jarvis.ai.pkgs.utils
====================

.. py:module:: jarvis.ai.pkgs.utils

.. autoapi-nested-parse::

   Helper functions for ML applications.



Attributes
----------

.. autoapisummary::

   jarvis.ai.pkgs.utils.typical_data_ranges


Functions
---------

.. autoapisummary::

   jarvis.ai.pkgs.utils.get_ml_data
   jarvis.ai.pkgs.utils.mean_absolute_deviation
   jarvis.ai.pkgs.utils.regr_scores
   jarvis.ai.pkgs.utils.binary_class_dat


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

.. py:data:: typical_data_ranges

.. py:function:: get_ml_data(ml_property='formation_energy_peratom', dataset='cfid_3d', data_ranges=typical_data_ranges)

   Provide arrays/pandas-dataframe as input for ML algorithms.

   Args:

       ml_property: target property to train

       data_ranges: range for filtering data

       dataset: dataset available in jarvis or other array

   Returns:
          X, Y , ids


.. py:function:: mean_absolute_deviation(data, axis=None)

   Get Mean absolute deviation.


.. py:function:: regr_scores(test, pred)

   Provide generic regresion scores.

   Args:

      pred: predicted values

      test: held data for testing

   Returns:
       info: with metrics


.. py:function:: binary_class_dat(X=[], Y=[], tol=0.1)

   Categorize a continous dataset in 1/0 with a threshold "tol".

   TODO: replace with OneHotEncoder