Test changes

pipeline/transform/poi_proximity.py

@@ -1,6 +1,8 @@
 """Compute POI proximity counts and distances per postcode from ArcGIS + filtered POIs."""
 
 import argparse
+import re
+import unicodedata
 from pathlib import Path
 
 import polars as pl
@@ -15,9 +17,25 @@ POI_GROUPS_2KM = {
     "groceries": ["Greengrocer", "Supermarket", "Convenience Store"],
 }
 
-# Groups for which to compute distance to nearest POI (from filtered POIs)
+# Groups for which to compute distance to nearest POI (from filtered POIs).
+# Keep `train_tube` for the existing backend feature; the individual POI
+# distance filters below power the frontend dropdown.
 DISTANCE_GROUPS = {
     "train_tube": ["Tube station", "Rail station"],
+    "grocery_store": [
+        "Greengrocer",
+        "Supermarket",
+        "Convenience Store",
+        "Waitrose",
+        "Tesco",
+    ],
+    "tube_station": ["Tube station"],
+    "rail_station": ["Rail station"],
+    "waitrose": ["Waitrose"],
+    "tesco": ["Tesco"],
+    "cafe": ["Café"],
+    "pub": ["Pub"],
+    "restaurant": ["Restaurant"],
 }
 
 # OS Open Greenspace function types used for park counts and distance calculation.
@@ -27,6 +45,69 @@ GREENSPACE_PARK_FUNCTIONS = {
     "parks": ["Public Park Or Garden", "Playing Field", "Play Space"],
 }
 
+GROCERY_DYNAMIC_FILTER_MIN_POIS = 100
+DYNAMIC_FILTER_ALL_GROUPS = {"Public Transport", "Leisure"}
+DYNAMIC_FILTER_COUNT_THRESHOLD_GROUPS = {"Groceries"}
+
+
+def _poi_category_slug(category: str) -> str:
+    ascii_text = (
+        unicodedata.normalize("NFKD", category)
+        .encode("ascii", "ignore")
+        .decode("ascii")
+        .lower()
+    )
+    slug = re.sub(r"[^a-z0-9]+", "_", ascii_text).strip("_")
+    return slug or "poi"
+
+
+def _build_poi_category_groups(
+    pois: pl.DataFrame,
+) -> tuple[dict[str, list[str]], dict[str, str]]:
+    """Build one proximity group for each POI category selected for filters."""
+    if "group" not in pois.columns:
+        raise ValueError("POI dataframe must include a 'group' column")
+
+    categories = (
+        pois.group_by("group", "category")
+        .len()
+        .filter(
+            pl.col("group").is_in(list(DYNAMIC_FILTER_ALL_GROUPS))
+            | (
+                pl.col("group").is_in(list(DYNAMIC_FILTER_COUNT_THRESHOLD_GROUPS))
+                & (pl.col("len") > GROCERY_DYNAMIC_FILTER_MIN_POIS)
+            )
+        )
+        .select("category")
+        .sort("category")
+        .to_series()
+        .to_list()
+    )
+    used_slugs: dict[str, int] = {}
+    groups: dict[str, list[str]] = {}
+    display_names: dict[str, str] = {}
+
+    for category in categories:
+        if not isinstance(category, str) or not category:
+            continue
+        base_slug = f"poi_{_poi_category_slug(category)}"
+        slug_count = used_slugs.get(base_slug, 0)
+        used_slugs[base_slug] = slug_count + 1
+        group_key = base_slug if slug_count == 0 else f"{base_slug}_{slug_count + 1}"
+        groups[group_key] = [category]
+        display_names[group_key] = category
+
+    return groups, display_names
+
+
+def _dynamic_poi_metric_renames(display_names: dict[str, str]) -> dict[str, str]:
+    renames: dict[str, str] = {}
+    for group_key, category in display_names.items():
+        renames[f"{group_key}_nearest_km"] = f"Distance to nearest {category} POI (km)"
+        renames[f"{group_key}_2km"] = f"Number of {category} POIs within 2km"
+        renames[f"{group_key}_5km"] = f"Number of {category} POIs within 5km"
+    return renames
+
 
 def main():
     parser = argparse.ArgumentParser(
@@ -56,12 +137,35 @@ def main():
     )
 
     pois = pl.read_parquet(args.pois)
+    poi_category_groups, poi_display_names = _build_poi_category_groups(pois)
 
     # Count amenity POIs within 2km
     counts_2km = count_pois_per_postcode(
         postcodes, pois, groups=POI_GROUPS_2KM, radius_km=2
     )
 
+    # Dynamic POI filters: nearest distance plus counts within 2km and 5km for
+    # the selected public transport, grocery, and leisure categories.
+    dynamic_counts_2km = count_pois_per_postcode(
+        postcodes, pois, groups=poi_category_groups, radius_km=2
+    )
+    dynamic_counts_5km = count_pois_per_postcode(
+        postcodes, pois, groups=poi_category_groups, radius_km=5
+    )
+    dynamic_distances = min_distance_per_postcode(
+        postcodes, pois, groups=poi_category_groups
+    )
+    dynamic_renames = _dynamic_poi_metric_renames(poi_display_names)
+    dynamic_counts_2km = dynamic_counts_2km.rename(
+        {k: v for k, v in dynamic_renames.items() if k in dynamic_counts_2km.columns}
+    )
+    dynamic_counts_5km = dynamic_counts_5km.rename(
+        {k: v for k, v in dynamic_renames.items() if k in dynamic_counts_5km.columns}
+    )
+    dynamic_distances = dynamic_distances.rename(
+        {k: v for k, v in dynamic_renames.items() if k in dynamic_distances.columns}
+    )
+
     # Distance to nearest train/tube station (from filtered POIs)
     distances = min_distance_per_postcode(postcodes, pois, groups=DISTANCE_GROUPS)
 
@@ -77,6 +181,9 @@ def main():
     # Join all results on postcode
     result = (
         counts_2km.join(distances, on="postcode")
+        .join(dynamic_counts_2km, on="postcode")
+        .join(dynamic_counts_5km, on="postcode")
+        .join(dynamic_distances, on="postcode")
         .join(park_counts_1km, on="postcode")
         .join(park_distances, on="postcode")
     )