Package elki.clustering.kmeans

Class KDTreeFilteringKMeans<V extends elki.data.NumberVector>

java.lang.Object

elki.clustering.kmeans.AbstractKMeans<V,KMeansModel>

elki.clustering.kmeans.KDTreePruningKMeans<V>

elki.clustering.kmeans.KDTreeFilteringKMeans<V>

Type Parameters:

V - vector datatype

All Implemented Interfaces:

elki.Algorithm, ClusteringAlgorithm<Clustering<KMeansModel>>, KMeans<V,KMeansModel>

@Title("K-d-tree K-means with Filtering")
@Reference(authors="D. Pelleg, A. Moore",title="Accelerating Exact k-means Algorithms with Geometric Reasoning",booktitle="Proc. ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining",url="https://doi.org/10.1145/312129.312248",bibkey="DBLP:conf/kdd/PellegM99") @Reference(authors="T. Kanungo, D. M. Mount, N. S. Netanyahu, C. D. Piatko, R. Silverman, A. Y. Wu",title="Computing Nearest Neighbors for Moving Points and Applications to Clustering",booktitle="Proc. 10th ACM-SIAM Symposium on Discrete Algorithms (SODA\'99)",url="http://dl.acm.org/citation.cfm?id=314500.315095",bibkey="DBLP:conf/soda/KanungoMNPSW99") @Reference(authors="T. Kanungo, D. M. Mount, N. S. Netanyahu, C. D. Piatko, R. Silverman, A. Y. Wu",title="An Efficient k-Means Clustering Algorithm: Analysis and Implementation",booktitle="IEEE Transactions on Pattern Analysis and Machine Intelligence 24(7)",url="https://doi.org/10.1109/TPAMI.2002.1017616",bibkey="DBLP:journals/pami/KanungoMNPSW02")
public class KDTreeFilteringKMeans<V extends elki.data.NumberVector>
extends KDTreePruningKMeans<V>

Filtering or "blacklisting" K-means with k-d-tree acceleration.

This is an implementation of the slightly later (1999) variant of Pelleg and Moore respectively Kanungo et al. using hyperplanes for filtering instead of a similar approach using minimum and maximum distances published in 1997 by Alsabti et al., see KDTreePruningKMeans.

References:

D. Pelleg and A. Moore
Accelerating Exact k-means Algorithms with Geometric Reasoning
Proc. ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining

T. Kanungo, D. M. Mount, N. S. Netanyahu, C. D. Piatko, R. Silverman, A. Y. Wu
Computing Nearest Neighbors for Moving Points and Applications to Clustering
Proc. 10th ACM-SIAM Symposium on Discrete Algorithms (SODA'99)

A more detailed analysis appeared later in:

T. Kanungo, D. M. Mount, N. S. Netanyahu, C. D. Piatko, R. Silverman, A. Y. Wu
An Efficient k-Means Clustering Algorithm: Analysis and Implementation
IEEE Transactions on Pattern Analysis and Machine Intelligence 24(7)

Since:

0.8.0

Author:

Cedrik Lüdicke (initial version), Erich Schubert (optimizations, rewrite)

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
protected class	KDTreeFilteringKMeans.Instance	Inner instance, storing state for a single data set.
static class	KDTreeFilteringKMeans.Par<V extends elki.data.NumberVector>	Parameterization class.

Nested classes/interfaces inherited from class elki.clustering.kmeans.KDTreePruningKMeans

KDTreePruningKMeans.KDNode, KDTreePruningKMeans.Split

Nested classes/interfaces inherited from interface elki.Algorithm

elki.Algorithm.Utils

Field Summary

Fields

Modifier and Type	Field	Description
private static elki.logging.Logging	LOG	The logger for this class.

Fields inherited from class elki.clustering.kmeans.KDTreePruningKMeans

leafsize, split

Fields inherited from class elki.clustering.kmeans.AbstractKMeans

distance, initializer, k, maxiter

Fields inherited from interface elki.clustering.kmeans.KMeans

DISTANCE_FUNCTION_ID, INIT_ID, K_ID, MAXITER_ID, SEED_ID, VARSTAT_ID

Constructor Summary

Constructors

Constructor	Description
KDTreeFilteringKMeans(elki.distance.NumberVectorDistance<? super V> distance, int k, int maxiter, KMeansInitialization initializer, KDTreePruningKMeans.Split split, int leafsize)	Constructor.

Method Summary

Modifier and Type	Method	Description
protected elki.logging.Logging	getLogger()	Get the (STATIC) logger for this class.
Clustering<KMeansModel>	run(elki.database.relation.Relation<V> relation)	Run the clustering algorithm.

Methods inherited from class elki.clustering.kmeans.AbstractKMeans

getDistance, getInputTypeRestriction, incrementalUpdateMean, initialMeans, means, minusEquals, nearestMeans, plusEquals, plusMinusEquals, setDistance, setInitializer, setK

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 elki.logging.Logging LOG

The logger for this class.

Constructor Detail

KDTreeFilteringKMeans

public KDTreeFilteringKMeans(elki.distance.NumberVectorDistance<? super V> distance,
                             int k,
                             int maxiter,
                             KMeansInitialization initializer,
                             KDTreePruningKMeans.Split split,
                             int leafsize)

Constructor.

Parameters:

distance - distance function

k - k parameter

maxiter - Maxiter parameter

initializer - Initialization method

split - Splitting strategy

leafsize - Leaf size

Method Detail

run

public Clustering<KMeansModel> run(elki.database.relation.Relation<V> relation)

Description copied from interface: KMeans

Run the clustering algorithm.

Specified by:

run in interface KMeans<V extends elki.data.NumberVector,KMeansModel>

Overrides:

run in class KDTreePruningKMeans<V extends elki.data.NumberVector>

Parameters:

relation - Relation to process.

Returns:

Clustering result

getLogger

protected elki.logging.Logging getLogger()

Description copied from class: AbstractKMeans

Get the (STATIC) logger for this class.

Overrides:

getLogger in class KDTreePruningKMeans<V extends elki.data.NumberVector>

Returns:

the static logger