source: branches/3136_Structural_GP/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SingleObjective/Evaluators/SymbolicRegressionSingleObjectiveMeanSquaredErrorEvaluator.cs @ 18095

Last change on this file since 18095 was 18095, checked in by dpiringe, 6 months ago

#3136

  • added a Evaluate method, which uses the static method Calculate and evaluates a ISymbolicExpressionTree without the need of an ExecutionContext
    • implemented this new method in all single objective SymReg evaluators
File size: 5.2 KB
RevLine 
[5500]1#region License Information
2/* HeuristicLab
[17180]3 * Copyright (C) Heuristic and Evolutionary Algorithms Laboratory (HEAL)
[5500]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.Collections.Generic;
23using HeuristicLab.Common;
24using HeuristicLab.Core;
25using HeuristicLab.Data;
26using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
[16565]27using HEAL.Attic;
[5500]28
29namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Regression {
[5618]30  [Item("Mean squared error Evaluator", "Calculates the mean squared error of a symbolic regression solution.")]
[16565]31  [StorableType("8D4B5243-1635-46A6-AEF9-18C9BCB725DD")]
[5500]32  public class SymbolicRegressionSingleObjectiveMeanSquaredErrorEvaluator : SymbolicRegressionSingleObjectiveEvaluator {
[7672]33    public override bool Maximization { get { return false; } }
[5500]34    [StorableConstructor]
[16565]35    protected SymbolicRegressionSingleObjectiveMeanSquaredErrorEvaluator(StorableConstructorFlag _) : base(_) { }
[5500]36    protected SymbolicRegressionSingleObjectiveMeanSquaredErrorEvaluator(SymbolicRegressionSingleObjectiveMeanSquaredErrorEvaluator original, Cloner cloner)
37      : base(original, cloner) {
38    }
39    public override IDeepCloneable Clone(Cloner cloner) {
40      return new SymbolicRegressionSingleObjectiveMeanSquaredErrorEvaluator(this, cloner);
41    }
[5505]42    public SymbolicRegressionSingleObjectiveMeanSquaredErrorEvaluator() : base() { }
43
[10291]44    public override IOperation InstrumentedApply() {
[5851]45      var solution = SymbolicExpressionTreeParameter.ActualValue;
[5500]46      IEnumerable<int> rows = GenerateRowsToEvaluate();
[5851]47
[12977]48      double quality = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows, ApplyLinearScalingParameter.ActualValue.Value);
[5851]49      QualityParameter.ActualValue = new DoubleValue(quality);
50
[10291]51      return base.InstrumentedApply();
[5500]52    }
53
[7672]54    public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IRegressionProblemData problemData, IEnumerable<int> rows, bool applyLinearScaling) {
[5500]55      IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
[7677]56      IEnumerable<double> targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
[5942]57      OnlineCalculatorError errorState;
[7672]58
59      double mse;
60      if (applyLinearScaling) {
[7677]61        var mseCalculator = new OnlineMeanSquaredErrorCalculator();
[8113]62        CalculateWithScaling(targetValues, estimatedValues, lowerEstimationLimit, upperEstimationLimit, mseCalculator, problemData.Dataset.Rows);
[7677]63        errorState = mseCalculator.ErrorState;
64        mse = mseCalculator.MeanSquaredError;
[8113]65      } else {
66        IEnumerable<double> boundedEstimatedValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
[7677]67        mse = OnlineMeanSquaredErrorCalculator.Calculate(targetValues, boundedEstimatedValues, out errorState);
[8113]68      }
[8664]69      if (errorState != OnlineCalculatorError.None) return double.NaN;
70      return mse;
[5500]71    }
[5607]72
[5613]73    public override double Evaluate(IExecutionContext context, ISymbolicExpressionTree tree, IRegressionProblemData problemData, IEnumerable<int> rows) {
[5722]74      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = context;
[5770]75      EstimationLimitsParameter.ExecutionContext = context;
[8664]76      ApplyLinearScalingParameter.ExecutionContext = context;
[5722]77
[8664]78      double mse = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, tree, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, problemData, rows, ApplyLinearScalingParameter.ActualValue.Value);
[5722]79
80      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = null;
[5770]81      EstimationLimitsParameter.ExecutionContext = null;
[8664]82      ApplyLinearScalingParameter.ExecutionContext = null;
[5722]83
84      return mse;
[5607]85    }
[18095]86
87    public override double Evaluate(IRegressionProblemData problemData,
88      ISymbolicExpressionTree solution,
89      ISymbolicDataAnalysisExpressionTreeInterpreter interpreter,
90      IEnumerable<int> rows = null,
91      bool applyLinearScaling = true,
92      double lowerEstimationLimit = double.MinValue,
93      double upperEstimationLimit = double.MaxValue) {
94      return Calculate(interpreter, solution, lowerEstimationLimit, upperEstimationLimit, problemData, rows ?? problemData.TrainingIndices, applyLinearScaling);
95    }
[5500]96  }
97}
Note: See TracBrowser for help on using the repository browser.