⚠️There's a newer version (1.1.2) of this package.Take me there.

embed (version 0.0.5)

Extra Recipes for Encoding Categorical Predictors

Description

Predictors can be converted to one or more numeric representations using simple generalized linear models or nonlinear models . All encoding methods are supervised.

Copy Link

Version

Install

install.packages('embed')

Monthly Downloads

1,844

Version

0.0.5

License

GPL-2

Issues

Pull Requests

Stars

144

Forks

Repository

https://github.com/tidymodels/embed

Homepage

https://tidymodels.github.io/embed

Maintainer

Max Kuhn

Last Published

January 7th, 2020

Functions in embed (0.0.5)

step_lencode_mixed

Supervised Factor Conversions into Linear Functions using Bayesian Likelihood Encodings

step_embed

Encoding Factors into Multiple Columns

step_umap

Supervised and unsupervised uniform manifold approximation and projection (UMAP)

step_lencode_bayes

Supervised Factor Conversions into Linear Functions using Bayesian Likelihood Encodings

step_lencode_glm

Supervised Factor Conversions into Linear Functions using Likelihood Encodings

woe_table

Crosstable with woe between a binary outcome and a predictor variable.

tunable.step_embed

tunable methods for embed

step_woe

Weight of evidence transformation

add_woe

Add WoE in a data frame

dictionary

Weight of evidence dictionary

reexports

Objects exported from other packages