More fixes

pipeline/transform/merge.py

@@ -186,11 +186,11 @@ def _build(
     lsoa_pop = pl.scan_parquet(lsoa_population_path)
     wide = wide.join(lsoa_pop, on="lsoa21", how="left")
     wide = wide.with_columns(
-        (pl.col("serious_crime_avg_yr") / pl.col("population") * 1000)
-        .round(1)
+        pl.when(pl.col("population") > 0)
+        .then((pl.col("serious_crime_avg_yr") / pl.col("population") * 1000).round(1))
         .alias("serious_crime_per_1k"),
-        (pl.col("minor_crime_avg_yr") / pl.col("population") * 1000)
-        .round(1)
+        pl.when(pl.col("population") > 0)
+        .then((pl.col("minor_crime_avg_yr") / pl.col("population") * 1000).round(1))
         .alias("minor_crime_per_1k"),
     ).drop("population")
 

pipeline/utils/download.py

@@ -37,4 +37,4 @@ def extract_zip(zip_path: Path, extract_dir: Path) -> None:
     """Extract a ZIP archive into the given directory."""
     extract_dir.mkdir(parents=True, exist_ok=True)
     with zipfile.ZipFile(zip_path, "r") as zf:
-        zf.extractall(extract_dir)
+        zf.extractall(extract_dir, filter="data")

pipeline/utils/fuzzy_join.py

@@ -84,7 +84,7 @@ def fuzzy_join_on_postcode(
             right_match["_right_postcode"],
             right_match["_right_address"],
         ):
-            if postcode is not None:
+            if address is not None and postcode is not None:
                 right_by_postcode.setdefault(postcode, []).append((idx, address))
 
         # Group left side by postcode