/// <summary>
/// Speciates the genomes in genomeList into the provided species. It is assumed that
/// the genomeList represents all of the required genomes and that the species are currently empty.
///
/// This method can be used for initialization or completely respeciating an existing genome population.
/// </summary>
public void SpeciateGenomes(IList <TGenome> genomeList, IList <Specie <TGenome> > specieList)
{
Debug.Assert(SpeciationUtils.TestEmptySpecies(specieList), "SpeciateGenomes(IList<TGenome>,IList<Species<TGenome>>) called with non-empty species");
Debug.Assert(genomeList.Count >= specieList.Count, string.Format("SpeciateGenomes(IList<TGenome>,IList<Species<TGenome>>). Specie count [{0}] is greater than genome count [{1}].", specieList.Count, genomeList.Count));
// Make a copy of genomeList and shuffle the items.
List <TGenome> gList = new List <TGenome>(genomeList);
Utilities.Shuffle(gList, _rng);
// We evenly distribute genomes between species.
// Calc how many genomes per specie. Baseline number given by integer division rounding down (by truncating fractional part).
// This is guaranteed to be at least 1 because genomeCount >= specieCount.
int genomeCount = genomeList.Count;
int specieCount = specieList.Count;
int genomesPerSpecie = genomeCount / specieCount;
// Allocate genomes to species.
int genomeIdx = 0;
for (int i = 0; i < specieCount; i++)
{
Specie <TGenome> specie = specieList[i];
for (int j = 0; j < genomesPerSpecie; j++, genomeIdx++)
{
specie.GenomeList.Add(gList[genomeIdx]);
}
}
// Evenly allocate any remaining genomes.
for (int i = 0; i < specieCount && genomeIdx < genomeCount; i++, genomeIdx++)
{
specieList[i].GenomeList.Add(gList[genomeIdx]);
}
}
/// <summary>
/// Speciates the genomes in genomeList into the provided specieList.
/// It is assumed that the genomeList represents all of the required
/// genomes and that the species are currently empty.
///
/// This method can be used for initialization or completely respeciating
/// an existing genome population.
/// </summary>
public void SpeciateGenomes(IList <TGenome> genomeList,
IList <Specie <TGenome> > specieList)
{
Debug.Assert(SpeciationUtils.TestEmptySpecies(specieList),
"SpeciateGenomes(IList<TGenome>,IList<Species<TGenome>>) called with non-empty species");
Debug.Assert(genomeList.Count >= specieList.Count,
string.Format("SpeciateGenomes(IList<TGenome>,IList<Species<TGenome>>). Species count [{0}] is greater than genome count [{1}].",
specieList.Count, genomeList.Count));
// Randomly allocate the first k genomes to their own specie.
// Because there is only one genome in these species each genome
// effectively represents a specie centroid. This is necessary to
// ensure we get k specieList. If we randomly assign all genomes to
// species from the outset and then calculate centroids then
// typically some of the species become empty. This approach ensures
// that each species will have at least one genome - because that
// genome is the specie centroid and therefore has distance of zero
// from the centroid (itself).
int specieCount = specieList.Count;
for (int i = 0; i < specieCount; i++)
{
Specie <TGenome> specie = specieList[i];
genomeList[i].SpecieIdx = specie.Idx;
specie.GenomeList.Add(genomeList[i]);
// Just set the specie centroid directly.
specie.Centroid = genomeList[i].Position;
}
// Now allocate the remaining genomes based on their distance from the centroids.
int genomeCount = genomeList.Count;
for (int i = specieCount; i < genomeCount; i++)
{
TGenome genome = genomeList[i];
Specie <TGenome> closestSpecie = FindClosestSpecie(genome, specieList);
genome.SpecieIdx = closestSpecie.Idx;
closestSpecie.GenomeList.Add(genome);
}
// Recalculate each specie's centroid.
foreach (Specie <TGenome> specie in specieList)
{
specie.Centroid = CalculateSpecieCentroid(specie);
}
// Perform the main k-means loop until convergence.
SpeciateUntilConvergence(genomeList, specieList);
Debug.Assert(SpeciationUtils.PerformIntegrityCheck(specieList));
}