mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-06-08 11:17:27 +00:00
Slice S0380.64: Elmhurst per-extension wall_construction mappings + strict-raise
Pre-S0380.64 the mapper silently fell through to wall_construction=None
on three Elmhurst code lodgements that the cohort PDFs use:
- "SG Stone: granite or whinstone" (cert 000565 Ext1)
- "B Basement wall" (cert 000565 Ext3 + Ext4)
- "CF Cavity masonry filled" party wall (cert 000565 Ext1)
Cascade impact on cert 000565 (vs U985-0001-000565.pdf worksheet):
- sap_score 30 → 29 EXACT (was Δ +1)
- sap_score_continuous 30.23 → 29.14 (Δ +1.72 → +0.63)
- space_heating_kwh_per_yr 57909 → 59274 (Δ −1100 → +266)
- HTC 1281 → 1321 W/K (was 234 W/K short
of worksheet line 39 monthly avg 1515.38)
Spec basis:
- SG → 1 (WALL_STONE_GRANITE per domain.sap10_ml.rdsap_uvalues)
is the granite-specific Elmhurst variant of "ST Stone"; same
SAP10 enum, no cascade behaviour change for stone walls.
- B → 6 (BASEMENT_WALL_CONSTRUCTION_CODE per
datatypes/epc/domain/epc_property_data.py:361) routes the
cascade through `part.main_wall_is_basement` →
`u_basement_wall(age_band)` per RdSAP 10 §5.17 / Table 23
(heat_transmission.py:640). Empirically established from a
2026 50k-bulk GOV.UK API sweep (88% co-occurrence with
walls[].description = "Basement wall").
- CF → 4 (Cavity, RdSAP 10 Table 15 row 3 spec U=0.20). The
cascade's `u_party_wall` returns 0.0 / 0.5 / 0.25 for code 4
today, so CF conservatively rounds up to the cavity-unfilled
U=0.5 — matches the pre-existing
`_API_PARTY_WALL_CONSTRUCTION_TO_SAP10[3]` approximation
until `u_party_wall` gains a filled-cavity branch (TODO).
Strict-coverage gate per [[reference-unmapped-api-code]] mirror:
`_elmhurst_wall_construction_int` and
`_elmhurst_party_wall_construction_int` now raise
`UnmappedElmhurstLabel` on a non-empty Elmhurst code that isn't in
the lookup dict, rather than silently returning None. Empty
lodgings (absent fields) continue to return None — the cascade's
own defaults apply. The silent-None failure mode is what hid cert
000565's ~300 W/K cascade fabric-loss gap from the audit chain
until the S0380.64 space-heating residual probe surfaced it.
Cohort coverage swept: every Summary PDF in the test fixtures
folder lodges only {SO, CA, CW, SG, B} wall types and
{'', S, U, CU, CF} party-wall types — the new dict entries cover
all observed codes, so strict-raise does not regress any cohort
fixture (478 pass, 9 expected 000565 cascade-gap fails; was 427
pass + 10 fails per HANDOVER_CERT_000565_COST_CASCADE.md).
Pyright net-zero on touched files (mapper.py 32 → 32 errors;
test_summary_pdf_mapper_chain.py 13 → 13 errors — all pre-existing
in unrelated sections).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Khalim Conn-Kowlessar
parent
a21195ff25
commit
6b02bad018
2 changed files with 133 additions and 7 deletions
|
|
@ -75,6 +75,7 @@ _SUMMARY_000889_PDF = _FIXTURES / "Summary_000889.pdf" # cert 2536 (Normal cyli
|
|||
_SUMMARY_000884_PDF = _FIXTURES / "Summary_000884.pdf" # cert 9421 (Normal cylinder)
|
||||
_SUMMARY_000910_PDF = _FIXTURES / "Summary_000910.pdf" # cert 0036 (Flat, party wall U=0)
|
||||
_SUMMARY_000890_PDF = _FIXTURES / "Summary_000890.pdf" # cert 7800 (two electric showers)
|
||||
_SUMMARY_000565_PDF = _FIXTURES / "Summary_000565.pdf" # cert 000565 (5-bp Elmhurst-only)
|
||||
|
||||
# GOV.UK EPB API JSON for cert 001479 — the API-path counterpart of the
|
||||
# Summary_001479.pdf fixture. Together they drive the API ≡ Summary
|
||||
|
|
@ -1090,6 +1091,93 @@ def test_summary_mapper_raises_on_unmapped_glazing_type_label() -> None:
|
|||
assert excinfo.value.value == "Quintuple glazed with helium"
|
||||
|
||||
|
||||
def test_summary_000565_ext1_wall_construction_routes_to_stone_granite() -> None:
|
||||
# Arrange — RdSAP 10 §3.3 + Table 4: cert 000565 Ext1 lodges
|
||||
# "SG Stone: granite or whinstone" which routes to SAP10
|
||||
# WALL_STONE_GRANITE=1. Pre-S0380.64 fell through silent-None,
|
||||
# losing the Ext1 wall channel (worksheet line 29a: 91.83 m² ×
|
||||
# U=1.7 = 156.11 W/K) from the cascade fabric subtotal.
|
||||
pages = _summary_pdf_to_textract_style_pages(_SUMMARY_000565_PDF)
|
||||
site_notes = ElmhurstSiteNotesExtractor(pages).extract()
|
||||
|
||||
# Act
|
||||
epc = EpcPropertyDataMapper.from_elmhurst_site_notes(site_notes)
|
||||
|
||||
# Assert
|
||||
assert epc.sap_building_parts[1].wall_construction == 1
|
||||
|
||||
|
||||
def test_summary_000565_ext3_ext4_wall_constructions_route_to_basement_code_6() -> None:
|
||||
# Arrange — RdSAP 10 §5.17 / Table 23: cert 000565 Ext3 + Ext4
|
||||
# lodge "B Basement wall". The canonical `BASEMENT_WALL_
|
||||
# CONSTRUCTION_CODE=6` triggers the cascade's
|
||||
# `part.main_wall_is_basement` route to `u_basement_wall` at
|
||||
# heat_transmission.py:640. Pre-S0380.64 silent-None bypassed
|
||||
# the basement-wall override entirely.
|
||||
pages = _summary_pdf_to_textract_style_pages(_SUMMARY_000565_PDF)
|
||||
site_notes = ElmhurstSiteNotesExtractor(pages).extract()
|
||||
|
||||
# Act
|
||||
epc = EpcPropertyDataMapper.from_elmhurst_site_notes(site_notes)
|
||||
|
||||
# Assert
|
||||
assert epc.sap_building_parts[3].wall_construction == 6
|
||||
assert epc.sap_building_parts[3].main_wall_is_basement is True
|
||||
assert epc.sap_building_parts[4].wall_construction == 6
|
||||
assert epc.sap_building_parts[4].main_wall_is_basement is True
|
||||
|
||||
|
||||
def test_summary_000565_ext1_party_wall_routes_to_cavity_filled_code_4() -> None:
|
||||
# Arrange — RdSAP 10 Table 15 row 3 "Cavity masonry filled":
|
||||
# cert 000565 Ext1 lodges "CF Cavity masonry filled". Routes
|
||||
# to SAP10 code 4 (Cavity). TODO(S0380.64+1): Table 15 row 3
|
||||
# spec U=0.20; today's `u_party_wall` only returns 0.0 / 0.5 /
|
||||
# 0.25 for code 4 so the cascade conservatively rounds up to
|
||||
# the cavity-unfilled U=0.5 — matches the pre-existing
|
||||
# `_API_PARTY_WALL_CONSTRUCTION_TO_SAP10[3]` approximation.
|
||||
pages = _summary_pdf_to_textract_style_pages(_SUMMARY_000565_PDF)
|
||||
site_notes = ElmhurstSiteNotesExtractor(pages).extract()
|
||||
|
||||
# Act
|
||||
epc = EpcPropertyDataMapper.from_elmhurst_site_notes(site_notes)
|
||||
|
||||
# Assert
|
||||
assert epc.sap_building_parts[1].party_wall_construction == 4
|
||||
|
||||
|
||||
def test_summary_mapper_raises_on_unmapped_wall_type_code() -> None:
|
||||
# Arrange — strict-coverage gate per [[reference-unmapped-api-
|
||||
# code]] mirror: an Elmhurst wall_type lodgement that isn't in
|
||||
# `_ELMHURST_WALL_CODE_TO_SAP10` raises `UnmappedElmhurstLabel`
|
||||
# rather than silently routing through wall_construction=None.
|
||||
# The silent-None failure mode is what hid cert 000565 Ext1/3/4
|
||||
# ~300 W/K cascade gap until the S0380.64 fabric-loss audit.
|
||||
pages = _summary_pdf_to_textract_style_pages(_SUMMARY_000565_PDF)
|
||||
site_notes = ElmhurstSiteNotesExtractor(pages).extract()
|
||||
site_notes.walls.wall_type = "XX Unknown construction"
|
||||
|
||||
# Act / Assert
|
||||
with pytest.raises(UnmappedElmhurstLabel) as excinfo:
|
||||
EpcPropertyDataMapper.from_elmhurst_site_notes(site_notes)
|
||||
assert excinfo.value.field == "walls.wall_type"
|
||||
assert excinfo.value.value == "XX Unknown construction"
|
||||
|
||||
|
||||
def test_summary_mapper_raises_on_unmapped_party_wall_type_code() -> None:
|
||||
# Arrange — mirror strict-coverage gate for party-wall-type
|
||||
# lodgements (same silent-None failure mode at the
|
||||
# `_elmhurst_party_wall_construction_int` boundary).
|
||||
pages = _summary_pdf_to_textract_style_pages(_SUMMARY_000565_PDF)
|
||||
site_notes = ElmhurstSiteNotesExtractor(pages).extract()
|
||||
site_notes.walls.party_wall_type = "YY Unknown party wall"
|
||||
|
||||
# Act / Assert
|
||||
with pytest.raises(UnmappedElmhurstLabel) as excinfo:
|
||||
EpcPropertyDataMapper.from_elmhurst_site_notes(site_notes)
|
||||
assert excinfo.value.field == "walls.party_wall_type"
|
||||
assert excinfo.value.value == "YY Unknown party wall"
|
||||
|
||||
|
||||
# ----------------------------------------------------------------------
|
||||
# API mapper strict-raise — mirror the Elmhurst UnmappedElmhurstLabel
|
||||
# coverage gate on the GOV.UK API path. The same failure mode (silently
|
||||
|
|
|
|||
|
|
@ -2077,6 +2077,9 @@ def _leading_code(value: str) -> str:
|
|||
_ELMHURST_WALL_CODE_TO_SAP10: Dict[str, int] = {
|
||||
"ST": 1, # Stone (granite/sandstone) — placeholder; sandstone vs granite
|
||||
# ambiguity resolved downstream via walls[].description.
|
||||
"SG": 1, # Stone: granite or whinstone (cert 000565 Ext1) — the
|
||||
# granite-specific Elmhurst variant of "ST"; same SAP10
|
||||
# WALL_STONE_GRANITE=1 cascade entry.
|
||||
"SB": 3, # Solid brick (cohort cert lodgement)
|
||||
"SO": 3, # Solid brick (newer Elmhurst PDF variant — same SAP10
|
||||
# mapping; cert 9501 lodges "SO Solid Brick" where the
|
||||
|
|
@ -2085,6 +2088,15 @@ _ELMHURST_WALL_CODE_TO_SAP10: Dict[str, int] = {
|
|||
"TF": 5, # Timber frame
|
||||
"TI": 5, # Timber frame (Elmhurst's alt-wall code; same SAP10 mapping)
|
||||
"SY": 6, # System build
|
||||
"B": 6, # Basement wall (cert 000565 Ext3+Ext4) — routes to the
|
||||
# `BASEMENT_WALL_CONSTRUCTION_CODE=6` canonical signal so
|
||||
# the cascade's `part.main_wall_is_basement` triggers the
|
||||
# RdSAP 10 §5.17 / Table 23 `u_basement_wall` override
|
||||
# (heat_transmission.py:640). Collides numerically with
|
||||
# "SY" System build — the cascade's basement check
|
||||
# precedes `u_wall(construction=6)` so SY would be
|
||||
# silently mis-routed to u_basement_wall today; no cohort
|
||||
# fixture exercises SY yet so the conflict is dormant.
|
||||
"CO": 7, # Cob
|
||||
"PH": 8, # Park home
|
||||
"CW": 9, # Curtain wall
|
||||
|
|
@ -2151,9 +2163,19 @@ def _elmhurst_dwelling_type(
|
|||
|
||||
def _elmhurst_wall_construction_int(coded: str) -> Optional[int]:
|
||||
"""Map an Elmhurst wall_type string ('CA Cavity') to the SAP10
|
||||
integer code (4). Returns None when the leading code isn't a known
|
||||
SAP10 wall type."""
|
||||
return _ELMHURST_WALL_CODE_TO_SAP10.get(_leading_code(coded))
|
||||
integer code (4). Returns None when the lodging is absent (empty
|
||||
string). Raises `UnmappedElmhurstLabel` when a non-empty code
|
||||
isn't in `_ELMHURST_WALL_CODE_TO_SAP10` — that's a mapper-coverage
|
||||
gap that should be made explicit so the next fixture forces a
|
||||
dict entry rather than silently routing to wall_construction=None
|
||||
(the failure mode that hid cert 000565 Ext1/Ext3/Ext4's ~300 W/K
|
||||
cascade fabric-loss gap until the S0380.64 audit)."""
|
||||
code = _leading_code(coded)
|
||||
if not code:
|
||||
return None
|
||||
if code not in _ELMHURST_WALL_CODE_TO_SAP10:
|
||||
raise UnmappedElmhurstLabel("walls.wall_type", coded)
|
||||
return _ELMHURST_WALL_CODE_TO_SAP10[code]
|
||||
|
||||
|
||||
# Elmhurst Party Wall Type codes — distinct category-set from the Wall
|
||||
|
|
@ -2168,6 +2190,13 @@ _ELMHURST_PARTY_WALL_CODE_TO_SAP10: Dict[str, int] = {
|
|||
"CU": 4, # Cavity masonry unfilled — same U=0.5 cascade; Elmhurst
|
||||
# encodes party-wall cavity type with the masonry sub-code
|
||||
# (CU vs CF filled) — observed first on cert 001479 Main.
|
||||
"CF": 4, # Cavity masonry filled (cert 000565 Ext1) — RdSAP 10
|
||||
# Table 15 row 3 spec U=0.20. The cascade's `u_party_wall`
|
||||
# only returns 0.0 / 0.5 / 0.25 for code 4 today, so CF
|
||||
# rounds up to the conservative cavity-unfilled U=0.5 —
|
||||
# matches the existing `_API_PARTY_WALL_CONSTRUCTION_TO
|
||||
# _SAP10[3]` approximation until u_party_wall gains the
|
||||
# filled-cavity branch (TODO).
|
||||
# "U Unable to determine" — the cohort's modal lodgement. The cohort
|
||||
# hand-built convention uses 0 as the explicit "unknown" sentinel
|
||||
# (rather than None) so cross-mapper field parity is preserved; the
|
||||
|
|
@ -2178,10 +2207,19 @@ _ELMHURST_PARTY_WALL_CODE_TO_SAP10: Dict[str, int] = {
|
|||
|
||||
|
||||
def _elmhurst_party_wall_construction_int(coded: str) -> Optional[int]:
|
||||
"""Map an Elmhurst party-wall-type string to a SAP10 wall_construction
|
||||
integer. Returns None for 'U Unable to determine' (cascade default
|
||||
U=0.25 then applies) and for unrecognised codes."""
|
||||
return _ELMHURST_PARTY_WALL_CODE_TO_SAP10.get(_leading_code(coded))
|
||||
"""Map an Elmhurst party-wall-type string to a SAP10
|
||||
wall_construction integer. Returns None when lodging is absent
|
||||
(empty string — cascade default U=0.25 applies). Raises
|
||||
`UnmappedElmhurstLabel` when a non-empty code isn't recognised
|
||||
(same strict-coverage gate as `_elmhurst_wall_construction_int`;
|
||||
silent-None routes to the same cascade default but hides genuinely-
|
||||
new party-wall variants from the next fixture probe)."""
|
||||
code = _leading_code(coded)
|
||||
if not code:
|
||||
return None
|
||||
if code not in _ELMHURST_PARTY_WALL_CODE_TO_SAP10:
|
||||
raise UnmappedElmhurstLabel("walls.party_wall_type", coded)
|
||||
return _ELMHURST_PARTY_WALL_CODE_TO_SAP10[code]
|
||||
|
||||
|
||||
class UnmappedApiCode(ValueError):
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue