Package elki.clustering.optics

Class OPTICSXi.ClusterHierarchyBuilder

java.lang.Object

elki.clustering.optics.OPTICSXi.ClusterHierarchyBuilder

Enclosing class:

OPTICSXi

private static class OPTICSXi.ClusterHierarchyBuilder
extends java.lang.Object

Class to build the hierarchical clustering result structure.

Author:

Erich Schubert

Field Summary

Fields

Modifier and Type	Field	Description
(package private) Clustering<OPTICSModel>	clustering	ELKI clustering object
(package private) java.util.HashSet<Cluster<OPTICSModel>>	curclusters	Current "unattached" clusters.
(package private) HashSetModifiableDBIDs	unclaimedids	Unclaimed objects that will be assigned to a top level or noise cluster in the end.

Constructor Summary

Constructors

Constructor	Description
ClusterHierarchyBuilder(DBIDs ids)	Constructor.

Method Summary

Modifier and Type	Method	Description
private void	addCluster(DBIDArrayIter tmp, int cstart, int cend)	Build a cluster object.
private Clustering<OPTICSModel>	build(ClusterOrder clusterOrder, DBIDArrayIter iter)	Build the main clustering result.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

clustering

Clustering<OPTICSModel> clustering

ELKI clustering object

curclusters

java.util.HashSet<Cluster<OPTICSModel>> curclusters

Current "unattached" clusters.

unclaimedids

HashSetModifiableDBIDs unclaimedids

Unclaimed objects that will be assigned to a top level or noise cluster in the end.

Constructor Detail

ClusterHierarchyBuilder

public ClusterHierarchyBuilder(DBIDs ids)

Constructor.

Parameters:

ids - All object ids (arbitrary order)

Method Detail

addCluster

private void addCluster(DBIDArrayIter tmp,
                        int cstart,
                        int cend)

Build a cluster object.

Parameters:

tmp - DBID array iterator

cstart - Interval start

cend - Interval end

build

private Clustering<OPTICSModel> build(ClusterOrder clusterOrder,
                                      DBIDArrayIter iter)

Build the main clustering result.

Parameters:

clusterOrder - Cluster order

iter - Array iterator for the cluster order

Returns:

Clustering