data(flights)
 
flights %>% skimr::skim()
Data summary
Name Piped data
Number of rows 336776
Number of columns 19
_______________________
Column type frequency:
character 4
numeric 14
POSIXct 1
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
carrier 0 1.00 2 2 0 16 0
tailnum 2512 0.99 5 6 0 4043 0
origin 0 1.00 3 3 0 3 0
dest 0 1.00 3 3 0 105 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
year 0 1.00 2013.00 0.00 2013 2013 2013 2013 2013 ▁▁▇▁▁
month 0 1.00 6.55 3.41 1 4 7 10 12 ▇▆▆▆▇
day 0 1.00 15.71 8.77 1 8 16 23 31 ▇▇▇▇▆
dep_time 8255 0.98 1349.11 488.28 1 907 1401 1744 2400 ▁▇▆▇▃
sched_dep_time 0 1.00 1344.25 467.34 106 906 1359 1729 2359 ▁▇▇▇▃
dep_delay 8255 0.98 12.64 40.21 -43 -5 -2 11 1301 ▇▁▁▁▁
arr_time 8713 0.97 1502.05 533.26 1 1104 1535 1940 2400 ▁▃▇▇▇
sched_arr_time 0 1.00 1536.38 497.46 1 1124 1556 1945 2359 ▁▃▇▇▇
arr_delay 9430 0.97 6.90 44.63 -86 -17 -5 14 1272 ▇▁▁▁▁
flight 0 1.00 1971.92 1632.47 1 553 1496 3465 8500 ▇▃▃▁▁
air_time 9430 0.97 150.69 93.69 20 82 129 192 695 ▇▂▂▁▁
distance 0 1.00 1039.91 733.23 17 502 872 1389 4983 ▇▃▂▁▁
hour 0 1.00 13.18 4.66 1 9 13 17 23 ▁▇▇▇▅
minute 0 1.00 26.23 19.30 0 8 29 44 59 ▇▃▆▃▅

Variable type: POSIXct

skim_variable n_missing complete_rate min max median n_unique
time_hour 0 1 2013-01-01 05:00:00 2013-12-31 23:00:00 2013-07-03 10:00:00 6936

Create Data frame functions

Example 1: count columns

code snippets

ncol_num <- flights %>%
   
    # Select a type of variables
    select(where(is.numeric)) %>%
   
    # Count columns
    ncol()
 
ncol_num
## [1] 14

Turn them into a function

count_numeric_var <- function(.data) {
   
    # body
    ncol_num <- .data %>%
   
    # Select a type of variables
    select(where(is.numeric)) %>%
   
    # Count columns
    ncol()
   
    # return value
    return(ncol_num)
   
}
 
flights %>% count_numeric_var()
## [1] 14
flights %>% .[, -1:-13] %>% count_numeric_var()
## [1] 4

Adding arguments for details of operation

# Create a function to count # of a type of columns
count_type_of_var <- function(.data, type = "numeric") {
   
    # if statement for type of variables
    if(type == "numeric") {
       
        # body
        ncol_num <- .data %>%
       
        # Select a type of variables
        select(where(is.numeric)) %>%
       
        # Count columns
        ncol()
       
    } else if(type == "character") {
       
        # body
        ncol_num <- .data %>%
       
        # Select a type of variables
        select(where(is.character)) %>%
       
        # Count columns
        ncol()       
        
    }
   
 
    # return value
    return(ncol_num)
   
}
 
flights %>% count_type_of_var(type = "character")
## [1] 4
flights %>% .[, -1:-13] %>% count_type_of_var(type = "character")
## [1] 1

Example 2: count rows

code snippets

nrow_num <- flights %>%
   
    filter(carrier == "UA") %>%
   
    # Count rows
    nrow()
 
nrow_num
## [1] 58665

Turn them into a function

count_n_flights_by_carrier <- function(.data, carrier_name) {
   
    # body
    nrow_num <- .data %>%
       
        # filter rows that meet a condition
        filter(carrier == carrier_name) %>%
       
        # Count rows
        nrow()
   
    nrow_num
   
    # return value
    return(nrow_num)
   
}
 
flights %>% count_n_flights_by_carrier(carrier_name = "UA")
## [1] 58665
flights %>% .[1:10, ] %>% count_n_flights_by_carrier(carrier_name = "UA")
## [1] 3

Example 3: count rows

nrow_flights <- flights %>%
    nrow()
 
nrow_flights
## [1] 336776

code snippets

ua_flights <- flights %>%
    filter(carrier == "UA")
 
ua_flights
## # A tibble: 58,665 × 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     1      517            515         2      830            819
##  2  2013     1     1      533            529         4      850            830
##  3  2013     1     1      554            558        -4      740            728
##  4  2013     1     1      558            600        -2      924            917
##  5  2013     1     1      558            600        -2      923            937
##  6  2013     1     1      559            600        -1      854            902
##  7  2013     1     1      607            607         0      858            915
##  8  2013     1     1      611            600        11      945            931
##  9  2013     1     1      623            627        -4      933            932
## 10  2013     1     1      628            630        -2     1016            947
## # ℹ 58,655 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>

Turn them into a function

count_n_flights_by_carrier <- function(.data, carrier_name) {
   
    # body
    nrow_num <- .data %>%
        # filter rows that meet a condition
        filter(carrier == carrier_name) %>%
        # count rows
        nrow()
   
    # return value
    return(nrow_num)
}
 
# Examples
flights %>% count_n_flights_by_carrier(carrier_name = "UA")
## [1] 58665
flights %>% .[1:10, ] %>% count_n_flights_by_carrier(carrier_name = "UA")
## [1] 3