.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/01_mne_integration.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_mne_integration.py>`
        to download the full example code.

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

.. _sphx_glr_auto_examples_01_mne_integration.py:


AMICA via MNE-Python
====================

This example shows how to fit AMICA through the :func:`amica.fit_ica`
wrapper.

The wrapper returns a standard :class:`mne.preprocessing.ICA` object, so the
usual MNE methods work as expected:

- ``plot_components``
- ``plot_sources``
- ``get_sources``
- ``apply``

The example uses the MNE sample dataset. To run it on your own data, replace
``load_raw()`` with your own loading code.

.. GENERATED FROM PYTHON SOURCE LINES 21-23

Imports
-------

.. GENERATED FROM PYTHON SOURCE LINES 23-30

.. code-block:: Python


    from __future__ import annotations

    import mne

    from amica import fit_ica


.. GENERATED FROM PYTHON SOURCE LINES 31-42

Load data
---------

Here we use the MNE sample dataset. You can replace this function with your
own data loader, for example:

.. code-block:: python

   raw = mne.io.read_raw_fif("your_data_raw.fif", preload=True)
   raw = mne.io.read_raw_eeglab("your_data.set", preload=True)
   raw = mne.io.read_raw_brainvision("your_data.vhdr", preload=True)

.. GENERATED FROM PYTHON SOURCE LINES 42-65

.. code-block:: Python



    def load_raw() -> mne.io.BaseRaw:
        """Load and minimally preprocess a Raw recording."""
        sample = mne.datasets.sample.data_path()
        raw = mne.io.read_raw_fif(
            sample / "MEG" / "sample" / "sample_audvis_raw.fif",
            preload=True,
        )

        raw.pick("eeg")
        raw.filter(1.0, 40.0)

        return raw


    raw = load_raw()

    print(
        f"Raw data: {len(raw.ch_names)} EEG channels, "
        f"{raw.n_times} samples @ {raw.info['sfreq']:.0f} Hz"
    )


.. GENERATED FROM PYTHON SOURCE LINES 66-70

Fit AMICA
---------

``fit_ica`` fits AMICA and returns a standard MNE ``ICA`` object.

.. GENERATED FROM PYTHON SOURCE LINES 70-80

.. code-block:: Python


    ica = fit_ica(
        raw,
        n_components=15,
        max_iter=500,
        random_state=42,
    )

    print(f"Fitted ICA with {ica.n_components_} components")


.. GENERATED FROM PYTHON SOURCE LINES 81-85

Inspect sources
---------------

Once fitted, the result behaves like any other MNE ICA object.

.. GENERATED FROM PYTHON SOURCE LINES 85-90

.. code-block:: Python


    sources = ica.get_sources(raw)

    print(f"Sources shape: {sources.get_data().shape}")


.. GENERATED FROM PYTHON SOURCE LINES 91-103

Next steps
----------

In an interactive session, you can use standard MNE visualization and
cleaning methods:

.. code-block:: python

   ica.plot_components()
   ica.plot_sources(raw)
   ica.exclude = [0, 1]
   ica.apply(raw)


.. _sphx_glr_download_auto_examples_01_mne_integration.py:

.. only:: html

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

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

      :download:`Download Jupyter notebook: 01_mne_integration.ipynb <01_mne_integration.ipynb>`

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

      :download:`Download Python source code: 01_mne_integration.py <01_mne_integration.py>`

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

      :download:`Download zipped: 01_mne_integration.zip <01_mne_integration.zip>`


.. only:: html

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

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