readme

序列模式挖掘prefixspan算法源代码。License: GPL2 (Gnu General Public License Version 2) Requirements: C++ comp

 prefixspan --- An Implementation of PrefixSpan 

 Author: Taku Kudo <[e-mail]>
         Nara Institute of Science and Technology, 
         Graduate School of Information Science, 
         Computational Linguistics Laboratory 

 License: GPL2 (Gnu General Public License Version 2)

 Reference:
  J. Pei, J. Han, H. Pinto, Q. Chen, U. Dayal, and M.-C. Hsu, 
  PrefixSpan: Mining Sequential Patterns Efficiently by Prefix-Projected Pattern Growth
  Proc. 2001 Int. Conf. on Data Engineering (ICDE'01), Heidelberg, Germany, April 2001.
  http://www.cs.sfu.ca/~peijian/personal/publications/span.pdf

 Requirements:
   C++ compiler with STL (Standard Template Library).

 Install:
  % make 

 Usage:
     ./prefixspan [options] < data

     option: 
         -m NUM:   set minimum support        (default: 1)
         -M NUM:   set minimum pattern length (default: 1)
         -L NUM:   set maximum pattern length (default: 0xffffffff)
         -t TYPE:  set item type, choose from [string|int|short|char]
                                              (default: string)
         -a:       print ALL patterns (default: no, print longest pattern only)
         -w:       print the list of transaction IDs
                   where the pattern occurs (default: no)
	 -d STR    use STR as delimiter between item and freq. (default: "/")
         -v:       set verbose mode (print the size of transactions first)

 Format of input data:
 
  foo bar do
  foo foo bar
  i you he
  she me 
 
  Each line corresponds to the each transaction which has a set of items separated by single space.
  For example, first transaction has 3 items (foo, bar, do).
  If you don't need to care the sequential order of items, 
  just sort items by dictionary order like:
  
  bar do foo
  bar foo foo
  he i you
  me she

 Format of results:
 
  item/freq. item/freq. ...
  item/freq. item/freq. ...
  ..
  
  Here is an example:
  
  bar/187 foo/113
  do/170 bar/134
  she/100
  i/501 by/232 the/108

  This result means:

  SEQUENTIAL PATTERN    : FREQUENCY
  bar                   : 187
  bar -> foo            : 113
  do                    : 170
  do -> bar             : 113
  she                   : 100
  i -> by -> the        : 108
  i -> by               : 232
  i                     : 501

  Each line represents the longest sequential pattern 
  whose frequency is larger than minsup (-m option).
  -M NUM1 and -L NUM2  options restrict the size of patterns extracted.
  By using -d option, the delimiter between item and freq can be changed. (default is "/") 

  Note that any prefix of the longest pattern are also sequential pattern.
  However, by using -a option, you can obtain ALL patterns, all prefix of
  the longest pattern. Here is an example:

  187 bar
  113 bar foo
  170 do
  134 do bar
  100 she
  501 i
  232 i by
  108 i by the
  
  By using -w option, the list of transaction IDs where each pattern 
  occurs can be obtained. Here is an example:

 * without -a option
 <pattern>
 <what>bar/187 foo/113</what>
 <where>54 141 218 264 295 472 768 839 900 931</where>
 </pattern>
 
 * with -a option
 <pattern>
 <freq>187</freq>
 <what>bar</what>
 <where>54 141 218 264 295 472 768 839 900 931 .... </where>
 </pattern>
 <pattern>
 <freq>113</freq>
 <what>bar foo</what>
 <where>54 141 218 264 295 472 768 839 900 931 .... </where>
 </pattern>
 
  Each result is surrounded by "<pattern>" tag.
  The pattern is in "<what>" tag, and transaction IDs are listed in "<where>" tag.