naniar

https://naniar.njtierney.com/
Admin
naniar is an R package that provides principled, tidy ways to summarise, visualise, and manipulate...
Tokens:77,455
Snippets:578
Trust Score:9
Update:6 months ago
Show doc for...
Tokens:
Raw
### Impute Median Examples

Source: https://naniar.njtierney.com/reference/impute_median.html

Examples demonstrating how to use impute_median on vectors and within dplyr pipelines.

```R
vec <- rnorm(10)

vec[sample(1:10, 3)] <- NA

impute_median(vec)
```

```R
library(dplyr)

dat <- tibble(
  num = rnorm(10),
  int = as.integer(rpois(10, 5)),
  fct = factor(LETTERS[1:10])
) %>%
  mutate(
    across(
      everything(),
      \(x) set_prop_miss(x, prop = 0.25)
    )
  )

dat
```

```R
dat %>%
  nabular() %>%
  mutate(
    num = impute_median(num),
    int = impute_median(int),
  )
```

```R
dat %>%
  nabular() %>%
  mutate(
    across(
      where(is.numeric),
      impute_median
    )
  )
```

```R
dat %>%
  nabular() %>%
  mutate(
    across(
      c("num", "int"),
      impute_median
    )
 )
```

--------------------------------

### Add Label Shadow Example

Source: https://naniar.njtierney.com/reference/add_label_shadow.html

Example of using add_label_shadow in a pipeline with airquality data to identify rows with missing values.

```R
airquality %>%
  add_shadow(Ozone, Solar.R) %>%
  add_label_shadow()
```

--------------------------------

### Example of gather_shadow with airquality dataset

Source: https://naniar.njtierney.com/reference/gather_shadow.html

Demonstrates the output format of gather_shadow using the built-in airquality dataset.

```R
gather_shadow(airquality)
#> # A tibble: 918 × 3
#>     case variable   missing
#>    <int> <chr>      <fct>  
#>  1     1 Ozone_NA   !NA    
#>  2     1 Solar.R_NA !NA    
#>  3     1 Wind_NA    !NA    
#>  4     1 Temp_NA    !NA    
#>  5     1 Month_NA   !NA    
#>  6     1 Day_NA     !NA    
#>  7     2 Ozone_NA   !NA    
#>  8     2 Solar.R_NA !NA    
#>  9     2 Wind_NA    !NA    
#> 10     2 Temp_NA    !NA    
#> # ℹ 908 more rows
```

--------------------------------

### Example of recode_shadow with .where

Source: https://naniar.njtierney.com/reference/where.html

Demonstrates how to use .where inside recode_shadow to conditionally recode shadow variables.

```R
if (FALSE) { # \dontrun{
df <- tibble::tribble(
~wind, ~temp,
-99,    45,
68,    NA,
72,    25
)

dfs <- bind_shadow(df)

recode_shadow(dfs,
              temp = .where(wind == -99 ~ "bananas"))

} # }
```

--------------------------------

### Install naniar Development Version

Source: https://naniar.njtierney.com/index.html

Install the latest development version of the naniar package from GitHub using the remotes package.

```r
# install.packages("remotes")
remotes::install_github("njtierney/naniar")
```

--------------------------------

### Install naniar from CRAN

Source: https://naniar.njtierney.com/index.html

Use this command to install the stable version of the naniar package from CRAN.

```r
install.packages("naniar")
```

--------------------------------

### Examples of cast_shadow_shift

Source: https://naniar.njtierney.com/reference/cast_shadow_shift.html

Demonstrates applying cast_shadow_shift to specific columns and using tidyselect helpers.

```R
airquality %>% cast_shadow_shift(Ozone,Temp)

airquality %>% cast_shadow_shift(dplyr::contains("o"))
```

--------------------------------

### Recoding Shadow Matrix Examples

Source: https://naniar.njtierney.com/reference/recode_shadow.html

Demonstrates creating a shadow matrix with bind_shadow and applying custom labels to missing values using recode_shadow.

```R
df <- tibble::tribble(
~wind, ~temp,
-99,    45,
68,    NA,
72,    25
)

dfs <- bind_shadow(df)

dfs
#> # A tibble: 3 × 4
#>    wind  temp wind_NA temp_NA
#>   <dbl> <dbl> <fct>   <fct>  
#> 1   -99    45 !NA     !NA    
#> 2    68    NA !NA     NA     
#> 3    72    25 !NA     !NA    

recode_shadow(dfs, temp = .where(wind == -99 ~ "bananas"))
#> # A tibble: 3 × 4
#>    wind  temp wind_NA temp_NA   
#>   <dbl> <dbl> <fct>   <fct>     
#> 1   -99    45 !NA     NA_bananas
#> 2    68    NA !NA     NA        
#> 3    72    25 !NA     !NA       

recode_shadow(dfs,
              temp = .where(wind == -99 ~ "bananas")) %>%
recode_shadow(wind = .where(wind == -99 ~ "apples"))
#> # A tibble: 3 × 4
#>    wind  temp wind_NA   temp_NA   
#>   <dbl> <dbl> <fct>     <fct>     
#> 1   -99    45 NA_apples NA_bananas
#> 2    68    NA !NA       NA        
#> 3    72    25 !NA       !NA       
```

--------------------------------

### Example usage of proportion functions

Source: https://naniar.njtierney.com/reference/pct-miss-complete-var.html

Demonstrates calculating the proportion of variables with missing or complete values using the airquality dataset.

```R
prop_miss_var(airquality)
#> [1] 0.3333333
prop_complete_var(airquality)
#> [1] 0.6666667
```

--------------------------------

### Example of `as_shadow_upset()` and `UpSetR::upset()` workflow

Source: https://naniar.njtierney.com/news/index.html

This code block shows the previous workflow for generating upset plots using `as_shadow_upset()` and `UpSetR::upset()`.

```R
data %>%
  as_shadow_upset() %>%
  UpSetR::upset()
```

--------------------------------

### Example of label_miss_1d

Source: https://naniar.njtierney.com/reference/label_miss_1d.html

Demonstrates labeling missing values in the Ozone column of the airquality dataset.

```R
label_miss_1d(airquality$Ozone)
#>   [1] Not Missing Not Missing Not Missing Not Missing Missing     Not Missing
#>  [7] Not Missing Not Missing Not Missing Missing     Not Missing Not Missing
#>  [13] Not Missing Not Missing Not Missing Not Missing Not Missing Not Missing
#>  [19] Not Missing Not Missing Not Missing Not Missing Not Missing Not Missing
#>  [25] Missing     Missing     Missing     Not Missing Not Missing Not Missing
#>  [31] Not Missing Missing     Missing     Missing     Missing     Missing    
#>  [37] Missing     Not Missing Missing     Not Missing Not Missing Missing    
#>  [43] Missing     Not Missing Missing     Missing     Not Missing Not Missing
#>  [49] Not Missing Not Missing Not Missing Missing     Missing     Missing    
#>  [55] Missing     Missing     Missing     Missing     Missing     Missing    
#>  [61] Missing     Not Missing Not Missing Not Missing Missing     Not Missing
#>  [67] Not Missing Not Missing Not Missing Not Missing Not Missing Missing    
#>  [73] Not Missing Not Missing Missing     Not Missing Not Missing Not Missing
#>  [79] Not Missing Not Missing Not Missing Not Missing Missing     Missing    
#>  [85] Not Missing Not Missing Not Missing Not Missing Not Missing Not Missing
#>  [91] Not Missing Not Missing Not Missing Not Missing Not Missing Not Missing
#>  [97] Not Missing Not Missing Not Missing Not Missing Not Missing Missing    
#> [103] Missing     Not Missing Not Missing Not Missing Missing     Not Missing
#> [109] Not Missing Not Missing Not Missing Not Missing Not Missing Not Missing
#> [115] Missing     Not Missing Not Missing Not Missing Missing     Not Missing
#> [121] Not Missing Not Missing Not Missing Not Missing Not Missing Not Missing
#> [127] Not Missing Not Missing Not Missing Not Missing Not Missing Not Missing
#> [133] Not Missing Not Missing Not Missing Not Missing Not Missing Not Missing
#> [139] Not Missing Not Missing Not Missing Not Missing Not Missing Not Missing
#> [145] Not Missing Not Missing Not Missing Not Missing Not Missing Missing    
#> [151] Not Missing Not Missing Not Missing
#> Levels: Missing Not Missing
```

--------------------------------

### Examples of miss_summary

Source: https://naniar.njtierney.com/reference/miss_summary.html

Demonstrates how to access specific summary components from the returned object and how to use the function with grouped data.

```R
s_miss <- miss_summary(airquality)
s_miss$miss_df_prop
#> [1] 0.04793028
s_miss$miss_case_table
#> [[1]]
#> # A tibble: 3 × 3
#>   n_miss_in_case n_cases pct_cases
#>            <int>   <int>     <dbl>
#> 1              0     111     72.5 
#> 2              1      40     26.1 
#> 3              2       2      1.31
#> 
s_miss$miss_var_summary
#> [[1]]
#> # A tibble: 6 × 3
#>   variable n_miss pct_miss
#>   <chr>     <int>    <num>
#> 1 Ozone        37    24.2 
#> 2 Solar.R       7     4.58
#> 3 Wind          0     0   
#> 4 Temp          0     0   
#> 5 Month         0     0   
#> 6 Day           0     0   
#> 
# etc, etc, etc.

if (FALSE) { # \dontrun{
library(dplyr)
s_miss_group <- group_by(airquality, Month) %>% miss_summary()
s_miss_group$miss_df_prop
s_miss_group$miss_case_table
# etc, etc, etc.
} # }
```

--------------------------------

### Advanced gg_miss_case configurations

Source: https://naniar.njtierney.com/reference/gg_miss_case.html

Examples demonstrating customization of the plot using ggplot2 themes, percentage display, ordering, and faceting.

```R
library(ggplot2)
gg_miss_case(airquality) + labs(x = "Number of Cases")
gg_miss_case(airquality, show_pct = TRUE)
gg_miss_case(airquality, order_cases = FALSE)
gg_miss_case(airquality, facet = Month)
gg_miss_case(airquality, facet = Month, order_cases = FALSE)
gg_miss_case(airquality, facet = Month, show_pct = TRUE)
```

--------------------------------

### Examples of add_label_missings

Source: https://naniar.njtierney.com/reference/add_label_missings.html

Demonstrates labeling rows as missing or complete using the airquality dataset with default and custom labels.

```R
airquality %>% add_label_missings()
```

```R
airquality %>% add_label_missings(Ozone, Solar.R)
```

```R
airquality %>% add_label_missings(Ozone, Solar.R, missing = "yes", complete = "no")
```

--------------------------------

### Example of impute_zero

Source: https://naniar.njtierney.com/reference/impute_zero.html

Demonstrates replacing missing values in a numeric vector with zero and using it within a data pipeline.

```R
vec <- rnorm(10)

vec[sample(1:10, 3)] <- NA

vec
#>  [1]          NA -0.25705805 -1.41422789  0.01887104  0.35647301  0.89006961
#>  [7]          NA          NA  0.43744452 -1.65606748

impute_zero(vec)
#>  [1]  0.00000000 -0.25705805 -1.41422789  0.01887104  0.35647301  0.89006961
#>  [7]  0.00000000  0.00000000  0.43744452 -1.65606748

library(dplyr)

dat <- tibble(
  num = rnorm(10),
  int = rpois(10, 5),
  fct = factor(LETTERS[1:10])
) %>%
  mutate(
    across(
      everything(),
      \(x) set_prop_miss(x, prop = 0.25)
    )
  )

dat
#> # A tibble: 10 × 3
#>       num   int fct  
#>     <dbl> <int> <fct>
#>  1 -1.30      5 A    
#>  2  2.19      3 B    
#>  3 -0.303    NA C    
#>  4  1.36      2 NA   
#>  5 -0.744     5 E    
#>  6 NA         6 NA   
#>  7  1.76      7 G    
#>  8  0.724    NA H    
#>  9 NA         3 I    
#> 10  1.38      7 J    

dat %>%
  nabular() %>%
  mutate(
    num = impute_fixed(num, -9999),
    int = impute_zero(int),
    fct = impute_factor(fct, "out")
  )
#> # A tibble: 10 × 6
#>          num   int fct   num_NA int_NA fct_NA
#>        <dbl> <dbl> <fct> <fct>  <fct>  <fct> 
#>  1    -1.30      5 A     !NA    !NA    !NA   
#>  2     2.19      3 B     !NA    !NA    !NA   
#>  3    -0.303     0 C     !NA    NA     !NA   
#>  4     1.36      2 out   !NA    !NA    NA    
#>  5    -0.744     5 E     !NA    !NA    !NA   
#>  6 -9999         6 out   NA     !NA    NA    
#>  7     1.76      7 G     !NA    !NA    !NA   
#>  8     0.724     0 H     !NA    NA     !NA   
#>  9 -9999         3 I     NA     !NA    !NA   
#> 10     1.38      7 J     !NA    !NA    !NA   
```

--------------------------------

### Examples of impute_mean usage

Source: https://naniar.njtierney.com/reference/impute_mean.html

Demonstrates applying impute_mean to a simple vector and within a dplyr pipeline using nabular data.

```R
library(dplyr)
vec <- rnorm(10)

vec[sample(1:10, 3)] <- NA

impute_mean(vec)
#>  [1]  0.5301633  0.7462801  1.3446716  0.5301633 -0.4860343  0.8088018
#>  [7]  0.3218633  0.0581052  0.5301633  0.9174552

dat <- tibble(
  num = rnorm(10),
  int = as.integer(rpois(10, 5)),
  fct = factor(LETTERS[1:10])
) %>%
  mutate(
    across(
      everything(),
      \(x) set_prop_miss(x, prop = 0.25)
    )
  )

dat
#> # A tibble: 10 × 3
#>       num   int fct  
#>     <dbl> <int> <fct>
#>  1 NA         7 A    
#>  2  1.35     NA B    
#>  3 NA         4 C    
#>  4  0.590     4 NA   
#>  5  1.23      5 E    
#>  6 -1.42     NA F    
#>  7 -1.04      9 NA   
#>  8  1.28      3 H    
#>  9 -1.31      7 I    
#> 10  1.60      6 J    

dat %>%
  nabular() %>%
  mutate(
    num = impute_mean(num),
    int = impute_mean(int),
    fct = impute_mean(fct),
  )
#> # A tibble: 10 × 6
#>       num   int fct   num_NA int_NA fct_NA
#>     <dbl> <dbl> <fct> <fct>  <fct>  <fct> 
#>  1  0.285  7    A     NA     !NA    !NA   
#>  2  1.35   5.62 B     !NA    NA     !NA   
#>  3  0.285  4    C     NA     !NA    !NA   
#>  4  0.590  4    J     !NA    !NA    NA    
#>  5  1.23   5    E     !NA    !NA    !NA   
#>  6 -1.42   5.62 F     !NA    NA     !NA   
#>  7 -1.04   9    J     !NA    !NA    NA    
#>  8  1.28   3    H     !NA    !NA    !NA   
#>  9 -1.31   7    I     !NA    !NA    !NA   
#> 10  1.60   6    J     !NA    !NA    !NA   

dat %>%
  nabular() %>%
  mutate(
    across(
      where(is.numeric),
      impute_mean
    )
  )
#> # A tibble: 10 × 6
#>       num   int fct   num_NA int_NA fct_NA
#>     <dbl> <dbl> <fct> <fct>  <fct>  <fct> 
#>  1  0.285  7    A     NA     !NA    !NA   
#>  2  1.35   5.62 B     !NA    NA     !NA   
#>  3  0.285  4    C     NA     !NA    !NA   
#>  4  0.590  4    NA    !NA    !NA    NA    
#>  5  1.23   5    E     !NA    !NA    !NA   
#>  6 -1.42   5.62 F     !NA    NA     !NA   
#>  7 -1.04   9    NA    !NA    !NA    NA    
#>  8  1.28   3    H     !NA    !NA    !NA   
#>  9 -1.31   7    I     !NA    !NA    !NA   
#> 10  1.60   6    J     !NA    !NA    !NA   

dat %>%
  nabular() %>%
  mutate(
    across(
      c("num", "int"),
      impute_mean
    )
  )
#> # A tibble: 10 × 6
#>       num   int fct   num_NA int_NA fct_NA
#>     <dbl> <dbl> <fct> <fct>  <fct>  <fct> 
#>  1  0.285  7    A     NA     !NA    !NA   
#>  2  1.35   5.62 B     !NA    NA     !NA   
#>  3  0.285  4    C     NA     !NA    !NA   
#>  4  0.590  4    NA    !NA    !NA    NA    
#>  5  1.23   5    E     !NA    !NA    !NA   
#>  6 -1.42   5.62 F     !NA    NA     !NA   
#>  7 -1.04   9    NA    !NA    !NA    NA    
#>  8  1.28   3    H     !NA    !NA    !NA   
#>  9 -1.31   7    I     !NA    !NA    !NA   
#> 10  1.60   6    J     !NA    !NA    !NA   
```

--------------------------------

### Create Example Data Frame

Source: https://naniar.njtierney.com/articles/replace-with-na.html

Creates a sample tibble with various representations of missing values, including strings and numeric codes, for demonstrating NA replacement.

```r
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)

```

--------------------------------

### Examples of pct_miss

Source: https://naniar.njtierney.com/reference/pct_miss.html

Demonstrates calculating the percentage of missing values for a data frame and a specific vector.

```R
pct_miss(airquality)
#> [1] 4.793028
pct_miss(airquality$Ozone)
#> [1] 24.18301
```

--------------------------------

### Examples of miss_scan_count

Source: https://naniar.njtierney.com/reference/miss_scan_count.html

Demonstrates searching for numeric values, character strings, and special characters using regular expressions.

```R
dat_ms <- tibble::tribble(~x,  ~y,    ~z,  ~specials,
                         1,   "A",   -100, "?",
                         3,   "N/A", -99,  "!",
                         NA,  NA,    -98,  ".",
                         -99, "E",   -101, "*",
                         -98, "F",   -1,  "-")

miss_scan_count(dat_ms,-99)
#> # A tibble: 4 × 2
#>   Variable     n
#>   <chr>    <int>
#> 1 x            1
#> 2 y            0
#> 3 z            1
#> 4 specials     0
miss_scan_count(dat_ms,c(-99,-98))
#> # A tibble: 4 × 2
#>   Variable     n
#>   <chr>    <int>
#> 1 x            2
#> 2 y            0
#> 3 z            2
#> 4 specials     0
miss_scan_count(dat_ms,c("-99","-98","N/A"))
#> # A tibble: 4 × 2
#>   Variable     n
#>   <chr>    <int>
#> 1 x            2
#> 2 y            1
#> 3 z            2
#> 4 specials     0
miss_scan_count(dat_ms, "\\?")
#> # A tibble: 4 × 2
#>   Variable     n
#>   <chr>    <int>
#> 1 x            0
#> 2 y            0
#> 3 z            0
#> 4 specials     1
miss_scan_count(dat_ms, "\\!")
#> # A tibble: 4 × 2
#>   Variable     n
#>   <chr>    <int>
#> 1 x            0
#> 2 y            0
#> 3 z            0
#> 4 specials     1
miss_scan_count(dat_ms, "\\.")
#> # A tibble: 4 × 2
#>   Variable     n
#>   <chr>    <int>
#> 1 x            0
#> 2 y            0
#> 3 z            0
#> 4 specials     1
miss_scan_count(dat_ms, "\\*")
#> # A tibble: 4 × 2
#>   Variable     n
#>   <chr>    <int>
#> 1 x            0
#> 2 y            0
#> 3 z            0
#> 4 specials     1
miss_scan_count(dat_ms, "-")
#> # A tibble: 4 × 2
#>   Variable     n
#>   <chr>    <int>
#> 1 x            2
#> 2 y            0
#> 3 z            5
#> 4 specials     1
miss_scan_count(dat_ms,common_na_strings)
#> # A tibble: 4 × 2
#>   Variable     n
#>   <chr>    <int>
#> 1 x            4
#> 2 y            4
#> 3 z            5
#> 4 specials     5
```

--------------------------------

### Impute Mode Examples

Source: https://naniar.njtierney.com/reference/impute_mode.html

Demonstration of imputing missing values in a numeric vector and within a tibble using naniar's nabular format.

```R
vec <- rnorm(10)

vec[sample(1:10, 3)] <- NA

impute_mode(vec)

library(dplyr)

dat <- tibble(
  num = rnorm(10),
  int = rpois(10, 5),
  fct = factor(LETTERS[1:10])
) %>%
  mutate(
    across(
      everything(),
      \(x) set_prop_miss(x, prop = 0.25)
    )
  )

dat

dat %>%
  nabular() %>%
  mutate(
    num = impute_mode(num),
    int = impute_mode(int),
    fct = impute_mode(fct)
  )
```

--------------------------------

### Demonstrate na_if length constraint

Source: https://naniar.njtierney.com/articles/replace-with-na.html

Example showing that dplyr::na_if cannot accept vectors of length greater than one.

```R
# Not run:
df_4 <- df %>% dplyr::na_if(x = ., y = na_strings)
# Error in check_length(y, x, fmt_args("y"), glue("same as {fmt_args(~x)}")) :
  # argument "y" is missing, with no default
```

--------------------------------

### Explore Missing Data Visually with ggplot2

Source: https://naniar.njtierney.com/reference/bind_shadow.html

This example demonstrates how to use the output of `bind_shadow` with `ggplot2` to visualize missing data. It facets the histogram of Ozone by whether Solar Radiation is missing or not.

```R
library(ggplot2)

# using the bounded shadow to visualise Ozone according to whether Solar
# Radiation is missing or not.

ggplot(data = aq_shadow,
       aes(x = Ozone)) +   geom_histogram() +   facet_wrap(~Solar.R_NA,
       ncol = 1)
```

--------------------------------

### Replace values with NA using naniar

Source: https://naniar.njtierney.com/reference/replace_with_na_at.html

Examples demonstrating how to replace values with NA in a tibble based on single or multiple column conditions.

```R
dat_ms <- tibble::tribble(~x,  ~y,    ~z,
                          1,   "A",   -100,
                          3,   "N/A", -99,
                          NA,  NA,    -98,
                          -99, "E",   -101,
                          -98, "F",   -1)

dat_ms
#> # A tibble: 5 × 3
#>       x y         z
#>   <dbl> <chr> <dbl>
#> 1     1 A      -100
#> 2     3 N/A     -99
#> 3    NA NA      -98
#> 4   -99 E      -101
#> 5   -98 F        -1

replace_with_na_at(data = dat_ms,
                 .vars = "x",
                 condition = ~.x == -99)
#> # A tibble: 5 × 3
#>       x y         z
#>   <dbl> <chr> <dbl>
#> 1     1 A      -100
#> 2     3 N/A     -99
#> 3    NA NA      -98
#> 4    NA E      -101
#> 5   -98 F        -1

replace_with_na_at(data = dat_ms,
                 .vars = c("x","z"),
                 condition = ~.x == -99)
#> # A tibble: 5 × 3
#>       x y         z
#>   <dbl> <chr> <dbl>
#> 1     1 A      -100
#> 2     3 N/A      NA
#> 3    NA NA      -98
#> 4    NA E      -101
#> 5   -98 F        -1

# replace using values in common_na_strings
replace_with_na_at(data = dat_ms,
                 .vars = c("x","z"),
                 condition = ~.x %in% common_na_strings)
#> # A tibble: 5 × 3
#>       x y         z
#>   <dbl> <chr> <dbl>
#> 1     1 A      -100
#> 2     3 N/A     -99
#> 3    NA NA      -98
#> 4   -99 E      -101
#> 5   -98 F        -1
```

--------------------------------

### Explore Missingness with ggplot2

Source: https://naniar.njtierney.com/reference/riskfactors.html

This example demonstrates how to use ggplot2 with geom_miss_point to visualize the relationship between two variables while highlighting missing data points. It also shows how to use faceting to explore missingness across different categories.

```R
library(ggplot2)
p <- ggplot(riskfactors,
       aes(x = health_poor,
           y = bmi)) +
     geom_miss_point()

 p
```

```R
p + facet_wrap(~sex)
```

```R
p + facet_wrap(~education)
```

--------------------------------

### Examples of replacing values with NA

Source: https://naniar.njtierney.com/reference/replace_with_na.html

Demonstrates replacing values in specific columns using a named list. The input data frame is defined using tibble::tribble.

```R
dat_ms <- tibble::tribble(~x,  ~y,    ~z,
                         1,   "A",   -100,
                         3,   "N/A", -99,
                         NA,  NA,    -98,
                         -99, "E",   -101,
                         -98, "F",   -1)

replace_with_na(dat_ms,
               replace = list(x = -99))

replace_with_na(dat_ms,
             replace = list(x = c(-99, -98)))

replace_with_na(dat_ms,
             replace = list(x = c(-99, -98),
                          y = c("N/A"),
                          z = c(-101)))
```

--------------------------------

### Summarise Missing Values by Month Span

Source: https://naniar.njtierney.com/reference/miss_var_span.html

This example demonstrates grouping by month before applying miss_var_span to analyze missing values within hourly counts for each month, with a span of 168 hours.

```R
library(dplyr)
pedestrian %>%
  group_by(month) %>%
    miss_var_span(var = hourly_counts,
                  span_every = 168)
```

--------------------------------

### Raw Data Snippet

Source: https://naniar.njtierney.com/reference/add_n_miss.html

This is a raw data snippet, likely from a file or output, showing numerical and NA values. It serves as an example of data that might be processed by analysis tools.

```text
#> 129    32      92 15.5   84     9   6           0
#> 130    20     252 10.9   80     9   7           0
#> 131    23     220 10.3   78     9   8           0
#> 132    21     230 10.9   75     9   9           0
#> 133    24     259  9.7   73     9  10           0
#> 134    44     236 14.9   81     9  11           0
#> 135    21     259 15.5   76     9  12           0
#> 136    28     238  6.3   77     9  13           0
#> 137     9      24 10.9   71     9  14           0
#> 138    13     112 11.5   71     9  15           0
#> 139    46     237  6.9   78     9  16           0
#> 140    18     224 13.8   67     9  17           0
#> 141    13      27 10.3   76     9  18           0
#> 142    24     238 10.3   68     9  19           0
#> 143    16     201  8.0   82     9  20           0
#> 144    13     238 12.6   64     9  21           0
#> 145    23      14  9.2   71     9  22           0
#> 146    36     139 10.3   81     9  23           0
#> 147     7      49 10.3   69     9  24           0
#> 148    14      20 16.6   63     9  25           0
#> 149    30     193  6.9   70     9  26           0
#> 150    NA     145 13.2   77     9  27           1
#> 151    14     191 14.3   75     9  28           0
#> 152    18     131  8.0   76     9  29           0
#> 153    20     223 11.5   68     9  30           0
```

--------------------------------

### Visualize Missing Data with vis_miss()

Source: https://naniar.njtierney.com/articles/naniar-visualisation.html

Use vis_miss() to get a visual overview of missing data in a dataset. It highlights missing values in black and provides overall missing percentage information.

```R
library(naniar)

vis_miss(airquality)
```

--------------------------------

### Visualize Missing Data Overview

Source: https://naniar.njtierney.com/reference/riskfactors.html

Use vis_miss to get a general overview of missing data in the dataset. This function provides a visual representation of missing values across variables.

```R
vis_miss(riskfactors)
```

--------------------------------

### Clone the repository

Source: https://naniar.njtierney.com/CONTRIBUTING.html

Initial step to create a local copy of the repository from your GitHub account.

```bash
git clone https://github.com/<yourgithubusername>/{repo}.git
```

--------------------------------

### GET /prop_complete_case

Source: https://naniar.njtierney.com/reference/prop-miss-complete-case.html

Calculates the proportion of cases (rows) that contain complete values.

```APIDOC
## GET /prop_complete_case

### Description
Calculate the proportion of cases (rows) that contain complete values.

### Method
GET

### Endpoint
prop_complete_case(data)

### Parameters
#### Request Body
- **data** (dataframe) - Required - A dataframe to analyze.

### Response
#### Success Response (200)
- **value** (numeric) - The proportion of cases that contain a complete value.

### Request Example
prop_complete_case(airquality)

### Response Example
0.7254902
```

--------------------------------

### Implement and Verify `shade` Values

Source: https://naniar.njtierney.com/news/index.html

This section introduces the concept of `shade` values and provides verification functions like `is_shade`, `are_shade`, and `which_are_shade`.

```R
is_shade()
are_shade()
which_are_shade()
```

--------------------------------

### GET /prop_miss_case

Source: https://naniar.njtierney.com/reference/prop-miss-complete-case.html

Calculates the proportion of cases (rows) that contain missing values.

```APIDOC
## GET /prop_miss_case

### Description
Calculate the proportion of cases (rows) that contain missing values.

### Method
GET

### Endpoint
prop_miss_case(data)

### Parameters
#### Request Body
- **data** (dataframe) - Required - A dataframe to analyze.

### Response
#### Success Response (200)
- **value** (numeric) - The proportion of cases that contain a missing value.

### Request Example
prop_miss_case(airquality)

### Response Example
0.2745098
```

--------------------------------

### Create a toy dataset

Source: https://naniar.njtierney.com/articles/special-missing-values.html

Initializes a tibble with specific values to demonstrate missingness handling.

```R
df <- tibble::tribble(
~wind, ~temp,
-99,    45,
68,    NA,
72,    25
)

df
```

--------------------------------

### GET miss_prop_summary

Source: https://naniar.njtierney.com/reference/miss_prop_summary.html

Calculates the proportion of missing values in a dataframe, variables, and cases.

```APIDOC
## GET miss_prop_summary

### Description
Returns missing data information about the dataframe, the variables, and the cases. It calculates the proportion of elements containing missing values at the dataframe level, variable level, and case level.

### Method
GET

### Endpoint
miss_prop_summary(data)

### Parameters
#### Path Parameters
- **data** (dataframe) - Required - A dataframe object to analyze for missing values.

### Request Example
miss_prop_summary(airquality)

### Response
#### Success Response (200)
- **df** (double) - Proportion of missing values in the entire dataframe.
- **var** (double) - Proportion of missing values across variables.
- **case** (double) - Proportion of missing values across cases.

#### Response Example
# A tibble: 1 × 3
#     df   var  case
#  <dbl> <dbl> <dbl>
# 1 0.0479 0.333 0.275
```

--------------------------------

### GET gg_miss_which

Source: https://naniar.njtierney.com/reference/gg_miss_which.html

Visualizes which variables in a dataframe contain missing values using a rectangle-based plot.

```APIDOC
## gg_miss_which

### Description
This function produces a set of rectangles indicating whether there is a missing element in a column or not. It returns a ggplot object.

### Arguments
- **x** (dataframe) - Required - The dataframe to analyze for missing values.

### Request Example
```r
gg_miss_which(airquality)
```

### Response
- **ggplot object** - A visualization showing missing value distribution across variables.
```

--------------------------------

### Sync with upstream

Source: https://naniar.njtierney.com/CONTRIBUTING.html

Commands to fetch and merge changes from the upstream repository.

```bash
git fetch upstream
```

```bash
git pull upstream
```

--------------------------------

### Configure upstream remote

Source: https://naniar.njtierney.com/CONTRIBUTING.html

Set up the upstream remote to track changes from the original repository.

```bash
git remote add upstream https://github.com/{owner}/{repo}.git
```

--------------------------------

### Verify Data Equality

Source: https://naniar.njtierney.com/articles/naniar.html

Confirms that bind_shadow and nabular produce identical results.

```R
all.equal(aq_shadow, aq_nab)
```

--------------------------------

### Get Variable Names with Missing Values

Source: https://naniar.njtierney.com/news/index.html

The `miss_var_which()` function returns a vector of variable names that contain missing values.

```R
miss_var_which(data)
```

--------------------------------

### Visualize missing data spans

Source: https://naniar.njtierney.com/reference/gg_miss_span.html

Examples of using gg_miss_span to visualize missing data, including faceting and ggplot2 theme customization.

```R
library(ggplot2)
gg_miss_span(pedestrian, hourly_counts, span_every = 3000)
gg_miss_span(pedestrian, hourly_counts, span_every = 3000, facet = sensor_name)
# works with the rest of ggplot
gg_miss_span(pedestrian, hourly_counts, span_every = 3000) + labs(x = "custom")
gg_miss_span(pedestrian, hourly_counts, span_every = 3000) + theme_dark()
```

--------------------------------

### Create nabular data

Source: https://naniar.njtierney.com/articles/special-missing-values.html

Uses bind_shadow to create a shadow matrix for the dataset.

```R
dfs <- bind_shadow(df)

dfs
```

--------------------------------

### Find Missing Values in Dataframe

Source: https://naniar.njtierney.com/reference/which_na.html

Use `which_na` to get the integer locations of missing values in a dataframe. This function is an alias for `which(is.na())`.

```r
which_na(airquality)
#>  [1]   5  10  25  26  27  32  33  34  35  36  37  39  42  43  45  46  52  53  54
#> [20]  55  56  57  58  59  60  61  65  72  75  83  84 102 103 107 115 119 150 158
#> [39] 159 164 180 249 250 251
```

--------------------------------

### Prepare Data for UpSetR Plotting

Source: https://naniar.njtierney.com/news/index.html

Use `as_shadow_upset()` to format data for plotting with `UpSetR`. This function prepares the data by converting it into a suitable structure for visualizing set intersections of missing values.

```R
airquality %>$
as_shadow_upset() %>$
UpSetR::upset()
```

--------------------------------

### Visualize Missing Data with vis_miss

Source: https://naniar.njtierney.com/reference/pedestrian.html

Visualizes the missingness pattern in the pedestrian dataset. Use this to get a general overview of where missing values occur.

```r
vis_miss(pedestrian)
```

--------------------------------

### Bind shadow data to create nabular format

Source: https://naniar.njtierney.com/index.html

Use bind_shadow or nabular to append shadow variables to the original dataset, creating a nabular format for tracking missingness.

```R
bind_shadow(airquality)
nabular(airquality)
```

--------------------------------

### Impute Missing Values with naniar

Source: https://naniar.njtierney.com/reference/scoped-impute_mean.html

Demonstrates how to impute missing values using mean imputation based on specific variables or predicates.

```R
library(dplyr)
impute_mean_at(airquality,
                .vars = vars(Ozone))

impute_mean_if(airquality,
                .predicate = is.numeric)
```

--------------------------------

### Impute Median Function

Source: https://naniar.njtierney.com/reference/impute_median.html

This function imputes the median value into a vector with missing values. It handles different data types and provides examples for its usage.

```APIDOC
## Impute Median Function

### Description
Impute the median value into a vector with missing values.

### Usage
```R
impute_median(x)

# Default S3 method
impute_median(x)

# S3 method for class 'factor'
impute_median(x)
```

### Arguments

*   **x** (vector) - The input vector that may contain missing values.

### Value

A vector with median values imputed for any missing entries.

### Examples

```R
# Example 1: Basic usage with a numeric vector
vec <- rnorm(10)
vec[sample(1:10, 3)] <- NA
impute_median(vec)

# Example 2: Using with dplyr and tibble
library(dplyr)

dat <- tibble(
  num = rnorm(10),
  int = as.integer(rpois(10, 5)),
  fct = factor(LETTERS[1:10])
) %>%
  mutate(
    across(
      everything(),
      ~ set_prop_miss(.x, prop = 0.25)
    )
  )

# Impute median for specific numeric columns
dat %>%
  nabular() %>%
  mutate(
    num = impute_median(num),
    int = impute_median(int)
  )

# Impute median for all numeric columns
dat %>%
  nabular() %>%
  mutate(
    across(
      where(is.numeric),
      impute_median
    )
  )

# Impute median for a subset of numeric columns
dat %>%
  nabular() %>%
  mutate(
    across(
      c("num", "int"),
      impute_median
    )
  )
```
```
Tokens:
Raw