public TrainingExample[] OverSample(TrainingExample[] trainingExamples, SamplingParams samplingParams)
{
if (!samplingParams.NeedSampling)
return trainingExamples;
var trainingSet = new TrainingSet(trainingExamples);
var delta = Math.Min(trainingSet.Majority.Length - trainingSet.Minority.Length, trainingSet.Minority.Length * samplingParams.MinorityClassMaxOversampling);
var additionalSamples = Enumerable.Range(0, delta).Select(x => OverSample(trainingSet, samplingParams)).ToArray();
return trainingExamples.Concat(additionalSamples).RandomShuffle().ToArray();
}
private TrainingExample OverSample(TrainingSet trainingSet, SamplingParams samplingParams)
{
switch (samplingParams.Strategy)
{
case SamplingStrategy.Random:
return OverSampleRandomly(trainingSet);
case SamplingStrategy.Generative:
return OverSampleGeneratively(trainingSet);
case SamplingStrategy.Perturbed:
return OverSamplePerturbed(trainingSet);
default:
throw new InvalidOperationException(string.Format("No implementation for strategy {0}", samplingParams.Strategy));
}
}
