def _compare_feature_dicts(a_dict, b_dict):
# We can't compare entityset dictionaries because variable lists are not
# guaranteed to be in the same order.
es_a = description_to_entityset(a_dict.pop('entityset'))
es_b = description_to_entityset(b_dict.pop('entityset'))
assert es_a == es_b
assert a_dict == b_dict
def _check_schema_version(version, es, error_text):
entities = {entity.id: serialize.entity_to_description(entity) for entity in es.entities}
relationships = [relationship.to_dictionary() for relationship in es.relationships]
dictionary = {
'schema_version': version,
'id': es.id,
'entities': entities,
'relationships': relationships,
}
if error_text:
with pytest.raises(RuntimeError) as excinfo:
deserialize.description_to_entityset(dictionary)
assert error_text == str(excinfo.value)
else:
deserialize.description_to_entityset(dictionary)
def metadata(self):
'''Returns the metadata for this EntitySet. The metadata will be recomputed if it does not exist.'''
if self._data_description is None:
description = serialize.entityset_to_description(self)
self._data_description = deserialize.description_to_entityset(description)
return self._data_description
def _check_schema_version(version, es, warning_text):
entities = {
entity.id: serialize.entity_to_description(entity)
for entity in es.entities
}
relationships = [
relationship.to_dictionary() for relationship in es.relationships
]
dictionary = {
'schema_version': version,
'id': es.id,
'entities': entities,
'relationships': relationships,
}
if warning_text:
with pytest.warns(UserWarning) as record:
deserialize.description_to_entityset(dictionary)
assert record[0].message.args[0] == warning_text
else:
deserialize.description_to_entityset(dictionary)
def _check_schema_version(version,
es,
warning_text,
caplog,
warning_type=None):
entities = {
entity.id: serialize.entity_to_description(entity)
for entity in es.entities
}
relationships = [
relationship.to_dictionary() for relationship in es.relationships
]
dictionary = {
'schema_version': version,
'id': es.id,
'entities': entities,
'relationships': relationships,
}
if warning_type == 'log' and warning_text:
logger = logging.getLogger('featuretools')
logger.propagate = True
deserialize.description_to_entityset(dictionary)
assert warning_text in caplog.text
logger.propagate = False
elif warning_type == 'warn' and warning_text:
with pytest.warns(UserWarning) as record:
deserialize.description_to_entityset(dictionary)
assert record[0].message.args[0] == warning_text
else:
deserialize.description_to_entityset(dictionary)
def test_all_ww_logical_types():
logical_types = list_logical_types()['type_string'].to_list()
dataframe = pd.DataFrame(columns=logical_types)
es = EntitySet()
ltype_dict = {ltype: ltype for ltype in logical_types}
ltype_dict['ordinal'] = Ordinal(order=[])
es.add_dataframe(dataframe=dataframe,
dataframe_name='all_types',
index='integer',
logical_types=ltype_dict)
description = serialize.entityset_to_description(es)
_es = deserialize.description_to_entityset(description)
assert es.__eq__(_es, deep=True)
def test_with_custom_ww_logical_type():
class CustomLogicalType(LogicalType):
pass
ww_type_system.add_type(CustomLogicalType)
columns = ['integer', 'natural_language', 'custom_logical_type']
dataframe = pd.DataFrame(columns=columns)
es = EntitySet()
ltype_dict = {
'integer': 'integer',
'natural_language': 'natural_language',
'custom_logical_type': CustomLogicalType,
}
es.add_dataframe(dataframe=dataframe,
dataframe_name='custom_type',
index='integer',
logical_types=ltype_dict)
description = serialize.entityset_to_description(es)
_es = deserialize.description_to_entityset(description)
assert isinstance(
_es['custom_type'].ww.logical_types['custom_logical_type'],
CustomLogicalType)
assert es.__eq__(_es, deep=True)
def test_dask_entityset_description(dask_es):
description = serialize.entityset_to_description(dask_es)
_es = deserialize.description_to_entityset(description)
assert dask_es.metadata.__eq__(_es, deep=True)
