Free cookie consent management tool by TermsFeed Policy Generator

source: branches/2931_OR-Tools_LP_MIP/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourRegression.cs @ 16720

Last change on this file since 16720 was 16720, checked in by ddorfmei, 5 years ago

#2931: Merged revision(s) 16235-16719 from trunk

File size: 5.9 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2019 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.Threading;
24using HeuristicLab.Common;
25using HeuristicLab.Core;
26using HeuristicLab.Data;
27using HeuristicLab.Optimization;
28using HeuristicLab.Parameters;
29using HEAL.Attic;
30using HeuristicLab.Problems.DataAnalysis;
31
32namespace HeuristicLab.Algorithms.DataAnalysis {
33  /// <summary>
34  /// Nearest neighbour regression data analysis algorithm.
35  /// </summary>
36  [Item("Nearest Neighbour Regression (kNN)", "Nearest neighbour regression data analysis algorithm (wrapper for ALGLIB).")]
37  [Creatable(CreatableAttribute.Categories.DataAnalysisRegression, Priority = 150)]
38  [StorableType("3F940BE0-4F44-4F7F-A3EE-E47423C7F22D")]
39  public sealed class NearestNeighbourRegression : FixedDataAnalysisAlgorithm<IRegressionProblem> {
40    private const string KParameterName = "K";
41    private const string NearestNeighbourRegressionModelResultName = "Nearest neighbour regression solution";
42    private const string WeightsParameterName = "Weights";
43    private const string SelfMatchParameterName = "SelfMatch";
44
45    #region parameter properties
46    public IFixedValueParameter<IntValue> KParameter {
47      get { return (IFixedValueParameter<IntValue>)Parameters[KParameterName]; }
48    }
49    public IFixedValueParameter<BoolValue> SelfMatchParameter {
50      get { return (IFixedValueParameter<BoolValue>)Parameters[SelfMatchParameterName]; }
51    }
52    public IValueParameter<DoubleArray> WeightsParameter {
53      get { return (IValueParameter<DoubleArray>)Parameters[WeightsParameterName]; }
54    }
55    #endregion
56    #region properties
57    public int K {
58      get { return KParameter.Value.Value; }
59      set {
60        if (value <= 0) throw new ArgumentException("K must be larger than zero.", "K");
61        else KParameter.Value.Value = value;
62      }
63    }
64    public bool SelfMatch {
65      get { return SelfMatchParameter.Value.Value; }
66      set { SelfMatchParameter.Value.Value = value; }
67    }
68    public DoubleArray Weights {
69      get { return WeightsParameter.Value; }
70      set { WeightsParameter.Value = value; }
71    }
72    #endregion
73
74    [StorableConstructor]
75    private NearestNeighbourRegression(StorableConstructorFlag _) : base(_) { }
76    private NearestNeighbourRegression(NearestNeighbourRegression original, Cloner cloner)
77      : base(original, cloner) {
78    }
79    public NearestNeighbourRegression()
80      : base() {
81      Parameters.Add(new FixedValueParameter<IntValue>(KParameterName, "The number of nearest neighbours to consider for regression.", new IntValue(3)));
82      Parameters.Add(new OptionalValueParameter<DoubleArray>(WeightsParameterName, "Optional: use weights to specify individual scaling values for all features. If not set the weights are calculated automatically (each feature is scaled to unit variance)"));
83      Parameters.Add(new FixedValueParameter<BoolValue>(SelfMatchParameterName, "Should we use equal points for classification?", new BoolValue(false)));
84      Problem = new RegressionProblem();
85    }
86
87    [StorableHook(HookType.AfterDeserialization)]
88    private void AfterDeserialization() {
89      // BackwardsCompatibility3.3
90      #region Backwards compatible code, remove with 3.4
91      if (!Parameters.ContainsKey(WeightsParameterName)) {
92        Parameters.Add(new OptionalValueParameter<DoubleArray>(WeightsParameterName, "Optional: use weights to specify individual scaling values for all features. If not set the weights are calculated automatically (each feature is scaled to unit variance)"));
93      }
94      if (!Parameters.ContainsKey(SelfMatchParameterName)) {
95        Parameters.Add(new FixedValueParameter<BoolValue>(SelfMatchParameterName, "Should we use equal points for classification?", new BoolValue(false)));
96      }
97      #endregion
98    }
99
100    public override IDeepCloneable Clone(Cloner cloner) {
101      return new NearestNeighbourRegression(this, cloner);
102    }
103
104    #region nearest neighbour
105    protected override void Run(CancellationToken cancellationToken) {
106      double[] weights = null;
107      if (Weights != null) weights = Weights.CloneAsArray();
108      var solution = CreateNearestNeighbourRegressionSolution(Problem.ProblemData, K, SelfMatch, weights);
109      Results.Add(new Result(NearestNeighbourRegressionModelResultName, "The nearest neighbour regression solution.", solution));
110    }
111
112    public static IRegressionSolution CreateNearestNeighbourRegressionSolution(IRegressionProblemData problemData, int k, bool selfMatch = false, double[] weights = null) {
113      var clonedProblemData = (IRegressionProblemData)problemData.Clone();
114      return new NearestNeighbourRegressionSolution(Train(problemData, k, selfMatch, weights), clonedProblemData);
115    }
116
117    public static INearestNeighbourModel Train(IRegressionProblemData problemData, int k, bool selfMatch = false, double[] weights = null) {
118      return new NearestNeighbourModel(problemData.Dataset,
119        problemData.TrainingIndices,
120        k,
121        selfMatch,
122        problemData.TargetVariable,
123        problemData.AllowedInputVariables,
124        weights);
125    }
126    #endregion
127  }
128}
Note: See TracBrowser for help on using the repository browser.