17.1 Exploring

17.1.1 naniar

http://naniar.njtierney.com/

library(naniar)

17.1.1.1 Shadown matrices

17.1.1.2 Summaries

17.1.1.3 Visualizations

http://naniar.njtierney.com/articles/naniar-visualisation.html

ggplot(airquality) + 
  geom_miss_point(aes(Ozone, Solar.R))

ggplot(data = airquality,
       aes(x = Ozone,
           y = Solar.R)) + 
  geom_miss_point() + 
  facet_wrap(~Month, ncol = 2) + 
  theme(legend.position = "bottom")

gg_miss_upset(airquality)

gg_miss_upset(riskfactors)

17.1.2 Replace a value with NA

It’s worth to mention one dplyr functions that does the same thing:
dplyr::na_if()

y <- c("abc", "def", "", "ghi")
na_if(y, "")
#> [1] "abc" "def" NA    "ghi"

# na_if is particularly useful inside mutate,
# and is meant for use with vectors rather than entire data frames
starwars %>%
  select(name, eye_color) %>%
  mutate(eye_color = na_if(eye_color, "unknown"))
#> # A tibble: 87 x 2
#>   name           eye_color
#>   <chr>          <chr>    
#> 1 Luke Skywalker blue     
#> 2 C-3PO          yellow   
#> 3 R2-D2          red      
#> 4 Darth Vader    yellow   
#> 5 Leia Organa    brown    
#> 6 Owen Lars      blue     
#> # ... with 81 more rows

article: http://naniar.njtierney.com/articles/replace-with-na.html

df <- tibble::tribble(
  ~name,           ~x,  ~y,              ~z,  
  "N/A",           1,   "N/A",           -100, 
  "N A",           3,   "NOt available", -99,
  "N / A",         NA,  "29",              -98,
  "Not Available", -99, "25",              -101,
  "John Smith",    -98, "28",              -1)

df %>% replace_with_na(replace = list(x = -99))
#> # A tibble: 5 x 4
#>   name              x y                 z
#>   <chr>         <dbl> <chr>         <dbl>
#> 1 N/A               1 N/A            -100
#> 2 N A               3 NOt available   -99
#> 3 N / A            NA 29              -98
#> 4 Not Available    NA 25             -101
#> 5 John Smith      -98 28               -1

df %>% replace_with_na(replace = list(x = c(-99, -98)))
#> # A tibble: 5 x 4
#>   name              x y                 z
#>   <chr>         <dbl> <chr>         <dbl>
#> 1 N/A               1 N/A            -100
#> 2 N A               3 NOt available   -99
#> 3 N / A            NA 29              -98
#> 4 Not Available    NA 25             -101
#> 5 John Smith       NA 28               -1

df %>%
  replace_with_na(replace = list(x = c(-99,-98),
                             z = c(-99, -98)))
#> # A tibble: 5 x 4
#>   name              x y                 z
#>   <chr>         <dbl> <chr>         <dbl>
#> 1 N/A               1 N/A            -100
#> 2 N A               3 NOt available    NA
#> 3 N / A            NA 29               NA
#> 4 Not Available    NA 25             -101
#> 5 John Smith       NA 28               -1

df %>% replace_with_na_all(condition = ~.x == -99)
#> # A tibble: 5 x 4
#>   name              x y                 z
#>   <chr>         <dbl> <chr>         <dbl>
#> 1 N/A               1 N/A            -100
#> 2 N A               3 NOt available    NA
#> 3 N / A            NA 29              -98
#> 4 Not Available    NA 25             -101
#> 5 John Smith      -98 28               -1

common_na_numbers
#> [1]    -9   -99  -999 -9999  9999    66    77    88

common_na_strings
#>  [1] "NA"     "N A"    "N/A"    "NA "    " NA"    "N /A"   "N / A"  " N / A"
#>  [9] "N / A " "na"     "n a"    "n/a"    "na "    " na"    "n /a"   "n / a" 
#> [17] " a / a" "n / a " "NULL"   "null"   ""       "\\?"    "\\*"    "\\."

df %>% replace_with_na_all(~.x %in% common_na_strings)
#> # A tibble: 5 x 4
#>   name              x y                 z
#>   <chr>         <dbl> <chr>         <dbl>
#> 1 <NA>              1 <NA>           -100
#> 2 <NA>              3 NOt available   -99
#> 3 <NA>             NA 29              -98
#> 4 Not Available   -99 25             -101
#> 5 John Smith      -98 28               -1

17.1.3 janitor

janitor::tabyl() generates a frequency table and exposing missing values at the same time

janitor::tabyl(df, y)
#>              y n percent
#>             25 1     0.2
#>             28 1     0.2
#>             29 1     0.2
#>            N/A 1     0.2
#>  NOt available 1     0.2

17.1.4 sjmisc

when missing variable is factor sjmisc::frq