def test_add_type_with_parent():
type_sys = TypeSystem()
type_sys.add_type(Double, inference_function=double_func)
type_sys.add_type(Integer, inference_function=integer_func, parent=Double)
assert Integer in type_sys.inference_functions.keys()
assert type_sys.inference_functions[Integer] is integer_func
assert len(type_sys.relationships) == 1
assert type_sys.relationships[0] == (Double, Integer)
def test_add_type_without_parent():
type_sys = TypeSystem()
type_sys.add_type(Double, inference_function=double_func)
assert Double in type_sys.inference_functions.keys()
assert type_sys.inference_functions[Double] is double_func
type_sys.add_type(Integer)
assert Integer in type_sys.inference_functions.keys()
assert type_sys.inference_functions[Integer] is None
def test_str_to_logical_type():
all_types = ww.type_system.registered_types
with pytest.raises(ValueError,
match='String test is not a valid logical type'):
ww.type_system.str_to_logical_type('test')
assert ww.type_system.str_to_logical_type('test',
raise_error=False) is None
for logical_type in all_types:
assert ww.type_system.str_to_logical_type(
logical_type.__name__) == logical_type
assert ww.type_system.str_to_logical_type(
logical_type.type_string) == logical_type
assert ww.type_system.str_to_logical_type('bOoLeAn') == Boolean
assert ww.type_system.str_to_logical_type(
'person_full_NAME') == PersonFullName
assert ww.type_system.str_to_logical_type(
'PersonFullnamE') == PersonFullName
ymd = '%Y-%m-%d'
datetime_with_format = ww.type_system.str_to_logical_type(
'datetime', params={'datetime_format': ymd})
assert datetime_with_format.__class__ == Datetime
assert datetime_with_format.datetime_format == ymd
assert datetime_with_format == Datetime(datetime_format=ymd)
datetime_no_format = ww.type_system.str_to_logical_type(
'datetime', params={'datetime_format': None})
assert datetime_no_format.__class__ == Datetime
assert datetime_no_format.datetime_format is None
assert datetime_no_format == Datetime()
# When parameters are supplied in a non-empty dictionary, the logical type gets instantiated
assert ww.type_system.str_to_logical_type('person_full_NAME',
params={}) == PersonFullName
assert datetime_no_format != Datetime
# Input a different type system
new_type_sys = TypeSystem()
with pytest.raises(ValueError,
match='String Integer is not a valid logical type'):
new_type_sys.str_to_logical_type('Integer')
new_type_sys.add_type(Boolean)
assert Boolean == new_type_sys.str_to_logical_type('Boolean')
def test_str_to_logical_type():
all_types = ww.type_system.registered_types
with pytest.raises(ValueError,
match="String test is not a valid logical type"):
ww.type_system.str_to_logical_type("test")
assert ww.type_system.str_to_logical_type("test",
raise_error=False) is None
for logical_type in all_types:
assert ww.type_system.str_to_logical_type(
logical_type.__name__) == logical_type
assert (ww.type_system.str_to_logical_type(
logical_type.type_string) == logical_type)
assert ww.type_system.str_to_logical_type("bOoLeAn") == Boolean
assert ww.type_system.str_to_logical_type(
"person_full_NAME") == PersonFullName
assert ww.type_system.str_to_logical_type(
"PersonFullnamE") == PersonFullName
ymd = "%Y-%m-%d"
datetime_with_format = ww.type_system.str_to_logical_type(
"datetime", params={"datetime_format": ymd})
assert datetime_with_format.__class__ == Datetime
assert datetime_with_format.datetime_format == ymd
assert datetime_with_format == Datetime(datetime_format=ymd)
datetime_no_format = ww.type_system.str_to_logical_type(
"datetime", params={"datetime_format": None})
assert datetime_no_format.__class__ == Datetime
assert datetime_no_format.datetime_format is None
assert datetime_no_format == Datetime()
# When parameters are supplied in a non-empty dictionary, the logical type gets instantiated
assert (ww.type_system.str_to_logical_type("person_full_NAME",
params={}) == PersonFullName)
assert datetime_no_format != Datetime
# Input a different type system
new_type_sys = TypeSystem()
with pytest.raises(ValueError,
match="String Integer is not a valid logical type"):
new_type_sys.str_to_logical_type("Integer")
new_type_sys.add_type(Boolean)
assert Boolean == new_type_sys.str_to_logical_type("Boolean")
def test_inference_multiple_matches_different_depths(default_relationships):
def always_true(series):
return True
inference_functions = {
Categorical: always_true,
Double: always_true,
Integer: always_true,
CountryCode: always_true,
}
type_sys = TypeSystem(inference_functions=inference_functions,
relationships=default_relationships,
default_type=NaturalLanguage)
type_sys.update_inference_function(Integer, always_true)
type_sys.update_inference_function(CountryCode, always_true)
type_sys.add_type(SubRegionCode, inference_function=always_true, parent=CountryCode)
inferred_type = type_sys.infer_logical_type(pd.Series([1, 2, 3]))
# Should match SubRegionCode as it is the deepest match
assert inferred_type == SubRegionCode