Package elki.clustering.kmedoids

Class FastPAM1.Instance

  • Direct Known Subclasses:
    FastPAM.Instance
    Enclosing class:
    FastPAM1<O>
    protected static class FastPAM1.Instance
extends PAM.Instance
    Instance for a single dataset.
    Author:
    Erich Schubert

    • Constructor Summary

      Constructors 
      Constructor Description
      Instance​(elki.database.query.distance.DistanceQuery<?> distQ, elki.database.ids.DBIDs ids, elki.database.datastore.WritableIntegerDataStore assignment)
      Constructor.

    • Method Summary

      All Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      protected double assignToNearestCluster​(elki.database.ids.ArrayDBIDs means)
      Returns a list of clusters.
      protected double computeReassignmentCost​(elki.database.ids.DBIDRef xj, double[] loss)
      Compute the reassignment cost, for all medoids in one pass.
      protected double run​(elki.database.ids.ArrayModifiableDBIDs medoids, int maxiter)
      Run the FastPAM optimization phase.
      protected void updateAssignment​(elki.database.ids.ArrayModifiableDBIDs medoids, elki.database.ids.DBIDArrayIter miter, elki.database.ids.DBIDRef h, int m)
      Update an existing cluster assignment.
      protected void updatePriorCost​(double[] pcost)
      Prior assignment costs.
      protected int updateSecondNearest​(elki.database.ids.DBIDRef j, elki.database.ids.DBIDArrayIter medoids, int h, double dist_h, int n)
      Find the second nearest medoid.

      • Methods inherited from class java.lang.Object

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

    • Constructor Detail

      • Instance

        public Instance​(elki.database.query.distance.DistanceQuery<?> distQ,
                elki.database.ids.DBIDs ids,
                elki.database.datastore.WritableIntegerDataStore assignment)
        Constructor.
        Parameters:
        distQ - Distance query
        ids - IDs to process
        assignment - Cluster assignment

    • Method Detail

      • run

        protected double run​(elki.database.ids.ArrayModifiableDBIDs medoids,
                     int maxiter)
        Run the FastPAM optimization phase.
        Overrides:
        run in class PAM.Instance
        Parameters:
        medoids - Medoids list
        maxiter -
        Returns:
        cost

      • updatePriorCost

        protected void updatePriorCost​(double[] pcost)
        Prior assignment costs.
        Parameters:
        pcost - Prior cost.

      • assignToNearestCluster

        protected double assignToNearestCluster​(elki.database.ids.ArrayDBIDs means)
        Returns a list of clusters. The kth cluster contains the ids of those objects, that are nearest to the kth mean.
        Overrides:
        assignToNearestCluster in class PAM.Instance
        Parameters:
        means - Object centroids
        Returns:
        Assignment cost

      • computeReassignmentCost

        protected double computeReassignmentCost​(elki.database.ids.DBIDRef xj,
                                         double[] loss)
        Compute the reassignment cost, for all medoids in one pass.
        Parameters:
        xj - Current object to swap with any medoid.
        loss - Loss change aggregation array, must have size k
        Returns:
        Loss change accumulator that applies to all

      • updateAssignment

        protected void updateAssignment​(elki.database.ids.ArrayModifiableDBIDs medoids,
                                elki.database.ids.DBIDArrayIter miter,
                                elki.database.ids.DBIDRef h,
                                int m)
        Update an existing cluster assignment.
        Parameters:
        medoids - Medoids set
        miter - Medoid iterator
        h - New medoid
        m - Position of replaced medoid

      • updateSecondNearest

        protected int updateSecondNearest​(elki.database.ids.DBIDRef j,
                                  elki.database.ids.DBIDArrayIter medoids,
                                  int h,
                                  double dist_h,
                                  int n)
        Find the second nearest medoid.
        Parameters:
        j - Query point
        medoids - Medoids
        h - Known medoid
        dist_h - Distance to h
        n - Known nearest
        Returns:
        Index of second nearest medoid, PAM.Instance.second is updated.