Week 8: Apply it to your data 7

Import your data

# csv file
jobs_gender <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-03-05/jobs_gender.csv")

## Rows: 2088 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): occupation, major_category, minor_category
## dbl (9): year, total_workers, workers_male, workers_female, percent_female, ...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

employees <- jobs_gender %>%
    
    select(total_workers, workers_male, workers_female) 

Pivoting

long to wide form

employees %>% 
    pivot_wider(names_from = total_workers, values_from = workers_male)

## # A tibble: 2,005 × 2,072
##    workers_fem…¹ 10242…² 97728…³ `14815` `43015` 75451…⁴ `44198` 10970…⁵ 48904…⁶
##            <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>
##  1        241859  782400      NA      NA      NA      NA      NA      NA      NA
##  2        295657      NA  681627      NA      NA      NA      NA      NA      NA
##  3          6440      NA      NA    8375      NA      NA      NA      NA      NA
##  4         25240      NA      NA      NA   17775      NA      NA      NA      NA
##  5        314436      NA      NA      NA      NA  440078      NA      NA      NA
##  6         28057      NA      NA      NA      NA      NA   16141      NA      NA
##  7         36830      NA      NA      NA      NA      NA      NA   72873      NA
##  8        134679      NA      NA      NA      NA      NA      NA      NA  354369
##  9        529769      NA      NA      NA      NA      NA      NA      NA      NA
## 10         11269      NA      NA      NA      NA      NA      NA      NA      NA
## # … with 1,995 more rows, 2,063 more variables: `990611` <dbl>, `14656` <dbl>,
## #   `307004` <dbl>, `41185` <dbl>, `218198` <dbl>, `175540` <dbl>,
## #   `185512` <dbl>, `499775` <dbl>, `469706` <dbl>, `708239` <dbl>,
## #   `132575` <dbl>, `740359` <dbl>, `5439` <dbl>, `17294` <dbl>, `96419` <dbl>,
## #   `546042` <dbl>, `16766` <dbl>, `28282` <dbl>, `414232` <dbl>,
## #   `279952` <dbl>, `6422` <dbl>, `3034121` <dbl>, `28413` <dbl>, `7184` <dbl>,
## #   `170412` <dbl>, `220927` <dbl>, `257730` <dbl>, `193020` <dbl>, …

employees %>% slice(-10) %>% arrange(total_workers, workers_male)

## # A tibble: 2,087 × 3
##    total_workers workers_male workers_female
##            <dbl>        <dbl>          <dbl>
##  1           658          658              0
##  2           732          722             10
##  3           747          747              0
##  4           836          358            478
##  5           847          847              0
##  6           929          493            436
##  7           947          338            609
##  8           972          972              0
##  9          1043          706            337
## 10          1209         1105            104
## # … with 2,077 more rows

wide to long form

employees %>%
    
    pivot_longer(cols = c(workers_male, workers_female), 
                 names_to = "workers",
                 values_to = "population")

## # A tibble: 4,176 × 3
##    total_workers workers        population
##            <dbl> <chr>               <dbl>
##  1       1024259 workers_male       782400
##  2       1024259 workers_female     241859
##  3        977284 workers_male       681627
##  4        977284 workers_female     295657
##  5         14815 workers_male         8375
##  6         14815 workers_female       6440
##  7         43015 workers_male        17775
##  8         43015 workers_female      25240
##  9        754514 workers_male       440078
## 10        754514 workers_female     314436
## # … with 4,166 more rows

Separating and Uniting

Separate a column

Unite two columns

employees %>%
    
    unite(col = population, sep = "/")

## # A tibble: 2,088 × 1
##    population           
##    <chr>                
##  1 1024259/782400/241859
##  2 977284/681627/295657 
##  3 14815/8375/6440      
##  4 43015/17775/25240    
##  5 754514/440078/314436 
##  6 44198/16141/28057    
##  7 109703/72873/36830   
##  8 489048/354369/134679 
##  9 990611/460842/529769 
## 10 14656/3387/11269     
## # … with 2,078 more rows

Missing Values