carbatpy.models.components.surrogates
=====================================

.. py:module:: carbatpy.models.components.surrogates

.. autoapi-nested-parse::

   Created on Tue Jul 30 16:15:25 2024
   structure to create Surrogate models
   01.08.2024: for multilayer perceptrons (have proven themselves)
   needs a labeled DataFrame with training data

   @author: welp



Attributes
----------

.. autoapisummary::

   carbatpy.models.components.surrogates.mode


Classes
-------

.. autoapisummary::

   carbatpy.models.components.surrogates.Surrogate


Module Contents
---------------

.. py:class:: Surrogate(title)

   .. py:attribute:: title


   .. py:method:: train_surrogate(DF, features_list, targets_list, split=0.2, random_state=42, hypo='def_hyperparameter.yaml', verbose=False)

      train MLP surrogate from dataframe with chosen features and targets,
      uses minmaxscaler and 'r2', 'neg_root_mean_squared_error' for scoring,
      the latter for refitting

      :param DF: DESCRIPTION.
      :type DF: TYPE
      :param features_list: DESCRIPTION.
      :type features_list: TYPE
      :param targets_list: DESCRIPTION.
      :type targets_list: TYPE
      :param split: DESCRIPTION. The default is 0.2.
      :type split: TYPE, optional
      :param random_state: DESCRIPTION. The default is 42.
      :type random_state: TYPE, optional
      :param hypo: DESCRIPTION. The default is "def_hyperparameter.yaml".
      :type hypo: TYPE, optional

      :returns: * **Y_test** (*TYPE DataFrame*) -- DESCRIPTION. test targets
                * **Y_pred** (*TYPE*) -- DESCRIPTION. predicted targets



   .. py:method:: save(path='default')

      save model

      :param path: DESCRIPTION. The default is CARBATPY_RES_DIR
      :type path: TYPE, optional

      :rtype: None.



   .. py:method:: load(path)


   .. py:method:: predict(DF_new_x)

      use existing surrogate to predict new data

      :param DF_new_x: DESCRIPTION.
      :type DF_new_x: TYPE

      :raises ValueError: DESCRIPTION. needs to contain features of model
          
          DESCRIPTION. does not extrapolate

      :returns: * **y** (*TYPE*) -- DESCRIPTION. target results
                * **DF_y** (*TYPE*) -- DESCRIPTION. target results



.. py:data:: mode
   :value: 1