Mailing List

A mailing list has been set up, serving as a common forum for users of ROSETTA for asking questions, receiving news and tips, etc. The mailing list archive is searchable.

Reading Material

The main help resources are:

Thesis – ROSETTA was developed as part of this doctoral dissertation. Contains background theory and a small walk-through example.
Manual – Technical reference manual.

Additional help resources include:

Puzzle – A short note on using ROSETTA to crack a logical puzzle. Shows how to compute the prime implicants of a problem-specific Boolean POS function.
Library – The ROSETTA C++ library. Source code for portions of ROSETTA's computational kernel.
Classes – An overview of files and classes in the ROSETTA C++ library.

FAQ

For questions not answered here, please consult some of the help resources.

RSES

RSES is a collection of algorithms and data structures for rough set computations, developed at the Group of Logic, Inst. of Mathematics, University of Warsaw, Poland. ROSETTA was designed so as to be able to make use of this legacy code, and suitable wrappers have been written so that the RSES library can be linked into the ROSETTA kernel.

The currently distributed ROSETTA binaries have a restricted version of the RSES library linked into them. The ROSETTA kernel is fully functional also without RSES present.

Sizing

I have not hardcoded any maximum table size into ROSETTA. However, the embedded RSES library does not support tables with more than 30000 objects. For larger tables, you have to use a version of ROSETTA without the RSES library. See the section below on source code availability for instructions on how to obtain such a version of ROSETTA.

For reference, the "widest" table I have tested ROSETTA on had over 2000 attributes. I have also successfully applied ROSETTA to a table with more than 15000 objects. I have heard of ROSETTA being applied to larger tables than this, though.

For large tables, be picky about which algorithms you apply. Not all algorithms scale up equally well. For example, computation of all reducts is NP-hard, so a brute force or exhaustive computation is something that is best left for small tables.

Some of the algorithms from the embedded RSES library are not applicable to tables larger than some predetermined size, currently 500 objects and 20 attributes. To process tables larger than this, you have two options:

Obtain a license key that lifts the current sizing restrictions in RSES. Licensing issues are described below.
Use some of the other available algorithms in ROSETTA. Algorithms that do not stem from the RSES library do not have a size restriction imposed on them.

Licensing

For details regarding commercial use of ROSETTA or for purchasing a license key to lift the restrictions on the embedded RSES library, please contact janko(at)lcb.uu.se.

Source Code

As a service to the research community, C++ source code for the ROSETTA computational kernel is made available. See the ROSETTA C++ Library homepage for details.

References

If you use ROSETTA as a tool in any published works, we kindly ask that a mention is made. You can, e.g., reference one or more of the following publications:

A. Øhrn, J. Komorowski (1997), ROSETTA: A Rough Set Toolkit for Analysis of Data, Proc. Third International Joint Conference on Information Sciences, Fifth International Workshop on Rough Sets and Soft Computing (RSSC'97), Durham, NC, USA, March 1-5, Vol. 3, pp. 403-407.
A. Øhrn, J. Komorowski, A. Skowron, P. Synak (1998), The Design and Implementation of a Knowledge Discovery Toolkit Based on Rough Sets: The ROSETTA System, In Rough Sets in Knowledge Discovery 1: Methodology and Applications, L. Polkowski and A. Skowron (eds.), Studies in Fuzziness and Soft Computing, Vol. 18, Chapter 19, pp. 376-399, Physica-Verlag. ISBN 3-7908-1119-X.
A. Øhrn, J. Komorowski, A. Skowron, P. Synak (1998), The ROSETTA Software System, In Rough Sets in Knowledge Discovery 2: Applications, Case Studies and Software Systems, L. Polkowski and A. Skowron (eds.), Studies in Fuzziness and Soft Computing, Vol. 19, pp. 572-576, Physica-Verlag. ISBN 3-7908-1130-3.
A. Øhrn (1999), Discernibility and Rough Sets in Medicine: Tools and Applications, PhD thesis, Department of Computer and Information Science, Norwegian University of Science and Technology (NTNU), Trondheim, Norway. NTNU report 1999:133, IDI report 1999:14, ISBN 82-7984-014-1. 239 pages. [download]
A. Øhrn (2000), ROSETTA Technical Reference Manual, Department of Computer and Information Science, Norwegian University of Science and Technology (NTNU), Trondheim, Norway. 66 pages. [download]
A. Øhrn (2000), The ROSETTA C++ Library: Overview of Files and Classes, Department of Computer and Information Science, Norwegian University of Science and Technology (NTNU), Trondheim, Norway. 45 pages.[download]
J. Komorowski, A. Øhrn, A. Skowron (2002), The ROSETTA Rough Set Software System, In Handbook of Data Mining and Knowledge Discovery, W. Klösgen and J. Zytkow (eds.), ch. D.2.3, Oxford University Press. ISBN 0-19-511831-6.

Sidebar Menu

Involved Institutions