Как уже отмечалось, это просто точечные данные, и CSV, который они предоставляют, может быть хорошей заменой:
library(tidyverse)
rp_csv_url <- "https://opendata.arcgis.com/datasets/24c0b37fa9bb4e16ba8bcaa7e806c615_0.csv"
httr::GET(
url = rp_csv_url,
httr::write_disk(basename(rp_csv_url)), # won't overwrite if it exists unless explicitly told to so you get caching for free
httr::progress() # I suspect this is a big file so it's nice to see a progress bar
)
raleigh_police <- read_csv(basename(rp_csv_url))
mutate(
raleigh_police,
longitude = as.numeric(longitude), # they come in wonky, still
latitude = as.numeric(latitude) # they come in wonky, still
) -> raleigh_police
raleigh_police %>%
filter(crime_description == "Burglary/Residential") %>%
ggplot() +
stat_density_2d(
aes(longitude, latitude, fill = stat(level)),
color = "#2b2b2b", size=0.125, geom = "polygon"
) +
viridis::scale_fill_viridis(direction=-1, option="magma") +
hrbrthemes::theme_ipsum_rc()
Если выхотелось бы превратить level во что-то более значимое:
h <- c(MASS::bandwidth.nrd(rp_br$longitude),
MASS::bandwidth.nrd(rp_br$latitude))
dens <- MASS::kde2d(
rp_br$longitude, rp_br$latitude, h = h, n = 100
)
breaks <- pretty(range(dens$z), 10)
zdf <- data.frame(expand.grid(x = dens$x, y = dens$y), z = as.vector(dens$z))
z <- tapply(zdf$z, zdf[c("x", "y")], identity)
cl <- grDevices::contourLines(
x = sort(unique(dens$x)), y = sort(unique(dens$y)), z = dens$z,
levels = breaks
)
sp::SpatialPolygons(
lapply(1:length(cl), function(idx) {
sp::Polygons(
srl = list(sp::Polygon(
matrix(c(cl[[idx]]$x, cl[[idx]]$y), nrow=length(cl[[idx]]$x), byrow=FALSE)
)),
ID = idx
)
})
) -> cont
sp::coordinates(rp_br) <- ~longitude+latitude
затем:
data_frame(
ct = sapply(sp::over(cont, sp::geometry(rp_br), returnList = TRUE), length),
id = 1:length(ct),
lvl = sapply(cl, function(x) x$level)
) %>%
count(lvl, wt=ct) %>%
mutate(
pct = n/nrow(rp_br),
pct_lab = sprintf("%s of the points fall within this level", scales::percent(pct))
)
## # A tibble: 10 x 4
## lvl n pct pct_lab
## <dbl> <int> <dbl> <chr>
## 1 10. 7302 0.927 92.7% of the points fall within this level
## 2 20. 6243 0.792 79.2% of the points fall within this level
## 3 30. 4786 0.607 60.7% of the points fall within this level
## 4 40. 3204 0.407 40.7% of the points fall within this level
## 5 50. 1945 0.247 24.7% of the points fall within this level
## 6 60. 1277 0.162 16.2% of the points fall within this level
## 7 70. 793 0.101 10.1% of the points fall within this level
## 8 80. 474 0.0601 6.0% of the points fall within this level
## 9 90. 279 0.0354 3.5% of the points fall within this level
## 10 100. 44 0.00558 0.6% of the points fall within this level