def test_process_clustering_output_signatures_without_author_id():
clusterer_mock = MagicMock()
clusterer_mock.clusterer.labels_ = numpy.array([1, 1])
clusterer_mock.X = numpy.array(
[
[
Signature(
author_affiliation="Rutgers U., Piscataway",
author_id=None,
author_name="Doe, John",
publication=Publication(
abstract="Many curated authors",
authors=[
"Doe, John",
"Doe, J",
"Doe, John",
"Doe, John",
"Doe, John",
"Doe, John",
"Jamie",
"Jamie",
],
collaborations=[],
keywords=["keyword"],
publication_id=1,
title="Title",
topics=["category"],
),
signature_block="JOhn",
signature_uuid="94fc2b0a-dc17-42c2-bae3-ca0024079e52",
is_curated_author_id=False,
)
],
[
Signature(
author_affiliation="Rutgers U., Piscataway",
author_id=None,
author_name="Doe, John",
publication=Publication(
abstract="Many curated authors",
authors=[
"Doe, John",
"Doe, J",
"Doe, John",
"Doe, John",
"Doe, John",
"Doe, John",
"Jamie",
"Jamie",
],
collaborations=[],
keywords=["keyword"],
publication_id=1,
title="Title",
topics=["category"],
),
signature_block="JOhn",
signature_uuid="94fc2b0a-dc17-42c2-bae3-ca0024079e54",
is_curated_author_id=False,
)
],
],
dtype=object,
)
expected_output = [{
"signatures": [
(1, "94fc2b0a-dc17-42c2-bae3-ca0024079e52"),
(1, "94fc2b0a-dc17-42c2-bae3-ca0024079e54"),
],
"authors": [],
}]
output = process_clustering_output(clusterer_mock)
assert not DeepDiff(output, expected_output, ignore_order=True)
def test_process_clustering_output_signatures_multiple_curated_author_ids():
clusterer_mock = MagicMock()
clusterer_mock.clusterer.labels_ = numpy.array([0, 0, 1, 1, 1])
clusterer_mock.X = numpy.array(
[
[
Signature(
author_affiliation="Rutgers U., Piscataway",
author_id=1,
author_name="Doe, John",
publication=Publication(
abstract="Many curated authors",
authors=[
"Doe, John",
"Doe, J",
"Doe, John",
"Doe, John",
"Doe, John",
"Doe, John",
"Jamie",
"Jamie",
],
collaborations=[],
keywords=["keyword"],
publication_id=11,
title="Title",
topics=["category"],
),
signature_block="JOhn",
signature_uuid="94fc2b0a-dc17-42c2-bae3-ca0024079e52",
is_curated_author_id=True,
)
],
[
Signature(
author_affiliation="Rutgers U., Piscataway",
author_id=None,
author_name="Doe, John",
publication=Publication(
abstract="Many curated authors",
authors=[
"Doe, John",
"Doe, J",
"Doe, John",
"Doe, John",
"Doe, John",
"Doe, John",
"Jamie",
"Jamie",
],
collaborations=[],
keywords=["keyword"],
publication_id=12,
title="Title",
topics=["category"],
),
signature_block="JOhn",
signature_uuid="94fc2b0a-dc17-42c2-bae3-ca0024079e53",
is_curated_author_id=False,
)
],
[
Signature(
author_affiliation="Rutgers U., Piscataway",
author_id=3,
author_name="Doe, John",
publication=Publication(
abstract="Many curated authors",
authors=[
"Doe, John",
"Doe, J",
"Doe, John",
"Doe, John",
"Doe, John",
"Doe, John",
"Jamie",
"Jamie",
],
collaborations=[],
keywords=["keyword"],
publication_id=13,
title="Title",
topics=["category"],
),
signature_block="JOhn",
signature_uuid="94fc2b0a-dc17-42c2-bae3-ca0024079e54",
is_curated_author_id=True,
)
],
[
Signature(
author_affiliation="Rutgers U., Piscataway",
author_id=None,
author_name="Doe, John",
publication=Publication(
abstract="Many curated authors",
authors=[
"Doe, John",
"Doe, J",
"Doe, John",
"Doe, John",
"Doe, John",
"Doe, John",
"Jamie",
"Jamie",
],
collaborations=[],
keywords=["keyword"],
publication_id=14,
title="Title",
topics=["category"],
),
signature_block="JOhn",
signature_uuid="94fc2b0a-dc17-42c2-bae3-ca0024079e55",
is_curated_author_id=False,
)
],
[
Signature(
author_affiliation="Rutgers U., Piscataway",
author_id=5,
author_name="Doe, John",
publication=Publication(
abstract="Many curated authors",
authors=[
"Doe, John",
"Doe, J",
"Doe, John",
"Doe, John",
"Doe, John",
"Doe, John",
"Jamie",
"Jamie",
],
collaborations=[],
keywords=["keyword"],
publication_id=15,
title="Title",
topics=["category"],
),
signature_block="JOhn",
signature_uuid="94fc2b0a-dc17-42c2-bae3-ca0024079e56",
is_curated_author_id=True,
)
],
],
dtype=object,
)
expected_output = [
{
"signatures": [
{
"publication_id": 11,
"signature_uuid": "94fc2b0a-dc17-42c2-bae3-ca0024079e52",
},
{
"publication_id": 12,
"signature_uuid": "94fc2b0a-dc17-42c2-bae3-ca0024079e53",
},
],
"authors": [{"author_id": 1, "has_claims": True}],
},
{
"signatures": [
{
"publication_id": 13,
"signature_uuid": "94fc2b0a-dc17-42c2-bae3-ca0024079e54",
},
{
"publication_id": 14,
"signature_uuid": "94fc2b0a-dc17-42c2-bae3-ca0024079e55",
},
{
"publication_id": 15,
"signature_uuid": "94fc2b0a-dc17-42c2-bae3-ca0024079e56",
},
],
"authors": [
{"author_id": 3, "has_claims": True},
{"author_id": 5, "has_claims": True},
],
},
]
output = process_clustering_output(clusterer_mock)
assert not DeepDiff(output, expected_output, ignore_order=True)