{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "\n\n# Decoding sensor space data with generalization across time and conditions\n\nThis example runs the analysis described in :footcite:`KingDehaene2014`. It\nillustrates how one can\nfit a linear classifier to identify a discriminatory topography at a given time\ninstant and subsequently assess whether this linear model can accurately\npredict all of the time samples of a second set of conditions.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "# Authors: Jean-R\u00e9mi King <jeanremi.king@gmail.com>\n#          Alexandre Gramfort <alexandre.gramfort@inria.fr>\n#          Denis Engemann <denis.engemann@gmail.com>\n#\n# License: BSD-3-Clause\n# Copyright the MNE-Python contributors."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "import matplotlib.pyplot as plt\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import StandardScaler\n\nimport mne\nfrom mne.datasets import sample\nfrom mne.decoding import GeneralizingEstimator\n\nprint(__doc__)\n\n# Preprocess data\ndata_path = sample.data_path()\n# Load and filter data, set up epochs\nmeg_path = data_path / \"MEG\" / \"sample\"\nraw_fname = meg_path / \"sample_audvis_filt-0-40_raw.fif\"\nevents_fname = meg_path / \"sample_audvis_filt-0-40_raw-eve.fif\"\nraw = mne.io.read_raw_fif(raw_fname, preload=True)\npicks = mne.pick_types(raw.info, meg=True, exclude=\"bads\")  # Pick MEG channels\nraw.filter(1.0, 30.0, fir_design=\"firwin\")  # Band pass filtering signals\nevents = mne.read_events(events_fname)\nevent_id = {\n    \"Auditory/Left\": 1,\n    \"Auditory/Right\": 2,\n    \"Visual/Left\": 3,\n    \"Visual/Right\": 4,\n}\ntmin = -0.050\ntmax = 0.400\n# decimate to make the example faster to run, but then use verbose='error' in\n# the Epochs constructor to suppress warning about decimation causing aliasing\ndecim = 2\nepochs = mne.Epochs(\n    raw,\n    events,\n    event_id=event_id,\n    tmin=tmin,\n    tmax=tmax,\n    proj=True,\n    picks=picks,\n    baseline=None,\n    preload=True,\n    reject=dict(mag=5e-12),\n    decim=decim,\n    verbose=\"error\",\n)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "We will train the classifier on all left visual vs auditory trials\nand test on all right visual vs auditory trials.\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "clf = make_pipeline(\n    StandardScaler(),\n    LogisticRegression(solver=\"liblinear\"),  # liblinear is faster than lbfgs\n)\ntime_gen = GeneralizingEstimator(clf, scoring=\"roc_auc\", n_jobs=None, verbose=True)\n\n# Fit classifiers on the epochs where the stimulus was presented to the left.\n# Note that the experimental condition y indicates auditory or visual\ntime_gen.fit(X=epochs[\"Left\"].get_data(copy=False), y=epochs[\"Left\"].events[:, 2] > 2)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Score on the epochs where the stimulus was presented to the right.\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "scores = time_gen.score(\n    X=epochs[\"Right\"].get_data(copy=False), y=epochs[\"Right\"].events[:, 2] > 2\n)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Plot\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "fig, ax = plt.subplots(layout=\"constrained\")\nim = ax.matshow(\n    scores,\n    vmin=0,\n    vmax=1.0,\n    cmap=\"RdBu_r\",\n    origin=\"lower\",\n    extent=epochs.times[[0, -1, 0, -1]],\n)\nax.axhline(0.0, color=\"k\")\nax.axvline(0.0, color=\"k\")\nax.xaxis.set_ticks_position(\"bottom\")\nax.set_xlabel(\n    'Condition: \"Right\"\\nTesting Time (s)',\n)\nax.set_ylabel('Condition: \"Left\"\\nTraining Time (s)')\nax.set_title(\"Generalization across time and condition\", fontweight=\"bold\")\nfig.colorbar(im, ax=ax, label=\"Performance (ROC AUC)\")\nplt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## References\n.. footbibliography::\n\n"
      ]
    }
  ],
  "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
}