def test_check_sentinels(data_raw):
expander = DataFrameETL(
cols_to_expand=['pid', 'djinn_type', 'animal', 'fruits'])
# fill in necessary parameters
expander._nan_sentinel = 'effrit'
expander.levels_ = {}
expander._cols_to_drop = expander.cols_to_drop
expander._cols_to_expand = expander.cols_to_expand
expander._check_sentinels(data_raw)
assert expander._nan_sentinel is not 'effrit'
assert not (data_raw[['pid', 'djinn_type', 'animal']]
== expander._nan_sentinel).any().any()
# The NaN sentinel can't be in the "fruits" column because
# "fruits" is numeric and the sentinel is not.
assert np.issubdtype(data_raw['fruits'].dtype, np.number)
assert not np.issubdtype(type(expander._nan_sentinel), np.number)
def test_create_col_names(data_raw):
expander = DataFrameETL(cols_to_expand=['pid', 'djinn_type', 'animal'],
cols_to_drop=['fruits'],
dummy_na='expanded')
expander._nan_sentinel = NAN_STRING
expander._cols_to_drop = expander.cols_to_drop
expander._cols_to_expand = expander.cols_to_expand
expander._dummy_na = 'expanded'
expander.levels_ = expander._create_levels(data_raw)
expander._unexpanded_nans = expander._flag_unexpanded_nans(data_raw)
(cnames, unexpanded) = expander._create_col_names(data_raw)
cols_expected = [
'pid_a', 'pid_b', 'pid_c', 'pid_NaN', 'djinn_type_effrit',
'djinn_type_marid', 'djinn_type_sila', 'djinn_type_NaN', 'age',
'animal_cat', 'animal_dog', 'animal_NaN'
]
assert cnames == cols_expected
assert unexpanded == ['pid', 'djinn_type', 'age', 'animal']
