Package elki.clustering.kmedoids

Class FasterPAM<O>

java.lang.Object

elki.clustering.kmedoids.PAM<O>

elki.clustering.kmedoids.FastPAM1<O>

elki.clustering.kmedoids.FastPAM<O>

elki.clustering.kmedoids.FasterPAM<O>

Type Parameters:

O - object datatype

All Implemented Interfaces:

Algorithm, ClusteringAlgorithm<Clustering<MedoidModel>>, KMedoidsClustering<O>

Direct Known Subclasses:

FasterCLARA

@Reference(authors="Erich Schubert and Peter J. Rousseeuw",
           title="Fast and Eager k-Medoids Clustering: O(k) Runtime Improvement of the PAM, CLARA, and CLARANS Algorithms",
           booktitle="arXiv preprint",
           url="https://arxiv.org/abs/2008.05171",
           bibkey="DBLP:journals/corr/abs-2008-05171")
public class FasterPAM<O>
extends FastPAM<O>

Variation of FastPAM that eagerly performs any swap that yields an improvement during an iteration. Compared to EagerPAM it considers all current medoids together, and chooses the best of these; hence apart from computing candidate swaps O(k) times faster, it will also be able to sometimes choose better swaps.

Reference:

Erich Schubert and Peter J. Rousseeuw
Fast and Eager k-Medoids Clustering: O(k) Runtime Improvement of the PAM, CLARA, and CLARANS Algorithms
Preprint

Since:

0.8.0

Author:

Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
protected static class	FasterPAM.Instance	Instance for a single dataset.
static class	FasterPAM.Par<O>	Parameterization class.

Nested classes/interfaces inherited from interface elki.Algorithm

Algorithm.Utils

Field Summary

Fields

Modifier and Type	Field	Description
private static java.lang.String	KEY	Key for statistics logging.
private static Logging	LOG	The logger for this class.

Fields inherited from class elki.clustering.kmedoids.FastPAM

fasttol

Fields inherited from class elki.clustering.kmedoids.PAM

distance, initializer, k, maxiter

Constructor Summary

Constructors

Constructor	Description
FasterPAM(Distance<? super O> distance, int k, int maxiter, KMedoidsInitialization<O> initializer)	Constructor.

Method Summary

Modifier and Type	Method	Description
protected Logging	getLogger()	Get the static class logger.
Clustering<MedoidModel>	run(Relation<O> relation, int k, DistanceQuery<? super O> distQ)	Run k-medoids clustering with a given distance query. Not a very elegant API, but needed for some types of nested k-medoids.

Methods inherited from class elki.clustering.kmedoids.PAM

getInputTypeRestriction, initialMedoids, run, wrapResult

Methods inherited from class java.lang.Object

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

Methods inherited from interface elki.clustering.ClusteringAlgorithm

autorun

Field Detail

LOG

private static final Logging LOG

The logger for this class.

KEY

private static final java.lang.String KEY

Key for statistics logging.

Constructor Detail

FasterPAM

public FasterPAM(Distance<? super O> distance,
                 int k,
                 int maxiter,
                 KMedoidsInitialization<O> initializer)

Constructor.

Parameters:

distance - distance function

k - k parameter

maxiter - Maxiter parameter

initializer - Function to generate the initial means

Method Detail

run

public Clustering<MedoidModel> run(Relation<O> relation,
                                   int k,
                                   DistanceQuery<? super O> distQ)

Description copied from interface: KMedoidsClustering

Run k-medoids clustering with a given distance query.
Not a very elegant API, but needed for some types of nested k-medoids.

Specified by:

run in interface KMedoidsClustering<O>

Overrides:

run in class FastPAM<O>

Parameters:

relation - relation to use

k - Number of clusters

distQ - Distance query to use

Returns:

result

getLogger

protected Logging getLogger()

Description copied from class: PAM

Get the static class logger.

Overrides:

getLogger in class FastPAM<O>