Package de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans

K-means clustering and variations.

See: Description

Interface Summary

Interface	Description
KMeans	Some constants and options shared among kmeans family algorithms.
KMeansInitialization<V>	Interface for initializing K-Means
KMedoidsInitialization<V>	Interface for initializing K-Medoids.

Class Summary

Class	Description
AbstractKMeans<V extends NumberVector<V,?>,D extends Distance<D>>	Abstract base class for k-means implementations.
AbstractKMeansInitialization<V>	Abstract base class for common k-means initializations.
AbstractKMeansInitialization.Parameterizer<V>	Parameterization class.
FirstKInitialMeans<V>	Initialize K-means by using the first k objects as initial means.
FirstKInitialMeans.Parameterizer<V extends NumberVector<V,?>>	Parameterization class.
KMeansLloyd<V extends NumberVector<V,?>,D extends Distance<D>>	Provides the k-means algorithm, using Lloyd-style bulk iterations.
KMeansLloyd.Parameterizer<V extends NumberVector<V,?>,D extends Distance<D>>	Parameterization class.
KMeansMacQueen<V extends NumberVector<V,?>,D extends Distance<D>>	Provides the k-means algorithm, using MacQueen style incremental updates.
KMeansMacQueen.Parameterizer<V extends NumberVector<V,?>,D extends Distance<D>>	Parameterization class.
KMeansPlusPlusInitialMeans<V,D extends NumberDistance<D,?>>	K-Means++ initialization for k-means.
KMeansPlusPlusInitialMeans.Parameterizer<V,D extends NumberDistance<D,?>>	Parameterization class.
KMediansLloyd<V extends NumberVector<V,?>,D extends Distance<D>>	Provides the k-medians clustering algorithm, using Lloyd-style bulk iterations.
KMediansLloyd.Parameterizer<V extends NumberVector<V,?>,D extends Distance<D>>	Parameterization class.
KMedoidsEM<V,D extends NumberDistance<D,?>>	Provides the k-medoids clustering algorithm, using a "bulk" variation of the "Partitioning Around Medoids" approach.
KMedoidsEM.Parameterizer<V,D extends NumberDistance<D,?>>	Parameterization class.
KMedoidsPAM<V,D extends NumberDistance<D,?>>	Provides the k-medoids clustering algorithm, using the "Partitioning Around Medoids" approach.
KMedoidsPAM.Parameterizer<V,D extends NumberDistance<D,?>>	Parameterization class.
PAMInitialMeans<V,D extends NumberDistance<D,?>>	PAM initialization for k-means (and of course, PAM).
PAMInitialMeans.Parameterizer<V,D extends NumberDistance<D,?>>	Parameterization class.
RandomlyChosenInitialMeans<V>	Initialize K-means by randomly choosing k exsiting elements as cluster centers.
RandomlyChosenInitialMeans.Parameterizer<V>	Parameterization class.
RandomlyGeneratedInitialMeans<V extends NumberVector<V,?>>	Initialize k-means by generating random vectors (within the data sets value range).
RandomlyGeneratedInitialMeans.Parameterizer<V extends NumberVector<V,?>>	Parameterization class.

Package de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans Description

K-means clustering and variations.