[14241] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
[16565] | 3 | * Copyright (C) 2002-2019 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
[14241] | 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;
|
---|
[14251] | 23 | using System.Collections;
|
---|
[14241] | 24 | using System.Collections.Generic;
|
---|
| 25 | using System.Linq;
|
---|
| 26 | using HeuristicLab.Algorithms.DataAnalysis;
|
---|
| 27 | using HeuristicLab.MainForm;
|
---|
| 28 | using HeuristicLab.Problems.DataAnalysis.Views.Classification;
|
---|
| 29 |
|
---|
| 30 | namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Classification.Views {
|
---|
| 31 | [View("Solution Comparison")]
|
---|
| 32 | [Content(typeof(ISymbolicClassificationSolution))]
|
---|
| 33 | public partial class SolutionComparisonView : ClassificationSolutionComparisonView {
|
---|
| 34 |
|
---|
| 35 | public SolutionComparisonView() {
|
---|
| 36 | InitializeComponent();
|
---|
| 37 | }
|
---|
| 38 |
|
---|
| 39 | public new ISymbolicClassificationSolution Content {
|
---|
| 40 | get { return (ISymbolicClassificationSolution)base.Content; }
|
---|
| 41 | set { base.Content = value; }
|
---|
| 42 | }
|
---|
| 43 |
|
---|
| 44 | protected override IEnumerable<IClassificationSolution> GenerateClassificationSolutions() {
|
---|
| 45 | var solutionsBase = base.GenerateClassificationSolutions();
|
---|
| 46 | var solutions = new List<IClassificationSolution>();
|
---|
| 47 |
|
---|
| 48 | var symbolicSolution = Content;
|
---|
| 49 |
|
---|
| 50 | // does not support lagged variables
|
---|
| 51 | if (symbolicSolution.Model.SymbolicExpressionTree.IterateNodesPrefix().OfType<LaggedVariableTreeNode>().Any()) return solutionsBase;
|
---|
| 52 |
|
---|
| 53 | var problemData = (IClassificationProblemData)symbolicSolution.ProblemData.Clone();
|
---|
| 54 | if (!problemData.TrainingIndices.Any()) return null; // don't create an comparison models if the problem does not have a training set (e.g. loaded into an existing model)
|
---|
| 55 |
|
---|
[14251] | 56 | var usedVariables = Content.Model.SymbolicExpressionTree.IterateNodesPostfix()
|
---|
| 57 | .OfType<IVariableTreeNode>()
|
---|
| 58 | .Select(node => node.VariableName).ToArray();
|
---|
| 59 |
|
---|
| 60 | var usedDoubleVariables = usedVariables
|
---|
| 61 | .Where(name => problemData.Dataset.VariableHasType<double>(name))
|
---|
[14241] | 62 | .Distinct();
|
---|
| 63 |
|
---|
[14251] | 64 | var usedFactorVariables = usedVariables
|
---|
| 65 | .Where(name => problemData.Dataset.VariableHasType<string>(name))
|
---|
[14241] | 66 | .Distinct();
|
---|
| 67 |
|
---|
[14251] | 68 | // gkronber: for binary factors we actually produce a binary variable in the new dataset
|
---|
| 69 | // but only if the variable is not used as a full factor anyway (LR creates binary columns anyway)
|
---|
| 70 | var usedBinaryFactors =
|
---|
| 71 | Content.Model.SymbolicExpressionTree.IterateNodesPostfix().OfType<BinaryFactorVariableTreeNode>()
|
---|
| 72 | .Where(node => !usedFactorVariables.Contains(node.VariableName))
|
---|
| 73 | .Select(node => Tuple.Create(node.VariableValue, node.VariableValue));
|
---|
| 74 |
|
---|
[14241] | 75 | // create a new problem and dataset
|
---|
| 76 | var variableNames =
|
---|
| 77 | usedDoubleVariables
|
---|
[14251] | 78 | .Concat(usedFactorVariables)
|
---|
| 79 | .Concat(usedBinaryFactors.Select(t => t.Item1 + "=" + t.Item2))
|
---|
[14241] | 80 | .Concat(new string[] { problemData.TargetVariable })
|
---|
| 81 | .ToArray();
|
---|
| 82 | var variableValues =
|
---|
[14251] | 83 | usedDoubleVariables.Select(name => (IList)problemData.Dataset.GetDoubleValues(name).ToList())
|
---|
| 84 | .Concat(usedFactorVariables.Select(name => problemData.Dataset.GetStringValues(name).ToList()))
|
---|
[14241] | 85 | .Concat(
|
---|
[14251] | 86 | // create binary variable
|
---|
| 87 | usedBinaryFactors.Select(t => problemData.Dataset.GetReadOnlyStringValues(t.Item1).Select(val => val == t.Item2 ? 1.0 : 0.0).ToList())
|
---|
[14241] | 88 | )
|
---|
| 89 | .Concat(new[] { problemData.Dataset.GetDoubleValues(problemData.TargetVariable).ToList() });
|
---|
| 90 |
|
---|
| 91 | var newDs = new Dataset(variableNames, variableValues);
|
---|
| 92 | var newProblemData = new ClassificationProblemData(newDs, variableNames.Take(variableNames.Length - 1), variableNames.Last());
|
---|
[15882] | 93 | newProblemData.PositiveClass = problemData.PositiveClass;
|
---|
[14241] | 94 | newProblemData.TrainingPartition.Start = problemData.TrainingPartition.Start;
|
---|
| 95 | newProblemData.TrainingPartition.End = problemData.TrainingPartition.End;
|
---|
| 96 | newProblemData.TestPartition.Start = problemData.TestPartition.Start;
|
---|
| 97 | newProblemData.TestPartition.End = problemData.TestPartition.End;
|
---|
| 98 |
|
---|
| 99 | try {
|
---|
| 100 | var oneR = OneR.CreateOneRSolution(newProblemData);
|
---|
| 101 | oneR.Name = "OneR Classification Solution (subset)";
|
---|
| 102 | solutions.Add(oneR);
|
---|
| 103 | } catch (NotSupportedException) { } catch (ArgumentException) { }
|
---|
| 104 | try {
|
---|
| 105 | var lda = LinearDiscriminantAnalysis.CreateLinearDiscriminantAnalysisSolution(newProblemData);
|
---|
| 106 | lda.Name = "Linear Discriminant Analysis Solution (subset)";
|
---|
| 107 | solutions.Add(lda);
|
---|
| 108 | } catch (NotSupportedException) { } catch (ArgumentException) { }
|
---|
| 109 |
|
---|
| 110 | return solutionsBase.Concat(solutions);
|
---|
| 111 | }
|
---|
| 112 | }
|
---|
| 113 | }
|
---|