categoryEncodings: Category Variable Encodings

Simple, fast, and automatic encodings for category data using a data.table backend. Most of the methods are an implementation of "Sufficient Representation for Categorical Variables" by Johannemann, Hadad, Athey, Wager (2019) <arXiv:1908.09874>, particularly their mean, sparse principal component analysis, low rank representation, and multinomial logit encodings.

Getting started

Package details

AuthorJuraj Szitas [aut, cre]
MaintainerJuraj Szitas <>
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:

Try the categoryEncodings package in your browser

Any scripts or data that you put into this service are public.

categoryEncodings documentation built on March 2, 2020, 5:07 p.m.