functions

Chapter 15

General format for writing a function

 name <- function(arguments) {
   body
 }

We’ll discuss 3 types of functions:

1. Vector

2. Data

3. Plotting

Vector Functions

Motivation for functions

1. Create 4 vectors, each containing 5 random numbers with mean = 2, and standard deviation = 3.
2. Normalize each vector to have min = 0 and max = 1.
3. Notice any inefficency?
4. Write a function to normalize a vector and use it.

 n <- function(a) {
 rng <- range(a, na.rm = TRUE)
 (a - rng[1])/(rng[2] - rng[1])
 }

5. Use the function inside mutate like this:

library(tidyverse)
 # using a function within mutate
 df |> mutate(
   a = rescale01(a),
   b = rescale01(b),
   c = rescale01(c),
   d = rescale01(d))

We can use across() to make the above even more efficient

### How to compute the mean of many columns

 library(tidyverse)
 # get the mean of columns a - d.
 df <- tibble(
   a = rnorm(10),
   b = rnorm(10),
   c = rnorm(10),
   d = rnorm(10)
 )
 
 print(df)

# A tibble: 10 × 4
         a       b       c       d
     <dbl>   <dbl>   <dbl>   <dbl>
 1  0.949   1.10   -1.36    0.623 
 2 -1.26   -1.39    1.56    0.0212
 3  0.421   0.856   0.130  -0.135 
 4 -0.813   2.15    1.01   -1.34  
 5 -1.63   -2.86   -0.0441 -1.12  
 6 -0.431   0.409  -1.06    1.57  
 7  0.510   0.775  -0.436   0.113 
 8  1.93   -0.164   0.220   0.414 
 9 -0.0219 -1.22    1.21   -0.254 
10  0.769  -0.0388  0.368   0.536 

 df |> summarize(across(a:d, mean))

# A tibble: 1 × 4
       a       b     c      d
   <dbl>   <dbl> <dbl>  <dbl>
1 0.0412 -0.0376 0.160 0.0433

### How to compute the median of numeric columns

 glimpse(diamonds)

Rows: 53,940
Columns: 10
$ carat   <dbl> 0.23, 0.21, 0.23, 0.29, 0.31, 0.24, 0.24, 0.26, 0.22, 0.23, 0.…
$ cut     <ord> Ideal, Premium, Good, Premium, Good, Very Good, Very Good, Ver…
$ color   <ord> E, E, E, I, J, J, I, H, E, H, J, J, F, J, E, E, I, J, J, J, I,…
$ clarity <ord> SI2, SI1, VS1, VS2, SI2, VVS2, VVS1, SI1, VS2, VS1, SI1, VS1, …
$ depth   <dbl> 61.5, 59.8, 56.9, 62.4, 63.3, 62.8, 62.3, 61.9, 65.1, 59.4, 64…
$ table   <dbl> 55, 61, 65, 58, 58, 57, 57, 55, 61, 61, 55, 56, 61, 54, 62, 58…
$ price   <int> 326, 326, 327, 334, 335, 336, 336, 337, 337, 338, 339, 340, 34…
$ x       <dbl> 3.95, 3.89, 4.05, 4.20, 4.34, 3.94, 3.95, 4.07, 3.87, 4.00, 4.…
$ y       <dbl> 3.98, 3.84, 4.07, 4.23, 4.35, 3.96, 3.98, 4.11, 3.78, 4.05, 4.…
$ z       <dbl> 2.43, 2.31, 2.31, 2.63, 2.75, 2.48, 2.47, 2.53, 2.49, 2.39, 2.…

 diamonds |> summarize(across(where(is.numeric), median))

# A tibble: 1 × 7
  carat depth table price     x     y     z
  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1   0.7  61.8    57  2401   5.7  5.71  3.53

## The range function

Use the range of a vector to minimize redundancy

 rescale01 <- function(x) {
   rng <- range(x, na.rm = TRUE)
   (x - rng[1]) / (rng[2] - rng[1])
 }

### The z-score

 z_score <- function(x) {
   (x - mean(x, na.rm = TRUE)) / sd(x, na.rm = TRUE)
 }

### Clamp

What happens if you remove the .default line?

 clamp <- function(x, min, max) {
   case_when(
     x < min ~ min,
     x > max ~ max,
     .default = x
   )
 }
 
 clamp(1:10, min = 3, max = 7)

 [1] 3 3 3 4 5 6 7 7 7 7

### A function on strings

 # notice what is gettings assigned TO
 first_upper <- function(x) {
   str_sub(x, 1, 1) <- str_to_upper(str_sub(x, 1, 1))
   x
 }
 
 first_upper("hello")

[1] "Hello"

### A string stripper

 # the order matters in the str_remove_all's below
 clean_number <- function(x) {
   is_pct <- str_detect(x, "%")
   num <- x |> 
     str_remove_all("%") |> 
     str_remove_all(",") |> 
     str_remove_all(fixed("$")) |> 
     as.numeric()
   if_else(is_pct, num / 100, num)
 }
 
 clean_number("$12,300")

[1] 12300

 clean_number("45%")

[1] 0.45

### Summarize functions

Here’s a somewhat advanced version. Observe the importance of the :=

f <- function(x,cat_var, num_var){
     x |> group_by({{cat_var}}) |> 
         summarize("{{num_var}}" := mean({{num_var}}))
 }