All good

pipeline/transform/join_epc_pp.py

@@ -10,6 +10,8 @@ import pyarrow as pa
 import pyarrow.csv as pa_csv
 import pyarrow.parquet as pq
 
+from pipeline.local_temp import local_tmp_dir
+
 from ..utils import (
     fuzzy_join_on_postcode,
     normalize_address_key,
@@ -192,7 +194,9 @@ def main():
     )
     args = parser.parse_args()
 
-    with tempfile.TemporaryDirectory(prefix="epc_certificates_") as tmpdir:
+    with tempfile.TemporaryDirectory(
+        prefix="epc_certificates_", dir=local_tmp_dir()
+    ) as tmpdir:
         _run(args.epc, args.price_paid, args.output, Path(tmpdir))
 
 

pipeline/transform/postcode_boundaries/uprn.py

@@ -3,6 +3,8 @@ from pathlib import Path
 import numpy as np
 import polars as pl
 
+from pipeline.local_temp import local_tmp_dir
+
 from .memory import release_memory
 
 
@@ -17,7 +19,9 @@ def load_uprns(uprn_path: Path) -> tuple[pl.DataFrame, dict[str, tuple[int, int]
     print("Loading UPRN lookup...")
 
     # Sort via streaming sink to avoid polars doubling memory during in-memory sort
-    with tempfile.NamedTemporaryFile(suffix=".parquet", delete=False) as tmp:
+    with tempfile.NamedTemporaryFile(
+        suffix=".parquet", delete=False, dir=local_tmp_dir()
+    ) as tmp:
         tmp_path = Path(tmp.name)
     (
         pl.scan_parquet(uprn_path)

pipeline/transform/test_transform_poi.py

@@ -79,6 +79,39 @@ def test_transform_grocery_retail_points_keeps_fascia_icon_category():
     ]
 
 
+def test_transform_grocery_retail_points_merges_cooperative_societies():
+    raw = pl.DataFrame(
+        {
+            "id": [101, 102, 103],
+            "retailer": [
+                "Central England Co-operative",
+                "Lincolnshire Co-operative",
+                "The Southern Co-operative",
+            ],
+            "fascia": [
+                "Central England Co-operative",
+                "The Co-operative Food",
+                None,
+            ],
+            "store_name": [
+                "Central Co-op Test",
+                "Lincolnshire Co-op Test",
+                "Southern Co-op Test",
+            ],
+            "long_wgs": [-0.141, -0.142, -0.143],
+            "lat_wgs": [51.515, 51.516, 51.517],
+        }
+    )
+
+    pois = transform_grocery_retail_points(raw, min_chain_locations=1)
+
+    assert pois.select("category", "icon_category").to_dicts() == [
+        {"category": "Co-op", "icon_category": "Co-op"},
+        {"category": "Co-op", "icon_category": "Co-op"},
+        {"category": "Co-op", "icon_category": "Co-op"},
+    ]
+
+
 def test_transform_grocery_retail_points_accepts_base_fascias():
     raw = pl.DataFrame(
         {

pipeline/transform/transform_poi.py

@@ -623,6 +623,7 @@ _CATEGORIES: list[tuple[str, str, str, list[str]]] = [
             "shop/outpost",
             "shop/pawnbroker",
             "shop/photo",
+            "shop/photo_studio",
             "shop/plant_hire",
             "shop/printer_ink",
             "shop/printing",
@@ -843,6 +844,7 @@ _CATEGORIES: list[tuple[str, str, str, list[str]]] = [
         [
             "healthcare/physiotherapist",
             "healthcare/podiatrist",
+            "healthcare/occupational_therapist",
         ],
     ),
     (
@@ -1171,7 +1173,6 @@ GROCERY_RETAILER_DISPLAY_NAME_OVERRIDES: dict[str, str] = {
     "Heron": "Heron Foods",
     "Marks and Spencer": "M&S",
     "Sainsburys": "Sainsbury's",
-    "The Co-operative Group": "Co-op",
 }
 
 
@@ -1238,6 +1239,8 @@ def normalize_grocery_retailer(retailer: str | None) -> str:
     if retailer is None:
         return ""
     retailer = retailer.strip()
+    if retailer in COOP_RETAILERS:
+        return "Co-op"
     return GROCERY_RETAILER_DISPLAY_NAME_OVERRIDES.get(retailer, retailer)