def test_make_transform_sets_kwargs_correctly(es):
def pd_is_in(array, list_of_outputs=None):
if list_of_outputs is None:
list_of_outputs = []
return pd.Series(array).isin(list_of_outputs)
def isin_generate_name(self, base_feature_names):
return u"%s.isin(%s)" % (base_feature_names[0],
str(self.kwargs['list_of_outputs']))
IsIn = make_trans_primitive(
pd_is_in, [ColumnSchema()],
ColumnSchema(logical_type=Boolean),
name="is_in",
description="For each value of the base feature, checks whether it is "
"in a list that is provided.",
cls_attributes={"generate_name": isin_generate_name})
isin_1_list = ["toothpaste", "coke_zero"]
isin_1_base_f = Feature(es['log'].ww['product_id'])
isin_1 = Feature(isin_1_base_f,
primitive=IsIn(list_of_outputs=isin_1_list))
isin_2_list = ["coke_zero"]
isin_2_base_f = Feature(es['log'].ww['session_id'])
isin_2 = Feature(isin_2_base_f,
primitive=IsIn(list_of_outputs=isin_2_list))
assert isin_1_base_f == isin_1.base_features[0]
assert isin_1_list == isin_1.primitive.kwargs['list_of_outputs']
assert isin_2_base_f == isin_2.base_features[0]
assert isin_2_list == isin_2.primitive.kwargs['list_of_outputs']
def test_feature_takes_timedelta_string(es):
feature = Feature(
Feature(es["log"].ww["id"]),
parent_dataframe_name="customers",
use_previous="1 day",
primitive=Count,
)
assert feature.use_previous == Timedelta(1, "d")
def test_encode_features_topn(entityset):
topn = Feature(entityset['log']['product_id'],
parent_entity=entityset['customers'],
primitive=NMostCommon(n=3))
features, feature_defs = dfs(entityset=entityset,
instance_ids=[0, 1, 2],
target_entity="customers",
agg_primitives=[NMostCommon(n=3)])
features_enc, feature_defs_enc = encode_features(features,
feature_defs,
include_unknown=True)
assert topn.hash() in [feat.hash() for feat in feature_defs_enc]
for name in topn.get_feature_names():
assert name in features_enc.columns
def test_encode_features_topn(pd_es):
topn = Feature(Feature(pd_es['log'].ww['product_id']),
parent_dataframe_name='customers',
primitive=NMostCommon(n=3))
features, feature_defs = dfs(entityset=pd_es,
instance_ids=[0, 1, 2],
target_dataframe_name="customers",
agg_primitives=[NMostCommon(n=3)])
features_enc, feature_defs_enc = encode_features(features,
feature_defs,
include_unknown=True)
assert topn.unique_name() in [
feat.unique_name() for feat in feature_defs_enc
]
for name in topn.get_feature_names():
assert name in features_enc.columns
assert features_enc.columns.tolist().count(name) == 1
def test_direct_of_multi_output_transform_feat(es):
class TestTime(TransformPrimitive):
name = "test_time"
input_types = [Datetime]
return_type = Numeric
number_output_features = 6
def get_function(self):
def test_f(x):
times = pd.Series(x)
units = ["year", "month", "day", "hour", "minute", "second"]
return [times.apply(lambda x: getattr(x, unit)) for unit in units]
return test_f
join_time_split = Feature(es["customers"]["signup_date"],
primitive=TestTime)
alt_features = [Feature(es["customers"]["signup_date"], primitive=Year),
Feature(es["customers"]["signup_date"], primitive=Month),
Feature(es["customers"]["signup_date"], primitive=Day),
Feature(es["customers"]["signup_date"], primitive=Hour),
Feature(es["customers"]["signup_date"], primitive=Minute),
Feature(es["customers"]["signup_date"], primitive=Second)]
fm, fl = dfs(
entityset=es,
target_entity="sessions",
trans_primitives=[TestTime, Year, Month, Day, Hour, Minute, Second])
# Get column names of for multi feature and normal features
subnames = DirectFeature(join_time_split, es["sessions"]).get_feature_names()
altnames = [DirectFeature(f, es["sessions"]).get_name() for f in alt_features]
# Check values are equal between
for col1, col2 in zip(subnames, altnames):
assert (fm[col1] == fm[col2]).all()
def test_direct_rename_multioutput(es):
n_common = Feature(es['log'].ww['product_id'],
parent_dataframe_name='customers',
primitive=NMostCommon(n=2))
feat = DirectFeature(n_common, 'sessions')
copy_feat = feat.rename("session_test")
assert feat.unique_name() != copy_feat.unique_name()
assert feat.get_name() != copy_feat.get_name()
assert feat.base_features[0].generate_name(
) == copy_feat.base_features[0].generate_name()
assert feat.dataframe_name == copy_feat.dataframe_name
def test_direct_rename_multioutput(es):
n_common = Feature(
es["log"].ww["product_id"],
parent_dataframe_name="customers",
primitive=NMostCommon(n=2),
)
feat = DirectFeature(n_common, "sessions")
copy_feat = feat.rename("session_test")
assert feat.unique_name() != copy_feat.unique_name()
assert feat.get_name() != copy_feat.get_name()
assert (feat.base_features[0].generate_name() ==
copy_feat.base_features[0].generate_name())
assert feat.dataframe_name == copy_feat.dataframe_name
def test_direct_from_identity(es):
device = Feature(es['sessions'].ww['device_type'])
d = DirectFeature(base_feature=device, child_dataframe_name='log')
feature_set = FeatureSet([d])
calculator = FeatureSetCalculator(es,
feature_set=feature_set,
time_last=None)
df = calculator.run(np.array([0, 5]))
df = to_pandas(df, index='id', sort_index=True)
v = df[d.get_name()].tolist()
if es.dataframe_type == Library.KOALAS.value:
expected = ['0', '1']
else:
expected = [0, 1]
assert v == expected
def test_direct_from_identity(es):
device = Feature(es["sessions"].ww["device_type"])
d = DirectFeature(base_feature=device, child_dataframe_name="log")
feature_set = FeatureSet([d])
calculator = FeatureSetCalculator(es,
feature_set=feature_set,
time_last=None)
df = calculator.run(np.array([0, 5]))
df = to_pandas(df, index="id", sort_index=True)
v = df[d.get_name()].tolist()
if es.dataframe_type == Library.SPARK.value:
expected = ["0", "1"]
else:
expected = [0, 1]
assert v == expected
def test_direct_of_multi_output_transform_feat(es):
# TODO: Update to work with Dask and Spark
if es.dataframe_type != Library.PANDAS.value:
pytest.xfail("Custom primitive is not compatible with Dask or Spark")
class TestTime(TransformPrimitive):
name = "test_time"
input_types = [ColumnSchema(logical_type=Datetime)]
return_type = ColumnSchema(semantic_tags={"numeric"})
number_output_features = 6
def get_function(self):
def test_f(x):
times = pd.Series(x)
units = ["year", "month", "day", "hour", "minute", "second"]
return [
times.apply(lambda x: getattr(x, unit)) for unit in units
]
return test_f
base_feature = IdentityFeature(es["customers"].ww["signup_date"])
join_time_split = Feature(base_feature, primitive=TestTime)
alt_features = [
Feature(base_feature, primitive=Year),
Feature(base_feature, primitive=Month),
Feature(base_feature, primitive=Day),
Feature(base_feature, primitive=Hour),
Feature(base_feature, primitive=Minute),
Feature(base_feature, primitive=Second),
]
fm, fl = dfs(
entityset=es,
target_dataframe_name="sessions",
trans_primitives=[TestTime, Year, Month, Day, Hour, Minute, Second],
)
# Get column names of for multi feature and normal features
subnames = DirectFeature(join_time_split, "sessions").get_feature_names()
altnames = [DirectFeature(f, "sessions").get_name() for f in alt_features]
# Check values are equal between
for col1, col2 in zip(subnames, altnames):
assert (fm[col1] == fm[col2]).all()
def test_feature_takes_timedelta_string(es):
feature = Feature(Feature(es['log'].ww['id']), parent_dataframe_name='customers',
use_previous="1 day", primitive=Count)
assert feature.use_previous == Timedelta(1, 'd')