de.lmu.ifi.dbs.elki.datasource.filter

Class HistogramJitterFilter<V extends NumberVector<?>>

java.lang.Object

de.lmu.ifi.dbs.elki.datasource.filter.AbstractStreamFilter

de.lmu.ifi.dbs.elki.datasource.filter.AbstractStreamConversionFilter<I,O>

de.lmu.ifi.dbs.elki.datasource.filter.AbstractVectorStreamConversionFilter<V,V>

de.lmu.ifi.dbs.elki.datasource.filter.HistogramJitterFilter<V>

Type Parameters:

V - Vector type

All Implemented Interfaces:

BundleStreamSource, ObjectFilter, StreamFilter, InspectionUtilFrequentlyScanned

@Description(value="Add uniform Jitter to a dataset, while preserving the total vector sum.")
public class HistogramJitterFilter<V extends NumberVector<?>>
extends AbstractVectorStreamConversionFilter<V,V>

Add Jitter, preserving the histogram properties (same sum, nonnegative). For each vector, the total sum of all dimensions is computed.
Then a random vector of the average length jitter * scale is added and the result normalized to the original vectors sum. The individual dimensions are drawn from an exponential distribution with scale jitter / dimensionality, so it is expected that the error in most dimensions will be low, and higher in few. This is designed to degrade the quality of a histogram, while preserving the total sum (e.g. to keep the normalization). The factor "jitter" can be used to control the degradation amount.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	HistogramJitterFilter.Parameterizer Parameterization class.

Nested classes/interfaces inherited from interface de.lmu.ifi.dbs.elki.datasource.bundle.BundleStreamSource

BundleStreamSource.Event

Field Summary

Fields

Modifier and Type	Field and Description
(package private) double	jitter Jitter amount.
(package private) ExponentialDistribution	rnd Random generator.

Fields inherited from class de.lmu.ifi.dbs.elki.datasource.filter.AbstractVectorStreamConversionFilter

factory

Fields inherited from class de.lmu.ifi.dbs.elki.datasource.filter.AbstractStreamConversionFilter

column, meta

Fields inherited from class de.lmu.ifi.dbs.elki.datasource.filter.AbstractStreamFilter

source

Constructor Summary

Constructors

Constructor and Description
HistogramJitterFilter(double jitter, RandomFactory rnd) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
protected SimpleTypeInformation<V>	convertedType(SimpleTypeInformation<V> in) Get the output type from the input type after conversion.
protected V	filterSingleObject(V obj) Normalize a single instance.
protected SimpleTypeInformation<? super V>	getInputTypeRestriction() Get the input type restriction used for negotiating the data query.

Methods inherited from class de.lmu.ifi.dbs.elki.datasource.filter.AbstractVectorStreamConversionFilter

initializeOutputType

Methods inherited from class de.lmu.ifi.dbs.elki.datasource.filter.AbstractStreamConversionFilter

data, getMeta, nextEvent

Methods inherited from class de.lmu.ifi.dbs.elki.datasource.filter.AbstractStreamFilter

filter, init

Methods inherited from class java.lang.Object

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

Field Detail

jitter

double jitter

Jitter amount.

rnd

ExponentialDistribution rnd

Random generator.

Constructor Detail

HistogramJitterFilter

public HistogramJitterFilter(double jitter,
                     RandomFactory rnd)

Constructor.

Parameters:

jitter - Relative amount of jitter to add

rnd - Random generator

Method Detail

filterSingleObject

protected V filterSingleObject(V obj)

Description copied from class: AbstractStreamConversionFilter

Normalize a single instance. You can implement this as UnsupportedOperationException if you override both public "normalize" functions!

Specified by:

filterSingleObject in class AbstractStreamConversionFilter<V extends NumberVector<?>,V extends NumberVector<?>>

Parameters:

obj - Database object to normalize

Returns:

Normalized database object

getInputTypeRestriction

protected SimpleTypeInformation<? super V> getInputTypeRestriction()

Description copied from class: AbstractStreamConversionFilter

Get the input type restriction used for negotiating the data query.

Specified by:

getInputTypeRestriction in class AbstractStreamConversionFilter<V extends NumberVector<?>,V extends NumberVector<?>>

Returns:

Type restriction

convertedType

protected SimpleTypeInformation<V> convertedType(SimpleTypeInformation<V> in)

Description copied from class: AbstractStreamConversionFilter

Get the output type from the input type after conversion.

Specified by:

convertedType in class AbstractStreamConversionFilter<V extends NumberVector<?>,V extends NumberVector<?>>

Parameters:

in - input type restriction

Returns:

output type restriction