Package elki.index.preprocessed.knn

Class AbstractMaterializeKNNPreprocessor<O>

java.lang.Object

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

Type Parameters:

O - Object type

All Implemented Interfaces:

Index, KNNIndex<O>

Direct Known Subclasses:

CachedDoubleDistanceKNNPreprocessor, KNNJoinMaterializeKNNPreprocessor, MaterializeKNNPreprocessor, MetricalIndexApproximationMaterializeKNNPreprocessor, NNDescent, PartitionApproximationMaterializeKNNPreprocessor, RandomSampleKNNPreprocessor, SpacefillingMaterializeKNNPreprocessor, SpatialApproximationMaterializeKNNPreprocessor

public abstract class AbstractMaterializeKNNPreprocessor<O>
extends java.lang.Object
implements KNNIndex<O>

Abstract base class for KNN Preprocessors.

Since:

0.4.0

Author:

Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	AbstractMaterializeKNNPreprocessor.Factory<O>	The parameterizable factory.

Field Summary

Fields

Modifier and Type	Field	Description
protected Distance<? super O>	distance	The distance function to be used.
protected DistanceQuery<O>	distanceQuery	The distance query we used.
protected int	k	The query k value.
protected Relation<O>	relation	The relation we are bound to.
protected WritableDataStore<KNNList>	storage	The data store.

Constructor Summary

Constructors

Constructor	Description
AbstractMaterializeKNNPreprocessor(Relation<O> relation, DistanceQuery<O> distanceQuery, int k)	Constructor.
AbstractMaterializeKNNPreprocessor(Relation<O> relation, Distance<? super O> distance, int k)	Constructor.

Method Summary

Modifier and Type	Method	Description
(package private) void	createStorage()	Create the default storage.
KNNList	get(DBIDRef id)	Get the k nearest neighbors.
DistanceQuery<O>	getDistanceQuery()	The distance query we used.
int	getK()	Get the value of 'k' supported by this preprocessor.
protected abstract Logging	getLogger()	Get the classes static logger.
void	initialize()	Initialize the index.
PreprocessorKNNQuery	kNNByDBID(DistanceQuery<O> distQ, int maxk, int flags)	Get a KNN query object for the given distance query and k.
KNNSearcher<O>	kNNByObject(DistanceQuery<O> distanceQuery, int maxk, int flags)	Deprecated. not possible
protected abstract void	preprocess()	Perform the preprocessing step.

Methods inherited from class java.lang.Object

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

Methods inherited from interface elki.index.Index

logStatistics

Field Detail

relation

protected final Relation<O> relation

The relation we are bound to.

k

protected final int k

The query k value.

distance

protected final Distance<? super O> distance

The distance function to be used.

distanceQuery

protected final DistanceQuery<O> distanceQuery

The distance query we used.

storage

protected WritableDataStore<KNNList> storage

The data store.

Constructor Detail

AbstractMaterializeKNNPreprocessor

public AbstractMaterializeKNNPreprocessor(Relation<O> relation,
                                          Distance<? super O> distance,
                                          int k)

Constructor.

Parameters:

relation - Relation

distance - Distance function

k - k

AbstractMaterializeKNNPreprocessor

public AbstractMaterializeKNNPreprocessor(Relation<O> relation,
                                          DistanceQuery<O> distanceQuery,
                                          int k)

Constructor.

Parameters:

relation - Relation

distanceQuery - Distance query

k - k

Method Detail

getDistanceQuery

public DistanceQuery<O> getDistanceQuery()

The distance query we used.

Returns:

Distance query

getK

public int getK()

Get the value of 'k' supported by this preprocessor.

Returns:

k

preprocess

protected abstract void preprocess()

Perform the preprocessing step.

get

public KNNList get(DBIDRef id)

Get the k nearest neighbors.

Parameters:

id - Object ID

Returns:

Neighbors

createStorage

void createStorage()

Create the default storage.

initialize

public void initialize()

Description copied from interface: Index

Initialize the index. For static indexes, this is the moment the index is bulk loaded.

Specified by:

initialize in interface Index

kNNByObject

@Deprecated
public KNNSearcher<O> kNNByObject(DistanceQuery<O> distanceQuery,
                                  int maxk,
                                  int flags)

Deprecated.

not possible

Description copied from interface: KNNIndex

Get a KNN query object for the given distance query and k.

This function MAY return null, when the given distance is not supported!

Specified by:

kNNByObject in interface KNNIndex<O>

Parameters:

distanceQuery - Distance query

maxk - Maximum value of k

flags - Hints for the optimizer

Returns:

KNN Query object or null

kNNByDBID

public PreprocessorKNNQuery kNNByDBID(DistanceQuery<O> distQ,
                                      int maxk,
                                      int flags)

Description copied from interface: KNNIndex

Get a KNN query object for the given distance query and k.

This function MAY return null, when the given distance is not supported!

Specified by:

kNNByDBID in interface KNNIndex<O>

Parameters:

distQ - Distance query

maxk - Maximum value of k

flags - Hints for the optimizer

Returns:

KNN Query object or null

getLogger

protected abstract Logging getLogger()

Get the classes static logger.

Returns:

Logger