R/e_complete_multiple_keys_ALL.R
e_complete_multiple_keys.RdWhen data are combined from multiple sources and multiple identifier keys (ID) are used, sometimes in combinations, then we may want to provide the most complete set of the IDs for each observation. By definition, each key value is unique within its column to identify an observational unit.
e_complete_multiple_keys(
dat_data,
dat_keys = NULL,
col_keys = c("a", "b", "c")
)data frame with a set of variables that are keys
optional data frame with only key variables, more complete than set in dat_data
key columns names
dat_data with updated key columns
## derive dat_keys from dat_data using columns col_keys
dat_data <-
tibble::tribble(
~a, ~b, ~c, ~x, ~d1, ~d2
, 1, 11, NA, NA, 1, 20
, 1, NA, 10, NA, 2, 21
, 2, NA, NA, NA, 3, 22
, NA, 22, 20, NA, 4, 23
, 2, NA, 20, NA, 5, 24
, 3, 33, NA, NA, 6, 25
, 4, NA, 40, NA, 7, 26
, 5, NA, NA, NA, 8, 27
, 6, NA, 60, NA, 9, 28
, 6, NA, 60, NA, 10, 29
, NA, 77, NA, NA, 11, 30
, NA, 88, 80, NA, 12, 31
, NA, 88, NA, NA, 13, 32
, NA, NA, NA, NA, 14, 33
)
dat_data_updated <-
e_complete_multiple_keys(
dat_data = dat_data
, dat_keys = NULL
, col_keys = c("a", "b", "c", "x")
)
dat_data_updated %>% print(n=Inf)
#> # A tibble: 14 × 6
#> a b c x d1 d2
#> <dbl> <dbl> <dbl> <lgl> <dbl> <dbl>
#> 1 1 11 10 NA 1 20
#> 2 1 11 10 NA 2 21
#> 3 2 22 20 NA 3 22
#> 4 2 22 20 NA 4 23
#> 5 2 22 20 NA 5 24
#> 6 3 33 NA NA 6 25
#> 7 4 NA 40 NA 7 26
#> 8 5 NA NA NA 8 27
#> 9 6 NA 60 NA 9 28
#> 10 6 NA 60 NA 10 29
#> 11 NA 77 NA NA 11 30
#> 12 NA 88 80 NA 12 31
#> 13 NA 88 80 NA 13 32
#> 14 NA NA NA NA 14 33
## specify dat_keys explicitly
dat_data <-
tibble::tribble(
~a, ~b, ~c, ~x, ~d1, ~d2
, 1, 11, NA, NA, 1, 20
, 1, NA, 10, NA, 2, 21
, 2, NA, NA, NA, 3, 22
, NA, 22, 20, NA, 4, 23
, 2, NA, 20, NA, 5, 24
, 3, 33, NA, NA, 6, 25
, 4, NA, 40, NA, 7, 26
, 5, NA, NA, NA, 8, 27
, 6, NA, 60, NA, 9, 28
, 6, NA, 60, NA, 10, 29
, NA, 77, NA, NA, 11, 30
, NA, 88, 80, NA, 12, 31
, NA, 88, NA, NA, 13, 32
, NA, NA, NA, NA, 14, 33
)
dat_keys <-
tibble::tribble(
~a, ~b, ~c
, 1, 11, 10
, 2, 22, 20
, 3, 33, NA
, 4, 99, 40 # over-specified (b)
, 5, NA, NA
, 6, NA, NA # underspecified (c)
# unspecified when a=NA
)
dat_data_updated <-
e_complete_multiple_keys(
dat_data = dat_data
, dat_keys = dat_keys
, col_keys = c("a", "b", "c")
)
dat_data_updated %>% print(n=Inf)
#> # A tibble: 14 × 6
#> a b c x d1 d2
#> <dbl> <dbl> <dbl> <lgl> <dbl> <dbl>
#> 1 1 11 10 NA 1 20
#> 2 1 11 10 NA 2 21
#> 3 2 22 20 NA 3 22
#> 4 2 22 20 NA 4 23
#> 5 2 22 20 NA 5 24
#> 6 3 33 NA NA 6 25
#> 7 4 99 40 NA 7 26
#> 8 5 NA NA NA 8 27
#> 9 6 NA 60 NA 9 28
#> 10 6 NA 60 NA 10 29
#> 11 NA 77 NA NA 11 30
#> 12 NA 88 80 NA 12 31
#> 13 NA 88 NA NA 13 32
#> 14 NA NA NA NA 14 33