Using geom_beeswarm() for visualization of price distributions across vehicle types
The Qatar Cars dataset provides a modern, internationally-focused alternative to classic automotive datasets like mtcars and mpg. Collected in early 2025 by Paul Musgrave and students in his international politics course at Georgetown University in Qatar, this dataset addresses “U.S. defaultism” in data science education by using International System (SI) units, featuring globally diverse car manufacturers including Chinese brands, and incorporating modern vehicle types like electric and hybrid cars. The dataset includes 2025 prices in Qatari Riyals (QAR), with exchange rates of 1 USD = 3.64 QAR and 1 EUR = 4.15 QAR at the time of collection. Available through the {qatarcars} R package and as part of #TidyTuesday, the dataset contains 15 variables covering car specifications (dimensions in meters, mass in kilograms), performance metrics (horsepower, 0-100 km/h acceleration time), economic factors (fuel economy in liters per 100 km, price), and categorical information (origin country, engine type, vehicle type).
.
pacman::p_load(
tidyverse, # All things tidy
scales, # Nice Scales for ggplot2
fontawesome, # Icons display in ggplot2
ggtext, # Markdown text support for ggplot2
showtext, # Display fonts in ggplot2
colorspace, # Lighten and Darken colours
patchwork # Composing Plots
)
pacman::p_load(ggbeeswarm)
qatarcars <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-12-09/qatarcars.csv')# Font for titles
font_add_google("Saira",
family = "title_font"
)
# Font for the caption
font_add_google("Saira Condensed",
family = "body_font"
)
# Font for plot text
font_add_google("Saira Extra Condensed",
family = "caption_font"
)
showtext_auto()
# A base Colour
bg_col <- "white"
seecolor::print_color(bg_col)
# Colour for highlighted text
text_hil <- "grey40"
seecolor::print_color(text_hil)
# Colour for the text
text_col <- "grey30"
seecolor::print_color(text_col)
line_col <- "grey30"
# Define Base Text Size
bts <- 80
mypal <- paletteer::paletteer_d("ltc::trio3")[c(2, 3, 1)]
# Caption stuff for the plot
sysfonts::font_add(
family = "Font Awesome 6 Brands",
regular = here::here("docs", "Font Awesome 6 Brands-Regular-400.otf")
)
github <- ""
github_username <- "aditya-dahiya"
xtwitter <- ""
xtwitter_username <- "@adityadahiyaias"
social_caption_1 <- glue::glue("<span style='font-family:\"Font Awesome 6 Brands\";'>{github};</span> <span style='color: {text_hil}'>{github_username} </span>")
social_caption_2 <- glue::glue("<span style='font-family:\"Font Awesome 6 Brands\";'>{xtwitter};</span> <span style='color: {text_hil}'>{xtwitter_username}</span>")
plot_caption <- paste0(
"**Data:** Georgetown University in Qatar | Paul Musgrave",
" | **Code:** ",
social_caption_1,
" | **Graphics:** ",
social_caption_2
)
rm(
github, github_username, xtwitter,
xtwitter_username, social_caption_1,
social_caption_2
)
plot_title <- "<span style='color:#E8A628;'>**Petrol**</span> <span style='color:grey30;'>Dominates,</span> <span style='color:#3EB595;'>**Hybrids**</span> <span style='color:grey30;'>Rise,<br>and</span> <span style='color:#5AADE2;'>**Electric**</span> <span style='color:grey30;'>Stays Premium</span>"
plot_subtitle <- "<span style='color:grey40;'>In Qatar's 2025 car market, <span style='color:#E8A628;'>**petrol vehicles**</span> span all price<br>ranges across every category. <span style='color:#3EB595;'>**Hybrids**</span> cluster in mid-to-high<br>tiers, particularly in SUVs and sedans, while <span style='color:#5AADE2;'>**electric cars**</span><br>command premium prices, especially in the coupe<br>and SUV segments.</span>"bts = 80
plotdf <- qatarcars |>
left_join(
qatarcars |>
slice_max(price, n = 15) |>
mutate(label_var = paste(model, "\n",make))
) |>
left_join(
qatarcars |>
slice_min(price, n = 15) |>
mutate(label_var = paste(model, "\n",make))
)bts <- 90
# Create the beeswarm plot
g <- plotdf |>
ggplot(
mapping = aes(
x = type,
y = price,
color = enginetype
)
) +
geom_beeswarm(
alpha = 0.9,
cex = 3,
pch = 20
) +
geom_text(
mapping = aes(label = label_var),
position = position_beeswarm(
cex = 3
),
family = "caption_font",
size = bts / 3,
check_overlap = TRUE,
hjust = -0.1,
vjust = -0.2,
lineheight = 0.25
) +
scale_y_continuous(
trans = "log10",
labels = label_number(scale_cut = cut_short_scale()),
n.breaks = 15
) +
annotate(
geom = "richtext",
x = Inf, y = 30e6,
hjust = 1, vjust = 1,
label = plot_title,
size = bts / 1.2,
label.size = NA,
family = "body_font",
lineheight = 0.45,
fill = alpha(bg_col, 0.3)
) +
annotate(
geom = "richtext",
x = Inf, y = 10e6,
hjust = 1, vjust = 1,
label = plot_subtitle,
size = bts / 2.5,
label.size = NA,
family = "body_font",
lineheight = 0.3,
fill = alpha(bg_col, 0.3)
) +
scale_size_continuous(
range = c(2, 10),
name = "Horsepower"
) +
scale_colour_manual(values = mypal) +
labs(
title = NULL,
subtitle = NULL,
x = NULL,
y = "Price (in Qatari Riyal)",
caption = plot_caption
) +
theme_minimal(
base_family = "body_font",
base_size = bts
) +
theme(
legend.position = "inside",
legend.position.inside = c(1,0.7),
legend.justification = c(1,1),
legend.direction = "horizontal",
legend.margin = margin(0,0,0,0, "mm"),
legend.title = element_text(
margin = margin(0,0,0,0, "mm"),
hjust = 0.5
),
legend.text = element_text(
margin = margin(0,0,0,0, "mm")
),
legend.text.position = "right",
legend.title.position = "top",
# Overall
text = element_text(
margin = margin(0, 0, 0, 0, "mm"),
colour = text_hil,
lineheight = 0.3
),
# Axes
axis.text.x.bottom = element_text(
margin = margin(4,0,0,0, "mm"),
size = bts * 1.5,
family = "caption_font"
),
axis.text.y.left = element_text(
size = bts,
margin = margin(0,4,0,0, "mm")
),
axis.title.y.left = element_text(
margin = margin(0,0,0,0, "mm"),
size = bts * 1.5
),
axis.ticks.x.bottom = element_blank(),
axis.ticks.y.left = element_blank(),
axis.ticks.length.x = unit(0, "mm"),
axis.ticks.length.y.left = unit(0, "mm"),
axis.line = element_blank(),
panel.grid = element_blank(),
panel.grid.major.y = element_line(
linetype = 3,
linewidth = 0.3,
colour = line_col
),
plot.caption = element_markdown(
family = "caption_font",
hjust = 0.5,
margin = margin(5,0,0,0, "mm"),
colour = text_hil
),
plot.caption.position = "plot",
plot.title.position = "plot",
plot.margin = margin(5, 15, 5, 5, "mm")
)
ggsave(
filename = here::here(
"data_vizs",
"tidy_qatar_cars.png"
),
plot = g,
width = 400,
height = 500,
units = "mm",
bg = bg_col
)# Saving a thumbnail
library(magick)
# Saving a thumbnail for the webpage
image_read(here::here(
"data_vizs",
"tidy_qatar_cars.png"
)) |>
image_resize(geometry = "x400") |>
image_write(
here::here(
"data_vizs",
"thumbnails",
"tidy_qatar_cars.png"
)
)pacman::p_load(
tidyverse, # All things tidy
scales, # Nice Scales for ggplot2
fontawesome, # Icons display in ggplot2
ggtext, # Markdown text support for ggplot2
showtext, # Display fonts in ggplot2
colorspace, # Lighten and Darken colours
patchwork, # Composing Plots
ggh4x, # Proportional facets
ggchicklet, # Rounded bars
ggstream # Labels in stacked bar chart
)
sessioninfo::session_info()$packages |>
as_tibble() |>
# The attached column is TRUE for packages that were
# explicitly loaded with library()
dplyr::filter(attached == TRUE) |>
dplyr::select(package,
version = loadedversion,
date, source
) |>
dplyr::arrange(package) |>
janitor::clean_names(
case = "title"
) |>
gt::gt() |>
gt::opt_interactive(
use_search = TRUE
) |>
gtExtras::gt_theme_espn()