def test_create_levels(data_raw, levels_dict):
expander = DataFrameETL(cols_to_expand=['pid', 'djinn_type', 'animal'])
expander._nan_sentinel = NAN_STRING
expander._cols_to_drop = expander.cols_to_drop
expander._cols_to_expand = expander.cols_to_expand
actual_levels = expander._create_levels(data_raw)
assert actual_levels == levels_dict
def test_create_levels(data_raw, levels_dict):
expander = DataFrameETL(cols_to_expand=['pid', 'djinn_type', 'animal'])
expander._is_numeric = {'pid': 0, 'djinn_type': 0, 'animal': 0}
expander._nan_numeric = NAN_NUMERIC
expander._nan_string = NAN_STRING
expander._cols_to_drop = expander.cols_to_drop
expander._cols_to_expand = expander.cols_to_expand
actual_levels = expander._create_levels(data_raw)
assert actual_levels == levels_dict
def test_create_levels_no_dummy(data_raw, levels_dict_numeric):
expander = DataFrameETL(cols_to_expand=['pid', 'fruits'], dummy_na=False)
# remove nan from pid levels
levels_dict_numeric['pid'] = ['a', 'b', 'c']
expander._nan_sentinel = NAN_STRING
expander._cols_to_drop = expander.cols_to_drop
expander._cols_to_expand = expander.cols_to_expand
actual_levels = expander._create_levels(data_raw)
assert actual_levels == levels_dict_numeric
def test_create_col_names_numeric(data_raw):
expander = DataFrameETL(cols_to_expand=['pid', 'fruits'],
cols_to_drop=['djinn_type', 'animal'],
dummy_na=True)
expander._is_numeric = {'pid': 0, 'djinn_type': 0, 'fruits': 0}
expander._nan_numeric = NAN_NUMERIC
expander._nan_string = NAN_STRING
expander._cols_to_drop = expander.cols_to_drop
expander._cols_to_expand = expander.cols_to_expand
expander.levels_ = expander._create_levels(data_raw)
(cnames, unexpanded) = expander._create_col_names(data_raw)
cols_numeric = ['pid_a', 'pid_b', 'pid_c', 'pid_NaN', 'fruits_1.0',
'fruits_3.0', 'fruits_NaN', 'age']
assert cnames == cols_numeric
assert unexpanded == ['pid', 'fruits', 'age']
def test_create_col_names_no_dummy(data_raw):
expander = DataFrameETL(cols_to_expand=['pid', 'djinn_type', 'animal'],
cols_to_drop=['fruits'],
dummy_na=False)
expander._nan_sentinel = NAN_STRING
expander._cols_to_drop = expander.cols_to_drop
expander._cols_to_expand = expander.cols_to_expand
expander.levels_ = expander._create_levels(data_raw)
(cnames, unexpanded) = expander._create_col_names(data_raw)
cols_expected = [
'pid_a', 'pid_b', 'pid_c', 'djinn_type_effrit', 'djinn_type_marid',
'djinn_type_sila', 'age', 'animal_cat', 'animal_dog'
]
assert cnames == cols_expected
assert unexpanded == ['pid', 'djinn_type', 'age', 'animal']
def test_create_col_names_numeric(data_raw):
expander = DataFrameETL(cols_to_expand=['pid', 'fruits'],
cols_to_drop=['djinn_type', 'animal'],
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_numeric = [
'pid_a', 'pid_b', 'pid_c', 'pid_NaN', 'fruits_1.0', 'fruits_3.0',
'fruits_NaN', 'age'
]
assert cnames == cols_numeric
assert unexpanded == ['pid', 'fruits', 'age']
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_create_col_names(data_raw):
expander = DataFrameETL(cols_to_expand=['pid', 'djinn_type', 'animal'],
cols_to_drop=['fruits'],
dummy_na=True)
expander._is_numeric = {'pid': 0, 'djinn_type': 0, 'animal': 0}
expander._nan_numeric = NAN_NUMERIC
expander._nan_string = NAN_STRING
expander._cols_to_drop = expander.cols_to_drop
expander._cols_to_expand = expander.cols_to_expand
expander.levels_ = expander._create_levels(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']
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()
