CollapseLevels: Collapses Levels, Computes Information Value and WoE

An update to the previous version ( 0.1.0 ) of the package. Functions in the previous version required the binary outcome variable of the data set to be strictly a factor.In version 0.2.0 the binary outcome variable may be both a factor (with two levels) or an integer (or numeric ). All functions of the previous version have been retained.No new functions have been added. Like the previous version,provides functions to collapse the levels of an attribute based on response rates. It also provides functions to compute and display information value, and weight of evidence (WoE) for the attributes, and to convert numeric variables to categorical ones by binning. These functions only work for binary classification problems.

Package details

AuthorKrishanu Mukherjee
MaintainerKrishanu Mukherjee <[email protected]>
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:

Try the CollapseLevels package in your browser

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

CollapseLevels documentation built on Dec. 4, 2017, 5:05 p.m.