Spatial Clustering Explorer
Upload a point file — .geojson, or a shapefile as a single .zip or as .shp/.dbf/.shx selected together — set a distance radius (ε) and a minimum group size, and find which points cluster together in space. Points that don’t belong to any dense-enough group are marked as noise, not forced into the nearest cluster.
Private by design. Your file is processed entirely in your browser (Python via WebAssembly) — it’s never uploaded to any server, including ours. Nothing to configure, nothing to trust: the code never gets the chance to see your data.
The code itself isn’t shown here — it’s a fixed, non-editable computation using scikit-learn’s DBSCAN underneath. Want to see it built up step by step, in Python and R? Read Finding Spatial Clusters with DBSCAN.
First run loads the Python engine — expect about a minute. Instant after that, and again each time you come back to this page.
Entry tool in the GeoML family — finds groups without knowing their labels ahead of time. Want to predict a label instead? Try Spatial Classifier. Want to understand why noise points aren’t forced into a cluster, see the actual code, or compare against R’s independent dbscan implementation (and the label-numbering difference between the two)? Read the full article.