de.lmu.ifi.dbs.elki.math.linearalgebra.pca
Class PCARunner<V extends NumberVector<V,?>,D extends NumberDistance<D,?>>

java.lang.Object
  de.lmu.ifi.dbs.elki.logging.AbstractLoggable
      de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PCARunner<V,D>

Type Parameters:

V - Vector type

D - Distance type

All Implemented Interfaces:

Parameterizable

Direct Known Subclasses:

PCAFilteredRunner

public class PCARunner<V extends NumberVector<V,?>,D extends NumberDistance<D,?>>
extends AbstractLoggable
implements Parameterizable

Class to run PCA on given data. The various methods will start PCA at different places (e.g. with database IDs, database query results, a precomputed covariance matrix or eigenvalue decomposition). The runner can be parameterized by setting a covariance matrix builder (e.g. to a weighted covariance matrix builder)

Author:

Erich Schubert

Field Summary

private ObjectParameter<CovarianceMatrixBuilder<V,D>>	COVARIANCE_PARAM Parameter to specify the class to compute the covariance matrix, must be a subclass of CovarianceMatrixBuilder.
protected CovarianceMatrixBuilder<V,D>	covarianceMatrixBuilder The covariance computation class.
static OptionID	PCA_COVARIANCE_MATRIX OptionID for COVARIANCE_PARAM

Fields inherited from class de.lmu.ifi.dbs.elki.logging.AbstractLoggable

debug, logger

Constructor Summary

PCARunner(Parameterization config)
Constructor, adhering to Parameterizable

Method Summary

CovarianceMatrixBuilder<V,D>	getCovarianceMatrixBuilder() Get covariance matrix builder
PCAResult	processCovarMatrix(Matrix covarMatrix) Process an existing covariance Matrix
PCAResult	processDatabase(Database<V> database) Run PCA on the complete database
PCAResult	processEVD(EigenvalueDecomposition evd) Process an existing eigenvalue decomposition
PCAResult	processIds(Collection<Integer> ids, Database<V> database) Run PCA on a collection of database IDs
PCAResult	processQueryResult(Collection<DistanceResultPair<D>> results, Database<V> database) Run PCA on a QueryResult Collection
void	setCovarianceMatrixBuilder(CovarianceMatrixBuilder<V,D> covarianceBuilder) Set covariance matrix builder.

Methods inherited from class de.lmu.ifi.dbs.elki.logging.AbstractLoggable

debugFine, debugFiner, debugFinest, exception, progress, verbose, warning

Methods inherited from class java.lang.Object

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

Field Detail

PCA_COVARIANCE_MATRIX

public static final OptionID PCA_COVARIANCE_MATRIX

OptionID for COVARIANCE_PARAM

COVARIANCE_PARAM

private ObjectParameter<CovarianceMatrixBuilder<V extends NumberVector<V,?>,D extends NumberDistance<D,?>>> COVARIANCE_PARAM

Parameter to specify the class to compute the covariance matrix, must be a subclass of CovarianceMatrixBuilder.

Default value: CovarianceMatrixBuilder

Key: -pca.covariance

covarianceMatrixBuilder

protected CovarianceMatrixBuilder<V extends NumberVector<V,?>,D extends NumberDistance<D,?>> covarianceMatrixBuilder

The covariance computation class.

Constructor Detail

PCARunner

public PCARunner(Parameterization config)

Constructor, adhering to Parameterizable

Parameters:

config - Parameterization

Method Detail

processDatabase

public PCAResult processDatabase(Database<V> database)

Run PCA on the complete database

Parameters:

database - the database used

Returns:

PCA result

processIds

public PCAResult processIds(Collection<Integer> ids,
                            Database<V> database)

Run PCA on a collection of database IDs

Parameters:

ids - a collection of ids

database - the database used

Returns:

PCA result

processQueryResult

public PCAResult processQueryResult(Collection<DistanceResultPair<D>> results,
                                    Database<V> database)

Run PCA on a QueryResult Collection

Parameters:

results - a collection of QueryResults

database - the database used

Returns:

PCA result

processCovarMatrix

public PCAResult processCovarMatrix(Matrix covarMatrix)

Process an existing covariance Matrix

Parameters:

covarMatrix - the matrix used for performing pca

Returns:

PCA result

processEVD

public PCAResult processEVD(EigenvalueDecomposition evd)

Process an existing eigenvalue decomposition

Parameters:

evd - eigenvalue decomposition to use

Returns:

PCA result

getCovarianceMatrixBuilder

public CovarianceMatrixBuilder<V,D> getCovarianceMatrixBuilder()

Get covariance matrix builder

Returns:

covariance matrix builder in use

setCovarianceMatrixBuilder

public void setCovarianceMatrixBuilder(CovarianceMatrixBuilder<V,D> covarianceBuilder)

Set covariance matrix builder.

Parameters:

covarianceBuilder - New covariance matrix builder.