cluster.1 2.2 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104
  1. .de TQ
  2. . br
  3. . ns
  4. . TP \\$1
  5. ..
  6. .TH CLUSTER 1 "3 March 2011"
  7. .SH NAME
  8. cluster \- find clusters in a graph and augment the graph with this information.
  9. .SH SYNOPSIS
  10. .B cluster
  11. [\fB\-v?\fP]
  12. [
  13. .BI \-C k
  14. ]
  15. [
  16. .BI \-c k
  17. ]
  18. [
  19. .B \-o
  20. .I outfile
  21. ]
  22. [
  23. .I files
  24. ]
  25. .SH DESCRIPTION
  26. .B cluster
  27. takes as input a graph in DOT format, finds node clusters and augments
  28. the graph with this information.
  29. The clusters are specified by the "cluster" attribute attached to nodes; cluster
  30. values are non-negative integers.
  31. .B cluster
  32. attempts to maximize the modularity of the clustering.
  33. If the edge attribute "weight" is defined, this will be used in
  34. computing the clustering.
  35. .SH OPTIONS
  36. The following options are supported:
  37. .TP
  38. .BI \-C k
  39. specifies a targeted number of clusters that should be generated.
  40. The specified number \fIk\fP is only a suggestion and may not be realisable.
  41. If \fIk == 0\fP, the default, the number of clusters that approximately optimizes the modularity is returned.
  42. .TP
  43. .BI \-c k
  44. specifies clustering method.
  45. If \fIk == 0\fP, the default, modularity clustering will be used.
  46. If \fIk == 1\fP modularity quality will be used.
  47. .TP
  48. .BI \-o outfile
  49. Specifies that output should go into the file \fIoutfile\fP. By default,
  50. \fIstdout\fP is used.
  51. .TP
  52. .BI \-v
  53. Verbose mode.
  54. .TP
  55. .BI \-?
  56. Prints the usage and exits.
  57. .SH EXAMPLES
  58. .PP
  59. Applying
  60. .B cluster
  61. to the following graph,
  62. .PP
  63. .nf
  64. \fB graph {
  65. 1--2 [weight=10.]
  66. 2--3 [weight=1]
  67. 3--4 [weight=10.]
  68. 4--5 [weight=10]
  69. 5--6 [weight=10]
  70. 3--6 [weight=0.1]
  71. 4--6 [weight=10.]
  72. }\fP
  73. .fi
  74. .PP
  75. gives
  76. .PP
  77. .nf
  78. \fB graph {
  79. node [cluster="-1"];
  80. 1 [cluster=1];
  81. 2 [cluster=1];
  82. 3 [cluster=2];
  83. 4 [cluster=2];
  84. 5 [cluster=2];
  85. 6 [cluster=2];
  86. 1 -- 2 [weight="10."];
  87. 2 -- 3 [weight=1];
  88. 3 -- 4 [weight="10."];
  89. 4 -- 5 [weight=10];
  90. 5 -- 6 [weight=10];
  91. 3 -- 6 [weight="0.1"];
  92. 4 -- 6 [weight="10."];
  93. }\fP
  94. .fi
  95. .SH AUTHOR
  96. Yifan Hu <[email protected]>
  97. .SH "SEE ALSO"
  98. .PP
  99. gvmap(1)
  100. .PP
  101. Blondel, V.D., Guillaume, J.L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. Journal of Statistical Mechanics: Theory and Experiment (2008), P10008.