public void BinaryTreeNumericAttributesDiscreteDependentFeatures()
{
// Given
var dataSet = TestDataBuilder.ReadIrisData();
var binaryTreeBuilder = new BinaryDecisionTreeModelBuilder(
new InformationGainRatioCalculator<string>(this.shannonEntropy, this.shannonEntropy as ICategoricalImpurityMeasure<string>),
new BinarySplitSelectorForCategoricalOutcome(new BinaryDiscreteDataSplitter(), new BinaryNumericDataSplitter(), new ClassBreakpointsNumericSplitFinder()),
new CategoricalDecisionTreeLeafBuilder());
// When
var decisionTree = binaryTreeBuilder.BuildModel(dataSet, "iris_class", null);
// Then
Assert.IsNotNull(decisionTree);
}
public void Regression_NumericAttrsAndOutcomesOnly_RegularizedRegression()
{
// Given
var randomizer = new Random(3);
var splitter = new CrossValidator<double>(randomizer);
var testData = TestDataBuilder.ReadHousingDataNormalizedAttrs();
var predictor = new DecisionTreePredictor<double>();
var numericTreeBuilder = new BinaryDecisionTreeModelBuilder(
new VarianceBasedSplitQualityChecker(),
new BestSplitSelectorForNumericValues(new BinaryNumericDataSplitter()),
new RegressionAndModelDecisionTreeLeafBuilder(new RegularizedLinearRegressionModelBuilder(0.005)));
// When
var accuracies = splitter.CrossValidate(
modelBuilder: numericTreeBuilder,
modelBuilderParams: modelBuilderParams,
predictor: predictor,
qualityMeasure: new GoodnessOfFitQualityMeasure(),
dataFrame: testData,
dependentFeatureName: "MEDV",
percetnagOfTrainData: 0.7,
folds: 15);
// Then
var averegeRsquared = accuracies.Select(report => report.Accuracy).Average();
Assert.IsTrue(averegeRsquared >= 0.6);
}