Package elki.evaluation.clustering.internal

Class DaviesBouldinIndex

  • All Implemented Interfaces:
    elki.evaluation.Evaluator, elki.result.ResultProcessor
    @Reference(authors="D. L. Davies, D. W. Bouldin",
           title="A Cluster Separation Measure",
           booktitle="IEEE Transactions Pattern Analysis and Machine Intelligence 1(2)",
           url="https://doi.org/10.1109/TPAMI.1979.4766909",
           bibkey="DBLP:journals/pami/DaviesB79")
public class DaviesBouldinIndex
extends java.lang.Object
implements elki.evaluation.Evaluator
    Compute the Davies-Bouldin index of a data set.

    Reference:

    D. L. Davies, D. W. Bouldin
    A Cluster Separation Measure
    IEEE Transactions Pattern Analysis and Machine Intelligence 1(2)

    Since:
    0.7.0
    Author:
    Stephan Baier

    • Nested Class Summary

      Nested Classes 
      Modifier and Type Class Description
      static class  DaviesBouldinIndex.Par
      Parameterization class.

    • Field Summary

      Fields 
      Modifier and Type Field Description
      private elki.distance.NumberVectorDistance<?> distance
      Distance function to use.
      private java.lang.String key
      Key for logging statistics.
      private static elki.logging.Logging LOG
      Logger for debug output.
      private NoiseHandling noiseOption
      Option for noise handling.
      private double p
      Exponent p for computing the power mean.

    • Constructor Summary

      Constructors 
      Constructor Description
      DaviesBouldinIndex​(elki.distance.NumberVectorDistance<?> distance, NoiseHandling noiseOpt, double p)
      Constructor.

    • Method Summary

      All Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      double evaluateClustering​(elki.database.relation.Relation<? extends elki.data.NumberVector> rel, Clustering<?> c)
      Evaluate a single clustering.
      void processNewResult​(java.lang.Object result)  
      double[] withinGroupDistances​(elki.database.relation.Relation<? extends elki.data.NumberVector> rel, java.util.List<? extends Cluster<?>> clusters, elki.data.NumberVector[] centroids)  

      • Methods inherited from class java.lang.Object

        clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

    • Field Detail

      • LOG

        private static final elki.logging.Logging LOG
        Logger for debug output.

      • noiseOption

        private NoiseHandling noiseOption
        Option for noise handling.

      • distance

        private elki.distance.NumberVectorDistance<?> distance
        Distance function to use.

      • p

        private double p
        Exponent p for computing the power mean.

      • key

        private java.lang.String key
        Key for logging statistics.

    • Constructor Detail

      • DaviesBouldinIndex

        public DaviesBouldinIndex​(elki.distance.NumberVectorDistance<?> distance,
                          NoiseHandling noiseOpt,
                          double p)
        Constructor.
        Parameters:
        distance - Distance function
        noiseOpt - Flag to control noise handling
        p - Power mean exponent p

    • Method Detail

      • evaluateClustering

        public double evaluateClustering​(elki.database.relation.Relation<? extends elki.data.NumberVector> rel,
                                 Clustering<?> c)
        Evaluate a single clustering.
        Parameters:
        rel - Data relation
        c - Clustering
        Returns:
        DB-index

      • withinGroupDistances

        public double[] withinGroupDistances​(elki.database.relation.Relation<? extends elki.data.NumberVector> rel,
                                     java.util.List<? extends Cluster<?>> clusters,
                                     elki.data.NumberVector[] centroids)

      • processNewResult

        public void processNewResult​(java.lang.Object result)
        Specified by:
        processNewResult in interface elki.result.ResultProcessor