def test_similarities__filebased_badid(empty_hits_df):
queries = pd.Series(['foo-bar'])
with pytest.raises(IncompleteHits) as e:
similarities(queries, 'data/similarities.h5', 0.55, 1)
assert_frame_equal(e.value.hits, empty_hits_df)
assert e.value.absent_identifiers == ['foo-bar']
def test_similarities__filebased_badid(empty_hits_df):
queries = pd.Series(['foo-bar'])
with pytest.raises(IncompleteHits) as e:
similarities(queries, 'data/similarities.h5', 0.55, 1)
assert_frame_equal(e.value.hits, empty_hits_df)
assert e.value.absent_identifiers == ['foo-bar']
def test_similarities__filebased_partbadid():
queries = pd.Series(['3j7u_NDP_frag24', 'foo-bar'])
with pytest.raises(IncompleteHits) as e:
similarities(queries, 'data/similarities.h5', 0.55, 1)
expected = [
{'query_frag_id': '3j7u_NDP_frag24', 'hit_frag_id': '3j7u_NDP_frag23', 'score': 0.8991},
]
assert_frame_equal(e.value.hits, pd.DataFrame(expected, columns=['query_frag_id', 'hit_frag_id', 'score']))
assert e.value.absent_identifiers == ['foo-bar']
def test_similarities__webbased_badid(base_url, empty_hits_df):
queries = pd.Series(['foo-bar'])
with requests_mock.mock() as m:
url = base_url + '/fragments/' + 'foo-bar' + '/similar?cutoff=0.55'
m.get(url, status_code=404)
with pytest.raises(IncompleteHits) as e:
similarities(queries, base_url, 0.55)
assert_frame_equal(e.value.hits, pd.DataFrame(empty_hits_df))
assert e.value.absent_identifiers == ['foo-bar']
def test_similarities__webbased_badid(base_url, empty_hits_df):
queries = pd.Series(['foo-bar'])
with requests_mock.mock() as m:
url = base_url + '/fragments/' + 'foo-bar' + '/similar?cutoff=0.55'
m.get(url, status_code=404)
with pytest.raises(IncompleteHits) as e:
similarities(queries, base_url, 0.55)
assert_frame_equal(e.value.hits, pd.DataFrame(empty_hits_df))
assert e.value.absent_identifiers == ['foo-bar']
def test_similarities__webbased_partbadid(base_url):
queries = pd.Series(['3j7u_NDP_frag24', 'foo-bar'])
body = [
{'query_frag_id': '3j7u_NDP_frag24', 'hit_frag_id': '3j7u_NDP_frag23', 'score': 0.8991},
]
with requests_mock.mock() as m:
m.get(base_url + '/fragments/' + 'foo-bar' + '/similar?cutoff=0.55', status_code=404)
url = base_url + '/fragments/' + '3j7u_NDP_frag24' + '/similar?cutoff=0.55'
m.get(url, json=body)
with pytest.raises(IncompleteHits) as e:
similarities(queries, base_url, 0.55)
assert_frame_equal(e.value.hits, pd.DataFrame(body, columns=['query_frag_id', 'hit_frag_id', 'score']))
assert e.value.absent_identifiers == ['foo-bar']
def test_similarities_limitof1():
queries = pd.Series(['3j7u_NDP_frag24'])
result = similarities(queries, 'data/similarities.h5', 0.55, 1)
expected = [
{'query_frag_id': '3j7u_NDP_frag24', 'hit_frag_id': '3j7u_NDP_frag23', 'score': 0.8991},
]
assert_frame_equal(result, pd.DataFrame(expected, columns=['query_frag_id', 'hit_frag_id', 'score']))
def test_similarities__filebased_partbadid():
queries = pd.Series(['3j7u_NDP_frag24', 'foo-bar'])
with pytest.raises(IncompleteHits) as e:
similarities(queries, 'data/similarities.h5', 0.55, 1)
expected = [
{
'query_frag_id': '3j7u_NDP_frag24',
'hit_frag_id': '3j7u_NDP_frag23',
'score': 0.8991
},
]
assert_frame_equal(
e.value.hits,
pd.DataFrame(expected,
columns=['query_frag_id', 'hit_frag_id', 'score']))
assert e.value.absent_identifiers == ['foo-bar']
def test_similarities__webbased_partbadid(base_url):
queries = pd.Series(['3j7u_NDP_frag24', 'foo-bar'])
body = [
{
'query_frag_id': '3j7u_NDP_frag24',
'hit_frag_id': '3j7u_NDP_frag23',
'score': 0.8991
},
]
with requests_mock.mock() as m:
m.get(base_url + '/fragments/' + 'foo-bar' + '/similar?cutoff=0.55',
status_code=404)
url = base_url + '/fragments/' + '3j7u_NDP_frag24' + '/similar?cutoff=0.55'
m.get(url, json=body)
with pytest.raises(IncompleteHits) as e:
similarities(queries, base_url, 0.55)
assert_frame_equal(
e.value.hits,
pd.DataFrame(body, columns=['query_frag_id', 'hit_frag_id', 'score']))
assert e.value.absent_identifiers == ['foo-bar']
def test_similarities_limitof1():
queries = pd.Series(['3j7u_NDP_frag24'])
result = similarities(queries, 'data/similarities.h5', 0.55, 1)
expected = [
{
'query_frag_id': '3j7u_NDP_frag24',
'hit_frag_id': '3j7u_NDP_frag23',
'score': 0.8991
},
]
assert_frame_equal(
result,
pd.DataFrame(expected,
columns=['query_frag_id', 'hit_frag_id', 'score']))
from kripodb.canned import similarities
# Map options to kripo arguments
query_column = options['fragment_id_column']
similarity_matrix = options['matrix']
cutoff = options['cutoff']
limit = options['limit']
# Select input column
queries = input_table[query_column]
# Fetch similarities
output_table = similarities(queries,
similarity_matrix,
cutoff,
limit)