def test_max_hlevel(es):
kwargs = dict(
target_entity_id='log',
entityset=es,
agg_primitives=[Count, Last],
trans_primitives=[Hour],
max_depth=-1,
)
dfs_h_n1 = DeepFeatureSynthesis(max_hlevel=-1, **kwargs)
dfs_h_0 = DeepFeatureSynthesis(max_hlevel=0, **kwargs)
dfs_h_1 = DeepFeatureSynthesis(max_hlevel=1, **kwargs)
feats_n1 = dfs_h_n1.build_features()
feats_n1 = [f.get_name() for f in feats_n1]
feats_0 = dfs_h_0.build_features()
feats_0 = [f.get_name() for f in feats_0]
feats_1 = dfs_h_1.build_features()
feats_1 = [f.get_name() for f in feats_1]
customer_log = Last(es['log']['value'], es['customers'])
session_log = Last(es['log']['value'], es['sessions'])
log_customer_log = Feature(customer_log, es['log'])
log_session_log = Feature(session_log, es['log'])
assert log_customer_log.get_name() in feats_n1
assert log_session_log.get_name() in feats_n1
assert log_customer_log.get_name() not in feats_1
assert log_session_log.get_name() in feats_1
assert log_customer_log.get_name() not in feats_0
assert log_session_log.get_name() not in feats_0
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_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_get_depth(es):
es = make_ecommerce_entityset()
f = Feature(es['log']['value'])
g = Feature(es['log']['value'])
agg1 = Last(f, es['sessions'])
agg2 = Last(agg1, es['customers'])
d1 = Feature(agg2, es['sessions'])
d2 = Feature(d1, es['log'])
assert d2.get_depth() == 4
# Make sure this works if we pass in two of the same
# feature. This came up when user supplied duplicates
# in the seed_features of DFS.
assert d2.get_depth(stop_at=[f, g]) == 4
assert d2.get_depth(stop_at=[f, g, agg1]) == 3
assert d2.get_depth(stop_at=[f, g, agg1]) == 3
assert d2.get_depth(stop_at=[f, g, agg2]) == 2
assert d2.get_depth(stop_at=[f, g, d1]) == 1
assert d2.get_depth(stop_at=[f, g, d2]) == 0
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]
def test_return_type_inference_numeric_time_index(es_numeric):
last = Last(es_numeric["log"]["datetime"], es_numeric["customers"])
assert last.variable_type == Numeric
def test_return_type_inference_datetime_time_index(es):
last = Last(es["log"]["datetime"], es["customers"])
assert last.variable_type == Datetime