How to make diamond plots after Bergstrom and West (2018) "Why scatter plots suggest causality, and what we can do about it"

gistfile1.txt

# https://arxiv.org/pdf/1809.09328.pdf & https://twitter.com/CT_Bergstrom/status/1035327464644333568
# they use Mathematica, boo! So let's make them with R

# starting with https://stackoverflow.com/q/33396168/1036500

library(ggplot2)


p <- ggplot() + 
  geom_point(data = anscombe,
             aes(x = x1,
                 y = y1),
             colour = "red",
             alpha = 0.5,
             size = 3) + 
  theme_minimal() +
  theme(axis.text.x=   element_text(size = 10),
        axis.text.y=   element_text(size = 10)) + 
  theme(axis.text.x =  element_text(angle=(-1 * rotation)),
        axis.text.y =  element_text(angle=(-1 * rotation)),
        axis.title.x = element_text(size = 12,
                                    angle=(-1 * rotation),
                                    vjust = 0.5, 
                                    margin = margin(t = 10),
                                    colour = "red"),
        axis.title.y = element_text(size = 12,
                                    angle=(-1 * rotation),
                                    hjust = 0.5,
                                    margin = margin(r = 20),
                                    colour = "red")) +
  coord_equal() +
  scale_x_continuous(limits = c(0, 15),
                     name  = "x") +
  scale_y_continuous(limits = c(0, 15),
                     name = "y") 


library(grid)
print(p, vp=viewport(angle=rotation,  
                     width = unit(.75, "npc"), 
                     height = unit(.75, "npc")))

How to draw a diamond plot visualization with R and ggplot2

Bergstrom and West 2018	gist of ggplot2 code