def test_feature_set_ingest_throws_exception_if_kafka_down(
self, dataframe, test_client, exception, mocker):
test_client.set_project("project1")
driver_fs = FeatureSet(
"driver-feature-set",
source=KafkaSource(brokers="localhost:4412", topic="test"),
)
driver_fs.add(Feature(name="feature_1", dtype=ValueType.FLOAT))
driver_fs.add(Feature(name="feature_2", dtype=ValueType.STRING))
driver_fs.add(Feature(name="feature_3", dtype=ValueType.INT64))
driver_fs.add(Entity(name="entity_id", dtype=ValueType.INT64))
# Register with Feast core
test_client.apply(driver_fs)
driver_fs = driver_fs.to_proto()
driver_fs.meta.status = FeatureSetStatusProto.STATUS_READY
mocker.patch.object(
test_client._core_service_stub,
"GetFeatureSet",
return_value=GetFeatureSetResponse(feature_set=driver_fs),
)
with pytest.raises(exception):
test_client.ingest("driver-feature-set", dataframe)
def test_apply_feature_set_success(self, client):
# Create Feature Sets
fs1 = FeatureSet("my-feature-set-1")
fs1.add(Feature(name="fs1-my-feature-1", dtype=ValueType.INT64))
fs1.add(Feature(name="fs1-my-feature-2", dtype=ValueType.STRING))
fs1.add(Entity(name="fs1-my-entity-1", dtype=ValueType.INT64))
fs2 = FeatureSet("my-feature-set-2")
fs2.add(Feature(name="fs2-my-feature-1", dtype=ValueType.STRING_LIST))
fs2.add(Feature(name="fs2-my-feature-2", dtype=ValueType.BYTES_LIST))
fs2.add(Entity(name="fs2-my-entity-1", dtype=ValueType.INT64))
# Register Feature Set with Core
client.apply(fs1)
client.apply(fs2)
feature_sets = client.list_feature_sets()
# List Feature Sets
assert (
len(feature_sets) == 2
and feature_sets[0].name == "my-feature-set-1"
and feature_sets[0].features[0].name == "fs1-my-feature-1"
and feature_sets[0].features[0].dtype == ValueType.INT64
and feature_sets[1].features[1].dtype == ValueType.BYTES_LIST
)
def test_feature_set_ingest_fail_if_pending(self, dataframe, exception,
test_client, mocker):
with pytest.raises(exception):
test_client.set_project("project1")
driver_fs = FeatureSet(
"driver-feature-set",
source=KafkaSource(brokers="kafka:9092", topic="test"),
)
driver_fs.add(Feature(name="feature_1", dtype=ValueType.FLOAT))
driver_fs.add(Feature(name="feature_2", dtype=ValueType.STRING))
driver_fs.add(Feature(name="feature_3", dtype=ValueType.INT64))
driver_fs.add(Entity(name="entity_id", dtype=ValueType.INT64))
# Register with Feast core
test_client.apply(driver_fs)
driver_fs = driver_fs.to_proto()
driver_fs.meta.status = FeatureSetStatusProto.STATUS_PENDING
mocker.patch.object(
test_client._core_service_stub,
"GetFeatureSet",
return_value=GetFeatureSetResponse(feature_set=driver_fs),
)
# Need to create a mock producer
with patch("feast.client.get_producer"):
# Ingest data into Feast
test_client.ingest("driver-feature-set", dataframe, timeout=1)
def test_feature_set_ingest_success(self, dataframe, client, mocker):
client.set_project("project1")
driver_fs = FeatureSet("driver-feature-set",
source=KafkaSource(brokers="kafka:9092",
topic="test"))
driver_fs.add(Feature(name="feature_1", dtype=ValueType.FLOAT))
driver_fs.add(Feature(name="feature_2", dtype=ValueType.STRING))
driver_fs.add(Feature(name="feature_3", dtype=ValueType.INT64))
driver_fs.add(Entity(name="entity_id", dtype=ValueType.INT64))
# Register with Feast core
client.apply(driver_fs)
driver_fs = driver_fs.to_proto()
driver_fs.meta.status = FeatureSetStatusProto.STATUS_READY
mocker.patch.object(
client._core_service_stub,
"GetFeatureSet",
return_value=GetFeatureSetResponse(feature_set=driver_fs),
)
# Need to create a mock producer
with patch("feast.client.get_producer") as mocked_queue:
# Ingest data into Feast
client.ingest("driver-feature-set", dataframe)
def test_feature_set_ingest_success(self, dataframe, client, mocker):
driver_fs = FeatureSet("driver-feature-set")
driver_fs.add(Feature(name="feature_1", dtype=ValueType.FLOAT))
driver_fs.add(Feature(name="feature_2", dtype=ValueType.STRING))
driver_fs.add(Feature(name="feature_3", dtype=ValueType.INT64))
driver_fs.add(Entity(name="entity_id", dtype=ValueType.INT64))
driver_fs.source = KafkaSource(topic="feature-topic",
brokers="127.0.0.1")
client._message_producer = MagicMock()
client._message_producer.produce = MagicMock()
# Register with Feast core
client.apply(driver_fs)
mocker.patch.object(
client._core_service_stub,
"GetFeatureSet",
return_value=GetFeatureSetResponse(
feature_set=driver_fs.to_proto()),
)
# Ingest data into Feast
client.ingest("driver-feature-set", dataframe=dataframe)
def test_unequal_feature_based_on_labels():
f1 = Feature(name="feature-1", dtype=ValueType.INT64, labels={"k1": "v1"})
f2 = Feature(name="feature-1", dtype=ValueType.INT64, labels={"k1": "v1"})
assert f1 == f2
f3 = Feature(name="feature-1", dtype=ValueType.INT64)
assert f1 != f3
f4 = Feature(name="feature-1",
dtype=ValueType.INT64,
labels={"k1": "notv1"})
assert f1 != f4
def test_import_tfx_schema(self):
tests_folder = pathlib.Path(__file__).parent
test_input_schema_json = open(tests_folder / "data" /
"tensorflow_metadata" /
"bikeshare_schema.json").read()
test_input_schema = schema_pb2.Schema()
json_format.Parse(test_input_schema_json, test_input_schema)
feature_set = FeatureSet(
name="bikeshare",
entities=[Entity(name="station_id", dtype=ValueType.INT64)],
features=[
Feature(name="name", dtype=ValueType.STRING),
Feature(name="status", dtype=ValueType.STRING),
Feature(name="latitude", dtype=ValueType.FLOAT),
Feature(name="longitude", dtype=ValueType.FLOAT),
Feature(name="location", dtype=ValueType.STRING),
],
)
# Before update
for entity in feature_set.entities:
assert entity.presence is None
assert entity.shape is None
for feature in feature_set.features:
assert feature.presence is None
assert feature.shape is None
assert feature.string_domain is None
assert feature.float_domain is None
assert feature.int_domain is None
feature_set.import_tfx_schema(test_input_schema)
# After update
for entity in feature_set.entities:
assert entity.presence is not None
assert entity.shape is not None
for feature in feature_set.features:
assert feature.presence is not None
assert feature.shape is not None
if feature.name in ["location", "name", "status"]:
assert feature.string_domain is not None
elif feature.name in ["latitude", "longitude"]:
assert feature.float_domain is not None
elif feature.name in ["station_id"]:
assert feature.int_domain is not None
def test_feature_set_ingest_success(self, dataframe, client, mocker):
driver_fs = FeatureSet("driver-feature-set")
driver_fs.add(Feature(name="feature_1", dtype=ValueType.FLOAT))
driver_fs.add(Feature(name="feature_2", dtype=ValueType.STRING))
driver_fs.add(Feature(name="feature_3", dtype=ValueType.INT64))
driver_fs.add(Entity(name="entity_id", dtype=ValueType.INT64))
# Register with Feast core
client.apply(driver_fs)
mocker.patch.object(
client._core_service_stub,
"GetFeatureSet",
return_value=GetFeatureSetResponse(feature_set=driver_fs.to_proto()),
)
# Ingest data into Feast
client.ingest("driver-feature-set", dataframe=dataframe)
def test_feature_class_contains_labels():
fs = FeatureSet("my-feature-set", labels={"key1": "val1", "key2": "val2"})
fs.add(
Feature(
name="my-feature-1",
dtype=ValueType.INT64,
labels={"feature_key1": "feature_val1"},
))
assert "feature_key1" in fs.features[0].labels.keys()
assert fs.features[0].labels["feature_key1"] == "feature_val1"
def test_feature_set_import_export_yaml(self):
test_feature_set = FeatureSet(
name="bikeshare",
entities=[Entity(name="station_id", dtype=ValueType.INT64)],
features=[
Feature(name="name", dtype=ValueType.STRING),
Feature(name="longitude", dtype=ValueType.FLOAT),
Feature(name="location", dtype=ValueType.STRING),
],
)
# Create a string YAML representation of the feature set
string_yaml = test_feature_set.to_yaml()
# Create a new feature set object from the YAML string
actual_feature_set_from_string = FeatureSet.from_yaml(string_yaml)
# Ensure equality is upheld to original feature set
assert test_feature_set == actual_feature_set_from_string
def test_feature_set_ingest_success(self, dataframe, client):
driver_fs = FeatureSet("driver-feature-set")
driver_fs.add(Feature(name="feature_1", dtype=ValueType.FLOAT))
driver_fs.add(Feature(name="feature_2", dtype=ValueType.STRING))
driver_fs.add(Feature(name="feature_3", dtype=ValueType.INT64))
driver_fs.add(Entity(name="entity_id", dtype=ValueType.INT64))
driver_fs.source = KafkaSource(topic="feature-topic",
brokers="127.0.0.1")
driver_fs._message_producer = MagicMock()
driver_fs._message_producer.send = MagicMock()
# Register with Feast core
client.apply(driver_fs)
# Ingest data into Feast
driver_fs.ingest(dataframe=dataframe)
# Make sure message producer is called
driver_fs._message_producer.send.assert_called()
def test_add_features_from_df_success(
self,
dataframe,
feature_count,
entity_count,
discard_unused_fields,
features,
entities,
):
my_feature_set = FeatureSet(
name="my_feature_set",
features=[Feature(name="dummy_f1", dtype=ValueType.INT64)],
entities=[Entity(name="dummy_entity_1", dtype=ValueType.INT64)],
)
my_feature_set.infer_fields_from_df(
dataframe,
discard_unused_fields=discard_unused_fields,
features=features,
entities=entities,
)
assert len(my_feature_set.features) == feature_count
assert len(my_feature_set.entities) == entity_count
def test_feature_set_types_success(self, test_client, dataframe, mocker):
test_client.set_project("project1")
all_types_fs = FeatureSet(
name="all_types",
entities=[Entity(name="user_id", dtype=ValueType.INT64)],
features=[
Feature(name="float_feature", dtype=ValueType.FLOAT),
Feature(name="int64_feature", dtype=ValueType.INT64),
Feature(name="int32_feature", dtype=ValueType.INT32),
Feature(name="string_feature", dtype=ValueType.STRING),
Feature(name="bytes_feature", dtype=ValueType.BYTES),
Feature(name="bool_feature", dtype=ValueType.BOOL),
Feature(name="double_feature", dtype=ValueType.DOUBLE),
Feature(name="float_list_feature", dtype=ValueType.FLOAT_LIST),
Feature(name="int64_list_feature", dtype=ValueType.INT64_LIST),
Feature(name="int32_list_feature", dtype=ValueType.INT32_LIST),
Feature(name="string_list_feature",
dtype=ValueType.STRING_LIST),
Feature(name="bytes_list_feature", dtype=ValueType.BYTES_LIST),
# Feature(name="bool_list_feature",
# dtype=ValueType.BOOL_LIST), # TODO: Add support for this
# type again https://github.com/feast-dev/feast/issues/341
Feature(name="double_list_feature",
dtype=ValueType.DOUBLE_LIST),
],
max_age=Duration(seconds=3600),
)
# Register with Feast core
test_client.apply(all_types_fs)
mocker.patch.object(
test_client._core_service_stub,
"GetFeatureSet",
return_value=GetFeatureSetResponse(
feature_set=all_types_fs.to_proto()),
)
# Need to create a mock producer
with patch("feast.client.get_producer"):
# Ingest data into Feast
test_client.ingest(all_types_fs, dataframe)
class TestFeatureSet:
@pytest.fixture(scope="function")
def server(self):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=10))
Core.add_CoreServiceServicer_to_server(CoreServicer(), server)
server.add_insecure_port("[::]:50051")
server.start()
yield server
server.stop(0)
@pytest.fixture
def client(self, server):
return Client(core_url="localhost:50051")
def test_add_remove_features_success(self):
fs = FeatureSet("my-feature-set")
fs.add(Feature(name="my-feature-1", dtype=ValueType.INT64))
fs.add(Feature(name="my-feature-2", dtype=ValueType.INT64))
fs.drop(name="my-feature-1")
assert len(fs.features) == 1 and fs.features[0].name == "my-feature-2"
def test_remove_feature_failure(self):
with pytest.raises(ValueError):
fs = FeatureSet("my-feature-set")
fs.drop(name="my-feature-1")
def test_update_from_source_failure(self):
with pytest.raises(Exception):
df = pd.DataFrame()
fs = FeatureSet("driver-feature-set")
fs.infer_fields_from_df(df)
@pytest.mark.parametrize(
"dataframe,feature_count,entity_count,discard_unused_fields,features,entities",
[
(
dataframes.GOOD,
3,
1,
True,
[],
[Entity(name="entity_id", dtype=ValueType.INT64)],
),
(
dataframes.GOOD_FIVE_FEATURES,
5,
1,
True,
[],
[Entity(name="entity_id", dtype=ValueType.INT64)],
),
(
dataframes.GOOD_FIVE_FEATURES,
6,
1,
True,
[Feature(name="feature_6", dtype=ValueType.INT64)],
[Entity(name="entity_id", dtype=ValueType.INT64)],
),
(
dataframes.GOOD_FIVE_FEATURES_TWO_ENTITIES,
5,
2,
True,
[],
[
Entity(name="entity_1_id", dtype=ValueType.INT64),
Entity(name="entity_2_id", dtype=ValueType.INT64),
],
),
(
dataframes.GOOD_FIVE_FEATURES_TWO_ENTITIES,
6,
3,
False,
[],
[
Entity(name="entity_1_id", dtype=ValueType.INT64),
Entity(name="entity_2_id", dtype=ValueType.INT64),
],
),
(
dataframes.NO_FEATURES,
0,
1,
True,
[],
[Entity(name="entity_id", dtype=ValueType.INT64)],
),
(
pd.DataFrame({
"datetime": [
datetime.utcnow().replace(tzinfo=pytz.utc)
for _ in range(3)
]
}),
0,
0,
True,
[],
[],
),
],
ids=[
"Test small dataframe update with hardcoded entity",
"Test larger dataframe update with hardcoded entity",
"Test larger dataframe update with hardcoded entity and feature",
"Test larger dataframe update with two hardcoded entities and discarding of existing fields",
"Test larger dataframe update with two hardcoded entities and retention of existing fields",
"Test dataframe with no featuresdataframe",
"Test empty dataframe",
],
)
def test_add_features_from_df_success(
self,
dataframe,
feature_count,
entity_count,
discard_unused_fields,
features,
entities,
):
my_feature_set = FeatureSet(
name="my_feature_set",
features=[Feature(name="dummy_f1", dtype=ValueType.INT64)],
entities=[Entity(name="dummy_entity_1", dtype=ValueType.INT64)],
)
my_feature_set.infer_fields_from_df(
dataframe,
discard_unused_fields=discard_unused_fields,
features=features,
entities=entities,
)
assert len(my_feature_set.features) == feature_count
assert len(my_feature_set.entities) == entity_count
def test_unequal_feature_other_has_no_labels():
f1 = Feature(name="feature-1", dtype=ValueType.INT64, labels={"k1": "v1"})
f2 = Feature(name="feature-1", dtype=ValueType.INT64)
assert f1 != f2
def test_feature_set_types_success(self, client, dataframe):
all_types_fs = FeatureSet(
name="all_types",
entities=[Entity(name="user_id", dtype=ValueType.INT64)],
features=[
Feature(name="float_feature", dtype=ValueType.FLOAT),
Feature(name="int64_feature", dtype=ValueType.INT64),
Feature(name="int32_feature", dtype=ValueType.INT32),
Feature(name="string_feature", dtype=ValueType.STRING),
Feature(name="bytes_feature", dtype=ValueType.BYTES),
Feature(name="bool_feature", dtype=ValueType.BOOL),
Feature(name="double_feature", dtype=ValueType.DOUBLE),
Feature(name="float_list_feature", dtype=ValueType.FLOAT_LIST),
Feature(name="int64_list_feature", dtype=ValueType.INT64_LIST),
Feature(name="int32_list_feature", dtype=ValueType.INT32_LIST),
Feature(name="string_list_feature",
dtype=ValueType.STRING_LIST),
Feature(name="bytes_list_feature", dtype=ValueType.BYTES_LIST),
Feature(name="bool_list_feature", dtype=ValueType.BOOL_LIST),
Feature(name="double_list_feature",
dtype=ValueType.DOUBLE_LIST),
],
max_age=Duration(seconds=3600),
)
all_types_fs.source = KafkaSource(topic="feature-topic",
brokers="127.0.0.1")
all_types_fs._message_producer = MagicMock()
all_types_fs._message_producer.send = MagicMock()
# Register with Feast core
client.apply(all_types_fs)
# Ingest data into Feast
all_types_fs.ingest(dataframe=dataframe)
# Make sure message producer is called
all_types_fs._message_producer.send.assert_called()
def test_feature_set_types_success(self, client, dataframe, mocker):
all_types_fs = FeatureSet(
name="all_types",
entities=[Entity(name="user_id", dtype=ValueType.INT64)],
features=[
Feature(name="float_feature", dtype=ValueType.FLOAT),
Feature(name="int64_feature", dtype=ValueType.INT64),
Feature(name="int32_feature", dtype=ValueType.INT32),
Feature(name="string_feature", dtype=ValueType.STRING),
Feature(name="bytes_feature", dtype=ValueType.BYTES),
Feature(name="bool_feature", dtype=ValueType.BOOL),
Feature(name="double_feature", dtype=ValueType.DOUBLE),
Feature(name="float_list_feature", dtype=ValueType.FLOAT_LIST),
Feature(name="int64_list_feature", dtype=ValueType.INT64_LIST),
Feature(name="int32_list_feature", dtype=ValueType.INT32_LIST),
Feature(name="string_list_feature", dtype=ValueType.STRING_LIST),
Feature(name="bytes_list_feature", dtype=ValueType.BYTES_LIST),
Feature(name="bool_list_feature", dtype=ValueType.BOOL_LIST),
Feature(name="double_list_feature", dtype=ValueType.DOUBLE_LIST),
],
max_age=Duration(seconds=3600),
)
# Register with Feast core
client.apply(all_types_fs)
mocker.patch.object(
client._core_service_stub,
"GetFeatureSet",
return_value=GetFeatureSetResponse(feature_set=all_types_fs.to_proto()),
)
# Ingest data into Feast
client.ingest(all_types_fs, dataframe=dataframe)
class TestFeatureSet:
@pytest.fixture(scope="function")
def server(self):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=10))
Core.add_CoreServiceServicer_to_server(CoreServicer(), server)
server.add_insecure_port("[::]:50051")
server.start()
yield server
server.stop(0)
@pytest.fixture
def client(self, server):
return Client(core_url="localhost:50051")
def test_add_remove_features_success(self):
fs = FeatureSet("my-feature-set")
fs.add(Feature(name="my-feature-1", dtype=ValueType.INT64))
fs.add(Feature(name="my-feature-2", dtype=ValueType.INT64))
fs.drop(name="my-feature-1")
assert len(fs.features) == 1 and fs.features[0].name == "my-feature-2"
def test_remove_feature_failure(self):
with pytest.raises(ValueError):
fs = FeatureSet("my-feature-set")
fs.drop(name="my-feature-1")
def test_update_from_source_failure(self):
with pytest.raises(Exception):
df = pd.DataFrame()
fs = FeatureSet("driver-feature-set")
fs.infer_fields_from_df(df)
@pytest.mark.parametrize(
"dataframe,feature_count,entity_count,discard_unused_fields,features,entities",
[
(
dataframes.GOOD,
3,
1,
True,
[],
[Entity(name="entity_id", dtype=ValueType.INT64)],
),
(
dataframes.GOOD_FIVE_FEATURES,
5,
1,
True,
[],
[Entity(name="entity_id", dtype=ValueType.INT64)],
),
(
dataframes.GOOD_FIVE_FEATURES,
6,
1,
True,
[Feature(name="feature_6", dtype=ValueType.INT64)],
[Entity(name="entity_id", dtype=ValueType.INT64)],
),
(
dataframes.GOOD_FIVE_FEATURES_TWO_ENTITIES,
5,
2,
True,
[],
[
Entity(name="entity_1_id", dtype=ValueType.INT64),
Entity(name="entity_2_id", dtype=ValueType.INT64),
],
),
(
dataframes.GOOD_FIVE_FEATURES_TWO_ENTITIES,
6,
3,
False,
[],
[
Entity(name="entity_1_id", dtype=ValueType.INT64),
Entity(name="entity_2_id", dtype=ValueType.INT64),
],
),
(
dataframes.NO_FEATURES,
0,
1,
True,
[],
[Entity(name="entity_id", dtype=ValueType.INT64)],
),
(
pd.DataFrame({
"datetime": [
datetime.utcnow().replace(tzinfo=pytz.utc)
for _ in range(3)
]
}),
0,
0,
True,
[],
[],
),
],
ids=[
"Test small dataframe update with hardcoded entity",
"Test larger dataframe update with hardcoded entity",
"Test larger dataframe update with hardcoded entity and feature",
"Test larger dataframe update with two hardcoded entities and discarding of existing fields",
"Test larger dataframe update with two hardcoded entities and retention of existing fields",
"Test dataframe with no featuresdataframe",
"Test empty dataframe",
],
)
def test_add_features_from_df_success(
self,
dataframe,
feature_count,
entity_count,
discard_unused_fields,
features,
entities,
):
my_feature_set = FeatureSet(
name="my_feature_set",
features=[Feature(name="dummy_f1", dtype=ValueType.INT64)],
entities=[Entity(name="dummy_entity_1", dtype=ValueType.INT64)],
)
my_feature_set.infer_fields_from_df(
dataframe,
discard_unused_fields=discard_unused_fields,
features=features,
entities=entities,
)
assert len(my_feature_set.features) == feature_count
assert len(my_feature_set.entities) == entity_count
def test_import_tfx_schema(self):
tests_folder = pathlib.Path(__file__).parent
test_input_schema_json = open(tests_folder / "data" /
"tensorflow_metadata" /
"bikeshare_schema.json").read()
test_input_schema = schema_pb2.Schema()
json_format.Parse(test_input_schema_json, test_input_schema)
feature_set = FeatureSet(
name="bikeshare",
entities=[Entity(name="station_id", dtype=ValueType.INT64)],
features=[
Feature(name="name", dtype=ValueType.STRING),
Feature(name="status", dtype=ValueType.STRING),
Feature(name="latitude", dtype=ValueType.FLOAT),
Feature(name="longitude", dtype=ValueType.FLOAT),
Feature(name="location", dtype=ValueType.STRING),
],
)
# Before update
for entity in feature_set.entities:
assert entity.presence is None
assert entity.shape is None
for feature in feature_set.features:
assert feature.presence is None
assert feature.shape is None
assert feature.string_domain is None
assert feature.float_domain is None
assert feature.int_domain is None
feature_set.import_tfx_schema(test_input_schema)
# After update
for feature in feature_set.features:
assert feature.presence is not None
assert feature.shape is not None
if feature.name in ["location", "name", "status"]:
assert feature.string_domain is not None
elif feature.name in ["latitude", "longitude"]:
assert feature.float_domain is not None
elif feature.name in ["station_id"]:
assert feature.int_domain is not None
def test_export_tfx_schema(self):
tests_folder = pathlib.Path(__file__).parent
test_input_feature_set = FeatureSet.from_yaml(
str(tests_folder / "data" / "tensorflow_metadata" /
"bikeshare_feature_set.yaml"))
expected_schema_json = open(tests_folder / "data" /
"tensorflow_metadata" /
"bikeshare_schema.json").read()
expected_schema = schema_pb2.Schema()
json_format.Parse(expected_schema_json, expected_schema)
_make_tfx_schema_domain_info_inline(expected_schema)
actual_schema = test_input_feature_set.export_tfx_schema()
assert len(actual_schema.feature) == len(expected_schema.feature)
for actual, expected in zip(actual_schema.feature,
expected_schema.feature):
assert actual.SerializeToString() == expected.SerializeToString()
def test_feature_set_import_export_yaml(self):
test_feature_set = FeatureSet(
name="bikeshare",
entities=[Entity(name="station_id", dtype=ValueType.INT64)],
features=[
Feature(name="name", dtype=ValueType.STRING),
Feature(name="longitude", dtype=ValueType.FLOAT),
Feature(name="location", dtype=ValueType.STRING),
],
)
# Create a string YAML representation of the feature set
string_yaml = test_feature_set.to_yaml()
# Create a new feature set object from the YAML string
actual_feature_set_from_string = FeatureSet.from_yaml(string_yaml)
# Ensure equality is upheld to original feature set
assert test_feature_set == actual_feature_set_from_string
def test_add_remove_features_success(self):
fs = FeatureSet("my-feature-set")
fs.add(Feature(name="my-feature-1", dtype=ValueType.INT64))
fs.add(Feature(name="my-feature-2", dtype=ValueType.INT64))
fs.drop(name="my-feature-1")
assert len(fs.features) == 1 and fs.features[0].name == "my-feature-2"
def test_feature_without_labels_empty_dict():
f = Feature("my feature", dtype=ValueType.INT64)
assert f.labels == OrderedDict()
assert len(f.labels) == 0
