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
|
package de.lmu.ifi.dbs.elki.index.vafile;
/*
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 java.util.Arrays;
import de.lmu.ifi.dbs.elki.data.NumberVector;
import de.lmu.ifi.dbs.elki.database.ids.DBIDIter;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.utilities.documentation.Reference;
import de.lmu.ifi.dbs.elki.utilities.io.ByteArrayUtil;
/**
* Dimension approximation file, a one-dimensional part of the
* {@link PartialVAFile}.
*
* Reference:
* <p>
* Hans-Peter Kriegel, Peer Kröger, Matthias Schubert, Ziyue Zhu:<br />
* Efficient Query Processing in Arbitrary Subspaces Using Vector Approximations
* <br />
* in Proc. 18th Int. Conf. on Scientific and Statistical Database Management
* (SSDBM 06), Wien, Austria, 2006.
* </p>
*
* @author Thomas Bernecker
* @author Erich Schubert
* @since 0.5.0
*/
@Reference(authors = "Hans-Peter Kriegel, Peer Kröger, Matthias Schubert, Ziyue Zhu", title = "Efficient Query Processing in Arbitrary Subspaces Using Vector Approximations", booktitle = "Proc. 18th Int. Conf. on Scientific and Statistical Database Management (SSDBM 06), Wien, Austria, 2006", url = "http://dx.doi.org/10.1109/SSDBM.2006.23")
public class DAFile {
/**
* Dimension of this approximation file.
*/
private final int dimension;
/**
* Splitting grid.
*/
private final double[] splitPositions;
/**
* Constructor.
*
* @param relation Relation to index
* @param dimension Dimension of this file
* @param partitions Number of partitions
*/
public DAFile(Relation<? extends NumberVector> relation, int dimension, int partitions) {
final int size = relation.size();
this.dimension = dimension;
this.splitPositions = new double[partitions + 1];
double[] tempdata = new double[size];
int j = 0;
for(DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
tempdata[j] = relation.get(iditer).doubleValue(dimension);
j += 1;
}
Arrays.sort(tempdata);
for(int b = 0; b < partitions; b++) {
int start = (int) (b * size / (double) partitions);
splitPositions[b] = tempdata[start];
}
// make sure that last object will be included
splitPositions[partitions] = tempdata[size - 1] + 0.000001;
}
/**
* Return the split positions.
*
* @return the split positions
*/
public double[] getSplitPositions() {
return splitPositions;
}
/**
* Return the dimension we indexed.
*
* @return the dimension
*/
public int getDimension() {
return dimension;
}
/**
* Estimate the IO costs for this index.
*
* @return IO costs
*/
public int getIOCosts() {
return splitPositions.length * ByteArrayUtil.SIZE_DOUBLE + 4;
}
}
|
