Sample from a data frame using group-specific sample sizes

Question

I want to sample rows from a data frame using unequal sample sizes from each group.

Let's say we have a simple data frame grouped by 'group':

library(dplyr)
set.seed(123)

df <- data.frame(group = rep(c("A", "B"), each = 10), 
                 value = rnorm(10))
df
#>    group       value
#> 1      A -0.56047565
#> 2      A -0.23017749
#> .....
#> 10     A -0.44566197
#> 11     B -0.56047565
#> 12     B -0.23017749
#> .....
#> 20     B -0.44566197

Using the slice_sample function from the dplyr package, you can easily slice equally sized groups from this dataframe:

df %>% group_by(group) %>% slice_sample(n = 2) %>% ungroup()

#> # A tibble: 4 x 2
#>   group  value
#>   <fct>  <dbl>
#> 1 A     -0.687
#> 2 A     -0.446
#> 3 B     -0.687
#> 4 B      1.56

Question

How do you sample a different number of values from each group (slice groups that are not equal in size)? For example, sample 4 rows from group A, and 5 rows from group B?

Answer 1

The easiest thing I can think of is a map2 solution using purrr.

library(dplyr)
library(purrr)

df %>% 
  group_split(group) %>% 
  map2_dfr(c(4, 5), ~ slice_sample(.x, n = .y))

# A tibble: 9 x 2
  group   value
  <chr>   <dbl>
1 A     -0.687 
2 A      1.56  
3 A      0.0705
4 A      1.72  
5 B     -0.560 
6 B      0.461 
7 B      0.129 
8 B      0.0705
9 B     -0.230 

A caution is that you need to understand the order of the split. I think group_split() will sort the group as factors. A way around that would be to adapt like this, and lookup the n from a named vector.

group_slice_n <- c(A = 4, B = 5)

df %>% 
  split(.$group) %>% 
  imap_dfr(~ slice_sample(.x, n = group_slice_n[.y]))

Answer 2

Try this:

group_sizes <- tibble(group = c("A", "B"), size = c(4, 5))
set.seed(2021)
df %>%
  left_join(group_sizes, by = "group") %>%
  group_by(group) %>%
  mutate(samp = sample(n())) %>%
  filter(samp <= size) %>%
  ungroup()
# # A tibble: 9 x 4
#   group   value  size  samp
#   <chr>   <dbl> <dbl> <int>
# 1 A      0.0705     4     2
# 2 A      0.129      4     4
# 3 A     -0.687      4     1
# 4 A     -0.446      4     3
# 5 B     -0.560      5     5
# 6 B      1.56       5     1
# 7 B      0.129      5     4
# 8 B      1.72       5     3
# 9 B     -1.27       5     2

Answer 3

You can use the stratified function from my "splitstackshape" package:

> library(splitstackshape)
> stratified(df, "group", c(A = 4, B = 5))
   group      value
1:     A -0.6868529
2:     A  0.4609162
3:     A  1.7150650
4:     A -0.4456620
5:     B  0.4609162
6:     B -0.4456620
7:     B  0.1292877
8:     B -1.2650612
9:     B -0.2301775

Answer 4

a data.table approach, with the use of mapply for looping over list-elemenst with sample-size in a vector (with length of list!)

library( data.table )
setDT(df) #make it a data.table
L <- split( df, by = "group" ) #split to a list by group
#function
mysamples <- function( dt, samplesize ) {
  dt[ sample( 1:nrow(dt), samplesize), ]
}
#mapply
mapply( mysamples, L, samplesize = c(4,5), SIMPLIFY = FALSE )

#output
# $A
# group      value
# 1:     A -0.6868529
# 2:     A -0.4456620
# 3:     A -0.5604756
# 4:     A  0.1292877
# 
# $B
# group      value
# 1:     B  1.5587083
# 2:     B -1.2650612
# 3:     B -0.2301775
# 4:     B  0.4609162
# 5:     B -0.6868529

Answer 5

set.seed(123)
library(tidyverse)

map2_df(unique(df$group), c(4,5),
        ~df %>% 
          filter(group == .x) %>% 
          slice_sample(n = .y))

  group      value
1     A -0.3724388
2     A -0.4168576
3     A  0.5629895
4     A -1.2601552
5     B  1.0527115
6     B -0.3745809
7     B  0.9769734
8     B -0.4168576
9     B -1.0491770

In case your data has not been arranged yet, you may use the following:

map2_df(unique(sort(df$group)), c(4,5),
        ~df %>% arrange(group) %>% 
          filter(group == .x) %>%
          slice_sample(n = .y))

Answer 6

Another data.table possibility based on a join.

Put the group-specific sample sizes in a "lookup table" (here, a list, .(...)); join with original data on 'group' (on = .(group)); for each match in i (by = .EACHI), pick a sample from 'value' of size = size[1])

setDT(df)[.(group = c("A", "B"), size = c(4, 5)), on = .(group), sample(value, size[1]),
         by = .EACHI]

#    group         V1
# 1:     A -0.6868529
# 2:     A -0.4456620
# 3:     A -0.5604756
# 4:     A  0.1292877
# 5:     B  1.5587083
# 6:     B -1.2650612
# 7:     B -0.2301775
# 8:     B  0.4609162
# 9:     B -0.6868529

Answer 7

Just adding an alternate answer that uses nest/unnest:

library(tidyverse)
set.seed(123)

df <- data.frame(
  group = rep(c("A", "B"), each = 10),
  value = rnorm(10)
)

df %>%
  nest(data = value) %>%
  mutate(
    sample_size = c(4, 5),
    data_sample = map2(data, sample_size, ~ slice_sample(.x, n = .y))
  ) %>%
  select(group, data_sample) %>%
  unnest(cols = data_sample)
#> # A tibble: 9 × 2
#>   group  value
#>   <chr>  <dbl>
#> 1 A     -0.687
#> 2 A     -0.446
#> 3 A     -0.560
#> 4 A      0.129
#> 5 B      1.56 
#> 6 B     -1.27 
#> 7 B     -0.230
#> 8 B      0.461
#> 9 B     -0.687

^{Created on 2022-10-28 by the reprex package (v2.0.1)}