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 = "AA")
## [1] 2

Import data

data <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-01-12/artwork.csv')
## Rows: 69201 Columns: 20
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (12): accession_number, artist, artistRole, title, dateText, medium, cre...
## dbl  (7): id, artistId, year, acquisitionYear, width, height, depth
## lgl  (1): thumbnailCopyright
## 
## 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.
data
## # A tibble: 69,201 × 20
##       id accession_number artist       artistRole artistId title dateText medium
##    <dbl> <chr>            <chr>        <chr>         <dbl> <chr> <chr>    <chr> 
##  1  1035 A00001           Blake, Robe… artist           38 A Fi… date no… Water…
##  2  1036 A00002           Blake, Robe… artist           38 Two … date no… Graph…
##  3  1037 A00003           Blake, Robe… artist           38 The … ?c.1785  Graph…
##  4  1038 A00004           Blake, Robe… artist           38 Six … date no… Graph…
##  5  1039 A00005           Blake, Will… artist           39 The … 1826–7,… Line …
##  6  1040 A00006           Blake, Will… artist           39 Ciam… 1826–7,… Line …
##  7  1041 A00007           Blake, Will… artist           39 The … 1826–7,… Line …
##  8  1042 A00008           Blake, Will… artist           39 The … 1826–7,… Line …
##  9  1043 A00009           Blake, Will… artist           39 The … 1826–7,… Line …
## 10  1044 A00010           Blake, Will… artist           39 The … 1826–7,… Line …
## # ℹ 69,191 more rows
## # ℹ 12 more variables: creditLine <chr>, year <dbl>, acquisitionYear <dbl>,
## #   dimensions <chr>, width <dbl>, height <dbl>, depth <dbl>, units <chr>,
## #   inscription <chr>, thumbnailCopyright <lgl>, thumbnailUrl <chr>, url <chr>

Example 3: count rows

code snippets

nrow_role <- data %>%
    
    # filter rows that meet a condition
    filter(artistRole == "artist") %>%
    
    # Count rows
    nrow()

nrow_role
## [1] 66907

Turn them into a function

count_num_artists_by_artistRole <- function(.data, artist_title) {
    
    # body
    nrow_role <- .data %>%
    
    # filter rows that meet a condition
    filter(artistRole == artist_title) %>%
    
    # Count rows
    nrow()
    
   # return the new vairable
    return(nrow_role)
    
}

data %>% .[1:10, "artistRole"] %>% 
count_num_artists_by_artistRole(artist_title = "pseduo")
## [1] 0
data %>% .[1:10, "artistRole"] %>% 
count_num_artists_by_artistRole(artist_title = "artist")
## [1] 10