private RegressionTreeParameters(RegressionTreeParameters original, Cloner cloner) : base(original, cloner) { problemData = cloner.Clone(original.problemData); random = cloner.Clone(original.random); leafModel = cloner.Clone(original.leafModel); splitter = cloner.Clone(original.splitter); pruning = cloner.Clone(original.pruning); minLeafSize = original.minLeafSize; }
public RegressionTreeParameters(IPruning pruning, int minleafSize, ILeafModel leafModel, IRegressionProblemData problemData, IRandom random, ISplitter splitter) { this.problemData = problemData; this.random = random; this.leafModel = leafModel; this.splitter = splitter; this.pruning = pruning; minLeafSize = Math.Max(pruning.MinLeafSize(problemData, leafModel), Math.Max(minleafSize, leafModel.MinLeafSize(problemData))); }
private static IScope InitializeScope(IRandom random, IRegressionProblemData problemData, IPruning pruning, int minLeafSize, ILeafModel leafModel, ISplitter splitter, bool generateRules, bool useHoldout, double holdoutSize) { var stateScope = new Scope("RegressionTreeStateScope"); //reduce RegressionProblemData to AllowedInput & Target column wise and to TrainingSet row wise var doubleVars = new HashSet <string>(problemData.Dataset.DoubleVariables); var vars = problemData.AllowedInputVariables.Concat(new[] { problemData.TargetVariable }).ToArray(); if (vars.Any(v => !doubleVars.Contains(v))) { throw new NotSupportedException("Decision tree regression supports only double valued input or output features."); } var doubles = vars.Select(v => problemData.Dataset.GetDoubleValues(v, problemData.TrainingIndices).ToArray()).ToArray(); if (doubles.Any(v => v.Any(x => double.IsNaN(x) || double.IsInfinity(x)))) { throw new NotSupportedException("Decision tree regression does not support NaN or infinity values in the input dataset."); } var trainingData = new Dataset(vars, doubles); var pd = new RegressionProblemData(trainingData, problemData.AllowedInputVariables, problemData.TargetVariable); pd.TrainingPartition.End = pd.TestPartition.Start = pd.TestPartition.End = pd.Dataset.Rows; pd.TrainingPartition.Start = 0; //store regression tree parameters var regressionTreeParams = new RegressionTreeParameters(pruning, minLeafSize, leafModel, pd, random, splitter); stateScope.Variables.Add(new Variable(RegressionTreeParameterVariableName, regressionTreeParams)); //initialize tree operators pruning.Initialize(stateScope); splitter.Initialize(stateScope); leafModel.Initialize(stateScope); //store unbuilt model IItem model; if (generateRules) { model = RegressionRuleSetModel.CreateRuleModel(problemData.TargetVariable, regressionTreeParams); RegressionRuleSetModel.Initialize(stateScope); } else { model = RegressionNodeTreeModel.CreateTreeModel(problemData.TargetVariable, regressionTreeParams); } stateScope.Variables.Add(new Variable(ModelVariableName, model)); //store training & pruning indices IReadOnlyList <int> trainingSet, pruningSet; GeneratePruningSet(pd.TrainingIndices.ToArray(), random, useHoldout, holdoutSize, out trainingSet, out pruningSet); stateScope.Variables.Add(new Variable(TrainingSetVariableName, new IntArray(trainingSet.ToArray()))); stateScope.Variables.Add(new Variable(PruningSetVariableName, new IntArray(pruningSet.ToArray()))); return(stateScope); }
public static IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData, IRandom random, ILeafModel leafModel = null, ISplitter splitter = null, IPruning pruning = null, bool useHoldout = false, double holdoutSize = 0.2, int minimumLeafSize = 1, bool generateRules = false, ResultCollection results = null, CancellationToken?cancellationToken = null) { if (leafModel == null) { leafModel = new LinearLeaf(); } if (splitter == null) { splitter = new Splitter(); } if (cancellationToken == null) { cancellationToken = CancellationToken.None; } if (pruning == null) { pruning = new ComplexityPruning(); } var stateScope = InitializeScope(random, problemData, pruning, minimumLeafSize, leafModel, splitter, generateRules, useHoldout, holdoutSize); var model = Build(stateScope, results, cancellationToken.Value); return(model.CreateRegressionSolution(problemData)); }