exploring-duplicates.md

library(tidyverse)
library(glue)
#> 
#> Attaching package: 'glue'
#> The following object is masked from 'package:dplyr':
#> 
#>     collapse

dupe_df <- function(.data){
  map_dfr(.data, function(x) duplicated(x)*1)
}

bind_dup <- function(.data){
  dupes <- dupe_df(.data)
  names(dupes) <- glue("{names(.data)}_dup")
  bind_cols(.data, dupes)
}

df <- tibble(x = c(1,1,3),
             y = c(1,2,2),
             z = c(2,2,4))

bind_dup(df)
#> # A tibble: 3 x 6
#>       x     y     z x_dup y_dup z_dup
#>   <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1     1     1     2     0     0     0
#> 2     1     2     2     1     0     1
#> 3     3     2     4     0     1     0
dupe_df(df)
#> # A tibble: 3 x 3
#>       x     y     z
#>   <dbl> <dbl> <dbl>
#> 1     0     0     0
#> 2     1     0     1
#> 3     0     1     0

# use dev visdat to get vis_binary
# install_github("ropensci/visdat")
library(visdat)
vis_binary(dupe_df(df))

^{Created on 2020-11-04 by the reprex package (v0.3.0)}