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 
rating <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2022/2022-01-25/ratings.csv', show_col_types = FALSE)
rating
## # A tibble: 21,831 × 10
##      num     id name          year  rank average bayes_average users_rated url  
##    <dbl>  <dbl> <chr>        <dbl> <dbl>   <dbl>         <dbl>       <dbl> <chr>
##  1   105  30549 Pandemic      2008   106    7.59          7.49      108975 /boa…
##  2   189    822 Carcassonne   2000   190    7.42          7.31      108738 /boa…
##  3   428     13 Catan         1995   429    7.14          6.97      108024 /boa…
##  4    72  68448 7 Wonders     2010    73    7.74          7.63       89982 /boa…
##  5   103  36218 Dominion      2008   104    7.61          7.50       81561 /boa…
##  6   191   9209 Ticket to R…  2004   192    7.41          7.30       76171 /boa…
##  7   100 178900 Codenames     2015   101    7.6           7.51       74419 /boa…
##  8     3 167791 Terraformin…  2016     4    8.42          8.27       74216 /boa…
##  9    15 173346 7 Wonders D…  2015    16    8.11          7.98       69472 /boa…
## 10    35  31260 Agricola      2007    36    7.93          7.81       66093 /boa…
## # ℹ 21,821 more rows
## # ℹ 1 more variable: thumbnail <chr>
ratings <- head(rating, 50)
ratings
## # A tibble: 50 × 10
##      num     id name          year  rank average bayes_average users_rated url  
##    <dbl>  <dbl> <chr>        <dbl> <dbl>   <dbl>         <dbl>       <dbl> <chr>
##  1   105  30549 Pandemic      2008   106    7.59          7.49      108975 /boa…
##  2   189    822 Carcassonne   2000   190    7.42          7.31      108738 /boa…
##  3   428     13 Catan         1995   429    7.14          6.97      108024 /boa…
##  4    72  68448 7 Wonders     2010    73    7.74          7.63       89982 /boa…
##  5   103  36218 Dominion      2008   104    7.61          7.50       81561 /boa…
##  6   191   9209 Ticket to R…  2004   192    7.41          7.30       76171 /boa…
##  7   100 178900 Codenames     2015   101    7.6           7.51       74419 /boa…
##  8     3 167791 Terraformin…  2016     4    8.42          8.27       74216 /boa…
##  9    15 173346 7 Wonders D…  2015    16    8.11          7.98       69472 /boa…
## 10    35  31260 Agricola      2007    36    7.93          7.81       66093 /boa…
## # ℹ 40 more rows
## # ℹ 1 more variable: thumbnail <chr>

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){
  ncol_num <- .data %>%
    
    # Select a type of variables
    select(where(is.numeric)) %>%
    
    # Count columns
    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 statement for type of variables
  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(ncol_type)
}
flights %>% count_ncol_type()
## [1] 14
flights %>% count_ncol_type("character")
## [1] 4
flights %>% .[1:10, 1:5] %>% count_ncol_type("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_flight_by_carrier <- function(.data, carrier_name) {
  # body
  nrow_num <- .data %>%
    
    # filter rows that meet a condition
    filter(carrier == carrier_name) %>%
    
    # Count rows
    nrow()
  
  # return new variable
  return(nrow_num)
}

flights %>% .[1:10, "carrier"] %>% count_num_flight_by_carrier("AA")
## [1] 2

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()

ratings
## # A tibble: 50 × 10
##      num     id name          year  rank average bayes_average users_rated url  
##    <dbl>  <dbl> <chr>        <dbl> <dbl>   <dbl>         <dbl>       <dbl> <chr>
##  1   105  30549 Pandemic      2008   106    7.59          7.49      108975 /boa…
##  2   189    822 Carcassonne   2000   190    7.42          7.31      108738 /boa…
##  3   428     13 Catan         1995   429    7.14          6.97      108024 /boa…
##  4    72  68448 7 Wonders     2010    73    7.74          7.63       89982 /boa…
##  5   103  36218 Dominion      2008   104    7.61          7.50       81561 /boa…
##  6   191   9209 Ticket to R…  2004   192    7.41          7.30       76171 /boa…
##  7   100 178900 Codenames     2015   101    7.6           7.51       74419 /boa…
##  8     3 167791 Terraformin…  2016     4    8.42          8.27       74216 /boa…
##  9    15 173346 7 Wonders D…  2015    16    8.11          7.98       69472 /boa…
## 10    35  31260 Agricola      2007    36    7.93          7.81       66093 /boa…
## # ℹ 40 more rows
## # ℹ 1 more variable: thumbnail <chr>
nrow_num <- ratings %>%
    
    # filter rows that meet a condition
    filter(year == 2008) %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 4

Turn them into a function

count_num_games_by_year <- function(.data, yr){
  nrow_num <- .data %>%
      
      # filter rows that meet a condition
      filter(year == yr) %>%
      
      # Count rows
      nrow()

  return(nrow_num)
}
count_num_games_by_year(ratings, 2008)
## [1] 4
count_num_games_by_year(ratings, 2009)
## [1] 3