private static TrainingResults LoadCompressed(string path)
{
log.Debug("LoadNormal: {0}", path);
TrainingHeader header = null;
Model model = null;
IArffDataSet dataSet = null;
using (ZipArchive archive = ZipFile.OpenRead(path))
{
foreach (ZipArchiveEntry entry in archive.Entries)
{
if (entry.FullName.EndsWith(headerFile, StringComparison.OrdinalIgnoreCase))
{
header = XDocument.Load(entry.Open()).XmlDeserialize <TrainingHeader>();
}
else if (entry.FullName.EndsWith(modelFile, StringComparison.OrdinalIgnoreCase))
{
model = Model.Read(entry.Open());
}
else if (entry.FullName.EndsWith(arffFile, StringComparison.OrdinalIgnoreCase))
{
using (StreamReader reader = new StreamReader(entry.Open()))
{
dataSet = ArffDataSet.LoadSimple(reader);
}
}
}
}
return(new TrainingResults(model, header, dataSet));
}
public void Compute()
{
var dataSet = ArffDataSet.LoadSimple(Path.Combine(TestContext.CurrentContext.TestDirectory, "Data", @"problem.arff"));
var problem = new ProblemSource(dataSet).GetProblem();
var transform = RangeTransform.Compute(problem);
var result = transform.Scale(problem);
Assert.IsNotNull(result);
}
public void Setup()
{
var file = Path.Combine(TestContext.CurrentContext.TestDirectory, "data", "data.arff");
var dataSet = ArffDataSet.LoadSimple(file);
file = Path.Combine(TestContext.CurrentContext.TestDirectory, "data", "model.dat");
var model = Wikiled.MachineLearning.Svm.Logic.Model.Read(file);
instance = new LearnedClassifier(
new DocumentParser(Global.TextSplitter, new DevExpressParserFactory(20)),
new SvmTestClient(dataSet, model));
}
public async Task TestTwoClass()
{
var problemFactory = new ProblemFactory(twoClassDataset);
SvmTraining training = new SvmTraining(problemFactory, twoClassDataset);
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");
threeClassDataset.Save(file);
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);
}
public void Classify(string arff, string modelName, object result)
{
var file = Path.Combine(TestContext.CurrentContext.TestDirectory, "data", arff);
var dataSet = result.GetType() == typeof(PositivityType)
? ArffDataSet.Load <PositivityType>(file)
: ArffDataSet.LoadSimple(file);
file = Path.Combine(TestContext.CurrentContext.TestDirectory, "data", modelName);
var model = Model.Read(file);
IProblemFactory factory = new ProblemFactory(dataSet);
var client = new SvmTesting(model, factory);
var dataHolder = dataSet.CreateDataSet("Test");
var review = dataHolder.AddDocument();
review.AddRecord("Good").Value = 2;
review.AddRecord("Bad").Value = 1;
client.Classify(dataHolder);
Assert.AreEqual(result, review.Class.Value);
}
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);
}
private static TrainingResults LoadNormal(string path)
{
log.Debug("LoadNormal: {0}", path);
if (!Directory.Exists(path))
{
throw new ArgumentOutOfRangeException(nameof(path), path);
}
var file = GetFile(path, headerFile);
var header = File.Exists(file) ? XDocument.Load(file).XmlDeserialize <TrainingHeader>() : null;
var model = Model.Read(GetFile(path, modelFile));
IArffDataSet arff;
using (FileStream stream = new FileStream(GetFile(path, arffFile), FileMode.Open))
{
using (StreamReader reader = new StreamReader(stream))
{
arff = ArffDataSet.LoadSimple(reader);
}
}
return(new TrainingResults(model, header, arff));
}
