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),
)
set.seed(1234)
# Rescale 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$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 0.336  0     0.614  1     
##  2 0.230  0.876 0.376  0.0865
##  3 0      1     0.0713 0     
##  4 0.321  0.781 0.265  0.904 
##  5 0.254  0.477 0.399  0.576 
##  6 0.523  0.223 0.332  0.863 
##  7 0.392  0.635 0      0.656 
##  8 0.0928 0.452 0.605  0.0924
##  9 0.415  0.764 1      0.378 
## 10 1      0.355 0.845  0.137
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 0.336  0     0.614  1     
##  2 0.230  0.876 0.376  0.0865
##  3 0      1     0.0713 0     
##  4 0.321  0.781 0.265  0.904 
##  5 0.254  0.477 0.399  0.576 
##  6 0.523  0.223 0.332  0.863 
##  7 0.392  0.635 0      0.656 
##  8 0.0928 0.452 0.605  0.0924
##  9 0.415  0.764 1      0.378 
## 10 1      0.355 0.845  0.137

Functions are for humans and computers

Conditional exectution

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")
    }
    
}

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()

Functional arguments

?mean
## starting httpd help server ... done
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 = 0.01)
## [1] 14.09091
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 function

one that takes a vector as the input another that takes a data frame as the input

Return values