def test_allowed_paths(es):
kwargs = dict(
target_entity_id='customers',
entityset=es,
agg_primitives=[Last],
trans_primitives=[],
max_depth=2,
seed_features=[]
)
dfs_unconstrained = DeepFeatureSynthesis(**kwargs)
features_unconstrained = dfs_unconstrained.build_features()
unconstrained_names = [f.get_name() for f in features_unconstrained]
customers_session_feat = Last(es['sessions']['device_type'],
es['customers'])
customers_session_log_feat = Last(es['log']['value'], es['customers'])
assert customers_session_feat.get_name() in unconstrained_names
assert customers_session_log_feat.get_name() in unconstrained_names
dfs_constrained = DeepFeatureSynthesis(allowed_paths=[['customers',
'sessions']],
**kwargs)
features = dfs_constrained.build_features()
names = [f.get_name() for f in features]
assert customers_session_feat.get_name() in names
assert customers_session_log_feat.get_name() not in names
def test_seed_features(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'])
dfs_obj = DeepFeatureSynthesis(
target_entity_id='sessions',
entityset=es,
agg_primitives=[Last],
trans_primitives=[],
max_depth=2,
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]
def test_allowed_paths(es):
kwargs = dict(target_entity_id='customers',
entityset=es,
agg_primitives=[Last],
trans_primitives=[],
max_depth=2,
seed_features=[])
dfs_unconstrained = DeepFeatureSynthesis(**kwargs)
features_unconstrained = dfs_unconstrained.build_features()
unconstrained_names = [f.get_name() for f in features_unconstrained]
customers_session_feat = Last(es['sessions']['device_type'],
es['customers'])
customers_session_log_feat = Last(es['log']['value'], es['customers'])
assert customers_session_feat.get_name() in unconstrained_names
assert customers_session_log_feat.get_name() in unconstrained_names
dfs_constrained = DeepFeatureSynthesis(
allowed_paths=[['customers', 'sessions']], **kwargs)
features = dfs_constrained.build_features()
names = [f.get_name() for f in features]
assert customers_session_feat.get_name() in names
assert customers_session_log_feat.get_name() not in names
def test_seed_features(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'])
dfs_obj = DeepFeatureSynthesis(target_entity_id='sessions',
entityset=es,
agg_primitives=[Last],
trans_primitives=[],
max_depth=2,
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]
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(Count(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]
