public void GradientBoostingTestTowerRelativeError()
{
var gbt = new GradientBoostedTreesAlgorithm();
var provider = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.Contains("Tower"));
var regProblem = new RegressionProblem();
regProblem.Load(provider.LoadData(instance));
#region Algorithm Configuration
gbt.Problem = regProblem;
gbt.Seed = 0;
gbt.SetSeedRandomly = false;
gbt.Iterations = 3000;
gbt.MaxSize = 20;
gbt.Nu = 0.005;
gbt.LossFunctionParameter.Value = gbt.LossFunctionParameter.ValidValues.First(l => l.ToString().Contains("Relative"));
gbt.CreateSolution = false;
#endregion
gbt.Start();
Console.WriteLine(gbt.ExecutionTime);
Assert.AreEqual(0.061954221604374943, ((DoubleValue)gbt.Results["Loss (train)"].Value).Value, 1E-6);
Assert.AreEqual(0.06316303473499961, ((DoubleValue)gbt.Results["Loss (test)"].Value).Value, 1E-6);
}
public void TestDecisionTreePersistence()
{
var provider = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.Contains("Tower"));
var regProblem = new RegressionProblem();
regProblem.Load(provider.LoadData(instance));
var problemData = regProblem.ProblemData;
var state = GradientBoostedTreesAlgorithmStatic.CreateGbmState(problemData, new SquaredErrorLoss(), randSeed: 31415, maxSize: 100, r: 0.5, m: 1, nu: 1);
GradientBoostedTreesAlgorithmStatic.MakeStep(state);
var model = ((IGradientBoostedTreesModel)state.GetModel());
var treeM = model.Models.Skip(1).First();
var origStr = treeM.ToString();
using (var memStream = new MemoryStream()) {
Persistence.Default.Xml.XmlGenerator.Serialize(treeM, memStream);
var buf = memStream.GetBuffer();
using (var restoreStream = new MemoryStream(buf)) {
var restoredTree = Persistence.Default.Xml.XmlParser.Deserialize(restoreStream);
var restoredStr = restoredTree.ToString();
Assert.AreEqual(origStr, restoredStr);
}
}
}
public void GradientBoostingTestTowerAbsoluteError()
{
var gbt = new GradientBoostedTreesAlgorithm();
var provider = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.Contains("Tower"));
var regProblem = new RegressionProblem();
regProblem.Load(provider.LoadData(instance));
#region Algorithm Configuration
gbt.Problem = regProblem;
gbt.Seed = 0;
gbt.SetSeedRandomly = false;
gbt.Iterations = 1000;
gbt.MaxSize = 20;
gbt.Nu = 0.02;
gbt.LossFunctionParameter.Value = gbt.LossFunctionParameter.ValidValues.First(l => l.ToString().Contains("Absolute"));
gbt.ModelCreation = GradientBoostedTrees.ModelCreation.QualityOnly;
#endregion
gbt.Start();
Console.WriteLine(gbt.ExecutionTime);
Assert.AreEqual(10.551385044666661, ((DoubleValue)gbt.Results["Loss (train)"].Value).Value, 1E-6);
Assert.AreEqual(12.918001745581172, ((DoubleValue)gbt.Results["Loss (test)"].Value).Value, 1E-6);
}
public void GradientBoostingTestTowerSquaredError()
{
var gbt = new GradientBoostedTreesAlgorithm();
var provider = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.Contains("Tower"));
var regProblem = new RegressionProblem();
regProblem.Load(provider.LoadData(instance));
#region Algorithm Configuration
gbt.Problem = regProblem;
gbt.Seed = 0;
gbt.SetSeedRandomly = false;
gbt.Iterations = 5000;
gbt.MaxSize = 20;
gbt.CreateSolution = false;
#endregion
gbt.Start();
Console.WriteLine(gbt.ExecutionTime);
Assert.AreEqual(267.68704241153921, ((DoubleValue)gbt.Results["Loss (train)"].Value).Value, 1E-6);
Assert.AreEqual(393.84704062205469, ((DoubleValue)gbt.Results["Loss (test)"].Value).Value, 1E-6);
}
public void TestDecisionTreePartialDependence()
{
var provider = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.Contains("Tower"));
var regProblem = new RegressionProblem();
regProblem.Load(provider.LoadData(instance));
var problemData = regProblem.ProblemData;
var state = GradientBoostedTreesAlgorithmStatic.CreateGbmState(problemData, new SquaredErrorLoss(), randSeed: 31415, maxSize: 10, r: 0.5, m: 1, nu: 0.02);
for (int i = 0; i < 1000; i++)
{
GradientBoostedTreesAlgorithmStatic.MakeStep(state);
}
var mostImportantVar = state.GetVariableRelevance().OrderByDescending(kvp => kvp.Value).First();
Console.WriteLine("var: {0} relevance: {1}", mostImportantVar.Key, mostImportantVar.Value);
var model = ((IGradientBoostedTreesModel)state.GetModel());
var treeM = model.Models.Skip(1).First();
Console.WriteLine(treeM.ToString());
Console.WriteLine();
var mostImportantVarValues = problemData.Dataset.GetDoubleValues(mostImportantVar.Key).OrderBy(x => x).ToArray();
var ds = new ModifiableDataset(new string[] { mostImportantVar.Key },
new IList[] { mostImportantVarValues.ToList <double>() });
var estValues = model.GetEstimatedValues(ds, Enumerable.Range(0, mostImportantVarValues.Length)).ToArray();
for (int i = 0; i < mostImportantVarValues.Length; i += 10)
{
Console.WriteLine("{0,-5:N3} {1,-5:N3}", mostImportantVarValues[i], estValues[i]);
}
}
public void GradientBoostingTestTowerRelativeError() {
var gbt = new GradientBoostedTreesAlgorithm();
var provider = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.Contains("Tower"));
var regProblem = new RegressionProblem();
regProblem.Load(provider.LoadData(instance));
#region Algorithm Configuration
gbt.Problem = regProblem;
gbt.Seed = 0;
gbt.SetSeedRandomly = false;
gbt.Iterations = 3000;
gbt.MaxSize = 20;
gbt.Nu = 0.005;
gbt.LossFunctionParameter.Value = gbt.LossFunctionParameter.ValidValues.First(l => l.ToString().Contains("Relative"));
gbt.CreateSolution = false;
#endregion
RunAlgorithm(gbt);
Console.WriteLine(gbt.ExecutionTime);
Assert.AreEqual(0.061954221604374943, ((DoubleValue)gbt.Results["Loss (train)"].Value).Value, 1E-6);
Assert.AreEqual(0.06316303473499961, ((DoubleValue)gbt.Results["Loss (test)"].Value).Value, 1E-6);
}
public void GradientBoostingTestTowerSquaredError() {
var gbt = new GradientBoostedTreesAlgorithm();
var provider = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.Contains("Tower"));
var regProblem = new RegressionProblem();
regProblem.Load(provider.LoadData(instance));
#region Algorithm Configuration
gbt.Problem = regProblem;
gbt.Seed = 0;
gbt.SetSeedRandomly = false;
gbt.Iterations = 5000;
gbt.MaxSize = 20;
gbt.CreateSolution = false;
#endregion
RunAlgorithm(gbt);
Console.WriteLine(gbt.ExecutionTime);
Assert.AreEqual(267.68704241153921, ((DoubleValue)gbt.Results["Loss (train)"].Value).Value, 1E-6);
Assert.AreEqual(393.84704062205469, ((DoubleValue)gbt.Results["Loss (test)"].Value).Value, 1E-6);
}
public void TestDecisionTreePersistence() {
var provider = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.Contains("Tower"));
var regProblem = new RegressionProblem();
regProblem.Load(provider.LoadData(instance));
var problemData = regProblem.ProblemData;
var state = GradientBoostedTreesAlgorithmStatic.CreateGbmState(problemData, new SquaredErrorLoss(), randSeed: 31415, maxSize: 100, r: 0.5, m: 1, nu: 1);
GradientBoostedTreesAlgorithmStatic.MakeStep(state);
var model = ((IGradientBoostedTreesModel)state.GetModel());
var treeM = model.Models.Skip(1).First();
var origStr = treeM.ToString();
using (var memStream = new MemoryStream()) {
Persistence.Default.Xml.XmlGenerator.Serialize(treeM, memStream);
var buf = memStream.GetBuffer();
using (var restoreStream = new MemoryStream(buf)) {
var restoredTree = Persistence.Default.Xml.XmlParser.Deserialize(restoreStream);
var restoredStr = restoredTree.ToString();
Assert.AreEqual(origStr, restoredStr);
}
}
}
public void TestDecisionTreePartialDependence() {
var provider = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.Contains("Tower"));
var regProblem = new RegressionProblem();
regProblem.Load(provider.LoadData(instance));
var problemData = regProblem.ProblemData;
var state = GradientBoostedTreesAlgorithmStatic.CreateGbmState(problemData, new SquaredErrorLoss(), randSeed: 31415, maxSize: 10, r: 0.5, m: 1, nu: 0.02);
for (int i = 0; i < 1000; i++)
GradientBoostedTreesAlgorithmStatic.MakeStep(state);
var mostImportantVar = state.GetVariableRelevance().OrderByDescending(kvp => kvp.Value).First();
Console.WriteLine("var: {0} relevance: {1}", mostImportantVar.Key, mostImportantVar.Value);
var model = ((IGradientBoostedTreesModel)state.GetModel());
var treeM = model.Models.Skip(1).First();
Console.WriteLine(treeM.ToString());
Console.WriteLine();
var mostImportantVarValues = problemData.Dataset.GetDoubleValues(mostImportantVar.Key).OrderBy(x => x).ToArray();
var ds = new ModifiableDataset(new string[] { mostImportantVar.Key },
new IList[] { mostImportantVarValues.ToList<double>() });
var estValues = model.GetEstimatedValues(ds, Enumerable.Range(0, mostImportantVarValues.Length)).ToArray();
for (int i = 0; i < mostImportantVarValues.Length; i += 10) {
Console.WriteLine("{0,-5:N3} {1,-5:N3}", mostImportantVarValues[i], estValues[i]);
}
}
