Agenda

• building maps in R
• leaflet maps
• interactive/animated graphics with highcharter

We need a few libraries to get us started on our way ...

library(ggplot2)
library(ggmap)
library(maps)
library(mapdata)
library(maptools)
library(ggthemes)

How about a county map of the USA? What about Ohio's 88 counties?

map_data("county") -> usa # get basic map data for all USA counties 
subset(usa, region == "ohio") -> oh # subset to counties in Ohio 
names(oh)

## [1] "long"      "lat"       "group"     "order"     "region"    "subregion"

• long = longitude -- measure east-west positions. The prime meridian is assigned the value of 0 degrees, and runs through Greenwich (England). Athens, Ohio has a longitude of -82.101255
• lat = latitude -- measure north-south position. The equator is defined as 0 degrees, the North Pole as 90 degrees north, and the South Pole as 90 degrees south. Athens, Ohio has a latitude of 39.329240
• group = an identifier that is unique for each subregion (here the counties)
• order = an identifier that indicates the order in which the boundary lines should be drawn
• region = string indicator for regions (here the states)
• subregion = string indicator for sub-regions (here the county names)

ggplot() +
  geom_polygon(data = oh, aes(x = long, y = lat), 
    fill = "white", color = "black") +
  ggtitle("a")  # bad 
ggplot() +
  geom_polygon(data = oh, aes(x = long, y = lat, 
    group = group), fill = "white", color = "black") +
  ggtitle("b")  # a slightly better basic map

ggplot() +
  geom_polygon(data = oh, aes(x = long, y = lat, 
    group = group), fill = "white", color = "black") +
  coord_fixed(1.3) +
  ggtitle("c")  # a better map 
ggplot() +
  geom_polygon(data = oh, aes(x = long, y = lat, 
    group = group, fill = subregion), color = "black", alpha = 0.3) +
  coord_fixed(1.3) +
  guides(fill = FALSE) +
  ggtitle("d")  # a colored map

Labeling the counties

• to label counties we need to find the centroid of each county and then use the county names
• county names will have to be formatted into titlecase
• taking the mean/median of latitude/longitude will not work so we use specific code to find the centroids

library(stringr)
str_to_title(oh$subregion) -> oh$county 
library(sp) 
getLabelPoint <- # Returns a county-named list of label points
function(county){Polygon(county[c('long', 'lat')])@labpt}
by(oh, oh$county, getLabelPoint) -> centroids # Returns list
do.call("rbind.data.frame", centroids) -> centroids2# Convert to Data Frame
rownames(centroids) -> centroids2$county 
names(centroids2) <- c('clong', 'clat', "county") # Appropriate Header

Now the code for the labeled plot ...

ggplot() + 
  geom_polygon(
    data = oh,
    aes(x = long, y = lat, group = group),
    fill = "white",
    color = "gray") + 
  coord_fixed(1.3) + 
  geom_text(
    data = centroids2,
    aes(x = clong, y = clat, label = county),
    color = "darkblue",
    size = 1)  + 
  theme_map()

... and the plot itself

Using fill

What if we want to fill each county with grouped values of some variable such as population density, percent in poverty, median educational attainment, etc?

(1) find and prepare the variable we want to use
(2) merge this variable with the data used to generate the map
(3) generate the map

library(readxl)
read_excel("data/acpovertyOH.xlsx", sheet = "counties") -> acpovertyOH 
c("ranking", "county", "child1216",
  "child0711", "all1216", "all0711") -> colnames(acpovertyOH) 
merge(oh, acpovertyOH[, c(2:3)], by = "county", all.x = TRUE, sort = FALSE) -> my.df 
my.df[order(my.df$order), ] -> my.df

Now the code for the map ...

ggplot() + 
  geom_polygon(
    data = my.df,
    aes(x = long, y = lat, group = group, fill = child1216),
    color = "black"
    ) + 
  coord_fixed(1.3) +
  geom_text(
    data = centroids2,
    aes(x = clong, y = clat, label = county),
    color = "black",
    size = 2.25
    ) + 
  scale_fill_distiller(palette = "Spectral") + 
  labs(fill = "Child Poverty %") + 
  theme_map() +
  theme(legend.position = "bottom")

... and now the map itself

That isn't a bad map but we could do better, by creating quartiles (4 groups) or quintiles (5 groups) so that it is easier to pinpoint which county falls into what group

library(dplyr)
my.df %>% 
  mutate(
    grouped_poverty = cut(
      child1216, 
      breaks = c(quantile(my.df$child1216,
      probs = seq(0, 1, by = 0.2))),
      labels = c("0-20", "20-40", "40-60", "60-80", "80-100"),
      include.lowest = TRUE)
    ) -> my.df

ggplot() +
  geom_polygon(data = my.df, aes(x = long, y = lat, 
    group = group, fill = grouped_poverty), color = "black") + 
    coord_fixed(1.3) +
  geom_text(data = centroids2, aes(x = clong, 
    y = clat, label = county), color = "white", size = 2.25) + 
    scale_fill_brewer(palette = "Set1", direction = -1) +
  labs(fill = "Poverty Quintiles") + 
  theme_map()

map is on the following slide ...

library(tidyverse)
library(urbnmapr)
states %>%
  ggplot(aes(long, lat, group = group)) +
    geom_polygon(fill = "grey", color = "#ffffff", size = 0.25) +
    coord_map(projection = "albers", lat0 = 39, lat1 = 45)

counties %>%
  ggplot(aes(long, lat, group = group)) +
    geom_polygon(fill = "grey", color = "#ffffff", size = 0.05) +
    coord_map(projection = "albers", lat0 = 39, lat1 = 45)

leaflet is an easy to learn a JavaScript library that generates interactive maps

library(leaflet)
library(leaflet.extras)
library(widgetframe)
leaflet() %>% 
  setView(lat = 39.322577, lng = -82.106336, zoom = 14) %>% 
  addTiles() %>% 
  setMapWidgetStyle() %>% 
  frameWidget(width = '1000', height = '320') -> m1 
m1

drop a pin on Building 21

leaflet() %>%
  setView(lat = 39.322577, lng = -82.106336, zoom = 15) %>% 
  addMarkers(lat = 39.319984, lng = -82.107084, popup = c("The Ridges, Building 21")) %>% 
  addTiles() %>% 
  setMapWidgetStyle() %>% 
  frameWidget(width = '1000', height = '320') -> m2 
m2

• popup = generates a default marker with specific text

NYC Bike data

Let us map some bike-share stations in New York City. The actual data-frame is large so we draw a random sample of 30 rows with the sample_n() command from dplyr

load("data/citibike.RData")
library(dplyr)
citibike %>% 
  sample_n(30) -> citibike2

leaflet(data = citibike2, width = "100%") %>% 
  setView(lat = 40.74, lng = -73.99, zoom = 12) %>% 
  addTiles() %>% 
  addMarkers(data  = citibike2,
             lat = ~start.station.latitude, lng = ~start.station.longitude,
             label = ~start.station.id, popup = ~start.station.name) %>% 
  setMapWidgetStyle() %>% 
  frameWidget(width = '1000', height = '320') -> m3
m3

• If you click on a marker you will see the station's name
• One can do a lot more in terms of customizing the markers but I leave that to you to explore
• leaflet will do more than just draw markers but unfortunately we do not have time to explore its other features

Often when you are building a visualization you end up needing to squeeze multiple graphics into a single canvas, like the example below

We can do this in many ways but the easiest library to use might be patchwork

• load ggplot2 and patchwork (and any other libraries you plan to use for the plots)
• start by naming each plot; most of us end up naming them p1, p2, and so on (why? because those were the earliest examples on the web)
• then decide on how you want the plots ... how many do you have? should they be side-by-side? two side-by-side and the third in a row below these two?

Let us create three plots

library(ggplot2)
library(patchwork)
data(mtcars)
ggplot(mtcars, aes(x = factor(am, labels = c("Automatic", "Manual")), y = mpg)) +
  geom_boxplot() +
  labs(x = "Automatic/Manual", y = "Miles per gallon") -> p1 
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  labs(x = "Curb Weight", y = "Miles per gallon") -> p2 
ggplot(mtcars, aes(x = qsec, y = mpg)) +
  geom_point() +
  labs(x = "Quarter Mile times", y = "Miles per gallon") +
  facet_wrap(~gear) -> p3

p1 + p2

p1 + p2 + plot_layout(ncol = 1)

plot_layout() has several options, key ones will be

• ncol, nrow: number of columns/rows
• byrow: how should the plots be embedded, by filling columns first or by filling rows first
• widths, heights: relative widths/heights of each column and row in the grid. Will get repeated to match the dimensions of the grid.

(p1 + (p2 + p3) + 
  plot_layout(ncol = 1))

(p1 | p2 | p1) / p3

the | specifies vertical layouts and the / specifies horizontal layouts

(p1 + (p2 + p3) + plot_layout(ncol = 1, heights = c(1,2)))

• see other settings here
• you can also explore cowplot here

highcharter is one of my favorite packages for dynamic plots because it builds them with ease and yet they are visually stunning (see below)

Scatterplot

load("data/epa.RData")
epa %>% 
  filter(year == 2019) %>% 
  sample_n(100) -> epa2 
hchart(epa2, "scatter", hcaes(x = city08, y = highway08, group = make)) -> hc1 
frameWidget(hc1, width = 1000, height = 350)

Line chart

load("data/unemprate.RData")
library(lubridate)
year(urate$yearmonth) -> urate$year 
urate %>% 
  group_by(educ_group, year) %>% 
  summarise(avg.urate = mean(rate, na.rm = TRUE)) -> urate2 
hchart(urate2, "line", hcaes(x = year, y = avg.urate, group = educ_group)) -> hc2 
frameWidget(hc2, width = 1000, height = 375)

Dressing up the highcharter plot

hchart(urate2, "line", hcaes(x = year, y = avg.urate, group = educ_group)) %>% 
   hc_title(text = "<span style=\"color:#e88e88\"> Unemployment Rates by Educational Group</span>", useHTML = TRUE) %>% 
  hc_tooltip(table = TRUE, sort = TRUE, digits = 2) %>% 
  hc_add_theme(hc_theme_flatdark()) -> hc3 
frameWidget(hc3, width = 1050, height = 400)