diff --git a/talks/matlab_vs_python/migp/fetch_data.ipynb b/talks/matlab_vs_python/migp/fetch_data.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..33f4f27bb97a47483b9f2f0308b95c6c460369e2
--- /dev/null
+++ b/talks/matlab_vs_python/migp/fetch_data.ipynb
@@ -0,0 +1,209 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Fetch Data\n",
+ "\n",
+ "This notebook will download an open fMRI dataset (~50MB) for use in the MIGP demo. It also regresses confounds from the data and performs spatial smoothing with 10mm FWHM.\n",
+ "\n",
+ "This data is a derivative from the COBRE sample found in the International Neuroimaging Data-sharing Initiative (http://fcon_1000.projects.nitrc.org/indi/retro/cobre.html), originally released under Creative Commons - Attribution Non-Commercial.\n",
+ "\n",
+ "It comprises 10 preprocessed resting-state fMRI selected from 72 patients diagnosed with schizophrenia and 74 healthy controls (6mm isotropic, TR=2s, 150 volumes).\n",
+ "\n",
+ "* [Download the data](#download-the-data)\n",
+ "* [Clean the data](#clean-the-data)\n",
+ "* [Run `melodic`](#run-melodic)\n",
+ "\n",
+ "Firstly we will import the necessary packages for this notebook: "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from nilearn import datasets\n",
+ "from nilearn import image\n",
+ "from nilearn import plotting\n",
+ "import nibabel as nb\n",
+ "import numpy as np\n",
+ "import os.path as op\n",
+ "import os\n",
+ "import glob\n",
+ "import matplotlib.pyplot as plt"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "This function will be used to plot ICs later:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def map_plot(d):\n",
+ "\n",
+ " N = d.shape[-1]\n",
+ "\n",
+ " fig, ax = plt.subplots(int(np.ceil((N/2))),2, figsize=(12, N))\n",
+ "\n",
+ " for img, ax0 in zip(image.iter_img(d), ax.ravel()):\n",
+ " coord = plotting.find_xyz_cut_coords(img, activation_threshold=2.3)\n",
+ " plotting.plot_stat_map(img, cut_coords=coord, vmax=10, axes=ax0)\n",
+ " \n",
+ " return fig"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "<a class=\"anchor\" id=\"download-the-data\"></a>\n",
+ "## Download the data\n",
+ "\n",
+ "We use a method from [`nilearn`](https://nilearn.github.io/index.html) called `fetch_cobre` to download the fMRI data:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Create a directory in the users home directory to store the downloaded data\n",
+ "data_dir = op.expanduser('~/nilearn_data')\n",
+ "\n",
+ "if not op.exists(data_dir):\n",
+ " os.makedirs(data_dir)\n",
+ " \n",
+ "# Download the data (if not already downloaded)\n",
+ "d = datasets.fetch_cobre(data_dir=data_dir) "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "<a class=\"anchor\" id=\"clean-the-data\"></a>\n",
+ "## Clean the data\n",
+ "\n",
+ "We use methods from [`nilearn`](https://nilearn.github.io/index.html) to regress confounds from the data (```clean_img```) and to spatially smooth the data with a gaussian filter of 10mm FWHM (```smooth_img```):"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Create a list of filenames for cleaned and smoothed data\n",
+ "clean = [f.replace('.nii.gz', '_clean.nii.gz') for f in d.func]\n",
+ "smooth = [f.replace('.nii.gz', '_clean_smooth.nii.gz') for f in d.func]\n",
+ "\n",
+ "# loop through each subject, regress confounds and smooth\n",
+ "for img, cleaned, smoothed, conf in zip(d.func, clean, smooth, d.confounds):\n",
+ " image.clean_img(img, confounds=conf).to_filename(cleaned)\n",
+ " image.smooth_img(img, 10).to_filename(smoothed)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "To run ```melodic``` we will need a brain mask in MNI152 space at the same resolution as the fMRI. Here we use [`nilearn`](https://nilearn.github.io/index.html) methods to load the MNI152 mask (```load_mni152_brain_mask```), resample to the resolution of the fMRI (```resample_to_img```), and binarize (```math_img```):"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# load a single fMRI dataset (func0)\n",
+ "func0 = nb.load(d.func[0].replace('.nii.gz', '_clean_smooth.nii.gz'))\n",
+ "\n",
+ "# load MNI153 brainmask, resample to func0 resolution, binarize, and save to nifti\n",
+ "mask = datasets.load_mni152_brain_mask()\n",
+ "mask = image.resample_to_img(mask, func0)\n",
+ "mask = image.math_img('img > 0.5', img=mask)\n",
+ "mask.to_filename(op.join(data_dir, 'brain_mask.nii.gz'))\n",
+ "\n",
+ "# plot brainmask to make sure it looks OK\n",
+ "disp = plotting.plot_anat(image.index_img(func0, 0))\n",
+ "disp.add_contours(mask, threshold=0.5)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "<a class=\"anchor\" id=\"run-melodic\"></a>\n",
+ "### Run ```melodic```\n",
+ "\n",
+ "Generate a command line string and run group ```melodic``` on the smoothed fMRI with a dimension of 10 components:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# generate melodic command line string\n",
+ "melodic_cmd = f\"melodic -i {','.join(smooth)} --mask={op.join(data_dir, 'brain_mask.nii.gz')} -d 10 -v --Oall -o cobre.gica \"\n",
+ "print(melodic_cmd)\n",
+ "\n",
+ "# run melodic\n",
+ "! {melodic_cmd}"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Now we can load and plot the group ICs generated by ```melodic```.\n",
+ "\n",
+ "Hopefully you can see some familiar looking RSN spatial patterns:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ics = nb.load('cobre.gica/melodic_IC.nii.gz')\n",
+ "fig = map_plot(ics)"
+ ]
+ }
+ ],
+ "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": "3.7.4"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}