Intro

When should you write a function?

# For reproducible work
set.seed(1234)
# Create a data frame
df <- tibble::tibble(
  a = rnorm(10),
  b = rnorm(10),
  c = rnorm(10),
  d = rnorm(10)
)
# Rescale each column

# 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))
rescale <- function(x) {
    
    # body
    x <- (df$a - min(df$a, na.rm = TRUE)) / (max(df$a, na.rm = TRUE) - min(df$a, 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)

Functions are for humans and computers

Conditional execution

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, but the function must stop")
  }
}
# 3 %>% detect_sign()
# 0 %>% detect_sign()

Function 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(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