public static async Task Evolve(
this IGeneticAlgorithm genetic,
IPopulation population,
CancellationToken token)
{
await genetic.EvolveUntil(population, _ => false, token);
}
public GameController(IDebug debug, IUiObject uiObject, IGeneticAlgorithm ga, IMainGameObject mainGameObject)
{
this.debug = debug;
this.uiObject = uiObject;
this.ga = ga;
this.mainGameObject = mainGameObject;
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <returns>True if termination has been reached, otherwise false.</returns>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
var bestFitness = geneticAlgorithm.BestChromosome.Fitness.Value;
//Console.WriteLine("Best Chromosome Fitness: {0}", bestFitness);
if (m_lastFitness == bestFitness)
{
//Console.WriteLine("Best Chromosome Fitness Value is still same");
m_stagnantGenerationsCount++;
}
else
{
//Console.WriteLine("Best Chromosome Fitness Value is changed");
m_stagnantGenerationsCount = 1;
}
//Console.WriteLine("Stagnant Generation Count: {0}", m_stagnantGenerationsCount);
m_lastFitness = bestFitness;
//if (m_stagnantGenerationsCount >= ExpectedStagnantGenerationsNumber)
//{
// Console.WriteLine("Stagnant Generation Count({0}) reached expected stagnant generation number({1})", m_stagnantGenerationsCount, ExpectedStagnantGenerationsNumber);
//}
//else
//{
// Console.WriteLine("Expected stagnant generation number({0}) is not reached yet.", ExpectedStagnantGenerationsNumber);
//}
return(m_stagnantGenerationsCount >= ExpectedStagnantGenerationsNumber);
}
/// <summary>
/// Runs one generation of genetic evolution on the population using the supplied solver.
/// </summary>
/// <param name="algorithm">Genetic algorithm to use during evolution.</param>
public virtual void Evolve(IGeneticAlgorithm algorithm)
{
var nextGeneration = algorithm.Evolve(this._Chromosomes, this.FitnessMetric, this.FitnessMode);
int size = (this.IsDynamic ? nextGeneration.Count() : this._Chromosomes.Count);
var newGeneration = new IChromosome[size];
for (int i = 0; i < size; i++)
{
IChromosome current;
if (i >= nextGeneration.Count() && !this.IsDynamic)
{
current = this.Random();
}
else
{
current = nextGeneration.ElementAt(i);
}
newGeneration[i] = current;
}
this.Apply(newGeneration);
}
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
/*var ga = geneticAlgorithm as GeneticAlgorithm;
*
* var bestFitness = geneticAlgorithm.BestChromosome.Fitness.Value;
*
* if (bestFitness <= m_lastFitness)
* {
* m_stagnantGenerationsCount++;
* Console.WriteLine($"Fitness stagnant for {m_stagnantGenerationsCount} generations.");
* }
* else
* {
* m_stagnantGenerationsCount = 1;
* }
*
* m_lastFitness = bestFitness;
*
*
* foreach (var c in ga.Population.CurrentGeneration.Chromosomes)
* {
* c.Fitness = null;
* }
*
* return m_stagnantGenerationsCount >= 50;*/
return(false);
}
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
var ga = geneticAlgorithm as GeneticAlgorithm;
var bestFitness = geneticAlgorithm.BestChromosome.Fitness.Value;
if (bestFitness <= m_lastFitness)
{
m_stagnantGenerationsCount++;
Debug.Log($"Fitness stagned for {m_stagnantGenerationsCount} generations.");
}
else
{
m_stagnantGenerationsCount = 1;
}
m_lastFitness = bestFitness;
foreach (var c in ga.Population.CurrentGeneration.Chromosomes)
{
c.Fitness = null;
}
return(m_stagnantGenerationsCount >= 50);
}
private void OnGeneticAlgorithmTerminated(object sender, GeneticAlgorithmTerminatedEventArgs args)
{
ConsoleEx.WriteLineGreen("\n\nGenetic algorithm finished because one of the stopping criteria!");
ConsoleEx.WriteLine("The final result: ");
IGeneticAlgorithm <T> ga = sender as IGeneticAlgorithm <T>;
if (ga != null)
{
string timeString = "";
if (ga.EvolutionTime < TimeSpan.FromSeconds(1))
{
timeString = ga.EvolutionTime.TotalMilliseconds + " ms";
}
else if (ga.EvolutionTime < TimeSpan.FromMinutes(1))
{
timeString = ga.EvolutionTime.TotalSeconds + " s";
}
else
{
timeString = (int)ga.EvolutionTime.TotalMinutes + " m " + ga.EvolutionTime.Seconds + " s";
}
Console.Write(string.Format(
"Time: {0, -10} Generations: {1, -8} Evaluations: {2, -10} Best fitness: {3, -20} Best individual: {4}",
timeString, ga.CurrentGeneration, ga.FitnessEvaluations, ga.BestIndividual.Fitness, ga.BestIndividual
));
}
}
public TextOptimization(IStringPatternService stringPatternService, IGeneticAlgorithm <StringPatternProcessor> geneticAlgorithm, IRawTextRepository rawTextRepository, ILog log, ITextOptimizationConfig textOptimizationConfig)
{
this.stringPatternService = stringPatternService;
this.geneticAlgorithm = geneticAlgorithm;
this.rawTextRepository = rawTextRepository;
this.log = log;
this.textOptimizationConfig = textOptimizationConfig;
}
private ISpecies[] epochStartSpecies; //temporary variable with all the simulated species of an epoch
public GeneticAlgorithmTrainerWindow(IGeneticAlgorithm geneticAlgorithm)
{
InitializeComponent();
this.geneticAlgorithm = geneticAlgorithm;
geneticAlgorithm.onScoresCalculated += (o, a) => { epochStartSpecies = geneticAlgorithm.Population.ToArray(); };
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <returns>True if termination has been reached, otherwise false.</returns>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
public bool HasReached(IGeneticAlgorithm geneticAlgorithm)
{
ExceptionHelper.ThrowIfNull("geneticAlgorithm", geneticAlgorithm);
m_hasReached = PerformHasReached(geneticAlgorithm);
return m_hasReached;
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <returns>True if termination has been reached, otherwise false.</returns>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
public bool HasReached(IGeneticAlgorithm geneticAlgorithm)
{
ExceptionHelper.ThrowIfNull("geneticAlgorithm", geneticAlgorithm);
m_hasReached = PerformHasReached(geneticAlgorithm);
return(m_hasReached);
}
public string Generate(IGeneticAlgorithm ga)
{
// Generate functions.
IFitness myFitness;
string originalTargetString = _targetParams.TargetString;
string program;
string appendCode = "";
// Split string into terms.
string[] parts = _targetParams.TargetString.Split(new char[] { ' ' });
// Build corpus of unique terms to generate functions.
Dictionary <string, string> terms = new Dictionary <string, string>();
foreach (string part in parts)
{
if (!string.IsNullOrEmpty(part))
{
terms[part] = part;
}
}
foreach (string term in terms.Values)
{
_targetParams.TargetString = term;
// Get the target fitness for this method.
myFitness = _getFitnessFunc();
_targetParams.TargetFitness = myFitness.TargetFitness;
// Run the genetic algorithm and get the best brain.
program = GAManager.Run(ga, _fitnessFunc, _generationFunc);
// Trim extraneous loop instructions from the end.
program = program.Replace("[]", "");
appendCode += program + "@";
// Reset the target fitness.
myFitness.ResetTargetFitness();
_bestStatus.Fitness = 0;
_bestStatus.TrueFitness = 0;
_bestStatus.Output = "";
_bestStatus.LastChangeDate = DateTime.Now;
_bestStatus.Program = "";
_bestStatus.Ticks = 0;
// Notify parent of progress.
_onStepComplete(appendCode, term);
}
// Restore target string.
_targetParams.TargetString = originalTargetString;
return(appendCode);
}
public GeneticAlgorithmRunner(
IGeneticAlgorithm <T> geneticAlgorithm, IOptions <GeneticOptions> geneticOptions,
IAlgorithmOutputManager <T> outputManager)
{
this.random = new Random();
this.geneticOptions = geneticOptions.Value;
this.geneticAlgorithm = geneticAlgorithm;
this.outputManager = outputManager;
}
public static async Task <GeneticEvolutionStates> TryEvolve(
this IGeneticAlgorithm genetic,
IPopulation population,
CancellationToken token)
{
var(result, _) = await genetic.TryEvolveUntil(population, _ => false, token);
return(result);
}
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
if (geneticAlgorithm?.BestChromosome?.Fitness != null &&
geneticAlgorithm.BestChromosome.Fitness.Value >= _fitnessThreshold)
{
return(true);
}
return(base.PerformHasReached(geneticAlgorithm));
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
/// <returns>
/// True if termination has been reached, otherwise false.
/// </returns>
public bool HasReached(IGeneticAlgorithm geneticAlgorithm)
{
ExceptionHelper.ThrowIfNull("geneticAlgorithm", geneticAlgorithm);
if (Terminations.Count < m_minOperands)
{
throw new InvalidOperationException("The {0} needs at least {1} terminations to perform. Please, add the missing terminations.".With(GetType().Name, m_minOperands));
}
return PerformHasReached(geneticAlgorithm);
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <returns>True if termination has been reached, otherwise false.</returns>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
var ga = geneticAlgorithm as GeneticAlgorithm;
if (ga == null)
{
throw new InvalidCastException("I am expecting genetic algorithm to be of Custom type!");
}
return(ga.Population.FruitlessGenerationsCount >= _fruitlessGenerations);
}
public override bool CheckTermination(IGeneticAlgorithm ga)
{
if (ga.GenerationNumber >= maxGenerations)
{
return(true);
}
else
{
return(false);
}
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
/// <returns>
/// True if termination has been reached, otherwise false.
/// </returns>
public bool HasReached(IGeneticAlgorithm geneticAlgorithm)
{
ExceptionHelper.ThrowIfNull("geneticAlgorithm", geneticAlgorithm);
if (Terminations.Count < m_minOperands)
{
throw new InvalidOperationException("The {0} needs at least {1} terminations to perform. Please, add the missing terminations.".With(GetType().Name, m_minOperands));
}
return(PerformHasReached(geneticAlgorithm));
}
static void Main(string[] args)
{
NeuralNetworkConfigurationSettings networkConfig = new NeuralNetworkConfigurationSettings
{
NumInputNeurons = 1,
NumOutputNeurons = 1,
NumHiddenLayers = 2,
NumHiddenNeurons = 3,
SummationFunction = new SimpleSummation(),
ActivationFunction = new TanhActivationFunction()
};
GenerationConfigurationSettings generationSettings = new GenerationConfigurationSettings
{
UseMultithreading = true,
GenerationPopulation = 500
};
EvolutionConfigurationSettings evolutionSettings = new EvolutionConfigurationSettings
{
NormalMutationRate = 0.05,
HighMutationRate = 0.5,
GenerationsPerEpoch = 10,
NumEpochs = 1000,
NumTopEvalsToReport = 10
};
MutationConfigurationSettings mutationSettings = new MutationConfigurationSettings
{
MutateAxonActivationFunction = true,
MutateNumberOfHiddenLayers = true,
MutateNumberOfHiddenNeuronsInLayer = true,
MutateSomaBiasFunction = true,
MutateSomaSummationFunction = true,
MutateSynapseWeights = true
};
var random = new RandomWeightInitializer(new Random());
INeuralNetworkFactory factory = NeuralNetworkFactory.GetInstance(SomaFactory.GetInstance(networkConfig.SummationFunction), AxonFactory.GetInstance(networkConfig.ActivationFunction), SynapseFactory.GetInstance(new RandomWeightInitializer(new Random()), AxonFactory.GetInstance(networkConfig.ActivationFunction)), SynapseFactory.GetInstance(new ConstantWeightInitializer(1.0), AxonFactory.GetInstance(new IdentityActivationFunction())), random);
IBreeder breeder = BreederFactory.GetInstance(factory, random).Create();
IMutator mutator = MutatorFactory.GetInstance(factory, random).Create(mutationSettings);
IEvalWorkingSet history = EvalWorkingSetFactory.GetInstance().Create(50);
IEvaluatableFactory evaluatableFactory = new GameEvaluationFactory();
IStorageProxy proxy = new NodeJSProxy(1, "http://localhost:3000", "123456789");
IEpochAction action = new BestPerformerUpdater(proxy);
var GAFactory = GeneticAlgorithmFactory.GetInstance(evaluatableFactory);
IGeneticAlgorithm evolver = GAFactory.Create(networkConfig, generationSettings, evolutionSettings, factory, breeder, mutator, history, evaluatableFactory, action);
evolver.RunSimulation();
}
public string Generate(IGeneticAlgorithm ga)
{
// Generate functions.
IFitness myFitness;
string originalTargetString = _targetParams.TargetString;
string program;
string appendCode = "";
// Split string into terms of 3-characters.
string[] parts = SplitInParts(_targetParams.TargetString, _chunkSize).ToArray();
// Build corpus of unique terms to generate functions.
Dictionary <string, string> terms = new Dictionary <string, string>();
foreach (string part in parts)
{
terms[part] = part;
}
foreach (string term in terms.Values)
{
_targetParams.TargetString = term;
// Get the target fitness for this method.
myFitness = _getFitnessFunc();
_targetParams.TargetFitness = myFitness.TargetFitness;
// Run the genetic algorithm and get the best brain.
program = GAManager.Run(ga, _fitnessFunc, _generationFunc);
appendCode += program + "@";
// Reset the target fitness.
myFitness.ResetTargetFitness();
_bestStatus.Fitness = 0;
_bestStatus.TrueFitness = 0;
_bestStatus.Output = "";
_bestStatus.LastChangeDate = DateTime.Now;
_bestStatus.Program = "";
_bestStatus.Ticks = 0;
}
// Restore target string.
_targetParams.TargetString = originalTargetString;
return(appendCode);
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <returns>True if termination has been reached, otherwise false.</returns>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
//Console.WriteLine("Genetic Algorithm Running Time: {0}", geneticAlgorithm.TimeEvolving);
//Console.WriteLine("Genetic Algorithm Max Running Time: {0}", MaxTime);
//if (geneticAlgorithm.TimeEvolving >= MaxTime)
//{
// Console.WriteLine("Genetic Algorithm Running Time reached Max Time to Run.");
//}
//else
//{
// Console.WriteLine("Genetic Algorithm has still some time to run.");
//}
return(geneticAlgorithm.TimeEvolving >= MaxTime);
}
public string Generate(IGeneticAlgorithm ga)
{
// Generate functions.
IFitness myFitness;
string originalTargetString = _targetParams.TargetString;
string program;
string appendCode = "";
// Split string into terms of 3-characters.
string[] parts = SplitInParts(_targetParams.TargetString, _chunkSize).ToArray();
// Build corpus of unique terms to generate functions.
Dictionary<string, string> terms = new Dictionary<string, string>();
foreach (string part in parts)
{
terms[part] = part;
}
foreach (string term in terms.Values)
{
_targetParams.TargetString = term;
// Get the target fitness for this method.
myFitness = _getFitnessFunc();
_targetParams.TargetFitness = myFitness.TargetFitness;
// Run the genetic algorithm and get the best brain.
program = GAManager.Run(ga, _fitnessFunc, _generationFunc);
appendCode += program + "@";
// Reset the target fitness.
myFitness.ResetTargetFitness();
_bestStatus.Fitness = 0;
_bestStatus.TrueFitness = 0;
_bestStatus.Output = "";
_bestStatus.LastChangeDate = DateTime.Now;
_bestStatus.Program = "";
_bestStatus.Ticks = 0;
}
// Restore target string.
_targetParams.TargetString = originalTargetString;
return appendCode;
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <returns>True if termination has been reached, otherwise false.</returns>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
var bestFitness = geneticAlgorithm.BestChromosome.Fitness.Value;
if (m_lastFitness == bestFitness)
{
m_stagnantGenerationsCount++;
}
else
{
m_stagnantGenerationsCount = 1;
}
m_lastFitness = bestFitness;
return m_stagnantGenerationsCount >= ExpectedStagnantGenerationsNumber;
}
public bool HasReached <T>(IGeneticAlgorithm <T> geneticAlgorithm) where T : IChromosome
{
double bestFitness = geneticAlgorithm.BestIndividual.Fitness;
if (_bestFitness == bestFitness)
{
_stagnatingGenerations++;
}
else
{
_stagnatingGenerations = 1;
}
_bestFitness = bestFitness;
return(_stagnatingGenerations >= MaxStagnatingGenerations);
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <returns>True if termination has been reached, otherwise false.</returns>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
var bestFitness = geneticAlgorithm.BestChromosome.Fitness.Value;
if (m_lastFitness == bestFitness)
{
m_stagnantGenerationsCount++;
}
else
{
m_stagnantGenerationsCount = 1;
}
m_lastFitness = bestFitness;
return(m_stagnantGenerationsCount >= ExpectedStagnantGenerationsNumber || bestFitness == 0 || geneticAlgorithm.TimeEvolving.TotalSeconds > 60);
}
/// <summary>
/// Setup the genetic algorithm and run it.
/// </summary>
/// <returns>Best brain's output source code</returns>
public static string Run(IGeneticAlgorithm iga, GAFunction fitnessFunc, OnGeneration generationFunc, Action setupFunc = null, bool resume = false)
{
GA ga = (GA)iga;
if (!resume)
{
if (setupFunc != null)
{
// Perform any additional setup for this fitness.
setupFunc();
}
try
{
// Delete any existing dat file.
File.Delete(Directory.GetCurrentDirectory() + "\\my-genetic-algorithm.dat");
}
catch (Exception excep)
{
Console.WriteLine("Unable to delete " + Directory.GetCurrentDirectory() + "\\my-genetic-algorithm.dat\n" + excep.Message);
}
// Start a new genetic algorithm.
ga.GAParams.Elitism = true;
ga.GAParams.HistoryPath = Directory.GetCurrentDirectory() + "\\history.txt";
ga.FitnessFunction = new GAFunction(fitnessFunc);
ga.OnGenerationFunction = new OnGeneration(generationFunc);
ga.Go();
}
else
{
// Load a saved genetic algorithm.
ga.Load("my-genetic-algorithm.dat");
ga.Resume(fitnessFunc, generationFunc);
}
// Results.
double[] weights;
double fitness;
ga.GetBest(out weights, out fitness);
Console.WriteLine("***** DONE! *****");
return(CommonManager.ConvertDoubleArrayToBF(weights));
}
/// <summary>
/// Метод, вызываемый после клика на кнопку "OK".
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private void buttonOK_Click(object sender, RoutedEventArgs e)
{
try
{
switch (Algorithm)
{
case GeneticAlgotithmMethod.ClassicGA:
ErrorMessageZeroIterationSize();
GA = new ClassicGA(
IterationSize, PopulationSize,
CMethod, CrossoverProbability, DotCrossover,
MMethod, MutationProbability, DotMutation,
SMethod, CountSelected, CountTour);
break;
case GeneticAlgotithmMethod.GenitorGA:
ErrorMessageZeroIterationSize();
GA = new GenitorGA(
IterationSize, PopulationSize,
CMethod, CrossoverProbability, DotCrossover,
MMethod, MutationProbability, DotMutation,
SMethod, CountSelected, CountTour);
break;
case GeneticAlgotithmMethod.CHCGA:
ErrorMessageZeroIterationSize();
GA = new CHCGA(
IterationSize, PopulationSize,
CrossoverProbability,
MMethod, DotMutation,
MinHemmingDistance);
break;
}
}
catch (Exception ex)
{
MessageBox.Show(ex.Message, "Error");
return;
}
DialogResult = true;
Close();
}
public GeneticCreater(IGeneticAlgorithm geneticAlgorithm, List <Input> inputList, int popopulationSize, float crossingVal, float mutationVal, int numberOfGeneration, int precision = 1)
{
if (inputList == null)
{
Console.WriteLine("Error : Input list is null !");
return;
}
this.numberOfGeneration = numberOfGeneration;
this.geneticAlgorithm = geneticAlgorithm;
inputSize = inputList.Count;
this.inputList = inputList;
chromosomes = new List <Chromosome>(popopulationSize);
AlgorithmRuleValuesCheck(popopulationSize, precision, crossingVal, mutationVal);
GetInputsBinarySize();
CreatePopulation();
NewGenerationCalculater();
chromosomesWriter(true);
generations = Chromosome.ProducerGenerations(this);
Chromosome.GetGenerationThatHaveMaxFitness(generations);
}
public void Setup()
{
var uiObject = Substitute.For <IUiObject>();
ga = Substitute.For <IGeneticAlgorithm>();
debug = Substitute.For <IDebug>();
brain1 = Substitute.For <ICarBrainController>();
brain2 = Substitute.For <ICarBrainController>();
brain3 = Substitute.For <ICarBrainController>();
brain4 = Substitute.For <ICarBrainController>();
brain5 = Substitute.For <ICarBrainController>();
mainGameObject = Substitute.For <IMainGameObject>();
mainGameObject.CreateCarBrainController(Arg.Any <List <decimal> >()).Returns(brain1, brain2, brain3, brain4, brain5);
controller = new GameController(debug, uiObject, ga, mainGameObject);
controller.Init(5);
}
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
var bestFitness = geneticAlgorithm.BestChromosome.Fitness.Value;
if (bestFitness == m_lastFitness)
{
m_stagnantGenerationsCount2++;
}
else
{
m_stagnantGenerationsCount2 = 1;
}
if (m_stagnantGenerationsCount2 == 2000)
{
List <Question> pitanja = DataAccess.DataAccess.GetInstance().GetQuestionsWhichContainDomainsAndAreSelected(Oblasti);
if (pitanja.Count != 0)
{
foreach (var p in pitanja)
{
p.Izabrano = false;
}
m_stagnantGenerationsCount2 = 1;
}
}
if (bestFitness == 0)
{
m_stagnantGenerationsCount1++;
}
else
{
m_stagnantGenerationsCount1 = 1;
}
m_lastFitness = bestFitness;
return((m_stagnantGenerationsCount1 >= ExpectedStagnantGenerationsNumber) || (m_stagnantGenerationsCount2 >= 2000));
}
/// <summary>
/// Setup the genetic algorithm and run it.
/// </summary>
/// <returns>Best brain's output source code</returns>
public static string Run(IGeneticAlgorithm iga, GAFunction fitnessFunc, OnGeneration generationFunc, Action setupFunc = null, bool resume = false)
{
GA ga = (GA)iga;
if (!resume)
{
if (setupFunc != null)
{
// Perform any additional setup for this fitness.
setupFunc();
}
// Delete any existing dat file.
File.Delete(Directory.GetCurrentDirectory() + "\\my-genetic-algorithm.dat");
// Start a new genetic algorithm.
ga.GAParams.Elitism = true;
ga.GAParams.HistoryPath = Directory.GetCurrentDirectory() + "\\history.txt";
ga.FitnessFunction = new GAFunction(fitnessFunc);
ga.OnGenerationFunction = new OnGeneration(generationFunc);
ga.Go();
}
else
{
// Load a saved genetic algorithm.
ga.Load("my-genetic-algorithm.dat");
ga.Resume(fitnessFunc, generationFunc);
}
// Results.
double[] weights;
double fitness;
ga.GetBest(out weights, out fitness);
Console.WriteLine("***** DONE! *****");
return CommonManager.ConvertDoubleArrayToBF(weights);
}
/// <summary>
/// Handles the Click event of the startStopButton control.
/// </summary>
/// <param name="sender">The source of the event.</param>
/// <param name="e">The <see cref="System.EventArgs" /> instance containing the event data.</param>
private void startStopButton_Click(object sender, EventArgs e)
{
GeneticAlgorithmParams parameters;
if (startStopButton.Text == "Start")
{
startStopButton.Text = "Stop";
EnableForm(false);
parameters = (GeneticAlgorithmParams)paramsComboBox.SelectedItem;
if (parameters.GetType() == typeof(TravellingSalesmanParams))
{
ga = new TravellingSalesmanGA((TravellingSalesmanParams)parameters);
}
else
{
ga = new NQueenGA((NQueenParams)parameters);
}
ga.SelectionMethod = (SelectionMethod)selectionComboBox.SelectedItem;
ga.CrossoverMethod = (CrossoverMethod)crossoverComboBox.SelectedItem;
ga.MutationMethod = (MutationMethod)mutationComboBox.SelectedItem;
ga.TerminationMethods.Clear();
ga.TerminationMethods.Add(new GALib.Termination.SolutionFound());
ga.TerminationMethods.Add(new GALib.Termination.GenerationLimit((int)terminationNumericUpDown.Value));
best = null;
backgroundWorker.RunWorkerAsync();
}
else
{
stopRequested = true;
}
}
/// <summary> /// Determines whether the specified geneticAlgorithm reached the termination condition. /// </summary> /// <param name="geneticAlgorithm">The genetic algorithm.</param> /// <returns> /// True if termination has been reached, otherwise false. /// </returns> protected abstract bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm);
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <returns>True if termination has been reached, otherwise false.</returns>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
return geneticAlgorithm.TimeEvolving >= MaxTime;
}
public bool HasReached <T>(IGeneticAlgorithm <T> geneticAlgorithm) where T : IChromosome
{
return(geneticAlgorithm.CurrentGeneration >= MaxGenerations);
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
/// <returns>
/// True if termination has been reached, otherwise false.
/// </returns>
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
return Terminations.All(t => t.HasReached(geneticAlgorithm));
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <returns>True if termination has been reached, otherwise false.</returns>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
return geneticAlgorithm.GenerationsNumber >= ExpectedGenerationNumber;
}
public InitialTeamSelectorStrategy(ILogger logger, IGeneticAlgorithm<FitTeam, IList<Player>> geneticTeamSelector)
{
_logger = logger;
_geneticTeamSelector = geneticTeamSelector;
}
/// <summary>
/// Determines whether the specified geneticAlgorithm reached the termination condition.
/// </summary>
/// <returns>True if termination has been reached, otherwise false.</returns>
/// <param name="geneticAlgorithm">The genetic algorithm.</param>
protected override bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm)
{
return geneticAlgorithm.BestChromosome.Fitness >= ExpectedFitness;
}
public Population(IGeneticAlgorithm genetics)
{
_genetics = genetics;
FitnessStats = new FitnessStats();
}
public TransferSelectorStrategy(IGeneticAlgorithm<FitTransferActions, SeasonState> geneticTransferSelector, ILogger logger)
{
_geneticTransferSelector = geneticTransferSelector;
_logger = logger;
}
/// <summary> /// Determines whether the specified geneticAlgorithm reached the termination condition. /// </summary> /// <returns>True if termination has been reached, otherwise false.</returns> /// <param name="geneticAlgorithm">The genetic algorithm.</param> protected abstract bool PerformHasReached(IGeneticAlgorithm geneticAlgorithm);
