From 4bc208b8fd492c3f126951d1d90e7ed4236c9312 Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Thu, 28 Aug 2025 23:17:15 +0100
Subject: [PATCH] pass averages to lighting cleaner

---
 backend/Property.py                                | 6 +++++-
 backend/tests/test_integration.py                  | 5 -----
 etl/epc_clean/epc_attributes/LightingAttributes.py | 3 +++
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/backend/Property.py b/backend/Property.py
index 6d17f0e2..c6542bb8 100644
--- a/backend/Property.py
+++ b/backend/Property.py
@@ -9,6 +9,7 @@ from etl.epc.Dataset import TrainingDataset
 from etl.epc.Record import EPCRecord
 from etl.epc.settings import LATEST_FIELD, MANDATORY_FIXED_FEATURES
 from etl.epc_clean.epc_attributes.all_cleaners import all_cleaner_map
+from etl.epc_clean.tests.test_lighting_attributes import averages
 from utils.logger import setup_logger
 from utils.s3 import read_dataframe_from_s3_parquet
 from etl.epc.settings import DATA_ANOMALY_MATCHES
@@ -624,7 +625,10 @@ class Property:
             if len(attributes) == 0:
                 # We attempt to perform the clean on the fly
                 cleaner_cls = all_cleaner_map[description]
-                cleaner_cls = cleaner_cls(self.data[description])
+                if description == "lighting-description":
+                    cleaner_cls = cleaner_cls(self.data[description], averages=None)
+                else:
+                    cleaner_cls = cleaner_cls(self.data[description])
                 processed = {
                     "original_description": self.data[description],
                     "clean_description": cleaner_cls.description.replace(
diff --git a/backend/tests/test_integration.py b/backend/tests/test_integration.py
index f0c25ac0..45bc7325 100644
--- a/backend/tests/test_integration.py
+++ b/backend/tests/test_integration.py
@@ -174,11 +174,6 @@ for p in input_properties:
     input_properties
 ]
 
-for p in tqdm(input_properties):
-    # TEMP
-    p.DATA_ANOMALY_MATCHES = DATA_ANOMALY_MATCHES
-    p.set_features(cleaned=cleaned, kwh_client=kwh_client, kwh_predictions=mocked_kwh_predictions)
-
 # Run the recommendations
 recommendations = {}
 recommendations_scoring_data = []
diff --git a/etl/epc_clean/epc_attributes/LightingAttributes.py b/etl/epc_clean/epc_attributes/LightingAttributes.py
index 712c6daa..78b31142 100644
--- a/etl/epc_clean/epc_attributes/LightingAttributes.py
+++ b/etl/epc_clean/epc_attributes/LightingAttributes.py
@@ -28,6 +28,9 @@ class LightingAttributes(Definitions):
         self.nodata = (not description) or (description in self.DATA_ANOMALY_MATCHES) or (
             description in self.OBSERVED_ERRORS) or (description == "SAP05:Lighting")
 
+        if description == "SAP05:Lighting":
+            self.description = description  # Reset self.description
+
     def welsh_translation_search(self):
         """
         For welsh text describing the percentage of low energy lighting, we match the regular