Package elki.outlier.distance.parallel

Class KNNWeightProcessor

  • All Implemented Interfaces:
    elki.parallel.processor.Processor
    public class KNNWeightProcessor
extends elki.parallel.processor.AbstractDoubleProcessor
    Compute the kNN weight score, used by ParallelKNNWeightOutlier. Needs the k nearest neighbors as input, for example from KNNProcessor
    Since:
    0.7.0
    Author:
    Erich Schubert

    • Nested Class Summary

      Nested Classes 
      Modifier and Type Class Description
      private static class  KNNWeightProcessor.Instance
      Instance for precomputing the kNN.

    • Field Summary

      Fields 
      Modifier and Type Field Description
      (package private) elki.parallel.variables.SharedObject<? extends elki.database.ids.KNNList> input
      KNN query object
      (package private) int k
      K parameter

      • Fields inherited from class elki.parallel.processor.AbstractDoubleProcessor

        output

    • Constructor Summary

      Constructors 
      Constructor Description
      KNNWeightProcessor​(int k)
      Constructor.

    • Method Summary

      All Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      void connectKNNInput​(elki.parallel.variables.SharedObject<? extends elki.database.ids.KNNList> input)
      Connect the input channel.
      KNNWeightProcessor.Instance instantiate​(elki.parallel.Executor executor)  

      • Methods inherited from class elki.parallel.processor.AbstractDoubleProcessor

        cleanup, connectOutput

      • Methods inherited from class java.lang.Object

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

    • Field Detail

      • k

        int k
        K parameter

      • input

        elki.parallel.variables.SharedObject<? extends elki.database.ids.KNNList> input
        KNN query object

    • Constructor Detail

      • KNNWeightProcessor

        public KNNWeightProcessor​(int k)
        Constructor.
        Parameters:
        k - K parameter

    • Method Detail

      • connectKNNInput

        public void connectKNNInput​(elki.parallel.variables.SharedObject<? extends elki.database.ids.KNNList> input)
        Connect the input channel.
        Parameters:
        input - Input channel

      • instantiate

        public KNNWeightProcessor.Instance instantiate​(elki.parallel.Executor executor)
        Specified by:
        instantiate in interface elki.parallel.processor.Processor
        Specified by:
        instantiate in class elki.parallel.processor.AbstractDoubleProcessor