[14528] | 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 |
|
---|
| 22 | using System;
|
---|
| 23 | using System.Collections.Generic;
|
---|
| 24 | using System.Linq;
|
---|
| 25 | using HeuristicLab.Common;
|
---|
| 26 | using HeuristicLab.Core;
|
---|
| 27 | using HeuristicLab.Data;
|
---|
| 28 | using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
|
---|
[14927] | 29 | using HeuristicLab.Persistence;
|
---|
[14528] | 30 |
|
---|
| 31 | namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Regression {
|
---|
| 32 | [Item("Variance Model Evaluator", "Can be used for modeling variance of a variable. Assumes that the variable values are sampled from a zero mean Gaussian. Use a model for the target variable to calculate the residuals. In a second step use the residuals as the target variable and use this evaluator to create the model for the conditional variance.")]
|
---|
[14927] | 33 | [StorableType("4a70f22b-b92c-4783-b119-fd50b29f2f38")]
|
---|
[14528] | 34 | public class SymbolicRegressionVarianceModelEvaluator : SymbolicRegressionSingleObjectiveEvaluator {
|
---|
| 35 | [StorableConstructor]
|
---|
[15018] | 36 | protected SymbolicRegressionVarianceModelEvaluator(StorableConstructorFlag deserializing) : base(deserializing) { }
|
---|
[14528] | 37 | protected SymbolicRegressionVarianceModelEvaluator(SymbolicRegressionVarianceModelEvaluator original, Cloner cloner)
|
---|
| 38 | : base(original, cloner) {
|
---|
| 39 | }
|
---|
| 40 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
| 41 | return new SymbolicRegressionVarianceModelEvaluator(this, cloner);
|
---|
| 42 | }
|
---|
| 43 |
|
---|
| 44 | public SymbolicRegressionVarianceModelEvaluator() : 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);
|
---|
| 53 | QualityParameter.ActualValue = new DoubleValue(quality);
|
---|
| 54 |
|
---|
| 55 | return base.InstrumentedApply();
|
---|
| 56 | }
|
---|
| 57 |
|
---|
| 58 | public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IRegressionProblemData problemData, IEnumerable<int> rows) {
|
---|
| 59 | IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
|
---|
| 60 | IEnumerable<double> targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
|
---|
| 61 | IEnumerable<double> boundedEstimatedValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
|
---|
| 62 |
|
---|
| 63 | // assumes residuals follow a zero-mean Gaussian distribution where the variance is a function of the inputs
|
---|
| 64 |
|
---|
| 65 | // boundedEstimatedValues is the estimator for std.dev.
|
---|
| 66 | // log likelihood for N(target_i | 0, boundesEstimatedValues)
|
---|
| 67 | var l2pi = Math.Log(2.0 * Math.PI);
|
---|
| 68 | var ll = -0.5 *
|
---|
| 69 | boundedEstimatedValues.Zip(targetValues, (s, t) =>
|
---|
| 70 | +l2pi
|
---|
| 71 | + Math.Log(s * s)
|
---|
| 72 | + (t * t) / (s * s)
|
---|
| 73 | ).Sum();
|
---|
| 74 |
|
---|
| 75 | return ll;
|
---|
| 76 | }
|
---|
| 77 |
|
---|
| 78 | public override double Evaluate(IExecutionContext context, ISymbolicExpressionTree tree, IRegressionProblemData problemData, IEnumerable<int> rows) {
|
---|
| 79 | SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = context;
|
---|
| 80 | EstimationLimitsParameter.ExecutionContext = context;
|
---|
| 81 |
|
---|
| 82 | double ll = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, tree, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, problemData, rows);
|
---|
| 83 |
|
---|
| 84 | SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = null;
|
---|
| 85 | EstimationLimitsParameter.ExecutionContext = null;
|
---|
| 86 |
|
---|
| 87 | return ll;
|
---|
| 88 | }
|
---|
| 89 | }
|
---|
| 90 | }
|
---|