source: branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/MultiObjective/PearsonRSquaredNumberOfVariablesEvaluator.cs @ 14238

Last change on this file since 14238 was 14238, checked in by gkronber, 3 years ago

#2650:

  • added weight for FactorVariable (necessary for LR)
  • introduced VariableBase and VariableTreeNodeBase and IVariableSymbol
  • support for factors in LR
  • extended variable impacts in solution view
  • fixed ERC view for regression
  • support for FactorVariable in simplifier
  • improved support for FactorVariable in constants optimizer
  • multiple related changes and small fixes
File size: 5.0 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2016 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 HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
30
31namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Regression {
32  [Item("Pearson R² & Number of Variables Evaluator", "Calculates the Pearson R² and the number of used variables of a symbolic regression solution.")]
33  [StorableClass]
34  public class PearsonRSquaredNumberOfVariablesEvaluator : SymbolicRegressionMultiObjectiveEvaluator {
35    [StorableConstructor]
36    protected PearsonRSquaredNumberOfVariablesEvaluator(bool deserializing) : base(deserializing) { }
37    protected PearsonRSquaredNumberOfVariablesEvaluator(PearsonRSquaredNumberOfVariablesEvaluator original, Cloner cloner)
38      : base(original, cloner) {
39    }
40    public override IDeepCloneable Clone(Cloner cloner) {
41      return new PearsonRSquaredNumberOfVariablesEvaluator(this, cloner);
42    }
43
44    public PearsonRSquaredNumberOfVariablesEvaluator() : base() { }
45
46    public override IEnumerable<bool> Maximization { get { return new bool[2] { true, false }; } } // maximize R² and minimize the number of variables
47
48    public override IOperation InstrumentedApply() {
49      IEnumerable<int> rows = GenerateRowsToEvaluate();
50      var solution = SymbolicExpressionTreeParameter.ActualValue;
51      var problemData = ProblemDataParameter.ActualValue;
52      var interpreter = SymbolicDataAnalysisTreeInterpreterParameter.ActualValue;
53      var estimationLimits = EstimationLimitsParameter.ActualValue;
54      var applyLinearScaling = ApplyLinearScalingParameter.ActualValue.Value;
55
56      if (UseConstantOptimization) {
57        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, ConstantOptimizationIterations, updateVariableWeights: ConstantOptimizationUpdateVariableWeights, lowerEstimationLimit: estimationLimits.Lower, upperEstimationLimit: estimationLimits.Upper);
58      }
59      double[] qualities = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows, ApplyLinearScalingParameter.ActualValue.Value, DecimalPlaces);
60      QualitiesParameter.ActualValue = new DoubleArray(qualities);
61      return base.InstrumentedApply();
62    }
63
64    public static double[] Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IRegressionProblemData problemData, IEnumerable<int> rows, bool applyLinearScaling, int decimalPlaces) {
65      double r2 = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, solution, lowerEstimationLimit, upperEstimationLimit, problemData, rows, applyLinearScaling);
66      if (decimalPlaces >= 0)
67        r2 = Math.Round(r2, decimalPlaces);
68      return new double[2] { r2, solution.IterateNodesPostfix().OfType<IVariableTreeNode>().Count() }; // count the number of variables
69    }
70
71    public override double[] Evaluate(IExecutionContext context, ISymbolicExpressionTree tree, IRegressionProblemData problemData, IEnumerable<int> rows) {
72      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = context;
73      EstimationLimitsParameter.ExecutionContext = context;
74      ApplyLinearScalingParameter.ExecutionContext = context;
75      // DecimalPlaces parameter is a FixedValueParameter and doesn't need the context.
76
77      double[] quality = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, tree, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, problemData, rows, ApplyLinearScalingParameter.ActualValue.Value, DecimalPlaces);
78
79      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = null;
80      EstimationLimitsParameter.ExecutionContext = null;
81      ApplyLinearScalingParameter.ExecutionContext = null;
82
83      return quality;
84    }
85  }
86}
Note: See TracBrowser for help on using the repository browser.