def test_feature_trie_with_needs_full_entity(diamond_es):
pd_es = diamond_es
amount = ft.IdentityFeature(pd_es['transactions']['amount'])
path_through_customers = backward_path(
pd_es, ['regions', 'customers', 'transactions'])
agg = ft.AggregationFeature(amount,
pd_es['regions'],
primitive=ft.primitives.Mean,
relationship_path=path_through_customers)
trans_of_agg = ft.TransformFeature(agg, ft.primitives.CumSum)
path_through_stores = backward_path(pd_es,
['regions', 'stores', 'transactions'])
trans = ft.TransformFeature(amount, ft.primitives.CumSum)
agg_of_trans = ft.AggregationFeature(trans,
pd_es['regions'],
primitive=ft.primitives.Mean,
relationship_path=path_through_stores)
features = [agg, trans_of_agg, agg_of_trans]
feature_set = FeatureSet(features)
trie = feature_set.feature_trie
assert trie.value == \
(True, {agg.unique_name(), trans_of_agg.unique_name()}, {agg_of_trans.unique_name()})
assert trie.get_node(path_through_customers).value == \
(True, {amount.unique_name()}, set())
assert trie.get_node(path_through_customers[:1]).value == (True, set(),
set())
assert trie.get_node(path_through_stores).value == \
(True, {amount.unique_name(), trans.unique_name()}, set())
assert trie.get_node(path_through_stores[:1]).value == (False, set(),
set())
def load_feature_plots():
es = ft.demo.load_mock_customer(return_entityset=True)
path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'getting_started/graphs/')
agg_feat = ft.AggregationFeature(ft.IdentityFeature(es['sessions'].ww['session_id']),
'customers', ft.primitives.Count)
trans_feat = ft.TransformFeature(ft.IdentityFeature(es['customers'].ww['join_date']), ft.primitives.TimeSincePrevious)
demo_feat = ft.AggregationFeature(ft.TransformFeature(ft.IdentityFeature(es['transactions'].ww['transaction_time']),
ft.primitives.Weekday),
'sessions', ft.primitives.Mode)
ft.graph_feature(agg_feat, to_file=os.path.join(path, 'agg_feat.dot'))
ft.graph_feature(trans_feat, to_file=os.path.join(path, 'trans_feat.dot'))
ft.graph_feature(demo_feat, to_file=os.path.join(path, 'demo_feat.dot'))
def test_feature_trie_with_needs_full_entity_direct(es):
value = ft.IdentityFeature(es['log']['value'], )
agg = ft.AggregationFeature(value,
es['sessions'],
primitive=ft.primitives.Mean)
agg_of_agg = ft.AggregationFeature(agg,
es['customers'],
primitive=ft.primitives.Sum)
direct = ft.DirectFeature(agg_of_agg, es['sessions'])
trans = ft.TransformFeature(direct, ft.primitives.CumSum)
features = [trans, agg]
feature_set = FeatureSet(features)
trie = feature_set.feature_trie
assert trie.value == \
(True, {direct.unique_name(), trans.unique_name()}, {agg.unique_name()})
assert trie.get_node(agg.relationship_path).value == \
(False, set(), {value.unique_name()})
parent_node = trie.get_node(direct.relationship_path)
assert parent_node.value == (True, {agg_of_agg.unique_name()}, set())
child_through_parent_node = parent_node.get_node(
agg_of_agg.relationship_path)
assert child_through_parent_node.value == (True, {agg.unique_name()},
set())
assert child_through_parent_node.get_node(agg.relationship_path).value == \
(True, {value.unique_name()}, set())
def test_base_features_not_in_list(es):
max_primitive = Max()
mult_primitive = MultiplyNumericScalar(value=2)
value = ft.IdentityFeature(es["log"].ww["value"])
value_x2 = ft.TransformFeature(value, mult_primitive)
max_feat = ft.AggregationFeature(value_x2, "sessions", max_primitive)
dictionary = {
"ft_version": ft.__version__,
"schema_version": SCHEMA_VERSION,
"entityset": es.to_dictionary(),
"feature_list": [max_feat.unique_name()],
"feature_definitions": {
max_feat.unique_name(): max_feat.to_dictionary(),
value_x2.unique_name(): value_x2.to_dictionary(),
value.unique_name(): value.to_dictionary(),
},
}
dictionary["primitive_definitions"] = {
"0": serialize_primitive(max_primitive),
"1": serialize_primitive(mult_primitive),
}
dictionary["feature_definitions"][
max_feat.unique_name()]["arguments"]["primitive"] = "0"
dictionary["feature_definitions"][
value_x2.unique_name()]["arguments"]["primitive"] = "1"
deserializer = FeaturesDeserializer(dictionary)
expected = [max_feat]
assert expected == deserializer.to_list()
def test_serialized_renamed_features(es):
def serialize_name_unchanged(original):
new_name = 'MyFeature'
original_names = original.get_feature_names()
renamed = original.rename(new_name)
new_names = [new_name] if len(original_names) == 1 else [
new_name + '[{}]'.format(i) for i in range(len(original_names))
]
check_names(renamed, new_name, new_names)
serializer = FeaturesSerializer([renamed])
serialized = serializer.to_dict()
deserializer = FeaturesDeserializer(serialized)
deserialized = deserializer.to_list()[0]
check_names(deserialized, new_name, new_names)
identity_original = ft.IdentityFeature(es['log'].ww['value'])
assert identity_original.get_name() == 'value'
value = ft.IdentityFeature(es['log'].ww['value'])
primitive = ft.primitives.Max()
agg_original = ft.AggregationFeature(value, 'customers', primitive)
assert agg_original.get_name() == 'MAX(log.value)'
direct_original = ft.DirectFeature(
ft.IdentityFeature(es['customers'].ww['age']), 'sessions')
assert direct_original.get_name() == 'customers.age'
primitive = ft.primitives.MultiplyNumericScalar(value=2)
transform_original = ft.TransformFeature(value, primitive)
assert transform_original.get_name() == 'value * 2'
zipcode = ft.IdentityFeature(es['log'].ww['zipcode'])
primitive = CumSum()
groupby_original = ft.feature_base.GroupByTransformFeature(
value, primitive, zipcode)
assert groupby_original.get_name() == 'CUM_SUM(value) by zipcode'
multioutput_original = ft.Feature(es['log'].ww['product_id'],
parent_dataframe_name='customers',
primitive=NMostCommon(n=2))
assert multioutput_original.get_name(
) == 'N_MOST_COMMON(log.product_id, n=2)'
featureslice_original = ft.feature_base.FeatureOutputSlice(
multioutput_original, 0)
assert featureslice_original.get_name(
) == 'N_MOST_COMMON(log.product_id, n=2)[0]'
feature_type_list = [
identity_original, agg_original, direct_original, transform_original,
groupby_original, multioutput_original, featureslice_original
]
for feature_type in feature_type_list:
serialize_name_unchanged(feature_type)
def test_feature_trie_with_needs_full_dataframe(diamond_es):
pd_es = diamond_es
amount = ft.IdentityFeature(pd_es["transactions"].ww["amount"])
path_through_customers = backward_path(
pd_es, ["regions", "customers", "transactions"]
)
agg = ft.AggregationFeature(
amount,
"regions",
primitive=ft.primitives.Mean,
relationship_path=path_through_customers,
)
trans_of_agg = ft.TransformFeature(agg, ft.primitives.CumSum)
path_through_stores = backward_path(pd_es, ["regions", "stores", "transactions"])
trans = ft.TransformFeature(amount, ft.primitives.CumSum)
agg_of_trans = ft.AggregationFeature(
trans,
"regions",
primitive=ft.primitives.Mean,
relationship_path=path_through_stores,
)
features = [agg, trans_of_agg, agg_of_trans]
feature_set = FeatureSet(features)
trie = feature_set.feature_trie
assert trie.value == (
True,
{agg.unique_name(), trans_of_agg.unique_name()},
{agg_of_trans.unique_name()},
)
assert trie.get_node(path_through_customers).value == (
True,
{amount.unique_name()},
set(),
)
assert trie.get_node(path_through_customers[:1]).value == (True, set(), set())
assert trie.get_node(path_through_stores).value == (
True,
{amount.unique_name(), trans.unique_name()},
set(),
)
assert trie.get_node(path_through_stores[:1]).value == (False, set(), set())
def load_feature_plots():
es = ft.demo.load_mock_customer(return_entityset=True)
path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'automated_feature_engineering/graphs/')
agg_feat = ft.AggregationFeature(es['sessions']['session_id'],
es['customers'], ft.primitives.Count)
trans_feat = ft.TransformFeature(es['customers']['join_date'],
ft.primitives.TimeSincePrevious)
ft.graph_feature(agg_feat, to_file=os.path.join(path, 'agg_feat.dot'))
ft.graph_feature(trans_feat, to_file=os.path.join(path, 'trans_feat.dot'))
def test_feature_trie_without_needs_full_entity(diamond_es):
es = diamond_es
country_name = ft.IdentityFeature(es['countries']['name'])
direct_name = ft.DirectFeature(country_name, es['regions'])
amount = ft.IdentityFeature(es['transactions']['amount'])
path_through_customers = backward_path(
es, ['regions', 'customers', 'transactions'])
through_customers = ft.AggregationFeature(
amount,
es['regions'],
primitive=ft.primitives.Mean,
relationship_path=path_through_customers)
path_through_stores = backward_path(es,
['regions', 'stores', 'transactions'])
through_stores = ft.AggregationFeature(
amount,
es['regions'],
primitive=ft.primitives.Mean,
relationship_path=path_through_stores)
customers_to_transactions = backward_path(es,
['customers', 'transactions'])
customers_mean = ft.AggregationFeature(
amount,
es['customers'],
primitive=ft.primitives.Mean,
relationship_path=customers_to_transactions)
negation = ft.TransformFeature(customers_mean, ft.primitives.Negate)
regions_to_customers = backward_path(es, ['regions', 'customers'])
mean_of_mean = ft.AggregationFeature(
negation,
es['regions'],
primitive=ft.primitives.Mean,
relationship_path=regions_to_customers)
features = [direct_name, through_customers, through_stores, mean_of_mean]
feature_set = FeatureSet(features)
trie = feature_set.feature_trie
assert trie.value == \
(False, set(), {f.unique_name() for f in features})
assert trie.get_node(direct_name.relationship_path).value == \
(False, set(), {country_name.unique_name()})
assert trie.get_node(regions_to_customers).value == \
(False, set(), {negation.unique_name(), customers_mean.unique_name()})
regions_to_stores = backward_path(es, ['regions', 'stores'])
assert trie.get_node(regions_to_stores).value == (False, set(), set())
assert trie.get_node(path_through_customers).value == \
(False, set(), {amount.unique_name()})
assert trie.get_node(path_through_stores).value == \
(False, set(), {amount.unique_name()})
def test_serialization(es):
value = ft.IdentityFeature(es['log']['value'])
primitive = ft.primitives.MultiplyNumericScalar(value=2)
value_x2 = ft.TransformFeature(value, primitive)
dictionary = {
'base_features': [value.unique_name()],
'primitive': serialize_primitive(primitive),
}
assert dictionary == value_x2.get_arguments()
assert value_x2 == \
ft.TransformFeature.from_dictionary(dictionary, es,
{value.unique_name(): value},
PrimitivesDeserializer())
def test_base_features_not_in_list(es):
value = ft.IdentityFeature(es["log"].ww["value"])
value_x2 = ft.TransformFeature(
value, ft.primitives.MultiplyNumericScalar(value=2))
max_feat = ft.AggregationFeature(value_x2, "sessions", ft.primitives.Max)
dictionary = {
"ft_version": ft.__version__,
"schema_version": SCHEMA_VERSION,
"entityset": es.to_dictionary(),
"feature_list": [max_feat.unique_name()],
"feature_definitions": {
max_feat.unique_name(): max_feat.to_dictionary(),
value_x2.unique_name(): value_x2.to_dictionary(),
value.unique_name(): value.to_dictionary(),
},
}
deserializer = FeaturesDeserializer(dictionary)
expected = [max_feat]
assert expected == deserializer.to_list()
def test_base_features_not_in_list(es):
value = ft.IdentityFeature(es['log']['value'])
value_x2 = ft.TransformFeature(value,
ft.primitives.MultiplyNumericScalar(value=2))
max_feat = ft.AggregationFeature(value_x2, es['sessions'], ft.primitives.Max)
dictionary = {
'ft_version': ft.__version__,
'schema_version': SCHEMA_VERSION,
'entityset': es.to_dictionary(),
'feature_list': [max_feat.unique_name()],
'feature_definitions': {
max_feat.unique_name(): max_feat.to_dictionary(),
value_x2.unique_name(): value_x2.to_dictionary(),
value.unique_name(): value.to_dictionary(),
}
}
deserializer = FeaturesDeserializer(dictionary)
expected = [max_feat]
assert expected == deserializer.to_list()
def test_serialized_renamed_features(es):
def serialize_name_unchanged(original):
renamed = original.rename('MyFeature')
assert renamed.get_name() == 'MyFeature'
serializer = FeaturesSerializer([renamed])
serialized = serializer.to_dict()
deserializer = FeaturesDeserializer(serialized)
deserialized = deserializer.to_list()[0]
assert deserialized.get_name() == 'MyFeature'
identity_original = ft.IdentityFeature(es['log']['value'])
assert identity_original.get_name() == 'value'
value = ft.IdentityFeature(es['log']['value'])
primitive = ft.primitives.Max()
agg_original = ft.AggregationFeature(value, es['customers'], primitive)
assert agg_original.get_name() == 'MAX(log.value)'
direct_original = ft.DirectFeature(es['customers']['age'], es['sessions'])
assert direct_original.get_name() == 'customers.age'
primitive = ft.primitives.MultiplyNumericScalar(value=2)
transform_original = ft.TransformFeature(value, primitive)
assert transform_original.get_name() == 'value * 2'
zipcode = ft.IdentityFeature(es['log']['zipcode'])
primitive = CumSum()
groupby_original = ft.feature_base.GroupByTransformFeature(
value, primitive, zipcode)
assert groupby_original.get_name() == 'CUM_SUM(value) by zipcode'
feature_type_list = [
identity_original, agg_original, direct_original, transform_original,
groupby_original
]
for feature_type in feature_type_list:
serialize_name_unchanged(feature_type)
def test_base_features_not_in_list(es):
value = ft.IdentityFeature(es['log'].ww['value'])
value_x2 = ft.TransformFeature(
value, ft.primitives.MultiplyNumericScalar(value=2))
max_feature = ft.AggregationFeature(value_x2, 'sessions',
ft.primitives.Max)
features = [max_feature]
serializer = FeaturesSerializer(features)
expected = {
'ft_version': ft.__version__,
'schema_version': SCHEMA_VERSION,
'entityset': es.to_dictionary(),
'feature_list': [max_feature.unique_name()],
'feature_definitions': {
max_feature.unique_name(): max_feature.to_dictionary(),
value_x2.unique_name(): value_x2.to_dictionary(),
value.unique_name(): value.to_dictionary(),
}
}
_compare_feature_dicts(expected, serializer.to_dict())
def test_relationship_path(es):
f = ft.TransformFeature(es['log']['datetime'], Hour)
assert len(f.relationship_path) == 0
def test_serialized_renamed_features(es):
def serialize_name_unchanged(original):
new_name = "MyFeature"
original_names = original.get_feature_names()
renamed = original.rename(new_name)
new_names = (
[new_name]
if len(original_names) == 1
else [new_name + "[{}]".format(i) for i in range(len(original_names))]
)
check_names(renamed, new_name, new_names)
serializer = FeaturesSerializer([renamed])
serialized = serializer.to_dict()
deserializer = FeaturesDeserializer(serialized)
deserialized = deserializer.to_list()[0]
check_names(deserialized, new_name, new_names)
identity_original = ft.IdentityFeature(es["log"].ww["value"])
assert identity_original.get_name() == "value"
value = ft.IdentityFeature(es["log"].ww["value"])
primitive = ft.primitives.Max()
agg_original = ft.AggregationFeature(value, "customers", primitive)
assert agg_original.get_name() == "MAX(log.value)"
direct_original = ft.DirectFeature(
ft.IdentityFeature(es["customers"].ww["age"]), "sessions"
)
assert direct_original.get_name() == "customers.age"
primitive = ft.primitives.MultiplyNumericScalar(value=2)
transform_original = ft.TransformFeature(value, primitive)
assert transform_original.get_name() == "value * 2"
zipcode = ft.IdentityFeature(es["log"].ww["zipcode"])
primitive = CumSum()
groupby_original = ft.feature_base.GroupByTransformFeature(
value, primitive, zipcode
)
assert groupby_original.get_name() == "CUM_SUM(value) by zipcode"
multioutput_original = ft.Feature(
es["log"].ww["product_id"],
parent_dataframe_name="customers",
primitive=NMostCommon(n=2),
)
assert multioutput_original.get_name() == "N_MOST_COMMON(log.product_id, n=2)"
featureslice_original = ft.feature_base.FeatureOutputSlice(multioutput_original, 0)
assert featureslice_original.get_name() == "N_MOST_COMMON(log.product_id, n=2)[0]"
feature_type_list = [
identity_original,
agg_original,
direct_original,
transform_original,
groupby_original,
multioutput_original,
featureslice_original,
]
for feature_type in feature_type_list:
serialize_name_unchanged(feature_type)
def test_feature_trie_without_needs_full_dataframe(diamond_es):
es = diamond_es
country_name = ft.IdentityFeature(es["countries"].ww["name"])
direct_name = ft.DirectFeature(country_name, "regions")
amount = ft.IdentityFeature(es["transactions"].ww["amount"])
path_through_customers = backward_path(es, ["regions", "customers", "transactions"])
through_customers = ft.AggregationFeature(
amount,
"regions",
primitive=ft.primitives.Mean,
relationship_path=path_through_customers,
)
path_through_stores = backward_path(es, ["regions", "stores", "transactions"])
through_stores = ft.AggregationFeature(
amount,
"regions",
primitive=ft.primitives.Mean,
relationship_path=path_through_stores,
)
customers_to_transactions = backward_path(es, ["customers", "transactions"])
customers_mean = ft.AggregationFeature(
amount,
"customers",
primitive=ft.primitives.Mean,
relationship_path=customers_to_transactions,
)
negation = ft.TransformFeature(customers_mean, ft.primitives.Negate)
regions_to_customers = backward_path(es, ["regions", "customers"])
mean_of_mean = ft.AggregationFeature(
negation,
"regions",
primitive=ft.primitives.Mean,
relationship_path=regions_to_customers,
)
features = [direct_name, through_customers, through_stores, mean_of_mean]
feature_set = FeatureSet(features)
trie = feature_set.feature_trie
assert trie.value == (False, set(), {f.unique_name() for f in features})
assert trie.get_node(direct_name.relationship_path).value == (
False,
set(),
{country_name.unique_name()},
)
assert trie.get_node(regions_to_customers).value == (
False,
set(),
{negation.unique_name(), customers_mean.unique_name()},
)
regions_to_stores = backward_path(es, ["regions", "stores"])
assert trie.get_node(regions_to_stores).value == (False, set(), set())
assert trie.get_node(path_through_customers).value == (
False,
set(),
{amount.unique_name()},
)
assert trie.get_node(path_through_stores).value == (
False,
set(),
{amount.unique_name()},
)
