Effective explanatory plots

Introduction to Data Visualization with ggplot2

Rick Scavetta

Founder, Scavetta Academy

Our goal, an effective explanatory plot

Complete data

dplyr::glimpse(gm2007_full)

Observations: 142
Variables: 3
$ country   <fct> "Afghanistan", "Albania", "Algeria", "Angola", "Argentina", "Au...
$ lifeExp   <dbl> 43.828, 76.423, 72.301, 42.731, 75.320, 81.235, 79.829, 75.635,...
$ continent <fct> Asia, Europe, Africa, Africa, Americas, Oceania, Europe, Asia, ...

¹ We would begin with our complete data set, which contains three variables for 142 countries.

First exploratory plots - distributions

ggplot(gm2007_full, aes(lifeExp)) +
  geom_histogram()

First exploratory plots - distributions

ggplot(gm2007_full_arranged, 
        aes(index, lifeExp)) +
  geom_point()

First exploratory plots - distributions

ggplot(gm2007_full_arranged, 
        aes(index, lifeExp, col = continent)) +
  geom_point()

Our data

dplyr::glimpse(gm2007)

Observations: 20
Variables: 3
$ country   <fct> "Swaziland", "Mozambique", "Zambia", "Sierra Leone", "Lesotho...
$ lifeExp   <dbl> 39.613, 42.082, 42.384, 42.568, 42.592, 42.731, 43.487, 43.82...
$ continent <fct> Africa, Africa, Africa, Africa, Africa, Africa, Africa, Asia,...
>

Use intuitive and attractive geoms

Add text labels to your plot

Use appropriate scales

Add useful titles and citations

Remove non-data ink

Add threshold lines

Add informative text

Add embellishments

Let's practice!

Introduction to Data Visualization with ggplot2