Create line density per polygon using tidyverse + sf R - r

Question

I have a GIS question that has been stumping me for some time now. The end goal would be to extract the density of lines per pixel/voxel/polygon using tidyverse/sf packages. As of now I have a function that works when I execute line-by-line, but not as a function. The ultimate end-goal would be to use this function in sfLappy of the snowfall package to be run in parallel. Any help on getting this to work as a function would be greatly appreciated! The data involved can be found here....
https://www.dropbox.com/s/zg9o2b5x4wizafo/hexagons.gpkg?dl=0
https://www.dropbox.com/s/x2gxx36pjkutxzm/railroad_lines.gpkg?dl=0
The function that I had created, which, again, works line-for-line but not as a function, can be found here:
length_in_poly <- function(fishnet, spatial_lines) {
require(sf)
require(tidyverse)
require(magrittr)
fishnet <- st_as_sf(do.call(rbind, fishnet))
spatial_lines <- st_as_sf(do.call(rbind, spatial_lines))
fish_length <- list()
for (i in 1:nrow(fishnet)) {
split_lines <- spatial_lines %>%
st_cast(., "MULTILINESTRING", group_or_split = FALSE) %>%
st_intersection(., fishnet[i, ]) %>%
mutate(lineid = row_number())
fish_length[[i]] <- split_lines %>%
mutate(length = sum(st_length(.)))
}
fish_length <- do.call(rbind, fish_length) %>%
group_by(hexid4k) %>%
summarize(length = sum(length))
fishnet <- fishnet %>%
st_join(., fish_length, join = st_intersects) %>%
mutate(hexid4k = hexid4k.x,
length = ifelse(is.na(length), 0, length),
pixel_area = as.numeric(st_area(geom)),
density = length/pixel_area)
}
To prep the data:
library(sf)
library(tidyverse)
library(snowfall)
input_hexagons <- st_read("hexagons.gpkg")
input_rail_lines <- st_read("railroad_lines.gpkg")
Using some code from here:
faster_as_tibble <- function(x) {
structure(x, class = c("tbl_df", "tbl", "data.frame", "sfc"), row.names = as.character(seq_along(x[[1]])))
}
split_fast_tibble <- function (x, f, drop = FALSE, ...) {
lapply(split(x = seq_len(nrow(x)), f = f, ...),
function(ind) faster_as_tibble(lapply(x, "[", ind)))
}
Create a state-wise list:
sub_hexnet <- split_fast_tibble(input_hexagons, input_hexagons$STUSPS) %>%
lapply(st_as_sf)
Finally, to run just as a single-core process:
test <- lapply(fishnet = as.list(sub_hexnet),
FUN = length_in_poly,
spatial_lines = input_rail_lines)
Or, in the perfect world, a multi-core process:
sfInit(parallel = TRUE, cpus = parallel::detectCores())
sfExport(list = c("sub_hexnet", "mask_rails"))
extractions <- sfLapply(fishnet = sub_hexnet,
fun = length_in_poly,
spatial_lines = input_rail_lines)
sfStop()
Thanks in advance for any help - I am completely stumped!

Answer 1

After messing around with this for a while I finally figured out a solution.
The key helper functions used:
load_data <- function(url, dir, layer, outname) {
file <- paste0(dir, "/", layer, ".shp")
if (!file.exists(file)) {
download.file(url, destfile = paste0(dir, ".zip"))
unzip(paste0(dir, ".zip"),
exdir = dir)
unlink(paste0(dir, ".zip"))
}
name <- paste0(outname, "_shp")
name <- sf::st_read(dsn = dir, layer = layer)
name
}
get_density <- function(x, grids, lines) {
require(tidyverse)
require(lubridate)
require(sf)
sub_grids <- grids %>%
dplyr::filter(hexid4k == x)
single_lines_hexid <- lines %>%
dplyr::filter(hexid4k == x) %>%
sf::st_intersection(., sub_grids) %>%
dplyr::select(hexid4k, STUSPS) %>%
dplyr::mutate(length_line = st_length(.),
length_line = ifelse(is.na(length_line), 0, length_line))
sub_grids <- sub_grids %>%
sf::st_join(., single_lines_hexid, join = st_intersects) %>%
dplyr::mutate(hexid4k = hexid4k.x) %>%
dplyr::group_by(hexid4k) %>%
dplyr::summarize(length_line = sum(length_line)) %>%
dplyr::mutate(pixel_area = as.numeric(st_area(geom)),
density = length_line/pixel_area) %>%
dplyr::select(hexid4k, length_line, density, pixel_area)
return(sub_grids)
}
Prep the input data:
usa_shp <- load_data(url = "https://www2.census.gov/geo/tiger/GENZ2016/shp/cb_2016_us_state_20m.zip",
dir = 'data',
layer = "cb_2016_us_state_20m",
outname = "usa") %>%
sf::st_transform(p4string_ea) %>%
dplyr::filter(!STUSPS %in% c("HI", "AK", "PR"))
usa_shp$STUSPS <- droplevels(usa_shp$STUSPS)
hex_points <- spsample(as(usa_shp, 'Spatial'), type = "hexagonal", cellsize = 4000)
hex_grid <- HexPoints2SpatialPolygons(hex_points, dx = 4000)
hexnet_4k <- st_as_sf(hex_grid) %>%
mutate(hexid4k = row_number()) %>%
st_intersection(., st_union(usa_shp)) %>%
st_join(., usa_shp, join = st_intersects) %>%
dplyr::select(hexid4k, STUSPS)
transmission_lines_hex <- load_data( url = "https://hifld-dhs-gii.opendata.arcgis.com/datasets/75af06441c994aaf8e36208b7cd44014_0.zip",
dir = 'data',
layer = 'Electric_Power_Transmission_Lines',
outname = 'tl')%>%
dplyr::select(LINEARID, STUSPS) %>%
st_join(., hexnet_4k, join = st_intersects) %>%
mutate(STUSPS = STUSPS.x) %>%
dplyr::select(LINEARID, hexid4k, STUSPS)
The resulting parallel process is as follows:
hexnet_list <- hexnet_4k %>%
split(., .$STUSPS)
sfInit(parallel = TRUE, cpus = num_cores)
sfExport('transmission_lines_hex')
sfSource('src/functions/helper_functions.R')
transmission_lines_density <- lapply(hexnet_list,
function (input_list) {
require(tidyverse)
require(magrittr)
require(lubridate)
require(lubridate)
require(sf)
sub_grid <- dplyr:::bind_cols(input_list)
unique_ids <- unique(sub_grid$hexid4k)
state_name <- unique(sub_grid$STUSPS)[1]
print(paste0('Working on ', state_name))
got_density <- lapply(unique_ids,
FUN = get_density,
grids = sub_grid,
lines = transmission_lines_hex)
print(paste0('Finishing ', state_name))
return(got_density)
}
)
sfStop()
I hope some of this may be useful to you and, as always, suggestions on optimization would be welcomed.