alright

pipeline/transform/transform_poi.py

@@ -1316,17 +1316,122 @@ 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(
+SCHOOL_ICON_CATEGORIES: dict[str, str] = {
+    "Nursery school": "🧸",
+    "Primary school": "🎒",
+    "Secondary school": "🏫",
+    "All-through school": "🏫",
+    "Sixth form": "📚",
+    "Further education college": "📚",
+    "University": "🎓",
+    "Special school": "🤝",
+    "School": "🏫",
+}
+
+
+def _school_icon_category_expr() -> pl.Expr:
+    """Pick an icon category from GIAS phase/type_group/age_range. type_group
+    wins for universities, FE colleges and special schools (which span multiple
+    phases); otherwise phase determines the bucket. For independent and other
+    non-statutory schools where GIAS leaves phase null, fall back to the
+    age_range bounds so they still split into the right pill."""
+    # GIAS phase mixes casing ("Middle deemed Primary" vs "Middle deemed
+    # primary") so we normalise before matching.
+    phase = pl.col("phase").str.to_lowercase()
+    # age_range is "<min>–<max>" using an em-dash; both ends may be missing.
+    age_parts = pl.col("age_range").str.split_exact("–", 1)
+    min_age = age_parts.struct.field("field_0").cast(pl.Int32, strict=False)
+    max_age = age_parts.struct.field("field_1").cast(pl.Int32, strict=False)
+    return (
+        pl.when(pl.col("type_group") == "Universities")
+        .then(pl.lit("University"))
+        .when(pl.col("type_group") == "Special schools")
+        .then(pl.lit("Special school"))
+        .when(pl.col("type_group") == "Colleges")
+        .then(pl.lit("Further education college"))
+        .when(phase == "nursery")
+        .then(pl.lit("Nursery school"))
+        .when(phase.is_in(["primary", "middle deemed primary"]))
+        .then(pl.lit("Primary school"))
+        .when(phase.is_in(["secondary", "middle deemed secondary"]))
+        .then(pl.lit("Secondary school"))
+        .when(phase == "all-through")
+        .then(pl.lit("All-through school"))
+        .when(phase.is_in(["16 plus", "sixth form"]))
+        .then(pl.lit("Sixth form"))
+        # Age-range fallback for null-phase rows (≈3k Independents + Academies
+        # GIAS doesn't classify by phase).
+        .when(max_age <= 5)
+        .then(pl.lit("Nursery school"))
+        .when(min_age >= 16)
+        .then(pl.lit("Sixth form"))
+        .when((min_age <= 6) & (max_age >= 16))
+        .then(pl.lit("All-through school"))
+        .when(max_age <= 11)
+        .then(pl.lit("Primary school"))
+        .when(min_age >= 10)
+        .then(pl.lit("Secondary school"))
+        .otherwise(pl.lit("School"))
+    )
+
+
+OFSTED_OEIF_LABELS = {
+    "1": "Outstanding",
+    "2": "Good",
+    "3": "Requires improvement",
+    "4": "Inadequate",
+}
+
+
+def _load_ofsted_ratings(ofsted_path: Path) -> pl.LazyFrame:
+    """Project the latest OEIF effectiveness grade to a human-readable label,
+    keyed by URN so it can be joined onto the GIAS register. Grades 1-4 map to
+    the conventional Ofsted labels; "Not judged" (post-2025 reform schools that
+    only have a report card) is preserved verbatim; null grades drop out."""
+    grade_col = pl.col("Latest OEIF overall effectiveness")
+    label = (
+        pl.when(grade_col == "1")
+        .then(pl.lit(OFSTED_OEIF_LABELS["1"]))
+        .when(grade_col == "2")
+        .then(pl.lit(OFSTED_OEIF_LABELS["2"]))
+        .when(grade_col == "3")
+        .then(pl.lit(OFSTED_OEIF_LABELS["3"]))
+        .when(grade_col == "4")
+        .then(pl.lit(OFSTED_OEIF_LABELS["4"]))
+        .when(grade_col == "Not judged")
+        .then(pl.lit("Not judged"))
+        .otherwise(None)
+    )
+    return (
+        pl.scan_parquet(ofsted_path)
+        .select(
+            pl.col("URN").cast(pl.Int64).alias("urn"),
+            label.alias("ofsted_rating"),
+        )
+        .filter(pl.col("ofsted_rating").is_not_null())
+    )
+
+
+def transform_gias_schools(gias_path: Path, ofsted_path: Path) -> pl.LazyFrame:
+    """Convert the GIAS register parquet into POI rows with school metadata.
+    Ofsted ratings are joined by URN so each school carries its latest OEIF
+    overall effectiveness grade (Outstanding/Good/Requires improvement/
+    Inadequate/Not judged), surfaced in the map popup."""
+    icon_category_expr = _school_icon_category_expr()
+    emoji_expr = icon_category_expr.replace_strict(SCHOOL_ICON_CATEGORIES)
+    ofsted = _load_ofsted_ratings(ofsted_path)
+    # category mirrors icon_category so the dashboard renders one toggle per
+    # school type (Nursery / Primary / Secondary / Sixth form / University /…)
+    # instead of bundling every GIAS row under a single "School" pill.
+    return pl.scan_parquet(gias_path).join(ofsted, on="urn", how="left").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"),
+        icon_category_expr.alias("category"),
+        icon_category_expr.alias("icon_category"),
         pl.lit("Education").alias("group"),
         pl.col("lat").cast(pl.Float64),
         pl.col("lng").cast(pl.Float64),
-        pl.lit("🏫").alias("emoji"),
+        emoji_expr.alias("emoji"),
         pl.col("phase").alias("school_phase"),
         pl.col("type").alias("school_type"),
         pl.col("type_group").alias("school_type_group"),
@@ -1346,6 +1451,7 @@ def transform_gias_schools(gias_path: Path) -> pl.LazyFrame:
         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"),
+        pl.col("ofsted_rating").alias("school_ofsted_rating"),
     )
 
 
@@ -1355,6 +1461,7 @@ def transform(
     boundary_path: Path,
     grocery_retail_points_path: Path,
     gias_path: Path,
+    ofsted_path: Path,
 ) -> pl.LazyFrame:
     lf = pl.scan_parquet(input_path)
 
@@ -1420,7 +1527,12 @@ def transform(
 
     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)]
+    frames = [
+        lf,
+        naptan,
+        grocery_pois.lazy(),
+        transform_gias_schools(gias_path, ofsted_path),
+    ]
 
     return pl.concat(frames, how="diagonal_relaxed")
 
@@ -1453,6 +1565,12 @@ def main():
         required=True,
         help="GIAS schools register parquet (replaces OSM schools)",
     )
+    parser.add_argument(
+        "--ofsted",
+        type=Path,
+        required=True,
+        help="Ofsted latest-inspections parquet (provides per-URN ratings)",
+    )
     parser.add_argument(
         "--output", type=Path, required=True, help="Output filtered POIs parquet file"
     )
@@ -1464,6 +1582,7 @@ def main():
         args.boundary,
         args.grocery_retail_points,
         args.gias,
+        args.ofsted,
     ).collect(engine="streaming")
 
     df.write_parquet(args.output)