{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-10-14T17:01:45.186531Z",
     "start_time": "2018-10-14T17:01:45.059712Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7fc749bd1f28>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 360x180 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# The data\n",
    "resnet = np.asarray([0.8375262254326821, 0.8678992675159352, 0.8527975528611832, 0.8523278104598541, 0.884647507843369, 0.9665709773157553, \n",
    "              0.941322385257967, 0.9607122054596926, 1.0446496050070293, 1.5978083756003671])\n",
    "fully = np.asarray([0.2938374312588796, 0.3047676507445782, 0.29713952786808656, 0.3112794673912947, 0.335618492063216, 0.3853395053207258, \n",
    "         0.40619997414669395, 0.43130068820046324, 0.5361458921673319, 0.6306651849357078])\n",
    "\n",
    "resnet = np.flip(resnet)\n",
    "fully = np.flip(fully)\n",
    "indices = range(len(resnet))\n",
    "names = ['1x','1x','2x','3x','4x', '5x', '6x', '7x', '8x', '9x', '10x']\n",
    "# Calculate optimal width\n",
    "width = np.min(np.diff(indices))/3.\n",
    "\n",
    "fig = plt.figure(figsize=(5,2.5))\n",
    "ax = fig.add_subplot(111)\n",
    "ax.bar(indices-width/2.,resnet,width,color='b',label='resnet (D)')\n",
    "ax.bar(indices+width/2.,fully,width,color='r',label='densenet (A)')\n",
    "#tiks = ax.get_xticks().tolist()\n",
    "#ax.axes.set_xticklabels(names)\n",
    "plt.xticks(np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9]), \n",
    "               ('1', '2', '3', '4', '5',  '6', '7', '8', '9', '10'))\n",
    "ax.set_xlabel('Training Data Size (multiples of 9K)')\n",
    "ax.set_ylabel('Test MRE (%)')\n",
    "ax.spines['top'].set_visible(False)\n",
    "ax.spines['right'].set_visible(False)\n",
    "ax.legend(loc=\"best\")\n",
    "#fig.savefig(\"datasize.pdf\", bbox_inches='tight')\n",
    "#ax.spines['bottom'].set_visible(False)\n",
    "#ax.spines['left'].set_visible(False)"
   ]
  }
 ],
 "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": "3.5.4"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}