maxlevels: Remove factors with too many levels

In OneR: One Rule Machine Learning Classification Algorithm with Enhancements

Description

Removes all columns of a data frame where a factor (or character string) has more than a maximum number of levels.

Usage

maxlevels(data, maxlevels = 20, na.omit = TRUE)

Arguments

data	data frame which contains the data.
maxlevels	number of maximum factor levels.
na.omit	logical value whether missing values should be treated as a level, defaults to omit missing values before counting.

Details

Often categories that have very many levels are not useful in modelling OneR rules because they result in too many rules and tend to overfit. Examples are IDs or names.

Character strings are treated as factors although they keep their datatype. Numeric data is left untouched. If data contains unused factor levels (e.g. due to subsetting) these are ignored and a warning is given.

Value

A data frame.

Author(s)

Holger von Jouanne-Diedrich

References

https://github.com/vonjd/OneR

See Also

OneR

Examples

df <- data.frame(numeric = c(1:26), alphabet = letters)
str(df)
str(maxlevels(df))

OneR documentation built on May 2, 2019, 9:33 a.m.