source: trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs @ 7134

Last change on this file since 7134 was 7134, checked in by mkommend, 10 years ago

#1698: Implemented IStorableContent in all ProblemDatas.

File size: 6.6 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2011 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.IO;
25using System.Linq;
26using HeuristicLab.Common;
27using HeuristicLab.Core;
28using HeuristicLab.Data;
29using HeuristicLab.Parameters;
30using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
31
32namespace HeuristicLab.Problems.DataAnalysis {
33  [StorableClass]
34  [Item("RegressionProblemData", "Represents an item containing all data defining a regression problem.")]
35  public class RegressionProblemData : DataAnalysisProblemData, IRegressionProblemData, IStorableContent {
36    protected const string TargetVariableParameterName = "TargetVariable";
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^1";
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      emptyProblemData = problemData;
95    }
96    #endregion
97
98    public ConstrainedValueParameter<StringValue> TargetVariableParameter {
99      get { return (ConstrainedValueParameter<StringValue>)Parameters[TargetVariableParameterName]; }
100    }
101    public string TargetVariable {
102      get { return TargetVariableParameter.Value.Value; }
103    }
104
105    [StorableConstructor]
106    protected RegressionProblemData(bool deserializing) : base(deserializing) { }
107    [StorableHook(HookType.AfterDeserialization)]
108    private void AfterDeserialization() {
109      RegisterParameterEvents();
110    }
111
112    protected RegressionProblemData(RegressionProblemData original, Cloner cloner)
113      : base(original, cloner) {
114      RegisterParameterEvents();
115    }
116    public override IDeepCloneable Clone(Cloner cloner) {
117      if (this == emptyProblemData) return emptyProblemData;
118      return new RegressionProblemData(this, cloner);
119    }
120
121    public RegressionProblemData()
122      : this(defaultDataset, defaultAllowedInputVariables, defaultTargetVariable) {
123    }
124
125    public RegressionProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable)
126      : base(dataset, allowedInputVariables) {
127      var variables = InputVariables.Select(x => x.AsReadOnly()).ToList();
128      Parameters.Add(new ConstrainedValueParameter<StringValue>(TargetVariableParameterName, new ItemSet<StringValue>(variables), variables.Where(x => x.Value == targetVariable).First()));
129      RegisterParameterEvents();
130    }
131
132    private void RegisterParameterEvents() {
133      TargetVariableParameter.ValueChanged += new EventHandler(TargetVariableParameter_ValueChanged);
134    }
135    private void TargetVariableParameter_ValueChanged(object sender, EventArgs e) {
136      OnChanged();
137    }
138
139    #region Import from file
140    public static RegressionProblemData ImportFromFile(string fileName) {
141      TableFileParser csvFileParser = new TableFileParser();
142      csvFileParser.Parse(fileName);
143
144      Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
145      dataset.Name = Path.GetFileName(fileName);
146
147      RegressionProblemData problemData = new RegressionProblemData(dataset, dataset.DoubleVariables.Skip(1), dataset.DoubleVariables.First());
148      problemData.Name = "Data imported from " + Path.GetFileName(fileName);
149      return problemData;
150    }
151    #endregion
152  }
153}
Note: See TracBrowser for help on using the repository browser.