choropleth.R

library(dplyr)
library(tidyr)
library(readr)

# For other measures, see http://ghdx.healthdata.org/us-data
# TODO: do this on the county level for more interesting data, like this post - https://fivethirtyeight.com/features/mortality-black-belt/
obesity <- read_csv("http://ghdx.healthdata.org/sites/default/files/record-attached-files/IHME_USA_OBESITY_PHYSICAL_ACTIVITY_2001_2011.csv")

# reshape data so value tracks 
ob <- obesity %>%
  gather(variable, value, matches("prevalence [0-9]+ \\(%\\)")) %>%
  mutate(year = stringr::str_extract(variable, "[0-9]+")) 

ob_sum <- ob %>%
  rename(name = State) %>%
  group_by(name, year) %>%
  summarise(value = mean(value, na.rm = TRUE))

d <- ob_sum %>%
  left_join(us_lcc) %>%
  st_as_sf()

p <- ggplot(d) + 
  geom_sf(aes(fill = value, frame = year)) + 
  ggthemes::theme_map()

gg <- plotly_build(p)

# TODO: perhaps I need to report this as a bug to plotly.js?
# https://github.com/plotly/plotly.js/issues/1721
gg$x$frames <- lapply(
  gg$x$frames, function(f) { 
    f$data <- lapply(f$data, function(d) d[!names(d) %in% c("x", "y")])
    f 
  })

gg