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 != '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_check_sentinels(data_raw):
expander = DataFrameETL(cols_to_expand=['pid', 'djinn_type',
'animal', 'fruits'])
# fill in necessary parameters
expander._nan_string = 'effrit'
expander._nan_numeric = 1.0
expander._is_numeric = {}
expander.levels_ = {}
expander._cols_to_drop = expander.cols_to_drop
expander._cols_to_expand = expander.cols_to_expand
for col in expander.cols_to_expand:
expander._is_numeric[col] = expander._flag_numeric(
pd.unique(data_raw[col]))
expander._check_sentinels(data_raw)
assert expander._nan_string is not 'effrit'
assert expander._nan_numeric is not 1.0
assert not (data_raw[['pid', 'djinn_type', 'animal']] ==
expander._nan_string).any().any()
assert not (data_raw['fruits'] == expander._nan_numeric).any().any()
