Clustering

Clustering is done using the scikit-learn clustering library. Other clustering classes can be used as long as they adhere to the same interface (Methods: fit; Attributes: cluster_centers_, labels_).

For example, MiniBatchKMeans can be directly passed to the cluster command of MetricData:

metricdata.cluster(MiniBatchKMeans(n_clusters=1000), mergesmall=3)

Contents:

• KCenters clustering method
• RegCluster regular sized clustering