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 
stocks <- tq_get(c("NOC", "WMT","UPS","UNH"),
                 get = "stock.prices",
                 from = "2016-01-01")

stocks %>% glimpse()
## Rows: 8,924
## Columns: 8
## $ symbol   <chr> "NOC", "NOC", "NOC", "NOC", "NOC", "NOC", "NOC", "NOC", "NOC"…
## $ date     <date> 2016-01-04, 2016-01-05, 2016-01-06, 2016-01-07, 2016-01-08, …
## $ open     <dbl> 185.98, 187.85, 190.16, 187.90, 188.79, 187.48, 189.06, 189.0…
## $ high     <dbl> 187.60, 192.86, 193.20, 189.68, 189.74, 188.71, 189.47, 189.4…
## $ low      <dbl> 185.31, 187.85, 190.00, 186.01, 185.90, 185.51, 187.53, 184.5…
## $ close    <dbl> 187.51, 192.39, 190.47, 188.11, 186.07, 188.11, 188.92, 184.8…
## $ volume   <dbl> 1476100, 2302200, 1879700, 2136100, 1503300, 1773800, 1010400…
## $ adjusted <dbl> 163.0530, 167.2965, 165.6269, 163.5747, 161.8009, 163.5747, 1…

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_numeric <- function(.data) {
   
     ncol_num <- flights %>%
    
    # Select a type of variables
    select(where(is.numeric)) %>%
    
    # Count columns
    ncol()
     return(ncol_num)}

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

Adding arguments for details of operation

count_ncol_types <- function(.data, type_data = "numeric") {
   
    # IF Statement
    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(ncol_num)}

flights %>% count_ncol_types()
## [1] 14

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
    return(nrow_num)
}

flights %>% .[1:10, "carrier"] %>%
 count_num_flights_by_carrier(carrier_name = "DL")
## [1] 1

Example 3: count rows

Create your own.

code snippets

Use the filter() function to select rows that meet a condition. Refer to Chapter 5.2 Filter rows with filter()

 ex <- stocks %>%
    filter(symbol == "NOC") %>%
    nrow()
    
ex
## [1] 2231

Turn them into a function

number_active_days <- function(.data, ticker) {
    
    n_row <- .data %>%
    filter(symbol == ticker) %>%
    nrow()
        return(n_row)
}

stocks %>% number_active_days(ticker = "UNH")
## [1] 2231