source: branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/Spliting/CorrelationSplitter.cs @ 15830

Last change on this file since 15830 was 15830, checked in by bwerth, 18 months ago

#2847 adapted project to new rep structure; major changes to interfaces; restructures splitting and pruning

File size: 3.7 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2017 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.Collections.Generic;
23using HeuristicLab.Common;
24using HeuristicLab.Core;
25using HeuristicLab.Data;
26using HeuristicLab.Parameters;
27using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
28
29namespace HeuristicLab.Algorithms.DataAnalysis {
30  [StorableClass]
31  [Item("CorrelationSplitter", "An experimental split selector that uses correlation coefficients")]
32  public class CorrelationSplitter : SplitterBase {
33    public const string OrderParameterName = "Order";
34    public IFixedValueParameter<DoubleValue> OrderParameter {
35      get { return (IFixedValueParameter<DoubleValue>)Parameters[OrderParameterName]; }
36    }
37    public double Order {
38      get { return OrderParameter.Value.Value; }
39    }
40
41    #region Constructors & Cloning
42    [StorableConstructor]
43    private CorrelationSplitter(bool deserializing) { }
44    private CorrelationSplitter(CorrelationSplitter original, Cloner cloner) : base(original, cloner) { }
45    public CorrelationSplitter() {
46      Parameters.Add(new FixedValueParameter<DoubleValue>(OrderParameterName, "The exponent in the split calculation ssrLeft^(1/Order)+ssrRight^(1/Order).", new DoubleValue(1)));
47    }
48    public override IDeepCloneable Clone(Cloner cloner) {
49      return new CorrelationSplitter(this, cloner);
50    }
51    #endregion
52
53    #region ISplitType
54    protected override void AttributeSplit(IReadOnlyList<double> attValues, IReadOnlyList<double> targetValues, int minLeafSize, out int leftSize, out double maxImpurity, out double splitValue) {
55      leftSize = -1;
56      splitValue = double.MinValue;
57      maxImpurity = double.NegativeInfinity;
58      var splitValues = new List<double>();
59      var splitSizes = new List<int>();
60      var length = attValues.Count;
61
62      var start = minLeafSize;
63      while (start < length && attValues[start - 1].IsAlmost(attValues[start]))
64        start++;
65      if (start >= length) return;
66
67      var imp = new CorrelationImpuritiyCalculator(minLeafSize, attValues, targetValues, Order);
68      maxImpurity = imp.Impurity;
69      splitValues.Add(imp.SplitValue);
70      splitSizes.Add(imp.LeftSize);
71
72      while (imp.LeftSize < length - minLeafSize) {
73        imp.Increment();
74        if (!imp.ValidPosition) continue; //splits can not be made between to equal points
75
76        if (imp.Impurity.IsAlmost(maxImpurity)) {
77          splitValues.Add(imp.SplitValue);
78          splitSizes.Add(imp.LeftSize);
79          continue;
80        }
81
82        if (imp.Impurity < maxImpurity) continue;
83        splitValues.Clear();
84        splitSizes.Clear();
85        maxImpurity = imp.Impurity;
86        splitValues.Add(imp.SplitValue);
87        splitSizes.Add(imp.LeftSize);
88      }
89
90      var j = splitSizes.Count / 2;
91      if (splitSizes.Count == 0) return;
92      splitValue = splitValues[j];
93      leftSize = splitSizes[j];
94    }
95    #endregion
96  }
97}
Note: See TracBrowser for help on using the repository browser.