Package elki.clustering.hierarchical

Class LinearMemoryNNChain.Instance<O extends NumberVector>

java.lang.Object

elki.clustering.hierarchical.LinearMemoryNNChain.Instance<O>

Type Parameters:

O - vector type

Enclosing class:

LinearMemoryNNChain<O extends NumberVector>

public static class LinearMemoryNNChain.Instance<O extends NumberVector>
extends java.lang.Object

Main worker instance of NNChain.

Author:

Erich Schubert

Field Summary

Fields

Modifier and Type	Field	Description
private GeometricLinkage	linkage	Linkage method.

Constructor Summary

Constructors

Constructor	Description
Instance(GeometricLinkage linkage)	Constructor.

Method Summary

Modifier and Type	Method	Description
protected void	merge(int end, double[][] clusters, ClusterMergeHistoryBuilder builder, int[] clustermap, double mindist, int x, int y)	Execute the cluster merge.
private void	nnChainCore(DBIDArrayIter aIt, DBIDArrayIter aIt2, ClusterMergeHistoryBuilder builder, Relation<O> rel)	Core function of NNChain.
ClusterMergeHistory	run(ArrayDBIDs ids, Relation<O> relation, ClusterMergeHistoryBuilder builder)

Methods inherited from class java.lang.Object

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

Field Detail

linkage

private GeometricLinkage linkage

Linkage method.

Constructor Detail

Instance

public Instance(GeometricLinkage linkage)

Constructor.

Parameters:

linkage - Linkage

Method Detail

run

public ClusterMergeHistory run(ArrayDBIDs ids,
                               Relation<O> relation,
                               ClusterMergeHistoryBuilder builder)

nnChainCore

private void nnChainCore(DBIDArrayIter aIt,
                         DBIDArrayIter aIt2,
                         ClusterMergeHistoryBuilder builder,
                         Relation<O> rel)

Core function of NNChain.

Parameters:

aIt - Iterator to access relation objects

aIt2 - Iterator to access relation objects

builder - Result builder

merge

protected void merge(int end,
                     double[][] clusters,
                     ClusterMergeHistoryBuilder builder,
                     int[] clustermap,
                     double mindist,
                     int x,
                     int y)

Execute the cluster merge.

Parameters:

end - Active set size

clusters - Array of cluster centers

builder - Hierarchy builder

clustermap - Cluster assignment

mindist - Distance that was used for merging

x - First matrix position

y - Second matrix position