public PredictionResult Test(IArffDataSet testingSet)
{
Guard.NotNull(() => testingSet, testingSet);
var problemSource = problemFactory.Construct(testingSet);
return(Prediction.Predict(problemSource.GetProblem(), trainedModel, false));
}
public IParameterSelection Create(TrainingHeader header, IArffDataSet dataset)
{
Guard.NotNull(() => header, header);
Guard.NotNull(() => dataset, dataset);
Parameter defaultParameter = new Parameter();
defaultParameter.KernelType = header.Kernel;
defaultParameter.CacheSize = 200;
defaultParameter.SvmType = header.SvmType;
var model = new TrainingModel(header);
if (!header.GridSelection)
{
return(new NullParameterSelection(defaultParameter, model));
}
GridSearchParameters searchParameters;
logger.Info("Investigate LibLinear");
if (header.Kernel == KernelType.Linear)
{
var gamma = GetList(1, 1, 1);
if (dataset.Header.Total > (dataset.TotalDocuments * 10))
{
logger.Info("Selecting Linear features >> instances");
defaultParameter.Shrinking = false;
}
else
{
logger.Warn("Investigate LibLinear");
}
var training = problemFactory.Construct(dataset).GetProblem();
defaultParameter.Weights = WeightCalculation.GetWeights(training.Y);
foreach (var classItem in defaultParameter.Weights)
{
logger.Info($"Using class [{classItem.Key}] with weight [{classItem.Value}]");
}
searchParameters = new GridSearchParameters(3, GetList(-1, 2, 1), gamma, defaultParameter);
}
else
{
searchParameters = new GridSearchParameters(3, GetList(-5, 15, 2), GetList(-15, 3, 2), defaultParameter);
}
return(new GridParameterSelection(taskFactory, model, searchParameters));
}
public async Task <TrainingResults> Train(IParameterSelection selection)
{
Guard.NotNull(() => selection, selection);
Problem problem = problemFactory.Construct(dataSet).GetProblem();
var parameters = await selection.Find(problem, CancellationToken.None).ConfigureAwait(false);
// it is reasonable to choose values between 1 and 10^15
// http://stackoverflow.com/questions/19089913/data-imbalance-in-svm-using-libsvm
// http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf
// http://stats.stackexchange.com/questions/31066/what-is-the-influence-of-c-in-svms-with-linear-kernel
log.Info("Training...");
var result = selection.Training.Train(problem, parameters);
log.Info("Training Done.");
return(new TrainingResults(result, selection.Training.Header, dataSet));
}
