public void Setup()
{
threeClassDataset = ArffDataSet.Create <PositivityType>("Test");
threeClassDataset.UseTotal = true;
twoClassDataset = ArffDataSet.CreateSimple("Test");
twoClassDataset.UseTotal = true;
twoClassDataset.Header.RegisterNominalClass("Positive", "Negative");
for (int i = 0; i < 20; i++)
{
var positive = threeClassDataset.AddDocument();
positive.Class.Value = PositivityType.Positive;
positive.AddRecord("Good");
positive = twoClassDataset.AddDocument();
positive.Class.Value = "Positive";
positive.AddRecord("Good");
var negative = threeClassDataset.AddDocument();
negative.Class.Value = PositivityType.Negative;
negative.AddRecord("Bad");
negative = twoClassDataset.AddDocument();
negative.Class.Value = "Negative";
negative.AddRecord("Bad");
}
}
public void Setup()
{
dataSet = ArffDataSet.CreateSimple("Test");
dataSet.Header.RegisterNominalClass("One");
var problemFactory = new ProblemFactory(dataSet);
factory = new ParametersSelectionFactory(Task.Factory, problemFactory);
}
public void Construct()
{
Assert.Throws <ArgumentNullException>(() => TrainedTreeData.Construct(null));
var result = TrainedTreeData.Construct(ArffDataSet.CreateSimple("Test"));
Assert.AreEqual(0, result.Children.Length);
Assert.AreEqual(0, result.Count);
Assert.AreEqual("Documents", result.Name);
Assert.AreEqual("Documents (0)", result.Description);
}
public void CreateNull()
{
TrainingHeader header = TrainingHeader.CreateDefault();
Assert.Throws <ArgumentNullException>(() => factory.Create(null, dataSet));
Assert.Throws <ArgumentNullException>(() => factory.Create(header, null));
header.GridSelection = false;
var result = factory.Create(header, ArffDataSet.CreateSimple("Test"));
Assert.IsInstanceOf <NullParameterSelection>(result);
}
public void Construct()
{
var arff = ArffDataSet.CreateSimple("Test");
var header = TrainingHeader.CreateDefault();
var model = new Model();
Assert.Throws <ArgumentNullException>(() => new TrainingResults(null, header, arff));
Assert.Throws <ArgumentNullException>(() => new TrainingResults(model, null, arff));
Assert.Throws <ArgumentNullException>(() => new TrainingResults(model, header, null));
var instance = new TrainingResults(model, header, arff);
Assert.IsNotNull(instance.Header);
Assert.IsNotNull(instance.Model);
}
public void Setup()
{
var dataSet = ArffDataSet.CreateSimple("Test");
var model = new Model();
model.NumberOfClasses = 2;
model.ClassLabels = null;
model.NumberOfSVPerClass = null;
model.PairwiseProbabilityA = null;
model.PairwiseProbabilityB = null;
model.SupportVectorCoefficients = new double[1][];
model.Rho = new double[1];
model.Rho[0] = 0;
model.Parameter = new Parameter();
instance = new TrainingResults(model, TrainingHeader.CreateDefault(), dataSet);
}
public void ConstructFull()
{
var dataSet = ArffDataSet.CreateSimple("Test");
dataSet.Header.RegisterNominalClass("One", "Two");
var review = dataSet.AddDocument();
review.Class.Value = "One";
review = dataSet.AddDocument();
review.Class.Value = "One";
review = dataSet.AddDocument();
review.Class.Value = "Two";
var result = TrainedTreeData.Construct(dataSet);
Assert.AreEqual(2, result.Children.Length);
Assert.AreEqual(3, result.Count);
Assert.AreEqual("Documents", result.Name);
}
public IArffDataSet CreateDataset(DocumentSet documentSet, CancellationToken token)
{
Guard.NotNull(() => documentSet, documentSet);
log.Debug("CreateDataset");
if (documentSet.Document == null ||
documentSet.Document.Length == 0)
{
log.Warn("No documents");
return(null);
}
var labels = (from item in documentSet.Document
from label in item.Labels
select label).Distinct().ToArray();
if (labels.Length == 0)
{
log.Warn("No labels found");
return(null);
}
var dataHolder = ArffDataSet.CreateSimple("subjectivity");
dataHolder.Header.RegisterNominalClass(labels);
foreach (var definition in documentSet.Document.Where(item => item.Labels.Length > 0))
{
token.ThrowIfCancellationRequested();
var label = definition.Labels.Last();
var review = dataHolder.AddDocument();
review.Class.Value = label;
foreach (var record in definition.WordsTable)
{
review.AddRecord(record.Key).Value = record.Value;
}
}
return(dataHolder);
}
public void Setup()
{
training = new Mock <ITrainingModel>();
var scheduler = new ConcurrentExclusiveSchedulerPair(TaskScheduler.Default, 2)
.ConcurrentScheduler;
taskFactory = new TaskFactory(scheduler);
parameters = new GridSearchParameters(5, new double[] { 1, 2, 3, 4 }, new double[] { 1, 2, 3, 4 }, new Parameter());
instance = new GridParameterSelection(taskFactory, training.Object, parameters);
var dataSet = ArffDataSet.CreateSimple("Test");
dataSet.Header.RegisterNominalClass("One", "Two", "Three");
dataSet.UseTotal = true;
var one = dataSet.AddDocument();
one.Class.Value = "One";
one.AddRecord("Good");
IProblemFactory factory = new ProblemFactory(dataSet);
problem = factory.Construct(dataSet).GetProblem();
resetEvent = new ManualResetEvent(false);
}
public async Task TestMultiClass()
{
var dataSet = ArffDataSet.CreateSimple("Test");
dataSet.Header.RegisterNominalClass("One", "Two", "Three");
dataSet.UseTotal = true;
for (int i = 0; i < 20; i++)
{
var one = dataSet.AddDocument();
one.Class.Value = "One";
one.AddRecord("Good");
var two = dataSet.AddDocument();
two.Class.Value = "Two";
two.AddRecord("Bad");
var three = dataSet.AddDocument();
three.Class.Value = "Three";
three.AddRecord("Some");
}
var problemFactory = new ProblemFactory(dataSet);
SvmTraining training = new SvmTraining(problemFactory, dataSet);
var parameters = training.SelectParameters(TrainingHeader.CreateDefault(), CancellationToken.None);
var results = await training.Train(parameters).ConfigureAwait(false);
var file = Path.Combine(TestContext.CurrentContext.TestDirectory, "data.arff");
dataSet.Save(file);
results.Model.Write(Path.Combine(TestContext.CurrentContext.TestDirectory, "label.dat"));
var testFile = ArffDataSet.LoadSimple(file);
SvmTesting testing = new SvmTesting(results.Model, problemFactory);
var result = testing.Test(testFile, Path.Combine(TestContext.CurrentContext.TestDirectory, "."));
Assert.AreEqual(1, result);
}
