source: branches/2971_named_intervals/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SingleObjective/Evaluators/SymbolicRegressionSingleObjectiveConstraintPearsonRSquaredEvaluator.cs @ 16851

Last change on this file since 16851 was 16851, checked in by chaider, 3 years ago

#2791 Refactored Constraint Evaluator and Analyzer

File size: 5.4 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2018 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 HEAL.Attic;
26using HeuristicLab.Common;
27using HeuristicLab.Core;
28using HeuristicLab.Data;
29using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
30
31namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Regression {
32  [Item("Pearson R² Constraint Evaluator", "Calculates the square of the pearson correlation coefficient (also known as coefficient of determination) of a symbolic regression solution.")]
33  [StorableType("D61462E4-2032-4790-B63D-5E6512987F64")]
34  public class SymbolicRegressionSingleObjectiveConstraintPearsonRSquaredEvaluator : SymbolicRegressionSingleObjectiveEvaluator {
35    [StorableConstructor]
36    protected SymbolicRegressionSingleObjectiveConstraintPearsonRSquaredEvaluator(StorableConstructorFlag _) : base(_) { }
37    protected SymbolicRegressionSingleObjectiveConstraintPearsonRSquaredEvaluator(SymbolicRegressionSingleObjectiveConstraintPearsonRSquaredEvaluator original, Cloner cloner)
38      : base(original, cloner) {
39    }
40    public override IDeepCloneable Clone(Cloner cloner) {
41      return new SymbolicRegressionSingleObjectiveConstraintPearsonRSquaredEvaluator(this, cloner);
42    }
43
44    public SymbolicRegressionSingleObjectiveConstraintPearsonRSquaredEvaluator() : base() { }
45
46    public override bool Maximization { get { return true; } }
47
48    public override IOperation InstrumentedApply() {
49      var solution = SymbolicExpressionTreeParameter.ActualValue;
50      IEnumerable<int> rows = GenerateRowsToEvaluate();
51
52      double quality = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows, ApplyLinearScalingParameter.ActualValue.Value);
53      QualityParameter.ActualValue = new DoubleValue(quality);
54      return base.InstrumentedApply();
55    }
56
57    public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IRegressionProblemData problemData, IEnumerable<int> rows, bool applyLinearScaling) {
58      IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
59      IEnumerable<double> targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
60      OnlineCalculatorError errorState = OnlineCalculatorError.None;
61
62      var constraints = problemData.IntervalConstraints.Constraints.Where(x => x.Enabled);
63      var variableRanges = problemData.VariableRanges.VariableIntervals;
64      var tree = solution;
65
66      double r;
67      if (applyLinearScaling) {
68        var rCalculator = new OnlinePearsonsRCalculator();
69        CalculateWithScaling(targetValues, estimatedValues, lowerEstimationLimit, upperEstimationLimit, rCalculator, problemData.Dataset.Rows);
70        var model = new SymbolicRegressionModel(problemData.TargetVariable, solution, interpreter, lowerEstimationLimit, upperEstimationLimit);
71        model.Scale(problemData);
72        tree = model.SymbolicExpressionTree;
73        errorState = rCalculator.ErrorState;
74        r = rCalculator.R;
75      } else {
76        IEnumerable<double> boundedEstimatedValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
77        r = OnlinePearsonsRCalculator.Calculate(targetValues, boundedEstimatedValues, out errorState);
78      }
79
80      if (!SymbolicRegressionConstraintAnalyzer.ConstraintsSatisfied(constraints, variableRanges, tree)) {
81        return 0;
82      }
83
84      if (errorState != OnlineCalculatorError.None) return double.NaN;
85      return r * r;
86    }
87
88
89    public override double Evaluate(IExecutionContext context, ISymbolicExpressionTree tree,
90      IRegressionProblemData problemData, IEnumerable<int> rows) {
91      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = context;
92      EstimationLimitsParameter.ExecutionContext = context;
93      ApplyLinearScalingParameter.ExecutionContext = context;
94
95      double r2 = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, tree,
96        EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, problemData, rows,
97        ApplyLinearScalingParameter.ActualValue.Value);
98
99      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = null;
100      EstimationLimitsParameter.ExecutionContext = null;
101      ApplyLinearScalingParameter.ExecutionContext = null;
102
103      return r2;
104    }
105  }
106}
Note: See TracBrowser for help on using the repository browser.