MergeLevelsCausataData: Combines least-frequently occurring levels of a factor into...

In Causata: Analysis utilities for binary classification and Causata users.

Description

MergeLevels is applied to a CausataData object, and the merge process is recorded so that it can be repeated during scoring.

Usage

## S3 method for class 'CausataData'
MergeLevels(this, variableName=NULL, max.levels, 
  other.name="Other", verbose=FALSE, ...)

Arguments

this	An object from CausataData.
variableName	If a name is supplied then the variable matching the name will have MergeLevels applied. If no name is provided then MergeLevels is applied to every factor in causataData.
max.levels	See MergeLevels.
other.name	See MergeLevels.
verbose	If TRUE then summary information will be printed to the screen.
...	Unused extra arguments.

Value

Returns an object of class CausataData.

Author(s)

Justin Hemann <[e-mail]>

See Also

CausataData, MergeLevels.

Examples

library(stringr)
df <- data.frame(
  f1__AP=factor(str_split("a a a b b b c c c d e f g h", " ")[[1]]), 
  f2__AP=factor(c(rep("x",7),rep("y",7))))
causataData <- CausataData(df, rep(0,nrow(df)))
# For the factor f1__AP, the levels d,e,f,g are merged into Other.
# f2__AP is not altered since it has only two levels.
causataData <- MergeLevels(causataData, max.levels=4) 

Causata documentation built on May 2, 2019, 3:26 a.m.