def test_feature_store_create(sagemaker_session_mock, role_arn,
feature_group_dummy_definitions, s3_uri):
feature_group = FeatureGroup(name="MyFeatureGroup",
sagemaker_session=sagemaker_session_mock)
feature_group.feature_definitions = feature_group_dummy_definitions
feature_group.create(
s3_uri=s3_uri,
record_identifier_name="feature1",
event_time_feature_name="feature2",
role_arn=role_arn,
enable_online_store=True,
)
sagemaker_session_mock.create_feature_group.assert_called_with(
feature_group_name="MyFeatureGroup",
record_identifier_name="feature1",
event_time_feature_name="feature2",
feature_definitions=[
fd.to_dict() for fd in feature_group_dummy_definitions
],
role_arn=role_arn,
description=None,
tags=None,
online_store_config={"EnableOnlineStore": True},
offline_store_config={
"DisableGlueTableCreation": False,
"S3StorageConfig": {
"S3Uri": s3_uri
},
},
)
def save_to_feature_store():
logger.info("Save to FeatureStore started")
global feature_group
df_data = pd.read_csv(feature_s3_url)
logger.info("Read data from S3: %s", df_data.head())
feature_store_session = Session(
boto_session=boto_session,
sagemaker_client=sagemaker_client,
sagemaker_featurestore_runtime_client=featurestore_runtime)
# You can modify the following to use a bucket of your choosing
logger.info("Default bucket: %s", default_bucket)
# record identifier and event time feature names
record_identifier_feature_name = "IDpol"
event_time_feature_name = "EventTime"
current_time_sec = int(round(time.time()))
# cast object dtype to string. The SageMaker FeatureStore Python SDK will then map the string dtype to String feature type.
cast_object_to_string(df_data)
df_data[event_time_feature_name] = pd.Series([current_time_sec] *
len(df_data),
dtype="float64")
feature_group_name = 'insurance-policy-feature-group-' + strftime(
'%d-%H-%M-%S', gmtime())
logger.info("Feature Group Name: %s", feature_group_name)
# Check if feature group already exists. Create a feature group if doesn't exist.
if feature_group_exist(feature_group_name) == False:
logger.info("Feature Group: %s doesn't exist. Create a new one.",
feature_group)
feature_group = FeatureGroup(name=feature_group_name,
sagemaker_session=feature_store_session)
# append EventTime feature
# load feature definitions to the feature group. SageMaker FeatureStore Python SDK will auto-detect the data schema based on input data.
feature_group.load_feature_definitions(data_frame=df_data)
# output is suppressed
feature_group.create(
s3_uri=f"s3://{default_bucket}/{prefix}",
record_identifier_name=record_identifier_feature_name,
event_time_feature_name=event_time_feature_name,
role_arn=get_execution_role(),
enable_online_store=True)
wait_for_feature_group_creation_complete(feature_group=feature_group)
feature_group.describe()
else:
logger.info("Feature Group: %s exits", feature_group)
# Init feature group object if already exists
feature_group = FeatureGroup(name=feature_group_name,
sagemaker_session=feature_store_session)
# ingest data into feature store
feature_group.ingest(data_frame=df_data, max_workers=5, wait=True)
def create_or_load_feature_group(prefix, feature_group_name):
# Feature Definitions for our records
feature_definitions = [
FeatureDefinition(feature_name="input_ids", feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name="input_mask", feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name="segment_ids", feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name="label_id", feature_type=FeatureTypeEnum.INTEGRAL),
FeatureDefinition(feature_name="review_id", feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name="date", feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name="label", feature_type=FeatureTypeEnum.INTEGRAL),
# FeatureDefinition(feature_name='review_body', feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name="split_type", feature_type=FeatureTypeEnum.STRING),
]
feature_group = FeatureGroup(
name=feature_group_name, feature_definitions=feature_definitions, sagemaker_session=sagemaker_session
)
print("Feature Group: {}".format(feature_group))
try:
print(
"Waiting for existing Feature Group to become available if it is being created by another instance in our cluster..."
)
wait_for_feature_group_creation_complete(feature_group)
except Exception as e:
print("Before CREATE FG wait exeption: {}".format(e))
# pass
try:
record_identifier_feature_name = "review_id"
event_time_feature_name = "date"
print("Creating Feature Group with role {}...".format(role))
feature_group.create(
s3_uri=f"s3://{bucket}/{prefix}",
record_identifier_name=record_identifier_feature_name,
event_time_feature_name=event_time_feature_name,
role_arn=role,
enable_online_store=True,
)
print("Creating Feature Group. Completed.")
print("Waiting for new Feature Group to become available...")
wait_for_feature_group_creation_complete(feature_group)
print("Feature Group available.")
feature_group.describe()
except Exception as e:
print("Exception: {}".format(e))
return feature_group
def test_ingest_without_string_feature(
feature_store_session,
role,
feature_group_name,
offline_store_s3_uri,
pandas_data_frame_without_string,
):
feature_group = FeatureGroup(name=feature_group_name,
sagemaker_session=feature_store_session)
feature_group.load_feature_definitions(
data_frame=pandas_data_frame_without_string)
with cleanup_feature_group(feature_group):
output = feature_group.create(
s3_uri=offline_store_s3_uri,
record_identifier_name="feature1",
event_time_feature_name="feature2",
role_arn=role,
enable_online_store=True,
)
_wait_for_feature_group_create(feature_group)
ingestion_manager = feature_group.ingest(
data_frame=pandas_data_frame_without_string,
max_workers=3,
wait=False)
ingestion_manager.wait()
assert output["FeatureGroupArn"].endswith(
f"feature-group/{feature_group_name}")
def test_ingest_multi_process(
feature_store_session,
role,
feature_group_name,
offline_store_s3_uri,
pandas_data_frame,
):
feature_group = FeatureGroup(name=feature_group_name,
sagemaker_session=feature_store_session)
feature_group.load_feature_definitions(data_frame=pandas_data_frame)
with cleanup_feature_group(feature_group):
output = feature_group.create(
s3_uri=offline_store_s3_uri,
record_identifier_name="feature1",
event_time_feature_name="feature3",
role_arn=role,
enable_online_store=True,
)
_wait_for_feature_group_create(feature_group)
feature_group.ingest(data_frame=pandas_data_frame,
max_workers=3,
max_processes=2,
wait=True)
assert output["FeatureGroupArn"].endswith(
f"feature-group/{feature_group_name}")
def create_feature_group(
feature_group_name,
feature_group_description,
df,
id_name,
event_time_name,
offline_feature_group_bucket,
sagemaker_session,
role,
):
"""
Create a new FeatureGroup.
:param feature_group_name: str
:param feature_group_description: str
:param df: pandas.DataFrame
:param id_name: str
:param event_time_name: str
:param offline_feature_group_bucket: str
:param sagemaker_session: sagemaker.Session()
:param role: str
:return: tuple(FeatureGroup, bool)
"""
feature_group = FeatureGroup(name=feature_group_name,
sagemaker_session=sagemaker_session)
feature_definitions = get_feature_definitions(df, feature_group)
feature_group.feature_definitions = feature_definitions
feature_group_already_exists = False
try:
print(f"Trying to create feature group {feature_group_description} \n")
feature_group.create(
description=feature_group_description,
record_identifier_name=id_name,
event_time_feature_name=event_time_name,
role_arn=role,
s3_uri=offline_feature_group_bucket,
enable_online_store=True,
)
wait_for_feature_group_creation_complete(feature_group)
except Exception as e:
code = e.response.get("Error").get("Code")
if code == "ResourceInUse":
print(f"Using existing feature group: {feature_group_name}")
feature_group_already_exists = True
else:
raise (e)
return feature_group, feature_group_already_exists
def test_create_feature_store(
feature_store_session,
role,
feature_group_name,
offline_store_s3_uri,
pandas_data_frame,
record,
create_table_ddl,
):
feature_group = FeatureGroup(name=feature_group_name,
sagemaker_session=feature_store_session)
feature_group.load_feature_definitions(data_frame=pandas_data_frame)
with cleanup_feature_group(feature_group):
output = feature_group.create(
s3_uri=offline_store_s3_uri,
record_identifier_name="feature1",
event_time_feature_name="feature3",
role_arn=role,
enable_online_store=True,
)
_wait_for_feature_group_create(feature_group)
# Ingest data
feature_group.put_record(record=record)
ingestion_manager = feature_group.ingest(data_frame=pandas_data_frame,
max_workers=3,
wait=False)
ingestion_manager.wait()
assert 0 == len(ingestion_manager.failed_rows)
# Query the integrated Glue table.
athena_query = feature_group.athena_query()
df = DataFrame()
with timeout(minutes=10):
while df.shape[0] < 11:
athena_query.run(
query_string=f'SELECT * FROM "{athena_query.table_name}"',
output_location=f"{offline_store_s3_uri}/query_results",
)
athena_query.wait()
assert "SUCCEEDED" == athena_query.get_query_execution().get(
"QueryExecution").get("Status").get("State")
df = athena_query.as_dataframe()
print(f"Found {df.shape[0]} records.")
time.sleep(60)
assert df.shape[0] == 11
nans = pd.isna(df.loc[df["feature1"].isin([5, 6, 7, 8,
9])]["feature4"])
for is_na in nans.items():
assert is_na
assert (create_table_ddl.format(
feature_group_name=feature_group_name,
region=feature_store_session.boto_session.region_name,
account=feature_store_session.account_id(),
) == feature_group.as_hive_ddl())
assert output["FeatureGroupArn"].endswith(
f"feature-group/{feature_group_name}")
def test_feature_store_create(
sagemaker_session_mock, role_arn, feature_group_dummy_definitions, s3_uri
):
feature_group = FeatureGroup(name="MyFeatureGroup", sagemaker_session=sagemaker_session_mock)
feature_group.feature_definitions = feature_group_dummy_definitions
feature_group.create(
s3_uri=s3_uri,
record_identifier_name="feature1",
event_time_feature_name="feature2",
role_arn=role_arn,
enable_online_store=True,
)
assert sagemaker_session_mock.create_feature_group.called_with(
feature_group_name="MyFeatureGroup",
record_identifier_name="feature1",
event_time_feature_name="feature2",
role_arn=role_arn,
online_store_config={"EnableOnlineStore": True},
feature_definitions=[fd.to_dict() for fd in feature_group_dummy_definitions],
)
def test_create_feature_store_online_only(
feature_store_session,
role,
feature_group_name,
pandas_data_frame,
):
feature_group = FeatureGroup(name=feature_group_name, sagemaker_session=feature_store_session)
feature_group.load_feature_definitions(data_frame=pandas_data_frame)
with cleanup_feature_group(feature_group):
output = feature_group.create(
s3_uri=False,
record_identifier_name="feature1",
event_time_feature_name="feature3",
role_arn=role,
enable_online_store=True,
)
_wait_for_feature_group_create(feature_group)
assert output["FeatureGroupArn"].endswith(f"feature-group/{feature_group_name}")
data['review_id'] = data['review_id'].astype('str').astype('string')
data['product_id'] = data['product_id'].astype('str').astype('string')
data['review_body'] = data['review_body'].astype('str').astype('string')
data['label'] = data['label'].astype('str').astype('string')
data['star_rating'] = data['star_rating'].astype('int64')
data['event_time'] = data['event_time'].astype('float64')
# Load feature definitions
feature_group.load_feature_definitions(data_frame=data)
# Create feature group
feature_group.create(
s3_uri='s3://{}/{}'.format(bucket, prefix),
record_identifier_name=record_identifier_feature_name,
event_time_feature_name=event_time_feature_name,
role_arn=role,
enable_online_store=True,
description="1.8M+ tokenized camera reviews from the Amazon Customer Reviews dataset",
tags=[
{ 'Key': 'Dataset', 'Value': 'amazon customer reviews' },
{ 'Key': 'Subset', 'Value': 'cameras' },
{ 'Key': 'Owner', 'Value': 'Julien Simon' }
]
)
# Wait for feature group to be ready
while feature_group.describe().get("FeatureGroupStatus") != 'Created':
sleep(1)
print('Feature group created')
# Ingest data
print('Ingesting data...')
try:
feature_group.ingest(data_frame=data, max_workers=max_workers, wait=True)
def create_or_load_feature_group(prefix, feature_group_name):
# Feature Definitions for our records
feature_definitions = [
FeatureDefinition(feature_name='input_ids',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='input_mask',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='segment_ids',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='label_id',
feature_type=FeatureTypeEnum.INTEGRAL),
FeatureDefinition(feature_name='review_id',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='date',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='label',
feature_type=FeatureTypeEnum.INTEGRAL),
# FeatureDefinition(feature_name='review_body', feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='split_type',
feature_type=FeatureTypeEnum.STRING)
]
feature_group = FeatureGroup(name=feature_group_name,
feature_definitions=feature_definitions,
sagemaker_session=sagemaker_session)
print('Feature Group: {}'.format(feature_group))
try:
print(
'Waiting for existing Feature Group to become available if it is being created by another instance in our cluster...'
)
wait_for_feature_group_creation_complete(feature_group)
except Exception as e:
print('Before CREATE FG wait exeption: {}'.format(e))
# pass
try:
record_identifier_feature_name = "review_id"
event_time_feature_name = "date"
print('Creating Feature Group with role {}...'.format(role))
feature_group.create(
s3_uri=f"s3://{bucket}/{prefix}",
record_identifier_name=record_identifier_feature_name,
event_time_feature_name=event_time_feature_name,
role_arn=role,
enable_online_store=True)
print('Creating Feature Group. Completed.')
print('Waiting for new Feature Group to become available...')
wait_for_feature_group_creation_complete(feature_group)
print('Feature Group available.')
feature_group.describe()
except Exception as e:
print('Exception: {}'.format(e))
# pass
# print('FAILED - NOW Creating Feature Group with service-role {}...'.format('arn:aws:iam::231218423789:role/service-role/AmazonSageMakerServiceCatalogProductsUseRole'))
# feature_group.create(
# s3_uri=f"s3://{bucket}/{prefix}",
# record_identifier_name=record_identifier_feature_name,
# event_time_feature_name=event_time_feature_name,
# role_arn='arn:aws:iam::231218423789:role/service-role/AmazonSageMakerServiceCatalogProductsUseRole',
# enable_online_store=True
# )
# print('Creating Feature Group. Completed.')
# feature_group.describe()
return feature_group
def create_or_load_feature_group(prefix, feature_group_name):
# Feature Definitions for the records
feature_definitions = [
FeatureDefinition(feature_name='review_id',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='date',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='sentiment',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='label_id',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='input_ids',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='review_body',
feature_type=FeatureTypeEnum.STRING),
FeatureDefinition(feature_name='split_type',
feature_type=FeatureTypeEnum.STRING)
]
# setup the Feature Group
feature_group = FeatureGroup(name=feature_group_name,
feature_definitions=feature_definitions,
sagemaker_session=sagemaker_session)
print('Feature Group: {}'.format(feature_group))
try:
print(
'Waiting for existing Feature Group to become available if it is being created by another instance in our cluster...'
)
wait_for_feature_group_creation_complete(feature_group)
except Exception as e:
print('Before CREATE FG wait exeption: {}'.format(e))
try:
record_identifier_feature_name = "review_id"
event_time_feature_name = "date"
print('Creating Feature Group with role {}...'.format(role))
# create Feature Group
feature_group.create(
s3_uri=f"s3://{bucket}/{prefix}",
record_identifier_name=record_identifier_feature_name,
event_time_feature_name=event_time_feature_name,
role_arn=role,
enable_online_store=False)
print('Creating Feature Group. Completed.')
print('Waiting for new Feature Group to become available...')
wait_for_feature_group_creation_complete(feature_group)
print('Feature Group available.')
# the information about the Feature Group
feature_group.describe()
except Exception as e:
print('Exception: {}'.format(e))
return feature_group
def test_one_step_ingestion_pipeline(sagemaker_session, feature_store_session,
feature_definitions, role, pipeline_name):
instance_count = ParameterInteger(name="InstanceCount", default_value=1)
instance_type = ParameterString(name="InstanceType",
default_value="ml.m5.4xlarge")
input_name = "features.csv"
input_file_path = os.path.join(DATA_DIR, "workflow", "features.csv")
input_data_uri = os.path.join("s3://", sagemaker_session.default_bucket(),
"py-sdk-ingestion-test-input/features.csv")
with open(input_file_path, "r") as data:
body = data.read()
S3Uploader.upload_string_as_file_body(
body=body,
desired_s3_uri=input_data_uri,
sagemaker_session=sagemaker_session)
inputs = [
ProcessingInput(
input_name=input_name,
source=input_data_uri,
destination="/opt/ml/processing/features.csv",
)
]
feature_group_name = f"py-sdk-integ-fg-{int(time.time() * 10**7)}"
feature_group = FeatureGroup(
name=feature_group_name,
feature_definitions=feature_definitions,
sagemaker_session=feature_store_session,
)
ingestion_only_flow, output_name = generate_data_ingestion_flow_from_s3_input(
input_name,
input_data_uri,
s3_content_type="csv",
s3_has_header=True,
)
outputs = [
ProcessingOutput(
output_name=output_name,
app_managed=True,
feature_store_output=FeatureStoreOutput(
feature_group_name=feature_group_name),
)
]
temp_flow_path = "./ingestion.flow"
with cleanup_feature_group(feature_group):
json.dump(ingestion_only_flow, open(temp_flow_path, "w"))
data_wrangler_processor = DataWranglerProcessor(
role=role,
data_wrangler_flow_source=temp_flow_path,
instance_count=instance_count,
instance_type=instance_type,
sagemaker_session=sagemaker_session,
max_runtime_in_seconds=86400,
)
data_wrangler_step = ProcessingStep(name="ingestion-step",
processor=data_wrangler_processor,
inputs=inputs,
outputs=outputs)
pipeline = Pipeline(
name=pipeline_name,
parameters=[instance_count, instance_type],
steps=[data_wrangler_step],
sagemaker_session=sagemaker_session,
)
try:
response = pipeline.create(role)
create_arn = response["PipelineArn"]
offline_store_s3_uri = os.path.join(
"s3://", sagemaker_session.default_bucket(),
feature_group_name)
feature_group.create(
s3_uri=offline_store_s3_uri,
record_identifier_name="f11",
event_time_feature_name="f10",
role_arn=role,
enable_online_store=False,
)
_wait_for_feature_group_create(feature_group)
execution = pipeline.start()
response = execution.describe()
assert response["PipelineArn"] == create_arn
try:
execution.wait(delay=60, max_attempts=10)
except WaiterError:
pass
execution_steps = execution.list_steps()
assert len(execution_steps) == 1
assert execution_steps[0]["StepName"] == "ingestion-step"
assert execution_steps[0]["StepStatus"] == "Succeeded"
athena_query = feature_group.athena_query()
with timeout(minutes=10):
athena_query.run(
query_string=f'SELECT * FROM "{athena_query.table_name}"',
output_location=f"{offline_store_s3_uri}/query_results",
)
athena_query.wait()
assert "SUCCEEDED" == athena_query.get_query_execution().get(
"QueryExecution").get("Status").get("State")
df = athena_query.as_dataframe()
assert pd.read_csv(input_file_path).shape[0] == df.shape[0]
finally:
try:
pipeline.delete()
except Exception as e:
print(f"Delete pipeline failed with error: {e}")
os.remove(temp_flow_path)
class FeatureGroupDataSet(AbstractDataSet):
def __init__(
self,
name: str,
s3_uri: str,
record_identifier_name: str,
event_time_name: str,
query: str,
description: str = None,
):
region = boto3.Session().region_name
boto_session = boto3.Session(region_name=region)
sagemaker_client = boto_session.client(
service_name="sagemaker", region_name=region
)
featurestore_runtime = boto_session.client(
service_name="sagemaker-featurestore-runtime", region_name=region
)
feature_store_session = Session(
boto_session=boto_session,
sagemaker_client=sagemaker_client,
sagemaker_featurestore_runtime_client=featurestore_runtime,
)
iam = boto3.client("iam")
role = iam.get_role(RoleName="AmazonSageMaker-ExecutionRole")["Role"]["Arn"]
# you can also suffix the feature group name with pipeline git version
self._feature_group = FeatureGroup(
name=name, sagemaker_session=feature_store_session
)
self._description = description
self._s3_uri = s3_uri
self._role = role
self._record_identifier_name = record_identifier_name
self._event_time_name = event_time_name
self._query = query
def _wait_for_feature_group_creation_complete(self):
status = self._feature_group.describe().get("FeatureGroupStatus")
while status == "Creating":
logger.info("Waiting for Feature Group Creation")
time.sleep(5)
status = self._feature_group.describe().get("FeatureGroupStatus")
if status != "Created":
raise RuntimeError(
f"Failed to create feature group {self._feature_group.name}"
)
logger.info("FeatureGroup %s successfully created.", self._feature_group.name)
def _describe(self):
return dict(feature_group=self._feature_group)
def _save(self, data):
self._feature_group.load_feature_definitions(data)
try:
self._feature_group.create(
description=self._description,
s3_uri=self._s3_uri,
record_identifier_name=self._record_identifier_name,
event_time_feature_name=self._event_time_name,
role_arn=self._role,
enable_online_store=True,
)
self._wait_for_feature_group_creation_complete()
except Exception as exc:
if (
f"Resource Already Exists: FeatureGroup with name {self._feature_group.name} already exists"
in str(exc)
):
pass
else:
raise
self._feature_group.ingest(data[:10]) # just for demo purpose
def _load(self) -> pd.DataFrame:
query = self._feature_group.athena_query()
print(self._query.format(table_name=query.table_name))
query.run(
self._query.format(table_name=query.table_name),
output_location=f"{self._s3_uri}/query_results/",
)
query.wait()
return query.as_dataframe()
