smile.math.distance

Class SparseMinkowskiDistance

java.lang.Object

smile.math.distance.SparseMinkowskiDistance

All Implemented Interfaces:

java.io.Serializable, Distance<SparseArray>, Metric<SparseArray>

public class SparseMinkowskiDistance
extends java.lang.Object
implements Metric<SparseArray>, java.io.Serializable

Minkowski distance of order p or L_p-norm, is a generalization of Euclidean distance that is actually L₂-norm. You may also provide a specified weight vector. For float or double arrays, missing values (i.e. NaN) are also handled. Also support sparse arrays of which zeros are excluded to save space.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
SparseMinkowskiDistance(int p) Constructor.
SparseMinkowskiDistance(int p, double[] weight) Constructor.

Method Summary

Modifier and Type	Method and Description
double	d(SparseArray x, SparseArray y) Returns the distance measure between two objects.
java.lang.String	toString()

Methods inherited from class java.lang.Object

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

Constructor Detail

SparseMinkowskiDistance

public SparseMinkowskiDistance(int p)

Constructor.

SparseMinkowskiDistance

public SparseMinkowskiDistance(int p,
                               double[] weight)

Constructor.

Parameters:

weight - the weight vector.

Method Detail

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

d

public double d(SparseArray x,
                SparseArray y)

Description copied from interface: Distance

Returns the distance measure between two objects.

Specified by:

d in interface Distance<SparseArray>