.. DQS documentation master file, created by
   sphinx-quickstart on Thu Oct  6 14:33:51 2022.
   You can adapt this file completely to your liking, but it should at least
   contain the root `toctree` directive.

.. image:: ./dqs.png
   :align: center

|

Documentation of DQS
================================================================================================================

.. role:: bluetext

DQS is a neural network toolkit for distribution regression, quantile regression, and survival analysis.
This toolkit provides various classes and methods useful for predicting probability distribution.
This toolkit is currently available for PyTorch.

.. image:: ./predict_distribution.png
  :width: 400

How to install
------------------

.. code-block:: shell

   pip install dqs

.. toctree::
   :maxdepth: 1
   :caption: Overview:

   howtouse
   predicting_distribution
   tutorial_torch_cnll

.. toctree::
   :maxdepth: 1
   :caption: API Reference:

   torch_distribution_DistributionLinear
   torch_layer_HierarchicalSoftmax
   torch_layer_SigSoftmax
   torch_loss_Brier
   torch_loss_CensoredBrier
   torch_loss_CensoredNegativeLogLikelihood
   torch_loss_CensoredRankedProbabilityScore
   torch_loss_NegativeLogLikelihood
   torch_loss_Pinball
   torch_loss_Portnoy
   torch_loss_RankedProbabilityScore

Citation
------------------

Please consider citing this paper: H. Yanagisawa, "Proper Scoring Rules for Survival Analysis," ICML 2023 (to appear).