public GeneString[] getBest(int num)
{
GeneString[] toReturn = new GeneString[num];
Array.Copy(result, toReturn, num);
return toReturn;
}
public GeneticAlgorithm newInstance(GeneString[] initial, GeneticInstanceParameters parameters)
{
if (!(parameters is FuzzyGeneticsInstanceParameters))
throw new WrongParameterTypeException("Fuzzy Genetics only accepts Fuzzy Genetics Instance Parameters");
FuzzyGeneticsInstanceParameters fuzzyParameters = (FuzzyGeneticsInstanceParameters)parameters;
return new FuzzyGenetics(initial, fuzzyParameters);
}
public GeneticAlgorithm newInstance(GeneString[] initial, GeneticInstanceParameters parameters)
{
if (!(parameters is RandomRestartInstanceParameters))
throw new WrongParameterTypeException("A Random Restart Genetics instance can only be constructed using Random Restart Genetics Instance Parameters");
RandomRestartInstanceParameters rrParameters = (RandomRestartInstanceParameters)parameters;
return new RandomRestartGenetics(initial, rrParameters);
}
public GeneratorParameters(GeneString[] initial, int numGenes, int populationSize, bool randomize, Object parameters)
{
if (initial == null) initial = new GeneString[0];
this.initial = initial;
this.numGenes = numGenes;
this.populationSize = populationSize;
this.randomize = randomize;
this.parameters = parameters;
}
public GeneString[] getAll()
{
GeneString[] toReturn = new GeneString[population.Count];
for (int n = 0; n < toReturn.Length; n++)
{
toReturn[n] = population[n].genestring;
}
return toReturn;
}
public GeneString[] getBest(int num)
{
GeneString[] bestGeneStrings = new GeneString[num];
for (int n = 0; n < num; n++)
{
bestGeneStrings[n] = population[n].genestring;
}
return bestGeneStrings;
}
// creates a basic genetics object with an initial population of genestrings and mutations of those strings.
public BasicGenetics(GeneString[] initial, BasicGeneticInstanceParameters parameters)
{
fitnessFunction = parameters.fitnessFunction;
if (initial != null) parameters.generatorParameters.initial = initial;
GeneString[] initialPopulation = parameters.generator.generatePopulation(parameters.generatorParameters);
population = evaluateAll(initialPopulation);
population.Sort();
}
public int evaluate(GeneString genestring)
{
int total = 0;
for (int n = 0; n < 100; n++)
{
World world = new World(new MissileProgramSemantics().parse(genestring));
total += evaluate(world);
}
int lengthWeight = (int)Math.Pow(1.006d, genestring.getGenes().Length);
lengthWeight /= 10;
return total - lengthWeight;
}
public int evaluate(GeneString geneString)
{
if (geneString == null) return 0;
String[] testStrings = getTestStrings();
List<Swap> swaps = semantics.parse(geneString);
String[] reversedTests = getReversedStrings(testStrings, swaps);
int result = 0;
for (int n = 0; n < testStrings.Length; n++)
{
result += evaluate(testStrings[n], reversedTests[n]);
}
return result;
}
protected Gene[] getCrossoverGenes(GeneString otherSource, bool keepLength)
{
Gene[] otherGenes = otherSource.getGenes();
int maxCut = Math.Min(genes.Length, otherGenes.Length);
int cutPoint1 = SharedRandom.Next(maxCut);
int cutPoint2 = (keepLength) ? cutPoint1 : SharedRandom.Next(maxCut);
Gene[] newGenes = new Gene[cutPoint1 + otherGenes.Length - cutPoint2];
for (int n = 0; n < cutPoint1; n++)
{
newGenes[n] = genes[n].copy();
}
for (int n = 0; n < otherGenes.Length - cutPoint2; n++)
{
newGenes[n + cutPoint1] = otherGenes[n + cutPoint2].copy();
}
return newGenes;
}
public FuzzyGenetics(GeneString[] initial, FuzzyGeneticsInstanceParameters parameters)
{
this.initial = initial;
}
public GeneticAlgorithm newInstance(GeneString[] initial, GeneticInstanceParameters parameters)
{
if (!(parameters is BasicGeneticInstanceParameters))
throw new WrongParameterTypeException("A Basic Genetics instance can only be constructed using Basic Genetics Instance Parameters");
BasicGeneticInstanceParameters bParameters = (BasicGeneticInstanceParameters)parameters;
return new BasicGenetics(initial, bParameters);
}
public GeneStringIndexPair(GeneString genestring, int index)
{
this.genestring = genestring;
this.index = index;
}
// evaluates all members of an array of genestrings and puts them in a list of string/fitness pairs. (Null strings get a value of 0)
private List<GeneStringFitnessPair> evaluateAll(GeneString[] geneStrings)
{
fitnessEvaluated = new GeneStringFitnessPair[geneStrings.Length];
tasksQueued = geneStrings.Length;
for (int n = 0; n < geneStrings.Length; n++)
{
ThreadPool.QueueUserWorkItem(ThreadPoolCallBack, new GeneStringIndexPair(geneStrings[n], n));
}
tasksDone.WaitOne();
tasksDone.Reset();
return fitnessEvaluated.ToList();
}
// remainder of 1 - mutation - crossover = copy chance
// returns max fitness this round
public int run(GeneticRunParameters parameters)
{
if (!(parameters is BasicGeneticRunParameters)) throw new WrongParameterTypeException("Basic Genetics only take Basic Genetics Run Parameters");
BasicGeneticRunParameters bParameters = (BasicGeneticRunParameters)parameters;
if (bParameters.mutationChance + bParameters.crossoverChance > 1.0d)
throw new OutOfBoundsException("mutation chance + crossover chance is more than 100%");
double crossoverChance = bParameters.crossoverChance + bParameters.mutationChance; // < mutation = mutation, else < crossover = crossover, else copy
GeneString[] newGeneration = new GeneString[population.Count];
for (int n = 0; n < bParameters.keepPerRound; n++)
{
newGeneration[n] = population[n].genestring.copy();
}
for (int n = bParameters.keepPerRound; n < population.Count; n++)
{
Double rnd = SharedRandom.NextDouble();
if (rnd < bParameters.mutationChance) newGeneration[n] = mutateFrom(bParameters.keepPerRound, bParameters.mutationSeverity);
else if (rnd < crossoverChance) newGeneration[n] = crossoverFrom(bParameters.keepPerRound, bParameters.keepLength);
else newGeneration[n] = copyFrom(bParameters.keepPerRound);
}
population = evaluateAll(newGeneration);
population.Sort();
return population[0].fitness;
}
public GeneStringFitnessPair(GeneString genestring, int fitness)
{
this.genestring = genestring;
this.fitness = fitness;
}
public RandomRestartGenetics(GeneString[] initial, RandomRestartInstanceParameters parameters)
{
this.initial = initial;
this.goalValue = parameters.startingGoal;
}
private int runChampionRound(RandomRestartRunParameters rrParameters, List<GeneStringFitnessPair> bestResults)
{
if (rrParameters.verbose) Console.WriteLine("running champion round");
GeneString[] geneStrings = new GeneString[bestResults.Count];
for (int n = 0; n < bestResults.Count; n++)
{
geneStrings[n] = bestResults[n].genestring;
}
subGenetics = rrParameters.algorithm.newInstance(geneStrings, rrParameters.algorithmInstanceParameters);
return runUntilRepeating(rrParameters.algorithmRunParameters, rrParameters.numRepeatsBeforeRestart, rrParameters.verbose);
}
public abstract GeneString crossover(GeneString otherSource, bool keepLength);
