has issues

pipeline/transform/transform_poi.py

@@ -182,6 +182,19 @@ DROP_CATEGORIES = {
     "public_transport/platform",
     "public_transport/station",
     "public_transport/stop_position",
+    # Education amenities — schools come from GIAS instead. OSM coverage for
+    # tertiary education, tutoring, and childcare is too noisy/incomplete to be
+    # useful on a property-search map.
+    "amenity/school",
+    "amenity/prep_school",
+    "amenity/language_school",
+    "amenity/music_school",
+    "amenity/university",
+    "amenity/college",
+    "building/university",
+    "amenity/kindergarten",
+    "amenity/childcare",
+    "office/tutoring",
 }
 
 
@@ -943,23 +956,10 @@ _CATEGORIES: list[tuple[str, str, str, list[str]]] = [
             "tourism/chalet",
         ],
     ),
-    (
-        "Education",
-        "School",
-        "🏫",
-        [
-            "amenity/school",
-            "amenity/prep_school",
-            "amenity/language_school",
-            "amenity/music_school",
-            "amenity/university",
-            "amenity/college",
-            "building/university",
-            "amenity/kindergarten",
-            "amenity/childcare",
-            "office/tutoring",
-        ],
-    ),
+    # Note: schools come from the GIAS register (see transform_gias_schools).
+    # Niche/tertiary education amenities that GIAS does not cover are dropped
+    # rather than mixed in with state-funded schools.
+
     (
         "Local Businesses",
         "Hotel",
@@ -1316,11 +1316,45 @@ def transform_grocery_retail_points(
     ).select("id", "name", "category", "icon_category", "group", "lat", "lng", "emoji")
 
 
+def transform_gias_schools(gias_path: Path) -> pl.LazyFrame:
+    """Convert the GIAS register parquet into POI rows with school metadata."""
+    return pl.scan_parquet(gias_path).select(
+        pl.concat_str([pl.lit("gias-"), pl.col("urn").cast(pl.String)]).alias("id"),
+        pl.col("name"),
+        pl.lit("School").alias("category"),
+        pl.lit("School").alias("icon_category"),
+        pl.lit("Education").alias("group"),
+        pl.col("lat").cast(pl.Float64),
+        pl.col("lng").cast(pl.Float64),
+        pl.lit("🏫").alias("emoji"),
+        pl.col("phase").alias("school_phase"),
+        pl.col("type").alias("school_type"),
+        pl.col("type_group").alias("school_type_group"),
+        pl.col("age_range").alias("school_age_range"),
+        pl.col("gender").alias("school_gender"),
+        pl.col("religious_character").alias("school_religious_character"),
+        pl.col("admissions_policy").alias("school_admissions_policy"),
+        pl.col("nursery_provision").alias("school_nursery_provision"),
+        pl.col("sixth_form").alias("school_sixth_form"),
+        pl.col("capacity").cast(pl.Int32, strict=False).alias("school_capacity"),
+        pl.col("pupils").cast(pl.Int32, strict=False).alias("school_pupils"),
+        pl.col("fsm_percent").cast(pl.Float32, strict=False).alias("school_fsm_percent"),
+        pl.col("trust").alias("school_trust"),
+        pl.col("address").alias("school_address"),
+        pl.col("postcode").alias("school_postcode"),
+        pl.col("local_authority").alias("school_local_authority"),
+        pl.col("website").alias("school_website"),
+        pl.col("telephone").cast(pl.String, strict=False).alias("school_telephone"),
+        pl.col("head_name").alias("school_head_name"),
+    )
+
+
 def transform(
     input_path: Path,
-    naptan_path: Path | None = None,
-    boundary_path: Path | None = None,
-    grocery_retail_points_path: Path | None = None,
+    naptan_path: Path,
+    boundary_path: Path,
+    grocery_retail_points_path: Path,
+    gias_path: Path,
 ) -> pl.LazyFrame:
     lf = pl.scan_parquet(input_path)
 
@@ -1372,24 +1406,21 @@ def transform(
     )
 
     naptan_df = pl.scan_parquet(naptan_path).collect()
-    if boundary_path is not None:
-        mask = in_england_mask(
-            boundary_path,
-            naptan_df["lat"].to_numpy(),
-            naptan_df["lng"].to_numpy(),
-        )
-        naptan_df = naptan_df.filter(pl.Series(mask))
+    mask = in_england_mask(
+        boundary_path,
+        naptan_df["lat"].to_numpy(),
+        naptan_df["lng"].to_numpy(),
+    )
+    naptan_df = naptan_df.filter(pl.Series(mask))
     naptan = naptan_df.lazy().with_columns(
         pl.col("category").replace_strict(NAPTAN_EMOJIS).alias("emoji"),
         pl.lit("Public Transport").alias("group"),
         pl.col("category").alias("icon_category"),
     )
 
-    frames = [lf, naptan]
-    if grocery_retail_points_path is not None:
-        grocery_df = pl.read_parquet(grocery_retail_points_path)
-        grocery_pois = transform_grocery_retail_points(grocery_df, boundary_path)
-        frames.append(grocery_pois.lazy())
+    grocery_df = pl.read_parquet(grocery_retail_points_path)
+    grocery_pois = transform_grocery_retail_points(grocery_df, boundary_path)
+    frames = [lf, naptan, grocery_pois.lazy(), transform_gias_schools(gias_path)]
 
     return pl.concat(frames, how="diagonal_relaxed")
 
@@ -1413,8 +1444,15 @@ def main():
     parser.add_argument(
         "--grocery-retail-points",
         type=Path,
+        required=True,
         help="GEOLYTIX Grocery Retail Points parquet",
     )
+    parser.add_argument(
+        "--gias",
+        type=Path,
+        required=True,
+        help="GIAS schools register parquet (replaces OSM schools)",
+    )
     parser.add_argument(
         "--output", type=Path, required=True, help="Output filtered POIs parquet file"
     )
@@ -1425,6 +1463,7 @@ def main():
         args.naptan,
         args.boundary,
         args.grocery_retail_points,
+        args.gias,
     ).collect(engine="streaming")
 
     df.write_parquet(args.output)