I want a way to automatically edit the label output from the following cut:
library(dplyr)
library(janitor)
set.seed(1)
df <- data.frame(a = sample(0:50, 200, replace = T))
df <- df %>%
mutate(a_cut = cut(a,
breaks = c(0:9, seq(10, 40, by = 5), Inf), include.lowest = FALSE,
right = FALSE))
tabyl(df, a_cut)
# a_cut n percent
# [0,1) 5 0.025
# [1,2) 3 0.015
# [2,3) 1 0.005
# [3,4) 1 0.005
# [4,5) 0 0.000
# [5,6) 7 0.035
# [6,7) 3 0.015
# [7,8) 0 0.000
# [8,9) 3 0.015
# [9,10) 4 0.020
# [10,15) 15 0.075
# [15,20) 17 0.085
# [20,25) 24 0.120
# [25,30) 17 0.085
# [30,35) 21 0.105
# [35,40) 27 0.135
# [40,Inf) 52 0.260
into the following cut labels (a_cut):
# a_cut n percent
# 0 5 0.025
# 1 3 0.015
# 2 1 0.005
# 3 1 0.005
# 4 0 0.000
# 5 7 0.035
# 6 3 0.015
# 7 0 0.000
# 8 3 0.015
# 9 4 0.020
# 10-14 15 0.075
# 15-19 17 0.085
# 20-24 24 0.120
# 25-29 17 0.085
# 30-34 21 0.105
# 35-39 27 0.135
# 40+ 52 0.260
I think the cutr or kimisc package could do it but I cant figure out the correct configuration.
#e.g., comes close
kimisc::cut_format(df$a, c(1:9, seq(10, 40, by = 5)), sep = "-", paren = c("", "", "", ""))
thanks
You can add a labels argument to cut:
library(dplyr)
library(janitor)
set.seed(1)
df <- data.frame(a = sample(0:50, 200, replace = T))
df <- df %>%
mutate(a_cut = cut(a,
breaks = c(0:9, seq(10, 40, by = 5), Inf),
labels = c(0:9, paste(2:7 * 5, 2:7 * 5 + 4, sep = '-'),
'40+'),
include.lowest = FALSE,
right = FALSE))
tabyl(df, a_cut)
#> a_cut n percent
#> 0 5 0.025
#> 1 3 0.015
#> 2 1 0.005
#> 3 1 0.005
#> 4 0 0.000
#> 5 7 0.035
#> 6 3 0.015
#> 7 0 0.000
#> 8 3 0.015
#> 9 4 0.020
#> 10-14 15 0.075
#> 15-19 17 0.085
#> 20-24 24 0.120
#> 25-29 17 0.085
#> 30-34 21 0.105
#> 35-39 27 0.135
#> 40+ 52 0.260