summaryrefslogtreecommitdiff
path: root/elki/src/main/java/de/lmu/ifi/dbs/elki/algorithm/statistics/AddSingleScale.java
blob: 9e15127e18b6d8301d01bd261d30d95a13ab4297 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
package de.lmu.ifi.dbs.elki.algorithm.statistics;

/*
 This file is part of ELKI:
 Environment for Developing KDD-Applications Supported by Index-Structures

 Copyright (C) 2015
 Ludwig-Maximilians-Universität München
 Lehr- und Forschungseinheit für Datenbanksysteme
 ELKI Development Team

 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU Affero General Public License as published by
 the Free Software Foundation, either version 3 of the License, or
 (at your option) any later version.

 This program is distributed in the hope that it will be useful,
 but WITHOUT ANY WARRANTY; without even the implied warranty of
 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 GNU Affero General Public License for more details.

 You should have received a copy of the GNU Affero General Public License
 along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
import de.lmu.ifi.dbs.elki.algorithm.Algorithm;
import de.lmu.ifi.dbs.elki.data.NumberVector;
import de.lmu.ifi.dbs.elki.data.type.TypeInformation;
import de.lmu.ifi.dbs.elki.data.type.TypeUtil;
import de.lmu.ifi.dbs.elki.database.Database;
import de.lmu.ifi.dbs.elki.database.ids.DBIDIter;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.database.relation.RelationUtil;
import de.lmu.ifi.dbs.elki.math.DoubleMinMax;
import de.lmu.ifi.dbs.elki.math.scales.LinearScale;
import de.lmu.ifi.dbs.elki.result.Result;
import de.lmu.ifi.dbs.elki.result.ResultUtil;
import de.lmu.ifi.dbs.elki.result.ScalesResult;
import de.lmu.ifi.dbs.elki.utilities.documentation.Description;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.OptionID;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.constraints.ListSizeConstraint;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.DoubleListParameter;

/**
 * Pseudo "algorithm" that computes the global min/max for a relation across all
 * attributes.
 *
 * FIXME: this should become part of relation metadata.
 *
 * @author Erich Schubert
 * @since 0.5.0
 */
@Description("Setup a scaling so that all dimensions are scaled equally in visualization.")
public class AddSingleScale implements Algorithm {
  /**
   * Minimum and maximum to use.
   */
  double[] minmax = null;

  /**
   * Constructor.
   *
   * @param minmax Minimum and maximum values
   */
  public AddSingleScale(double[] minmax) {
    super();
    this.minmax = minmax;
  }

  @SuppressWarnings("unchecked")
  @Override
  public Result run(Database database) {
    for(Relation<?> rel : database.getRelations()) {
      if(TypeUtil.NUMBER_VECTOR_FIELD.isAssignableFromType(rel.getDataTypeInformation())) {
        ScalesResult res = run((Relation<? extends NumberVector>) rel);
        ResultUtil.addChildResult(rel, res);
      }
    }
    return null;
  }

  /**
   * Add scales to a single vector relation.
   *
   * @param rel Relation
   * @return Scales
   */
  private ScalesResult run(Relation<? extends NumberVector> rel) {
    final int dim = RelationUtil.dimensionality(rel);
    LinearScale[] scales = new LinearScale[dim];
    if(minmax == null) {
      DoubleMinMax mm = new DoubleMinMax();
      for(DBIDIter iditer = rel.iterDBIDs(); iditer.valid(); iditer.advance()) {
        NumberVector vec = rel.get(iditer);
        for(int d = 0; d < dim; d++) {
          final double val = vec.doubleValue(d);
          if(val != val) {
            continue; // NaN
          }
          mm.put(val);
        }
      }
      LinearScale scale = new LinearScale(mm.getMin(), mm.getMax());
      for(int i = 0; i < dim; i++) {
        scales[i] = scale;
      }
    }
    else {
      // Use predefined.
      LinearScale scale = new LinearScale(minmax[0], minmax[1]);
      for(int i = 0; i < dim; i++) {
        scales[i] = scale;
      }
    }
    ScalesResult res = new ScalesResult(scales);
    return res;
  }

  @Override
  public TypeInformation[] getInputTypeRestriction() {
    return TypeUtil.array(TypeUtil.NUMBER_VECTOR_FIELD);
  }

  /**
   * Parameterization class.
   *
   * @author Erich Schubert
   *
   * @apiviz.exclude
   */
  public static class Parameterizer extends AbstractParameterizer {
    /**
     * Minimum and maximum values.
     */
    public static final OptionID MINMAX_ID = new OptionID("scales.minmax", "Forcibly set the scales to the given range.");

    /**
     * Minimum and maximum to use.
     */
    double[] minmax = null;

    @Override
    protected void makeOptions(Parameterization config) {
      super.makeOptions(config);
      DoubleListParameter minmaxP = new DoubleListParameter(MINMAX_ID) //
      .setOptional(true) //
      .addConstraint(new ListSizeConstraint(2));
      if(config.grab(minmaxP)) {
        minmax = minmaxP.getValue().clone();
      }
    }

    @Override
    protected AddSingleScale makeInstance() {
      return new AddSingleScale(minmax);
    }
  }
}