I would like to randomly add NA values to my dataframe with the proportion set by group.
library(tidyverse)
set.seed(1)
dat <- tibble(group = c(rep("A", 100),
rep("B", 100)),
value = rnorm(200))
pA <- 0.5
pB <- 0.2
# does not work
# was trying to create another column that i could use with
# case_when to set value to NA if missing==1
dat %>%
group_by(group) %>%
mutate(missing = rbinom(n(), 1, c(pA, pB))) %>%
summarise(mean = mean(missing))
I'd create a small tibble to keep track of the expected missingness rates, and join it to the first data frame. Then go through row by row to decide whether to set a value to missing or not.
This is easy to generalize to more than two groups as well.
library("tidyverse")
set.seed(1)
dat <- tibble(
group = c(
rep("A", 100),
rep("B", 100)
),
value = rnorm(200)
)
expected_nans <- tibble(
group = c("A", "B"),
p = c(0.5, 0.2)
)
dat_with_nans <- dat %>%
inner_join(
expected_nans,
by = "group"
) %>%
mutate(
r = runif(n()),
value = if_else(r < p, NA_real_, value)
) %>%
select(
-p, -r
)
dat_with_nans %>%
group_by(
group
) %>%
summarise(
mean(is.na(value))
)
#> # A tibble: 2 × 2
#> group `mean(is.na(value))`
#> <chr> <dbl>
#> 1 A 0.53
#> 2 B 0.17
Created on 2022-03-11 by the reprex package (v2.0.1)
Nesting and unnesting works
library(tidyverse)
dat <- tibble(group = c(rep("A", 1000),
rep("B", 1000)),
value = rnorm(2000))
pA <- .1
pB <- 0.5
set.seed(1)
dat %>%
group_by(group) %>%
nest() %>%
mutate(p = case_when(
group=="A" ~ pA,
TRUE ~ pB
)) %>%
mutate(data = purrr::map(data, ~ mutate(.x, missing = rbinom(n(), 1, p)))) %>%
unnest() %>%
summarise(mean = mean(missing))
# A tibble: 2 × 2
group mean
<chr> <dbl>
1 A 0.11
2 B 0.481
set.seed(1)
dat %>%
group_by(group) %>%
nest() %>%
mutate(p = case_when(
group=="A" ~ pA,
TRUE ~ pB
)) %>%
mutate(data = purrr::map(data, ~ mutate(.x, missing = rbinom(n(), 1, p)))) %>%
unnest() %>%
ungroup() %>%
mutate(value = case_when(
missing == 1 ~ NA_real_,
TRUE ~ value
)) %>%
select(-p, -missing)