def test_analyze_sample_names_drop_incorrectly_named_samples():
test_df = make_test_data()
test_df.loc[2, "Sample ID"] = "hello, world!"
dropped_both = td.analyze_sample_names(
test_df, drop_incorrectly_named_samples=True, drop_buffers=True
)
assert len(dropped_both) == 1
assert len(td._identify_buffer_measurements(dropped_both)) == 0
dropped_incorrect_not_buffers = td.analyze_sample_names(
test_df, drop_incorrectly_named_samples=True, drop_buffers=False
)
assert len(dropped_incorrect_not_buffers) == 2
assert len(td._identify_buffer_measurements(dropped_incorrect_not_buffers)) == 1
with pytest.warns(UserWarning) as sample_name_divergence:
td.analyze_sample_names(test_df, drop_incorrectly_named_samples=False)
assert (
"Sample names do not adhere to requirements"
in sample_name_divergence[0].message.args[0]
)
assert (
"Identify incorrectly named samples by running analyze_sample_names"
in sample_name_divergence[0].message.args[0]
)
def test_identify_buffer_measurements():
test_df = make_test_data()
assert (td._identify_buffer_measurements(test_df) == [1]).all()
test_df.loc[2, "Sample ID"] = "Buffer_100_0.5"
assert (td._identify_buffer_measurements(test_df) == [1, 2]).all()
test_df.loc[:, "Sample ID"] = "Peptide_100_0.5"
assert len(td._identify_buffer_measurements(test_df)) == 0
def test_analyze_sample_names_buffer_dropping_only():
test_df = make_test_data()
dropped = td.analyze_sample_names(test_df, drop_buffers=True)
assert len(dropped) == 2
assert len(td._identify_buffer_measurements(dropped)) == 0
not_dropped = td.analyze_sample_names(test_df, drop_buffers=False)
assert len(not_dropped) == 3
assert len(td._identify_buffer_measurements(not_dropped)) == 1
assert len(not_dropped.loc[not_dropped["Sample ID"] == "blank", :]) == 1
def test_handle_incorrectly_named_samples_keep_buffers_only():
test_df = make_test_data()
dropped = td._handle_incorrectly_named_samples(
test_df, [0], drop_incorrectly_named_samples=True, drop_buffers=False
)
assert len(dropped) == 2
assert len(td._identify_buffer_measurements(dropped)) == 1
def test_handle_incorrectly_named_samples_drop_buffers_only():
test_df = make_test_data()
with pytest.warns(UserWarning):
dropped = td._handle_incorrectly_named_samples(
test_df, [0], drop_incorrectly_named_samples=False, drop_buffers=True
)
assert len(dropped) == 2
assert len(td._identify_buffer_measurements(dropped)) == 0
def test_run_all_explicitly_keep_buffers():
df = test_run_all(
to_glob="test_data/*.csv",
file_reader_kwargs={},
drop_incorrectly_named_samples=True,
drop_buffers=False,
)
assert "RG7" in df["Peptide"].values
assert len(td._identify_buffer_measurements(df)) > 0