Merge branch 'development' into 'main'

Package: camalienr

Title: Functions Used in the CamAlien Biodiversa+ Project

Version: 0.4.0

Title: Functions Used in the Plant Module of the Biodiversa+ Pilot on Invasive Alien Species

Version: 0.4.2

Authors@R: 

    person("Lars", "Dalby", , "lars.dalby@ecos.au.dk", role = c("aut", "cre"),

           comment = c(ORCID = "0000-0002-7270-6999"))

Description: What the package does (one paragraph).

Description: Tools used in the work with the vehicle mounted CamAlien system for monitoring plants. The package provides functions to interact with the CamAlien database.  

License: MIT + file LICENSE

Encoding: UTF-8

Roxygen: list(markdown = TRUE)

# camalienr 0.4.2

* Update the `ias` dataset with names from [GBIF](http://gbif.org)

# camalienr 0.4.1

* Update desc.

# camalienr 0.4.0

* Version bump after publication on r-universe.dev.

#'

#' Each partner has their own list of invasive alien species

#' which they targeted during the field campaign. The same species

#' can be on the list of multiple partners.

#' can be on the list of multiple partners. Target species can be

#' an entire genus. The scientific and the canonical name are from

#' a lookup on [GBIF](http://gbif.org).

#'

#' @format Data.frame with gbifid and name

#' \describe{

#'   \item{partner}{chr, The partner name}

#'   \item{canonical_name}{chr, The canonical name from GBIF with the modification that for

#' genera we add .sp}

#'   \item{scientificname}{chr, The scientific taxon name}

#'   \item{gbifid}{int, The gbifid used by Plantnet and in the camalien database}

#'   \item{pnid}{int, The ID used by Plantnet (hence pnid) and in the camalien database}

#'   \item{scientificname}{chr, The scientific binomial species name}

#'   \item{taxon_name_key}{chr, The GBIF key for the taxon name}

#'   \item{taxon_rank}{chr, The taxon rank, either species or genus. Derived from GBIF rankMarker}

#' }

"ias"

library(dplyr, warn.conflicts = FALSE)

library(camalienr)

library(googledrive)

library(rgbif)

library(purrr)

tmp <- tempfile()

drive_get("Updated list of species") |>

  drive_download(path = tmp)

readxl::read_xlsx(fs::path(glue::glue("{tmp}.xlsx")),

                  col_names = c("partner_acronym", "type", "scientificname", "gbifid", "comments"),

                  skip = 1) |>

readxl::read_xlsx(

  fs::path(glue::glue("{tmp}.xlsx")),

  col_names = c(

    "partner_acronym",

    "type",

    "scientificname",

    "gbifid",

    "comments"

  ),

  skip = 1

) |>

  filter(type == "Plant") |>

  select(-any_of(c("type", "comments"))) |>

  select(-any_of(c("type", "comments", "scientificname"))) |>

  mutate(gbifid = as.integer(gbifid)) -> ias_sp

# Get the accepted name from GBIF ----------------------------------------

map_dfr(unique(ias_sp$gbifid), function(id) {

  res <- name_usage(id, data = "name")$data

  if (!is.null(res)) {

    tibble(

      gbifid = id,

      taxon_name_key = res$key,

      scientificname = res$scientificName,

      canonical_name = res$canonicalName,

      rankMarker = res$rankMarker

    )

  } else {

    tibble(

      gbifid = id,

      taxon_name_key = NA,

      scientificname = NA,

      canonical_name = NA,

      rankMarker = NA

    )

  }

}) |>

  dplyr::mutate(

    taxonomic_rank = if_else(rankMarker == "gen.", "genus", "species"),

    canonical_name = if_else(

      rankMarker == "gen.",

      glue::glue("{canonical_name} sp."),

      canonical_name

    ),

    .keep = "unused"

  ) |>

  left_join(x = ias_sp, y = _, by = "gbifid") -> ias_sp

inner_join(partners, ias_sp, by = "partner_acronym") |>

  select(partner, scientificname, gbifid) -> ias

  select(

    partner,

    canonical_name,

    scientificname,

    gbifid,

    taxon_name_key,

    taxonomic_rank

  ) |>

  mutate(canonical_name = as.character(canonical_name)) -> ias

ids <- ias$gbifid

  filter(gbifid %in% ids) |>

  collect() |>

  right_join(ias, by = "gbifid", relationship = "many-to-many") |>

  select(partner, scientificname, gbifid, pnid) |>

  select(

    partner,

    canonical_name,

    scientificname,

    gbifid,

    pnid,

    taxon_name_key,

    taxonomic_rank

  ) |>

  arrange(partner, scientificname) |>

  # We need a hack to avoid saving as int64 (will gives issue when loading later)

  mutate(across(where(is.integer), as.double)) |>