I have a dataframe that looks like this:
df <- tibble::tribble(
~subcateg, ~names, ~categ, ~names2,
"A00", "Kidney failure", "A00", "Kidney failure",
"A001", "Kidney failure reason1", "A00", "Kidney failure",
"A002", "Kidney failure reason2","A00", "Kidney failure",
"A003", "Kidney failure reason3","A00", "Kidney failure",
"B00", "Heart failure", "B00", "Heart failure",
"B001", "Heart failure reason1", "B00", "Heart failure",
"B002", "Heart failure reason2", "B00", "Heart failure",
"B003", "Heart failure reason3", "B00", "Heart failure",
"C00", "Lung failure", "C00", "Lung failure",
"C001", "Lung failure reason1", "C00", "Lung failure",
"C002", "Lung failure reason2", "C00", "Lung failure",
"C003", "Lung failure reason3", "C00", "Lung failure",
)
And I need to add an "X" to the values of column 1 that have only 3 chr. This is, the values where columns subcateg=categ, so it should look like this:
df <- tibble::tribble(
~subcateg, ~names, ~categ, ~names2,
"A00X", "Kidney failure", "A00", "Kidney failure",
"A001", "Kidney failure reason1", "A00", "Kidney failure",
"A002", "Kidney failure reason2","A00", "Kidney failure",
"A003", "Kidney failure reason3","A00", "Kidney failure",
"B00X", "Heart failure", "B00", "Heart failure",
"B001", "Heart failure reason1", "B00", "Heart failure",
"B002", "Heart failure reason2", "B00", "Heart failure",
"B003", "Heart failure reason3", "B00", "Heart failure",
"C00X", "Lung failure", "C00", "Lung failure",
"C001", "Lung failure reason1", "C00", "Lung failure",
"C002", "Lung failure reason2", "C00", "Lung failure",
"C003", "Lung failure reason3", "C00", "Lung failure",
)
I've tried something like this:
df %>%
filter(subcateg = categ) %>%
paste0(df$subcateg, "X")
but it doesn't work. Any ideas?
Thanks!
CodePudding user response:
We could use nchar
in an ifelse
statement:
library(dplyr)
df %>%
mutate(subcateg= ifelse(nchar(subcateg)==3, paste0(subcateg, "X"), subcateg))
subcateg names categ names2
<chr> <chr> <chr> <chr>
1 A00X Kidney failure A00 Kidney failure
2 A001 Kidney failure reason1 A00 Kidney failure
3 A002 Kidney failure reason2 A00 Kidney failure
4 A003 Kidney failure reason3 A00 Kidney failure
5 B00X Heart failure B00 Heart failure
6 B001 Heart failure reason1 B00 Heart failure
7 B002 Heart failure reason2 B00 Heart failure
8 B003 Heart failure reason3 B00 Heart failure
9 C00X Lung failure C00 Lung failure
10 C001 Lung failure reason1 C00 Lung failure
11 C002 Lung failure reason2 C00 Lung failure
12 C003 Lung failure reason3 C00 Lung failure
CodePudding user response:
We may use case_when
to create a logical vector based on the nchar
value of 3 in 'subcateg' to paste
(str_c
) the 'X' at the end of 'subcateg'
library(dplyr)
library(stringr)
df %>%
mutate(subcateg = case_when(nchar(subcateg) == 3 ~
str_c(subcateg, 'X'), TRUE ~ subcateg))
-ouptut
# A tibble: 12 × 4
subcateg names categ names2
<chr> <chr> <chr> <chr>
1 A00X Kidney failure A00 Kidney failure
2 A001 Kidney failure reason1 A00 Kidney failure
3 A002 Kidney failure reason2 A00 Kidney failure
4 A003 Kidney failure reason3 A00 Kidney failure
5 B00X Heart failure B00 Heart failure
6 B001 Heart failure reason1 B00 Heart failure
7 B002 Heart failure reason2 B00 Heart failure
8 B003 Heart failure reason3 B00 Heart failure
9 C00X Lung failure C00 Lung failure
10 C001 Lung failure reason1 C00 Lung failure
11 C002 Lung failure reason2 C00 Lung failure
12 C003 Lung failure reason3 C00 Lung failure