Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Tracking coverage of OA entities #211

Draft
wants to merge 6 commits into
base: main
Choose a base branch
from
Draft

Tracking coverage of OA entities #211

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
b8a0378
coverage for works first draft
yjunechoe Feb 26, 2024
f28cf5c
consult oa_entities()
yjunechoe Feb 26, 2024
755bf5b
document
yjunechoe Feb 26, 2024
59c702e
add get_coverage to pkgdown
yjunechoe Feb 26, 2024
4a445be
test for field coverage
yjunechoe Feb 27, 2024
1dc2d53
document coverage of authors
yjunechoe Feb 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
1 change: 1 addition & 0 deletions NAMESPACE
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
export(authors2df)
export(concepts2df)
export(funders2df)
export(get_coverage)
export(institutions2df)
export(oa2bibliometrix)
export(oa2df)
Expand Down
112 changes: 112 additions & 0 deletions R/openalexR-coverage.R
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,112 @@
#' Get coverage of OpenAlex fields in openalexR
#'
#' @param entity The OA entity to inspect field coverage for. Returns
#' information for all fields if `NULL` (default).
#'
#' @return Data frame of field coverage information
#' @export
#'
#' @seealso oa_entities()
#' @examples
#' oa_entities()
#' head(get_coverage(entity = "works"))
get_coverage <- function(entity = NULL) {
if (!is.null(entity)) {
entity <- match.arg(entity, oa_entities())
oa2df_coverage[[entity]]
} else {
oa2df_coverage
}
}

#' @keywords internal
oa2df_coverage <- list()

oa2df_coverage$works <- tibble::tribble(
~original, ~covered_by, ~comments,
"abstract_inverted_index", "ab", "reconstructed from inverted index",
"apc_list", NA, NA,
"apc_paid", NA, NA,
"authorships", "author", NA,
"best_oa_location", NA, NA,
"biblio", "volume", NA,
"biblio", "issue", NA,
"biblio", "first_page", NA,
"biblio", "last_page", NA,
"cited_by_api_url", "cited_by_api_url", NA,
"cited_by_count", "cited_by_count", NA,
"cited_by_percentile_year", NA, NA,
"concepts", "concepts", NA,
"corresponding_author_ids", NA, "reconstructable from `author$is_corresponding`",
"corresponding_institution_ids", NA, "reconstructable from `author$is_corresponding`",
"countries_distinct_count", NA, "reconstructable from `author$institution_country_code`",
"counts_by_year", "counts_by_year", NA,
"created_date", NA, NA,
"display_name", "display_name", NA,
"doi", "doi", NA,
"fulltext_origin", NA, NA,
"grants", "grants", NA,
"has_fulltext", "any_repository_has_fulltext", NA,
"id", "id", NA,
"ids", "ids", NA,
"indexed_in", NA, NA,
"institutions_distinct_count", NA, "reconstructable from `author$institution_id`",
"is_paratext", "is_paratext", NA,
"is_retracted", "is_retracted", NA,
"keywords", NA, NA,
"language", "language", NA,
"locations", NA, NA,
"locations_count", NA, NA,
"mesh", NA, NA,
"ngrams_url", NA, "see `oa_ngrams()`",
"open_access", "is_oa_anywhere", "see PR #135",
"open_access", "oa_status", NA,
"open_access", "oa_url", NA,
"primary_location", "is_oa", NA,
"primary_location", "so", NA,
"primary_location", "so_id", NA,
"primary_location", "host_organization", NA,
"primary_location", "issn_l", NA,
"primary_location", "url", NA,
"primary_location", "pdf_url", NA,
"primary_location", "license", NA,
"primary_location", "version", NA,
"primary_topic", NA, NA,
"publication_date", "publication_date", NA,
"publication_year", "publication_year", NA,
"referenced_works", "referenced_works", NA,
"referenced_works_count", NA, "reconstructable from `referenced_works`",
"related_works", "related_works", NA,
"sustainable_development_goals", NA, NA,
"title", "display_name", NA,
"topics", NA, NA,
"type", "type", NA,
"type_crossref", NA, NA,
"updated_date", NA, NA
)

oa2df_coverage$authors <- tibble::tribble(
~original, ~covered_by, ~comments,
"id", "id", NA,
"orcid", "orcid", NA,
"display_name", "display_name", NA,
"display_name_alternatives", "display_name_alternatives", NA,
"works_count", "works_count", NA,
"cited_by_count", "cited_by_count", NA,
"summary_stats", NA, NA,
"ids", "ids", NA,
"affiliations", "affiliation_display_name", NA,
"affiliations", "affiliation_id", NA,
"affiliations", "affiliation_ror", NA,
"affiliations", "affiliation_country_code", NA,
"affiliations", "affiliation_type", NA,
"affiliations", "affiliation_lineage", NA,
"affiliations", "affiliations_other", NA,
"last_known_institution", NA, "first entry in `affiliation_id`",
"last_known_institutions", NA, "`affiliation_id` + `affiliations_other`",
"x_concepts", "x_concepts", NA,
"counts_by_year", "counts_by_year", NA,
"works_api_url", "works_api_url", NA,
"updated_date", NA, NA,
"created_date", NA, NA
)
1 change: 1 addition & 0 deletions _pkgdown.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,4 +34,5 @@ reference:
- countrycode
- concept_abbrev
- oa_entities
- get_coverage
- oa2bibliometrix
25 changes: 25 additions & 0 deletions man/get_coverage.Rd
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

16 changes: 16 additions & 0 deletions tests/testthat/test-coverage.R
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
test_that("field coverage information is up to date", {
skip_on_cran()
cols <- lapply(get_coverage(), function(x) {
covered_by <- x$covered_by[!is.na(x$covered_by)]
# Additional fields from the parent Search entity
c(covered_by, "relevance_score")
})

# Works
w <- oa_fetch("works", options = list(sample = 1))
expect_true(all(colnames(w) %in% cols$works))

# Authors
a <- oa_fetch("authors", options = list(sample = 1))
expect_true(all(colnames(a) %in% cols$authors))
})