1  #region License Information


2  /* HeuristicLab


3  * Copyright (C) 20022016 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.Linq;


24  using HeuristicLab.Common;


25  using HeuristicLab.Core;


26  using HeuristicLab.Data;


27  using HeuristicLab.Optimization;


28  using HeuristicLab.Parameters;


29  using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;


30  using HeuristicLab.Problems.DataAnalysis;


31 


32  namespace HeuristicLab.Algorithms.DataAnalysis {


33  /// <summary>


34  /// Nearest neighbour classification data analysis algorithm.


35  /// </summary>


36  [Item("Nearest Neighbour Classification (kNN)", "Nearest neighbour classification data analysis algorithm (wrapper for ALGLIB).")]


37  [Creatable(CreatableAttribute.Categories.DataAnalysisClassification, Priority = 150)]


38  [StorableClass]


39  public sealed class NearestNeighbourClassification : FixedDataAnalysisAlgorithm<IClassificationProblem> {


40  private const string KParameterName = "K";


41  private const string NearestNeighbourClassificationModelResultName = "Nearest neighbour classification solution";


42  private const string WeightsParameterName = "Weights";


43 


44 


45  #region parameter properties


46  public IFixedValueParameter<IntValue> KParameter {


47  get { return (IFixedValueParameter<IntValue>)Parameters[KParameterName]; }


48  }


49  public IValueParameter<DoubleArray> WeightsParameter {


50  get { return (IValueParameter<DoubleArray>)Parameters[WeightsParameterName]; }


51  }


52  #endregion


53  #region properties


54  public int K {


55  get { return KParameter.Value.Value; }


56  set {


57  if (value <= 0) throw new ArgumentException("K must be larger than zero.", "K");


58  else KParameter.Value.Value = value;


59  }


60  }


61  public DoubleArray Weights {


62  get { return WeightsParameter.Value; }


63  set { WeightsParameter.Value = value; }


64  }


65  #endregion


66 


67  [StorableConstructor]


68  private NearestNeighbourClassification(bool deserializing) : base(deserializing) { }


69  private NearestNeighbourClassification(NearestNeighbourClassification original, Cloner cloner)


70  : base(original, cloner) {


71  }


72  public NearestNeighbourClassification()


73  : base() {


74  Parameters.Add(new FixedValueParameter<IntValue>(KParameterName, "The number of nearest neighbours to consider for regression.", new IntValue(3)));


75  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)"));


76  Problem = new ClassificationProblem();


77  }


78  [StorableHook(HookType.AfterDeserialization)]


79  private void AfterDeserialization() {


80  // BackwardsCompatibility3.3


81  #region Backwards compatible code, remove with 3.4


82  if (!Parameters.ContainsKey(WeightsParameterName)) {


83  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)"));


84  }


85  #endregion


86  }


87 


88  public override IDeepCloneable Clone(Cloner cloner) {


89  return new NearestNeighbourClassification(this, cloner);


90  }


91 


92  #region nearest neighbour


93  protected override void Run() {


94  double[] weights = null;


95  if (Weights != null) weights = Weights.CloneAsArray();


96  var solution = CreateNearestNeighbourClassificationSolution(Problem.ProblemData, K, weights);


97  Results.Add(new Result(NearestNeighbourClassificationModelResultName, "The nearest neighbour classification solution.", solution));


98  }


99 


100  public static IClassificationSolution CreateNearestNeighbourClassificationSolution(IClassificationProblemData problemData, int k, double[] weights = null) {


101  var problemDataClone = (IClassificationProblemData)problemData.Clone();


102  return new NearestNeighbourClassificationSolution(Train(problemDataClone, k, weights), problemDataClone);


103  }


104 


105  public static INearestNeighbourModel Train(IClassificationProblemData problemData, int k, double[] weights = null) {


106  return new NearestNeighbourModel(problemData.Dataset,


107  problemData.TrainingIndices,


108  k,


109  problemData.TargetVariable,


110  problemData.AllowedInputVariables,


111  weights,


112  problemData.ClassValues.ToArray());


113  }


114  #endregion


115  }


116  }

