private static Edu.Stanford.Nlp.Classify.RVFDataset <string, string> ReadSVMLightFormat(string filename, IIndex <string> featureIndex, IIndex <string> labelIndex, IList <string> lines)
{
BufferedReader @in = null;
Edu.Stanford.Nlp.Classify.RVFDataset <string, string> dataset;
try
{
dataset = new Edu.Stanford.Nlp.Classify.RVFDataset <string, string>(10, featureIndex, labelIndex);
@in = IOUtils.ReaderFromString(filename);
while (@in.Ready())
{
string line = @in.ReadLine();
if (lines != null)
{
lines.Add(line);
}
dataset.Add(SvmLightLineToRVFDatum(line));
}
}
catch (IOException e)
{
throw new RuntimeIOException(e);
}
finally
{
IOUtils.CloseIgnoringExceptions(@in);
}
return(dataset);
}
public virtual void AddAllWithSourcesAndIds(Edu.Stanford.Nlp.Classify.RVFDataset <L, F> data)
{
for (int index = 0; index < data.size; index++)
{
this.Add(data.GetRVFDatumWithId(index), data.GetRVFDatumSource(index), data.GetRVFDatumId(index));
}
}
public static void Main(string[] args)
{
Edu.Stanford.Nlp.Classify.RVFDataset <string, string> data = new Edu.Stanford.Nlp.Classify.RVFDataset <string, string>();
ClassicCounter <string> c1 = new ClassicCounter <string>();
c1.IncrementCount("fever", 3.5);
c1.IncrementCount("cough", 1.1);
c1.IncrementCount("congestion", 4.2);
ClassicCounter <string> c2 = new ClassicCounter <string>();
c2.IncrementCount("fever", 1.5);
c2.IncrementCount("cough", 2.1);
c2.IncrementCount("nausea", 3.2);
ClassicCounter <string> c3 = new ClassicCounter <string>();
c3.IncrementCount("cough", 2.5);
c3.IncrementCount("congestion", 3.2);
data.Add(new RVFDatum <string, string>(c1, "cold"));
data.Add(new RVFDatum <string, string>(c2, "flu"));
data.Add(new RVFDatum <string, string>(c3, "cold"));
data.SummaryStatistics();
LinearClassifierFactory <string, string> factory = new LinearClassifierFactory <string, string>();
factory.UseQuasiNewton();
LinearClassifier <string, string> c = factory.TrainClassifier(data);
ClassicCounter <string> c4 = new ClassicCounter <string>();
c4.IncrementCount("cough", 2.3);
c4.IncrementCount("fever", 1.3);
RVFDatum <string, string> datum = new RVFDatum <string, string>(c4);
c.JustificationOf((IDatum <string, string>)datum);
}
public virtual Edu.Stanford.Nlp.Classify.RVFDataset <L, F> ScaleDatasetGaussian(Edu.Stanford.Nlp.Classify.RVFDataset <L, F> dataset)
{
Edu.Stanford.Nlp.Classify.RVFDataset <L, F> newDataset = new Edu.Stanford.Nlp.Classify.RVFDataset <L, F>(this.featureIndex, this.labelIndex);
for (int i = 0; i < dataset.Size(); i++)
{
RVFDatum <L, F> datum = ((RVFDatum <L, F>)dataset.GetDatum(i));
newDataset.Add(ScaleDatumGaussian(datum));
}
return(newDataset);
}
public override Pair <GeneralDataset <L, F>, GeneralDataset <L, F> > Split(int start, int end)
{
int devSize = end - start;
int trainSize = Size() - devSize;
int[][] devData = new int[devSize][];
double[][] devValues = new double[devSize][];
int[] devLabels = new int[devSize];
int[][] trainData = new int[trainSize][];
double[][] trainValues = new double[trainSize][];
int[] trainLabels = new int[trainSize];
lock (typeof(Runtime))
{
System.Array.Copy(data, start, devData, 0, devSize);
System.Array.Copy(values, start, devValues, 0, devSize);
System.Array.Copy(labels, start, devLabels, 0, devSize);
System.Array.Copy(data, 0, trainData, 0, start);
System.Array.Copy(data, end, trainData, start, Size() - end);
System.Array.Copy(values, 0, trainValues, 0, start);
System.Array.Copy(values, end, trainValues, start, Size() - end);
System.Array.Copy(labels, 0, trainLabels, 0, start);
System.Array.Copy(labels, end, trainLabels, start, Size() - end);
}
if (this is WeightedRVFDataset <object, object> )
{
float[] trainWeights = new float[trainSize];
float[] devWeights = new float[devSize];
WeightedRVFDataset <L, F> w = (WeightedRVFDataset <L, F>) this;
lock (typeof(Runtime))
{
System.Array.Copy(w.weights, start, devWeights, 0, devSize);
System.Array.Copy(w.weights, 0, trainWeights, 0, start);
System.Array.Copy(w.weights, end, trainWeights, start, Size() - end);
}
WeightedRVFDataset <L, F> dev = new WeightedRVFDataset <L, F>(labelIndex, devLabels, featureIndex, devData, devValues, devWeights);
WeightedRVFDataset <L, F> train = new WeightedRVFDataset <L, F>(labelIndex, trainLabels, featureIndex, trainData, trainValues, trainWeights);
return(new Pair <GeneralDataset <L, F>, GeneralDataset <L, F> >(train, dev));
}
else
{
GeneralDataset <L, F> dev = new Edu.Stanford.Nlp.Classify.RVFDataset <L, F>(labelIndex, devLabels, featureIndex, devData, devValues);
GeneralDataset <L, F> train = new Edu.Stanford.Nlp.Classify.RVFDataset <L, F>(labelIndex, trainLabels, featureIndex, trainData, trainValues);
return(new Pair <GeneralDataset <L, F>, GeneralDataset <L, F> >(train, dev));
}
}
public override Pair <GeneralDataset <L, F>, GeneralDataset <L, F> > Split(double percentDev)
{
int devSize = (int)(percentDev * Size());
int trainSize = Size() - devSize;
int[][] devData = new int[devSize][];
double[][] devValues = new double[devSize][];
int[] devLabels = new int[devSize];
int[][] trainData = new int[trainSize][];
double[][] trainValues = new double[trainSize][];
int[] trainLabels = new int[trainSize];
lock (typeof(Runtime))
{
System.Array.Copy(data, 0, devData, 0, devSize);
System.Array.Copy(values, 0, devValues, 0, devSize);
System.Array.Copy(labels, 0, devLabels, 0, devSize);
System.Array.Copy(data, devSize, trainData, 0, trainSize);
System.Array.Copy(values, devSize, trainValues, 0, trainSize);
System.Array.Copy(labels, devSize, trainLabels, 0, trainSize);
}
Edu.Stanford.Nlp.Classify.RVFDataset <L, F> dev = new Edu.Stanford.Nlp.Classify.RVFDataset <L, F>(labelIndex, devLabels, featureIndex, devData, devValues);
Edu.Stanford.Nlp.Classify.RVFDataset <L, F> train = new Edu.Stanford.Nlp.Classify.RVFDataset <L, F>(labelIndex, trainLabels, featureIndex, trainData, trainValues);
return(new Pair <GeneralDataset <L, F>, GeneralDataset <L, F> >(train, dev));
}
