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
|
package de.lmu.ifi.dbs.elki.utilities.datastructures.heap;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2012
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.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import de.lmu.ifi.dbs.elki.database.ids.DBID;
import de.lmu.ifi.dbs.elki.database.query.DistanceResultPair;
import de.lmu.ifi.dbs.elki.database.query.GenericDistanceResultPair;
import de.lmu.ifi.dbs.elki.distance.distancevalue.Distance;
/**
* Heap used for KNN management.
*
* @author Erich Schubert
*
* @apiviz.has KNNList oneway - - serializes to
*
* @param <D> distance type
*/
public class KNNHeap<D extends Distance<D>> extends TiedTopBoundedHeap<DistanceResultPair<D>> {
/**
* Serial version
*/
private static final long serialVersionUID = 1L;
/**
* Maximum distance, usually infiniteDistance
*/
private final D maxdist;
/**
* Constructor.
*
* @param k k Parameter
* @param maxdist k-distance to return for less than k neighbors - usually
* infiniteDistance
*/
public KNNHeap(int k, D maxdist) {
super(k, new Comp<D>());
this.maxdist = maxdist;
}
/**
* Simplified constructor. Will return {@code null} as kNN distance with less
* than k entries.
*
* @param k k Parameter
*/
public KNNHeap(int k) {
this(k, null);
}
@Override
public ArrayList<DistanceResultPair<D>> toSortedArrayList() {
ArrayList<DistanceResultPair<D>> list = super.toSortedArrayList();
Collections.reverse(list);
return list;
}
/**
* Serialize to a {@link KNNList}. This empties the heap!
*
* @return KNNList with the heaps contents.
*/
public KNNList<D> toKNNList() {
return new KNNList<D>(this);
}
/**
* Get the K parameter ("maxsize" internally).
*
* @return K
*/
public int getK() {
return super.getMaxSize();
}
/**
* Get the distance to the k nearest neighbor, or maxdist otherwise.
*
* @return Maximum distance
*/
public D getKNNDistance() {
if(size() < getK()) {
return maxdist;
}
return peek().getDistance();
}
/**
* Get maximum distance in heap
*/
public D getMaximumDistance() {
if(isEmpty()) {
return maxdist;
}
return peek().getDistance();
}
/**
* Add a distance-id pair to the heap unless the distance is too large.
*
* Compared to the super.add() method, this often saves the pair construction.
*
* @param distance Distance value
* @param id ID number
* @return success code
*/
public boolean add(D distance, DBID id) {
if(size() < maxsize || peek().getDistance().compareTo(distance) >= 0) {
return super.add(new GenericDistanceResultPair<D>(distance, id));
}
return true; /* "success" */
}
/**
* Comparator to use.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Comp<D extends Distance<D>> implements Comparator<DistanceResultPair<D>> {
@Override
public int compare(DistanceResultPair<D> o1, DistanceResultPair<D> o2) {
return -o1.compareByDistance(o2);
}
}
}
|