Introduction

When should you write a function?

# Create a data frame
df <- tibble::tibble(
  a = rnorm(10),
  b = rnorm(10),
  c = rnorm(10),
  d = rnorm(10)
)
# Re-scale each column

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$b, na.rm = TRUE) - min(df$a, 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 0.904 3.46  1     0.890 
##  2 0.389 2.41  0.395 0.505 
##  3 0.432 1.72  0.463 0.0754
##  4 0.675 1.73  0.783 0.703 
##  5 0     3.34  0.950 0.0998
##  6 0.525 0     0     1     
##  7 0.138 0.976 0.756 0.101 
##  8 1     2.35  0.455 0.553 
##  9 0.456 3.16  0.576 0     
## 10 0.764 2.21  0.382 0.604
rescale <- function(x) {
    
    # body
    x <- (x - min(x, na.rm = TRUE)) / 
  (max(x, na.rm = TRUE) - min(x, na.rm = TRUE))
    
    # return value
    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 0.904 1     1     0.890 
##  2 0.389 0.698 0.395 0.505 
##  3 0.432 0.499 0.463 0.0754
##  4 0.675 0.501 0.783 0.703 
##  5 0     0.965 0.950 0.0998
##  6 0.525 0     0     1     
##  7 0.138 0.282 0.756 0.101 
##  8 1     0.680 0.455 0.553 
##  9 0.456 0.915 0.576 0     
## 10 0.764 0.639 0.382 0.604

When creating functions and name, it is better that the prefix of the names are the same and the last part after the _ is what differs.

Conditional execution

|| = or && = and

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

# When the if statement can fit in one line we can drop the {}, otherwise it has to be there

Function arguments

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

two types of functions

Return values