public GAIndividual(int nvert)
{
// Create a random individual of size numv,
// numv: number of vertices of the grapg
this.nvert = nvert;
int leftsize = randg.Next(nvert - 1) + 1;
left = new int[leftsize];
right = new int[nvert - leftsize];
int[] tmp = GAUtils.randperm(nvert);
for (int i = 0; i < left.Length; i++)
{
left[i] = tmp[i];
}
for (int i = left.Length; i < nvert; i++)
{
right[i - left.Length] = tmp[i];
}
picklist = GAUtils.perm2picklist(tmp);
evalFitness(); // evaluate fitness of this new individual
}
private void Init(int numItems)
{
Started = false;
Generation = 0;
// Create the sack items
ExternalItems = new List <SackItem>();
do
{
SackItem item = new SackItem(GAUtils.RandInt(0, 100), GAUtils.RandInt(0, 10));
if (!ExternalItems.Any(i => i.Weight == item.Weight))
{
ExternalItems.Add(item);
}
} while (ExternalItems.Count < numItems);
int geneCombinations = numItems;
int chromosoneLength = geneCombinations * 1; // 1 genes per chromosone (item in or out)
// initialize the GA
Algorithm = new GeneticAlgorithm <KnapsackGenome>(
GeneticAlgorithm <KnapsackGenome> .DefaultCrossoverRate,
GeneticAlgorithm <KnapsackGenome> .DefaultMutationRate,
GeneticAlgorithm <KnapsackGenome> .DefaultPopulationSize,
chromosoneLength,
geneCombinations);
// grab the genomes
GenomePopulation = Algorithm.GrabGenomes();
}
public static void Main()
{
GAIndividual.adj_matrix = GAUtils.readMatrix(@"d:\graph.txt");
int nvert = GAIndividual.adj_matrix.Length; // number of vertices
GAEvolve.evolveAndMakeMFile(@"d:\ga.m", 1, 400, 200, nvert, 50, 50);
}
/// <summary>
/// Takes 2 parent gene vectors, selects a midpoint and then swaps the ends
/// of each genome creating 2 new genomes which are stored in baby1 and baby2
/// </summary>
/// <param name="other"></param>
/// <param name="baby1"></param>
/// <param name="baby2"></param>
public void CrossOver(Genome <TMainModel, TCombinationModel> other, Genome <TMainModel, TCombinationModel> baby1, Genome <TMainModel, TCombinationModel> baby2)
{
// just return parents as offspring dependent on the rate
// or if parents are the same
if ((GAUtils.RandDouble() > _settings.CrossoverRate) || (this == other))
{
baby1.Genes = this.Genes;
baby2.Genes = other.Genes;
return;
}
if (baby1.Genes.Count <= 1 || baby2.Genes.Count <= 1)
{
baby1.Genes = this.Genes;
baby2.Genes = other.Genes;
return;
}
// determine a crossover point
int crossOverPoint = GAUtils.RandInt(0, this.Genes.Count - 1); // = 29
for (int i = 0; i < this.Genes.Count; i++)
{
var crossed = Genes[i].Cross(other.Genes[i], i < crossOverPoint);
baby1.Genes.Add(crossed[0]);
baby2.Genes.Add(crossed[1]);
}
}
public static void Main(string[] args)
{
int[] a = new int[] { 2, 4, 3, 1, 0, 5 };
int[] b = GAUtils.perm2picklist(a);
float[][] matrix = GAUtils.readMatrix("graph.txt");
for (int i = 0; i < matrix.Length; i++)
{
Console.WriteLine(GAUtils.array2string(matrix[i]));
}
}
public static void main(string[] args)
{
GAIndividual.adj_matrix = GAUtils.readMatrix("graph.txt");
int nvert = GAIndividual.adj_matrix.Length; // number of vertices
GAIndividual i1 = new GAIndividual(nvert);
GAIndividual i2 = new GAIndividual(nvert);
for (int i = 0; i < 1000; i++)
{
Console.WriteLine(new GAIndividual(nvert));
}
}
public static void Main()
{
GAIndividual.adj_matrix = GAUtils.readMatrix(@"d:\graph.txt");
int nvert = GAIndividual.adj_matrix.Length; // number of vertices
GAPopulation gap = new GAPopulation(100, nvert);
for (int i = 0; i < 100; i++)
{
Console.WriteLine(gap.ind[gap.best_index]);
gap = GAPopulation.generate(gap, 60, 30);
}
Console.WriteLine(gap.ind[gap.best_index]);
}
public void Initialize()
{
int geneSize = _settings.InitialPopulation.Count; // number of all items to be combined
Parts.Clear(); // for re-initialisation when there is already a gene that's the same
for (int i = 0; i < geneSize; i++)
{
Parts.Add(new GenePart <TCombinationModel>
{
Model = _settings.InitialPopulation[i],
Active = GAUtils.RandDouble() > 0.5
});
}
}
public virtual GAIndividual mutate()
{
int[] child_picklist = new int[nvert];
for (int i = 0; i < nvert; i++)
{
child_picklist[i] = picklist[i];
}
// mutate one point:
int m_point = randg.Next(nvert - 1); // mutation point
child_picklist[m_point] = randg.Next(nvert - m_point);
int[] tmp = GAUtils.picklist2perm(child_picklist);
int[] l, r;
if (nextBoolean() == true)
{
// this mutation preserves structure:
if (nextBoolean() == true)
{
l = new int[left.Length];
r = new int[right.Length];
}
else
{
l = new int[right.Length];
r = new int[left.Length];
}
}
else
{
// mutate structure:
int dpoint = 1 + randg.Next(nvert - 1); // tmp division point
l = new int[dpoint];
r = new int[nvert - dpoint];
}
for (int i = 0; i < l.Length; i++)
{
l[i] = tmp[i];
}
for (int i = 0; i < r.Length; i++)
{
r[i] = tmp[l.Length + i];
}
return(new GAIndividual(l, r));
}
/// <summary>
/// Iterates through each gene flipping the bits acording to the mutation rate
/// </summary>
public void Mutate()
{
// Go through each gene
for (int i = 0; i < Genes.Count; i++)
{
Gene <TCombinationModel> gene = Genes[i];
int mutationCounter = 0;
for (int j = 0; j < gene.Parts.Count; j++)
{
//do we flip this bit?
if (GAUtils.RandDouble() < _settings.MutationRate)
{
//flip the bit
gene.Parts[j].Active = gene.Parts[j].Active == false;
mutationCounter++;
}
}
//Debug.WriteLineIf(mutationCounter > 0, $"> Mutated {mutationCounter}/{gene.Parts.Count} items");
}
}
public static GAIndividual xover1p(GAIndividual f, GAIndividual m)
{
// 1-point cross over
int xpoint = 1 + randg.Next(f.nvert - 1);
int[] child_picklist = new int[f.nvert];
for (int i = 0; i < xpoint; i++)
{
child_picklist[i] = f.picklist[i];
}
for (int i = xpoint; i < f.nvert; i++)
{
child_picklist[i] = m.picklist[i];
}
int[] tmp = GAUtils.picklist2perm(child_picklist);
int[] l, r;
if (nextBoolean() == true)
{
l = new int[f.left.Length]; // WHY?
r = new int[tmp.Length - f.left.Length];
}
else
{
l = new int[m.left.Length]; // WHY?
r = new int[tmp.Length - m.left.Length];
}
for (int i = 0; i < l.Length; i++)
{
l[i] = tmp[i];
}
for (int i = 0; i < r.Length; i++)
{
r[i] = tmp[l.Length + i];
}
return(new GAIndividual(l, r));
}
private Genome <TMainModel, TCombinationModel> RouletteWheelSelection()
{
double fSlice = GAUtils.RandDouble() * TotalFitnessScore;
double cfTotal = 0.0;
int selectedGenome = 0;
for (int i = 0; i < Genomes.Count; ++i)
{
cfTotal += Genomes[i].Fitness;
if (cfTotal > fSlice)
{
selectedGenome = i;
break;
}
}
return(Genomes[selectedGenome]);
}
public GAIndividual(int[] l, int[] r)
{
nvert = l.Length + r.Length;
int[] tmp = new int[nvert];
left = new int[l.Length];
for (int i = 0; i < l.Length; i++)
{
left[i] = l[i];
tmp[i] = l[i];
}
right = new int[r.Length];
for (int i = 0; i < r.Length; i++)
{
right[i] = r[i];
tmp[l.Length + i] = r[i];
}
picklist = GAUtils.perm2picklist(tmp);
evalFitness(); // evaluate fitness of this new individual
}
