{
  "nbformat_minor": 0, 
  "nbformat": 4, 
  "cells": [
    {
      "execution_count": null, 
      "cell_type": "code", 
      "source": [
        "%matplotlib inline"
      ], 
      "outputs": [], 
      "metadata": {
        "collapsed": false
      }
    }, 
    {
      "source": [
        "\n# Analysis of evoked response using ICA and PCA reduction techniques\n\n\nThis example computes PCA and ICA of evoked or epochs data. Then the\nPCA / ICA components, a.k.a. spatial filters, are used to transform\nthe channel data to new sources / virtual channels. The output is\nvisualized on the average of all the epochs.\n\n"
      ], 
      "cell_type": "markdown", 
      "metadata": {}
    }, 
    {
      "execution_count": null, 
      "cell_type": "code", 
      "source": [
        "# Authors: Jean-Remi King <jeanremi.king@gmail.com>\n#          Asish Panda <asishrocks95@gmail.com>\n#\n# License: BSD (3-clause)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nimport mne\nfrom mne.datasets import sample\nfrom mne.decoding import UnsupervisedSpatialFilter\n\nfrom sklearn.decomposition import PCA, FastICA\n\nprint(__doc__)\n\n# Preprocess data\ndata_path = sample.data_path()\n\n# Load and filter data, set up epochs\nraw_fname = data_path + '/MEG/sample/sample_audvis_filt-0-40_raw.fif'\nevent_fname = data_path + '/MEG/sample/sample_audvis_filt-0-40_raw-eve.fif'\ntmin, tmax = -0.1, 0.3\nevent_id = dict(aud_l=1, aud_r=2, vis_l=3, vis_r=4)\n\nraw = mne.io.read_raw_fif(raw_fname, preload=True)\nraw.filter(1, 20)\nevents = mne.read_events(event_fname)\n\npicks = mne.pick_types(raw.info, meg=False, eeg=True, stim=False, eog=False,\n                       exclude='bads')\n\nepochs = mne.Epochs(raw, events, event_id, tmin, tmax, proj=False,\n                    picks=picks, baseline=None, preload=True,\n                    verbose=False)\n\nX = epochs.get_data()"
      ], 
      "outputs": [], 
      "metadata": {
        "collapsed": false
      }
    }, 
    {
      "source": [
        "Transform data with PCA computed on the average ie evoked response\n\n"
      ], 
      "cell_type": "markdown", 
      "metadata": {}
    }, 
    {
      "execution_count": null, 
      "cell_type": "code", 
      "source": [
        "pca = UnsupervisedSpatialFilter(PCA(30), average=False)\npca_data = pca.fit_transform(X)\nev = mne.EvokedArray(np.mean(pca_data, axis=0),\n                     mne.create_info(30, epochs.info['sfreq'],\n                                     ch_types='eeg'), tmin=tmin)\nev.plot(show=False, window_title=\"PCA\")"
      ], 
      "outputs": [], 
      "metadata": {
        "collapsed": false
      }
    }, 
    {
      "source": [
        "Transform data with ICA computed on the raw epochs (no averaging)\n\n"
      ], 
      "cell_type": "markdown", 
      "metadata": {}
    }, 
    {
      "execution_count": null, 
      "cell_type": "code", 
      "source": [
        "ica = UnsupervisedSpatialFilter(FastICA(30), average=False)\nica_data = ica.fit_transform(X)\nev1 = mne.EvokedArray(np.mean(ica_data, axis=0),\n                      mne.create_info(30, epochs.info['sfreq'],\n                                      ch_types='eeg'), tmin=tmin)\nev1.plot(show=False, window_title='ICA')\n\nplt.show()"
      ], 
      "outputs": [], 
      "metadata": {
        "collapsed": false
      }
    }
  ], 
  "metadata": {
    "kernelspec": {
      "display_name": "Python 2", 
      "name": "python2", 
      "language": "python"
    }, 
    "language_info": {
      "mimetype": "text/x-python", 
      "nbconvert_exporter": "python", 
      "name": "python", 
      "file_extension": ".py", 
      "version": "2.7.13", 
      "pygments_lexer": "ipython2", 
      "codemirror_mode": {
        "version": 2, 
        "name": "ipython"
      }
    }
  }
}