Since mldata.org is down, download MNIST elsewhere

08_dimensionality_reduction.ipynb

@@ -806,6 +806,41 @@
     "# MNIST compression"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true,
+    "deletable": true,
+    "editable": true
+   },
+   "outputs": [],
+   "source": [
+    "from six.moves import urllib\n",
+    "from sklearn.datasets import fetch_mldata\n",
+    "try:\n",
+    "    mnist = fetch_mldata('MNIST original')\n",
+    "except urllib.error.HTTPError as ex:\n",
+    "    print(\"Could not download MNIST data from mldata.org, trying alternative...\")\n",
+    "\n",
+    "    # Alternative method to load MNIST, if mldata.org is down\n",
+    "    from scipy.io import loadmat\n",
+    "    mnist_alternative_url = \"https://github.com/amplab/datascience-sp14/raw/master/lab7/mldata/mnist-original.mat\"\n",
+    "    mnist_path = \"./mnist-original.mat\"\n",
+    "    response = urllib.request.urlopen(mnist_alternative_url)\n",
+    "    with open(mnist_path, \"wb\") as f:\n",
+    "        content = response.read()\n",
+    "        f.write(content)\n",
+    "    mnist_raw = loadmat(mnist_path)\n",
+    "    mnist = {\n",
+    "        \"data\": mnist_raw[\"data\"].T,\n",
+    "        \"target\": mnist_raw[\"label\"][0],\n",
+    "        \"COL_NAMES\": [\"label\", \"data\"],\n",
+    "        \"DESCR\": \"mldata.org dataset: mnist-original\",\n",
+    "    }\n",
+    "    print(\"Success!\")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 30,
@@ -817,9 +852,7 @@
    "outputs": [],
    "source": [
     "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.datasets import fetch_mldata\n",
     "\n",
-    "mnist = fetch_mldata('MNIST original')\n",
     "X = mnist[\"data\"]\n",
     "y = mnist[\"target\"]\n",
     "\n",