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

Class GlobalPrincipalComponentAnalysisTransform<O extends NumberVector>

java.lang.Object

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

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

de.lmu.ifi.dbs.elki.datasource.filter.transform.GlobalPrincipalComponentAnalysisTransform<O>

Type Parameters:

O - Vector type

All Implemented Interfaces:

ObjectFilter

@Alias(value={"whiten","whitening","pca"})
public class GlobalPrincipalComponentAnalysisTransform<O extends NumberVector>
extends AbstractVectorConversionFilter<O,O>

Apply principal component analysis to the data set. This process is also known as "Whitening transformation". If you want to also reduce dimensionality, set the GlobalPrincipalComponentAnalysisTransform.Parameterizer.FILTER_ID parameter!

Since:

0.5.0

Author:

Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	GlobalPrincipalComponentAnalysisTransform.Parameterizer<O extends NumberVector> Parameterization class.

Field Summary

Fields

Modifier and Type	Field and Description
(package private) double[]	buf Projection buffer.
(package private) CovarianceMatrix	covmat Covariance matrix builder.
(package private) int	dim Actual dataset dimensionality.
(package private) EigenPairFilter	filter Filter to use for dimensionality reduction.
private static Logging	LOG Class logger.
(package private) double[]	mean Vector for data set centering.
(package private) double[][]	proj Final projection after analysis run.

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

factory

Constructor Summary

Constructors

Constructor and Description
GlobalPrincipalComponentAnalysisTransform(EigenPairFilter filter) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
protected SimpleTypeInformation<? super O>	convertedType(SimpleTypeInformation<O> in) Get the output type from the input type after conversion.
protected O	filterSingleObject(O obj) Normalize a single instance.
protected SimpleTypeInformation<? super O>	getInputTypeRestriction() Get the input type restriction used for negotiating the data query.
protected Logging	getLogger() Class logger.
protected void	prepareComplete() Complete the initialization phase.
protected void	prepareProcessInstance(O obj) Process a single object during initialization.
protected boolean	prepareStart(SimpleTypeInformation<O> in) Return "true" when the normalization needs initialization (two-pass filtering!).

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

initializeOutputType

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

filter

Methods inherited from class java.lang.Object

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

Field Detail

LOG

private static final Logging LOG

Class logger.

filter

EigenPairFilter filter

Filter to use for dimensionality reduction.

dim

int dim

Actual dataset dimensionality.

covmat

CovarianceMatrix covmat

Covariance matrix builder.

proj

double[][] proj

Final projection after analysis run.

buf

double[] buf

Projection buffer.

mean

double[] mean

Vector for data set centering.

Constructor Detail

GlobalPrincipalComponentAnalysisTransform

public GlobalPrincipalComponentAnalysisTransform(EigenPairFilter filter)

Constructor.

Parameters:

filter - Filter to use for dimensionality reduction.

Method Detail

prepareStart

protected boolean prepareStart(SimpleTypeInformation<O> in)

Description copied from class: AbstractConversionFilter

Return "true" when the normalization needs initialization (two-pass filtering!).

Overrides:

prepareStart in class AbstractConversionFilter<O extends NumberVector,O extends NumberVector>

Parameters:

in - Input type information

Returns:

true or false

prepareProcessInstance

protected void prepareProcessInstance(O obj)

Description copied from class: AbstractConversionFilter

Process a single object during initialization.

Overrides:

prepareProcessInstance in class AbstractConversionFilter<O extends NumberVector,O extends NumberVector>

Parameters:

obj - Object to process

prepareComplete

protected void prepareComplete()

Description copied from class: AbstractConversionFilter

Complete the initialization phase.

Overrides:

prepareComplete in class AbstractConversionFilter<O extends NumberVector,O extends NumberVector>

filterSingleObject

protected O filterSingleObject(O obj)

Description copied from class: AbstractConversionFilter

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

Specified by:

filterSingleObject in class AbstractConversionFilter<O extends NumberVector,O extends NumberVector>

Parameters:

obj - Database object to normalize

Returns:

Normalized database object

getInputTypeRestriction

protected SimpleTypeInformation<? super O> getInputTypeRestriction()

Description copied from class: AbstractConversionFilter

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

Specified by:

getInputTypeRestriction in class AbstractConversionFilter<O extends NumberVector,O extends NumberVector>

Returns:

Type restriction

convertedType

protected SimpleTypeInformation<? super O> convertedType(SimpleTypeInformation<O> in)

Description copied from class: AbstractConversionFilter

Get the output type from the input type after conversion.

Specified by:

convertedType in class AbstractConversionFilter<O extends NumberVector,O extends NumberVector>

Parameters:

in - input type restriction

Returns:

output type restriction

getLogger

protected Logging getLogger()

Description copied from class: AbstractConversionFilter

Class logger.

Specified by:

getLogger in class AbstractConversionFilter<O extends NumberVector,O extends NumberVector>

Returns:

Logger