def test_to_pseudonym_dates(): ints = Series(['07/15/2019', '07/24/2019', '07/23/2019', '07/22/2019', '07/21/2019', '07/22/2019', '07/23/2019', '07/24/2019', '07/23/2019', '07/22/2019', '07/15/2019']) attr = Attribute(ints, name='Date') pseudonyms = attr.pseudonymize() assert array_equal(ints.value_counts().values, pseudonyms.value_counts().values)
def test_pseudonymize_ints(): ints = Series([11, 2, 3, 4, 5, 4, 3, 2, 3, 4, 11]) attr = Attribute(ints, name='Integer') pseudonyms = attr.pseudonymize() assert array_equal(ints.value_counts().values, pseudonyms.value_counts().values)
def test_pseudonymize_floats(): floats = Series([11.5, 2.6, 3.0, 4.3, 5, 4.3, 3.0, 2.6, 3.0, 4.3, 11.6]) attr = Attribute(floats, name='Float') pseudonyms = attr.pseudonymize() assert array_equal(floats.value_counts().values, pseudonyms.value_counts().values)
def test_pseudonymize_strings(): strings = Series(['Abc', 'edf', 'Abc', 'take', '中国', 'edf', 'Abc']) attr = Attribute(strings, name='String') pseudonyms = attr.pseudonymize() assert array_equal(strings.value_counts().values, pseudonyms.value_counts().values)