def test_check_replicate_summary_method():
for metric in get_available_summary_methods():
check_replicate_summary_method(metric)
with pytest.raises(ValueError) as ve:
output = check_replicate_summary_method("fail")
assert "fail method not supported. Select one of:" in str(ve.value)
def test_compare_distributions():
# Define two distributions using a specific compound as an example
compound = "BRD-K07857022-002-01-1"
profile_id = "Metadata_profile_378"
target_group = similarity_melted_full_df.query(
"Metadata_profile_id_pair_a == @profile_id")
replicate_group_values = target_group.query(
"Metadata_broad_sample_pair_b == @compound"
).similarity_metric.values.reshape(-1, 1)
control_group_values = target_group.query(
"Metadata_broad_sample_pair_b == 'DMSO'"
).similarity_metric.values.reshape(-1, 1)
control_perts = df.query(
"Metadata_broad_sample == 'DMSO'").Metadata_profile_id.tolist()
hardcoded_values_should_not_change = {
"zscore": {
"mean": 5.639379456018854,
"median": 5.648269672347573
}
}
for summary_method in get_available_summary_methods():
hardcoded = hardcoded_values_should_not_change["zscore"][
summary_method]
result = compare_distributions(
target_distrib=replicate_group_values,
control_distrib=control_group_values,
method="zscore",
replicate_summary_method=summary_method,
)
assert np.round(result, 5) == np.round(hardcoded, 5)
grit_result = (grit(
similarity_melted_full_df,
control_perts=control_perts,
profile_col="Metadata_profile_id",
replicate_group_col="Metadata_broad_sample",
replicate_summary_method=summary_method,
).query("perturbation == @profile_id").grit.values[0])
assert result == grit_result
def test_get_available_summary_methods():
expected_result = ["mean", "median"]
assert expected_result == get_available_summary_methods()