1  #region License Information


2  /* HeuristicLab


3  * Copyright (C) 20022012 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.Collections.Generic;


24  using System.Linq;


25  using HeuristicLab.Common;


26  using HeuristicLab.Core;


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


28  using HeuristicLab.Problems.DataAnalysis;


29 


30  namespace HeuristicLab.Algorithms.DataAnalysis {


31  [StorableClass]


32  [Item(Name = "Scaling", Description = "Contains information about scaling of variables for dataanalysis algorithms.")]


33  public class Scaling : Item {


34  [Storable]


35  private Dictionary<string, Tuple<double, double>> scalingParameters = new Dictionary<string, Tuple<double, double>>();


36  [StorableConstructor]


37  protected Scaling(bool deserializing) : base(deserializing) { }


38  protected Scaling(Scaling original, Cloner cloner)


39  : base(original, cloner) {


40  foreach (var pair in original.scalingParameters)


41  scalingParameters.Add(pair.Key, Tuple.Create(pair.Value.Item1, pair.Value.Item2));


42  }


43  public Scaling(Dataset ds, IEnumerable<string> variables, IEnumerable<int> rows) {


44  foreach (var variable in variables) {


45  var values = ds.GetDoubleValues(variable, rows);


46  var min = values.Where(x => !double.IsNaN(x)).Min();


47  var max = values.Where(x => !double.IsNaN(x)).Max();


48  scalingParameters[variable] = Tuple.Create(min, max);


49  }


50  }


51 


52  public override IDeepCloneable Clone(Cloner cloner) {


53  return new Scaling(this, cloner);


54  }


55 


56  public IEnumerable<double> GetScaledValues(Dataset ds, string variable, IEnumerable<int> rows) {


57  double min = scalingParameters[variable].Item1;


58  double max = scalingParameters[variable].Item2;


59  if (min.IsAlmost(max)) return rows.Select(i => 0.0); // return enumerable of zeros


60  return ds.GetDoubleValues(variable, rows).Select(x => (x  min) / (max  min)); // scale to range [0..1]


61  }


62 


63  public void GetScalingParameters(string variable, out double min, out double max) {


64  min = scalingParameters[variable].Item1;


65  max = scalingParameters[variable].Item2;


66  }


67  }


68  }

