scorecard (version 0.2.3)

one_hot: One Hot Encoding

Description

One-hot encoding on categorical variables and replace missing values. It is not needed when creating a standard scorecard model, but required in models that without doing woe transformation.

Usage

one_hot(dt, var_skip = NULL, var_encode = NULL, nacol_rm = FALSE,
  replace_na = NULL)

Arguments

dt

A data frame.

var_skip

Name of categorical variables that will skip for one-hot encoding. Default is NULL.

var_encode

Name of categorical variables to be one-hot encoded, default is NULL. If it is NULL, then all categorical variables except in var_skip are counted.

nacol_rm

Logical. One-hot encoding on categorical variable contains missing values, whether to remove the column generated to indicate the presence of NAs. Default is FALSE.

replace_na

Replace missing values with a specified value such as -1, or the mean/median value for numeric variable and mode value for categorical variable. Default is NULL, which means no missing values will be replaced.

Value

A data frame

Examples

# NOT RUN {
# load germancredit data
data(germancredit)

library(data.table)
dat = rbind(
  germancredit[, c(sample(20,3),21)],
  data.table(creditability=sample(c("good","bad"),10,replace=TRUE)),
  fill=TRUE)

# one hot encoding
## keep na columns from categorical variable
dat_onehot1 = one_hot(dat, var_skip = 'creditability', nacol_rm = FALSE) # default
str(dat_onehot1)
## remove na columns from categorical variable
dat_onehot2 = one_hot(dat, var_skip = 'creditability', nacol_rm = TRUE)
str(dat_onehot2)

## one hot and replace NAs
dat_onehot3 = one_hot(dat, var_skip = 'creditability', replace_na = -1)
str(dat_onehot3)


# replace missing values only
## replace with -1
dat_repna1 = one_hot(dat, var_skip = names(dat), replace_na = -1)
## replace with median for numeric, and mode for categorical
dat_repna2 = one_hot(dat, var_skip = names(dat), replace_na = 'median')
## replace with to mean for numeric, and mode for categorical
dat_repna3 = one_hot(dat, var_skip = names(dat), replace_na = 'mean')


# }