Copenhagen Phase 2: prepare.py merges + clips + colours -> master.gpkg

- prepare.py: merge per-mode OSM lines, resolve colours
  (GTFS route_color -> OSM colour tag -> keyed palette, robust to pd.NA),
  categorise buses (A/C/S/regular via regex), clip lines+stops to area,
  write master.gpkg layers (lines/stops/stations)
- download_osm.py: add stations query (public_transport=station /
  railway=station nodes+areas, out center) -> stations.gpkg with proper
  human-readable names + subway/light_rail mode tags for labelling
- verified: 135 lines (8 metro/16 s-tog/28 regional/83 bus), 90 named
  stations, zero NaN colours

copenhagen/scripts/download_osm.py

@@ -126,14 +126,64 @@ def parse(data, mode):
     return lines, stops
 
 
+def stations_query(bbox):
+    s, n, w, e = bbox
+    return f"""[out:json][timeout:180];
+(
+  node["railway"="station"]({s},{w},{n},{e});
+  node["public_transport"="station"]({s},{w},{n},{e});
+  way["railway"="station"]({s},{w},{n},{e});
+  way["public_transport"="station"]({s},{w},{n},{e});
+);
+out center;
+"""
+
+
+def parse_stations(data):
+    """Stations (nodes or area centroids) with proper human-readable names."""
+    rows = []
+    seen = set()
+    for e in data["elements"]:
+        if e["type"] not in ("node", "way"):
+            continue
+        tags = e.get("tags", {})
+        name = tags.get("name")
+        if not name:
+            continue
+        if e["type"] == "node":
+            geom = Point(e["lon"], e["lat"])
+        else:
+            c = e.get("center")
+            if not c:
+                continue
+            geom = Point(c["lon"], c["lat"])
+        key = (name, round(geom.x, 5), round(geom.y, 5))
+        if key in seen:
+            continue
+        seen.add(key)
+        rows.append({
+            "name": name,
+            "railway": tags.get("railway"),
+            "public_transport": tags.get("public_transport"),
+            "station": tags.get("station"),
+            "subway": tags.get("subway"),
+            "light_rail": tags.get("light_rail"),
+            "train": tags.get("train"),
+            "uic_ref": tags.get("uic_ref"),
+            "geometry": geom,
+        })
+    return rows
+
+
 def main():
     modes = yaml.safe_load((CONFIG / "modes.yaml").read_text())["modes"]
     area = gpd.read_file(PROCESSED / "area.gpkg")
     w, s, e, n = area.total_bounds  # (minx, miny, maxx, maxy) = (west, south, east, north)
+    bbox = (s, n, w, e)
 
     OSM_RAW.mkdir(parents=True, exist_ok=True)
     for mode, cfg in modes.items():
-        ql = build_query(cfg, (s, n, w, e))
+        ql = build_query(cfg, bbox)
         (OSM_RAW / f"{mode}.overpassql").write_text(ql)
         print(f"[{mode}] querying Overpass bbox=({s:.4f},{w:.4f},{n:.4f},{e:.4f})...", flush=True)
         data = overpass(ql)
@@ -146,6 +196,18 @@ def main():
         if stops:
             sgdf = gpd.GeoDataFrame(stops, crs="EPSG:4326")
             sgdf.to_file(OSM_RAW / f"{mode}.gpkg", driver="GPKG", layer="stops")
+
+    # stations (named station nodes/areas) for labelling
+    sql = stations_query(bbox)
+    (OSM_RAW / "stations.overpassql").write_text(sql)
+    print("[stations] querying Overpass...", flush=True)
+    sdata = overpass(sql)
+    st = parse_stations(sdata)
+    print(f"  -> {len(st)} named stations", flush=True)
+    if st:
+        gpd.GeoDataFrame(st, crs="EPSG:4326").to_file(
+            OSM_RAW / "stations.gpkg", driver="GPKG", layer="stations"
+        )
     print("done.")