simulate_missings: Generate MCAR missings in dataset.

In NADIA: NA Data Imputation Algorithms

Generate MCAR missings in dataset.

Description

Function generates random missing values in given dataset according to set parameters.

Usage

simulate_missings(
  df,
  per_missings,
  per_instances_missings = NULL,
  per_variables_missings = NULL,
  variables_with_missings = NULL
)

Arguments

df	Data.frame or data.table where missing values will be generated
per_missings	Overall percentage of missing values generated in dataset. Must be set every time.
per_instances_missings	Percentage of instances which will have missing values.
per_variables_missings	Percentage of variables which will have missing values.
variables_with_missings	Only when 'per_variables_missings' is 'NULL'. Vector of column indexes where missings will be generated.

Value

Dataset with generated missings.

Examples

{
  data_NA <- simulate_missings(iris, 20)

  # check
  sum(is.na(data_NA)) > 0
}

NADIA documentation built on Oct. 3, 2022, 1:05 a.m.