source: trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisProblemData.cs @ 11156

Last change on this file since 11156 was 11156, checked in by gkronber, 8 years ago

#2206: made several changes / improvements to the data-preprocessing code while reviewing the code

File size: 9.7 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2013 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.Text;
26using HeuristicLab.Collections;
27using HeuristicLab.Common;
28using HeuristicLab.Core;
29using HeuristicLab.Data;
30using HeuristicLab.Parameters;
31using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
32
33namespace HeuristicLab.Problems.DataAnalysis {
34  [StorableClass]
35  public abstract class DataAnalysisProblemData : ParameterizedNamedItem, IDataAnalysisProblemData {
36    protected const string DatasetParameterName = "Dataset";
37    protected const string InputVariablesParameterName = "InputVariables";
38    protected const string TrainingPartitionParameterName = "TrainingPartition";
39    protected const string TestPartitionParameterName = "TestPartition";
40    protected const string TransformationsParameterName = "Transformations";
41
42    #region parameter properites
43    public IFixedValueParameter<Dataset> DatasetParameter {
44      get { return (IFixedValueParameter<Dataset>)Parameters[DatasetParameterName]; }
45    }
46    public IFixedValueParameter<ReadOnlyCheckedItemList<StringValue>> InputVariablesParameter {
47      get { return (IFixedValueParameter<ReadOnlyCheckedItemList<StringValue>>)Parameters[InputVariablesParameterName]; }
48    }
49    public IFixedValueParameter<IntRange> TrainingPartitionParameter {
50      get { return (IFixedValueParameter<IntRange>)Parameters[TrainingPartitionParameterName]; }
51    }
52    public IFixedValueParameter<IntRange> TestPartitionParameter {
53      get { return (IFixedValueParameter<IntRange>)Parameters[TestPartitionParameterName]; }
54    }
55    public IFixedValueParameter<ReadOnlyItemList<ITransformation>> TransformationsParameter {
56      get { return (IFixedValueParameter<ReadOnlyItemList<ITransformation>>)Parameters[TransformationsParameterName]; }
57    }
58    #endregion
59
60    #region properties
61    protected bool isEmpty = false;
62    public bool IsEmpty {
63      get { return isEmpty; }
64    }
65    public Dataset Dataset {
66      get { return DatasetParameter.Value; }
67    }
68    public ICheckedItemList<StringValue> InputVariables {
69      get { return InputVariablesParameter.Value; }
70    }
71    public IEnumerable<string> AllowedInputVariables {
72      get { return InputVariables.CheckedItems.Select(x => x.Value.Value); }
73    }
74
75    public IntRange TrainingPartition {
76      get { return TrainingPartitionParameter.Value; }
77    }
78    public IntRange TestPartition {
79      get { return TestPartitionParameter.Value; }
80    }
81
82    public virtual IEnumerable<int> TrainingIndices {
83      get {
84        return Enumerable.Range(TrainingPartition.Start, Math.Max(0, TrainingPartition.End - TrainingPartition.Start))
85                         .Where(IsTrainingSample);
86      }
87    }
88    public virtual IEnumerable<int> TestIndices {
89      get {
90        return Enumerable.Range(TestPartition.Start, Math.Max(0, TestPartition.End - TestPartition.Start))
91           .Where(IsTestSample);
92      }
93    }
94
95    public IEnumerable<ITransformation> Transformations {
96      get { return TransformationsParameter.Value; }
97    }
98
99    public virtual bool IsTrainingSample(int index) {
100      return index >= 0 && index < Dataset.Rows &&
101        TrainingPartition.Start <= index && index < TrainingPartition.End &&
102        (index < TestPartition.Start || TestPartition.End <= index);
103    }
104
105    public virtual bool IsTestSample(int index) {
106      return index >= 0 && index < Dataset.Rows &&
107             TestPartition.Start <= index && index < TestPartition.End;
108    }
109    #endregion
110
111    protected DataAnalysisProblemData(DataAnalysisProblemData original, Cloner cloner)
112      : base(original, cloner) {
113      isEmpty = original.isEmpty;
114      RegisterEventHandlers();
115    }
116    [StorableConstructor]
117    protected DataAnalysisProblemData(bool deserializing) : base(deserializing) { }
118
119    [StorableHook(HookType.AfterDeserialization)]
120    private void AfterDeserialization() {
121      if (!Parameters.ContainsKey(TransformationsParameterName)) {
122        Parameters.Add(new FixedValueParameter<ReadOnlyItemList<ITransformation>>(TransformationsParameterName, "", new ItemList<ITransformation>().AsReadOnly()));
123        TransformationsParameter.Hidden = true;
124      }
125      RegisterEventHandlers();
126    }
127
128    protected DataAnalysisProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<ITransformation> transformations = null) {
129      if (dataset == null) throw new ArgumentNullException("The dataset must not be null.");
130      if (allowedInputVariables == null) throw new ArgumentNullException("The allowedInputVariables must not be null.");
131
132      if (allowedInputVariables.Except(dataset.DoubleVariables).Any())
133        throw new ArgumentException("All allowed input variables must be present in the dataset and of type double.");
134
135      var inputVariables = new CheckedItemList<StringValue>(dataset.DoubleVariables.Select(x => new StringValue(x)));
136      foreach (StringValue x in inputVariables)
137        inputVariables.SetItemCheckedState(x, allowedInputVariables.Contains(x.Value));
138
139      int trainingPartitionStart = 0;
140      int trainingPartitionEnd = dataset.Rows / 2;
141      int testPartitionStart = dataset.Rows / 2;
142      int testPartitionEnd = dataset.Rows;
143
144      var transformationsList = new ItemList<ITransformation>(transformations ?? Enumerable.Empty<ITransformation>());
145
146      Parameters.Add(new FixedValueParameter<Dataset>(DatasetParameterName, "", dataset));
147      Parameters.Add(new FixedValueParameter<ReadOnlyCheckedItemList<StringValue>>(InputVariablesParameterName, "", inputVariables.AsReadOnly()));
148      Parameters.Add(new FixedValueParameter<IntRange>(TrainingPartitionParameterName, "", new IntRange(trainingPartitionStart, trainingPartitionEnd)));
149      Parameters.Add(new FixedValueParameter<IntRange>(TestPartitionParameterName, "", new IntRange(testPartitionStart, testPartitionEnd)));
150      Parameters.Add(new FixedValueParameter<ReadOnlyItemList<ITransformation>>(TransformationsParameterName, "", transformationsList.AsReadOnly()));
151
152      TransformationsParameter.Hidden = true;
153
154      ((ValueParameter<Dataset>)DatasetParameter).ReactOnValueToStringChangedAndValueItemImageChanged = false;
155      RegisterEventHandlers();
156    }
157
158    private void RegisterEventHandlers() {
159      DatasetParameter.ValueChanged += new EventHandler(Parameter_ValueChanged);
160      InputVariables.CheckedItemsChanged += new CollectionItemsChangedEventHandler<IndexedItem<StringValue>>(InputVariables_CheckedItemsChanged);
161      TrainingPartition.ValueChanged += new EventHandler(Parameter_ValueChanged);
162      TestPartition.ValueChanged += new EventHandler(Parameter_ValueChanged);
163      TransformationsParameter.ValueChanged += new EventHandler(Parameter_ValueChanged);
164    }
165
166    private void InputVariables_CheckedItemsChanged(object sender, CollectionItemsChangedEventArgs<IndexedItem<StringValue>> e) {
167      OnChanged();
168    }
169
170    private void Parameter_ValueChanged(object sender, EventArgs e) {
171      OnChanged();
172    }
173
174    public event EventHandler Changed;
175    protected virtual void OnChanged() {
176      var listeners = Changed;
177      if (listeners != null) listeners(this, EventArgs.Empty);
178    }
179
180    protected virtual bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
181      errorMessage = string.Empty;
182      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
183
184      //check allowed input variables
185      StringBuilder message = new StringBuilder();
186      var variables = new HashSet<string>(problemData.InputVariables.Select(x => x.Value));
187      foreach (var item in AllowedInputVariables) {
188        if (!variables.Contains(item))
189          message.AppendLine("Input variable '" + item + "' is not present in the new problem data.");
190      }
191
192      if (message.Length != 0) {
193        errorMessage = message.ToString();
194        return false;
195      }
196      return true;
197
198    }
199
200    public virtual void AdjustProblemDataProperties(IDataAnalysisProblemData problemData) {
201      DataAnalysisProblemData data = problemData as DataAnalysisProblemData;
202      if (data == null) throw new ArgumentException("The problem data is not a data analysis problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
203
204      string errorMessage;
205      if (!data.IsProblemDataCompatible(this, out errorMessage)) {
206        throw new InvalidOperationException(errorMessage);
207      }
208
209      foreach (var inputVariable in InputVariables) {
210        var variable = data.InputVariables.FirstOrDefault(i => i.Value == inputVariable.Value);
211        InputVariables.SetItemCheckedState(inputVariable, variable != null && data.InputVariables.ItemChecked(variable));
212      }
213
214      TrainingPartition.Start = TrainingPartition.End = 0;
215      TestPartition.Start = 0;
216      TestPartition.End = Dataset.Rows;
217    }
218  }
219}
Note: See TracBrowser for help on using the repository browser.