def test_ordinal_requires_instance_on_update(sample_series):
dc = DataColumn(sample_series, logical_type="NaturalLanguage")
error_msg = 'Must use an Ordinal instance with order values defined'
with pytest.raises(TypeError, match=error_msg):
dc.set_logical_type(Ordinal)
with pytest.raises(TypeError, match=error_msg):
dc.set_logical_type("Ordinal")
def test_set_logical_type_retains_time_index_tag(sample_datetime_series):
data_col = DataColumn(sample_datetime_series,
logical_type=Datetime,
semantic_tags='original_tag',
use_standard_tags=False)
data_col._set_as_time_index()
assert data_col.semantic_tags == {'time_index', 'original_tag'}
new_col = data_col.set_logical_type(Categorical)
assert new_col.semantic_tags == {'time_index'}
new_col = data_col.set_logical_type(Categorical, retain_index_tags=False)
assert new_col.semantic_tags == set()
def test_set_logical_type_without_standard_tags(sample_series):
data_col = DataColumn(sample_series,
logical_type=NaturalLanguage,
semantic_tags='original_tag',
use_standard_tags=False)
new_col = data_col.set_logical_type(Categorical)
assert isinstance(new_col, DataColumn)
assert new_col is not data_col
assert new_col.logical_type == Categorical
assert new_col.semantic_tags == set()
def test_ordinal_with_order(sample_series):
if (ks and isinstance(sample_series, ks.Series)) or (dd and isinstance(sample_series, dd.Series)):
pytest.xfail('Fails with Dask and Koalas - ordinal data validation not compatible')
ordinal_with_order = Ordinal(order=['a', 'b', 'c'])
dc = DataColumn(sample_series, logical_type=ordinal_with_order)
assert isinstance(dc.logical_type, Ordinal)
assert dc.logical_type.order == ['a', 'b', 'c']
dc = DataColumn(sample_series, logical_type="NaturalLanguage")
new_dc = dc.set_logical_type(ordinal_with_order)
assert isinstance(new_dc.logical_type, Ordinal)
assert new_dc.logical_type.order == ['a', 'b', 'c']
def test_dtype_update_on_ltype_change():
dc = DataColumn(pd.Series([1, 2, 3]),
logical_type='Integer')
assert dc._series.dtype == 'Int64'
dc = dc.set_logical_type('Double')
assert dc._series.dtype == 'float64'