/// <summary>Builds a sigmoid model to turn the classifier outputs into probabilities.</summary>
private LinearClassifier <L, L> FitSigmoid(SVMLightClassifier <L, F> classifier, GeneralDataset <L, F> dataset)
{
RVFDataset <L, L> plattDataset = new RVFDataset <L, L>();
for (int i = 0; i < dataset.Size(); i++)
{
RVFDatum <L, F> d = dataset.GetRVFDatum(i);
ICounter <L> scores = classifier.ScoresOf((IDatum <L, F>)d);
scores.IncrementCount(null);
plattDataset.Add(new RVFDatum <L, L>(scores, d.Label()));
}
LinearClassifierFactory <L, L> factory = new LinearClassifierFactory <L, L>();
factory.SetPrior(new LogPrior(LogPrior.LogPriorType.Null));
return(factory.TrainClassifier(plattDataset));
}
public virtual Edu.Stanford.Nlp.Classify.GeneralDataset <L, F> SampleDataset(long randomSeed, double sampleFrac, bool sampleWithReplacement)
{
int sampleSize = (int)(this.Size() * sampleFrac);
Random rand = new Random(randomSeed);
Edu.Stanford.Nlp.Classify.GeneralDataset <L, F> subset;
if (this is RVFDataset)
{
subset = new RVFDataset <L, F>();
}
else
{
if (this is Dataset)
{
subset = new Dataset <L, F>();
}
else
{
throw new Exception("Can't handle this type of GeneralDataset.");
}
}
if (sampleWithReplacement)
{
for (int i = 0; i < sampleSize; i++)
{
int datumNum = rand.NextInt(this.Size());
subset.Add(this.GetDatum(datumNum));
}
}
else
{
ICollection <int> indicedSampled = Generics.NewHashSet();
while (subset.Size() < sampleSize)
{
int datumNum = rand.NextInt(this.Size());
if (!indicedSampled.Contains(datumNum))
{
subset.Add(this.GetDatum(datumNum));
indicedSampled.Add(datumNum);
}
}
}
return(subset);
}
public virtual void TestCombiningDatasets()
{
RVFDatum <string, string> datum1 = NewRVFDatum(null, "a", "b", "a");
RVFDatum <string, string> datum2 = NewRVFDatum(null, "c", "c", "b");
RVFDataset <string, string> data1 = new RVFDataset <string, string>();
data1.Add(datum1);
RVFDataset <string, string> data2 = new RVFDataset <string, string>();
data1.Add(datum2);
RVFDataset <string, string> data = new RVFDataset <string, string>();
data.AddAll(data1);
data.AddAll(data2);
IEnumerator <RVFDatum <string, string> > iterator = data.GetEnumerator();
NUnit.Framework.Assert.AreEqual(datum1, iterator.Current);
NUnit.Framework.Assert.AreEqual(datum2, iterator.Current);
NUnit.Framework.Assert.IsFalse(iterator.MoveNext());
}
public virtual void TestSVMLightIntegerFormat()
{
RVFDataset <bool, int> dataset = new RVFDataset <bool, int>();
dataset.Add(NewRVFDatum(true, 1, 2, 1, 0));
dataset.Add(NewRVFDatum(false, 2, 2, 0, 0));
dataset.Add(NewRVFDatum(true, 0, 1, 2, 2));
File tempFile = File.CreateTempFile("testSVMLightIntegerFormat", ".svm");
dataset.WriteSVMLightFormat(tempFile);
RVFDataset <bool, int> newDataset = new RVFDataset <bool, int>();
try
{
newDataset.ReadSVMLightFormat(tempFile);
NUnit.Framework.Assert.Fail("expected failure with empty indexes");
}
catch (Exception)
{
}
newDataset = new RVFDataset <bool, int>(dataset.Size(), dataset.FeatureIndex(), dataset.LabelIndex());
newDataset.ReadSVMLightFormat(tempFile);
NUnit.Framework.Assert.AreEqual(CollectionUtils.ToList(dataset), CollectionUtils.ToList(newDataset));
}
public _IEnumerator_980(RVFDataset <L, F> _enclosing)
{
this._enclosing = _enclosing;
}