:py:mod:`orcanet.lib.sample_modifiers`
======================================

.. py:module:: orcanet.lib.sample_modifiers

.. autoapi-nested-parse::

   Some basic sample modifiers to use with orcanet.
   Use them by setting .cfg.sample_modifier of the orcanet.core.Organizer.

   ..
       !! processed by numpydoc !!


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

Classes
~~~~~~~

.. autoapisummary::

   orcanet.lib.sample_modifiers.PerInputModifier
   orcanet.lib.sample_modifiers.JoinedModifier
   orcanet.lib.sample_modifiers.Permute
   orcanet.lib.sample_modifiers.Reshape
   orcanet.lib.sample_modifiers.GraphEdgeConv




.. py:class:: PerInputModifier

   
   For modifiers that do the same operation on each input.
   Apply modify on x_value of each input, and output as dict.
















   ..
       !! processed by numpydoc !!
   .. py:method:: modify(x_value)
      :abstractmethod:

      
      x_value is a batch of input data as a numpy array.
















      ..
          !! processed by numpydoc !!


.. py:class:: JoinedModifier(sample_modifiers)



   
   For applying multiple sample modifiers after each other.
















   ..
       !! processed by numpydoc !!
   .. py:method:: modify(x_value)

      
      x_value is a batch of input data as a numpy array.
















      ..
          !! processed by numpydoc !!


.. py:class:: Permute(axes)



   
   Permute the axes of the samples to given order.
   Batchsize axis is excluded, i.e. start indexing with 1!
















   ..
       !! processed by numpydoc !!
   .. py:method:: modify(x_value)

      
      x_value is a batch of input data as a numpy array.
















      ..
          !! processed by numpydoc !!


.. py:class:: Reshape(newshape)



   
   Reshape samples to given shape.
   Batchsize axis is excluded!
















   ..
       !! processed by numpydoc !!
   .. py:method:: modify(x_value)

      
      x_value is a batch of input data as a numpy array.
















      ..
          !! processed by numpydoc !!


.. py:class:: GraphEdgeConv(knn=16, node_features=('pos_x', 'pos_y', 'pos_z', 'time', 'dir_x', 'dir_y', 'dir_z'), coord_features=('pos_x', 'pos_y', 'pos_z', 'time'), ragged=True, with_lightspeed=True, column_names=None, is_valid_features='is_valid', n_hits_padded=None)

   
   Read out points and coordinates, intended for the MEdgeConv layers.

   For DL files produced with OrcaSong in graph mode.

   :Parameters:

       **knn** : int or None
           Number of nearest neighbors used in the edge conv.
           Pad events with too few hits by duping first hit, and give a warning.

       **node_features** : tuple
           Defines the node features.

       **coord_features** : tuple
           Defines the coordinates.

       **ragged** : bool, optional
           If True, return ragged tensors (nodes, coordinates).
           If False, return regular tensors, padded to fixed length.
           n_hits_padded and is_valid_features need to be given in this case.

       **with_lightspeed** : bool
           Multiply time for coordinates input with lightspeed.
           Requires coord_features to have the entry 'time'.

       **column_names** : tuple, optional
           Name and order of the features in the last dimension of the array.
           If None is given, will attempt to auto-read the column names from
           the attributes of the dataset.

       **is_valid_features** : str
           Only for when ragged = False.
           Defines the is_valid.

       **n_hits_padded** : int, optional
           Only for when ragged = False.
           Pad or cut to exactly this many hits using 0s.
           Non-indexed datasets will automatically set this value.














   ..
       !! processed by numpydoc !!
   .. py:method:: reset_cache()

      
      Clear cached column names.
















      ..
          !! processed by numpydoc !!