Type specification of fields of GBIF occurrence downloads

type_GBIF_occurrence_fields.R

library(readr)
col_types <- cols(
     acceptedNameUsage = col_character(),
     acceptedNameUsageID = col_character(),
     accessRights = col_character(),
     associatedReferences = col_character(),
     associatedSequences = col_character(),
     associatedTaxa = col_character(),
     bed = col_character(),
     behavior = col_character(),
     bibliographicCitation = col_character(),
     catalogNumber = col_character(),
     collectionID = col_character(),
     continent = col_character(),
     coordinatePrecision = col_double(),
     county = col_character(),
     created = col_date(),
     dateIdentified = col_character(),
     dataGeneralizations = col_character(),
     datasetID = col_character(),
     day = col_integer(),
     disposition = col_character(),
     dynamicProperties = col_character(),
     earliestEonOrLowestEonothem = col_character(),
     elevation = col_double(),
     elevationAccuracy = col_double(),
     endDayOfYear = col_integer(),
     establishmentMeans = col_character(),
     fieldNotes = col_character(),
     fieldNumber = col_character(),
     footprintSRS = col_character(),
     footprintSpatialFit = col_character(),
     footprintWKT = col_character(),
     georeferencedBy = col_character(),
     georeferencedDate = col_date(),
     georeferenceProtocol = col_character(),
     georeferenceRemarks = col_character(),
     georeferenceSources = col_character(),
     georeferenceVerificationStatus = col_character(),
     habitat = col_character(),
     higherClassification = col_character(),
     identificationID = col_character(),
     identificationQualifier = col_character(),
     identificationReferences = col_character(),
     identificationRemarks = col_character(),
     identificationVerificationStatus = col_character(),
     individualCount = col_integer(),
     infraspecificEpithet = col_character(),
     informationWithheld = col_character(),
     institutionID = col_character(),
     language = col_character(),
     latestEraOrHighestErathem = col_character(),
     latestPeriodOrHighestSystem = col_character(),
     lifeStage = col_character(),
     lithostratigraphicTerms = col_character(),
     locationAccordingTo = col_character(),
     locationRemarks = col_character(),
     minimumDistanceAboveSurfaceInMeters = col_double(),
     month = col_integer(),
     municipality = col_character(),
     nameAccordingTo = col_character(),
     nameAccordingToID = col_character(),
     namePublishedInID = col_character(),
     nomenclaturalCode = col_character(),
     nomenclaturalStatus = col_character(),
     organismQuantity = col_character(),
     otherCatalogNumbers = col_character(),
     ownerInstitutionCode = col_character(),
     parentNameUsage = col_character(),
     parentNameUsageID = col_character(),
     pointRadiusSpatialFit = col_double(),
     preparations = col_character(),
     recordNumber = col_character(),
     reproductiveCondition = col_character(),
     sampleSizeUnit = col_character(),
     sampleSizeValue = col_double(),
     samplingEffort = col_character(),
     scientificNameID = col_character(),
     sex = col_character(),
     taxonConceptID = col_character(),
     taxonID = col_character(),
     taxonRemarks = col_character(),
     type = col_character(),
     typeStatus = col_character(),
     verbatimElevation = col_character(),
     verbatimSRS = col_character(),
     verbatimTaxonRank = col_character(),
     vernacularName = col_character(),
     waterBody = col_character(),
     year = col_integer()
)
# Load occurrences
occ_df <- read_delim(
  file = occ_df_file, delim = "\t",
  escape_double = FALSE, trim_ws = TRUE,
  col_types = col_types)
occ_df <- occ_df %>%
  mutate(dateIdentified = as_datetime(dateIdentified))