def test_get_cherrypicked_samples_test_db_connection_close(app):
"""
Test Scenario
- Check that connection is close when we call get_cherrypicked_samples
"""
samples = ["MCM001", "MCM002", "MCM003", "MCM004", "MCM005"]
plate_barcodes = ["123", "456"]
with app.app_context():
with patch("sqlalchemy.create_engine") as mock_sql_engine:
mock_db_connection = Mock()
mock_sql_engine().connect.return_value = mock_db_connection
get_cherrypicked_samples(samples, plate_barcodes)
mock_db_connection.close.assert_called_once()
def test_get_cherrypicked_samples_repeat_tests_sentinel_and_beckman(
app, freezer, mlwh_sentinel_and_beckman_cherrypicked, event_wh_data):
# the following come from MLWH_SAMPLE_STOCK_RESOURCE and
# MLWH_SAMPLE_LIGHTHOUSE_SAMPLE in fixture_data
root_sample_ids = [
"root_1", "root_2", "root_3", "root_4", "root_5", "root_1"
]
plate_barcodes = ["pb_1", "pb_2", "pb_3", "pb_4", "pb_5", "pb_6"]
# root_1 will match 2 samples, but only one of those will match a Sentinel event (on pb_1)
# root_2 will match a single sample with a matching Sentinel event (on pb_2)
# root_3 will match 2 samples, but not match either a Sentinel or Beckman event
# root_4 will match 2 samples, but only one of those will match a Beckman event (on pb_4)
# root_5 will match a single sample with a matching Beckman event (on pb_5)
# We also chunk to further test different scenarios
expected_rows = [
["root_1", "pb_1", "positive", "A1"],
["root_2", "pb_2", "positive", "A1"],
["root_4", "pb_4", "positive", "A1"],
["root_5", "pb_5", "positive", "A1"],
]
expected_columns = [
FIELD_ROOT_SAMPLE_ID, FIELD_PLATE_BARCODE, "Result_lower",
FIELD_COORDINATE
]
expected = pd.DataFrame(np.array(expected_rows),
columns=expected_columns,
index=[0, 1, 2, 3])
with app.app_context():
chunk_size = 2
returned_samples = get_cherrypicked_samples(root_sample_ids,
plate_barcodes, chunk_size)
pd.testing.assert_frame_equal(expected, returned_samples)
def test_get_cherrypicked_samples_sentinel_and_beckman(app):
expected = [
pd.DataFrame(
[
# Sentinel
"MCM001",
"MCM006",
# Beckman
"MCM001",
"MCM003",
"MCM005",
],
columns=[FIELD_ROOT_SAMPLE_ID],
index=[0, 1, 2, 3, 4],
), # Cherrypicking query response
]
samples = ["MCM001", "MCM002", "MCM003", "MCM004", "MCM005", "MCM006"]
plate_barcodes = ["123", "456"]
with app.app_context():
with patch("sqlalchemy.create_engine", return_value=Mock()):
with patch(
"pandas.read_sql",
side_effect=expected,
):
returned_samples = get_cherrypicked_samples(
samples, plate_barcodes)
assert returned_samples.at[0, FIELD_ROOT_SAMPLE_ID] == "MCM001"
assert returned_samples.at[1, FIELD_ROOT_SAMPLE_ID] == "MCM006"
assert returned_samples.at[2, FIELD_ROOT_SAMPLE_ID] == "MCM003"
assert returned_samples.at[3, FIELD_ROOT_SAMPLE_ID] == "MCM005"
def test_get_cherrypicked_samples_repeat_tests_no_sentinel(
app, mlwh_beckman_cherrypicked, event_wh_data):
# the following come from MLWH_SAMPLE_LIGHTHOUSE_SAMPLE in fixture_data
root_sample_ids = ["root_4", "root_5", "root_4"]
plate_barcodes = ["pb_4", "pb_5", "pb_6"]
# root_4 will match 2 samples, but only one of those will match an event (on sample uuid)
# therefore we only get 1 of the samples called 'root_4' back (the one on plate 'pb_4')
# this also checks we don't get a duplicate row for root_4 / pb_4, despite it cropped up in 2
# different 'chunks'
expected_rows = [["root_4", "pb_4", "positive", "A1"],
["root_5", "pb_5", "positive", "A1"]]
expected_columns = [
FIELD_ROOT_SAMPLE_ID, FIELD_PLATE_BARCODE, "Result_lower",
FIELD_COORDINATE
]
expected = pd.DataFrame(np.array(expected_rows),
columns=expected_columns,
index=[0, 1])
with app.app_context():
chunk_size = 2
returned_samples = get_cherrypicked_samples(root_sample_ids,
plate_barcodes, chunk_size)
# The view could be returning the rows in a different order, which we solve by sorting and
# reindexing the rows for returned_samples, so we can compare with our expected frame
resorted_returned_samples = returned_samples.sort_values(
by=FIELD_ROOT_SAMPLE_ID, ignore_index=True)
pd.testing.assert_frame_equal(expected, resorted_returned_samples)
def test_get_cherrypicked_samples_chunking_no_sentinel(app):
# Note: This represents the results of three different (Sentinel, Beckman) sets of
# database queries, each Sentinel query getting indexed from 0. Do not change the
# indices here unless you have modified the behaviour of the query.
query_results = [
pd.DataFrame(["MCM001"], columns=[FIELD_ROOT_SAMPLE_ID],
index=[0]), # Cherrypicking query resp.
pd.DataFrame(["MCM003"], columns=[FIELD_ROOT_SAMPLE_ID],
index=[0]), # Cherrypicking query resp.
pd.DataFrame(["MCM005"], columns=[FIELD_ROOT_SAMPLE_ID],
index=[0]), # Cherrypicking query resp.
]
expected = pd.DataFrame(["MCM001", "MCM003", "MCM005"],
columns=[FIELD_ROOT_SAMPLE_ID],
index=[0, 1, 2])
samples = ["MCM001", "MCM002", "MCM003", "MCM004", "MCM005"]
plate_barcodes = ["123", "456"]
with app.app_context():
with patch("sqlalchemy.create_engine", return_value=Mock()):
with patch(
"pandas.read_sql",
side_effect=query_results,
):
returned_samples = get_cherrypicked_samples(
samples, plate_barcodes, 2)
pd.testing.assert_frame_equal(expected, returned_samples)
def test_get_cherrypicked_samples_repeat_tests_no_beckman(
app, mlwh_sentinel_cherrypicked, event_wh_data):
# the following come from MLWH_SAMPLE_STOCK_RESOURCE in fixture_data
root_sample_ids = ["root_1", "root_2", "root_1"]
plate_barcodes = ["pb_1", "pb_2", "pb_3"]
# root_1 will match 2 samples, but only one of those will match an event (on Sanger Sample Id)
# therefore we only get 1 of the samples called 'root_1' back (the one on plate 'pb_1')
# this also checks we don't get a duplicate row for root_1 / pb_1, despite it cropped up in 2
# different 'chunks'
expected_rows = [["root_1", "pb_1", "positive", "A1"],
["root_2", "pb_2", "positive", "A1"]]
expected_columns = [
FIELD_ROOT_SAMPLE_ID, FIELD_PLATE_BARCODE, "Result_lower",
FIELD_COORDINATE
]
expected = pd.DataFrame(np.array(expected_rows),
columns=expected_columns,
index=[0, 1])
with app.app_context():
chunk_size = 2
returned_samples = get_cherrypicked_samples(root_sample_ids,
plate_barcodes, chunk_size)
print(returned_samples)
pd.testing.assert_frame_equal(expected, returned_samples)
def test_get_cherrypicked_samples(app, freezer):
expected = pd.DataFrame(
["MCM001", "MCM003", "MCM005"], columns=[FIELD_ROOT_SAMPLE_ID], index=[0, 1, 2]
)
samples = ["MCM001", "MCM002", "MCM003", "MCM004", "MCM005"]
plate_barcodes = ["123", "456"]
with app.app_context():
with patch("sqlalchemy.create_engine", return_value=Mock()):
with patch(
"pandas.read_sql", return_value=expected,
):
returned_samples = get_cherrypicked_samples(samples, plate_barcodes)
assert returned_samples.at[0, FIELD_ROOT_SAMPLE_ID] == "MCM001"
assert returned_samples.at[1, FIELD_ROOT_SAMPLE_ID] == "MCM003"
assert returned_samples.at[2, FIELD_ROOT_SAMPLE_ID] == "MCM005"