The side-by-side comparative form
We can use the data from the D3 animated treemap to make a first cut of the comparative treemaps. First we load the data and transform it as required.
library(tidyr)
library(dplyr)
library(ggplot2)
library(ggtreemap)
xp <- read.csv("https://worldbank.github.io/wdi-sdg/sdg1/extreme_poverty.csv", stringsAsFactors = FALSE)
xp <- xp %>%
gather("year", "num_poor", year_1990:year_2013) %>%
mutate(year = substr(year, 6, 10))
# Generate the 2 year dataset
xp_2yr <- xp %>%
filter(year %in% range(year))
# Generate max of the two years
xp_max_2yr <- xp_2yr %>%
group_by(iso3c) %>%
summarise(year_max_2yr = max(num_poor))
xp_2yr <- xp_2yr %>% left_join(xp_max_2yr)
knitr::kable(head(xp_2yr))| country | iso3c | region | income_FY17 | region3c | year_max | year | num_poor | year_max_2yr |
|---|---|---|---|---|---|---|---|---|
| Albania | ALB | Europe & Central Asia | Upper middle income | ECS | 0.098898 | 1990 | 0.003619 | 0.029580 |
| Angola | AGO | Sub-Saharan Africa | Upper middle income | SSF | 7.626078 | 1990 | 5.170998 | 6.434680 |
| Argentina | ARG | Latin America & Caribbean | High Income | LCN | 4.745408 | 1990 | 0.250536 | 0.680750 |
| Armenia | ARM | Europe & Central Asia | Lower middle income | ECS | 0.943263 | 1990 | 0.384444 | 0.384444 |
| Azerbaijan | AZE | Europe & Central Asia | Upper middle income | ECS | 0.524576 | 1990 | 0.044392 | 0.044392 |
| Bangladesh | BGD | South Asia | Lower middle income | SAS | 49.732098 | 1990 | 45.083893 | 45.083893 |
Then we can make a basic version of the treemap using standard ggplot.
# Only label those with > 0.25% of the max
np.total <- sum(xp_max_2yr$year_max_2yr)
iso3c_labelled <- xp_max_2yr$iso3c[xp_max_2yr$year_max_2yr / np.total > 0.0025]
ar <- 0.75
base_plot <- ggplot(xp_2yr, aes(area = num_poor, layout_area = year_max_2yr, fill = region3c, subgroup = region3c)) +
geom_rect(aes(area = year_max_2yr), stat = "treemap", aspect.ratio = ar, color = NA, alpha = 0.25) +
geom_rect(stat = "treemap", aspect.ratio = ar, color = NA) +
geom_rect(aes(area = year_max_2yr), stat = "treemap", aspect.ratio = ar, color = "white", fill=NA, size = 0.35) +
scale_y_reverse() +
facet_wrap(~ year) +
guides(fill = guide_legend(nrow = 1, direction = "horizontal"))
base_plot +
geom_text(aes(label = iso3c),stat = "treemap", aspect.ratio = ar,color = "white", size = 2) +
theme_minimal() +
theme(axis.text = element_blank(), panel.grid = element_blank(),
legend.position = "top", strip.text = element_text(size = rel(1.2), face = "bold"))
And finally, we can polish it using country names and colors from wbgcharts, an internal package that is (not yet) public. It’s not perfect - labels should be dark when over light areas, and some of the longer country names should be split over multiple lines.
if (require(wbgcharts)) {
style <- style_atlas()
finished_plot <- base_plot +
geom_text(
aes(
label = ifelse(iso3c %in% iso3c_labelled, wbgref$countries$labels[iso3c], ""),
size = cut(year_max_2yr,c(0,50,100,Inf))
),
stat = "treemap", aspect.ratio = ar,
color = "white",
family = style$theme()$text$family
) +
scale_size_manual(values = c(0.7,0.8,1)*style$gg_text_size, guide = "none") +
scale_fill_manual(values = style$colors$regions, labels = wbgref$regions$labels) +
labs(
title = "The number of people living in extreme poverty has fallen in most countries but has risen in many Sub-Saharan African countries",
subtitle = "People living on less than $1.90 a day (2011 PPP), 1990 and 2013",
caption = "Note: *Uzbekistan (1990) based on 1998 rate because of quality issues with earlier survey data.\nSource: World Bank PovcalNet; WDI (SI.POV.DDAY)."
) +
style$theme() +
theme(axis.text = element_blank(), panel.grid = element_blank(),
legend.position = "top", strip.text = element_text(size = rel(1.2), face = "bold"))
print(finished_plot)
}