Import your data

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 
data <- read_excel("../00_data/myData.xlsx")
## New names:
## • `` -> `...1`
data
## # A tibble: 4,810 × 24
##     ...1  rank position hand  player   years total…¹ status yr_st…² season   age
##    <dbl> <dbl> <chr>    <chr> <chr>    <chr>   <dbl> <chr>    <dbl> <chr>  <dbl>
##  1     1     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1978-…    18
##  2     2     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1978-…    18
##  3     3     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1978-…    18
##  4     4     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1979-…    19
##  5     5     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1980-…    20
##  6     6     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1981-…    21
##  7     7     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1982-…    22
##  8     8     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1983-…    23
##  9     9     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1984-…    24
## 10    10     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1985-…    25
## # … with 4,800 more rows, 13 more variables: team <chr>, league <chr>,
## #   season_games <dbl>, goals <dbl>, assists <dbl>, points <dbl>,
## #   plus_minus <chr>, penalty_min <dbl>, goals_even <chr>,
## #   goals_power_play <chr>, goals_short_handed <chr>, goals_game_winner <chr>,
## #   headshot <chr>, and abbreviated variable names ¹​total_goals, ²​yr_start

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_ncol_num <- function(.data) {
    
    ncol_num <- .data %>%
    
         # Select a type of variables
         select(where(is.numeric)) %>%
    
         # Count columns
          ncol()
    # Return the new variable
    return(ncol_num)
    
}

flights %>% count_ncol_num()
## [1] 14
flights %>% .[1:10, -1:-13] %>% count_ncol_num()
## [1] 4

Adding arguments for details of operation

count_ncol_types <- function(.data, type_data = "numeric") {
    
    # if statement for type of variables
    if(type_data == "numeric") {
        ncol_type <- .data %>%
    
         # Select a type of variables
         select(where(is.numeric)) %>%
    
         # Count columns
            ncol()
    } else if(type_data == "character") {
        ncol_type <- .data %>%
    
         # Select a type of variables
         select(where(is.character)) %>%
    
         # Count columns
            ncol()
    }
    
   
    # Return the new variable
    return(ncol_type)
    
}

flights %>% count_ncol_types() 
## [1] 14
flights %>% count_ncol_types(type_data = "character")
## [1] 4
flights %>% .[1:10, 1:5] %>% count_ncol_types(type_data = "character")
## [1] 0

Example 2: count rows

code snippets

nrow_num <- flights %>%
    
    # filter rows that meet a condition
    filter(carrier == "DL") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 48110

Turn them into a function

count_num_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 the new variable
    return(nrow_num)
}
flights %>% .[1:10, "carrier"] %>% count_num_flights_by_carrier(carrier_name = "AA")
## [1] 2

Example 3: count rows

Create your own.

code snippets

nrow_numtm <- data %>%
    
    # filter rows that meet a condition
    filter(team == "DET") %>%
    
    # Count rows
    nrow()

nrow_numtm
## [1] 297

Turn them into a function

count_num_seasons_per_team <- function(.data, team_name) {
    
    # body
    nrow_numtm <- .data %>%
        
        # filter rows that meet a condition
        filter(team == team_name) %>%
        
        # Count rows
        nrow()
   
     # return the new variable
    return(nrow_numtm)
}

data %>% count_num_seasons_per_team(team_name = "EDM")
## [1] 120