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

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) {
    
    # Body
    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_numeric()
## [1] 14
flights %>% .[1:10, -1:-13] %>% count_ncol_numeric() 
## [1] 4

Adding arguments for details of operation

count_ncol_type <- function(.data, type_data = "numeric") {
    
    # If Statement for Type of Variables
    if(type_data == "numeric") {
         # Body
    ncol_type <- .data %>%
    
        # Select a type of variables
        select(where(is.numeric)) %>%
    
        # Count columns
        ncol()
    } else if (type_data == "character") {
        # Body
    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_type()
## [1] 14
flights %>% count_ncol_type(type_data = "character")
## [1] 4
flights %>% .[1:10, 1:5] %>% count_ncol_type(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 = "DL") 
## [1] 1

Example 3: count rows

Create your own.

# Importing data
data(mtcars)
mtcars %>% skimr::skim()
Data summary
Name Piped data
Number of rows 32
Number of columns 11
_______________________
Column type frequency:
numeric 11
________________________
Group variables None

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
mpg 0 1 20.09 6.03 10.40 15.43 19.20 22.80 33.90 ▃▇▅▁▂
cyl 0 1 6.19 1.79 4.00 4.00 6.00 8.00 8.00 ▆▁▃▁▇
disp 0 1 230.72 123.94 71.10 120.83 196.30 326.00 472.00 ▇▃▃▃▂
hp 0 1 146.69 68.56 52.00 96.50 123.00 180.00 335.00 ▇▇▆▃▁
drat 0 1 3.60 0.53 2.76 3.08 3.70 3.92 4.93 ▇▃▇▅▁
wt 0 1 3.22 0.98 1.51 2.58 3.33 3.61 5.42 ▃▃▇▁▂
qsec 0 1 17.85 1.79 14.50 16.89 17.71 18.90 22.90 ▃▇▇▂▁
vs 0 1 0.44 0.50 0.00 0.00 0.00 1.00 1.00 ▇▁▁▁▆
am 0 1 0.41 0.50 0.00 0.00 0.00 1.00 1.00 ▇▁▁▁▆
gear 0 1 3.69 0.74 3.00 3.00 4.00 4.00 5.00 ▇▁▆▁▂
carb 0 1 2.81 1.62 1.00 2.00 2.00 4.00 8.00 ▇▂▅▁▁

code snippets

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

nrow_num <- mtcars %>%
  
  # Filter rows that meet a condition
  filter(cyl == 6) %>%
  
  # Count rows
  nrow()

nrow_num
## [1] 7

Turn them into a function

count_rows_by_condition <- function(.data, column_name, condition) {
    
    # body
    filtered_data <- .data %>%
        
        # filter rows that meet a condition
        filter({{column_name}} == condition)
    
        # count rows
        row_count <- nrow(filtered_data)
        
    # return the new variable
    return (row_count)
    
}

mtcars %>% count_rows_by_condition(cyl, 6)
## [1] 7
mtcars %>% count_rows_by_condition(cyl, 8)
## [1] 14