def test_inspector_adult_easy_str_pipeline():
"""
Tests whether the str version of the inspector works
"""
with open(ADULT_SIMPLE_PY) as file:
code = file.read()
inspector_result = PipelineInspector\
.on_pipeline_from_string(code)\
.add_required_inspection(MaterializeFirstOutputRows(5)) \
.add_check(NoBiasIntroducedFor(['race'])) \
.add_check(NoIllegalFeatures()) \
.execute()
extracted_dag = inspector_result.dag
expected_dag = get_expected_dag_adult_easy("<string-source>")
compare(networkx.to_dict_of_dicts(extracted_dag),
networkx.to_dict_of_dicts(expected_dag))
assert HistogramForColumns(['race']) in list(
inspector_result.dag_node_to_inspection_results.values())[0]
check_to_check_results = inspector_result.check_to_check_results
assert check_to_check_results[NoBiasIntroducedFor(
['race'])].status == CheckStatus.SUCCESS
assert check_to_check_results[
NoIllegalFeatures()].status == CheckStatus.FAILURE
def test_get_dag_as_pretty_string():
"""
Tests whether the .py version of the inspector works
"""
extracted_dag = get_expected_dag_adult_easy("<string-source>")
pretty_string = get_dag_as_pretty_string(extracted_dag)
print(pretty_string)
def test_inspector_adult_easy_py_pipeline_without_inspections():
"""
Tests whether the .py version of the inspector works
"""
inspector_result = PipelineInspector\
.on_pipeline_from_py_file(ADULT_SIMPLE_PY)\
.execute()
extracted_dag = inspector_result.dag
expected_dag = get_expected_dag_adult_easy(ADULT_SIMPLE_PY)
compare(networkx.to_dict_of_dicts(extracted_dag),
networkx.to_dict_of_dicts(expected_dag))
def test_save_fig_to_path():
"""
Tests whether the .py version of the inspector works
"""
extracted_dag = get_expected_dag_adult_easy("<string-source>")
filename = os.path.join(str(get_project_root()), "example_pipelines",
"adult_simple", "adult_simple.png")
save_fig_to_path(extracted_dag, filename)
assert os.path.isfile(filename)
def test_pipeline_executor_nb_file(mocker):
"""
Tests whether the PipelineExecutor works for .ipynb files
"""
before_call_pandas_spy = mocker.spy(PandasBackend, 'before_call')
after_call_pandas_spy = mocker.spy(PandasBackend, 'after_call')
before_call_sklearn_spy = mocker.spy(SklearnBackend, 'before_call')
after_call_sklearn_spy = mocker.spy(SklearnBackend, 'after_call')
extracted_dag = _pipeline_executor.singleton.run(
notebook_path=ADULT_SIMPLE_IPYNB).dag
expected_dag = get_expected_dag_adult_easy(ADULT_SIMPLE_IPYNB, 6)
compare(networkx.to_dict_of_dicts(extracted_dag),
networkx.to_dict_of_dicts(expected_dag))
assert before_call_pandas_spy.call_count == 5
assert after_call_pandas_spy.call_count == 5
assert before_call_sklearn_spy.call_count == 7
assert after_call_sklearn_spy.call_count == 7
def test_pipeline_executor_py_file_without_code_reference_tracking(mocker):
"""
Tests whether the PipelineExecutor works for .py files
"""
before_call_pandas_spy = mocker.spy(PandasBackend, 'before_call')
after_call_pandas_spy = mocker.spy(PandasBackend, 'after_call')
before_call_sklearn_spy = mocker.spy(SklearnBackend, 'before_call')
after_call_sklearn_spy = mocker.spy(SklearnBackend, 'after_call')
extracted_dag = _pipeline_executor.singleton.run(
python_path=ADULT_SIMPLE_PY, track_code_references=False).dag
expected_dag = get_expected_dag_adult_easy(ADULT_SIMPLE_PY,
with_code_references=False)
compare(networkx.to_dict_of_dicts(extracted_dag),
networkx.to_dict_of_dicts(expected_dag))
assert before_call_pandas_spy.call_count == 5
assert after_call_pandas_spy.call_count == 5
assert before_call_sklearn_spy.call_count == 7
assert after_call_sklearn_spy.call_count == 7