Package elki.index.preprocessed.knn

Class NNDescent.Factory<O>

java.lang.Object

elki.index.preprocessed.knn.AbstractMaterializeKNNPreprocessor.Factory<O>

elki.index.preprocessed.knn.NNDescent.Factory<O>

Type Parameters:

O - Object type

All Implemented Interfaces:

IndexFactory<O>

Enclosing class:

NNDescent<O>

public static class NNDescent.Factory<O>
extends AbstractMaterializeKNNPreprocessor.Factory<O>

Index factory.

Author:

Evelyn Kirner

Field Summary

Fields

Modifier and Type	Field	Description
private double	delta	early termination parameter
private int	iterations	maximum number of iterations
private boolean	noInitialNeighbors	set initial neighbors?
private double	rho	sample rate
private RandomFactory	rnd	Random generator

Fields inherited from class elki.index.preprocessed.knn.AbstractMaterializeKNNPreprocessor.Factory

distance, DISTANCE_FUNCTION_ID, k, K_ID

Constructor Summary

Constructors

Constructor	Description
Factory(int k, Distance<? super O> distance, RandomFactory rnd, double delta, double rho, boolean noInitialNeighbors, int iterations)	Constructor.

Method Summary

Modifier and Type	Method	Description
NNDescent<O>	instantiate(Relation<O> relation)	Sets the database in the distance function of this index (if existing).

Methods inherited from class elki.index.preprocessed.knn.AbstractMaterializeKNNPreprocessor.Factory

getDistance, getInputTypeRestriction

Methods inherited from class java.lang.Object

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

Field Detail

rnd

private final RandomFactory rnd

Random generator

delta

private final double delta

early termination parameter

rho

private final double rho

sample rate

noInitialNeighbors

private final boolean noInitialNeighbors

set initial neighbors?

iterations

private final int iterations

maximum number of iterations

Constructor Detail

Factory

public Factory(int k,
               Distance<? super O> distance,
               RandomFactory rnd,
               double delta,
               double rho,
               boolean noInitialNeighbors,
               int iterations)

Constructor.

Parameters:

k - K

distance - distance function

rnd - Random generator

delta - Delta threshold

rho - Rho threshold

noInitialNeighbors - Do not use initial neighbors

iterations - Maximum number of iterations

Method Detail

instantiate

public NNDescent<O> instantiate(Relation<O> relation)

Description copied from interface: IndexFactory

Sets the database in the distance function of this index (if existing).

Specified by:

instantiate in interface IndexFactory<O>

Specified by:

instantiate in class AbstractMaterializeKNNPreprocessor.Factory<O>

Parameters:

relation - the relation to index