TANAGRA

Tanagra represents free data mining software for academic and research purposes. It provides several data mining methods from exploratory data analysis, statistical learning, machine learning and databases area.

It is a successor of SIPINA which means that various supervised learning algorithms are provided, especially an interactive and visual construction of decision trees. Because it contains supervised learning but also other paradigms such as clustering, factorial analysis, parametric and nonparametric statistics, association rule, feature selection and construction algorithms, Tanagra is very powerful.

The main goal of this project is giving researchers and student’s easy-to-use data mining software and second goal is to propose to researchers an architecture allowing them to easily add their own data mining methods, to compare their performances. In order of letting users going to the essential of the work dispensing members dealing with the data management, Tanagra acts more as an experimental platform. The last goal of this platform is diffusing a possible methodology for building this kind of software.

This platform is last born of a series of software intended for the data analysis. It is an "open source project" which means that every user can access to the source code, and adding its own algorithms, but it necessary to agree and confirm the software distribution license.

Concepts available in Tanagra are stream diagram - the graph has been replaced with a simpler form of it: a tree which means that only one source can provide data in the same diagram, so the user must prepare them before importing; file format – imported data are included in the saved file with file format *bdm which can only be exploited by TANAGRA. Available components in Tanagra are data source, visualization, descriptive statistics etc.