Package elki.clustering.kmeans

Class HartiganWongKMeans<V extends NumberVector>

  • Type Parameters:
    V - Number vector type
    All Implemented Interfaces:
    Algorithm, ClusteringAlgorithm<Clustering<KMeansModel>>, KMeans<V,​KMeansModel>
    @Reference(authors="J. A. Hartigan, M. A. Wong",
           title="Algorithm AS 136: A K-Means Clustering Algorithm",
           booktitle="J. Royal Statistical Society. Series C (Applied Statistics) 28(1)",
           url="https://doi.org/10.2307/2346830",
           bibkey="doi:10.2307/2346830")
public class HartiganWongKMeans<V extends NumberVector>
extends AbstractKMeans<V,​KMeansModel>
    Hartigan and Wong k-means clustering. This implementation is derived from the Fortran code included in the referenced publication, but not a literal port.

    Reference:

    J. A. Hartigan, M. A. Wong
    Algorithm AS 136: A K-Means Clustering Algorithm
    J. Royal Statistical Society. Series C (Applied Statistics) 28(1)

    Since:
    0.8.0
    Author:
    Minh Nhat Nguyen, Erich Schubert

    • Field Detail

      • LOG

        private static final Logging LOG
        Class logger

    • Constructor Detail

      • HartiganWongKMeans

        public HartiganWongKMeans​(int k,
                          KMeansInitialization initializer)
        Constructor.
        Parameters:
        k - Number of clusters
        initializer - Initialization method