public void ThetasPropertyAfterTrainingReturnsTheSameThetasAsTrainerReturns()
{
// arrange
var dataSetMock = new Mock <IDataSet <bool, double> >();
dataSetMock.Setup(ds => ds.GetTrainingSamplesCount()).Returns(2);
dataSetMock.Setup(ds => ds.GetData()).Returns(new[] { TrainingSample.Create(true, new[] { 0.0 }),
TrainingSample.Create(false, new[] { 1.0 }) });
const int FeaturesCount = 1;
const double RegularizationParameter = 0.0;
var classifier = new LogisticRegressionClassifier(FeaturesCount, RegularizationParameter);
classifier.Train(dataSetMock.Object);
var classifierTraining = new LogisticRegressionClassifierTraining(FeaturesCount, RegularizationParameter, dataSetMock.Object);
var expectedThetas = classifierTraining.Train();
// act
var thetas = classifier.Thetas;
// assert
Assert.IsTrue(expectedThetas.SequenceEqual(thetas));
}
public static IDataSet <T, double> MapTwoFeaturesDataSetToDegree <T>(IDataSet <T, double> dataSet, int degree)
where T : IEquatable <T>
{
return(InMemoryDataSet.Create((from data in dataSet.GetData()
let x1 = data.Attributes[0]
let x2 = data.Attributes[1]
select TrainingSample.Create(data.Category, MapTwoFeaturesToDegrees(x1, x2, degree), data.Count))
.ToArray()));
}
private static IDataSet <bool, double> GetDataSet(string resourceName)
{
var dataLines = GetResourceLines(resourceName);
var parsedDataLines = ParseDoublesLines(dataLines, new[] { ',' });
var dataSet1 = InMemoryDataSet.Create(parsedDataLines
.Select(pl => TrainingSample.Create(pl[2] != 0, new[] { pl[0], pl[1] }))
.ToArray());
return(dataSet1);
}
public void ConstructorDoesNotThrowExceptionIfAllParametersIsGood()
{
// arrange
var dataSetMock = new Mock <IDataSet <bool, double> >();
dataSetMock.Setup(ds => ds.GetTrainingSamplesCount()).Returns(1);
dataSetMock.Setup(ds => ds.GetData()).Returns(new[] { TrainingSample.Create(true, new double[1]) });
// act
var trainer = new LogisticRegressionClassifierTraining(1, 0.0, dataSetMock.Object);
// assert
}
public void CostFunctionThrowsArgumentNullExceptionIfThetasIsNull()
{
// arrange
var dataSetMock = new Mock <IDataSet <bool, double> >();
dataSetMock.Setup(ds => ds.GetTrainingSamplesCount()).Returns(1);
dataSetMock.Setup(ds => ds.GetData()).Returns(new[] { TrainingSample.Create(true, new double[1]) });
var trainer = new LogisticRegressionClassifierTraining(1, 0.0, dataSetMock.Object);
// act
var cost = trainer.CostFunction(null, new double[0]);
// assert
Assert.Fail();
}
public void CostFunctionThrowsArgumentOutOfRangeExceptionIfOneOfTheTrainingSamplesAttributesLengthIsNotEqualToFeaturesCount()
{
// arrange
var dataSetMock = new Mock <IDataSet <bool, double> >();
dataSetMock.Setup(ds => ds.GetTrainingSamplesCount()).Returns(1);
dataSetMock.Setup(ds => ds.GetData()).Returns(new[] { TrainingSample.Create(true, new double[0]) });
var trainer = new LogisticRegressionClassifierTraining(1, 0.0, dataSetMock.Object);
// act
var cost = trainer.CostFunction(new double[2], new double[2]);
// assert
Assert.Fail();
}
public void CostFunctionThrowsNullReferenceExceptionIfOneOfTheTrainingSamplesAttributesIsNull()
{
// arrange
var dataSetMock = new Mock <IDataSet <bool, double> >();
dataSetMock.Setup(ds => ds.GetTrainingSamplesCount()).Returns(1);
dataSetMock.Setup(ds => ds.GetData()).Returns(new[] { TrainingSample.Create(true, (double[])null) });
var trainer = new LogisticRegressionClassifierTraining(1, 0.0, dataSetMock.Object);
// act
var cost = trainer.CostFunction(new double[2], new double[2]);
// assert
Assert.Fail();
}
public void TrainDoesNotThrowExceptionOnValidDataSet()
{
// arrange
var dataSetMock = new Mock <IDataSet <bool, double> >();
dataSetMock.Setup(ds => ds.GetTrainingSamplesCount()).Returns(1);
dataSetMock.Setup(ds => ds.GetData()).Returns(new[] { TrainingSample.Create(true, new double[1]) });
var classifier = new LogisticRegressionClassifier(1, 0.0);
// act
classifier.Train(dataSetMock.Object);
// assert
}
public void GetCategoryProbabilityThrowsInvalidOperationExceptionIfClassifierIsNotTrained()
{
// arrange
var dataSetMock = new Mock <IDataSet <bool, double> >();
dataSetMock.Setup(ds => ds.GetTrainingSamplesCount()).Returns(1);
dataSetMock.Setup(ds => ds.GetData()).Returns(new[] { TrainingSample.Create(true, new double[1]) });
var classifier = new LogisticRegressionClassifier(1, 0.0);
// act
classifier.GetCategoryProbability(true, new double[1]);
// assert
Assert.Fail();
}
public void CorrectlyClassifiesTestDataSetFromExample13Dot1()
{
var trainingData = InMemoryDataSet.Create(new[]
{
TrainingSample.Create("China", new[] { "Chinese", "Beijing", "Chinese" }),
TrainingSample.Create("China", new[] { "Chinese", "Chinese", "Shanghai" }),
TrainingSample.Create("China", new[] { "Chinese", "Makao" }),
TrainingSample.Create("Not China", new[] { "Tokio", "Japan", "Chinese" }),
});
var classifier = MultinomialNaiveBayesClassifier.Create(trainingData);
Assert.AreEqual("China", classifier.Classify(new[] { "Chinese", "Chinese", "Chinese", "Tokio", "Japan" }));
Assert.AreEqual("Not China", classifier.Classify(new[] { "Tokio" }));
Assert.AreEqual("China", classifier.Classify(new[] { "Chinese", "Tokio" }));
Assert.AreEqual("China", classifier.Classify(new[] { "Unknown", "Chinese", "Tokio" }));
Assert.AreEqual("Not China", classifier.Classify(new[] { "Chinese", "Tokio", "Japan" }));
}
public void ClassifyThrowsArgumentOutOfRangeExceptionIfAttributesCountIsNotEqualToFeaturesCount()
{
// arrange
var dataSetMock = new Mock <IDataSet <bool, double> >();
dataSetMock.Setup(ds => ds.GetTrainingSamplesCount()).Returns(1);
dataSetMock.Setup(ds => ds.GetData()).Returns(new[] { TrainingSample.Create(true, new double[1]) });
var classifier = new LogisticRegressionClassifier(1, 0.0);
classifier.Train(dataSetMock.Object);
// act
classifier.Classify(new double[0]);
// assert
Assert.Fail();
}
public void GetCategoryProbabilityThrowsArgumentNullExceptionIfAttributesIsNull()
{
// arrange
var dataSetMock = new Mock <IDataSet <bool, double> >();
dataSetMock.Setup(ds => ds.GetTrainingSamplesCount()).Returns(1);
dataSetMock.Setup(ds => ds.GetData()).Returns(new[] { TrainingSample.Create(true, new double[1]) });
var classifier = new LogisticRegressionClassifier(1, 0.0);
classifier.Train(dataSetMock.Object);
// act
classifier.GetCategoryProbability(true, null);
// assert
Assert.Fail();
}