featurebyte.Target.compute_targets

compute_targets(

observation_table: Union[ObservationTable, DataFrame],

serving_names_mapping: Union[Dict[str, str], NoneType]=None,

skip_entity_validation_checks: bool=False

) -> DataFrame

Description

Returns a DataFrame with target values for analysis, model training, or evaluation. The target request data consists of an observation set that combines points-in-time and key values of the primary entity from the target.

Associated serving entities can also be utilized.

Parameters

• observation_table: Union[ObservationTable, DataFrame]
  Observation set DataFrame or ObservationTable object, which combines points-in-time and values of the target primary entity or its descendant (serving entities). The column containing the point-in-time values should be named POINT_IN_TIME, while the columns representing entity values should be named using accepted serving names for the entity.
  
  
• serving_names_mapping: Union[Dict[str, str], NoneType]
  Optional serving names mapping if the training events table has different serving name columns than those defined in Entities, mapping from original serving name to new name.
  
  
• skip_entity_validation_checks: bool
  default: False
  Whether to skip entity validation checks.
  
  

Returns

• DataFrame
  Materialized target.

Note: POINT_IN_TIME values will be converted to UTC time.

Examples

>>> target = catalog.get_target("target")
>>> target.compute_targets(observation_table)