# Load packages
 
# Core
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.2
## ✔ ggplot2   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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(tidyquant)
## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo 
## ── Attaching core tidyquant packages ─────────────────────── tidyquant 1.0.11 ──
## ✔ PerformanceAnalytics 2.0.8      ✔ TTR                  0.24.4
## ✔ quantmod             0.4.28     ✔ xts                  0.14.1── Conflicts ────────────────────────────────────────── tidyquant_conflicts() ──
## ✖ zoo::as.Date()                 masks base::as.Date()
## ✖ zoo::as.Date.numeric()         masks base::as.Date.numeric()
## ✖ dplyr::filter()                masks stats::filter()
## ✖ xts::first()                   masks dplyr::first()
## ✖ dplyr::lag()                   masks stats::lag()
## ✖ xts::last()                    masks dplyr::last()
## ✖ PerformanceAnalytics::legend() masks graphics::legend()
## ✖ quantmod::summary()            masks base::summary()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(ggrepel)

Ch19 Functions

Introduction

When should you write a function?

# For reproducible work
set.seed(1234)
 
# Creat 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$a, na.rm = TRUE))
df$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 0.332 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
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()
## 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()

Function arguments

?mean
 
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