rise_tabular
============

.. py:module:: rise_tabular

.. autoapi-nested-parse::

   RISE tabular explainer.



Classes
-------

.. autoapisummary::

   rise_tabular.RISETabular


Module Contents
---------------

.. py:class:: 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: Optional[callable] = None, class_names=None, keep_masks: bool = False, keep_masked: bool = False, keep_predictions: bool = False)

   RISE explainer for tabular data.


   .. py:attribute:: training_data


   .. py:attribute:: n_masks


   .. py:attribute:: feature_res


   .. py:attribute:: p_keep


   .. py:attribute:: preprocess_function


   .. py:attribute:: masks
      :value: None



   .. py:attribute:: masked
      :value: None



   .. py:attribute:: predictions
      :value: None



   .. py:attribute:: keep_masks


   .. py:attribute:: keep_masked


   .. py:attribute:: keep_predictions


   .. py:attribute:: mode


   .. py:method:: explain(model_or_function: Union[str, callable], input_tabular: numpy.array, labels: Optional[Iterable[int]] = None, mask_type: Optional[Union[str, callable]] = 'most_frequent', batch_size: Optional[int] = 100) -> numpy.array

      Run the RISE explainer.

      :param model_or_function: The function that runs the model to be explained
                                or the path to a ONNX model on disk.
      :param input_tabular: Data to be explained.
      :param labels: Indices of classes to be explained.
      :param num_samples: Number of samples
      :param mask_type: Imputation strategy for masked features
      :param batch_size: Number of samples to process by the model per batch

      :returns: An Explanation object containing the LIME explanations for each class.
      :rtype: explanation