Free cookie consent management tool by TermsFeed Policy Generator

source: trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassification.cs @ 14185

Last change on this file since 14185 was 14185, checked in by swagner, 8 years ago

#2526: Updated year of copyrights in license headers

File size: 9.6 KB
Line 
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
22using HeuristicLab.Common;
23using HeuristicLab.Core;
24using HeuristicLab.Data;
25using HeuristicLab.Optimization;
26using HeuristicLab.Parameters;
27using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
28using HeuristicLab.Problems.DataAnalysis;
29
30namespace HeuristicLab.Algorithms.DataAnalysis {
31  /// <summary>
32  /// Random forest classification data analysis algorithm.
33  /// </summary>
34  [Item("Random Forest Classification (RF)", "Random forest classification data analysis algorithm (wrapper for ALGLIB).")]
35  [Creatable(CreatableAttribute.Categories.DataAnalysisClassification, Priority = 120)]
36  [StorableClass]
37  public sealed class RandomForestClassification : FixedDataAnalysisAlgorithm<IClassificationProblem> {
38    private const string RandomForestClassificationModelResultName = "Random forest classification solution";
39    private const string NumberOfTreesParameterName = "Number of trees";
40    private const string RParameterName = "R";
41    private const string MParameterName = "M";
42    private const string SeedParameterName = "Seed";
43    private const string SetSeedRandomlyParameterName = "SetSeedRandomly";
44    private const string CreateSolutionParameterName = "CreateSolution";
45
46    #region parameter properties
47    public IFixedValueParameter<IntValue> NumberOfTreesParameter {
48      get { return (IFixedValueParameter<IntValue>)Parameters[NumberOfTreesParameterName]; }
49    }
50    public IFixedValueParameter<DoubleValue> RParameter {
51      get { return (IFixedValueParameter<DoubleValue>)Parameters[RParameterName]; }
52    }
53    public IFixedValueParameter<DoubleValue> MParameter {
54      get { return (IFixedValueParameter<DoubleValue>)Parameters[MParameterName]; }
55    }
56    public IFixedValueParameter<IntValue> SeedParameter {
57      get { return (IFixedValueParameter<IntValue>)Parameters[SeedParameterName]; }
58    }
59    public IFixedValueParameter<BoolValue> SetSeedRandomlyParameter {
60      get { return (IFixedValueParameter<BoolValue>)Parameters[SetSeedRandomlyParameterName]; }
61    }
62    public IFixedValueParameter<BoolValue> CreateSolutionParameter {
63      get { return (IFixedValueParameter<BoolValue>)Parameters[CreateSolutionParameterName]; }
64    }
65    #endregion
66    #region properties
67    public int NumberOfTrees {
68      get { return NumberOfTreesParameter.Value.Value; }
69      set { NumberOfTreesParameter.Value.Value = value; }
70    }
71    public double R {
72      get { return RParameter.Value.Value; }
73      set { RParameter.Value.Value = value; }
74    }
75    public double M {
76      get { return MParameter.Value.Value; }
77      set { MParameter.Value.Value = value; }
78    }
79    public int Seed {
80      get { return SeedParameter.Value.Value; }
81      set { SeedParameter.Value.Value = value; }
82    }
83    public bool SetSeedRandomly {
84      get { return SetSeedRandomlyParameter.Value.Value; }
85      set { SetSeedRandomlyParameter.Value.Value = value; }
86    }
87    public bool CreateSolution {
88      get { return CreateSolutionParameter.Value.Value; }
89      set { CreateSolutionParameter.Value.Value = value; }
90    }
91    #endregion
92
93    [StorableConstructor]
94    private RandomForestClassification(bool deserializing) : base(deserializing) { }
95    private RandomForestClassification(RandomForestClassification original, Cloner cloner)
96      : base(original, cloner) {
97    }
98
99    public RandomForestClassification()
100      : base() {
101      Parameters.Add(new FixedValueParameter<IntValue>(NumberOfTreesParameterName, "The number of trees in the forest. Should be between 50 and 100", new IntValue(50)));
102      Parameters.Add(new FixedValueParameter<DoubleValue>(RParameterName, "The ratio of the training set that will be used in the construction of individual trees (0<r<=1). Should be adjusted depending on the noise level in the dataset in the range from 0.66 (low noise) to 0.05 (high noise). This parameter should be adjusted to achieve good generalization error.", new DoubleValue(0.3)));
103      Parameters.Add(new FixedValueParameter<DoubleValue>(MParameterName, "The ratio of features that will be used in the construction of individual trees (0<m<=1)", new DoubleValue(0.5)));
104      Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The random seed used to initialize the new pseudo random number generator.", new IntValue(0)));
105      Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "True if the random seed should be set to a random value, otherwise false.", new BoolValue(true)));
106      Parameters.Add(new FixedValueParameter<BoolValue>(CreateSolutionParameterName, "Flag that indicates if a solution should be produced at the end of the run", new BoolValue(true)));
107      Parameters[CreateSolutionParameterName].Hidden = true;
108
109      Problem = new ClassificationProblem();
110    }
111
112    [StorableHook(HookType.AfterDeserialization)]
113    private void AfterDeserialization() {
114      // BackwardsCompatibility3.3
115      #region Backwards compatible code, remove with 3.4
116      if (!Parameters.ContainsKey(MParameterName))
117        Parameters.Add(new FixedValueParameter<DoubleValue>(MParameterName, "The ratio of features that will be used in the construction of individual trees (0<m<=1)", new DoubleValue(0.5)));
118      if (!Parameters.ContainsKey(SeedParameterName))
119        Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The random seed used to initialize the new pseudo random number generator.", new IntValue(0)));
120      if (!Parameters.ContainsKey((SetSeedRandomlyParameterName)))
121        Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "True if the random seed should be set to a random value, otherwise false.", new BoolValue(true)));
122      if (!Parameters.ContainsKey(CreateSolutionParameterName)) {
123        Parameters.Add(new FixedValueParameter<BoolValue>(CreateSolutionParameterName, "Flag that indicates if a solution should be produced at the end of the run", new BoolValue(true)));
124        Parameters[CreateSolutionParameterName].Hidden = true;
125      }
126      #endregion
127    }
128
129    public override IDeepCloneable Clone(Cloner cloner) {
130      return new RandomForestClassification(this, cloner);
131    }
132
133    #region random forest
134    protected override void Run() {
135      double rmsError, relClassificationError, outOfBagRmsError, outOfBagRelClassificationError;
136      if (SetSeedRandomly) Seed = new System.Random().Next();
137
138      var model = CreateRandomForestClassificationModel(Problem.ProblemData, NumberOfTrees, R, M, Seed, out rmsError, out relClassificationError, out outOfBagRmsError, out outOfBagRelClassificationError);
139      Results.Add(new Result("Root mean square error", "The root of the mean of squared errors of the random forest regression solution on the training set.", new DoubleValue(rmsError)));
140      Results.Add(new Result("Relative classification error", "Relative classification error of the random forest regression solution on the training set.", new PercentValue(relClassificationError)));
141      Results.Add(new Result("Root mean square error (out-of-bag)", "The out-of-bag root of the mean of squared errors of the random forest regression solution.", new DoubleValue(outOfBagRmsError)));
142      Results.Add(new Result("Relative classification error (out-of-bag)", "The out-of-bag relative classification error  of the random forest regression solution.", new PercentValue(outOfBagRelClassificationError)));
143
144      if (CreateSolution) {
145        var solution = new RandomForestClassificationSolution(model, (IClassificationProblemData)Problem.ProblemData.Clone());
146        Results.Add(new Result(RandomForestClassificationModelResultName, "The random forest classification solution.", solution));
147      }
148    }
149
150    // keep for compatibility with old API
151    public static RandomForestClassificationSolution CreateRandomForestClassificationSolution(IClassificationProblemData problemData, int nTrees, double r, double m, int seed,
152      out double rmsError, out double relClassificationError, out double outOfBagRmsError, out double outOfBagRelClassificationError) {
153      var model = CreateRandomForestClassificationModel(problemData, nTrees, r, m, seed, out rmsError, out relClassificationError, out outOfBagRmsError, out outOfBagRelClassificationError);
154      return new RandomForestClassificationSolution(model, (IClassificationProblemData)problemData.Clone());
155    }
156
157    public static RandomForestModel CreateRandomForestClassificationModel(IClassificationProblemData problemData, int nTrees, double r, double m, int seed,
158      out double rmsError, out double relClassificationError, out double outOfBagRmsError, out double outOfBagRelClassificationError) {
159      return RandomForestModel.CreateClassificationModel(problemData, nTrees, r, m, seed, out rmsError, out relClassificationError, out outOfBagRmsError, out outOfBagRelClassificationError);
160    }
161    #endregion
162  }
163}
Note: See TracBrowser for help on using the repository browser.