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)
entities = dataframes.keys()
es_id = 'ecommerce'
if with_integer_time_index:
es_id += "_int_time_index"
variable_types = make_variable_types(
with_integer_time_index=with_integer_time_index)
time_indexes = make_time_indexes(
with_integer_time_index=with_integer_time_index)
es = EntitySet(id=es_id)
for entity in entities:
time_index = time_indexes.get(entity, None)
ti_name = None
secondary = None
if time_index is not None:
ti_name = time_index['name']
secondary = time_index['secondary']
df = dataframes[entity]
es.entity_from_dataframe(entity,
df,
index='id',
variable_types=variable_types[entity],
time_index=ti_name,
secondary_time_index=secondary)
es.normalize_entity('customers',
'cohorts',
'cohort',
additional_variables=['cohort_name'],
make_time_index=True,
new_entity_time_index='cohort_end')
es.add_relationships([
Relationship(es[u'régions']['id'], es['customers'][u'région_id']),
Relationship(es[u'régions']['id'], es['stores'][u'région_id']),
Relationship(es['customers']['id'], es['sessions']['customer_id']),
Relationship(es['sessions']['id'], es['log']['session_id']),
Relationship(es['products']['id'], es['log']['product_id'])
])
return es
def test_sets_time_when_adding_entity():
transactions_df = pd.DataFrame({
"id": [1, 2, 3, 4, 5, 6],
"card_id": [1, 2, 1, 3, 4, 5],
"transaction_time": [10, 12, 13, 20, 21, 20],
"fraud": [True, False, False, False, True, True]
})
accounts_df = pd.DataFrame({
"id": [3, 4, 5],
"signup_date":
[datetime(2002, 5, 1),
datetime(2006, 3, 20),
datetime(2011, 11, 11)]
})
accounts_df_string = pd.DataFrame({
"id": [3, 4, 5],
"signup_date": ["element", "exporting", "editable"]
})
# create empty entityset
es = EntitySet("fraud")
# assert it's not set
assert getattr(es, "time_type", None) is None
# add entity
es.entity_from_dataframe("transactions",
transactions_df,
index="id",
time_index="transaction_time")
# assert time_type is set
assert es.time_type == variable_types.NumericTimeIndex
# add another entity
es.normalize_entity("transactions",
"cards",
"card_id",
make_time_index=True)
# assert time_type unchanged
assert es.time_type == variable_types.NumericTimeIndex
# add wrong time type entity
error_text = "accounts time index is <class 'featuretools.variable_types.variable.DatetimeTimeIndex'> type which differs from other entityset time indexes"
with pytest.raises(TypeError, match=error_text):
es.entity_from_dataframe("accounts",
accounts_df,
index="id",
time_index="signup_date")
# add non time type as time index
error_text = "Attempted to convert all string column signup_date to numeric"
with pytest.raises(TypeError, match=error_text):
es.entity_from_dataframe("accounts",
accounts_df_string,
index="id",
time_index="signup_date")
def test_sets_time_when_adding_entity(self):
transactions_df = pd.DataFrame({
"id": [1, 2, 3, 4, 5, 6],
"card_id": [1, 2, 1, 3, 4, 5],
"transaction_time": [10, 12, 13, 20, 21, 20],
"fraud": [True, False, False, False, True, True]
})
accounts_df = pd.DataFrame({
"id": [3, 4, 5],
"signup_date": [
datetime(2002, 5, 1),
datetime(2006, 3, 20),
datetime(2011, 11, 11)
]
})
accounts_df_string = pd.DataFrame({
"id": [3, 4, 5],
"signup_date": ["element", "exporting", "editable"]
})
# create empty entityset
entityset = EntitySet("fraud")
# assert it's not set
assert getattr(entityset, "time_type", None) is None
# add entity
entityset.entity_from_dataframe("transactions",
transactions_df,
index="id",
time_index="transaction_time")
# assert time_type is set
assert entityset.time_type == variable_types.NumericTimeIndex
# add another entity
entityset.normalize_entity("transactions",
"cards",
"card_id",
make_time_index=True)
# assert time_type unchanged
assert entityset.time_type == variable_types.NumericTimeIndex
# add wrong time type entity
with pytest.raises(TypeError):
entityset.entity_from_dataframe("accounts",
accounts_df,
index="id",
time_index="signup_date")
# add non time type as time index
with pytest.raises(TypeError):
entityset.entity_from_dataframe("accounts",
accounts_df_string,
index="id",
time_index="signup_date")
def test_sets_time_when_adding_entity():
transactions_df = pd.DataFrame({"id": [1, 2, 3, 4, 5, 6],
"card_id": [1, 2, 1, 3, 4, 5],
"transaction_time": [10, 12, 13, 20, 21, 20],
"fraud": [True, False, False, False, True, True]})
accounts_df = pd.DataFrame({"id": [3, 4, 5],
"signup_date": [datetime(2002, 5, 1),
datetime(2006, 3, 20),
datetime(2011, 11, 11)]})
accounts_df_string = pd.DataFrame({"id": [3, 4, 5],
"signup_date": ["element",
"exporting",
"editable"]})
# create empty entityset
entityset = EntitySet("fraud")
# assert it's not set
assert getattr(entityset, "time_type", None) is None
# add entity
entityset.entity_from_dataframe("transactions",
transactions_df,
index="id",
time_index="transaction_time")
# assert time_type is set
assert entityset.time_type == variable_types.NumericTimeIndex
# add another entity
entityset.normalize_entity("transactions",
"cards",
"card_id",
make_time_index=True)
# assert time_type unchanged
assert entityset.time_type == variable_types.NumericTimeIndex
# add wrong time type entity
error_text = "accounts time index is <class 'featuretools.variable_types.variable.DatetimeTimeIndex'> type which differs from other entityset time indexes"
with pytest.raises(TypeError, match=error_text):
entityset.entity_from_dataframe("accounts",
accounts_df,
index="id",
time_index="signup_date")
# add non time type as time index
error_text = "Attempted to convert all string column signup_date to numeric"
with pytest.raises(TypeError, match=error_text):
entityset.entity_from_dataframe("accounts",
accounts_df_string,
index="id",
time_index="signup_date")
def test_make_time_index_keeps_original_sorting():
trips = {
'trip_id': [999 - i for i in range(1000)],
'flight_time': [datetime(1997, 4, 1) for i in range(1000)],
'flight_id': [1 for i in range(350)] + [2 for i in range(650)]
}
order = [i for i in range(1000)]
df = pd.DataFrame.from_dict(trips)
es = EntitySet('flights')
es.entity_from_dataframe("trips",
dataframe=df,
index="trip_id",
time_index='flight_time')
assert (es['trips'].df['trip_id'] == order).all()
es.normalize_entity(base_entity_id="trips",
new_entity_id="flights",
index="flight_id",
make_time_index=True)
assert (es['trips'].df['trip_id'] == order).all()
def test_make_time_index_keeps_original_sorting():
trips = {
'trip_id': [999 - i for i in range(1000)],
'flight_time': [datetime(1997, 4, 1) for i in range(1000)],
'flight_id': [1 for i in range(350)] + [2 for i in range(650)]
}
order = [i for i in range(1000)]
df = pd.DataFrame.from_dict(trips)
es = EntitySet('flights')
es.entity_from_dataframe("trips",
dataframe=df,
index="trip_id",
time_index='flight_time')
assert (es['trips'].df['trip_id'] == order).all()
es.normalize_entity(base_entity_id="trips",
new_entity_id="flights",
index="flight_id",
make_time_index=True)
assert (es['trips'].df['trip_id'] == order).all()
def test_sets_time_when_adding_entity(self):
transactions_df = pd.DataFrame({"id": [1, 2, 3, 4, 5, 6],
"card_id": [1, 2, 1, 3, 4, 5],
"transaction_time": [10, 12, 13, 20, 21, 20],
"fraud": [True, False, False, False, True, True]})
accounts_df = pd.DataFrame({"id": [3, 4, 5],
"signup_date": [datetime(2002, 5, 1),
datetime(2006, 3, 20),
datetime(2011, 11, 11)]})
accounts_df_string = pd.DataFrame({"id": [3, 4, 5],
"signup_date": ["element",
"exporting",
"editable"]})
# create empty entityset
entityset = EntitySet("fraud")
# assert it's not set
assert getattr(entityset, "time_type", None) is None
# add entity
entityset.entity_from_dataframe("transactions",
transactions_df,
index="id",
time_index="transaction_time")
# assert time_type is set
assert entityset.time_type == variable_types.NumericTimeIndex
# add another entity
entityset.normalize_entity("transactions",
"cards",
"card_id",
make_time_index=True)
# assert time_type unchanged
assert entityset.time_type == variable_types.NumericTimeIndex
# add wrong time type entity
with pytest.raises(TypeError):
entityset.entity_from_dataframe("accounts",
accounts_df,
index="id",
time_index="signup_date")
# add non time type as time index
with pytest.raises(TypeError):
entityset.entity_from_dataframe("accounts",
accounts_df_string,
index="id",
time_index="signup_date")
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