dcnum.feat.feat_background.base
===============================

.. py:module:: dcnum.feat.feat_background.base


Attributes
----------

.. autoapisummary::

   dcnum.feat.feat_background.base.mp_spawn


Classes
-------

.. autoapisummary::

   dcnum.feat.feat_background.base.Background


Functions
---------

.. autoapisummary::

   dcnum.feat.feat_background.base.get_available_background_methods


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

.. py:data:: mp_spawn
   :value: None


.. py:class:: Background(input_data, output_path, compress=True, num_cpus=None, **kwargs)

   Bases: :py:obj:`abc.ABC`


   Base class for background computation

   :param input_data: The input data can be either a path to an HDF5 file with
                      the "evtens/image" dataset or an array-like object that
                      behaves like an image stack (first axis enumerates events)
   :type input_data: array-like or pathlib.Path
   :param output_path: Path to the output file. If `input_data` is a path, you can
                       set `output_path` to the same path to write directly to the
                       input file. The data are written in the "events/image_bg"
                       dataset in the output file.
   :type output_path: pathlib.Path
   :param compress: Whether to compress background data. Set this to False
                    for faster processing.
   :type compress: bool
   :param num_cpus: Number of CPUs to use for median computation. Defaults to
                    `dcnum.common.cpu_count()`.
   :type num_cpus: int
   :param kwargs: Additional keyword arguments passed to the subclass.


   .. py:attribute:: logger


   .. py:attribute:: output_path


   .. py:attribute:: kwargs

      background keyword arguments


   .. py:attribute:: num_cpus
      :value: None


      number of CPUs used


   .. py:attribute:: image_proc

      fraction of images that have been processed


   .. py:attribute:: hdin
      :value: None


      HDF5Data instance for input data


   .. py:attribute:: h5in
      :value: None


      input h5py.File


   .. py:attribute:: h5out
      :value: None


      output h5py.File


   .. py:attribute:: paths_ref
      :value: []


      reference paths for logging to the output .rtdc file


   .. py:attribute:: image_shape

      shape of event images


   .. py:attribute:: image_count

      number of images in the input data


   .. py:attribute:: writer


   .. py:method:: __enter__()


   .. py:method:: __exit__(type, value, tb)


   .. py:method:: check_user_kwargs(**kwargs)
      :abstractmethod:


      Implement this to check the kwargs during init



   .. py:method:: get_ppid()

      Return a unique background pipeline identifier

      The pipeline identifier is universally applicable and must
      be backwards-compatible (future versions of dcnum will
      correctly acknowledge the ID).

      The segmenter pipeline ID is defined as::

          KEY:KW_BACKGROUND

      Where KEY is e.g. "sparsemed" or "rollmed", and KW_BACKGROUND is a
      list of keyword arguments for `check_user_kwargs`, e.g.::

          kernel_size=100^batch_size=10000

      which may be abbreviated to::

          k=100^b=10000



   .. py:method:: get_ppid_code()
      :classmethod:



   .. py:method:: get_ppid_from_ppkw(kwargs)
      :classmethod:


      Return the PPID based on given keyword arguments for a subclass



   .. py:method:: get_ppkw_from_ppid(bg_ppid)
      :staticmethod:


      Return keyword arguments for any subclass from a PPID string



   .. py:method:: get_progress()

      Return progress of background computation, float in [0,1]



   .. py:method:: process()

      Perform the background computation

      This irreversibly removes/overrides any "image_bg" and
      "bg_off" features defined in the output file `self.h5out`.



   .. py:method:: process_approach()
      :abstractmethod:


      The actual background computation approach



.. py:function:: get_available_background_methods()

   Return dictionary of background computation methods