3.1 What is spocc?
spocc is an R package that is a single user interface to occurrence data.
spocc
currently interfaces with ten major biodiversity repositories
- Global Biodiversity Information Facility (GBIF) (via
rgbif
) - Berkeley Ecoengine (via
ecoengine
) - iNaturalist
- VertNet (via
rvertnet
) - Biodiversity Information Serving Our Nation (via
rbison
) - eBird (via
rebird
) - AntWeb (via
AntWeb
) - iDigBio (via
ridigbio
) - OBIS
- Atlas of Living Australia
3.2 Basic example
Load spocc
and request data for a given taxonomic name, for each of three different data sources, specify options across all data sources (e.g., limit
number of records), and options for specific data sources (using gbifopts = list()
, etc. for each data source).
library(spocc)out <- occ(query = 'Setophaga caerulescens', from = c('gbif','bison','inat'), limit = 3, gbifopts = list(country = 'US'))
Access GBIF data
out$gbif#> Species [Setophaga caerulescens (3)] #> First 10 rows of [Setophaga_caerulescens]#> #> # A tibble: 3 x 73#> name longitude latitude prov issues key scientificName datasetKey#> <chr> <dbl> <dbl> <chr> <chr> <chr> <chr> <chr> #> 1 Seto… -96.7 32.9 gbif cdrou… 2550… Setophaga cae… 50c9509d-…#> 2 Seto… -96.7 32.9 gbif gass8… 2557… Setophaga cae… 50c9509d-…#> 3 Seto… -96.7 32.9 gbif gass8… 2563… Setophaga cae… 50c9509d-…#> # … with 65 more variables: publishingOrgKey <chr>, installationKey <chr>,#> # publishingCountry <chr>, protocol <chr>, lastCrawled <chr>,#> # lastParsed <chr>, crawlId <int>, hostingOrganizationKey <chr>,#> # basisOfRecord <chr>, occurrenceStatus <chr>, taxonKey <int>,#> # kingdomKey <int>, phylumKey <int>, classKey <int>, orderKey <int>,#> # familyKey <int>, genusKey <int>, speciesKey <int>, acceptedTaxonKey <int>,#> # acceptedScientificName <chr>, kingdom <chr>, phylum <chr>, order <chr>,#> # family <chr>, genus <chr>, species <chr>, genericName <chr>,#> # specificEpithet <chr>, taxonRank <chr>, taxonomicStatus <chr>,#> # dateIdentified <chr>, stateProvince <chr>, year <int>, month <int>,#> # day <int>, eventDate <date>, modified <chr>, lastInterpreted <chr>,#> # references <chr>, license <chr>, isInCluster <lgl>, geodeticDatum <chr>,#> # class <chr>, countryCode <chr>, country <chr>, rightsHolder <chr>,#> # identifier <chr>, `http://unknown.org/nick` <chr>, verbatimEventDate <chr>,#> # datasetName <chr>, gbifID <chr>, verbatimLocality <chr>,#> # collectionCode <chr>, occurrenceID <chr>, taxonID <chr>,#> # catalogNumber <chr>, recordedBy <chr>,#> # `http://unknown.org/occurrenceDetails` <chr>, institutionCode <chr>,#> # rights <chr>, eventTime <chr>, identifiedBy <chr>, identificationID <chr>,#> # coordinateUncertaintyInMeters <dbl>, occurrenceRemarks <chr>
Access BISON data
out$bison#> Species [Setophaga caerulescens (3)] #> First 10 rows of [Setophaga_caerulescens]#> #> # A tibble: 3 x 33#> name longitude latitude prov providedScienti… date countryCode#> <chr> <dbl> <dbl> <chr> <chr> <date> <chr> #> 1 Dend… -82.5 48.2 bison Dendroica caeru… NA US #> 2 Dend… -82.5 36.9 bison Dendroica caeru… NA US #> 3 Dend… -82.6 45.8 bison Dendroica caeru… NA US #> # … with 26 more variables: ambiguous <lgl>, generalComments <chr>,#> # latlon <chr>, computedCountyFips <chr>, occurrenceID <chr>,#> # basisOfRecord <chr>, providedCommonName <chr>, collectionID <chr>,#> # ownerInstitutionCollectionCode <chr>, institutionID <chr>,#> # computedStateFips <chr>, license <chr>, TSNs <chr>, providerID <int>,#> # geo <chr>, provider <chr>, calculatedCounty <chr>,#> # ITISscientificName <chr>, pointPath <chr>, kingdom <chr>,#> # calculatedState <chr>, hierarchy_hom*onym_string <chr>, centroid <chr>,#> # ITIScommonName <chr>, resourceID <chr>, ITIStsn <chr>
Access iNaturalist data
out$inat#> Species [Setophaga caerulescens (3)] #> First 10 rows of [Setophaga_caerulescens]#> #> # A tibble: 3 x 140#> name longitude latitude prov quality_grade time_observed_at taxon_geoprivacy#> <chr> <chr> <chr> <chr> <chr> <chr> <chr> #> 1 Seto… -83.1629… 41.6155… inat research 2017-05-18T10:3… open #> 2 Seto… -80.2931… 25.7411… inat research 2020-12-11T15:3… open #> 3 Seto… -81.8480… 42.3150… inat research 2020-05-23T15:1… open #> # … with 133 more variables: annotations <list>, uuid <chr>, id <int>,#> # cached_votes_total <int>, identifications_most_agree <lgl>,#> # species_guess <chr>, identifications_most_disagree <lgl>, tags <chr>,#> # positional_accuracy <int>, comments_count <int>, site_id <int>,#> # created_time_zone <chr>, license_code <chr>, observed_time_zone <chr>,#> # quality_metrics <list>, public_positional_accuracy <int>,#> # reviewed_by <list>, oauth_application_id <int>, flags <list>,#> # created_at <chr>, description <chr>, time_zone_offset <chr>,#> # project_ids_with_curator_id <list>, observed_on <date>,#> # observed_on_string <chr>, updated_at <chr>, sounds <list>,#> # place_ids <list>, captive <lgl>, ident_taxon_ids <list>, outlinks <list>,#> # faves_count <int>, ofvs <list>, num_identification_agreements <int>,#> # comments <list>, map_scale <int>, uri <chr>, project_ids <list>,#> # community_taxon_id <int>, owners_identification_from_vision <lgl>,#> # identifications_count <int>, obscured <lgl>,#> # num_identification_disagreements <int>, geoprivacy <chr>, location <chr>,#> # votes <list>, spam <lgl>, mappable <lgl>, identifications_some_agree <lgl>,#> # project_ids_without_curator_id <list>, place_guess <chr>,#> # identifications <list>, project_observations <list>,#> # observation_sounds <list>, photos <list>, observation_photos <list>,#> # faves <list>, non_owner_ids <list>, observed_on_details.date <chr>,#> # observed_on_details.week <int>, observed_on_details.month <int>,#> # observed_on_details.hour <int>, observed_on_details.year <int>,#> # observed_on_details.day <int>, created_at_details.date <chr>,#> # created_at_details.week <int>, created_at_details.month <int>,#> # created_at_details.hour <int>, created_at_details.year <int>,#> # created_at_details.day <int>, taxon.is_active <lgl>, taxon.ancestry <chr>,#> # taxon.min_species_ancestry <chr>, taxon.endemic <lgl>,#> # taxon.iconic_taxon_id <int>, taxon.min_species_taxon_id <int>,#> # taxon.threatened <lgl>, taxon.rank_level <int>, taxon.introduced <lgl>,#> # taxon.native <lgl>, taxon.parent_id <int>, taxon.rank <chr>,#> # taxon.extinct <lgl>, taxon.id <int>, taxon.ancestor_ids <list>,#> # taxon.photos_locked <lgl>, taxon.taxon_schemes_count <int>,#> # taxon.wikipedia_url <chr>, taxon.current_synonymous_taxon_ids <lgl>,#> # taxon.created_at <chr>, taxon.taxon_changes_count <int>,#> # taxon.complete_species_count <lgl>, taxon.universal_search_rank <int>,#> # taxon.observations_count <int>, taxon.atlas_id <lgl>,#> # taxon.complete_rank <chr>, taxon.iconic_taxon_name <chr>,#> # taxon.preferred_common_name <chr>, taxon.flag_counts.unresolved <int>,#> # taxon.flag_counts.resolved <int>, …