{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <font color=\"880000\"> DeLong: Teaching Economics </font>\n",
    "\n",
    "Last edited: 2019-10-12\n",
    "\n",
    "# <font color=\"880000\"> Deep Roots of Relative Development </font>\n",
    "\n",
    "#### <font color=\"008800\"> Due ???? via upload to ??? </font>\n",
    "\n",
    "### <font color=\"000088\"> J. Bradford DeLong </font>\n",
    "\n",
    "#### Derived from QuantEcon: Linear Regression in Python: <https://python.quantecon.org/ols.html>\n",
    "\n",
    "&nbsp;\n",
    "\n",
    "You should have gotten to this point vis this link:\n",
    "\n",
    "&nbsp;\n",
    "\n",
    "### <font color=\"000088\"> Table of Contents </font>\n",
    "\n",
    "1. \n",
    "2. \n",
    "3. \n",
    "\n",
    "&nbsp;"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: linearmodels in /Users/delong/anaconda3/lib/python3.6/site-packages (4.13)\n",
      "Requirement already satisfied: scipy>=0.18 in /Users/delong/anaconda3/lib/python3.6/site-packages (from linearmodels) (0.19.0)\n",
      "Requirement already satisfied: mypy-extensions>=0.4 in /Users/delong/anaconda3/lib/python3.6/site-packages (from linearmodels) (0.4.2)\n",
      "Requirement already satisfied: patsy in /Users/delong/anaconda3/lib/python3.6/site-packages (from linearmodels) (0.4.1)\n",
      "Requirement already satisfied: statsmodels>=0.8 in /Users/delong/anaconda3/lib/python3.6/site-packages (from linearmodels) (0.8.0)\n",
      "Requirement already satisfied: pandas>=0.20 in /Users/delong/anaconda3/lib/python3.6/site-packages (from linearmodels) (0.20.1)\n",
      "Requirement already satisfied: cached-property>=1.5.1 in /Users/delong/anaconda3/lib/python3.6/site-packages (from linearmodels) (1.5.1)\n",
      "Requirement already satisfied: numpy>=1.13 in /Users/delong/anaconda3/lib/python3.6/site-packages (from linearmodels) (1.17.2)\n",
      "Requirement already satisfied: six in /Users/delong/anaconda3/lib/python3.6/site-packages (from patsy->linearmodels) (1.10.0)\n",
      "Requirement already satisfied: python-dateutil>=2 in /Users/delong/anaconda3/lib/python3.6/site-packages (from pandas>=0.20->linearmodels) (2.6.0)\n",
      "Requirement already satisfied: pytz>=2011k in /Users/delong/anaconda3/lib/python3.6/site-packages (from pandas>=0.20->linearmodels) (2017.2)\n",
      "\u001b[33mWARNING: You are using pip version 19.2.3, however version 19.3 is available.\n",
      "You should consider upgrading via the 'pip install --upgrade pip' command.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/delong/anaconda3/lib/python3.6/site-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.\n",
      "  from pandas.core import datetools\n"
     ]
    }
   ],
   "source": [
    "#libraries:\n",
    "\n",
    "!pip install linearmodels\n",
    "\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import statsmodels.api as sm\n",
    "from statsmodels.iolib.summary2 import summary_col\n",
    "from linearmodels.iv import IV2SLS\n",
    "\n",
    "\n",
    "# inline graphics\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>shortnam</th>\n",
       "      <th>euro1900</th>\n",
       "      <th>excolony</th>\n",
       "      <th>avexpr</th>\n",
       "      <th>logpgp95</th>\n",
       "      <th>cons1</th>\n",
       "      <th>cons90</th>\n",
       "      <th>democ00a</th>\n",
       "      <th>cons00a</th>\n",
       "      <th>extmort4</th>\n",
       "      <th>logem4</th>\n",
       "      <th>loghjypl</th>\n",
       "      <th>baseco</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AFG</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>93.699997</td>\n",
       "      <td>4.540098</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AGO</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5.363636</td>\n",
       "      <td>7.770645</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>280.000000</td>\n",
       "      <td>5.634789</td>\n",
       "      <td>-3.411248</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ARE</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7.181818</td>\n",
       "      <td>9.804219</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ARG</td>\n",
       "      <td>60.000004</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6.386364</td>\n",
       "      <td>9.133459</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>68.900002</td>\n",
       "      <td>4.232656</td>\n",
       "      <td>-0.872274</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ARM</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7.682482</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  shortnam   euro1900  excolony    avexpr  logpgp95  cons1  cons90  democ00a  \\\n",
       "0      AFG   0.000000       1.0       NaN       NaN    1.0     2.0       1.0   \n",
       "1      AGO   8.000000       1.0  5.363636  7.770645    3.0     3.0       0.0   \n",
       "2      ARE   0.000000       1.0  7.181818  9.804219    NaN     NaN       NaN   \n",
       "3      ARG  60.000004       1.0  6.386364  9.133459    1.0     6.0       3.0   \n",
       "4      ARM   0.000000       0.0       NaN  7.682482    NaN     NaN       NaN   \n",
       "\n",
       "   cons00a    extmort4    logem4  loghjypl  baseco  \n",
       "0      1.0   93.699997  4.540098       NaN     NaN  \n",
       "1      1.0  280.000000  5.634789 -3.411248     1.0  \n",
       "2      NaN         NaN       NaN       NaN     NaN  \n",
       "3      3.0   68.900002  4.232656 -0.872274     1.0  \n",
       "4      NaN         NaN       NaN       NaN     NaN  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ajr_df = pd.read_csv('https://delong.typepad.com/files/ajr.csv')\n",
    "ajr_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let’s use a scatterplot to see whether any obvious relationship exists between GDP per capita and the protection against expropriation index:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAe0AAAFXCAYAAACP5RboAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x11c3cda20>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.style.use('seaborn')\n",
    "\n",
    "ajr_df.plot.scatter(x='avexpr', y='logpgp95')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's add three-letter country labels to the points:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAd8AAAFJCAYAAADaPycGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzs3XdUFNfbwPHv7oKLCKgooCCKBTUJGmvssdeIFSPRWBKj\nRgV7wY6xEpWoGLEmGjW/2DX2Ho29RmMSu6I0aaJ02GXfP3jZsCoWAgvK8zkn57gzd2aeu6BP7p1b\nFDqdTocQQgghjEaZ2wEIIYQQ+Y0kXyGEEMLIJPkKIYQQRibJVwghhDAySb5CCCGEkUnyFUIIIYzM\nxBgPCQ+PMcZjjKZoUXMeP47P7TByRX6tu9Q7/8mvdZd6Zx8bG8tMz0nLNwtMTFS5HUKuya91l3rn\nP/m17lJv45DkK4QQQhiZJF8hhBDCyCT5CiGEEEYmyVcIIYQwMkm+QgghhJEZZaqREEIIkdddunSB\nHTu2MG3abP0xf38/ypRxQqFQsHfvLnQ6HRpNCl98MYCPPqqrLzdu3Ah0Oh3ffrvgtZ4lyVcIIYR4\nidjYWLZs2cC6dZswNTUlIiKc/v37sGXLLpRKJaGhoSQkJKDRaAgKCsTBodQr7yndzkIIIcRLFChg\nSkpKCtu2bSYoKJDixW3YsGE7SmVaCt29ewcNGzamdet2bNu2+bXuKclXCCGEeAm12oxFi5YSGPiA\nUaM86dq1Pbt3/wpAamoqBw/up02bdrRo0YojRw6SlJT4yntKt7MQQghBWpJNTk4xOJaQkLbkZFJS\nEiNHjgPgwYMARo0aStWq1QgLe0RCQhze3pOA9GS8j/btO730WZJ8hRBC5Ki1a1dz4cI5tFoNCoWC\nIUOGU7nyexw6tJ+tWzcBoFQqcXauxODBQzE1NcXNzRU7uxIolUp0Oh1WVoWZNMkbc/NC2R7fw7AY\nfr8Wiq1FcW7dukFERATFixcnKSmJK1cu06bNJ3zzzWT8/Vdibl6IEiVKUqRIYUxNTdi1azvjxk2m\nfv2GAFy9+gcLFsyV5CuEECL33Lt3l5Mnj+PvvwqFQsGtWzeYMcObr78ews6d2/Hx+Q5LS0t0Oh1+\nfr7s3buLDh06A+Druxi1Wg3AkiWL2L17J926uWdrfA/DYli4+SpRT5OwtlLzWe+vGTt2GGq1GRpN\nCl27duf9911wc+vOkCH9UavN0Gq1tG/fCQsLS/7++y+D0dFVq1YjOTmZP/+8QrNmDTN9riRfIYQQ\nOcbCwoJHj0LZvXsHderUx9m5EitWrGH8+NEMHjwMS8u0nX8UCgWeniNRKBTP3UOn0xEbG0Pp0mWy\nPb5r96KIepoEQNTTJMztXPjhh/XPlXN17YSr6/Ot2W3b9jx3bN26Ta98riRfIYQQOcbGxpY5c3zZ\nsmUDP/ywAjMzMwYMGExISBClSqVNybl27SpLly5Gq9Vga2unb0mOHOmBUqlEoVDw3nsf0KbNJ9ke\nn0tZaw5fDNS3fF3KWmf7M15Ekq8QQogc8TAshuPn/6JiqSJMmDAVgOvX/2b06KFUqFCR4OBgnJ0r\n4uJSlcWLlxMQcJ+5c2fpr8/Y7ZxTHG0tGeZWlfthcTjZFsLRNvM9eLOTTDUSQgiR7dLfpW4/cBbv\nGTO4FxQFgKNjaSwsLOna9VOWLFlIbGys/prLly+8sNs5pznaWtKlqbPREi9Iy1cIIbLsZcsRbt++\nheXLVwNw5cofzJ49jenTfXB2rsj582dZt241ycnJqFQqSpa0Z9iw0VhYWORSTbJf+rtUy5JVSI4N\nY9Tw/tgVL0xqqo7Bg4fRqFETtFot48ePAiAuLo6yZcsxduzEXI7cOCT5CiFEDrp06QK+vj58++0C\nSpcuw61bN/H3X4SPz3fY2NgCsGHDetavX8PAgUNyOdrsk/FdqnPNdgxz83quZdmkSXOaNGn+wus3\nb95pjDBzjSRfIYTIIefPn2XhwnnMm+dHiRIlANixYwt9+vTTJ16A7t175laIOSb9Xeq1e1G4lLU2\napfu20CSrxBC/AcXL17Aw2OA/nNwcBBfffU1wcGBLF++hKSkZJKTEzOcD8bBwVFfdtasaQBotVr8\n/VcZN/gc5mhrKUk3EzLgSggh/oOaNWuxePFy/X8tW7YBoEABNfPnL2L48NFMnjxev96vnZ0dISFB\nANjbO7B48XLmz/cjPDws1+rwrrh79w5jxgzD03MgX33Vm1WrlqHT6QA4fPggLVo0JCIiXF9+1apl\n9O/fG41Goz82YEBfQkKCczxWSb5CCPGGHobFsPdsAOHRCZmWKV7cBiurwjRo0IgPP6yGr++3AHTs\n2JU1a34gIiJCX/bSpdwZ5fsuiYmJwdt7AkOHjsLPbxnLlv3InTu32bFjCwA7d27Dzc2dHTu2GlwX\nEhLCunWrjR6vdDsLIcQbyLgcoSrhAUUSNa+8ZsiQ4fTv35u9e3fRtm17Bg8eysyZU9FoNCQmJlC8\nuC3Tp/sYIfp314kTx6hRozaOjqUBUKlUTJo0DVNTU4KDg3j69Ck9e/ahX7/P6dOnHyYmaemvR4/e\n7Nq1nU8+aY2NjaPR4n2t5HvlyhXmzZvH2rVrCQgIwMvLC4VCgbOzM1OnTtXvaSiEEO+6jMsRaguW\nplm7pgbnBw3yBKBdO1f9MbVazU8/bdB/rlGjFjVq1DJCtPlHREQ49vYOBsfMzc0B2LVrB5980gFL\nS0tcXKpy7NgRmjdv9f9lCjJ27ES8vLzw9//RaPG+MmuuWLGCSZMmkZSU9ss2e/Zshg8fzs8//4xO\np+Pw4cM5HqQQQuQVLmWtsbZKW3XJmMsRipezsytJWNgjg2PBwUFcvnyRAwf28ttvhxk50pOHDwPY\nsmWjQblq1WpQv359Vq5carR4X5l8S5cujZ+fn/7zX3/9xUcffQTAxx9/zKlTp3IuOiGEyGPSp9B0\na1qeYW5VZTRvLkt//16mYjXOnj1FUFAgABqNBj+/77h16yaVK7+Pn98yfH39WLHiJ6Kiorh9+5bB\nfUaMGMGZMycJCnpolLhf2e3cunVrAgMD9Z91Op1+YEChQoWIiYl55UOKFjXHxET1H8LMe2xs8u9f\nuPxad6l3/pNZ3W1sLKnxgb2RozGenPqZr1ixgjVr1nD48GHUajVeXl60a9eOjz/+WF+mQYMGnDx5\nksTERLy9vQkLCyMhIQEbGxumTZtG0aJF9WXvBT/Bb+ufREQnUryIGSPHTcXXdzY6nY64uDiaNm3K\nn39e4tNPuxnUyd39U/bs2YatrS0WFmb6c99+64O7uzvW1oVy/Pf+jQdcZXy/GxcXh5WV1Suvefw4\n/k0fk6fZ2FgSHv7q/+l4F+XXuku985/8WvecrPe2bdtp2rQFv/yyhXbtXElMTOHJkwSD56Wm6ggP\nj2Hr1k2Ym1vh45O23OTGjT8zb94Chg8frS/7+6WHRESnTeGKiE4kNM6B+fO/f+GzMz6jUyf3587Z\n2FhSooQTv/125rnyWfWyBP7GI6Xef/99zp49C8Dx48epVUsGDQghhHi5S5cuYG9fik6durJ166v3\nu7W2tub8+TOcOHGcuLhYunbtjofHcIMyb/P79zdu+Y4bN47Jkyfj6+tLuXLlaN26dU7EJYQQ4h2y\na9cOXF07Ubq0E6ampvz117UXlkuf7tykSXMUCgW7d+9g1qxplCtXnhEjxlK+fAV92bd5CcvXSr6l\nSpVi48a00WFly5Zl3bp1ORqUEEKId8fTp085ffokjx9HsXnzBuLiYtm6dQMFC5qTkpJsUFar1QJw\n7dpVatb8iMaNm6HVatm/fw8zZ3rzww+G+edtXcJSFtkQQgiRIx6GxXDtXhSBf/9G+/YdGTJkGACJ\niYl069aBzz77nGPHjtKoURMArly5jJNTOQAOHdpP4cJF+OKL/qhUKsqXd6ZAgQK5VZVsJ8lXCCFE\ntsu4EljgiS1MmfKN/pyZmRmNGzcjMTGRggXN6du3B+bm5piamjJ27AQABgwYjK/vt/Tt24OCBc0w\nMyuIl9fk3KpOtpPkK4QQIttlXAmsVMPhxOiKGpwfPdrrpdebmxdi0qRpORZfbpN1IYUQQmS7t3kk\nsjFIy1cIIUS2e5tHIhuDJF8hhBA5wpgjkS9dusD48aP46acN2NmVAMDf349ixYpz/PhRfbmEhARu\n377J3r1H6d27O+vXb0atVhslxowk+QohhHgnmJoWYNasb1iw4Hv9MsgWFhYsXrwcgNTUVMaOHc7A\ngUP0Ox7lFnnnK4QQ4p1Qs2YtrKys2Lp14wvPL126GAsLS3r06G3kyJ4nyVcIIcQ7Y/RoLzZs+JnA\nQMPdiQ4fPsiFC+cYPz5vTFeS5CuEEOKtlb6lYHh0AgCFCxdh6NBRzJw5FZ0uFYA7d26zdKkfs2bN\nQ602y81w9ST5CiGEeCulL+Sx6egdNh+7Q3yiBoCGDT/G0bEMe/bsIibmKVOmeDFhwlRKlCiRyxH/\nSwZcCSGEeCtlXMgjJi4FReK/60QPGzaKixfPk5iYyOPHj1m1apnBtemrZQ0a1A+FQoGJiZKmTVvi\n7v65UWJX6HQ6XU4/5F3bEzO/7vMJ+bfuUu/8J7/W/W2qd8YlLK2t1Axzq5rlqU05Ue+X7ecrLV8h\nhBBvpbd5IQ9JvkIIId5ab+uWgjLgSgghhDAySb5CCCGEkUnyFUIIIYxMkq8QQghhZJJ8hRBCCCOT\n5CuEEEIYmSRfIYQQwsgk+QohhBBGJslXCCGEMDJJvkIIIYSRSfIVQgghjEzWdhZC5IhLly4wdOjX\neHvPpEWL1vrjffq4U7FiZS5fvsj69ZtRq9X6c9OmTSI8PIzQ0BBMTEwpXrw45ctXYMSIsblRBSFy\njCRfIUSOKVPGicOHD+iT7507t0lISMi0/NSpMwBYtWoZxYoVo1MnN6PEKYSxSbezECLHVKjgTGho\nCLGxsQDs37+HVq3a5nJUQuQ+Sb5CiBzVuHEzjh07gk6n459//sLFpWpuhyRErpPkK4TIUS1btuHw\n4QP88cclPvywem6HI0SeIMlXCJGtHobFsPdsAOHRae92HRxKkZCQwObNv0iXsxD/TwZcCSGyzcOw\nGBZuvkrU0yRUCQ8okqgBoHnzluzfv4fSpcsQHBykLz9oUD8UCgUALVu2xt398xyP8e7dO/j7LyIx\nMZGEhATq1WtA27bt8faeyPLlq/Xl/ve//xEQEES/fgPp0KE1v/66P8djE/mHJF8hRLa5di+KqKdJ\nAGgLlqZZu6YAuLm54+bmDkDduvWpW7f+S+/Tr9/AHIkvJiYGb+8JzJw5F0fH0mi1WiZP9uLcudM5\n8jwhMiPdzkKIbONS1hprq7R5u9ZWalzKWudyRIZOnDhGjRq1cXQsDYBKpWLSpGnUqFE7lyMT+Y20\nfIUQ2cbR1pJhblW5di8Kl7LWONpa5nZIBiIiwrG3dzA4Zm5ujqmpKffv38PDY4D+eHR0FE2btjR2\niCKfkOQrhMhWjraW2ZZ0L126wJQp43FyKgtAcnIyo0d7sWnTLzRv3sqg+zr9vWxSUiLz5s0hIiKc\nxMREihUrxpgxEyhcuAh2diW5efO6wTOCg4MIC3uEk1NZFi9erj9+6NAuAgKCECInSPIVQuRpNWvW\nYtq02QCcO3eGlSuXUrhwkUzL7969E2vrYkyc6A3Axo0/47dkCTWb9aRcxWqsXfsDnTu74eBQCo1G\ng5/fd9SuXccYVRFCT5KvEOKtERPzlCJFiqLT6TItY21tza5d26lS5UOqV69BnUbtOBt2lU1H72Bt\npearwWPx8ZlBamoq8fHxNGjQiLp167Nv3+5M7/nkSTT9+vXSf3Z370nLlm2ytW4if1HoXvZbnE3C\nw2Ny+hFGZWNj+c7V6XXl17pLvXNHxm7nlJQUbt++yezZ8zl4cB83b17H0tJKX/batav89tsZAI4d\nO8K+fbu5cuUPitiUQuHQCrVVSQC6NS1P2zplXvns3K57bpF6Z+89MyMtXyFEnvMwLIZr96JQxiUY\ndDs/eHCfgQO/pHbtOgwaNPS5d76QloRr1vyIxo2bodVq+d+mraxdvx6HBkPz5AhskT9J8hVC5CmZ\nLdQBULRosVdef+jQfgoXLsIXX/RHpVJRu3oVDh8sTLem5fPkCGyRP0nyFULkKRkX6oiJSyHg2kU8\nPAagUqmIj4/D03MEly9fzPT6AQMG4+v7LX379qBgQTPMzAoydbI3Tk6v7moWwljknW8W5Nd3IpB/\n6y71Np6MLV9rKzXD3KrmSmtVfub5i7zzFULka3l9oQ4hsoMkXyFEnpOdC3UIkRdJ8hUij1m/fg0b\nN/7Mxo2/olarmTnT22BazZMn0bi7f84nn3QA4Pz5s6xbt5rk5GRUKhUlS9ozbNhoLCwscrMaQoiX\nkOQrRB5z4MBemjdvxeHDB2jXzhXAYFrN06dP6NXrU9q1c+X27Vv4+y/Cx+c7bGxsAdiwYT3r169h\n4MAhuVYHIcTLya5GQuQhly5dwN6+FJ06dWXr1k0vLBMZGUmBAmoUCgU7dmyhT59++sQL0L17T0m8\nQuRx0vIVIg/ZtWsHrq6dKF3aCVNTU/766xoA/v6L+OmnHwgNDcHJqRzTp88BIDg4GAcHx///cxCz\nZk0DQKvV4u+/KncqIYR4JUm+QuSy9NWcnGxMOX36JI8fR7F58wbi4mLZunUDSqVK3+18+vQJ/P39\nsLcvBYCdnR0hIUFUqOCMvb0DixcvJykpiZ493YwWv4fHAL74oj81a/67J+6CBfM4duwIVlZWBktA\ntmnTjvbtO9GwYS1mz55Ho0ZNADhz5hSHDx/Qb4YgxLtOkq8QuSjjnNbkkLM0btYWrzFjAEhMTKRb\ntw5Urvyevny9eg25du1Pvv12JjNm+NCxY1fmzZvNe++5ULx4cSCt61qhUBitDq6undi3b7c++aak\npHDy5O988EEV2rfvaLAEZDozMzP8/L6jSpVqFCmS+Q5FQryr5J2vELko42pOwTdPUaLCR/pzZmZm\nNG7cjPPnzxpc07fvV9y/f49Tp05QufJ7DB48lJkzp+LpOZD+/Xvz66/bmD7dJ9tivHTpAlOnjjc4\n5u/vx549O2nVqjE7dmzl0KH9fPVVb4YNG8yBA3spXrw4165dNbhm4sQxbNu2GQBz80K4u3/OvHmz\nsy1OId4m0vIVIhe5lLXm8MVAop4mUcPVi+YNqhqcHz3ai9GjvQyOmZqasm7dRv3nGjVqUaNGLaPE\n+ywnp7IsWbKSBQvm8v77Lty9e4f169cwdepMxo4djo/PDBwcSvH48WMeP47iyy8H6q/t3NmN33//\njQMH9mFlZfWSpwjx7pGWrxC5KH01p25Ny+faMor/RXKKlr1nA6jdoBX79u3mwYMANBoNlSpVpkqV\nD9FoUhg1yguVSsn69ZspX76C/lqFQsH48VNYscKfiIjwXKyFEMYnLV8hctnbuprTjTsB3Lt3F9+Z\nY1CkJpASF0mlSpXp0SNt0/mCBQvSunU7vv76C7y9Z1G0aNHn7mFra8eXX/bn++8XUq9eA2NXQYhc\nIy1fIcRLqdVmJCenGBxLSIjncawWUws7HOt/jX09D6yK2nD79k1atWqnL3f+/FmSkpJYv34NHh4D\nWLVq2XP3b9u2PVWqfJjj9RAiL5GWrxDihR6GxfD7tVBsLYpz69YNIiIiKF68OElJSVy5chmPkd6c\nO3McgOJFLRg1ZxGTxgwgKCgQZ+eK+mlDHTq0ZvHi5Qb3/vXX/QafZ8+eZ5Q6CZFXZCn5JicnM378\neB4+fIiFhQVTpkzByckpm0MTQuSWZ7f1+6z314wdOwy12gyNJoWuXbtTytaKEtbmBpvUDxkynLlz\nZ7F06Q8olf+9Y+3SpQsMHfo13t4zadGitf54nz7uVKxYmcuXL2JnV8JgapWHxwhiYp6wePECli9f\ng1qtJjw8jFGjPJk/389gNTAhckuWku/GjRsxNzdn48aN3L17l+nTp7NqlaymI8S7IuMUqKinSZjb\nufDDD+ufK7f6x7UGn1u1akurVm0Njj3byn1TZco4cfjwAX3yvXPnNgkJCfrzvr6LUavVz11Xp049\n/Px8GT58DFOnTsDTc4QkXpFnZCn53r59m48//hiAcuXKcefOnWwNSgiRuzJOgbK2UuNS1jrXYqlQ\nwZkHDwKIjY3FwsKC/fv30KpVWx49Cn3pdQMGDGHQoC8ZN24ktWp9RO3adQEICgrE338RYWFhmJmZ\noVarGTRoKOXKlQdg3LgR6HQ6fvzx3waFm5urvoWdkJBAs2Yt6NmzT85VWrzzspR833vvPY4ePUqL\nFi24cuUKjx49QqvVolKpXli+aFFzTExefO5tZWPz9o1OzS75te75qd42NpZ4Fy3E5RthVK9kS1n7\nwrkSR5Ei5qjVprRr15ZLl07RpUsXbt++Tv/+/dmzZw8qlZJx44bpu7iVSiVr1qzRX9+zZw+8vb2Z\nM2cmNjaWJCQkMGnSGKZPn0716tUBuHr1KnPnzmXt2rUEBwcTFRXBP//8w08//UTv3r0BUKmUxMfH\nEh4ejo2NDTt3bqNXr88oVqwYc+bMQaVSMWbMGJYvX86pU6fQaDQoFArGjRuHi4uL8b+4/yg//a5n\nZMx6Zyn5du3alTt37tCjRw9q1KjBBx98kGniBXj8OD7LAeZFNjaWhIfH5HYYuSK/1v1drfflyxcN\nRiCHh4dhZVWYFSvWcPb4YebM+Yb//W8r4aZpyW3Pnp2sXLkUe3sH/TXu7j1p2LBxjsQXHR1PUlIK\n9es3Zf78OVhaFuP996vy5EkCiYkpaLWp+PgsNOh2Tv85hYQEs2zZcgYN8mT48JEsWrSU3347zIcf\n1qBUqQr6ciVLlmX+/O8JD4/hp59+5r33qvDoURhr166lbdvOACQmJpGaqqNevYZotVrOnDlFbKyG\nK1dOcObMWfz9f+DcuSvs338Qf/9VKBQKbt26wdixXqxZ878c+W5yyrv6u/4qOVHvlyXzLCXfP//8\nk3r16jFhwgT+/PNPgoODsxycECL3VK9eUz8SOSoqksGDv8LTcwTA/7fuerFjx1b69ft3ZaqWLdsw\naJBnjsaVvtmEMi7t3a6DQykSEhLYvPkXBg70IDg46KXXp6SkMGXKeIYOHUm9eg25ceM6P/64ArXa\nTL8LFICX10hiY2OJjIzgu++WcPDgfjw8hhEZGc7Jk78TGRlBsWLFSUxMwMTEhDNnTqHT6dBoNDx4\ncJ8FC+Yxdep0TExMsLCw4NGjUHbv3kGdOvVxdq7EihVrXhKlyM+yNByxTJkyrFmzhu7du7Nw4UK8\nvLxefZEQIs/SaDRMmjSOzz7rRdWq1QgODuLp06f079+f/fv3oNFojBZL+kjrTUfvsPnYHeIT057d\nvHlLwsIeUbp0GYPyI0d64OExQP/fsWNHWbz4O6pWrUa9eg0BGDVqHIcO7SchIZ6QkH8T95w5vixe\nvBxLSytOnz5BQkIcq1ev4s8/r6JWq1m2bDE6nY6UlBSGDx9D3br12bZtD6VKOTJkyABcXTtSurQT\nADY2tsyZ48vVq1cYOPALevToyqlTvxvnSxNvnSy1fK2trVm9enU2hyJE3nDp0gWmTBmPk1NZFAoF\nSUlJdOnSiTZtOgHQt28PqlT5kFGjxumvedu3yFuwYB5ly5ajY8cuQNq+wp980gErKytcXKpy7NgR\nmjdvBcDBg/v4668/AShSpCgzZmTfJg5gONJaW7A0zdo1BcDNzR03N3cA6tat/8LdktI1btzU4HNU\nnI4+IxZQoURBpk/25Nq1P3FxqQJAYOBDwsPDOHLkIOPGTcbMzIwdO7bQvn07Jk6cSNu2rpiaFtDf\ny9TUlDJlnAgNDaFtW1f98cDAhxQqVIgJE6YCcP3634wePZQaNWphZZU778xF3iWLbAjxAjVr1mLa\ntLQdd5KTk+nVqxsNGjTn3r07lC9fnkuXzhMfH4e5eSHg7d4ib/fuX7l79zaLFi0FQKvVcuDAXkqW\ntOf8+VNERkaxZUuIPvnmdLdzdo+0fnbO8vCxM9i06QeWLo1Eq9WgVKrw8BjOwoW+PMYek+i0lnG7\ndu3w8vJi1aplFCxYkOXLl/DkSTSDB3+Fra0dBQsWNHjOnTu32LFjGz4+vpiamuLoWBoLC0uUyndr\nsKnIHpJ8hXiF+Ph4lEolKpWKnTu306RJc2xtS7B37y66du0OGG6Rl90twZzyMCyGA8fOsXfjKpYv\n+wETk7R/Dk6fPknlyu8zY4aPfhCKu3sXbt++lW3Pvnv3Dv7+i0hMTCQhIYF69Rrw5ZcDiI6OZs3y\nBTx5GEhCfDLKUiUxV1UCLNmzZycBAfffOPE/O2f5UVwB/f9YpXsYFkPFNpPZcvw+qoQHFPn/ru5B\ngzzZv38P27fvfa43w83N1eAejRs34/79e3z1VW/MzQuSmqpj8OBhWFhYZO1LEu80Sb5CvMDFixfw\n8BiAUqnExMSEyZMno9OlcvXqH4wbNwknp3KMHz9an3zh7doiL701ePXASrSJiYwbPxa1aVoLzczM\njE6duhqUd3XtyJYtG6lSpSrR0dGMGTPMIHG2bduevn17ULFiJSCtt6BgQXOmT5+DlZUVbm6urF+/\nGbVaTUxMDN7eE5g5cy6OjqXRarVMnuzF9u1bOHhwH5999rm++/78+bOMHTuC5ctXZ7mur9OSzkpX\n9+bNO5+7T58+/ejTp1+WYxX5hyRfIV4gY7czpE0ZWL78R1JTdYwdmzYaODIyggsXzlGr1kfAv1vk\nDRkygD59vsyVuF9XerIpVbc/AF2alqdtnTKZlk9fUCImJoZffln3XOI8d+40Tk5lDdZwXrp0Mbt2\n7dDvcpTuxIlj1KhRG0fH0gCoVComTZrG/ft3OX36hD7xAtSuXYedO7dz5crlLNc1fdvGa/ei9Mtg\nPisvLSoi8gdJvkL8v2entzxr587t+Pj46ldCOnBgL1u3btInX3h7tsjLarLJLHFGRISzZ88ufTmd\nTkdY2CNKlSr13D0iIsIN5gkDmJubExISgr19Kfz8vuPGjX+IiookMTERgCNHDlK6dBliYp6ye/ev\nODmVBWDhQn+SkpJYvnwJt27dQKFQYG5eCA+P4Qajol+1bePrJGghspMkXyEwHJST8Z1fur/++gvQ\n6RMvpL1R7tZGAAAgAElEQVTjW7TI97llDtu2bc/x478ZIeqsy2qyySxxmpqacv/+PTw8BhAT85Sk\npCRatmxDmzbtn7uHnV1Jbt68bnAsODgIa2trQkODmTPHF0D/jjco6CETJ3rz6FEo586dQadLNeiV\n8PGZQZUqVRk+fDQAt27dZMKE0Sxd+uMbvW99W/dVFm8nSb5CkPk7v3QffPDBcxsLqNVqdu06CLyd\nW+RlJdlkljjDwh7pu52TkhIZO3Yk1tbF9IO4AALDY7kZFEq5itVYu/YHOnd2w8GhFBqNBj+/76hV\n6yMiIyM5ceI4DRt+rL93YGAg1arVYP/+Pc/FEx0dzd27t5k2bZb+mLNzRerXb8SxY0f45JMOr1Wv\njNPLIO2d9cyZ01m+fBU3b17H0jLtHf6TJ9G4u39ucN/0taC//XbBa36LQkjyFQKQd36vkt4ln1ni\nrF27jr6sWm3G1KnT+eKLHri4VMXZuSIabSrfb/uT6LhUrK3UfDV4LD4+M0hNTSU+Pp4GDRrRpUs3\nmjVrwcKF81m79kceP36MiYmKhQv99cvXnjt3Gp0O+vVLe488ZMgwHBye79q2t3cgNDTkjeqY8T3/\nuXNnWLhwIQULWjBo0FD9QKunT5/Qq9entGvnikKhIDQ0lISEBDQaDUFBgS+MRYgXkeQrBPLO72We\nnSf7osRZt2599u3brb/G2rqYwd6+KZpUop4moVSZEvU0iXhlKf284oxiU0yp03YALmWt+fPCbwQE\n3NdvA9iunSslSpRkx44t+iQZFvaI0NDndzcKDHyob8VmRUzMU6ytrUlISDY4HhkZSYECav3+wbt3\n76Bhw8ao1Wq2bduMh8fwLD9T5C+SfIX4f/LO78WenSebWeJ8djpQxr19l67aaJDAX9SzkDHJH74Y\nSDXrxFfGZmtrh4ODA1u2bKRr108BuHHjOidPHn/jKT/p08tSUlK4ffsmS5YsYfPmbfj7L+Knn34g\nNDQEJ6dyTJ8+B4DU1FQOHtzP8uU/olKp6NWrO/37f41abfZGzxX5kyRfIcRLZUeX/Ov0LDyb5AO1\nsRR+jX+hJk36hu+/X0j//n1QqVRYWloye/Z8LC3f7H+kMnY7P3hwn0GD+lGz5kf6bufTp0/g7++H\nvX1a1/LZs6dJSIjD23sSkJ6M99G+fac3eq7InyT5CiFeKru65F/Vs/Bsku/p5vZc+Ro1alGjRi2D\nYwULFmT06Kxt7pLZ9LKiRYs9V7ZevYZcu/Yn3347kxkzfNi1azvjxk2mfv20zRuuXv2DBQvmSvIV\nr0WSrxDilYzRJW/s9+7PTi8LOn8eD48BqFQq4uPj8PLy4vjxkwbX9O37FV980ZO9e3fx999/GUx5\nqlq1GsnJyfz55xWqVPkwR2MXbz+FTqfT5fRD3rWNmfPrZtOQf+su9X737D0bwKajd/Sfuz2zyte7\nXPeXkXpn7z0zk6X9fIUQ4m3nUtYaays1gEwvE0Yn3c5CiHxJppeJ3CTJVwiRb8n0MpFbpNtZCCGE\nMDJJvkIIIYSRSfIVQgghjEySrxBCCGFkknyFEEIII5PkK4QQQhiZTDUSIg/y8/uOGzf+ISoqksTE\nROztHShSpChhYY/4+msP/cbvERHhpKSk8N57H/Dbb4fp1MmNe/fuoFAoiI5+jK2tHb6+i1m1ahnF\nihWjUyc3/TMGDOjLtGmzKFnSPhdrKkT+JMlXiDzI03MEAHv27CQg4D6DBnkSEhLM1KkTgH934Nm+\nfTORkZH06zeQpk3rsW/fbn75ZRvFixdnz56d+Pr6EB0dnZtVEUK8gHQ7C/GO0Ol0uLl9yoIFc4G0\nDe0bNPiYIkWK5HJkQohnSctXiLdQ+sbvERHhaDQaChYsSGpqKj179mXKFC8OHNiHlZUVBQoUeOl9\nFAqFkSIWQmQkLV8h8piHYTHsPRvAwzDDHVbUajUpKclAWrfz4sXL6dChC507u9GjR2+UShXh4Y8Y\nP34KK1b4ExERTnh4GBEREajVapKTUwzul5AQj1qtNlq9hBD/kpavyFcuXbqgH6ykUChISkqiVas2\n3LhxnZs3r2NpaaUv26ZNO9q370STJnWpUaMGyckatFoNWm0q3t4zsbd3yPb4Mu4xe/hiINWsE/Xn\nYlNMiYh6yt837wGg1Wq5cOEsn3/eF0hLzqtXr2LKlOl8+WV//Px8SU5ORqVSUqlSZdatW0OXLt0w\nMTEhKCiQlJQUihaVnXyEyA2yn28W5Nf9LuHtr/ulSxfYsWOLfhP05ORkevToirNzRTp27ErduvWf\nu6ZDh9acPn1KX+/t27dw9+5tRo4cl+3xPbvHbMVCARQ2iaVcpWrMnjkZZQErUuLD0WlTKFCgAIUL\nFyY+PgGApKRErKysePLkCS4uVbl37w6OjqW5ceM6/v6rOHXqBMeP/0ahQoXQ6XQMGTIMF5eqL43n\nbf95/xf5te5S7+y9Z2ak5Svytfj4eJRKJSqV6rWvefQo1KCF/CIZW9gAGo2Gbt0+o3nzljx+/Jjv\nv19AaGgIqamp2Nra4ek5gmLFihN57xw3d/ng2GAIDmUq0tPNjZLWBWnVuilKUyucGg8HoGN9e3as\nnsH48ZNxdq4EQGJiIoMHf8Xw4WNp1qwFAD4+M6hevRZbt25i4kRv+vUbmJWvSQiRzST5inwnfbCS\nUqnExMSEESPGcOTIIfz9F7Fu3Wp9uREjxlK+fAWePn1Cr169iI5+wtOnT2ncuCn9+n39yuekTweC\ntCTv4TEAR0dHFiyYx2effU6jRk0AOH/+LGPHjmD58tVYW5lh71CaEsr7DHNzw9HWkhMnjmNubk5S\natrgKGsrNTUqO0DHLhw9eliffGfPnkadOvX0iTc+Pp6LF8+zdu1G+vRxJzo6WkY+C5FHSPIV+U7G\npJjuyJFDDBo09IXdzlZWhVm7di2hodHMmuWNiYkp5ubmb/RMc3NzOnbswsqVS7GwsNAnXoDateuw\nc+d2rly5DECjhg05e/YMDsULAXDo0H4+qv0Rf//zD92altdv/H7f2pqbN68DsH79GuLj4+nff5D+\nvocPH6Bx42ao1WqaNWvJrl3b9e+HhRC5S0Y7i3zjYVgM5/55RHyiJkvXq1Qqxo6dyPHjRzl16sQb\nX29tbc29e/ewty/13Dl7ewdCQ0MAMDExxcWlCn/8cYmbAY+4HxSBSl0IUxMlbeuU0W/+Hhoaio2N\nLefPn2Xv3l1MnToTpfLfv9I7d27n2rWrjBzpyZUrl9mxYxupqalZqrsQIntJy1fkC+mjiAPvBpMQ\nHM3DsBh9Ekv3bLdz9eo1n3tHqlab4eU1mRkzvKlevSYFCxZ87RhCQ0Np2/YTfWs1o8DAB9SuXYdH\nj0IBaNmyDdt37iQgpgixpuW4fDMME82/iTMuLpadO7cxY4YPo0YNY+7cBVhYWOjP37lzm9TUVJYv\n/7c+w4cP5tSp32nYsPFrxyyEyBmSfEWOCAoKxN9/EWFhYZiZmaFWqxk0aCgLF85Dq9Xy4EEARYsW\nxdLSitq162BjY8usWdNYuvRHXFyqAGmDlDp2bE2XLp/+54FC1+5FEfU0CfPi5TEvXp5r96IMku/E\nid6ZXvvrr/sNPn/4YXU2bdrxwrIPw2K4di8KZVyCwfGMyfL06ZOcOHGchg0/BuDMmVMEBgZSrVoN\n9u/fA6Ql/plzZhOnNadE9R5E3jxAXGgIHh4DUKlUaLVa+vUbyP/+t46UlGTmzTPsRre3d6B163YG\nx1xdO7Nly0ZJvkLkAZJ8RbZLTEzEy2sk48ZN0k9l+fvva/j6+rB48XIAZs70pnnzVvp3rHv27KRM\nGScOHz6gT75nzpyiUCGLFz/kDbmUtebwxUCiniZhbaXGpWz2z2/NOEdXlfCAoPPnn0uWpUs78e23\n37Fw4XzWrv0RAFtbO+bOXWAw4lqpVFKrVh3OXLmFytSMosVL0ry2OyOGeho8s3HjZq8dX/PmLWne\nvGX2VFYI8Z9I8hXZ7uTJ49SsWdtgDun777vg57fspdfVrVufs2fPkJqailKp5NCh/bRo0TpbYnK0\ntWSYW1Wu3YvSD1jKbumtawBtwdJ4Tl1F2zplnitXtKg13t4zX3iPdu1c9X+eMG6cviXtUrZ2jsQs\nhMgdknxFtgsODsbBwVH/2ctrJLGxsURGRrBwoT+2tnYvvC7jQKPKld8jPj4OW1tbIiMjsyUuR1vL\nHE1gOdG6zumYhRC5Q5KvyHZ2dnZcv/63/vOcOb5A2v6xWq32pde2bNmGgwf38+hRKB9/3BSNJuWl\n5fMSY7SuhRDvBplqJLJN+oYAZSvV5MKFc1y79qf+XGDgQ8LDw165i0716jX5++8/OXr0EE2bNs/p\nkLOdo62lwXQgIYR4EWn5imyRcbCRtZWa4WNnsGnTDyxdGolWq0GpVOHpOZISJUq+9D7pA43Cwh5l\n22Ar8ebSl8esWNGZlBRtphtQPHkSjbv75zRt2py+fXswadI0qlatBsCNG9f55ptJrFjx0xsvSiLE\nu042VsiC/LrwOGRe92c3BOjWtPwLBxu9rfLbzzx9A4olSxYTHh6T6QYUT58+oUOH1qxe/T8eP45i\n/PjR2NnZsXLlWgYO/IJRo7zw91/E48dRrF+/WX//Y8eOMHHiWDZt+pWSJe1zq5ovld9+5umk3tl7\nz8xIt7PIFi5lrbG2StsbNqem8ojck9kGFJGRkSiVShQKBe+99wEqlQqNRsvcubP4+OMmfPCBi77s\nrVs39H8+dOjAK3tBhHiXSbezyBYy2Ojdc/HiBXr16oVGk/rcBhQ//fQDoaEhODmV0+/cdOTIQVq0\naMXp0yc5deoEO3bs09+rRYvWHDy4H2fnSsTExJCcnIS1dbHcqpoQuU5aviLbyGCjt1/6oLnw6ARq\n1qzF2rVrWbRoKb6+i6lXryEAgwYNZcmSlYwZM56IiDAKFEjr8di5czsdO3alVau26HQ6oqL+nSLW\noEEjzpw5iU6n47ffDtOkyds3mE6I7CTJVwgB/DtobtPRO2w+duelG1DEx8dTu3ZdGjVqwsOHD0hO\nTubevTssXryAAwf2oVDA9u1b9OXVajOcnStx7dpVfv/9tzdamUuId5EkXyEEYLhCV0xcCk/ikl9Y\nLjw6Ac9RYzh07BS9e39JfHwc33+/gP79B+Pr60fr1m3p1q0Hu3f/SkrKv/O0W7Zsw4YN67G0tJTR\nzyLfk+QrhAAMB82VKvc+k6fMeK5M7/6jOHbXjHjLmny38Du+GvAF7u6fc+/eXZo3bwVAv34D6dPn\nSypUcObo0cP6a2vV+ogrV/7ItiVDhXibyVSjLMivQ/Eh/9Y9v9T737Wk0wbNPVvvd31KWUb55Wf+\nLKl39t4zMzLaWQih96q1pI2xO9TrCAkJZurUCZQp46Rf9EOr1VKkSBE8PUdib+/AqlXLOHPmJP7+\nP2BikvZP3YABfZk2bVaenVss8g9JvkKI15YXp5QNGjRUv+jHlSuXmTJlPCtX/gRASEgI69atpm/f\nr3IzRCGeI+98hRBvJH1KWXjgDRo2rMWhQ/sNzvfp487Mmd4ARESE07x5A44cOaQ/f+nSBdq3b4mH\nxwA8PQfy5ZefM2nSOIPBWVn14YfVMTExITDwIQA9evTmwIG93Lx5/T/fW4jsJMlXCJFlZco4cfjw\nAf3nO3duk5CQoP+8e/evuLm5s3XrRoPratasxeLFy/HzW8YPP6zDxMSEEyeOZUtMRYtaEx0dDYC5\neUHGjp3IzJnTSE5+8ehtIXKDJF8hRJZVqOBMaGgIsbGxAOzfv4dWrdoCoNPp2L9/D+7un6PRaLh7\n9/YL75GSkkJkZIR+s4aXSV8EJCQyLtMyjx6FYGtrq/9crVoNatX6iJUrl75J1YTIUZJ8hRD/SePG\nzTh27Ag6nY5//vkLF5eqAFy4cI5y5SpQtGhRPvmkA1u3btJfc/HiBTw8BvD559348suefPxxU2rV\n+uilz8m4CMgPe/4hOeX5vaHPnz+DWm2Gra2dwfEBAwZz5sxJgoIeZkONhfjvZMCVEOKNpE9HUsal\ndS+3bNmG+fPnYG/vwIcfVteX27lzOyEhwYwc6YlGk8Lt27f4+mtPIK3bedq02Tx5Es2IEUNea/Rx\nxkVAnsQmk5SUtgKXv/8i1q1bjUqlwtzcnG++mf3ctWq1mgkTpjJw4Bf/uf5CZAdJvkKI15Zx32ZV\nwgOKJGpwcChFQkICmzf/wsCBHgQHB/HkSTR37txm48Yd+p2QfHxmsHfvLsqXr6C/X+HCRZg8eTpD\nh35N5co/U7x48UyfnXGak12JkgzzWP7S0db9+g00+Fy58vscO3b2P34DQmSPLCXflJQUvLy8CAoK\nQqlUMn36dMqXL5/dsYk8au3a1Vy4cA6tVoNCoWDIkOFs2bKB5s1b6ad8AMyYMZVq1WrQvn1H/bEN\nG9bz5MkTBgwYnBuh52uXLl1gypTx+l2IAIoUKcqMGT4cOrRf3y2sVCpxdq7E4MFDOXr0KHPnzmPl\nyrWYmppy7V4UN85sBoWKQjaVUCSmDWJq3rwl+/fvoXTpMgQHB/HHH5dxde1osAWhq2snZsyYyujR\n4w3iKlu2HG5u3VmwYC4zZvhkGn9enOYkRFZlKfkeO3YMjUbDL7/8wsmTJ1mwYAF+fn7ZHZvIg27f\nvs3Jk8fx91+FQqHg1q0bzJjhTcWKlZ4r6+ramRUrlhgk3717dzN79rwci+/ZBJOcnMzo0V5UrFiZ\nI0cOsWXLBhQKBVqtlg4dOtO2bXsA3NxcWb9+M2q1OsdiywvSu3szOn36BDt3bsfH5zssLS3R6XT4\n+fmyd+8u+vXrzc6de1i9eiX9+w+iQFIwydEB2NcdRLEi5gxzcwfAzc0dt///c9269Tlw4PmRy++/\n78LPP6dttlCjRi2Dc3369Hut+F+1CIgQb4ssJd+yZcui1WpJTU0lNjZWv3qMePdZWlry6FEou3fv\noE6d+jg7V2LFijXMnTvrubIffliN6OhoQkNDKFGiJP/88xfW1sVyfHWhjAnm3LkzrFy5lK5du7Nj\nxxZ8fL7DwsKCpKREJk0ah1ptRrNmLXI0nrxu8+aNDB48DEvLtKSmUCjw9ByJQqEAYNiwUXz55ec0\natSEn9cs4Ztp04lKtpDWpxD/QZayprm5OUFBQbRt25bHjx+zdOnLh/AXLWqOiYnqpWXeNi9bs/Pd\nZsmyZUtZt24da9aswszMjBEjRmBmZkrhwgWf+17c3T/lxInDDBo0iO+/30fv3j1z9LsrUsQctdpU\n/wyFIoUSJWzZuXML48ePo2zZkvp6TJ48kalTp9K9e2dUKiU2NpaEhYUxd+5cQkNDMTMzw8zMjDFj\nxvDLL6spXrw4n332mf5Zn376KfPmzWP06NH07t2b9u3TWtGhoaH07NmTn3/+GTs7u2dDzDVFiphz\n+fJFRo78t8u/cePGhIWFUK3ae1hYWHD58mV8fX1JSUmhZMmSfPfdd5QpU4JZs2YyZMhgRo0aRftW\ndXOxFsaVX/+eS71zXpaS7+rVq2nYsCGjRo0iJCSEPn36sHPnzky77B4/jv9PQeY1+XXh8YdhMVy4\ndotSxcwZOXICANev/83o0UP54IMqPHmS8Nz30rBhC4YNG4SrazdOnz7DwIHDcvS7i46O59Sp03Tv\n/hkpKSncvn2T2bPns2jRfMzNrQ2ebWZWhIcPAwkPj0GrTeXhw3A8PAYwbtwk/XSZv/++xqRJU2jY\nsD6xsYkG16ekaImOTmDcuMkMHz4EZ2cXrK2LMXbseL7+2hOl0jxP/J78Ozo5kurVaz7X7Xz06DGu\nXr2Bs3NFSpWqgK/vEgIC7ut7M8LDYyhX7n0KFbKgUaOWeaJOxpBf/55LvbP3npnJUvK1srLC1NQU\ngMKFC6PRaNBqn59zJ94d6aNcA25cID74PIsXLKKsgzWOjqWxsLBEqXxxz0aRIkVwcnJi9eqVNGrU\nxCivKDJ2Oz94cJ+BA7+kUqXKhIYGY2X170IOgYEPsLMrof98+vQJatasrU+8kPae0s9vGRs2rMn0\neaVLO9GjRy8WLpxHvXoNKV68OE2aNM+Bmr25F41OfpabW3eWLFnI9Ok+WFhYAHD58gV9t7MQIvtl\n6V/Cvn37MmHCBHr06EFKSgojRoyQzbHfcelzLC1LViE5NoxRw/tjV7wwqak6Bg8exu+//8aCBfMo\nVKgQAKVLl2Hq1LT9YF1dOzNmzDD9YJuc8Ozc03RFixYD0gYEff/9ImbN+pZChSyIj4/n++8X0aVL\nN33Z0NAQHBwc9Z+9vEYSGxtLZGQEdep8hJNTBZ6VnqC6du3O778fZ+PGn1m8eEVOVDFLMs6NjYlL\nIeDaRTw8BhiUmT9/ERqNhvHjRwEQFxdH2bLlGDt2otHjFSK/kP18syA/dstkbEFZW6kZ5lY1zwy2\nebZ1F3R+HeXKlUOlUhEfH0fnzt1o186VAwf2snXrJhQKBampqbi6dqR9+04AdOr8CSnaVHTaFEqW\nKEnLlq1xd/8cSNuGrm3b1qSkwKef/vvOt1evT1m0aClFi6Ztq7dnz04CAu4zaJCn8b+ETPzXn1t+\n/F1Pl1/rLvXO3ntmRoYpi9eSPsfyflgcTraF8kziBcPWnbZgaTynrnrhBu+tWrXVrzuc0cOwGCq0\nnEBE1FOCTi+hZ18PmjWqA0Bg4EPCw8OwsbFh06YtdOnSDRMTE4KCAklJSdEn3rxK5sYKkTdJ8hWv\nzdHWkhof2Oe5/yv+rxu8pydvpYmaEjX78MuGn9m6YRVarQalUoWn50g6d+7MjRt36NevF4UKFUKn\n0zFp0rQcqlH2krmxQuQ90u2cBfm1Wwbybt3T3/lmpXX3Ol2zebXeOS2/1hvyb92l3tl7z8xIy1e8\nE/5L6066ZoUQxibJV+Q569evYePGn9m48Vf93PHM1h42NTVFo9Gwdu2PnD9/FqVSiYmJCf37D+aD\nD1xe+5nSNSuEMCZJviLPOXBgL82bt+Lw4QO0a+f60rWHO3TozMqVS0lN1bJ48XKUSiWhoSGMGTMM\nH5/vsLd3yO3qCCHEc5S5HYAQGV26dAF7+1J06tRV39LNbO3hDh06A2nJesCAISiVab/OJUqUpEuX\nT9m7d1eOxTh1quHOPB4eAwgIuA9AfHw8Hh4DWLt2tf784cMHadGiIRER4TkSkxDi7SLJV+Qpu3bt\nwNW1E6VLO2Fqaspff10jJCSIUqVKAXDt2lU8PAYweHA/pk4dz+PHUVhaWj23cpa9vQOhoSFGjz8u\nLpZRozxp1qwlvXr11R/fuXMbbm7u7Nix1egxCSHyHkm+Itc9DIth79kA/rkbzOnTJ9m06X+MHOlJ\nXFwsW7duwNbWjuDgYABcXKqyePFyvLymEBkZiYWFJTExT9FoDJdNfHbpSGOIiYlh+PAhdOjQ2WDl\nrODgIJ4+fUrPnn3Yv3/Pc7EKIfIfSb4iV+0/8jsew0ey6egdZi5cQ+NmbalYsTItWrQiIOA+p06d\npHXrdixZspANG9azatUyAAYN+pJbt24yYsQQNBoN/fv3ISEhbWnJoKBAtm3brN+r11imT5+MiYkJ\n4eFhBsd37drBJ590wNLSEheXqhw7dsSocQkh8h4ZcCVy1b2QpyRrUgEIvnmKFk1GkxB6FYBChdIW\n+Q8NDaFjxy4sW/Y9KSkpnDz5O8nJKSxb9iPly1dAo9EwfPhgunfviIODIwUKFGDcuEk4OJQyal2+\n/tqDjz6qS79+valS5UOqV6+JVqvlwIG9lCxpz8mTvxMT84QtW0Jo3ryVUWMTQuQtknxFripb0ooC\nJmkdMDVcvWjeoCq7tqQl31KlHKlWrTpxcXE0adKc6OjHREZG0q/fQNzcXClVKm0TBBMTE+bPX0TP\nnt3w91+Vo/E+DIvh3D+PiH/B7kDlylWgUCELJk2axpQpXqxatZa//rpG5crvM2OGj76cu3sXbt++\nRYUKzjkaqxAi75LkK3KVTZGCpETfI/GfNTwxM8HnbxXBwUF89dXXAHz11SD69+/DlSt/vPQ+arUZ\nycnJORpr+kpYgXeDCbl0ll59elDAJG0rxYyjmF1cqtChQ2e8vSdhZqbG1bWTwX1cXTuyZctGxo2T\nXYOEyK8k+YpcV7t2bYMN3v39/fR/LlCgABMmTGXatIm4unbO9B5xcbE5vq1l+hrQ5sXLU76VN92a\nln/hBg4Afft+Rd++L75Pz559ci5IIcRbQQZciVyRPsI5PDrhlWUrVapMy5ZtWL8+8w3t16//iWbN\nWmZniM9xKWuNtVXailtZ2cBBCCHSSctXGN2z++8WecH702f16vUFJ0/+bnBs5EgPlEolqampODtX\nZMiQ4TkVMiBrQAshso/sapQF+XXXD8ieuu89G8Cmo3f0n1/WfZtX5NefeX6tN+Tfuku9s/eemZFu\nZ2F00n0rhMjvJPkKo7h06QKtWzfm0aNQffdtsbhTVLMOZsTgHiQlJQFw5cplhg8fjIfHAL76qrd+\nfWchhHiXyDtfYTSmpgWYNesbFiz4HkdbS8rZF8baykx/PigokAUL5jJ/vh/W1sVISkrE0/Nr7O0d\nqFu3fi5GLoQQ2UtavsJoatashZWVFVu3bnzh+f3799CmzSdYWxcD0ubu+voupnbtOsYMUwghcpy0\nfIVRjR7tRf/+fahT5/mWbEREOM7OFQ2OWVhYGCu0POnu3Tv4+y8iMTGRhIQE6tVrQNu27fn0044M\nHOhhsHPSuHEjiIuLY/Hi5Xh4DCApKRG12gydTkdMzFMGDRpKvXoNcq8yQgg9Sb7CqAoXLsLQoaOY\nOXMqVap8aHCuRImShIU9Mjh269ZNdLpUKlasbMww84SYmBi8vScwc+ZcHB1Lo9VqmTzZiwMH9mJm\nVpA1a1Zx/vwZ1Go1vXp9wfXrf6NSpf2V/uuva7i792TgwCEAnD59ksmTx3Ho0IncrJIQ4v9Jt7PI\ncc+uh9yw4cc4OpZhzx7Dze5btmzDzp07ePz4MZC2Kf3cubOIjIwwesx5wYkTx6hRozaOjqUBUKlU\njGWAbxMAACAASURBVB49nn37dlOiREmqV6/ByJHj+OKL/syaNY3KlT8wuH7v3l08eHAfSOtVUKlU\nxq6CECIT0vIVOSrjesgJwdE8DItJG+08bBQXL543KFuypD2DBw9l4sQxKJVK4uPjcXXtRL16DXMp\n+twVERGOvb2DwbHLly9QpcqHBATcp0WL1hw+fIB+/QZSsqQDFStW5tatG/qyarWafv16U6hQIcqW\nLU/p0k5GroEQIjOSfEWOyrgesnnx8ly7F4WjrSWFClmwZUtay7ddO1d9+Y8+qstHH9XNrXDzFDu7\nkty8ed3g2I0b/1CoUCEAGjVqQufObTl79jQBAfcoU8bJoOyMGd+ydetGHj9+TEREOGq1OsuxvOjd\n85dfDqBjxzb88stWunfvzIYN2w3W1/7iix58880cfctdCPEv6XYWOUoW1Hhz6etel6lYjbNnTxEU\nFAiARqPh4sUL3L2btjqYubk5devWx86uBMWK2ehHiWfk6TmCgIB7FChQgJCQ4CzFk/7ueejQUfj5\nLWPZsh+5c+c2O3Zs+f84CtGgQSN+++2w/prr1//B0tJKEq8Q/9fefQdEXfcBHH8fQ5AloGCiLE2z\nHKXi6nGbMzUVLEdPmoNEcJsrxZXiykkJKKSZZYYjVyiOnKk4coUzNBEFAvXY854/eLhEpADhDrnP\n6y/5zc8X9T733QWQmq8OKKjW8vjxY778cgUPHz4gOzsbW9uqjB49nsqVqwBw48Y1AgK+IjExkQoV\nKmBubs68eXPQ0yv87kGyHnLRPL3utbWFEcNHTWbRos/Jzs7miTKBak71ibh2FqMKhgB06tSNhQvn\nYWhokGdbw1wmJqZ8+ul0Zs2aRmJiIjdv3sg3ovzfPK/vecaMORgaGhIUtBaAnj374O/vq27F2LNn\nJ716FbwLlRC6TpJvOVfQiNkdO7YSGhrCgAEf0rp1OwDCwk4zefJ4AgLW8+jRI+bOncn8+UvUzZlH\njhxm8eLFTJ06u0gx2Nual4uku3Hjes6ePUNWViYKhQJPz3Fs3foDN25cw9zcQn1d167d6dGjN61a\nueDjs1T9+z116iQHD+7ns89mF/iO3GZ6gHhlGsl6NVi1yk+dlP9SplHVpQEV447h5eVOVlYmjo5O\nuLp+QGpqChUrVgSgcuXKODjkrJfduLELnTp15caN60VOvPD8vudnt2+sV68+SqWS6OiHWFlZc/bs\nacaMmVDkdwmhKyT5lnMF1Vru3PmDX389rk4MAE2bNmfXrh1cvHiB33+/Qo8e7+XpR2zbtj2urj35\n669EDZdC+27dusWJE0dZsyYQhULBzZvX+fzz2dSp8xoeHmOeuwKXsbExq1cvp0GDt7C0tCzUe+o7\nW3PwXKS65pvbTP90Uk7ONuPdvl7/uBlFcPCuPD+PGTOxcAV9juf1PUdF3c83LaxHj17s3/8z1arZ\n0apVWwwNDYv9TiHKO+nzLecKqrU8ePAAO7sa+a63s6vOw4cPePAgiho17AFIS0vFy8sdLy93OnUq\n3T1zyypzc3Oiox+yZ89PxMbGULv2a6xdW/D+wpDT5Nu//4csXeqjPpacnMSMGZNxdx/CmDEj+fTT\nsfzxx20CA/3ZsSNY3Uzfr30t/grzwyArZ5eV+s7WPLn+E3ePrtBY3/m9mAS2Hb753L7n1auXq/ue\nc3Xu3J2jRw8TGhoiTc5C/Aup+ZZj92ISeJhoSOaDe3mOR0Xdx9ramocP8w/AiYz8k6ZNmxMbG0NU\nVM55IyNjfH0DAOjdu2vpB14GVa1alYULl7F16w/4+3/JkydPcHBwRKlUcuhQKFWq2GBjYwtAXFwc\nLi7NAOjTx41jx36hS5d2fPbZbM6dC2PSpGmsW+ePu/soTExMWLZsEY0aNVG/K7eZfnvg3/NybSwM\nqZD+gFdr1aRT3exSb8b/p77n5ORk/vOf1vTp48b69evU91hYWODg4ER8fJwMtBLiX0jyLadyPzxj\n46yJOrWZTl174dKwrrrW4uLSjLi4OI4fP0qrVm2AnD7JyMhI3nqrMTVq2DNpUk5zam7f4bVr4SQn\nJ2uzWFpxLyaB7YfOU6OyCdOnz+L8+bNs3BjEzZs3qFevAT179mHFiiX4+HxBRMRtfvppK+fPh6FS\nqVAoFEyb5o2bW09Onz6JubkFQUEBzJgxm/r1GwKwerU/QUEB/xjDoUOhtGzenBYt/sPOndvo0qF1\nqZa5oL7nZ+3cuS/PzzNnzi3VuIQoLyT5llO5H576hsbYNHif5csWYmVWQV1r6du3Hx06vMPKlV+w\ncePXANjaVmXJkhXo6+tTteoreHt/jq/vCpKTk0hPT8fU1JSvvvpKyyXTrNwvMXevnyU5KgzfFauA\nnCZlMzNz9PT0SUtLRU9PD319fXbt2kG7dh2xtX2FrVt/AHJ+rxUrmhASsofsbBUBAeupXbsOU6dO\nIDExkbi4v3jzzUaEhu7jwIH96nffuROh/vOuXTv49NPpODk5s3SpD7GxMeqadmkoqO9ZFM2DB1HM\nmjUdR0cnkpKSWLBgifpcr15d2LlzH3v37mLdOj/s7Kqrv7B9/PEImjRpqsXIRWmT5PsC/m30a1ZW\nFpaWlowePQE7u+oEBvpz6tQJ1qwJwsAg51fv7j6EOXMWUK2aXYnG9vSHp51DLcZO6JOvqdLKyprZ\ns+cX+IzateuwePHyPMdsbMyJjU0o0VjLstwvMebVGpCeGMPEcSMwNdbnzz/vYm/vyNWrlzl79gzV\nqlVj0qTRXLsWjq1tVbp378mmTd+on5OVlfn/P6lISsoZsLZw4TIg599AVlYW/fsPpHdvN/U97u5D\ngJwkHBFxG1/fFQAoFAp27NjKiBEepVbu3L7nOzFJONmalovR6tp26dJvhITsoWvXd/Od69SpKx4e\nowGIj4/D03MEvr4B6ml/ovyR5FtMERF/FGr068WLF/D2nsa6dTkfxA8ePODbb9czZMjwUo1P5teW\njKe/xNRu0p2xblOJjbzOTz9tZc4cnzzXbt8eTGzsX4SH/054+O+Ymppy9uwZXFyaoQIGj1nETxsX\nM2vWdNav/w4rK2siI+8RGxuDk5NzgTHs2rWDESNG4er6PgAPHz5k5MiPGTJkeKmOKLa3NadxPTud\n+rJVmkaO9CQwMIDGjV2wta1a4HXW1pVp164jJ08ep2fP3hqMUGiSJN9iMjMzU49+bd78bfXo1yVL\nFuS57s03G2FgYEBkZM6gp4EDP2L37h28/XarUt+pp7zMr9WmZ2uAQJ5NIp62a9cOFi1aRs2atQDY\nv/9ntm37kaoOr5ONIb+Ep1Ot2XAeXdrEwIGuODo6oa9vwOjRE4iIuM3mzZuwt3fM09y4bp0foaEh\nNG/+tjr5vvLKKzx58pjDhw+SmZnBggVz8PP7mvr1GwA5o5Hfe68Lffu+z7Bhn5T2r0j8i/T0dM6f\nP8vVq5cxMqrAxx8PYvVqf1JSkmnTphmenuPU1z56FE/v3t1o3/4dsrKy6Ny5LXXqvAZASkoKI0d6\n0rSpLL9aHshUo2KysbFl4cJlXLp0kU8++ZiBA105efLYc6+1srLm8ePHAJiYVGTy5M+YP38O6enp\nmgxZFJO9rTl929cGYGXwJX65EMWNezmbROS6fv0aoFInXoC2bTtw6dJvnDx/g2yVCsiZozvIaxF1\n675Bs2Yt+fLLtXTo8A7Dhn3Cxx+PICRkj/r+L79cy6VLF2nTpj3h4VfznDM3t6Bz55yR546OThw8\n+Hdf8alTJzE11e19kMuKtLQ07t27i7NzLcaMmci33/5IrVqvMn36JADs7R0ID7+qvv7gwf1UrfoK\nSuUTKleujJOTM76+Afj6BjBr1uesWrVMW0URJUySbzFFRt7D1NSU6dNnsW3bHry957F0qQ9K5ZN8\n10ZHP8DW9u/BMW+91RgXl2asW5d/9Kgou57eJKJywwFciYhXn3vttboEBW3Kc72RkRG7d4fyduM6\nNHXN6Vu3tjCiQc3KLF/+JUOHuue5vl27jpw7F0ZqaioAx44doVmz5lSsWFHdZPnswhYALVq8TVjY\nabKzswE4cGAf77zTpUTLLoruXkwC3wSHYFzRBCsrK/XxOXN8yM7OJiMjgw4dOuVJvidOHKNx46bc\nuHGdRo1c8jwvISEBKysZ+FZeSPItotyFB06fv8SyZYvJyMgAcr7B5o5+fVrOZufG+fp43N1HcerU\nCe7fzzsHV5Rdxd0k4umFM8a6NSywK8DIyIg2bdpx9OhhAPbu3cl77/UFoEoVW0aMGMnChfPy3Wdg\nYEj9+g347bfzJCcnkZyclOfLntC83FHyYZdukZIBSak5nxNTp05g5swppKenkZmZSeXKlTE0NCQk\nZA8jRgzmjz9uExZ2ih493sPc3Jw7dyLw8nLHw2MYY8eOpHPnbloumSgp0udbBHkXHrDE6dU3GD78\nI0xMKpKdrWLUqLEcO/YLa9as4ttv16Ovr4+JiQlz5/rke5aRkRHTp8/ik08+1kJJRHG8yCC2wva/\n9+zZhy+/XEmjRk1ISEjIMy6gc+duHD16mO3bg/Pd16lTV0JD9xEd/ZA2bdqTmZlR6NhyrV69nOvX\nw4mPjyM1NRU7u+pUrWqDl9ckvvpqJXfuRGBsbIy+vj4ffzyCN99sBMDNmzfw8/MlLS2VzMxMGjVq\nwtCh7jq9vGRuK4mRRTVUqixa93CnRXNH9UBMd/ch6r7b/v0/JD4+jszMTN58sxFnzpxSz63PbXYG\niIv7i6FDB+Hi0oxXXqmmnYKJEiPJtwieXXigY/vujBmVd7pHmzbtCrz/2cEvdeu+wZEjp0s8TlF6\nSmsQ272YhP8n9aqkpCTx44+beffdXvmumzhxGp98MoTk5KQ8xxs1asKqVV8QFxfLrFmfExoaUuQY\nRo8eD8Devbu4e/cOHh6jqVLFDDe39xkw4L/qDSHu349kxozJrF37DUrlE+bM+YwFC5bi4OCISqVi\n/fp1rFq1jIkTpxT9F1FO1He2Zt+ZP8l+pR5PIo5glP4QyEmoz45wb9euI+PHe2JiYsqQIcM5c+bU\nc59pYVGJChWMycrK0lQxRCmS5FsEsvCAKA1Pt6gcPBdJy9ad+X5jAFu37s53rZWVFaNHj2fatEl5\njuvp6eHi0pyYmOgSHWx16dIlKlWqRNu27dXHqlevQVDQJhQKBSEhe+nevZe6pqZQKBgyZDjvv/8e\naWmpGBkZl1gsLyM9AyNebT2cn3cHs+2HQLKyMtHT01ePcIecmRO2trZUr14DPb28PYG5zc56enqk\npKTQq1dvqlfPvya7ePlI8i0CWXhAlIZnW1RsmrTk55/7q88/uwVh69btOH78LIB6/1z4u+YK5Fms\n40VERkaqN9gAWLx4Pn/+eZfHjx8zdepMoqLu07Rp8zz3KBQKrK0rEx8fX+KLx7wsrkTEo0zKafpP\nw5xez92F6h31n+bP/3vlq9zFNgD27z9SqnEK7ZEBV0WUO+1EEq8oKcUdyFWS7sUk8PPpu3mmT0HO\nnOLcDTYAJk/+DF/fAGrVqkV6eho2Njb5NujIysrir79idXpkbln4OxVlm07WfM+fP5tvhaI1a1ZT\nqVIlTp48TmJiIn/9Favuk1m5cg0ffNCbTZuCMTIy0lbYopzS9mpkzzZ7v2Wdqj7XqFEj4uPjOH78\nCK1atQVyBv7cvXsXhUJBt249GD/ek7ffbo29vQMqlYqvv15Ly5b/wdhYd5uctf13Kso+nUy+BbG0\ntMLXN+C5yVmI0qTN1ciebfaOzEqk0v8/GfT09Fi0aDn+/r58991GIGcFrT593HjzzUbo6ekxc+Zc\nvvhiYZ7RzmPGTNRKWcoSWWFO/BNJvkLouGcHEg5yc8uTNCwtLZkyZUaB99et+wYrVujWbldCvCid\nTb7nzp3Fy+vvFYaiou4zfPhILUYkhHZIE6kQmqdTyTd3LqVeUgpNmrjk6/MVQldJE6kQmqUzyffp\nQSX6KX9i+ZxdaYQQQghN0Jnk+/SgkoSkDBSpsqOQKJ5nB+QdPnyAoKAArKysefLkMebmFupru3bt\nTo8evWnVygUfn6W0bt0OyNl56ODB/fnm8AohdIPOJN+nB5XUqPkGY9365zn/9MT2xo1daNw4744i\nwcG7NBKneLmEhobw/fffsnLlGtasWc3AgR+p1+99mrGxMatXL6dBg7ewtLTUQqRCiLJEZxbZKOzO\nMkIUVkjIHrZs+Y4VK77C2rryP15rYmJK//4fsnSpTF8TQuhQzRdkUIkoORcv/kZsbCxKpTLPQve5\nO1rlGj9+MrVqvQpAnz5uHDv2C/v3h2BhYfHsI4UQOkSnkq8QL+peTAJnwqMxr2TF8uVfsnv3DubN\nm8nSpasA8PAY89xmZ8hZ83jaNG88Pd0ZPHioJsMWQpQxOtPsLMSLyh0x/8uFKJQZpsQ8ScfV9QMM\nDAz55pugQj3D1rYqQ4eOwM/Pt5SjFUKUZVLzfUkUtB61o6MTLVu2+sfNzgGWLl3I1auX+Prr77QR\nfrnw9Ij59MxsrkTEY29rzrRp3gwdOgg9PT1u3LiWp9m5UaMm+fZx7tatB0eP/qLByIUQZU2xku+2\nbdvYvn07AGlpaYSHh3PixAnpx9IClUrFtGkTC9zs3MDAgNTUVC5f/g1n51qcP38230huUTi5I+ah\nFjVqvqHeqcbKyort2/f+4707d+7L87OPz9LSClMI8RIoVvLt27cvffv2BWDOnDm4urpK4tWSR4/i\n/3Gzc4BDh0Jp0qQpLVr8h23btkjyLSZZhlEIUVJeqM/38uXL3Lp1iw8++KCk4hFFVLlylXybnXt5\nufPf/37AlSuXAdi1awc9evTGxaUZN25cJzY2RlvhvvTsbc3p1txREq8Q4oW8UJ+vv78/np6e/3qd\nlZUJBgb6L/KqMsfGRnMfvhFRTwi/n0RKWvoz781EqYwjLi5GfXzJkoUAjB8/HhMTfZTKGO7c+YOA\ngJy1qw0M9Nm/fxfjxo0rdjyaLHtZIuXWPbpadil36St28lUqlURERNCiRYt/vfbRo+TivqZMsrEx\nJzY2QSPvyh1hGxuXxL0Llzl47DIN6zqRlpbGqVOnmTdvEYcO/cL27bvzbHZ+48YtnjxJYc+eTQwf\n7oGr6/sAPHz4kJEjP+b99z/C0NCwyPFosuxliZRb9+hq2aXcJfvMghQ7+YaFhdGyZcvi3v7CLlw4\nR2Cgv/rn2NgYLCwqsXbtBg4eDMXHZw6bN2+nShUbAAID/QkN3UeVKlUAUCqf0LFjZwYPHqaV+Asr\nd4StvqExleu+y5xZn2JrbUFmZgaurh/g4OBY4Gbn9es3ZPbsz9iwYbP6ea+88gqvvlqbw4cP0rlz\n11KJ+fz5s3h7T8PJyRmA9PR0Jk2aSp06dTlwYB/btv0I5GzUXrv2a4waNQZDQ0Pc3HpSteorKBQK\n0tPTee211/HyGoeRkVGpxCmEENqiUKlUquLcuG7dOgwMDBgyZMi/Xlva36Li4+MYNWo406fPomHD\ntxg3bhR1676BoaGheppHYKA/lStXpndvNyAnIXz4YT/8/b/Gysq6SO/TRs03d6NzbS+NWZiyPzst\n6syZUwQHb6ZPHzc2b97E558vxtzcHJVKxerVy3ByqkmvXn1wc+vJpk3B6mS7YUMgSqWS0aPHl3q5\n/o3UBnSPrpZdyl2yzyxIsWu+w4cPL+6tJSozM5MZM6YwYMB/adjwLaKi7qNUKhk0aDDDhn3I4MHD\nMDDIX0yl8gmZmZllvlaVO8I2cP0GDny3ngcnnLCyslbXJidOHENaWhoZGRlUqFABAFtbW956qwle\nXuPw9p6KSqWiefOW7N8fov5dNG3anCFDNPN3mJCgxNLSiuDgLYwaNRZz85x/kAqFgtGjJ6hHZT+r\nf/9BDBrUr0wkXyGEKEkv/SIbK1Ysxdm5Ju+9lzP1affun3j33V6Ym5tTv35Djhw5RMeOnQHYvPk7\nDhzYT3R0NDY2NkydOhMTE1Nthl8o9rbmvO5oxUkTUxwcHPHx+YIzZ06xcuUXZGZm4OzsTFxcXL5a\n44oVS0hJSSE6+iEKhYJVq/wwMjIiMzOTOXNmcObMKZo1+/c+++I4d+4sXl7uZGRkcOvWDXx8vmDF\niiXUqFEDgCtXLuHn50tWVia2tlXzLB6Sy8jImPR02fpRCFH+vNTJd8+enfzxxy1WrfIDICsri/37\nf6ZaNTtOnDhGQsITtm59oE6+/fsPpHdvN65dC2f27OnY2ztoM/wiMzMz4+HDByQmJpKQoCQhQUnN\nmq+SmZmR79r+/Qfx3ntdGTr0E777bgO2tlXVidnAwIC5c30KrHEW172YBK5ExKOXlEKTJi7qhPrn\nn3f45JOhvPZaXaKioqhduw716zfE1zeAu3fvsGTJguc+LykpERMTk+eeO3/+LNOmTeSbb36gatVX\ngL9X/Grf/h0CAr7iypVLGBkZoVAocHPrn2cu9KZNG9iy5Tu2bNlZ5ls/hBDlz0u5tvO9mAQCfzzI\n1+sD+fzzReqm1F9/PUHdum+werU/y5atZu3ab4iPj+fWrZt57q9b93U+/HAws2ZNJzs7WxtFKJZH\nj+JJSEhg6NBBzJ8/G4VCD1vbqkRERBAXF8f48Z4sX74YAEPDCiQnJ9O1a3eys1WcOHGMtLRUjhw5\njJeXO+7uQ/D1XVFiseX2Tf94+DbBR26TnJqpPmdllbPdnqvr+3z11UoSExPV5y5cOFvgl4BNm76h\nQ4dOBb7T0LACCxbM5dlhCz4+c7Gzq87atRvw9Q1g7tyFbNiwDqXyifqa/ft/pmPHzhw8uL9Y5RVC\niBfx0tV8cz/kL+1fR1ZqKlOmTcbIMGcOsbGxMb17u+a5vmfP99i6dYt6lHOuHj16c/BgKNu3B6un\n4ZRV92ISCL/7CItKVqxcuYYvvljIsGHuLFo0H3t7B3Wz8/LlX6prcUeOHAZg9uwZJCcnYWJiSmho\nCD169KZt2/acOnWyRBPP0+seJyRlcPfKOby83NHX1yc5OYnRo8fTunU7srKymDZtIgBJSUk4O9dk\n8uTP1M+ZMMELPT09srOzqV27Dp6eBc9HbtLEhexsFdu2bcHVNWehl7i4OP788y5z5/7djG1lZUVg\n4LfqJH/+/Fns7GrQu7crc+d60717zxL7PQghRGG8dMk390O+RosRAPRtX4tuzR0LvH7QoMEFnlu+\n/MsSj6+k3YtJ4IsffuPOzTiUSelkG1YiJSWFQ4cO/OM83bVrv6Jdu47MnevDjz9u5tdfTxAc/AM9\nevQmKyuLixcvlGizc+66x/HKNGrUfIMlk3967qjsdu060q5dx+c+Izh4V5HfO2nSVEaMGEzz5n9v\n42dnV13958BAfy5cOEdCQgJDhgyjfft32L37J3r27I2DgxOGhoZcvXqFevXqF/ndQghRXC9d8n36\nQ97awki9uH15dfzSA5RJOX26mWkJTBw/Cv3sJG7evM6ECVMICzutvja31piWlkZsbAyBgd8C0K9f\nfwwNDVi9ejlDhw4CoF69hnzyyb+vTlZYmlz3OHdP3eTUTCpVsmTMmInMnz+LBg3eJCsrk4cPo9TX\n5k41W7NmNSkpKSiVSn799QSPHsUTHPwDSUmJbNv2gyRfIYRGvXTJV9cWt8+tm1rXao11rdZ0dqlB\n/3fqqM8Xtsm0d2839RznF3H69Gk8PDyeO9Bp8eL51K/fkD1PXT9r1ueEhZ1m3To/dY00MTGRBg3e\nZOLEKUV+f263Q+QfUaREPeZeTAKtWrXh6NHD7N27m1GjxlCtmh3btv1I37791O+7efM6Tk7O7N+/\nlx493sPTcywAqamp9OvXi0ePHmFlZfVivxwhhCikly75Qk4CLu9JN9d/GlbjVHg0yqQMLEwN+U/D\natoOST3QacWKL/M0XVtYVMLXN+C593Tq1BUPj9EAZGdn4+k5nGvXfqdu3TeK9O6C9tQdO3Yi586F\nATBjxlyCggLw8BiGvr4+KSkptG/fkY4dOzNixGBmzpyrfp6xsTFt23Zg167tfPTR0CLFIoQQxfVS\nJl9dYm9rzsQP3ipTNf3nDXQqiuTkZBISEjE1NSvyvQXtqWtqasbWrbvV1+XWbJ+1YcP3+Y5NmjS1\nyHEIIcSLkOT7EiiLNf3nDXRSKp/g5eWu/tnGxpZZsz4HIDQ0hKtXL/PXX39hamrKRx8NLdY8a13r\ndhBClE+SfEWxPDvQCQrX7BwVdZ+JE0fj4FD8BU7K4pcRIYQoipdykQ2hHfdiEjh2IVK9gEarVm2w\nt3dk797d/3Ln3+zsqjNhwhRmzpxKampqaYUqhBBlmtR8RaH8Pcr4rnqU8bMDnZ5tdgYYOdIr37Oa\nNm2Oi0szAgP9C+ybFUKI8kySryiU3FHGJlVqYVKllnqU8dMDnQqa9lS/fsN8x6ZMmVGq8QohRFkm\nzc6iUOo7W2NtkbN0pS4sbiKEEKVJar6iUHJHGd+JScLJ1lQGPAkhxAuQ5CsKzd7WnMb17IiNTdB2\nKEII8VKTZudiOn/+LK1auXDgwL48xwcP7s/8+bNxc+tJWlpavntmzZqmyTCFEEKUQZJ8X4Cjo1Oe\nbflu375FSkqKFiMSQgjxMpDk+wJefbU2Dx8+UG8Ov2/fXjp37qblqIQQQpR1knxfUNu2HThy5BAq\nlYrw8KvPnVYjhBBCPE2S7wvq1KkrBw/u57ffzvPmm420HY4QQoiXgCTfIroXk8C2wzeJfZzTt1u9\neg1SUlIIDt4sTc5CCCEKRaYaFUHuEovxyjT0U/7E8v9rHHfs2Il9+/bi4OBIVNR99fUeHsPU+912\n6tSFOnXqaiVuIYQQZYsk3yJ4eiP3rIoOdOjeHgA3t/64ufUHoEWLt2nR4u0Cn9G4sUvpByqEEKJM\nk2bnIpAlFoUQQpQEqfkWgSyxKIQQoiRI8i0iWWJRCCHEi5JmZyGEEELDJPkKIYQQGibJVwghhNAw\nSb5CCCGEhknyFUIIITRMkq8QQgihYZJ8hRBCCA2T5CuEEEJomCRfIYQQQsMk+QohhBAaJstLK23O\nEQAACbdJREFUCp22ceN6zp49Q1ZWJgqFAk/PcWzd+gMdO3bOsztVZGQkPXv2ok6d1/Lcv3LlGvT1\n9TUddj6rVy/n+vVw4uPjSE1Nxc6uOubmFiQkKNXXPHnymMePH7Nr134Afv/9CqNGDWfNmkBef72e\ntkIXQidJ8hU6KyLiD06cOMqaNYEoFApu3rzO55/Pzpdgczk5OePrG6DRGAtr9OjxAOzdu4u7d+/g\n4TE6z/nU1FRGjRrO+PGT1cd27dpB//4fsm3bj3z2mSRfITRJmp2FzjIzMyM6+iF79vxEbGwMtWu/\nxtq1G7QdVqnw8ZlD8+Yt6dDhHQCSk5M5dy6Mjz8eweXLF3n8+LGWIxRCt0jNV+gsGxtbFi5cxtat\nPxAUtBZjY2Pc3UcVeP2dOxF4ebmrf37ttdfVNc6ybNOmDSQnJzNihIf62MGD+2nbtgNGRkZ06NCJ\n3bt38OGHQ7QXpBA6RpKv0En3YhI4GnaVOjUsmT59FgDXrv3OpEljqFevwXPvKavNzvdiErgSEU99\nZ+t858LCTvPzz7vx8/saPb2/G7p27dqBvr4+EyaMJi0tlZiYGAYO/CjPNUKI0iPJV+icezEJrAy+\nxN3rZ0mOCsN3xSqcq1tjb++AmZk5enraH0BVWLlliVemcfBcJG9Zp6rPPXgQxeLFC1iyZAVmZmbq\n47dv3yI7O5uAgPXqY+PGjeLkyWO0atVWk+ELobMk+QqdcyUinnhlGubVGpCeGMPEcSOoWqUS2dkq\nRo0ay7Fjv7BixVJMTU0BcHBwZOrUT/M1OwNMnz4LO7vq2igG8HdZAOKVaURmJVLp//+rv/kmiIyM\ndJYu9clzj51ddbp06Z7nWM+efdi6dYskXyE0RKFSqVSl/ZLY2ITSfoVG2diYl7syFVZ5KPvTtUVr\nCyPGujXE3tb8H+8pq+UuTlmKoqyWWxN0texS7pJ9ZkGk5it0jr2tOWPdGqr7SUsyWWlaeSqLELpE\nkq/QCefPn8XbexpOTs7qYwqFgj3/b/i5desG9vYOGBkZ07Vrd6Kjo6lcuTK9e7upr3d3H8KcOQuo\nVs1O4/H/E3tbc0m6QrxkJPkKndGkiQtz5vg895yXlzuffjodR0cnAAID/TUYmRBC18i8AiGEEELD\npOYrdMa5c2fzjFZ+++1WDBz4UYHXb978HQcO5KyDXKGCAXfuRJR6jEII3SDJV+iMf2p2fp7+/Qeq\n+3xtbMzp08e1tEITQugYSb6iXMtd/UkvKUXboQghhJokX1FuPT0HVj/lT+6HheVbJOOLL1ZhZGSs\npQiFELpKFtkoBl2dhA4vV9l/Pn2XHw/fVv/cr30tujV3LNazXqZylyRdLTfobtml3CX7zILIaGdR\nbtV3tsbawggAawuj5248IIQQ2iDNzqLcktWfhBBllSRfUa7J6k9CiLKo2MnX39+fQ4cOkZGRwYAB\nA+jXr19JxiWEEEKUW8VKvqdPn+bChQt8//33pKSkEBQUVNJxCSGEEOVWsZLv8ePHqVOnDp6eniQm\nJjJ58uSSjksIIYQot4o11WjGjBlERUXh5+dHZGQkHh4ehISEoFAonnt9ZmYWBgb6LxysEEIIUR4U\nq+ZraWlJzZo1qVChAjVr1sTIyIj4+HgqV6783OsfPUp+oSDLGl2dBwe6W3Ypt+7R1bJLuUv2mQUp\n1jzfJk2acOzYMVQqFdHR0aSkpGBpaVnsAIUQQghdUqyab/v27QkLC8PNzQ2VSoW3tzf6+tKsLIQQ\nQhRGsacaySArIYQQonhkeUkhhBBCwyT5CiGEEBqmkV2NhBBCCPE3qfkKIYQQGibJVwghhNAwSb5C\nCCGEhknyFUIIITRMkq8QQgihYZJ8hRBCCA0r9gpXuiouLo6+ffsSFBRErVq1tB2OxvTp0wczMzMA\natSogY+Pj5Yj0gx/f38OHTpERkYGAwYMoF+/ftoOSSO2bdvG9u3bAUhLSyM8PJwTJ05gYWGh5chK\nV0ZGBlOnTuX+/fvo6ekxb948nfl/np6ezrRp07h37x5mZmZ4e3vj5OSk7bBK1cWLF1m6dCkbN27k\n7t27TJ06FYVCQe3atZk1axZ6eqVXP5XkWwQZGRl4e3tjbGys7VA0Ki0tDZVKxcaNG7UdikadPn2a\nCxcu8P3335OSkkJQUJC2Q9KYvn370rdvXwDmzJmDq6truU+8AEeOHCEzM5PNmzdz4sQJVqxYwerV\nq7UdlkZs2bIFExMTtmzZwh9//MG8efMIDAzUdlilZu3atezcuZOKFSsC4OPjw7hx42jevDne3t4c\nPHiQTp06ldr7pdm5CBYtWkT//v2xtbXVdigade3aNVJSUhg6dCgfffQRv/32m7ZD0ojjx49Tp04d\nPD09GTlyJO3atdN2SBp3+fJlbt26xQcffKDtUDTC2dmZrKwssrOzSUxMxMBAd+ont27dok2bNgDU\nrFmT27dvazmi0uXg4JDni9XVq1dp1qwZAG3atOHkyZOl+n7d+Zf1grZt24a1tTWtW7cmICBA2+Fo\nlLGxMcOGDaNfv37cuXOHESNGEBISUu4/mB49ekRUVBR+fn5ERkbi4eFBSEgICoVC26FpjL+/P56e\nntoOQ2NMTEy4f/8+3bp149GjR/j5+Wk7JI15/fXXOXz4MO+88w4XL14kOjqarKyscrtjXZcuXYiM\njFT/rFKp1P+3TU1NSUgo3T2NpeZbSFu3buXkyZP897//JTw8nClTphAbG6vtsDTC2dmZXr16oVAo\ncHZ2xtLSUifKbmlpSatWrahQoQI1a9bEyMiI+Ph4bYelMUqlkoiICFq0aKHtUDRm/fr1tGrVin37\n9vHTTz8xdepU0tLStB2WRri6umJmZsbAgQMJDQ2lXr165TbxPs/T/btJSUml3s0iybeQNm3axLff\nfsvGjRt5/fXXWbRoETY2NtoOSyOCg4NZuHAhANHR0SQmJupE2Zs0acKxY8dQqVRER0eTkpKCpaWl\ntsPSmLCwMFq2bKntMDTKwsICc3NzACpVqkRmZiZZWVlajkozLl++TMuWLfn+++/p2rUr9vb22g5J\no9544w1Onz4NwNGjR3FxcSnV95XvdkNRItzc3Jg2bRoDBgxAoVCwYMGCct/kDNC+fXvCwsJwc3ND\npVLh7e2tUzWBiIgIatSooe0wNGrIkCFMnz6dgQMHkpGRwfjx4zExMdF2WBrh6OjIypUr8fPzw9zc\nnPnz52s7JI2aMmUKM2fOZNmyZdSsWZMuXbqU6vtkVyMhhBBCw6TZWQghhNAwSb5CCCGEhknyFUII\nITRMkq8QQgihYZJ8hRBCCA2T5CuEEEJomCRfIYQQQsMk+QohhBAa9j+FK3Vuwn8GHAAAAABJRU5E\nrkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10a4254a8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "1       5.363636\n",
       "3       6.386364\n",
       "5       9.318182\n",
       "11      4.454545\n",
       "12      5.136364\n",
       "15      7.500000\n",
       "19      5.636364\n",
       "20      7.909091\n",
       "25      9.727273\n",
       "27      7.818182\n",
       "29      7.000000\n",
       "30      6.454545\n",
       "31      4.681818\n",
       "32      7.318182\n",
       "35      7.045455\n",
       "40      6.181818\n",
       "41      6.500000\n",
       "42      6.545455\n",
       "43      6.772727\n",
       "47      5.727273\n",
       "51      7.818182\n",
       "54      6.272727\n",
       "55      6.545455\n",
       "56      8.272727\n",
       "59      5.136364\n",
       "60      5.886364\n",
       "61      8.136364\n",
       "62      5.318182\n",
       "64      3.727273\n",
       "66      7.590909\n",
       "         ...    \n",
       "90      7.090909\n",
       "92      4.454545\n",
       "93      7.500000\n",
       "95      4.000000\n",
       "96      7.227273\n",
       "103     7.954545\n",
       "105     5.000000\n",
       "106     5.545455\n",
       "107     5.227273\n",
       "111     9.727273\n",
       "113     6.045455\n",
       "114     5.909091\n",
       "115     5.772727\n",
       "121     6.954545\n",
       "127     4.000000\n",
       "128     6.000000\n",
       "129     9.318182\n",
       "130     5.818182\n",
       "131     5.000000\n",
       "141     6.909091\n",
       "145     7.454545\n",
       "146     6.454545\n",
       "149     6.636364\n",
       "150     4.454545\n",
       "152     7.000000\n",
       "153    10.000000\n",
       "155     7.136364\n",
       "156     6.409091\n",
       "159     6.863636\n",
       "160     3.500000\n",
       "Name: avexpr, Length: 64, dtype: float64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = ajr_df['avexpr']\n",
    "y = ajr_df['logpgp95']\n",
    "labels = ajr_df['shortnam']\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "ax.scatter(x, y, marker='.')\n",
    "\n",
    "for i, txt in enumerate(labels):\n",
    "    ax.annotate(txt, (x.iloc[i], y.iloc[i]))\n",
    "    \n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1       5.363636\n",
       "3       6.386364\n",
       "5       9.318182\n",
       "11      4.454545\n",
       "12      5.136364\n",
       "15      7.500000\n",
       "19      5.636364\n",
       "20      7.909091\n",
       "25      9.727273\n",
       "27      7.818182\n",
       "29      7.000000\n",
       "30      6.454545\n",
       "31      4.681818\n",
       "32      7.318182\n",
       "35      7.045455\n",
       "40      6.181818\n",
       "41      6.500000\n",
       "42      6.545455\n",
       "43      6.772727\n",
       "47      5.727273\n",
       "51      7.818182\n",
       "54      6.272727\n",
       "55      6.545455\n",
       "56      8.272727\n",
       "59      5.136364\n",
       "60      5.886364\n",
       "61      8.136364\n",
       "62      5.318182\n",
       "64      3.727273\n",
       "66      7.590909\n",
       "         ...    \n",
       "90      7.090909\n",
       "92      4.454545\n",
       "93      7.500000\n",
       "95      4.000000\n",
       "96      7.227273\n",
       "103     7.954545\n",
       "105     5.000000\n",
       "106     5.545455\n",
       "107     5.227273\n",
       "111     9.727273\n",
       "113     6.045455\n",
       "114     5.909091\n",
       "115     5.772727\n",
       "121     6.954545\n",
       "127     4.000000\n",
       "128     6.000000\n",
       "129     9.318182\n",
       "130     5.818182\n",
       "131     5.000000\n",
       "141     6.909091\n",
       "145     7.454545\n",
       "146     6.454545\n",
       "149     6.636364\n",
       "150     4.454545\n",
       "152     7.000000\n",
       "153    10.000000\n",
       "155     7.136364\n",
       "156     6.409091\n",
       "159     6.863636\n",
       "160     3.500000\n",
       "Name: avexpr, Length: 64, dtype: float64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's fit a linear model to this scatter:\n",
    "\n",
    "> (1) $ \\ln(pgp_95)_i= β_0 + β_1(avexpr_i) + u_i $\n",
    "\n",
    "* $ β_0 $ is the intercept of the linear trend line on the y-axis\n",
    "* $ β_1 $ is the slope of the linear trend line, representing the marginal association of protection against against expropriation risk with log GDP per capita\n",
    "* $ u_i $ is an error term.\n",
    "\n",
    "Fitting this linear model chooses a straight line that best fits the data in a least-squares, as in the following plot (Figure 2 in AJR):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAe0AAAFlCAYAAADGV7BOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x11ee8e6a0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# dropping NA's is required to use numpy's polyfit...\n",
    "# using only 'base sample' for plotting purposes...\n",
    "\n",
    "\n",
    "ajr_df = ajr_df.dropna(subset=['logpgp95', 'avexpr'])\n",
    "ajr_df = ajr_df[ajr_df['baseco'] == 1]\n",
    "\n",
    "x = ajr_df['avexpr'].tolist()\n",
    "y = ajr_df['logpgp95'].tolist()\n",
    "labels = ajr_df['shortnam'].tolist()\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "ax.scatter(x, y, marker='.')\n",
    "\n",
    "for i, txt in enumerate(labels):\n",
    "    ax.annotate(txt, (x[i], y[i]))\n",
    "    \n",
    "ax.plot(np.unique(x),\n",
    "         np.poly1d(np.polyfit(x, y, 1))(np.unique(x)),\n",
    "         color='black')\n",
    "\n",
    "ax.set_xlabel('Inverse Expropriation Risk Classification, 1985-95')\n",
    "ax.set_ylabel('Log GDP per capita 1995 (PPP)')\n",
    "ax.set_title('Figure 2: OLS Relationship: Prosperity and \"Property Security Institutions\"')\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To estimate the constant term $ β_0 $, we need to add a column of 1’s to our dataframe so that we can use statsmodels's OLS routines:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:               logpgp95   R-squared:                       0.540\n",
      "Model:                            OLS   Adj. R-squared:                  0.533\n",
      "Method:                 Least Squares   F-statistic:                     72.82\n",
      "Date:                Wed, 16 Oct 2019   Prob (F-statistic):           4.72e-12\n",
      "Time:                        11:23:22   Log-Likelihood:                -68.168\n",
      "No. Observations:                  64   AIC:                             140.3\n",
      "Df Residuals:                      62   BIC:                             144.7\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "constant       4.6604      0.409     11.408      0.000       3.844       5.477\n",
      "avexpr         0.5221      0.061      8.533      0.000       0.400       0.644\n",
      "==============================================================================\n",
      "Omnibus:                        7.098   Durbin-Watson:                   2.064\n",
      "Prob(Omnibus):                  0.029   Jarque-Bera (JB):                6.657\n",
      "Skew:                          -0.781   Prob(JB):                       0.0358\n",
      "Kurtosis:                       3.234   Cond. No.                         31.2\n",
      "==============================================================================\n",
      "\n",
      "Warnings:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "ajr_df['constant'] = 1\n",
    "\n",
    "regression_1 = sm.OLS(endog=ajr_df['logpgp95'], \n",
    "                exog=ajr_df[['constant', 'avexpr']], \n",
    "                missing='drop')\n",
    "results_1 = regression_1.fit()\n",
    "print(results_1.summary())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We extend our bivariate regression model to a multivariate regression model by adding in other factors correlated with $ \\ln(pgp_95)_i $:\n",
    "\n",
    "* climate, as proxied by latitude\n",
    "* the different culture and history of different continents\n",
    "\n",
    "latitude is used to proxy this\n",
    "differences that affect both economic performance and institutions, eg. cultural, historical, etc.; controlled for with the use of continent dummies\n",
    "Let’s estimate some of the extended models considered in the paper (Table 2) using data from"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        Table 2 - OLS Regressions\n",
      "=========================================\n",
      "                 Model 1 Model 3 Model 4 \n",
      "-----------------------------------------\n",
      "constant         4.63*** 4.87*** 5.85*** \n",
      "                 (0.30)  (0.33)  (0.34)  \n",
      "avexpr           0.53*** 0.46*** 0.39*** \n",
      "                 (0.04)  (0.06)  (0.05)  \n",
      "lat_abst                 0.87*   0.33    \n",
      "                         (0.49)  (0.45)  \n",
      "asia                             -0.15   \n",
      "                                 (0.15)  \n",
      "africa                           -0.92***\n",
      "                                 (0.17)  \n",
      "other                            0.30    \n",
      "                                 (0.37)  \n",
      "R-squared        0.61    0.62    0.72    \n",
      "No. observations 111     111     111     \n",
      "=========================================\n",
      "Standard errors in parentheses.\n",
      "* p<.1, ** p<.05, ***p<.01\n"
     ]
    }
   ],
   "source": [
    "ajr2_df = pd.read_csv('https://delong.typepad.com/files/ajr2.csv')\n",
    "ajr2_df['constant'] = 1\n",
    "\n",
    "X1 = ['constant', 'avexpr']\n",
    "X2 = ['constant', 'avexpr', 'lat_abst']\n",
    "X3 = ['constant', 'avexpr', 'lat_abst', 'asia', 'africa', 'other']\n",
    "\n",
    "regression_2 = sm.OLS(ajr2_df['logpgp95'], ajr2_df[X1], missing='drop').fit()\n",
    "regression_3 = sm.OLS(ajr2_df['logpgp95'], ajr2_df[X2], missing='drop').fit()\n",
    "regression_4 = sm.OLS(ajr2_df['logpgp95'], ajr2_df[X3], missing='drop').fit()\n",
    "\n",
    "info_dict={'R-squared' : lambda x: f\"{x.rsquared:.2f}\",\n",
    "           'No. observations' : lambda x: f\"{int(x.nobs):d}\"}\n",
    "\n",
    "results_table = summary_col(results=[regression_2, regression_3, regression_4],\n",
    "                            float_format='%0.2f',\n",
    "                            stars = True,\n",
    "                            model_names=['Model 1',\n",
    "                                         'Model 3',\n",
    "                                         'Model 4'],\n",
    "                            info_dict=info_dict,\n",
    "                            regressor_order=['constant',\n",
    "                                             'avexpr',\n",
    "                                             'lat_abst',\n",
    "                                             'asia',\n",
    "                                             'africa'])\n",
    "\n",
    "results_table.add_title('Table 2 - OLS Regressions')\n",
    "\n",
    "print(results_table)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAe0AAAFlCAYAAADGV7BOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x11ee94208>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Dropping NA's is required to use numpy's polyfit\n",
    "df1_subset2 = ajr_df.dropna(subset=['logem4', 'avexpr'])\n",
    "\n",
    "X = df1_subset2['logem4']\n",
    "y = df1_subset2['avexpr']\n",
    "labels = df1_subset2['shortnam']\n",
    "\n",
    "# Replace markers with country labels\n",
    "fig, ax = plt.subplots()\n",
    "ax.scatter(X, y, marker='')\n",
    "\n",
    "for i, label in enumerate(labels):\n",
    "    ax.annotate(label, (X.iloc[i], y.iloc[i]))\n",
    "\n",
    "# Fit a linear trend line\n",
    "ax.plot(np.unique(X),\n",
    "         np.poly1d(np.polyfit(X, y, 1))(np.unique(X)),\n",
    "         color='black')\n",
    "\n",
    "ax.set_xlim([1.8,8.4])\n",
    "ax.set_ylim([3.3,10.4])\n",
    "ax.set_xlabel('Log of Settler Mortality')\n",
    "ax.set_ylabel('Average Expropriation Risk 1985-95')\n",
    "ax.set_title('Figure 3: First-stage relationship between settler mortality \\\n",
    "    and expropriation risk')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                          IV-2SLS Estimation Summary                          \n",
      "==============================================================================\n",
      "Dep. Variable:               logpgp95   R-squared:                      0.1870\n",
      "Estimator:                    IV-2SLS   Adj. R-squared:                 0.1739\n",
      "No. Observations:                  64   F-statistic:                    37.568\n",
      "Date:                Wed, Oct 16 2019   P-value (F-stat)                0.0000\n",
      "Time:                        11:23:24   Distribution:                  chi2(1)\n",
      "Cov. Estimator:            unadjusted                                         \n",
      "                                                                              \n",
      "                             Parameter Estimates                              \n",
      "==============================================================================\n",
      "            Parameter  Std. Err.     T-stat    P-value    Lower CI    Upper CI\n",
      "------------------------------------------------------------------------------\n",
      "const          1.9097     1.0106     1.8897     0.0588     -0.0710      3.8903\n",
      "avexpr         0.9443     0.1541     6.1293     0.0000      0.6423      1.2462\n",
      "==============================================================================\n",
      "\n",
      "Endogenous: avexpr\n",
      "Instruments: logem4\n",
      "Unadjusted Covariance (Homoskedastic)\n",
      "Debiased: False\n"
     ]
    }
   ],
   "source": [
    "df4 = pd.read_stata('https://github.com/QuantEcon/QuantEcon.lectures.code/raw/master/ols/maketable4.dta')\n",
    "df4 = df4[df4['baseco'] == 1]\n",
    "df4['const'] = 1\n",
    "\n",
    "iv = IV2SLS(dependent=df4['logpgp95'],\n",
    "            exog=df4['const'],\n",
    "            endog=df4['avexpr'],\n",
    "            instruments=df4['logem4']).fit(cov_type='unadjusted')\n",
    "\n",
    "print(iv.summary)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "----\n",
    "\n",
    "&nbsp;\n",
    "\n",
    "## <font color=\"880000\"> Deep Roots of Relative Development </font>\n",
    "\n",
    "<img src=\"https://tinyurl.com/20190119a-delong\" width=\"300\" style=\"float:right\" />\n",
    "\n",
    "### <font color=\"000088\">Catch Our Breath—Further Notes:</font>\n",
    "\n",
    "<br clear=\"all\" />\n",
    "\n",
    "----\n",
    "\n",
    "* weblog support: <https://github.com/braddelong/LS2019/blob/master/Deep-Roots-of-Relative-Development.ipynb>\n",
    "* nbViewer: <https://nbviewer.jupyter.org/github/braddelong/LS2019/blob/master/Deep-Roots-of-Relative-Development.ipynb>\n",
    "* datahub: <http://datahub.berkeley.edu/user-redirect/interact?account=braddelong&repo=LS2019&branch=master&path=Deep-Roots-of-Relative-Development.ipynb>\n",
    "\n",
    "&nbsp;\n",
    "\n",
    "----"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "pwt91_df = pd.read_csv('https://delong.typepad.com/files/pwt91-data.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>countrycode</th>\n",
       "      <th>country</th>\n",
       "      <th>currency_unit</th>\n",
       "      <th>year</th>\n",
       "      <th>rgdpe</th>\n",
       "      <th>rgdpo</th>\n",
       "      <th>pop</th>\n",
       "      <th>emp</th>\n",
       "      <th>avh</th>\n",
       "      <th>hc</th>\n",
       "      <th>...</th>\n",
       "      <th>csh_x</th>\n",
       "      <th>csh_m</th>\n",
       "      <th>csh_r</th>\n",
       "      <th>pl_c</th>\n",
       "      <th>pl_i</th>\n",
       "      <th>pl_g</th>\n",
       "      <th>pl_x</th>\n",
       "      <th>pl_m</th>\n",
       "      <th>pl_n</th>\n",
       "      <th>pl_k</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ABW</td>\n",
       "      <td>Aruba</td>\n",
       "      <td>Aruban Guilder</td>\n",
       "      <td>1950</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ABW</td>\n",
       "      <td>Aruba</td>\n",
       "      <td>Aruban Guilder</td>\n",
       "      <td>1951</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ABW</td>\n",
       "      <td>Aruba</td>\n",
       "      <td>Aruban Guilder</td>\n",
       "      <td>1952</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ABW</td>\n",
       "      <td>Aruba</td>\n",
       "      <td>Aruban Guilder</td>\n",
       "      <td>1953</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ABW</td>\n",
       "      <td>Aruba</td>\n",
       "      <td>Aruban Guilder</td>\n",
       "      <td>1954</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 52 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  countrycode country   currency_unit  year  rgdpe  rgdpo  pop  emp  avh  hc  \\\n",
       "0         ABW   Aruba  Aruban Guilder  1950    NaN    NaN  NaN  NaN  NaN NaN   \n",
       "1         ABW   Aruba  Aruban Guilder  1951    NaN    NaN  NaN  NaN  NaN NaN   \n",
       "2         ABW   Aruba  Aruban Guilder  1952    NaN    NaN  NaN  NaN  NaN NaN   \n",
       "3         ABW   Aruba  Aruban Guilder  1953    NaN    NaN  NaN  NaN  NaN NaN   \n",
       "4         ABW   Aruba  Aruban Guilder  1954    NaN    NaN  NaN  NaN  NaN NaN   \n",
       "\n",
       "   ...   csh_x  csh_m  csh_r  pl_c  pl_i  pl_g  pl_x  pl_m  pl_n  pl_k  \n",
       "0  ...     NaN    NaN    NaN   NaN   NaN   NaN   NaN   NaN   NaN   NaN  \n",
       "1  ...     NaN    NaN    NaN   NaN   NaN   NaN   NaN   NaN   NaN   NaN  \n",
       "2  ...     NaN    NaN    NaN   NaN   NaN   NaN   NaN   NaN   NaN   NaN  \n",
       "3  ...     NaN    NaN    NaN   NaN   NaN   NaN   NaN   NaN   NaN   NaN  \n",
       "4  ...     NaN    NaN    NaN   NaN   NaN   NaN   NaN   NaN   NaN   NaN  \n",
       "\n",
       "[5 rows x 52 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pwt91_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}