featurebyte.FeatureList.compute_historical_feature_table¶
compute_historical_feature_table(
observation_set: Union[ObservationTable, DataFrame],
historical_feature_table_name: str,
serving_names_mapping: Optional[Dict[str, str]]=None
) -> HistoricalFeatureTableDescription¶
Materialize feature list using an observation table asynchronously. The historical features will be materialized into a historical feature table.
Parameters¶
- observation_set: Union[ObservationTable, DataFrame]
Observation set withPOINT_IN_TIME
and serving names columns. This can be either an ObservationTable or a pandas DataFrame. - historical_feature_table_name: str
Name of the historical feature table to be created - serving_names_mapping: Optional[Dict[str, str]]
Optional serving names mapping if the training events table has different serving name
Returns¶
- HistoricalFeatureTable
Examples¶
>>> # Get the desired observation table
>>> observation_table = catalog.get_observation_table(<observation_table_name>)
>>> # Get the desired feature list
>>> my_feature_list = catalog.get_feature_list(<feature_list_name>)
>>> # Decide the name of the historical feature table
>>> training_table_name = (
... '2y Features for Customer Purchase next 2w '
... 'up to end 22 with Improved Feature List'
... )