The Big R-Book

♣D♣Code Not Shown in the Body of the Book

In rare occasions, we did not show all code. This was done out of concern that the code would get in the way of understanding the subject discussed. However, we do not want to deprive you from this code and will reproduce it here for all the occurrences where certain code was not omitted.

Code from Chapter 19 on page 343

In this section we introduce a simple method to visualize some aspects of the data that are helpful for deciding on how to bin the data and have used base-R. It might be useful to know that in ggplot2 these results are equally easy to obtain and might suit better your needs. The output of this code is in Figure D.1 on page 840.

# -- remind the data fabrication ---
set.seed(1865)
age <- rlnorm(1000, meanlog = log(40), sdlog = log(1.3))
y <- rep(NA, length(age))
for(n in 1:length(age)) {
y[n] <- max(0,
           dnorm(age[n], mean= 40, sd=10)
                 + rnorm(1, mean = 0, sd = 10 * dnorm(age[n], 
                 mean= 40, sd=15)) * 0.075)
}
y <- y / max(y)
dt <- tibble (age = age, spending_ratio = y)

# -- plotting loesss and histogram with ggplot2 ---
library(ggplot2)
library(gridExtra)
p1 <- ggplot(dt, mapping = aes(x = age, y = spending_ratio)) + 
      geom_point(alpha=0.2, size = 2) + 
      geom_smooth(method = “loess”)
p2 <- qplot(dt$age, geom=“histogram”, binwidth=5)
grid.arrange(p1, p2, ncol=2)

Figure D.1: A visual aid to select binning borders ...