Store different representations of missing values in a new column? about allodb HOT 3 CLOSED

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
library(allodb)

# All columns as text
allodb::wsg %>% 
  filter(sample_size == "NRA")
#> # A tibble: 16 x 8
#>    wsg_id family  species   wsg   wsg_specificity sample_size site  ref_id
#>    <chr>  <chr>   <chr>     <chr> <chr>           <chr>       <chr> <chr> 
#>  1 <NA>   Rhamna~ Ceanothu~ 0.67  <NA>            NRA         UCSC  <NA>  
#>  2 <NA>   Grossu~ Ribes di~ 0.73  <NA>            NRA         UCSC  <NA>  
#>  3 <NA>   Ericac~ Vacciniu~ 0.47  <NA>            NRA         UCSC  <NA>  
#>  4 <NA>   Rosace~ Holodisc~ 0.71  <NA>            NRA         Wind~ <NA>  
#>  5 <NA>   Rosace~ Rubus le~ NRA   <NA>            NRA         Wind~ <NA>  
#>  6 <NA>   Rosace~ Rubus sp~ NRA   <NA>            NRA         Wind~ <NA>  
#>  7 <NA>   Ericac~ Vacciniu~ 0.47  <NA>            NRA         Wind~ <NA>  
#>  8 <NA>   Ericac~ Vacciniu~ 0.47  <NA>            NRA         Wind~ <NA>  
#>  9 <NA>   Ericac~ Vacciniu~ 0.47  <NA>            NRA         Wind~ <NA>  
#> 10 <NA>   Ericac~ Arctosta~ 0.72  <NA>            NRA         Yose~ <NA>  
#> 11 <NA>   Rhamna~ Ceanothu~ 0.67  <NA>            NRA         Yose~ <NA>  
#> 12 <NA>   Rhamna~ Ceanothu~ 0.67  <NA>            NRA         Yose~ <NA>  
#> 13 <NA>   Rhamna~ Ceanothu~ 0.67  <NA>            NRA         Yose~ <NA>  
#> 14 <NA>   Rosace~ Holodisc~ 0.71  <NA>            NRA         Yose~ <NA>  
#> 15 <NA>   Grossu~ Ribes ne~ NRA   <NA>            NRA         Yose~ <NA>  
#> 16 <NA>   Grossu~ Ribes ro~ NRA   <NA>            NRA         Yose~ <NA>

# Preserves different representations of missing values, e.g. "NRA".
allodb::wsg %>% 
  filter(sample_size == "NRA")
#> # A tibble: 16 x 8
#>    wsg_id family  species   wsg   wsg_specificity sample_size site  ref_id
#>    <chr>  <chr>   <chr>     <chr> <chr>           <chr>       <chr> <chr> 
#>  1 <NA>   Rhamna~ Ceanothu~ 0.67  <NA>            NRA         UCSC  <NA>  
#>  2 <NA>   Grossu~ Ribes di~ 0.73  <NA>            NRA         UCSC  <NA>  
#>  3 <NA>   Ericac~ Vacciniu~ 0.47  <NA>            NRA         UCSC  <NA>  
#>  4 <NA>   Rosace~ Holodisc~ 0.71  <NA>            NRA         Wind~ <NA>  
#>  5 <NA>   Rosace~ Rubus le~ NRA   <NA>            NRA         Wind~ <NA>  
#>  6 <NA>   Rosace~ Rubus sp~ NRA   <NA>            NRA         Wind~ <NA>  
#>  7 <NA>   Ericac~ Vacciniu~ 0.47  <NA>            NRA         Wind~ <NA>  
#>  8 <NA>   Ericac~ Vacciniu~ 0.47  <NA>            NRA         Wind~ <NA>  
#>  9 <NA>   Ericac~ Vacciniu~ 0.47  <NA>            NRA         Wind~ <NA>  
#> 10 <NA>   Ericac~ Arctosta~ 0.72  <NA>            NRA         Yose~ <NA>  
#> 11 <NA>   Rhamna~ Ceanothu~ 0.67  <NA>            NRA         Yose~ <NA>  
#> 12 <NA>   Rhamna~ Ceanothu~ 0.67  <NA>            NRA         Yose~ <NA>  
#> 13 <NA>   Rhamna~ Ceanothu~ 0.67  <NA>            NRA         Yose~ <NA>  
#> 14 <NA>   Rosace~ Holodisc~ 0.71  <NA>            NRA         Yose~ <NA>  
#> 15 <NA>   Grossu~ Ribes ne~ NRA   <NA>            NRA         Yose~ <NA>  
#> 16 <NA>   Grossu~ Ribes ro~ NRA   <NA>            NRA         Yose~ <NA>



# All columns of the type that is most suitable for computation**
# E.g.: Notice that `sample_size` is integer.
as_allodb(allodb::wsg)
#> # A tibble: 419 x 8
#>    wsg_id family  species   wsg   wsg_specificity sample_size site  ref_id
#>  * <chr>  <chr>   <chr>     <chr> <chr>                 <int> <chr> <chr> 
#>  1 <NA>   Sapind~ Acer rub~ 0.49  <NA>                     NA Lill~ <NA>  
#>  2 <NA>   Sapind~ Acer sac~ 0.56  <NA>                     NA Lill~ <NA>  
#>  3 <NA>   Rosace~ Amelanch~ 0.66  <NA>                     NA Lill~ <NA>  
#>  4 <NA>   Rosace~ Amelanch~ 0.66  <NA>                     NA Lill~ <NA>  
#>  5 <NA>   Rosace~ Amelanch~ 0.66  <NA>                     NA Lill~ <NA>  
#>  6 <NA>   Annona~ Asimina ~ 0.47  <NA>                     NA Lill~ <NA>  
#>  7 <NA>   Betula~ Carpinus~ 0.58  <NA>                     NA Lill~ <NA>  
#>  8 <NA>   Juglan~ Carya al~ 0.62  <NA>                     10 Lill~ <NA>  
#>  9 <NA>   Juglan~ Carya co~ 0.6   <NA>                     10 Lill~ <NA>  
#> 10 <NA>   Juglan~ Carya gl~ 0.66  <NA>                     10 Lill~ <NA>  
#> # ... with 409 more rows

# Weird representation of missing values are lost (e.g. no more "NRA"")
as_allodb(allodb::wsg) %>% 
  filter(sample_size == "NRA")
#> # A tibble: 0 x 8
#> # ... with 8 variables: wsg_id <chr>, family <chr>, species <chr>,
#> #   wsg <chr>, wsg_specificity <chr>, sample_size <int>, site <chr>,
#> #   ref_id <chr>



# ** Notice a possible bug: `wsg` should be double -- not character.