Update script and data

threaded.py

@@ -8,6 +8,12 @@ Compares two GeoJSON files containing road data and identifies:
 
 Only reports differences that are significant (above minimum length threshold).
 Optimized for performance with parallel processing and spatial indexing.
+
+TODO:
+- put properties properly on removed roads, so they're visible in JOSM
+- handle polygons properly (on previous geojson step?) for circular roads
+- ignore roads that aren't LIFECYCLE ACTV or Active
+- include OneWay=Y
 """
 
 import json
@@ -15,7 +21,7 @@ import argparse
 from pathlib import Path
 from typing import List, Dict, Any, Tuple
 import geopandas as gpd
-from shapely.geometry import LineString, MultiLineString, Point
+from shapely.geometry import LineString, MultiLineString, Point, Polygon
 from shapely.ops import unary_union
 from shapely.strtree import STRtree
 import pandas as pd
@@ -35,7 +41,7 @@ warnings.filterwarnings('ignore')
 import re
 def titlecase(s):
     return re.sub(
-        r"[A-Za-z]+('[A-Za-z]+)?",
+        r"[A-Za-z0-9]+('[A-Za-z0-9]+)?",
         lambda word: word.group(0).capitalize(),
         s)
 
@@ -70,8 +76,8 @@ class RoadComparator:
             # Use pyogr engine for faster loading of large files
             gdf = gpd.read_file(filepath, engine='pyogrio')
             
-            # Filter only LineString and MultiLineString geometries
-            line_types = ['LineString', 'MultiLineString']
+            # Filter only LineString, MultiLineString, and Polygon geometries
+            line_types = ['LineString', 'MultiLineString', 'Polygon']
             gdf = gdf[gdf.geometry.type.isin(line_types)].copy()
             
             if len(gdf) == 0:
@@ -202,7 +208,7 @@ class RoadComparator:
             if isinstance(geom, MultiLineString):
                 lines = list(geom.geoms)
             else:
-                lines = [geom]
+                lines = [geom] # Polygon and Line can be accessed directly
             
             for line in lines:
                 try:
@@ -302,8 +308,8 @@ class RoadComparator:
                     
                     # Include the entire road if:
                     # 1. The uncovered portion is above minimum threshold, AND
-                    # 2. More than 50% of the road is uncovered
-                    if uncovered_ratio > 0.5:
+                    # 2. More than 10% of the road is uncovered
+                    if uncovered_ratio > 0.1:
                         #uncovered_length >= min_length_deg and 
                         # Include entire original road with all original metadata
                         original_properties = dict(row.drop('geometry'))