improve data cleaning code for BirdLife data (PR #59)

# aoh 0.0.2.14 - Update `create_spp_info_data()` to make data cleaning functionality more robust for the BirdLife species' range dataset. - Update built-in helper script for processing area of habitat data to include (i) mammal species with terrestrial and freshwater distributions and (ii) mammal species with terrestrial and marine distributions (see `inst/scripts/aoh-data.R`) - New built-in helper script to download all species identifiers from the IUCN Red List (see `inst/scripts/iucn-species-list.R`)
prioritizr · Aug 20, 2024 · 5910162 · 5910162
1 parent f1b6970
commit 5910162
Show file tree

Hide file tree

Showing 285 changed files with 25,165 additions and 5,637 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -51,6 +51,7 @@ frc-data-birds-part-5.Rout
 frc-data-birds-part-6.Rout
 frc-data-mammals.Rout
 frc-data-reptiles.Rout
+iucn-species-list.csv
 ^aoh.R$
 ^customization.R$
 codecov.yml
diff --git a/.github/workflows/documentation.yaml b/.github/workflows/documentation.yaml
@@ -93,6 +93,9 @@ jobs:
         run: |
           result <- urlchecker::url_check()
           result <- result[!startsWith(result$URL, "https://doi.org/"), , drop = FALSE]
+          result <- result[!startsWith(result$URL, "https://land.copernicus.eu"), , drop = FALSE]
+          result <- result[!startsWith(result$URL, "https://www.iucnredlist.org"), , drop = FALSE]
+          result <- result[!startsWith(result$URL, "https://lpdaac.usgs.gov"), , drop = FALSE]
           if (nrow(result) > 0) {
             print(result)
             stop("Invalid URLs detected")

diff --git a/.gitignore b/.gitignore
@@ -50,6 +50,7 @@ frc-data-birds-part-5.Rout
 frc-data-birds-part-6.Rout
 frc-data-mammals.Rout
 frc-data-reptiles.Rout
+iucn-species-list.csv
 
 # system files
 .directory

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: aoh
 Type: Package
-Version: 0.0.2.13
+Version: 0.0.2.14
 Title: Create Area of Habitat Data
 Description: Create Area of Habitat data to characterize species distributions.
     Data are produced following procedures outlined by Brooks et al. (2019)
@@ -73,7 +73,7 @@ SystemRequirements: GDAL (>= 3.0.2) (optional), PROJ (>= 7.2.0) (optional)
 URL: https://prioritizr.github.io/aoh/, https://github.com/prioritizr/aoh
 BugReports: https://github.com/prioritizr/aoh/issues
 VignetteBuilder: knitr
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Collate:
     'internal.R'
     'calc_spp_frc_data.R'

diff --git a/Makefile b/Makefile
@@ -38,7 +38,9 @@ prep_lumbierres_habitat_data: inst/scripts/lumbierres-habitat-data.R
 	R CMD BATCH --no-restore --no-save inst/scripts/lumbierres-habitat-data.R
 
 # process aoh data
-aoh_global_data: aoh_amphibians aoh_mammals aoh_reptiles aoh_birds
+aoh_global_data: aoh_amphibians aoh_mammals aoh_reptiles aoh_birds aoh_mammals
+
+aoh_mammals: aoh_mammals_land aoh_mammals_land_freshwater aoh_mammals_land_marine
 
 aoh_amphibians:
 	R CMD BATCH --no-restore --no-save '--args amphibians' inst/scripts/aoh-data.R aoh-data-amphibians.Rout
@@ -51,8 +53,14 @@ aoh_birds:
 	R CMD BATCH --no-restore --no-save '--args birds-part-5' inst/scripts/aoh-data.R aoh-data-birds-part-5.Rout
 	R CMD BATCH --no-restore --no-save '--args birds-part-6' inst/scripts/aoh-data.R aoh-data-birds-part-6.Rout
 
-aoh_mammals:
-	R CMD BATCH --no-restore --no-save '--args mammals' inst/scripts/aoh-data.R aoh-data-mammals.Rout
+aoh_mammals_land:
+	R CMD BATCH --no-restore --no-save '--args mammals-land' inst/scripts/aoh-data.R aoh-data-mammals-land.Rout
+
+aoh_mammals_land_freshwater:
+	R CMD BATCH --no-restore --no-save '--args mammals-land-freshwater' inst/scripts/aoh-data.R aoh-data-mammals-land-freshwater.Rout
+
+aoh_mammals_land_marine:
+	R CMD BATCH --no-restore --no-save '--args mammals-land-marine' inst/scripts/aoh-data.R aoh-data-mammals-land-marine.Rout
 
 aoh_reptiles:
 	R CMD BATCH --no-restore --no-save '--args reptiles' inst/scripts/aoh-data.R aoh-data-reptiles.Rout
@@ -132,4 +140,4 @@ purl_vigns:
 	R --slave -e "lapply(dir('vignettes', '^.*\\\\.Rmd$$'), function(x) knitr::purl(file.path('vignettes', x), gsub('.Rmd', '.R', x, fixed = TRUE)))"
 	rm -f Rplots.pdf
 
-.PHONY: initc vigns clean data docs readme site test check checkwb build  purl_vigns install man spellcheck examples prep_habitat_data prep_elevation_data aoh_reptiles aoh_mammals aoh_birds aoh_amphibians aoh_global_data frc_reptiles frc_mammals frc_birds frc_amphibians frc_global_data
+.PHONY: initc vigns clean data docs readme site test check checkwb build  purl_vigns install man spellcheck examples prep_habitat_data prep_elevation_data aoh_reptiles aoh_mammals aoh_mammals_land aoh_mammals_land_freshwater aoh_mammals_land_marine aoh_birds aoh_amphibians aoh_global_data frc_reptiles frc_mammals frc_birds frc_amphibians frc_global_data
diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,14 @@
+# aoh 0.0.2.14
+
+- Update `create_spp_info_data()` to make data cleaning functionality more
+  robust for the BirdLife species' range dataset.
+- Update built-in helper script for processing area of habitat data to
+  include (i) mammal species with terrestrial and freshwater distributions and
+  (ii)  mammal species with terrestrial and marine distributions
+  (see `inst/scripts/aoh-data.R`)
+- New built-in helper script to download all species identifiers from the
+  IUCN Red List (see `inst/scripts/iucn-species-list.R`)
+
 # aoh 0.0.2.13
 
 - Update `read_spp_range_data()` and `create_spp_info_data()` to fix

diff --git a/R/clean_spp_range_data.R b/R/clean_spp_range_data.R
@@ -402,28 +402,38 @@ clean_spp_range_data <- function(x,
   # step 6: convert MULTISURFACE to MULTIPOLYGON
   x <- sf::st_set_precision(x, geometry_precision)
   idx <- which(vapply(sf::st_geometry(x), inherits, logical(1), "MULTISURFACE"))
-  if (length(idx) > 0) { # nocov start
+  # nocov start
+  if (length(idx) > 0) {
     g <- sf::st_geometry(x)
-    g2 <- lapply(g[idx], sf::st_cast, "MULTIPOLYGON")
+    g2 <- g[idx]
+    g2 <- lapply(g2, sf::st_cast, "MULTIPOLYGON")
     g2 <- lapply(g2, sf::st_buffer, 0)
     g2 <- lapply(g2, sf::st_make_valid)
     for (i in seq_along(idx)) {
       g[[idx[[i]]]] <- g2[[i]]
     }
     x <- sf::st_set_geometry(x, g)
     rm(g, g2)
-  } # nocov end
+  }
+  # nocov end
+
+  # force construction of object, this seems to be needed for some reason
+  # that I do not understand, otherwise st_collection_extract() throws
+  # an error
+  x <- x[seq_len(nrow(x)), , drop = FALSE]
   x <- suppressWarnings(sf::st_collection_extract(x, "POLYGON"))
-  invisible(gc())
 
   # step 7: fix any potential geometry issues
   x <- st_repair_geometry(x, geometry_precision)
   invisible(gc())
 
   # step 8: wrap geometries to dateline
   x <- sf::st_set_precision(x, geometry_precision)
-  x <- suppressWarnings(sf::st_wrap_dateline(x,
-    options = c("WRAPDATELINE=YES", "DATELINEOFFSET=180"))
+  x <- suppressWarnings(
+    sf::st_wrap_dateline(
+      x,
+      options = c("WRAPDATELINE=YES", "DATELINEOFFSET=180")
+    )
   )
   invisible(gc())
 

diff --git a/R/st_repair_geometry.R b/R/st_repair_geometry.R
@@ -153,7 +153,7 @@ st_repair_geometry <- function(x, geometry_precision = 1e5) {
       requireNamespace("prepr", quietly = TRUE),
       msg = paste(
         "the \"prepr\" package needs to be installed, use: \n",
-        "remotes::install_github(\"dickoa/prepr\")"
+        "remotes::install_github(\"prioritizr/prepr\")"
       )
     )
     ### find geometries to repair

diff --git a/README.Rmd b/README.Rmd
@@ -26,7 +26,14 @@ knitr::opts_chunk$set(
 [![Coverage Status](https://img.shields.io/codecov/c/github/prioritizr/aoh?label=Coverage)](https://app.codecov.io/gh/prioritizr/aoh/branch/master)
 
 ```{r, include = FALSE}
+# load developmental version of package
 devtools::load_all()
+
+# check if being prepared for website
+## see https://github.com/r-lib/pkgdown/blob/main/R/pkgdown.R
+in_pkgdown <- function() {
+  identical(Sys.getenv("IN_PKGDOWN"), "true")
+}
 ```
 
 ### Overview
@@ -180,7 +187,7 @@ print(spp_aoh_rasters)
 
 Finally, let's create some maps to compare the range data with the Area of habitat data.
 
-```{r "map", message = FALSE, warning = FALSE, results = "hide", dpi = 200, fig.width = 5.5, fig.height = 4, out.width = ifelse(isTRUE(knitr::is_html_output(excludes = c("markdown"))), "60%", "90%")}
+```{r "map", message = FALSE, warning = FALSE, results = "hide", dpi = 200, fig.width = 5.5, fig.height = 4, out.width = ifelse(isTRUE(in_pkgdown()), "60%", "90%")}
 # create maps
 ## N.B. you might need to install the ggmap package
 map <-

diff --git a/README.md b/README.md
@@ -354,7 +354,7 @@ map <-
 print(map)
 ```
 
-<img src="man/figures/README-map-1.png" width="60%" style="display: block; margin: auto;" />
+<img src="man/figures/README-map-1.png" width="90%" style="display: block; margin: auto;" />
 
 ### Citation
 
@@ -366,7 +366,7 @@ produce Area of Habitat data.
     relevant data using:
 
       Hanson JO (2024) aoh: Create Area of Habitat Data. R package version
-      0.0.2.12. Available at https://github.com/prioritizr/aoh.
+      0.0.2.14. Available at https://github.com/prioritizr/aoh.
 
       IUCN [insert year] IUCN Red List of Threatened Species. Version
       [insert version]. Available at www.iucnredlist.org.

diff --git a/_pkgdown.yml b/_pkgdown.yml
@@ -1,8 +1,11 @@
+url: https://prioritizr.github.io/aoh
+
 authors:
   Jeffrey O Hanson:
     href: http://jeffrey-hanson.com
 
 template:
+  bootstrap: 5
   params:
     bootswatch: flatly
 

diff --git a/docs/404.html b/docs/404.html