public void Run()
{
GA Ga;
Ga = new GA();
Ga.EncodingType = EncodingType.Integer;
Ga.MinIntValue = -5000;
Ga.MaxIntValue = 5000;
Ga.ChromosomeLength = Coefficients.Length;
Ga.PopulationSize = Coefficients.Length * 10;
Ga.Objective = new ObjectiveDelegate( this.LinearDiophantineObjective );
Ga.ObjectiveType = ObjectiveType.MinimizeObjective;
Ga.Terminate += new TerminateEventHandler( new ObjectiveThresholdTerminator(0).Terminate );
Ga.Terminate += new TerminateEventHandler( new EvolutionTimeTerminator( new TimeSpan(0,0,20) ).Terminate );
Ga.NewPopulation += new NewPopulationEventHandler( OnNewPopulation_ShowSummary );
Ga.FitnessScaling = FitnessScaling.LinearRanked;
Ga.Run();
Console.WriteLine("Best Individual: (obj={0})", Ga.BestObjective);
PopulationSummary ps = new PopulationSummary( Ga, Ga.Population );
Console.WriteLine(ps.BestChromosome);
Console.WriteLine("Finished. Hit return.");
Console.ReadLine();
}
static void Main()
{
//
// Create the genetic algorithm component, and set the required
// properties.
//
GA ga = new GA();
ga.EncodingType = EncodingType.Binary;
ga.ChromosomeLength = 10;
ga.PopulationSize = 50;
ga.MaxGenerations = 10;
//
// Set the objective function for the run, which provides feedback
// to the algorithm as to the relative merit of candidate solutions.
//
ga.Objective = new ObjectiveDelegate( BinaryAlternateObjective );
//
// Set a "NewPopulation" event handler so that we get a callback on
// each new generation. During the callback, we print out the
// generation's statistics and the best chromosome found so far.
//
ga.NewPopulation += new NewPopulationEventHandler( OnNewPopulation_ShowSummary );
//
// Run the algorithm. It will stop after ga.MaxGenerations have elapsed.
//
ga.Run();
//
// Output the best individual that was found during the run.
//
Console.WriteLine("Best Individual:");
PopulationSummary ps = new PopulationSummary( ga, ga.Population );
Console.WriteLine(ps.BestChromosome);
Console.WriteLine("Finished. Hit return.");
Console.ReadLine();
}
static void Main()
{
//
// Describe the coding of our problem as an array of 10 integers
// in the range [-10,10].
//
GA ga = new GA();
ga.ChromosomeLength = 10;
ga.PopulationSize = 100;
ga.MaxGenerations = 100;
ga.EncodingType = EncodingType.Integer;
ga.MinIntValue = -10;
ga.MaxIntValue = 10;
ga.Objective = new ObjectiveDelegate( IntegerMaximizationObjective );
ga.MutationOperator = MutationOperator.GeneSpecific;
//
// Set a "NewPopulation" event handler so that we get a callback on
// each new generation. During the callback, we print out the
// generation's statistics and the best chromosome found so far.
//
ga.NewPopulation += new NewPopulationEventHandler( OnNewPopulation_ShowSummary );
//
// Let it run until default termination criteria are met, or
// MaxGenerations has elapsed.
//
ga.Run();
//
// Output the best individual that was found during the run.
//
Console.WriteLine("Best Individual:");
PopulationSummary ps = new PopulationSummary( ga, ga.Population );
Console.WriteLine( ps.BestChromosome );
Console.WriteLine("Finished. Hit return.");
Console.ReadLine();
}
static void Main(string[] args)
{
GA Ga;
TravellingSalesman1dObjective Objective;
TravelingSalesman2dObjective Objective2;
int[] cities = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 1400, 15000};
Objective = new TravellingSalesman1dObjective(cities);
//
// Create the objective.
//
System.Collections.ArrayList cities2 = new System.Collections.ArrayList();
//System.IO.StreamReader sr = System.IO.File.OpenText("../../xpf131.tsp");
System.IO.StreamReader sr = System.IO.File.OpenText("../../xit1083.tsp");
string s;
bool gotime = false;
s = sr.ReadLine();
while ( s != null )
{
s.Trim();
if ( !gotime )
{
if (s == "NODE_COORD_SECTION" )
{
gotime = true;
}
s = sr.ReadLine();
continue;
}
if ( s == "EOF" )
{
break;
}
string[] sa = s.Split(' ', '\t');
if ( sa.Length != 3 )
{
throw new Exception();
}
int city = Int32.Parse(sa[0]);
int x = Int32.Parse(sa[1]);
int y = Int32.Parse(sa[2]);
cities2.Add( new Point(x, y) );
s = sr.ReadLine();
}
sr.Close();
//Point[] cities2 = new Point[] { };
Objective2 = new TravelingSalesman2dObjective( (Point[]) cities2.ToArray(typeof(Point)));
//
// Create the mutator
//
Ga = new GA();
Ga.GeneDescriptors = new GeneDescriptor[] { new IntegerGeneDescriptor() };
Ga.Homogeneous = true;
//Ga.ChromosomeLength = cities.Length;
Ga.ChromosomeLength = cities2.Count;
Ga.Recombinator = new RecombinationDelegate( new genX.Recombination.PartiallyMatchedCrossover().Recombine );
Ga.OrderMutator = new OrderMutationDelegate( genX.Reordering.Swap.Reorder );
Ga.ValueMutator = null;
Ga.Scaler = new ScalingDelegate( new genX.Scaling.LinearRankedFitnessScaler(1.6).Scale );
Ga.RecombinationProbability = 0.7;
Ga.PopulationSize = 500;
// Ga.Objective = new ObjectiveDelegate( Objective.GetObjective );
Ga.Objective = new ObjectiveDelegate( Objective2.GetObjective );
Ga.ObjectiveType = ObjectiveType.MinimizeObjective;
Ga.MaxGenerations = 1000000;
Ga.NewPopulation += new NewPopulationEventHandler( OnNewPopulation );
Ga.Run();
Console.WriteLine("Best Individual:");
Console.WriteLine( Ga.Population.Summary.BestChromosome );
Console.WriteLine("Finished. Hit return.");
Console.ReadLine();
}
static void Main()
{
//
// Create the genetic algorithm, and set the required properties.
//
GA ga = new GA();
ga.EncodingType = EncodingType.Binary;
ga.ChromosomeLength = 25;
//ga.Objective = new ObjectiveDelegate( BinaryMaximizationObjective );
ga.Objective = new ObjectiveDelegate( BinaryAlternateObjective );
ga.PopulationSize = 25;
//ga.Mutated += new MutatedEventHandler( OnMutated );
//ga.NewPopulation += new NewPopulationEventHandler( OnNewPopulation );
//ga.NewPopulation += new NewPopulationEventHandler( OnNewPopulation_ShowParents );
ga.NewPopulation += new NewPopulationEventHandler( OnNewPopulation_ShowSummary );
//ga.NewPopulation += new NewPopulationEventHandler( new BinaryPersist().NewPopulationHandler );
//ga.NewPopulation += new NewPopulationEventHandler( new BinaryPersist().NewPopulationHandlerSoap );
optimalObjective = 25;
//ga.Terminate += new TerminateEventHandler( OnTerminate_CheckForOptimal );
ga.Terminate += new TerminateEventHandler( new ObjectiveThresholdTerminator(optimalObjective).Terminate );
ga.FitnessScaling = FitnessScaling.LinearRanked;
ga.GeneMutationProbability = 0.05;
ga.Run(50);
//
// Output the best individual that was found during the run.
//
Console.WriteLine("Best Individual:");
PopulationSummary ps = new PopulationSummary( ga, ga.Population );
Console.WriteLine(ps.BestChromosome);
Console.WriteLine("Finished. Hit return.");
Console.ReadLine();
}
static void Main(string[] args)
{
GA ga;
ga = new GA();
ga.Homogeneous = true;
ga.ChromosomeLength = 5;
ga.EncodingType = EncodingType.Real;
ga.MinDoubleValue = -30;
ga.MaxDoubleValue = 30;
ga.Objective = new ObjectiveDelegate(AckleyMinimizationObjective);
ga.ObjectiveType = ObjectiveType.MinimizeObjective;
ga.Run();
PopulationSummary ps = new PopulationSummary( ga, ga.Population );
Console.WriteLine("Best Individual:");
Console.WriteLine(ps.BestChromosome);
Console.WriteLine("Finished. Hit return.");
Console.ReadLine();
}
static void Main(string[] args)
{
GA Ga;
Ga = new GA();
Ga.PopulationSize = 25;
Ga.EncodingType = EncodingType.Binary;
Ga.ChromosomeLength = 10;
Ga.NewPopulation += new NewPopulationEventHandler( OnNewPopulation );
Ga.Objective = new ObjectiveDelegate( Objective.GetObjective );
Ga.FitnessScaling = FitnessScaling.LinearRanked;
Ga.MaxGenerations = 35;
Ga.RecombinationProbability = 0.6;
Objective.Dump();
Ga.Run();
Console.WriteLine("Finished. Hit return.");
Console.ReadLine();
}
