def test_SingleCells_init():
"""
Testing initialization of SingleCells
"""
assert ap.file_or_conn == file
assert ap.strata == ["Metadata_Plate", "Metadata_Well"]
assert ap.merge_cols == ["TableNumber", "ImageNumber"]
assert ap.image_cols == ["TableNumber", "ImageNumber", "Metadata_Site"]
pd.testing.assert_frame_equal(image_df.sort_index(axis=1),
ap.image_df.sort_index(axis=1))
assert ap.subsample_frac == 1
assert ap_subsample.subsample_frac == 1
assert ap.subsample_n == "all"
assert ap_subsample.subsample_n == 2
assert ap.subset_data_df == "none"
assert ap.output_file == "none"
assert ap.aggregation_operation == "median"
assert not ap.is_aggregated
assert ap.subsampling_random_state == "none"
assert ap_subsample.subsampling_random_state == 123
assert ap.fields_of_view == "all"
assert ap.fields_of_view_feature == "Metadata_Site"
assert ap.object_feature == "Metadata_ObjectNumber"
assert ap.compartment_linking_cols == get_default_linking_cols()
assert ap.compartments == get_default_compartments()
def create_linking_columns(noncanonical, noncanonical_compartments):
linking_columns = get_default_linking_cols()
if noncanonical:
for comp in noncanonical_compartments:
linking_columns[comp] = {"cytoplasm": "ObjectNumber"}
linking_columns["cytoplasm"][
comp] = f"Cytoplasm_Parent_{comp.capitalize()}" # This will not work if the feature name uses CamelCase.
return linking_columns
def test_provide_linking_cols_feature_name_update():
expected_result = {
"Cytoplasm_Parent_Cells": "Metadata_Cytoplasm_Parent_Cells",
"Cytoplasm_Parent_Nuclei": "Metadata_Cytoplasm_Parent_Nuclei",
"ObjectNumber": "Metadata_ObjectNumber",
}
result = provide_linking_cols_feature_name_update()
assert result == expected_result
new_linking_cols = get_default_linking_cols()
new_linking_cols["cytoplasm"]["new"] = "Cytoplasm_Parent_New"
new_linking_cols["new"] = {"cytoplasm": "ObjectNumber"}
result = provide_linking_cols_feature_name_update(new_linking_cols)
expected_result = {
"Cytoplasm_Parent_Cells": "Metadata_Cytoplasm_Parent_Cells",
"Cytoplasm_Parent_Nuclei": "Metadata_Cytoplasm_Parent_Nuclei",
"Cytoplasm_Parent_New": "Metadata_Cytoplasm_Parent_New",
"ObjectNumber": "Metadata_ObjectNumber",
}
assert result == expected_result
new_cytoplasm_df.to_sql("cytoplasm",
con=test_new_engine,
index=False,
if_exists="replace")
nuclei_df.to_sql("nuclei",
con=test_new_engine,
index=False,
if_exists="replace")
new_compartment_df.to_sql("new",
con=test_new_engine,
index=False,
if_exists="replace")
new_compartments = ["cells", "cytoplasm", "nuclei", "new"]
new_linking_cols = get_default_linking_cols()
new_linking_cols["cytoplasm"]["new"] = "Cytoplasm_Parent_New"
new_linking_cols["new"] = {"cytoplasm": "ObjectNumber"}
# Setup SingleCells Class
ap = SingleCells(file_or_conn=file, object_feature="Metadata_ObjectNumber")
ap_subsample = SingleCells(
file_or_conn=file,
subsample_n=2,
subsampling_random_state=123,
object_feature="Metadata_ObjectNumber",
)
ap_new = SingleCells(
file_or_conn=new_file,
load_image_data=False,
compartments=new_compartments,
def test_default_linking_cols():
linking_cols = get_default_linking_cols()
assert linking_cols == default_linking_cols
