Full list of problematic values from `dm_examine_constraints()`

[asadow]

Is it possible to receive the full list of problem values from dm_examine_constraints() instead of ... below?

library(dm)
#> 
#> Attaching package: 'dm'
#> The following object is masked from 'package:stats':
#> 
#>     filter
dm <- dm_nycflights13(cycle = TRUE)
output <- dm_examine_constraints(dm)
output$problem
#> [1] "values of `flights$dest` not in `airports$faa`: SJU (30), BQN (6), STT (4), PSE (2)"                               
#> [2] "values of `flights$tailnum` not in `planes$tailnum`: N725MQ (6), N537MQ (5), N722MQ (5), N730MQ (5), N736MQ (5), …"
#> [3] ""                                                                                                                  
#> [4] ""                                                                                                                  
#> [5] ""                                                                                                                  
#> [6] ""                                                                                                                  
#> [7] ""                                                                                                                  
#> [8] ""                                                                                                                  
#> [9] ""

^{Created on 2024-03-04 with reprex v2.1.0}

[TSchiefer]

not as part of {dm}, you would need to create this list yourself from the info given in the output, e.g.:

suppressPackageStartupMessages({
  library(dm)
  library(tidyverse)
})

dm <- dm_nycflights13(cycle = TRUE)
output <- dm_examine_constraints(dm)

problematic <- as_tibble(output) %>% 
  filter(!is_key)

problematic
#> # A tibble: 2 × 6
#>   table   kind  columns ref_table is_key problem                                
#>   <chr>   <chr> <keys>  <chr>     <lgl>  <chr>                                  
#> 1 flights FK    dest    airports  FALSE  values of `flights$dest` not in `airpo…
#> 2 flights FK    tailnum planes    FALSE  values of `flights$tailnum` not in `pl…

# full list of entries in flights$dest that are not in airports$faa:
anti_join(
  dm$flights,
  dm$airports,
  by = c("dest" = "faa")
)
#> # A tibble: 42 × 19
#>     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
#>    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
#>  1  2013     1    10        3           2359         4      426            437
#>  2  2013     1    10       16           2359        17      447            444
#>  3  2013     1    10      535            540        -5     1015           1017
#>  4  2013     1    10      610            610         0     1028           1051
#>  5  2013     1    10      633            630         3     1142           1140
#>  6  2013     1    10      705            710        -5     1158           1203
#>  7  2013     1    10      742            745        -3     1214           1234
#>  8  2013     1    10      807            810        -3     1247           1315
#>  9  2013     1    10      818            819        -1     1251           1307
#> 10  2013     1    10      828            830        -2     1258           1335
#> # ℹ 32 more rows
#> # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
#> #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
#> #   hour <dbl>, minute <dbl>, time_hour <dttm>

# count per entry (partly given in the output of `dm_examine_constraints()`):
anti_join(
  dm$flights,
  dm$airports,
  by = c("dest" = "faa")
) %>% 
  count(dest) %>% 
  arrange(desc(n))
#> # A tibble: 4 × 2
#>   dest      n
#>   <chr> <int>
#> 1 SJU      30
#> 2 BQN       6
#> 3 STT       4
#> 4 PSE       2

# full list of entries in flights$tailnum that are not in planes$tailnum:
anti_join(
  dm$flights,
  dm$planes,
  by = "tailnum"
)
#> # A tibble: 282 × 19
#>     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
#>    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
#>  1  2013     1    10      531            540        -9      832            850
#>  2  2013     1    10      553            600        -7      837            910
#>  3  2013     1    10      555            600        -5      733            745
#>  4  2013     1    10      555            605       -10      746            805
#>  5  2013     1    10      556            600        -4      818            825
#>  6  2013     1    10      604            610        -6      851            910
#>  7  2013     1    10      604            610        -6      858            915
#>  8  2013     1    10      606            615        -9      740            750
#>  9  2013     1    10      619            630       -11      814            830
#> 10  2013     1    10      621            630        -9      823            830
#> # ℹ 272 more rows
#> # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
#> #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
#> #   hour <dbl>, minute <dbl>, time_hour <dttm>

# count per entry
anti_join(
  dm$flights,
  dm$planes,
  by = "tailnum"
) %>% 
  count(tailnum) %>% 
  arrange(desc(n))
#> # A tibble: 167 × 2
#>    tailnum     n
#>    <chr>   <int>
#>  1 <NA>        9
#>  2 N725MQ      6
#>  3 N537MQ      5
#>  4 N722MQ      5
#>  5 N730MQ      5
#>  6 N736MQ      5
#>  7 N3GBAA      4
#>  8 N509MQ      4
#>  9 N719MQ      4
#> 10 N723MQ      4
#> # ℹ 157 more rows

^{Created on 2024-03-04 with reprex v2.0.2}