Section: New Software and Platforms

MIXMOD software

Participants : Gilles Celeux [Correspondant] , Benjamin Auder, Jonas Renault.

Mixture model, cluster analysis, discriminant analysis mixmod is being developed in collaboration with Christophe Biernacki, Florent Langrognet (Université de Franche-Comté) and Gérard Govaert (Université de Technologie de Compiègne). mixmod (mix ture mod eling) software fits mixture models to a given data set, with either a clustering or a discriminant analysis purpose. mixmod uses a large variety of algorithms to estimate mixture parameters, e.g., EM, Classification EM, and Stochastic EM. They can be combined to create different strategies that lead to a sensible maximum of the likelihood (or completed likelihood) function. Moreover, different information criteria for choosing a parsimonious model, e.g. the number of mixture components, some of them favoring either a cluster analysis or a discriminant analysis point of view, are included. Many Gaussian models for continuous variables and multinomial models for discrete variable are included. Written in C++, mixmod is interfaced with Matlab . The software, statistical documentation, and user guide are available here: http://www.mixmod.org .

Since 2010, mixmod has a proper graphical user interface. A version of mixmod in R is now available: http://cran.r-project.org/web/packages/Rmixmod/index.html .

Benjamin Auder contributes to the software improvement of mixmod . He has implemented an interface to test any mathematical library (Armadillo, Eigen, etc.) to replace NEWMAT. He has contributed to the continuous integration setup using Jenkins tools, and has prepared an automated testing framework for unit and non-regression tests.

This year, mixmod has received the support of an ADT (MASSICCC) for three years. This ADT MASSICCC has been obtained conjointly with the MODAL team (Inria Lille). This year, an engineer, Jonas Renault, has been appointed for two years. He is in charge of developing a web version of mixmod .