de.lmu.ifi.dbs.elki.distance.distancefunction.correlation

Class WeightedSquaredPearsonCorrelationDistanceFunction

java.lang.Object

de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractPrimitiveDistanceFunction<NumberVector>

de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractNumberVectorDistanceFunction

de.lmu.ifi.dbs.elki.distance.distancefunction.correlation.WeightedSquaredPearsonCorrelationDistanceFunction

All Implemented Interfaces:

DistanceFunction<NumberVector>, NumberVectorDistanceFunction<NumberVector>, PrimitiveDistanceFunction<NumberVector>, WeightedNumberVectorDistanceFunction<NumberVector>

public class WeightedSquaredPearsonCorrelationDistanceFunction
extends AbstractNumberVectorDistanceFunction
implements WeightedNumberVectorDistanceFunction<NumberVector>

Squared Pearson correlation distance function for feature vectors. The squared Pearson correlation distance is computed from the Pearson correlation coefficient r as: 1-r 2. Hence, possible values of this distance are between 0 and 1. The distance between two vectors will be low (near 0), if their attribute values are dimension-wise strictly positively or negatively correlated. For Features with uncorrelated attributes, the distance value will be high (near 1). This variation is for weighted dimensions.

Since:

0.3

Author:

Arthur Zimek, Erich Schubert

Nested Class Summary

Nested Classes

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

Field Summary

Fields

Modifier and Type	Field and Description
private double[]	weights Weights

Fields inherited from interface de.lmu.ifi.dbs.elki.distance.distancefunction.WeightedNumberVectorDistanceFunction

WEIGHTS_ID

Constructor Summary

Constructors

Constructor and Description
WeightedSquaredPearsonCorrelationDistanceFunction(double[] weights) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
double	distance(NumberVector v1, NumberVector v2) Computes the squared Pearson correlation distance for two given feature vectors.
boolean	equals(Object obj)

Methods inherited from class de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractNumberVectorDistanceFunction

dimensionality, dimensionality, dimensionality, dimensionality, getInputTypeRestriction

Methods inherited from class de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractPrimitiveDistanceFunction

instantiate, isMetric, isSymmetric

Methods inherited from class java.lang.Object

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

Methods inherited from interface de.lmu.ifi.dbs.elki.distance.distancefunction.PrimitiveDistanceFunction

getInputTypeRestriction

Methods inherited from interface de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction

instantiate, isMetric, isSymmetric

Field Detail

weights

private double[] weights

Weights

Constructor Detail

WeightedSquaredPearsonCorrelationDistanceFunction

public WeightedSquaredPearsonCorrelationDistanceFunction(double[] weights)

Constructor.

Parameters:

weights - Weights

Method Detail

distance

public double distance(NumberVector v1,
              NumberVector v2)

Computes the squared Pearson correlation distance for two given feature vectors. The squared Pearson correlation distance is computed from the Pearson correlation coefficient r as: 1-r 2. Hence, possible values of this distance are between 0 and 1.

Specified by:

distance in interface NumberVectorDistanceFunction<NumberVector>

Specified by:

distance in interface PrimitiveDistanceFunction<NumberVector>

Specified by:

distance in class AbstractPrimitiveDistanceFunction<NumberVector>

Parameters:

v1 - first feature vector

v2 - second feature vector

Returns:

the squared Pearson correlation distance for two given feature vectors v1 and v2

equals

public boolean equals(Object obj)

Overrides:

equals in class Object