org.aksw.limes.core.evaluation.qualititativeMeasures

Class PseudoFM

java.lang.Object

org.aksw.limes.core.evaluation.qualititativeMeasures.PseudoFM

Deprecated.

Use PseudoFMeasure instead

@Deprecated
public class PseudoFM
extends Object

Implements a quality measure for unsupervised ML algorihtms, dubbed pseudo F-Measure. Thereby, not relying on any gold standard. The basic idea is to measure the quality of the a given Mapping by calc. how close it is to an assumed 1-to-1 Mapping between source and target.

Author:

Klaus Lyko (lyko@informatik.uni-leipzig.de), Axel-C. Ngonga Ngomo (ngonga@informatik.uni-leipzig.de)

Field Summary

Fields

Modifier and Type	Field and Description
boolean	symmetricPrecision Deprecated.

Constructor Summary

Constructors

Constructor and Description
PseudoFM() Deprecated.
PseudoFM(boolean symmetricPrecision) Deprecated. Use this constructor to toggle between symmetric precision (true) and the older asymmetric Pseudo-Precision (false)

Method Summary

Modifier and Type	Method and Description
double	getPseudoFMeasure(List<String> sourceUris, List<String> targetUris, AMapping result) Deprecated. Computes the balanced Pseudo-F1-measure.
double	getPseudoFMeasure(List<String> sourceUris, List<String> targetUris, AMapping result, double beta) Deprecated. Computes Pseudo-f-measure for different beta values
double	getPseudoPrecision(List<String> sourceUris, List<String> targetUris, AMapping result) Deprecated. Computes the pseudo-precision, which is basically how well the mapping maps one single s to one single t
double	getPseudoRecall(List<String> sourceUris, List<String> targetUris, AMapping result) Deprecated. The assumption here is a follows.
boolean	isUse1To1Mapping() Deprecated.
void	setUse1To1Mapping(boolean use1To1Mapping) Deprecated.

Methods inherited from class java.lang.Object

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

Field Detail

symmetricPrecision

public boolean symmetricPrecision

Deprecated.

Constructor Detail

PseudoFM

public PseudoFM()

Deprecated.

PseudoFM

public PseudoFM(boolean symmetricPrecision)

Deprecated.

Use this constructor to toggle between symmetric precision (true) and the older asymmetric Pseudo-Precision (false)

Parameters:

symmetricPrecision - sets/clears the flag for symmetric precision

Method Detail

isUse1To1Mapping

public boolean isUse1To1Mapping()

Deprecated.

Returns:

the use1To1Mapping

setUse1To1Mapping

public void setUse1To1Mapping(boolean use1To1Mapping)

Deprecated.

getPseudoFMeasure

public double getPseudoFMeasure(List<String> sourceUris,
                                List<String> targetUris,
                                AMapping result)

Deprecated.

Computes the balanced Pseudo-F1-measure.

Parameters:

sourceUris - Source URIs

targetUris - Target URIs

result - Mapping resulting from ML algorihtms

Returns:

Pseudo measure

getPseudoFMeasure

public double getPseudoFMeasure(List<String> sourceUris,
                                List<String> targetUris,
                                AMapping result,
                                double beta)

Deprecated.

Computes Pseudo-f-measure for different beta values

Parameters:

sourceUris - Source URIs

targetUris - Target URIs

result - Mapping resulting from ML algorihtms

beta - Beta for F-beta

Returns:

Pseudo measure

getPseudoPrecision

public double getPseudoPrecision(List<String> sourceUris,
                                 List<String> targetUris,
                                 AMapping result)

Deprecated.

Computes the pseudo-precision, which is basically how well the mapping maps one single s to one single t

Parameters:

sourceUris - List of source uris

targetUris - List of target uris

result - Mapping of source to targer uris

Returns:

double-Pseudo precision score

getPseudoRecall

public double getPseudoRecall(List<String> sourceUris,
                              List<String> targetUris,
                              AMapping result)

Deprecated.

The assumption here is a follows. We compute how many of the s and t were mapped.

Parameters:

sourceUris - URIs in source cache

targetUris - URIs in target cache

result - Mapping computed by our learner

Returns:

double-Pseudo recall