The Robust re-scaling transformation (RR) is a transformation the help reveal latent structure in data. It uses three steps to transform the data:
The sequence of these transformations helps focus analyses on consequential variance in the data rather than having it be focused on variation resulting from the feature’s measurement scale or outliers.
This is the github page for our R package ‘rrscale’ to perform the transformation.
Our R package is available on CRAN: https://cran.r-project.org/package=rrscale
Our docker image for reproducing the analysis in paper can be found here.