blob: 415630874c7bce9f128d36a2380ed1df3e8d8cfc (
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
|
package de.lmu.ifi.dbs.elki.visualization.opticsplot;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2011
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.List;
import de.lmu.ifi.dbs.elki.data.Cluster;
import de.lmu.ifi.dbs.elki.data.Clustering;
import de.lmu.ifi.dbs.elki.data.model.ClusterModel;
import de.lmu.ifi.dbs.elki.data.model.Model;
import de.lmu.ifi.dbs.elki.database.ids.DBIDUtil;
import de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs;
import de.lmu.ifi.dbs.elki.distance.distancevalue.Distance;
import de.lmu.ifi.dbs.elki.result.optics.ClusterOrderEntry;
import de.lmu.ifi.dbs.elki.result.optics.ClusterOrderResult;
/**
* Compute a partitioning from an OPTICS plot by doing a horizontal cut.
*
* @author Heidi Kolb
* @author Erich Schubert
*
* @apiviz.uses ClusterOrderResult
* @apiviz.uses OPTICSDistanceAdapter
*/
// TODO: add non-flat clusterings
public class OPTICSCut {
/**
* Compute an OPTICS cut clustering
*
* @param <D> Distance type
* @param co Cluster order result
* @param adapter Distance adapter
* @param epsilon Epsilon value for cut
* @return New partitioning clustering
*/
public static <D extends Distance<D>> Clustering<Model> makeOPTICSCut(ClusterOrderResult<D> co, OPTICSDistanceAdapter<D> adapter, double epsilon) {
List<ClusterOrderEntry<D>> order = co.getClusterOrder();
// Clustering model we are building
Clustering<Model> clustering = new Clustering<Model>("OPTICS Cut Clustering", "optics-cut");
// Collects noise elements
ModifiableDBIDs noise = DBIDUtil.newHashSet();
double lastDist = Double.MAX_VALUE;
double actDist = Double.MAX_VALUE;
// Current working set
ModifiableDBIDs current = DBIDUtil.newHashSet();
// TODO: can we implement this more nicely with a 1-lookahead?
for(int j = 0; j < order.size(); j++) {
lastDist = actDist;
actDist = adapter.getDoubleForEntry(order.get(j));
if(actDist <= epsilon) {
// the last element before the plot drops belongs to the cluster
if(lastDist > epsilon && j > 0) {
// So un-noise it
noise.remove(order.get(j - 1).getID());
// Add it to the cluster
current.add(order.get(j - 1).getID());
}
current.add(order.get(j).getID());
}
else {
// 'Finish' the previous cluster
if(!current.isEmpty()) {
// TODO: do we want a minpts restriction?
// But we get have only core points guaranteed anyway.
clustering.addCluster(new Cluster<Model>(current, ClusterModel.CLUSTER));
current = DBIDUtil.newHashSet();
}
// Add to noise
noise.add(order.get(j).getID());
}
}
// Any unfinished cluster will also be added
if(!current.isEmpty()) {
clustering.addCluster(new Cluster<Model>(current, ClusterModel.CLUSTER));
}
// Add noise
clustering.addCluster(new Cluster<Model>(noise, true, ClusterModel.CLUSTER));
return clustering;
}
}
|