public void DataTransformers()
{
PakiraDecisionTreeGenerator pakiraGenerator = PakiraGeneratorTests.CreatePakiraGeneratorInstance();
TrainData trainData = new TrainData();
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 2, 3 }), 42);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 120, 140 }), 54);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 190, 200 }), 42);
PassThroughTransformer passThroughTransformer = new PassThroughTransformer();
MeanDistanceDataTransformer meanDistanceDataTransformer = new MeanDistanceDataTransformer();
Converter <IEnumerable <double>, IEnumerable <double> > dataTransformers = null;
dataTransformers += passThroughTransformer.ConvertAll;
dataTransformers += meanDistanceDataTransformer.ConvertAll;
pakiraGenerator.CertaintyScore = 10.0;
PakiraDecisionTreeModel pakiraDecisionTreeModel = new PakiraDecisionTreeModel(dataTransformers, trainData.Samples[0]);
pakiraDecisionTreeModel = pakiraGenerator.Generate(pakiraDecisionTreeModel, trainData);
pakiraDecisionTreeModel.Tree.Root.ShouldNotBeNull();
pakiraDecisionTreeModel.PredictNode(trainData.Samples[0]).Value.ShouldBe(trainData.Labels[0]);
pakiraDecisionTreeModel.PredictNode(trainData.Samples[1]).Value.ShouldBe(trainData.Labels[1]);
pakiraDecisionTreeModel.PredictNode(trainData.Samples[2]).Value.ShouldBe(trainData.Labels[2]);
// The data transformers should allow to produce a very shallow tree
pakiraDecisionTreeModel.Tree.GetNodes().Count().ShouldBe(3);
}
public void CertaintyScore()
{
PakiraDecisionTreeGenerator pakiraGenerator = PakiraGeneratorTests.CreatePakiraGeneratorInstance();
pakiraGenerator.CertaintyScore = 1.0;
TrainData trainData = new TrainData();
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 2, 90 }), 42);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 250, 140 }), 54);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 200, 100 }), 42);
PakiraDecisionTreeModel pakiraDecisionTreeModel = new PakiraDecisionTreeModel(trainData.Samples[0]);
pakiraDecisionTreeModel = pakiraGenerator.Generate(pakiraDecisionTreeModel, trainData);
pakiraDecisionTreeModel.Tree.Root.ShouldNotBeNull();
pakiraDecisionTreeModel.PredictNode(trainData.Samples[0]).Value.ShouldBe(trainData.Labels[0]);
pakiraDecisionTreeModel.PredictNode(trainData.Samples[1]).Value.ShouldBe(trainData.Labels[1]);
pakiraDecisionTreeModel.PredictNode(trainData.Samples[2]).Value.ShouldBe(trainData.Labels[2]);
pakiraDecisionTreeModel.PredictNode(new SabotenCache(trainData.Samples[0])).PakiraLeaf.Value.ShouldBe(trainData.Labels[0]);
pakiraDecisionTreeModel.PredictNode(new SabotenCache(trainData.Samples[1])).PakiraLeaf.Value.ShouldBe(trainData.Labels[1]);
pakiraDecisionTreeModel.PredictNode(new SabotenCache(trainData.Samples[2])).PakiraLeaf.Value.ShouldBe(trainData.Labels[2]);
}
public void DeepTree()
{
PakiraDecisionTreeGenerator pakiraGenerator = PakiraGeneratorTests.CreatePakiraGeneratorInstance();
TrainData trainData = new TrainData();
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 2, 3 }), 42);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 250, 254 }), 54);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 250, 255 }), 42);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 251, 253 }), 6);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 251, 254 }), 9);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 1, 2 }), 96);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 2, 1 }), 97);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 2, 2 }), 98);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 3, 2 }), 99);
PakiraDecisionTreeModel pakiraDecisionTreeModel = new PakiraDecisionTreeModel(trainData.Samples[0]);
pakiraGenerator.MinimumSampleCount = 100;
pakiraDecisionTreeModel = pakiraGenerator.Generate(pakiraDecisionTreeModel, trainData);
pakiraDecisionTreeModel.Tree.Root.ShouldNotBeNull();
pakiraDecisionTreeModel.Tree.GetNodes().Count().ShouldBeGreaterThanOrEqualTo(15, "If the test fails because of this, the number can be reduced as long as it stays 'high'. Instead, the tree depth could also be validated.");
pakiraDecisionTreeModel.PredictNode(trainData.Samples[0]).Value.ShouldBe(trainData.Labels[0]);
pakiraDecisionTreeModel.PredictNode(trainData.Samples[1]).Value.ShouldBe(trainData.Labels[1]);
pakiraDecisionTreeModel.PredictNode(trainData.Samples[2]).Value.ShouldBe(trainData.Labels[2]);
}
public void MinimumSampleCount()
{
PakiraDecisionTreeGenerator pakiraGenerator = PakiraGeneratorTests.CreatePakiraGeneratorInstance();
TrainData trainData = new TrainData();
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 2, 3 }), 42);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 20, 140 }), 54);
trainData = trainData.AddSample(ImmutableList.CreateRange(new double[] { 33, 200 }), 42);
PakiraDecisionTreeModel pakiraDecisionTreeModel = new PakiraDecisionTreeModel(trainData.Samples[0]);
pakiraDecisionTreeModel = pakiraGenerator.Generate(pakiraDecisionTreeModel, trainData);
pakiraDecisionTreeModel.Tree.Root.ShouldNotBeNull();
pakiraDecisionTreeModel.PredictNode(trainData.Samples[0]).Value.ShouldBe(trainData.Labels[0]);
pakiraDecisionTreeModel.PredictNode(trainData.Samples[1]).Value.ShouldBe(trainData.Labels[1]);
pakiraDecisionTreeModel.PredictNode(trainData.Samples[2]).Value.ShouldBe(trainData.Labels[2]);
}