rise_tabular

RISE tabular explainer.

Classes

RISETabular

RISE explainer for tabular data.

Module Contents

class rise_tabular.RISETabular(training_data: numpy.array, mode: str = 'classification', feature_names: List[str] = None, categorical_features: List[int] = None, n_masks: int = 1000, feature_res: int = 8, p_keep: float = 0.5, preprocess_function: callable | None = None, class_names=None, keep_masks: bool = False, keep_masked: bool = False, keep_predictions: bool = False)

RISE explainer for tabular data.

training_data

n_masks

feature_res

p_keep

preprocess_function

masks = None

masked = None

predictions = None

keep_masks

keep_masked

keep_predictions

mode

explain(model_or_function: str | callable, input_tabular: numpy.array, labels: Iterable[int] | None = None, mask_type: str | callable | None = 'most_frequent', batch_size: int | None = 100) → numpy.array

Run the RISE explainer.

Parameters:

• model_or_function – The function that runs the model to be explained or the path to a ONNX model on disk.

• input_tabular – Data to be explained.

• labels – Indices of classes to be explained.

• num_samples – Number of samples

• mask_type – Imputation strategy for masked features

• batch_size – Number of samples to process by the model per batch

Returns:

An Explanation object containing the LIME explanations for each class.

Return type:

explanation