Creating the descriptive violin plot for the beer data set, as used in the session on linear regression.

beer_violins.R

library(ggplot2)
library(tidyr)
library(dplyr)
library(DataScienceExercises) # https://github.com/graebnerc/DataScienceExercises/

beer_data <- DataScienceExercises::beer
# Original source: http://www.principlesofeconometrics.com/poe4/poe4stata.htm
beer_data_plot <- beer_data %>%
  pivot_longer(
    cols = everything(), 
    names_to = "variable", 
    values_to = "value") %>%
  ggplot(
    data = ., 
    aes(x=variable, y=value, fill=variable)
    ) +
  geom_violin(# To draw a violin plot
    draw_quantiles = c(0.25, 0.5, 0.75), # Show quantiles
    alpha=0.5 # Transparency
    ) + 
  geom_jitter(# To draw non-overlapping points
    alpha=0.5, size=0.5 # Transparency and smaller size
    ) +
  scale_fill_brewer(palette = "Dark2") +
  facet_wrap(~variable, # To get different sub-plots for each variable
             ncol = 5, # Five columns
             scales = "free" # Scales adjusted to each variable
             ) + 
  theme_icae() +
  theme(
    axis.title = element_blank(), 
    strip.text = element_blank(), 
    legend.position = "none")