Free cookie consent management tool by TermsFeed Policy Generator

source: branches/VNS/HeuristicLab.Problems.DataAnalysis.Regression/3.3/Symbolic/Analyzers/SymbolicRegressionModelQualityAnalyzer.cs @ 5594

Last change on this file since 5594 was 5445, checked in by swagner, 14 years ago

Updated year of copyrights (#1406)
File size: 15.8 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2011 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.Analysis;
26using HeuristicLab.Common;
27using HeuristicLab.Core;
28using HeuristicLab.Data;
29using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
30using HeuristicLab.Operators;
31using HeuristicLab.Optimization;
32using HeuristicLab.Parameters;
33using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
34using HeuristicLab.Problems.DataAnalysis.Evaluators;
35using HeuristicLab.Problems.DataAnalysis.Symbolic;
36
37namespace HeuristicLab.Problems.DataAnalysis.Regression.Symbolic.Analyzers {
38  /// <summary>
39  /// "An operator for analyzing the quality of symbolic regression solutions symbolic expression tree encoding."
40  /// </summary>
41  [Item("SymbolicRegressionModelQualityAnalyzer", "An operator for analyzing the quality of symbolic regression solutions symbolic expression tree encoding.")]
42  [StorableClass]
43  public sealed class SymbolicRegressionModelQualityAnalyzer : SingleSuccessorOperator, ISymbolicRegressionAnalyzer {
44    private const string SymbolicExpressionTreeInterpreterParameterName = "SymbolicExpressionTreeInterpreter";
45    private const string SymbolicExpressionTreeParameterName = "SymbolicExpressionTree";
46    private const string ProblemDataParameterName = "ProblemData";
47    private const string ResultsParameterName = "Results";
48
49    private const string TrainingMeanSquaredErrorQualityParameterName = "Mean squared error (training)";
50    private const string MinTrainingMeanSquaredErrorQualityParameterName = "Min mean squared error (training)";
51    private const string MaxTrainingMeanSquaredErrorQualityParameterName = "Max mean squared error (training)";
52    private const string AverageTrainingMeanSquaredErrorQualityParameterName = "Average mean squared error (training)";
53    private const string BestTrainingMeanSquaredErrorQualityParameterName = "Best mean squared error (training)";
54
55    private const string TrainingAverageRelativeErrorQualityParameterName = "Average relative error (training)";
56    private const string MinTrainingAverageRelativeErrorQualityParameterName = "Min average relative error (training)";
57    private const string MaxTrainingAverageRelativeErrorQualityParameterName = "Max average relative error (training)";
58    private const string AverageTrainingAverageRelativeErrorQualityParameterName = "Average average relative error (training)";
59    private const string BestTrainingAverageRelativeErrorQualityParameterName = "Best average relative error (training)";
60
61    private const string TrainingRSquaredQualityParameterName = "R² (training)";
62    private const string MinTrainingRSquaredQualityParameterName = "Min R² (training)";
63    private const string MaxTrainingRSquaredQualityParameterName = "Max R² (training)";
64    private const string AverageTrainingRSquaredQualityParameterName = "Average R² (training)";
65    private const string BestTrainingRSquaredQualityParameterName = "Best R² (training)";
66
67    private const string TestMeanSquaredErrorQualityParameterName = "Mean squared error (test)";
68    private const string MinTestMeanSquaredErrorQualityParameterName = "Min mean squared error (test)";
69    private const string MaxTestMeanSquaredErrorQualityParameterName = "Max mean squared error (test)";
70    private const string AverageTestMeanSquaredErrorQualityParameterName = "Average mean squared error (test)";
71    private const string BestTestMeanSquaredErrorQualityParameterName = "Best mean squared error (test)";
72
73    private const string TestAverageRelativeErrorQualityParameterName = "Average relative error (test)";
74    private const string MinTestAverageRelativeErrorQualityParameterName = "Min average relative error (test)";
75    private const string MaxTestAverageRelativeErrorQualityParameterName = "Max average relative error (test)";
76    private const string AverageTestAverageRelativeErrorQualityParameterName = "Average average relative error (test)";
77    private const string BestTestAverageRelativeErrorQualityParameterName = "Best average relative error (test)";
78
79    private const string TestRSquaredQualityParameterName = "R² (test)";
80    private const string MinTestRSquaredQualityParameterName = "Min R² (test)";
81    private const string MaxTestRSquaredQualityParameterName = "Max R² (test)";
82    private const string AverageTestRSquaredQualityParameterName = "Average R² (test)";
83    private const string BestTestRSquaredQualityParameterName = "Best R² (test)";
84
85    private const string RSquaredValuesParameterName = "R²";
86    private const string MeanSquaredErrorValuesParameterName = "Mean squared error";
87    private const string RelativeErrorValuesParameterName = "Average relative error";
88
89    private const string UpperEstimationLimitParameterName = "UpperEstimationLimit";
90    private const string LowerEstimationLimitParameterName = "LowerEstimationLimit";
91
92    #region parameter properties
93    public ScopeTreeLookupParameter<SymbolicExpressionTree> SymbolicExpressionTreeParameter {
94      get { return (ScopeTreeLookupParameter<SymbolicExpressionTree>)Parameters[SymbolicExpressionTreeParameterName]; }
95    }
96    public IValueLookupParameter<ISymbolicExpressionTreeInterpreter> SymbolicExpressionTreeInterpreterParameter {
97      get { return (IValueLookupParameter<ISymbolicExpressionTreeInterpreter>)Parameters[SymbolicExpressionTreeInterpreterParameterName]; }
98    }
99    public IValueLookupParameter<DataAnalysisProblemData> ProblemDataParameter {
100      get { return (IValueLookupParameter<DataAnalysisProblemData>)Parameters[ProblemDataParameterName]; }
101    }
102    public IValueLookupParameter<DoubleValue> UpperEstimationLimitParameter {
103      get { return (IValueLookupParameter<DoubleValue>)Parameters[UpperEstimationLimitParameterName]; }
104    }
105    public IValueLookupParameter<DoubleValue> LowerEstimationLimitParameter {
106      get { return (IValueLookupParameter<DoubleValue>)Parameters[LowerEstimationLimitParameterName]; }
107    }
108    public ILookupParameter<ResultCollection> ResultsParameter {
109      get { return (ILookupParameter<ResultCollection>)Parameters[ResultsParameterName]; }
110    }
111    #endregion
112    #region properties
113    public DoubleValue UpperEstimationLimit {
114      get { return UpperEstimationLimitParameter.ActualValue; }
115    }
116    public DoubleValue LowerEstimationLimit {
117      get { return LowerEstimationLimitParameter.ActualValue; }
118    }
119    #endregion
120
121    [StorableConstructor]
122    private SymbolicRegressionModelQualityAnalyzer(bool deserializing) : base(deserializing) { }
123    private SymbolicRegressionModelQualityAnalyzer(SymbolicRegressionModelQualityAnalyzer original, Cloner cloner) : base(original, cloner) { }
124    public SymbolicRegressionModelQualityAnalyzer()
125      : base() {
126      Parameters.Add(new ScopeTreeLookupParameter<SymbolicExpressionTree>(SymbolicExpressionTreeParameterName, "The symbolic expression trees to analyze."));
127      Parameters.Add(new ValueLookupParameter<ISymbolicExpressionTreeInterpreter>(SymbolicExpressionTreeInterpreterParameterName, "The interpreter that should be used to calculate the output values of the symbolic expression tree."));
128      Parameters.Add(new ValueLookupParameter<DataAnalysisProblemData>(ProblemDataParameterName, "The problem data containing the input varaibles for the symbolic regression problem."));
129      Parameters.Add(new ValueLookupParameter<DoubleValue>(UpperEstimationLimitParameterName, "The upper limit that should be used as cut off value for the output values of symbolic expression trees."));
130      Parameters.Add(new ValueLookupParameter<DoubleValue>(LowerEstimationLimitParameterName, "The lower limit that should be used as cut off value for the output values of symbolic expression trees."));
131      Parameters.Add(new ValueLookupParameter<DataTable>(MeanSquaredErrorValuesParameterName, "The data table to collect mean squared error values."));
132      Parameters.Add(new ValueLookupParameter<DataTable>(RSquaredValuesParameterName, "The data table to collect R² correlation coefficient values."));
133      Parameters.Add(new ValueLookupParameter<DataTable>(RelativeErrorValuesParameterName, "The data table to collect relative error values."));
134      Parameters.Add(new LookupParameter<ResultCollection>(ResultsParameterName, "The result collection where the best symbolic regression solution should be stored."));
135    }
136
137    public override IDeepCloneable Clone(Cloner cloner) {
138      return new SymbolicRegressionModelQualityAnalyzer(this, cloner);
139    }
140
141    public override IOperation Apply() {
142      double upperEstimationLimit = UpperEstimationLimit != null ? UpperEstimationLimit.Value : double.PositiveInfinity;
143      double lowerEstimationLimit = LowerEstimationLimit != null ? LowerEstimationLimit.Value : double.NegativeInfinity;
144      Analyze(SymbolicExpressionTreeParameter.ActualValue, SymbolicExpressionTreeInterpreterParameter.ActualValue,
145        upperEstimationLimit, lowerEstimationLimit, ProblemDataParameter.ActualValue,
146        ResultsParameter.ActualValue);
147      return base.Apply();
148    }
149
150    public static void Analyze(IEnumerable<SymbolicExpressionTree> trees, ISymbolicExpressionTreeInterpreter interpreter,
151      double upperEstimationLimit, double lowerEstimationLimit,
152      DataAnalysisProblemData problemData, ResultCollection results) {
153      int targetVariableIndex = problemData.Dataset.GetVariableIndex(problemData.TargetVariable.Value);
154      IEnumerable<double> originalTrainingValues = problemData.Dataset.GetEnumeratedVariableValues(targetVariableIndex, problemData.TrainingIndizes);
155      IEnumerable<double> originalTestValues = problemData.Dataset.GetEnumeratedVariableValues(targetVariableIndex, problemData.TestIndizes);
156      List<double> trainingMse = new List<double>();
157      List<double> trainingR2 = new List<double>();
158      List<double> trainingRelErr = new List<double>();
159      List<double> testMse = new List<double>();
160      List<double> testR2 = new List<double>();
161      List<double> testRelErr = new List<double>();
162
163      OnlineMeanSquaredErrorEvaluator mseEvaluator = new OnlineMeanSquaredErrorEvaluator();
164      OnlineMeanAbsolutePercentageErrorEvaluator relErrEvaluator = new OnlineMeanAbsolutePercentageErrorEvaluator();
165      OnlinePearsonsRSquaredEvaluator r2Evaluator = new OnlinePearsonsRSquaredEvaluator();
166
167      foreach (var tree in trees) {
168        #region training
169        var estimatedTrainingValues = interpreter.GetSymbolicExpressionTreeValues(tree, problemData.Dataset, problemData.TrainingIndizes);
170        mseEvaluator.Reset();
171        r2Evaluator.Reset();
172        relErrEvaluator.Reset();
173        var estimatedEnumerator = estimatedTrainingValues.GetEnumerator();
174        var originalEnumerator = originalTrainingValues.GetEnumerator();
175        while (estimatedEnumerator.MoveNext() & originalEnumerator.MoveNext()) {
176          double estimated = estimatedEnumerator.Current;
177          if (double.IsNaN(estimated)) estimated = upperEstimationLimit;
178          else estimated = Math.Min(upperEstimationLimit, Math.Max(lowerEstimationLimit, estimated));
179          mseEvaluator.Add(originalEnumerator.Current, estimated);
180          r2Evaluator.Add(originalEnumerator.Current, estimated);
181          relErrEvaluator.Add(originalEnumerator.Current, estimated);
182        }
183        if (estimatedEnumerator.MoveNext() || originalEnumerator.MoveNext()) {
184          throw new InvalidOperationException("Number of elements in estimated and original enumeration doesn't match.");
185        }
186        trainingMse.Add(mseEvaluator.MeanSquaredError);
187        trainingR2.Add(r2Evaluator.RSquared);
188        trainingRelErr.Add(relErrEvaluator.MeanAbsolutePercentageError);
189        #endregion
190        #region test
191        var estimatedTestValues = interpreter.GetSymbolicExpressionTreeValues(tree, problemData.Dataset, problemData.TestIndizes);
192
193        mseEvaluator.Reset();
194        r2Evaluator.Reset();
195        relErrEvaluator.Reset();
196        estimatedEnumerator = estimatedTestValues.GetEnumerator();
197        originalEnumerator = originalTestValues.GetEnumerator();
198        while (estimatedEnumerator.MoveNext() & originalEnumerator.MoveNext()) {
199          double estimated = estimatedEnumerator.Current;
200          if (double.IsNaN(estimated)) estimated = upperEstimationLimit;
201          else estimated = Math.Min(upperEstimationLimit, Math.Max(lowerEstimationLimit, estimated));
202          mseEvaluator.Add(originalEnumerator.Current, estimated);
203          r2Evaluator.Add(originalEnumerator.Current, estimated);
204          relErrEvaluator.Add(originalEnumerator.Current, estimated);
205        }
206        if (estimatedEnumerator.MoveNext() || originalEnumerator.MoveNext()) {
207          throw new InvalidOperationException("Number of elements in estimated and original enumeration doesn't match.");
208        }
209        testMse.Add(mseEvaluator.MeanSquaredError);
210        testR2.Add(r2Evaluator.RSquared);
211        testRelErr.Add(relErrEvaluator.MeanAbsolutePercentageError);
212        #endregion
213      }
214
215      AddResultTableValues(results, MeanSquaredErrorValuesParameterName, "mean squared error (training)", trainingMse.Min(), trainingMse.Average(), trainingMse.Max());
216      AddResultTableValues(results, MeanSquaredErrorValuesParameterName, "mean squared error (test)", testMse.Min(), testMse.Average(), testMse.Max());
217      AddResultTableValues(results, RelativeErrorValuesParameterName, "mean relative error (training)", trainingRelErr.Min(), trainingRelErr.Average(), trainingRelErr.Max());
218      AddResultTableValues(results, RelativeErrorValuesParameterName, "mean relative error (test)", testRelErr.Min(), testRelErr.Average(), testRelErr.Max());
219      AddResultTableValues(results, RSquaredValuesParameterName, "Pearson's R² (training)", trainingR2.Min(), trainingR2.Average(), trainingR2.Max());
220      AddResultTableValues(results, RSquaredValuesParameterName, "Pearson's R² (test)", testR2.Min(), testR2.Average(), testR2.Max());
221    }
222
223    private static void AddResultTableValues(ResultCollection results, string tableName, string valueName, double minValue, double avgValue, double maxValue) {
224      if (!results.ContainsKey(tableName)) {
225        results.Add(new Result(tableName, new DataTable(tableName)));
226      }
227      DataTable table = (DataTable)results[tableName].Value;
228      AddValue(table, minValue, "Min. " + valueName, string.Empty);
229      AddValue(table, avgValue, "Avg. " + valueName, string.Empty);
230      AddValue(table, maxValue, "Max. " + valueName, string.Empty);
231    }
232
233    private static void AddValue(DataTable table, double data, string name, string description) {
234      DataRow row;
235      table.Rows.TryGetValue(name, out row);
236      if (row == null) {
237        row = new DataRow(name, description);
238        row.Values.Add(data);
239        table.Rows.Add(row);
240      } else {
241        row.Values.Add(data);
242      }
243    }
244
245
246    private static void SetResultValue(ResultCollection results, string name, double value) {
247      if (results.ContainsKey(name))
248        results[name].Value = new DoubleValue(value);
249      else
250        results.Add(new Result(name, new DoubleValue(value)));
251    }
252  }
253}
Note: See TracBrowser for help on using the repository browser.