Debian Codegraph @

doc/clmresidue.azm

raw ◀ ▶
Source reconstructed at patch state 0 of 1 — not the installed (fully patched) source.
1 Debian patch touch this file
1 \import{mcx.zmm}
2
3 \begin{pud::man}{
4
5 {name}{clm residue}
6 {html_title}{The clm residue manual}
7 {author}{Stijn van Dongen}
8 {section}{1}
9 {synstyle}{long}
10 {defstyle}{long}
11
12 \man_share
13 }
14
15 \${html}{\"pud::man::maketoc"}
16
17 \sec{name}{NAME}
18 \NAME{clm residue}{extend clustering of subgraph to clustering of graph.}
19
20 \disclaim_clm{residue}
21
22 \sec{synopsis}{SYNOPSIS}
23 \par{
24 \clm{residue}
25 \synreqopt{-icl}{fname}{input clustering}
26 \synreqopt{-imx}{fname}{input graph}
27 \synoptopt{-rpm}{fname}{residue projection matrix}
28 \synoptopt{-o}{fname}{output clustering file}
29 }
30
31 \sec{description}{DESCRIPTION}
32
33 \par{
34 The cluster file presumably contains a clustering of a subgraph of the
35 graph\~\v{G} contained by the matrix file, implying that the row domain of
36 that clustering is a subset of the node domain of the graph. \clm{residue} will
37 compute a simple upwards projection of that clustering, resulting in a
38 clustering of\~\v{G}.
39 }
40
41 \sec{options}{OPTIONS}
42
43 \begin{itemize}{\mcx_itemopts}
44
45 \item{\defopt{-imx}{fname}{input graph}}
46 \item{\defopt{-icl}{fname}{input clustering}}
47
48 \item{\defopt{-rpm}{fname}{residue projection matrix}}
49 \car{
50 The name for the file in which the residue projection matrix is stored.
51 It contains for each node and for each cluster in the input clustering
52 the combined weight of the (edges to the) neighbours of that node
53 in that cluster.
54 }
55
56 \car{
57 The default output file name is \v{out.rpm}.
58 }
59
60 \item{\defopt{-o}{fname}{output clustering file}}
61 \car{
62 The name for the file in which the majority vote projection clustering
63 is stored. Aka the majority vote projection clustering storage file name.
64 }
65
66 \par{
67 This embodies a very crude approach to distributing the missing nodes in the
68 input clustering onto that same cluster. For each node, the cluster is
69 taken for which the residue projection is the largest (see above). The
70 residue (i.e. the set of missing nodes) is initially viewed as a cluster;
71 the set of nodes for which the projection is largest for the residue itself
72 will form a new cluster, if it is not empty.
73 }
74
75 \par{
76 By default output is sent to STDOUT.
77 }
78
79 \end{itemize}
80
81 \sec{author}{AUTHOR}
82 \par{
83 Stijn van Dongen.
84 }
85
86 \sec{seealso}{SEE ALSO}
87 \par{
88 \mysib{mclfamily} for an overview of all the documentation
89 and the utilities in the mcl family.
90 }
91
92 \end{pud::man}