// Methods
public override bool ExecuteCommand()
{
// Initialize the text-to-Id mappers:
int gold_i = 0;
featureToFeatureId = new TextIdMapper();
classToClassId = new TextIdMapper();
TextIdMapper[] headerToHeaderIds = new TextIdMapper[] { classToClassId };
// Workaround: Read everything from STDIN to a file. (Files are used as the text source throughout this application.)
var svmLight_data = Console.In.ReadToEnd();
Console.Error.WriteLine("{0} characters of input received.", svmLight_data.Length);
string tempFile = Path.GetTempFileName();
int[] goldClasses;
List <FeatureVector> vectors;
try
{
File.WriteAllText(tempFile, svmLight_data);
FeatureVectorFile vectorFile = new FeatureVectorFile(path: tempFile, noOfHeaderColumns: 1, featureDelimiter: ' ', isSortRequired: false);
vectors = vectorFile.LoadFromSVMLight(featureToFeatureId, headerToHeaderIds, FeatureType.Binary);
goldClasses = vectorFile.Headers[gold_i];
}
finally
{
File.Delete(tempFile);
}
Debug.Assert(vectors.Count > 0);
IdValuePair <double>[] chiSquare = new IdValuePair <double> [featureToFeatureId.Count];
//TODO: Make the implementation less binary dependent (i.e. the hardcoded 2 below).
double[][,] contingencyTable_f = new double[featureToFeatureId.Count][, ];
for (int f_i = 0; f_i < featureToFeatureId.Count; f_i++)
{
// Create a contingency table for this vector.
contingencyTable_f[f_i] = new double[classToClassId.Count, 2];
for (int v_i = 0; v_i < vectors.Count; v_i++)
{
FeatureVector v = vectors[v_i];
contingencyTable_f[f_i][v.Headers[gold_i], (int)v.Features[f_i]]++;
}
chiSquare[f_i] = new IdValuePair <double>(f_i, StatisticsHelper.CalculateChiSquare(contingencyTable_f[f_i]));
}
ReportChiSquareResults(contingencyTable_f, chiSquare);
return(true);
}
