fonction de répartition empirique

Code R de l'exemple ggplot2

library(ggplot2)
library(dplyr)
library(palmerpenguins)

## Each name goes left of its curve, at a height where no other curve passes.
labels <- penguins |>
  filter(!is.na(body_mass_g)) |>
  mutate(y = c(Adelie = 0.25, Chinstrap = 0.9, Gentoo = 0.5)[as.character(species)]) |>
  group_by(species) |>
  summarise(y = first(y), x = quantile(body_mass_g, y))

p <- ggplot(penguins, aes(x = body_mass_g, colour = species)) +
  stat_ecdf(linewidth = 0.7, na.rm = TRUE) +
  geom_text(data = labels, aes(x = x, y = y, label = species),
            hjust = 1, nudge_x = -60, size = 3.5) +
  scale_x_continuous(labels = lex_number, breaks = lex_break_breaks, expand = lex_break_expand) +
  scale_y_continuous(labels = scales::label_percent(), expand = expansion(mult = c(0, 0.05))) +
  labs(title = "Half the Gentoo penguins weigh 5 kg or more",
       subtitle = "Share of penguins of each species at or below each body mass",
       x = "Body mass (g)", y = "Penguins",
       caption = "Data: palmerpenguins (Horst, Hill & Gorman 2020)") +
  theme_lex_viz(break_not_zero = "x") +
  theme(legend.position = "none")