Code Along 11

knitr::opts_chunk$set(echo = TRUE)

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.3     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.3     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(conflicted)
library(dplyr)

Introduction

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

df$a <= (df$a - min(df$a, na.rm = TRUE)) /
    (max(df$a, na.rm = TRUE) - min(df$a, na.rm = TRUE))

##  [1]  TRUE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE

df$b <= (df$b - min(df$b, na.rm = TRUE)) /
    (max(df$b, na.rm = TRUE) - min(df$b, na.rm = TRUE))

##  [1]  TRUE  TRUE  TRUE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE FALSE

df$c <= (df$c - min(df$c, na.rm = TRUE)) /
    (max(df$c, na.rm = TRUE) - min(df$c, na.rm = TRUE))

##  [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE

df$d <= (df$d - min(df$d, na.rm = TRUE)) /
    (max(df$d, na.rm = TRUE) - min(df$d, na.rm = TRUE))

##  [1] FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE

df

## # A tibble: 10 × 4
##         a       b       c      d
##     <dbl>   <dbl>   <dbl>  <dbl>
##  1 -1.21  -0.477   0.134   1.10 
##  2  0.277 -0.998  -0.491  -0.476
##  3  1.08  -0.776  -0.441  -0.709
##  4 -2.35   0.0645  0.460  -0.501
##  5  0.429  0.959  -0.694  -1.63 
##  6  0.506 -0.110  -1.45   -1.17 
##  7 -0.575 -0.511   0.575  -2.18 
##  8 -0.547 -0.911  -1.02   -1.34 
##  9 -0.564 -0.837  -0.0151 -0.294
## 10 -0.890  2.42   -0.936  -0.466

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

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, the function must stop")
        print(x)
    }
}

# 3 %>% detect_sign()
# 0 %>% detect_sign()
# -1 %>% 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()

## [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

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

Return Values