public void LearningCurvesCalculator_Calculate_Sample_Percentage_Too_Low()
{
var sut = new LearningCurvesCalculator <double>(new RandomTrainingTestIndexSplitter <double>(0.8, 42),
new RandomIndexSampler <double>(42),
new MeanSquaredErrorRegressionMetric(), new double[] { 0.0, 0.8 });
var observations = new F64Matrix(10, 10);
var targets = new double[] { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 };
sut.Calculate(new RegressionDecisionTreeLearner(),
observations, targets);
}
public void LearningCurvesCalculator_Calculate()
{
var sut = new LearningCurvesCalculator <double>(new RandomTrainingTestIndexSplitter <double>(0.8, 42),
new RandomIndexSampler <double>(42), new MeanSquaredErrorRegressionMetric(), new double[] { 0.2, 0.8 });
var(observations, targets) = DataSetUtilities.LoadDecisionTreeDataSet();
var actual = sut.Calculate(new RegressionDecisionTreeLearner(),
observations, targets);
var expected = new List <LearningCurvePoint>()
{
new LearningCurvePoint(32, 0, 0.141565953928265),
new LearningCurvePoint(128, 0.0, 0.068970597423950036)
};
CollectionAssert.AreEqual(expected, actual);
}
public void LearningCurvesCalculator_Calculate()
{
var sut = new LearningCurvesCalculator <double>(new RandomTrainingTestIndexSplitter <double>(0.8, 42),
new RandomIndexSampler <double>(42), new MeanSquaredErrorRegressionMetric(), new double[] { 0.2, 0.8 });
var targetName = "T";
var parser = new CsvParser(() => new StringReader(Resources.DecisionTreeData));
var observations = parser.EnumerateRows(v => !v.Contains(targetName)).ToF64Matrix();
var targets = parser.EnumerateRows(targetName).ToF64Vector();
var actual = sut.Calculate(new RegressionDecisionTreeLearner(),
observations, targets);
var expected = new List <LearningCurvePoint>()
{
new LearningCurvePoint(32, 0, 0.141565953928265),
new LearningCurvePoint(128, 0.0, 0.068970597423950036)
};
CollectionAssert.AreEqual(expected, actual);
}