{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "\n# Reduce EOG artifacts through regression\n\nReduce artifacts by regressing the EOG channels onto the rest of the channels\nand then subtracting the EOG signal.\n\nThis is a quick example to show the most basic application of the technique.\nSee the `tutorial <tut-artifact-regression>` for a more thorough\nexplanation that demonstrates more advanced approaches.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "# Author: Marijn van Vliet <w.m.vanvliet@gmail.com>\n#\n# License: BSD-3-Clause\n# Copyright the MNE-Python contributors."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Import packages and load data\n\nWe begin as always by importing the necessary Python modules and loading some\ndata, in this case the `MNE sample dataset <sample-dataset>`.\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "from matplotlib import pyplot as plt\n\nimport mne\nfrom mne.datasets import sample\nfrom mne.preprocessing import EOGRegression\n\nprint(__doc__)\n\ndata_path = sample.data_path()\nraw_fname = data_path / \"MEG\" / \"sample\" / \"sample_audvis_filt-0-40_raw.fif\"\n\n# Read raw data\nraw = mne.io.read_raw_fif(raw_fname, preload=True)\nevents = mne.find_events(raw, \"STI 014\")\n\n# Highpass filter to eliminate slow drifts\nraw.filter(0.3, None, picks=\"all\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Perform regression and remove EOG\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "# Fit the regression model\nweights = EOGRegression().fit(raw)\nraw_clean = weights.apply(raw, copy=True)\n\n# Show the filter weights in a topomap\nweights.plot()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Before/after comparison\nLet's compare the signal before and after cleaning with EOG regression. This\nis best visualized by extracting epochs and plotting the evoked potential.\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "tmin, tmax = -0.1, 0.5\nevent_id = {\"visual/left\": 3, \"visual/right\": 4}\nevoked_before = mne.Epochs(\n    raw, events, event_id, tmin, tmax, baseline=(tmin, 0)\n).average()\nevoked_after = mne.Epochs(\n    raw_clean, events, event_id, tmin, tmax, baseline=(tmin, 0)\n).average()\n\n# Create epochs after EOG correction\nepochs_after = mne.Epochs(raw_clean, events, event_id, tmin, tmax, baseline=(tmin, 0))\nevoked_after = epochs_after.average()\n\nfig, ax = plt.subplots(\n    nrows=3, ncols=2, figsize=(10, 7), sharex=True, sharey=\"row\", layout=\"constrained\"\n)\nevoked_before.plot(axes=ax[:, 0], spatial_colors=True)\nevoked_after.plot(axes=ax[:, 1], spatial_colors=True)\nfig.suptitle(\"Before --> After\")"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.12.2"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}