1CLUSTER(1)                  General Commands Manual                 CLUSTER(1)
2
3
4

NAME

6       cluster  -  find  clusters  in  a graph and augment the graph with this
7       information.
8

SYNOPSIS

10       cluster [-v?]  [ -Ck ] [ -ck ] [ -o outfile ] [ files ]
11

DESCRIPTION

13       cluster takes as input a graph in DOT format, finds node  clusters  and
14       augments  the  graph with this information.  The clusters are specified
15       by the "cluster" attribute attached to nodes; cluster values  are  non-
16       negative  integers.  cluster attempts to maximize the modularity of the
17       clustering.  If the edge attribute "weight" is defined,  this  will  be
18       used in computing the clustering.
19

OPTIONS

21       The following options are supported:
22
23       -Ck    specifies  a  targeted  number of clusters that should be gener‐
24              ated.  The specified number k is only a suggestion and  may  not
25              be  realisable.   If k == 0, the default, the number of clusters
26              that approximately optimizes the modularity is returned.
27
28       -ck    specifies clustering method.  If k == 0, the default, the  modu‐
29              larity will be used. If k == 1 modularity quality will be used.
30
31       -ooutfile
32              Specifies  that  output  should  go  into  the  file outfile. By
33              default, stdout is used.
34
35       -v     Verbose mode.
36

EXAMPLES

38       Applying cluster to the following graph,
39
40          graph {
41              1--2 [weight=10.]
42              2--3 [weight=1]
43              3--4 [weight=10.]
44              4--5 [weight=10]
45              5--6 [weight=10]
46              3--6 [weight=0.1]
47              4--6 [weight=10.]
48             }
49
50       gives
51
52          graph {
53                node [cluster="-1"];
54                1 [cluster=1];
55                2 [cluster=1];
56                3 [cluster=2];
57                4 [cluster=2];
58                5 [cluster=2];
59                6 [cluster=2];
60                1 -- 2 [weight="10."];
61                2 -- 3 [weight=1];
62                3 -- 4 [weight="10."];
63                4 -- 5 [weight=10];
64                5 -- 6 [weight=10];
65                3 -- 6 [weight="0.1"];
66                4 -- 6 [weight="10."];
67          }
68
69
70

AUTHOR

72       Yifan Hu <yifanhu@research.att.com>
73

SEE ALSO

75       gvmap(1)
76
77       Blondel, V.D., Guillaume,  J.L.,  Lambiotte,  R.,  Lefebvre,  E.:  Fast
78       unfolding  of  communities  in  large  networks. Journal of Statistical
79       Mechanics: Theory and Experiment (2008), P10008.
80
81
82
83                                 3 March 2011                       CLUSTER(1)
Impressum