def test_make_dfeat_of_agg_feat_through_parent(entityset, backend):
"""
The graph looks like this:
R C = Customers, the entity we're trying to predict on
/ \\ R = Regions, a parent of customers
S C S = Stores, a child of regions
|
etc.
We're trying to calculate a DFeat from C to R on an agg_feat of R on S.
"""
store_id_feat = IdentityFeature(entityset['stores']['id'])
store_count_feat = Count(store_id_feat,
parent_entity=entityset[u'régions'])
num_stores_feat = DirectFeature(store_count_feat,
child_entity=entityset['customers'])
pandas_backend = backend([num_stores_feat])
df = pandas_backend.calculate_all_features(instance_ids=[0],
time_last=None)
v = df[num_stores_feat.get_name()][0]
assert (v == 3)
def test_make_dfeat_of_agg_feat_through_parent(entityset, backend):
"""
The graph looks like this:
R C = Customers, the entity we're trying to predict on
/ \\ R = Regions, a parent of customers
S C S = Stores, a child of regions
|
etc.
We're trying to calculate a DFeat from C to R on an agg_feat of R on S.
"""
store_id_feat = IdentityFeature(entityset['stores']['id'])
store_count_feat = Count(store_id_feat,
parent_entity=entityset[u'régions'])
num_stores_feat = DirectFeature(store_count_feat,
child_entity=entityset['customers'])
pandas_backend = backend([num_stores_feat])
df = pandas_backend.calculate_all_features(instance_ids=[0],
time_last=None)
v = df[num_stores_feat.get_name()][0]
assert (v == 3)
def test_direct_rename(es):
# should be same behavior as test_direct_from_identity
feat = DirectFeature(base_feature=es['sessions']['device_type'],
child_entity=es['log'])
copy_feat = feat.rename("session_test")
assert feat.hash() != copy_feat.hash()
assert feat.get_name() != copy_feat.get_name()
assert feat.base_features[0].generate_name() == copy_feat.base_features[0].generate_name()
assert feat.entity == copy_feat.entity
def test_make_dfeat(entityset, backend):
f = DirectFeature(entityset['customers']['age'],
child_entity=entityset['sessions'])
pandas_backend = backend([f])
df = pandas_backend.calculate_all_features(instance_ids=[0],
time_last=None)
v = df[f.get_name()][0]
assert (v == 33)
def test_make_dfeat(entityset, backend):
f = DirectFeature(entityset['customers']['age'],
child_entity=entityset['sessions'])
pandas_backend = backend([f])
df = pandas_backend.calculate_all_features(instance_ids=[0],
time_last=None)
v = df[f.get_name()][0]
assert (v == 33)
def test_direct_from_identity(es):
device = es['sessions']['device_type']
d = DirectFeature(base_feature=device, child_entity=es['log'])
assert d.variable == device
pandas_backend = PandasBackend(es, [d])
df = pandas_backend.calculate_all_features(instance_ids=[0, 5],
time_last=None)
v = df[d.get_name()].tolist()
assert v == [0, 1]
def test_dfs_builds_on_seed_features_more_than_max_depth(es):
seed_feature_sessions = Count(es['log']["id"], es['sessions']) > 2
seed_feature_log = Hour(es['log']['datetime'])
session_agg = Last(seed_feature_log, es['sessions'])
# Depth of this feat is 2 relative to session_agg, the seed feature,
# which is greater than max_depth so it shouldn't be built
session_agg_trans = DirectFeature(Mode(session_agg, es['customers']),
es['sessions'])
dfs_obj = DeepFeatureSynthesis(
target_entity_id='sessions',
entityset=es,
agg_primitives=[Last, Count],
trans_primitives=[],
max_depth=1,
seed_features=[seed_feature_sessions, seed_feature_log])
features = dfs_obj.build_features()
assert seed_feature_sessions.get_name() in [f.get_name() for f in features]
assert session_agg.get_name() in [f.get_name() for f in features]
assert session_agg_trans.get_name() not in [f.get_name() for f in features]
def test_dfs_builds_on_seed_features_more_than_max_depth(es):
seed_feature_sessions = Count(es['log']["id"], es['sessions']) > 2
seed_feature_log = Hour(es['log']['datetime'])
session_agg = Last(seed_feature_log, es['sessions'])
# Depth of this feat is 2 relative to session_agg, the seed feature,
# which is greater than max_depth so it shouldn't be built
session_agg_trans = DirectFeature(Mode(session_agg, es['customers']),
es['sessions'])
dfs_obj = DeepFeatureSynthesis(target_entity_id='sessions',
entityset=es,
agg_primitives=[Last, Count],
trans_primitives=[],
max_depth=1,
seed_features=[seed_feature_sessions,
seed_feature_log])
features = dfs_obj.build_features()
assert seed_feature_sessions.get_name() in [f.get_name()
for f in features]
assert session_agg.get_name() in [f.get_name() for f in features]
assert session_agg_trans.get_name() not in [f.get_name()
for f in features]
def test_make_dfeat_of_agg_feat_on_self(entityset, backend):
"""
The graph looks like this:
R R = Regions, a parent of customers
|
C C = Customers, the entity we're trying to predict on
|
etc.
We're trying to calculate a DFeat from C to R on an agg_feat of R on C.
"""
customer_count_feat = Count(entityset['customers']['id'],
parent_entity=entityset[u'régions'])
num_customers_feat = DirectFeature(customer_count_feat,
child_entity=entityset['customers'])
pandas_backend = backend([num_customers_feat])
df = pandas_backend.calculate_all_features(instance_ids=[0],
time_last=None)
v = df[num_customers_feat.get_name()][0]
assert (v == 3)
def test_make_dfeat_of_agg_feat_on_self(entityset, backend):
"""
The graph looks like this:
R R = Regions, a parent of customers
|
C C = Customers, the entity we're trying to predict on
|
etc.
We're trying to calculate a DFeat from C to R on an agg_feat of R on C.
"""
customer_count_feat = Count(entityset['customers']['id'],
parent_entity=entityset[u'régions'])
num_customers_feat = DirectFeature(customer_count_feat,
child_entity=entityset['customers'])
pandas_backend = backend([num_customers_feat])
df = pandas_backend.calculate_all_features(instance_ids=[0],
time_last=None)
v = df[num_customers_feat.get_name()][0]
assert (v == 3)