Chapter 19 Functions

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

ncol_num <- flights %>%
  select(where(is.numeric)) %>%
  ncol()

ncol_num
## [1] 14

Turn into a Function

count_ncol_numeric <- function(.data) {
  ncol_num <- .data %>%
    select(where(is.numeric)) %>%
    ncol()
  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 (type_data == "numeric") {
    ncol_type <- .data %>%
      select(where(is.numeric)) %>%
      ncol()
  } else if (type_data == "character") {
    ncol_type <- .data %>%
      select(where(is.character)) %>%
      ncol()
  }
  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

nrow_num <- flights %>%
  filter(carrier == "UA") %>%
  nrow()

nrow_num
## [1] 58665

Turn into a Function

count_num_flights_by_carrier <- function(.data, carrier_name) {
  nrow_num <- .data %>%
    filter(carrier == carrier_name) %>%
    nrow()
  return(nrow_num)
}

flights %>% count_num_flights_by_carrier(carrier_name = "UA")
## [1] 58665
flights %>% .[1:10, "carrier"] %>% count_num_flights_by_carrier(carrier_name = "AA")
## [1] 2

Example 3: Create Your Own Function

mydata <- read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-07-01/weekly_gas_prices.csv')
## Rows: 22360 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (3): fuel, grade, formulation
## dbl  (1): price
## date (1): date
## 
## 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.
nrow_regular_high <- mydata %>%
  filter(grade == "regular") %>%
  filter(price > 3.5) %>%
  nrow()

nrow_regular_high
## [1] 699

Turn into a Function

count_num_regular_over_price <- function(.data, price_threshold = 3.5) {
  nrow_regular_high <- .data %>%
    filter(grade == "regular") %>%
    filter(price > price_threshold) %>%
    nrow()
  return(nrow_regular_high)
}

mydata %>% count_num_regular_over_price()
## [1] 699
mydata %>% count_num_regular_over_price(price_threshold = 4)
## [1] 122