mexca.postprocessing
====================

.. py:module:: mexca.postprocessing

.. autoapi-nested-parse::

   Post-process extracted emotion expression features.



Attributes
----------

.. autoapisummary::

   mexca.postprocessing.AU_REF
   mexca.postprocessing.LANDMARKS_REF


Functions
---------

.. autoapisummary::

   mexca.postprocessing.split_list_columns
   mexca.postprocessing.get_face_speaker_mapping
   mexca.postprocessing.sub_labels


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

.. py:data:: AU_REF
   :value: [1, 2, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 32,...


   Names of facial action units.

.. py:data:: LANDMARKS_REF

   Indices of facial landmarks.

.. py:function:: split_list_columns(df: Union[polars.LazyFrame, polars.DataFrame], au_columns: Iterable, landmark_columns: Iterable) -> Union[polars.LazyFrame, polars.DataFrame]

   Split (nested) list columns into separate columns.

   :param df: Data frame with extracted emotion expression features as stored in :class:`Multimodal.features`.
   :type df: polars.LazyFrame or polars.DataFrame
   :param au_columns: Names for new facial action unit columns.
   :type au_columns: Iterable
   :param landmark_columns: Names for new landmark columns.
   :type landmark_columns: Iterable

   .. rubric:: Notes

   For example, :class:`Pipeline.apply()` returns a `polars.LazyFrame`
   with (nested) list columns `face_box`, `face_au`, and `face_landmarks` containing multiple coordinates or predictions
   for multiple facial action units per row. These can be split into separate columns which only contain a single value per row.


.. py:function:: get_face_speaker_mapping(df: polars.DataFrame, face_label_column_name: str = 'face_label', speaker_label_column_name: str = 'segment_speaker_label') -> Dict[str, str]

   Get optimal mapping between face and speaker labels by counting overlapping frames.

   Uses the Hungarian algorithm to find an optimal mapping between face and speaker labels.

   :param df: Data frame with columns `face_label_column_name` and speaker_label_column_name`.
   :type df: polars.DataFrame
   :param face_label_column_name: Name of the face label column.
   :type face_label_column_name: str, default="face_label"
   :param speaker_label_column_name: Name of the speaker label column.
   :type speaker_label_column_name: str, default="segment_speaker_label"


.. py:function:: sub_labels(df: Union[polars.LazyFrame, polars.DataFrame], mapping: Dict, column: str) -> Union[polars.LazyFrame, polars.DataFrame]

   Replace label column with labels from a mapping.

   df : polars.LazyFrame or polars.DataFrame
       Data frame with label column.
   mapping : dict
       Dictionary with mapping.
   column : str
       Name of label column in data frame.