Line Charts & Scatter Plots

April 23, 2024

Links to Classwork Folders

Box
Dropbox

Huntington’s Three Waves

Setup

library(vdemdata)
library(tidyverse)

dem_waves_ctrs <- vdem |>
  select(
    country = country_name,     
    year, 
    polyarchy = v2x_polyarchy, 
  ) |>
  filter( 
    country %in% c("United States of America", # select countries in this list
                   "Japan", 
                   "Portugal")
    )

write_csv(dem_waves_ctrs, "data/dem_waves_ctrs.csv")

02:00

Line Chart

Here is the code…

# in this ggplot() call, we add a third dimension for line color
ggplot(dem_waves_ctrs, aes(x = year, y = polyarchy, color = country)) +
  geom_line(linewidth = 1) + # our geom is a line with a width of 1
  labs(
    x = "Year", 
    y = "Polyarchy Score", 
    title = 'Democracy in countries representing three different "waves"', 
    caption = "Source: V-Dem Institute", 
    color = "Country" # make title of legend to upper case
  )

Use geom_line() to specify a line chart…

# in this ggplot() call, we add a third dimension for line color
ggplot(dem_waves_ctrs, aes(x = year, y = polyarchy, color = country)) +
  geom_line(linewidth = 1) + # our geom is a line with a width of 1
  labs(
    x = "Year", 
    y = "Polyarchy Score", 
    title = 'Democracy in countries representing three different "waves"', 
    caption = "Source: V-Dem Institute", 
    color = "Country" # make title of legend to upper case
  )

Add third dimension to the aes() call for line color…

# in this ggplot() call, we add a third dimension for line color
ggplot(dem_waves_ctrs, aes(x = year, y = polyarchy, color = country)) +
  geom_line(linewidth = 1) + # our geom is a line with a width of 1
  labs(
    x = "Year", 
    y = "Polyarchy Score", 
    title = 'Democracy in countries representing three different "waves"', 
    caption = "Source: V-Dem Institute", 
    color = "Country" # make title of legend to upper case
  )

Modify the legend title…

# in this ggplot() call, we add a third dimension for line color
ggplot(dem_waves_ctrs, aes(x = year, y = polyarchy, color = country)) +
  geom_line(linewidth = 1) + # our geom is a line with a width of 1
  labs(
    x = "Year", 
    y = "Polyarchy Score", 
    title = 'Democracy in countries representing three different "waves"', 
    caption = "Source: V-Dem Institute", 
    color = "Country" # make title of legend to upper case
  )

Problem

Color Blindness

Color Vision Deficiency (CVD) or color blindness affects 8 percent of men and 1 in 200 women
There are different types of CVD but most common is red-green color blindness
Therefore, don’t include red and green in the same chart!
Look for color blind safe palettes

Solution: Use a colorblind safe color scheme like viridis…

Use scale_color_viridis_d() in this case to specify the viridis color scheme…

# in this ggplot() call, we add a third dimension for line color
ggplot(dem_waves_ctrs, aes(x = year, y = polyarchy, color = country)) +
  geom_line(linewidth = 1) + # our geom is a line with a width of 1
  labs(
    x = "Year", 
    y = "Polyarchy Score", 
    title = 'Democracy in countries representing three different "waves"', 
    caption = "Source: V-Dem Institute", 
    color = "Country" # make title of legend to upper case
  ) +
  scale_color_viridis_d(option = "mako", end = .8) # use viridis color palette

Better!

Palettes

There are a number of viridis palettes
See this reference to view different palettes and options
You can also use scale_color_viridis_c() to specify a continuous color scale
Also check out the paletteer package for easy access to many more palettes

Your Turn!

See table three of this article
Select three countries to visualize
Adjust setup code to filter data on those countries
Visualize with geom_line()
Use scale_color_viridis_d() to specify a viridis color scheme

10:00

Scatter Plot Setup

dem_summary_ctry <- read_csv("data/dem_women.csv") |>
  group_by(country, region) |> # group by country, keep region
  summarize(
    polyarchy = mean(polyarchy, na.rm = TRUE),
    gdp_pc = mean(gdp_pc, na.rm = TRUE), 
    flfp = mean(flfp, na.rm = TRUE), 
    women_rep = mean(women_rep, na.rm = TRUE)
  )

Scatter Plot

Use geom_point()…

ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy, color = region, size = women_rep)) +
  geom_point() + # use geom_point() for scatter plots
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute", 
    color = "Region",
    size = "Women Reps"
    ) +
  scale_color_viridis_d(option = "inferno", end = .8)

Scatter Plot

Four dimensions…

ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy, color = region, size = women_rep)) + 
  geom_point() + # use geom_point() for scatter plots
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute", 
    color = "Region",
    size = "Women Reps"
    ) +
  scale_color_viridis_d(option = "inferno", end = .8)

Scatter Plot

Stretch axis on log scale and use scales package to adjust labels…

ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy, color = region, size = women_rep)) + 
  geom_point() + # use geom_point() for scatter plots
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute", 
    color = "Region",
    size = "Women Reps"
    ) +
  scale_color_viridis_d(option = "inferno", end = .8)

Scatter Plot

Change legend titles…

ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy, color = region, size = women_rep)) + 
  geom_point() + # use geom_point() for scatter plots
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute", 
    color = "Region",
    size = "Women Reps"
    ) +
  scale_color_viridis_d(option = "inferno", end = .8)

Your Turn!

There are four variables in dem_summary_ctry
Pick one related to women’s empowerment
Visualize it on the y-axis with gdp_pc or polyarchy on the x-axis
Change labels and legend titles to match your visualization
Interpret your plot

05:00

Add a Trend Line

ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy)) + 
  geom_point(aes(color = region)) + 
  geom_smooth(method = "lm", linewidth = 1) + 
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute", 
    color = "Region"
    ) +
  scale_color_viridis_d(option = "inferno", end = .8)

Add a Trend Line

Taking out size and adding color to geom_point() call…

ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy)) + 
  geom_point(aes(color = region)) + 
  geom_smooth(method = "lm", linewidth = 1) + 
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute", 
    color = "Region"
    ) + 
  scale_color_viridis_d(option = "inferno", end = .8)

Add a Trend Line

Changing legend titles…

ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy)) + 
  geom_point(aes(color = region)) + 
  geom_smooth(method = "lm", linewidth = 1) + 
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute", 
    color = "Region"
    ) +
  scale_color_viridis_d(option = "inferno", end = .8)

Your Turn!

Add a trendline to your plot
Change the labels accordingly
Try using method = "loess" instead of a “lm”

05:00

Facet Wrapping

Use facet_wrap() with ~ before variable you want to wrap on…

ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy)) + 
  geom_point() + 
  geom_smooth(method = "lm", linewidth = 1) + 
  facet_wrap(~ region) +
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute"
    )

Facet Wrapping

What else changes? Back down to two dimensions…

ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy)) + 
  geom_point() + 
  geom_smooth(method = "lm", linewidth = 1) + 
  facet_wrap(~ region) +
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute"
    )

Facet Wrapping

Don’t forget to take the legend title out of the captions…

ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy)) + 
  geom_point() + 
  geom_smooth(method = "lm", linewidth = 1) + 
  facet_wrap(~ region) +
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute"
    )

Your Turn!

Facet wrap your scatter plot
Use scales = "free" in facet_wrap call to fix the West
- facet_wrap(~ region, scales = "free")

05:00

Labeling Points

Filter for Asia, add labels with geom_text()…

dem_summary_ctry |> 
  filter(region == "Asia") |>
  ggplot(aes(x = gdp_pc, y = polyarchy)) + 
    geom_point() + 
    geom_text(aes(label = country), size = 2, vjust = 2) +
    geom_smooth(method = "lm", linewidth = 1) +
    scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
      labs(
        x= "GDP Per Capita", 
        y = "Polyarchy Score",
        title = "Wealth and democracy in Asia, 1990 - present", 
        caption = "Source: V-Dem Institute"
        )

Your Turn!

Filter for Asia or another region
Use geom_text() to add labels to your points
Play with size and vjust paramters

05:00

Make it Interactive

Use plotly to make any plot interactive…

library(plotly)

modernization_plot <- ggplot(dem_summary_ctry, aes(x = gdp_pc, y = polyarchy)) + 
  geom_point(aes(color = region)) + 
  aes(label = country) +
  geom_smooth(method = "lm", linewidth = 1) + 
  scale_x_log10(labels = scales::label_number(prefix = "$", suffix = "k")) +
  labs(
    x= "GDP per Capita", 
    y = "Polyarchy Score",
    title = "Wealth and democracy, 1990 - present", 
    caption = "Source: V-Dem Institute", 
    color = "Region"
    ) +
  scale_color_viridis_d(option = "inferno", end = .8)

ggplotly(modernization_plot, tooltip = c("country", "gdp_pc", "polyarchy"))