def __init__(
self,
featurestore_id,
featurestore_name,
created,
hdfs_store_path,
project_name,
project_id,
featurestore_description,
inode_id,
offline_featurestore_name,
hive_endpoint,
online_enabled,
num_feature_groups=None,
num_training_datasets=None,
num_storage_connectors=None,
online_featurestore_name=None,
mysql_server_endpoint=None,
online_featurestore_size=None,
):
self._id = featurestore_id
self._name = featurestore_name
self._created = created
self._hdfs_store_path = hdfs_store_path
self._project_name = project_name
self._project_id = project_id
self._description = featurestore_description
self._inode_id = inode_id
self._online_feature_store_name = online_featurestore_name
self._online_feature_store_size = online_featurestore_size
self._offline_feature_store_name = offline_featurestore_name
self._hive_endpoint = hive_endpoint
self._mysql_server_endpoint = mysql_server_endpoint
self._online_enabled = online_enabled
self._num_feature_groups = num_feature_groups
self._num_training_datasets = num_training_datasets
self._num_storage_connectors = num_storage_connectors
self._feature_group_api = feature_group_api.FeatureGroupApi(self._id)
self._storage_connector_api = storage_connector_api.StorageConnectorApi(
self._id)
self._training_dataset_api = training_dataset_api.TrainingDatasetApi(
self._id)
self._expectations_api = expectations_api.ExpectationsApi(self._id)
self._feature_group_engine = feature_group_engine.FeatureGroupEngine(
self._id)
self._transformation_function_engine = (
transformation_function_engine.TransformationFunctionEngine(
self._id))
self._feature_view_engine = feature_view_engine.FeatureViewEngine(
self._id)
def __init__(
self,
featurestore_id,
featurestore_name,
created,
hdfs_store_path,
project_name,
project_id,
featurestore_description,
inode_id,
offline_featurestore_name,
hive_endpoint,
online_enabled,
online_featurestore_name=None,
mysql_server_endpoint=None,
online_featurestore_size=None,
):
self._id = featurestore_id
self._name = featurestore_name
self._created = created
self._hdfs_store_path = hdfs_store_path
self._project_name = project_name
self._project_id = project_id
self._description = featurestore_description
self._inode_id = inode_id
self._online_feature_store_name = online_featurestore_name
self._online_feature_store_size = online_featurestore_size
self._offline_feature_store_name = offline_featurestore_name
self._hive_endpoint = hive_endpoint
self._mysql_server_endpoint = mysql_server_endpoint
self._online_enabled = online_enabled
self._feature_group_api = feature_group_api.FeatureGroupApi(self._id)
self._storage_connector_api = storage_connector_api.StorageConnectorApi(
self._id)
self._training_dataset_api = training_dataset_api.TrainingDatasetApi(
self._id)
self._feature_group_engine = feature_group_engine.FeatureGroupEngine(
self._id)
def __init__(
self,
name,
version,
featurestore_id,
description="",
partition_key=None,
primary_key=None,
hudi_precombine_key=None,
featurestore_name=None,
created=None,
creator=None,
id=None,
features=None,
location=None,
online_enabled=False,
time_travel_format=None,
statistics_config=None,
validation_type="NONE",
expectations=None,
):
super().__init__(featurestore_id)
self._feature_store_id = featurestore_id
self._feature_store_name = featurestore_name
self._description = description
self._created = created
self._creator = creator
self._version = version
self._name = name
self._id = id
self._features = [
feature.Feature.from_response_json(feat)
if isinstance(feat, dict) else feat for feat in features
]
self._location = location
self._online_enabled = online_enabled
self._time_travel_format = (time_travel_format.upper() if
time_travel_format is not None else None)
if id is not None:
# initialized by backend
self._primary_key = [
feat.name for feat in self._features if feat.primary is True
]
self._partition_key = [
feat.name for feat in self._features if feat.partition is True
]
if time_travel_format is not None and time_travel_format.upper(
) == "HUDI":
# hudi precombine key is always a single feature
self._hudi_precombine_key = [
feat.name for feat in self._features
if feat.hudi_precombine_key is True
][0]
else:
self._hudi_precombine_key = None
self.statistics_config = statistics_config
else:
# initialized by user
self.primary_key = primary_key
self.partition_key = partition_key
self._hudi_precombine_key = (
hudi_precombine_key.lower() if hudi_precombine_key is not None
and time_travel_format is not None
and time_travel_format.upper() == "HUDI" else None)
self.statistics_config = statistics_config
self._data_validation_engine = data_validation_engine.DataValidationEngine(
featurestore_id, self.ENTITY_TYPE)
self._validation_type = validation_type.upper()
if expectations is not None:
self._expectations_names = [
expectation.name for expectation in expectations
]
else:
self._expectations_names = []
self._feature_group_engine = feature_group_engine.FeatureGroupEngine(
featurestore_id)
def __init__(
self,
name,
version,
description,
featurestore_id,
partition_key=None,
primary_key=None,
featurestore_name=None,
created=None,
creator=None,
descriptive_statistics=None,
feature_correlation_matrix=None,
features_histogram=None,
cluster_analysis=None,
id=None,
features=None,
location=None,
jobs=None,
desc_stats_enabled=None,
feat_corr_enabled=None,
feat_hist_enabled=None,
cluster_analysis_enabled=None,
statistic_columns=None,
num_bins=None,
num_clusters=None,
corr_method=None,
online_enabled=False,
hudi_enabled=False,
default_storage="offline",
):
self._feature_store_id = featurestore_id
self._feature_store_name = featurestore_name
self._description = description
self._created = created
self._creator = creator
self._version = version
self._descriptive_statistics = descriptive_statistics
self._feature_correlation_matrix = feature_correlation_matrix
self._features_histogram = features_histogram
self._cluster_analysis = cluster_analysis
self._name = name
self._id = id
self._features = [
feature.Feature.from_response_json(feat) for feat in features
]
self._location = location
self._jobs = jobs
self._desc_stats_enabled = desc_stats_enabled
self._feat_corr_enabled = feat_corr_enabled
self._feat_hist_enabled = feat_hist_enabled
self._cluster_analysis_enabled = cluster_analysis_enabled
self._statistic_columns = statistic_columns
self._num_bins = num_bins
self._num_clusters = num_clusters
self._corr_method = corr_method
self._online_enabled = online_enabled
self._default_storage = default_storage
self._hudi_enabled = hudi_enabled
self._primary_key = primary_key
self._partition_key = partition_key
self._feature_group_engine = feature_group_engine.FeatureGroupEngine(
featurestore_id)
def __init__(
self,
name,
version,
featurestore_id,
description="",
partition_key=None,
primary_key=None,
hudi_precombine_key=None,
featurestore_name=None,
created=None,
creator=None,
id=None,
features=None,
location=None,
jobs=None,
desc_stats_enabled=None,
feat_corr_enabled=None,
feat_hist_enabled=None,
statistic_columns=None,
online_enabled=False,
time_travel_format=None,
statistics_config=None,
):
super().__init__(featurestore_id)
self._feature_store_id = featurestore_id
self._feature_store_name = featurestore_name
self._description = description
self._created = created
self._creator = creator
self._version = version
self._name = name
self._id = id
self._features = [
feature.Feature.from_response_json(feat)
if isinstance(feat, dict) else feat for feat in features
]
self._location = location
self._jobs = jobs
self._online_enabled = online_enabled
self._time_travel_format = (time_travel_format.upper() if
time_travel_format is not None else None)
if id is not None:
# initialized by backend
self.statistics_config = StatisticsConfig(
desc_stats_enabled,
feat_corr_enabled,
feat_hist_enabled,
statistic_columns,
)
self._primary_key = [
feat.name for feat in self._features if feat.primary is True
]
self._partition_key = [
feat.name for feat in self._features if feat.partition is True
]
if time_travel_format is not None and time_travel_format.upper(
) == "HUDI":
# hudi precombine key is always a single feature
self._hudi_precombine_key = [
feat.name for feat in self._features
if feat.hudi_precombine_key is True
][0]
else:
self._hudi_precombine_key = None
else:
# initialized by user
self.statistics_config = statistics_config
self._primary_key = primary_key
self._partition_key = partition_key
self._hudi_precombine_key = (
hudi_precombine_key if time_travel_format is not None
and time_travel_format.upper() == "HUDI" else None)
self._feature_group_engine = feature_group_engine.FeatureGroupEngine(
featurestore_id)
def __init__(
self,
name,
version,
description,
featurestore_id,
partition_key=None,
primary_key=None,
featurestore_name=None,
created=None,
creator=None,
id=None,
features=None,
location=None,
jobs=None,
desc_stats_enabled=None,
feat_corr_enabled=None,
feat_hist_enabled=None,
statistic_columns=None,
online_enabled=False,
hudi_enabled=False,
default_storage="offline",
statistics_config=None,
):
self._feature_store_id = featurestore_id
self._feature_store_name = featurestore_name
self._description = description
self._created = created
self._creator = creator
self._version = version
self._name = name
self._id = id
self._features = [
feature.Feature.from_response_json(feat) for feat in features
]
self._location = location
self._jobs = jobs
self._online_enabled = online_enabled
self._default_storage = default_storage
self._hudi_enabled = hudi_enabled
if id is None:
# Initialized from the API
self._primary_key = primary_key
self._partition_key = partition_key
else:
# Initialized from the backend
self._primary_key = [f.name for f in self._features if f.primary]
self._partition_key = [
f.name for f in self._features if f.partition
]
if id is not None:
# initialized by backend
self.statistics_config = StatisticsConfig(
desc_stats_enabled,
feat_corr_enabled,
feat_hist_enabled,
statistic_columns,
)
self._primary_key = [
feat.name for feat in self._features if feat.primary is True
]
self._partition_key = [
feat.name for feat in self._features if feat.partition is True
]
else:
# initialized by user
self.statistics_config = statistics_config
self._primary_key = primary_key
self._partition_key = partition_key
self._feature_group_engine = feature_group_engine.FeatureGroupEngine(
featurestore_id)
self._statistics_engine = statistics_engine.StatisticsEngine(
featurestore_id, self.ENTITY_TYPE)
