Class KMC2
- java.lang.Object
-
- elki.clustering.kmeans.initialization.AbstractKMeansInitialization
-
- elki.clustering.kmeans.initialization.KMC2
-
- All Implemented Interfaces:
KMeansInitialization
- Direct Known Subclasses:
AFKMC2
@Title("K-MC\u00b2") @Reference(authors="O. Bachem, M. Lucic, S. H. Hassani, A. Krause", title="Approximate K-Means++ in Sublinear Time", booktitle="Proc. 30th AAAI Conference on Artificial Intelligence", url="http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12147", bibkey="DBLP:conf/aaai/BachemLHK16") public class KMC2 extends AbstractKMeansInitialization
K-MC² initializationReference:
O. Bachem, M. Lucic, S. H. Hassani, A. Krause
Approximate K-Means++ in Sublinear Time
Proc. 30th AAAI Conference on Artificial Intelligence- Since:
- 0.8.0
- Author:
- Erich Schubert
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description protected static class
KMC2.Instance
Abstract instance implementing the weight handling.static class
KMC2.Par
Parameterization class.
-
Field Summary
Fields Modifier and Type Field Description private static Logging
LOG
Class logger.protected int
m
Number of sampling attempts.-
Fields inherited from class elki.clustering.kmeans.initialization.AbstractKMeansInitialization
rnd
-
-
Constructor Summary
Constructors Constructor Description KMC2(int m, RandomFactory rnd)
Constructor.
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description double[][]
chooseInitialMeans(Relation<? extends NumberVector> relation, int k, NumberVectorDistance<?> distance)
Choose initial means-
Methods inherited from class elki.clustering.kmeans.initialization.AbstractKMeansInitialization
unboxVectors
-
-
-
-
Field Detail
-
LOG
private static final Logging LOG
Class logger.
-
m
protected int m
Number of sampling attempts.
-
-
Constructor Detail
-
KMC2
public KMC2(int m, RandomFactory rnd)
Constructor.- Parameters:
m
- M parameterrnd
- Random generator.
-
-
Method Detail
-
chooseInitialMeans
public double[][] chooseInitialMeans(Relation<? extends NumberVector> relation, int k, NumberVectorDistance<?> distance)
Description copied from interface:KMeansInitialization
Choose initial means- Parameters:
relation
- Relationk
- Parameter kdistance
- Distance function- Returns:
- List of chosen means for k-means
-
-