Einführung in R (Frühjahrssemester 2024): Tag 3 - Visualisierung

# Skript zu Tag 3 - Visualisierung

Hier findet sich das Skript zur Entwicklung der beiden Beispielabbildung, die wir im Kurs am 15. Juli 2024 entwickelt haben, sowie den weiteren Visualisiserungsnotizen.

DevelopFigure.R

library(DataScienceExercises)
library(ggplot2)
library(scales)

# Bubble plot------
gdp_data <- DataScienceExercises::gdplifexp2007
# In the following, lines with changes are marked with '# <---'

# 1st step: empty list
gdp_plot <- ggplot()
gdp_plot

# 2nd step: add reference to underlying data set
gdp_plot <- ggplot(data = gdp_data)
gdp_plot

# 3rd step: add aesthetic mappings
gdp_plot <- ggplot(
  data = gdp_data, 
  mapping = aes(x = gdpPercap, y = lifeExp) # <---
  ) 
gdp_plot

# 4th step: add point geometry
gdp_plot <- ggplot(
  data = gdp_data, 
  mapping = aes(x = gdpPercap, y = lifeExp)) + 
  geom_point() # <---
gdp_plot

# 5th step: add size aesthetic
gdp_plot <- ggplot(
  data = gdp_data, 
  mapping = aes(
    y = lifeExp, 
    color = continent, 
    size = pop, # <---
    x = gdpPercap)
  ) + 
  geom_point()
gdp_plot

# 6th step: specify transparency of points and use different shape to 
#  get difference between color and fill aesthetic
#  source for different shapes (scroll down to the bottom):
#  https://ggplot2.tidyverse.org/reference/aes_linetype_size_shape.html
gdp_plot <- ggplot(
  data = gdp_data, 
  mapping = aes(
    y = lifeExp, 
    fill = continent, # <---
    size = pop,
    x = gdpPercap)
) + 
  geom_point(alpha=0.65, shape = 21) # <---
gdp_plot

# 7th step: modify the scales for fill, size, and x aesthetic (i.e. the way
#  the values are mapped on these aesthetics):
gdp_plot <- ggplot(
  data = gdp_data, 
  mapping = aes(
    y = lifeExp, 
    fill = continent, 
    size = pop,
    x = gdpPercap)
) + 
  geom_point(alpha=0.65, shape = 21) + 
  scale_fill_brewer(palette = "Dark2") + # <---   
  scale_size_continuous(range = c(0.1, 21)) + # <---
  scale_x_continuous(
    labels = label_number(scale = 0.001, suffix = "k") # <---
    ) 
gdp_plot

# 8th step: specify the labels for x and y axis, title, and add caption
gdp_plot <- ggplot(
  data = gdp_data, 
  mapping = aes(
    y = lifeExp, 
    fill = continent, 
    size = pop,
    x = gdpPercap)
) + 
  geom_point(alpha=0.65, shape = 21) + 
  scale_fill_brewer(palette = "Dark2") +   
  scale_size_continuous(range = c(0.1, 21)) +
  scale_x_continuous(
    labels = label_number(scale = 0.001, suffix = "k")
  ) +
  labs( # <---
    x="GDP per capita", # <---
    y = "Life expectancy in years", # <---
    title = "Life expectancy and income per capita", # <---
    caption = "Data: Gapminder.") # <---
gdp_plot

# 9th step: Remove label for size aesthetic
gdp_plot <- ggplot(
  data = gdp_data, 
  mapping = aes(
    y = lifeExp, 
    fill = continent, 
    size = pop,
    x = gdpPercap)
) + 
  geom_point(alpha=0.65, shape = 21) + 
  scale_fill_brewer(palette = "Dark2") +   
  scale_size_continuous(range = c(0.1, 21), guide = "none") + # <---
  scale_x_continuous(
    labels = label_number(scale = 0.001, suffix = "k")
  ) +
  labs(
    x="GDP per capita", 
    y = "Life expectancy in years", 
    title = "Life expectancy and income per capita", 
    caption = "Data: Gapminder.")
gdp_plot

# 10th step: Use theme_bw() to fix background and other smaller plot issues
#  theme_bw() is one of the many gggplot2() themes that summarize many
#   changes to the function theme() into one call. See an overview, e.g., here:
#   https://ggplot2-book.org/themes#sec-themes
gdp_plot <- ggplot(
  data = gdp_data, 
  mapping = aes(
    y = lifeExp, 
    fill = continent, 
    size = pop,
    x = gdpPercap)
) + 
  geom_point(alpha=0.65, shape = 21) + 
  scale_fill_brewer(palette = "Dark2") +   
  scale_size_continuous(range = c(0.1, 21), guide = "none") +
  scale_x_continuous(
    labels = label_number(scale = 0.001, suffix = "k")
  ) +
  labs(
    x="GDP per capita", 
    y = "Life expectancy in years", 
    title = "Life expectancy and income per capita", 
    caption = "Data: Gapminder.") + 
  theme_bw() +  # <---
  theme(
    legend.position = "bottom",  # <---
    legend.title = element_blank(), # <---
    panel.border = element_blank(), # <---
    axis.line = element_line(colour = "grey"), # <---
    axis.ticks = element_blank() # <---
    )
gdp_plot

# 11th step: Use theme() to fix position of the legend and remove legend title
gdp_plot <- ggplot(
  data = gdp_data, 
  mapping = aes(
    y = lifeExp, 
    fill = continent, 
    size = pop,
    x = gdpPercap)
) + 
  geom_point(alpha=0.65, shape = 21) + 
  scale_fill_brewer(palette = "Dark2") +   
  scale_size_continuous(range = c(0.1, 21), guide = "none") +
  scale_x_continuous(
    labels = label_number(scale = 0.001, suffix = "k")
  ) +
  labs(
    x="GDP per capita", 
    y = "Life expectancy in years", 
    title = "Life expectancy and income per capita", 
    caption = "Data: Gapminder.") + 
  theme_bw() +
  theme(
    legend.position = "bottom",  # <---
    legend.title = element_blank() # <---
  )
gdp_plot

# 12th step: Use theme() to fix the panel border and axis lines and ticks
gdp_plot <- ggplot(
  data = gdp_data, 
  mapping = aes(
    y = lifeExp, 
    fill = continent, 
    size = pop,
    x = gdpPercap)
) + 
  geom_point(alpha=0.65, shape = 21) + 
  scale_fill_brewer(palette = "Dark2") +   
  scale_size_continuous(range = c(0.1, 21), guide = "none") +
  scale_x_continuous(
    labels = label_number(scale = 0.001, suffix = "k")
  ) +
  labs(
    x="GDP per capita", 
    y = "Life expectancy in years", 
    title = "Life expectancy and income per capita", 
    caption = "Data: Gapminder.") + 
  theme_bw() +
  theme(
    legend.position = "bottom",
    legend.title = element_blank(),
    panel.border = element_blank(), # <---
    axis.line = element_line(colour = "grey"), # <---
    axis.ticks = element_blank() # <---
    
  )
gdp_plot

# Line plot------
gdp_data_time <- DataScienceExercises::aggGDPlifexp

# The following code is copy-pasted from above, with changes being marked by comments
gdp_line_plot <- ggplot(
  data = gdp_data_time, # Change data set 
  mapping = aes(# Adjust mappings
    y = gdpPercap, 
    color = continent, 
    x = year)
) + 
  geom_point(alpha=0.65) + # Remove shape specification
  geom_line() + # Add lines to the plot
  scale_color_brewer(palette = "Dark2") + # Change fill to color  
  # scale_size_continuous( # Not necessary any more
  #   range = c(0.1, 21), guide = "none") +
  scale_y_continuous(# Change from scale_x
    labels = scales::label_number(scale = 0.001, suffix = "k")
  ) +
  labs(# Adjust labels
    y="GDP per capita", 
    title = "Divergences in income", 
    caption = "Data: Gapminder.") + 
  theme_bw() +
  theme(
    legend.position = "bottom", 
    legend.title = element_blank(),
    panel.border = element_blank(),
    axis.line = element_line(colour = "grey"),
    axis.ticks = element_blank(),
    axis.title.x = element_blank() # Remove title for x axis
  )
gdp_line_plot

use-icaeDesign.R

# You can write your own themes and default functions for visualization. 
#  I have, for instance, written the package icaeDesign, which contains some
#  functions that I now use very frequently:
#  https://github.com/graebnerc/icaeDesign
#  Here is an example of how this can simplify your code:

library(DataScienceExercises)
library(icaeDesign)
# To install the package:
# install.packages("devtools")
# devtools::install_github("graebnerc/icaeDesign")

gdp_time_data <- DataScienceExercises::aggGDPlifexp

ggplot(
  data = gdp_time_data,
  mapping = aes(
    x = year, 
    y = gdpPercap, 
    color = continent)
) + 
  geom_line() + geom_point() + 
  scale_color_euf(palette = "mixed") + # To get the EUF color scheme
  theme_icae() # To use some useful default values that I like