sina plot

Code R de l'exemple ggplot2

set.seed(20261015)
library(ggplot2)
library(ggforce)
library(dplyr)
library(datarium)

## Cleveland, the most complete of the four sites. `num` grades the narrowing
## of the arteries from 0 (none) to 4; above 0, the disease is present.
cleveland <- heartdisease |>
  filter(dataset == "cleveland") |>
  mutate(disease = factor(num > 0, levels = c(FALSE, TRUE), labels = c("No disease", "Heart disease")))

p <- ggplot(cleveland, aes(x = disease, y = thalach, colour = disease)) +
  geom_sina(size = 1.2, alpha = 0.7, maxwidth = 0.7) +
  scale_y_continuous(labels = lex_number, breaks = lex_break_breaks, expand = lex_break_expand) +
  labs(title = "Peak heart rate is lower in patients with heart disease",
       subtitle = "303 patients at the Cleveland Clinic, during an exercise test",
       x = NULL, y = "Maximum heart rate (beats per min)",
       caption = "Data: Janosi et al. 1989, UCI Machine Learning Repository (CC BY 4.0), via the datarium R package") +
  theme_lex_viz(grid = "y", arrows = "y", break_not_zero = "y") +
  theme(legend.position = "none")