Package elki.distance

Class MatrixWeightedQuadraticDistance

java.lang.Object

elki.distance.AbstractNumberVectorDistance

elki.distance.MatrixWeightedQuadraticDistance

All Implemented Interfaces:

Distance<NumberVector>, Norm<NumberVector>, NumberVectorDistance<NumberVector>, PrimitiveDistance<NumberVector>

Direct Known Subclasses:

HSBHistogramQuadraticDistance, MahalanobisDistance, RGBHistogramQuadraticDistance

public class MatrixWeightedQuadraticDistance
extends AbstractNumberVectorDistance
implements Norm<NumberVector>

Matrix weighted quadratic distance, the squared form of MahalanobisDistance. For a weight matrix M, this distance is defined as \[ \text{Mahalanobis}^2_M(\vec{x},\vec{y}) := (\vec{x}-\vec{y})^T * M * (\vec{x}-\vec{y}) \] TODO: Add a factory with parameterizable weight matrix! Right now, this can only be used from Java and from subclasses, not from command line or MiniGUI.

Since:

0.1

Author:

Elke Achtert

Field Summary

Fields

Modifier and Type	Field	Description
protected double[][]	weightMatrix	The weight matrix.

Constructor Summary

Constructors

Constructor	Description
MatrixWeightedQuadraticDistance(double[][] weightMatrix)	Constructor.

Method Summary

Modifier and Type	Method	Description
double	distance(NumberVector o1, NumberVector o2)	Computes the distance between two given DatabaseObjects according to this distance function.
boolean	equals(java.lang.Object obj)
VectorFieldTypeInformation<? super NumberVector>	getInputTypeRestriction()	Get the input data type of the function.
int	hashCode()
boolean	isSquared()	Squared distances, that would become metric after square root.
double	norm(NumberVector obj)	Compute the norm of object obj.

Methods inherited from class elki.distance.AbstractNumberVectorDistance

dimensionality, dimensionality, dimensionality, dimensionality, dimensionality, dimensionality, dimensionality, dimensionality

Methods inherited from class java.lang.Object

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

Methods inherited from interface elki.distance.Distance

isMetric, isSymmetric

Methods inherited from interface elki.distance.PrimitiveDistance

instantiate

Field Detail

weightMatrix

protected double[][] weightMatrix

The weight matrix.

Constructor Detail

MatrixWeightedQuadraticDistance

public MatrixWeightedQuadraticDistance(double[][] weightMatrix)

Constructor.

Parameters:

weightMatrix - weight matrix

Method Detail

distance

public double distance(NumberVector o1,
                       NumberVector o2)

Description copied from interface: PrimitiveDistance

Computes the distance between two given DatabaseObjects according to this distance function.

Specified by:

distance in interface NumberVectorDistance<NumberVector>

Specified by:

distance in interface PrimitiveDistance<NumberVector>

Parameters:

o1 - first DatabaseObject

o2 - second DatabaseObject

Returns:

the distance between two given DatabaseObjects according to this distance function

isSquared

public boolean isSquared()

Description copied from interface: Distance

Squared distances, that would become metric after square root.

E.g. squared Euclidean.

Specified by:

isSquared in interface Distance<NumberVector>

Returns:

true when squared.

norm

public double norm(NumberVector obj)

Description copied from interface: Norm

Compute the norm of object obj.

Specified by:

norm in interface Norm<NumberVector>

Parameters:

obj - Object

Returns:

Norm

equals

public boolean equals(java.lang.Object obj)

Overrides:

equals in class java.lang.Object

hashCode

public int hashCode()

Overrides:

hashCode in class java.lang.Object

getInputTypeRestriction

public VectorFieldTypeInformation<? super NumberVector> getInputTypeRestriction()

Description copied from interface: Distance

Get the input data type of the function.

Specified by:

getInputTypeRestriction in interface Distance<NumberVector>

Specified by:

getInputTypeRestriction in interface PrimitiveDistance<NumberVector>

Overrides:

getInputTypeRestriction in class AbstractNumberVectorDistance

Returns:

Type restriction