Question

How can I select the first and last row for each unique id in the following dataframe?

tmp <- structure(list(id = c(15L, 15L, 15L, 15L, 21L, 21L, 22L, 22L, 
22L, 23L, 23L, 23L, 24L, 24L, 24L, 24L), d = c(1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), gr = c(2L, 1L, 
1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 2L), mm = c(3.4, 
4.9, 4.4, 5.5, 4, 3.8, 4, 4.9, 4.6, 2.7, 4, 3, 3, 2, 4, 2), area = c(1L, 
2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 2L, 3L)), .Names = c("id", 
"d", "gr", "mm", "area"), class = "data.frame", row.names = c(NA, 
-16L))
tmp
#>    id d gr  mm area
#> 1  15 1  2 3.4    1
#> 2  15 1  1 4.9    2
#> 3  15 1  1 4.4    1
#> 4  15 1  1 5.5    2
#> 5  21 1  1 4.0    2
#> 6  21 1  2 3.8    2
#> 7  22 1  1 4.0    2
#> 8  22 1  1 4.9    2
#> 9  22 1  2 4.6    2
#> 10 23 1  1 2.7    2
#> 11 23 1  1 4.0    2
#> 12 23 1  2 3.0    2
#> 13 24 1  1 3.0    2
#> 14 24 1  1 2.0    3
#> 15 24 1  1 4.0    2
#> 16 24 1  2 2.0    3

Answer 1

A plyr solution (tmp is your data frame):

library("plyr")
ddply(tmp, .(id), function(x) x[c(1, nrow(x)), ])
#    id d gr  mm area
# 1  15 1  2 3.4    1
# 2  15 1  1 5.5    2
# 3  21 1  1 4.0    2
# 4  21 1  2 3.8    2
# 5  22 1  1 4.0    2
# 6  22 1  2 4.6    2
# 7  23 1  1 2.7    2
# 8  23 1  2 3.0    2
# 9  24 1  1 3.0    2
# 10 24 1  2 2.0    3

Or with dplyr (see also here):

library("dplyr")
tmp %>%
group_by(id) %>%
slice(c(1, n())) %>%
ungroup()
# # A tibble: 10 × 5
#       id     d    gr    mm  area
#    <int> <int> <int> <dbl> <int>
# 1     15     1     2   3.4     1
# 2     15     1     1   5.5     2
# 3     21     1     1   4.0     2
# 4     21     1     2   3.8     2
# 5     22     1     1   4.0     2
# 6     22     1     2   4.6     2
# 7     23     1     1   2.7     2
# 8     23     1     2   3.0     2
# 9     24     1     1   3.0     2
# 10    24     1     2   2.0     3