langtest.transform.bias.BaseBias#
- class BaseBias#
Bases:
ABC
Abstract base class for implementing bias measures.
- alias_name#
A name or list of names that identify the bias measure.
- Type:
str
- transform(data
List[Sample]) -> Any: Transforms the input data into an output based on the implemented bias measure.
- __init__()#
Methods
__init__
()async_run
(sample_list, model, **kwargs)Abstract method that implements the creation of an asyncio task for the bias measure.
run
(sample_list, model, **kwargs)Abstract method that implements the bias measure.
transform
(sample_list, *args, **kwargs)Abstract method that implements the bias measure.
Attributes
supported_tasks
test_types
- async classmethod async_run(sample_list: List[Sample], model: ModelAPI, **kwargs)#
Abstract method that implements the creation of an asyncio task for the bias measure.
- Parameters:
sample_list (List[Sample]) – The input data to be transformed.
model (ModelAPI) – The model to be used for the bias measure.
- Returns:
The asyncio task for the bias measure.
- Return type:
asyncio.Task
- abstract async static run(sample_list: List[Sample], model: ModelAPI, **kwargs) List[Sample] #
Abstract method that implements the bias measure.
- Parameters:
sample_list (List[Sample]) – The input data to be transformed.
model (ModelAPI) – The model to be used for the bias measure.
- Returns:
The transformed data based on the implemented bias measure.
- Return type:
List[Sample]
- abstract transform(sample_list: List[Sample], *args, **kwargs) List[Sample] #
Abstract method that implements the bias measure.
- Parameters:
sample_list (List[Sample]) – The input data to be transformed.
- Returns:
The transformed data based on the implemented bias measure.
- Return type:
List[Sample]