This repository is for developing python code to do feature selection for high-dimensional genotype data. The data must be coded with columns subject_id, population, rs_ids. Subject_id is a unique identifier, population is text categorical, and rs_ids are coded 0,1,2.
nobel1154 / supportvector Goto Github PK
View Code? Open in Web Editor NEWThis project forked from wathenmj/supportvector