[4056] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
| 3 | * Copyright (C) 2002-2010 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
| 4 | *
|
---|
| 5 | * This file is part of HeuristicLab.
|
---|
| 6 | *
|
---|
| 7 | * HeuristicLab is free software: you can redistribute it and/or modify
|
---|
| 8 | * it under the terms of the GNU General Public License as published by
|
---|
| 9 | * the Free Software Foundation, either version 3 of the License, or
|
---|
| 10 | * (at your option) any later version.
|
---|
| 11 | *
|
---|
| 12 | * HeuristicLab is distributed in the hope that it will be useful,
|
---|
| 13 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 14 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 15 | * GNU General Public License for more details.
|
---|
| 16 | *
|
---|
| 17 | * You should have received a copy of the GNU General Public License
|
---|
| 18 | * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
|
---|
| 19 | */
|
---|
| 20 | #endregion
|
---|
| 21 |
|
---|
[4068] | 22 | using System.Collections.Generic;
|
---|
[4056] | 23 | using System.Linq;
|
---|
| 24 | using HeuristicLab.Core;
|
---|
| 25 | using HeuristicLab.Data;
|
---|
[4068] | 26 | using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
|
---|
| 27 | using HeuristicLab.Parameters;
|
---|
[4056] | 28 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
[4068] | 29 | using HeuristicLab.Problems.DataAnalysis.MultiVariate.Regression.Symbolic.Interfaces;
|
---|
[4056] | 30 | using HeuristicLab.Problems.DataAnalysis.Regression.Symbolic;
|
---|
| 31 | using HeuristicLab.Problems.DataAnalysis.Symbolic;
|
---|
[5275] | 32 | using HeuristicLab.Common;
|
---|
[4056] | 33 |
|
---|
| 34 | namespace HeuristicLab.Problems.DataAnalysis.MultiVariate.Regression.Symbolic.Evaluators {
|
---|
| 35 | [Item("SymbolicVectorRegressionScaledNormalizedMseEvaluator", "Represents an operator that calculates the sum of the normalized mean squared error over all components.")]
|
---|
| 36 | [StorableClass]
|
---|
[4194] | 37 | public class SymbolicVectorRegressionScaledNormalizedMseEvaluator : SingleObjectiveSymbolicVectorRegressionEvaluator {
|
---|
[4056] | 38 | private const string AlphaParameterName = "Alpha";
|
---|
| 39 | private const string BetaParameterName = "Beta";
|
---|
| 40 |
|
---|
| 41 | #region parameter properties
|
---|
| 42 | public ILookupParameter<DoubleArray> AlphaParameter {
|
---|
| 43 | get { return (ILookupParameter<DoubleArray>)Parameters[AlphaParameterName]; }
|
---|
| 44 | }
|
---|
| 45 | public ILookupParameter<DoubleArray> BetaParameter {
|
---|
| 46 | get { return (ILookupParameter<DoubleArray>)Parameters[BetaParameterName]; }
|
---|
| 47 | }
|
---|
| 48 |
|
---|
| 49 | #endregion
|
---|
| 50 |
|
---|
[5275] | 51 | [StorableConstructor]
|
---|
| 52 | protected SymbolicVectorRegressionScaledNormalizedMseEvaluator(bool deserializing) : base(deserializing) { }
|
---|
| 53 | protected SymbolicVectorRegressionScaledNormalizedMseEvaluator(SymbolicVectorRegressionScaledNormalizedMseEvaluator original, Cloner cloner)
|
---|
| 54 | : base(original, cloner) {
|
---|
| 55 | }
|
---|
[4056] | 56 | public SymbolicVectorRegressionScaledNormalizedMseEvaluator()
|
---|
| 57 | : base() {
|
---|
| 58 | Parameters.Add(new LookupParameter<DoubleArray>(AlphaParameterName, "The alpha parameter for linear scaling."));
|
---|
| 59 | Parameters.Add(new LookupParameter<DoubleArray>(BetaParameterName, "The beta parameter for linear scaling."));
|
---|
| 60 | }
|
---|
[5275] | 61 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
| 62 | return new SymbolicVectorRegressionScaledNormalizedMseEvaluator(this, cloner);
|
---|
| 63 | }
|
---|
[4194] | 64 | public override double Evaluate(SymbolicExpressionTree tree, ISymbolicExpressionTreeInterpreter interpreter, MultiVariateDataAnalysisProblemData problemData, IEnumerable<string> targetVariables, IEnumerable<int> rows, DoubleArray lowerEstimationBound, DoubleArray upperEstimationBound) {
|
---|
[4056] | 65 | List<string> targetVariablesList = targetVariables.ToList();
|
---|
| 66 | double nmseSum = 0.0;
|
---|
| 67 |
|
---|
| 68 | DoubleArray alpha = new DoubleArray(targetVariablesList.Count);
|
---|
| 69 | DoubleArray beta = new DoubleArray(targetVariablesList.Count);
|
---|
| 70 |
|
---|
| 71 | // use only the i-th vector component
|
---|
| 72 | List<SymbolicExpressionTreeNode> componentBranches = new List<SymbolicExpressionTreeNode>(tree.Root.SubTrees[0].SubTrees);
|
---|
[4068] | 73 | while (tree.Root.SubTrees[0].SubTrees.Count > 0) tree.Root.SubTrees[0].RemoveSubTree(0);
|
---|
[4056] | 74 | for (int i = 0; i < targetVariablesList.Count; i++) {
|
---|
| 75 | tree.Root.SubTrees[0].AddSubTree(componentBranches[i]);
|
---|
| 76 | double compAlpha;
|
---|
| 77 | double compBeta;
|
---|
| 78 | double nmse = SymbolicRegressionScaledNormalizedMeanSquaredErrorEvaluator.Calculate(interpreter, tree,
|
---|
| 79 | lowerEstimationBound[i], upperEstimationBound[i],
|
---|
[4087] | 80 | problemData.Dataset, targetVariablesList[i], rows, out compBeta, out compAlpha);
|
---|
[4056] | 81 | alpha[i] = compAlpha;
|
---|
| 82 | beta[i] = compBeta;
|
---|
| 83 | nmseSum += nmse;
|
---|
| 84 | tree.Root.SubTrees[0].RemoveSubTree(0);
|
---|
| 85 | }
|
---|
| 86 | // restore tree
|
---|
| 87 | foreach (var treeNode in componentBranches) {
|
---|
| 88 | tree.Root.SubTrees[0].AddSubTree(treeNode);
|
---|
| 89 | }
|
---|
| 90 | AlphaParameter.ActualValue = alpha;
|
---|
| 91 | BetaParameter.ActualValue = beta;
|
---|
[4194] | 92 | return nmseSum;
|
---|
[4056] | 93 | }
|
---|
| 94 | }
|
---|
| 95 | }
|
---|