private List <LabelVector> findCenterCandidates(object arg)
{
Job job = arg as Job;
List <LabelVector> result = new List <LabelVector>();
double norm = OversampleRate / _phi;
for (int i = job.StartIndex; i < job.EndIndex; i++)
{
LabelVector x = _data[i];
double sample = x.FeatureValue * norm;
if (ThreadsafeRandom.Test(sample))
{
LabelVector center = x.Clone() as LabelVector;
result.Add(center);
}
}
return(result);
}
private void seedCenters()
{
UpdateManager.WriteLine("Performing K-Means++ initialization...");
LabelVector center = _data.SelectRandom().Clone() as LabelVector;
center.Label = 0;
_centers.Add(center);
Stopwatch sw = new Stopwatch();
for (int i = 1; i < _k; i++)
{
sw.Reset();
UpdateManager.Write("Recalculating phi...");
sw.Start();
runJobs(o => calculatePhi(o));
sw.Stop();
UpdateManager.WriteLine("Done [{0}ms]", sw.ElapsedMilliseconds);
float[] dist = _data.Select(o => o.FeatureValue).ToArray().Normalize();
LabelVector x = _data[dist.Sample()];
_centers.Add(x.Clone() as LabelVector);
}
}