Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Updated path to new NHD S3 bucket #9

Merged
merged 4 commits into from
Dec 12, 2022
Merged

Updated path to new NHD S3 bucket #9

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1c0508b
updated paths
SimonTopp Dec 9, 2022
988f7cb
lowercase columns
SimonTopp Dec 12, 2022
7cf94b1
removed GET
SimonTopp Dec 12, 2022
8db391d
Original drive cache
SimonTopp Dec 12, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 11 additions & 7 deletions 1_crosswalk_fetch/src/fetch_nhdhr.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@


create_nhd_HR_download_plan <- function(states, min_size, d_tolerance, remove_IDs = NULL, keep_IDs = NULL){
base_url <- 'ftp://rockyftp.cr.usgs.gov/vdelivery/Datasets/Staged/Hydrography/NHD/State/HighResolution/GDB/NHD_H_%s_State_GDB.zip'
base_url <- 'https://prd-tnm.s3.amazonaws.com/StagedProducts/Hydrography/NHD/State/GDB/NHD_H_%s_State_GDB.zip'

fetch_as_sf_step <- create_task_step(
step_name = 'fetch_NHD_as_sf',
Expand Down Expand Up @@ -41,15 +41,19 @@ fetch_NHD_as_sf <- function(url,min_size, d_tol){
unlink(unzip_dir, recursive = TRUE)
unlink(dl_dest)
})


if(getOption('timeout') < 120){
options(timeout = 120)
}
download.file(url, destfile = dl_dest, quiet = TRUE, method='curl')
unzip(dl_dest, exdir = unzip_dir)

sf::read_sf(file.path(unzip_dir,paste0(tools::file_path_sans_ext(basename(url)), '.gdb')), layer = 'NHDWaterbody') %>%
filter(FType %in% c(390, 436, 361)) %>% #select only lakes/ponds/reservoirs. This drops things like swamp/marsh
mutate(area_m2 = AreaSqKm * 1000000) %>%
filter(ftype %in% c(390, 436, 361)) %>% #select only lakes/ponds/reservoirs. This drops things like swamp/marsh
mutate(area_m2 = areasqkm * 1000000) %>%
filter(area_m2 > min_size) %>%
mutate(site_id = paste0('nhdhr_', Permanent_Identifier)) %>% dplyr::select(site_id, GNIS_Name, Elevation, FType, FCode) %>% #geometry selected automatically
mutate(site_id = paste0('nhdhr_', permanent_identifier)) %>%
dplyr::select(site_id, gnis_name, elevation, ftype, fcode) %>% #geometry selected automatically
# bad Idaho site!
filter(site_id != 'nhdhr_{5BEDE13F-C94B-4501-B979-E00C29EA374B}') %>%
sf::st_transform(crs = 4326) %>%
Expand All @@ -64,7 +68,7 @@ GNIS_Name_xwalk <- function(ind_file, ...){

sf_lakes <- rbind(...)
deduped_sf_lakes <- st_drop_geometry(sf_lakes[!duplicated(sf_lakes$site_id), ]) %>%
dplyr::select(site_id, GNIS_Name)
dplyr::select(site_id, gnis_name)

saveRDS(deduped_sf_lakes, data_file)
gd_put(ind_file, data_file)
Expand All @@ -75,7 +79,7 @@ combine_nhd_sfs <- function(ind_file, ...){

sf_lakes <- rbind(...)
deduped_sf_lakes <- sf_lakes[!duplicated(sf_lakes$site_id), ] %>%
dplyr::select(site_id, Elevation, FType, FCode)
dplyr::select(site_id, elevation, ftype, fcode)

saveRDS(deduped_sf_lakes, data_file)
gd_put(ind_file, data_file)
Expand Down