Created
September 17, 2018 03:49
-
-
Save etachov/9342997b91efa5fd9f1b03780a4b74a8 to your computer and use it in GitHub Desktop.
Dot density map of the 2018 NYC Democrat Governor Primary
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(rvest) # web scraping | |
library(tidyverse) # general data munging | |
library(sf) # spatial functions and stats | |
library(lwgeom) # not 100% sure why, but i needed to load this so `udunits` doesn't throw an error | |
## import data ------------ | |
# import a geojson of assembly district outlines | |
nyc_ad <- st_read("http://services5.arcgis.com/GfwWNkhOj9bNBqoJ/arcgis/rest/services/nyad/FeatureServer/0/query?where=1=1&outFields=*&outSR=4326&f=geojson") | |
# scrape the table with assembly district level results from the Bureau of Elections | |
dem_gov <- read_html("https://enrweb.boenyc.us/CD22370AD0.html") %>% | |
html_node(".underline") %>% | |
html_table() %>% | |
select("AssemDist" = X1, | |
"NixonVotes" = X3, | |
"CuomoVotes" = X5, | |
"WriteInVotes" = X7) %>% | |
# clean up the table | |
filter(grepl("AD", AssemDist)) %>% | |
mutate(AssemDist = gsub("AD ", "", AssemDist)) %>% | |
mutate_all(as.numeric) | |
# join the geometry and the results. isn't `sf` grand? | |
nyc_ad_results <- left_join(nyc_ad, dem_gov) %>% | |
st_as_sf() | |
## calculating dots inside assembly districts -------------- | |
# random rounding algo to prevent systemic bias in counting. credit: https://github.com/mountainMath/dotdensity/blob/master/R/dot-density.R | |
random_round <- function(x) { | |
v=as.integer(x) | |
r=x-v | |
test=runif(length(r), 0.0, 1.0) | |
add=rep(as.integer(0),length(r)) | |
add[r>test] <- as.integer(1) | |
value=v+add | |
ifelse(is.na(value) | value<0,0,value) | |
return(value) | |
} | |
results_dots <- as.data.frame(nyc_ad_results) %>% | |
select(NixonVotes:WriteInVotes) %>% | |
# dividing results by 10 so that each dot represents 10 votes | |
mutate_all(funs(. / 10)) %>% | |
# use the random_round algot to prevent systemic bias | |
mutate_all(random_round) | |
# generate lat lon points inside assembly districts | |
# huge credit here to Paul Campbell's classic post: https://www.cultureofinsight.com/blog/2018/05/02/2018-04-08-multivariate-dot-density-maps-in-r-with-sf-ggplot2/ | |
nyc_primary_dots <- map_df(names(results_dots), | |
~ st_sample(nyc_ad_results, size = results_dots[, .x], type = "random") %>% | |
st_cast("POINT") %>% | |
st_coordinates() %>% | |
as_tibble() %>% | |
setNames(c("lon","lat")) %>% | |
mutate(Candidate = .x)) %>% | |
slice(sample(1:n())) | |
# set the palette | |
pal <- c("CuomoVotes" = "#70147A", "NixonVotes" = "#78B943", "WriteInVotes" = "#FCBB30") | |
# build the plot | |
p <- ggplot() + | |
geom_sf(data = nyc_ad_results, fill = "transparent",colour = "white") + | |
geom_point(data = nyc_primary_dots, aes(lon, lat, colour = Candidate), alpha = .6, size = .7) + | |
scale_colour_manual(values = pal) + | |
theme_void() + | |
theme(panel.grid = element_line(color = "#141414"), | |
plot.background = element_rect(fill = "#141414", color = NA), | |
panel.background = element_rect(fill = "#141414", color = NA), | |
legend.background = element_rect(fill = "#141414", color = NA), | |
) | |
ggsave("nyc_primary_density.png", plot = p, dpi = 400, width = 90, height = 70, units = "cm") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment