de.lmu.ifi.dbs.elki.evaluation.scores.adapter

Class VectorOverThreshold

java.lang.Object

de.lmu.ifi.dbs.elki.evaluation.scores.adapter.VectorOverThreshold

All Implemented Interfaces:

ScoreEvaluation.Predicate<AbstractVectorIter>

Direct Known Subclasses:

VectorNonZero

public class VectorOverThreshold
extends java.lang.Object
implements ScoreEvaluation.Predicate<AbstractVectorIter>

Class that uses a NumberVector as reference, and considers all non-zero values as positive entries.

Since:

0.7.0

Author:

Erich Schubert

Field Summary

Fields

Modifier and Type	Field and Description
(package private) int	numpos Number of positive values.
(package private) double	threshold Threshold
(package private) NumberVector	vec Vector to use as reference

Constructor Summary

Constructors

Constructor and Description
VectorOverThreshold(NumberVector vec, double threshold) Constructor.

Method Summary

Modifier and Type	Method and Description
int	getDimensionality() Dimensionality of the underlying truth vector (positive and negative values).
int	numPositive() Return the number of positive ids.
boolean	test(AbstractVectorIter o) Test a result.

Methods inherited from class java.lang.Object

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

Field Detail

vec

NumberVector vec

Vector to use as reference

threshold

double threshold

Threshold

numpos

int numpos

Number of positive values.

Constructor Detail

VectorOverThreshold

public VectorOverThreshold(NumberVector vec,
                           double threshold)

Constructor.

Parameters:

vec - Reference vector.

threshold - Threshold value.

Method Detail

test

public boolean test(AbstractVectorIter o)

Description copied from interface: ScoreEvaluation.Predicate

Test a result.

Specified by:

test in interface ScoreEvaluation.Predicate<AbstractVectorIter>

Parameters:

o - Object to test

Returns:

true when positive.

numPositive

public int numPositive()

Description copied from interface: ScoreEvaluation.Predicate

Return the number of positive ids.

Specified by:

numPositive in interface ScoreEvaluation.Predicate<AbstractVectorIter>

Returns:

Number of positive elements

getDimensionality

public int getDimensionality()

Dimensionality of the underlying truth vector (positive and negative values).

Returns:

Dimensionality