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 
data <- read_excel("myData.xlsx")
data
## # A tibble: 32,754 × 20
##         id original_title original_language overview tagline release_date       
##      <dbl> <chr>          <chr>             <chr>    <chr>   <dttm>             
##  1  760161 Orphan: First… en                After e… "There… 2022-07-27 00:00:00
##  2  760741 Beast          en                A recen… "Fight… 2022-08-11 00:00:00
##  3  882598 Smile          en                After w… "Once … 2022-09-23 00:00:00
##  4  717728 Jeepers Creep… en                Forced … "Evil … 2022-09-15 00:00:00
##  5  772450 Presencias     es                A man w…  <NA>   2022-09-07 00:00:00
##  6 1014226 Sonríe         es                <NA>      <NA>   2022-08-18 00:00:00
##  7  913290 Barbarian      en                In town… "Some … 2022-09-08 00:00:00
##  8  830788 The Invitation en                After t… "You a… 2022-08-24 00:00:00
##  9  927341 Hunting Ava B… en                Billion… "\"If … 2022-04-01 00:00:00
## 10  762504 Nope           en                Residen… "What’… 2022-07-20 00:00:00
## # ℹ 32,744 more rows
## # ℹ 14 more variables: title <chr>, popularity <dbl>, revenue <dbl>,
## #   budget <dbl>, poster_path <chr>, vote_count <dbl>, vote_average <dbl>,
## #   runtime <dbl>, status <chr>, adult <lgl>, backdrop_path <chr>,
## #   genre_names <chr>, collection <chr>, collection_name <chr>
small_data <- data %>%
  slice(1:5) %>%
  select(id, original_title, release_date, popularity, revenue,)

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 <- flights %>%
        
    
         # 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] 14

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, 1:15] %>% count_ncol_type(type_data = "character")
## [1] 4

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()

Turn them into a function

# Define the function
count_movies <- function(data, limit) {
  data %>%
    filter(popularity > limit) %>%
    nrow()
}

# Use the function
count_movies(small_data, 1000)
## [1] 4