def test_flat_summary(): now = datetime.datetime.utcnow() original = DatasetProfile(name="test", session_id="test.session.id", session_timestamp=now, tags={ "key": "value"}, metadata={"key": "value"},) flat_summary = original.flat_summary() assert flat_summary is not None assert len(original.flat_summary()) == 4
def test_track_null_item(): prof = DatasetProfile("name") prof.track("column_name", 1) prof = DatasetProfile("name") prof.track("column_name", None) assert prof.flat_summary()["summary"]["column"][0] == "column_name" assert prof.flat_summary()["summary"]["null_count"][0] == 1 prof.track("column_name", None) assert prof.flat_summary()["summary"]["null_count"][0] == 2 assert prof.flat_summary()["summary"]["column"][0] == "column_name"