Week 4: Apply 3

Import data

# excel file
data <- read_excel("data/MyData.xlsx")
data

## # A tibble: 8,351 × 23
##     acc_id acc_date            acc_state acc_city       fix_port source bus_type
##      <dbl> <dttm>              <chr>     <chr>          <chr>    <chr>  <chr>   
##  1 1005813 2010-06-12 00:00:00 OH        Cleveland      F        Ohio … Sports …
##  2 1004032 2010-06-12 00:00:00 OH        Cleveland      P        Unite… Sports …
##  3 1007658 2010-07-10 00:00:00 CA        Anaheim        F        Calif… Amuseme…
##  4 1007098 2010-07-10 00:00:00 CA        Carlsbad       F        Calif… Water p…
##  5 1000094 2010-07-29 00:00:00 CO        Littleton      F        Color… Family …
##  6 1005756 2010-07-30 00:00:00 WI        Wisconsin Del… F        Wisco… Amuseme…
##  7 1005757 2010-08-05 00:00:00 WI        Milwaukee      P        Media… Unknown 
##  8 1000103 2010-08-11 00:00:00 CO        Morrison       F        Color… Zoo or …
##  9 1003973 2010-08-15 00:00:00 WI        West Allis     P        Unite… Carniva…
## 10 1004460 2010-09-05 00:00:00 ME        Old Orchard B… F        Maine… Carniva…
## # ℹ 8,341 more rows
## # ℹ 16 more variables: industry_sector <chr>, device_category <chr>,
## #   device_type <chr>, tradename_or_generic <chr>, manufacturer <chr>,
## #   num_injured <dbl>, age_youngest <dbl>, gender <chr>, acc_desc <chr>,
## #   injury_desc <chr>, report <chr>, category <chr>, mechanical <dbl>,
## #   op_error <dbl>, employee <dbl>, notes <chr>

Plot data

data %>%
    
    ggplot(aes(gender)) +
    geom_bar()

data %>%
    
    ggplot(aes(age_youngest)) +
    geom_bar()

## Warning: Removed 684 rows containing non-finite values (`stat_count()`).