def create_data_source(
self,
df: pd.DataFrame,
destination_name: str,
suffix: Optional[str] = None,
event_timestamp_column="ts",
created_timestamp_column="created_ts",
field_mapping: Dict[str, str] = None,
) -> DataSource:
destination_name = self.get_prefixed_table_name(destination_name)
aws_utils.upload_df_to_redshift(
self.client,
self.offline_store_config.cluster_id,
self.offline_store_config.database,
self.offline_store_config.user,
self.s3,
f"{self.offline_store_config.s3_staging_location}/copy/{destination_name}.parquet",
self.offline_store_config.iam_role,
destination_name,
df,
)
self.tables.append(destination_name)
return RedshiftSource(
table=destination_name,
event_timestamp_column=event_timestamp_column,
created_timestamp_column=created_timestamp_column,
date_partition_column="",
field_mapping=field_mapping or {"ts_1": "ts"},
)
def prep_redshift_fs_and_fv(
source_type: str, ) -> Iterator[Tuple[FeatureStore, FeatureView]]:
client = aws_utils.get_redshift_data_client("us-west-2")
s3 = aws_utils.get_s3_resource("us-west-2")
df = create_dataset()
table_name = f"test_ingestion_{source_type}_correctness_{int(time.time_ns())}_{random.randint(1000, 9999)}"
offline_store = RedshiftOfflineStoreConfig(
cluster_id="feast-integration-tests",
region="us-west-2",
user="******",
database="feast",
s3_staging_location=
"s3://feast-integration-tests/redshift/tests/ingestion",
iam_role="arn:aws:iam::402087665549:role/redshift_s3_access_role",
)
aws_utils.upload_df_to_redshift(
client,
offline_store.cluster_id,
offline_store.database,
offline_store.user,
s3,
f"{offline_store.s3_staging_location}/copy/{table_name}.parquet",
offline_store.iam_role,
table_name,
df,
)
redshift_source = RedshiftSource(
table=table_name if source_type == "table" else None,
query=f"SELECT * FROM {table_name}"
if source_type == "query" else None,
event_timestamp_column="ts",
created_timestamp_column="created_ts",
date_partition_column="",
field_mapping={
"ts_1": "ts",
"id": "driver_id"
},
)
fv = driver_feature_view(redshift_source)
e = Entity(
name="driver",
description="id for driver",
join_key="driver_id",
value_type=ValueType.INT32,
)
with tempfile.TemporaryDirectory(
) as repo_dir_name, tempfile.TemporaryDirectory() as data_dir_name:
config = RepoConfig(
registry=str(Path(repo_dir_name) / "registry.db"),
project=f"test_bq_correctness_{str(uuid.uuid4()).replace('-', '')}",
provider="local",
online_store=SqliteOnlineStoreConfig(
path=str(Path(data_dir_name) / "online_store.db")),
offline_store=offline_store,
)
fs = FeatureStore(config=config)
fs.apply([fv, e])
yield fs, fv
fs.teardown()
# Clean up the uploaded Redshift table
aws_utils.execute_redshift_statement(
client,
offline_store.cluster_id,
offline_store.database,
offline_store.user,
f"DROP TABLE {table_name}",
)
name="driver_id",
# The join key of an entity describes the storage level field/column on which
# features can be looked up. The join key is also used to join feature
# tables/views when building feature vectors
join_key="driver_id",
# The storage level type for an entity
value_type=ValueType.INT64,
)
# Indicates a data source from which feature values can be retrieved. Sources are queried when building training
# datasets or materializing features into an online store.
driver_stats_source = RedshiftSource(
# The Redshift table where features can be found
table="feast_driver_hourly_stats",
# The event timestamp is used for point-in-time joins and for ensuring only
# features within the TTL are returned
event_timestamp_column="event_timestamp",
# The (optional) created timestamp is used to ensure there are no duplicate
# feature rows in the offline store or when building training datasets
created_timestamp_column="created",
)
# Feature views are a grouping based on how features are stored in either the
# online or offline store.
driver_stats_fv = FeatureView(
# The unique name of this feature view. Two feature views in a single
# project cannot have the same name
name="driver_hourly_stats",
# The list of entities specifies the keys required for joining or looking
# up features from this feature view. The reference provided in this field
# correspond to the name of a defined entity (or entities)
entities=["driver_id"],
def test_historical_features_from_redshift_sources(provider_type,
infer_event_timestamp_col,
capsys, full_feature_names):
client = aws_utils.get_redshift_data_client("us-west-2")
s3 = aws_utils.get_s3_resource("us-west-2")
offline_store = RedshiftOfflineStoreConfig(
cluster_id="feast-integration-tests",
region="us-west-2",
user="******",
database="feast",
s3_staging_location=
"s3://feast-integration-tests/redshift/tests/ingestion",
iam_role="arn:aws:iam::402087665549:role/redshift_s3_access_role",
)
start_date = datetime.now().replace(microsecond=0, second=0, minute=0)
(
customer_entities,
driver_entities,
end_date,
orders_df,
start_date,
) = generate_entities(start_date, infer_event_timestamp_col)
redshift_table_prefix = (
f"test_hist_retrieval_{int(time.time_ns())}_{random.randint(1000, 9999)}"
)
# Stage orders_df to Redshift
table_name = f"{redshift_table_prefix}_orders"
entity_df_query = f"SELECT * FROM {table_name}"
orders_context = aws_utils.temporarily_upload_df_to_redshift(
client,
offline_store.cluster_id,
offline_store.database,
offline_store.user,
s3,
f"{offline_store.s3_staging_location}/copy/{table_name}.parquet",
offline_store.iam_role,
table_name,
orders_df,
)
# Stage driver_df to Redshift
driver_df = driver_data.create_driver_hourly_stats_df(
driver_entities, start_date, end_date)
driver_table_name = f"{redshift_table_prefix}_driver_hourly"
driver_context = aws_utils.temporarily_upload_df_to_redshift(
client,
offline_store.cluster_id,
offline_store.database,
offline_store.user,
s3,
f"{offline_store.s3_staging_location}/copy/{driver_table_name}.parquet",
offline_store.iam_role,
driver_table_name,
driver_df,
)
# Stage customer_df to Redshift
customer_df = driver_data.create_customer_daily_profile_df(
customer_entities, start_date, end_date)
customer_table_name = f"{redshift_table_prefix}_customer_profile"
customer_context = aws_utils.temporarily_upload_df_to_redshift(
client,
offline_store.cluster_id,
offline_store.database,
offline_store.user,
s3,
f"{offline_store.s3_staging_location}/copy/{customer_table_name}.parquet",
offline_store.iam_role,
customer_table_name,
customer_df,
)
with orders_context, driver_context, customer_context, TemporaryDirectory(
) as temp_dir:
driver_source = RedshiftSource(
table=driver_table_name,
event_timestamp_column="event_timestamp",
created_timestamp_column="created",
)
driver_fv = create_driver_hourly_stats_feature_view(driver_source)
customer_source = RedshiftSource(
table=customer_table_name,
event_timestamp_column="event_timestamp",
created_timestamp_column="created",
)
customer_fv = create_customer_daily_profile_feature_view(
customer_source)
driver = Entity(name="driver",
join_key="driver_id",
value_type=ValueType.INT64)
customer = Entity(name="customer_id", value_type=ValueType.INT64)
if provider_type == "local":
store = FeatureStore(config=RepoConfig(
registry=os.path.join(temp_dir, "registry.db"),
project="default",
provider="local",
online_store=SqliteOnlineStoreConfig(path=os.path.join(
temp_dir, "online_store.db"), ),
offline_store=offline_store,
))
elif provider_type == "aws":
store = FeatureStore(config=RepoConfig(
registry=os.path.join(temp_dir, "registry.db"),
project="".join(
random.choices(string.ascii_uppercase + string.digits,
k=10)),
provider="aws",
online_store=DynamoDBOnlineStoreConfig(region="us-west-2"),
offline_store=offline_store,
))
else:
raise Exception(
"Invalid provider used as part of test configuration")
store.apply([driver, customer, driver_fv, customer_fv])
try:
event_timestamp = (DEFAULT_ENTITY_DF_EVENT_TIMESTAMP_COL
if DEFAULT_ENTITY_DF_EVENT_TIMESTAMP_COL
in orders_df.columns else "e_ts")
expected_df = get_expected_training_df(
customer_df,
customer_fv,
driver_df,
driver_fv,
orders_df,
event_timestamp,
full_feature_names,
)
job_from_sql = store.get_historical_features(
entity_df=entity_df_query,
features=[
"driver_stats:conv_rate",
"driver_stats:avg_daily_trips",
"customer_profile:current_balance",
"customer_profile:avg_passenger_count",
"customer_profile:lifetime_trip_count",
],
full_feature_names=full_feature_names,
)
start_time = datetime.utcnow()
actual_df_from_sql_entities = job_from_sql.to_df()
end_time = datetime.utcnow()
with capsys.disabled():
print(
str(f"\nTime to execute job_from_sql.to_df() = '{(end_time - start_time)}'"
))
assert sorted(expected_df.columns) == sorted(
actual_df_from_sql_entities.columns)
assert_frame_equal(
expected_df.sort_values(by=[
event_timestamp, "order_id", "driver_id", "customer_id"
]).reset_index(drop=True),
actual_df_from_sql_entities[expected_df.columns].sort_values(
by=[
event_timestamp, "order_id", "driver_id", "customer_id"
]).reset_index(drop=True),
check_dtype=False,
)
table_from_sql_entities = job_from_sql.to_arrow()
assert_frame_equal(
actual_df_from_sql_entities.sort_values(by=[
event_timestamp, "order_id", "driver_id", "customer_id"
]).reset_index(drop=True),
table_from_sql_entities.to_pandas().sort_values(by=[
event_timestamp, "order_id", "driver_id", "customer_id"
]).reset_index(drop=True),
)
timestamp_column = ("e_ts" if infer_event_timestamp_col else
DEFAULT_ENTITY_DF_EVENT_TIMESTAMP_COL)
entity_df_query_with_invalid_join_key = (
f"select order_id, driver_id, customer_id as customer, "
f"order_is_success, {timestamp_column} FROM {table_name}")
# Rename the join key; this should now raise an error.
assertpy.assert_that(
store.get_historical_features(
entity_df=entity_df_query_with_invalid_join_key,
features=[
"driver_stats:conv_rate",
"driver_stats:avg_daily_trips",
"customer_profile:current_balance",
"customer_profile:avg_passenger_count",
"customer_profile:lifetime_trip_count",
],
).to_df).raises(errors.FeastEntityDFMissingColumnsError
).when_called_with()
job_from_df = store.get_historical_features(
entity_df=orders_df,
features=[
"driver_stats:conv_rate",
"driver_stats:avg_daily_trips",
"customer_profile:current_balance",
"customer_profile:avg_passenger_count",
"customer_profile:lifetime_trip_count",
],
full_feature_names=full_feature_names,
)
# Rename the join key; this should now raise an error.
orders_df_with_invalid_join_key = orders_df.rename(
{"customer_id": "customer"}, axis="columns")
assertpy.assert_that(
store.get_historical_features(
entity_df=orders_df_with_invalid_join_key,
features=[
"driver_stats:conv_rate",
"driver_stats:avg_daily_trips",
"customer_profile:current_balance",
"customer_profile:avg_passenger_count",
"customer_profile:lifetime_trip_count",
],
).to_df).raises(errors.FeastEntityDFMissingColumnsError
).when_called_with()
start_time = datetime.utcnow()
actual_df_from_df_entities = job_from_df.to_df()
end_time = datetime.utcnow()
with capsys.disabled():
print(
str(f"Time to execute job_from_df.to_df() = '{(end_time - start_time)}'\n"
))
assert sorted(expected_df.columns) == sorted(
actual_df_from_df_entities.columns)
assert_frame_equal(
expected_df.sort_values(by=[
event_timestamp, "order_id", "driver_id", "customer_id"
]).reset_index(drop=True),
actual_df_from_df_entities[expected_df.columns].sort_values(
by=[
event_timestamp, "order_id", "driver_id", "customer_id"
]).reset_index(drop=True),
check_dtype=False,
)
table_from_df_entities = job_from_df.to_arrow()
assert_frame_equal(
actual_df_from_df_entities.sort_values(by=[
event_timestamp, "order_id", "driver_id", "customer_id"
]).reset_index(drop=True),
table_from_df_entities.to_pandas().sort_values(by=[
event_timestamp, "order_id", "driver_id", "customer_id"
]).reset_index(drop=True),
)
finally:
store.teardown()