Make k score out of de-identified data

This gives you a data.frame with rows grouped based on the columns parameter and tell you how many unique values are in each group.

make_k_score(data, columns = NULL, quiet = FALSE, minimum_k_score = 3)

Arguments

data	The data.frame with the data you want to make the k score from.
columns	A string or vector of strings for the names of columns to group the data by.
quiet	A Boolean (default FALSE) for whether you want to output a message that tells you if there are groups with too few observations - you can set how many is 'too few' in the parameter minimum_k_score, default is 3.
minimum_k_score	A single integer which sets the number of observations in each group that will message (if quiet is FALSE) saying how many groups have fewer observations below that group.

Value

A data.frame

Examples

make_k_score(mtcars, columns = c("cyl", "vs", "am", "gear"))
#> Note: There are 9 groups with 3 or fewer observations.
#>    cyl vs am gear number_of_observations
#> 1    4  0  1    5                      1
#> 2    4  1  0    3                      1
#> 3    4  1  1    5                      1
#> 4    6  0  1    5                      1
#> 5    4  1  0    4                      2
#> 6    6  0  1    4                      2
#> 7    6  1  0    3                      2
#> 8    6  1  0    4                      2
#> 9    8  0  1    5                      2
#> 10   4  1  1    4                      6
#> 11   8  0  0    3                     12