Highlight possibly-conflicting (nearby) addresses in yellow

compare-addresses.py

@@ -27,6 +27,9 @@ import warnings
 warnings.filterwarnings('ignore')
 
 
+CONFLICT_RADIUS_METERS = 5.0
+
+
 class AddressComparator:
     def __init__(self, tolerance_meters: float = 500.0):
         self.tolerance_meters = tolerance_meters
@@ -62,6 +65,27 @@ class AddressComparator:
         s = re.sub(r'\s+', ' ', s).strip()
         return s
 
+    @staticmethod
+    def _flag_close_conflicts(addresses: List[Dict], radius_meters: float = CONFLICT_RADIUS_METERS) -> None:
+        """Mark each address dict's 'conflict' key True when another point in the
+        same list falls within radius_meters. Doesn't dedupe or exclude anything -
+        just surfaces tight clusters (e.g. ambiguous source data reusing the same
+        unit label across distinct points) for manual review in the map UI."""
+        if not addresses:
+            return
+        geoms = [a['geometry'] for a in addresses]
+        tree = STRtree(geoms)
+        radius_deg = radius_meters / 111000.0
+        for i, addr in enumerate(addresses):
+            conflict = False
+            for j in tree.query(geoms[i].buffer(radius_deg)):
+                if j == i:
+                    continue
+                if geoms[i].distance(geoms[j]) * 111000.0 <= radius_meters:
+                    conflict = True
+                    break
+            addr['conflict'] = conflict
+
     def compare_addresses(self, local_file: str, osm_file: str) -> Tuple[List[Dict], List[Dict], List[Dict]]:
         """Compare local and OSM address data.
 
@@ -175,6 +199,8 @@ class AddressComparator:
                 props['status'] = 'removed'
                 removed_addresses.append({'geometry': osm_row.geometry, **props})
 
+        self._flag_close_conflicts(new_addresses)
+
         return new_addresses, existing_addresses, removed_addresses
 
     def save_results(self, new_addresses, existing_addresses, removed_addresses, output_dir):