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

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 <- .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
# this take only ONE argument

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, 1:5] %>% 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 == "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.

Import your data

data(diamonds)

diamonds %>% skimr::skim()
Data summary
Name Piped data
Number of rows 53940
Number of columns 10
_______________________
Column type frequency:
factor 3
numeric 7
________________________
Group variables None

Variable type: factor

skim_variable n_missing complete_rate ordered n_unique top_counts
cut 0 1 TRUE 5 Ide: 21551, Pre: 13791, Ver: 12082, Goo: 4906
color 0 1 TRUE 7 G: 11292, E: 9797, F: 9542, H: 8304
clarity 0 1 TRUE 8 SI1: 13065, VS2: 12258, SI2: 9194, VS1: 8171

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
carat 0 1 0.80 0.47 0.2 0.40 0.70 1.04 5.01 ▇▂▁▁▁
depth 0 1 61.75 1.43 43.0 61.00 61.80 62.50 79.00 ▁▁▇▁▁
table 0 1 57.46 2.23 43.0 56.00 57.00 59.00 95.00 ▁▇▁▁▁
price 0 1 3932.80 3989.44 326.0 950.00 2401.00 5324.25 18823.00 ▇▂▁▁▁
x 0 1 5.73 1.12 0.0 4.71 5.70 6.54 10.74 ▁▁▇▃▁
y 0 1 5.73 1.14 0.0 4.72 5.71 6.54 58.90 ▇▁▁▁▁
z 0 1 3.54 0.71 0.0 2.91 3.53 4.04 31.80 ▇▁▁▁▁

code snippets

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

nrow_num <- diamonds %>%
    
    # filter rows that meet a condition
    filter(cut == "Premium") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 13791

Turn them into a function

count_cut_by_type <- function(.data, cut_type) {
    
    # body
    nrow_num <- .data %>%
    
        # filter rows that meet a condition
        filter(cut == cut_type) %>%
        
        # Count rows
        nrow()
    
    # return the new variable
    return(nrow_num)
}

diamonds %>% count_cut_by_type(cut_type = "Premium")
## [1] 13791
diamonds %>% .[1:10, "cut"] %>% count_cut_by_type(cut_type = "Premium")
## [1] 2
# [1:10] in the fisrt 10 rows, how many do I have that are Premium