mst_clustering: Clustering via Euclidean Minimum Spanning Trees
Jake Vanderplas · The Journal of Open Source Software · 2016
This package contains a Python implementation of a clustering algorithm based on an efficiently-constructed approximate Euclidean minimum spanning tree (described in The method produces a Hierarchical clustering of input data, and is quite similar to single-linkage Agglomerative clustering. The advantage of this implementation is the ability to find significant clusters even in the presence of background noise, and is particularly useful for researchers hoping to detect structure in physical data.