.. _f-quantilemlpregressor:

module ``mlmodel.quantile_mlpregressor``
========================================





.. inheritance-diagram:: mlinsights.mlmodel.quantile_mlpregressor


Short summary
+++++++++++++

module ``mlinsights.mlmodel.quantile_mlpregressor``

Implements a quantile non-linear regression.


:githublink:`%|py|6`




Classes
+++++++

+-------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| class                                                                                                             | truncated documentation                                                                                                                                                            |
+===================================================================================================================+====================================================================================================================================================================================+
| :class:`CustomizedMultilayerPerceptron <mlinsights.mlmodel.quantile_mlpregressor.CustomizedMultilayerPerceptron>` | Customized MLP Perceptron based on `BaseMultilayerPerceptron <https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/neural_network/multilayer_perceptron.py#L40>`_. ... |
+-------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| :class:`QuantileMLPRegressor <mlinsights.mlmodel.quantile_mlpregressor.QuantileMLPRegressor>`                     | Quantile MLP Regression or neural networks regression trained with norm :epkg:`L1`. This class inherits from :epkg:`sklearn:neural_networks:MLPRegressor`. ...                     |
+-------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+




Functions
+++++++++

+--------------------------------------------------------------------------------+--------------------------------------------+
| function                                                                       | truncated documentation                    |
+================================================================================+============================================+
| :func:`absolute_loss <mlinsights.mlmodel.quantile_mlpregressor.absolute_loss>` | Computes the absolute loss for regression. |
+--------------------------------------------------------------------------------+--------------------------------------------+
| :func:`float_sign <mlinsights.mlmodel.quantile_mlpregressor.float_sign>`       | Returns 1 if *a > 0*, otherwise -1         |
+--------------------------------------------------------------------------------+--------------------------------------------+




Properties
++++++++++

+--------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------+
| property                                                                                                     | truncated documentation                                                                                          |
+==============================================================================================================+==================================================================================================================+
| :py:meth:`_repr_html_ <mlinsights.mlmodel.quantile_mlpregressor.CustomizedMultilayerPerceptron._repr_html_>` | HTML representation of estimator. This is redundant with the logic of `_repr_mimebundle_`. The latter should ... |
+--------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------+
| :py:meth:`_repr_html_ <mlinsights.mlmodel.quantile_mlpregressor.QuantileMLPRegressor._repr_html_>`           | HTML representation of estimator. This is redundant with the logic of `_repr_mimebundle_`. The latter should ... |
+--------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------+






Methods
+++++++

+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| method                                                                                                                                 | truncated documentation                                                                                               |
+========================================================================================================================================+=======================================================================================================================+
| :py:meth:`__init__ <mlinsights.mlmodel.quantile_mlpregressor.CustomizedMultilayerPerceptron.__init__>`                                 |                                                                                                                       |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| :py:meth:`__init__ <mlinsights.mlmodel.quantile_mlpregressor.QuantileMLPRegressor.__init__>`                                           | See :epkg:`sklearn:neural_networks:MLPRegressor`                                                                      |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| :py:meth:`_backprop <mlinsights.mlmodel.quantile_mlpregressor.CustomizedMultilayerPerceptron._backprop>`                               | Computes the MLP loss function and its corresponding derivatives with respect to each parameter: weights and bias ... |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| :py:meth:`_backprop <mlinsights.mlmodel.quantile_mlpregressor.QuantileMLPRegressor._backprop>`                                         | Computes the MLP loss function and its corresponding derivatives with respect to each parameter: weights and bias ... |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| :py:meth:`_get_loss_function <mlinsights.mlmodel.quantile_mlpregressor.CustomizedMultilayerPerceptron._get_loss_function>`             | Returns the loss functions.                                                                                           |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| :py:meth:`_get_loss_function <mlinsights.mlmodel.quantile_mlpregressor.QuantileMLPRegressor._get_loss_function>`                       | Returns the loss functions.                                                                                           |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| :py:meth:`_modify_loss_derivatives <mlinsights.mlmodel.quantile_mlpregressor.CustomizedMultilayerPerceptron._modify_loss_derivatives>` | Modifies the loss derivatives.                                                                                        |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| :py:meth:`_modify_loss_derivatives <mlinsights.mlmodel.quantile_mlpregressor.QuantileMLPRegressor._modify_loss_derivatives>`           | Modifies the loss derivatives.                                                                                        |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| :py:meth:`_validate_input <mlinsights.mlmodel.quantile_mlpregressor.QuantileMLPRegressor._validate_input>`                             |                                                                                                                       |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| :meth:`predict <mlinsights.mlmodel.quantile_mlpregressor.QuantileMLPRegressor.predict>`                                                | Predicts using the multi-layer perceptron model.                                                                      |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+
| :meth:`score <mlinsights.mlmodel.quantile_mlpregressor.QuantileMLPRegressor.score>`                                                    | Returns mean absolute error regression loss.                                                                          |
+----------------------------------------------------------------------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+


Documentation
+++++++++++++

.. automodule:: mlinsights.mlmodel.quantile_mlpregressor
    :members:
    :special-members: __init__
    :show-inheritance: