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

set.seed(1234)


df <- tibble::tibble(
  a = rnorm(10),
  b = rnorm(10),
  c = rnorm(10),
  d = rnorm(10)
)
df$a <- (df$a - min(df$a, na.rm = TRUE)) / 
  (max(df$a, na.rm = TRUE) - min(df$a, na.rm = TRUE))
df$b <- (df$b - min(df$b, na.rm = TRUE)) / 
  (max(df$b, na.rm = TRUE) - min(df$b, na.rm = TRUE))
df$c <- (df$c - min(df$c, na.rm = TRUE)) / 
  (max(df$c, na.rm = TRUE) - min(df$c, na.rm = TRUE))
df$d <- (df$d - min(df$d, na.rm = TRUE)) / 
  (max(df$d, na.rm = TRUE) - min(df$d, na.rm = TRUE))

df
## # A tibble: 10 × 4
##        a      b     c     d
##    <dbl>  <dbl> <dbl> <dbl>
##  1 0.332 0.153  0.782 1    
##  2 0.765 0      0.473 0.519
##  3 1     0.0651 0.498 0.448
##  4 0     0.311  0.943 0.511
##  5 0.809 0.573  0.373 0.168
##  6 0.831 0.260  0     0.308
##  7 0.516 0.143  1     0    
##  8 0.524 0.0255 0.210 0.256
##  9 0.519 0.0472 0.708 0.575
## 10 0.424 1      0.253 0.522
rescale <- function(x) {
    
    # body
    x <- (x - min(x, na.rm = TRUE)) / 
  (max(x, na.rm = TRUE) - min(x, na.rm = TRUE))
    
    # return values
    return(x)
    
}
df$a <- rescale(df$a)
df$b <- rescale(df$b)
df$c <- rescale(df$c)
df$d <- rescale(df$d)

df
## # A tibble: 10 × 4
##        a      b     c     d
##    <dbl>  <dbl> <dbl> <dbl>
##  1 0.332 0.153  0.782 1    
##  2 0.765 0      0.473 0.519
##  3 1     0.0651 0.498 0.448
##  4 0     0.311  0.943 0.511
##  5 0.809 0.573  0.373 0.168
##  6 0.831 0.260  0     0.308
##  7 0.516 0.143  1     0    
##  8 0.524 0.0255 0.210 0.256
##  9 0.519 0.0472 0.708 0.575
## 10 0.424 1      0.253 0.522

Adding arguments for details of operation

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

detect_sign <- function(x) {
    
    if(x > 0) {
        message("Value is positive") 
        print(x)
    } else if(x == 0) {
        warning("Value is not positive, but it can be accepted")
        print(x)
    } else {
        stop("Value is negative, the function must stop")
        print(x)
    }
    
}

3 %>% detect_sign()
## Value is positive
## [1] 3
0 %>% detect_sign()
## Warning in detect_sign(.): Value is not positive, but it can be accepted
## [1] 0
# -1 %>% detect_sign()

Example 3: count rows

?mean

x <- c(1:10, 100, NA)
x
##  [1]   1   2   3   4   5   6   7   8   9  10 100  NA
x %>% mean()
## [1] NA
x %>% mean(na.rm = TRUE)
## [1] 14.09091
x %>% mean(na.rm = TRUE, trim = 0.1)
## [1] 6
mean_remove_na <- function(x, na.rm = TRUE, ...) {
    
    avg <- mean(x, na.rm = na.rm, ...)
    
    return(avg)
    
}

x %>% mean_remove_na()
## [1] 14.09091
x %>% mean_remove_na(na.rm = FALSE)
## [1] NA
x %>% mean_remove_na(trim = 0.1)
## [1] 6