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());
}
/// <summary>Method to convert this dataset to RVFDataset using L1-normalized TF-IDF features</summary>
/// <returns>RVFDataset</returns>
public virtual RVFDataset <L, F> GetL1NormalizedTFIDFDataset()
{
RVFDataset <L, F> rvfDataset = new RVFDataset <L, F>(this.Size(), this.featureIndex, this.labelIndex);
ICounter <F> featureDocCounts = GetFeatureCounter();
for (int i = 0; i < this.Size(); i++)
{
IDatum <L, F> datum = this.GetDatum(i);
RVFDatum <L, F> rvfDatum = GetL1NormalizedTFIDFDatum(datum, featureDocCounts);
rvfDataset.Add(rvfDatum);
}
return(rvfDataset);
}
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));
}
/// <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));
}
