dqs.torch.loss.Pinball
================================================

This class is used to compute the Pinball loss.

.. code-block:: python

    class Pinball(
        distribution,
        loss_boundaries)


Parameters:

=================== ================ ===================================================================================
Args                Type             Description
=================== ================ ===================================================================================
distribution        dqs.distribution Object from dqs.distribution package to store probability distribution.
boundaries          list (float)     Quantile levels used in Portnoy estimator.
=================== ================ ===================================================================================


loss(pred, y, e=None)
---------------------------------

Parameters:

=================== ================ ===================================================================================
Args                Type             Description
=================== ================ ===================================================================================
pred                Tensor (float)   Estimated probability distribution to be evaluated.
y                   Tensor (float)   One-dimensional tensor to represent labels from a dataset.
e                   Tensor (bool)    Optional for survival analysis.  One-dimensional tensor to represent censored (False) or uncensored (True).
=================== ================ ===================================================================================

Return type: Tensor representing a single float.


Example
---------------------------------

The following code computes the value of Portnoy estimator based on estimated probability distributions (``pred``) and labels (``y``).

.. code-block:: python

    boundaries = torch.linspace(0.0, 1.0, 11)
    dist = dqs.distribution.DistributionLinear(boundaries)
    loss_fn = dqs.loss.Pinball(dist, boundaries)
    pred = torch.Tensor([[0.4,0.6],[0.2,0.8]])
    y = torch.Tensor([0.5,0.5])
    loss = loss_fn.loss(pred, y)