From eb3cf7b7d9bad1b8e00553b411bf3cc6fed0c4da Mon Sep 17 00:00:00 2001
From: marvin <marvin@nubo.sh>
Date: Sun, 13 Sep 2026 23:15:29 +0200
Subject: [PATCH] Cluster same-name stops within 50m into single markers

Same-name stops within 50m (opposite sides of a road, different
platforms/entrances) are now merged into one marker at the cluster
centroid. Uses scipy hierarchical clustering (single linkage, distance
criterion).

Stop counts after clustering:
  bus:  1610 -> 892 markers
  metro:   91 ->  46 markers
  s_tog:   76 ->  34 markers
  regional: 27 ->  10 markers

Threshold configurable via styling.yaml stations.stop_cluster_m.
---
 copenhagen/config/styling.yaml |  1 +
 copenhagen/scripts/render.py   | 54 ++++++++++++++++++++++++++++++----
 2 files changed, 50 insertions(+), 5 deletions(-)

diff --git a/copenhagen/config/styling.yaml b/copenhagen/config/styling.yaml
index b79a479..e318b5c 100644
--- a/copenhagen/config/styling.yaml
+++ b/copenhagen/config/styling.yaml
@@ -73,6 +73,7 @@ basemap:
 stations:
   show: true              # draw station markers (symbols without text)
   styles: [metro, s_tog, regional, bus]
+  stop_cluster_m: 50       # merge same-name stops within this distance (opposite sides of road)
   marker:
     shape: circle         # circle | square
     fill: white
diff --git a/copenhagen/scripts/render.py b/copenhagen/scripts/render.py
index 9292ccf..79dd3ff 100644
--- a/copenhagen/scripts/render.py
+++ b/copenhagen/scripts/render.py
@@ -169,6 +169,26 @@ def classify_station(r):
     return None
 
 
+def cluster_stops(coords, threshold_m):
+    """Cluster (x, y) coordinates within threshold_m; return list of centroids."""
+    from scipy.cluster.hierarchy import fcluster, linkage
+    from scipy.spatial.distance import pdist
+
+    coords = np.asarray(coords)
+    if len(coords) <= 1:
+        return coords.tolist() if len(coords) else []
+
+    dists = pdist(coords)
+    links = linkage(dists, method="single")
+    labels = fcluster(links, t=threshold_m, criterion="distance")
+
+    centroids = []
+    for label in set(labels):
+        members = coords[labels == label]
+        centroids.append(members.mean(axis=0).tolist())
+    return centroids
+
+
 def plot_stations(ax, stations, styling, active_styles):
     if stations is None or stations.empty:
         return
@@ -176,6 +196,7 @@ def plot_stations(ax, stations, styling, active_styles):
     if not cfg.get("show", True):
         return
     marker_styles = set(cfg.get("styles", ["metro", "s_tog", "regional"]))
+    cluster_m = cfg.get("stop_cluster_m", 50)
     mk = cfg.get("marker", {})
     sizes = mk.get("size", {})
     shape = mk.get("shape", "circle")
@@ -184,19 +205,30 @@ def plot_stations(ax, stations, styling, active_styles):
     lw = mk.get("linewidth", 0.8)
     marker = "o" if shape == "circle" else "s"
 
+    # group coordinates by style, then by name for clustering
     pts_by_style = {}
+    names_by_style = {}
     for _, r in stations.iterrows():
         s = classify_station(r)
         if s is None or s not in marker_styles or s not in active_styles:
             continue
-        pts_by_style.setdefault(s, []).append((r.geometry.x, r.geometry.y))
+        coord = (r.geometry.x, r.geometry.y)
+        name = r.get("name") if isinstance(r.get("name"), str) else None
+        pts_by_style.setdefault(s, []).append(coord)
+        names_by_style.setdefault(s, {}).setdefault(name, []).append(coord)
 
     zord = styling["zorder"]
     top_z = max(zord.values()) + 1  # all markers above all lines
     for s in sorted(pts_by_style, key=lambda k: zord.get(k, 0)):
-        pts = pts_by_style[s]
+        # cluster same-name stations to one marker; keep unnamed as-is
+        centroids = []
+        for name, coords in names_by_style[s].items():
+            if name and len(coords) > 1:
+                centroids.extend(cluster_stops(coords, cluster_m))
+            else:
+                centroids.extend(coords)
         sz = sizes.get(s, 3.0)
-        ax.scatter([p[0] for p in pts], [p[1] for p in pts],
+        ax.scatter([p[0] for p in centroids], [p[1] for p in centroids],
                    s=sz ** 2, marker=marker, c=fill, edgecolors=edge,
                    linewidths=lw, zorder=top_z, alpha=1.0)
 
@@ -212,6 +244,7 @@ def plot_bus_stops(ax, stops, styling, active_styles):
     if bus.empty:
         return
 
+    cluster_m = cfg.get("stop_cluster_m", 50)
     mk = cfg.get("marker", {})
     sizes = mk.get("size", {})
     sz = sizes.get("bus", 1.5)
@@ -221,8 +254,19 @@ def plot_bus_stops(ax, stops, styling, active_styles):
     shape = mk.get("shape", "circle")
     marker = "o" if shape == "circle" else "s"
     top_z = max(styling["zorder"].values()) + 1
-    ax.scatter(bus.geometry.x, bus.geometry.y, s=sz ** 2, marker=marker,
-               c=fill, edgecolors=edge, linewidths=lw, zorder=top_z, alpha=0.8)
+
+    # cluster same-name bus stops within threshold (opposite sides of road)
+    centroids = []
+    for name, grp in bus.groupby("name"):
+        coords = [(r.geometry.x, r.geometry.y) for _, r in grp.iterrows()]
+        if name and len(coords) > 1:
+            centroids.extend(cluster_stops(coords, cluster_m))
+        else:
+            centroids.extend(coords)
+
+    ax.scatter([p[0] for p in centroids], [p[1] for p in centroids],
+               s=sz ** 2, marker=marker, c=fill, edgecolors=edge,
+               linewidths=lw, zorder=top_z, alpha=0.8)
 
 
 def label_stations(ax, stations, styling, active_styles):