Some corrections and create_dateset.ipynb

create_dataset.ipynb

@@ -0,0 +1,70 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.datasets import fetch_openml\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import os\n",
+    "import pickle\n",
+    "import numpy as np\n",
+    "\n",
+    "print('fetching MNIST data...')\n",
+    "mnist = fetch_openml('mnist_784')\n",
+    "mnist['target'] = np.array([int(x) for x in mnist['target']])\n",
+    "\n",
+    "# use a random subset of n records to reduce training time.\n",
+    "n = 20000\n",
+    "shuffle_index = np.random.permutation(70000)[:n]\n",
+    "X, y = mnist['data'][shuffle_index], mnist['target'][shuffle_index]\n",
+    "\n",
+    "os.makedirs('dataset',exist_ok=True)\n",
+    "with open('dataset/mnist.pkl','wb') as f:\n",
+    "    pickle.dump((X,y),f)\n",
+    "\n",
+    "print('Done')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "inputHidden": false,
+    "outputHidden": false
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernel_info": {
+   "name": "python3"
+  },
+  "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": "3.6.9"
+  },
+  "nteract": {
+   "version": "nteract-front-end@1.0.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}