mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-07-12 13:29:04 +00:00
ffaedd8d14
Measurement honesty so we optimise SAP-relevant accuracy, not SAP-neutral misses (ADR-0030 Component Accuracy): - Add construction_age_band_pm1: an exact-or-adjacent-band hit. Adjacent RdSAP age bands carry near-identical U-values, so an off-by-one is ~SAP-neutral. Full corpus: exact 78.5% but ±1-band 91.7% (fixture 63.9% -> 83.3%) — most age misses are adjacent. - Drop window_count from the gate's residual ceilings (cosmetic): the predicted picture clusters at a mapper-default 4 windows vs actuals 1-21, but total_window_area (the SAP-relevant signal) stays tight at ~3.4 m2. Gate: + construction_age_band_pm1 floor 0.8333; window_count no longer gated. Closes #1222 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
109 lines
4.1 KiB
Python
109 lines
4.1 KiB
Python
"""Tier-1 ratcheting Component Accuracy gate (ADR-0030).
|
|
|
|
Runs the calculator-free leave-one-out scorer over the committed, anonymised
|
|
fixture and asserts each per-component classification rate / geometry residual is
|
|
no worse than a committed baseline. Because the prediction is deterministic and
|
|
the fixture is frozen, every run reproduces the same numbers exactly — so a
|
|
failure means a real *regression* in prediction quality, never sample noise.
|
|
|
|
The floors / ceilings are the currently-measured values and only ever **tighten**
|
|
(the repo's no-tolerance-widening ethos applied to an aggregate): when prediction
|
|
improves, ratchet the relevant floor up in the same change. The end-to-end
|
|
SAP / carbon / PE guards are deliberately *not* here — they need the calculator,
|
|
whose API-path residual is a separate workstream; the component floors are the
|
|
real gate (ADR-0030).
|
|
"""
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from domain.epc_prediction.validation import (
|
|
ComponentAccuracy,
|
|
evaluate_component_accuracy,
|
|
)
|
|
from harness.epc_prediction_corpus import load_corpus
|
|
|
|
_FIXTURE = Path(__file__).parents[3] / "tests" / "fixtures" / "epc_prediction"
|
|
|
|
# Minimum classification hit-rate per component (ratchet floors). Tighten — never
|
|
# loosen — as prediction improves. Values are the measured rates over the frozen
|
|
# 36-target fixture; a 1e-3 tolerance absorbs float rounding only.
|
|
_RATE_FLOORS: dict[str, float] = {
|
|
"wall_construction": 0.8889,
|
|
"wall_insulation_type": 0.7778,
|
|
"construction_age_band": 0.6389,
|
|
"construction_age_band_pm1": 0.8333,
|
|
"roof_construction": 0.7222,
|
|
"floor_construction": 0.7500,
|
|
"heating_main_fuel": 0.9722,
|
|
"heating_main_category": 0.8889,
|
|
"heating_main_control": 0.7500,
|
|
"water_heating_fuel": 0.9167,
|
|
"water_heating_code": 0.8889,
|
|
"has_hot_water_cylinder": 0.8889,
|
|
"cylinder_insulation_type": 0.1667,
|
|
"secondary_heating_type": 0.0000,
|
|
"roof_insulation_thickness": 0.4118,
|
|
"floor_insulation": 0.9062,
|
|
"has_room_in_roof": 0.8333,
|
|
"modal_glazing_type": 0.5000,
|
|
"has_pv": 1.0000,
|
|
"solar_water_heating": 1.0000,
|
|
}
|
|
|
|
# Maximum mean absolute residual per numeric component (ratchet ceilings).
|
|
# window_count is deliberately excluded — it is cosmetic for SAP (issue #1222):
|
|
# the predicted picture clusters at a mapper-default 4 windows while actuals
|
|
# spread 1-21, yet total_window_area (the SAP-relevant signal) stays tight.
|
|
_RESIDUAL_CEILINGS: dict[str, float] = {
|
|
"floor_area": 12.2175,
|
|
"total_window_area": 4.4067,
|
|
"building_parts": 0.3333,
|
|
"door_count": 0.6389,
|
|
}
|
|
|
|
_TOLERANCE = 1e-3
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def accuracy() -> ComponentAccuracy:
|
|
if not (_FIXTURE / "_index.json").exists():
|
|
pytest.skip(f"no EPC Prediction fixture at {_FIXTURE}")
|
|
return evaluate_component_accuracy(load_corpus(_FIXTURE))
|
|
|
|
|
|
def test_fixture_yields_the_expected_target_count(
|
|
accuracy: ComponentAccuracy,
|
|
) -> None:
|
|
# The frozen fixture must still produce its full set of SAP-10.2 targets — a
|
|
# drop means the fixture or the target filter changed.
|
|
assert accuracy.targets >= 36
|
|
|
|
|
|
@pytest.mark.parametrize("component,floor", sorted(_RATE_FLOORS.items()))
|
|
def test_classification_rate_does_not_regress(
|
|
accuracy: ComponentAccuracy, component: str, floor: float
|
|
) -> None:
|
|
# Arrange / Act
|
|
rate = accuracy.rate(component)
|
|
|
|
# Assert — the component is still applicable and at or above its floor.
|
|
assert rate is not None, f"{component} had no applicable targets"
|
|
assert rate >= floor - _TOLERANCE, (
|
|
f"{component} classification regressed: {rate:.4f} < floor {floor:.4f}"
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize("component,ceiling", sorted(_RESIDUAL_CEILINGS.items()))
|
|
def test_residual_does_not_regress(
|
|
accuracy: ComponentAccuracy, component: str, ceiling: float
|
|
) -> None:
|
|
# Arrange / Act
|
|
mean_abs = accuracy.mean_abs_residual(component)
|
|
|
|
# Assert — the mean absolute residual is at or below its ceiling.
|
|
assert mean_abs is not None, f"{component} had no residuals"
|
|
assert mean_abs <= ceiling + _TOLERANCE, (
|
|
f"{component} residual regressed: {mean_abs:.4f} > ceiling {ceiling:.4f}"
|
|
)
|