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

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

ncol_num
## [1] 14

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_numeric_cols <- function(df) {
  df %>%
    select(where(is.numeric)) %>%
    ncol()
}

# Test it
count_numeric_cols(flights)
## [1] 14

Adding arguments for details of operation

count_columns_by_type <- function(df, type = "numeric") {
  if (type == "numeric") {
    df %>% select(where(is.numeric)) %>% ncol()
  } else if (type == "character") {
    df %>% select(where(is.character)) %>% ncol()
  } else if (type == "logical") {
    df %>% select(where(is.logical)) %>% ncol()
  } else {
    stop("type must be 'numeric', 'character', or 'logical'")
  }
}

# Test it
count_columns_by_type(flights, "numeric")
## [1] 14
count_columns_by_type(flights, "character")
## [1] 4

Example 2: count rows

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

nrow_num
## [1] 58665

code snippets

nrow_num <- flights %>%
    
    # filter rows that meet a condition
    filter(carrier == "UA") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 58665

Turn them into a function

count_rows_by_carrier <- function(df, carrier_code) {
  df %>%
    filter(carrier == carrier_code) %>%
    nrow()
}

# Test it
count_rows_by_carrier(flights, "UA")
## [1] 58665
count_rows_by_carrier(flights, "AA")
## [1] 32729
count_rows_by_carrier(flights, "DL")
## [1] 48110

Example 3: count rows

Create your own. ### Task: Use filter() to create your own counting function. ### Example: Count how many flights departed late (dep_delay > X minutes)

code snippets

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

late_flights <- flights %>%
  filter(dep_delay > 60) %>%
  nrow()

late_flights
## [1] 26581

Turn them into a function

count_late_flights <- function(df, minutes = 60) {
  df %>%
    filter(dep_delay > minutes) %>%
    nrow()
}

# Test it
count_late_flights(flights, 60)   # more than 60 min late
## [1] 26581
count_late_flights(flights, 120)  # more than 2 hours late
## [1] 9723
count_late_flights(flights, 0)    # any delay counted
## [1] 128432