dataeval.detectors.drift.DriftUncertainty
=========================================

.. py:class:: dataeval.detectors.drift.DriftUncertainty(x_ref, model, p_val = 0.05, x_ref_preprocessed = False, update_x_ref = None, preds_type = 'probs', batch_size = 32, preprocess_batch_fn = None, device = None)

   Test for a change in the number of instances falling into regions on which the
   model is uncertain.

   Performs a K-S test on prediction entropies.

   :param x_ref: Data used as reference distribution.
   :type x_ref: ArrayLike
   :param model: :term:`Classification` model outputting class probabilities (or logits)
   :type model: Callable
   :param p_val: :term:`P-Value` used for the significance of the test.
   :type p_val: float, default 0.05
   :param x_ref_preprocessed: Whether the given reference data ``x_ref`` has been preprocessed yet.
                              If ``True``, only the test data ``x`` will be preprocessed at prediction time.
                              If ``False``, the reference data will also be preprocessed.
   :type x_ref_preprocessed: bool, default False
   :param update_x_ref: Reference data can optionally be updated using an UpdateStrategy class. Update
                        using the last n instances seen by the detector with LastSeenUpdateStrategy
                        or via reservoir sampling with ReservoirSamplingUpdateStrategy.
   :type update_x_ref: UpdateStrategy | None, default None
   :param preds_type: Type of prediction output by the model. Options are 'probs' (in [0,1]) or
                      'logits' (in [-inf,inf]).
   :type preds_type: "probs" | "logits", default "logits"
   :param batch_size: Batch size used to evaluate model. Only relevant when backend has been
                      specified for batch prediction.
   :type batch_size: int, default 32
   :param preprocess_batch_fn: Optional batch preprocessing function. For example to convert a list of
                               objects to a batch which can be processed by the model.
   :type preprocess_batch_fn: Callable | None, default None
   :param device: Device type used. The default None tries to use the GPU and falls back on
                  CPU if needed. Can be specified by passing either 'cuda', 'gpu' or 'cpu'.
   :type device: str | None, default None


   .. py:method:: predict(x)

      Predict whether a batch of data has drifted from the reference data.

      :param x: Batch of instances.
      :type x: ArrayLike

      :returns: Dictionary containing the drift prediction, :term:`p-value<P-Value>`, and threshold
                statistics.
      :rtype: DriftUnvariateOutput