.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/asr/plot_03_adaptive_asr.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_asr_plot_03_adaptive_asr.py>`
        to download the full example code.

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

.. _sphx_glr_auto_examples_asr_plot_03_adaptive_asr.py:


Adaptive ASR with chunk updates
===============================

This example demonstrates the AASR-style adaptive update workflow. The
calibration state is initialized on one chunk, updated on a second chunk, and
then applied to the full signal with MATLAB-style ``reconstruct``.

.. GENERATED FROM PYTHON SOURCE LINES 9-66



.. image-sg:: /auto_examples/asr/images/sphx_glr_plot_03_adaptive_asr_001.png
   :alt: Input, After adaptive update + reconstruct
   :srcset: /auto_examples/asr/images/sphx_glr_plot_03_adaptive_asr_001.png
   :class: sphx-glr-single-img





.. code-block:: Python


    from __future__ import annotations

    import matplotlib.pyplot as plt
    import numpy as np

    from mne_denoise.asr import AdaptiveASR

    rng = np.random.default_rng(7)
    sfreq = 250.0
    duration = 18.0
    n_times = int(sfreq * duration)
    n_channels = 8
    t = np.arange(n_times) / sfreq

    brain = np.zeros((n_channels, n_times), dtype=np.float64)
    for ch_idx in range(n_channels):
        phase = rng.uniform(0.0, 2.0 * np.pi)
        brain[ch_idx] = (
            0.5 * np.sin(2.0 * np.pi * 10.0 * t + phase)
            + 0.15 * np.sin(2.0 * np.pi * 6.0 * t + 0.5 * phase)
            + 0.05 * rng.standard_normal(n_times)
        )

    data = brain.copy()
    spatial = rng.standard_normal((n_channels, 2))
    spatial /= np.linalg.norm(spatial, axis=0, keepdims=True)
    for onset, stop in ((4.0, 4.9), (9.5, 10.2), (13.5, 14.4)):
        start = int(onset * sfreq)
        stop_samp = int(stop * sfreq)
        source = rng.standard_normal((2, stop_samp - start)) * 8.0
        data[:, start:stop_samp] += spatial @ source

    chunk = int(6.0 * sfreq)
    asr = AdaptiveASR(
        sfreq=sfreq,
        cutoff=20.0,
        variant="psw",
        verbose=False,
    )
    asr.fit(data[:, :chunk])
    asr.partial_fit(data[:, chunk : 2 * chunk])
    cleaned = asr.transform(data)

    fig, axes = plt.subplots(2, 1, figsize=(10, 5), sharex=True, layout="constrained")
    axes[0].plot(t, data[0], color="tab:red", lw=1.0, label="Noisy")
    axes[0].plot(t, brain[0], color="k", lw=1.0, alpha=0.7, label="Underlying")
    axes[0].set_title("Input")
    axes[0].legend(loc="upper right")

    axes[1].plot(t, cleaned[0], color="tab:blue", lw=1.0, label="AdaptiveASR")
    axes[1].plot(t, brain[0], color="k", lw=1.0, alpha=0.7, label="Underlying")
    axes[1].set_title("After adaptive update + reconstruct")
    axes[1].set_xlabel("Time (s)")
    axes[1].legend(loc="upper right")

    plt.show()


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

   **Total running time of the script:** (0 minutes 1.113 seconds)


.. _sphx_glr_download_auto_examples_asr_plot_03_adaptive_asr.py:

.. only:: html

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

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

      :download:`Download Jupyter notebook: plot_03_adaptive_asr.ipynb <plot_03_adaptive_asr.ipynb>`

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

      :download:`Download Python source code: plot_03_adaptive_asr.py <plot_03_adaptive_asr.py>`

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

      :download:`Download zipped: plot_03_adaptive_asr.zip <plot_03_adaptive_asr.zip>`