-calibrated
but CO2/PE both run ~+5-10% high (uniform across fuels — a systematic
CO2/PE-factor or scope gap, not yet investigated). Thresholds ratchet as
slices tighten each metric.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Builds the frozen validation corpus: samples postcodes from the register, then
caches each postcode's full cohort of raw cert payloads (the shape
from_api_response consumes), grouped by postcode, resumably. Reads the token
from backend/.env; cache dir /tmp/epc_prediction_corpus (EPC_PREDICTION_CORPUS
override). IO plumbing, not test-driven. Pairs with the leave-one-out harness.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The mixer-shower hot-water demand (worksheet 42a) divided N_shower by the
count of MIXER outlets only. But SAP 10.2 Appendix J step 1a is explicit:
"Establish how many shower outlets are present in the dwelling, Noutlets
(including in the count any instantaneous electric showers)" — and the
electric-shower step (64a) uses that same Noutlets from step 1a. So a
dwelling with both a mixer and an electric shower assigned the FULL N_shower
to the mixer system AND billed the electric shower on top of it, double-
counting shower demand → over-counted main HW → under-rated the dwelling.
Fix: thread the electric-shower count into the mixer demand so the
denominator is the total outlet count (mixer + electric), iterating the
warm-water draw over the mixer outlets only (per step 1e).
shower_types=1,2 cohort: -0.37 median -> +0.28 (crossed zero); API gauge
68.4% -> 69.0% within-0.5. Golden cert 0300-2747 (1 mixer + 1 electric)
re-pinned: PE +0.93 -> -0.10, CO2 +0.25 -> +0.15 (both toward zero,
confirming the double-count). Worksheet harness 47/47, 0 divergers (the
Elmhurst fixtures have no electric showers).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The no-PCDB MEV fan-electricity path fed the SAP 10.2 Table 4g default SFP
(0.8 W/(l/s)) directly as SFPav. But Table 4g note 3 (PDF p.176) is explicit:
the default SFP values "are to be multiplied by the appropriate in-use factor
for default data from the PCDB" — PCDB Table 329 system_type 10 ("default
data, used when SFP is taken from Table 4g rather than the PCDB"), IUF 2.5
(duct-agnostic per note 2). Table 4h, which previously held these factors, is
retired ("no longer used – data now stored in the PCDB").
Omitting the IUF under-billed the index-less MEV fan electricity by 2.5x
(SFPav 0.8 instead of 0.8 x 2.5 = 2.0), so cost was too low and the cohort
over-rated. This is distinct from the with-index path, which already applies
the tested-product system_type-2 "no scheme" IUF (~1.45) per fan.
Index-less gas-house MEV cohort: +1.37 median -> -0.18 (12% -> 92% within 0.5),
no overshoot — the missing IUF was exactly the over-rate. API gauge 67.7% ->
68.4% within-0.5 (mean|err| 0.992 -> 0.986, signed +0.031 -> +0.006).
Worksheet harness 47/47, 0 divergers (Summary-path MEV certs carry a PCDB
index or are natural, so unaffected).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Promote RdSAP-Schema-17.0 into SUPPORTED so all 1000 corpus certs are held to
the strict parse+map guard. Drop the now-redundant cert[0] tracer (subsumed by
the parametrised bucket); keep the reduced-field synthesis behavioural test.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the 17.0 synthesis seam over the shared _synthesise_reduced_field_windows
core (inherited 20.0.0 coefficients, ND glazing -> DG-modal default 2, per
ADR-0028). 17.0 glazed_type codes (1-4,7) are a subset of the verified 1-8
space. The 10 rich certs use lodged window_area directly; the windowless 990
synthesise a 4-way N/E/S/W split.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Dispatch RdSAP-Schema-17.0 through from_api_response, parse-fix the schema
(data-driven required->optional, validated against the 1000-cert 17.0 corpus
per ADR-0028 — incl. SapHeating.cylinder_insulation_type and the
has_hot_water_cylinder / has_fixed_air_conditioning / has_heated_separate_
conservatory flags), and port the defensive mapper reads (dwelling_type
str/dict/number, photovoltaic_supply guard, sap_floor_dimensions guard). All
1000 corpus certs now parse and map.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reusable per-schema profiler: glazed_area band mix, Validation Cohort size,
observed-vs-predicted band glazing/floor ratio, and the ND/str sentinels that
drive schema widening. Regenerates the ADR-0028 transfer-check table from any
harvested corpus.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Promote RdSAP-Schema-19.0 into SUPPORTED so all 1000 corpus certs are held to
the strict parse+map guard. Drop the now-redundant cert[0] tracer (subsumed by
the parametrised bucket); keep the reduced-field synthesis behavioural test.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the 19.0 synthesis seam over the shared _synthesise_reduced_field_windows
core (inherited 20.0.0 coefficients, ND glazing -> DG-modal default 2, per
ADR-0028). 19.0 glazed_type codes (1-4,6,7) are a subset of the verified 1-8
space. The 6 rich certs use lodged window_area directly; the windowless 994
synthesise a 4-way N/E/S/W split.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Dispatch RdSAP-Schema-19.0 through from_api_response, parse-fix the schema
(data-driven required->optional, validated against the 1000-cert 19.0 corpus
per ADR-0028), and port 18.0's defensive mapper reads (dwelling_type str/dict/
number, photovoltaic_supply guard, sap_room_in_roof Measurement coercion).
All 1000 corpus certs now parse and map.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Orchestrator runs recommend_secondary_heating_removal; report._triggers_for
explains it via the lodged secondary_heating_type; harness catalogue + ARA seed
price it. Re-pins the golden/integration plans it shifts: it is a cheap (\£250)
SAP lever, so on gas-main certs lodging an electric secondary (691) it displaces
the \£12k ASHP (0330, 0036) or joins the all-beneficial-measures package (000490,
where its marginal SAP is 0 under the category-4 ASHP but the heater is still
physically removed). Consistent with the optimiser's existing kitchen-sink
package behaviour.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Two cascade tests on the worksheet-pinned 001431 build_epc() (the user's
before/after Summary PDFs trip the documented 001431 window-extraction bug, so
the repo's sanctioned 001431 baseline is used instead):
- electric-storage main (code 402) + secondary 691: removal reproduces the
secondary-removed cert at delta 0 — RdSAP §A.2.2 re-forces a default secondary,
matching the user's F35→F35 example;
- gas combi main (code 104) + secondary 691: removal strictly raises SAP
(74.22→77.61) — the Table 11 fraction reallocates to the cheaper main.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Records the four load-bearing design decisions from the grill-with-docs session:
standalone co-selectable rec; eligibility = lodged-only (no effectiveness gate,
electric-storage §A.2.2 no-op is the Optimiser's call); dedicated clearing
SecondaryHeatingOverlay; flat per-dwelling cost (a lodged secondary is fixed per
RdSAP, so a real decommission job, not room-scaled).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The gov-EPC API surfaces the assessor's RdSAP-assessed per-element U-values
as `roof_u_value` / `wall_u_value` / `floor_u_value` on each building part.
These were undeclared on the RdSAP 21.0.0/21.0.1 schemas, so `from_dict`
silently dropped them, and `heat_transmission` re-derived each U from the §5.6
/§5.7/§5.11 construction-default cascade. The gov OPEN data routinely redacts
the backing insulation thickness, so that re-derivation mis-bills an insulated
element as uninsulated.
RdSAP 10 §5.1: a known element U-value (documentary evidence / the lodged
RdSAP output) is used directly in place of the construction-default cascade.
Per [[project_per_cert_mapper_validation_state]] the gov API carries RdSAP
OUTPUT, so the lodged U reproduces the official's element heat loss exactly.
Worst case in the 2026 sample: cert 7921-0052-0940-5007-0663, an age-C
"Pitched, sloping ceiling" (rc=8) top-floor flat lodging roof_u_value=0.2 with
no thickness. The cascade returned the uninsulated 2.30 W/m²K → SAP 56.9 vs
lodged 80 (-23.09, the single largest error in the sample). The roof override
alone recovers ~15 SAP; the wall override (lodged 0.34 vs cascade) closes the
rest of this cohort.
Override applies to the MAIN wall only (alt-wall sub-areas keep their own
per-area U) and the part's floor=0. Fires only when the rare field is present
(9 of 909 computed certs), so the Summary path — which never lodges these
API fields — is untouched.
API gauge: 67.1% → 67.7% within-0.5, mean|err| 1.024 → 0.992.
Worksheet harness: 47/47, 0 divergers (unchanged).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Flat per-dwelling decommission price (sample_catalogue \£250) + 0.25 contingency
(covers unknown heater count / hard-wired-vs-plugged / repaint extent). The JSON
repo joins the contingency from config, proven by the new repo test. No composite
Products machinery — a lodged secondary is one roughly-fixed job, not room-scaled.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
recommend_secondary_heating_removal offers one standalone Option that clears the
lodged secondary system. Eligibility is purely physical (offer iff
sap_heating.secondary_heating_type is set) — no effectiveness gate, since a
lodged secondary is a fixed emitter per RdSAP (portables are ignored), and the
electric-storage §A.2.2 no-op is the Optimiser's call (ADR-0028 decisions 1-2).
Priced at a flat per-dwelling decommission cost, not room-scaled.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
ADR-0028's deferred extraction, triggered by 17.1 as the second instance: the
inherited 20.0.0 coefficients (0.148 + band multipliers + 4-way split) now live
in one `_synthesise_reduced_field_windows` core. The 20.0.0 / 18.0 / 17.1 seams
keep their own names (so each can diverge) but collapse to glazing-type
resolution (cascade + that spec's ND handling) plus a call to the core.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rich certs (14/1000) use lodged window_area; the windowless majority synthesise
glazing from the glazed_area band via _synthesise_17_1_sap_windows (own seam,
inherited 20.0.0 coefficients); lighting/ventilation/hot-water mirror 18.0.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The first overlay surface that sets fields to *absent* rather than to a
target state: _fold_secondary_heating clears sap_heating.secondary_heating_type
+ secondary_fuel_type, so the calculator's Table 11 secondary-fraction split
(SAP 10.2 §9a) routes 100% of space heating to the main. On an electric-storage
main RdSAP §A.2.2 re-forces a default secondary, making removal a no-op there —
left to the Optimiser to de-select (ADR-0028 decisions 2-3).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Schema-fix delivered in the prior slice; this promotes the 1000-cert corpus
into the strict guard (matches 18.0/20.0.0).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The §5.16 Table 22 thermal-mass-parameter (TMP) "always low-mass" set was
{timber 5, cob 7, park home 8}. But wall_construction code 8 is OVERLOADED by
the same gov-API/calc code-space divergence as the wall-U fix: the Summary
path's "PH" mapping uses 8 for park home, while the gov-EPC API enum uses 8
for SYSTEM BUILD (Summary system build = code 6). So every API system-built
cert was mis-rated as low-mass 100 kJ/m²K instead of masonry 250 (Table 22
lists system build as masonry — PDF p.48, line "System build 250...").
A too-low TMP shortens the §7 time constant tau = Cm/(3.6·H), over-cutting
the temperature reduction so mean internal temperature is UNDER-stated →
space-heating demand under-stated → SAP over-rated. This was the cause of the
uninsulated system-built over-rate cluster (n=9 gas-boiler certs at signed
+2.39 vs cavity +0.43 / solid-brick +0.08 at the same bands — a system-built-
specific anomaly with a spec-correct wall U).
Fix: drop 8 from the always-low set and gate it on `property_type` — code 8 is
the low-mass park-home value only when the dwelling really is a park home,
otherwise it is gov-API system build and keeps masonry 250. Disambiguated by
the same `property_type == "park home"` signal used elsewhere in the cascade.
Worksheet harness UNAFFECTED (47/47, 0 divergers): the Summary path uses code
6 for system build and code 8 only for genuine park homes (which stay
low-mass via the property_type gate). API gauge 65.3% -> 67.1% within-0.5
(mean|err| 1.059 -> 1.024, signed +0.050 -> -0.002). The uninsulated
system-built cluster collapses +2.82 -> +0.28 signed (0/11 -> 7/11 within
0.5). 2 AAA tests (parametrised code-8 system-built -> 250; park-home
property -> 100). pyright net-zero.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
