de.jstacs.clustering.distances

Class DistanceMetric<T>

java.lang.Object

de.jstacs.clustering.distances.DistanceMetric<T>

Type Parameters:

T - the generic type on which the metric is defined

Direct Known Subclasses:

PearsonCorrelationDistanceMetric, SequenceScoreDistance

public abstract class DistanceMetric<T>
extends Object

This abstract class defined a DistanceMetric (which may be used for clustering) on a generic type T.

Author:

Jan Grau

Constructor Summary

Constructors

Constructor and Description
DistanceMetric()

Method Summary

Methods

Modifier and Type	Method and Description
abstract double	getDistance(T o1, T o2) Returns the distance according to the metric of the two supplied objects.
static <T> double[][]	getPairwiseDistanceMatrix(DistanceMetric<T> metric, T... objects) Returns the matrix of all pairwise distance of the supplied objects, where rows and colums are indexed in the order of the supplied objects.

Methods inherited from class java.lang.Object

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

Constructor Detail

DistanceMetric

public DistanceMetric()

Method Detail

getDistance

public abstract double getDistance(T o1,
                 T o2)
                            throws Exception

Returns the distance according to the metric of the two supplied objects.

Parameters:

o1 - the first object

o2 - the second object

Returns:

the distance

Throws:

Exception - if the distance could not be computed

getPairwiseDistanceMatrix

public static <T> double[][] getPairwiseDistanceMatrix(DistanceMetric<T> metric,
                                       T... objects)
                                            throws Exception

Returns the matrix of all pairwise distance of the supplied objects, where rows and colums are indexed in the order of the supplied objects.

Parameters:

metric - the metric

objects - the objects

Returns:

the pairwise distances

Throws:

Exception - if the distance could not be computed for one pair of objects