k-Medoids Clustering in Python with FasterPAM
copied from cf-staging / kmedoidsThis python package implements k-medoids clustering with PAM and variants of clustering by direct optimization of the (Medoid) Silhouette, including the DynMSC variant that automatically chooses the number of clusters (based on the optimum medoid silhouette). It can be used with arbitrary dissimilarites, as it only requires a dissimilarity matrix as input. A sklearn compatible API is included.
