Package de.uni_mannheim.informatik.dws.melt.matching_jena_matchers.multisource.dispatchers.clustermerge

Class ClustererELKI

java.lang.Object

de.uni_mannheim.informatik.dws.melt.matching_jena_matchers.multisource.dispatchers.clustermerge.ClustererELKI

All Implemented Interfaces:

Clusterer

public class ClustererELKI
extends Object
implements Clusterer

Clusterer based on the ELKI library and always using the Andernberg algorithm.

Field Summary

Fields

Modifier and Type	Field	Description
private boolean	alwaysUseAnderberg
private static final org.slf4j.Logger	LOGGER

Constructor Summary

Constructors

Constructor	Description
ClustererELKI()
ClustererELKI(boolean alwaysUseAnderberg)	Constructor for ELKI which also needs information if anderberg should be always used or if also SLINK and CLINK should be used.

Method Summary

Modifier and Type	Method	Description
private de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction<de.lmu.ifi.dbs.elki.data.NumberVector>	getDistance(ClusterDistance linkage)
private de.lmu.ifi.dbs.elki.algorithm.clustering.hierarchical.linkage.Linkage	getLinkage(ClusterLinkage linkage)
MergeOrder	run(double[][] features, ClusterLinkage linkage, ClusterDistance distance)
static MergeOrder	transformPointerHierarchy(de.lmu.ifi.dbs.elki.algorithm.clustering.hierarchical.PointerHierarchyRepresentationResult r)

Methods inherited from class java.lang.Object

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

Field Details

LOGGER

private static final org.slf4j.Logger LOGGER

alwaysUseAnderberg

private boolean alwaysUseAnderberg

Constructor Details

ClustererELKI

public ClustererELKI()

ClustererELKI

public ClustererELKI(boolean alwaysUseAnderberg)

Constructor for ELKI which also needs information if anderberg should be always used or if also SLINK and CLINK should be used.

Parameters:

alwaysUseAnderberg - if true, only the anderberg algorithm is used. if false (default), then for single and complete linkage, SLINK/CLINK is used instead.

Method Details

run

public MergeOrder run(double[][] features,
 ClusterLinkage linkage,
 ClusterDistance distance)

Specified by:

run in interface Clusterer

transformPointerHierarchy

public static MergeOrder transformPointerHierarchy(de.lmu.ifi.dbs.elki.algorithm.clustering.hierarchical.PointerHierarchyRepresentationResult r)

getDistance

private de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction<de.lmu.ifi.dbs.elki.data.NumberVector> getDistance(ClusterDistance linkage)

getLinkage

private de.lmu.ifi.dbs.elki.algorithm.clustering.hierarchical.linkage.Linkage getLinkage(ClusterLinkage linkage)