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 
colony <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-01-11/colony.csv')
## Rows: 1222 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): months, state
## dbl (8): year, colony_n, colony_max, colony_lost, colony_lost_pct, colony_ad...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
colony %>% skimr::skim()
Data summary
Name Piped data
Number of rows 1222
Number of columns 10
_______________________
Column type frequency:
character 2
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
months 0 1 10 16 0 4 0
state 0 1 4 14 0 47 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
year 0 1.00 2017.77 1.89 2015 2016 2018 2019 2021 ▇▃▃▃▆
colony_n 47 0.96 123578.04 437835.18 1300 8000 17500 55500 3181180 ▇▁▁▁▁
colony_max 72 0.94 79112.77 190823.42 1700 9000 21000 68750 1710000 ▇▁▁▁▁
colony_lost 47 0.96 16551.32 60544.42 20 950 2200 6500 502350 ▇▁▁▁▁
colony_lost_pct 54 0.96 11.38 7.23 1 6 10 15 52 ▇▅▁▁▁
colony_added 83 0.93 17243.20 68167.65 10 420 1800 6500 736920 ▇▁▁▁▁
colony_reno 131 0.89 15278.86 62588.04 10 260 960 4585 806170 ▇▁▁▁▁
colony_reno_pct 260 0.79 9.10 9.66 1 2 6 12 77 ▇▁▁▁▁

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 variable
            select(where(is.numeric)) %>%
            
            # count columns
            ncol()
    } else if (type_data == "character") {
        # body
        ncol_type <- .data %>%
            
            # Select a type of variable
            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 = "UA")
## [1] 3

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()

nrow_state <- colony %>%
    
    # filter rows that meet a condition
    filter(state == "Alabama") %>%
    
    # Count rows
    nrow()

nrow_state
## [1] 26

Turn them into a function

count_num_colony_by_state <- function(.data, state_name) {
    
    # body
    nrow_state <- .data %>%
        
        # filter rows that meet a condition
        filter(state == state_name) %>%
        
        # Count rows
        nrow()
    
    #return the new variable
    return(nrow_state)
}

colony %>% count_num_colony_by_state(state_name = "Alabama")
## [1] 26
colony %>% .[1:10, "state"] %>% count_num_colony_by_state(state_name = "Alabama")
## [1] 1
colony %>% .[1:500, "state"] %>% count_num_colony_by_state(state_name = "Texas")
## [1] 10