merlin_standard_lib.schema package

Submodules

merlin_standard_lib.schema.schema module

class merlin_standard_lib.schema.schema.ColumnSchema(name: str = <betterproto._PLACEHOLDER object>, deprecated: bool = <betterproto._PLACEHOLDER object>, presence: merlin_standard_lib.proto.schema_bp.FeaturePresence = <betterproto._PLACEHOLDER object>, group_presence: merlin_standard_lib.proto.schema_bp.FeaturePresenceWithinGroup = <betterproto._PLACEHOLDER object>, shape: merlin_standard_lib.proto.schema_bp.FixedShape = <betterproto._PLACEHOLDER object>, value_count: merlin_standard_lib.proto.schema_bp.ValueCount = <betterproto._PLACEHOLDER object>, value_counts: merlin_standard_lib.proto.schema_bp.ValueCountList = <betterproto._PLACEHOLDER object>, type: merlin_standard_lib.proto.schema_bp.FeatureType = <betterproto._PLACEHOLDER object>, domain: str = <betterproto._PLACEHOLDER object>, int_domain: merlin_standard_lib.proto.schema_bp.IntDomain = <betterproto._PLACEHOLDER object>, float_domain: merlin_standard_lib.proto.schema_bp.FloatDomain = <betterproto._PLACEHOLDER object>, string_domain: merlin_standard_lib.proto.schema_bp.StringDomain = <betterproto._PLACEHOLDER object>, bool_domain: merlin_standard_lib.proto.schema_bp.BoolDomain = <betterproto._PLACEHOLDER object>, struct_domain: merlin_standard_lib.proto.schema_bp.StructDomain = <betterproto._PLACEHOLDER object>, natural_language_domain: merlin_standard_lib.proto.schema_bp.NaturalLanguageDomain = <betterproto._PLACEHOLDER object>, image_domain: merlin_standard_lib.proto.schema_bp.ImageDomain = <betterproto._PLACEHOLDER object>, mid_domain: merlin_standard_lib.proto.schema_bp.MIDDomain = <betterproto._PLACEHOLDER object>, url_domain: merlin_standard_lib.proto.schema_bp.URLDomain = <betterproto._PLACEHOLDER object>, time_domain: merlin_standard_lib.proto.schema_bp.TimeDomain = <betterproto._PLACEHOLDER object>, time_of_day_domain: merlin_standard_lib.proto.schema_bp.TimeOfDayDomain = <betterproto._PLACEHOLDER object>, distribution_constraints: merlin_standard_lib.proto.schema_bp.DistributionConstraints = <betterproto._PLACEHOLDER object>, annotation: merlin_standard_lib.proto.schema_bp.Annotation = <betterproto._PLACEHOLDER object>, skew_comparator: merlin_standard_lib.proto.schema_bp.FeatureComparator = <betterproto._PLACEHOLDER object>, drift_comparator: merlin_standard_lib.proto.schema_bp.FeatureComparator = <betterproto._PLACEHOLDER object>, in_environment: List[str] = <betterproto._PLACEHOLDER object>, not_in_environment: List[str] = <betterproto._PLACEHOLDER object>, lifecycle_stage: merlin_standard_lib.proto.schema_bp.LifecycleStage = <betterproto._PLACEHOLDER object>, unique_constraints: merlin_standard_lib.proto.schema_bp.UniqueConstraints = <betterproto._PLACEHOLDER object>)

Bases: merlin_standard_lib.proto.schema_bp.Feature

classmethod create_categorical(name: str, num_items: int, shape: Optional[Union[Tuple[int, …], List[int]]] = None, value_count: Optional[Union[merlin_standard_lib.proto.schema_bp.ValueCount, merlin_standard_lib.proto.schema_bp.ValueCountList]] = None, min_index: int = 0, tags: Optional[Union[List[str], List[merlin_standard_lib.schema.tag.Tag], List[Union[merlin_standard_lib.schema.tag.Tag, str]]]] = None, **kwargs) → merlin_standard_lib.schema.schema.ColumnSchema

classmethod create_continuous(name: str, is_float: bool = True, min_value: Optional[Union[int, float]] = None, max_value: Optional[Union[int, float]] = None, disallow_nan: bool = False, disallow_inf: bool = False, is_embedding: bool = False, shape: Optional[Union[Tuple[int, …], List[int]]] = None, value_count: Optional[Union[merlin_standard_lib.proto.schema_bp.ValueCount, merlin_standard_lib.proto.schema_bp.ValueCountList]] = None, tags: Optional[Union[List[str], List[merlin_standard_lib.schema.tag.Tag], List[Union[merlin_standard_lib.schema.tag.Tag, str]]]] = None, **kwargs) → merlin_standard_lib.schema.schema.ColumnSchema

copy(**kwargs) → merlin_standard_lib.schema.schema.ColumnSchema

with_name(name: str)

with_tags(tags: Union[List[str], List[merlin_standard_lib.schema.tag.Tag], List[Union[merlin_standard_lib.schema.tag.Tag, str]]]) → merlin_standard_lib.schema.schema.ColumnSchema

with_tags_based_on_properties(using_value_count=True, using_domain=True) → merlin_standard_lib.schema.schema.ColumnSchema

with_properties(properties: Dict[str, Union[str, int, float]]) → merlin_standard_lib.schema.schema.ColumnSchema

to_proto_text() → str

property tags

property properties

class merlin_standard_lib.schema.schema.Schema(feature: Sequence[merlin_standard_lib.proto.schema_bp.Feature] = <betterproto._PLACEHOLDER object>, sparse_feature: List[merlin_standard_lib.proto.schema_bp.SparseFeature] = <betterproto._PLACEHOLDER object>, weighted_feature: List[merlin_standard_lib.proto.schema_bp.WeightedFeature] = <betterproto._PLACEHOLDER object>, string_domain: List[merlin_standard_lib.proto.schema_bp.StringDomain] = <betterproto._PLACEHOLDER object>, float_domain: List[merlin_standard_lib.proto.schema_bp.FloatDomain] = <betterproto._PLACEHOLDER object>, int_domain: List[merlin_standard_lib.proto.schema_bp.IntDomain] = <betterproto._PLACEHOLDER object>, default_environment: List[str] = <betterproto._PLACEHOLDER object>, annotation: merlin_standard_lib.proto.schema_bp.Annotation = <betterproto._PLACEHOLDER object>, dataset_constraints: merlin_standard_lib.proto.schema_bp.DatasetConstraints = <betterproto._PLACEHOLDER object>, tensor_representation_group: Dict[str, merlin_standard_lib.proto.schema_bp.TensorRepresentationGroup] = <betterproto._PLACEHOLDER object>)

Bases: merlin_standard_lib.proto.schema_bp._Schema

A collection of column schemas for a dataset.

feature: List[merlin_standard_lib.schema.schema.ColumnSchema] = Field(name=None,type=None,default=<betterproto._PLACEHOLDER object>,default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'betterproto': FieldMetadata(number=1, proto_type='message', map_types=None, group=None, wraps=None)}),_field_type=None)

classmethod create(column_schemas: Optional[Union[List[Union[merlin_standard_lib.schema.schema.ColumnSchema, str]], Dict[str, Union[merlin_standard_lib.schema.schema.ColumnSchema, str]]]] = None, **kwargs)

with_tags_based_on_properties(using_value_count=True, using_domain=True) → merlin_standard_lib.schema.schema.Schema

apply(selector) → merlin_standard_lib.schema.schema.Schema

apply_inverse(selector) → merlin_standard_lib.schema.schema.Schema

filter_columns_from_dict(input_dict)

select_by_type(to_select) → merlin_standard_lib.schema.schema.Schema

remove_by_type(to_remove) → merlin_standard_lib.schema.schema.Schema

select_by_tag(to_select) → merlin_standard_lib.schema.schema.Schema

remove_by_tag(to_remove) → merlin_standard_lib.schema.schema.Schema

select_by_name(to_select) → merlin_standard_lib.schema.schema.Schema

remove_by_name(to_remove) → merlin_standard_lib.schema.schema.Schema

map_column_schemas(map_fn: Callable[[merlin_standard_lib.schema.schema.ColumnSchema], merlin_standard_lib.schema.schema.ColumnSchema]) → merlin_standard_lib.schema.schema.Schema

filter_column_schemas(filter_fn: Callable[[merlin_standard_lib.schema.schema.ColumnSchema], bool], negate=False) → merlin_standard_lib.schema.schema.Schema

categorical_cardinalities() → Dict[str, int]

property column_names

property column_schemas

property item_id_column_name

from_json(value: Union[str, bytes]) → merlin_standard_lib.schema.schema.Schema

to_proto_text() → str

from_proto_text(path_or_proto_text: str) → merlin_standard_lib.schema.schema.Schema

copy(**kwargs) → merlin_standard_lib.schema.schema.Schema

add(other, allow_overlap=True) → merlin_standard_lib.schema.schema.Schema

merlin_standard_lib.schema.tag module

class merlin_standard_lib.schema.tag.Tag(value)

Bases: enum.Enum

An enumeration.

CATEGORICAL = 'categorical'

CONTINUOUS = 'continuous'

LIST = 'list'

TEXT = 'text'

TEXT_TOKENIZED = 'text_tokenized'

TIME = 'time'

USER = 'user'

USER_ID = 'user_id'

ITEM = 'item'

ITEM_ID = 'item_id'

SESSION = 'session'

SESSION_ID = 'session_id'

CONTEXT = 'context'

TARGETS = 'target'

BINARY_CLASSIFICATION = 'binary_classification'

MULTI_CLASS_CLASSIFICATION = 'multi_class'

REGRESSION = 'regression'

Module contents