changelog.txt

来自「这是一个用于数据挖掘的常用算法的模板库（数据挖掘的C++模板库for UNIX)」· 文本 代码 · 共 38 行

1.0 release - 07/26/2006
------------------------

 - Added a new back end - file_storage_manager. Now the VATs can be
   stored in a persistent storage. The file "outfile.dat" is used to
   house the temporary file cache. 
   IMPORTANT NOTE: The storage manager scales beyond 2 Gigabytes limit
   only when compiled with gcc 4.0 (this is because in gcc4.0 the
   fstream class can handle > 2GB files).

 - Added another set of properties - Tokenizer property. These
   properties control the tokenizer that would be invoked. For
   different input file formats new tokenizers can be defined. As an
   example, a FASTA format tokenizer has been added for biosequences.

 - Improved the sequence mining implementation of induced and embedded
   sequences.

 - Fixed bug in embedded/induced sequence mining which occurred because the
   gap between consecutive items in a sequence was hard-coded.

 - Changed the command line inputs. -i, -s and -p are added for input
   file, support and print patterns, respectively.

 - Includes support for multi-set pattern.  NOTE: Right now the
   multi-set pattern does not have a file_storage_manager as a back
   end.

 - Added LINE_SZ in tokenizer_utils.h so that long input lines can be
   parsed from the input files.


Alpha 0.1 - 11/30/2005
----------------------

 - Initial alpha release.