Merge pull request #92 from b-cubed-eu/simple-mapping

Simple mapping

.zenodo.json

@@ -1,6 +1,6 @@
 {
   "title": "gcube: Simulating Biodiversity Data Cubes",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "license": "MIT",
   "upload_type": "software",
   "description": "<p>Simulation framework for biodiversity data cubes.<\/p>",

CITATION.cff

@@ -25,4 +25,4 @@ abstract: "Simulation framework for biodiversity data cubes."
 identifiers:
 - type: url
   value: https://b-cubed-eu.github.io/gcube/
-version: 0.2.0
+version: 0.3.0

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: gcube
 Title: Simulating Biodiversity Data Cubes
-Version: 0.2.0
+Version: 0.3.0
 Authors@R: c(
     person("Ward", "Langeraert", , "ward.langeraert@inbo.be", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0002-5900-8109", affiliation = "Research Institute for Nature and Forest (INBO)")),

NEWS.md

@@ -1,3 +1,8 @@
+# gcube 0.3.0
+
+*	`generate_taxonomy()` also creates species key.
+*	Fix bug for mapping simulate occurrences without specified temporal function.
+
 # gcube 0.2.0
 
 *	Improve function checks with `stopifnot()` and the [assertthat](https://CRAN.R-project.org/package=assertthat) package.

R/generate_taxonomy.R

@@ -96,9 +96,13 @@ generate_taxonomy <- function(
 
     # Generate species names
     species_df$species <- paste0("species", seq_len(num_species))
+
+    # Generate species keys
+    species_df$species_key <- seq_len(num_species)
   } else {
     # Generate species names
-    species_df <- data.frame(species = paste0("species", seq_len(num_species)))
+    species_df <- data.frame(species = paste0("species", seq_len(num_species)),
+                             species_key = seq_len(num_species))
   }
 
   # Check if number of species is smaller than number of genera is smaller than
@@ -170,8 +174,8 @@ generate_taxonomy <- function(
     dplyr::left_join(orders_to_classes, by = "order") %>%
     dplyr::left_join(classes_to_phyla, by = "class") %>%
     dplyr::left_join(phyla_to_kingdoms, by = "phylum") %>%
-    dplyr::select("species", "genus", "family", "order", "class", "phylum",
-                  "kingdom", everything())
+    dplyr::select("species", "species_key", "genus", "family", "order", "class",
+                  "phylum", "kingdom", everything())
 
   return(taxonomy)
 }

R/utils.R

@@ -22,7 +22,8 @@ get_function_arguments <- function(f, df) {
   f_args <- f_args_raw[f_args_raw != "..."]
 
   # Also get argument names of temporal_function if necessary
-  if (identical(f, simulate_occurrences)) {
+  if (identical(f, simulate_occurrences) &&
+      "temporal_function" %in% colnames(df)) {
     temp_f_args <- sapply(df$temporal_function, function(f) {
       if (is.function(f)) methods::formalArgs(f)
     })

codemeta.json

@@ -8,7 +8,7 @@
   "codeRepository": "https://github.com/b-cubed-eu/gcube",
   "issueTracker": "https://github.com/b-cubed-eu/gcube/issues",
   "license": "https://spdx.org/licenses/MIT",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "programmingLanguage": {
     "@type": "ComputerLanguage",
     "name": "R",
@@ -346,7 +346,7 @@
     },
     "SystemRequirements": null
   },
-  "fileSize": "524.384KB",
+  "fileSize": "549.025KB",
   "citation": [
     {
       "@type": "SoftwareSourceCode",
@@ -358,7 +358,7 @@
           "familyName": "Langeraert"
         }
       },
-      "name": "gcube: Simulating Biodiversity Data Cubes. Version 0.2.0",
+      "name": "gcube: Simulating Biodiversity Data Cubes. Version 0.3.0",
       "url": "https://b-cubed-eu.github.io/gcube/"
     }
   ],

inst/CITATION

@@ -2,12 +2,12 @@ citHeader("To cite `gcube` in publications please use:")
 # begin checklist entry
 bibentry(
   bibtype = "Manual",
-  title = "gcube: Simulating Biodiversity Data Cubes. Version 0.2.0",
+  title = "gcube: Simulating Biodiversity Data Cubes. Version 0.3.0",
   author = c( author = c(person(given = "Ward", family = "Langeraert"))),
   year = 2024,
   url = "https://b-cubed-eu.github.io/gcube/",
   abstract = "Simulation framework for biodiversity data cubes.",
-  textVersion = "Langeraert, Ward (2024) gcube: Simulating Biodiversity Data Cubes. Version 0.2.0. https://b-cubed-eu.github.io/gcube/",
+  textVersion = "Langeraert, Ward (2024) gcube: Simulating Biodiversity Data Cubes. Version 0.3.0. https://b-cubed-eu.github.io/gcube/",
   keywords = "simulation; data cubes; B-Cubed; biodiversity; Monte-Carlo",
 )
 # end checklist entry

tests/testthat/test-generate_taxonomy.R

@@ -1,7 +1,7 @@
 ## Prepare example data
 n_spec <- 5
-colnames_tax <- c("species", "genus", "family", "order", "class", "phylum",
-                  "kingdom")
+colnames_tax <- c("species", "species_key", "genus", "family", "order", "class",
+                  "phylum", "kingdom")
 
 # Example dataframe
 existing_df <- data.frame(
@@ -11,7 +11,6 @@ existing_df <- data.frame(
 
 
 ## Unit tests
-
 test_that("generate_taxonomy function works correctly", {
   # Is the output format correct?
   # Testing with default values

tests/testthat/test-map_grid_designation.R

@@ -4,7 +4,7 @@ plgn <- st_polygon(list(cbind(c(5, 10, 8, 2, 3, 5), c(2, 1, 7, 9, 5, 2))))
 
 # Create grid
 cube_grid <- st_make_grid(
-    st_buffer(plgn, 25),
+    st_buffer(plgn, 50),
     n = c(20, 20),
     square = TRUE) %>%
   st_sf()
@@ -106,6 +106,29 @@ test_that("map_grid_designation works with simple column names", {
   expect_equal(occ_cube_unnested_test, occ_cube_unnested)
 })
 
+test_that("map_grid_designation works with pipes", {
+  occ_cube_piped <- tibble(
+      species = c("species1", "species2", "species3"),
+      plgn = rep(list(plgn), 3),
+      grid = rep(list(cube_grid), 3),
+      seed = 123
+    ) %>%
+    map_simulate_occurrences() %>%
+    map_sample_observations() %>%
+    map_filter_observations() %>%
+    map_add_coordinate_uncertainty() %>%
+    map_grid_designation(nested = FALSE)
+
+  # Is the occurrence_cube_df column removed?
+  expect_false("occurrence_cube_df" %in% colnames(occ_cube_piped))
+  # Do we have the expected columns?
+  expect_equal(
+    sort(colnames(occ_cube_piped)),
+    sort(c("species", "plgn", "grid", "seed", "occurrences",
+           "observations_total", "observations", "time_point", "id", "n",
+           "min_coord_uncertainty", "geometry")))
+})
+
 test_that("map_grid_designation works with arg_list for renaming columns", {
   # Test with arg_list
   occ_cube_nested <- map_grid_designation(df = obs_uncertainty2,

tests/testthat/test-map_simulate_occurrences.R

@@ -4,6 +4,11 @@ plgn <- st_polygon(list(cbind(c(5, 10, 8, 2, 3, 5), c(2, 1, 7, 9, 5, 2))))
 
 # Specify dataframe for 3 species with custom function arguments
 # Dataframe with column names equal to arguments
+species_dataset_df <- tibble(
+  plgn = rep(list(plgn), 3),
+  n_time_points = rep(6, 3),
+  seed = 123)
+
 species_dataset_df1 <- tibble(
   taxonID = c("species1", "species2", "species3"),
   plgn = rep(list(plgn), 3),
@@ -21,6 +26,19 @@ species_dataset_df2 <- species_dataset_df1 %>%
 
 
 ## Unit tests
+test_that("map_simulate_occurrences works with simple column names", {
+  result <- map_simulate_occurrences(df = species_dataset_df)
+
+  # Are previous column names retained and one extra column name created?
+  expect_true("occurrences" %in% colnames(result))
+  expect_equal(sort(c(colnames(species_dataset_df), "occurrences")),
+               sort(colnames(result)))
+  # Is the new column a list-column?
+  expect_true(inherits(result$occurrences, "list"))
+  # Is the output of the function an sf object for each species (each row)?
+  expect_true(all(sapply(result$occurrences, inherits, "sf")))
+})
+
 
 test_that("map_simulate_occurrences works with simple column names", {
   # Test with nested is TRUE