The ROSETTA C++ library is a collection of C++ classes and routines that enable discernibility-based empirical modelling and data mining, developed as part of my dissertation. A brief presentation of the library can be found therein.
The library comprises the computational kernel (minus the embedded RSES library) of the ROSETTA system, and is made available as a service to the research community under the GNU General Public License.
The library is not tied up to any particular hardware platform, operating system or compiler, and has been successfully compiled and tested under several flavors of both Windows and UNIX.
Source code and documentation can be downloaded from SourceForge:
The main routine that accompanies the source code implements a simple command-line interface to ROSETTA. Here are other example main routines you can use:
| main.cpp | An example pipeline from my dissertation. | |
| main.cpp | The command-line version of HYPOCLASS. |
Since the RSES library is excluded from this distribution, the file formats for reducts and rules differ between the library and the downloadable ROSETTA binaries that do contain RSES. (Apart from reducts and rules, file formats are otherwise identical.) So that such data created by yourself can be loaded into and viewed in the ROSETTA GUI, a special version of the executable that uses the present library distribution is included in the SourceForge bundle.
You might want to join the ROSETTA mailing list, a common forum for users of ROSETTA and the ROSETTA C++ library for receiving news and tips, asking questions, etc.:
Enjoy!