TidyTuesday 2026 Week 1: African Languages

This week we’re exploring data about popular languages spoken on the African continent. The dataset this week comes from the Languages of Africa page on Wikipedia.

Tree Plot of African Lnaguages

1. R code

# | echo: true
# | eval: false
# | warning: false
# | message: false

if(!require(tidyverse)){install.packages("tidyverse"); library(tidyverse)}
if(!require(scales)){install.packages("scales"); library(scales)}
if(!require(treemapify)){install.packages("treemapify"); library(treemapify)}
if(!require(CustomGGPlot2Theme)){devtools::install("CustomGGPlot2Theme"); library(CustomGGPlot2Theme)}

options(scipen=999)

africa <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2026/2026-01-13/africa.csv')

africa_tree <- africa %>%
  group_by(family, language) %>%
  summarise(
    native_speakers = max(native_speakers, na.rm = TRUE),
    .groups = "drop"
  ) %>% 
  filter(native_speakers >= 500000) %>%
  group_by(family) %>%
  mutate(
    language_label = paste0(
      language, 
      "\n", 
      scales::label_number(accuracy = 0.1, scale_cut = cut_short_scale())(native_speakers)
    )
  )


plot1 <- ggplot(
  africa_tree,
  aes(
    area = native_speakers,
    fill = family,
    label = language_label, 
    subgroup = family 
  )
) +
  geom_treemap() +
  geom_treemap_subgroup_border() +
  geom_treemap_subgroup_text(
    place = "centre",
    grow = TRUE,
    alpha = 0.7,
    min.size = 0 
  ) +
  geom_treemap_text(
    colour = "white",
    place = "centre",
    reflow = TRUE,
    size = 8
  ) +
  labs(
    title = "African Languages by Family",
    subtitle = "Showing langauge families with at least 500k speakers",
    fill = "Language Family"
  ) +
  theme(legend.position = "bottom")