Here, we are not counting the number of rows in the dataset, but rather we are counting the number observations for each keys in the data.
Examples
library(dplyr)
#>
#> Attaching package: ‘dplyr’
#> The following objects are masked from ‘package:stats’:
#>
#> filter, lag
#> The following objects are masked from ‘package:base’:
#>
#> intersect, setdiff, setequal, union
# you can explore the data to see those cases that have exactly two
# observations:
heights %>%
add_n_obs() %>%
filter(n_obs == 2)
#> # A tsibble: 16 x 5 [!]
#> # Key: country [8]
#> country year n_obs continent height_cm
#> <chr> <dbl> <int> <chr> <dbl>
#> 1 Botswana 1910 2 Africa 165.
#> 2 Botswana 1980 2 Africa 167.
#> 3 Burundi 1920 2 Africa 166.
#> 4 Burundi 1930 2 Africa 169.
#> 5 Costa Rica 1940 2 Americas 166.
#> 6 Costa Rica 1980 2 Americas 174.
#> 7 El Salvador 1990 2 Americas 169.
#> 8 El Salvador 2000 2 Americas 171.
#> 9 Libya 1890 2 Africa 166.
#> 10 Libya 1920 2 Africa 165.
#> 11 Mongolia 1910 2 Asia 163.
#> 12 Mongolia 1930 2 Asia 165.
#> 13 Singapore 1970 2 Asia 172.
#> 14 Singapore 2000 2 Asia 175.
#> 15 Trinidad and Tobago 1980 2 Americas 174.
#> 16 Trinidad and Tobago 2000 2 Americas 174.