def stats():
"""Hidden URL for statistics
I've intentionally not publicised this feature because it makes lots of HTTP
requests to the Sanger website and I probably only want me / administrators to
use it on an infrequent basis"""
all_pubmed_ids = set(publications.keys())
confirmed_pubmed_ids = set(publications.confirmed().keys())
denied_pubmed_ids = set(publications.denied().keys())
to_be_confirmed_ids = all_pubmed_ids.difference(confirmed_pubmed_ids, denied_pubmed_ids)
library_pubmed_ids = set(LibrarySearcher.get_pubmed_ids())
confirmed_in_library_ids = library_pubmed_ids.intersection(confirmed_pubmed_ids)
to_be_confirmed_in_library_ids = library_pubmed_ids.intersection(to_be_confirmed_ids)
not_in_libary_ids = all_pubmed_ids.difference(library_pubmed_ids)
confirmed_not_in_library = not_in_libary_ids.intersection(confirmed_pubmed_ids)
to_be_confirmed_not_in_library = not_in_libary_ids.intersection(to_be_confirmed_ids)
statistics = {
'tracked: total': len(all_pubmed_ids),
'tracked: confirmed': len(confirmed_pubmed_ids),
'tracked: possible': len(to_be_confirmed_ids),
'tracked: denied': len(denied_pubmed_ids),
'library: total': len(library_pubmed_ids),
'library: confirmed': len(confirmed_in_library_ids),
'library: possible': len(to_be_confirmed_in_library_ids),
'other: total': len(confirmed_not_in_library) + len(to_be_confirmed_not_in_library),
'other: confirmed': len(confirmed_not_in_library),
'other: possible': len(to_be_confirmed_not_in_library)
}
return jsonify(**statistics)
def stats():
"""Hidden URL for statistics
I've intentionally not publicised this feature because it makes lots of HTTP
requests to the Sanger website and I probably only want me / administrators to
use it on an infrequent basis"""
all_pubmed_ids = set(publications.keys())
confirmed_pubmed_ids = set(publications.confirmed().keys())
denied_pubmed_ids = set(publications.denied().keys())
to_be_confirmed_ids = all_pubmed_ids.difference(confirmed_pubmed_ids,
denied_pubmed_ids)
library_pubmed_ids = set(LibrarySearcher.get_pubmed_ids())
confirmed_in_library_ids = library_pubmed_ids.intersection(
confirmed_pubmed_ids)
to_be_confirmed_in_library_ids = library_pubmed_ids.intersection(
to_be_confirmed_ids)
not_in_libary_ids = all_pubmed_ids.difference(library_pubmed_ids)
confirmed_not_in_library = not_in_libary_ids.intersection(
confirmed_pubmed_ids)
to_be_confirmed_not_in_library = not_in_libary_ids.intersection(
to_be_confirmed_ids)
statistics = {
'tracked: total':
len(all_pubmed_ids),
'tracked: confirmed':
len(confirmed_pubmed_ids),
'tracked: possible':
len(to_be_confirmed_ids),
'tracked: denied':
len(denied_pubmed_ids),
'library: total':
len(library_pubmed_ids),
'library: confirmed':
len(confirmed_in_library_ids),
'library: possible':
len(to_be_confirmed_in_library_ids),
'other: total':
len(confirmed_not_in_library) + len(to_be_confirmed_not_in_library),
'other: confirmed':
len(confirmed_not_in_library),
'other: possible':
len(to_be_confirmed_not_in_library)
}
return jsonify(**statistics)
def missing():
"""Hidden URL for missing publications
I've intentionally not publicised this feature because it makes lots of HTTP
requests to the Sanger website and I probably only want me / administrators to
use it on an infrequent basis.
This endpoint lists all of the publicatons which are currently not in the
Sanger Library's dataset"""
library_pubmed_ids = set(LibrarySearcher.get_pubmed_ids())
possible_pubmed_ids = set(publications.not_denied().keys())
missing_pubmed_ids = possible_pubmed_ids.difference(library_pubmed_ids)
missing_publications = Publications([publications[pubmed_id] for pubmed_id in
missing_pubmed_ids])
return render_template('affiliated.html',
publications=missing_publications,
users=users,
user_title="Publications not in the Sanger Library")
def missing():
"""Hidden URL for missing publications
I've intentionally not publicised this feature because it makes lots of HTTP
requests to the Sanger website and I probably only want me / administrators to
use it on an infrequent basis.
This endpoint lists all of the publicatons which are currently not in the
Sanger Library's dataset"""
library_pubmed_ids = set(LibrarySearcher.get_pubmed_ids())
possible_pubmed_ids = set(publications.not_denied().keys())
missing_pubmed_ids = possible_pubmed_ids.difference(library_pubmed_ids)
missing_publications = Publications(
[publications[pubmed_id] for pubmed_id in missing_pubmed_ids])
return render_template('affiliated.html',
publications=missing_publications,
users=users,
user_title="Publications not in the Sanger Library")
with open(options.usersfile, "r") as usersfile:
users = User.from_yaml(usersfile.read())
users_count = len(users)
logging.info("Loaded %s users from %s" % (users_count, options.usersfile))
pubmed_ids = set()
logging.info("Searching pubmed for publications")
for user in users.values():
new_pubmed_ids = Searcher.get_pubmed_ids_for_user(user, options.start, options.end)
pubmed_ids.update(new_pubmed_ids)
pubmed_id_count = len(pubmed_ids)
logging.info("Found %s citations by searching pubmed" % pubmed_id_count)
logging.info("Getting pubmed_ids from the Library")
new_pubmed_ids = LibrarySearcher.get_pubmed_ids(options.start, options.end)
pubmed_ids.update(new_pubmed_ids)
logging.info("Found additional %s publications in Library" % (len(pubmed_ids) - pubmed_id_count))
new_publications = Publications.from_pubmed_ids(list(pubmed_ids))
publications = Publications.merge(publications, new_publications)
for publication in publications.values():
publication.update_authors(users)
if options.outputfile != "":
with open(options.outputfile, "wb") as output:
affiliated_publications = publications.not_denied()
affiliated_publications.to_csv(output)
logging.info("%s citations with at least one user matching the input queries have been printed to %s" % (
len(affiliated_publications), options.outputfile))
with open(options.usersfile, "r") as usersfile:
users = User.from_yaml(usersfile.read())
users_count = len(users)
logging.info("Loaded %s users from %s" % (users_count, options.usersfile))
pubmed_ids = set()
logging.info("Searching pubmed for publications")
for user in users.values():
new_pubmed_ids = Searcher.get_pubmed_ids_for_user(
user, options.start, options.end)
pubmed_ids.update(new_pubmed_ids)
pubmed_id_count = len(pubmed_ids)
logging.info("Found %s citations by searching pubmed" % pubmed_id_count)
logging.info("Getting pubmed_ids from the Library")
new_pubmed_ids = LibrarySearcher.get_pubmed_ids(options.start, options.end)
pubmed_ids.update(new_pubmed_ids)
logging.info("Found additional %s publications in Library" %
(len(pubmed_ids) - pubmed_id_count))
new_publications = Publications.from_pubmed_ids(list(pubmed_ids))
publications = Publications.merge(publications, new_publications)
for publication in publications.values():
publication.update_authors(users)
if options.outputfile != "":
with open(options.outputfile, "wb") as output:
affiliated_publications = publications.not_denied()
affiliated_publications.to_csv(output)
logging.info(
