SelvarClustMV (Apprentissage)


Variable selection in model-based clustering, taking into account missing values

It is devoted to the variable selection in model-based clustering, taking into account missing values. It is a greedy algorithm associated to the SR modeling proposed in Maugis et al. (Biometrics, 2009), taking into account missing values. This software allows to study data where individuals are described by quantitative block variables. It returns a data clustering and the selected model, composed of the number of clusters and the variable partition. This software is here only proposed for Gaussian mixtures whose variance matrices are assumed to be identical and free (m=[pkLC]).


Informations générales
Informations spécifiques
Langage(s) de développement
C++
Langage(s) d'interface
C++


Porteur(s)
Unité
MIA-Paris
Auteur(s)
Maugis-Rabusseau C.
Martin-Magniette M.-L.
Pelletier S.


 

 

Système d'information scientifique MIA classé par unité (UR, UMR)

Logo BIOSP     Logo MISTEA     Logo MIA Toulouse     Logo MaIAGE     Logo MIA Paris