info.debatty.spark.kmedoids.neighborgenerator

Class SANeighborGenerator<T>

java.lang.Object

info.debatty.spark.kmedoids.neighborgenerator.AbstractNeighborGenerator<T>

info.debatty.spark.kmedoids.neighborgenerator.SANeighborGenerator<T>

Type Parameters:

T - Type of data that will be clustered

All Implemented Interfaces:

NeighborGenerotor<T>

public class SANeighborGenerator<T>
extends AbstractNeighborGenerator<T>

Simulated Annealing is used to select replacement point to build the candidate solution.

Author:

Thibault Debatty

Constructor Summary

Constructors

Constructor and Description
SANeighborGenerator(double initial_temp, double gamma) Initialize a Simulated Annealing based neighbor generator.

Method Summary

Modifier and Type	Method and Description
ArrayList<T>	getNeighbor(NeighborGeneratorHelper<T> helper, Solution<T> current_solution, Similarity<T> similarity) Create a neighbor candidate solution.

Methods inherited from class info.debatty.spark.kmedoids.neighborgenerator.AbstractNeighborGenerator

init, notifyCandidateSolutionCost, notifyNewSolution

Methods inherited from class java.lang.Object

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

Constructor Detail

SANeighborGenerator

public SANeighborGenerator(double initial_temp,
                           double gamma)

Initialize a Simulated Annealing based neighbor generator.

Parameters:

initial_temp -

gamma -

Method Detail

getNeighbor

public final ArrayList<T> getNeighbor(NeighborGeneratorHelper<T> helper,
                                      Solution<T> current_solution,
                                      Similarity<T> similarity)
                               throws NoNeighborFoundException

Description copied from interface: NeighborGenerotor

Create a neighbor candidate solution.

Returns:

Throws:

NoNeighborFoundException - if we could not find a neighbor solution