def test_feature_infer_compartments():
features = infer_cp_features(population_df=data_df, compartments=["CElls"])
expected = ["Cells_Something_Something"]
features2 = infer_cp_features(population_df=data_df,
compartments=["nothing"])
expected2 = ["Nothing_somethingwrong"]
assert features == expected
assert features2 == expected2
def get_na_columns(population_df, features="infer", samples="all", cutoff=0.05):
"""
Get features that have more NA values than cutoff defined
Arguments:
population_df - pandas DataFrame storing profiles
features - list of features present in the population dataframe [default: "infer"]
if "infer", then assume cell painting features are those that do not
start with "Cells", "Nuclei", or "Cytoplasm"
samples - if provided, a list of samples to provide operation on
[default: "all"] - if "all", use all samples to calculate
cutoff - float to exclude features that have a higher proportion of missingness
Output:
A list of the features to exclude
"""
if samples != "all":
population_df = population_df.loc[samples, :]
if features == "infer":
features = infer_cp_features(population_df)
else:
population_df = population_df.loc[:, features]
num_rows = population_df.shape[0]
na_prop_df = population_df.isna().sum() / num_rows
na_prop_df = na_prop_df[na_prop_df > cutoff]
return list(set(na_prop_df.index.tolist()))
def test_feature_infer():
features = infer_cp_features(population_df=data_df)
expected = [
"Cells_Something_Something",
"Cytoplasm_Something_Something",
"Nuclei_Correlation_Manders_AGP_DNA",
"Nuclei_Correlation_RWC_ER_RNA",
]
assert features == expected
def test_metadata_feature_infer():
features = infer_cp_features(population_df=data_df, metadata=True)
expected = ["Metadata_Something_Something"]
assert features == expected
def test_feature_infer_nocp():
with pytest.raises(AssertionError) as nocp:
features = infer_cp_features(population_df=non_cp_data_df)
assert "No CP features found." in str(nocp.value)