#region License Information /* HeuristicLab * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL) * * This file is part of HeuristicLab. * * HeuristicLab is free software: you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation, either version 3 of the License, or * (at your option) any later version. * * HeuristicLab is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with HeuristicLab. If not, see . */ #endregion using System.Collections.Generic; using System.Linq; using HeuristicLab.Analysis; using HeuristicLab.Common; using HeuristicLab.Core; using HeuristicLab.Data; using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding; using HeuristicLab.Optimization; using HeuristicLab.Parameters; using HeuristicLab.Persistence.Default.CompositeSerializers.Storable; namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Regression { /// /// An operator that analyzes the training best symbolic regression solution for multi objective symbolic regression problems. /// [Item("SymbolicRegressionMultiObjectiveTrainingBestSolutionAnalyzer", "An operator that analyzes the training best symbolic regression solution for multi objective symbolic regression problems.")] [StorableClass("F9AA824E-BDF7-40FB-A348-D746510B500F")] public sealed class SymbolicRegressionMultiObjectiveTrainingBestSolutionAnalyzer : SymbolicDataAnalysisMultiObjectiveTrainingBestSolutionAnalyzer, ISymbolicDataAnalysisInterpreterOperator, ISymbolicDataAnalysisBoundedOperator { private const string ProblemDataParameterName = "ProblemData"; private const string SymbolicDataAnalysisTreeInterpreterParameterName = "SymbolicDataAnalysisTreeInterpreter"; private const string EstimationLimitsParameterName = "EstimationLimits"; private const string MaximumSymbolicExpressionTreeLengthParameterName = "MaximumSymbolicExpressionTreeLength"; private const string ValidationPartitionParameterName = "ValidationPartition"; #region parameter properties public ILookupParameter ProblemDataParameter { get { return (ILookupParameter)Parameters[ProblemDataParameterName]; } } public ILookupParameter SymbolicDataAnalysisTreeInterpreterParameter { get { return (ILookupParameter)Parameters[SymbolicDataAnalysisTreeInterpreterParameterName]; } } public IValueLookupParameter EstimationLimitsParameter { get { return (IValueLookupParameter)Parameters[EstimationLimitsParameterName]; } } public ILookupParameter MaximumSymbolicExpressionTreeLengthParameter { get { return (ILookupParameter)Parameters[MaximumSymbolicExpressionTreeLengthParameterName]; } } public IValueLookupParameter ValidationPartitionParameter { get { return (IValueLookupParameter)Parameters[ValidationPartitionParameterName]; } } #endregion [StorableConstructor] private SymbolicRegressionMultiObjectiveTrainingBestSolutionAnalyzer(bool deserializing) : base(deserializing) { } private SymbolicRegressionMultiObjectiveTrainingBestSolutionAnalyzer(SymbolicRegressionMultiObjectiveTrainingBestSolutionAnalyzer original, Cloner cloner) : base(original, cloner) { } public SymbolicRegressionMultiObjectiveTrainingBestSolutionAnalyzer() : base() { Parameters.Add(new LookupParameter(ProblemDataParameterName, "The problem data for the symbolic regression solution.") { Hidden = true }); Parameters.Add(new LookupParameter(SymbolicDataAnalysisTreeInterpreterParameterName, "The symbolic data analysis tree interpreter for the symbolic expression tree.") { Hidden = true }); Parameters.Add(new ValueLookupParameter(EstimationLimitsParameterName, "The lower and upper limit for the estimated values produced by the symbolic regression model.") { Hidden = true }); Parameters.Add(new LookupParameter(MaximumSymbolicExpressionTreeLengthParameterName, "Maximal length of the symbolic expression.") { Hidden = true }); Parameters.Add(new ValueLookupParameter(ValidationPartitionParameterName, "The validation partition.")); } [StorableHook(HookType.AfterDeserialization)] private void AfterDeserialization() { if (!Parameters.ContainsKey(MaximumSymbolicExpressionTreeLengthParameterName)) Parameters.Add(new LookupParameter(MaximumSymbolicExpressionTreeLengthParameterName, "Maximal length of the symbolic expression.") { Hidden = true }); if (!Parameters.ContainsKey(ValidationPartitionParameterName)) Parameters.Add(new ValueLookupParameter(ValidationPartitionParameterName, "The validation partition.")); } public override IDeepCloneable Clone(Cloner cloner) { return new SymbolicRegressionMultiObjectiveTrainingBestSolutionAnalyzer(this, cloner); } protected override ISymbolicRegressionSolution CreateSolution(ISymbolicExpressionTree bestTree, double[] bestQuality) { var model = new SymbolicRegressionModel((ISymbolicExpressionTree)bestTree.Clone(), SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper); if (ApplyLinearScalingParameter.ActualValue.Value) model.Scale(ProblemDataParameter.ActualValue); return new SymbolicRegressionSolution(model, (IRegressionProblemData)ProblemDataParameter.ActualValue.Clone()); } public override IOperation Apply() { var operation = base.Apply(); var paretoFront = TrainingBestSolutionsParameter.ActualValue; IResult result; ScatterPlot qualityToTreeSize; if (!ResultCollection.TryGetValue("Pareto Front Analysis", out result)) { qualityToTreeSize = new ScatterPlot("Quality vs Tree Size", ""); qualityToTreeSize.VisualProperties.XAxisMinimumAuto = false; qualityToTreeSize.VisualProperties.XAxisMaximumAuto = false; qualityToTreeSize.VisualProperties.YAxisMinimumAuto = false; qualityToTreeSize.VisualProperties.YAxisMaximumAuto = false; qualityToTreeSize.VisualProperties.XAxisMinimumFixedValue = 0; qualityToTreeSize.VisualProperties.XAxisMaximumFixedValue = MaximumSymbolicExpressionTreeLengthParameter.ActualValue.Value; qualityToTreeSize.VisualProperties.YAxisMinimumFixedValue = 0; qualityToTreeSize.VisualProperties.YAxisMaximumFixedValue = 2; ResultCollection.Add(new Result("Pareto Front Analysis", qualityToTreeSize)); } else { qualityToTreeSize = (ScatterPlot)result.Value; } int previousTreeLength = -1; var sizeParetoFront = new LinkedList(); foreach (var solution in paretoFront.OrderBy(s => s.Model.SymbolicExpressionTree.Length)) { int treeLength = solution.Model.SymbolicExpressionTree.Length; if (!sizeParetoFront.Any()) sizeParetoFront.AddLast(solution); if (solution.TrainingNormalizedMeanSquaredError < sizeParetoFront.Last.Value.TrainingNormalizedMeanSquaredError) { if (treeLength == previousTreeLength) sizeParetoFront.RemoveLast(); sizeParetoFront.AddLast(solution); } previousTreeLength = treeLength; } qualityToTreeSize.Rows.Clear(); var trainingRow = new ScatterPlotDataRow("Training NMSE", "", sizeParetoFront.Select(x => new Point2D(x.Model.SymbolicExpressionTree.Length, x.TrainingNormalizedMeanSquaredError))); trainingRow.VisualProperties.PointSize = 8; qualityToTreeSize.Rows.Add(trainingRow); var validationPartition = ValidationPartitionParameter.ActualValue; if (validationPartition.Size != 0) { var problemData = ProblemDataParameter.ActualValue; var validationIndizes = Enumerable.Range(validationPartition.Start, validationPartition.Size).ToList(); var targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, validationIndizes).ToList(); OnlineCalculatorError error; var validationRow = new ScatterPlotDataRow("Validation NMSE", "", sizeParetoFront.Select(x => new Point2D(x.Model.SymbolicExpressionTree.Length, OnlineNormalizedMeanSquaredErrorCalculator.Calculate(targetValues, x.GetEstimatedValues(validationIndizes), out error)))); validationRow.VisualProperties.PointSize = 7; qualityToTreeSize.Rows.Add(validationRow); } return operation; } } }