1. Upload libraries:

rm(list = ls(all=T)) #clear workspace
library(dplyr)
library(readr)
library(stringr)
library(tidyr)
library(readxl)
library(classInt)
library(RColorBrewer)
library(maptools) #to read shapefiles

2. Download the data files (note they are not ready for use but need some cleaning as there are more areas in the excel files than polygons in the shape file). I copy here the code as I have used it in my script but it’s available at RPubs thanks to David Robinson.

download.file("http://www2.census.gov/prod2/statcomp/usac/excel/LND01.xls", "LND01.xls")
download.file("http://www2.census.gov/prod2/statcomp/usac/excel/POP01.xls", "POP01.xls")

according to metadata, this is Land Area in 2010 and resident population in 2010:

us_county_area <- read_excel("LND01.xls") 
transmute(CountyCode = as.character(as.integer(STCOU)), Area = LND110210D)

us_county_population <- read_excel("POP01.xls") 
transmute(CountyCode = as.character(as.integer(STCOU)),Population = POP010210D)

3. Adjust data

election_url <- "https://raw.githubusercontent.com/Prooffreader/election_2016_data/master/data/presidential_general_election_2016_by_county.csv"
county_data <- read_csv(election_url) 
group_by(CountyCode = as.character(fips)) 
mutate(TotalVotes = sum(votes)) 
ungroup() 
mutate(name = str_replace(name, ".\\. ", "")) 
filter(name %in% c("Trump", "Clinton", "Johnson", "Stein")) 
transmute(County = str_replace(geo_name, " County", ""),
State = state,
CountyCode = as.character(fips),
Candidate = name,
Percent = vote_pct / 100,
TotalVotes) 
spread(Candidate, Percent, fill = 0) 
inner_join(us_county_population, by = "CountyCode") 
inner_join(us_county_area, by = "CountyCode")

you can save the data into a csv file:

# write_csv(county_data, "county_election_2016.csv")

You can download the cleaned datafile here: data_election_2016_by_county

4. Upload data and shape files

setwd("/Users/...")

dt <- read.csv("new_county_election_2016.csv", header=T)
us <- readShapePoly("./USA_adm/USA_adm2.shp")
us0 <- readShapePoly("./USA_adm/USA_adm0.shp")
us.m <- us[-c(which(us$NAME_1=="Alaska")),] #get rid of Alaska
us.d <- us.m[-c(67:71),]

5. Prepare the color palette(s)

nclassint <- 5 #number of colors to be used in the palette
cat.T <- classIntervals(dt$Trump[-c(67:71)], nclassint,style = "jenks") #style refers to how the breaks are created
colpal.T <- brewer.pal(nclassint,"Reds")
color.T <- findColours(cat.T,colpal.T) #sequential
bins.T <- cat.T$brks
lb.T <- length(bins.T)

5. Plot the maps with map basic…

# pdf("Where are the trump voters.pdf")
# plot(us.d, col=color.T, border=F)
# plot(us0,add=T, lwd=0.1)
# legend("bottomleft",fill=colpal.T,legend=paste(round(bins[-length(bins.T)],1),":",round(bins.T[-1],1)),cex=1, bg="white")
# dev.off()

… or ggplot2

library(ggplot2)
library(scales)
theme_set(theme_bw())

ggplot(county_data, aes(Population / Area, Trump)) +
  geom_point() +
  geom_point(data=county_data[which(county_data$State=="Texas"),], aes(x=Population/Area, y=Trump), colour="red")+
  scale_x_log10() +
  scale_y_continuous(labels = percent_format()) +
  xlab("Population density (ppl / square mile)") +
  ylab("% of votes going to Trump") +
  geom_text(aes(label = County), vjust = 1, hjust = 1, check_overlap = TRUE) +
  geom_smooth(method = "lm") +
  ggtitle("Population density vs Trump voters by county (Texas Counties in red)")

This is the code to plot in red points according to State (in red) and to add red labels to those points. The check_overlap=T avoids overlapping labels.

# ggplot(county_data, aes(Population / Area, Trump)) +
#   geom_point() +
#   geom_point(data=county_data[which(county_data$State=="California"),], aes(x=Population/Area, y=Trump), colour="red")+
#   scale_x_log10() +
#   scale_y_continuous(labels = percent_format()) +
#   xlab("Population density (ppl / square mile)") +
#   ylab("% of votes going to Trump") +
#   geom_text(data=county_data[which(county_data$State=="California"),], aes(label = ifelse(Trump>.5, as.character(dt$County), "" )), color= "red",size=5,vjust = 1, hjust = 1, check_overlap = TRUE) +
#   geom_smooth(method = "lm") +
#   ggtitle("Population density vs Trump voters by county (California in red)")