dummy_recodes: Creation of dummy variables.

dummy_recodesR Documentation

Creation of dummy variables.

Description

Create dummy variables for the factor variables in the dataset. The function is based on the functions in R 'dummies' package.

Usage

dummy_recodes(data = data, sep = "_", drop = FALSE, all = FALSE)

Arguments

data

An object such as a data.frame or matrix that has colnames.

sep

For the names of the created dummy variables, sep is the character used between the variable name and the value. Default: "_".

drop

Logical. Whether to drop one level with smallest mean value. This is very useful to create dummy variables for regression since we can at most keep n-1 levels of a variable in the model. Default: False.

all

Logical. Whether to return columns that are not dummy classes. The default is FALSE and not returns all classes. Non dummy classes are dropped

Value

A synthetic data frame with the dummy variables. If all is TRUE, columns that are not dummy classes will be returned as well. If drop is TRUE, only (n-1) dummy variables will be created for one factor variable.

Examples

mag <- data(mag)

var.factor <- c("NFAC1_2", "NFAC2_2", "NFAC3_2", "NFAC4_2", "NFAC5_2", "NFAC6_2", "NFAC7_2", "childhh", "ethnic", "maritalstat",
                "educat", "homestat", "employstat", "dvryes", "cabdsl")

var.num <- c("agemid", "incmid")

#coerce var.factor to factor and var.num to numeric
mag1 <- mag %>%
  dplyr::mutate_at(vars(var.factor), as.factor) %>%
  dplyr::mutate_at(vars(var.num), as.numeric)
  
#only works on factors
results <- dummy_recodes(mag1, drop=TRUE, all=FALSE)


yangx227/SimmonsResearchR documentation built on April 24, 2022, 6:44 a.m.