def test_create_stream_feature_view():
stream_source = KafkaSource(
name="kafka",
event_timestamp_column="",
bootstrap_servers="",
message_format=AvroFormat(""),
topic="topic",
batch_source=FileSource(path="some path"),
)
StreamFeatureView(
name="test batch feature view",
entities=[],
ttl=timedelta(days=30),
source=stream_source,
)
with pytest.raises(ValueError):
StreamFeatureView(name="test batch feature view",
entities=[],
ttl=timedelta(days=30))
with pytest.raises(ValueError):
StreamFeatureView(
name="test batch feature view",
entities=[],
ttl=timedelta(days=30),
source=FileSource(path="some path"),
)
def test_feature_table_import_export_yaml(self, batch_source):
stream_source = KafkaSource(
field_mapping={
"ride_distance": "ride_distance",
"ride_duration": "ride_duration",
},
bootstrap_servers="localhost:9094",
message_format=ProtoFormat(class_path="class.path"),
topic="test_topic",
event_timestamp_column="ts_col",
)
test_feature_table = FeatureTable(
name="car_driver",
features=[
Feature(name="ride_distance", dtype=ValueType.FLOAT),
Feature(name="ride_duration", dtype=ValueType.STRING),
],
entities=["car_driver_entity"],
labels={"team": "matchmaking"},
batch_source=batch_source,
stream_source=stream_source,
)
# Create a string YAML representation of the feature table
string_yaml = test_feature_table.to_yaml()
# Create a new feature table object from the YAML string
actual_feature_table_from_string = FeatureTable.from_yaml(string_yaml)
# Ensure equality is upheld to original feature table
assert test_feature_table == actual_feature_table_from_string
def test_apply_feature_table_success(self, test_client):
test_client.set_project("project1")
# Create Feature Tables
batch_source = FileSource(
file_format="parquet",
file_url="file://feast/*",
event_timestamp_column="ts_col",
created_timestamp_column="timestamp",
date_partition_column="date_partition_col",
)
stream_source = KafkaSource(
bootstrap_servers="localhost:9094",
class_path="random/path/to/class",
topic="test_topic",
event_timestamp_column="ts_col",
created_timestamp_column="timestamp",
)
ft1 = FeatureTable(
name="my-feature-table-1",
features=[
Feature(name="fs1-my-feature-1", dtype=ValueType.INT64),
Feature(name="fs1-my-feature-2", dtype=ValueType.STRING),
Feature(name="fs1-my-feature-3", dtype=ValueType.STRING_LIST),
Feature(name="fs1-my-feature-4", dtype=ValueType.BYTES_LIST),
],
entities=["fs1-my-entity-1"],
labels={"team": "matchmaking"},
batch_source=batch_source,
stream_source=stream_source,
)
# Register Feature Table with Core
test_client.apply_feature_table(ft1)
feature_tables = test_client.list_feature_tables()
# List Feature Tables
assert (
len(feature_tables) == 1
and feature_tables[0].name == "my-feature-table-1"
and feature_tables[0].features[0].name == "fs1-my-feature-1"
and feature_tables[0].features[0].dtype == ValueType.INT64
and feature_tables[0].features[1].name == "fs1-my-feature-2"
and feature_tables[0].features[1].dtype == ValueType.STRING
and feature_tables[0].features[2].name == "fs1-my-feature-3"
and feature_tables[0].features[2].dtype == ValueType.STRING_LIST
and feature_tables[0].features[3].name == "fs1-my-feature-4"
and feature_tables[0].features[3].dtype == ValueType.BYTES_LIST
and feature_tables[0].entities[0] == "fs1-my-entity-1"
)
def feature_table():
return FeatureTable(
name="ft",
entities=[],
features=[],
stream_source=KafkaSource(
topic="t",
bootstrap_servers="",
message_format=AvroFormat(""),
event_timestamp_column="",
),
)
def basic_featuretable():
batch_source = FileSource(
field_mapping={
"dev_entity": "dev_entity_field",
"dev_feature_float": "dev_feature_float_field",
"dev_feature_string": "dev_feature_string_field",
},
file_format="PARQUET",
file_url="gs://example/feast/*",
event_timestamp_column="datetime_col",
created_timestamp_column="timestamp",
date_partition_column="datetime",
)
stream_source = KafkaSource(
field_mapping={
"dev_entity": "dev_entity_field",
"dev_feature_float": "dev_feature_float_field",
"dev_feature_string": "dev_feature_string_field",
},
bootstrap_servers="localhost:9094",
class_path="random/path/to/class",
topic="test_topic",
event_timestamp_column="datetime_col",
created_timestamp_column="timestamp",
)
return FeatureTable(
name="basic_featuretable",
entities=["driver_id", "customer_id"],
features=[
Feature(name="dev_feature_float", dtype=ValueType.FLOAT),
Feature(name="dev_feature_string", dtype=ValueType.STRING),
],
max_age=Duration(seconds=3600),
batch_source=batch_source,
stream_source=stream_source,
labels={
"key1": "val1",
"key2": "val2"
},
)
def _create_ft(self, client: Client, features) -> None:
entity = Entity(
name="driver_car_id",
description="Car driver id",
value_type=ValueType.STRING,
labels={"team": "matchmaking"},
)
# Register Entity with Core
client.apply_entity(entity)
# Create Feature Tables
batch_source = FileSource(
file_format=ParquetFormat(),
file_url="file://feast/*",
event_timestamp_column="ts_col",
created_timestamp_column="timestamp",
date_partition_column="date_partition_col",
)
stream_source = KafkaSource(
bootstrap_servers="localhost:9094",
message_format=ProtoFormat("class.path"),
topic="test_topic",
event_timestamp_column="ts_col",
created_timestamp_column="timestamp",
)
ft1 = FeatureTable(
name=self.table_name,
features=features,
entities=["driver_car_id"],
labels={"team": "matchmaking"},
batch_source=batch_source,
stream_source=stream_source,
)
# Register Feature Table with Core
client.apply_feature_table(ft1)
def test_apply_feature_table_integration(self, test_client):
# Create Feature Tables
batch_source = FileSource(
file_format=ParquetFormat(),
file_url="file://feast/*",
event_timestamp_column="ts_col",
created_timestamp_column="timestamp",
date_partition_column="date_partition_col",
)
stream_source = KafkaSource(
bootstrap_servers="localhost:9094",
message_format=ProtoFormat("class.path"),
topic="test_topic",
event_timestamp_column="ts_col",
)
ft1 = FeatureTable(
name="my-feature-table-1",
features=[
Feature(name="fs1-my-feature-1", dtype=ValueType.INT64),
Feature(name="fs1-my-feature-2", dtype=ValueType.STRING),
Feature(name="fs1-my-feature-3", dtype=ValueType.STRING_LIST),
Feature(name="fs1-my-feature-4", dtype=ValueType.BYTES_LIST),
],
entities=["fs1-my-entity-1"],
labels={"team": "matchmaking"},
batch_source=batch_source,
stream_source=stream_source,
)
# Register Feature Table with Core
test_client.apply(ft1)
feature_tables = test_client.list_feature_tables()
# List Feature Tables
assert (len(feature_tables) == 1
and feature_tables[0].name == "my-feature-table-1"
and feature_tables[0].features[0].name == "fs1-my-feature-1"
and feature_tables[0].features[0].dtype == ValueType.INT64
and feature_tables[0].features[1].name == "fs1-my-feature-2"
and feature_tables[0].features[1].dtype == ValueType.STRING
and feature_tables[0].features[2].name == "fs1-my-feature-3"
and feature_tables[0].features[2].dtype
== ValueType.STRING_LIST
and feature_tables[0].features[3].name == "fs1-my-feature-4"
and feature_tables[0].features[3].dtype == ValueType.BYTES_LIST
and feature_tables[0].entities[0] == "fs1-my-entity-1")
feature_table = test_client.get_feature_table("my-feature-table-1")
assert (feature_table.name == "my-feature-table-1"
and feature_table.features[0].name == "fs1-my-feature-1"
and feature_table.features[0].dtype == ValueType.INT64
and feature_table.features[1].name == "fs1-my-feature-2"
and feature_table.features[1].dtype == ValueType.STRING
and feature_table.features[2].name == "fs1-my-feature-3"
and feature_table.features[2].dtype == ValueType.STRING_LIST
and feature_table.features[3].name == "fs1-my-feature-4"
and feature_table.features[3].dtype == ValueType.BYTES_LIST
and feature_table.entities[0] == "fs1-my-entity-1")
test_client.delete_feature_table("my-feature-table-1")
feature_tables = test_client.list_feature_tables()
assert len(feature_tables) == 0
def test_default_data_source_kw_arg_warning():
# source_class = request.param
with pytest.warns(DeprecationWarning):
source = KafkaSource(
"name", "column", "bootstrap_servers", ProtoFormat("class_path"), "topic"
)
assert source.name == "name"
assert source.timestamp_field == "column"
assert source.kafka_options.bootstrap_servers == "bootstrap_servers"
assert source.kafka_options.topic == "topic"
with pytest.raises(ValueError):
KafkaSource("name", "column", "bootstrap_servers", topic="topic")
with pytest.warns(DeprecationWarning):
source = KinesisSource(
"name",
"column",
"c_column",
ProtoFormat("class_path"),
"region",
"stream_name",
)
assert source.name == "name"
assert source.timestamp_field == "column"
assert source.created_timestamp_column == "c_column"
assert source.kinesis_options.region == "region"
assert source.kinesis_options.stream_name == "stream_name"
with pytest.raises(ValueError):
KinesisSource(
"name", "column", "c_column", region="region", stream_name="stream_name"
)
with pytest.warns(DeprecationWarning):
source = RequestSource(
"name", [Field(name="val_to_add", dtype=Int64)], description="description"
)
assert source.name == "name"
assert source.description == "description"
with pytest.raises(ValueError):
RequestSource("name")
with pytest.warns(DeprecationWarning):
source = PushSource(
"name",
BigQuerySource(name="bigquery_source", table="table"),
description="description",
)
assert source.name == "name"
assert source.description == "description"
assert source.batch_source.name == "bigquery_source"
with pytest.raises(ValueError):
PushSource("name")
# No name warning for DataSource
with pytest.warns(UserWarning):
source = KafkaSource(
event_timestamp_column="column",
bootstrap_servers="bootstrap_servers",
message_format=ProtoFormat("class_path"),
topic="topic",
)
