From d8f015fb0ed316b97219031396975b01ec00ac77 Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Mon, 15 Jun 2026 15:07:22 +0000
Subject: [PATCH] feat(epc-prediction): report floor-area MAE + MAPE vs typical
 size

Adds a floor_area line giving MAE (m2), MAPE (% of actual), and the typical
(median actual) size, so the absolute error reads relative to dwelling size.
Corpus: MAE 10.48 m2 / MAPE 13.2% / typical 61 m2.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 scripts/validate_epc_prediction.py | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/scripts/validate_epc_prediction.py b/scripts/validate_epc_prediction.py
index 04433607..3c817078 100644
--- a/scripts/validate_epc_prediction.py
+++ b/scripts/validate_epc_prediction.py
@@ -29,6 +29,7 @@ from pathlib import Path
 from typing import Optional
 
 from datatypes.epc.domain.epc_property_data import EpcPropertyData
+from domain.epc_prediction.comparable_properties import Comparable
 from domain.epc_prediction.validation import (
     evaluate_component_accuracy,
     iter_predictions,
@@ -70,6 +71,7 @@ def main() -> None:
         if total:
             print(f"CLASSIFICATION  {name}: {hits}/{total} = {hits / total:.1%}")
     print()
+    _floor_area_error(cohorts)
     _residual("floor_area (m2)", accuracy.residuals.get("floor_area", []))
     _residual("window_count", accuracy.residuals.get("window_count", []))
     _residual(
@@ -131,6 +133,28 @@ def main() -> None:
     _sap_line("  floor: PEI |calc(actual) − lodged|", pei_floor)
 
 
+def _floor_area_error(cohorts: list[list[Comparable]]) -> None:
+    """Floor-area accuracy as MAE (m²) and MAPE (% of the actual), plus the
+    typical (median actual) size — so the absolute error can be read relative to
+    how big dwellings are. The predicted area is the cohort median, set
+    independently of the geo/similarity weighting that drives the categoricals."""
+    pairs = [
+        (predicted.total_floor_area_m2, actual.total_floor_area_m2)
+        for predicted, actual in iter_predictions(cohorts)
+    ]
+    valid = [(p, a) for p, a in pairs if a]
+    if not valid:
+        print("RESIDUAL  floor_area: (none)")
+        return
+    mae = statistics.mean(abs(p - a) for p, a in valid)
+    mape = statistics.mean(abs(p - a) / a for p, a in valid)
+    typical = statistics.median(a for _, a in valid)
+    print(
+        f"RESIDUAL  floor_area: MAE {mae:.2f} m2 | MAPE {mape:.1%} | "
+        f"typical (median actual) {typical:.0f} m2 (n={len(valid)})"
+    )
+
+
 def _residual(label: str, values: list[float]) -> None:
     if not values:
         print(f"RESIDUAL  {label}: (none)")