org.apache.spark.streamdm.clusterers
Data structure for managing all buckets for streamKM++ algorithm.
A Clusters trait defines the needed operations for maintaining a clustering data structure.
A MicroCluster contains the underlying structure for the Clustream processing framework, and summarizes a number of instances belonging to the same MicroCluster.
The MicroClusters object contains a number of microclusters in an Array.
A TreeCoreset contains the underlying tree structure for the coreset extraction framework.