private void Run()
{
DateTime start = DateTime.Now;
GReportBufferG.Clear(BackColor);
GReportBufferG.DrawString("gbp.AI.GeneticAlgorithms Environment initializing..", f, ForeColor1, 0, 0);
GReportBufferG.DrawString("started " + start.ToString(), f, ForeColor2, 0, 10);
GReportBufferG.DrawString("population size " + Size.ToString(), f, ForeColor2, 0, 20);
GReportBufferG.DrawString("crossover chance " + CrossoverChance.ToString(), f, ForeColor2, 0, 30);
GReportBufferG.DrawString("mutation chance " + MutationChance.ToString(), f, ForeColor2, 0, 40);
GReport.DrawImage(GReportBuffer, 0, 0);
GenerationBests = new ArrayList(100);
Graph2D gfitness = new Graph2D(3, GReportBufferG, new RectangleF(280, 5, 200, 140), BackColor, Color.DarkOrange);
gfitness.SetComponent(0, "average raw fitness", Color.Orange);
gfitness.SetComponent(1, "worst raw fitness", Color.DarkOrange);
gfitness.SetComponent(2, "best raw fitness", Color.Yellow);
Graph2D gdiversity = new Graph2D(1, GReportBufferG, new RectangleF(490, 5, 200, 140), BackColor, Color.DarkOrange);
gdiversity.SetComponent(0, "diversity", Color.Orange);
GraphHistogram ghistogram = new GraphHistogram("raw fitness distribution", 15, GReportBufferG, new RectangleF(700, 5, 200, 140), BackColor, Color.DarkOrange, Color.DarkOrange);
for (int g = 0 ; g < Generations && !Abort ; g++)
{
GReport3BufferG.Clear(BackColor);
GReport3BufferG.DrawString("GENERATION " + g.ToString(), f2, ForeColor1, 0, 0);
GReport3.DrawImage(GReport3Buffer, 0, 0);
GiveFitnesses(g);
GReportBufferG.Clear(BackColor);
GReportBufferG.DrawString("gbp.AI.GeneticAlgorithms Environment running..", f, ForeColor1, 0, 0);
GReportBufferG.DrawString("started " + start.ToString(), f, ForeColor2, 0, 10);
GReportBufferG.DrawString("population size " + Size.ToString(), f, ForeColor2, 0, 20);
GReportBufferG.DrawString("crossover chance " + CrossoverChance.ToString(), f, ForeColor2, 0, 30);
GReportBufferG.DrawString("mutation chance " + MutationChance.ToString(), f, ForeColor2, 0, 40);
GReportBufferG.DrawString("generation " + g.ToString() + ":", f, ForeColor1, 0, 60);
GReportBufferG.DrawString("average raw fitness " + AverageRawFitness.ToString(), f, ForeColor2, 0, 70);
GReportBufferG.DrawString("diversity " + Diversity.ToString(), f, ForeColor2, 0, 80);
GReportBufferG.DrawString("best individual:", f, ForeColor1, 0, 120);
GReportBufferG.DrawString("raw fitness " + Individuals[BestIndex].RawFitness.ToString(), f, ForeColor2, 0, 130);
GReportBufferG.DrawString("fitness " + Individuals[BestIndex].Fitness.ToString(), f, ForeColor2, 0, 140);
gfitness.AddValue(0, AverageRawFitness);
gfitness.AddValue(1, Individuals[WorstIndex].RawFitness);
gfitness.AddValue(2, Individuals[BestIndex].RawFitness);
gfitness.Draw();
gdiversity.AddValue(0, Diversity);
gdiversity.Draw();
float[] rawfitnesses = new float[Size];
for (int i = 0 ; i < Size ; i++)
rawfitnesses[i] = Individuals[i].RawFitness;
ghistogram.SetValues(rawfitnesses);
ghistogram.Draw();
GReport.DrawImage(GReportBuffer, 0, 0);
GenerationBests.Add(Individuals[BestIndex]);
if (Individuals[BestIndex].RawFitness >= FitnessTreshold)
{
SF(Individuals[BestIndex].Genome, g);
break;
}
NextGeneration();
}
STP();
}
private void Run()
{
DateTime start = DateTime.Now;
GReportBufferG.Clear(BackColor);
GReportBufferG.DrawString("gbp.AI.GeneticAlgorithms Environment initializing..", f, ForeColor1, 0, 0);
GReportBufferG.DrawString("started " + start.ToString(), f, ForeColor2, 0, 10);
GReportBufferG.DrawString("population size " + Size.ToString(), f, ForeColor2, 0, 20);
GReportBufferG.DrawString("crossover chance " + CrossoverChance.ToString(), f, ForeColor2, 0, 30);
GReportBufferG.DrawString("mutation chance " + MutationChance.ToString(), f, ForeColor2, 0, 40);
GReport.DrawImage(GReportBuffer, 0, 0);
GenerationBests = new ArrayList(100);
Graph2D gfitness = new Graph2D(3, GReportBufferG, new RectangleF(280, 5, 200, 140), BackColor, Color.DarkOrange);
gfitness.SetComponent(0, "average raw fitness", Color.Orange);
gfitness.SetComponent(1, "worst raw fitness", Color.DarkOrange);
gfitness.SetComponent(2, "best raw fitness", Color.Yellow);
Graph2D gdiversity = new Graph2D(1, GReportBufferG, new RectangleF(490, 5, 200, 140), BackColor, Color.DarkOrange);
gdiversity.SetComponent(0, "diversity", Color.Orange);
GraphHistogram ghistogram = new GraphHistogram("raw fitness distribution", 15, GReportBufferG, new RectangleF(700, 5, 200, 140), BackColor, Color.DarkOrange, Color.DarkOrange);
for (int g = 0; g < Generations && !Abort; g++)
{
GReport3BufferG.Clear(BackColor);
GReport3BufferG.DrawString("GENERATION " + g.ToString(), f2, ForeColor1, 0, 0);
GReport3.DrawImage(GReport3Buffer, 0, 0);
GiveFitnesses(g);
GReportBufferG.Clear(BackColor);
GReportBufferG.DrawString("gbp.AI.GeneticAlgorithms Environment running..", f, ForeColor1, 0, 0);
GReportBufferG.DrawString("started " + start.ToString(), f, ForeColor2, 0, 10);
GReportBufferG.DrawString("population size " + Size.ToString(), f, ForeColor2, 0, 20);
GReportBufferG.DrawString("crossover chance " + CrossoverChance.ToString(), f, ForeColor2, 0, 30);
GReportBufferG.DrawString("mutation chance " + MutationChance.ToString(), f, ForeColor2, 0, 40);
GReportBufferG.DrawString("generation " + g.ToString() + ":", f, ForeColor1, 0, 60);
GReportBufferG.DrawString("average raw fitness " + AverageRawFitness.ToString(), f, ForeColor2, 0, 70);
GReportBufferG.DrawString("diversity " + Diversity.ToString(), f, ForeColor2, 0, 80);
GReportBufferG.DrawString("best individual:", f, ForeColor1, 0, 120);
GReportBufferG.DrawString("raw fitness " + Individuals[BestIndex].RawFitness.ToString(), f, ForeColor2, 0, 130);
GReportBufferG.DrawString("fitness " + Individuals[BestIndex].Fitness.ToString(), f, ForeColor2, 0, 140);
gfitness.AddValue(0, AverageRawFitness);
gfitness.AddValue(1, Individuals[WorstIndex].RawFitness);
gfitness.AddValue(2, Individuals[BestIndex].RawFitness);
gfitness.Draw();
gdiversity.AddValue(0, Diversity);
gdiversity.Draw();
float[] rawfitnesses = new float[Size];
for (int i = 0; i < Size; i++)
{
rawfitnesses[i] = Individuals[i].RawFitness;
}
ghistogram.SetValues(rawfitnesses);
ghistogram.Draw();
GReport.DrawImage(GReportBuffer, 0, 0);
GenerationBests.Add(Individuals[BestIndex]);
if (Individuals[BestIndex].RawFitness >= FitnessTreshold)
{
SF(Individuals[BestIndex].Genome, g);
break;
}
NextGeneration();
}
STP();
}