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

Class DropEigenPairFilter

java.lang.Object

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

All Implemented Interfaces:

EigenPairFilter

@Title(value="Drop EigenPair Filter")
public class DropEigenPairFilter
extends Object
implements EigenPairFilter

The "drop" filter looks for the largest drop in normalized relative eigenvalues. Let s_1 .. s_n be the eigenvalues. Let a_k := 1/(n-k) sum_{i=k..n} s_i Then r_k := s_k / a_k is the relative eigenvalue. The drop filter searches for argmax_k r_k / r_{k+1}

Since:

0.2

Author:

Erich Schubert

Nested Class Summary

Nested Classes

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

Field Summary

Fields

Modifier and Type	Field and Description
static double	DEFAULT_WALPHA The default value for walpha.
private double	walpha The noise tolerance level for weak eigenvectors

Constructor Summary

Constructors

Constructor and Description
DropEigenPairFilter(double walpha) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
FilteredEigenPairs	filter(SortedEigenPairs eigenPairs) Filters the specified eigenpairs into strong and weak eigenpairs, where strong eigenpairs having high variances and weak eigenpairs having small variances.

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_WALPHA

public static final double DEFAULT_WALPHA

The default value for walpha. Not used by default, we're going for maximum contrast only.

See Also:

Constant Field Values

walpha

private double walpha

The noise tolerance level for weak eigenvectors

Constructor Detail

DropEigenPairFilter

public DropEigenPairFilter(double walpha)

Constructor.

Parameters:

walpha -

Method Detail

filter

public FilteredEigenPairs filter(SortedEigenPairs eigenPairs)

Description copied from interface: EigenPairFilter

Filters the specified eigenpairs into strong and weak eigenpairs, where strong eigenpairs having high variances and weak eigenpairs having small variances.

Specified by:

filter in interface EigenPairFilter

Parameters:

eigenPairs - the eigenPairs (i.e. the eigenvectors and

Returns:

the filtered eigenpairs