noether.data.preprocessors.normalizers
======================================

.. py:module:: noether.data.preprocessors.normalizers


Classes
-------

.. autoapisummary::

   noether.data.preprocessors.normalizers.ShiftAndScaleNormalizer
   noether.data.preprocessors.normalizers.MeanStdNormalization
   noether.data.preprocessors.normalizers.PositionNormalizer


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

.. py:class:: ShiftAndScaleNormalizer(normalizer_config, **kwargs)

   Bases: :py:obj:`noether.data.preprocessors.PreProcessor`


   Preprocessor that shifts and scales the input data, with (x + shift) * scale.

   :param normalizer_config: Configuration containing shift and scale values.

   :raises ValueError: If `shift` and `scale` do not have the same length.
   :raises ValueError: If `logscale_shift` and `logscale_scale` do not have the same length when `logscale` is True.
   :raises TypeError: If `shift`, `scale`, `logscale_shift`, or `logscale_scale` are not of type Sequence or torch.Tensor.
   :raises ValueError: If `scale` contains zero values (to avoid division by zero).
   :raises ValueError: If `scale` contains negative values.
   :raises ValueError: If `shift` and `scale` are provided but not both.


   .. py:attribute:: shift
      :type:  torch.Tensor | None
      :value: None



   .. py:attribute:: scale
      :type:  torch.Tensor | None
      :value: None



   .. py:attribute:: logscale


   .. py:method:: denormalize(x)

      Denormalizes the input data by applying the inverse operation of the normalization.

      :param x: torch.Tensor: The input tensor to denormalize.



.. py:class:: MeanStdNormalization(normalizer_config, **kwargs)

   Bases: :py:obj:`ShiftAndScaleNormalizer`


   Normalizes data using mean and standard deviation. It shifts the data by subtracting the mean and scales it by dividing by the standard deviation.

   :param normalizer_config: Configuration containing mean and std values. Imports MeanStdNormalizerConfig.
   :param \*\*kwargs: Additional arguments passed to the parent class.

   :raises ValueError: If `mean` and `std` do not have the same length.
   :raises ValueError: If any value in `std` is zero (to avoid division by zero).
   :raises ValueError: If any value in `std` is negative.


   .. py:attribute:: EPSILON
      :value: 1e-06



   .. py:attribute:: mean


   .. py:attribute:: std


.. py:class:: PositionNormalizer(normalizer_config, **kwargs)

   Bases: :py:obj:`ShiftAndScaleNormalizer`


   Normalizes position data to a range of [0, scale]. It inherits from ShiftAndScaleNormalizer and applies a shift and scale based on the provided raw position min and max values.

   :param normalizer_config: Configuration containing raw position min, max, and scale values.
   :param \*\*kwargs: Additional arguments passed to the parent class.

   :raises ValueError: If `raw_pos_min` and `raw_pos_max` do not have the same length.
   :raises ValueError: If `raw_pos_max` is equal to `raw_pos_min`.
   :raises ValueError: If `scale` is not a positive number.


   .. py:attribute:: raw_pos_min


   .. py:attribute:: raw_pos_max


   .. py:attribute:: resizing_scale