def create_schema(kafka_broker, topic_name, feature_table_name):
entity = Entity(name="key", description="Key", value_type=ValueType.INT64)
feature_table = FeatureTable(
name=feature_table_name,
entities=["key"],
features=[Feature("num", ValueType.INT64), Feature("set", ValueType.STRING)],
batch_source=FileSource(
event_timestamp_column="event_timestamp",
file_format=ParquetFormat(),
file_url="/dev/null",
),
stream_source=KafkaSource(
event_timestamp_column="event_timestamp",
bootstrap_servers=kafka_broker,
message_format=AvroFormat(avro_schema()),
topic=topic_name,
),
)
return entity, feature_table
def test_streaming_ingestion(feast_client: Client, local_staging_path: str,
kafka_server):
entity = Entity(
name="s2id",
description="S2id",
value_type=ValueType.INT64,
)
kafka_broker = f"{kafka_server[0]}:{kafka_server[1]}"
topic_name = f"avro-{uuid.uuid4()}"
feature_table = FeatureTable(
name="drivers_stream",
entities=["s2id"],
features=[Feature("unique_drivers", ValueType.INT64)],
batch_source=FileSource(
event_timestamp_column="event_timestamp",
created_timestamp_column="event_timestamp",
file_format=ParquetFormat(),
file_url=os.path.join(local_staging_path, "batch-storage"),
),
stream_source=KafkaSource(
"event_timestamp",
"event_timestamp",
kafka_broker,
AvroFormat(avro_schema()),
topic=topic_name,
),
)
feast_client.apply_entity(entity)
feast_client.apply_feature_table(feature_table)
job = feast_client.start_stream_to_online_ingestion(feature_table)
wait_retry_backoff(
lambda: (None, job.get_status() == SparkJobStatus.IN_PROGRESS), 60)
wait_retry_backoff(
lambda: (None, check_consumer_exist(kafka_broker, topic_name)), 60)
try:
original = generate_data()[[
"s2id", "unique_drivers", "event_timestamp"
]]
for record in original.to_dict("records"):
record["event_timestamp"] = (
record["event_timestamp"].to_pydatetime().replace(
tzinfo=pytz.utc))
send_avro_record_to_kafka(
topic_name,
record,
bootstrap_servers=kafka_broker,
avro_schema_json=avro_schema(),
)
def get_online_features():
features = feast_client.get_online_features(
["drivers_stream:unique_drivers"],
entity_rows=[{
"s2id": s2_id
} for s2_id in original["s2id"].tolist()],
).to_dict()
df = pd.DataFrame.from_dict(features)
return df, not df["drivers_stream:unique_drivers"].isna().any()
ingested = wait_retry_backoff(get_online_features, 60)
finally:
job.cancel()
pd.testing.assert_frame_equal(
ingested[["s2id", "drivers_stream:unique_drivers"]],
original[[
"s2id", "unique_drivers"
]].rename(columns={"unique_drivers": "drivers_stream:unique_drivers"}),
)
def test_validation_with_ge(feast_client: Client, kafka_server):
entity = Entity(name="key", description="Key", value_type=ValueType.INT64)
kafka_broker = f"{kafka_server[0]}:{kafka_server[1]}"
topic_name = f"avro-{uuid.uuid4()}"
feature_table = FeatureTable(
name="validation_test",
entities=["key"],
features=[
Feature("num", ValueType.INT64),
Feature("set", ValueType.STRING)
],
batch_source=FileSource(
event_timestamp_column="event_timestamp",
file_format=ParquetFormat(),
file_url="/dev/null",
),
stream_source=KafkaSource(
event_timestamp_column="event_timestamp",
bootstrap_servers=kafka_broker,
message_format=AvroFormat(avro_schema()),
topic=topic_name,
),
)
feast_client.apply_entity(entity)
feast_client.apply_feature_table(feature_table)
train_data = generate_train_data()
ge_ds = PandasDataset(train_data)
ge_ds.expect_column_values_to_be_between("num", 0, 100)
ge_ds.expect_column_values_to_be_in_set("set", ["a", "b", "c"])
expectations = ge_ds.get_expectation_suite()
udf = create_validation_udf("testUDF", expectations)
apply_validation(feast_client,
feature_table,
udf,
validation_window_secs=1)
job = feast_client.start_stream_to_online_ingestion(feature_table)
wait_retry_backoff(
lambda: (None, job.get_status() == SparkJobStatus.IN_PROGRESS), 120)
wait_retry_backoff(
lambda: (None, check_consumer_exist(kafka_broker, topic_name)), 120)
test_data = generate_test_data()
ge_ds = PandasDataset(test_data)
validation_result = ge_ds.validate(expectations, result_format="COMPLETE")
invalid_idx = list({
idx
for check in validation_result.results
for idx in check.result["unexpected_index_list"]
})
entity_rows = [{"key": key} for key in test_data["key"].tolist()]
try:
ingested = ingest_and_retrieve(
feast_client,
test_data,
avro_schema_json=avro_schema(),
topic_name=topic_name,
kafka_broker=kafka_broker,
entity_rows=entity_rows,
feature_names=["validation_test:num", "validation_test:set"],
expected_ingested_count=test_data.shape[0] - len(invalid_idx),
)
finally:
job.cancel()
test_data["num"] = test_data["num"].astype(np.float64)
test_data["num"].iloc[invalid_idx] = np.nan
test_data["set"].iloc[invalid_idx] = None
pd.testing.assert_frame_equal(
ingested[["key", "validation_test:num", "validation_test:set"]],
test_data[["key", "num", "set"]].rename(columns={
"num": "validation_test:num",
"set": "validation_test:set"
}),
)
def test_streaming_ingestion(feast_client: Client, local_staging_path: str,
kafka_server, pytestconfig):
entity = Entity(
name="s2id",
description="S2id",
value_type=ValueType.INT64,
)
kafka_broker = f"{kafka_server[0]}:{kafka_server[1]}"
topic_name = f"avro-{uuid.uuid4()}"
feature_table = FeatureTable(
name="drivers_stream",
entities=["s2id"],
features=[Feature("unique_drivers", ValueType.INT64)],
batch_source=FileSource(
event_timestamp_column="event_timestamp",
created_timestamp_column="event_timestamp",
file_format=ParquetFormat(),
file_url=os.path.join(local_staging_path, "batch-storage"),
),
stream_source=KafkaSource(
event_timestamp_column="event_timestamp",
bootstrap_servers=kafka_broker,
message_format=AvroFormat(avro_schema()),
topic=topic_name,
),
)
feast_client.apply(entity)
feast_client.apply(feature_table)
if not pytestconfig.getoption("scheduled_streaming_job"):
job = feast_client.start_stream_to_online_ingestion(feature_table)
assert job.get_feature_table() == feature_table.name
wait_retry_backoff(
lambda: (None, job.get_status() == SparkJobStatus.IN_PROGRESS),
120)
else:
job = None
wait_retry_backoff(
lambda: (None, check_consumer_exist(kafka_broker, topic_name)), 300)
test_data = generate_data()[["s2id", "unique_drivers", "event_timestamp"]]
try:
ingested = ingest_and_retrieve(
feast_client,
test_data,
avro_schema_json=avro_schema(),
topic_name=topic_name,
kafka_broker=kafka_broker,
entity_rows=[{
"s2id": s2_id
} for s2_id in test_data["s2id"].tolist()],
feature_names=["drivers_stream:unique_drivers"],
)
finally:
if job:
job.cancel()
else:
feast_client.delete_feature_table(feature_table.name)
pd.testing.assert_frame_equal(
ingested[["s2id", "drivers_stream:unique_drivers"]],
test_data[[
"s2id", "unique_drivers"
]].rename(columns={"unique_drivers": "drivers_stream:unique_drivers"}),
)
root_path = pathlib.Path(__file__).parent.resolve()
driver_hourly_stats = FileSource(
path=f"{root_path}/data/driver_stats.parquet",
event_timestamp_column="event_timestamp",
created_timestamp_column="created",
)
driver_hourly_stats_kafka_source = KafkaSource(
bootstrap_servers="broker1",
event_timestamp_column="datetime",
created_timestamp_column="datetime",
topic="driver_hourly_stats",
message_format=AvroFormat(schema_json=re.sub(
"\n[ \t]*\\|",
"",
"""'{"type": "record",
|"name": "driver_hourly_stats",
|"fields": [
| {"name": "conv_rate", "type": "float"},
| {"name": "acc_rate", "type": "float"},
| {"name": "avg_daily_trips", "type": "int"},
| {"name": "datetime", "type": {"type": "long", "logicalType": "timestamp-micros"}}]}'""",
)),
)
# Define an entity for the driver. You can think of entity as a primary key used to
# fetch features.
driver = Entity(
name="driver_id",
value_type=ValueType.INT64,
description="Internal identifier of the driver",
