Free cookie consent management tool by TermsFeed Policy Generator

source: branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/M5Utilities/M5StaticUtilities.cs @ 15614

Last change on this file since 15614 was 15614, checked in by bwerth, 6 years ago

#2847 made changes to M5 according to review comments

File size: 3.6 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;
23using System.Collections.Generic;
24using System.Linq;
25using System.Threading;
26using HeuristicLab.Common;
27using HeuristicLab.Core;
28using HeuristicLab.Data;
29using HeuristicLab.Optimization;
30using HeuristicLab.Problems.DataAnalysis;
31
32namespace HeuristicLab.Algorithms.DataAnalysis {
33  internal static class M5StaticUtilities {
34    public static ResultCollection RunSubAlgorithm(IAlgorithm alg, int random, CancellationToken cancellationToken) {
35      if (alg.Parameters.ContainsKey("SetSeedRandomly") && alg.Parameters.ContainsKey("Seed")) {
36        var seed = alg.Parameters["Seed"].ActualValue as IntValue;
37        var setSeed = alg.Parameters["SetSeedRandomly"].ActualValue as BoolValue;
38        if (seed == null || setSeed == null)
39          throw new ArgumentException("The parameters SetSeedRandomly and Seed do not have the expected type");
40        setSeed.Value = false;
41        seed.Value = random;
42      }
43      if (alg.ExecutionState != ExecutionState.Paused) alg.Prepare();
44      alg.Start(cancellationToken);
45      return alg.Results;
46    }
47
48    public static void SplitRows(IReadOnlyList<int> rows, IDataset data, string splitAttr, double splitValue, out IReadOnlyList<int> leftRows, out IReadOnlyList<int> rightRows) {
49      //TODO check and revert points at borders are now used multipe times
50      var assignment = data.GetDoubleValues(splitAttr, rows).Select(x => x.IsAlmost(splitValue) ? 2 : x < splitValue ? 0 : 1).ToArray();
51      leftRows = rows.Zip(assignment, (i, b) => new {i, b}).Where(x => x.b == 0 || x.b == 2).Select(x => x.i).ToList();
52      rightRows = rows.Zip(assignment, (i, b) => new {i, b}).Where(x => x.b > 0).Select(x => x.i).ToList();
53    }
54
55    public static IRegressionModel BuildModel(IReadOnlyList<int> rows, M5Parameters parameters, ILeafModel leafModel, CancellationToken cancellation, out int numParams) {
56      var reducedData = ReduceDataset(parameters.Data, rows, parameters.AllowedInputVariables.ToArray(), parameters.TargetVariable);
57      var pd = new RegressionProblemData(reducedData, parameters.AllowedInputVariables.ToArray(), parameters.TargetVariable);
58      pd.TrainingPartition.Start = 0;
59      pd.TrainingPartition.End = pd.TestPartition.Start = pd.TestPartition.End = reducedData.Rows;
60
61      int numP;
62      var model = leafModel.Build(pd, parameters.Random, cancellation, out numP);
63      numParams = numP;
64      cancellation.ThrowIfCancellationRequested();
65      return model;
66    }
67
68    public static IDataset ReduceDataset(IDataset data, IReadOnlyList<int> rows, IReadOnlyList<string> inputVariables, string target) {
69      return new Dataset(inputVariables.Concat(new[] {target}), inputVariables.Concat(new[] {target}).Select(x => data.GetDoubleValues(x, rows).ToList()));
70    }
71  }
72}
Note: See TracBrowser for help on using the repository browser.