spot_outliers_scatter_plot.R

library(tidyverse)
tbl <- tribble(~main_cat, ~success, ~projects,
               "Dancer", 63, 4,
               "Theater", 60, 11,
               "Comics", 55, 11,
               "Music", 47, 52,
               "Art", 42, 28,
               "Film & Video", 38, 63,
               "Games", 36, 30,
               "Design", 36, 30,
               "Publishing", 32, 40,
               "Photography", 31, 11,
               "Fashion", 26, 23,
               "Food", 25, 24,
               "Crafts", 25, 9,
               "Journalism", 22, 5,
               "Technology", 21, 32)

ggplot(tbl,
       aes(x = success, y = projects)) + 
  geom_point() +
  saridr::theme_sarid() + 
  geom_hline(yintercept = 25) + 
  geom_vline(xintercept = 37) +
  ggrepel::geom_label_repel(aes(label = main_cat)) + 
  xlab("Success rate (%)") + 
  ylab("Number of Projects (K)") + 
  ggtitle("Project versus Success rate", subtitle = "Solid lines indicate averages")