Upgrades to austraits for v.5.0.0

.github/workflows/R-CMD-check.yml

@@ -5,10 +5,10 @@ on:
     branches:
       - master
       - develop
-      - upgrade
   pull_request:
     branches:
       - master
+      - develop
 
 name: R-CMD-check
 

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: austraits
 Title: Helpful functions to access, summarise and wrangle austraits data
-Version: 2.1.2
+Version: 2.2.2
 Authors@R:
     c(person(given = "Daniel",
              family = "Falster",
@@ -22,7 +22,7 @@ Encoding: UTF-8
 Language: en
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.1
+RoxygenNote: 7.2.3
 Depends: 
     R (>= 4.0.0),
     RefManageR
@@ -39,20 +39,20 @@ Imports:
     utils,
     magrittr,
     janitor,
-    lifecycle
-Suggests: 
+    lifecycle,
     ggplot2,
-    knitr,
-    rmarkdown,
-    testthat (>= 3.0.0),
-    markdown,
-    ggpointdensity, 
-    ggbeeswarm,
+    ggpointdensity,
+    ggbeeswarm (>= 0.7.1),
     gridExtra,
     scales,
     forcats,
     viridis,
-    kableExtra
+    lubridate
+Suggests: 
+    knitr,
+    rmarkdown,
+    testthat (>= 3.0.0),
+    markdown
 VignetteBuilder: knitr
 Config/testthat/edition: 3
 URL: https://traitecoevo.github.io/austraits/

NAMESPACE

@@ -15,12 +15,8 @@ export(join_locations)
 export(join_methods)
 export(join_sites)
 export(join_taxonomy)
-export(list1_to_df)
 export(load_austraits)
 export(lookup_trait)
-export(my_kable_styling_html)
-export(my_kable_styling_markdown)
-export(my_kable_styling_pdf)
 export(plot_locations)
 export(plot_site_locations)
 export(plot_trait_distribution_beeswarm)
@@ -34,6 +30,7 @@ importFrom(dplyr,arrange)
 importFrom(dplyr,filter)
 importFrom(dplyr,group_by)
 importFrom(dplyr,select)
+importFrom(dplyr,summarise)
 importFrom(lifecycle,deprecated)
 importFrom(magrittr,"%>%")
 importFrom(stats,family)

NEWS.md

@@ -1,6 +1,5 @@
-# austraits 2.1.2
--   Minor bug fix in `as_wide_table`
--   Minor bug fix in `join_contexts`
--   Removed pkgdown docs/
-
-
+# austraits 2.2.2
+- Upgrades to `as_wide_table`, `join_`, `trait_pivot_` to work with multiple versions of AusTraits
+- Minor fixes across all function so `tidyselect` is happy
+- Minor changes to documentation 
+- Minor fixes to `load_austraits` and `get_versions` due to Zenodo changes

R/as_wide_table.R

@@ -19,20 +19,21 @@
   version <- what_version(austraits)
 
   switch (version,
-          'new' = as_wide_table2(austraits),
-          'old' = as_wide_table1(austraits),
-  )
+          "5-series" = as_wide_table3(austraits),
+          "4-series" = as_wide_table2(austraits),
+          "3-series-earlier" = as_wide_table1(austraits)
+          )
 }
 
-#' Turning entire AusTraits object into wide table >3.0.2
+#' Turning entire AusTraits object into wide table v5
 #' @noRd
 #' @keywords internal
-as_wide_table2 <- function(austraits){
+as_wide_table3 <- function(austraits){
 
   # Function to collapse columns in locations and contexts into single column
-  process_table2 <- function(data) {
+  process_table3 <- function(data) {
     data %>% 
-      tidyr::pivot_wider(names_from = property, values_from = value) %>% 
+      tidyr::pivot_wider(names_from = "property", values_from = "value") %>% 
       tidyr::nest(data=-dplyr::any_of(c("dataset_id", "location_id", "latitude (deg)", "longitude (deg)"))) %>%
       dplyr::mutate(location = purrr::map_chr(data, collapse_cols)) %>%
       dplyr::select(-data) 
@@ -48,61 +49,139 @@
   # Getting rid of the columns that will soon be deleted in the next austraits release and renaming the description column
   austraits$methods <- 
     austraits$methods %>% 
-    dplyr::rename(c("dataset_description" = "description"))  %>% 
+    dplyr::rename(dataset_description = "description")  %>% 
     dplyr::distinct()
 
   # collapse into one column
   austraits$locations <- 
     austraits$locations %>% 
     dplyr::filter(value!="unknown") %>% 
-    dplyr::rename(c("property" = "location_property")) %>%
+    dplyr::rename("property" = "location_property") %>%
     split(., .$dataset_id) %>%
-    purrr::map_dfr(process_table2)
+    purrr::map_dfr(process_table3)
 
-  # rename taxonomic_reference field to reflect the APC/APNI name matching process better
+  # rename taxonomic_dataset field to reflect the APC/APNI name matching process better
   austraits$taxa <- 
     austraits$taxa %>% 
-    dplyr::rename(c("taxonNameValidation" = "taxonomic_reference")) %>% 
+    # dplyr::rename("taxonNameValidation" = "taxonomic_dataset") %>% 
     dplyr::distinct()
 
   austraits_wide <- 
     austraits$traits %>% 
     dplyr::left_join(by=c("dataset_id", "location_id"), austraits$locations) %>%
-    dplyr::left_join(by=c("dataset_id", "trait_name"), austraits$methods) %>%
+    dplyr::left_join(by=c("dataset_id", "method_id", "trait_name"), austraits$methods) %>%
     dplyr::left_join(by=c("taxon_name"), austraits$taxa)
 
     # reorder the names to be more intuitive
     austraits_wide %>% dplyr::select(
 
     # The most useful (if you are filtering for just one taxon_name)
-      dataset_id, observation_id, trait_name, taxon_name, value, unit, 
-      entity_type, population_id, individual_id,
-      value_type, basis_of_value, 
-      replicates, 
+      "dataset_id", "observation_id", "trait_name", "taxon_name", "value", "unit", 
+      "entity_type", "population_id", "individual_id",
+      "value_type", "basis_of_value", 
+      "replicates", 
     # tissue, trait_category,  # Add after new zenodo release
 
     # More stuff you can filter on
-    collection_date, basis_of_record, life_stage, sampling_strategy, 
-    treatment_id, temporal_id, 
+    "collection_date", "basis_of_record", "life_stage", "sampling_strategy", 
+    "treatment_context_id", "temporal_context_id", 
 
     #stuff relating to locations
-    `latitude (deg)`, `longitude (deg)`, location, plot_id,
+    "latitude (deg)", "longitude (deg)", "location", "plot_context_id",
 
     #stuff relating to contexts and methods
-    context, methods, method_id, original_name,
+    "context", "methods", "method_id", "method_context_id", "original_name",
 
     #the citations
-    dataset_description, source_primary_citation, source_secondary_citation,
+    "dataset_description", "source_primary_citation", "source_secondary_citation",
 
     #the taxa details
-    taxonomic_status, taxon_distribution, 
-    taxon_rank, genus, family, #accepted_name_usage_id, 
-    scientific_name_authorship
+    "taxonomic_status", "taxon_distribution", 
+    "taxon_rank", "genus", "family"
     )
 
   austraits_wide
 }
 
+#' Turning entire AusTraits object into wide table v4
+#' @noRd
+#' @keywords internal
+as_wide_table2 <- function(austraits){
+
+  # Function to collapse columns in locations and contexts into single column
+  process_table2 <- function(data) {
+    data %>% 
+      tidyr::pivot_wider(names_from = "property", values_from = "value") %>% 
+      tidyr::nest(data=-dplyr::any_of(c("dataset_id", "location_id", "latitude (deg)", "longitude (deg)"))) %>%
+      dplyr::mutate(location = purrr::map_chr(data, collapse_cols)) %>%
+      dplyr::select(-data) 
+  }
+
+  ################################################################################
+  # Define and adapt each table in the list of austraits to prepare for the wide table format 
+
+  # The contexts table needs the contexts collapsed to one context name per site
+  austraits %>% 
+    join_contexts(collapse_context = TRUE) -> austraits
+
+  # Getting rid of the columns that will soon be deleted in the next austraits release and renaming the description column
+  austraits$methods <- 
+    austraits$methods %>% 
+    dplyr::rename(dataset_description = "description")  %>% 
+    dplyr::distinct()
+
+  # collapse into one column
+  austraits$locations <- 
+    austraits$locations %>% 
+    dplyr::filter(value!="unknown") %>% 
+    dplyr::rename("property" = "location_property") %>%
+    split(., .$dataset_id) %>%
+    purrr::map_dfr(process_table2)
+
+  # rename taxonomic_dataset field to reflect the APC/APNI name matching process better
+  austraits$taxa <- 
+    austraits$taxa %>% 
+    dplyr::rename("taxonNameValidation" = "taxonomic_dataset") %>% 
+    dplyr::distinct()
+
+  austraits_wide <- 
+    austraits$traits %>% 
+    dplyr::left_join(by=c("dataset_id", "location_id"), austraits$locations) %>%
+    dplyr::left_join(by=c("dataset_id", "trait_name"), austraits$methods) %>%
+    dplyr::left_join(by=c("taxon_name"), austraits$taxa)
+
+  # reorder the names to be more intuitive
+  austraits_wide %>% dplyr::select(dplyr::any_of(
+
+    # The most useful (if you are filtering for just one taxon_name)
+    "dataset_id", "observation_id", "trait_name", "taxon_name", "value", "unit", 
+    "entity_type", "population_id", "individual_id",
+    "value_type", "basis_of_value", 
+    "replicates", 
+    # tissue, trait_category,  # Add after new zenodo release
+
+    # More stuff you can filter on
+    "collection_date", "basis_of_record", "life_stage", "sampling_strategy", 
+    "treatment_id", "temporal_id", 
+
+    #stuff relating to locations
+    "latitude (deg)", "longitude (deg)", "location", "plot_id",
+
+    #stuff relating to contexts and methods
+    "context", "methods", "method_id", "original_name",
+
+    #the citations
+    "dataset_description", "source_primary_citation", "source_secondary_citation",
+
+    #the taxa details
+    "taxonomic_status", "taxon_distribution", 
+    "taxon_rank", "genus", "family"
+
+  ))
+
+  austraits_wide
+}
+
 #' Turning entire AusTraits object into wide table <=3.0.2
 #' @noRd
 #' @keywords  internal
@@ -128,7 +207,7 @@
   process_table <- function(data) {
 
     data %>% 
-      tidyr::pivot_wider(names_from = property, values_from = value) %>% 
+      tidyr::pivot_wider(names_from = "property", values_from = "value") %>% 
       tidyr::nest(data=-dplyr::any_of(c("dataset_id", "site_name", "context_name", "latitude (deg)", "longitude (deg)"))) %>%
       dplyr::mutate(site = purrr::map_chr(data, collapse_cols)) %>%
       dplyr::select(-data) 
@@ -140,15 +219,15 @@
   # the trait table needs little prep. Rename the value columns as value
   austraits$traits <- 
     austraits$traits %>% 
-    dplyr::rename(c("trait_value" = "value")) 
+    dplyr::rename(trait_value = "value")
 
   # The contexts table needs the contexts collapsed to one context name per site
   austraits$contexts <- 
     austraits$contexts %>% 
-    dplyr::rename(c("property" = "context_property")) %>%
+    dplyr::rename(property = "context_property") %>%
     split(austraits$contexts$dataset_id) %>%
     purrr::map_dfr(process_table)  %>% 
-    dplyr::rename(c("context" = "site"))
+    dplyr::rename(context = "site")
 
   # Getting rid of the columns that will soon be deleted in the next austraits release and renaming the description column
   austraits$methods <- 
@@ -161,23 +240,23 @@
     dplyr::slice(1) %>%
     dplyr:: ungroup() %>%
     #------------
-  dplyr::select(-year_collected_start, -year_collected_end) %>% 
-    dplyr::rename(c("dataset_description" = "description"))  
+  dplyr::select(-c("year_collected_start", "year_collected_end")) %>% 
+    dplyr::rename(dataset_description = "description")  
 
   # collapse into one column
   austraits$sites <- 
     austraits$sites %>% 
     dplyr::filter(value!="unknown") %>% 
     # next line is a fix -- one dataset in 3.0.2 has value "site_name"
     dplyr::mutate(site_property = gsub("site_name", "name", site_property)) %>%
-    dplyr::rename(c("property" = "site_property")) %>%
+    dplyr::rename("property" = "site_property") %>%
     split(., .$dataset_id) %>%
     purrr::map_dfr(process_table)
 
   # rename source data field to reflect the APC/APNI name matching process better
   austraits$taxa <- 
     austraits$taxa %>% 
-    dplyr::rename(c("taxonNameValidation" = "source"))
+    dplyr::rename(taxonNameValidation = "source")
 
   austraits_wide <- 
     austraits$traits %>%
@@ -190,26 +269,26 @@
     dplyr::select(
 
       # The most useful (if you are filtering for just one taxon_name)
-      dataset_id, observation_id, trait_name, taxon_name, trait_value, unit, 
-      value_type, replicates, 
+      "dataset_id", "observation_id", "trait_name", "taxon_name", "trait_value", "unit", 
+      "value_type", "replicates", 
       # tissue, trait_category,  # Add after new zenodo release
 
       # More stuff you can filter on
-      date, collection_type, sample_age_class, sampling_strategy, 
+      "date", "collection_type", "sample_age_class", "sampling_strategy", 
 
       #stuff relating to sites
-      `latitude (deg)`, `longitude (deg)`, site_name, site,
+      "latitude (deg)", "longitude (deg)", "site_name", "site",
 
       #stuff relating to contexts and methods
-      context_name, context, methods, original_name,
+      "context_name", "context", "methods", "original_name",
 
       #the citations
-      dataset_description, source_primary_citation, source_secondary_citation,
+      "dataset_description", "source_primary_citation", "source_secondary_citation",
 
       #the taxa details
-      taxonomicStatus, taxonDistribution, 
-      taxonRank, genus, family, acceptedNameUsageID, 
-      scientificNameAuthorship, ccAttributionIRI
+      "taxonomicStatus", "taxonDistribution", 
+      "taxonRank", "genus", "family", "acceptedNameUsageID", 
+      "scientificNameAuthorship", "ccAttributionIRI"
     )
 
   austraits_wide