Class KMedoidsKMedoidsInitialization<O>
- java.lang.Object
-
- elki.clustering.kmedoids.initialization.KMedoidsKMedoidsInitialization<O>
-
- All Implemented Interfaces:
KMedoidsInitialization<O>
@Title("K-medoids Initialization by K-medoids") @Description("Initialize k-medoids with k-medoids, usually a less expensive variant.") public class KMedoidsKMedoidsInitialization<O> extends java.lang.Object implements KMedoidsInitialization<O>
Initialize k-medoids with k-medoids, for methods such as PAMSIL.
This could also be used to initialize, e.g., PAM with CLARA.TODO: this could be made more useful by adding a sampling option.
- Since:
- 0.8.0
- Author:
- Erich Schubert
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description static class
KMedoidsKMedoidsInitialization.Par<O>
Parameterization class.
-
Field Summary
Fields Modifier and Type Field Description private KMedoidsClustering<O>
inner
Inner k-medoids clustering to use.
-
Constructor Summary
Constructors Constructor Description KMedoidsKMedoidsInitialization(KMedoidsClustering<O> inner)
Constructor.
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description DBIDs
chooseInitialMedoids(int k, DBIDs ids, DistanceQuery<? super O> distance)
Choose initial means
-
-
-
Field Detail
-
inner
private KMedoidsClustering<O> inner
Inner k-medoids clustering to use.
-
-
Constructor Detail
-
KMedoidsKMedoidsInitialization
public KMedoidsKMedoidsInitialization(KMedoidsClustering<O> inner)
Constructor.- Parameters:
inner
- Inner clustering
-
-
Method Detail
-
chooseInitialMedoids
public DBIDs chooseInitialMedoids(int k, DBIDs ids, DistanceQuery<? super O> distance)
Description copied from interface:KMedoidsInitialization
Choose initial means- Specified by:
chooseInitialMedoids
in interfaceKMedoidsInitialization<O>
- Parameters:
k
- Parameter kids
- Candidate IDs.distance
- Distance function- Returns:
- List of chosen means for k-means
-
-