Areal data and creating high-quality graphics

Prof Ron Yurko

2024-09-30

Reminders, previously, and today…

Infographic draft is due Wednesday night! (more details later today…)
Your EDA report is due Friday Oct 4th by 11:59 PM ET (1 per group)
No lecture on Wednesday! But I will have virtual office hours during class time

Wrapped up basics of time series data
Introduction to spatial data and the different types
Walked through visualizing point-reference data

TODAY:

Visualizations for areal data
Discuss making high-quality graphics

Thinking about areal data

Areal Data: Geographic regions associated with one or more variables specific to those regions
Areal data will have the following form (example US states data from 1970s):

state_data |> dplyr::slice(1:3)

# A tibble: 3 × 9
  Population Income Illiteracy `Life Exp` Murder `HS Grad` Frost   Area state  
       <dbl>  <dbl>      <dbl>      <dbl>  <dbl>     <dbl> <dbl>  <dbl> <chr>  
1       3615   3624        2.1       69.0   15.1      41.3    20  50708 alabama
2        365   6315        1.5       69.3   11.3      66.7   152 566432 alaska 
3       2212   4530        1.8       70.6    7.8      58.1    15 113417 arizona

High-level overview of steps

Need to match the region with the actual geographic boundaries
Many geographic boundaries/features are stored as “shapefiles”
- i.e., complicated polygons
Can contain the lines, points, etc. to represent any geographic feature
Shapefiles are readily available for countries, states, counties, etc.

Access shapefiles using `map_data()`

library(maps)
state_borders <- map_data("state") 
head(state_borders)

       long      lat group order  region subregion
1 -87.46201 30.38968     1     1 alabama      <NA>
2 -87.48493 30.37249     1     2 alabama      <NA>
3 -87.52503 30.37249     1     3 alabama      <NA>
4 -87.53076 30.33239     1     4 alabama      <NA>
5 -87.57087 30.32665     1     5 alabama      <NA>
6 -87.58806 30.32665     1     6 alabama      <NA>

For example: map_data("world"), map_data("state"), map_data("county") (need to install maps package)
Contains lat/lon coordinates to draw geographic boundaries

Typica workflow for plotting areal data

Get state-specific data
Get state boundaries
Merge state-specific data with state boundaries (using left_join())

state_plot_data <- state_borders |>
  left_join(state_data, by = c("region" = "state"))
head(state_plot_data)

       long      lat group order  region subregion Population Income Illiteracy
1 -87.46201 30.38968     1     1 alabama      <NA>       3615   3624        2.1
2 -87.48493 30.37249     1     2 alabama      <NA>       3615   3624        2.1
3 -87.52503 30.37249     1     3 alabama      <NA>       3615   3624        2.1
4 -87.53076 30.33239     1     4 alabama      <NA>       3615   3624        2.1
5 -87.57087 30.32665     1     5 alabama      <NA>       3615   3624        2.1
6 -87.58806 30.32665     1     6 alabama      <NA>       3615   3624        2.1
  Life Exp Murder HS Grad Frost  Area
1    69.05   15.1    41.3    20 50708
2    69.05   15.1    41.3    20 50708
3    69.05   15.1    41.3    20 50708
4    69.05   15.1    41.3    20 50708
5    69.05   15.1    41.3    20 50708
6    69.05   15.1    41.3    20 50708

Plot the data

Create a choropleth map with `geom_polygon()`

state_plot_data |>
  ggplot() + 
  geom_polygon(aes(x = long, y = lat, group = group, fill = Illiteracy), 
               color = "black") + 
  scale_fill_gradient2(low = "darkgreen", mid = "lightgrey", 
                       high = "darkorchid4", midpoint = 0.95) +
  theme_void() +
  coord_map("polyconic") + 
  labs(fill = "Illiteracy %") + 
  theme(legend.position = "bottom")

Create a choropleth map with `geom_polygon()`

Uniform size with `statebins`

library(statebins)
state_data$new_state <- str_to_title(state_data$state)
statebins(state_data = state_data, 
          state_col = "new_state", value_col = "Illiteracy") +
  theme_statebins()

Many choices for displaying maps…

Visual randomization test

Infographics draft and feedback assignment

You turn in via Gradescope and email a single page PDF draft of your infographic to your assigned partner with myself cc’ed by 11:59 PM Wednesday night (no code is necessary for this draft)
For only this draft submission, you are allowed to use something like google slides or powerpoint to create your draft PDF
Detailed grading rubric for your final submission (due Oct 11th by 11:59 PM ET) is posted on Canvas

You must provide feedback to your assigned infographics partner via email (see emails I sent this morning) by Saturday night 11:59 PM ET and turn in via Gradescope as well
Feedback template is available on Canvas (and is 10% of your grade!)

Creating compound figures

Two different scenarios we may face:

Creating the same type of plot many times

e.g., using facet_wrap() or facet_grid()

Combining several distinct plots into one cohesive display

e.g., using flexible arrangement packages like cowplot or patchwork

Creating the same type of plot many times

penguins |>
  ggplot(aes(x = flipper_length_mm, y = body_mass_g)) +
  geom_point(alpha = 0.5) +
  facet_wrap(~species) +
  theme_light()

Creating the same type of plot many times

penguins |>
  ggplot(aes(x = flipper_length_mm, y = body_mass_g)) +
  geom_point(alpha = 0.5) +
  facet_grid(island ~ species) +
  theme_light()

Creating a single cohesive display of multiple plots

plot1 <- penguins |>
  ggplot(aes(x = flipper_length_mm, y = body_mass_g)) +
  geom_point(alpha = 0.5)
plot1

Creating a single cohesive display of multiple plots

plot2 <- penguins |>
  ggplot(aes(x = species, y = bill_depth_mm)) +
  geom_violin(alpha = 0.5)
plot2

Using `cowplot` to arrange plots together

library(cowplot)
plot_grid(plot1, plot2)

Using `cowplot` to arrange plots together

library(cowplot)
plot_grid(plot1, plot2, labels = c('A', 'B'), label_size = 12)

Using `patchwork` to arrange plots together

library(patchwork)
plot1 + plot2

Using `patchwork` to arrange plots together

plot1 / plot2

Using `patchwork` to arrange plots together

plot1 / plot2 + plot_annotation(tag_levels = "A")

Using `patchwork` to arrange plots together

plot3 <- penguins |>
  ggplot(aes(x = bill_length_mm, y = bill_depth_mm,
             color = species)) +
  geom_point(alpha = 0.5)
plot4 <- penguins |>
  ggplot(aes(x = bill_length_mm, y = body_mass_g,
             color = species)) +
  geom_point(alpha = 0.5)
(plot1 + plot2) / (plot3 + plot4) + plot_layout(guides = 'collect')

Using `patchwork` to arrange plots together

Using `patchwork` to arrange plots together

(plot1 + plot2) / (plot3 + plot4) + plot_layout(guides = 'collect') +
  plot_annotation(tag_levels = "A")

Using `patchwork` to arrange plots together

(plot1 + plot2) / (plot3 + plot4) + plot_layout(guides = 'collect') +
  plot_annotation(tag_levels = "A", title = "A plot about penguins",
                  subtitle = "With subtitle...", caption = "...and caption")

Infographics vs figures in papers/reports

Infographics should standalone, thus they must have a title along with a relevant subtitle and caption (located within the plot)

Infographics vs figures in papers/reports

Figures in papers/reports will have captions containing the information from the standalone title/subtitle/caption, see example:

Figure 1. Corruption and human development. The most developed countries experience the least corruption. Data sources: Transparency International & UN Human Development Report.

Thinking about themes…

See posted demo walking through color scales and customizing themes

Default choices tend to treat each element with equal weight, e.g., axes stand out as much as the data or background elements look the same as the points of emphasis

You want to design your plot with the visual hierarchy in mind:

Make elements of your plot that are more important look more important!
i.e., customize your plot so that the data is the focus, not the axes and grid lines!
Match visual weight to focus of the graphic you want to communicate

I tend to use theme_bw() or theme_light(), but there are other options from various packages such as ggthemes

Using `patchwork` to arrange plots together

(plot1 + plot2) / (plot3 + plot4) + plot_layout(guides = 'collect') +
  plot_annotation(tag_levels = "A", title = "A plot about penguins",
                  subtitle = "With subtitle...", caption = "...and caption") & 
  theme_minimal_grid()

Annotation

Using text can be a great way to highlight and explain aspects of a visualization when you’re not there to explain it
annotate() is an easy way to add text to ggplot objects or add rectangle layers for highlighting displays

mtcars |>
  ggplot(aes(x = wt, y = mpg)) + 
  geom_point() + 
  annotate("text", x = 4, y = 25, label = "Some text") +
  annotate("rect", xmin = 3, xmax = 4.2, ymin = 12, ymax = 21, alpha = .2)

Annotation tools

We’ve discussed gghighlight and ggrepel, but directlabels and ggforce are also useful

library(ggforce)
ggplot(iris, aes(Petal.Length, Petal.Width)) +
  geom_mark_rect(aes(fill = Species, label = Species)) +
  geom_point()

Saving plots

Default function for saving the last ggplot you created is ggsave
I tend to use the save_plot() function from cowplot since it has easier customization for handling panels of multiple figures

Recap and next steps

Walked through basics of visualizing areal data
Discussed various aspects of making high-quality graphics and relevant tools
No lecture on Wednesday! But I will have virtual office hours during class time
Infographic draft is due Wednesday night!
Your EDA report is due Friday Oct 4th by 11:59 PM ET (1 per group)
KH Chapter 7 Draw Maps, creating bivariate choropleths, CW Chapter 21 Multi-panel figures, CW Chapter 23 Balance the data and the context, KH Chapter 8 Refine your plots

Areal data and creating high-quality graphics

Reminders, previously, and today…

Thinking about areal data

High-level overview of steps

Access shapefiles using map_data()

Typica workflow for plotting areal data

Create a choropleth map with geom_polygon()

Create a choropleth map with geom_polygon()

Uniform size with statebins

Many choices for displaying maps…

Visual randomization test

Visual randomization test

Infographics draft and feedback assignment

Creating compound figures

Creating the same type of plot many times

Creating the same type of plot many times

Creating a single cohesive display of multiple plots

Creating a single cohesive display of multiple plots

Using cowplot to arrange plots together

Using cowplot to arrange plots together

Using patchwork to arrange plots together

Using patchwork to arrange plots together

Using patchwork to arrange plots together

Using patchwork to arrange plots together

Using patchwork to arrange plots together

Using patchwork to arrange plots together

Using patchwork to arrange plots together

Infographics vs figures in papers/reports

Infographics vs figures in papers/reports

Thinking about themes…

Using patchwork to arrange plots together

Annotation

Annotation tools

Saving plots

Recap and next steps

Access shapefiles using `map_data()`

Create a choropleth map with `geom_polygon()`

Create a choropleth map with `geom_polygon()`

Uniform size with `statebins`

Using `cowplot` to arrange plots together

Using `cowplot` to arrange plots together

Using `patchwork` to arrange plots together

Using `patchwork` to arrange plots together

Using `patchwork` to arrange plots together

Using `patchwork` to arrange plots together

Using `patchwork` to arrange plots together

Using `patchwork` to arrange plots together

Using `patchwork` to arrange plots together

Using `patchwork` to arrange plots together