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

java.lang.Object
  extended by de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PercentageEigenPairFilter
All Implemented Interfaces:
EigenPairFilter, InspectionUtilFrequentlyScanned, Parameterizable

@Title(value="Percentage based Eigenpair filter")
@Description(value="Sorts the eigenpairs in decending order of their eigenvalues and returns the first eigenpairs, whose sum of eigenvalues is higher than the given percentage of the sum of all eigenvalues.")
public class PercentageEigenPairFilter
extends Object
implements EigenPairFilter

The PercentageEigenPairFilter sorts the eigenpairs in descending order of their eigenvalues and marks the first eigenpairs, whose sum of eigenvalues is higher than the given percentage of the sum of all eigenvalues as strong eigenpairs.


Nested Class Summary
static class PercentageEigenPairFilter.Parameterizer
          Parameterization class.
 
Field Summary
private  double alpha
          The threshold for strong eigenvectors: the strong eigenvectors explain a portion of at least alpha of the total variance.
static OptionID ALPHA_ID
          The threshold for 'strong' eigenvectors: the 'strong' eigenvectors explain a portion of at least alpha of the total variance.
static double DEFAULT_ALPHA
          The default value for alpha.
private static Logging logger
          The logger for this class.
 
Constructor Summary
PercentageEigenPairFilter(double alpha)
          Constructor.
 
Method Summary
 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

logger

private static final Logging logger
The logger for this class.


ALPHA_ID

public static final OptionID ALPHA_ID
The threshold for 'strong' eigenvectors: the 'strong' eigenvectors explain a portion of at least alpha of the total variance.

Default value: DEFAULT_ALPHA

Key: -pca.filter.alpha


DEFAULT_ALPHA

public static final double DEFAULT_ALPHA
The default value for alpha.

See Also:
Constant Field Values

alpha

private double alpha
The threshold for strong eigenvectors: the strong eigenvectors explain a portion of at least alpha of the total variance.

Constructor Detail

PercentageEigenPairFilter

public PercentageEigenPairFilter(double alpha)
Constructor.

Parameters:
alpha -
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

Release 0.4.0 (2011-09-20_1324)