def make_ecommerce_entityset(with_integer_time_index=False):
""" Makes a entityset with the following shape:
R Regions
/ \\ .
S C Stores, Customers
| .
S P Sessions, Products
\\ / .
L Log
"""
dataframes = make_ecommerce_dataframes(
with_integer_time_index=with_integer_time_index)
dataframe_names = dataframes.keys()
es_id = 'ecommerce'
if with_integer_time_index:
es_id += "_int_time_index"
logical_types = make_logical_types(
with_integer_time_index=with_integer_time_index)
semantic_tags = make_semantic_tags()
time_indexes = make_time_indexes(
with_integer_time_index=with_integer_time_index)
es = EntitySet(id=es_id)
for df_name in dataframe_names:
time_index = time_indexes.get(df_name, None)
ti_name = None
secondary = None
if time_index is not None:
ti_name = time_index['name']
secondary = time_index['secondary']
df = dataframes[df_name]
es.add_dataframe(df,
dataframe_name=df_name,
index='id',
logical_types=logical_types[df_name],
semantic_tags=semantic_tags[df_name],
time_index=ti_name,
secondary_time_index=secondary)
es.normalize_dataframe('customers',
'cohorts',
'cohort',
additional_columns=['cohort_name'],
make_time_index=True,
new_dataframe_time_index='cohort_end')
es.add_relationships([(u'régions', 'id', 'customers', u'région_id'),
(u'régions', 'id', 'stores', u'région_id'),
('customers', 'id', 'sessions', 'customer_id'),
('sessions', 'id', 'log', 'session_id'),
('products', 'id', 'log', 'product_id')])
return es
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
def make_ecommerce_entityset(with_integer_time_index=False):
"""Makes a entityset with the following shape:
R Regions
/ \\ .
S C Stores, Customers
| .
S P Sessions, Products
\\ / .
L Log
"""
dataframes = make_ecommerce_dataframes(
with_integer_time_index=with_integer_time_index
)
dataframe_names = dataframes.keys()
es_id = "ecommerce"
if with_integer_time_index:
es_id += "_int_time_index"
logical_types = make_logical_types(with_integer_time_index=with_integer_time_index)
semantic_tags = make_semantic_tags()
time_indexes = make_time_indexes(with_integer_time_index=with_integer_time_index)
es = EntitySet(id=es_id)
for df_name in dataframe_names:
time_index = time_indexes.get(df_name, None)
ti_name = None
secondary = None
if time_index is not None:
ti_name = time_index["name"]
secondary = time_index["secondary"]
df = dataframes[df_name]
es.add_dataframe(
df,
dataframe_name=df_name,
index="id",
logical_types=logical_types[df_name],
semantic_tags=semantic_tags[df_name],
time_index=ti_name,
secondary_time_index=secondary,
)
es.normalize_dataframe(
"customers",
"cohorts",
"cohort",
additional_columns=["cohort_name"],
make_time_index=True,
new_dataframe_time_index="cohort_end",
)
es.add_relationships(
[
("régions", "id", "customers", "région_id"),
("régions", "id", "stores", "région_id"),
("customers", "id", "sessions", "customer_id"),
("sessions", "id", "log", "session_id"),
("products", "id", "log", "product_id"),
]
)
return es