.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/01_add_functionality/3_add_biosignal_feature.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_01_add_functionality_3_add_biosignal_feature.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_01_add_functionality_3_add_biosignal_feature.py:


====================================
Adding a Custom Biosignal Feature
====================================

Below is an example of how to create and register a new feature by inheriting from
a base filter class from `MyoVerse <https://nsquaredlab.github.io/MyoVerse/modules/filters.html>`_.

This custom feature calculates the variance of the input signal.

.. admonition:: We Recommend Implementing any Additions in *user_config.py*

   The *user_config.py* module is specifically designed for end-users to register
   and configure their own custom components such as models, features,
   and filters. This keeps your modifications modular, reduces conflicts with
   core MyoGestic settings, and simplifies upgrades in the future.

   .. important::
      By registering your addition in ``user_config.py``, you ensure that your custom
      configuration stays separate from core MyoGestic functionality and remains
      compatible with future updates.


Example Overview
----------------
1. **Define** a new feature class inheriting from the base class.
2. **Implement** the core logic in the ``_filter`` method.
3. **Register** the feature so it becomes available globally.

.. GENERATED FROM PYTHON SOURCE LINES 31-38

.. code-block:: Python


    import numpy as np
    from myogestic.utils.config import CONFIG_REGISTRY
    # Ensure this import references your actual base class location:
    from myoverse.datasets.filters._template import FilterBaseClass









.. GENERATED FROM PYTHON SOURCE LINES 39-42

--------------------------------
Step 1: Inherit and define logic
--------------------------------

.. GENERATED FROM PYTHON SOURCE LINES 42-73

.. code-block:: Python

    class MyVarianceFeature(FilterBaseClass):
        """
        A feature that computes the variance of the input signal.

        Parameters
        ----------
        input_is_chunked : bool, optional
            Indicates whether the input data is chunked.
        allowed_input_type : Literal["both", "chunked", "not chunked"], optional
            Whether the filter accepts chunked, unchunked, or both.
        is_output : bool, optional
            If True, this feature's output is set as a final output in the pipeline.
        """

        def _filter(self, input_array: np.ndarray) -> np.ndarray:
            """
            Compute the variance of the input signal.

            Parameters
            ----------
            input_array : np.ndarray
                The data on which variance is computed.

            Returns
            -------
            np.ndarray
                The variance output as a single-element array, for consistency.
            """
            return np.array([np.var(input_array)], dtype=float)









.. GENERATED FROM PYTHON SOURCE LINES 74-77

-----------------------------------------------
Step 2: Register the custom feature
-----------------------------------------------

.. GENERATED FROM PYTHON SOURCE LINES 77-80

.. code-block:: Python

    CONFIG_REGISTRY.register_feature("My Variance Feature", MyVarianceFeature)









.. GENERATED FROM PYTHON SOURCE LINES 81-84

-----------------------------------------------
Example Usage
-----------------------------------------------

.. GENERATED FROM PYTHON SOURCE LINES 84-96

.. code-block:: Python

    if __name__ == "__main__":
        # Create a small signal for demonstration
        sample_data = np.array([1.2, 2.5, 2.7, 2.8, 3.1])

        # Instantiate and apply the feature
        feature_instance = MyVarianceFeature(
            input_is_chunked=False,
            allowed_input_type="not chunked"
        )
        variance_value = feature_instance(sample_data)

        print(f"Variance of {sample_data} = {variance_value[0]:.4f}")




.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    Variance of [1.2 2.5 2.7 2.8 3.1] = 0.4344





.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 0.574 seconds)

**Estimated memory usage:**  570 MB


.. _sphx_glr_download_auto_examples_01_add_functionality_3_add_biosignal_feature.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: 3_add_biosignal_feature.ipynb <3_add_biosignal_feature.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: 3_add_biosignal_feature.py <3_add_biosignal_feature.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: 3_add_biosignal_feature.zip <3_add_biosignal_feature.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_