// Methods
public override double ExecuteCommand()
{
FeatureVectorFile vectorFile_train = new FeatureVectorFile(path: vector_file, noOfHeaderColumns: 1, featureDelimiter: ':', isSortRequired: false);
double accuracy = Program.ReportOnModel(vectorFile_train, sys_output
, classifierFactory: (classToClassId, featureToFeatureId) =>
{
return(MaxEntClassifier.LoadModel(model_file, classToClassId, featureToFeatureId));
}
, getDetailsFunc: (classifier, vectors, classToClassId, featureToFeatureId) =>
{
return(ProgramOutput.GetDistributionDetails(classifier, vectors, classToClassId));
}
);
return(accuracy);
}
// Methods
public override bool ExecuteCommand()
{
FeatureVectorFile vectorFile_train = new FeatureVectorFile(path: training_data_file, noOfHeaderColumns: 1, featureDelimiter: ' ', isSortRequired: false);
int gold_i = 0;
TextIdMapper featureToFeatureId = new TextIdMapper();
TextIdMapper classToClassId = new TextIdMapper();
TextIdMapper[] headerToHeaderIds = new TextIdMapper[] { classToClassId };
var trainingVectors = vectorFile_train.LoadFromSVMLight(featureToFeatureId, headerToHeaderIds, FeatureType.Binary);
var goldClasses_train = vectorFile_train.Headers[gold_i];
// model_file is optional.
Func <int, FeatureVector, double> calculate_Prob_c_v;
// If it is not given, p(v|c_i) = 1/|C|, where |C| is the number of class_labels.
if (string.IsNullOrWhiteSpace(model_file))
{
double kProbability = 1D / classToClassId.Count;
calculate_Prob_c_v = (v, c_i) => { return(kProbability); };
}
// If it is given, it is used to calculate p(y|xi).
else
{
MaxEntClassifier classifier = MaxEntClassifier.LoadModel(model_file, classToClassId, featureToFeatureId);
calculate_Prob_c_v =
(c_i, v) =>
{
double[] details;
int sysClass = classifier.Classify(v, out details);
return(details[c_i]);
};
}
double[,] expectation = CalculateModelExpectation(trainingVectors, calculate_Prob_c_v);
OutputEmpiricalCount(expectation, trainingVectors.Count, requiresSort: true);
return(true);
}
