---
title: "Choropleth maps with {ggplot2} and {mapdata}"
author: "Rubén F. Bustillo"
output:
flexdashboard::flex_dashboard:
source_code: embed
orientation: columns
theme: simplex
vertical_layout: fill
---
```{r setup, include=FALSE}
## Packages / libraries to be loaded:
library(flexdashboard)
library(tidyverse)
library(gapminder)
library(mapdata)
library(stringr)
library(viridis)
# country codes in gapminder::country_codes
gapminder_codes <- gapminder::country_codes
# countries with info in gapminder::gapminder_unfiltered
gapminder <-gapminder::gapminder_unfiltered
# We join both datasets with inner_join to get a dataset with the info by
# country, continent and country-code
gapminder <- gapminder %>%
inner_join(gapminder_codes, by= "country") %>%
mutate(code = iso_alpha)
# A map of the world (Antarctica removed)
world <- map_data("world") %>%
filter(region != "Antarctica")
```
[www.rquer.netlify.com](https://rquer.netlify.com/)
Row {.tabset .tabset-fade}
-------------------------------------------------------------
### Base Map
```{r, fig.height=6, fig.width= 12}
# our first try would be this:
# gapminder %>%
# filter(year == 2007) %>%
# inner_join(maps::iso3166 %>%
# select(a3, mapname), by= c(code = "a3")) %>%
# inner_join(world, by= c(mapname = "region")) %>%
# ggplot(aes(long, lat, group= group, fill= lifeExp)) +
# geom_polygon() +
# labs("Malaria deaths in 2000 ")
# But China, Norway and Findland do not appear in the map. The reason is that they come with more info in brackets:
# maps::iso3166 %>% filter( a3 == "NOR" | a3 == "CHN" | a3 == "FIN")
# We modify our dataset removing the brackets using regular expresions:
# We join (inner join) our dataset with map::iso3166 to ensure the names of
# the countries are the same.
gapminder_data <- gapminder %>%
inner_join(maps::iso3166 %>%
select(a3, mapname), by= c(code = "a3")) %>%
mutate(mapname = str_remove(mapname, "\\(.*"))
# Our first map (Base Map) for 2007
map_data("world") %>%
tbl_df() %>%
inner_join(gapminder_data, by=c(region= "mapname")) %>%
filter(year == 2007) %>%
ggplot(aes(long, lat, group= group, fill= lifeExp)) +
geom_polygon(color = "white", size= 0.2) +
labs(title="Life Expectancy",
subtitle = "Year: 2007",
caption = "Source: gapminder.org",
fill = "Years") +
theme(plot.title=element_text(size = 18,
hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
plot.caption = element_text(size = 8, hjust = 1)) +
coord_fixed (ratio = 1.3)
```
### Color gradient
```{r, fig.height=6, fig.width= 12}
# We can modify the colors indicating a low value, a high value and a
# midpoint with `scale_fill_gradient2()`.
# The POSITION OF THE LEGEND can be modified also and moved to another location.
# We can change some aspects of the map (background, title position, etc.)
map_data("world") %>%
tbl_df() %>%
inner_join(gapminder_data, by=c(region= "mapname")) %>%
filter(year == 2007) %>%
ggplot(aes(long, lat, group= group, fill= lifeExp)) +
geom_polygon(color = "white", size = 0.05) +
scale_fill_gradient2(low = "firebrick1",
high= "cornflowerblue",
midpoint = 60) +
labs(title="Life Expectancy",
subtitle = "Year: 2007",
caption = "Source: gapminder.org",
fill = "Years") +
theme(
axis.line = element_blank(),
axis.text = element_blank(),
axis.title = element_blank(),
axis.ticks = element_blank(),
plot.background = element_rect(fill = "snow", color = NA),
panel.background = element_rect(fill = "snow", color = NA),
plot.title = element_text(size = 16, hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
plot.caption = element_text(size = 8, hjust = 1),
legend.title = element_text(color = "grey40", size = 8),
legend.text = element_text(color = "grey40", size = 7, hjust = 0),
legend.position = c(0.1, 0.25),
legend.background = element_blank(),
plot.margin = unit(c(0.5,2,0.5,1), "cm")) +
coord_fixed (ratio = 1.3)
```
### Color gradient with {Viridis}
```{r, fig.height=6, fig.width= 12}
# We can use the color palettes of the {viridis} package:
# https://cran.r-project.org/web/packages/viridis/vignettes/intro-to-viridis.html
map_data("world") %>%
tbl_df() %>%
inner_join(gapminder_data, by=c(region= "mapname")) %>%
filter(year == 2007) %>%
ggplot(aes(long, lat, group= group, fill= lifeExp)) +
geom_polygon(color = "black", size = 0.05, alpha = 0.8) +
scale_fill_viridis(option = "C") +
labs(title="Life Expectancy",
subtitle = "Year: 2007",
caption = "Source: gapminder.org",
fill = "Years") +
theme(
axis.line = element_blank(),
axis.text = element_blank(),
axis.title = element_blank(),
axis.ticks = element_blank(),
plot.background = element_rect(fill = "lightsteelblue1", color = NA),
panel.background = element_rect(fill = "lightsteelblue1", color = NA),
plot.title = element_text(size = 16, hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
plot.caption = element_text(size = 8, hjust = 1),
legend.title = element_text(color = "grey40", size = 8),
legend.text = element_text(color = "grey40", size = 7, hjust = 0),
legend.position = c(0.05, 0.25),
legend.background = element_blank(),
plot.margin = unit(c(0.5,2,0.5,1), "cm")) +
coord_fixed (ratio = 1.3)
```
### Set breaks with `scale_fill_gradientn()`
```{r, fig.height=6, fig.width= 12}
# We can set the gradient breaks with `scale_fill_gradientn(breaks = c())`.
# For example, lets add breaks each 5 years.
# In this example the order of the legend values has been revered with `trans = "reverse"`
map_data("world") %>%
tbl_df() %>%
inner_join(gapminder_data, by=c(region= "mapname")) %>%
filter(year == 2007) %>%
ggplot(aes(long, lat, group= group, fill= lifeExp)) +
geom_polygon(color = "white", size = 0.1) +
scale_fill_gradientn(colours = terrain.colors(11),
trans = "reverse",
breaks = c(40,45,50,55,60,65,70,75,80,85)) +
labs(title="Life Expectancy",
subtitle = "Year: 2007",
caption = "Source: gapminder.org",
fill = "Years") +
theme_minimal() +
coord_fixed (ratio = 1.3) +
theme(plot.title = element_text(size = 16, hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
plot.caption = element_text(size = 8, hjust = 1))
```
### Logarithmic scale
```{r, fig.height=6, fig.width= 12}
# We might need to represent log scales in the legend. For example, if we
# want to represent in the map the population of the countries of our dataset,
# where China and India have more than one thousand million people,
# we will have to adjust our legend. To do that we can use the function
# `scale_fill_gradientn(trans = "log10", breaks = c()).
# We use 'options(scipen=10000)` to avoid scientific notations.
# To add commas use: `scale_fill_gradientn(labels = scales::comma)
# In this ocassion we have used the rainbow palette with 11
options(scipen=10000)
map_data("world") %>%
tbl_df() %>%
inner_join(gapminder_data, by=c(region= "mapname")) %>%
filter(year == 2007) %>%
ggplot(aes(long, lat, group= group, fill= pop)) +
geom_polygon(color = "darkgrey", size = 0.7, alpha = 0.5) +
scale_fill_gradientn(colours = rainbow(11),
trans = "log10",
breaks = c(10000, 100000,1000000, 10000000, 100000000, 1000000000),
labels = scales::comma) +
theme_void() +
labs(title="Population by country in 2007 ",
fill ="Population (log scale)") +
theme(plot.title=element_text(size = 16,
hjust = 0.5))+
coord_fixed (ratio = 1.3)
```
### Colors for group intervals
```{r, fig.height=6, fig.width= 12}
# In this maps 6 year groups have been created using the function `case_when()`
# The Spectral palette is used to select a color for each group.
# Spectral: Divergin palette from {RColorBrewer}
map_data("world") %>%
tbl_df() %>%
inner_join(gapminder_data, by=c(region= "mapname")) %>%
filter(year == 2007) %>%
mutate(groups = case_when(
lifeExp > 0 & lifeExp <= 40 ~ "Less than 40",
lifeExp > 40 & lifeExp <= 50 ~ "between 40 & 50",
lifeExp > 50 & lifeExp <= 60 ~ "between 50 & 60",
lifeExp > 60 & lifeExp <= 70 ~ "between 60 & 70",
lifeExp > 70 & lifeExp <= 80 ~ "between 70 & 80",
TRUE ~ "More than 80"
)) %>%
ggplot(aes(long, lat, group= group, fill= groups)) +
geom_polygon(color = "black", size = 0.2, alpha = 0.8) +
theme_void() +
labs(title="Life expectancy by country in 2007",
fill = "") +
coord_fixed (ratio = 1.3) +
theme(plot.title=element_text(size = 16,
hjust = 0.5),
panel.background = element_rect(colour = "grey", size = 1),
legend.position = "bottom") +
scale_fill_brewer(palette = "Spectral")
```
### Colors with `scale_fill_manual()`
```{r, fig.height=6, fig.width= 12}
# We can select manually the colors we want to use for each one of the
# groups created in the previous map.
# To do that we use scale_fill_manual(values = c())` where we indicate the
# preferred color for each group.
# List of colors here: http://www.stat.columbia.edu/~tzheng/files/Rcolor.pdf
map_data("world") %>%
tbl_df() %>%
inner_join(gapminder_data, by=c(region= "mapname")) %>%
filter(year == 2007) %>%
mutate(groups = case_when(
lifeExp > 0 & lifeExp <= 40 ~ "Less than 40",
lifeExp > 40 & lifeExp <= 50 ~ "between 40 & 50",
lifeExp > 50 & lifeExp <= 60 ~ "between 50 & 60",
lifeExp > 60 & lifeExp <= 70 ~ "between 60 & 70",
lifeExp > 70 & lifeExp <= 80 ~ "between 70 & 80",
TRUE ~ "More than 80"
)) %>%
ggplot(aes(long, lat, group= group, fill= groups)) +
geom_polygon(color = "white", size = 0.2, alpha = 0.8) +
theme_void() +
labs(title="Life expectancy by country in 2007",
fill = "") +
coord_fixed (ratio = 1.3) +
theme(plot.title=element_text(size = 16,
hjust = 0.5),
panel.background = element_rect(colour = "grey", size = 1),
legend.position = "top") +
scale_fill_manual(values = c("sienna1", "sienna3", "sienna", "seagreen2", "red2","seagreen" ))
```
### Facets with `facet_wrap()`
```{r, fig.height=6, fig.width= 12}
# We can also use facets when plotting maps.
# In this case 4 different years are selected by using `filter(year %in% c(1992, 1997, 2002, 2007))
# We use again the {viridis} package for the color palette (magma)
# Legend is located at the bottom using a color bar
map_data("world") %>%
tbl_df() %>%
inner_join(gapminder_data, by=c(region= "mapname")) %>%
filter(year %in% c(1992, 1997, 2002, 2007)) %>%
ggplot(aes(long, lat, group= group, fill= lifeExp)) +
geom_polygon(color = "white", size = 0.05, alpha = 0.8) +
scale_fill_viridis(
option= "magma",
direction = -1,
name = "Life Expectancy",
guide =guide_colorbar(
direction = "horizontal",
barheight = unit(2, units = "mm"),
barwidth = unit(50, units = "mm"),
draw.ulim = F,
title.position = "top",
title.hjust = 0.5,
label.hjust = 0.5
)) +
theme_void() +
facet_wrap(~year) +
labs(title="Life Expectancy in selected years") +
coord_fixed (ratio = 1.3) +
theme(plot.title=element_text(size = 16,
hjust = 0.5),
legend.position = "bottom")
```
### Subregion with `xlim()` & `ylim()`
```{r}
# One of the methods we can use to select a portion of the total maps is
# using xlim() and ylim(), indicating the coordinates of the are we want to plot.
# In this maps the color, size and font of the x and y axis title and text have been modified.
# The color and size of the legend tittle and values have also been modified.
map_data("world") %>%
tbl_df() %>%
inner_join(gapminder_data, by=c(region= "mapname")) %>%
filter(year == 2007) %>%
ggplot(aes(long, lat, group= group, fill= lifeExp)) +
geom_polygon(color = "white", size = 0.1) +
scale_fill_gradientn(colours = terrain.colors(11),
trans = "reverse",
breaks = c(40,60,80)) +
labs(title="Life Expectancy",
subtitle = "Year: 2007",
caption = "Source: gapminder.org",
fill = "Years") +
theme_minimal() +
coord_fixed (ratio = 1.3) +
theme(plot.title = element_text(size = 12, hjust = 0.5),
plot.subtitle = element_text(size = 8, hjust = 0.5),
plot.caption = element_text(size = 5, hjust = 1),
legend.title = element_text(color = "brown", size = 8),
legend.text = element_text(color = "limegreen", size = 6),
axis.text.x = element_text(face = "italic", colour = "grey", size = rel(0.5)),
axis.text.y = element_text(face = "italic", colour = "grey", size = rel(0.5)),
axis.title.x = element_text(colour = "darkgrey", size = rel(0.7)),
axis.title.y = element_text(colour = "darkgrey", size = rel(0.7))) +
xlim(c(-30, 70)) +
ylim(c(-45, 75))
```
### Subregion with `filter()`
```{r}
# In this case we use `filter(continent= "Asia")` to select a continent.
# The only countries represented in the maps are those included in the new dataset.
map_data("world") %>%
tbl_df() %>%
inner_join(gapminder_data, by=c(region= "mapname")) %>%
filter(year == 2007) %>%
filter(continent == "Asia") %>%
ggplot(aes(long, lat, group= group, fill= lifeExp)) +
geom_polygon(color = "lightgrey", size = 0.05) +
scale_fill_gradient2(low = "firebrick1",
high= "cornflowerblue",
midpoint = 65) +
labs(title="Life Expectancy in Asia",
subtitle = "Year: 2007",
caption = "Source: gapminder.org",
fill = "Years") +
theme(
axis.line = element_blank(),
axis.text = element_blank(),
axis.title = element_blank(),
axis.ticks = element_blank(),
plot.background = element_rect(fill = "snow", color = NA),
panel.background = element_rect(fill= "snow", color = NA),
plot.title = element_text(size = 16, hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
plot.caption = element_text(size = 8, hjust = 1),
legend.title = element_text(color = "grey40", size = 8),
legend.text = element_text(color = "grey40", size = 7, hjust = 0),
legend.position = c(0.05, 0.1),
plot.margin = unit(c(0.5,2,0.5,1), "cm")) +
coord_fixed (ratio = 1.3)
```
### Highlighting a region
```{r, fig.height=6, fig.width= 12}
# To highlight a specific region we can plot that region on top of a wold map.
# We will have to play with the table joins. In this case we use # `right_join()` so all the countries in the world map will stay in the dataset # even if there is no data about those places.
# We can see that there is no data in our Asia dataset of the Republic of Lao or North Korea.
gapminder_data%>%
filter(year == 2007) %>%
filter(continent == "Asia") %>%
right_join(world, by= c(mapname = "region")) %>%
ggplot(aes(long, lat, group= group, fill= lifeExp)) +
geom_polygon(color = "white", size = 0.01) +
theme_void() +
scale_fill_viridis(option = "B") +
labs(title="Life Expectancy in Asia",
subtitle = "Year: 2007",
caption = "Source: gapminder.org",
fill = "Years") +
theme(
axis.line = element_blank(),
axis.text = element_blank(),
axis.title = element_blank(),
axis.ticks = element_blank(),
plot.background = element_rect(fill = "snow", color = NA),
panel.background = element_rect(fill= "snow", color = NA),
plot.title = element_text(size = 16, hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
plot.caption = element_text(size = 8, hjust = 1),
legend.title = element_text(color = "grey40", size = 8),
legend.text = element_text(color = "grey40", size = 7, hjust = 0),
legend.position = c(0.05, 0.25),
plot.margin = unit(c(0.5,2,0.5,1), "cm")) +
coord_fixed (ratio = 1.3)
```
