ba8bc7d
committed
Commits
Comments (0)
Files changed (5)

+2 3README.rst

+4 0docs/rst/Orange.evaluation.reliability.rst

+2 3docs/rst/index.rst

+47 72orangecontrib/reliability/__init__.py

+1 1setup.py
docs/rst/Orange.evaluation.reliability.rst
.. [Bosnic2010] Bosnić, Z., Kononenko, I. (2010) `Automatic selection of reliability estimates for individual regression predictions. <http://journals.cambridge .org/abstract_S0269888909990154>`_ *The Knowledge Engineering Review* 25(1), pp. 2747.
.. [Pevec2011] Pevec, D., Štrumbelj, E., Kononenko, I. (2011) `Evaluating Reliability of Single Classifications of Neural Networks. <http://www.springerlink.com /content/48u881761h127r33/exportcitation/>`_ *Adaptive and Natural Computing Algorithms*, 2011, pp. 2230.
+.. [Wolpert1992] Wolpert, David H. (1992) `Stacked generalization.` *Neural Networks*, Vol. 5, 1992, pp. 241259.
docs/rst/index.rst
orangecontrib/reliability/__init__.py
+ Reference estimate for classification: :math:`O_{ref} = 2 (\hat y  \hat y ^2) = 2 \hat y (1\hat y)`, where :math:`\hat y` is the estimated probability of the predicted class [Pevec2011]_.
 Note that for this method, in contrast with all others, a greater estimate means lower reliability (greater expected error).
 3. :math:`LCV(x) = \\frac{ \sum_{(x_i, c_i) \in N} d(x_i, x) * E_i }{ \sum_{(x_i, c_i) \in N} d(x_i, x) }`
:param stack_learner: a data modelling method. Default (if None): unregularized linear regression with prior normalization.
README.rst