Package org.uma.jmetal.util

Class KNearestDistanceCalculator

java.lang.Object

org.uma.jmetal.util.KNearestDistanceCalculator

public class KNearestDistanceCalculator
extends Object

Utility class for computing the distance of each row in a matrix to its K-th nearest neighbor using Euclidean distance, with optional normalization. Code created with an AI generative tool

Constructor Summary

Constructors

Constructor	Description
KNearestDistanceCalculator(int k, boolean normalize)	Creates a new KNearestDistanceCalculator.

Method Summary

Modifier and Type	Method	Description
double[]	compute(double[][] matrix)	Computes the distance of each row to its K-th nearest neighbor.

Methods inherited from class java.lang.Object

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

Constructor Details

KNearestDistanceCalculator

public KNearestDistanceCalculator(int k,
 boolean normalize)

Creates a new KNearestDistanceCalculator.

Parameters:

k - The number of nearest neighbors to consider (must be positive and less than the number of rows - 1)

normalize - Whether to normalize the input matrix before computing distances

Throws:

IllegalArgumentException - if k is not positive or if k is greater than or equal to the number of rows - 1

Method Details

compute

public double[] compute(double[][] matrix)

Computes the distance of each row to its K-th nearest neighbor.

Parameters:

matrix - The input matrix (n x m) where n is the number of rows and m is the number of features

Returns:

An array where the i-th element is the distance of the i-th row to its K-th nearest neighbor

Throws:

IllegalArgumentException - if the input matrix is null, empty, or contains rows of different lengths

IllegalStateException - if k is greater than or equal to the number of rows - 1