Free cookie consent management tool by TermsFeed Policy Generator

source: trunk/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SingleObjective/Evaluators/SymbolicRegressionLogResidualEvaluator.cs

Last change on this file was 18220, checked in by gkronber, 2 years ago

#3136: reintegrated structure-template GP branch into trunk

File size: 5.7 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 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
22using System;
23using System.Collections.Generic;
24using System.Linq;
25using HeuristicLab.Common;
26using HeuristicLab.Core;
27using HeuristicLab.Data;
28using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
29using HEAL.Attic;
30
31namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Regression {
32  [Item("Log Residual Evaluator", "Evaluator for symbolic regression models that calculates the mean of logarithmic absolute residuals avg(log( 1 + abs(y' - y)))" +
33                                  "This evaluator does not perform linear scaling!" +
34                                  "This evaluator can be useful if the modeled function contains discontinuities (e.g. 1/x). " +
35                                  "For some data sets (e.g. Korns benchmark instances containing inverses of near zero values) the squared error or absolute " +
36                                  "error put too much emphasis on modeling the outlier values. Using log-residuals instead has the " +
37                                  "effect that smaller residuals have a stronger impact on the total quality compared to the large residuals." +
38                                  "This effects GP convergence because functional fragments which are necessary to explain small variations are also more likely" +
39                                  " to stay in the population. This is useful even when the actual objective function is mean of squared errors.")]
40  [StorableType("8CEA1A56-167D-481B-9167-C1DED8E06680")]
41  public class SymbolicRegressionLogResidualEvaluator : SymbolicRegressionSingleObjectiveEvaluator {
42    [StorableConstructor]
43    protected SymbolicRegressionLogResidualEvaluator(StorableConstructorFlag _) : base(_) { }
44    protected SymbolicRegressionLogResidualEvaluator(SymbolicRegressionLogResidualEvaluator original, Cloner cloner)
45      : base(original, cloner) {
46    }
47    public override IDeepCloneable Clone(Cloner cloner) {
48      return new SymbolicRegressionLogResidualEvaluator(this, cloner);
49    }
50
51    public SymbolicRegressionLogResidualEvaluator() : base() { }
52
53    public override bool Maximization { get { return false; } }
54
55    public override IOperation InstrumentedApply() {
56      var tree = SymbolicExpressionTreeParameter.ActualValue;
57      IEnumerable<int> rows = GenerateRowsToEvaluate();
58
59      double quality = Calculate(
60        tree, ProblemDataParameter.ActualValue,
61        rows, SymbolicDataAnalysisTreeInterpreterParameter.ActualValue,
62        EstimationLimitsParameter.ActualValue.Lower,
63        EstimationLimitsParameter.ActualValue.Upper);
64      QualityParameter.ActualValue = new DoubleValue(quality);
65
66      return base.InstrumentedApply();
67    }
68
69    public static double Calculate(
70      ISymbolicExpressionTree tree,
71      IRegressionProblemData problemData,
72      IEnumerable<int> rows,
73      ISymbolicDataAnalysisExpressionTreeInterpreter interpreter,
74      double lowerEstimationLimit,
75      double upperEstimationLimit) {
76      IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(tree, problemData.Dataset, rows);
77      IEnumerable<double> targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
78      IEnumerable<double> boundedEstimatedValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
79
80      var logRes = boundedEstimatedValues.Zip(targetValues, (e, t) => Math.Log(1.0 + Math.Abs(e - t)));
81
82      OnlineCalculatorError errorState;
83      OnlineCalculatorError varErrorState;
84      double mlr;
85      double variance;
86      OnlineMeanAndVarianceCalculator.Calculate(logRes, out mlr, out variance, out errorState, out varErrorState);
87      if (errorState != OnlineCalculatorError.None) return double.NaN;
88      return mlr;
89    }
90
91    public override double Evaluate(IExecutionContext context, ISymbolicExpressionTree tree, IRegressionProblemData problemData, IEnumerable<int> rows) {
92      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = context;
93      EstimationLimitsParameter.ExecutionContext = context;
94
95      double mlr = Calculate(
96        tree, problemData, rows,
97        SymbolicDataAnalysisTreeInterpreterParameter.ActualValue,
98        EstimationLimitsParameter.ActualValue.Lower,
99        EstimationLimitsParameter.ActualValue.Upper);
100
101      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = null;
102      EstimationLimitsParameter.ExecutionContext = null;
103
104      return mlr;
105    }
106
107    public override double Evaluate(
108      ISymbolicExpressionTree tree,
109      IRegressionProblemData problemData,
110      IEnumerable<int> rows,
111      ISymbolicDataAnalysisExpressionTreeInterpreter interpreter,
112      bool applyLinearScaling = true,
113      double lowerEstimationLimit = double.MinValue,
114      double upperEstimationLimit = double.MaxValue) {
115      return Calculate(tree, problemData, rows, interpreter, lowerEstimationLimit, upperEstimationLimit);
116    }
117  }
118}
Note: See TracBrowser for help on using the repository browser.