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 
# excel file
airlines <- read_excel("../00_data/MyData.xlsx") %>%
     mutate(n_events = as.numeric(n_events)) %>%
    mutate(avail_seat_km_per_week = as.numeric(avail_seat_km_per_week))
airlines
## # A tibble: 336 × 6
##      Ref airline               avail_seat_km_per_week year_range type_…¹ n_eve…²
##    <dbl> <chr>                                  <dbl> <chr>      <chr>     <dbl>
##  1    NA Aer Lingus                         320906734 85_99      incide…       2
##  2     2 Aeroflot*                         1197672318 85_99      incide…      76
##  3     3 Aerolineas Argentinas              385803648 85_99      incide…       6
##  4     4 Aeromexico*                        596871813 85_99      incide…       3
##  5     5 Air Canada                        1865253802 85_99      incide…       2
##  6     6 Air France                        3004002661 85_99      incide…      14
##  7     7 Air India*                         869253552 85_99      incide…       2
##  8     8 Air New Zealand*                   710174817 85_99      incide…       3
##  9     9 Alaska Airlines*                   965346773 85_99      incide…       5
## 10    10 Alitalia                           698012498 85_99      incide…       7
## # … with 326 more rows, and abbreviated variable names ¹​type_of_event,
## #   ²​n_events
airlines
## # A tibble: 336 × 6
##      Ref airline               avail_seat_km_per_week year_range type_…¹ n_eve…²
##    <dbl> <chr>                                  <dbl> <chr>      <chr>     <dbl>
##  1    NA Aer Lingus                         320906734 85_99      incide…       2
##  2     2 Aeroflot*                         1197672318 85_99      incide…      76
##  3     3 Aerolineas Argentinas              385803648 85_99      incide…       6
##  4     4 Aeromexico*                        596871813 85_99      incide…       3
##  5     5 Air Canada                        1865253802 85_99      incide…       2
##  6     6 Air France                        3004002661 85_99      incide…      14
##  7     7 Air India*                         869253552 85_99      incide…       2
##  8     8 Air New Zealand*                   710174817 85_99      incide…       3
##  9     9 Alaska Airlines*                   965346773 85_99      incide…       5
## 10    10 Alitalia                           698012498 85_99      incide…       7
## # … with 326 more rows, and abbreviated variable names ¹​type_of_event,
## #   ²​n_events

## Create Data frame functions

### Example 1: count columns

#### code snippets

```r
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) {
    
    
    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 variable
    if(type_data == "numeric") {
        ncol_type <- .data %>%
        
            # Select a type of variables
            select(where(is.numeric)) %>%
            
            # Count columns
            ncol()
        
    } else if(type_data == "character") {
        
        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 == "UA") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 58665

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

Example 3: count rows

Create your own.

nrow_num <- airlines %>%
    
    # filter rows that meet a condition
    filter(airline == "Air Canada") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 6

code snippets

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

Turn them into a function

count_num_airline_by_carrier <- function(.data, airline_carrier) {
    
    # Body
    nrow_num <- .data %>%
        
        # filter rows that meet a condition
        filter(airline == airline_carrier) %>%
        
        # Count rows
        nrow()    
    # return new variable
    return(nrow_num)
}

airlines %>% count_num_airline_by_carrier(airline_carrier = "Air Canada")
## [1] 6