Codex changes

pipeline/transform/school_proximity.py

@@ -1,4 +1,4 @@
-"""Compute good-rated school proximity counts per postcode."""
+"""Compute Ofsted-rated school proximity counts per postcode."""
 
 import argparse
 from pathlib import Path
@@ -8,14 +8,16 @@ import polars as pl
 from pipeline.utils.poi_counts import count_pois_per_postcode
 
 SCHOOL_GROUPS = {
-    "good_primary": ["good_primary"],
-    "good_secondary": ["good_secondary"],
+    "good_primary": ["good_primary", "outstanding_primary"],
+    "good_secondary": ["good_secondary", "outstanding_secondary"],
+    "outstanding_primary": ["outstanding_primary"],
+    "outstanding_secondary": ["outstanding_secondary"],
 }
 
 
 def main():
     parser = argparse.ArgumentParser(
-        description="Count good+ primary/secondary schools within 2km per postcode"
+        description="Count good+ and outstanding primary/secondary schools near each postcode"
     )
     parser.add_argument(
         "--ofsted", type=Path, required=True, help="Ofsted inspection parquet"
@@ -39,12 +41,25 @@ def main():
     )
 
     print(f"Good+ schools: {len(ofsted):,}")
+    print(
+        "Outstanding schools: "
+        f"{ofsted.filter(pl.col('Latest OEIF overall effectiveness') == '1').height:,}"
+    )
 
-    # Assign category based on phase
+    # Assign category based on phase and rating. Good+ groups include both
+    # category variants; outstanding groups count grade 1 only.
     ofsted = ofsted.with_columns(
         pl.when(pl.col("Ofsted phase") == "Primary")
-        .then(pl.lit("good_primary"))
-        .otherwise(pl.lit("good_secondary"))
+        .then(
+            pl.when(pl.col("Latest OEIF overall effectiveness") == "1")
+            .then(pl.lit("outstanding_primary"))
+            .otherwise(pl.lit("good_primary"))
+        )
+        .otherwise(
+            pl.when(pl.col("Latest OEIF overall effectiveness") == "1")
+            .then(pl.lit("outstanding_secondary"))
+            .otherwise(pl.lit("good_secondary"))
+        )
         .alias("category")
     ).select(
         pl.col("Postcode").alias("postcode"),