smile.math.distance

Interface Distance<T>

All Superinterfaces:

java.io.Serializable, java.util.function.ToDoubleBiFunction<T,T>

All Known Subinterfaces:

Metric<T>

All Known Implementing Classes:

ChebyshevDistance, CorrelationDistance, DynamicTimeWarping, EditDistance, EuclideanDistance, HammingDistance, JaccardDistance, JensenShannonDistance, LeeDistance, MahalanobisDistance, ManhattanDistance, MinkowskiDistance, SparseChebyshevDistance, SparseEuclideanDistance, SparseManhattanDistance, SparseMinkowskiDistance, TaxonomicDistance

public interface Distance<T>
extends java.util.function.ToDoubleBiFunction<T,T>, java.io.Serializable

An interface to calculate a distance measure between two objects. A distance function maps pairs of points into the nonnegative reals and has to satisfy

• non-negativity: d(x, y) ≥ 0
• isolation: d(x, y) = 0 if and only if x = y
• symmetry: d(x, y) = d(x, y)

Note that a distance function is not required to satisfy triangular inequality |x - y| + |y - z| ≥ |x - z|, which is necessary for a metric.

Method Summary

Modifier and Type	Method and Description
default double	apply(T x, T y) Returns the distance measure between two objects.
default double	applyAsDouble(T x, T y)
default Matrix	D(T[] x) Returns the pairwise distance matrix.
default Matrix	D(T[] x, T[] y) Returns the pairwise distance matrix.
double	d(T x, T y) Returns the distance measure between two objects.

Method Detail

d

double d(T x,
         T y)

Returns the distance measure between two objects.

apply

default double apply(T x,
                     T y)

Returns the distance measure between two objects. This is simply for Scala convenience.

applyAsDouble

default double applyAsDouble(T x,
                             T y)

Specified by:

applyAsDouble in interface java.util.function.ToDoubleBiFunction<T,T>

D

default Matrix D(T[] x)

Returns the pairwise distance matrix.

Parameters:

x - samples.

Returns:

the pairwise distance matrix.

D

default Matrix D(T[] x,
                 T[] y)

Returns the pairwise distance matrix.

Parameters:

x - samples.

y - samples.

Returns:

the pairwise distance matrix.