Stop doing manual caching

pipeline/download/pois/config.py

@@ -4,31 +4,29 @@ DATA_DIR = Path("./data_sources")
 GB_PBF_FILE = DATA_DIR / "great-britain-latest.osm.pbf"
 OUTPUT_FILE = DATA_DIR / "uk_pois.parquet"
 
+
+BATCH_SIZE = 50_000
+
+MIN_OCCURENCE_COUNT = 20
+
 GEOFABRIK_GB_URL = (
     "https://download.geofabrik.de/europe/great-britain-latest.osm.pbf"
 )
 
-# UK bounding box (west, south, east, north) — used for way centroid filtering
 UK_BBOX_WEST = -7.57
 UK_BBOX_SOUTH = 49.96
 UK_BBOX_EAST = 1.68
 UK_BBOX_NORTH = 58.64
 
-# OSM tag keys that indicate a POI. Any element with one of these keys is kept,
-# regardless of the specific value.  When multiple keys match, their values are
-# concatenated with " / ".
 POI_TAG_KEYS: list[str] = [
     "amenity",
-    "shop",
-    "leisure",
-    "tourism",
-    "railway",
-    "aeroway",
-    "highway",
-    "public_transport",
-    "station",
     "building",
-    "military",
+    "craft",
     "emergency",
     "healthcare",
+    "leisure",
+    "office",
+    "shop",
+    "tourism",
+    "public_transport",
 ]