- April 6th, 2005
Bayes Junk Tool 0.2.1 released!
- March 30th, 2005
- July 18th, 2003
Bayes Junk Tool 0.2 released!
- July 14th, 2003
Bayes Junk Tool project becomes Project of the Week!
- July 12th, 2003
Bayes Junk Tool Mozdev website opens for business!
- June 23rd, 2003
Bayes Junk Tool 0.1 released!
- Many thanks to Mozdev.org for providing space for this project!
The Bayes Junk Tool project has now changed hands and with that a maintenance release providing a compatibility fix for Java 5.0. The Bayes Junk Tool is ready for prime time, so please feel free to use it to unlock the mysteries of the Mozilla Bayesian Junk Mail Filter.
The current version of the Bayes Junk Tool (0.2.1) has many features, including:
- Viewing of data contained with Mozilla's training.dat
- Exporting of data as HTML, XML, plain text, or well-formed .dat (you can take a .dat and drop it in the Mozilla folder, and it should work perfectly)
- GUI which allows adding new tokens, removing tokens, and editing the counts associated with each token
- Removal of certain sets of tokens based on their good or bad count
- A status bar which displays the name of the file being viewed, the number of tokens in total, and the number of tokens selected.
- Equivalent application functionality from both the command-line and the GUI
- Full JavaDoc of the Bayes Junk Tool API so that its functionality can be more easily incorporated into other programs
- Sorting of data on any column in the GUI. This allows you to see, for example, the most frequently encountered good and bad tokens in email
- Importing of data from an existing training.dat or XML file and merging with an existing training.dat.
I believe this last feature is very important as it will allow a new user to get up and running very quickly by importing a well-known XML file containing useful values for spam tokens, thus greatly reducing the training period for Mozilla's mail filters. I have included a copy of several sample training files in both XML and DAT format, and I encourage others who have a well-trained filter to upload theirs so that new users can benefit from it. For more information about sending in your token file, please visit the Download page.