Free cookie consent management tool by TermsFeed Policy Generator

source: branches/3.0/sources/HeuristicLab.DataAnalysis/Dataset.cs @ 17131

Last change on this file since 17131 was 345, checked in by gkronber, 16 years ago
  • merged r338 r341 and r343 from the ticket-specific trunk into the HL3.0 stable branch
  • fixed serialization and display of floating point numbers in HL3.0 stable plugins HeuristicLab.Functions and HeuristicLab.DataAnalysis

(ticket #175)

File size: 8.1 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2008 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.Xml;
25using HeuristicLab.Core;
26using HeuristicLab.Data;
27using System.Globalization;
28using System.Text;
29
30namespace HeuristicLab.DataAnalysis {
31  public class Dataset : ItemBase {
32
33    private string name;
34    public string Name {
35      get { return name; }
36      set { name = value; }
37    }
38
39    private double[] samples;
40    private int rows;
41    Dictionary<int, Dictionary<int, double>>[] cachedMeans;
42    Dictionary<int, Dictionary<int, double>>[] cachedRanges;
43
44    public int Rows {
45      get { return rows; }
46      set { rows = value; }
47    }
48    private int columns;
49
50    public int Columns {
51      get { return columns; }
52      set { columns = value; }
53    }
54
55    public double GetValue(int i, int j) {
56      return samples[columns * i + j];
57    }
58
59    public void SetValue(int i, int j, double v) {
60      if(v != samples[columns * i + j]) {
61        samples[columns * i + j] = v;
62        FireChanged();
63      }
64    }
65
66    public double[] Samples {
67      get { return samples; }
68      set {
69        samples = value;
70        CreateDictionaries();
71        FireChanged();
72      }
73    }
74
75    private string[] variableNames;
76    public string[] VariableNames {
77      get { return variableNames; }
78      set { variableNames = value; }
79    }
80
81    public Dataset() {
82      Name = "-";
83      VariableNames = new string[] { "Var0" };
84      Columns = 1;
85      Rows = 1;
86      Samples = new double[1];
87    }
88
89    void samples_Changed(object sender, EventArgs e) {
90      CreateDictionaries();
91    }
92
93    private void CreateDictionaries() {
94      // keep a means and ranges dictionary for each column (possible target variable) of the dataset.
95
96      cachedMeans = new Dictionary<int, Dictionary<int, double>>[columns];
97      cachedRanges = new Dictionary<int, Dictionary<int, double>>[columns];
98
99      for(int i = 0; i < columns; i++) {
100        cachedMeans[i] = new Dictionary<int, Dictionary<int, double>>();
101        cachedRanges[i] = new Dictionary<int, Dictionary<int, double>>();
102      }
103    }
104
105    public override IView CreateView() {
106      return new DatasetView(this);
107    }
108
109    public override object Clone(IDictionary<Guid, object> clonedObjects) {
110      Dataset clone = new Dataset();
111      clonedObjects.Add(Guid, clone);
112      double[] cloneSamples = new double[rows * columns];
113      Array.Copy(samples, cloneSamples, samples.Length);
114      clone.rows = rows;
115      clone.columns = columns;
116      clone.Samples = cloneSamples;
117      clone.Name = Name;
118      clone.VariableNames = new string[VariableNames.Length];
119      Array.Copy(VariableNames, clone.VariableNames, VariableNames.Length);
120      return clone;
121    }
122
123    public override XmlNode GetXmlNode(string name, XmlDocument document, IDictionary<Guid, IStorable> persistedObjects) {
124      XmlNode node = base.GetXmlNode(name, document, persistedObjects);
125      XmlAttribute problemName = document.CreateAttribute("Name");
126      problemName.Value = Name;
127      node.Attributes.Append(problemName);
128      XmlAttribute dim1 = document.CreateAttribute("Dimension1");
129      dim1.Value = rows.ToString(CultureInfo.InvariantCulture.NumberFormat);
130      node.Attributes.Append(dim1);
131      XmlAttribute dim2 = document.CreateAttribute("Dimension2");
132      dim2.Value = columns.ToString(CultureInfo.InvariantCulture.NumberFormat);
133      node.Attributes.Append(dim2);
134
135      XmlAttribute variableNames = document.CreateAttribute("VariableNames");
136      variableNames.Value = GetVariableNamesString();
137      node.Attributes.Append(variableNames);
138
139      node.InnerText = ToString(CultureInfo.InvariantCulture.NumberFormat);
140      return node;
141    }
142
143    public override void Populate(XmlNode node, IDictionary<Guid, IStorable> restoredObjects) {
144      base.Populate(node, restoredObjects);
145      Name = node.Attributes["Name"].Value;
146      rows = int.Parse(node.Attributes["Dimension1"].Value, CultureInfo.InvariantCulture.NumberFormat);
147      columns = int.Parse(node.Attributes["Dimension2"].Value, CultureInfo.InvariantCulture.NumberFormat);
148
149      VariableNames = ParseVariableNamesString(node.Attributes["VariableNames"].Value);
150
151      string[] tokens = node.InnerText.Split(';');
152      if(tokens.Length != rows * columns) throw new FormatException();
153      samples = new double[rows * columns];
154      for(int row = 0; row < rows; row++) {
155        for(int column = 0; column < columns; column++) {
156          if(double.TryParse(tokens[row * columns + column], NumberStyles.Float, CultureInfo.InvariantCulture.NumberFormat, out samples[row * columns + column]) == false) {
157            throw new FormatException("Can't parse " + tokens[row * columns + column] + " as double value.");
158          }
159        }
160      }
161      CreateDictionaries();
162    }
163
164    public override string ToString() {
165      return ToString(CultureInfo.CurrentCulture.NumberFormat);
166    }
167
168    private string ToString(NumberFormatInfo format) {
169      StringBuilder builder = new StringBuilder();
170      for(int row = 0; row < rows; row++) {
171        for(int column = 0; column < columns; column++) {
172          builder.Append(";");
173          builder.Append(samples[row * columns + column].ToString("r",format));
174        }
175      }
176      if(builder.Length > 0) builder.Remove(0, 1);
177      return builder.ToString();
178    }
179
180    private string GetVariableNamesString() {
181      string s = "";
182      for(int i = 0; i < variableNames.Length; i++) {
183        s += variableNames[i] + "; ";
184      }
185
186      if(variableNames.Length > 0) {
187        s = s.TrimEnd(';', ' ');
188      }
189      return s;
190    }
191
192    private string[] ParseVariableNamesString(string p) {
193      p = p.Trim();
194      string[] tokens = p.Split(new char[] { ';' }, StringSplitOptions.RemoveEmptyEntries);
195      return tokens;
196    }
197
198    public double GetMean(int column) {
199      return GetMean(column, 0, Rows - 1);
200    }
201
202    public double GetMean(int column, int from, int to) {
203      if(!cachedMeans[column].ContainsKey(from) || !cachedMeans[column][from].ContainsKey(to)) {
204        double[] values = new double[to - from + 1];
205        for(int sample = from; sample <= to; sample++) {
206          values[sample - from] = GetValue(sample, column);
207        }
208        double mean = Statistics.Mean(values);
209        if(!cachedMeans[column].ContainsKey(from)) cachedMeans[column][from] = new Dictionary<int, double>();
210        cachedMeans[column][from][to] = mean;
211        return mean;
212      } else {
213        return cachedMeans[column][from][to];
214      }
215    }
216
217    public double GetRange(int column) {
218      return GetRange(column, 0, Rows - 1);
219    }
220
221    public double GetRange(int column, int from, int to) {
222      if(!cachedRanges[column].ContainsKey(from) || !cachedRanges[column][from].ContainsKey(to)) {
223        double[] values = new double[to - from + 1];
224        for(int sample = from; sample <= to; sample++) {
225          values[sample - from] = GetValue(sample, column);
226        }
227        double range = Statistics.Range(values);
228        if(!cachedRanges[column].ContainsKey(from)) cachedRanges[column][from] = new Dictionary<int, double>();
229        cachedRanges[column][from][to] = range;
230        return range;
231      } else {
232        return cachedRanges[column][from][to];
233      }
234    }
235  }
236}
Note: See TracBrowser for help on using the repository browser.