GPL C/C++ software for data analysis of discrete data using principal/independent component methods. Examples are DPCA, LDA, GaP (like PLSI and NMF). Targetted at text, with MPI and multithreading.
BAYDA software implements Bayesian predictive discriminant analysis, where the aim is to build a model for predicting the value of one discrete (class, group, category) variable using other variables.