feat(epc-prediction): recency-weighted glazing mode (#1223)

Per-component method: glazing type is now the recency-weighted cohort mode
applied to every predicted window, rather than copied from the template.
Glazing is retrofitted over a dwelling's life (single -> double), so a
recent neighbour reflects the current state — same family as roof-insulation
thickness. Recency is the CORRECT weighting here: plain moding regressed the
fixture (-5.6pp) and was previously reverted; similarity weighting also
regressed it; recency improves BOTH (window geometry stays on the template,
only the glazing categorical moves).

modal_glazing_type: corpus (150pc/514) 60.7 -> 66.7% (+6.0pp); fixture
0.5000 -> 0.5278 (floor ratcheted up). Heating, geometry residuals and all
other components unchanged. Refactored _recency_weighted_mode to a reusable
_recency_weighted_choice(value_of) shared by roof insulation + glazing.

Closes the #1223 per-component approach: floor-area (median estimate) +
glazing (recency) shipped as distinct best-fit methods rather than a global
recency template, which would have disturbed the coherence-coupled heating
cluster.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

domain/epc_prediction/epc_prediction.py

@@ -15,7 +15,7 @@ import statistics
 from collections import Counter, defaultdict
 from dataclasses import dataclass
 from datetime import date
-from typing import Iterable, Optional, Union
+from typing import Callable, Iterable, Optional, Union
 
 from datatypes.epc.domain.epc_property_data import (
     EpcPropertyData,
@@ -64,9 +64,28 @@ class EpcPrediction:
         predicted: EpcPropertyData = copy.deepcopy(template.epc)
         predicted.total_floor_area_m2 = _median_floor_area(comparables.members)
         self._apply_categorical_modes(predicted, comparables)
+        self._apply_glazing_mode(predicted, comparables)
         self._apply_overrides(predicted, target)
         return predicted
 
+    @staticmethod
+    def _apply_glazing_mode(
+        predicted: EpcPropertyData, comparables: ComparableProperties
+    ) -> None:
+        """Set every window's glazing type to the recency-weighted cohort mode.
+        Glazing is retrofitted over a dwelling's life (single → double), so a
+        recent neighbour reflects the current state — its correct method is the
+        recency-weighted mode (like roof insulation), NOT the plain mode (which
+        regressed) or the template copy. The window geometry (size, count) is
+        left on the template; only the glazing categorical moves."""
+        glazing = _recency_weighted_choice(
+            comparables.members, _comparable_modal_glazing
+        )
+        if glazing is None:
+            return
+        for window in predicted.sap_windows:
+            window.glazing_type = glazing
+
     def confidence(
         self, comparables: ComparableProperties
     ) -> PredictionConfidence:
@@ -305,20 +324,23 @@ def _modal_share(
     return modal_count / len(present)
 
 
-def _recency_weighted_mode(
-    members: tuple[Comparable, ...], attr: str
+def _recency_weighted_choice(
+    members: tuple[Comparable, ...],
+    value_of: Callable[[Comparable], Optional[Union[int, str]]],
 ) -> Optional[Union[int, str]]:
-    """The cohort mode of a main-part attribute, weighting each comparable's vote
-    by recency — an exponential decay in the cert's age relative to the newest in
-    the cohort. Newer neighbours dominate, so a stale majority can't outvote the
-    current state. Falls back to a plain mode when no registration dates are
-    lodged (all ages 0 ⇒ equal weight)."""
+    """The recency-weighted cohort mode of a per-comparable value: each
+    neighbour's vote decays exponentially with the cert's age relative to the
+    newest in the cohort, so newer neighbours dominate and a stale majority can't
+    outvote the current state. Falls back to a plain mode when no registration
+    dates are lodged (all ages 0 ⇒ equal weight). Returns None when no comparable
+    supplies a value. Used for the time-varying components — those upgraded over a
+    dwelling's life (loft top-ups, glazing retrofits)."""
     newest: date = max(
         (c.registration_date or date.min for c in members), default=date.min
     )
     weights: dict[Union[int, str], float] = defaultdict(float)
     for comparable in members:
-        value = _main_part_attr(comparable, attr)
+        value = value_of(comparable)
         if value is None:
             continue
         lodged: date = comparable.registration_date or date.min
@@ -327,3 +349,22 @@ def _recency_weighted_mode(
     if not weights:
         return None
     return max(weights, key=lambda value: weights[value])
+
+
+def _recency_weighted_mode(
+    members: tuple[Comparable, ...], attr: str
+) -> Optional[Union[int, str]]:
+    """`_recency_weighted_choice` over a main building-part attribute."""
+    return _recency_weighted_choice(
+        members, lambda comparable: _main_part_attr(comparable, attr)
+    )
+
+
+def _comparable_modal_glazing(
+    comparable: Comparable,
+) -> Optional[Union[int, str]]:
+    """A comparable's modal glazing type — the most common across its windows, or
+    None when it lodges none. One glazing signal per neighbour, robust to a single
+    odd window, matching how the harness scores `modal_glazing_type`."""
+    types = [window.glazing_type for window in comparable.epc.sap_windows]
+    return Counter(types).most_common(1)[0][0] if types else None

tests/domain/epc_prediction/test_component_accuracy_gate.py

@@ -47,7 +47,7 @@ _RATE_FLOORS: dict[str, float] = {
     "roof_insulation_thickness": 0.4118,
     "floor_insulation": 0.9375,
     "has_room_in_roof": 0.8333,
-    "modal_glazing_type": 0.5000,
+    "modal_glazing_type": 0.5278,
     "has_pv": 1.0000,
     "solar_water_heating": 1.0000,
 }

tests/domain/epc_prediction/test_epc_prediction.py

@@ -348,6 +348,29 @@ def test_confidence_excludes_absent_component_values_from_the_denominator() -> N
     assert confidence.cohort_size == 3
 
 
+def test_glazing_follows_the_recency_weighted_cohort_mode() -> None:
+    # Arrange — an old majority single-glazed (type 1, 2015) and a recent
+    # minority double-glazed (type 3, 2025). Glazing is retrofitted over time
+    # (single → double), so the recent neighbours reflect the current state: the
+    # recency-weighted mode must pick double over the stale single-glazed
+    # majority, like roof insulation thickness.
+    cohort = _dated_cohort(
+        (_epc(glazing_type=1), date(2015, 1, 1)),
+        (_epc(glazing_type=1), date(2015, 1, 1)),
+        (_epc(glazing_type=1), date(2015, 1, 1)),
+        (_epc(glazing_type=3), date(2025, 1, 1)),
+        (_epc(glazing_type=3), date(2025, 1, 1)),
+    )
+
+    # Act
+    predicted: EpcPropertyData = EpcPrediction().predict(
+        PredictionTarget(postcode="LS6 1AA", property_type="2"), cohort
+    )
+
+    # Assert — every predicted window takes the recent glazing over the majority.
+    assert all(window.glazing_type == 3 for window in predicted.sap_windows)
+
+
 def test_applies_a_known_wall_override_over_the_mode() -> None:
     # Arrange — the cohort mode is cavity (1), but we KNOW the target is solid
     # brick (2), a Landlord Override. The known value must win over the estimate.