emmi.pipeline.sample_processors.moment_normalization
====================================================

.. py:module:: emmi.pipeline.sample_processors.moment_normalization


Classes
-------

.. autoapisummary::

   emmi.pipeline.sample_processors.moment_normalization.MomentNormalizationSampleProcessor


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

.. py:class:: MomentNormalizationSampleProcessor(item, mean = None, std = None, logmean = None, logstd = None, logscale = False)

   Bases: :py:obj:`ksuit.data.pipeline.SampleProcessor`


   Normalizes a value with its mean and standard deviation (i.e., its moments).

   :param item: The item to normalize.
   :param mean: The mean of the value. Mandatory if logscale=False.
   :param std: The standard deviation of the value. Mandatory if logscale=False.
   :param logmean: The mean of the value in logscale. Mandatory if logscale=True.
   :param logstd: The standard deviation of the value in logscale. Mandatory if logscale=True.
   :param logscale: Whether to convert the value to logscale before normalization.


   .. py:attribute:: item


   .. py:attribute:: mean_tensor
      :value: None



   .. py:attribute:: std_tensor
      :value: None



   .. py:attribute:: logmean_tensor
      :value: None



   .. py:attribute:: logstd_tensor
      :value: None



   .. py:attribute:: logscale
      :value: False



   .. py:method:: inverse(key, value)

      Inverts the normalization from the __call__ method of a single item in the batch.

      :param key: The name of the item.
      :param value: The value of the item.

      :returns: The same name and the denormalized value.
      :rtype: (key, value)