1 | #region License Information |
---|
2 | /* HeuristicLab |
---|
3 | * Copyright (C) 2002-2015 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.Linq; |
---|
23 | using HeuristicLab.Common; |
---|
24 | using HeuristicLab.Core; |
---|
25 | using HeuristicLab.Optimization; |
---|
26 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable; |
---|
27 | using HeuristicLab.Problems.DataAnalysis; |
---|
28 | |
---|
29 | namespace HeuristicLab.Algorithms.DataAnalysis { |
---|
30 | /// <summary> |
---|
31 | /// 0R classification algorithm. |
---|
32 | /// </summary> |
---|
33 | [Item("ZeroR Classification", "The simplest possible classifier, ZeroR always predicts the majority class.")] |
---|
34 | [StorableClass] |
---|
35 | public sealed class ZeroR : FixedDataAnalysisAlgorithm<IClassificationProblem> { |
---|
36 | |
---|
37 | [StorableConstructor] |
---|
38 | private ZeroR(bool deserializing) : base(deserializing) { } |
---|
39 | private ZeroR(ZeroR original, Cloner cloner) |
---|
40 | : base(original, cloner) { |
---|
41 | } |
---|
42 | public ZeroR() |
---|
43 | : base() { |
---|
44 | Problem = new ClassificationProblem(); |
---|
45 | } |
---|
46 | |
---|
47 | public override IDeepCloneable Clone(Cloner cloner) { |
---|
48 | return new ZeroR(this, cloner); |
---|
49 | } |
---|
50 | |
---|
51 | protected override void Run() { |
---|
52 | var solution = CreateZeroRSolution(Problem.ProblemData); |
---|
53 | Results.Add(new Result("ZeroR solution", "The simplest possible classifier, ZeroR always predicts the majority class.", solution)); |
---|
54 | } |
---|
55 | |
---|
56 | public static IClassificationSolution CreateZeroRSolution(IClassificationProblemData problemData) { |
---|
57 | var dataset = problemData.Dataset; |
---|
58 | string target = problemData.TargetVariable; |
---|
59 | var targetValues = dataset.GetDoubleValues(target, problemData.TrainingIndices); |
---|
60 | |
---|
61 | |
---|
62 | // if multiple classes have the same number of observations then simply take the first one |
---|
63 | var dominantClass = targetValues.GroupBy(x => x).ToDictionary(g => g.Key, g => g.Count()) |
---|
64 | .MaxItems(kvp => kvp.Value).Select(x => x.Key).First(); |
---|
65 | |
---|
66 | var model = new ConstantModel(dominantClass, target); |
---|
67 | var solution = model.CreateClassificationSolution(problemData); |
---|
68 | return solution; |
---|
69 | } |
---|
70 | } |
---|
71 | } |
---|