Bubble chart with R
A bubble chart displays multi-dimensional data in a two-dimensional plot. It can be considered as a variation of the scatterplot, in which the dots are replaced with bubbles. However, unlike a scatterplot which has only two variables defined by the X and Y axis, on a bubble chart each data point (bubble) can be assigned with a third variable (by size of bubble) and a fourth variable (by colour of bubble)
More about: Bubble chart
Bubble chart
# Loading required packages
library(unhcrthemes)
library(tidyverse)
library(scales)
library(ggrepel)
# Loading data
df <- read_csv("https://raw.githubusercontent.com/GDS-ODSSS/unhcr-dataviz-platform/master/data/correlation/bubble.csv")
# Plot
ggplot(df, aes(
x = refugee_number,
y = idp_number
)) +
geom_point(aes(size = total_number),
color = unhcr_pal(n = 1, "pal_blue"),
alpha = 0.6
) +
scale_size(
range = c(4, 16),
name = "Total population",
labels = label_number_si(),
breaks = c(8e6, 10e6, 12e6)
) +
geom_text_repel(aes(label = region),
size = 8 / .pt
) +
labs(
title = "Comparison of refugee and IDP population by region | 2021",
y = "Number of IDPs",
x = "Number of refugees",
caption = "Source: UNHCR Refugee Data Finder\n© UNHCR, The UN Refugee Agency"
) +
scale_x_continuous(labels = label_number_si()) +
scale_y_continuous(
labels = label_number_si(),
breaks = pretty_breaks(n = 6)
) +
coord_cartesian(clip = "off") +
theme_unhcr(
grid = "XY",
axis = FALSE,
axis_title = "xy",
legend_title = TRUE
)
Bubble chart with colours
# Loading required packages
library(unhcrthemes)
library(tidyverse)
library(scales)
library(ggrepel)
# Loading data
df <- read_csv("https://raw.githubusercontent.com/GDS-ODSSS/unhcr-dataviz-platform/master/data/correlation/bubble.csv")
# Order regions for visualization
df$region <- factor(df$region,
levels = c("East and Horn of Africa and Great Lakes", "Southern Africa", "West and Central Africa", "Americas", "Asia and the Pacific", "Europe", "Middle East and North Africa")
)
# Plot
ggplot(
df,
aes(
x = refugee_number,
y = idp_number
)
) +
geom_point(aes(
size = total_number,
color = region
),
alpha = 0.6
) +
scale_size(
range = c(4, 16),
name = "Total population",
labels = label_number_si(),
breaks = c(8e6, 10e6, 12e6)
) +
geom_text_repel(aes(label = region),
size = 8 / .pt
) +
labs(
title = "Comparison of refugee and IDP population by region | 2021",
y = "Number of IDPs",
x = "Number of refugees",
caption = "Source: UNHCR Refugee Data Finder\n© UNHCR, The UN Refugee Agency"
) +
scale_x_continuous(labels = label_number_si()) +
scale_y_continuous(
labels = label_number_si(),
breaks = pretty_breaks(n = 6)
) +
scale_color_unhcr_d(
palette = "pal_unhcr_region",
guide = "none"
) +
coord_cartesian(clip = "off") +
theme_unhcr(
grid = "XY",
axis = FALSE,
axis_title = "xy",
legend_title = TRUE
) +
guides(size = guide_legend(override.aes = list(shape = 21)))
