def test_isin_feat(es):
isin = IsIn(es['log']['product_id'],
list_of_outputs=["toothpaste", "coke zero"])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [True, True, True, False, False, True, True, True]
v = df[isin.get_name()].values.tolist()
assert true == v
def test_isin_feat_custom(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, [Variable],
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 = ft.Feature(
es['log']['product_id'],
primitive=IsIn(list_of_outputs=["toothpaste", "coke zero"]))
features = [isin]
df = ft.calculate_feature_matrix(entityset=es,
features=features,
instance_ids=range(8))
true = [True, True, True, False, False, True, True, True]
v = df[isin.get_name()].values.tolist()
assert true == v
isin = ft.Feature(es['log']['product_id']).isin(
["toothpaste", "coke zero"])
features = [isin]
df = ft.calculate_feature_matrix(entityset=es,
features=features,
instance_ids=range(8))
true = [True, True, True, False, False, True, True, True]
v = df[isin.get_name()].values.tolist()
assert true == v
isin = ft.Feature(es['log']['value']).isin([5, 10])
features = [isin]
df = ft.calculate_feature_matrix(entityset=es,
features=features,
instance_ids=range(8))
true = [False, True, True, False, False, False, False, False]
v = df[isin.get_name()].values.tolist()
assert true == v
def test_isin_feat_custom(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_get_name(self):
return u"%s.isin(%s)" % (self.base_features[0].get_name(),
str(self.kwargs['list_of_outputs']))
IsIn = make_trans_primitive(
pd_is_in, [Variable],
Boolean,
name="is_in",
description="For each value of the base feature, checks whether it is "
"in a list that is provided.",
cls_attributes={"_get_name": isin_get_name})
isin = IsIn(es['log']['product_id'],
list_of_outputs=["toothpaste", "coke zero"])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [True, True, True, False, False, True, True, True]
v = df[isin.get_name()].values.tolist()
assert true == v
isin = Feature(es['log']['product_id']).isin(["toothpaste", "coke zero"])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [True, True, True, False, False, True, True, True]
v = df[isin.get_name()].values.tolist()
assert true == v
isin = Feature(es['log']['value']).isin([5, 10])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [False, True, True, False, False, False, False, False]
v = df[isin.get_name()].values.tolist()
assert true == v
def test_isin_feat_custom(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):
return u"%s.isin(%s)" % (self.base_features[0].get_name(),
str(self.kwargs['list_of_outputs']))
IsIn = make_trans_primitive(
pd_is_in,
[Variable],
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 = IsIn(es['log']['product_id'],
list_of_outputs=["toothpaste", "coke zero"])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [True, True, True, False, False, True, True, True]
v = df[isin.get_name()].values.tolist()
assert true == v
isin = Feature(es['log']['product_id']).isin(["toothpaste", "coke zero"])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [True, True, True, False, False, True, True, True]
v = df[isin.get_name()].values.tolist()
assert true == v
isin = Feature(es['log']['value']).isin([5, 10])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [False, True, True, False, False, False, False, False]
v = df[isin.get_name()].values.tolist()
assert true == v
def test_args_string_default():
assert IsIn().get_args_string() == ''
def test_single_args_string():
assert IsIn([1, 2, 3]).get_args_string() == ', list_of_outputs=[1, 2, 3]'
def test_deserializer_uses_common_primitive_instances_with_args(es, tmp_path):
# Single argument
scalar1 = MultiplyNumericScalar(value=1)
scalar5 = MultiplyNumericScalar(value=5)
features = ft.dfs(
entityset=es,
target_dataframe_name="products",
features_only=True,
agg_primitives=["sum"],
trans_primitives=[scalar1, scalar5],
)
scalar1_features = [
f
for f in features
if f.primitive.name == "multiply_numeric_scalar" and " * 1" in f.get_name()
]
scalar5_features = [
f
for f in features
if f.primitive.name == "multiply_numeric_scalar" and " * 5" in f.get_name()
]
# Make sure we have multiple features of each type
assert len(scalar1_features) > 1
assert len(scalar5_features) > 1
# DFS should use the the passed in primitive instance for all features
assert all([f.primitive is scalar1 for f in scalar1_features])
assert all([f.primitive is scalar5 for f in scalar5_features])
file = os.path.join(tmp_path, "features.json")
ft.save_features(features, file)
deserialized_features = ft.load_features(file)
new_scalar1_features = [
f
for f in deserialized_features
if f.primitive.name == "multiply_numeric_scalar" and " * 1" in f.get_name()
]
new_scalar5_features = [
f
for f in deserialized_features
if f.primitive.name == "multiply_numeric_scalar" and " * 5" in f.get_name()
]
# After deserialization all features that share a primitive should use the same primitive instance
new_scalar1_primitive = new_scalar1_features[0].primitive
new_scalar5_primitive = new_scalar5_features[0].primitive
assert all([f.primitive is new_scalar1_primitive for f in new_scalar1_features])
assert all([f.primitive is new_scalar5_primitive for f in new_scalar5_features])
assert new_scalar1_primitive.value == 1
assert new_scalar5_primitive.value == 5
# Test primitive with multiple args - pandas only due to primitive compatibility
if es.dataframe_type == Library.PANDAS.value:
distance_to_holiday = DistanceToHoliday(
holiday="Victoria Day", country="Canada"
)
features = ft.dfs(
entityset=es,
target_dataframe_name="customers",
features_only=True,
agg_primitives=[],
trans_primitives=[distance_to_holiday],
)
distance_features = [
f for f in features if f.primitive.name == "distance_to_holiday"
]
assert len(distance_features) > 1
# DFS should use the the passed in primitive instance for all features
assert all([f.primitive is distance_to_holiday for f in distance_features])
file = os.path.join(tmp_path, "distance_features.json")
ft.save_features(distance_features, file)
new_distance_features = ft.load_features(file)
# After deserialization all features that share a primitive should use the same primitive instance
new_distance_primitive = new_distance_features[0].primitive
assert all(
[f.primitive is new_distance_primitive for f in new_distance_features]
)
assert new_distance_primitive.holiday == "Victoria Day"
assert new_distance_primitive.country == "Canada"
# Test primitive with list arg
is_in = IsIn(list_of_outputs=[5, True, "coke zero"])
features = ft.dfs(
entityset=es,
target_dataframe_name="customers",
features_only=True,
agg_primitives=[],
trans_primitives=[is_in],
)
is_in_features = [f for f in features if f.primitive.name == "isin"]
assert len(is_in_features) > 1
# DFS should use the the passed in primitive instance for all features
assert all([f.primitive is is_in for f in is_in_features])
file = os.path.join(tmp_path, "distance_features.json")
ft.save_features(is_in_features, file)
new_is_in_features = ft.load_features(file)
# After deserialization all features that share a primitive should use the same primitive instance
new_is_in_primitive = new_is_in_features[0].primitive
assert all([f.primitive is new_is_in_primitive for f in new_is_in_features])
assert new_is_in_primitive.list_of_outputs == [5, True, "coke zero"]
def isin(self, list_of_output):
from featuretools.primitives import IsIn
return IsIn(self, list_of_outputs=list_of_output)
