def update_pagerank():
print('Query for uris')
uri_response = query.query_sparql(uri_query)
print('Query for uris complete')
adjacency_list = populate_uris(uri_response)
print('Query for links')
link_response = query.query_sparql(link_query)
print('Query for links complete')
populate_links(link_response, adjacency_list)
g = graph(adjacency_list)
print('Running pagerank')
pr = pagerank(g, tolerance=float(utils.get_config()['pagerank_tolerance']))
print('Running pagerank complete')
pr_vector = np.squeeze(np.asarray(pr))
return make_uri2rank(pr_vector, g.uri2index)
def update_clusters():
print('Query for sequences')
sequences_response = query.query_sparql(sequence_query)
print('Query for sequences complete')
write_fasta(sequences_response)
print('Running uclust')
run_uclust()
print('Running uclust complete')
analyze_uclust()
return uclust2clusters()
def update_pagerank():
utils.log('Query for uris')
uri_response = query.query_sparql(uri_query)
utils.log('Query for uris complete')
adjacency_list = populate_uris(uri_response)
utils.log('Query for links')
link_response = query.query_sparql(link_query)
utils.log('Query for links complete')
populate_links(link_response, adjacency_list)
g = graph(adjacency_list)
utils.log('Running pagerank')
pr = pagerank(g, tolerance=float(utils.get_config()['pagerank_tolerance']))
utils.log('Running pagerank complete')
pr_vector = np.squeeze(np.asarray(pr))
# after squeeze, make sure it at least has a dimension in the case that there is only one element
if pr_vector.shape == ():
pr_vector = np.array([pr_vector])
return make_uri2rank(pr_vector, g.uri2index)
def incremental_remove_collection(subject, uri_prefix):
collection_membership_query = '''
SELECT
?s
WHERE {
<''' + subject + '''> sbol2:member ?s .
FILTER(STRSTARTS(str(?s),''' + "'" + uri_prefix + "'" + '''))
}
'''
members = query.query_sparql(collection_membership_query)
delete_subject(subject)
for member in members:
delete_subject(member['s'])