/// <summary>Constructs a Dataset by reading in a file in SVM light format.</summary>
/// <remarks>
/// Constructs a Dataset by reading in a file in SVM light format.
/// the created dataset has the same feature and label index as given
/// </remarks>
public static Edu.Stanford.Nlp.Classify.Dataset <string, string> ReadSVMLightFormat(string filename, IIndex <string> featureIndex, IIndex <string> labelIndex, IList <string> lines)
{
Edu.Stanford.Nlp.Classify.Dataset <string, string> dataset;
try
{
dataset = new Edu.Stanford.Nlp.Classify.Dataset <string, string>(10, featureIndex, labelIndex);
foreach (string line in ObjectBank.GetLineIterator(new File(filename)))
{
if (lines != null)
{
lines.Add(line);
}
dataset.Add(SvmLightLineToDatum(line));
}
}
catch (Exception e)
{
throw new Exception(e);
}
return(dataset);
}
/// <summary>
/// <inheritDoc/>
///
/// </summary>
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][];
int[] devLabels = new int[devSize];
int[][] trainData = new int[trainSize][];
int[] trainLabels = new int[trainSize];
lock (typeof(Runtime))
{
System.Array.Copy(data, start, devData, 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(labels, 0, trainLabels, 0, start);
System.Array.Copy(labels, end, trainLabels, start, Size() - end);
}
if (this is WeightedDataset <object, object> )
{
float[] trainWeights = new float[trainSize];
float[] devWeights = new float[devSize];
WeightedDataset <L, F> w = (WeightedDataset <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);
}
WeightedDataset <L, F> dev = new WeightedDataset <L, F>(labelIndex, devLabels, featureIndex, devData, devSize, devWeights);
WeightedDataset <L, F> train = new WeightedDataset <L, F>(labelIndex, trainLabels, featureIndex, trainData, trainSize, trainWeights);
return(new Pair <GeneralDataset <L, F>, GeneralDataset <L, F> >(train, dev));
}
Edu.Stanford.Nlp.Classify.Dataset <L, F> dev_1 = new Edu.Stanford.Nlp.Classify.Dataset <L, F>(labelIndex, devLabels, featureIndex, devData, devSize);
Edu.Stanford.Nlp.Classify.Dataset <L, F> train_1 = new Edu.Stanford.Nlp.Classify.Dataset <L, F>(labelIndex, trainLabels, featureIndex, trainData, trainSize);
return(new Pair <GeneralDataset <L, F>, GeneralDataset <L, F> >(train_1, dev_1));
}
