Last night

pipeline/utils/poi_counts.py

@@ -1,14 +1,12 @@
 """Count POIs within a radius of properties, optimized via postcode deduplication."""
 
-import tempfile
-
 import numpy as np
 import polars as pl
 
 from .haversine import haversine_km
 
 
-def _count_pois_per_postcode(
+def count_pois_per_postcode(
     postcodes_df: pl.DataFrame,
     pois: pl.DataFrame,
     groups: dict[str, list[str]],
@@ -64,9 +62,7 @@ def _count_pois_per_postcode(
     pc_codes = postcodes_df["postcode"].to_list()
 
     # Initialize result arrays
-    result_counts = {
-        group: np.zeros(n_postcodes, dtype=np.int32) for group in groups
-    }
+    result_counts = {group: np.zeros(n_postcodes, dtype=np.int32) for group in groups}
 
     # Process in batches with progress
     batch_size = 50000
@@ -128,47 +124,3 @@ def _count_pois_per_postcode(
     result = pl.DataFrame(result_data)
     print("  Completed POI counting")
     return result
-
-
-def count_pois_within_radius(
-    properties: pl.DataFrame, pois: pl.DataFrame, radius_km: float = 2.0
-) -> dict[str, pl.Series]:
-    """
-    Count POIs within radius for properties, optimized by deduplicating postcodes.
-
-    Returns dict of {column_name: count_series} aligned to properties dataframe.
-    """
-    # Get unique postcodes with coordinates
-    print("Deduplicating postcodes...")
-    unique_postcodes = properties.select(["postcode", "lat", "lon"]).unique(
-        subset=["postcode"]
-    )
-
-    print(
-        f"  {len(properties):,} properties → {len(unique_postcodes):,} unique postcodes"
-    )
-
-    # Count POIs per postcode
-    postcode_counts = _count_pois_per_postcode(unique_postcodes, pois, radius_km)
-
-    print("  Writing postcode counts to temp file...")
-    with tempfile.NamedTemporaryFile(suffix=".parquet") as tmp:
-        tmp_path = tmp.name
-        postcode_counts.write_parquet(tmp_path)
-
-        # Join using lazy evaluation
-        print("  Joining counts back to properties (lazy)...")
-        count_cols = [f"{group}_{int(radius_km)}km" for group in POI_GROUPS]
-
-        # Convert properties to lazy frame, join, then collect
-        result_lazy = (
-            properties.lazy()
-            .select("postcode")
-            .join(pl.scan_parquet(tmp_path), on="postcode", how="left")
-            .select(count_cols)
-            .fill_null(0)
-        )
-
-        result_df = result_lazy.collect(engine="streaming")
-
-        return {col: result_df[col] for col in count_cols}