def __init__( self, name, version, description, data_format, location, featurestore_id, storage_connector=None, splits=None, seed=None, cluster_analysis=None, created=None, creator=None, descriptive_statistics=None, feature_correlation_matrix=None, features=None, features_histogram=None, featurestore_name=None, id=None, jobs=None, inode_id=None, storage_connector_name=None, storage_connector_id=None, storage_connector_type=None, training_dataset_type=None, ): self._id = id self._name = name self._version = version self._description = description self._data_format = data_format self._seed = seed self._location = location self._training_dataset_api = training_dataset_api.TrainingDatasetApi( featurestore_id) self._training_dataset_engine = training_dataset_engine.TrainingDatasetEngine( featurestore_id) self._storage_connector_api = storage_connector_api.StorageConnectorApi( featurestore_id) # set up depending on user initialized or coming from backend response if training_dataset_type is None: # no type -> user init self._features = features self.storage_connector = storage_connector self.splits = splits else: # type available -> init from backend response # make rest call to get all connector information, description etc. self._storage_connector = self._storage_connector_api.get_by_id( storage_connector_id, storage_connector_type) self._features = [ feature.Feature.from_response_json(feat) for feat in features ] self._splits = splits self._training_dataset_type = training_dataset_type
def __init__(self, feature_store_id): self._feature_store_id = feature_store_id self._feature_view_api = feature_view_api.FeatureViewApi( feature_store_id) self._tags_api = tags_api.TagsApi(feature_store_id, self.ENTITY_TYPE) self._storage_connector_api = storage_connector_api.StorageConnectorApi( feature_store_id) self._transformation_function_engine = ( transformation_function_engine.TransformationFunctionEngine( feature_store_id)) self._td_code_engine = code_engine.CodeEngine( feature_store_id, self._TRAINING_DATA_API_PATH) self._statistics_engine = statistics_engine.StatisticsEngine( feature_store_id, self._TRAINING_DATA_API_PATH) self._training_dataset_engine = training_dataset_engine.TrainingDatasetEngine( feature_store_id) self._query_constructor_api = query_constructor_api.QueryConstructorApi( )
def __init__( self, name, version, data_format, featurestore_id, location="", event_start_time=None, event_end_time=None, coalesce=False, description=None, storage_connector=None, splits=None, validation_size=None, test_size=None, train_start=None, train_end=None, validation_start=None, validation_end=None, test_start=None, test_end=None, seed=None, created=None, creator=None, features=None, statistics_config=None, featurestore_name=None, id=None, inode_id=None, training_dataset_type=None, from_query=None, querydto=None, label=None, transformation_functions=None, train_split=None, ): self._id = id self._name = name self._version = version self._description = description self._data_format = data_format self._start_time = self._convert_event_time_to_timestamp( event_start_time) self._end_time = self._convert_event_time_to_timestamp(event_end_time) self._validation_size = validation_size self._test_size = test_size self._train_start = train_start self._train_end = train_end self._validation_start = validation_start self._validation_end = validation_end self._test_start = test_start self._test_end = test_end self._coalesce = coalesce self._seed = seed self._location = location self._from_query = from_query self._querydto = querydto self._feature_store_id = featurestore_id self._transformation_functions = transformation_functions self._train_split = train_split self._training_dataset_api = training_dataset_api.TrainingDatasetApi( featurestore_id) self._training_dataset_engine = training_dataset_engine.TrainingDatasetEngine( featurestore_id) self._statistics_engine = statistics_engine.StatisticsEngine( featurestore_id, self.ENTITY_TYPE) self._code_engine = code_engine.CodeEngine(featurestore_id, self.ENTITY_TYPE) self._transformation_function_engine = ( transformation_function_engine.TransformationFunctionEngine( featurestore_id)) if training_dataset_type: self.training_dataset_type = training_dataset_type else: self._training_dataset_type = None # set up depending on user initialized or coming from backend response if created is None: # no type -> user init self._features = features self.storage_connector = storage_connector self.splits = splits self.statistics_config = statistics_config self._label = label if validation_size or test_size: self._train_split = TrainingDatasetSplit.TRAIN self.splits = { TrainingDatasetSplit.TRAIN: 1 - (validation_size or 0) - (test_size or 0), TrainingDatasetSplit.VALIDATION: validation_size, TrainingDatasetSplit.TEST: test_size, } self._set_time_splits( train_start, train_end, validation_start, validation_end, test_start, test_end, ) else: # type available -> init from backend response # make rest call to get all connector information, description etc. self._storage_connector = StorageConnector.from_response_json( storage_connector) if features is None: features = [] self._features = [ training_dataset_feature.TrainingDatasetFeature. from_response_json(feat) for feat in features ] self._splits = [ TrainingDatasetSplit.from_response_json(split) for split in splits ] self._statistics_config = StatisticsConfig.from_response_json( statistics_config) self._label = [ feat.name.lower() for feat in self._features if feat.label ] self._vector_server = vector_server.VectorServer( featurestore_id, features=self._features)
def __init__( self, name, version, data_format, location, featurestore_id, coalesce=False, description=None, storage_connector=None, splits=None, seed=None, created=None, creator=None, features=None, statistics_config=None, featurestore_name=None, id=None, inode_id=None, training_dataset_type=None, from_query=None, querydto=None, label=None, ): self._id = id self._name = name self._version = version self._description = description self._data_format = data_format self._coalesce = coalesce self._seed = seed self._location = location self._from_query = from_query self._querydto = querydto self._feature_store_id = featurestore_id self._prepared_statement_connection = None self._prepared_statements = None self._serving_keys = None self._training_dataset_api = training_dataset_api.TrainingDatasetApi( featurestore_id) self._training_dataset_engine = training_dataset_engine.TrainingDatasetEngine( featurestore_id) self._statistics_engine = statistics_engine.StatisticsEngine( featurestore_id, self.ENTITY_TYPE) # set up depending on user initialized or coming from backend response if training_dataset_type is None: # no type -> user init self._features = features self.storage_connector = storage_connector self.splits = splits self.statistics_config = statistics_config self._label = label else: # type available -> init from backend response # make rest call to get all connector information, description etc. self._storage_connector = StorageConnector.from_response_json( storage_connector) self._features = [ training_dataset_feature.TrainingDatasetFeature. from_response_json(feat) for feat in features ] self._splits = splits self._training_dataset_type = training_dataset_type self._statistics_config = StatisticsConfig.from_response_json( statistics_config) self._label = [ feat.name.lower() for feat in self._features if feat.label ]
def __init__( self, name, version, data_format, location, featurestore_id, description=None, storage_connector=None, splits=None, seed=None, created=None, creator=None, features=None, statistics_config=None, featurestore_name=None, id=None, jobs=None, inode_id=None, storage_connector_name=None, storage_connector_id=None, storage_connector_type=None, training_dataset_type=None, from_query=None, querydto=None, ): self._id = id self._name = name self._version = version self._description = description self._data_format = data_format self._seed = seed self._location = location self._from_query = from_query self._querydto = querydto self._training_dataset_api = training_dataset_api.TrainingDatasetApi( featurestore_id) self._training_dataset_engine = training_dataset_engine.TrainingDatasetEngine( featurestore_id) self._storage_connector_api = storage_connector_api.StorageConnectorApi( featurestore_id) self._statistics_engine = statistics_engine.StatisticsEngine( featurestore_id, self.ENTITY_TYPE) # set up depending on user initialized or coming from backend response if training_dataset_type is None: # no type -> user init self._features = features self.storage_connector = storage_connector self.splits = splits self.statistics_config = statistics_config else: # type available -> init from backend response # make rest call to get all connector information, description etc. self._storage_connector = self._storage_connector_api.get_by_id( storage_connector_id, storage_connector_type) self._features = [ training_dataset_feature.TrainingDatasetFeature. from_response_json(feat) for feat in features ] self._splits = splits self._training_dataset_type = training_dataset_type self.statistics_config = None