Free cookie consent management tool by TermsFeed Policy Generator

source: trunk/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs @ 17999

Last change on this file since 17999 was 17999, checked in by mkommend, 3 years ago

#3129: Work on variable range calculation of datasets.

Renamed method to calculate variable ranges to a more appropriate method name.
Added possibility to ignore NaNs for range calculation.

File size: 8.5 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 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 HEAL.Attic;
26using HeuristicLab.Common;
27using HeuristicLab.Core;
28using HeuristicLab.Data;
29using HeuristicLab.Parameters;
30
31namespace HeuristicLab.Problems.DataAnalysis {
32  [StorableType("EE612297-B1AF-42D2-BF21-AF9A2D42791C")]
33  [Item("RegressionProblemData", "Represents an item containing all data defining a regression problem.")]
34  public class RegressionProblemData : DataAnalysisProblemData, IRegressionProblemData, IStorableContent {
35    protected const string TargetVariableParameterName = "TargetVariable";
36    protected const string VariableRangesParameterName = "VariableRanges";
37    public string Filename { get; set; }
38
39    #region default data
40    private static double[,] kozaF1 = new double[,] {
41          {2.017885919, -1.449165046},
42          {1.30060506,  -1.344523885},
43          {1.147134798, -1.317989331},
44          {0.877182504, -1.266142284},
45          {0.852562452, -1.261020794},
46          {0.431095788, -1.158793317},
47          {0.112586002, -1.050908405},
48          {0.04594507,  -1.021989402},
49          {0.042572879, -1.020438113},
50          {-0.074027291,  -0.959859562},
51          {-0.109178553,  -0.938094706},
52          {-0.259721109,  -0.803635355},
53          {-0.272991057,  -0.387519561},
54          {-0.161978191,  -0.193611001},
55          {-0.102489983,  -0.114215349},
56          {-0.01469968, -0.014918985},
57          {-0.008863365,  -0.008942626},
58          {0.026751057, 0.026054094},
59          {0.166922436, 0.14309643},
60          {0.176953808, 0.1504144},
61          {0.190233418, 0.159916534},
62          {0.199800708, 0.166635331},
63          {0.261502822, 0.207600348},
64          {0.30182879,  0.232370249},
65          {0.83763905,  0.468046718}
66    };
67    private static readonly Dataset defaultDataset;
68    private static readonly IEnumerable<string> defaultAllowedInputVariables;
69    private static readonly string defaultTargetVariable;
70
71    private static readonly RegressionProblemData emptyProblemData;
72    public static RegressionProblemData EmptyProblemData {
73      get { return emptyProblemData; }
74    }
75
76    static RegressionProblemData() {
77      defaultDataset = new Dataset(new string[] { "y", "x" }, kozaF1);
78      defaultDataset.Name = "Fourth-order Polynomial Function Benchmark Dataset";
79      defaultDataset.Description = "f(x) = x^4 + x^3 + x^2 + x";
80      defaultAllowedInputVariables = new List<string>() { "x" };
81      defaultTargetVariable = "y";
82
83      var problemData = new RegressionProblemData();
84      problemData.Parameters.Clear();
85      problemData.Name = "Empty Regression ProblemData";
86      problemData.Description = "This ProblemData acts as place holder before the correct problem data is loaded.";
87      problemData.isEmpty = true;
88
89      problemData.Parameters.Add(new FixedValueParameter<Dataset>(DatasetParameterName, "", new Dataset()));
90      problemData.Parameters.Add(new FixedValueParameter<ReadOnlyCheckedItemList<StringValue>>(InputVariablesParameterName, ""));
91      problemData.Parameters.Add(new FixedValueParameter<IntRange>(TrainingPartitionParameterName, "", (IntRange)new IntRange(0, 0).AsReadOnly()));
92      problemData.Parameters.Add(new FixedValueParameter<IntRange>(TestPartitionParameterName, "", (IntRange)new IntRange(0, 0).AsReadOnly()));
93      problemData.Parameters.Add(new ConstrainedValueParameter<StringValue>(TargetVariableParameterName, new ItemSet<StringValue>()));
94      problemData.Parameters.Add(new FixedValueParameter<IntervalCollection>(VariableRangesParameterName, "", new IntervalCollection()));
95      emptyProblemData = problemData;
96    }
97    #endregion
98
99    #region parameter properties
100    public IConstrainedValueParameter<StringValue> TargetVariableParameter => (IConstrainedValueParameter<StringValue>)Parameters[TargetVariableParameterName];
101    public IFixedValueParameter<IntervalCollection> VariableRangesParameter => (IFixedValueParameter<IntervalCollection>)Parameters[VariableRangesParameterName];
102    #endregion
103
104    #region properties
105    public IntervalCollection VariableRanges {
106      get => VariableRangesParameter.Value;
107    }
108
109    public string TargetVariable {
110      get { return TargetVariableParameter.Value.Value; }
111      set {
112        if (value == null) throw new ArgumentNullException("targetVariable", "The provided value for the targetVariable is null.");
113        if (value == TargetVariable) return;
114
115        var matchingParameterValue = TargetVariableParameter.ValidValues.FirstOrDefault(v => v.Value == value);
116        if (matchingParameterValue == null) throw new ArgumentException("The provided value is not valid as the targetVariable.", "targetVariable");
117        TargetVariableParameter.Value = matchingParameterValue;
118      }
119    }
120    public IEnumerable<double> TargetVariableValues => Dataset.GetDoubleValues(TargetVariable);
121    public IEnumerable<double> TargetVariableTrainingValues => Dataset.GetDoubleValues(TargetVariable, TrainingIndices);
122    public IEnumerable<double> TargetVariableTestValues => Dataset.GetDoubleValues(TargetVariable, TestIndices);
123    #endregion
124
125
126
127    [StorableConstructor]
128    protected RegressionProblemData(StorableConstructorFlag _) : base(_) { }
129    [StorableHook(HookType.AfterDeserialization)]
130    private void AfterDeserialization() {
131      if (!Parameters.ContainsKey(VariableRangesParameterName)) {
132        var variableRanges = Dataset.GetVariableRanges();
133        Parameters.Add(new FixedValueParameter<IntervalCollection>(VariableRangesParameterName, intervalCollection));
134      }
135
136      RegisterParameterEvents();
137    }
138
139    protected RegressionProblemData(RegressionProblemData original, Cloner cloner)
140      : base(original, cloner) {
141      RegisterParameterEvents();
142    }
143    public override IDeepCloneable Clone(Cloner cloner) {
144      if (this == emptyProblemData) return emptyProblemData;
145      return new RegressionProblemData(this, cloner);
146    }
147
148    public RegressionProblemData()
149      : this(defaultDataset, defaultAllowedInputVariables, defaultTargetVariable) {
150    }
151    public RegressionProblemData(IRegressionProblemData regressionProblemData)
152      : this(regressionProblemData.Dataset, regressionProblemData.AllowedInputVariables, regressionProblemData.TargetVariable) {
153      TrainingPartition.Start = regressionProblemData.TrainingPartition.Start;
154      TrainingPartition.End = regressionProblemData.TrainingPartition.End;
155      TestPartition.Start = regressionProblemData.TestPartition.Start;
156      TestPartition.End = regressionProblemData.TestPartition.End;
157    }
158
159    public RegressionProblemData(IDataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable,
160      IEnumerable<ITransformation> transformations = null,
161      IntervalCollection variableRanges = null)
162      : base(dataset, allowedInputVariables, transformations ?? Enumerable.Empty<ITransformation>()) {
163      var variables = InputVariables.Select(x => x.AsReadOnly()).ToList();
164      Parameters.Add(new ConstrainedValueParameter<StringValue>(TargetVariableParameterName, new ItemSet<StringValue>(variables), variables.Where(x => x.Value == targetVariable).First()));
165      if (variableRanges == null) {
166        variableRanges = Dataset.GetVariableRanges();
167      }
168      Parameters.Add(new FixedValueParameter<IntervalCollection>(VariableRangesParameterName, variableRanges));
169    }
170    private void RegisterParameterEvents() {
171      TargetVariableParameter.ValueChanged += new EventHandler(Parameter_ValueChanged);
172      // VariableRanges are fixed parameters
173    }
174    private void Parameter_ValueChanged(object sender, EventArgs e) {
175      OnChanged();
176    }
177  }
178}
Note: See TracBrowser for help on using the repository browser.