Decision Trees and Random Forests - Kyphosis dataset.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('kyphosis.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Kyphosis</th>\n",
       "      <th>Age</th>\n",
       "      <th>Number</th>\n",
       "      <th>Start</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>absent</td>\n",
       "      <td>71</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>absent</td>\n",
       "      <td>158</td>\n",
       "      <td>3</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>present</td>\n",
       "      <td>128</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>absent</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>absent</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Kyphosis  Age  Number  Start\n",
       "0   absent   71       3      5\n",
       "1   absent  158       3     14\n",
       "2  present  128       4      5\n",
       "3   absent    2       5      1\n",
       "4   absent    1       4     15"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 81 entries, 0 to 80\n",
      "Data columns (total 4 columns):\n",
      "Kyphosis    81 non-null object\n",
      "Age         81 non-null int64\n",
      "Number      81 non-null int64\n",
      "Start       81 non-null int64\n",
      "dtypes: int64(3), object(1)\n",
      "memory usage: 2.6+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.PairGrid at 0x7f052aafbf98>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmEAAAIUCAYAAABSGvs5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAIABJREFUeJzs3XuYHGWZN/7vXX2Y9BxghqFnhCRDWF8IZtksmpEVcFdcRFEOMXIwwZCIbMJBF3VRQXd98fd6WFiWFQ9LgLBIYiAhghgUDyAL4gYFJqwihkRUQhLEzDDMQObA9HTX/fujujs9M9XVPVVdXdU93891zdXT1XV4qvqpp+6ueg6iqiAiIiKi6jKCTgARERHRTMQgjIiIiCgADMKIiIiIAsAgjIiIiCgADMKIiIiIAsAgjIiIiCgADMKIiIiIAsAgjIiIiCgADMKIiIiIAlDTQdhpp52mAPjHv1J/gWNe5V+Zf4FjXuVfmX9UATUdhL388stBJ4GoLMyrVCuYV4mqp6aDMCIiIqJaxSCMiIiIKAAMwoiIiIgCwCCMiIiIKAAMwoiIiIgCEA06AUQUDNNU9A+nkEpnEI9G0N4Uh2FI0MkiCi2eM1RpDMKIZiDTVOzctx+r1vdg78Ao5rQlsHZFN+Z3tvCiQmSD5wz5gY8jiWag/uFU/mICAHsHRrFqfQ/6h1MBp4wonHjOkB98C8JEZK6IPCwiz4rIb0Xk49nph4jIgyLyXPa1LTtdROTrIvJ7EXlaRN7iV9qIZrpUOpO/mOTsHRhFKp0JKEVE4cZzhvzg552wNIArVPVNAN4G4KMisgDAVQAeUtWjADyUfQ8A7wVwVPZvNYA1PqaNaEaLRyOY05aYMG1OWwLxaCSgFBGFG88Z8oNvQZiqvqSqT2X/3w/gWQCzASwGsC472zoA78/+vxjAerX8EkCriBzmV/qIZrL2pjjWrujOX1Ry9Vvam+IBp4wonHjOkB+qUjFfROYBeDOAxwF0qupLgBWoiUhHdrbZAPYULLY3O+2laqSRaCYxDMH8zhbce9lJbOlFVAaeM+QH34MwEWkGcA+AT6jqayJFM6zdB1NGaheR1bAeV6Krq6tSySSquOnk1SCavhuGINnS4Os2qDawXC1PPZwz7GYjXHxtHSkiMVgB2B2q+t3s5H25x4zZ197s9L0A5hYsPgfAnyavU1VvUdVuVe1OJpP+JZ7Io3Lzaq7p+5Ibt+Kkax/Gkhu3Yue+/TDNKb9BiHzBcnVmYFkTPn62jhQA/wXgWVX9j4KP7gOwMvv/SgBbCqavyLaSfBuAV3OPLYnqGZu+E1E1sKwJHz8fR54E4AIAvxGRX2WnfQ7ANQA2i8hFAHYDODf72Q8BvA/A7wGMALjQx7QRhQabvhNRNbCsCR/fgjBV/R/Y1/MCgFNs5lcAH/UrPURhlWv6Xlg4suk7EVUay5rwYY/5RAFj03ciqgaWNeHDsSOJAsam70RUDSxrwodBGFEI1EPTdyIKP5Y14cLHkUREREQBYBBGREREFAA+jiSaodhzNlHt4vlbHxiEEYVAtQvUXM/ZuY4bc62k5ne2sCAnColi5QLP3/rBx5FEAQtiKBGvPWebpqJv/xheHBhB3/4xDntC5FKxc8mpXGDP9/WDQRhRwIIoUL30nM3x54gqw22gxZ7v6weDMKKABVGg5nrOLlRuz9n8FU5UGW4DLS/nL4ULgzCigAVRoHrpOZu/wokqw22gxZ7v6wcr5hMFLFegTq5k62eB6qXnbI4/R1QZTueSU7nAnu/rh1jjZtem7u5u7enpCToZFH6Bl0yl8qrb1pFBNFNnyyxfBX4AWa5WT6lzKYhW09PYXuB5tR7wThhRCLgZSiSoYIi/wokqo9S5VM0hhvjjKhisE0ZUo4KsIJ+7OMxua0SypYGFNJFLYTmX2OAmGAzCiGoUK8gTUaWwPAkGgzCiGsVm6kRUKSxPgsEgjKhGeW2mzl7viYIXlvOQ3V4EgxXziWqUYQiOSjZj88UnIJ0xEY0Y6Ggur06J10q4HDyYyLtS52E6baJ3aAzjGROx7Pkdjfpz74QNboLBIIyoRpmmYs/AMIZe+TNa4yb6UwbGxt+AI9qbSxacxSrh3nvZSSVbY7EVFVFl9A+ncMODO/C1Mw5HR6Ogd0Rxw4M78KUlf422RAw79u3HJRu25c+zm5YvwjGdLb4GYtVqjUkWPo4kqlGvjo6hbeg5/NWPPoC5647HX/3oA2gbeg6vjo6VXNZLJVy2oiKqDDUz+MpJUSx68FzMXXc8Fj14Lr5yUhRqZtA7NJYPwADrPLtkwzb0DpU+v6l2MAgjqlGN4wNo3bISGNxtTRjcjdYtK9E4PlByWS+VcNmKiqgy2vAa2r8/8Rxu//5KtOE1jGdM2/MsnTEDSCn5xbcgTERuE5FeEXmmYNoXRORFEflV9u99BZ99VkR+LyI7ReQ9fqWLKIzcVM6N6viBwjtncLc1vQQvlXDZioqoMpzO4VjEsD3PopHSl+2wVPan0vysE3Y7gG8CWD9p+ldV9d8LJ4jIAgBLAfwlgMMB/FREjlbVivy0nnfV/WXPu+ua0yuxSaKyua1jZUQbgNauiYV4a5c1vQQvlXCDGOuSqB5JNG57Dks0jo5ZDbhp+aIpdcI6mllns574FoSp6qMiMq/M2RcD2KSqYwCeF5HfAzgewC98Sh5RaLitJC9NSejSjZBNy6xCvLXLet+ULGu7bivhshUVUYU0JoGlG4GCcxhLNwKNSUQNA8d0tkxp/VyqUr6XRjdUfUG0jvyYiKwA0APgClUdADAbwC8L5tmbnUZU99zWsTIheCFyBIbe+120xk0Mpgw0R96AIyC+V/ZkKyqiCjAMoGMB8A8/BdIpIBq3AjPDOoOjUQOHtyZKrGQi1tmsLdUOwtYA+CIAzb5eD+AjsB+N3fYhtoisBrAaALq6uvxJJVEFlJtXc3WsCgvOcupY9Q+ncMFtT05abg9/8dK0sVwNkGEAzZ0VW52I2JYnIrxTHUZVbR2pqvtUNaOqJoC1sB45Atadr7kFs84B8Kci67hFVbtVtTuZLO+xC1EQys2rbivJ8xdv9dR7RedqlKv1fgzDIiLAtWcvnFCeXHv2QkQYg4VSVe+EichhqvpS9u0SALmWk/cBuFNE/gNWxfyjADxRzbQRBcVtHSu3d9BoeljR2Tsew+oxDAPrHnsenz9jAVoTMQyOjmPdY8/jy0sWBp00suFbECYiGwGcDOBQEdkL4GoAJ4vIcbAeNe4CcDEAqOpvRWQzgO0A0gA+WqmWkUS1wE0dK6+tFL0MPTSThi1iRWfvZsIxrPY5UWx77U1xfPLU+Wy9XCP8bB25zGbyfznM/2UAX/YrPUT1xjAE8zua8PAlCyCZMWikAZHmJt/HjpxpdzU8PfY1TWCkz7bS9Uzi26Pzah/fItur9jlRantsvVw7Zl5pQFQvTBNG37OIfetURL++ELFvnQqj71nrQlGCl6GHZtqwRa47pzVNoHc7cOu7gBuOtV57t5f1/dQbXzr4rfbxddhetc+JUtvL3Vmf3daIZEsDA7AQYxBGVKtG+g70LwRYr5uWWdNL8HJnYqY1CHA9uoCH76feeBmhoahqH1+H7VX7nJhp52A9C6KfMCKqhHTKdsgTpEv/+o5FDdtK/bESHUECM69BgOvHOx6+n3rjyyOyah9fh+1V+5zwcv5SuPAbI6pVuSFPCrV2WdNLLWoIrjtnYjP2685ZiOg0hi2q6F2NkHP1eMfD91OPKv6IrNrH12F71T4nvJy/FC68E0YUAq5aVjkMeVLKaCqDLU/txfcvPBoJI41RM4prf7YX//iuo4Em52UNQ/B/Dm3CXavfhrSpiBqCjmbWO5nCw/cTai4rw1e89WC1j6/D9rzc6UunTfQOjWE8YyJW5tBEo6kM/u3HOyd0Q/FvP96Jb57/5pLnL4ULgzCigLluWVViyBMnjXEDV3WbaL3zvcDgbsxq7cJVi9dB46WXTadN7OwdmjKw8DGdLSUvHjOKh+8ntHKV0ycHIh0LHPfLl9aD1T6+JbbnppuZdNrEjn37p30uxaMR9A2N4eJvb8tPq+cqAfWshksDovrgqWVVbsiT1rnWa5kXoFbzVbRuWTmhknHrlpVoNV8tuWzv0Fj+opFL7yUbtqF3aKysbc8oLr+f0HJZGd5THjdNYGgfMLjHei1s/Vjt4+tye8VGC3B7Ls3EKgH1infCiAIWSEunzJh9JeNM6YvieMa0TW86M/O6XphxXFaGd53HXd55CxOnu4BuzyX2BVY/aiMXE9WxeDSCdy/owM0XLMJdq9+Gmy9YhHcv6PD10YLCsK1krChdiMcihm2fT9EIi5O657IyvOt+wmqom49id7uc7gJ6OZfYF1h9YKlJFLC2RAyXn3I0vviD7fjgLb/EF3+wHZefcjTaEjHftmmKAZz1zQMX1NYu4KxvwpTSgV9HcwNuWr5owqOQm5YvQkdzfQw/Qw5yldML800ZleFdPz6rkW4+cne7lty4FSdd+zCW3LgVO/fth2mq411AnkvEx5FEARsYHbetF1LWuHouW6opDODxm4H3fAVItAGjA8DjN0Pf9x8ll41GDRzT2YLNF5+AdMZEtMwWXVQHXFaGdz3EVu7OW2EgFsJuPpzGxnTqQ4znEjEIIwpYKp1BsrlhQnPzmx75g6/1ZSLNSaTf8VlEN5+fXzZ93p2INJfXvD9qAIdHXwOQvRAbNd7tApUvVzl9OrJDbBnTzat+dUNR4TEnne52HXawddev2IDahiGIRQyoKmIRg48VZxgGYUQBS8Qj+Mxp8/Hpu5/OF9LXnbMQibjL+jL/8NOSF0kjEoHZ8SakPvwADHMcphGD0ZyEESmjHlodVJamKnObV/3ohsKH/Ot0t8upEr1fA3+76XuMgsFvhShgaVPzARhg/YL+9N1PI52t2FuMFqkvo2XUlzFNxXN9I/j7m5/F//m33+Dvb34Wz/WN5CsTO6qhytIUEl7qdlW6Gwof8m+pOm/FKtH7MfB3ru+x827+Bd5x3SM47+ZfYMe+/Uin2Xo5jHgnjChg42n7ZurjJQrNtMQQs6kvk5YYSlXpd6rDUrIeWpCVpSv8GImqJEx1u9IpoLljYn3IrTd4yr9uu4zwo3uaYn2Pbb74BBzemiixNFUbSy+igLltvj+Ag9B/5roJLdX6z1yHARxUcpueCv+gxkTMPUa69V3ADcdar73bJ3beSeHkslWlL2IJ4JQvAD/5HHD76dbrKV+wpnvgpssI1113OGA/frWFQRhRwNoSMdtm6qW6qBAjgs9tTWPbqd/BnpVPYNup38HntqYhRukC3FPhH9QFlY9Ba1dh3a5PPGO9BlWH0MwAWy6bmI+2XGZNrzI/er5nP361peTjSBHpBPAVAIer6ntFZAGAE1T1v3xPHdEMMDA6jq8/9LsJrSO//tDv8OUlCx0fDbYlYvjHU+ZPGXeunP7FcoV/sRZbjoIaE7FG+oyiIty0qvRDpkg+KmO0iErzo+f7pgYDa5YvwqUF5cKa5YvQ1MAgLIzKqRN2O4BvAfjn7PvfAbgLAIMwogpIpTN4YHsvHtjeO2H61Wc6/zJ3G7wBFSj8g7ighqleEdWukOUjNwN/Oxl6PYMf/GovvvXhtyJiCDKm4u6e3Vhx4pE4mFXCQqecIOxQVd0sIp8FAFVNi0j179sS1Smn5u1O3AZvOZUu/H3nV59RNLPUeT7KqOLmn+/CzT/fNWH6h044MpgEkaNygrBhEWkHoAAgIm8D8KqvqSKaQdw+GnQbvAXObQvHoB6DUrAq3SK2zvPRrJh9uTArVh/7V2/KCcL+CcB9AN4oIlsBJAGc42uqiGYQt48GPdXrCorXjjLDUq+IqsOvjoHrOB8d2tRgWy4c2lRDd71nkJJBmKo+JSLvADAfgADYqarjvqeMaAZx82jQMARHJZux+eITJvSMHephTzz08k8z0AzIL6ap6B9OVaxivh+V/ck/5bSO/MCkSUeLyKsAfqOqvXbLZJe7DcAZAHpV9djstENgVeqfB2AXgPNUdUBEBMDXALwPwAiAD6vqU9PfHaKZw+r1fqjiQ574ii0caTrqPL+UGrbIbYBWc/U9Z7By7udeBOBWAB/K/q2F9Yhyq4hc4LDc7QBOmzTtKgAPqepRAB7KvgeA9wI4Kvu3GsCaMtNPNGO9PDxm2+v9y8NjAafMQVAdvVJtqvP84jRsUS5AW3LjVpx07cNYcuNW7Ny3v7yhxahmlBOEmQDepKpnq+rZABYAGAPwNwCuLLaQqj4K4JVJkxcDWJf9fx2A9xdMX6+WXwJoFZHDyt8Nopnn9XH7Xu9fHw9xz9hh6jmdwq/O84vTyBVexpU0TUXf/jG8ODCCvv1jDNxCrJyK+fNUdV/B+14AR6vqKyIy3bphnar6EgCo6ksi0pGdPhvAnoL59manvTR5BSKyGtbdMnR1dU3+mCg0/M6rURG8Z0ESqxcdhI5GQe+I4pZtryEa0ieRAOq+ZVqtCm25Wi/5pUgLT6cWzm6HFiv1iJPCpZyc/HMR+YGIrBSRlQC2AHhURJoADFYoHXY5wzZ0V9VbVLVbVbuTyfr4NUT1ye+8Oitm4JunzMKiB8/F3HXHY9GD5+Kbp8wKf1P0XMu01rnWa61dUOtQqMvVWs8vDmOeOg1b5HZoMS930Kj6ysnNH4XVY/5x2b8nAKiqDqvqO6e5vX25x4zZ11zF/r0A5hbMNwfAn6a5bqIZpSk9gNh3PjSh5VjsOx9CU3og2IQR0QEOY54WtmTceuU7ce9lJ+XvWLkdV9LtHTQKRjldVKiI/AFWHbDzADwP4B6X27sPwEoA12RftxRM/5iIbMpu59XcY0sishfVcduWY9Fq9CBT6Q40iepVOgU0dwDv+QqQaANGB4CtN+RbeBZryei2q4lY1LB9xBmL8vwMo6JBmIgcDWApgGUA+mF1LSHl3v0SkY0ATgZwqIjsBXA1rOBrs4hcBGA3gHOzs/8QVvcUv4fVRcWFbnaGaCYxjTgiNmPgmUYcvvaZ71cHmkT1KJYATvkCsOWyA+fL4hut6SW46WoiagiuO2chPn330/k6YdedsxBR1gcLJac7YTsA/BzAmar6ewAQkU+Wu2JVXVbko1Ns5lVYjz2JqEwDOAgN71+Pg7+3Il+4v/r+9RjDQegovbj7TiJnQAeaRBVjZg4EYID1uuUy4KKf+rK50VQG9z714oQBvNc++kd8/F1HAU2+bJI8cArCzoZ1J+xhEfkxgE2wr0BPRAEQI4LPPDqO1ad+50DryEdfw5eWlL4P5qkFVZ13oElUUZki50vGn/MlEY9gyVtm48Lbn5xwJywRD/mYsjNU0WcHqnqvqn4QwDEAHgHwSQCdIrJGRN5dpfQRURHtTXF84tRj8PEf/Al/e/Pv8fEf/AmfOPWYssaO9NSCqs470CSqqCqfL2lT848iAevc/vTdTyPNvsJCqZyK+cMA7gBwR3bYoXNh9XT/gM9pIyIHXsaI89SCKteB5uQ6YXXSgSZRRXk5X1w0gBlPm7bn9ng6xJ04z2DldNaap6qvALg5+0dEAXM7RpxTJ5Flic4CTr8eiDUC4yPWe5oRKj3gdN1z2+GsywYwns9tqio2ZSKagdoSMdy0fNGEPohuWr4IbYlY6YVH+oANS4A7zgVuP9163bDEmk51jeMZuuSmw1mH/sWcuO1fjIIxrTthRFQfBkbH8fWHfofPn7EArYkYBrPvv7xkYck7a5pOQWwqGms6VVbLHd5JqV3F6hLee9lJru7IkoMSDWCczqOGqIEvLj4WjfEIRlIZNLCPsNBiEEY0A6XSGTywvRcPbO+dMP3qM0vXCUtLDDGb/snSEkOp+2gc1662sTf2KspV6J90niEadzyP+odTWHHbE1MeRzJQDieGx0QzkNtx6QCrf7L+M9cdaPHV2oX+M9dhAAeVXJbj2tU2L/mGpilXob/gPMtV6Hc6jxgo1xbeCSOagXL1Rib/ki6n3ogYEdy6I46Pnv99zDJMvG4auPXJIXzk70pfiHmBqG3tTXF8+yNvxdArf0Zr3MRgykDzIW9gfSM/OFTodzqPWDG/tjAII6phbutXeeneor0xik+9WRG580xgcDeaW7vwqfPuhDSWLk54gahtBhTzMi9AfmRVGJ/b2gVduhGCBfCrL+8ZXYcwV6F/kng0gncv6MDZi+bm63Tes21P/vi4/YFF1ccgjKhGea1f5bZ7Cxl5Gcbm8ye02opsPh960U+BFudhi3iBqHEjfZBJLfbExyGrWIfQXlsihstPORqXbNiWPy651s1efmBR9bFOGFGNCqp+lZkes221ZabHSi5beIHYeuU7ce9lJ834C2pNqfKQVWGrQ2iair79Y3hxYAR9+8cC65pjYHQ8H4AB1nG5ZMM2DIyOAzjwA2t2WyOSLQ08v0KMd8KIalRQ9avSEkOkSOvIch4qur0DRyHg0GLPD2GqQximu3JhOi7kDYOwGW7eVfdPa/5d15zuU0pouoKqX/Wa0YrY4nVo3bIy35P34OJ1GDdawYGL6lyVh6wKUx3CMPWRFqbjQt7wcSRRjQqqZ2xTgRei8/Cb934Xe1Y+gd+897t4IToP7DR9BihssfeJZ6zXEsPoeBGm3t/DdPcpTMeFvOGdMKIaFVQFXMMw8J8P/wFnL5qLkVgMg+lx3PPwH/DlJQt93S6FRJEWe/5sKjyVzMN09ylMx4W8YRBGFAJeuppw+yjE7Tbbm+L45Knz2cJxhqp2lxFhqUMYtpa9bo/LjO7yI4QYhBEFLIgKv1626flXuGlagxBP6oCSwi9MldOrzVO+D0men8nfX1ix5CMKWBDN8L1u03UTeNMEercDt74LuOFY67V3uzWdQi9sXUZUm6t8H6I8P9O/vzBiEEYUsCAq/AZWyXik70DLOsB63bTMmk6hF6bK6TUjRHme31/4MAgjClgQgyIHNhBzlTv7pMriAN4uhCjP8/sLHwZhRAELorm5522aJjC0DxjcY72W+2gl19lnIR87+6TKCl3XCG7zYTWFKM+H7vujYCrmi8guAPsBZACkVbVbRA4BcBeAeQB2AThPVQeCSB9RNQXR3NxzJePe7VM77CynvyiPnX2yZVewQtU1gpd86LjaCuexKndw6yRU3x8BCLZ15DtV9eWC91cBeEhVrxGRq7LvrwwmaUTVFUQzfNfbLFbHpZxBnAs7+5xmSzG27AqHsHQZ4SkfFuFLHvOQ5/0Qmu+PAITrceRiAOuy/68D8P4A00JExXit45Lr7LN1rvVa5sWILbtoAh/qWvmWx1zmeap/Qd0JUwAPiIgCuFlVbwHQqaovAYCqviQiHXYLishqAKsBoKury24WTziWIlWK33k1MFUexDmHLbv8U5N51Yd8yDxG1RZUOH6Sqr4FwHsBfFRE/q7cBVX1FlXtVtXuZJLDBVN41W1ezdVxyVU2rlIdF7bs8k9N5lUf8iHzGFVbIHfCVPVP2ddeEbkXwPEA9onIYdm7YIcB6A0ibURUQkB1XNqb4vj2R96KoVf+jNa4icGUgeZD3sCWXTOVYQDJY4ALfwRkxoFIDGh+g6d8GLahiaj+VT0IE5EmAIaq7s/+/24A/w/AfQBWArgm+7ql2mkjojJVcRDn/CahmJd5AfIjqzL23NYu6NKNECwAwIr5M45pAn07Kto6kq0HqdqCeBzZCeB/ROTXAJ4AcL+q/hhW8HWqiDwH4NTseyIiy0gfZFJrOGFv+zOXTz3Rux6Si8iFqt8JU9U/Avhrm+n9AE6pdnqIqEaEqOdxCgHmB6oDQfYTNiOx9SVVkpeOJWuu49OAWmVSSNVJfvDjPKy5c3sGYxBGVKNMU7Grfxgv9I+gMR7BSCqDI9obMa+9qWSBW5Mdn4ao53EKgTrID36chzV5bs9gDMKIatTgaAr7Xnsdn9/yTL6wve6chWhtjOGQJucesYt1SnnvZSeFtzftkPU8TgGrg/zw8vCY7Xn43ctOREfLLFfrrMlzewZjEEZUo0ZTGXz67qcnFLafvvtp3LX6bUCT87I12yllAK0yKcRqPD+8Pm5/Hr4+7n4g8lQ6g2RzAz5/xgK0JmIYHB3HTY/8Ifzn9gzFIIyoRpmqtgW4qaWXzXVKWbg8O6Ukqq6IiO15GPHw1DARj+Azp83P/0DL3SFPxHluhxGDsJCbbkV+v7FhQXhEDMO+AC+j3gc7pSQKXiIewXXnLKxowJQ21fYO+XcvO7FSyaYKYhBGVKMiAlx79kJcec+BAvzasxeW9SvaMARHJZux+eITkM6YiEYMdDSHv08ktvoiv1Uzj7Um4pjTlsDtFx4PQwBTgYaooDXh/sfQeNq0vUM+nnb/iJP8wyCMqEYZhoF1jz0/oe7Huseex5eXLCy5rGkqnusbqqkWVGz1RX4LIo8NjWWmbM8LVjWoLbXTjISIJmhviuOTp87HF3+wHR+85Zf44g+245Onzi/rkWKxFlT9w+Ht6LIW00y1pdp5zI/t5aoa5AYiZ1WDcOOdMKIQcPMIxMs4d7XYOrIW00y1pdp5zI/t1WpVg5mKQRhRwLw8AsmNczddQT6ycFvnho9ZyG/xaATvXtCBsxfNzT/iv2fbHt/ymB95uharGsxkDMLIV2xNWVoQnSu2N8Wx/iPHT+ltv9xHFm4DKS8BJ1t0hl+tN5xoS8Rw+SlH45IN2/J57Kbli9CWiJVc1s2++5Gn2VlrbWEQRhSwoB6zjY2bE3rbX3tBeRWCvQRSXi4QXh6/kv/qoeHEwOh4PgADrPx5yYZt+fxZLNByu+9+5Gk+tq8tDMKIAhbEY7aXh8ew6tuTgqFvlzdcSv9wCl99cOeEVplffXAnvrxkYclAyusFwoAiKYOApACJA0gCqI0LfL3rH07hhgd34GtnHI6ORkHviOKGB3fgS0v+umbuwDjlT6dAy+uPi0oen2o/UiVvGIQRBSyIx2xehksxTRMrTzxySv9kpll6WU8Bp2kCvdunDtjcsaCmxgusV2pm8JWTomj//rnA4G7Mbe3CV85ch4xZO3dgnPKnU6AVprtPXh6pUvWx5CIKWOEjia1XvhP3XnaS749wcsOlFCp3uJSMIh+AAdbF5sp7nkamjOGSPDWfH+k7EIAB1uumZdZ0ClwbXkP791fZxVryAAAgAElEQVRO+H7av78SbXgt2IRNg1P+dAq0csFboaAajRR7pDowOl71tFBpvBNGFAJuH0m4rQjtZbgULTJmpWrpKMxTHZh06sAFPmdwtzWdAhfVcdvvJ6q1c/F3yp9Od8mCuJtd7NwP0105Ko1BmEdhG9uxmF2zzve8jnmv31mBlJAdN8GUl4rQrYk4Og+ahS8uPjbfOrLzoFllDZfitQ6b6zow0bj1CLLwQt/aZU2nwEmR70dq7Psplj+dAi0vPy4qfe6XOj9rvQVrveHjSKKA5QrUJTduxUnXPowlN27Fzn37YZrOd5a89LZtGIJ57U04dvbBmNOWwLGzD8a89qayCuO2RAw3LV804ZFNVeqcNCatOmCtXdb7XJ2wxqS/26XyBPD9mKaib/8YXhwYQd/+sZLnjBelqg3kgrfZbY1ItpTXOaof577TI1W32yP/8E4YUcDctqzy3NLQ5R2pgdFxfP2h301oHfn1h35XVutITwzDqoT/Dz+1HkFG49YFnpXyw6HK308QXWJUuiWjH+e+0125vv1j7EMsZBiEEQXMbTAl2cr1kx87iPj7aCGVzuCB7b14YHvvhOlXn1mFOieGATR3+r8dcqeK3089dErq9tx3WyWA9cXCh0EYUcDc9usTjwjWfOgtuPSOp/J3AtZ86C2Il9PE0WN6OXzQzBWWOkX1EFC4Pfed6qeVqi/GPsTCJXRBmIicBuBrACIAblXVawJOEpGv3PbrYypgCCZUrjfEml6OdNpE79AYxjMmYtlBfqPR0o+OcnXC2A/RzBOmXvH9+jHgR5BZbJ1uz32nQbqdHjmyD7HwCVUQJiIRAP8J4FQAewE8KSL3qer2YFPmv0q0XqwH02ltWi/jTL4ymrLt16dU7/XpjImLNzw15SK0efXbSm4znTaxY9/+KYXxMZ0tJQOxwOqEUeDC9AjQj24h/AgyndZZapgkp3UWG6R7zOEO4cAoXG2P/BOqIAzA8QB+r6p/BAAR2QRgMYC6D8Jo5nLbe/24ad9fV7qMW2G9Q2O2hfHmi0/A4a0Jx2UDrRNGgQrTI0A/xl30I8j0o6d9p3UKYHuHEAjX90eWsDUrmg1gT8H7vdlpRHXLbe/1EcN+uXIuQuMZ0z6Ay5Q/9NDk7bJeSf0L23fvplsIJ34EKX70tO+0ThHg2rMXTuii4tqzF8KQ8H1/FL4gzO4MmvCzXkRWi0iPiPT09XG4EgqvcvNqrvf6wkKznN7r4xHDdrl4pPRpHYsYtoVxtIxlPQ09RKFUbl6t9+/ejyDFaZ1uj6dzOgXrHnsenz9jAe5a/TZ8/owFWPfY81BI3X9/tUjKGWqkWkTkBABfUNX3ZN9/FgBU9V/t5u/u7taenp6S662FXu1roU5Y2HrMn0adsMC7g3bKq6ap2NU/jBf6R/IV7I9obyzZeWo6bWLXK8PY88pofrm5hyQw75CmkvW6vNQJy6U5DC3k6lDgB7FUuVrP332164QZhlS8x3zTVMdzu4LfX3186QELWxAWBfA7AKcAeBHAkwDOV9Xf2s3PIKy6GIS559eFLdfCsbCFVDlBlNdlyTehz6v1rpqtI/1aZ5XO7cDzaj0IVcV8VU2LyMcA/ARWFxW3FQvAKqkWAqAwKHWcwhak1RK3PXFHo0bJivR+LEtUryrdK34Q6+S5XTtCFYQBgKr+EMAPg04HERERkZ/47IGIiIgoAAzCiIiIiALAIIyIiIgoAAzCiIiIiAIQqi4qpktE+gC8UGK2QwG8XIXkBI37WdzLqnqaH4kpV5l5tZQwfsdMU3nKTVPY8mqYjiXTYi+otASeV+tBTQdh5RCRHlXtDjodfuN+1r8w7jvTVJ4wpqkcYUo302IvTGmh6ePjSCIiIqIAMAgjIiIiCsBMCMJuCToBVcL9rH9h3HemqTxhTFM5wpRupsVemNJC01T3dcKIiIiIwmgm3AkjIiIiCh0GYUREREQBYBBGREREFAAGYUREREQBYBBGREREFAAGYUREREQBYBBGREREFAAGYUREREQBYBBGREREFAAGYUREREQBYBBGREREFAAGYUREREQBYBBGREREFAAGYUREREQBqOkg7LTTTlMA/ONfqb/AMa/yr8y/wDGv8q/MP6qAmg7CXn755aCTQFQW5lWqFcyrRNVT00EYERERUa1iEEZEREQUAAZhRERERAFgEEZEREQUgECCMBG5TUR6ReSZgmmHiMiDIvJc9rUtiLQRERERVUNQd8JuB3DapGlXAXhIVY8C8FD2PQXJNIGhfcDgHuvVNINOERHRASyjqMZFg9ioqj4qIvMmTV4M4OTs/+sAPALgyqoliiYyTaB3O7BpGTC4G2jtApZuBDoWAAafYhNRwFhGUR0IU07tVNWXACD72hFwema2kb4DhRtgvW5aZk0nIgoayyiqA2EKwsoiIqtFpEdEevr6eLL5Jp06ULjlDO62plNZmFepVtRkXmUZRXUgTEHYPhE5DACyr712M6nqLararardyWSyqgmcUaJx6/Z+odYuazqVhXmVakVN5lWWUVQHwhSE3QdgZfb/lQC2BJgWakxa9StyhVyuvkVjjRTQRFTfWEZRHQikYr6IbIRVCf9QEdkL4GoA1wDYLCIXAdgN4Nwg0kZZhmFVcP2Hn1q396Nxq3BjhVciCgOWUVQHgmoduazIR6dUNSHkzDCA5s6gU0FEZI9lFNU4/mQgIiIiCgCDMCIiIqIAMAgjIiIiCgCDMCIiIqIAMAgjIiIiCgCDMCIiIqIAMAgjIiIiCgCDMCIiIqIABNJZK9UW01T0D6eQSmcQj0bQ3hSHYUjQySKiGsJyhGgqBmHkyDQVO/ftx6r1Pdg7MIo5bQmsXdGN+Z0tLECJqCwsR4js8XEkOeofTuULTgDYOzCKVet70D+cCjhlRFQrWI4Q2WMQRo5S6Uy+4MzZOzCKVDoTUIqIqNawHCGyxyCMHMWjEcxpS0yYNqctgXg0ElCKiKjWsBwhsscgjBy1N8WxdkV3vgDN1eVob4oHnDIiqhUsR4jssWI+OTIMwfzOFtx72Uls1URErrAcIbLHIIxKMgxBsqUh6GQQUQ1jOUI0FR9HEhEREQWAQRgRERFRABiEEREREQWAQRgRERFRABiEEREREQWAQRgRERFRANhFBVENmnfV/WXNt+ua031OCRERuRW6O2Ei8kkR+a2IPCMiG0VkVtBpIiIiIqq0UAVhIjIbwOUAulX1WAARAEuDTRURERFR5YUqCMuKAkiISBRAI4A/BZweIiIioooLVRCmqi8C+HcAuwG8BOBVVX0g2FQRERERVV6ogjARaQOwGMCRAA4H0CQiyyfNs1pEekSkp6+vL4hkEpWFeZVqBfMqUTBCFYQBeBeA51W1T1XHAXwXwImFM6jqLararardyWQykEQSlYN5lWoF8ypRMMIWhO0G8DYRaRQRAXAKgGcDThMRERFRxYUqCFPVxwHcDeApAL+Blb5bAk0UERERkQ9C11mrql4N4Oqg00FERETkp1DdCSMiIiKaKRiEEREREQWAQRgRERFRABiEEREREQWAQRgRERFRABiEEREREQWAQRgRERFRAELXTxgRVc68q+4ve95d15zuY0qIiGiymR2EmSYw0gekU0A0DjQmAcOAaSr6h1NIpTOIRyNob4rDMKRyy1ZTkXQSEVVctcsbt9tzWK7aZXjorhlUVZ6CMBExADytqsdWKD3VY5pA73Zg0zJgcDfQ2gUs3Qgz+Sbs7B3GqvU92DswijltCaxd0Y35nS0HTgwvy4ZgH9GxgIEYEVVWtcsbt9tzWM6EYOe+/VUrw01Tq7o9Ch9PZ4aqmgB+LSJdFUpP9Yz0HTgJAet10zJkhvryJwQA7B0Yxar1PegfTlVm2Woqkk6M9AWTHiKqX9Uub9xuz2G5/uFUVcvwam+PwqcSjyMPA/BbEXkCwHBuoqqeVYF1+yedOnAS5gzuhmRS+RMiZ+/AKFLpTGWWraYi6USaJzgRVVi1yxu323NYLqWZqpbhqXR1t0fhU4kg7P+rwDqqLxq3bkMXnoytXdBIHHPaEhNOjDltCcSjkcosW01F0oloPJj0EFH9qnZ543Z7DsvFNVLVMjwere72KHw8P6hX1Z8B2AUglv3/SQBPeV2v7xqTVj2A1uyT1Gy9gEhzEmtXdGNOWwIA8s/o25vilVm2moqkE43JYNJDRPWr2uWN2+05LNfeFK9qGV7t7VH4iKp6W4HIKgCrARyiqm8UkaMA3KSqp1QigU66u7u1p6fH/QrYOnKmCLyGq+e8Osl0up4oF7uoCIXazqtsHeliF0J2zShfTSQy7CrxOPKjAI4H8DgAqOpzItJRgfX6zzCA5k6byYJkS4N/y1ZTkXQSEVVctcsbt9tzWK7aZXjorhlUVZX4iTKmqvmakCISBeDt9hoRERFRnatEEPYzEfkcgISInArgOwC+X4H1EhEREdWtSgRhVwHoA/AbABcD+CGAf6nAeomIiIjqluc6Yapqisg6WHXCFMBO9Vrbn4iIiKjOeQ7CROR0ADcB+AOs1hJHisjFqvojr+smIiIiqleVeBx5PYB3qurJqvoOAO8E8NUKrJeIiIjqnIgMFfz/PhF5zs1wiCLyBRH5VAXSc6uILPC6nnJUoouKXlX9fcH7PwLorcB6iYiIaIYQkVMAfAPAu1V1d6n5/aKq/1Ctbbm+EyYiHxCRD8AaN/KHIvJhEVkJq2Xkkx7W2yoid4vIDhF5VkROcLsuIiIiCj8R+VsAawGcrqp/EJEWEXleRGLZzw8SkV0iEhORR0TkBhF5TESeEZHjC1a1IPv5H0Xk8oL1/1N23mdE5BPZaU0icr+I/Do7/YPZ6Y+ISLeIRETk9uxnvxGRT1Z6v73cCTuz4P99AN6R/b8PQJuH9X4NwI9V9RwRiQNo9LCusvnWa/E0enT2nAb2jk9E9abK5Zov1wIf9qGGe9q30wBgC4CTVXUHAKjqfhF5BMDpAL4HYCmAe1R1XEQAoElVTxSRvwNwG4Bjs+s6Bla1qBYAO0VkDYCFAC4E8Dew6q4/LiI/A/AXAP6kqqcDgIgcPCldxwGYrarHZj9vrfSOuw7CVPXCSiYEsCJdAH8H4MPZbaQApJyWqQTTVOzctx+r1vdg78Bofvyu+Z0t3jK1aQK924FNy6zBYnNjlHUsmHICek7DNLZFRFQTqlyu+XIt8GEffLtmBWccwGMALgLw8YLptwL4DKwg7EIAqwo+2wgAqvpo9i5ZLkC6X1XHAIyJSC+ATgBvB3Cvqg4DgIh8F8DfAvgxgH8XkWsB/EBVfz4pXX8E8Bci8g0A9wN4oFI7nOM5F4vIkSLyHyLyXRG5L/fncnV/AetO2rdE5H+zleOavKaxlP7hVD4zA8DegVGsWt+D/mGP8d9I34ETD7BeNy2zplc6DdPYFhFRTahyuebLtcCHffDtmhUcE8B5AN6a7fwdAKCqWwHME5F3AIio6jMFy0zuCiv3fqxgWgbWzSbbyFRVfwdgEax+Tv9VRP7vpM8HAPw1gEdgDdF46/R2q7RK/JT4HoBdsCrTXV/w50YUwFsArFHVNwMYhtUZbJ6IrBaRHhHp6eurzImYSmfymTln78AoUumMtxWnUwdOvJzB3db0SqdhGtui6vAjrxL5IbR5tcrlmi/XAh/2wbdrVoBUdQTAGQA+JCIXFXy0HtZdr29NWiRXf+vtAF5V1VcdVv8ogPeLSGP2xs4SAD8XkcMBjKjqBgD/Div+yBORQwEYqnoPgM9P/rwSKhGEva6qX1fVh1X1Z7k/l+vaC2Cvqj6efX83Ju20qt6iqt2q2p1MJr2kOy8ejWBOW2LCtDltCcSjEW8rjsatW8+FWrus6ZVOwzS2RdXhR14l8kNo82qVyzVfrgU+7INv16yAqeorAE4D8C8isjg7+Q5Y9cw3Tpp9QEQeg9VP6UVwoKpPAbgdwBOwOpa/VVX/F8BfAXhCRH4F4J8BfGnSorMBPJL9/HYAn3W3Z8VVIgj7mohcLSIniMhbcn9uVqSqfwawR0TmZyedAmB7BdLoqL0pjrUruvOZOvd8vb3J44nemLSe/edOwFxdgMaphZznNExjW0RENaHK5Zov1wIf9sG3a1ZAVLW54P89qnqkqm7JTno7gLtVdXDSYveo6omqeqyqPpFd9guq+u8F6zpWVXdl//+P7PtjVfWG7LSfqOpCVT1OVd+qqj3Z6Serao+q/lpV35L9/Dg/OqEXryMMici/ArgAVo/5Znayqurfu1zfcbCeu8ZhVYq7MPtcdoru7m7t6elxs5kp2DqyrgVeU7WSeRUA5l11f8XWlbPrmtMrvk6atrrLq56xdWT10jk9vm8sWyH+vQDel62/lZv+CIBP5YKmWlaJzlqXAPiLbEtGz1T1VwC6K7Gu6TAMQbKlwY8VA82d1UnDNLZF4eRHcFVp00kjAzvyrMrlmi/XAh/2wbdrVoio6j8WmX5ylZPim0r8nPg1gIr3nUFERERUzypxJ6wTwA4ReRIFTUNV9awKrJuIiIioLlUiCLu6AusgIiIimlE8B2EeuqMgIiIimrEq0WP+fhF5Lfv3uohkROS1SiSOiIiIyC0RGfJ5/Z8rPVdxnoMwVW1R1YOyf7MAnA3gm17XS0RERBRywQZhk6nq9wC46iOMiIiI6ttYOnPCiwOjj73QP/z8iwOjj42lMydUYr0i8j0R2SYivxWR1QXTrxeRp0TkIRFJZqddLiLbReRpEdmUndYkIreJyJPZ8asXZ6d/ODs+9o9F5DkR+bfs9GsAJETkVyJyh5s0e64TJiIfKHhrwOrjy1sPsERERFR3xtKZE363b+i+SzdsO3TvwCjmtCXmrVm+6L6jO5vPaohGfuFx9R9R1VdEJAHgSRG5B0ATgKdU9YrsAN1XA/gYrHGpj1TVMRHJdbP1zwD+W1U/kp32hIj8NPvZcQDeDKsXiJ0i8g1VvUpEPqaqx7lNcCVaR55Z8H8a1mDei+1nra7JPQq3JWIYGB2f8P6V0RReH88gIoJEPILWhMdeh8voGbkwXc0NBhLjgzAyY9BIA6TpUOwfS6NxfABRHYcRbYA0ZddRiV6XbdZhQjA4msJoKoOMKmbFIji0yeoEsNwemcvpvTkEPTwTkUdmJoPMUB8kW2ZFmpMwItaYhVU/x92WiS6Xc9o/x3132F4qlUbfcAppUxE1BMmmOOJx69Ls9lin0yZ6h8YwnjERixjoaG5ANBqO0VNe3p+6PheAAdbA45du2HboXatPuH52W+JEj6u/XESWZP+fC+AoWCP53JWdtgHAd7P/Pw3gDhH5HoDvZae9G8BZIvKp7PtZAHIDfz6UGyRcRLYDOALAHo/prUjryAu9rsMPpqnYuW8/Vq3vwd6BUbx7QQcuP+VoXLJhm+37OW0JXHfOQnQeNAvz2pvcFRymCfRuBzYtAwZ3HxgjrGNB/oQrTNfb/+IQfPFEA7HvfCg/f+a8OxGXGBruOjc/TZduhCSPAfp2OK7bTfp06Ua8FD8SuwdG8em7n84fi7UXdKMhZmDFbU8cmLaiG/M7W2yDq8JjbTdvOfMQUbiZmQzMfdsR23x+vgxJn3cn0LkAEKO653gZ5W0ll3MqwwAU33do0e2l0iZ29g3j0oLr0JrlizA/2YRoRFwda9NU7Ni3f8K17abli3BMZ0soArG0aR6WC8By9g6MIm2ah3lZr4icDOBdAE5Q1ZHs0EazbGbNPak7HcDfATgLwOdF5C9hDcV0tqrunLTuv0FBP6gAMqjMTSz3dcJE5P86/H2+Eonzon84lc+gAHD2orn5TGn3fm82CHmhfwT9wy5HYBrpO3CiAdbrpmXWdJt0XfmOQw8EYNn5I5vPR9PQ7gnTZNMyYOjPJdftJn2yaRmaMwP5ACx3LFZ9uwcv9I9MnLa+x/bYTD7WdvOWMw8RhVtmqA/RXFAAAIO7Ed18PjJDfdU/x8sobyu5nNP+Oe67w/b6hlP5ACy33KUbtqFvOOX6WPcOjU25tl2yYRt6hwpjiOBEDeOl3MDjOXPaEogaxkseV30wgIFsAHYMgLdlpxsAzsn+fz6A/xERA8BcVX0YwGdgjfrTDOAnAP5RRAQAROTNZWx3XERibhPtJSwetvkDgIsAXOlhvRWRSmdQGG23JmKO7wErszbGI0ilM+42mk4dOGFyBndb023SlTDS9vPHGqdOy4yXXLfb9DVIpuixmDzN7thMPtZ285YzDxGFm2TGbMsQyaSqf46XUd5Wcjmn/XPcd4ftpU21XS5tqutjPZ4x7deZMR33r1oObYlfsWb5opdzgVj27t/Lh7bEr/C46h8DiIrI0wC+COCX2enDAP5SRLbBajT4/wBEAGwQkd8A+F8AX1XVwexyMQBPi8gz2fel3JKdv7oV81X1+tz/ItIC4OMALgSwCcD1xZarlng0gjltiXxmHBwdd3wPWJlhJGU9X3clGrduNReeOK1d1nSbdI2aUcyym398ZOJ6W7uASKzkut2mb0wjRY9FoTltCdtjM/lY281bzjxEFG4aabAtQzQSR9yo8jleRnlbyeVKlWFFP5Pi24uq2C4XNQRquDvWkjHt1xkJ/lEkADREI784urP5rLtWn3B92jQPixrGS4e2xK/wWilfVccAvNfmo+bs6+QndG+3WccogIttpt8O4PaC92cU/H8lPNx48vStiMghIvIlWBXcogDeoqpXqmqvl/VWQntTHGtXdCMXbd+zbQ9uWr6o6PtcnbAj2hvR3jSNwKZQY9J61t+arceXe/bfmLRN17U/exnj594xYf7MeXdiuLlrwjRduhFofkPJdbtJny7diKFIG647Z+GEY7H2gm4c0d44cdqKbttjM/lY281bzjxEFG6R5qRVL6mgDEmfdycizcnqn+NllLeVXM5p/xz33WF7yaY41ky6Dq1ZvgjJprjrY93R3DDl2nbT8kXoaG6YztH1VUM08ovZbYkTj2hvOnJ2W+LECrSKrFmi6q43CRG5DsAHYN2K+09V9bVXWjvd3d3a09NT9PPyW0eaiAgCbh2ZgkbiIWgdCcyKGfXWOjLwmv+l8mrOvKvur0Jq7O265vSy5ptOGstdJ+WFPq8eaLFnlVlsHVmN1pHTO9a51pHpjImof60jA8+r9cBL7f4rYLUW+BcA/5ytxwZYX4yq6kEe0+aZYQiSLROj/8nvO1rsGk942ijQ3DnNdL1hwudt0SgAm4YiZazbTfoMAIc0NVi9qUwy+XgVX+3UY+1mHiIKNyMSgXHwG+w/q/Y57rZMdLmc0/457rvD9uLxKGbH7S/Fbo91NGrg8NaE7WcULl7qhIXjATMRERFRDWIgRURERBQABmFEREREAWAQRkRERFQBIvIJEWksPaeFQRgRERHVPRGpRseUnwDAIIyIiIhCKD12Agb3PIZXnn8eg3seQ3rsBK+rFJF5IrJDRNaJyNMicreINIrIruxwiv8D4FwReaOI/FhEtonIz7NDHEFEzhWRZ0Tk1yLyaHZaRESuE5Ens+u8ODv9ZBF5JLuNHSJyh1guB3A4gIdF5OFy0l2RASiJiIiISkqPnYDeZ+/D5gsOzQ5MPg/nffs+dLzpLEQbvHbaOh/ARaq6VURuA3BZdvrrqvp2ABCRhwBcoqrPZQfmvhHWcEb/F8B7VPVFEWnNLncRgFdV9a0i0gBgq4g8kP3szQD+EsCfAGwFcJKqfl1E/gnAO1X15XISHLo7YdnI839F5AdBp4WIiIgqaKj3+nwABljDMm2+4FAM9VZiuMM9qro1+/8GHBia6C4AEJFmACcC+I6I/ArAzTjQKedWALeLyCpYY0sCwLsBrMjO+ziAdgBHZT97QlX3qqoJ4FcA5rlJcBjvhH0cwLMAPHf2mus1eDxjIlak1+Bi89j1RgyU34N8oen2Il04fyIeQdpUjKdNTz1QF0uDmcnAHHkFkcyo1atzLAFtPBT9I2mYpomMAqpakR7z3R6PSi9PRO6l02mYQ30wzBRMIw6jOYlo1MdLSSVGCpnW5kr3RG93TXG7XDnXKTtOPe27XWdVmOnDbAc0N9M2PZRP2+QhgHLvh7OvBoBBVT1uyoKql2TvjJ0O4Fcichyszuf/UVV/UjiviJwMq7P6nAxcxlOhCsJEZA6sA/BlAP/kZV3ptIkd+/bjkg3bsHdgND9+1jGdLRMyv9088zua8fuXh7FqfU9++vqPHI+xtDlh2toV3Zjf2VIyoNq5b3/ZyxXOn2xuwGdOm49P3/30tLZZbhqOSjYCrzyP6PCfgS2XIXtrGOYH78R/PWXgb+d34sp7Sm97Ovs43ePh9XgSUeWk02mg91nEN5+fLy/S592JdMeb/AnETBPo3Q5sWpbfHpZuBDoW+BKIOZUvpqlFrymGIa6WA1DyOmUnlUpjZ98wLi1Ybs3yRZifbIJhGK7WWTVG9CW0ds2bMqC5EX2pAmvvEpETVPUXAJYB+B9Yjw0BAKr6mog8LyLnqup3xBrqZ6Gq/lpE3qiqjwN4XETOBDAXwE8AXCoi/62q4yJyNIAXS6RhP4AWADX5OPIGAJ8BYHpdUe/QWD4TAsDegVFcsmEbeofGypondzLlpr/QPzJl2qr1PegfTjmmo384Na3lCue/5OQ35gOw6Wyz3DSYQ32Ivvr8gQAMAAZ3I3LX+bj4rQfnA7BS257OPk73eFR6eSJyzxzqQzQXgAHA4G5EN58Pc6jPnw2O9B0IwLLbw6Zl1nQfOJUvTtcLt8uVc52y0zecygdgueUu3bANfSW2FwrNHVfgvG+/PGFA8/O+/TKaO66owNqfBbBSRJ4GcAiANTbzfAjARSLyawC/BbA4O/06EfmNiDwD4FEAvwZwK4DtAJ7KTr8ZpW9e3QLgRzVXMV9EzgDQq6rbsrf6is23GsBqAOjq6iq6vvGMmc+EOXsHRpHOmKXnMXXK9MZ4xHbeVDrjuF+pdGZayxXO35qIudpmuWkwzBQQa4TdreGEUX66p7OP0z0elV6+mlu6cUwAACAASURBVMrNq0RBKzevGmbKtrwwzHF/Epa23x7S/vzocipf7K4LuWuKqv1nJZfL/m/3mZOi6zQVQPHthUK04RfoeNNZ+PAPr4eZPgxG9CU0d1xRgUr5AGCq6iWTps0rfKOqzwM4bfKCqvoBm/UpgM9l/wo9kv3LLfuxgv+/AeAb5SY4THfCTgJwlojsArAJwN+LyIbJM6nqLararardyWSy6MpiEQNz2iYOYDqnLYFoxCg9jyFTpo+kMrbzxqPO3Y7Eo5FpLVc4/+DouKttlpsG04gD4yPI/yLJae3CqFl+uqezj9M9HpVevprKzatEQSs3r5pG3La8MI2YPwmL2m8P0bgvm3MqX5yuKW6XK+c6ZcfuGpW7drldZ1VFG36B1rkn4pAjj0Tr3BMrFIDVpNB8K6r6WVWdo6rzACwF8N+qutzt+jqaG3DT8kX5zJh7Lt7R3FDWPGtXdE+YfkR745Rpa1d05yvsF9PeFJ/WcoXz3/TIH3DdOQunvc1y02A0J5E++Ehg8Y0ovDWc+eCduPnJV3Ht2eVtezr7ON3jUenlicg9ozmJ9Hl3Tigv0ufdCaPZpx8ZjUmrDljho6ulG63pPnAqX5yuF26XK+c6ZSfZFMeaScutWb4IyRLbq2equktVjw06HdMlqpMbEwQv+zjyU6p6htN83d3d2tPTU/TzXAuRdMZEtETryMnzsHVkXbWODLzGfqm8mjPvqvurkBp7u645vaz5ppPGctdJeaHPqwdaR47DNGIzsnWk3TXF7XLlXKfslNM6crrrnKbA82o9CE2dsEKq+ggKnre6FY0aOLw14WoewxAkW6b+crCbVkqxdVVqfi/rNCIRGC0Tf1UKgGTL9B7vTSfNXvfPj+NDROWJRqNAayV6EyiTYQDNnVXcXPHyxema4na5cq5TduLxKGbH7S/hbtdJ1Reax5FEREREMwmDMCIiIqIAMAgjIiIiCgCDMCIiIqIAMAgjIiIiCgCDMCIiIqIAMAgjIiIiCgCDMCIiIqIAhLKz1koZH89YvQZnexRujBsQEQyPZZBRxaxYBIc2NZTVe32u9/iMacIQQSIeQWvCXe/1k9c9nZ7jc8tEYKI5MwjDTME0GvCqHITRzMR9sut5H6aJNryGqI5DSvU+bdNTtQmZmmYodLgPZnoMaYlhJNaGgxNWp4VeesangH3hYNvJu2ZNnTbv9Tt9TgzVPJc93zuVk15H35ju9lz33u+wXHo8jcxwHyJmChkjjkhTEtHYxJ7vxzMmYtPoof/119PoHz3Qm357Io5Zs0pf7v04nuSsboOw8fEMdvQO4dIN27B3YBRz2hK47cPdSKUVlxRMW7uiG/M7W2wzmmkqdu7bj68+uBMrTzwSV97zdH65685ZiM6DZmFee5PrYYR27tuPVet7ykpL4TJbntqDK47LIPadDwGDu4HWLsQWr8PqHw6jb2gca1d046hkM57rG8Kq9T1INjfgM6fNx+1b/4ivnBRF7Psr88th6UagY8HUgsQ0gd7twKZl+Xl16Ua8EDkCF9z2ZD7N3/7IWzEv8wJk0zJEBncj0tqF0cXr8NLB8/HaWGZa+0dEdcqmPCla9kxYrHg5CWDaZWjpZDqUy1BX++C07+mMCfQ9i4bN5wODuxHNjsWZTr4JEAM79u2fcL26afkiHJPdv2LpTKUyeK5/eMK1b83yRTiqvckxEHNzTSLv6vZxZO/QWD4TAsDegVG8OPB6PkPnpq1a34P+4ZTtOvqHU1i1vgdnL5qbD8Byy3367qfxQv9I0WVLya273LQULnPxWw8+EIABwOButG5ZiX85OZlfT+/QWH79l5z8Rnz67qexetFBaM8FYNnlsGmZ9QttspG+A4VGdl7ZtAxDr/x5QpqHXvkzZNJ8rVtWojkzMO39I6I6ZVOeFC17CjiVk27K0FIc1+lyH5yWywz3IZoNwHKfRTefj8xwH3qHxqZcry7ZsA29Q2POx2U0NeXad+mGbegfdT4ufhxPKq1u74SlTc1nppzGeGTKtL0Do0ilM7brSKUz2DswitZEzHa5xnik6LKl5NZdbloKl0kY6QMnbc7gbnQ0Sn496YyZX38u/R2NYrsc0jYnWTplO29r3JwwqTVu2s7XINPfPyKqU0XKE9uyp0CpcrLSZYzj9sTdPjjte8S0Lz8NcxzjatqmJZ0xoTr1+pZLp921b+/AqFUdxYGbaxJ5V7d3wqKGYE7bxAFMR1KZKdPmtCUQj9oPVh2PRjCnLYHB0XHb5UZSmaLLlpJbd7lpKVxm1Ixat7QLtXahd0Tz64lGjPz6c+nvHVHb5RCNT91YNG4772BqYpYZTBm2843p9PePiOpUkfLEtuwp4FROuilDS3Fcp8t9cFouY9h/ZhoxxArK8MK0RCOGYzrtrn1z2hKIlnik6MfxpNLqNgjraG7AmuWL8plqTlsCs9tm4aZJ09au6EZ7k/1J1N4Ux9oV3bhn2x5ce/bCCctdd85CHNHeWHTZUnLrLjcthcvc/OSrGD/3jgMnb2sXBhevw5ce6cuvp6O5Ib/+mx75A647ZyFu2fYa+s9cN2E5LN1oVRKdrDFpfVYwry7diOZD3jAhzc2HvAE6ab7BxeswFGmb9v6Re7tmnV/2H1HV2ZQnRcueAk7lpJsytBTHdbrcB6flIk1JpM+7c8Jn6fPuRKQpiY7mhinXq5uWL0JHc4PzcUnEp1z71ixfhPaE83Hx43hSaaLqfIsyzLq7u7Wnp6fo586tI4FZMcNF60iFIQhR68hxmEY82zpy4j6xdWRe4LVKS+XVnHlX3e9q/dMJroq1ZNx1zekTJxRpHelpnVRKzeTVaWPrSMfWkVZZHrNtHZnOmIiGr3Vk4Hm1HtRtnTAAiMUimN3WOGV669RJRRmGINnSUMFUeVv3xGUO3Dq2+y1WfP1lHgDDAJo7J04CbNYpkJZORABEABR+6texI6IaY1OelLdY8XLSj/LZcZ0u98FpuWgsimjrYfafRQ0c3pqw/cwpnbNmRTG7jKBrOuskf9Tt40giIiKiMGMQRkRERBQABmFEREREAajrOmFEVKOm0SgAX3jVv3QQEfmId8KIiIiIAsAgjIiIiCgADMKIiIiIAhCqIExE5orIwyLyrIj8VkQ+HnSaiIiIiPwQtor5aQBXqOpTItICYJuIPKiq212tLNvb8HjGRCxiINkUx+Dr6aK9AfvR+7Kf63WzXeBAL/YigogAhmGgLRHDwOh42Wn0sk/lLhvUcSOiyqv389nt/vkxIkAqlUbf8IEe85NNccTj0ZKfUfWF6sir6ksAXsr+v19EngUwG8C0g7B02sSOfftxyYZt2Dswmh8/6xsP/Q4PbO/Nj4s1v7MlP8TPzn37sWp9T37+ws/d8mu9bra7/iPHYyxtTph27dkLse6x53H5KUfj60WOTSX3qdxlgzpuM0HRIY6+UPltTR6GyY+xK4sN9cQhk8Kj3s9nt/vntBwAV+tMpdLY2TeMSydd++Ynm6x1FvmMgVgwQvU4spCIzAPwZgCPu1m+d2gsH4ABwN6BUVy6YRvOXjQ3/37V+h70D6cAWHeHcpnd7nO3/Fqvm+2+0D8yZdqV9zyNsxfNxSUOx6aS+1TuskEdNyKqvHo/n93un9NybtfZN5zKB1m55S7dsA19wynHzygYoQzCRKQZwD0APqGqr036bLWI9IhIT19fX9F1jGfMfEbL2TswitZEbML7VDoDAEilM7bz///t3XuUJHWVJ/DvjczK7uqqliqarOLRNO2DaexhkaVq2FFcF1ePA4676MIwNNOCL7BldGR3dYejZ9U9c+Ys6jq6+KCXVhZahJYRWWYVlceqqLs+qhlsobFRmaZpha6iH9LVXXRWZtz9IyKrsrIiKuOZv4jI7+ecOlUZGY8bv/hl5q3I+N1oPh9VWuuNst0VlZJvmyzVNkHWHXSfgi5rqt2SFLSvEpmWdl8twut5KVH3b6nloq6zbqvncnVbl3yOzMhcEiYifXASsK+o6tfbn1fVm1R1XFXHq1Wv21Y7+koWVg8vvPHp6uF+HJqZXfC4Ui4BACrlkuf8zeejSmu9UbZ7tNbwbZOl2ibIuoPuU9BlTbVbkoL2VSLT0u6rRXg9LyXq/i21XNR1li3xXK5syZLPkRmZSsJERAB8CcDjqvp3cdY1MrgMmzeOzXW45nffd21/eu7xlivG5y5WXzVQwZYrxhfM3/p8VGmtN8p2T1u1YtG0j198Fu7a/jQ2L9E2Se5T0GVNtRsRJa/or+eo+7fUclHXWR2o4EaPz77qQGXJ58gMUc3OaUgReTWAHwD4BQDbnfwhVb3Xa/7x8XGdmJjwXV9zdGS9YaPM0ZG9PDrS+L95nfpqk99F5p2kccF7GGtfuD3QfKlcmO+z7ZxemJ+bvhoWR0eGXy7joyOLc/AMytRwCFX9IRI8sOWyhZOHFp56rfb5n8q1LEF15bKkNp/6eqNu1y+WMDHG2aegy5pqN+otYRLfRYld0Htc8v6WhX89R92/pZaLus5KpYxTfBKrpZ6j7svU15FEREREvYJJGBEREZEBTMKIiIiIDGASRkRERGQAkzAiIiIiAzJVoiIsEZkC8FSH2U4A8FwXwjGN++nvOVW9II1gggrYVzvJ4jFmTMEEjSlrfTVLbclYvJmKxXhfLYJcJ2FBiMiEqo6bjiNt3M/iy+K+M6ZgshhTEFmKm7F4y1IsFB6/jiQiIiIygEkYERERkQG9kITdZDqALuF+Fl8W950xBZPFmILIUtyMxVuWYqGQCn9NGBEREVEW9cKZMCIiIqLMYRJGREREZACTMCIiIiIDmIQRERERGcAkjIiIiMgAJmFEREREBjAJIyIiIjKASRgRERGRAUzCiIiIiAxgEkZERERkAJMwIiIiIgOYhBEREREZwCSMiIiIyAAmYUREREQGMAkjIiIiMiDXSdgFF1ygAPjDn04/xrGv8ifgj3Hsq/wJ+EMJyHUS9txzz5kOgSgQ9lXKC/ZVou7JdRJGRERElFdMwoiIiIgMYBJGREREZACTMCIiIiIDyqYDoOKybcX+IzXU6g1UyiWsGqjAssR0WIXCNiYiyi8mYZQK21bs2ncYV22dwN6DM1g93I8tV4xj3ehKJgkJYRsT9aa1130z1Py7r//TlCKhuPh1JKVi/5HaXHIAAHsPzuCqrRPYf6RmOLLiYBsTEeUbkzBKRa3emEsOmvYenEGt3jAUUfGwjYmI8o1JGKWiUi5h9XD/gmmrh/tRKZcMRVQ8bGMionxjEkapWDVQwZYrxueShOb1SqsGKoYjKw62MRFRvvHCfEqFZQnWja7E3decx5F7KWEbExHlG5MwSo1lCaorl5kOo9DYxkRE+VXoJKy9htJwfx8Ozsx2/awBazlF00vtVqvVMXWkhrqtKFuC6kAFlUqhX55ERD2vsO/yXjWUNm8cww0PPoH7dk52raYSazlF00vtVqvVsWvqCN5z2/a5fb1x4xjWVQeYiBERFVhhL8z3qqG06bbtuHjs1LnH3aipxFpO0fRSu00dqc0lYICzr++5bTumCrivREQ0r7BJmF8NpaH+vgWP066pxFpO0fRSu9Vt9dzXuq2GIiIiom4obBLmV0Pp0Mzsgsdp11RiLadoeqndypZ47mu5YF+7EhHRQoVNwrxqKG3eOIa7tj8997gbNZVYyymaXmq36kAFN24cW7CvN24cQ7WA+0pERPNENb9feYyPj+vExITv8xwdmW8Jtpvxxu7UVzk6klyZ76tkXkZu4G28rxZBod/lbVuhqlAAR2t1qCpOGFw290Fu24qpw8eWTNIAzCUCfWULZUswUwuXFISp5dQpcWw+tm0bDQVU1TeWet3G5PQxzDZsDC4r4VhdMduw0VeyMDK4DOVy+BOhzfiCbD8u1sDq7IUX6tg/M5+8reqvYPnyYC/r1v4Rtk/EWZaIiByFTcLqdRu7DxzB1OFj+ODXdsyXOXjrONaduBIAOpaw2PqOc3Gsbi+Y55OXnIVPfHsXpqaPJV4yob0swxvWj+CvXvcH2NRSumDzxjH870f24jXrRvHXd+3wLd9Qr9v45b7D2HTbdrzqJauw8ZWn4ZqvPLxgPWeMrgz1wdmM79P378KVr3rxktun4KKWqHjhhTp+tX/xcqevGuiYiLX2j7B9Is6yREQ0r7DvmJPTx/D0gZm5BAxwyxx82SlzEKSExVP7jy6a54Nf24FN5780lZIJ7TFdPHbq3Adda4yXjK+ZS4Dm9qstlsnpY3PLXvWal8wlYK3rmZw+Fim+i8dO7bh9Ci5qiYr9M97L7Z/pfBxa+0dz2aB9Is6yREQ0r7BnwmYbNlZUSkuWOehUwsJv+eY8SZdMaC/LMNTf57n9kiUdyzfMNuy5efzmrzfsSPH5xVXE8hHdELVERZzSFq39Y8GyAfpEnGWJiGheYc+E9ZUsHK01fMscBClh4bd8c56kSya0x3RoZtZz+w1bO5Zv6CtZc/P4zV8uhTv8zfj84ipi+YhuiFqiIk5pi9b+sWDZAH0izrJERDSvsO+aI4PLcOrxzjVcC8ocvNUpcxCkhMVpq1YsmueTl5yFzd/7TSolE9pjumv709jcVrpg88YxfG1iDz5+cdt+tcUyMrhsbtktDz2JL/zFOYvWMzIY7qL3Znx3bX+64/YpuKglKlb1ey+3qr/zcWjtH81lg/aJOMsSEdG8QpeoqNdtHDhaQ61hw7YVy/tKi0ZHdiphAcQfHRlGGqMj6w0bA+7oyHrDRjknoyMTZDywtEpUJDE6MkqfiLMsLSnzfZXMY4mK4jByTZiI3AzgTQAmVfVMd9rHAFwFYMqd7UOqem+c7ZTLFkZetNz3ea8SCF4lERZNG4gT1dKCxBS0bEO5bOHkof7OM4bAshHpqFTKOCVCXbDly8s4JWDS1S5O/0ijbxER9RpTF+bfAuBzALa2Tf+0qv63pDbiVewTQKYKp7bG2I0zbWFiSutsF4vXJidOW8YpEBtnuzz+REQOI0mYqj4kImvT3EZ7zS2/ul8m61t5xZhmHbIwMaVVC8xrn1ljLJo4bRm1Nlnc7fL4ExHNy9pFHO8VkR0icrOIDMdZkVcdMK+6XybrW3nFmGYdsjAxpVULzGufWWMsmjhtGbU2Wdzt8vgTEc3LUhJ2I4CXAjgbwDMAPuU1k4hcLSITIjIxNTXlNQuAxTW3AP+6X6bqW3nFmGYdsjAxpVULzG+fi1hjLGhfjSpOW8apMRZnu710/PMk7b5KRN4yk4Sp6j5VbaiqDWALgHN95rtJVcdVdbxarfquz6sO2FJ1w0zoVKvMRGxp1wLz2+ci1hgL2lejitOWcWqMxdluLx3/PEm7rxKRt8wkYSJyUsvDtwB4NM76vOqAedX9MlnfyivGNOuQhYkprVpgXvvMGmPRxGnLqLXJ4m6Xx5+IaJ6ROmEicgeA8wGcAGAfgI+6j88GoAB2A3i3qj6z1Ho61bPh6Mh4MRVodKTxK77Tqr3E0ZGFY7whWCcs+1gnrDhMjY7c4DH5S0lvx6+mVZbqXHnG2G8DR6eA52tAuQKsqAKW90nLND7QotQCaxbvnG3Y6GPxztCiHkfbVsw2bNRthbhFiYMe/6i1yQAAamPIPgjRY1B7GaBVAMG+UmStOSIiR2Fv4J1btg1M7gS2bQAO7QGG1gCX3QGMrF+UiGVluH+9buOX+w5jU0u5g80bx3DG6MpFiVhWYs6SqG0Spt0TjbfRgL1vJ/ruvHyuj9YvvR0YXQ+rxGu7iIiC4qmKrDk6NZ+AAc7vbRuc6W2yMtx/cvrYXCLQjGPTbdsxOX0sszFnSdQ2CdPuSWpMT6HcTMAA4NAelO+8HI1pjqojIgqDSVjW1GvzH25Nh/Y409tkZbj/bMP2LnfQsBfNm5WYsyRqm4Rp9yRJ45hnH5VG7ybSRERRMAnLmnLF+Qqy1dAaZ3qbrAz37ytZ3uUOSou7V1ZizpKobRKm3ZOkpWWefVRLHOFIRBQGk7CsWVF1rgFrfsg1rwlbsbh2T1aG+48MLsPmtnIHmzeOYWRw8cXXWYk5S6K2SZh2T1JpsOpcA9bSR+uX3o7SIOtLERGFYaRERVIKO5TadkdH1s2MjoyiOTqy3rBR7jA6kiUqFovaJmHaPUl2o4HG9BSkUYOWKigNVnlRfjIy31fJPJaoKA6OjswiywIGRwPOmo3h/uWyhZOH+jvPiOzEnCVR2yRMuyfJKpVgHXdi17dLRFQkhU7C2s8uDPf34eDMbMezDX5FXg/N1DBTa6ChiuV9JZwwsCwTZRXCnEVJZd9sG3pkCnb9GOrSh6N9wziuf/HyWTlrl0WRz4TN1tE4MoWSXUPDqqA0UEW5L9jLOk5ttziFXuNgHyKiIilsEuZVe2nzxjHc8OATuG/npG8tJr+aTYPLnJt/f/BrOzJV3ypMjalU9s22oZM7Ids2oHRoD0pDazBz0a14avB0nLZqcG551gfzF7lO2GwdmHocy9xyEWX32qx69eUdE7E4NcZqtTp2TR3Be1qWvXHjGNZVB1JNxNiHiKhoCnthvlftpU23bcfFY6fOPfaqxeRXs+lYXeeSlKWW77YwNaZS2bejU5C2umZD91yJ6QPPLlie9cH8RW2bxhGfel1HOtfrilNjbOpIbS4Bay77ntu2YyrlY8k+RERFU9gkzK/20lB/34LH7bWY/JazBJmsbxWmxlQq++ZT12yoYi9YnvXB/EVtm5Lt3faWPdtxm3FqjNVt9V7WTneQD/sQERVNYZMwv9pLh2ZmFzxur8Xkt5ytyGR9qzA1plLZN5+6Zodq1oLlWR/MX9S2aVjebW9bfd4LtIhTY6xsifeyKX8lyD5EREVT2CTMq/bS5o1juGv703OPvWox+dVsWlYWfPKSszJX3ypMjalU9m1FFdpW1+zQRbdi8PgTFyzP+mD+orZNacCnXtdA53pdcWqMVQcquLFt2Rs3jqGa8rFkHyKioil0nbD0RkcCy/usgo6OjLBv2R8dafwgpVYnzB0dadmzsK2+SKMjo9QY4+jI1BjfGdYJyz7WCSuOwo6O9BK0FpPffMcPLAMGQm40ROHVUOsqVQCrBMzOwCpXUB2oAlb4fUvkQ82yICtHUQJQAuAXBeuD+YtcJ6xkOYlTXYCyBUS4ZVGUf8MqZQun9B2e79flENXyY7wm2IeIqEgKm4RlYji7bQOTO4Hm6MHmLYhG1odPxLzWddEXgAc/BkxPRlpvJtqIoovRv+KUqIjVr5N8TRAR5Vxh3/UyMZz96NT8hw3g/N62wZmexLruuQY479rI681EG1F0MfpXnBIVsfp1kq8JIqKcK2wSlonh7D7lG1CPkOT4rat/OPJ6M9FGFF2M/hWnREWsfp3ka4KIKOcKm4RlYji7T/kGlCOM5vJb18zByOvNRBtRdDH6V5wSFbH6dZKvCSKinCtsEpaJ4ewrqs71Li0lBHDZHc70JNZ10ReAH30m8noz0UYUXYz+FadERax+neRrgogo53qqRIWR4exdGB0ZZ72ZaKP0Gd+h1Ib9x+hfcUpUxOrXSb4miqe4fZUSwxIVxVHY0ZFARoazWxYwOJq9dc2tMgNtRNHF6BPlsoWTh/o7z5jwdtPox0REeVToJCyIHjkTtEiQ/e7VtjHBRFvH2Sb7BlFywp7ZouLo6SSsV+tkBdnvXm0bE0y0dZxtsm8QESWjpy/E6NU6WUH2u1fbxgQTbR1nm+wbRETJ6OkkrFfrZAXZ715tGxNMtHWcbbJvEBElI1YSJiKLruj2mpZVvVonK8h+92rbmGCireNsk32DiCgZcc+E/b+A0zKpV+tkBdnvXm0bE0y0dZxtsm8QESUjUp0wETkRwCkAbgNwOebrhbwIwGZVPSOxCJeQRD2bXh3l1WOjI40HncWadhwdmUnGG5F1wrov7dGRrBOWXVFHR/4JgLcBWA3gU5g/GM8D+FCnhUXkZgBvAjCpqme6044H8FUAawHsBnCpqh6MGF+mZeEDLEh9MAuKqhwCpAZIBUAVWXjdZaH9kha5XluMwqe2rZht2KjbCmnYsG3NfTsSEeVJpCRMVW8VkS8D2KCqX4mwilsAfA7A1pZp1wF4UFWvF5Hr3Md/HSW+oPJWGqCrbBuY3Als2+DcYLl5e5mR9Uarm+em/bohxjGq1238ct9hbLpt+1w7bt44hjNGV3asms9jQESUjMifpqpqA3h3xGUfAnCgbfJFAG51/74VwJujxhZU3koDdNXRqfkPd8D5vW2DM92g3LRfN8Q4RpPTx+YSMMBpx023bcfk9LGOy/IYEBElI+4pjftF5AMicqqIHN/8ibiuUVV9BgDc3yNeM4nI1SIyISITU1PxEoK8lQboqnpt/sO96dAeZ7pBuWk/JNtXPcU4RrMN27Md6w2747J5OgYUTOp9lYg8xU3C3gHgLwE8BGC7+5PqFZ2qepOqjqvqeLVajbWuvJUG6Kpyxfl6q9XQGme6QblpPyTbVz3FOEZ9JcuzHculzm8JeToGFEzqfZWIPMVKwlT1xR4/L4m4un0ichIAuL8n48QWRN5KA3TViqpzfVHzQ755vdEKs2/QuWm/bohxjEYGl2HzxrEF7bh54xhGBjsPDuAxICJKRqQSFQtWIHImgPUAljenqepW/yXmllsL4BstoyM/CWB/y4X5x6vqf1pqHXktUZGb0X0xRt6lG1bo9jPeuKkN+49xjOp1G5PTx1Bv2CiXLIwMLut4Uf78ZnPSh/PHeCOyREX3sURF74p1A28R+SiA8+EkYfcCuBDAD7Fw1KPXcne4y50gInsBfBTA9QDuFJF3AtgD4M/ixBZU5NIAOdtmJJYFDI6ajmKR3LRfN8Q4RuWyhZOH+jvP6LlZHgMiorhiJWEALgHwCgD/qKpvF5FRAF/stJCqbvB56nUx41kgzH/r7fMO9/fh4Mxs6P/0eYaAuimPBVfzGDMRURriJmEzqmqLSF1EXgTnOq6o14QlKkwtI695N28cww0PPoH7dk4GPyS0mwAAFShJREFUroPE+knUTXH6m6m+mseYiYjSEvcCnwkRGQKwBc7IyIcB/DR2VAkIU8vIa95Nt23HxWOndlw26jaJ4orT30z11TzGTESUllhnwlT1GvfPzSLybQAvUtUd8cOKL0wtI795h/r7Oi4bdZtEccXpb6b6ah5jJiJKS6wzYSLyYPNvVd2tqjtap5kUppaR37yHZmY7Lht1m0RxxelvpvpqHmMmIkpLpCRMRJa7lfFPEJHhlmr5awGcnGSAUYWpZeQ17+aNY7hr+9Mdl426TaK44vQ3U301jzETEaUlUp0wEXk/gGvhJFy/bXnqMIAtqvq5ZMJbWqd6NhwdSS7jByCt2kt5HGmYx5i7yPjOsE5Y97FOWO+Kek3Y/wVwJ4BLVPWzInIlgIsB7AZwe0KxxRamlpHXvFHqIGWuflJ7Mc/+VcDM/swVYKVo4vS3WH01RpHYWDFDUZVDgNQAqQCogp8FRJRXUZOw/wHg9W4C9hoA/xXA+wCcDeAmOPXDyDTbBiZ3Ats2ODd2HloDXPpl4PufAHZ9c/42NyPrmYhRcF79qhv9yNR2iYhSEvWdq6SqB9y//xzATap6l6r+ZwAvSyY0iu3o1PwHFuD8vvOtwNkb5h9v2+DMRxSUV7/qRj8ytV0iopRETsJEpHkW7XUA/k/Lc3ELwFJS6rX5D6ymQ3uA/uGFj+uss0Qh+PWrtPuRqe0SEaUkahJ2B4Dvi8g9AGYA/AAARORlAH6fUGwUV7nifGXTamgNMHNw4eMyR5dRCH79Ku1+ZGq7REQpiZSEqerfAviPAG4B8GqdH2Jpwbk2jLJgRdW5Zqb5wdW8JuyRO+YfX3aHMx9RUF79qhv9yNR2iYhSEvmrQ1X9sce0J+KFQ4myLOei5Xc9sHB05L/5NHDhxzk6kqLx6lfd6EemtktElBJev1V0lgUMji6c1v6YKCyvflXk7RIRpYD/QhIREREZwCSMiIiIyAAmYUREREQGMAkjIiIiMoBJGBEREZEBTMKIiIiIDGASRkRERGRAT9UJs23F/iM11OoNVMolrBqowLIk6sqcGwe3F430m55HRdqXgkq0T4fbsJm+kbc+mbd4iaireiYJs23Frn2HcdXWCew9OIPVw/3YcsU41o2uDP+hZdvA5E5g2wbnBsLN26dUzwCmfrl4+sj6/L3x+u1jHveloBLt0+E2bKZv5K1P5i1eIuq6nnkn2H+kNvdhBQB7D87gqq0T2H+kFn5lR6fm31gB5/e2DcD0s97Tj04ltBdd5LePedyXgkq0T4dhqm/krU/mLV4i6rqeScJq9cbch1XT3oMzqNUb4VdWr82/sTYd2gM0Zr2n11P+UEyD3z7mcV8KKtE+HYapvpG3Ppm3eImo63omCauUS1g93L9g2urhflTKpfArK1ecrxZaDa0BSn3e08uV8NswzW8f87gvBZVonw7DVN/IW5/MW7xE1HU9k4StGqhgyxXjcx9azetnVg1EeENcUXWu7Wi+wTav9Rg80Xv6impCe9FFfvuYx30pqET7dBim+kbe+mTe4iWirhNVNR1DZOPj4zoxMRF4fo6ODKk4+9KF4YJLC9tXg+LoyIz3yfDxFravkr+1130z1fXvvv5P01it8b5aBJkbHSkiuwEcBtAAUFfV8aTWbVmC6splSa0MGBwNPj2PirQvBZVonw63YTN9I299Mm/xElFXZS4Jc71WVZ8zHUTaEj+LEeUsQd7OLNACsfoQz2YRERmV1SSs8BKv8RSlJhHrGOVarD7EWl9ERMZl8V1PAdwnIttF5GrTwaQl8RpPUWoSsY5RrsXqQ6z1RURkXBbPhJ2nqr8TkREA94vIL1X1oeaTbmJ2NQCsWbPGbx2Zl3iNpyg1iVjHKFVp99VYfYi1vqhFUd5XifImc2fCVPV37u9JAHcDOLft+ZtUdVxVx6vV/A71TrzGU5SaRKxjlKq0+2qsPsRaX9SiKO+rRHmTqSRMRAZEZGXzbwBvAPCo2ajSkXiNpyg1iVjHKNdi9SHW+iIiMi5rX0eOArhbRAAntttV9dtmQ0qHZQnWja7E3decl8zoSMtyLm5+1wPBR51FWYYyI1YfMnXs2eeIiOZkKglT1ScBvMJ0HN2SeI2nKDWJWMco12L1Idb6IiIyKlNJGBERUdaErWifUoV6KiB+B0BERERkAJMwIiIiIgOYhBEREREZwCSMiIiIyAAmYUREREQGcHQkERFl28eOCzDP79OPI6c4ujO7mIT1Gtt2bpbcVijTthX7j9Q8i34u9RwlI3Ib+xxPShZfA0SUBiZhvcS2gcmdwLYNzk2T3VvG2NWXY9fkEVy1dQJ7D87M3f5m3ehKAMCufYc9n+OHUDJsW6O1sc/xxMh6JmIJinx8iIg64Dt1Lzk6Nf+BDTi/t21AY3pq7gMGAPYenMFVWyew/0gN+4/UfJ+jZERuY5/jiaNTKUfcW/gaIKK08ExYL6nX5j+wmw7tgTRqcx8wTXsPzqBWb8z97fccxVerN6K1sc/xRJ3JQZIiHx8iog6YhPWScsX5yqr1g3toDbRUwerh/gUfNKuH+1Epl+b+9nuO4quUS9Ha2Od4olxJKdLeFPn4FFyYi72zdqF32AvVidLCryN7yYqqc83Q0BrnsXsNUWmwii1XjGP1cD8AzF3zsmqgglUDFd/nKBmR29jneGJFNeWIewtfA0SUFp4J6yWW5Vy0/a4HFoymsywL60ZX4u5rzvMc/bXUcxSfZUm0NvY5nrwoP1mRjw8RUQdMwnqNZQGDox6TBdWVy3wW8X+OkhG5jX2OJyWLrwEiSkNvJ2G2DT0yBbt+DHXpw9G+YRzXv4z/4RJ1YKxuFuuiEVGB9G4SZtvQyZ2QbRtQOrQHpaE1mLnoVjw1eDpOWzXIRIzIh7G6WayLRkQF07tJ2NEpSFuNpaF7rsTTF34d+5ev4VcPRD786mbdfc156b5u/OqivesBfiVrwO7ll3ecZ+0Lt3chkozirZYogN7999GnxtJQxWb9H6IlGKubxbpoRFQwvZuENWsstRpag0M1q+fr/xAtpVk3q1VX6mb5vGZZF42I8qp3k7AVVWhbjaVDF92KweNPZP0foiUYq5vFumhEVDC9e02YZUFG1kPf+cDc6EjtG8ZpHB1JtCRjdbNYF42ICqbQSVjHYfSWBVk5ihKAEoC0LileMg6PIfc2pLvD/znsvyfV63XY01Ow7BpsqwJrsIpyOeBbgtoYsg9C9BjUXgZoFc6rKGWsi0ZEBVLYJMzYMPowcUAXDbnXy+7AU6XT8Nabf9aduDnsvyfV63Vg8nFU7rx87rjXL70d9ZGXd0zE7EYD9r6d6GtbFqPrYZV4PSUtFvdejbuXJxSIO2JxqfUlMaJz7XXfDBZzgHiSiomyqbCfsn7D6Pcf6e5IqiXj8BhyL9s2YPrAs92L22/Y/9GpdLZHmWBPT6HcTKIA4NAelO+8HPZ05+Pe8Fm2EWBZIiKaV9gzYcaG0YeJQ/zLZHjOnwYO++9Jlu193C17tuOy0jjmuaw02GeIiMIo7JkwY8Pow8SxRJkMz/nTwGH/Pcm2vI+7bfV1XFZLyzyX1RL7DBFRGIVNwowNow8Th8eQe73sDgwef2L34uaw/55kDVad67hajnv90tthDXY+7iWfZUsBliUionmF/TrS2DD6UHHIoiH3sqKK0yDdi5vD/ntSuVxGfeTlqL3tPlj2LGyrL/DoSKtUAkbXY/bt90MaNWipgtJglRflExGFlLkkTEQuAPDf4Yx3/6KqXh91XZYlmbgH5JJxeAy5t4Duxs1h/z2pXC4DQydFWtYqlWAdd2LCEVHR5PH+knmMmfIrU6c7RKQE4PMALgSwHsAGEVlvNioiIiKi5GUqCQNwLoBfq+qTqloDsA3ARYZjIiIiIkpc1pKwUwA83fJ4rzuNiIiIqFCyloR5XX2uC2YQuVpEJkRkYmqKxSEpu9hXKS/YV4nMyFoSthfAqS2PVwP4XesMqnqTqo6r6ni1yiHxlF3sq5QX7KtEZoiqdp6rS0SkDOAJAK8D8FsAPwNwuao+5jP/FICnOqz2BADPJRlnRnE//T2nqhekEUxQAftqJ1k8xowpmKAxZa2vZqktGYs3U7EY76tFkKkSFapaF5H3AvgOnBIVN/slYO78Hf9lE5EJVR1PMMxM4n5mW5C+2kkW950xBZPFmPy09tUsxc1YvGUpFgovU0kYAKjqvQDuNR0HERERUZqydk0YERERUU/ohSTsJtMBdAn3s/iyuO+MKZgsxhREluJmLN6yFAuFlKkL84mIiIh6RS+cCSMiIiLKnMImYSJygYjsEpFfi8h1puOJS0RuFpFJEXm0ZdrxInK/iPzK/T3sThcRucHd9x0ico65yIMTkVNF5Lsi8riIPCYi73enF2o/l+LXBm3znC8ivxeRR9yfj3Qhrt0i8gt3exMez3f1WIjIupb9f0REnheRa9vm6Uo7hXlteix7pTvPr0TkyjTiiyJL75+d+l7K2458bLsUy8dE5LctffyN3YiFEqSqhfuBU97iNwBeAqAC4OcA1puOK+Y+vQbAOQAebZn2CQDXuX9fB+Dj7t9vBPAtOHcg+GMAPzEdf8B9PAnAOe7fK+HUjFtftP2M0gZt85wP4Btdjms3gBOWeN7YsXBf788COM1EO4V5bbYtdzyAJ93fw+7fw6b6Xlt7Zub9s1Pfy+Kx7WIsHwPwAdN9hj/Rf4p6JqxwNwJX1YcAHGibfBGAW92/bwXw5pbpW9XxYwBDInJSdyKNTlWfUdWH3b8PA3gczr1DC7WfS1miDbLO5LF4HYDfqGrcYriRhHxttvoTAPer6gFVPQjgfgBZKH5ZuPfPqGIc227FQjlX1CSsV24EPqqqzwDOhzeAEXd67vdfRNYC+OcAfoIC7+dS2tqg3StF5Oci8i0R+cMuhKMA7hOR7SJytcfzJo/FZQDu8Hmu2+3U5NdnW2W1/2Ytrk59r9uCHNtueq97CcDN3fpqlJJT1CSs443ACy7X+y8igwDuAnCtqj6/1Kwe03Kzn0vp0AYPw/nq7RUAPgvgf3UhpPNU9RwAFwL4SxF5TdvzRo6FiFQA/FsAf+/xtIl2CiOr/TdrcXXqe73sRgAvBXA2gGcAfMpsOBRWUZOwjjcCL4h9za983N+T7vTc7r+I9MFJPr6iql93JxduP5fi0wZzVPV5VZ12/74XQJ+InJBmTKr6O/f3JIC74Xxl1crUsbgQwMOquq/9CRPt1MKvz7bKav/NVFwB+l63BTm2XaGq+1S1oao2gC0w3zYUUlGTsJ8BOF1EXuz+p3wZgH8wHFMa/gFAc0TVlQDuaZl+hTti7Y8B/L55+jzLREQAfAnA46r6dy1PFWo/l7JEG7TOc6I7H0TkXDiv4/0pxjQgIiubfwN4A4BH22YzdSw2wOeryG63Uxu/PtvqOwDeICLD7tdIb3CnmZaZ98+Afa/bghzbrmi77vItMN82FJbpkQFp/cAZrfUEnFE+HzYdTwL7cwec082zcP5TfSeAVQAeBPAr9/fx7rwC4PPuvv8CwLjp+APu46vhfO2xA8Aj7s8bi7afEdtgE4BN7jzvBfAYnFFrPwbwqpRjeom7rZ+72/2wO701pq4fCwAr4CRVx7VM63o7hXxtjgP4Ysuy7wDwa/fn7ab7X0tcmXj/9Ot7Xdx+4GNrKJYvu6+3HXCSw5NM9x3+hPthxXwiIiIiA4r6dSQRERFRpjEJIyIiIjKASRgRERGRAUzCiIiIiAxgEkZERERkAJOwnBGRt4iIisgZpmOh3uP2vU+1PP6AiHwsoXXfIiKXJLEuoiBE5MMi8ph7259HRORfiMi1IrIiwrreJiInpxEnFReTsPzZAOCHcAooEnXbMQD/rouV5wMRkZLpGChfROSVAN4E4BxVPQvA6+HcM/NaODXowqyrBOBtAJiEUShMwnLEvZ/geXCK9F3mTrNE5Avuf3PfEJF7m2cTRGRMRL7v3vj2O23VlYmiqAO4CcC/b3+i/UyWiEy7v893++GdIvKEiFwvIn8hIj8VkV+IyEtbVvN6EfmBO9+b3OVLIvJJEfmZe8bi3S3r/a6I3A6nYCVRGCcBeE5VjwGAqj4H4BI4idR3ReS7ACAiN4rIhPse+1+aC4vIbhH5iIj8EM4/x+MAvuKeUevv+t5QLpVNB0ChvBnAt1X1CRE5ICLnwKkovRbAPwMwAuBxADe79x/8LICLVHVKRP4cwN/CqdBNFMfnAewQkU+EWOYVAF4O4ACAJ+FUjT9XRN4P4H1wzj4ATl/+V3BuSvxdEXkZgCvg3Abpj0RkGYAfich97vznAjhTVf8p7k5Rz7kPwEdE5AkADwD4qqreICL/AcBr3aQMcKr0H3DPdj0oImep6g73uRdU9dUAICLvAvABVZ3o9o5QfjEJy5cNAD7j/r3NfdwH4O/VuYHrs83/3gCsA3AmgPvd2+eV4NzygigWVX1eRLYC+CsAMwEX+5m695IUkd/A+QAEnDNYr22Z7063L/9KRJ4EcAac+wWe1XKW7TgApwOoAfgpEzCKQlWnRWQMwL+E0we/KiLXecx6qYhcDefz8iQA6+HcJggAvtqVYKmwmITlhIisAvCvAZwpIgonqVIAd/stAuAxVX1ll0Kk3vIZAA8D+J8t0+pwL3Fwb5xdaXnuWMvfdstjGwvfh9rvo6Zw+vL7VHXBza1F5HwAR6KFTwSoagPA9wB8T0R+gfkbcwMAROTFAD4A4I9U9aCI3AJgecss7H8UC68Jy49LAGxV1dNUda2qngrgnwA8B+Bi99qwUQDnu/PvAlB1Lz6FiPSJyB+aCJyKR1UPALgTzvWJTbsBjLl/XwTnLG1Yf+b25ZfC+ap9F4DvAHiP+xU7ROQPRGQgauxEACAi60Tk9JZJZwN4CsBhACvdaS+Ck2j93n1/vXCJVbYuRxQIz4TlxwYA17dNuwvOdTZ7ATwK4AkAP4Fz/UzN/frmBhE5Ds6x/gyAx7oXMhXcpwC8t+XxFgD3iMhPATyIaGcJdgH4PoBRAJtU9QUR+SKca8Ueds+wTcG5PpIojkEAnxWRIThncX8N4Go477XfEpFnVPW1IvKPcN43nwTwoyXWdwuAzSIyA+CVqhr0q3rqYaLafvaf8kZEBt3rG1YB+CmA81T1WdNxERERkT+eCSuGb7j/zVUA/A0TMCIiouzjmTAiIiIiA3hhPhEREZEBTMKIiIiIDGASRkRERGQAkzAiIiIiA5iEERERERnAJIyIiIjIgP8PzoYHW1OUVSwAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 614.125x540 with 12 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.pairplot(df,hue='Kyphosis',diag_kind='hist')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df.drop('Kyphosis', axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = df['Kyphosis']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "dtree = DecisionTreeClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,\n",
       "            max_features=None, max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, presort=False, random_state=None,\n",
       "            splitter='best')"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dtree.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict = dtree.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report,confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[18  2]\n",
      " [ 3  2]]\n",
      "\n",
      "\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "     absent       0.86      0.90      0.88        20\n",
      "    present       0.50      0.40      0.44         5\n",
      "\n",
      "avg / total       0.79      0.80      0.79        25\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(confusion_matrix(y_test,predict))\n",
    "print('\\n')\n",
    "print(classification_report(y_test,predict))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/paschal/anaconda3/lib/python3.7/site-packages/sklearn/ensemble/weight_boosting.py:29: DeprecationWarning: numpy.core.umath_tests is an internal NumPy module and should not be imported. It will be removed in a future NumPy release.\n",
      "  from numpy.core.umath_tests import inner1d\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "rfc = RandomForestClassifier(n_estimators=200)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, n_estimators=200, n_jobs=1,\n",
       "            oob_score=False, random_state=None, verbose=0,\n",
       "            warm_start=False)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rfc.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "rfc_pred = rfc.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[19  1]\n",
      " [ 4  1]]\n",
      "\n",
      "\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "     absent       0.83      0.95      0.88        20\n",
      "    present       0.50      0.20      0.29         5\n",
      "\n",
      "avg / total       0.76      0.80      0.76        25\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(confusion_matrix(y_test,rfc_pred))\n",
    "print('\\n')\n",
    "print(classification_report(y_test,rfc_pred))"
   ]
  }
 ],
 "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}