featurebyte.ValueBeyondEndpointImputation¶
class ValueBeyondEndpointImputation(
*,
imputed_value: Union[StrictInt, StrictFloat, StrictStr, bool, NoneType]=None,
type: Literal["less_than", "less_than_or_equal", "greater_than", "greater_than_or_equal"],
end_point: Union[StrictInt, StrictFloat, StrictStr, bool]
)Description¶
ValueBeyondEndpointImputation class is used to declare the operation to impute the value when the value in the column exceeds a specified endpoint type.
If the imputed_value parameter is None, the values to impute are replaced by missing values and the corresponding rows are ignored during aggregation operations.
Parameters¶
- imputed_value: Union[StrictInt, StrictFloat, StrictStr, bool, NoneType]
The value that will be used to replace any value that falls outside a specified range. - type: Literal["less_than", "less_than_or_equal", "greater_than", "greater_than_or_equal"]
Determines how the boundary values are treated.
- If type isless_than
, any value that is less than the end_point value will be replaced with imputed_value.
- If type isless_than_or_equal
, any value that is less than or equal to the end_point value will be replaced with imputed_value.
- If type isgreater_than
, any value that is greater than the end_point value will be replaced with imputed_value.
- If type isgreater_than_or_equal
, any value that is greater than or equal to the end_point value will be replaced with imputed_value. - end_point: Union[StrictInt, StrictFloat, StrictStr, bool]
The value that marks the boundary.
Examples¶
Create an imputation rule to replace value less than 0 to 0.
Create an imputation rule to ignore value higher than 1M.