def test_operations_invalidate_metadata(es):
new_es = EntitySet(id="test")
# test metadata gets created on access
assert new_es._data_description is None
assert new_es.metadata is not None # generated after access
assert new_es._data_description is not None
if not isinstance(es['customers'].df, pd.DataFrame):
customers_vtypes = es["customers"].variable_types
customers_vtypes['signup_date'] = variable_types.Datetime
else:
customers_vtypes = None
new_es.entity_from_dataframe("customers",
es["customers"].df,
index=es["customers"].index,
variable_types=customers_vtypes)
if not isinstance(es['sessions'].df, pd.DataFrame):
sessions_vtypes = es["sessions"].variable_types
else:
sessions_vtypes = None
new_es.entity_from_dataframe("sessions",
es["sessions"].df,
index=es["sessions"].index,
variable_types=sessions_vtypes)
assert new_es._data_description is None
assert new_es.metadata is not None
assert new_es._data_description is not None
r = Relationship(new_es["customers"]["id"],
new_es["sessions"]["customer_id"])
new_es = new_es.add_relationship(r)
assert new_es._data_description is None
assert new_es.metadata is not None
assert new_es._data_description is not None
new_es = new_es.normalize_entity("customers", "cohort", "cohort")
assert new_es._data_description is None
assert new_es.metadata is not None
assert new_es._data_description is not None
new_es.add_last_time_indexes()
assert new_es._data_description is None
assert new_es.metadata is not None
assert new_es._data_description is not None
# automatically adding interesting values not supported in Dask or Koalas
if any(isinstance(entity.df, pd.DataFrame) for entity in new_es.entities):
new_es.add_interesting_values()
assert new_es._data_description is None
assert new_es.metadata is not None
assert new_es._data_description is not None
def test_operations_invalidate_metadata(es):
new_es = EntitySet(id="test")
# test metadata gets created on access
assert new_es._data_description is None
assert new_es.metadata is not None # generated after access
assert new_es._data_description is not None
if not isinstance(es['customers'], pd.DataFrame):
customers_ltypes = es["customers"].ww.logical_types
customers_ltypes['signup_date'] = Datetime
else:
customers_ltypes = None
new_es.add_dataframe(es["customers"],
"customers",
index=es["customers"].index,
logical_types=customers_ltypes)
if not isinstance(es['sessions'], pd.DataFrame):
sessions_ltypes = es["sessions"].ww.logical_types
else:
sessions_ltypes = None
new_es.add_dataframe(es["sessions"],
"sessions",
index=es["sessions"].index,
logical_types=sessions_ltypes)
assert new_es._data_description is None
assert new_es.metadata is not None
assert new_es._data_description is not None
new_es = new_es.add_relationship("customers", "id", "sessions",
"customer_id")
assert new_es._data_description is None
assert new_es.metadata is not None
assert new_es._data_description is not None
new_es = new_es.normalize_dataframe("customers", "cohort", "cohort")
assert new_es._data_description is None
assert new_es.metadata is not None
assert new_es._data_description is not None
new_es.add_last_time_indexes()
assert new_es._data_description is None
assert new_es.metadata is not None
assert new_es._data_description is not None
# automatically adding interesting values not supported in Dask or Koalas
if new_es.dataframe_type == Library.PANDAS.value:
new_es.add_interesting_values()
assert new_es._data_description is None
assert new_es.metadata is not None
assert new_es._data_description is not None