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 |
|
---|
22 | using System.Collections.Generic;
|
---|
23 | using System.Linq;
|
---|
24 | using HeuristicLab.Common;
|
---|
25 | using HeuristicLab.Core;
|
---|
26 | using HeuristicLab.Data;
|
---|
27 | using HeuristicLab.Parameters;
|
---|
28 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
29 | using HeuristicLab.Problems.DataAnalysis;
|
---|
30 |
|
---|
31 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
32 | public abstract class PruningBase : ParameterizedNamedItem, IPruningType {
|
---|
33 | private const string PruningStrengthParameterName = "PruningStrength";
|
---|
34 |
|
---|
35 | public IFixedValueParameter<DoubleValue> PruningStrengthParameter {
|
---|
36 | get { return Parameters[PruningStrengthParameterName] as IFixedValueParameter<DoubleValue>; }
|
---|
37 | }
|
---|
38 |
|
---|
39 | public double PruningStrength {
|
---|
40 | get { return PruningStrengthParameter.Value.Value; }
|
---|
41 | }
|
---|
42 |
|
---|
43 | #region Constructors & Cloning
|
---|
44 | [StorableConstructor]
|
---|
45 | protected PruningBase(bool deserializing) : base(deserializing) { }
|
---|
46 | protected PruningBase(PruningBase original, Cloner cloner) : base(original, cloner) { }
|
---|
47 | protected PruningBase() : base() {
|
---|
48 | Parameters.Add(new FixedValueParameter<DoubleValue>(PruningStrengthParameterName, "The strength of the pruning. Higher values force the algorithm to create simpler models", new DoubleValue(2.0)));
|
---|
49 | }
|
---|
50 | #endregion
|
---|
51 |
|
---|
52 | #region IPruningType
|
---|
53 | public abstract ILeafType<IRegressionModel> ModelType(ILeafType<IRegressionModel> leafType);
|
---|
54 | public abstract void GenerateHoldOutSet(IReadOnlyList<int> allrows, IRandom random, out IReadOnlyList<int> training, out IReadOnlyList<int> holdout);
|
---|
55 | internal virtual bool Prune(M5NodeModel node, M5CreationParameters m5CreationParams, IReadOnlyList<int> testRows, double globalStdDev) {
|
---|
56 | if (testRows.Count == 0) return true;
|
---|
57 | var vars = m5CreationParams.AllowedInputVariables.Concat(new[] {m5CreationParams.TargetVariable}).ToArray();
|
---|
58 | var reducedData = new Dataset(vars, vars.Select(x => m5CreationParams.Data.GetDoubleValues(x, testRows).ToList()));
|
---|
59 | var pd = new RegressionProblemData(reducedData, m5CreationParams.AllowedInputVariables, m5CreationParams.TargetVariable);
|
---|
60 | pd.TrainingPartition.Start = pd.TrainingPartition.End = pd.TestPartition.Start = 0;
|
---|
61 | pd.TestPartition.End = reducedData.Rows;
|
---|
62 |
|
---|
63 | var rmsModel = node.NodeModel.CreateRegressionSolution(pd).TestRootMeanSquaredError;
|
---|
64 | var rmsSubTree = node.CreateRegressionSolution(pd).TestRootMeanSquaredError;
|
---|
65 |
|
---|
66 | var adjustedRmsModel = rmsModel * PruningFactor(pd.Dataset.Rows, node.NodeModelParams);
|
---|
67 | var adjustedRmsTree = rmsSubTree * PruningFactor(pd.Dataset.Rows, node.Left.NumParam + node.Right.NumParam + 1);
|
---|
68 | return adjustedRmsModel <= adjustedRmsTree || adjustedRmsModel < globalStdDev * 0.0001;
|
---|
69 | }
|
---|
70 | #endregion
|
---|
71 |
|
---|
72 | private double PruningFactor(int noInstances, int noParams) {
|
---|
73 | return noInstances <= noParams ? 10.0 : (noInstances + PruningStrength * noParams) / (noInstances - noParams);
|
---|
74 | }
|
---|
75 | }
|
---|
76 | } |
---|