de.lmu.ifi.dbs.elki.math.linearalgebra.pca

Class PCAFilteredRunner<V extends NumberVector<?>>

java.lang.Object

de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PCARunner<V>

de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PCAFilteredRunner<V>

Type Parameters:

V - Vector class to use

All Implemented Interfaces:

InspectionUtilFrequentlyScanned, Parameterizable

Direct Known Subclasses:

PCAFilteredAutotuningRunner

public class PCAFilteredRunner<V extends NumberVector<?>>
extends PCARunner<V>

PCA runner that will do dimensionality reduction. PCA is computed as with the regular runner, but afterwards, an EigenPairFilter is applied.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	PCAFilteredRunner.Parameterizer<V extends NumberVector<?>> Parameterization class.

Field Summary

Fields

Modifier and Type	Field and Description
private double	big Holds the value of BIG_ID.
static OptionID	BIG_ID Parameter to specify a constant big value to reset high eigenvalues, must be a double greater than 0.
private EigenPairFilter	eigenPairFilter Holds the instance of the EigenPairFilter specified by PCA_EIGENPAIR_FILTER.
static OptionID	PCA_EIGENPAIR_FILTER Parameter to specify the filter for determination of the strong and weak eigenvectors, must be a subclass of EigenPairFilter.
private double	small Holds the value of SMALL_ID.
static OptionID	SMALL_ID Parameter to specify a constant small value to reset low eigenvalues, must be a double greater than 0.

Fields inherited from class de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PCARunner

covarianceMatrixBuilder, PCA_COVARIANCE_MATRIX

Constructor Summary

Constructors

Constructor and Description
PCAFilteredRunner(CovarianceMatrixBuilder<V> covarianceMatrixBuilder, EigenPairFilter eigenPairFilter, double big, double small) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
protected EigenPairFilter	getEigenPairFilter() Retrieve the EigenPairFilter to be used.
PCAFilteredResult	processCovarMatrix(Matrix covarMatrix) Process an existing Covariance Matrix.
PCAFilteredResult	processEVD(EigenvalueDecomposition evd) Process an existing eigenvalue decomposition.
PCAFilteredResult	processIds(DBIDs ids, Relation<? extends V> database) Run PCA on a collection of database IDs.
<D extends NumberDistance<D,?>> PCAFilteredResult	processQueryResult(DistanceDBIDResult<D> results, Relation<? extends V> database) Run PCA on a QueryResult Collection.

Methods inherited from class de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PCARunner

getCovarianceMatrixBuilder, processDatabase, setCovarianceMatrixBuilder

Methods inherited from class java.lang.Object

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

Field Detail

PCA_EIGENPAIR_FILTER

public static final OptionID PCA_EIGENPAIR_FILTER

Parameter to specify the filter for determination of the strong and weak eigenvectors, must be a subclass of EigenPairFilter.

Default value: PercentageEigenPairFilter

Key: -pca.filter

BIG_ID

public static final OptionID BIG_ID

Parameter to specify a constant big value to reset high eigenvalues, must be a double greater than 0.

Default value: 1.0

Key: -pca.big

SMALL_ID

public static final OptionID SMALL_ID

Parameter to specify a constant small value to reset low eigenvalues, must be a double greater than 0.

Default value: 0.0

Key: -pca.small

eigenPairFilter

private EigenPairFilter eigenPairFilter

Holds the instance of the EigenPairFilter specified by PCA_EIGENPAIR_FILTER.

big

private double big

Holds the value of BIG_ID.

small

private double small

Holds the value of SMALL_ID.

Constructor Detail

PCAFilteredRunner

public PCAFilteredRunner(CovarianceMatrixBuilder<V> covarianceMatrixBuilder,
                 EigenPairFilter eigenPairFilter,
                 double big,
                 double small)

Constructor.

Parameters:

covarianceMatrixBuilder - Covariance matrix builder

eigenPairFilter - Eigen pair filter

big - Replacement for large eigenvalues

small - Replacement for small eigenvalues

Method Detail

processIds

public PCAFilteredResult processIds(DBIDs ids,
                           Relation<? extends V> database)

Run PCA on a collection of database IDs.

Overrides:

processIds in class PCARunner<V extends NumberVector<?>>

Parameters:

ids - a collection of ids

database - the database used

Returns:

PCA result

processQueryResult

public <D extends NumberDistance<D,?>> PCAFilteredResult processQueryResult(DistanceDBIDResult<D> results,
                                                                   Relation<? extends V> database)

Run PCA on a QueryResult Collection.

Overrides:

processQueryResult in class PCARunner<V extends NumberVector<?>>

Type Parameters:

D - distance type

Parameters:

results - a collection of QueryResults

database - the database used

Returns:

PCA result

processCovarMatrix

public PCAFilteredResult processCovarMatrix(Matrix covarMatrix)

Process an existing Covariance Matrix.

Overrides:

processCovarMatrix in class PCARunner<V extends NumberVector<?>>

Parameters:

covarMatrix - the matrix used for performing PCA

Returns:

Filtered result

processEVD

public PCAFilteredResult processEVD(EigenvalueDecomposition evd)

Process an existing eigenvalue decomposition.

Overrides:

processEVD in class PCARunner<V extends NumberVector<?>>

Parameters:

evd - eigenvalue decomposition to use

Returns:

filtered result

getEigenPairFilter

protected EigenPairFilter getEigenPairFilter()

Retrieve the EigenPairFilter to be used. For derived PCA Runners

Returns:

eigenpair filter configured.