Commit graph

8 commits

Author SHA1 Message Date
Jun-te Kim
7baab9376c Backfill uniform secondary-glazing overrides misfiled as Single glazing
39 Hyde-796 property_overrides rows ('100% secondary glazing (sap 9.94)')
plus the classifier-cache row; the cache phase self-gates on the
'Secondary glazing' pgEnum label landing (assessment-model#345).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-02 11:12:25 +00:00
Jun-te Kim
c1169b2d39
Merge pull request #1402 from Hestia-Homes/fix/glazing-dominant-single-guard
Resolve dominant-single glazing deterministically in the mix guard
2026-07-02 10:19:16 +01:00
Jun-te Kim
0fa47b1047
Merge pull request #1409 from Hestia-Homes/fix/property-type-leading-token-guard
Guard property_type to its leading dwelling-type token
2026-07-02 10:00:03 +01:00
Jun-te Kim
deec22302a Resolve dominant double/triple glazing when the era is stated
Addresses PR #1402 review: the guard only claimed dominant-single, leaving
the symmetric bug open — the LLM can flatten a dominant-double/triple split
onto its minority single (e.g. "96% Double glazing 2002 or later, 4% Single").

A dominant double/triple whose era is explicit ("pre-2002" / "2002 or later")
is just as fully determined as era-free single, so the guard now claims it via
_DOMINANT_MEMBER. Only a genuinely ambiguous era ("unknown age", unstated) still
defers to the LLM — the "96% double -> None" contract now holds solely for the
era-unknown case, not the era-stated one.

Backfill script reuses the same guard, so it now corrects any dominant split;
renamed reclassify_dominant_single_glazing.py -> reclassify_dominant_glazing.py
to match. Tests cover double/triple x pre-2002/2002-or-later and the still-
deferred unknown-age case; 14 green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-02 08:07:13 +00:00
Jun-te Kim
88bae2166f Guard property_type to its leading dwelling-type token
The landlord property-type description is a "<dwelling type>: <built form>: <floor>"
split whose leading token IS the dwelling type; the built-form tail is not. The
LLM occasionally over-read the tail and flipped the type — a handful of
"Bungalow: EndTerrace" / "Bungalow: MidTerrace" dwellings were stored as House.

Adds property_type_guard (claims the recognised leading token: House / Bungalow /
Flat / Maisonette / Park home; defers unrecognised phrasings to the LLM) and wires
property_type through a GuardedColumnClassifier, so the built-form tail can never
flip the type and the live path is deterministic.

Applied the scoped backfill to portfolio 796 (Hyde): 3 rows corrected from House
back to Bungalow. No enum migration needed — the targets are original members.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-01 17:24:37 +00:00
Jun-te Kim
5330bc20d9 Add individual wood-logs main-fuel archetype (API 6 / RdSAP Table 32 code 20)
MainFuelType had no individual wood-logs member — only "biomass (community)" —
so the LLM classifier funnelled "Solid Fuel: Wood Logs" into the community fuel,
inventing a community heat network the dwelling isn't on (and mislabelling the
connection). main_fuel had no deterministic guard at all, so nothing caught it.

Verified against domain/sap10_calculator/docs/specs: RdSAP 10 Specification
Table 32 lists "wood logs" as a solid fuel (code 20, 0.028 kgCO2e/kWh); the
calculator's input scheme (the gov EPC API fuel enum) codes it 6 -> Table 32 20
(sap_efficiencies._API_TO_TABLE32), and water_heating_overlay already pins the
same fuel to 6. So _FUEL_CODES["wood logs"] = 6 is confirmed, not guessed.

Adds MainFuelType.WOOD_LOGS + the _FUEL_CODES entry, a main_fuel_guard mirroring
water_heating_guard (claims the "wood log" token; dual fuel keeps its own member
since it has no "wood log" substring), and wires main_fuel through a
GuardedColumnClassifier so the live path is deterministic.

Applied the scoped backfill to portfolio 796 (Hyde): 21 rows off
"biomass (community)" -> "wood logs". property_overrides (TEXT) only; the
classifier-cache pgEnum member is deferred to the FE Drizzle migration.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-01 17:00:24 +00:00
Jun-te Kim
646f66ff89 Resolve dominant-single glazing deterministically in the mix guard
A landlord glazing split like "4% Double glazing 2002 or later, 96% Single
Glazing" is a near-uniform *single*-glazing dwelling, but the LLM classifier
latched onto the 4% minority and wrote a "Double glazing…" override — over-
crediting the dwelling.

glazing_mix_guard rescued genuine mixes (no type >= 90%) to MIXED but returned
None for near-uniform splits, trusting the LLM to have applied the dominant type.
It hadn't. Single glazing is era-free, so a dominant-single split is fully
determined: the guard now returns SINGLE for it (dominant double/triple still
carry era ambiguity, so they stay the LLM's job — the existing "96% double" case
still defers).

Adds a portfolio-scoped backfill (reuses the same guard, so it can't drift from
the live path) and applied it to portfolio 796 (Hyde): 115 glazing overrides
corrected from a spurious Double back to Single.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-01 15:59:18 +00:00
Jun-te Kim
0e85da1507 Resolve a landlord mains-gas override to the primary fuel code 🟩
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 12:15:54 +00:00