public CrossValidationResults CrossValidate(int folds = 10)
{
CrossValidation <T> xval = new CrossValidation <T>();
xval.Folds = folds;
xval.Sentences.AddRange(corpus);
CrossValidationResults results = xval.Evaluate();
return(results);
}
public CrossValidationResults Evaluate()
{
Helpers.XorShiftRandom random = new Helpers.XorShiftRandom(RandomSeed);
List <Sentence> sentences = Randomize ? Sentences.OrderBy(s => random.NextUInt()).ToList() : Sentences;
List <Sentence>[] folds = new List <Sentence> [Folds];
for (int i = 0; i < Folds; i++)
{
folds[i] = new List <Sentence>();
}
for (int i = 0; i < sentences.Count; i++)
{
folds[i % Folds].Add(sentences[i]);
}
CrossValidationResults results = new CrossValidationResults();
DateTime start = DateTime.Now;
int iterationsCount = 0;
Parallel.For(0, Folds, (i) =>
{
CrossValidationResults.Result result = new CrossValidationResults.Result();
result.Fold = i + 1;
result.Test = folds[i].Select(sentence => sentence.Clone()).ToList();
result.Train = new List <Sentence>();
for (int j = 0; j < Folds; j++)
{
if (j != i)
{
result.Train.AddRange(folds[j].Select(sentence => sentence.Clone()));
}
}
ITrainableTagger tagger = Activator.CreateInstance <T>();
if (tagger is Tagging.Perceptron.PerceptronTagger)
{
Tagging.Perceptron.PerceptronTagger ptagger = tagger as Tagging.Perceptron.PerceptronTagger;
ptagger.IterationFinished += (it) =>
{
lock (folds) iterationsCount++;
if (Progress != null)
{
Progress(((double)iterationsCount / (ptagger.Iterations * Folds)));
}
};
}
tagger.Train(result.Train);
tagger.Tag(result.Test);
results.Add(result);
});
results.Duration = DateTime.Now - start;
return(results);
}