Learn R Programming
⚠️There's a newer version (1.6.4) of this package.Take me there.

vtreat (version 0.5.23)

Simple Variable Treatment

Description

Prepares variables so that data has fewer exceptional cases, making it easier to safely use models in production. Common problems 'vtreat' defends against: Inf, NA, too many categorical values, rare categorical values, new categorical values (levels seen during application, but not during training). 'vtreat::prepare' should be used as you would use 'model.matrix'.

Copy Link

Version

Install

install.packages('vtreat')

Monthly Downloads

10,294

Version

0.5.23

License

GPL-3

Issues

0

Pull Requests

0

Stars

286

Forks

45

Maintainer

John Mount

Last Published

April 29th, 2016

Functions in vtreat (0.5.23)

format.vtreatment

Display treatment plan.
vorig

Original variable name from a treatmentplan$treatment item.
pressStatOfBestLinearFit

Compute the PRESS R-squared statistic of a 1-variable linear model
mkCrossFrameNExperiment

Run numeric cross frame experiment.
vtreat-package

vtreat: a package for simple variable treatment
designTreatmentsC

Build all treatments for a data frame to predict a categorical outcome.
catScore

return a pseudo R-squared from a 1 variable logistic regression
buildEvalSets

Build disjoint set partition for out-of sample evaluation.
designTreatmentsN

build all treatments for a data frame to predict a numeric outcome
vnames

New treated variable names from a treatmentplan$treatment item.
designTreatmentsZ

Design variable treatments with no outcome variable.
print.vtreatment

Print treatmentplan.
mkCrossFrameCExperiment

Run categorical cross-frame experiment.
prepare

Apply treatments and restrict to useful variables.
hold1OutMeans

of all but the i-th y. Useful for normalizing PRESS style statistics.