Recommender

pnpxai.core.recommender.recommender

CAM_BASED_EXPLAINERS = {GradCam, GuidedGradCam} module-attribute

RecommenderOutput dataclass

detected_architectures: Set[ModuleType] instance-attribute

explainers: list instance-attribute

__init__(detected_architectures: Set[ModuleType], explainers: list) -> None

print_tabular()

RecommendationMap

data = data instance-attribute

headers = headers instance-attribute

__init__(data: Dict[Any, Set[Any]], headers: Sequence[str]) -> None

print_tabular()

XaiRecommender

Recommender class that suggests explainers and evaluation metrics based on the user's input. The recommender analyzes the model architecture and the selected modality to provide the most suitable explainers and detected architecture.

architecture_to_explainers_map = self._build_architecture_to_explainers_map() instance-attribute

__init__()

recommend(modality: Union[Modality, Tuple[Modality]], model: Model) -> RecommenderOutput

Recommends explainers and evaluation metrics based on the user's input.

Args: - modality (Union[Modality], Tuple[Modality]): Modality of the input data (e.g., ImageModality, TextModality, TabularModality). - model (Model): Neural network module, used for the architecture-based filtering.

Returns: - RecommenderOutput: An object containing recommended explainers.