Class GeneticAlgorithm

java.lang.Object

org.apache.commons.math3.genetics.GeneticAlgorithm

public class GeneticAlgorithm
extends Object

Implementation of a genetic algorithm. All factors that govern the operation of the algorithm can be configured for a specific problem.

Since:

2.0

Field Summary

Fields

Modifier and Type	Field	Description
private final CrossoverPolicy	crossoverPolicy	the crossover policy used by the algorithm.
private final double	crossoverRate	the rate of crossover for the algorithm.
private int	generationsEvolved	the number of generations evolved to reach StoppingCondition in the last run.
private final MutationPolicy	mutationPolicy	the mutation policy used by the algorithm.
private final double	mutationRate	the rate of mutation for the algorithm.
private static RandomGenerator	randomGenerator	Static random number generator shared by GA implementation classes.
private final SelectionPolicy	selectionPolicy	the selection policy used by the algorithm.

Constructor Summary

Constructors

Constructor	Description
GeneticAlgorithm(CrossoverPolicy crossoverPolicy, double crossoverRate, MutationPolicy mutationPolicy, double mutationRate, SelectionPolicy selectionPolicy)	Create a new genetic algorithm.

Method Summary

Modifier and Type	Method	Description
Population	evolve(Population initial, StoppingCondition condition)	Evolve the given population.
CrossoverPolicy	getCrossoverPolicy()	Returns the crossover policy.
double	getCrossoverRate()	Returns the crossover rate.
int	getGenerationsEvolved()	Returns the number of generations evolved to reach StoppingCondition in the last run.
MutationPolicy	getMutationPolicy()	Returns the mutation policy.
double	getMutationRate()	Returns the mutation rate.
static RandomGenerator	getRandomGenerator()	Returns the (static) random generator.
SelectionPolicy	getSelectionPolicy()	Returns the selection policy.
Population	nextGeneration(Population current)	Evolve the given population into the next generation.
static void	setRandomGenerator(RandomGenerator random)	Set the (static) random generator.

Methods inherited from class Object

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

Field Details

randomGenerator

private static RandomGenerator randomGenerator

Static random number generator shared by GA implementation classes. Set the randomGenerator seed to get reproducible results. Use setRandomGenerator(RandomGenerator) to supply an alternative to the default JDK-provided PRNG.

crossoverPolicy

private final CrossoverPolicy crossoverPolicy

the crossover policy used by the algorithm.

crossoverRate

private final double crossoverRate

the rate of crossover for the algorithm.

mutationPolicy

private final MutationPolicy mutationPolicy

the mutation policy used by the algorithm.

mutationRate

private final double mutationRate

the rate of mutation for the algorithm.

selectionPolicy

private final SelectionPolicy selectionPolicy

the selection policy used by the algorithm.

generationsEvolved

private int generationsEvolved

the number of generations evolved to reach StoppingCondition in the last run.

Constructor Details

GeneticAlgorithm

public GeneticAlgorithm(CrossoverPolicy crossoverPolicy,
 double crossoverRate,
 MutationPolicy mutationPolicy,
 double mutationRate,
 SelectionPolicy selectionPolicy)
                 throws OutOfRangeException

Create a new genetic algorithm.

Parameters:

crossoverPolicy - The CrossoverPolicy

crossoverRate - The crossover rate as a percentage (0-1 inclusive)

mutationPolicy - The MutationPolicy

mutationRate - The mutation rate as a percentage (0-1 inclusive)

selectionPolicy - The SelectionPolicy

Throws:

OutOfRangeException - if the crossover or mutation rate is outside the [0, 1] range

Method Details

setRandomGenerator

public static void setRandomGenerator(RandomGenerator random)

Set the (static) random generator.

Parameters:

random - random generator

getRandomGenerator

public static RandomGenerator getRandomGenerator()

Returns the (static) random generator.

Returns:

the static random generator shared by GA implementation classes

evolve

public Population evolve(Population initial,
 StoppingCondition condition)

Evolve the given population. Evolution stops when the stopping condition is satisfied. Updates the generationsEvolved property with the number of generations evolved before the StoppingCondition is satisfied.

Parameters:

initial - the initial, seed population.

condition - the stopping condition used to stop evolution.

Returns:

the population that satisfies the stopping condition.

nextGeneration

public Population nextGeneration(Population current)

Evolve the given population into the next generation.

1. Get nextGeneration population to fill from current generation, using its nextGeneration method
2. Loop until new generation is filled:
• Apply configured SelectionPolicy to select a pair of parents from current
• With probability = getCrossoverRate(), apply configured CrossoverPolicy to parents
• With probability = getMutationRate(), apply configured MutationPolicy to each of the offspring
• Add offspring individually to nextGeneration, space permitting
3. Return nextGeneration

Parameters:

current - the current population.

Returns:

the population for the next generation.

getCrossoverPolicy

public CrossoverPolicy getCrossoverPolicy()

Returns the crossover policy.

Returns:

crossover policy

getCrossoverRate

public double getCrossoverRate()

Returns the crossover rate.

Returns:

crossover rate

getMutationPolicy

public MutationPolicy getMutationPolicy()

Returns the mutation policy.

Returns:

mutation policy

getMutationRate

public double getMutationRate()

Returns the mutation rate.

Returns:

mutation rate

getSelectionPolicy

public SelectionPolicy getSelectionPolicy()

Returns the selection policy.

Returns:

selection policy

getGenerationsEvolved

public int getGenerationsEvolved()

Returns the number of generations evolved to reach StoppingCondition in the last run.

Returns:

number of generations evolved

Since:

2.1