Skip to content
Snippets Groups Projects
07_regression.ipynb 429 KiB
Newer Older
  • Learn to ignore specific revisions
  • {
     "cells": [
      {
       "cell_type": "code",
    
       "execution_count": 1,
    
       "metadata": {},
       "outputs": [
        {
         "data": {
          "text/html": [
           "<style>\n",
           "    \n",
           "    @import url('http://fonts.googleapis.com/css?family=Source+Code+Pro');\n",
           "    \n",
           "    @import url('http://fonts.googleapis.com/css?family=Kameron');\n",
           "    @import url('http://fonts.googleapis.com/css?family=Crimson+Text');\n",
           "    \n",
           "    @import url('http://fonts.googleapis.com/css?family=Lato');\n",
           "    @import url('http://fonts.googleapis.com/css?family=Source+Sans+Pro');\n",
           "    \n",
           "    @import url('http://fonts.googleapis.com/css?family=Lora'); \n",
           "\n",
           "    \n",
           "    body {\n",
           "        font-family: 'Lora', Consolas, sans-serif;\n",
           "       \n",
           "        -webkit-print-color-adjust: exact important !;\n",
           "        \n",
           "      \n",
           "       \n",
           "    }\n",
           "    \n",
           "    .alert-block {\n",
           "        width: 95%;\n",
           "        margin: auto;\n",
           "    }\n",
           "    \n",
           "    .rendered_html code\n",
           "    {\n",
           "        color: black;\n",
           "        background: #eaf0ff;\n",
           "        background: #f5f5f5; \n",
           "        padding: 1pt;\n",
           "        font-family:  'Source Code Pro', Consolas, monocco, monospace;\n",
           "    }\n",
           "    \n",
           "    p {\n",
           "      line-height: 140%;\n",
           "    }\n",
           "    \n",
           "    strong code {\n",
           "        background: red;\n",
           "    }\n",
           "    \n",
           "    .rendered_html strong code\n",
           "    {\n",
           "        background: #f5f5f5;\n",
           "    }\n",
           "    \n",
           "    .CodeMirror pre {\n",
           "    font-family: 'Source Code Pro', monocco, Consolas, monocco, monospace;\n",
           "    }\n",
           "    \n",
           "    .cm-s-ipython span.cm-keyword {\n",
           "        font-weight: normal;\n",
           "     }\n",
           "     \n",
           "     strong {\n",
           "         background: #f5f5f5;\n",
           "         margin-top: 4pt;\n",
           "         margin-bottom: 4pt;\n",
           "         padding: 2pt;\n",
           "         border: 0.5px solid #a0a0a0;\n",
           "         font-weight: bold;\n",
           "         color: darkred;\n",
           "     }\n",
           "     \n",
           "    \n",
           "    div #notebook {\n",
           "        # font-size: 10pt; \n",
           "        line-height: 145%;\n",
           "        }\n",
           "        \n",
           "    li {\n",
           "        line-height: 145%;\n",
           "    }\n",
           "\n",
           "    div.output_area pre {\n",
           "        background: #fff9d8 !important;\n",
           "        padding: 5pt;\n",
           "       \n",
           "       -webkit-print-color-adjust: exact; \n",
           "        \n",
           "    }\n",
           " \n",
           "    \n",
           " \n",
           "    h1, h2, h3, h4 {\n",
           "        font-family: Kameron, arial;\n",
           "\n",
           "\n",
           "    }\n",
           "    \n",
           "    div#maintoolbar {display: none !important;}\n",
    
    schmittu's avatar
    schmittu committed
           "</style>\n",
           "    <script>\n",
           "IPython.OutputArea.prototype._should_scroll = function(lines) {\n",
           "        return false;\n",
           "}\n",
           "    </script>\n"
    
          ],
          "text/plain": [
           "<IPython.core.display.HTML object>"
          ]
         },
    
         "execution_count": 1,
    
         "metadata": {},
         "output_type": "execute_result"
        }
       ],
       "source": [
    
    schmittu's avatar
    schmittu committed
        "# IGNORE THIS CELL WHICH CUSTOMIZES LAYOUT AND STYLING OF THE NOTEBOOK !\n",
        "import matplotlib.pyplot as plt\n",
        "%matplotlib inline\n",
        "%config InlineBackend.figure_format = 'retina'\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore', category=FutureWarning)\n",
    
    schmittu's avatar
    schmittu committed
        "warnings.filterwarnings('ignore', category=DeprecationWarning)\n",
    
    schmittu's avatar
    schmittu committed
        "warnings.filterwarnings = lambda *a, **kw: None\n",
    
        "from IPython.core.display import HTML; HTML(open(\"custom.html\", \"r\").read())"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "# Chapter 7: Regression\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "Regression belongs like classification to the field of supervised learning. \n",
        "\n",
    
        "<div class=\"alert alert-block alert-warning\">\n",
    
    schmittu's avatar
    schmittu committed
        "<i class=\"fa fa-info-circle\"></i>&nbsp; \n",
        "<strong>Regression predicts numerical values</strong> \n",
        "in contrast to classification which predicts categories.\n",
        "</div>\n",
        "\n",
    
        "<img src=\"./images/30416v.jpg\" title=\"made at imgflip.com\" width=35%/>\n",
    
    schmittu's avatar
    schmittu committed
        "\n",
    
    schmittu's avatar
    schmittu committed
        "<div class=\"alert alert-block alert-warning\">\n",
        "<i class=\"fa fa-info-circle\"></i>&nbsp; \n",
        "    Other differences are:\n",
    
        "\n",
        "* Accuracy is measured differently\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "\n",
    
    schmittu's avatar
    schmittu committed
        "* Other algorithms\n",
        "</div>"
    
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "## Example: Salmon weight\n",
        "\n",
        "The dataset `salmon.csv` holds measurements of `circumference`, `length` and `weight` for  `atlantic` and `sockeye` salmons.\n",
        "\n",
        "Our goal is to predict `weight` based on the other three features."
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 2,
    
       "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>circumference</th>\n",
           "      <th>length</th>\n",
           "      <th>kind</th>\n",
           "      <th>weight</th>\n",
           "    </tr>\n",
           "  </thead>\n",
           "  <tbody>\n",
           "    <tr>\n",
           "      <th>0</th>\n",
           "      <td>25.5</td>\n",
           "      <td>85.5</td>\n",
           "      <td>atlantic</td>\n",
           "      <td>31.2</td>\n",
           "    </tr>\n",
           "    <tr>\n",
           "      <th>1</th>\n",
           "      <td>22.5</td>\n",
           "      <td>62.5</td>\n",
           "      <td>atlantic</td>\n",
           "      <td>12.4</td>\n",
           "    </tr>\n",
           "    <tr>\n",
           "      <th>2</th>\n",
           "      <td>29.0</td>\n",
           "      <td>88.0</td>\n",
           "      <td>atlantic</td>\n",
           "      <td>34.8</td>\n",
           "    </tr>\n",
           "    <tr>\n",
           "      <th>3</th>\n",
           "      <td>32.5</td>\n",
           "      <td>85.5</td>\n",
           "      <td>atlantic</td>\n",
           "      <td>62.7</td>\n",
           "    </tr>\n",
           "    <tr>\n",
           "      <th>4</th>\n",
           "      <td>24.5</td>\n",
           "      <td>74.5</td>\n",
           "      <td>atlantic</td>\n",
           "      <td>24.2</td>\n",
           "    </tr>\n",
           "  </tbody>\n",
           "</table>\n",
           "</div>"
          ],
          "text/plain": [
           "   circumference  length      kind  weight\n",
           "0           25.5    85.5  atlantic    31.2\n",
           "1           22.5    62.5  atlantic    12.4\n",
           "2           29.0    88.0  atlantic    34.8\n",
           "3           32.5    85.5  atlantic    62.7\n",
           "4           24.5    74.5  atlantic    24.2"
          ]
         },
    
         "execution_count": 2,
    
         "metadata": {},
         "output_type": "execute_result"
        }
       ],
       "source": [
        "import pandas as pd\n",
        "\n",
        "df = pd.read_csv(\"salmon.csv\")\n",
        "df.head()"
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 3,
    
       "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>circumference</th>\n",
           "      <th>length</th>\n",
           "      <th>kind</th>\n",
           "      <th>weight</th>\n",
           "    </tr>\n",
           "  </thead>\n",
           "  <tbody>\n",
           "    <tr>\n",
           "      <th>95</th>\n",
           "      <td>19.0</td>\n",
           "      <td>69.5</td>\n",
           "      <td>sockeye</td>\n",
           "      <td>18.8</td>\n",
           "    </tr>\n",
           "    <tr>\n",
           "      <th>96</th>\n",
           "      <td>18.5</td>\n",
           "      <td>67.0</td>\n",
           "      <td>sockeye</td>\n",
           "      <td>18.9</td>\n",
           "    </tr>\n",
           "    <tr>\n",
           "      <th>97</th>\n",
           "      <td>24.5</td>\n",
           "      <td>67.5</td>\n",
           "      <td>sockeye</td>\n",
           "      <td>24.7</td>\n",
           "    </tr>\n",
           "    <tr>\n",
           "      <th>98</th>\n",
           "      <td>21.0</td>\n",
           "      <td>66.5</td>\n",
           "      <td>sockeye</td>\n",
           "      <td>26.0</td>\n",
           "    </tr>\n",
           "    <tr>\n",
           "      <th>99</th>\n",
           "      <td>27.5</td>\n",
           "      <td>86.5</td>\n",
           "      <td>sockeye</td>\n",
           "      <td>43.4</td>\n",
           "    </tr>\n",
           "  </tbody>\n",
           "</table>\n",
           "</div>"
          ],
          "text/plain": [
           "    circumference  length     kind  weight\n",
           "95           19.0    69.5  sockeye    18.8\n",
           "96           18.5    67.0  sockeye    18.9\n",
           "97           24.5    67.5  sockeye    24.7\n",
           "98           21.0    66.5  sockeye    26.0\n",
           "99           27.5    86.5  sockeye    43.4"
          ]
         },
    
         "execution_count": 3,
    
         "metadata": {},
         "output_type": "execute_result"
        }
       ],
       "source": [
        "df.tail()"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "Let us inspect the features and their distributions:"
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 4,
    
       "metadata": {},
       "outputs": [
        {
         "data": {
          "image/png": "iVBORw0KGgoAAAANSUhEUgAABMgAAAQdCAYAAACrPXSTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAWJQAAFiUBSVIk8AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzs3X94U+X9P/5nTmjTpi1r+ovS2kC1TadYqNhi8f0eIKiz+mVOpggiKhtlDpxMRBzjjV1FnDo+7yGDbYKbbqg4dTh089d7LQUvoNBaC0WgpVBJy4/+gCBN05b2nPP9oyb0R5ImbZKTNs/HdXldJrlzn/vk8jzxfnGf+6hkWZZBREREREREREQUoASlB0BERERERERERKQkFsiIiIiIiIiIiCigsUBGREREREREREQBjQUyIiIiIiIiIiIKaCyQERERERERERFRQGOBjIiIiIiIiIiIAhoLZEREREREREREFNBYICMiIiIiIiIiooDGAhkREREREREREQU0FsiIiIiIiIiIiCigsUBGREREREREREQBjQUyIiIiIiIiIiIKaCyQERERERERERFRQGOBjIiIiIiIiIiIAhoLZEREREREREREFNBYICMiIiIiIiIiooDGAhkREREREREREQU0FsiIiIiIiIiIiCigjVB6ANTT2rVrcezYMXz3u9/FqlWrlB4OEdGQwOwkInIfs5OIiOgKFsj8zLFjx3DgwAGlh0FENKQwO4mI3MfsJCIiuoK3WBIRERERERERUUBjgYyIiIiIiIiIiAIaC2RERERERERERBTQAm4PMlEU8eabb+K9995DTU0NQkNDcf311+Ohhx7CtGnTerQ9e/Zsn/e6mzhxIrZt2+bdARMRERERERERkVcFXIFs5cqV2LFjB8LDwzF58mR0dHTgwIED2LNnDx5//HEsWbLE1vbIkSMAgLS0NBgMhj59JScn+2zcRERERERERETkHQFVIPvoo4+wY8cOJCcn44033kBMTAwA4Pjx45g7dy42btyIu+66C2PHjgUAHD16FACwcOFC/OAHP1Bq2ERERERERERE5EUBtQfZBx98AABYvny5rTgGAKmpqZg5cyYkScKePXts71tXkI0bN863AyUiIiIiIiIiIp8JqBVkGzZswNdff21bIdZdS0sLAECtVtveO3r0KLRaLW+lJCIiIiIiIiIaxgKqQBYcHGx3L7GdO3fik08+gVarxa233goAuHjxIs6cOYNx48bhtddew44dO3Dq1ClERETglltuwWOPPYZRo0b5+hSIiIiIiIiIiMjDAqpA1l1bWxtWrFiB6upqnDhxAgkJCXjppZdst15a9x/76quvUFVVhaysLMTHx6OiogLvvPMOdu7cib/97W+4+uqr+z3W9u3b8f7777s0LutxiYgCHbOTiMh9zE4iIqKBCdgC2ZkzZ/Dpp5/2eK+yshJZWVkAruw/ZjAY8Ic//AFJSUkAAIvFgtWrV+Nf//oXli9fju3bt/d7rNOnT+PAgQMePgMiouGN2UlE5D5mJxER0cAEbIEsPj4excXFEAQBe/fuxdq1a7FmzRpYLBYsWrQIjzzyCG6//XaEhYUhKirK9j2tVovnnnsOJSUl+Oqrr1BeXo6MjAynx0pMTMSkSZNcGtfRo0fR3Nw8qHMjIhoOmJ1EniFKEtSC4PA1DS/MTqKhgdlM5H9UsizLSg/CH5SXl2POnDkICwvD3r17odFonLZfsWIFduzYgWeeeQbz5s3z2Djmz5+PAwcOYNKkSdi6davH+iUiGs6YnUR9iZIMtaBCeVUDCkpqYWpuhy5CgxlZScgwxNk+p8DF7CTyPWYzkf8K2BVkvWVkZECv1+PUqVOora1FSkqK0/bWvcpaW1t9MTwiIiIil4mSDEtbB/K3FKPSaOrxWVFZHdL0OuTlZkMbEsSJGBGRjzCbifxbwKzhlGUZL730Ep544gl0dnbabRMcHAwA6OzsxMaNG/H444+jsrLSbtu6ujoAXbdqEhEREfkTtaCyOwGzqjSakL+lmBMwIiIfYjYT+beAKZCpVCoUFBTgo48+wp49e/p8Xltbi5qaGmi1WiQnJ6OyshKffvopPv744z5tz58/jz179iAoKAg33XSTL4ZPRERE5BJRklBe1eBwAmZVaTShvKoRosTdNoiIvI3ZTOT/AqZABgCzZ88GADz33HM4d+6c7f36+nosW7YMnZ2deOCBB6DRaHD//fcDAF577TV88cUXtrYtLS341a9+BbPZjHvvvRexsbG+PQkiIiIiJ9SCgIKSWpfaFpYauVKBiMgHmM1E/i+g9iB76KGHsH//fuzatQs5OTmYOHEiRFHEwYMHYbFYMHXqVCxduhQA8N///d9YsGABXnvtNTz44IOYOHEidDodSktLYTKZkJmZiaefflrhMyIiIiLqy9Tc7tF2REQ0eMxmIv8WUAWyoKAg/PGPf8Rbb72F7du3o6SkBIIgwGAwYNasWZg9ezaEbo/W/eUvf4kJEybgjTfewJEjRyBJEvR6PRYuXIiHH34YQUFBCp4NERERkX26COdP43a3HRERDR6zmci/BVSBDADUajXmz5+P+fPnu9Q+JycHOTk5Xh4VERERkWeIkoQZWUkoKqvrt+30TD1ESfb7W3lESYK6219i9n7tahsiot58lR3+ms3MTqIrAq5ARkRERDScqQUBGYY4pOl1TjeDTtPrkGHw771UrRPEiuomFJTUwtTcDl2EBjOykpBhiLNtYt1fG38vABKR77mSL57MDn/LZl+fP9FQwAIZERER0TAjSjLycrORv6XY7kQsTa9DXm62X0+AREmGpa3D7jkUldXZziFUMwLPvLIPX1Y1OmyjDQny2/MkIt9zNV88nR3+ks1KnT+Rv2OBjIiIiGiYUQsqaEOCsG7pFJRXNaKw1GhbHTA9U48MQ6xfF8eArnNwNIkEgEqjCflbirFu6RSkJun6FMh6tyEisnInXzx9XH/IZqXOn8jfsUBGRERENAxZJ1jpKdE9btfpfluivxIlCRXVTU5vQwK6JnFfVjXgjslj8N7O45C+PbfebcqrGpGeEuPX50xEvuFOvngjO5TOZqXPn8ifcfc9IiIiomGs92bLQ2GioxYEFJTUutR2Z2ktYnVa6EdFOGxTWGocEudNRN7nTr54MzuUymZ/OX8if8QCGRERERH5HVNzu1vttCGOb4xwtS8iCgzu5stwE+jnT+QIC2REREREQ5QoSU5f+6oPb/Sli9C41c7S1jnovojIMzyZBd7gbr74gi/z3B/Pn8gfcA8yIiIioiHGuolzRXUTCkpqbZs8z8hKQoYhzqVNnj3Rhzf66upPwoysJBSV1fXb9pbMJDSaLDDWNztsMz1T7/cPJSAaDjydBd4Zo+v54ovs8HWe+9v5E/kTFsiIiIiIhhBRkmFp67D7BLKisjqk6XXIy82GNiTI4aTGE314oy8rtSAgwxCHNL3O6UbSaXodbjDEYetHR+1u0G9t030jbCLyDm9kgTe4ky/ezg4l8tyfzp/I3/AWSyIiIqIhRC2o7E6ErCqNJuRvKXY6AfVEH97oqztRkpGXm400vc7u59ZJX6coocrBsa1tRAfFMyLyHG9lgTe4mi/ezg6l8txfzp/I33AFGREREdEQIUoSKqqbnP6tP9A1ISqvakR6SkyfiZUn+vBGX72pBRW0IUFYt3QKyqsaUVhqtN02ND1TjwxDrG3ytubRm5228YcJOdFw5s0s8AZX88W7t1Yql+f+cP5E/ogFMiIiIqIhQi0IKCipdaltYanR7u0xnujDG33Z779rcpaeEt3ju9bCWPfJmyttiMg7vJ0F3uBOvnjn+MrmudLnT+SPeIslERER0RBiam4fdDtP9OGNvhxRC0Kv130nbq60ISLv8UUWeIOS2eEPec7sJLqCBTIiIiKiIUQXoRl0O0/04Y2+iGjoYha4z9/ynCjQsUBGRERENESIkoQZWUkutZ2eqbe7wfJg+xAlyaPjIaKhbzhnQffMs/d6MP0qnedE1BP3ICMiIiIaItSCgAxDHNL0OqebMqfpdQ73+BloH9YNmyuqm1BQUgtTczvumDwG/z0hcVDjIaKhzxPZ5G/sZZ4uQoMZWUnIMMQNehN7JfOciOzjCjIiIiKiIUSUZOTlZiNNr7P7eZpeh7zcbKcrBdztQ5RkWNo6sPzl3Vj9yj4UldXh4PFG/OG9gzh3vgWrf3LToMZDREOfJ7LJXzjKvKKyOqx+ZR+Wv7wblraOQZ+LEnlORI5xBRkRERHREKIWVNCGBGHd0ikor2pEYanRtrJheqYeGYbYflc2uNuHWlAhf0txnxUKzZYOPLN5H55dNHlQ4yGioc8T2eQvHGWeVaXRhPwtxVi3dMqgj+PrPCcix1ggIyIiIhpirBOd9JToPrdBdv/cE32IkoSK6iaHE8WzTS1Ytn4XciYn475bUwc8HiIa+jyRTUrrL/OsKo0mlFc1Ij0lZpC3Wvouz4nIOd5iSURERDREqQWh12v3J0H99aEWBBSU1Drto9nSgXcKqvDHfxwc9HiIaOjzRDYpxZXMsyosNXrs3HyR50TkHAtkREREROSUqbndpXYXLrnWjojIn7maea62I6KhgQUyIiIiIgWIkuT0tT/RRWg82o6IyF/Yy15mHlFg4h5kRERERD5k3Sy5oroJBSW1ts2UZ2QlIcMQ53ebKYuShBlZSSgqq+u37fRMvd+Nn4jIHntZHDVSgyX3TmDmEQUoFsiIiIiIfESUZFjaOuw+Ha2orA5peh3ycrOhDQnymwmXWhCQYYhDml7ndNPqNL2ux+bQRET+ylkWx+q0mJ9zLTOPKADxFksiIiIiH1ELKrsTMqtKown5W4r9pjhmJUoy8nKzkabX2f3cWtizPjGNiMifOcvij/fW4Nz5Fqz+yU3MPKIAwxVkRERERD4gShIqqpucrkgAuopk5VWNSE+J8ZtCmVpQQRsShHVLp6C8qhGFpUbbraHTM/XIMMTyNiMiGhL6y+JmSwee2bwPzy6azMwjCjAskBERERH5gFoQUFBS61LbwlKj3926Y50IpqdE9xibdQUFJ4pENBS4ksVnm1qwbP0uLL53Aianj2bmEQUI3mJJRERE5CMjw4IxdvRICP1MrEzN7T4akfvUgtDrNSeJRDS0uJKxzZYOfFp8iplHFEC4goyIiIjIy0RJgloQkPvDdABA48VWfLLva3y8twbNlo4+7XURGh+P0Lesv4ej10QUWHydCa5mbH/tmGVEwwsLZEREREReYt2jpqK6CQUltd32sEnC/JxrcdskPZ7ZvA9nm1p6fG96pn5Y7m/j6PeYkZWEDEPcsDxnInJMiUwQJQkzspJQVFbXb1tHWcwsIxqeWCAjIiIi8gJRkmFp67D7pLSisjqk6XVY/ZOb8OyiyVi2fpdtJVmaXud3+495giu/R15uNrQhQZxYEgUApTJBLQjIMMQhTa9z+tAUR1nMLCMavrj+k4iIiMgL1ILK7gTKqtJowpo/70d8dBhyJicDgG1iZd0Eejhx5ffI31LMCSVRgFAyE0RJRl5uNtL0OrufO8tiZhnR8MUVZEREREQeJkoSKqqbnK5OALomUl9WNeAHU65GekoMMgyxw/LWHHd+j/KqRqSnxAy734CIrlA6E9SCCtqQIKxbOgXlVY0oLDV2uwVe7zCLlR43EXkXC2REREREHqYWBBSU1LrUdmdpLW54IA7pKTHffnf4Tabc+T0KS43D8hZTIrrCHzLBmrXpKdE9+reuGrOXxf4wbiLyHt5iSUREROQFpuZ2t9oNx8JYd+7+HkQ0vPlLJvR+6mR/Wewv4yYiz2OBjIiIiMgLdBEaj7Yb6vh7EFF3QzUThuq4iah/LJAREREROSFKktPXjr4zIyvJpf6nZ+q9sin/QMbtLf7wexCRdwzVjByIoTpuInIN9yAjIiIissO6QXNFdRMKSmptGzjPyEpChiHO6Wb6akFAhiEOaXqd082c0/Q6j+9RM5hxe4uSvwcReYcvM1Lyk0ITs4xoeGOBjIiIiKgXUZJhaetA/pbiPpOgorI6pOl1yMvNhjYkyOEEUJRk5OVm2+0DgK0PTxasPDFub1Hi9yAi7/BVRq7+yU1outgKTbBakdyyh1lGNHyxQEZERETUi1pQOZz8AECl0YT8LcVYt3SK0z60IUFYt3QKyqsaUVhqtK2wmJ6pR4Yh1uMTKE+M21uU+D2IyDs8nZFfVjVgZ+mVVWi3ZCbhBkMczp1vwTOb92GkNliR3LKHWUY0fLFARkRERNSNKEmoqG5yevsM0DUBLK9qRHpKjJPbiLreT0+J7nG7jXVfGk9OoDw5bm/x5e9BRN7h2ayRcbapBVfFhmPZAzfa3m00WbD1o6P4aG8NzK0dOIsWxXLLHmYZ0fDEAhkRERFRN2pBQEFJrUttC0uNLu0zoxaEXq89P3nyxri9xRe/BxF5hyezRi0IeOvTSuwuPw39qAhoQ0bA0tYJY31zn33HlM4te5hlRMMLC2REREREvZia2z3azleG6riJaGjxZNaYmtshSTK+PnvJI8ckIhooof8mRERERIFFF6HxaDtfUWrcoiQ5fU1Ew4sns8ZXucWcIqL+cAUZERERUTeiJGFGVhKKyur6bTs9U+83mzErMW5rHxXVTSgoubLB9oysJGQY4vzmtyEiz/Fk1vgit5hTROQqFsiIiIiIulELAjIMcUjT65xuQp2m1/nVfji+HrcoybC0ddh9kl1RWR3S9Drk5WZDGxLEySfRMOLJrPF2bjGniMgdvMWSiIiIqBdRkpGXm400vc7u59ZJldhrE2ml+XLcakFld9JpVWk0IX9LMSedRMOQJ7PGm7nFnCIid3AFGREREVEvakEFbUgQ1i2dgvKqRhSWGm235UzP1CPDEOuXt+X4atyiJKGiusnpig+ga/JZXtWI9JQYv/utiGjgPJk13sot5hQRucsvC2QtLS0ICwtTehhEREQUwKwTpfSU6B639lhXMfjrRMoX41YLAgpKal1qW1hq9KtbUYnIMzyZNd7ILeYUEbnLL26xPHfuHF544QXceeedGDduHLKysgAA9fX1ePDBB1FYWKjwCImIiChQqQWh12v/LIz15u1xm5rbPdqOiIYmT2aNp3OLOUVE7lB8Bdnnn3+OZcuWwWw2Q5a7/oZApeoKwrq6OpSWluKLL77AkiVL8Nhjjyk5VCIiIiL6li5C49F2RESexpwiIncouoLMaDTi8ccfR3NzM+644w5s3LgR1113ne3zsWPH4p577oEsy9i0aROKioqUGywRERHRAImS5PT1UCNKEmZkJbnUdnqm3u8eZkDkj4ZbTiiNOUVE7lJ0Bdkrr7yC1tZW/OIXv8Cjjz4KAPjLX/5i+zw6Ohq/+c1vcM0112DdunV46623MG3aNIVGS0REROQe68bSFdVNKCiptW08PSMrCRmGOL/c6N8VakFAhiEOaXqd0w2w0/Q67utD1I/hmhNKY04RkbsULZDt2bMH3/nOd5Cbm+u03YIFC/Dqq6/i0KFDPhoZERER0eCIkgxLWwfytxT3mZwVldUhTa9DXm42tCFBQ3LyK0oy8nKz7Z4fANv5cXJP5NhwzwmlMaeIyB2KFsjOnz+PtLQ0qNVqp+3UajWuuuoqHDt2zEcjIyIiIhoctaByOCkDgEqjCflbirFu6RQfj8wz1IIK2pAgrFs6BeVVjSgsNdpWvkzP1CPDEMtJJ1E/hntOKI05RUTuULRANnLkSJw5c8altvX19YiMjPTyiIiIiIgGT5QkVFQ3Ob2tB+ia/JZXNSI9JWZITtCsY05Pie5xi5J1L5+heE5EvhIoOaE05hQRuUrRTfozMjJgMpnwySefOG330UcfobGxERMmTPDRyIiIiIgGTi0IKCipdaltYalxyE/Q1ILQ6/XQPh8iXwi0nFAac4qI+qNogeyRRx6BLMtYvXo1/vnPf6K9vb3H552dnXjvvfewatUqqFQqzJs3b9DHFEURf/vb3/CDH/wA6enpmDRpEn784x87fEJmTU0Nli1bhqlTp2LChAmYOXMmtm7dColPlSEiIiInTM3t/Tdyox0RDT/MCSIi/6HoLZZZWVl4/PHHsWHDBqxcudJWCAOAmTNnoq6uDm1tbZBlGQsWLMDNN9886GOuXLkSO3bsQHh4OCZPnoyOjg4cOHAAe/bsweOPP44lS5bY2h47dgzz5s2D2WzGxIkTkZ6ejv379+O5557DwYMHsW7dukGPh4iIiIYnXYTGo+08QZSkHqsoer8mIt/yRk7wOiciGhhFC2QAsHjxYqSkpGDDhg2orq62vX/8+HEAQGJiIhYvXowf/ehHgz7WRx99hB07diA5ORlvvPEGYmJibMeaO3cuNm7ciLvuugtjx46FLMtYsWIFzGYzXnrpJdx9990AgAsXLuCRRx7Bhx9+iNtuuw3f//73Bz0uIiIiGl5EScKMrCQUldX123Z6pt7rm0Rb+6+obkJBSa1tk+oZWUnIMMRxk2oiBXg6J3idExENjuIFMgC4/fbbcfvtt6O2thbV1dUwm80IDQ3F2LFjkZKS4rHjfPDBBwCA5cuX24pjAJCamoqZM2firbfewp49ezB27Fjs2bMHlZWVmDRpkq04BgBRUVH49a9/jblz52Lr1q0skCns5Fr3CqdXr/qHl0ZCRER0hVoQkGGIQ5pe53QD7jS9rsem0d4gSjIsbR12n5RXVFaHNL0OebnZ0IYEcfJM5EOezAle50REg+c3a20bGxuRlJSEW265BTNnzsStt96Kixcv4tixYx47xoYNG/Dhhx9iypS+j0luaWkBAKjVagDA559/DgC49dZb+7SdOHEioqOj8cUXX8BsNntsfERERDR8iJKMvNxspOl1dj+3TlitT1LzFrWgsjtptqo0mpC/pZiTZiIFeConeJ0TEQ2e4ivI6uvrsXLlShw4cAB79+7FyJEjbZ9t2bIFu3fvRnZ2Nn7zm98gPj5+UMcKDg6GwWDo8/7OnTvxySefQKvV2gpi1ts97bUHgOTkZJw/fx4nTpzg0zWJiIioD7WggjYkCOuWTkF5VSMKS422W56mZ+qRYYj1wa2VEiqqm5yuTgG6Js/lVY1IT4nhBJrIhzyRE7zOiYg8Q9ECWWNjI2bPno36+nqMGDECDQ0NPQpko0aNQkhICPbt24f58+dj+/btiIiI8Mix29rasGLFClRXV+PEiRNISEjASy+9ZLv1sqGhAQAQG2t/ObP1/aampn6PtX37drz//vsujevo0aMutSMiGu6YnTQcWCeh6SnRPW6Rsq4G8fYkVS0IKCipdaltYanR67d7kvcxO4eeweYEr3MiIs9QtEC2adMm1NfXIzs7G7/97W/7FKOeffZZLFu2DE8++ST27t2LzZs348knn/TIsc+cOYNPP/20x3uVlZXIysoCALS2tgIAQkJC7H7f+r7FYun3WKdPn8aBAwcGM1wiooDD7KThpPcT5Hy5esPU3O7RduTfmJ1D12Bygtc5EdHgKVog2717N0JDQ7F+/XpERkbabRMZGYnf/va3uOWWW/DZZ595rEAWHx+P4uJiCIKAvXv3Yu3atVizZg0sFgsWLVpk24tMpXL+B5MkSf0eKzExEZMmTXJpXEePHkVzc7NLbYmIhjNmJ5Fn6CI0Hm1H/o3ZGZh4nRMRDZ7it1impqY6LI5ZRUVFITk5GSdOnPDYsbVaLbRaLQAgJycHo0ePxpw5c/DKK6/g4YcfRmhoKICuWzHtsb4fFhbW77FmzZqFWbNmuTSu+fPn82/9iIjA7CTyBFGSMCMrCUVldf22nZ6p9/qeaOR9zM7Aw+uciMgzFH2KZWRkJEwm55tJWpnNZltByxsyMjKg1+thNptRW1uLuLg4AI73GGtsbATgeI8yIiIiIqWpBQEZhjiHT8izStPrkGGI5aSZaAjidU5E5BmKFsiuu+46nDt3Dv/5z3+cttuzZw/q6uowbty4AR9LlmW89NJLeOKJJ9DZ2Wm3TXBwMACgs7MTqampAK48zbJ3XydPnoRarcY111wz4DEREREReZsoycjLzXY4eU7T65CXm23bEJyIhh5e50REg6foLZZz587Frl27sGLFCjz99NO4++67e2yKf/nyZfzrX//CCy+8AJVKhblz5w74WCqVCgUFBfj666/xwx/+EFOnTu3xeW1tLWpqaqDVapGcnIzvfe97ePXVV1FQUIB58+b1aFtWVoYLFy5g0qRJCA8PH/CYiIiIiLxNLaigDQnCuqVTUF7ViMJSI0zN7dBFaDA9U48MQyxvuSIa4nidExENnqIFsmnTpmHu3LnYtm0bfv3rX2PNmjVITExEWFgYLBYLTp8+jc7OTsiyjNmzZ+O2224b1PFmz56Nl156Cc899xzS0tIQHx8PAKivr8eyZcvQ2dmJRx55BBqNBpMmTUJqair27NmDd955B7NnzwYAXLhwAfn5+QCABQsWDO4HICIiIvIB66Q4PSUaGYYr20NYV5Nw0kw09PE6JyIaHEULZACQl5eH9PR0vPLKKzh16hROnTrV4/PRo0dj0aJFg1o9ZvXQQw9h//792LVrF3JycjBx4kSIooiDBw/CYrFg6tSpWLp0KQBAEAQ8//zzePjhh7F69Wq89957iIuLw4EDB/DNN99g9uzZmD59+qDHREREROQrakHo9ZoTZqLhhtc5EdHAKF4gA648befUqVMwGo24ePEiQkNDMXbsWKSkpHjsOEFBQfjjH/+It956C9u3b0dJSQkEQYDBYMCsWbMwe/ZsCN3+QBk/fjzeffddbNiwAfv378fx48cxZswYLFu2DPfdd5/HxkVERERERERERMrxiwKZ1ZgxYzBmzBivHkOtVmP+/PmYP3++S+1TUlKwYcMGr46JiIiInBMlqceqiN6vB9t+KBiO50Q0lHnjmnTWJzOAiMi7/KZA1tLSArPZDEmSIMuOn66SkJDgw1ERERGRkqybSldUN6GgpNa26fSMrCRkGOL6bDrtbvuhYDieE9FQ5o1r0lGfOTePRdqYKGYAEZEPKF4g+89//oP169fjxIkT/bZVqVQ4cuSID0ZFREREShMlGZa2DuRvKUal0dTjs6KyOqTpdcjLzYY2JAhqQeV2+6FgOJ4T0VDmjWvSUZ+gbHxUAAAgAElEQVQR2iA8eMd3YbZcxpo/72cGEBF5maJrcvfu3Yuf//znqK6uhizL/f4jSZKSwyUiIiIfUgsqu5NQq0qjCflbim2TQnfbDwXD8ZyIhjJvXJOO+sy5ORmjosPsFscGczwiIrJP0RVkr776KmRZRlZWFn7xi18gOTkZISEhSg6JiIiI/IAoSaiobnI4KbSqNJpQXtWI9JRoN9vH+P2E0v3fwP/PiWgo88Y16ahPQVDhjslj8WVlAzOAiMhHFF1BdujQIYSFheFPf/oTbrzxRkRFRUGr1Tr9h4iIiIY/tSCgoKTWpbaFpUaoBQEHjze50d7/J5Hu/wb+f05EQ5k3rklHfepHRSA2MhSFpcwAIiJfUbRAJooixo4di7CwMCWHQURERH7I1NzuVrvLHaJH+/UH7v4GRORd3rgm7bXVhozw2vGIiMg+RQtkycnJqKurU3IIRERE5Kd0ERq32gUHqT3arz9w9zcgIu/yxjVpr62lrdNrxyMiIvsULZDNnTsX33zzDd566y0lh0FERER+RpQkzMhKcqnt9Ew9REnChNQYN9rLgxmeT7j/G/j/ORENZd64Jh31aaxvRuPFVkzPZAYQEfmKopv033fffTh06BCef/55VFdXY8qUKRg1ahSCgoIcficlJcWHIyQiIiIlqAUBGYY4pOl1TjeoTtPrkGGIBQC32/u7gfwGROQ93rgmHfUpSTI+2fc15udcywwgIvIRRQtkEydOBNC1F9m2bduwbds2p+1VKhWOHDnii6ER2XVy7Y9cbnv1qn94cSRERMOfKMnIy81G/pZiu5PDNL0OebnZECUZakHldvuhYDieE9FQ5o1r0lGfH++twW2T9Fj9k5uw5s/7mQFERF6maIHMYrG41V6WuWyYiIgoUKgFFbQhQVi3dArKqxpRWGqEqbkduggNpmfqkWGI7TEpdLf9UDAcz4loKPPGNemszwuX2pE2RssMICLyAUULZMeOHVPy8EREROTnrJO+9JToHrcQWffa6T0pdLf9UDAcz4loKPPGNemsT2YAEZFvKLpJPxEREZEr1ILQ67XzCaG77YeC4XhOREOZN65JZ30yA4iIvMuvCmTnz59HaWkpdu7cCQCQJAlms1nhURERERERERER0XCm6C2WVgUFBdi0aROOHj0K4Mpm/HV1dfjhD3+I+++/H08++SRGjPCL4RIREZEfECWpx4oKSZIgo+cqi95tBtLvQPpQsn8iUk7363kw1/pAvstsISIaHMUrThs3bsSmTZsgyzJUKhXUajVEUQQAnD59GhaLBa+//jqqqqqwefNmqNVqhUdMRERESrLuyVNR3YSCkloIggoL/r9xiIzQoLyqAQUltbZNrGdkJSHDEOfSJta9+x1IH0r2T0TKsV6/ladMSIgJR2SEBoeON6Gw1L1rfSA5wWwhIvIMRQtk+/btw8aNGxEeHo7ly5fjzjvvxKOPPoovv/wSAHDTTTfhhRdewJo1a7B3715s27YNDz74oJJDJiIiIgWJkgxLWwfytxSj0mhChDYIv/vFVKhUwPKXd6PSaOrRvqisDml6HfJys6ENCXI6Ke3e70D6cGfcnu6fiJRjvb5/u7UUS+6dMOA8GkhOMFuIiDxH0TW3f/3rX6FSqfDb3/4Wc+bMwciRI3t8LggCfvjDH2L9+vWQZRkffPCBQiMlIiIif6AWVD0mgjk3J2NUdBjW/Hl/n8mhVaXRhPwtxU4nh737HUgf7ozb0/0TkXKs13eqXjeoPBpITjBbiIg8R9ECWXl5OeLj43HLLbc4bfe9730PCQkJqK6u9tHIiIiIyN+IkoTyqgbbRFAQVLhj8lh8WdngcHJoVWk0obyqEaIk99vvQPpwZ9ye7p+IlGO9vo/XXRxUHg0kJ5gtRESepWiBrKWlBTqdzqW2UVFR6Ozs9PKIiIiIyF+pBQEFJbW21/pREYiNDEVhaa2Tb11RWGp0sGqjZ78D6cMZb/dPRMqxXt+DzaOB5ASzhYjIsxTdgywuLg41NTXo7Ox0+oTKy5cvo6amBrGxsT4cHREREfkbU3O77d/DtUF93nP1u719Y27H2NEjoQ0ZAUtbJ4z1zZDsrLZw9VgD/d435oH1T0TKMTW3QxvSNZfRBKtxXXKU0xyxfseV9/r7bn/fEQQV9KMiMDIs2KW+iYgCmaIFsv/6r//Cu+++iz/96U947LHHHLbbtGkTWlpacOedd/pwdERERORvdBEaRGiDkHNzMu76r2Tbe65+15GnHpyIiLAQ2+vzF1vw0T4jPt5bg2ZLh0t9DPTYAGzndM+U5B7vy5IIlcAneBP5s9HRWowZPRKiJOGx+zJs7zdebMUn+77ukyOA/UwYSJY5+o41U+6crEd0ZJjtfXuZ0vs95g4RBSpFC2SLFi3Chx9+iE2bNuH06dO466670NbWBgD45ptvcOLECbz99tv48MMPodFo8OMf/1jJ4RIREZGCRElCzs1j8eAd38Wo6DB8WdmAEWoVpmcmoaisrt/vT8/UQ5TkHrcZyZIElSBAXV+JhooiiOaLUIdHIix9GubnTMDtk5KwenMxzja1OOzDlXHPyHI8xtExYXjup9mIiwqH5eTBHuMIHz8N2uQJtnESkX8RJQk/+cH1CNGMQHlVAwpKamFqbocuQoPpmUmYn3MtbpukxzOb99lyBOibJf3lRHfW7wKy3e90z5SWkwfRsMt+pgCAShDQeuowzIeYO0REihbIrrrqKmzYsAFPPPEE3n//ffzzn/+0fZadnQ0AkGUZGo0GL774IpKTkx11RURERMOcWhCQNiYKZstlLH95NyqNJsy+1YD5OdciTa9zulF1ml6HDEPPrRpkSYLU3oJzb69F+5njPT4zH94NTUIq4mb/CmsWZeOJ9buREBPepw9Xx51hiLM7xghtEJ77aTZ0GgmnX/ulw3HEz1kFQRPGySqR31GhQ5TwP99mUndFZXVI0+uw+ic34dlFk7Fs/S40Wzrs5pGznOiu53dVfb7jSqaEJk9A/P2/gnS51Wn+MXeIKNAonnbf+973sGPHDjzwwAOIj4+HLMu2f3Q6He655x5s374dd9xxh9JDJSIiIoWpBRXW/Hm/bTL48d4anDvfgtU/uQlpevsP/knT65CXm93nCW4qQbA7ObRqP3McDe88j1HR4Zifc63dPlwlSjLycrP7jDHn5mTERYWj4Z3nnY7j3NtrOUkl8kNqQYX8LcUOi1qVRhPW/Hk/4qPDkDM52WEeAY5zwsred3t/x5VM0SSkQKUe0W/+MXeIKNAouoKstrYWSUlJSExMxDPPPINnnnkGLS0tMJvN0Gq1iIiIUHJ4RERE5EdESUJFdVOPiWizpQPPbN6HZxdNxrqlU/BlVQN2lna/xUmPDEOsnVsrRbSeOuxwcmjVfuY4LDWHcEf29ZCgGvBT4NSCCtqQIKxbOgXlVY0oLDXiG3M77pmSDMvJgy6PI3TM9ZywEvkJe5lkT6XRhPKqBtx3ayrm33mtw9u07eVEf1nW+zspiRHOM0UlYOTE22E5Wc7cISLqRdEC2eLFi9Ha2or33nsPkZGRAICwsDCEhYX1800iIiIKNGpBQEFJbZ/3zza1YNn6XciZnIw7Jo/BsgdutH1mXWnRezKqEtQwHypy6bjmQ0XQJo/HYLesto4hPSW6x+1VDRXujYOI/IOjTLKnsLQWGYa4b7/nuNDuKCccZVnv76gFwWmmBMcmYcTIGFzY+aZL42buEFEgUbRAZjQacdVVV9mKY0RERETOmJrb7b7fbOnAOwVVeG/ncehHRWBCagwW3p3udCIqmi+6dEyxxfnqEHepe63EUGocRDR4jjJpoO2seueEK6tXrd9xlimCRttvm+6YO0QUSBRdKzty5EjbUyuJiIiI+qOL0Dj9XJJkfH32Ei61XO63L3W4a39Bpw6zvx+Qp/jLOIjIff1lkrvtPMFZpkjtln7b9OiLuUNEAUTRAtnPfvYznD59Gi+++CJaW1uVHAoRERH5OVGSMCMryaW20zP1TjfUlyUR4eOnudRX+PhpkCWpz/edvXZG7NaXkuMgIteIva4762tPZlJ/HF3r9t53limXG2vReakJ4elTXTquvdwhIhquFL3Fsr29HRkZGXj99dfx5ptvIjU1FbGxsdBo7P8Ni0qlwvr16308SiIiIvIHakFAhiEOaXqd002x0/S6Hnv32KMS1NAmT4AmIdXpRtWahNQe++/IkgSVIKD11GGYDxVBNF+EOjwS4eOnQZs8wfa5PdbNtSuqm1BQ0vUggTsmj8F/T/DtOIjINfauWV2EBjOykpBhiIMKKo9lkiP2rvXgUWOhm3I/VMHqPhkQOWW282yTJVwq+wxR0x5wO3eIiIY7RQtkL774IlQqFWRZxuXLl/HVV185ba9SDezJUYHu5Nofudz26lX/8MgxZz65wyP9AMCH/+9uj/WlhMH8FkP93ImIPE2UZOTlZiN/S7HdCWmaXoe83GyHT4nrTpYkxM9ZhXNvr7U7SdQkpCJ+zirbBFWWJEjtLXbbmw/vtrUXNGF9ilOiJMPS1tFn3CdPX0TqVd9B3P2r0PB374+DiFzj6JoFgKKyOlvWaENGeCyTerN3rQuh4Yi561HIHe04/eav+2SA5UQZrlr4v06zrf1MNWSx0638IyIKBIoWyJYsWcKiFxEREblMLaigDQnCuqVTUF7ViMJSo21Vx/RMPTIMsS5PRFWCAEEThsQFL8BSc6hrFUaLCeow3bcrscb3mByqBMHhZBIA2s8cx7m31yJxwQt2x21vAt1s6cDqzcVYsyjbJ+MgItc4umatKo0m5G8pxrqlUzyWSb3Zu9ZHTvw+giJH4fRrv7SbAVKrGWfeyEPCg/n9Zoo7+UdEFAgULZD9/Oc/V/LwRERENARZJ5rpKdE9bluy7u/jzkTUOvkLHTOuzy2M3T+XJRGtpw47vR0J6CpOWWoOIXTM9bbvipKEiuomhxPts00teGL9buRMTsb9t16LOC+Ng4hc0981a1VpNKG8qhHpKTEAPJNJVnavdZWAkRNvh+VkudMM6DSdRd2ry5DwyIv9ZhvQf/4REQUKph4RERENSepek7eBTEKtVIK612uhz+fmQ0Uu9WU+VNTj+2pBQEFJrdPvNFs68E5BFTb945DXxkFErnHlmrUqLDXassfTmdT7Wg+OTcKIkTEwV+zq9/tSqxkXP3+n32yzHqu/NkREgcAv0s9isWDr1q3Izc3FrbfeiuzsbADAhQsX8PTTT+Po0aMKj5CIiIgCnWi+6Fq7lr6rTkzN7S5998Kl/tsNZhxE5BpXr1lX2w1E72td0Gjtvu/w+8wAIiK3KHqLJQB89dVX+PnPf46zZ89ClruWIVv3JautrcWOHTvw73//G88++yxmzZql5FCJiIgogKnDI11rF6br854uwv4TugfSbjDjICLXePKaHaje17rUbrH7vsPvMwOIiNyi6AqyxsZG5Obm4syZMxg/fjxWrlyJa665xvZ5TEwMbrrpJnR2dmLVqlUoKytTcLREREQUqGRJRPj4aS61DR8/zbaHD9C1n9GMrCSXvjs9U2/bt8jT4yAi13jymh0oe9f65cZadF5qQnj6VJf6YAYQEblH0QLZ5s2bceHCBcybNw9///vf8fDDD+M73/mO7fPExET89a9/xUMPPQRZlvH6668rN1giIiIKWCpBDW3yBGgSUp220ySkQps8vs8eZBmGOKTpna/mSNPrkGGIdbpv0WDGQUSu8eQ1O1B2r3VZwqWyz6C9OoMZQETkBYomZlFREbRaLZ566imn7Z588kmEh4dzBRkREREpRpYkxM9Z5XBiqklIRfycVXZXbIiSjLzcbIcT7jS9Dnm52S6tRBnMOIjINZ68ZgfK3rV+qexTdJjqET97JTOAiMjDFN2DrL6+HgaDASEhIU7baTQajBkzBpWVlT4aGREREVFPKkGAoAlD4oIXYKk5BPOhIogtJqjDdAgfPw3a5PGQJcnuig21oII2JAjrlk5BeVUjCkuNMDW3QxehwfRMPTIMsRAl2aWVKIMZBxG5xpPX7EA5utYvffEJdFPuZwYQEXmYogWy0NBQNDQ0uNTWZDIhPDzcyyMiIiIicsw64QwdMw7a5PG2960rNZxNSK0T6fSUaGQYYm3vW1eguDPRHsw4iMg1nrxmB6q/a50ZQETkOYom5/XXX4/Gxkbs37/fabt9+/bhzJkzGDdunI9GRkREROSYSlD3eu36/1Kpe7UdzCR7MOMgItd48podKEfXOjOAiMhzFE3QuXPnQpZlrFixAiUlJXbb7Nu3D8uXL4dKpcK9997r4xESEREREREREdFwp+gtlrfeeivuu+8+vPvuu3jooYcQHR0Ni8UCAHj00UdRU1MDo9EIWZaRk5ODnJwcJYdLREREXiBKUo8VGr1f+yNZEnus3Oj9moj8i9I5w8wgIvJ/ihbIAGDNmjW4+uqr8corr6Cpqcn2flFREQBAq9XikUcewZIlSxQaIREREXmDdYPriuomFJTU2jbAnpGVhAxDnNc3wB4I68bXracOd22Mbb4IdXjktxtjT+DG2ER+RumcYWYQEQ0dPiuQFRcXIzExEUlJSX0+W7BgAebNm4cvvvgCJ06cgNlsRmhoKMaOHYvMzEyEhYX5aphERETkA6Ikw9LWgfwtxag0mnp8VlRWhzS9Dnm52dCGBPlNkUyWJEjtLTj39lq0nzne4zPz4d3QJKQifs4qCJowTniJ/IDSOcPMICIaWnyWxCtWrMDixYt7vLdx40Zs374dABAcHIzJkyfjwQcfxKOPPoqHH34YU6dOZXGMiIhoGFILKruTVqtKown5W4r9pjgGdG1+bW+ia9V+5jjOvb2WE10iP6F0zjAziIiGFp+lsclkwogRPResbdy4Ef/4xz98NQQiIiLyA6IkobyqweGk1arSaEJ5VSNESfbRyByTJRGWmoMOJ7pW7WeOw1JzCLIk+WhkRGSP0jnDzCAiGnp8doulTqdDVVUV3nvvPWRmZiI4OBgAcPnyZZw5c8blfhISErw1RCIiIvIBtSCgoKTWpbaFpUZkGGK9PKL+qQQ1zIeKXGprPlQEbfJ47w6IiJxSOmeYGUREQ4/PCmS333473njjDaxevdr2nkqlwuHDhzFjxgyX+lCpVDhy5Ii3hkhEREQ+Ympud/iZIKigHxUBbcgIaIL85ylvovmia+1anK9YISLfcJYzA2nnLtF8EVAJCI5NgqDRQmq34HJjLSD3XC3GzCAi8g8+K5A99dRTsFgs+OSTT2CxWAB0Fbxk2fXlzO60JSIiIv+li9D0eS9CG4Scm5Nx52Q9oiOv7EEqSyJUgncKZaIkQd1t/5/er7tTh0e61Kc6TGf7995j7/7anWMTkfvs5cxg2rkrYuJtiJ25BCNGxtje67zUhEtln+FS2aeQWs0AemYG4N3MIyIix3xWINNoNHj++efx/PPP4/Lly+jo6MCNN96IG264AX/+8599NQwiIiJSmChJmJGVhKKyOtt7o2PC8NxPsxEXFY6WkwfRsKsIovki1OGRCB8/DdrkCZAlyWObWYuSDLWgQkV1EwpKamFqbocuQoMZWUnIMMTZPreSJRHh46fBfHh3v32Hj59mm+C2njoM8yH751J5yoSP937d77GJyH32csaR6Zl6j193siQi/NqbYTlZjgs737ySAelTETXtAURMmIGz29ag03QW4eOnQbRcQsM/10Md9h2vZB4REfXPZwWy7oKDgxEcHIyEhASMGjUKWq1WiWEQERGRAtSCgAxDHNL0OlQaTYjQBuG5n2ZDp5Fw+rVf9tnU2nx4NzQJqYifswqCJmzQE0ZRkmFp67D7dLuisjqk6XXIy82GNiTINmFWCWpokydAk5DqdNNtTUIqtMnjIXW048xfVzk8l7j7VyF6pAZfHKtHs6XD6bGJyH29c8aRNL3O4/uPyZIIqd1i9wmWtjybvRKj565G08evQJs8HheK3kJrzcGebTyUeURE5BpFCmRWhYWFSh6enDi59kdutb96lfefRjrzyR22f//w/93t9eMRuav7f6ODxf/GabgTJRl5udnI31KMCYZYxEWF2y2OWbWfOY5zb69F4oIXBn1staCyWxyzqjSakL+lGOuWTunxvixJiJ+zyu6kF4BtQitLEs6984LTc2n4e9e55ExOxjsFVf0em4jc1z1n7F3v1oK0p1ePqQS1w5wAvs2zd36DxAUvYNS9K9BhqselLz7t28ZDmUdERK5RtEBmdenSJVRVVaGlpaXftlOnTvXBiIiIiMib1IIK2pAgrFs6BZcvd8By8qDTlVlA14TRUnMIoWOuH/CKClGSUFHd5HRFCdBVqCqvakR6Sky3VWQCBE0YEhe8AEvNoa5bJ1tMUIfpvr0lajxkSUTb6Uq0fX2o/3M5eRA5k1Pw3s7jkKQr+6zaOzYRua97zpRXNaKw1Gi7pXl6ph4Zhliv3FrZ+vVh1/Ms6VqcfXstpDaz4zaDyDwiInKdogWyzs5O5Ofn4/3334coiv2251MsiYiIhg/rpDQ4OAgXK4pc+o75UBG0yeMHcUwBBSW1LrUtLDX2ufXKOkkNHTOuxzhkSfr2czWayz5zqX9zxS7E3T0B+lER+PrspX6PTUTus+ZMekp0j2tK/LYo7ekitEpQw+xmngkjHE/JBpt5RETkOkULZBs3bsS7774LoGtfssjISIxw8geEJ4iiiG3btuH999/HyZMnIYoikpKScOedd2LhwoXQaK48xaa0tBTz5s1z2NfMmTOxbt06r46XiIgoEIjmi661a3G+8ssVpub2Qbfr/YS57qs73D0XbUjf//dxdYxE5JreT4j15upMdzNA0Djej9kTmUdERK5RtED2wQcfQKVS4emnn8b8+fOhVnv3ccaiKGLx4sUoKiqCVqvFhAkTMGLECBw8eBAbNmzArl278Ne//hWhoaEAYFutdsMNN+Cqq67q09/EiRO9Ol4iIqJAoQ6PdK1dmG7Qx9JFaPpv5Ea73tw9F0tbp8eOTUTK0ySkQBY7ILVbcLmxFpAlu+2sGSC1Wxz25YnMIyIi1yhaIGtsbIRer8cjjzzik+O9++67KCoqQlpaGrZs2YJRo0YBAC5cuIDFixfjyy+/xB/+8Ac8+eSTAICjR48CAJ566inceOONPhkjERGRvxElqcfqi96vB0uWRISPnwbz4d39tg0fPw2yJA1qD7IZWUkoKqvrt+30TH2f/YlkSeyxeszea5fPJX0qmkwtMNY3u3RsIvI9d/NPlkRE3XLlDpTOS024VPYZLpV9Cqm15z5j4elT0flNY1cRzYHBZh4REblO0QJZbGwsBB+G/fvvvw8A+NWvfmUrjgFAVFQUfv3rX+Puu+/Gv//9b1uB7MiRIxAEAddee63PxkhEROQvrAWaiuomFJTU2ja3npGVhAxDnMcKOCpBDW3yBGgSUp1ubK1JSB30XjxqQUCGIQ5pep3TjfrT9Loe+xVZJ6itpw53bc5vvgh1eOS3m/NPsH3u1rlcPQH/+Ohojw367R2biHzP3fxzmBHpUxE17QFETJiBs9vWoNN0FsCVDLhQ9JbDFWaeyDwiInKdogWynJwcvP766zh27Bi++93vev14Op0OV199NcaP7/sHzdixYwEADQ0NAIDLly/jxIkTuPrqq6HVOt4XgIiIaDgSJRmWtg7kbynuU0gqKqtDml6HvNxsaEOCPFIkkyUJ8XNW4dzba+0WljQJqYifs8ojKylESUZebrbdcwNgOzfrBFiWJEjtLXbHZj682zY2QRMGlSC4dC5x969C/XkzPtpb4/TYROR77uafSxkxeyVGz12N06+tQJBuNOLnrIIkdqLttP1Cuiczj4iIXKNogeyxxx7D559/jsceewz5+fm46aabvLpJ/5/+9CeHn1VUVAAA4uPjAQDHjx9HR0cHEhMT8bvf/Q6fffYZTp8+jZiYGHz/+9/Hz372M4wcOdJrYyUiIlKSWlA5LCABQKXRhPwtxVi3dIpHjqcSBAiaMCQueAGWmkNdKzBaTFCH6b5dpTXeYxNFtaCCNiQI65ZOQXlVIwpLjbbVIdMz9cgwxPYoUKkEwWGxCwDazxzHubfXInHBC26dy/n6i8i6bpTTYxOR77mbfy5lxDu/QeKCF5DwyIsIjopHc0sbNKKMhHl5Xs88IiJyjaIFstDQUCxfvhyPPvooFi5cCLVajfDwcKhU9v+nUKVSYe/evR4fhyzLePnllwEAt99+O4ArG/Tv2rULJSUlyMrKQnx8PCoqKvCXv/wFhYWF2LZtG6Kiojw+HiIiIiWJkoSK6iantyACXZPE8qpGpKfEeOhWy66JYOiYcT1uK5IlqcfnnmAdb3pKdI/bGcVvb3e0fi5LIlpPHXZ6uyTQNQG21BxC6Jjrv73Vsv9zSRsTieuSr+xx2vvYROR77ubfhJQoNzNiHAAgIizEds37IvOIiKh/ihbI9uzZg8WLF0OWZciyjM7OTly86PixyI4KZ4P1v//7vygpKUFMTAwWLlwI4MoG/ZMmTcLLL79sK4RduHABy5Ytw759+5CXl4ff//73/fa/fft22/5n/bEel4go0DE7laMWBBSUON40urvCUqPH98vqvul912vvTRJ7b7bduzilEtQwHypyqS/zoaI++wU5O5f+jk00EMzOwXEn/w5VNyLDEDvgjLiyStV3mUdERI4pWiDbtGkTOjs7cd1112Hu3LlISEhAUFCQT8fw8ssvY/PmzQgODsb69etthbCVK1di/vz5iI2NRXh4uK19VFQUXnzxRdxxxx34v//7PzQ0NCAuLs7pMU6fPo0DBw549TyIiIYbZqeyTM3ttn8XBBX0oyKgDRkBS1snjPXNto3lu7cbrkSz47+869GuxfmKEyJfYHYOniZYDUFQ9XmARu8s7OgUATAjiIiGC0ULZMeOHcPIkSOxdetWhIWF+fTYnZ2dePbZZ/H3v/8dGo0Gv//975GVldo1qT4AACAASURBVGX7PCgoCMnJyXa/O2rUKFx33XUoLS3FkSNH+i2QJSYmYtKkSS6N6+jRo2hu7vu4dyKiQMPs9AxRknqsVOr92tF7uggNIrRByLk5GXdO1iM68sqf0+cvtuCjfUZ8vLcGugiNR8bgiz6ckSWxxyqO7q/V4ZEu9aEO03lsPEQDNVyz01MZYK8fFQAVZNs1/9h9GZh7W6ot5wDYzUJLa9dfEDAjiIiGB0ULZEFBQUhMTPR5caylpQVLly7F559/jpEjR+IPf/hDj+KYK2JiYgAAra2t/badNWsWZs2a5VK/8+fP59/6ERGB2TlY1o3eK6qbUFBSa9sIfkZWEjIMcT32u+reJmqkBkvunYCcm8difk4a4qLC0XLyIBp2FUE0X4Q6PBJh6dMwP2cCbp+UhPOXLjvcVN6VMfR3W6En+nDGugl266nDXZtkf3uOXZtkT4AsiQgfPw3mw7v77St8/DRuqk2KG27ZaS1oHapuQmG3DJielYQbDHEuF8rsZUlywkg8eEcaNMFBsNQc7JEB1pzLydZDpQKiI8P6ZGF4+jTIY693OyMA3kZJROSPFC2Q3XDDDSgpKUFLS4vPimTffPMNFixYgK+++gqjR4/G5s2bYTAY+rRbs2YNzp07h2effRbR0dF9Pq+rqwNw5amXRERE/kKUZFjaOuw+ha2orA5peh3ycrMRqhmBZ17Zhy+rGnu0SYyLwOzpKehsa8Hp137ZZ/Np8+Hd0CSkIu7+VYjTRULloDjmyhi0IUEOC1ye6MMZWZIgtbfYffqc9RxHP5gPbfIEaBJSnW7CrUlI7bP/GBENjihJsLR2Iv9VJxmwMBva0BFOi2T2siRCG4THZ4+H0NGK02+udpgB8XNWQRUcirNvPYvWmoN92sTk/BQjJ97uckZ888WnCL/uZgiaMBbJiIj8jKKp/Nhjj6G9vR3/8z//A4vF4vXjXb58GYsWLcJXX32FlJQUvP3223aLYwDw5Zdf4j//+Q8KCwv7fFZVVYWjR48iMjIS48aN8/awiYiI3KIWVHaLSlaVRhPytxRjhFpAalLfW366bjUS0PD3voUjq/Yzx9Hw97UOJ3iujsFZYcsTfTijEgS7xTGr9jPH0XJkL2RJQvz9v4ImIdVuO01CKuLv/5VtZQgReYZaEOwWx6wqjSbkv1rc7woye1mSc3My4qLC0fDO804z4NzbayGoR0CTkGK3zYWiN9F56Tzi56xynhGzV6LDVA9T0Vs497bj7CQiIuUouoKsvr4e99xzD959913s3bsXN954I0aNGoXQ0FC77VUqFZ566qkBH2/Dhg0oLy/H6NGjsXXrVtuG/Pbcf//9eOaZZ/C73/0OEydOxDXXXAOg6ymWK1euhCiKWLhwIYKDgwc8HiIiIk8TJQkV1U0OJ5RWlUYTvqxqwB2Tx+C9ncdtm1ELggozMq9Cy8mDTldDAF2TR0vNIYSOub7HZM+dMZRXNSI9JaZPkcsTfTgjSyJaTx12fo4qAaHJ6Wirq8SIiCgkLngBlpMHYa7YBbHFBHWYDuHpU6G9egI6TPW4fP4MQhINnPgSeYAoSTjkVgZE2y2U2csSQVDhzsl613Pu5EGMvOE2XNz7PiD3LIRLrWaceSMPVy1c15URNYe6btW0kxFnt62B1GZ2mJ1ERKQsRQtkS5YsgUrV9T+z33zzDQoLC22ve5NleVAFMpPJhK1btwLoehLl888/77DtunXrcN9992HPnj349NNPcffddyMzMxOhoaHYv38/WlpakJOTgx//+McDGgsREZG3qAUBBSW1LrXdWVr7/7N37+FRVff++N+zZ5JJZiYhE8iVJiFpLqLkQgQFWiVCBbG1WusXkR76lXrr8dtqvbRVOGiVqpzzwx7tOT1VrOV7yhcVrEWPFdRzgIAVaMGQm1ICJiRcQi4wIZmZZJLZa//+mMwkk7ntCUkmkPfrefqU2XvNWp+Z55k37sXaa+PR5VcjMyUOJ5o7AQCZKXGYnGBE655yVX1Yq8t9bi0Mp4Zdh5pQkp/kc3wk+ghGI2lhrS4P2iY6KQO6+Ck4v3sz7F9WIL50MeJn3ojkWx/ytHFeaMP58jfQ+dlHMORejdiMK8Kqg4j800oSdo1ABvjLkrBzrmYPkm99CNFJGehtbfQ577Q048Jf/wzzdXdAnzINhgAZIXqsA336yU4iIoqsiE6Q3XbbbQEnxEbawYMH0dPTAwD4/PPP8fnnnwdsu379ekiShJdffhlbtmzB22+/jcOHD0OSJOTm5mLp0qW44447xqx2IiKicFi6HEHPS5IGmSlxiDe6VkGbYgf+c8AQ4/qzbO1QNZZs87+6w9Ll8IxjiNHB3uNEU0uXZ6WamlovWIP34T43yTS81dwBP6NGQnRSBmIyprva2S5AdFvR8ek76Nj/Hoz5s6A1JkC2dcBWdwgQzv52wVe6EFF4QmWZ2nb6aC0kSePJjuHmXHRqNiS9AcJhR2+ba9ItOikDkt4AREW5avn0T5A72yHbOyF6rOhtP43oKVMRnZQx8D5FMC+IiMahiE6QrVu3bszGWrRoEY4ePRrWezQaDZYtW4Zly5aNUlVEREQjzxyn93s8zhCFJfOycfPcTExOGHg4zs9XzML7n57Ajn0NsPe4Jnu0pgRVY2mNvnuYAcBNc7PwyLJir3HOddiwfX8TduxrQJe9z6dWRcjQSFrP69V3z4ZTAMbYKM+xto5u7Dp0EhooWDgrE5MTBrZlcD/NTu1T7YZ+RinW5FolVroIuvgpnuPJt/0EnYf/G1AUxBWVeZ1zdrajs+JjdFZ8FPC7IKLhCZRlwdr5y4Ef/a8S3HljAT7cf3E5l3zLjwfG6bEBigJtrMlzTBEyptx4NwDA2XUOve2nED3lK9DFDTzwy50Zsn1gNRkREY0PEZ0gI3r/xVtHpS0R0UQlC4GFszNQXnHK63jaFCN++cAcJCeaYKuvQuuecsjWDmhNCTAWlmHFkmIsuiYDT7/2V5zrsMFYWAZr7d6Q45mKyqAI4bWPjiJkfL14atBx1mw4gOZ2G26am+2ZGOturHXt3dPf3lRUBmN2MS50deP3fz4CIRQsmTsNdyzIg1bSoLKuFf/3gy9g6XLAHKfHglkZmFmQjL4+Aa1egiyUgPuSKUKGqWjgM+rMaUhbvgZRCSmw11fi/O7NA3UUlsH8te9CEQI9p/4+5Nx8JJYtR1zxQjitFp/vgoiGRxYCC/xkmT8LZmV6JsTcv//qY+3YdeikVz6sWDIdN16TiV+8diDsnBO9PWj/cAMADRIXroDOmAB7Q5V3ZhWWwZBTDKetA30drTBkF0P09uDc//wneltOeGWG6O1hXhARjTOcICMiIrqMaCUJJfnJKMg0ezaljjNE4ZcPzIFZL3B64xM+m1Jba/dCn56H5KWr8Mx912LnoVNY+o1i6NPzgm5grU/P89lDRxECwmH3+3TIweOsvX8Ofv/+F5ielQDhsIVsv3xRPta8uh//cNMVsNp7sfb1v/ps3l1ecQoFmWasuedaWLv7oI/WwhAT5XeSTCNpYch2fcY+SzPSlq+BFBUT9PtJvXMVdHGTYf+yAqLb6nMuZlISL3aJRohWkjBzSJb5U5BpRkl+Ehy9TnR0O6DTSvinV/YFzYdf3Dcn7Jw7X/4G7Mc/w9Qf/As00ATPiqVPQmdKRPMbzyL51ocRf/VNOL3xZxAnrANtlq2GRseHfRERjScRnSCbPn16WO01Gg2++OKLUaqGIqn+ue+G1T5n9TsjMu4tj72nqt3luHpN7WdX43L8foguZbJQ8PR9c/DMawdwtMmCJfOykZxo8ntB5+Y4cwytW5/H1JXroCganL9gR+qy1X4nrgB4LvCGroDQSFLA9wwd56f/cHVY7f/xjmKkTDbi8Zf3BrxgPtpkwdrX/4r1D1+PHfsasGRedsDvSRECqctWw3ZkP6ISUkJ+P2e3uOqIL12Mjk/f8XuOiEaOLASevncOnvndAb+/+YJMM56+bw5koeCTyjP4xjWZqvNBUTRoOWdF8tJVaN36fOCcu3MV+iwt6PzsI8RfvVhdVmx9AVNXroM+Pdfz58G54ThzDGffeo6ZQUQ0zkR0gkxRlNCN+sXFxY1iJURERJcPraSBISYK6x++HpV1bcidGgd7fVXQVRKA66LNXl+N78yfjujoKChCxtSV62BvqHbdRmSzQGs0w1RUBkN2kd9bK7sba9WN01CN2KyrYG9QW1cVinKuwuGjrUFXkwCui+DDda2YNT0FlXVtKMydEmAVmQRJb0RcycIwvp8qxM+8ER37tgGK8POZZnAVGdEI0UoSDLE6T5btOtQ06JbJTJTkJ0EWAkcbz6M4P0l1PlTWtWLxnExsKz+O5YsKguZcn6UFzW+uhXDYEV+6CPb6yrCzwl9uMDOIiMafiE6Qvf/++wHPdXd3o62tDTt37sS7776L7373u3jiiSfGsDoiIqJLl3tCqDB3MrSShNaaclXvs9aUIznHdduke8P82KyrvG6lVIToP+99UaeRtLBWqxun50QtDNlFqttba/bAkFOM6uPtqtrvPnQSjy6/Gjv2n0BJflLAdu7PYFX9/exB8q0PITopA72tjd7nqst9bjkloovj3mi/MHey129Z7s8hrSTh0Bct+P43r8QfPlB3p8mu/nxYecsMtHfY0dDchQI/OWc9sg/t21+F6LEiOjkLuvgpOL97s6oxBmdFoNxgZhARjS8RnSDLy8sL2WbhwoW44oor8MILL2DGjBn41re+NQaVERERXR7cF5eytUNVe9nmu/pi8JMlXa8Dr3ZQO45wOoZVV2+frKq9pcsRVvtw65D0hoDniGjkDX0y7eDXjv7fuft3H4q73UtvVmB3xSlckWXGP//oOrR98Fv0nTsNXUIKkr/9Y3RV/DdEj2u/QfdvfjhZESg3mBlEROPLJbGe93vf+x7MZjM2bdoU6VKIiIguSVpTgrp2RvOYjCPp9GG1d9cVHaUN0dLFHKcPq324dQiHPeA5IhpbqYmuiSf37z4Ud7svT1+AEArsPU4AgOLsRc/JI+htaQDgnQvu3/xwsiJQbjAziIjGl0tigkyr1SItLQ11dXWRLoWIiGjcct9yNPS1ImSYispU9WEqKvPcQhmucMaJmTYjvLoK50N2OlGUO0VV+xtmZaDNYkdRbhJkEXzP03DrcF5oQ2/bSd9zF/HdEZGvQJk29Ngt138VshBYODtDVb/ufGhq6QIANLV04VyHDcbCMgBAb9tJODvbYSqc73mPv2PBDM6KQLnBzCAiGl8uiQkyq9WKEydOICoqKtKlEBERjTvuCaCa4+14cfNn+KdX9uHFzZ+hpn+/LgUSDNnF0KcH39pAn553UfvhhDuORtKqb59TjOr685hZkIyCzOCrLgoyzZiZn4xDR1pQkp/kd4P+wcKto/Pwf3tt0O/9mS6J/7QiGtdCZZosFJ82uw+dQkm++nz4cH8jRH8fQijYvr8Jxpz+HFAEOis+hiGnZCAX/B0LYHBW6NO+6jc3mBlERONPRBO5u7s74P/sdjs6Ojpw+PBh/OM//iPsdjtKSkoiWS4REdG4IwsF9p4+PP7yXqx5dT/KK06h6lgbyitOYc2r+/H4y3th6+mDImSkLlsd8MJOn56H1KVPwtl5DsJhC3tVgywU2Hr6cP6CHclLVwUfZ9lqT/+KECHrSl66Ci3nrPiPP1bh7Dkb1txzbcCL4IJMM9bccy3aO7rx9ZKpIVePuampI/XOVeiztKDzs4+CfiYiGr5QmfbUq/ugKL5tfv9+rap8ePq+OXDKAnVDnna5Y18DWs5ZkXynKwc6Kz5Cn6UFqUuf9OSCv2NDubO0z9KCntPHPH8enBvMDCKi8Smim/SXlpaqaqcoCrRaLe6///5RroiIiOjSopU0eOa1Azja5H+z56NNFjzz2gGsf/h6SHojpq5cB3t9Faw1eyDbLNAazTAVzochpxh9lhY0v7kW2lgTpq5cN6w6Ou29WHv/nADjlMGQUwRFCM+qCY0kDdTVUA1rdflA+6IyGLKLcKGrG298fATTpyXifKcDBVkGrH/4elTWtWHXoSZYuhwwx+lxw6wMzMxPRo/DiUkmPWShhFw95qamDkUI9J47A0Pu1X7PcSUI0cULlWl5mWbotJJPmy57H57asB/P3j8X6x++HofrWrH70ElPPiyYlYmS/IFbrtf+cJ5Phpzr7EWyOcGTA52ffYhJ197ilQuWv2xF4oIV/rOiP0udtg44rRakf+9piN4edO5/F/q0HGYGEdE4F9EJMkVR96+6BQUFeOihhzBr1qxRroiIiOjSIQuBmuPtAS8k3Y42WVBZ14bi3ET0nm9G9OR0JN/6kOe880Ibzpe/gc7PPoLoscJpAewN1YjNmqHqAm5oHY+8tBdL5mZjydxcJN9a7GnXbrHhQrsNyYkGDN463z1GbNZVXrd4KkJACIFJcbF45K7S/rEGJr0KcyejJD9pUB2u/66I6t+YX+3kmJo63OdjpuYhNuMKv+eI6OKEyjRJ0uCmudNw+Gir3zbN7TY8+tIeLJmbjZvmZuHR5VcP6tuVD4NzwV+GaPrPD82Boa/lHhv0qTl+s0JnTIAUHeuaBNNFYfI3/rdPG2YGEdH4E9EJsp07dwY9r9PpEB8fj9jY2DGqiIiI6NKhlSTsPOi7Wbw/1cfbUJKfhI5PtsL6+V8QnZQBSW+AcNhdG0cP2VPLWl2uej+yoXV02fuwdWcd/rj7GDJT4mCI0cHe40RTSxfmz5zqddE6mEbSDnktYegU1+CLW+2QC0z3uXAnxtTUoeYcEV2cUJmWmRKHpIRY/OGDLwK2GZw/370hF9+/+cr+vn1zIVCGAP5+667Xlk/ehu3v+z0b7g9kaTeg0UCKjoFw2BGdko3kb//YZ0xmBhHR+BXRCbKpU6cGPS+EgMS/RIiIiAKydDlUtevtkwEAsrUDUAR6WxuDtpdtwVelqalDCAUnmjtDtiMicguWEYYYXcg2bkIoOHayY8Tqcus5eQQAEPOVgoD/wAAAWuOkER+biIhGV0QnyNz+/Oc/47333sNvf/tb6HQDJf30pz9FfX09Vq5ciW9/+9sRrJCIiGh8MsfpVbWLdt92aEpQ1V5rDP4kuOHWobZdMIqQvVZ3DH1NRJeuYBlh73GGbKO2L3/UZEvybT+B1hDvee3sbEdnxcforPgIotsKAJBiTYibuYhZRUR0iYn4HmSrVq3Cu+++CwBobGzEV7/6Vc/5xsZGHDlyBD//+c9x6NAhPPvss5EqlYiIaNyRhcDC2RkorzgVsu2s6alQhAxTURmstXtDtjcVlaneRDqcOhbMygxr8/zB3BeX3SdqYa0ph2ztgNaU0L/5fzEvPokucaGypKmlC20d3Vgwa2Tzxp113Y21rk333dlSVAZDdrHXvmGOsw1D8mc+EsuWI654IZrfXAsASFu+BlEJKbA3VAXsj7daEhGNPxGdIHvrrbewbds2GAwG/OhHP0JaWprX+Q0bNuDjjz/Gr371K7z99tuYM2cObr755ghVS0RENL5oJQkl+ckoyDQH3ah/Zn4SpmclQJH7YMguhj49D44zxwK216fnqd5/LJw6CjLNXhtih0MRMoTDjrNvPedTu7V2L/TpeUhdthqS3sBJMqJLVKgsEULBh/tPYMWS6SOWN4oQEA5bwGyJzS5G6p2rIHq7g+fP0ieRtvwp1z5kUXqc3vhEiKwycpKMiGiciWgqv/POO9BoNNiwYQN+8IMfwGAweJ1PTEzEsmXL8O///u9QFAVvvPFGhColIiIan2Sh4On75qAg0/8tkQWZZqxeeQ00koSWt/8ZfZYWpC59Evr0PL/t3Rdv7hUTI1nH0/fN8TxJLlwaSev34tTNceYYzr71HCfHiC5xobLkWJMFTlmMWN5oJClotujTc6HR6kLnz9YXEJWQjKhJSTi75XkVWcXJMSKi8SaiK8i+/PJLZGdnY9asWUHbXXPNNcjIyMAXXwR+Yg0REdFEpJU0MMREYf3D16Oyrg27DjXB0uWAOU6PBbMyUZKfBEXIsDdUobuhCs1vrkXaXWswdeU62OurYK3ZA9lmgdZohqlw/qBbFcO7eFNTx8XcWtl9ojboqjfAdeFpb6hGbNZVnCgjukSpzZKRyBtFyOhuDJItGgnxpYtgr68MnT/NX0L0OdBz6u9hZNUMTpQREY0jEZ0gkyQJUVFRqtrGxcWhra1tlCsiIiK69LgvAgtzJ3vdUuRePaGRtLBWlwMAnJZmnN74M8SXLkb8zBuRfOtDnvbOC22wHtkH0/R5o1LHcCbHPPXXlKtqa60uD+v2UCIaf8LJkovJm8HZ6E90UgZ08VNwfvfmkH1FJ2VAitIH7W8wZhUR0fgT0QmyrKws1NXV4ezZs0hNTQ3Yrr29HXV1dcjOzh7D6oiIiC4t2iErEQZfIMrWDs+fRbcVHZ++g45921wXdXoDhMOO3raTiJ02Y9gTZGrqGK7B9QdtZwu8JxERXVrUZMnF5k2wbJH0hpBthtMWYFYREY1HEV3Te9NNN8HpdOKRRx6BxeL/L4muri489thjkGUZixcvHuMKiYiILg9aU4LvQUWgt7URPSePoLe1EVAEtEb/e/pEmt/6/bUbp/UT0fgULFuEwx6yDTQSopOzoDOnerftPx6TeSWMV8xFTOZViE7OAjSuyy9mFRHR+BPRFWTf+9738O677+Lw4cP4xje+gbKyMuTn58NgMKC7uxvHjx9HeXk5Ojs7kZWVhbvvvjuS5RIREY1LshBeqyiGvlaEDFNRGay1e0P2ZSoqgyJE0H1xXHuUaQO+ViOcPhQhw1QYTv3++wo05nDqJyL1QmXUWPD3+wc0MJUsDJgtvW0n4exsh6lwvk8bKdbkulW9dBF08VM8fZpKFkI3KQnxVy+GLm6yz/jOrnPo/OwjxGQXh8xaIiIaWxGdIDMajfjd736Hn//85zh48CA++OADbN++3XNeUVx7CBQXF+Nf//VfYTKZIlUqXabef/HWSJcQMUM/+y2PvRehSohouNybUNccb8fOgyc9m1QvnJ2Bkvxkz3mNpIUhuxj69Lygm0fr0/OC7onjvpjrbqyFtbocsrUDWlMCTEVlMKi82BtOHxpJC0PO8OsPOGbhfBhySqA4+6CJ1vJilWiEqc2o0RQqc2IzroThijmw//2Avzejs+JjJJYt98ofnTkNacvXICohBfb6SpzfvRmytQPx194CQ04JDFkzYG+owvld/88nbyS9EYlly5k3RETjUEQnyAAgPT0dmzZtwuHDh1FeXo6TJ0+io6MDMTExmDZtGq677jrMnTs30mUSERGNK7JQYO/pwzOvHcDRJu9tCsorTqEg04yn75sDQ0wUtJIGihBIXbYaZ996zu8kkz49D6nLVge8aFOEgHDY/L7fWrvX835Jbwx40XcxfShCVln/0FUiKsZc+iScPTZooqKD1k9E6oWbUaNBbeak3PYIzm55Ht0NVT59OM4chyI7PfnTZ2lG2vI1kKJicHrjE55+pVgTopMymDdERJewiE6Qbd68GV/96lcxZ84czJw5EzNnzoxkOTSB1D/33bDa56x+Z5QqGXmR/GwjvQrNvcptJPsdzT6JxpJW0vi98HQ72mTBM68dwPqHrwcAaCQJkt6IqSvXwd5Q7VpJYbNAazT3r6QoCrqiQSNJASenAMBx5hjOvvUcpq5cF7Dmi+lDI2kh6Q0h6ve9VVLVmFtfwNSV63Dhs48w6Wrud0o0EsLNqNEQTuakLX8qaDa687PXchZRCSlek2MAEF+6GFGTknyO+4zHvCEiGrciOkH2yiuvwGq1Ys+ePYiPj49kKURERJcMWQjUHG8PeOHpdrTJgsq6NhTmTum/1dI1+RWbdZXXrYiKEAAQZOWXjO7G2qC3NwKuiz97QzVis2b4XQF2sX24J79865e9zg9rzPoqGHNLA45NROoNN6NG0nAyR002Rk1Kgr2hyrtfjYT40kWw11cyb4iILmERTeMLFy4gOzubk2NERERh0EoSdh48qartrkNNPhee/lZZBaORtLBWl6saz1pd7re/kehjcF/BXg9rzJo90E1KQveJGl6sEl2ki82okTCczFGTjf76jU7KgC5+Cqw1e9SNx7whIhqXIrqCbPr06Th+/DgsFgvMZj7qmIiISK0LVgempcXDEKODvceJppYuAEBmSpzXMUuXY0TGk60d6trZAq8Yka0dgKSDMX82tMZJkG0XYKs7CAin6j7C5VW3RkJ0UgYkvQHCYUdv20lAEV5jKs7eERubaCJTmz0jlVH+aHR6QOOagIpOzkJ0ShYADXpbTqC3tdHn96+WJ1f6MyUmY7r38VDvZ94QEY1LEZ0ge/7553HPPffgrrvuwj333IOSkhIkJSVBr9cHfE9sbOwYVkhERDQ+/fQfShFnjPG8tnf3AlBgiB34O/Rchw3HT3UCcN3ypB20UmHo61C0pgR17YyB/8Er8caViJ6cBo02ynNMkfvQ3fQF2ne8CqelJWQf4dKaEiDFmhBfuhjxpYugi5/iOefsbEdnxcforPjIM6ZGFz1iYxNNZOa4wP89P1jaZAOA0BklhIAChMyxwXsRJn3zh0hcuAIarQ5SlN6rjejtQeehHbjwt/d9Msf3YR/er3XmVCRMzfPJlHBzknlDRDS+RHSC7Cc/+Qk0Gg0aGxvx1FNPhWyv0WjwxRdfjEFlRERE45N7I31ty1G01pQDGgmJC1fAYEyAvaEKrdXlkK0d0JoSYCwsw7UziqEIgaONFuzYdwKWLgfMcXosnJ2BkvxkyEIJeXuTImSYispgrd0bsj5TUZnfzf4VIUOfnAl7fRWsNQM1mgrLYMgpxlfufxlntzyPnhPVAfsIlyJkxJUugnn+MkQlpMBeX4nzuzcPGns+EsuWI654IZxd5+G80IbYaYUjMjbRRCYLgYWzM1BecSpou7QpRvzglhkAgJrj7dh58KQnoxbMzsDM/GRYvmIo+gAAIABJREFUuhzQSkC8UY/KulavNoNzTIICjSShu7HWtdG++3deVAZDdjGctg6c37kJUIQndxLm3Q5TYRmcne1e+40F6sPVRsHkb/xvSNExA5liu4Dk234CU6HKnCycz7whIhqHIjpBduxY8E0sh1IUZZQqISIiGv8UISAcNs9T2aRYE6b+4F+ggcbvk9OstXuhT89D8p2rMTlej8/+3oIuex8AoLziFAoyzXj6vjkwxEQFnCSThQKnU4Ehuxj69LygG1Dr0/O8NrgeqFuGcNj9Pk3OXWPqstVIvXMVWt99yW8fw6GRtIiZWgDRYw36/aTeuQoxkwrQVV2O+JIFIzI20USmlSSU5CejINMccKP+OEMUXnjwa+iTBf7p5b0+7corTmFmfhKeumcOuh1OPB6kzS/uvRaiN0TGLH0S5uuW4vTGn3n99nWmBOjiEgHAK1/99rFsNSS9AYrch9Mbf+HV7sLf/ozEsuXqcjKnmE+xJCIahyL6zxU7d+4M+39EREQTlUaSvC7e4ksXIyohBWe3vhDwgsxx5hhatzyHlMkmLJmb7XXuaJMFz7x2IOgKMq2kwSeVZ6AIgeQ7V0Ofnue3nXsizr0Kw7turd+LzsE1nn3rOUi6KCR/5xG/fQyXRpJwdsvzwcfe8jw0kgTTVV8b0bGJJjJZKHj6vjkoyPR/y/SKJVdi8qRYPPPagYCTaHmZZuh0Ep75XfA2klZFxmx9AVHmFMSXLh44tuV5aLS6/g36JVU5pZG0sH6xz6ddZ8VH6LO0IHXpk0FzMnXpk3B2noPpynnMGyKicSaiK8imTp0ayeGJiIguGYqQ0d1YO3BRppEQX7oI9vrKoKsVANeFnb2+Ckvm5uKPu49BiIEV2UebLKisa0Nh7hSfiTJZCNQcb0dxfhKOnLBg8iQ9pq5c13+b5B7INgu0RjNMhfNhyClGyzkrzrV0oCDL7OlLETK6T9Sqq7GhGrFZV43Y7UY+39kYjk000WklDQwxUVj/8PWorGvDrkNNA7dPzspEYe5kVNa1Bpz4kiQNbpo7DYePBm9z89xM2OqrVOdg/Mwb0bFvG6AIz7HYrBnoblKfFcbcUpzTSJ5N/gFAdFvR/OZapN21xpWTDdWu2zSH5KTo7YHWOIm3VhIRjUMRnSAjIiIidTSSFtbqcs/r6KQM6OKn4Pzuzareb63Zg+Rbi5GZEocTzZ1e53YdakJJfpLPe7SShOpj7SjJT8YfPvgCn/29BUvmZmPJ3Fwk31rsadduseGd7UewfV8DZl+ZgiuzE73rrin36dtvjdXlI3Z7pWfsQd/ZWI5NRPBMlBfmTvbKGPfehzsPngz43syUOCQlxOIPHwTefzgzJQ6TE4xo3VOuqh5XDj6E6KQM11MsAfQ0fg5DTnFYWTG0DzenpRmnN/4M8aWLMemab8Fw60Oec549zvo35ufkGBHR+DNmE2R33HEHNBoNfv3rXyMtLc1zLBwajQZvv/32aJRHREQ07snWDs+fJb3B51jQ99pcKzAMMb5/9Vu6HAHf5+iTPW267H3YurMOf9x9DJkpcTDE6GDvcaKppcuzKs1fX+HWOJIiOTYRuQx90qR74ixY9rizSk2bcH/n7vwEAOF0XHQfg4luKzo+fQeO5uNIu2vgIWTuCTFOjBERjV9jNkFWW1sLjUaDnp4er2Ph0GiCP2WLiIjocqY1JXj+LBx2n2NB32t07QNk73H6nDPH6QO+Tx+l9WkjhOKzCi1YX+HWOJIiOTYRBRcse9xZFaxNT69rAj/c37k7PwFA0ukvug+/7Qzq+iMiovFjzCbIXnjhBQBAUlKSzzEiIqKJThEyNJLW72tFuC4CTUVlsNbuBQD0tp2Es7MdpsL5nmPBmArno91iQ1NLl8+5BbMyPbc8DSYLgaK8KWjr6MaCWRkorzgVcpyhfSlChqmwTF2NRWWuJ15C47XiRBbCZwWKGoqQvb6z0GNzTyCisSILgYWzA+dKU0tXwOyJM0RhybxsfHNeVni/88L5cF5oQ2+b69ZOKdYEU/ENYWfF4D6CtWOmEBFdWsZsguw73/lOwGM9PT3YtWsXbr75Zq/zW7ZsgcPhwG233Yb4+PgxqZOIiGgsuS+guhtrXRs6WzugNSXAVFQGQ3YxFCHQc6oOss0C0/R50KfnuTaSVgQ6Kz5GYtnygWMB6NPzYMgpxjvbj3ht0A8ABZlmv/uPAa7bokryk7Fj3wksmTcNBZnmgJtlB+pLI2lhyClWV2P/HmA1da3YefCkZ0PvhbMzUJKf7HcSLxiNpIUhO7yxiWhsuPMlUK4IoeDD/SewYsl0rzZpU4z45QNzkJxogr2hCrYzNu9sDMCdg+fL3wAUAZ05DekrnoUuLhG9luawsuLCZx95bdAfqB0REV1aIv5PGvv27cP8+fPx2GOPoaWlxevcjh078MILL+Cmm27C/v37I1QhERHR6FCEgHDYcHrjEzj7xrOw1u5F94lqWGv34uwbz+L0xicgeqzQxSXi/O7/hz5LC1KXPgl9eh4AoLPiI59jQ+nT85B852q0nLNi+74Gr3MFmWY8fd8cyEMmzQaThYKvl6SjvaMba+65FgWZ/m9FDNaXImSkLlsdtMbUZauhCBnPb/wb1ry6H+UVp1B1rA3lFaew5tX9ePzlvbD39AWt1R9FCJVjB77YJaKRJwsFTlkEzZVjTRY4nQJP3zsHBZlmxBmi8MsH5sCsVzy52b7jVVU5mLr0SfRZWtD52UeQYk1IX/EsNLoonN74BM5sfEJdH/05ZbpyHjOFiOgyFNGnWFZXV+P++++H0+lEfn4++vr6vM7ffPPN6OnpQWVlJR588EG88847yMnJiVC1REREI0sjSTj71nMBVyw4zhzD2S3PY+rKdTBd+XU0v7kWaXetwdSV62Cvr4K1Zg8sf9mKxAUrXMcaql2r0GwWaI3m/lVoRVCEwLmWDsy+MsWzKmvBrEyU5CeFXJWllTQwxEQhzhCNHocT6x++HofrWrH70EnVfWkkLSS9IUSNMja8W4v9tc1+6zjaZMEzrx3A+oevD/s7lvTGkN8Pb4MiGltaSYN1/3kQd3/rKr+5csOsDMzsXzmq00lY//D1aG63ITnRiNMbn/Dkpui2+s3Gob9zp60Dlr9shSH3aiRc97+gi0v06kdNH+6sYKYQEV2eIjpB9tprr8HpdGLlypX4+c9/7nN+6dKlWLp0KdavX4/f/e53ePXVV/HP//zPEaiUiIhoZClCRndjbdDbeQDXJJm9vgrxM29Ex75tOL3xZ4gvXYz4mTci+daHBvUnEJt1lddtPe4VDBpJQkFWAq7Mvtpzzr0SS80ti+42UVGuC76i3CmYmZ8cVl/u/dR8a5QhhMDfT1jw509PBK3jaJMFlXVtKMydEuatllKAsYXXeSIaG7IQqDnejk+rm1F9vB1L5mbjprlZeHT5QEa1WezYtP0ISvKTcGXOZAihIDUxBvaGKp/cdFqaA2aj7HRCEQI6YwKSb/kxAFfuDO0nWB/ufSCHPomSmUJEdHmJ6ATZZ599hsTERDz++ONB2/3kJz/B22+/jX379o1RZURERKNLI2lhrS5X1dZaswfJtz6E6KQM9LY2ouPTd9CxbxuikzJgvGIezNfd4feCbPCxoZvchzPBNLSPi+lr8IMI3K81AHbsb1T1/l2HmgLumRb+2LyIJYoErSRh50HXJvdd9j5s3VmHP+4+hsyUOBhidLD3ONHU0gUhFLR12FGYO8X9zoC5KbqtfrPxjf+uw4olV3q1DZS/Q/uQ9AboM6Zj8g3f8zsmM4WI6PIS0Qmyrq4uFBQUQKvVBm2n0+mQkZGBo0ePjlFlREREo0+2dqhrZ3NtTi3pDQMHFYHe1kZojZMA3DEK1Y0tS5fD73FJ0nhdNF+w+m9HRJeWob95IRScaO4M2S5obmok18RWjAkKXCtbjTFRfpsG7ac/X6GREDXlK4HbERHRZSWiE2TJyck4efIkZFkOOkkmhMDp06eRkJAwhtURERGNLq1J3d9rWqNrA2vhsAc8N1IUIXutihj6erSY4/Rer+MMUVgyLxs3z83E5ASj57jV1uPzXlkIr1VtQghooETkcxBNREN/g6FeA76/+UCGtvOXm1KsyXVr5NWLoYub7PV7v/2GPL+//2D56+mvdBF08VM8x5kjRESXt4hOkF177bXYtm0bfvvb3+JHP/pRwHYbN26ExWLBN7/5zTGsji7G+y/eGukSxo3hfhe3PPbeCFdCROOJImSYispgrd0bsq2pcD6cF9rQ23bS91xRmetpmNAM67bJgXpcm0p3N9a6Np22dkBrSujfdLp4VDedloXAwtkZKK84BQBIm2LELx+Yg+REE2z1VWjdM6iewjIgpxhdth7IigYJJj2qj7dj18GTkCQNfvCtKzEpzrVP0Vh/DqKJxv1gjprj7dh5cGCD/YWzM1CSn+yZGBt8PjFej/9zR7HXbz6YBbMyPfscShAwFXrnps6chrTlaxCVkALR65pA7z5R49pkP8DvP1j+Du7PXl+J87s3M0eIiCaIiE6Q3X333fjzn/+M3/zmN2hoaMDtt9+OvLw8GAwGdHd34/jx43jvvffwX//1X9DpdLj33nsjWS4REdGI0UhaGLKLoU/PC7pRvz49D4acYpwvfwNQhO+57CLs2NeAr5dMhSEmaliTZIoQEA6b3ydqWmv3Qp+eh9RlqyHpjaNyUaiVJJTkJ6Mg04wz7Vb88oE5MOuF1xPm/NWDaAOeenUfDte1Ic4QhZceuR4GqRenN/4iIp+DaCKRhQJ7Tx+eee0AjjZZvM6VV5xCQaYZT987B44+Gf+y6RC67ANPq08yG7BiyXQUZJp93jtYQabZ84Rce08f/lJ5BkvmDeSmFGtC2vI1kKJi4ew6D42kxenNan7//vN3oL+YkPnDHCEiuvxEdIIsPz8fzz77LJ566il88MEH2L59u08bRVGg0+mwdu1aTJ8+PQJVUjjqn/tuWO1zVr8zSpWMH/xOiCgQRQikLlvtd2IKcE2Apd65Cn2WFnR+9pHPueSlq9Byzoo/bD+CnQdPYv3D1w+rDo0kBawBcD1J8+xbz2HqynXD6l8NWSh4+r45+EvlGSQnmvxenPqrJy/DjMN1bVgyLzus9xHRxdFKGr+TY25Hmyx45ncHsP7h67Fkbja27qzznNuxrwE3XpOJNfdci7Wv/9VvHwWZZjx93xyI/lVqz7x2AGfarSgtmILkpavRuvU5xGYXISohBZ0VHyO+dFFYv39/+RtfuhhRCSnMESKiCSqiE2QAcNttt6G4uBi///3vsWfPHrS2tnrOmc1mfP3rX8c999yDK664IoJVEhERjTyNJEHSGzF15TrYG6pdtwTaLNAazf238hRBEQK9587AkHv1wLnC+TDkFKPlnBVrNhyAtbsPR5ssqKxrQ2HulLBWkSlCRndjbdBVbIDrotDeUI3YrBmjtIpMA0NMFG6akwF7fZW6euqrsGRuLv605zhunpsJm9r3jeLnIJoIZCFQc7w96OovwDVJdriuFTfNzcIfdx+D6L9Vssveh6c27Mez98/F+oevR2VdG3YdavLcorlgVqZn5ZgCBZV1bZ6x1mw4gLX3z8HUlesg+hyw11fBkFsKe31l2L9/r/yt2YNJs7+pPn+YI0REl52IT5ABQHZ2NtauXQsA6O3thcViQWxsLOLj4yNcGRER0ehyX1zFZl0FQ3aR57gihOe80zwNybc+5DnXbrHhne1HsH1fA6zdA7ct7TrUhJL8pDDH18JaXa6qrbW63KvGkeaa2NPCWqOynpo9SL61GNdemYLJCUa07lH5vlH+HESXO60kYedB3z0R/dl96CQeXX41MlPivJ5S2dxuw6Mv7cGDdxRjbmGaV3a59xxzZYLGa6zmdhseeWkvli+6At+6Lgc9jbWu29B3b1ZVz+Dfv7/8VZ0/zBEiosvOuJggGyw6OhopKSmRLoOIiGhMDX0y2uBVCf/f5gpYuhwwxOhg73GiqaXLsxJjMEuXY1hjy9YOde1swVeLjJRw65lk0g/rfUQ0fGrzxt3OEON72dFl78NHBxrx9eKpXseHroIdOlaXvQ+fVJ3Gt67LgejrBXBxv//B+cscISKauLgmmIiIaJy7MnsyAODvjRacaO70OzkGAOY4/bD615oS1LUzmofVf7jCreeC1eH7Po2E6OQsxGRMR3RyFqCRfN5HRMOnNm/c7VInGzAtLR7SkMkvNf3kZyT4vM/e4wQASFHRAEYux8ZbHhIR0dgZdyvIiIiIyEURMjSSFssWFWDZogKc67Bh+/4m7NjX4PVEOLcFszIh929oraZf959NRWWw1u4NWY+pqAyKEJ7VbbIQ0I7w/jth1VM4H+0WG/76RQvOddhgLCyD/csKxJcuRnzpIujip3jaOjvb0VnxMTorPvL5HEQUHlkILJydgfKKUyHbunPpkbuuBgC0dXTjw/0nPDkWKLcG58v3v3kllnwt2+t9TS1dONdhQ0zWDDg722EqnK8uN0oW9t/CrnitHFOE7Do/zDwkIqJLHyfIiIiIxhn3RVd3Y61r435rB7SmBBgLy7BiSTEWXZOBNRsOoLnd5nlPQaY55P5j/vqNK70RpunzoE/PC7oxtT49D4bsInQ7+vDKnyohhIKFszNQkp+salJOLY2khSG7WF09OcV4Z/sROJ0C2/c3YcWSYujv+1fo4hJhr6/E+d2bPd+dqXA+EsuWI750MXTxk0ekVqKJSitJKMlPRkGmOehG/e5c+kvlaXx4oLF/A/4MrFgyHTdek4n/++fPfXLLnSc1x9ux8+DJQRv3D7zvqQ370dxu8/zu3U+xDJUbhivmIDZjOjSSBHt9Faw1A/nqejBKsfr84f5jRESXHU6QERERjSOKEBAOG86+9ZzPBZq1di/06XlIXroKa++fg0de2osuex8KMs14+r45QSeqAvXraKmHPvWrSL1zFc5ued7vRaF7zPMX7NBptbhrUQEefWkPyitOecY2xESN2CSZIgRSl632+x2460ldthqyLKOu/+L8k8OncNeNedDoonB64xMBv7vUZau9VtAR0fDIQsHT983BM68d8DtJVpBpxpp7rsXZczb85o9VngeKuHNjzT3X4vF/mOWVW7JQYO/p89vn4Pc9e/9cPPrSHuzY14BF12Qg8Yq5UJx9QXMjNrsYKbc9EjRfY7OLkXrnKlX5w9VjRESXH06QERERjSMaSQp4YQYAjjPH0Lr1eUxduQ4P3lEMU2w0SvKTQq7iCtSv6Lai+c21SLtrDaauXAd7Q7VrdZnNAq3RDFPhfBhyitFyzoo1G/Yh3hCN9Q9fjyVzs7F1Zx2ONlnwzGsHsP7h60f0O5D0Rv/1FJXBkF2ELlsPnHYn1v5wHirr2mDr7oVOp8PpTcG/u7NvPYepK9eNWK1EE5VW0sAQE4X1D1+Pyro27DrUNGi1VyZK8pNw9pwNT23Y7/W0XQA42mTB2tf/6pMbWkkTcMJt6Pt+cMtVqD7ejnOdvUg2J0AjSVDsna7cqK+CtWaPT44BCJqv3Q1VaHn3X5HynceC5g8nx4iILk+cICMiIhonFCGju7E26K09gGuix95Qja8VzoCAa1Is2ORYqH6dlmac3vgzxJcuRsK8271uHWq32PDO9iPYvq8B1u4+NMOGw3WtuGluFv64+xiEUHC0yYLKujYU5k4ZwVstXRefsVlXedWjCAEhBOKMMZ5jhbmTIUGBvaFK9XcXmzWDF7hEF8n9ey/Mnex1q2RPrxObBuWGP0NzQxYCNcfbg96yOfh9N8zKxDeuyYIsFAAC9oYqtG77lWsPwpk3IvnWhzzvcV5og9xthaP5eMiMsP/9ALpPHkFsxnS/+QOA2UFEdJniBBkREdE4oZG0sFaXq2prrS6HIbsIam4UVNOv6Lai49N34Ow8h+Rv/xgvvVmBL09fQFNLl89TM3cfOolHl1+NzJQ4nGjuBADsOtQUcg+04Rh6K6RGkjB0Cs69kXe43x0RjYyhD+v4jz9WYfdnoTfwH5wbWknCzoMnVY3n/T4NAFfGuXOsY982RCdlQNIbIBx2QCPhK/euh7Vmj6r+rZU7Yci6yuc4J8aIiC5vE26CTJZlvPnmm9i2bRvq6+shyzIyMjJw8803495774Ve7/2o6ZqaGvzmN79BTU0N7HY7cnNz8f3vfx+33HJLhD4BERFdzmRrh7p2tuCrLIbdr/U8AKD5nM0z+TWUpcsBADDE6HyORdJofXdEFJ7znb55IEkaZKbEwRCjg73HiaaWLp/cUJsj/tp5/f4Vgd7WRs/LmIzpvm2CYEYQEU1ME2qCTJZlPPjggygvL4fBYEBxcTF0Oh2qqqrw61//Gnv27MF//ud/IjY2FgDw6aef4oEHHoAQArNnz0ZsbCz279+Pxx9/HMePH8cjjzwS4U9ERESXG60pQV07o3lU+7X3OAO2Mcfpfdq4jw0mC+G1smTo65E2Wt8dEYVncB7EGaKwZF42bpo7DUkJsZ7jbR3dqGs8H/B9avt3C/b7Fw57yDZefTEjiIgmpAk1Qfb222+jvLwcBQUFeO2115CSkgIAOH/+PB588EEcPnwY//Ef/4HHHnsMPT09+OlPfwoA+P3vf485c+YAAJqamrBixQq88soruPHGGzFjxoyIfR4iIrq8KEKGqagM1tq9IduaispUbRQtCwUSBEyFKvstnI92iw1NLV0B29wwKwNtFrtXmwWzMj0PCnD/f83xduw8eNKzcffC2RkoyU8O+UCB4RiN746IwicLgYWzM1BecQppU4xYe/9cpEw24vDRVvzhgy8GbeSfga8VT4XTKfCbP1Zi5S1XYUH/+0IZnDdA6N9/b9tJODvbYSqcz4wgIqKAJlTqb9u2DQCwatUqz+QYACQmJuIXv/gFAOCDDz4AALz33ns4d+4cbrnlFs/kGABkZmbi8ccfBwBs2rRpjConIqKJQCNpYcguhj49L2g7fXoeDNlFqibH7D19+PDASRhyVPabU4wd+5t89h1zK8g0Y2Z+Mj7c3+hpU5BpRkl+kmdyzN7Th8df3os1r+5HecUpVB1rQ3nFKax5dT8ef3kv7D19/Rtrj5yR/u6IaHi0koSS/GTMzE/C2vvnIkavw+Mv78VTG7zz4KkN/Xng6MOdNxbgw/0nMDM/GQWZwVdvDc4bt5C/f0Wgs+JjGHJKmBFERBTQhEp+s9mMnJwcFBX5bsw7bdo0AEBraysA4JNPPgEALFy40KftDTfcAK1Wi717Q/8LFBERUTgUIZC6bHXAizh9eh5Sl632PE0tGK2kwTOvHcCmHV+g5ZwVyUtXhexXyDLqAjxFriDTjDX3XIuz52zYvq/Bc+zp++Z4JrzcYwZ6Et3RJgueee3AiK8gA0b2uyOi4ZOFgtUrr0HKZCPWvv7XoHnw7O/+itTJRiiKBmfP2bDmnmsDTpINzZvBQv3+HWeOQ5GdzAgiIgpoQt1i+corrwQ8V1NTAwBITU0FABw75noEdH5+vk9bk8mE5ORkNDc3o729HVOmTBmFaomIaCLSSBIkvRFTV66DvaEa1upyyDYLtEYzTEVlMGQXqby1UqDmeLvnwnTNhgNYe/8cV7/1VbDW7PHbr4AGa384D5V1bdh1qGnQ7VCZKMlPQkdXD978+ChmX5niOTZwa6X3mIEcbbKgsq4NhblTRnSibKS+OyK6OFpJA+gkVNa1qsqDw3WtWDDrK1izYT9+ce8crH/4+oAZFOgWbXW/f3mgTZAcZEYQEU1ME2qCLBBFUfDyyy8DABYtWgQAaGtrAwAkJfl/ZH1SUpLqCbI//elPnts7Qzly5IjasomILmsTOTvdF2exWVfBkD2w6tm9qkHNxZtWkrDz4EnP6+Z2Gx55aS+WzM3Gkrm5SL612HOuy9bj6Vfbf6wwdzJK8gf+DpSFAiEEEuJi8MhdpZ5jrrE0fscMZtehJq/+R8pIfHdEl7Lxkp3h5MHuQyfx6PKrEaWV8OhLe7Bkbja+fX0OHl1+tafN0LzxJ/TvX+t5HTttBgw5xX7aMCOIiCYqTpAB+NWvfoWDBw9iypQpuPfeewEA3d3dAICYmBi/73Eft9vtIfs/ffo0/va3v41QtUREEwOzc+BibuB1eBduli6H1+suex+27qzDH3cfQ2ZKHAwxOth7nEiM1+OZ++d5tR36tEnXRanGz7HgY6qtbaRd7HdHdKkaT9kZbh4YYnQ40ezKqeOnLF65FM5q01C/f395wIwgIqIJP0H28ssvY8OGDYiOjsZLL72ExMREAIBWq4WiKNBogv9lLFTsUTB16lRcc801quo5cuQIuroCPzmMiGiiYHZePHOc3u9xIRScaO70vM5O/8qojzncdkQUnvGUneHmgb3H6Tk2ycSMICKisTVhJ8icTieeffZZbNmyBXq9Hv/2b/+G2bNne87Hxsais7MTDocDer3vX9A9Pa7bUYxGY8ixbr/9dtx+++2q6lqxYsW4+Vc/IqJIYnZeHFkILJydgfKKUyHbLpiVGXBfn/E+JhF5Gy/ZGU4e3DArA20WO5paBibrmBFERDTWJuRaYpvNhh/+8IfYsmUL4uPj8frrr2P+/PlebZKTkwEM7EU2VKg9yoiIiCJJK0koyU8O+DQ4t4JMM0ryk0bkIjQSYxLR+BROHszMT8aH+xsh+vcZY0YQEVEkTLgJsgsXLmDFihX45JNPkJaWhs2bN3utHHPLy3M9/vnLL7/0OWe1WtHa2orExEQ+wZKIiMYtWSh4+r45AS9QCzLNePq+OZ7Nry/VMYlofFKTB2vuuRZnz9mwfV+D5xgzgoiIImFC3WLZ29uL+++/H59//jlyc3Px+uuvIzU11W/b6667Djt27MD//M//+Kwu27VrF2RZ9jlONFpueey9kG3ef/HWMaiEiC4lWkkDQ0wU1j98PSrr2rDrUBMsXQ6Y4/RYMCsTJflJI34LUyTGJKLxSU0edHT14M2Pj2L2lSnMCCJ3DAeSAAAgAElEQVQiiqgJNUH261//GpWVlUhLS8OmTZs8G/L7s3jxYrz44ovYtm0bvvGNb3gmw06ePIkXX3wRGo0Gd9999xhVTkRENDzui8zC3MkoyR/YFsC9OmM0LkIjMSYRjU/B8kAIgYS4GDxyV6nn2OD3EBERjaUJM0FmsViwadMmAEBiYiKef/75gG3Xr18Pk8mEtWvX4qGHHsIDDzyA2bNnw2g04sCBA+ju7sYjjzyCK664YqzKJyIiuihaSRryevQvQCMxJhGNT/7zQOPnGBERUWRMmAmygwcPep48+fnnn+Pzzz8P2Hb9+vUAgIULF2LTpk34zW9+g6qqKiiKgoKCAtx9991YsmTJmNRNRERERERERESja8JMkC1atAhHjx4N+32lpaV4/fXXR6EiIiKiAYqQoZG0AV9fbF+ABppBKzgGtxmJsUeyfiIiNcLNOn+viYiI3CbMBBkREdF4pAgBjSShu7EW1upyyNYOaE0JMBWVwZBd7Dk/En05bR04v3MToAiYCstgyCmGImQ4WhrQ+bcPhjX2SNZPRKRGqNyR7Z1QhAKdaRK6T9TCWsNsIiKi0DhBRkREFCGKEBAOG86+9RwcZ455nbPW7oU+PQ+py1ZD0htVTVSF7GvpkzBftxSnN/7Mq//opCz0nD4Kp6UlrLFHsn4iIjXU5o421oDmN55Fd0NVwDbMJiIiGox/IxAREUWIRpL8XuS5Oc4cw9m3nlN1Aaeqr60vIMqcgvjSxV79S7ooTLnpgbDHHsn6iYjUUJ07Wh306bnB2zCbiIhoEP6tQEREFAGKkGFvqAp4kefmOHMM9oZqKEKMTF/1VYifeSOgkbz6j828EpB0vu0DjD2S9RMRqXExWee3DbOJiIgG4QQZERFRBGgkLazV5araWqvLQ6zkCqOvmj3QTUpCdFKGd/+6KBjzZ6keeyTrJyJS42KzzqcNs4mIiAbhHmREREQRIls71LWzWdT1pZEQnZQBSW+AcNjR23YSULxXR7j7kvQGn2NaY8JAQ3dfhrgxqZ+ISA2v3AmSef6yzqcvZhMREQ3CCTIiIqIgFCFDI2kDvr4YWlNC6EYAtEZzyDZxpTci6Zb/A138FM8xZ2c7Ois+RmfFRxDdVq++hMPu079s64AUa0J86WLEly7y6svf5x7J+omIBguUvVpTQsCcGpx5/rJuKGYTERENxgkyIiIiPxQhoJEkdDfWwlpdDtnaAa0pAaaiMhiyiz3nh9+/DFNRGay1e0O2NRWVBR1PETJM0+fBXl+J87s3D9RaOB+JZcsRV7wQzW+uhdPSDFPhfDgvtLlWWgzu39kHR9spTP3BvyAqIcW3ryGfeyTrJyJyC5i9hWWInTYDcaWLYJ6/zH9ODco8Z9d5n6wbitlERESDcYKMiIhoCEUICIfN75PSrLV7oU/PQ+qy1ZD0xmFfWGkkLQzZxdCn5wXdcFqfngdDdlGIWu3Ba136JNLuWoP2Ha/CkFOM8+VveG5DcvdvP1GLtGWrIEXF4PTGJ1R87pGpn4jILVT2Jn3rRzAVzofosQbPqTtXIWZSATr2/cnnNnM3ZhMREQ3Ffy4hIiIaQiNJfi/Q3BxnjuHsW89d9KoDRQikLlsNfXqe3/PuCalgT1lTVevWFxBlTkHKHT9Dn6UFnZ995NW/cPah92w9ohJScHbrC6o/90jUT0TkFirPnNbzrjZbng+eU1ueh0aSoDUl+m3DbCIiIn+4goyIiGgQRcjobqwNuioKcF2E2RuqEZs14yJWkUmQ9EZMXbkO9oZq1+1ENgu0RnP/LY1FIW+tDKvWzCth+fRtGHKvHtS/DEfLCcQVlcFeXxn2576Y+omI3ELmmUZCXOH8sHIqrqgMuklTmE1ERKQKJ8iIiIgG0UhaWKvLVbW1Vpdf9C067gu02KyrvPpyr2wIdgE3nFqTv/Wj/v5lTx/6lGmuvmr2hNXXxdZPROQWKs+ikzKgi5+C87s3q+rPnVPMJiIiUot/MxAREQ0hWzvUtbNZRmzMoU+IVHvxNtxaB4/n/vPFfO7h1k9E5BYsgyS9IWQbr776c4rZREREavFvCCIioiG0pgR17YzmUa5ERQ0jWOul9LmJ6PITLIOEwx6yjVdfzCkiIgoTJ8iIiIj6KUKGImSYispUtTcVlY3YJs/uWx4DvQ70npGoNZKfm4gmJn+ZFyyDettOwtnZDlPhfFX9M6eIiChc3IOMaJx6/8Vb/f6ZiEaeImRoJC26T9RCOGwwTZ8HfXpe0I2g9el5F73/mGts10bR3Y21ro2krR3QmhL6N5IuDrqRtEbSwpBdPOxaB48tesb2cxPRxOQv86JTpsFctjx4nikCnRUfI7FsOXOKiIhGBSfIiIhoQlOEDOGw4+xbz8Fx5hikWBP0qV9F6tIncXbrC34vwvTpeUhdtvqin4KmCAHhsHnGHsxau9czjqQ3BnmSpUDqstV++whW69Cxx/JzE9HE5C/zpFgTpnzzh1Ac3XDaO4NmkOPMcSiyc1iZR0REFAonyIjGqfrnvhtW+5zV74xSJUSXN42k9brQEt1WNL+5Fml3rcHUletgr6+CtWYPZJsFWqO5f2VX0YhcfGkkKeBFHgA4zhzD2beew9SV64L2IemNrlobql0rMlTUOnTssfzcRDQx+cu8+NLFiEpIwemNT0DutgbOoML5MOQUo+9COwAwp4iIaMRxgoyIiCYsRcjoPlHrM0HltDTj9MafIb50MeJn3ojkWx8a9B7XnjYXe/GlCBndjb5jD+U4cwz2hmrEZs0Icqul63hs1lVetxUFqjXQ2GPxuYloYvKbOxoJ8aWLYK+v9BwPlEHOC204X/4GOj/7CNDAbxvR5+DkGBERDRsnyIiIaMLSSFpYa8r9nhPdVnR8+g469m1DdFIGjFfMg/m6O0bswksjaWGt9j/2UNbqclX76Wgk7ZDXgfcuCzT2aH9uIpqY/OVOdFIGdPFTcH73Zs+xwRlkLLgGKd/9Kc7t3owL+98FlIFN9wfnlKQ3QDjsiE7JRvK3fzxWH4mIiC4znCAjIqIJTbZ2BG+gCPS2NkJrnATgjrEd293OZhnRcVWNPYqfm4gmpqG5I+kNfo8DABQB2XYBANB75rjX5NjgNr2tjZ6XrrwiIiIaHv5zMBERTWhaU4K6dkYzxyYiughDc0c47H6Pqz3v0z/zioiILgInyIiIaMJShAxTYZmqtqaiMihCHtmxi8IZ28/qiUtwbCKamPzlTm/bSTg722EqnO/3PaHODzXSOU1ERBMLJ8iIiGjC0khaGHKKoU/PC9pOn54HQ3aRzx5fFz12djhjj9xf2ZEcm4gmJr+5owh0VnwMQ06J/zwKdX6Q0chpIiKaWPhfvERENKEpQkbqstUBL7706XlIXbZ6VFYlKEKoHHvkV3BFcmwimpj85U5nxUfos7QgdemTfvOos+IjODvPRSyniYho4uAm/URENKFpJC0kvQFTV66DvaEa1upyyDYLtEYzTEVlMGQXQRHyqKxK0EgSJL0xxNhiVFZwRXJsIpqYAuVO52cfwnz9nQHzSBc/GYqQI5LTREQ0cXCCjIiIJjz3RVVs1lUwZBd5jrtXI4zmRZd7Asp3bOF1/nIbm4gmplC5EziPIpfTREQ0MfC/fImIiPoNvcAaywsu37HH7q/oSI5NRBNToNwJlUeRzGkiIrq88b+AiYiIiIiIiIhoQuMEGRERERERERERTWicICMiIiIi+v/Zu/f4puu7///PJJS26QHKoZykUIRW1JaKWMFrIAMVcZfiF10HMqbM4fbbnHzVXVxTREAEubxwc6jXNg/z+sk8oYM5N89gcYLISWj9DSgnKZRTS1vpgZaST35/lISmTdKkTZo0edxvN29b8nl/kk9aDU9en/f79QYAAFGNAhkAAAAAAACiGgUyAAAAAAAARDUKZAAAAAAAAIhqFMgAAAAAAAAQ1SiQAQAAAAAAIKpRIAMAAAAAAEBUo0AGAAAAAACAqGay2+32UF8ELhg3bpxOnDihpKQkDR8+vF2vtXLlygBdFYBQmTlzZsBe65JLLtG8efMC9nrhJJDfnQDQFN+dAOC/SP7uROTqEuoLgKva2lpJUlVVlTZv3tyu18rMzAzEJQFA2AvkdycARAu+OwEAuIACWZi56KKLdOTIEVmtVg0aNCjUl+O3Xbt2qaqqijuRXvAz8o6fT+va+jO65JJLgnhVodXZvzub47+D0ON3EFrh9PPnuzO6hNO/e5GAn2fgdLafZSR/dyJyscQSATVz5kxt3rxZubm5LPH0gJ+Rd/x8WsfPKPLxOw49fgehxc8focK/e4HFzzNw+FkCwUeTfgAAAAAAAEQ1CmQAAAAAAACIahTIAAAAAAAAENUokAEAAAAAACCqUSADAAAAAABAVKNABgAAAAAAgKhGgQwAAAAAAABRjQIZAAAAAAAAohoFMgAAAAAAAEQ1y8KFCxeG+iIQWYYPH67c3FwNHz481JcStvgZecfPp3X8jCIfv+PQ43cQWvz8ESr8uxdY/DwDh58lEFwmu91uD/VFAAAAAAAAAKHCEksAAAAAAABENQpkAAAAAAAAiGoUyAAAAAAAABDVKJABAAAAAAAgqlEgAwAAAAAAQFSjQAYAAAAAAICoRoEMAAAAAAAAUY0CGQAAAAAAAKIaBTIAAAAAAABENQpkAAAAAAAAiGoUyAAAAAAAABDVKJABAAAAAAAgqlEgAwAAAAAAQFSjQAYAAAAAAICoRoEMAAAAAAAAUY0CGQAAAAAAAKIaBTIAAAAAAABENQpkAAAAAAAAiGoUyAAAAAAAABDVKJABAAAAAAAgqlEgAwAAAAAAQFSjQAYAAAAAAICoRoEMAAAAAAAAUY0CGQAAAAAAAKIaBTIAAAAAAABENQpkAAAAAAAAiGoUyAAAAAAAABDVKJABAAAAAAAgqlEgAwAAAAAAQFSjQAYAAAAAAICoRoEMAAAAAAAAUY0CGQAAAAAAAKIaBTIAAAAAAABENQpkAAAAAAAAiGoUyAAAAAAAABDVuoT6AuBqyZIl2r17ty655BLNmzcv1JcDAJ0C350A4D++OwEAuIACWZjZvXu3Nm/eHOrLAIBOhe9OAPAf350AAFzAEksAAAAAAABENQpkAAAAAAAAiGoUyAAAAAAAABDVKJABAAAAAAAgqlEgAwAAAAAAQFSjQAYAAAAAAICoRoEMAAAAAAAAUY0CGQAAAAAAAKIaBTIAAAAAAABENQpkAAAAAAAAiGoUyAAAAAAAABDVKJABQAjYDMPrYwAAAAQfmQyAQ5dQXwAARBObYZfFbFLhvjKt3XJYFVX1SkmK1cSrBionI9V5HAAAAMFDJgPQHAUyAOggNsOu2roGLXphk/YUV7gcy99+RJlpKVowe7SscTEEMgAAgCAhkwFwhyWWANBBLGaT2yDmsKe4Qote2EQQAwAACCIyGQB3KJABQAewGYZ2FJ30GMQc9hRXaEdRqWyGvYOuDAAAIHqQyQB4QoEMADqAxWzW2i2HfRq7bmsxdywBAACCgEwGwBMKZADQQSqq6gM6DgAAAP4jkwFwhwIZAHSQlKTYgI4DAACA/8hkANyhQAYAHcBmGJp41UCfxk4YlUa/CwAAgCAgkwHwhAIZAHQAi9msnIxUZaalSJLMZpMG90vWpek9NLhfsszn+1tkpqUoJ6M3/S4AAACCoHkm84RMBkSfLqG+AACIFjbDrgWzR+vzHUc16tI+6t093nmstPKMtv7rhL6T0182w04YAwAACBJHJlv0wia3u1lmpqVowezRUZHJbIYhi9ns8TEQTSiQAUAHsZhNssZ10eRrBuuropN65R//UkVVvVKSYjXhqoGafM3g86EksoMYAABAKDVmshgtnzNOO4pKtW5r8YVMNipNORm9I7445vh8hfvKtHbLYefnn3jVQOVkpEb85wfcoUAGAB3EZthVW3fO7d3K/O1HnHcrrXExBBIAAIAgcmStrKE9lZPR2/m8o+dYJGexxkzaQCYFmmHuJAB0EIvZ5HEqvyTtKa7Qohc2EUQAAAA6SPPlhNGQw8ikgHsRVyBbvXq1MjMztXXrVrfHDx48qAceeEDXXnutRowYoZtvvlkrV66UYRhux584cUKPPvqoJk6cqOzsbE2aNEnPPfeczp49G8yPASDC2AxDO4pOegwiDnuKK7SjqJQdkwAAABBwZFLAs4gqkH311VdavHixx+O7d+/W7bffrn/84x/q37+/xo4dq+PHj+vxxx/X3LlzW4w/fvy48vLy9Oabbyo5OVnjx49XTU2NVqxYobvvvlsNDQ3B/DgAIojFbNbaLYd9GrtuazF37AAAABBwZFLAs4jpQfbhhx/qoYceUm1trdvjdrtdc+fOVXV1tZ588klNmTJFklReXq677rpL7777rq6//npNmjTJec7ChQt1/PhxzZkzRz//+c8lSbW1tfrFL36hjRs3auXKlfrxj38c/A8HICJUVNUHdBwAAADgLzIp4F6nn0F2/PhxzZ07V/fdd58Mw1CvXr3cjtuwYYP27Nmj3NxcZ3FMknr06KGFCxdKklauXOl8/sCBA8rPz1daWpp+9rOfOZ+3Wq1asmSJLBaL/vznPwfnQwGISClJsQEdBwAAAPiLTAq41+kLZE8//bTeeecdXX755XrzzTc1ZMgQt+P++c9/SpKuu+66FsdGjhypnj17atu2baqurpYkff7557Lb7frud78rc7PGjf3799ell16qkpIS7du3L8CfCEAkshmGJl410KexE0al0e8BAAAAAUcmBTzr9AWyIUOG6L/+67/01ltvKTMz0+M4RyErIyPD7fH09HQZhqH9+/e7jB82bJjH95WkoqKiNl87gOhhMZuVk5GqzLQUr+My01KUk9Gbfg8AAAAIODIp4Fmn70F2zz33+DTu5MmTkqTevXu7Pe54vqyszGV8amqqT+O9Wb16tdasWePTde7atcuncQA6H5th14LZoz1uq52ZlqIFs0fLZtgJI+K7EwDagu9OAK0hkwLudfoCma/OnDkjSYqLi3N73PG8o8m/v+O9KSkp0ebNm/27YAARx2I2yRoXo+VzxmlHUanWbS1WRVW9UpJiNWFUmnIyehNEmuC7EwD8x3cngNaQSQH3oqZAZrFYJEkmk/f/yA3DaNN4bwYMGKDc3FxfLlO7du1SVVWVT2MBBIbNMGRp0muw+eNAcgSNrKE9lZNxYUaro78DQeQCvjsBwH98dwIdpyMzZKCRSYGWoqZAFh8fL0mqq6tze9zxfEJCgl/jrVZrq+89depUTZ061afrnDlzJnf9gA7iuDNWuK9Ma7ccdt45m3jVQOVkpAb1zlnz8EQIaYnvTgDwH9+dQPCFMkMGGpkUuCBqCmSpqanatWuXysrKdPHFF7c4XlpaKulCbzFH7zFPPcYc4z31KAMQ3myGXbV1DW57L+RvP+LsvWCNiyEoACF284PvBOR13n1qSkBeBwAQvciQQOTqHPM/A8CxG6Vjd8qm7Ha7Dhw4IIvF4iyeeRsvybnbpaddMQGEN4vZ5LExqSTtKa7Qohc2EWwAAADgRIYEIlfUFMjGjh0rSVq7dm2LY9u3b1d5ebmuvPJKJSYmuoz/9NNPW/QZO3r0qHbt2qUBAwZo6NChQb5yAIFmMwztKDrpMdg47Cmu0I6iUmcvBgAAAEQvMiQQ2aKmQJabm6thw4Zpw4YNWrVqlfP58vJyLVq0SJI0a9Ys5/MDBw7U2LFjdeDAAf3ud79zPl9bW6tHHnlENpvNZTyAzsNiNmvtlsM+jV23tZg7gAAAACBDAhEuanqQmc1mLV26VHfeeafmz5+vt99+W6mpqdq8ebO+/fZb5eXlacKECS7nLFiwQNOnT9cf/vAHrVu3Tunp6dq+fbtKS0s1btw4TZ8+PUSfBkB7VVTVB3QcAAAAIh8ZEohcUTODTJKys7P11ltvadKkSTp06JA2bNig/v37a9GiRVq4cGGL8QMHDtRbb72lqVOnqry8XPn5+erWrZsefPBBPfvss+rSJWrqi0DESUmKDeg4AAAARD4yJBC5Iq7Cs3LlSq/Hhw4dqhUrVvj8ev369dMTTzzR3ssCEEZshqGJVw1U/vYjrY6dMCqtU23VDQAAgOAgQwKRLapmkAGA1Ng/IicjVZlpKV7HZaalKCejN8EGAAAAZEggwlEgAxCVbIZdC2aP9hhwMtNStGD26DbvPmRrtvtt88cAAADofIKdIduD/Am0T8QtsQQAX1jMJlnjYrR8zjjtKCrVuq3FqqiqV0pSrCaMSlNORu82TYt3nFO4r0xrtxx2vubEqwYqJyOVqfYAAACdWLAyZHuQP4HAoEAGIGo5gkLW0J7KyejtfN5xx68txbHaugYtemGT9hRXuBzL337EeUfRGhdDSAEAAOikAp0h24P8CQQOSywBRIT2TCm3mM3NHrctPFjMJrfhxGFPcYUWvbCJcAIAANDBgrH8MFAZsn3XQP4EAoUZZAA6tXCZUm4zDBXuK/MYThz2FFdoR1Gpsob2IqgAAAAEWbhkxWAgfwKBRYEMQKcVTlPKLWaz1m457NPYdVuLXabjAwAAIPDCKSsGA/kTCCyWWALotMJtSnlFVX1AxwEAAKDtwi0rBgP5EwgcCmQAOiWbYWhH0Umfp5R3xFbbKUmxAR0HAACAtgnHrBgM5E8gcCiQAeiU/J1SHow7g02bu9oMQxOvGujTeRNGpXXaEAYAANAZBCorBqO5f6CQP4HAogcZgE4rVFPK3TV7vXHMIH1nxABlpqV4vVOZmZZC/wcAAIAO0J6s2Bma+1vMZuVkpJI/gQChQAag0wrFlHJPzV4PlFRq6EXdNf/uq7X4pS/dhhRHI9hwCFQAAACRrq1ZsTM197cZdi2YPdpjrzXyJ+A7CmQAOiXHlPL87UdaHeuYUh6IUOCp2WtVbYMeff4LPXbPGC2fM047ikq1bmux827jhFFpysnoTTgBAADoAO3Jir42918+Z1xAr7ktLGaTrHEx5E8gACiQAeiUQjGl3GYYKtxX5vH9jpXV6IGn12vymHR9/7phLu/r6PlAOAEAAAi+tmbF1vKeg6O5f9bQXiHPd473zxrak/wJtANN+gF0Wo4p5ZlpKW6PN51SHgi+NHutqm3QqrVF+v1fdjY7l2ACAADQkdqSFcNhI6i2spjNzR6Hz7UBnQEzyAB0WqGYUu5rs9fy04HdGAAAAAD+aWtWDNVGUABCiwIZgE6to6eUh2JjACAQDiy5rc3nDpn3lwBeCQAAHactWZG8B0QnllgCiAgdMaXc0ezVF45mrwAAAAg9X7MieQ+IXhTIAMBHTZu9euNo9krfBwAAgM6FvAdELwpkAOCHjt4YAAAAAB2LvAdEJ3qQAYAfQrExAAAAADoOeQ+IThTIAMBPvjR7tRmGS6+L5o8BAAAiVSTkoI7eCApA6FEgA4A2ctfs1XE3sXBfmdZuOey82zjxqoHKyUjlbiMAAIhYkZiDOmIjKADhgQIZAASIzbCrtq5Bi17YpD3FFS7H8rcfcfarsMbFEK4AAEBEIQcB6Ow61zxXAAhjFrPJbSh02FNcoUUvbCIUAgCAiEMOAtDZUSADgACwGYZ2FJ30GAod9hRXaEdRKbseAQCAiEEOAhAJKJABCBs2w/D6OJxZzGat3XLYp7HrthZz9xQAAARFKPIUOQhAJKAHGYCQi5SGrhVV9QEdBwAA4KtQ5ylyEIDOjgIZgJCKpIauKUmxARkXCVujAwCAjhMOeSpQOShakPeA8MN/gQBCKlIautoMQxOvGujT2Amj0tz23nA8V7ivTE+9uk2P/GGjnnp1mwr3lbkcBwAAaCrUeSoQOShakPeA8MUMMgAhYzMMFe4r87mha9bQXmFbKLOYzcrJSFVmWorXz5OZlqKcjN4tng+HO78AAKDzCYc85chB40depM92lMjwUOTxlIOiBXkPCG/MIAMQMh3V0LWjmtXaDLsWzB6tzLQUt8cdocfdncFQ3/kFAACdU6gb5DfNVQ/OuFL/++gNyrsuQ0nWGJdx3nJQtCDvAeEt6maQNTQ0aOXKlfrrX/+qb775RklJSRoxYoTuuece5eTktBh/8OBBPfPMM9q2bZsqKyuVlpamvLw8zZgxQ2bWiAPtFsyGrh3drNZiNskaF6Plc8ZpR1Gp1m0tdr7nhFFpysno7fY9w+HOLwAA6LxC0SDfW86aOXm4bv5Oul7++79kt9u95qBoQd4Dwl9UFcjOnj2ru+++W5s3b1ZMTIyys7MVHx+vL774Qvn5+Xr00Uc1bdo05/jdu3drxowZqq6u1siRI5WVlaUvv/xSjz/+uHbu3Knly5eH8NMAkSFYDV1DNYXd8VpZQ3u6LCFw3C11917+3vmN5qUJAACgpY5ukO9rzrrvB1fIYjZ5zUHRgrwHhL+omgL1P//zP9q8ebMGDBig1atX67XXXtNLL72k999/X0OHDtVjjz2m3bt3S5Lsdrvmzp2r6upqPfnkk3r99df17LPP6sMPP1RmZqbeffddffjhhyH+REDnFsyGrqGewt58F6LW3oet0QEAQFuEokG+vzkrmgtjTZH3gPAWVQWyt99+W5K0ePFiZWRkOJ/v27evFi9eLJvNpmeeeUaStGHDBu3Zs0e5ubmaMmWKc2yPHj20cOFCSdLKlSs77uKBCNS0sb03joauvoYrm2FoR9FJn6ewh0MvDLZGBwAAbRGsPOVJZ8xZ4YK8B4S3qCmQlZeXq7S0VHFxcRozZkyL447llhs2bJDNZtM///lPSdJ1113XYuzIkSPVs2dPbdu2TdXV1UG/diCStaexvSehblbrL7ZGBwAA7RGMPOVJZ8tZ4YK8B4S/qOlBZpzfXSU+Pt5tc32TySSz2ayamhodPXpU+/btkySXmWZNpaen69SpU9q/f79GjBgRvAsHIlxbG9u3pjNNYW9659fb3dho3xodAAC4F6w85UlnylnhgrwHhL+oKZD16NFD3decUxMAACAASURBVLp1U0VFhfbv36+LL77Y5fju3btVU1MjSaqoqNDJkyclSb17u/9ycjxfVlbW6nuvXr1aa9as8ek6d+3a5dM4wFd2wyaT2eLxcThoS2P71oR6CrvNMFz6kDV/3HJ8451fT/08mt75jZY7sXx3AoD/+O6MLk1zncVskt2wKTuAecqTUOeszsqfvCfZvWZHAIEXNQUys9msW265RStXrtR//ud/6rnnnlOfPn0kNRa5Hn30UefYs2fP6syZM5KkuLg4t6/neL62trbV9y4pKdHmzZvb+xEAv9gNQyazWWcOfa3qgnzZqitlSeyuxOzxsqaPcB4PJ/42tvfEMYU9f/uRVsc6prAHKjR62/I8JyPV43t19J3fzoDvTgDwH9+d0cGfnBfo7BDKnNXZ+ZL3Tn1bp1Wf/H+68pJUr9kRQOBFTYFMkv7v//2/2rZtmwoLC3XjjTcqJydHZrNZO3fuVO/evTV69Ght2rRJXbp0kcXSeCfGZPL+ZeRYuunNgAEDlJub69M17tq1S1VVVT6NBTyxG4aM+hodf2OJ6o/udTlW/fVniu0/TH2nzZM5NiHsimSBEKop7L5ueW6Ni/FYJJMCO5OuM+O7EwD8x3dn5At1zmOpYPt4ynulFbVa+d4uvbfxoKrPNOiv6/e3mh0BBFZUFcgSExP16quv6o9//KP+/ve/a8uWLUpNTdW0adP0s5/9TPfdd58kKSkpSfHx8ZKkuro6t6/leD4hIaHV9506daqmTp3q0zXOnDmTu35oN5PZ7DY0OdQf3avjbyzRgFnLOvjKOk4oliz6uuX58jnjWnmdwMyk6+z47gQA//HdGfnCIefRGqL9HHnvubd2aPehChWfqJLRrDG/r9kRQGBEVYFMkqxWq+6//37df//9LY4dOHBAJpNJ/fr1U2pqqnbt2qWysrIW/cokqbS0VJLnHmVAqNgNm84c+tpjaHKoP7pXtQcLFD/o8gidRdaxSxZthqHCfWU+b3meNbQXgREAAPglXHIerSHaz5EdP9h0yOs4siPQcaKqQLZ3716VlJTommuuUdeuXV2OHTp0SMeOHdPFF18sq9WqYcOGaf369dq3b5+uvvpql7F2u10HDhyQxWJxWzwDQslktqi6IN+nsdUF+bKmZwf8GvxtUB8sHblk0d8tz1lyAAAAmmstQ4VDznOgNUT7kB2B8BNVBbLf//73+sc//qGXX35Z11xzjcuxN954Q5J04403SpLGjh2rF198UWvXrtWMGTNcxm7fvl3l5eXKzc1VYmJix1w84AdbdaVv42q8z3by+33b2KA+2DpqySJbngMAgLbwJ0OFKud5QmuItiM7AuElqgpkEydO1D/+8Q/97ne/U05OjqxWqyTpk08+0SuvvKLk5GTdddddkqTc3FwNGzZMGzZs0KpVq5SXlydJKi8v16JFiyRJs2bNCsnnAFpjSezu27iElIC9Z3sb1EcCtjwHAAD+8jdDhSLnITjIjkB4ibzGQ15873vf07XXXqsdO3bohhtu0L333qvvf//7+sUvfqGYmBg9++yzSk5OliSZzWYtXbpUVqtV8+fPV15enu69917deOON2rNnj/Ly8jRhwoQQfyKgJbthU2L2eJ/GJmaPl92HnVh94WuD+kgtjjm2PPeFY8tzAAAAfzJUqHIeAo/sCISfqCqQSdKKFSv0s5/9TF27dlV+fr5OnTqlW2+9VatXr27Rayw7O1tvvfWWJk2apEOHDmnDhg3q37+/Fi1apIULF4bmAwCtMJktsqaPUGz/YV7HxfYfJmt6dkAat9oMQzuKTvrcoD4S/4BvuuW5N44tzyO1UAgAAHznb4ayy9zhOQ/BQXYEwk9ULbGUpLi4OI+7WLozdOhQrVixIshXBQSW3TDUd9o8j1uAx/Yfpr7T5sluGAEJTjQZbcSW5wAAwB9tyVAdnfMQPGRHILxEXYEMiAYms1nm2AQNmLVMtQcLVF2QL1tNhSwJKUrMHi9renbAQxNNRtnyHAAA+M/fDBWKnIfgIDsC4YUCGRChHKEoftBlLlt8O3pRmMxm2Q2bTGZLk2Ouj/1Bk9FGbHkOAAD80ZYM5UvO81Ug8yD8R3YEwgcFMiDCNQ84jYWxxruKZw593XjXsbpSlsTu5+86jvD7rqOjyWj+9iOtjnU0GY30P+zZ8hwAALSmvRnKXc7zVaDzINqH7AiEHgUyIMrYDUNGfY3bvhXVX3/m7Fthjk3wORQ1bTLqrcmso8koAAAAQpehgpEHAaCz49sOiDIms9ljU1dJqj+6V8ffWOJ3GHI0GfW0E0/TJqMAAABoFIoMFaw8CACdGTPIgChiN2w6c+hrj2HIof7oXtUeLFD8oMv9mEVGk1EAAAB/dXSGCmYeBIDOjAIZECZshuHSe6D540AwmS2qLsj3aWx1Qb5L01dfRGKT0Y74vQAAgMjka47oyAwV7DzY2ZD1ADhQIANCzHFHsHBfmdZuOey8YzjxqoHKyUgN+KwrW3Wlb+NqPPfBaE0kNBnt6N8LAACIHG3NER2VoToiD4Y7sh6A5iiQASFkM+yqrWvQohc2tWjMmr/9iLPnhDUuJmB/QFsSu/s2LsF9H4xoEIrfCwAAiAyOHLH4xU06c9Yma1wX1dadU+H+srDJEdGeB8l6ANxh7igQQhazye0fzA57iiu06IVN7fqD2WYYzv9vN2xKzB7v03mJ2eNlb3Ju09eJdB3xewEAAJ1D8wzUWiaymE36fMdR/cePrtIzv/qu/uvesXrmV9/Vi/OuV951GTpaVh3SHNGePBgpyHoA3GEGGRAiNsNQ4b4yr1t6S41/QO8oKlXW0F5+/SHtbtr4jWMG6TsjRii2/zCvjVlj+w+TNT1bn+8o0QebDkXVdPNg/14AAEDn0JYleDbDUEODocnXDNZXe07qlX/8q0nD/YGaOXm4rs9N06PPfxGyHGEyW2RN9z0PRhqyHgBPKJABIWIxm7V2y2Gfxq7bWuzSsLU1nqaNHyip1LCLuin1B/N08k33W3vH9h+m1B/M04lT1Xru7Z2qPtMgKTymmweriWrT17GYzRoyoJvyrsvQ+xsPqqq2weN5/v5eAABA59D2JXgmnT1n0yN/2OjxvPl3X63H7hmj1Z/ubdaQv+OaxdsNQ32nzdPxNzznwb7T5sluGB2yg2VHfvZgZnAAnRsFMiCEKqrqAzrOwdO08araBs1/fpMW3zNaA2YtU+3BAlUX5MtWUyFLQooSs8fLmp6tE6eqNf/5Tc7imINjuvnyOeP8up72ClYTVU+v2/wO77GyGrfn+/t7AQAAnYOvS/CaZyKL2aTHXvzS63mLX/pSy+eMU0ZaY3+vUDSLN5nNMscmeM2DHVEcC1Wj/GBlcACdGwUyIIRSkmKd/99sNimtT5KzkWvxiSoZ57f2bjquNa1NGz9WVqP7n/5Mk8ek6wfXDVdqk6nzZ882aOV7u/TexoMtimMOHT3dPFhNVH15Xccd3geeXu92Jpk/vxcAANA5tHUJnj/nfVV0UrmX9nXmkefXFOpkRa1LBgz27H1H8St+0GUuSykdPcc6ojgWqkb5vmY4sh4QXWjSD4SIzTA08aqBSrLGKO+6DP1p3kSXRq5/mjdReddlKMkaowmj0mQ7XyxrjS/TxqtqG7RqbZGe+0uBy/PPvl2gVWuLPBbHHNZtLe6wJZbBaqLqy+sufulL9e2ZoMlj0t2O8ef3AgAAOgd/l+A5Mog/53269bCSE2NlMZtk2Gx6cMaVbjNgRzSLN5ktzR53zF8RQ9Uo35HBfUHWA6ILM8iAELGYzcrJSNVzvxqvlG5W1RzYqZPr82WrrpQlsbsSssZr5uQR+t41g9Sjm9Wv1/Z1Onj56Xqvj9v7+u0VrCaq/t7hvXHMIL396V7njD5JykxLoScFAAARqq1L8Hw9z2I2yW7YZDJb1KW0SCfXtcyAN+QO1PznN0Vks/hQNsp3ZPDMtBSv70/WA6IPBTIghOyGTcldbSp5+dctGqRWf/1ZkwapthZ397xp67TxcJtuHqwmqv7e4X3gjiuV1idJ3xw7LUnOKf+RvqMnAADRKphZKskao7tvvkxGfa3bJvmODJia97AW3zNa9z/9WcQ1iw91o3ybYdeC2aM9zmAj6wHRiQIZEEIms8Xj7kGSVH90r46/sUQDZi3z+TUd08bztx9pdaxj2rijb0Zbzgu2YDVR9fd1RwzrpfT+yZowKk05Gb0JTAAARKhgZ6nJ16QrMSFWJS8v8JoBT65aqgGzlmnymHQVHfY+06ozCmWjfIvZJGtcjJbPGacdRaVat7W4yWZNZD0gWlEgA0LEbth05tDXHoORQ/3Rvao9WKD4QZf71BOirdPGw3W6ebBmtfn7uj+ZkiVJzj4UBCYAACJTMLOU2WzSLd8ZrNqDO33LgAd2avKYoSr7trZtHyaMhXrlgiPLZQ3t6fJ7JOsB0Ysm/UCImMwWVRfk+zS2uiDfr4apjmnjmee3D2+u6bTxQJwXLMFqotqe1yUsAQAQ+YKVpcblDFC3pHjfM2DhevVKadwwKJKaxYdTo3xLs4xN1gOiFzPIgBCyVVf6Nq7Gv2n1bZ02Hm7TzYM1qy1cZ8sBAIDwEMwsJfmfAS8Z3COwHzDEyGIAwhEFMiCELIndfRuX4P4upNdz2jhtPNymmweriSrNWQEAgDfBylKS/xkwEvMIWQxAuAlKgezIkSN66aWX9NVXX6myslL19Z4bK5pMJm3cuDEYlwGENbthU2L2eFV//VmrYxOzx8tuGH4ts3Ro67TxcJluHqxZbeE2Ww4AAISnQGcp/zOgTRY/djPvLMhiAMJNwAtkhw8f1m233aaqqirZ7a2vFTeZ+MJDdDKZLbKmj1Bs/2Eem7Sa4xPVY/wMxQ+6zKU4ZjdsMvkYlJqP9efccBGsWW3hNlsOAABEpqb5y2S2KH7Q5eo1+acqz39Vxplqt+fE9h8ma3p2i/PdPe6syGIAwknAC2TPPPOMTp8+rd69e+vOO+/U0KFDZbVaA/02QESwG4b6Tpun428saVEk65LST/1nPqYuST1Ue3CnqgvyZauulCWxuxKzx8uaPsLrrDLHsTOHvvb73HAVrFlt4TJbDgAARBZveSx55A2yDr1SR/+8QOcqjrmcF9t/mPpOf8RZCIukPOcOWQxAOAh4gWzjxo2KiYnRypUrNXjw4EC/PBBRTGazzLEJGjBrmWoPFjQGn5oKdeneTz2v+5HstgaVvPzrFsWz6q8/awxO0+bJHJvQIhjZDUNGfY3bwltr5wIAAKD9HHms7MM/yXa6VEZ9rc6WHpbshkseu+gny3Xqk1d0rvKYLAkp54tf2bIbNhn1teQ5AOggAS+QnT59Wunp6RTHELG8TXFvbfq7t8fxgy5zTqN3KHl5ocfll/VH9+r4G0s0YNayFsdMZrPbMOXLuQAAAGgb16WUZpm7xqvPrXOcx8+dLtPp7R/p9PYPXfJY75vuafIaxvnzLeQ5AOhAAS+Q9evXT7W1tYF+WSDkfFmyWFdSpKrtH7k55sv0eNfC2ZlDX3sMRA71R/eq9mCB4gdd7rxz2J5zAQAA4D+POTFrvKxDRuhcVbm+/fJdxQ8ZoR7j71DSiIk69vpit3nMZDaT5wAgBAJeILvpppv0hz/8QRs2bNC//du/BfrlgZDwacniDx5Wl8Qeqt2/3dlstXb/dl00+7cydYnxa3q8yWxRdUG+T9dWXZDvMvOsPedGKpthuPS2aP4YAACgrXzKiXkPKfnKG1Xy8lzFpPRT37yH1G/6fJW8PNdtHovWPEdmAxBKAf+2mT17tjIzM/Xggw/q3XffVU1NTaDfAuhwPi1ZfHOpYlL6KHnkJOfzySMnqUtSD5+mxze/62errvTp2mw1FS2fa8e5kcSxA1LhvjI99eo2PfKHjXrq1W0q3FfmchwAAKCtfMqJq55w5sTmjz3lsWjKc2Q2AOGgXTPIxowZ4/b5s2fPqra2VnPnzpUkWa1Wde3a1e1Yk8mkjRs3tucygKDya4r7gZ1KvuJ6VW5cI0lKHnmDag/saNP0eEtid5+uz5KQ0vK5dpwbKWyGXbV1DVr0wibtKXYNjvnbjygzLUULZo+WNS6GnZIAAECbtDUnNn1cfvqU23OiJc+R2QCEi3bNIKuoqHD7T01Njex2u/Ofmpoaj2MrKjr/HQ9ENr+muBeuV5duvdW190B17T1QXZJ7qbpwvW/nFuS79BFLzB7v03mJ2eOdzVzbe24ksZhNboOWw57iCi16YRNBCwAAtFlbc2LTx0kjJ7XIY9GU58hsAMJFu2aQvfLKK4G6jg71zjvv6NVXX1VRUZEMw1B6erqmTp2qH/7wh7JYLC5jDx48qGeeeUbbtm1TZWWl0tLSlJeXpxkzZsjMevio4TLF3WRW194DZY61umzXLV2Y4m6Otbo/19t7NJkebzJbZE0fodj+w7zekYztP8xtz4q2nhspbIahwn1lHoOWw57iCu0oKlXW0F6ELgAA0Cbm+GR1TR3kkgndaZ4THY/jL8poMTZa8hyZDUA4aVeBLDc3N1DX0WGefPJJvfTSS+ratauuuuoqWSwWbd26VUuXLtXmzZv17LPPymRq/NLdvXu3ZsyYoerqao0cOVJZWVn68ssv9fjjj2vnzp1avnx5iD8NOoolsbvM8YlKHjlJySNvUJfkXs5jTbfrdkxxN+prXc716T2aTY+3G4b6TpvnsaeFo7m/Y9ekQJ3r0JmbpFrMZq3dctinseu2Fisno3eQrwgAAEQaxy7lvW6YJck1Ezo2bGqqeU50PPaUxwKR58IdmQ1AOAn4LpYPPfSQ0tPTdc8997Q69vHHH9eePXu0cuXKQF+GW7t379af/vQn9ejRQ6+99prS09MlSSdOnND06dP1ySef6KOPPtKkSZNkt9s1d+5cVVdX68knn9SUKVMkSeXl5brrrrv07rvv6vrrr9ekSZO8vSUigN2wKWnkDUq5dppiuvdR7YEdKv/01Sbbd1/r3K77XFW5zn1b2ngHUY1BKTHrWlV//Vmr7+OYHt90i29zbIIGzFqm2oMFjVuG11TIkpCixOzxsqZnewxE7TnXZthlMZtUuK9Ma7ccVkVVvVKSYjXxqoHKyUh1Hg93FVX1AR0HhIubH3zHr/HvPjUlSFfS+R1Yclubzx0y7y8BvBIAnYkjQ5059HVjxnKTCY+9vljnKo65nJeYda1LTmzMfo1FNnfak+c6EzIbgHAR8ALZmjVrdOWVV/pUIPvyyy9VXFwc6Evw6IsvvpDdbtctt9ziLI5JUp8+fXTHHXfov//7v7VlyxZNmjRJGzZs0J49e5Sbm+ssjklSjx49tHDhQk2fPl0rV66kQBYFTGaL4gZkyqirVsnLv/a8ffcPHlZct0xVblztnF5/evtH6jH+jjZPj3cEnvhBl7kcd/SZ8BaI2nJuJDVJTUmKDeg4AAAAu2HIqK9xO6vLmQnzHlK/6fNV8vJc50yy2P7DZB0yQuX5r0l2w+elke3Jgp0FmQ1AuGhXgeybb77RqlWrWjxfUlKiJ5980uN5drtdR48e1d69e9WrVy+P4wLNsXTyxIkTLY45Ngvo3r1xOdw///lPSdJ1113XYuzIkSPVs2dPbdu2TdXV1UpMTAzWJSNMmMxmHX9zqfftu99cqgGzlrk8f3r7h0oeOand0+Ob31n0Jwx5O7f5XUuzDH2+46iOlrVcFiBdaJK6fM44n98/FGyGoYlXDVT+9iOtjp0wKq3TzIoDAACh48hqnjKddD4TrnpCA2YtU/LISarc8Bdn0ayh4oROb/uwTUsj25oFm2c9bzPWQoHMBiCctKtANmjQIG3atEm7du1yPmcymXTixAm9/PLLXs+12+2SpJtvvrk9l+CXsWPHatmyZfrggw/0/PPP6/bbb1eXLl300Ucf6ZVXXlG3bt10222Nyy327dsnScrIaNk0U5LS09N16tQp7d+/XyNGjOiwz4CO59f23QcLlDzyBtUd/pcs1u5KzB6vLsk9ZTdsYTU93vPSgPGafM0IjczspfnPb9KxspoW53aGJqkWs1k5GanKTEvx2vQ1My2FXhYAAMArR26y2xp05pvdvmXCAzvVLfffFTfoclnTs3Wuqlynt32g1KkPdkj285j1ssfLmj4ibJZmktkAhJN2FchMJpMee+wxvfrqq87n1qxZo169emns2LFez7NarcrMzNTUqVPbcwl+ufjii7V48WItWbJETz31lJ566innsSuuuEJPPPGE+vXrJ0k6efKkJKl3b/dfxI7ny8rKWn3f1atXa82aNT5dY9NiI8KDX9t3F+TLOuU+9Zv+qCTp3Lel+nbbh0q89BqZYxO8To/vqKb4viwNSM17WIvvGa37n/5MVbUNLV6jMzRJtRl2LZg92uO24Y7lotyJDF98dwKA//juDCxHbir78E/qc+scVRfm+3RedeF6WYeMUPygyyRJXZJ6qOd1d3rNfoG+Zq/LQKfNkzk2ISyKZGQ2AOGi3T3ILr/8cj3xxBPOx2vWrNGgQYNcngsnI0eO1JgxY7Rp0yZlZ2fLbDZr586dKiws1GuvvaaHH35YJpNJZ86ckSTFxcW5fR3H87W1tW6PN1VSUqLNmzcH7kOgw9mqK30bd3677rIPXlDd4V3O7b6rCz5tsfxScoSjjm2K78vSgJOrGpeLTh6TrlVri1qM6QxNUi1mk6xxMVo+Z5x2FJVq3dZi5892wqg05WT0JmiFOb47AcB/fHcGliM3mSyNf23yNxP+v+/v1v8Zd7G6JcVp1zen9P7Gb1R+OvRZ7/gbS9xm01AgswEIFwFv0r927VrFxoZnA8UdO3boxz/+sQYMGKC///3vGjBggKTGnmT33nuvXnnlFSUmJmrOnDmyWBrX5jv6lnlinL8L5M2AAQOUm5vr0zXu2rVLVVVVPo1Fx7Ekdvdt3PntuusO79LZk4eczzuWX8YPutzlTl1HN8X3a7nogZ2aPGao3v50rwzD7nK8szRJdfzMsob2dJnxZjv/eQha4Y3vTgDwH9+dgdM0N3VNHSTJ/0x487+ly2wx67m3dmj3oQoVn6hy5qqQZz032TRUyGwAwkHAC2SOolM4Wrp0qWpqarRkyRKX6+zTp49+85vf6MYbb9T//u//6p577lF8fLwkqa6uzu1rOZ5PSEho9X2nTp3q81LSmTNnctcvQALVlNRu2JSYPV7VX3/W6tjm23c3VV2Q32K3IovZ5HE6uRT4pvh+LRctXK/UKSOU1idJ3xw77XKsszVJbb58obNcd7TjuxMA/Md3Z+A0zU1nSw/r3OkyJWZd63MmPHu2QT2SY2UyW/SL7+dIkk5V1ui9L4r1/saDqqptCG3Wc5NNQ43Mhkjz61//WmvWrNGbb76pnJwct2NWr16thx56SA8++KDuueeeDn9/XBDwAtnEiRN9f/MuXRQbG6vevXtr+PDhmjp1qoYMGRLoS5LUWNAqKChQcnKysrNb/kEwcOBApaena+/evTp06JBSU1O1a9culZWV6eKLL24xvrS0VJLnHmUInaZNSeu++VpGw1mZY7oqbvDlbWpKajJbZE0fodj+w7zejWu+fXdzjqn2zseGocJ9ZV4bkkqBb4rv79IAa5zr1wRNUgEAQLQwdYmVTGbJbuj09o/UY/wdPmdCSao7uk+1e75U/bH9siR0U0LWeM2cPEI35A50bogU6qwHILSGDx+ue++9VyNHjgz1pUS9gBfISkpK/D6nqKhIGzdu1MqVK7Vo0SLdeuutgb4sVVVVyW63y+ylMOJYVtnQ0KBhw4Zp/fr12rdvn66++mqXcXa7XQcOHJDFYnFbPEPHcTdLzG47p+rCjYpPz5I1/cIOo+dOl+n09o+UMHyM301J7YahvtPmeezn0Hz7bnccU+2dj81mrd3ScqaZO4Fsiu/v0oDaunPO52iSCgAAIl3TfNn7ez9TytjbdXr7R6r+1+dKGjFRffMe0vFVT3jOhNPmOV8jrv9QxfUf6syhpX/9jSpT+rXYECmUWQ9AaA0fPlzDhw8P9WVAQepBtmTJEq1bt05ZWVmaNm2aLr30UiUkJKimpkZFRUV6++23tWXLFmVlZemuu+7S6dOn9dlnn+nTTz/V/PnzlZmZGfB/QXr27Knu3bursrJSBQUFLWaRnThxQvv371dMTIyGDBmisWPH6sUXX9TatWs1Y8YMl7Hbt29XeXm5cnNzlZiYGNDrhG9a27o6Meta1R3ZrfJPX71wLOtaJY+8QedOn5IpPsmv9zOZzTLHJmjArGWqPVjQ+J41FbIkpJx/z2w1VJzQsdcXy6irdvsaidnjW8xe87XZfaCa4vu1XDR7vKpq6tQjOVbp/S+iSSoAAIhoHvNl1rXqMf4OJY2YqNL3/qDeN/2sMRMe2KnqwvUtMqHdMFR3ZLeqvvrY7Wsce31xiw2RQpX1/F1ZAQCRLOAFsi+//FKffvqpbrvtNj3++OMtmtwPHz5cU6ZM0RNPPKFXXnlFJpNJ06dP1/Tp0/X888/rN7/5jVauXKmlS5cG9LrMZrNuv/12vfjii5o3b55efPFF9enTR5JUXl6uX/3qV2poaNC0adOUkJCg3NxcDRs2TBs2bNCqVauUl5fnHLto0SJJ0qxZswJ6jfCNT1tX/+BhdUnqqdr922WcqXY9lveQjLN1MnXp6udSy8ax8YMuc+nXYDcMfbvtQ1Xkv+axOBbbf5jbHg++NrsPVFN8v5aLnr/eRfdcI4kmqQAAIHL5lC/zHlLvm36mY68vUuKl31HyFdcrdcp9TV7DJqOhXsdXLVPdNwUeX6Pf9PkqeXmuy4ZIocx6ADrWkSNHdMcdd6i8vFzPPvusysvLW/Qgmzlzpg4cOKB33nlHTz31lPLz81VdXa1hw4bpxz/+sf793//d5TXPnj2rF154Qe+8846OHz+uQYMG6ac//WkoPl6nFvDbBX/+85+VkJCg+fPne90B8sEHH1RSUpJefvll53OzZs1S4dcO9gAAIABJREFUcnJy0JqF3nfffcrNzVVRUZGuv/563X333frJT36iSZMmafPmzcrJydF//ud/SmosqC1dulRWq1Xz589XXl6e7r33Xt14443as2eP8vLyNGHChKBcJ7zzaevqN5cqJqWPkkdOanls1RMyd41r890yd43+Ey+9RjE9+rkdf2GqvWtfMpthaOJVA316T0dT/EBwLBeN7T/M7XFP10thDAAARCqf8uWqJxST0keJl35HlRv+ouLnfq4Tf31atvra8zOxLDr25wUtimPuXiN55CRVF65Xr5QEpfVJCousByD4Tpw4obvuukvl5eVasWKFxo8f73FsfX29ZsyYoW3btul73/uebr75Zu3bt08PPvig1q9f7xxnt9v185//XCtWrFBcXJymTZumfv366cEHH9Tnn3/eAZ8qcgR8Btn+/fuVkZGhuLg4r+O6du2qQYMGae/eC38IxcTE6KKLLtL+/fsDfVmSpNjYWP3pT3/Sa6+9pnfeeUfbtm2TYRgaPHiwZs+erbvuuktdu3Z1js/OztZbb72lFStW6Msvv9TevXs1aNAgPfDAA/r+978flGuEd35tXX1gp5KvuF6VG9e4NM13HIsfnBWQKeW+LL90N33dYjYrJyNVmWkpXhv1B7opfluvFwAAIBL5nS+vuknnTp9SYta1ztwk2VV7cKdfGbX0vd9Lki4ZRNYDokF5eblmzZql48eP6+mnn251wk1VVZVGjBih3//+9846xfjx4/XLX/5Sr776qq699lpJ0t/+9jf985//1I033qjly5crJiZGkvTWW2/pkUceCe6HijABL5B169ZNJSUlMgzDa0N8wzBUUlKi2FjX6cR1dXVKSvKvP5Q/YmJidOedd+rOO+/0afzQoUO1YsWKoF1PtHDXTN/x2Nux5vzaurpwvVKn3KeuvQfq7MlDLY45dhcKBG/LL5seb85m2LVg9mgtemGT2yJZsJrit/V6fWUzDJdtups/BgAACBZfsmXT5/zOl0PuU+otv5TdsJ0/vzHj+J1R+zZu9nXXv1/W6bIeAP9UVVXpJz/5iQ4dOqTf/va3uu6663w6b9asWS6TeBxFsUOHLvz99m9/+5skae7cuc7imCR9//vf15tvvqnCwsJAfISoEPACWU5Ojj7++GP9z//8j+69916P4/74xz+qvLzcZUphSUmJDh06pKysrEBfFkKktWb6dsNQXUmRqrZ/5PaYuz+8/d262hxr9Xgs0JqHr9bCh8VskjUuRsvnjNOOolKt21qsiqp6pSTFdkhTfH+vtzWOay3cV6a1Ww47P8vEqwYqJyOVBv8AACBofMmdklzGmOOT1euGWX7nS0naue+U1m45rOSErpp9a5bfr5GQebXshqG42C6dJusBaJuHH35YJ0+eVPfu3TVq1Cifzxs8eLDL49jYWMXExKihocH53K5du9SzZ08NGDCgxflXXnklBTI/BLxA9tOf/lTr1q3Tc889p6KiIuXl5SkzM1Px8fHOXSxXr16tDz74QBaLxdk4Lj8/X0899ZQMw9CUKVMCfVkIAZ+b6Sf2cN9Mf9o8mWMTWi5N9HPraqO+1uOxcOAIRFlDe7pMrw91U3x/Z4HZDLtq6xrczobL337EORvOGhdDkQwAAARUa7kzPn2E+v7gYRlnz7iM6Zo6SJL/+fKpV7cpf/sRSdLgfslteo24/kMbH/t0VuuYwQ+Er7KyMk2YMEHr1q3TkiVL9NRTT/l0XvMVd5Ja9Ho/ffq0+vfv7/b8bt26+X+xUSzgBbLLLrtMTz75pB5++GF99NFH+vjjj1uMsdvtiouL02OPPaYrrrhCkrRixQrt3btXl1xyiW677bZAXxZCwNdm+gNmLVPyyEmq3PAX12NvLNGAWctczvFr6+qsa3Xu21KdLT3c8lgYbmvdPMCErjDWtllgFrPJ41JRSdpTXKFFL2zS8jnjgv0RAABAlGktd8b2HyqTpUuLMWdLD+vc6TIlZl3rW77MHq/K02f02Y4S53PFJ6p0qrJGCVm+Z1S77ZxkMgckizKDHwh/8+bN0/Tp03X77bfr73//u6ZMmaJx4wLz96Ju3bqpqqrK7bHa2paTReBZUKoDN910kz744AP98Ic/1IABA2S3253/pKamavr06Xr33Xd1yy23OM/JzMzU3Llz9frrr7ussUXnZDdsfjcqlcnc8tjBApcddppuXe1NbP9hsg4ZodNffezSoN95LD07rIpj4cIxC+xXv/tM8//4hfK3H9HOvaXK335E8//4hX71u89UW9fQYpclm2FoR9FJr5sNSI1Fsh1FpQHbpQkAAKDV3GkyK3nkDao9sKPlGLuh09s/knVIjm/5Mj1b737+jYwmWcYw7Hrvi2IlDPE9owayONaW7AagY11++eWyWCxatGiRzGazFi5cqJqamoC9dnl5uQ4ePNjiWEGB+1114V7QKgR9+/bVI488ok8++UQFBQX67LPPtHXrVq1fv14LFizQwIEDXcY/8cQT+vGPf6z4+PhgXRI6kL/NTrt0662uvQe2PFaQ3yI8+LR19Q8eVkPFCZ3e9mHLY+3c1trW7NzmjzszX2eBNb8LaTGbtXZLy5l67qzbWsxdTAAA0CbuclhrubNr74HqktxL1YXr3R4/vf1DNVScUN+8h7zny2nz9G3VGb23seVfQt/feFAnTlUrNe/hVl8jkKsY2prdAIRGdna2pk2bppKSEv32t78NyGs6VuAtXbpUdXV1zuc//vhjbd68OSDvES0CvsTSna5duyo1NbUj3gphJFjN9H3duvrsqaOyDr0yYNtaN52+XrC3TPUNNsXGWJQ9rFdETF+3GYYK95X5PAssa2gvl89bUVXv0/v4Og4AAMDB0zLCW8YN0bCBKV5zpyNjehpjnKnWsdcXq9/0+Y358sBOVReud5sh//TXHao+09DiNapqG7TgxS+15Kdjzr9GgaoL3WfUQBXH2pvdAITGAw88oI8//livvvqqbr755na/3g033KApU6bonXfe0a233qqxY8fq+PHj+uSTT5SWluay4yW8C1qBrLCwUDt37lR1dbVsNpvsds/Ter3tdonOK5jN9H3ZujpuwDDFD7zE7TF/Oaavf77jqEZd2kc5GRcKvqWVZ/T+xm/0nZz+na4BfdPmrf7OAmu6oYAkpSS1bCDpjq/jALj37lPRt5FNNH5mABd42wjom2On9cyvvus1dzoyprcx5yqOqeTluUoeOUndcv+9cRnkeU0zpOFmqWKSNUaTr0nXjWMGq2f3xtUw8YMvk3WI+4zqC18a7rc3uwEIjaSkJD388MO6//779cgjj2jmzJntfs1ly5bp8ssv15tvvqk33nhDffv21fz583Xq1Ck9++yzAbjq6BDwAtnZs2d1//33a926da2OtdvtMplMFMgiUEc10/e2dXUgt7W2mE0622DT5GsG66s9J/XKP/7lvHM5YdRATb5msMoqzyjJ2jn65zW/C+vYnryts8BshqGJVw107ubkzYRRaZ1+th0AAOg43pYR+tIg39dG/MaZalVu+Ivi0i5X/ODLndnR8b/u8k6/XglafM8Y9emZ4JIReyTH6qZrBuuSwT3P5x5fC2P+NdxnBj8Q3pYtW6Zly5a1eP6mm27STTfd5Hycl5fncnzlypUeX7OwsLDFc2azWT/60Y/0ox/9qMWxX/7yl/5cclQLeIHs5Zdf1tq1ayVJaWlpSk9Pd7s1KSJb02b63hr1OxqVlue/5rGZvmHYFcpSis0w1NBgqIvFrF/97rMW4Sx/+xFlpqVo/t1Xq67+nGJiLGFd/HF3F9axPXlbZ4FZzGblZKQqMy3F6zT/zLQU7l4CfjqwpH07Ow+Z95fWB/no5gff8Xrcl5legfo87XmdQP5MpNZ/Lr5iphzQUmvLCB0N8mdO9pI7zzfi7zH+Dh+zabaOldUotYfVJdM58s74kRfpZEWtTCbp/mkjFRfbxW1GXP9VicblDND/c1u2Yrt2aTUfepsp58ibC2aPdlmxwAx+AAicgBfI/va3v8lkMmnevHn64Q9/GOiXRyfiaKbvacvt1prpp+Y9rG+rzqhbUuA3brAbNpcZZs0fN2Uxm2WJNeuRP2z02gB18UtfavmcwGzVG0zu7sIWn6hSaeUZTRjV9llgNsOuBbNHe7zD6wh1zB4DACC6+LJc0BNflhG+v/Gg/s+4dK+5s/7oPhm2c61m09S8h3XiVLXW5O/Tz2/PaTHGbtj04IwrXR5/sOmwjpZVO59zLLm8aUyaenZPcBnrKW82flbfGu478iYz+AEgsAJeIDt8+LD69etHcQzem+lnjZd1yPlm+mUlrs30s66VdcgInThVrdc+2qX7p48M2DU5gsmZb75ubJxaXSlLYvfz1zPCbXCxGYYK9vrWAPWropPKHto7bMOHp7uwhmHXB198o5mTh/s8C6x5Dw6L2SRrXIyWzxmnHUWlKthXqrMNNnWNsSh7aG/lZPQmmAEAEEX8XS7oSWvLA2vqzumsTYrpEue+yf75bFlWUSPJ7CGbXsif85/fpD49XDePcrT8OHPo68bzmmTIydeM0MjMXpr//CZJ0uM/Ha3UHomqObBTJ9c3GZs9Xtb0EW7bh7St4T4z+AEgkAJeIEtISFBiYmKgXxadlKdm+lXVdXrzkz2SXZo4Kk2pU+5zHiurqNFf3tul9zYe1FWX9gnYtdgNm4z6Wrd3Dau//sy59bY51upSJLOYzVq31bcGqJ9uPawrmjTw9+cOaUfwdhf2/Y0HdX1umubffbUWv/Slx1lg8+++WpVVdeqeFOfm9RtDbtbQni5BzLElO8UxAACiQ1uWC3rS2vLAtD5J6pEcp+fe2qHkhFhNHjNUqVMuNNlvmi1NJunnt4/Qv2W5ZtOmY6rPNOiSQRc2irIbhoz6Gq8ZMjXvYT3+09Eym0zq1tWmkpd/3UreTHApkrWl4X5jvjIxgx8AAiTgBbJRo0YpPz9f5eXl6tGjR6BfHp1U04KTzTC0/+hp/fn93ZKk1z7ao7Q+SbLGdVFt3TkVn6hyzk4K5HRwk9nicUq9JNUf3avjbyzRgFktmyj62wD1pXcKVVl91u87pB3B02epqm3Qo89/ocfuGaPlc8bpq6KT+nTrhbu93x01UFdkpOr4qRq9/tEetzP7AnWnGAAAdG7+Lhf0xJdlhNa4xr/SHDtVqw82HdLbn+71mC0l6cNNh/SdEQP029e36fipWrdjGjNo441Ok9ncaoY8uWqpM0O6K441HRuovHmg5FsNG5gia1wX5wz+dVuLm2wklcYMfgDwQ8ALZL/4xS+Un5+vefPm6Xe/+526du0cu/qh45gkv6aDu9tO2192w6Yz33zttSmr1Bhaag8WKH7QZS5FPX8boO7YW6Zvjp32+w5pR/D2WY6V1eiBp9dr8ph03TJuiK6448JsuNKKWq30MrMvkHeKAQBA59W25YLus4Evywhr685Jknokx2pwv2RnYWz3oQq3OdKRhQ6UnNY3x063OO7IoPVnz8ncxa4zh3zIkMf2y2ioV92R3X7kzctdZpH5mzdXvLlDsTEWLZg9WglxMW5m8Dd+dnIXAPgm4AWy4uJi3X777Xr99dc1btw45ebmqk+fPoqJiXE73mQy6T/+4z8CfRkIY2azWRVVdXr07qu1oeCYci/t7dLA9FRljTb/q1T/lt3P41I+f5nMFlUX5vs0trog32XKvb8NUMsqz6j4RJXzOV/vkHYEXz5LVW2DVq0t0uVDe2pQ3yT995+3qbq2odWZfYG6UwwAADq3tiwX9Ka1jYB6JsfKZhi69/Zsde164e8cpypr9N4XxXp/40FV1TY4n58wKk0Vp+tc8pqDo53E8VM1+su6vfrF93NUXZDf6ufo2nugzDGxPo2V2pc3vztqoEorap3Z7EK+ci2EURgDAP8EvEB23333yWRq/DKurKzURx995HzcnN1up0AWpf6av18zJ2dq8jWDVdu8gen5Zqfnzp3Tyvf3aNbNlwXkPW3Vlb6Nq3ENXv42QF353q4Wdyt9uUPaEfz5LFdkpGrle7v09f5TLY41D7KBvFMMAAA6P3+XC3rTfCOgpssIbxyTruGDustkNqu+pFCVTRroJ2SN18zJI3RD7kDNf36TjpXVuOSYhbNHe2wn8ejzXzhnavmSIc2xVvdjTebG4lmsVUZ9rc6WHpbsRrvypiOjOfIm+QoAAiPgBbJbb73VY0EMcJg6/mLZ68+oZKW3ZqfzNP36Ye3aGvz/Z+/OA6Kq18ePv+cM+yaLgoCAuGaJpLmkaZKWW/q1q4Wl18ruLfPbvrtkZpotX2/XFn8t1rUyb6VZlqVpuRYuaS6oKWqgKCGLgDDszJnfH+OMM8zCDIKiPK+/LuecOfMZ8o6Pz3k+z2NJGxDs2nX+ITbH9KrKrH9ez+wPnTRA/ef1VNXo2bLX/pO/up6Q1p6gWdco8Pqq6yms5ZPT1VszbM7Za/Ta0E+KhRBCCHF5c3e7YF0cDQIyDmGqu4H+nAeuZ+FXqTwzsSd61cDOg9m0bxPMk+OvM19v2U5CV16Nt6cxDnMlhlQry6yuVXwDCOoxlKAeQ/AIamm+rqY4n+Ld69CX6WzucSExmsRXQghx4Ro8Qfbqq7YNJ4WwpKoqLQJ9yFr8Yh3NTo0NTLPzdfx3bdoFNXw3qHoCEpLQHdhS57UB3ZJsklNaRaGyWu+0eX1+UTmB/l7ceG0blq0/YnNfR09IHY4NdzIK/EI4ewpr2cw1K6+UXldHuNzotSGfFAshhBDi8uVuewp3YjrLh6SqakBxYQiTqYH+S5P7md/r+5Tj7P8z32kz/8ycEop1FQR0qzuGrMo7iVpdSUC3JCqyjhI5fiaewRGUpe+lYONSi50SAwlNGo9aVWET4zmL0WpXt+nKq63eX+IrIYS4cA2eIBOiLhoMlGXsc62BaXoqniHt2bI3yxyw1Kfhu0bR4tcuEe+ojk7f1zuqo1U/CDi/ffD1JbsY3jeeYX3jHD5tfPbungzrG8dXG4/abLO094TUlbHh9kaBXyhHT2Etm7l2jgvm6vjr7J6zp6GfFAshhBDi8uRue4r60KsGNAaV0nTXhzB5xVxtfgAaEuiNqhrsNuk3UVUD+/88ww2JrsWQiqc3fvGJRN3zMhrsT7O0jO80HrbDzBzFaLWr22qT+EoIIS5cw/2L2460tDQWLVrE9OnTefTRRwEoLS1lxYoVVFVVNeZbiyZMo2hdb2C6fxMtQ/yJjQi0Om5q+O5OnwWDqqf1nTPwjupo97wpWDGoeqvjVtsHNVD7LRWN8bhGAxt3naRViJ/NeuH8E1JLrowNP/3Fyw2aHLNUe6tq7W2Tjs7VZnpS7Ap7vwchhBBCXFlM2wU7x9q2rgDrtg31oVU0KFotpW4MYfLw8ECraNyKW4L8vZ3GkIpvAC2HTyZq4kvmYx7+LTAYDPjGd0PxDbB5jSvxnVZR0KsqR08W8sj8jfxz3s8sW3/EbnIMJL4SQoiG0CgVZGfPnmXGjBmsX78eON+MH+DkyZPMmDGDt956iw8++IDOnTs3xhJEE+duw3w/H9s/qu42JNUoWhRvP6InvUpZRqpxO2NpIVr/kHPbGbs57PulKBoWPHEj4aEBlNYaKmDZAPa/647YXa+9J6QGVe/a2HAHo8CbkovxpFgIIYQQlw9XWzrUp6m8XlVJzzpLx5iQeg1hciduSehg7B+mePvbxJBe4W0JuXEcipcPZRn7rFtlnNtKGZg4mOzP51BTmG11b1fiO62i0DEmBG9Prc3OhNrrlPhKCCEuXIMnyKqqqrjvvvs4ePAgfn5+9O3bl/3795OXlwcYk2VBQUHk5OQwceJEVq5cSVRUVEMvQzRx7jbML6uosXve3YakpuSXb9w1VlspTVVjjpri3zfyavyUKqel8uHJ07lvZBeb9TpqbO9WJZ2dUeD1GVTQmFxpLGvv9yCEEEKIK5MrLR3qd1+FbanZdIwJqfcQJr2q8vKUfry8+Df2HMmzub523GJKYlnGkKZWGfb66pq3UiZPI/KumWQtfha13Loxf+34zh6Jr4QQjlgWIjUFTW099dHg/8L+7LPPOHjwIL169eLnn39m4cKFtGnTxny+S5cubNiwgV69elFSUsKiRYsaegmiiTOoegK6Jbl0bUDCQPILS8nMKbF7vr4NSWsnwpxNizQNFchdNq/OBrAtAn2pqKwhNMibm65rw5zJ/Zj/2I0Oe6W5+9Rz0cr9/Gvp7+w/lm883oRK6S2fFM+Z3I+brmvDtZ1aufR7EEIIIcSVy522Da46dqqIM0Wl+CckuXR9QEIS1dU1lJRV8unqP9h/LB9vLw9m3d+X1x4e4HLcYhkzutQqY9kreIZEENRjqM15y6o2RyS+EkLYk5KSwj//+U+rY19//TWdO3dmxowZF3Utubm5PPXUU+zcudPq+KBBg+jcuTOnT5++qOu5EA1eQfb999/j4eHB/PnzCQ0NtXtNQEAA8+fP5+abb+aXX35p6CWIJk6jaPGLd7FhfrtEVqw+5LCs3FlD0trbJR1tn6xzve4MFThXKj/7gX5A3U9I3X3qmXosn+PZxfUaVHAxNNaTYiGEEEIISy0CvFm9LZOJw12NKY2VWp6eHtw94mrOFJWyZutx+l8b5fZgInCzVUb6PoK630LR1m/AoJrP1a5qc0TiKyGEpZycHO677z6io6Mv9VIAmDp1KikpKSQnJ1/qpVywBq8gy8jIoEOHDkRERDi9LiIignbt2pGTk9PQSxCXAYOq1tkwPzx5OjlndKzemuHwPvYakhpUY+BRfuIAud++SfbS2eR++yblJw5YnXeVu1sha4/rduRCK+nqM6jgYmmMJ8VCCCGEEHB+ONCarRnknNERnjy9ziFMalUFeavfM8eFPgXHGN6vLdXVNfWKW9wbOrUZjxat8GplPRggoFuSW3GpxFdCCDBuZWxKVAffYx9//DGrV6+mZcuWF3lF9dfgFWQajYby8nKXrlVVFS8v2/HG4sqnURS7zU4tG+YXnC1j5gdbHU7rsd/43tgLwl65u+VYbcXb362G9/VpAFuXhqikc3dQgRBCCCHE5c7UZD+qZQAzP9jOnAeuN8aU6fvQ7d9sE1PWFJ8h6+PpKB6eKN5+VOWeQPfFXLwj2xOePJ3Kymo8PD3cjqXcjQ8Vbz/zMe+ojnX2HxNCiMtZbGzspV6C2xo8QRYfH8/hw4c5deqUVe+x2jIzMzl27Bhdu3Zt6CWIy4S9ZqdwLsmlGvD09CDIz4tsSm1e2y8hkmf+fp2dbZMGqgtPoy8vtvueprHa0ZNedWut9W0AWxdTJZ2j/hWuVNK5O6hACCGEEOJyZ9m8/okFWxjeN57hfTsQPjrRfI1BVSnZt4GakgKiJszCI+h8FUNNcT7Fu9eR/+0CIse/UK81uBsfqpVlwPmqNoOqNtkJ5UJcCWoPNmuKg84sFRUV8fHHH7Np0yYyMzOpqqoiNDSUPn36MGXKFNq1a8fbb7/NO++8A0BWVhadO3emd+/eLFmyxOF9y8vLWbp0KevWrSMjI4Py8nJatGhB9+7deeCBB+jW7fy/xXfs2MHdd9/Nfffdx5gxY/j3v//Nrl27qKyspEuXLvzzn//k5ptvBuDUqVMMHjzY/Nq7774bgPXr19OmTRsGDRpEVlYWmzdvpnXr1ubriouLWbx4MWvXriUrK4vg4GASExN56KGH6Ny5c4P+Tt3V4AmyUaNGcfDgQZ577jkWLlxIcLDtXxxFRUU8/fTTAAwfPryhlyAuM7YN8xU04HA0+P8MaE/76EA0ivbck0LLkdpJ+LVLpM0Db3L6y3lUHE+1eT9XxmpbMm2F1B3YUue1plJ5V4Mdp5V0CUn4tetGzhkdMz/Y7rCSrr6DCoQQQgghLleWzetNseLby/fRvk0wfROi6BAdSEXWEXzirsEzOIKy9L0UbFxqETMOJDRpPNWFOZRnHsanTSeX4zfjtkgDAQkuxocJA6kpLcIrIp7Qm+/FL76bJMeEaESmqa77j+WzfudJ878jB/eK4dpO4U1y6mt+fj7jxo3j1KlTxMXF0a9fP8rLyzlw4ADfffcdGzduZNWqVXTu3JlbbrmFn376CT8/PwYPHkz79u0d3reiooIJEyZw8OBBWrduTc+ePVFVlYMHD/LTTz+xadMmPv/8cxISEqxed/jwYZKTkwkICOC6664jJyeHPXv28NBDD/HWW28xdOhQ/Pz8GDVqFNu3bycvL49+/foRFhaGn5+fg9VAdnY29957L8ePHyciIoKBAweSk5PD2rVr2bhxI59++indu3dvsN+ruxo8QTZ+/Hh++OEHfv/9d0aMGEHfvn05deoUAIsXLyY9PZ1169Zx9uxZOnbsyIQJExp6CeIK4aghqUHVo1aW1bmNsvW46Zz64DFqCm373LkyVtvEra2Qte7pylMKR5V0JboKlqw+xOqtGQ6TY+B8UIEQQgghxJXKWfN6jaLBMzQSDRqyFk91HDMmT8MzrLVbyTG1spTSQ9sI6jHE5VYZAOH/84i555gkx4RoHHrVQFlFNbMXbSct07r9TVMddAawcOFCTp06xb333svUqVPRaIxr0+l03H///ezevZuVK1cyZcoUunXrxk8//URISAjz5893et/PPvuMgwcPMnToUN544w08PIwpoKqqKp5++mnWrl3Ll19+aZMg27p1K2PGjOHFF1/E29v4780FCxbw7rvv8tFHHzF06FBCQ0OZP38+9957L3l5eTz44IP06dPH6Xpmz57N8ePHueOOO5g1axaenp4AfPPNN0ydOpXp06ezZs2aev0OG0KDfzN7eXnx4YcfkpSUREFBAT/88AO5ubkYDAZef/11li9fztmzZ+nVqxcfffSR+ZcthCO1E0waRVv3SO0vXkbx8KTlsMl2r3GnVxi4NlSg9Z0zqKysZuHyvTz/3lb+tfR39h/LN76fgymcliwr6fSqyp9/FbNs/RGnyTGwP6hACCGYxCMyAAAgAElEQVSEEKK5cNS83sM/mNPLXnEeMy57BQ9/17ZKgjGxdfqLlynYtJTqwhxaJ0+rMz60bMQviTEhGpdW0dhNjpk01UFnISEhDBgwgEceecScHAMICAhg5MiRgLH6yl0+Pj4MHDiQp556ypwcA2PeZsyYMQ7v6+3tzYwZM6zyNabipqNHnU/vdSQnJ4eNGzfSqlUrXnjhBXNyDOBvf/sb/fv3p0WLFuTn59fr/g2hwSvIAFq0aMF7773HgQMH+Pnnn0lPT0en0+Hr60tcXBxJSUn07t27Md5aXOEMqp7y4y6O1M5IxTf2alA8QK2xOu9urzBXhwpM/X+byc4/3zOtvk8pTM1nO8eGOPxyB/uDCoQQ4lIb9dS3NsdW/Wv0JViJEKK5citmTN+Hb9sEVDR1TiAvP3H+ntmfzyHyrplOBwTIVkohLh69qrL/WL7Tfz9B0xx09uijj9ocKygoIC0tjV27dgFQXe28cMKev//97/z973+3OlZcXMyRI0fYssW4RbyqqsrmdR06dCAgIMDqWMuWLd0ayljbjh07ABgwYIDdYY0fffRRve7bkBolQWbStWtXacLfjFyMJogaRYtu/yaXrjVto/Tv1JPSw9utzrnbK8z43o6GCug5cqKQ/1u6i9NnymxeZ3pKMf+xG11+L7BuPmvvS96UeGuKe+iFEEIIIerSmLGjWzHj/s34tUvEauxTrUFQpp91qefvWVOYTdbiZwnqMZSg7rcQPvr8P3D1ZcXn1iHJMSEuFq2isH7nSZeubYqDzjIzM/nss8/YvXs3GRkZ6HQ6AHNFmcFQv11Dubm5LF26lB07dpCRkUFRUZHVfe0JDAy0OabRaFAUBb1eX6915OXlAVg17G9qLihB9thjj13wAjQaDQsWLLjg+7jC1YkIn376qdXe2YyMDN5++21+//13ioqKiI2NJTk5mQkTJqDIX3oXvQmiuyO1tbXK5us7VtuUUCs/cYDy4wcwVFeh8fTCN64rndolMndyX2Z+sN2qgsykPk8p7DWfNf1uB/WM5dpOrSQ5JoQQQojLzsWKHd2NGY9nFxMX4Y9G0VJ+4oBxx8C5pv5BvW7FJ6qDzT3Vch1FKSso2voNXq1iULz9UCvL0AYEE3lX/aZjCiHqz9UBZk1t0NmqVat47rnn0Ov1tG3blhtvvJH27duTkJDA6dOneeGF+n2fbN++nQcffJDy8nKioqLo3bs37dq1o2vXrnh4ePDggw/afZ2z5Fl91TexdjFdUIJs7dq1F7yAxvjFOzJq1CiH5zIzM9m3bx+BgYHExMSYjx8+fJgJEyag0+no0aMHCQkJ7Nixg7lz57Jv3746m+Jd6S5FE0R3R2rrS88HMq6O1a79BNPZYICzW7/GO6oj4cnTmfPA9TyxYAslZbblr/V5SuGs+azleSGEEEKIy0FDx47OqtDcjRlbBnk7jPeqck/Q5v43HN/ToFKVe8L8Y0B4W5feWwjRsFwdYNaUBp2VlpYya9YsFEXh3XffZeDAgVbnlyxZUq/7GgwGnn/+ecrLy5k7dy533HGH1fkNGzbUe8310bJlSwBOnz5t9/zOnTvJzs6mT58+REREXMylmV1Qguzhhx9uqHVcFI6SWWVlZYwZMwaNRsO//vUvoqKiAOMfqGeffRadTsfrr7/O6NHG/ikFBQXce++9rFq1iltuuYWhQ4detM/Q1LjaBNHd7YWOGFS96yO1uyVh0NegVlcQ0HWgS70g7D3RHNY3jv6J0XUOBshdNo/oSa8yvG88y9YfsbnmQp5SOGo+K4QQQghxOWmo2LGuKjSDqiegm4sxY0ISpeVVBPh7k7V4lt14ryrvJDXF+QQkDHQ9DpX+Y0JcVHpVZXCvGDbtPlXntaZBZ03h31V//vknpaWlXHvttTbJMYCUlBQAVNMUXBeLjAoKCjh58iStWrWySY7Zu299ubqe7t27A7Bt2zZqamqshgYAvPXWW/z2228sX75cEmSX0rx588jIyGDixIlWfyBTUlJIS0ujd+/e5uQYQGhoKC+++CJ33XUXS5YsabYJskvRBFGjaPFrl+jaSO1z2ygj75wJUOdYbXtPNBVFwxN3JlKavs/lJq/D+3bgq41HUWtNlmxKTymEEEIIIS62hoodTTHbnA+3U16lx8/Hg7KKGvb/mW+uQnt5Sj/84l2MGdt1o6y8kjJn8Z5BpXj3OkKTxrsVhwohLp7LddCZqSfXkSNHOHnypHlHm16v54MPPmDjxo0AVFYaCy5MDe5LS0sxGAwOE1TBwcH4+PiQn5/Pvn37SExMBIyFQF9//TWff/651X3ryzTpsqSkxOl18fHx3HDDDaSkpPDaa68xdepUtFpjr8eVK1fy22+/ER8fT0JCwgWt50I0apP+y0FqaipfffUVkZGRPPnkk1bnfvnlFwBuvvlmm9f16NGDsLAwfv/9d3Q6nc2Eh8uVo4ak9lyqJogGVU/rO2c4rOg6v43Seu11PcGz90QzNiKQsGB/cjdvcmltuv2bCR+dSGxEIMezi63ONaWnFEIIIYQQF1tDxY5aRcOve//iubuvIyzY33z8TFEpq7dlsmZrBi8v/o3Z919fZ8wYnjydM0VlhAX7kVtHU//i3WsJTBxM63HTOf3lvDriUKkeE+JSuBwHnYWHhzNixAhWr17NqFGj6N27Nx4eHqSmppKXl0eHDh04duwY+fn5gDHxFRwcTFFREXfddRcJCQnMmDHD5r5arZaJEyeyaNEiJkyYQO/evfHz8+PQoUOcOnWK9u3bk56ebr5vfcXFxQEwe/ZsvvvuO5566inzsdrmzp3LhAkT+PTTT9mwYQPXXHMNWVlZHDhwAF9fXxYsWHBR23DV1uwTZPPmzcNgMPD000/j5+dnde7YsWMAdOrUye5r4+PjOXPmDH/++ac5G3u5smxAb9mQ1LgtMdHhX/KXogmiRtGiePsZR2pnpBrXazNS23Fizx5HTzT9fIz/F3G3yavpdSZN7SmFEEIIIcSlcKGxo15VqanRM7xfW0rT95G7+Xzc6p+QxMThiQzpHcPMD7Zz6EQRXeJaGGPG9FR0+y1ixoSB+LVLJOeMjk9W/8GzE3vWGe+p5TqyP59D1MSX6ohDJTkmxKVyuQ46mzdvHu3ateOHH35g27ZteHp60q5dO6ZMmcIdd9xB//792bt3LwUFBYSGhvL666/zyiuvcODAAfLz8+0myAAef/xxWrVqxVdffcXu3bsBiI2N5fHHH2fSpEkkJyeTlpbG4cOHueqqq+q19smTJ3P8+HF27NhBSkoKY8eOdZggi4qKYsWKFbz//vv8/PPPbNiwAX9/f4YNG8bDDz9Mx44d67WGhtKsE2Rbtmxhz549dOjQgVtvvdXmfG5uLgCtWtlPbJiO15Vx/frrr/nmm29cWtOhQ4dcuq4hGVQVtbLU7tM13YEt5idhire/zV/2l6oJoin55Rt3jVUJu0HVW513laMnmmUVNcbzbjZ5Nb0OmuZTCiEuB039u1MIIZqipv7deaGxowJoayrIWjrTYdxqGpy0YuMxro6/FlU14BN3DX7tzseM+YWlrFh9iNVbM+jZxdjrxpV4r6Ywm8JfvqLViAfsxKHO23kIIS6Oy3HQma+vL4888giPPPKI3fO//fab1c8DBw606Vc2ZswYxowZY3XMw8ODe+65h3vuucfufb/77jurn/v06UNaWprDdf7xxx82x0JDQ3n//fdtjjsaAhAaGsq0adOYNm2aw/e5VJp1guyTTz4B4IEHHrBbxldeXg6Aj4+P3debjpeVlTl9n6ysLJs/0E2JRlHqbEB/+ouXiZ70qtXxptAEsXYizN3EmCV7Tyozc0o4U1SKvxuDAUpKKwgN8iY+qk2TfkohRFPX1L87hRCiKWrK350NETtqFIWcL10bnNQp1vjgUlE06FVj0uroySK27f+LP08V0SLAm+fu7sW1nVq51dTfv8v156rEasehkhgToimRQWfCXc02QZaenk5KSgpRUVGMHDnS7jWmhnF17YGta+pDdHQ0vXv3dmldhw4dqrO5XUMyqHrKTxxwrQF9Riq+cV3Nf/lfrk0QHbH3pFJVDazelsnE4e4NBpj9QD+gaT+lEKKpa8rfnUII0VQ15e/OC40d3Ypb0/fR55rOFu9tjMXaRQfRMeZ8pZgpVtMoWteb+ksDfiGEuCI12wTZjz/+iMFgYNSoUeZEWG2+vr4AVFRU2D1vOu7v72/3vIm9UkdHJk6ceFGf+mkULbrUTS5dq0vdZBMQXOomiHpVtXoyYPmzOwMHnD3RXLM1gyG9YwhPnk7uMvcaskpiTIj6a8rfnUII0VQ19e/OC4kd3Ypb928mvF2izX2cVZQYVNXFQVDn4z134k0hhBBNW7NNkP38888AdnuPmYSHh3Po0CHy8/Np3769zfm8vDzAcY+yy4W7DegtXaomiKZ77j+Wz/qdJ83vObxfW7rEhbg9cMDZE82SsmpmfrCdOQ9cLw1ZhRBCCCEuQH1iR8uf3Y1b3YlBNYqC4u3vUrxX3wFXQgghmq5mmSA7c+YMBw8epG3btnTu3NnhdR07dmTz5s0cO3aMPn36WJ0zGAykp6ej1WrtJs8uJ+42oLc57kITRGeVXu7SqwbKKqptnjwG+nkycXhnaipKybXTm6KugQPOnmhm55ey8KtUZkzqLQ1ZhRBCCCFc5CwGdCV2NMV9H3yzn6cmXHfBcWtdTPGcs3jvQgZcCSGEaLqaZYIsNTUVgO7duzu9bsCAAXz44YesX7+eCRMmWJ3bvXs3BQUF9O7dm4CAgEZba2NzpyFpQLckp0/D7JWsO6r0Gtwrhms7hderukyraOwmsYb3iyc8NICsxVPdHjhguq8rTzQ1dprFCiGEEEKI81yLAZ3HjrryavonRjN70XaOniri3luvcmtw0oVUcTlrwF/fAVdCCCGatmaZIDtw4AAAXbt2dXpd79696dixIykpKSxbtozk5GQACgoKmD17NgCTJk1q3MU2ssZsSOqo0gtg0+5T5h4Tfj6eLifJ9KrK/mP5NvdTFA0j+sZSmr6vXgMHTC7HkcBCCCGEEE1JfWNAy9cdPVXEhzNuYU9arvke9Rmc1NAuZMCVEEKIpq1ZflufOmVsxN6yZUun1ymKwrx58/Dz82PmzJkkJyfz8MMPM2zYMNLS0khOTmbQoEEXY8mNytSQ1Duqo93zlg1J3eGo0sskLbOQ2Yu2u5V00ioK63eetDkeGxFIWLA/pfs3uXQfXeomp8FKfUcCG1S905/1tX6HtX8WQgghhLjc1TcGtHxdbEQgrYJ92bDrfNy3ZmsGOWd0hCdPb/C41VEMVztWc3fAlSTHhBDi8tEsK8gKCgoACAoKqvPabt26sXz5ct566y127NjB0aNHiYuL48knn+SOO+5o7KVeFO40JHVV7UovRdEQGxGIn48HZRU1ZOaUoKoG0jIL2Xskj4QOLV1OQhWWVNoc8/Mx/lG+kIEDF6LuRq3GiUYNudVUCCGEEKKpcVTtX1vtGLD26wJ8jbFdkL8XbSODyMwpsR2clL6PihMHUWsqUTy88Wnb1e24ta4YrqZaz8dr/yDjr2K6tgvjziGdL1m8KYQQonE1ywTZokWL3Lq+Q4cOvPXWW420movP2TjqhmpAb6r0CvTzZHi/eIb1bUurYF/z+byicn7cdpw1WzPYsCvTajtjXUICvW2OlVXUGN+3kRu32uNqo9azVVpeX7KLkrJq8/n6bjUVQgghhGiKHFX722MZA9aOHW+9IR6A+29LAKxjx5nvb+N/xyaS0P4a/Nolmu9nqvpyJzlWVwwXnjydkTe05YkFWzirq+TOIZ0vSbwphBCi8TXLBFlz5do4ascNSd2lKBr+/fhAIsL82ZOWy6c//GHR9D6GicO7cEvvWL74Kc3le+pVlUE9Y9i0+5TV8cycEs4UlV60xq2W3GnUOrxvPMvWH7E6b9pmMP+xGy94LUIIIYQQl5q9an9XrqsdOy5eddAmdhx2fRyKxmBsrZG+j9L9jmLaumO8OmO47D8p+GkxEbc9xvghV/HR9wcvWbwphBCi8UmCrJm4FOOoJ428Bo0Gnn5zi90Grd07tWL6vb155I5Eq3O1K9wsaRWF7p3D6RwbYnVPVTVcksatbjVqTd/H8L4d+GrjUdRzTf9N6rPVVAghhBCiKbJX7e/Kda7EjrP+2QeqyuxOLXcnpnUWwym+AQT1GEpQjyF4BBl7Fo8c0I6+Ca05mavj2k6XdlCAEEKIxiEJsmbiYo+jVlWV4EBvuwEOQGRLfx6+oxs+3h6UZexzUtFmHdjoVZXqapWZ/+jDnI92WN17zdYMhvSOIXzcDHK/tP9ZLRu3Nkz1mBuNWvdvJnx0IrERgRzPLrY57+5WUyGEuNhW/Wt0g14nhLjy6FWVwb1sq/3tGdQz1tyHta7YEaBjbAharZasBohpHcVwHiGRRI6fiWdwBGXpeynYuNQco/onJHFtp0RqamoIH/c8uV/OvSjxphBCiItDEmTNwKUYR20A9h7JtRvgBPp5Mnfy9YR4q24//dMqClpvBV15NfMfu5E9R3LZuOt80/szxZWEh4Q06MCBurjbqNU0UKA2V7cjCCGEEEI0VVpF4dpOttX+tXWODbF6MGiKHY+eKqJtZJDNYCdF0TCibyyl6fsaLKatHcMpvgFEjp+J4unjNEYNT56Bxtv3osabQgghGp8kyK5QltsU3R1Hbd2k3/F2R2ecNWgd3i+e8NAAu4GHibOnf3rVgLeXljVbM+jZJYInx19nPpdXWMb6XScZcG10gw0cqIu7jVpNAwVqc3U7ghBCXCrpL4+t92vbzVjRgCsR7hr11LcNch9TdWBD309cWfSqgVn3X8/sRdvtJslMA4osp3hrFeMD0P/MGExYsL/52jNFpazelsnB9HzCgv3J3bzJpTXUjmntqR3DBfUYimdwRJ0xau4yY4x6PPsscRcp3hRCiMa2Y8cO7r77bvr27cvHH398qZdzSUiC7ApTuxG/4htEyyGT3K5yyl+3GLW82O1mp5bsVUQ1xNM/raLBz8c44WjvkTzWbDtOVbUeL08t3Tq04ubecehVA5pavbwaI1AxqHoCurnYqDVhIPmFpWTmlNg9b7nNQAghhBDicmWK1eY/diN7j+SxYVemRbP9WK7t1Mom5jGoKv0ToylN30fu5k1W2xonDk+k4GwZ4H7lvqMY1iaG0ygE9RhCWfpel3vLRrW5GhUFy0fJkhgTQojLlyTIriD2GvF7hccB7lc5VZzYT1XuiQtq4G+vIio2IrBBnv6ZAqqEDmFW5fn6c83vLzTJVLtyzlElnUbR4hfvYqPWdomsWH3IpkE/2G4zEEIIIYS4nLkTq7kyTCr8zueNr3MzplWrylG8fG1i2NoxnFerGDyCWlKwcalL99ft30x4O9cHTQkhhGj65BHHFcReI/6qvJPUFOcTkDDQpXsEJAyk5mweVXnnt0eatju6kxwzNWitzdR/y92nf45oa63pwhNjxrL48hMHyP32TbKXzib32zcpP3HA6nzt14SPm4F3VEe79zQlGAvOlrF6a4bNecttBkIIIYQQVxJXYjVXhknlfjnPWPWVkOTS+5piWmcxrEFVaX2nMYZTvP0A92PUwl+WuxQvCiGEaPqkguwK4bARv0GlePc6QpPGu1zlVLDpv2Cw/ovd3Qb+tRu0KoqG2IhAIsOMPSXcffp3Mbjy9LJ2JZ1eVUk7UUhYkLexUWv6PnT7N59v1JowEL92xmlHob4ePHd3L5e2GQghhBBCNAcuD5PKSqO6KBe/dq5X7hds+i+VWWkOY1iNoqB4+xM96VXKs44A7seopYe3UZV7AnA+aEoIcfG5uiuoqdi8eTOffPIJR44c4ezZs0RERNC/f38mT55MZGSk1bXffvstX375JYcPH6ampoa4uDhGjhzJPffcg4+Pj829U1NTWbx4Mbt27aKkpITo6GiGDRvGpEmTCAgIcLqu1NRU7r33XioqKpg/fz4jRowwn/vzzz9577332LZtG0VFRYSHhzNo0CCmTJlCWFgYAFVVVQwYMICzZ8+yfv16oqOjbd7jtttu4/Dhw/z000/ExBgLbU6fPs27777Lli1byMvLIzg4mP79+/PQQw+Zr2lo8q19hXDWiL9491qqC3NonTzNeZVT8jSqC3Mo/n2t3Wt0qZvcrCIzNmj937GJ/GfGYN5++iYev6uHueeDKwK6JTXKUziDqq/1s1rn08vqwmxKD23DOGfJSKsoxIT7s2nPX3z5cxplIR0IH/0okeNnET76UcpCOrBk9SGmvL6RX/dlkdAhjCfHX8ecyf14cvx1JHRoee4+khwTQgghRPPjzjCps9tXWVV92WMvpq0dw1rGgRpFwaCq+ES2dztG1ZfrqNFZ73aoz84LIUTDqs+uoEvtp59+4sEHH2Tnzp107NiRm266CYDPP/+c22+/nby8PABUVeWpp57i2Wef5cCBA3Tv3p0BAwaQm5vLG2+8wfjx4ykuLra698qVKxk/fjyrV68mKiqKAQMGoNPpeOedd7jvvvuorLTtHW5y9OhR7r//fsrLy3nttdeskmO//vorY8eO5bvvviMsLIxBgwbh5eXFkiVLGDt2LCdPGneleXl5MWrUKAwGA6tWrbJ5j7S0NA4dOkSvXr3Mia8//viD2267jS+++AJvb29uuukmWrVqxTfffMOYMWNITU29sF+4A1JBdgVxVBKuluvI/nwOkXfNdFrlVF2YQ/aX8/Btm4DWvwX60rOUHtkJqnHqYl3bHWvTKhoCfLQM79eWMouGq4E9biGgSz/Xnv7VMX3IXbWHGOh1RWgDQ2g5fDLlJw47XI9HSCSR42fiGRxx7vd3vnlsQEIS425OJOeMjuff346nh2Izmhxg7fYT9E+0zpZLYkwIIYQQzZ2r2xprirKNcZzqVXdM+/kc1MoyvMLjUPwCAftxoFdEW0JuHIfi5UP12TzXe8uei1Gj732V7M/nUFOYbT7v7s4LIUTDqc+uoKbgtddeQ1EUVq5cSfv27QHQ6/U888wz/PDDD3zxxRc88sgjfPbZZ3z//fe0bduWjz76iDZt2gCg0+l46qmn2LRpE7NmzeLf//43ANnZ2cyePRuARYsWceONNwJQWVnJQw89xC+//MInn3zCAw88YLOmzMxMJk2axNmzZ3nllVcYNWqU+VxBQQFPPvkk1dXVvPPOO9xyyy0AGAwG3nvvPRYsWMAzzzzDF198AcDYsWNZsmQJ3333HQ8++KDV+6xcuRKAMWPGAMaKs0cffZTCwkJmzpzJ3//+d6trp06dyuOPP86PP/6Il5fXBf7mrUmC7ArirCS8pjCbrMXPEtRjKC16j8TPoqmovqyYoh3f4dW6HTH3z0ej9TSfM+irKc/8g/w179e53VGvqlZ9JgyqHrWyzObLqTInHe/W7Wk9bjqnv5xnNwAxfXHVNT2z9nvW/tmSoy9Lr/A4FE9vh08vFd8AIsfPRPH0sTv229w8Nnk6s+/vwxMLtnA8u9rmPvaGFgghhBBCNAfOYjZ3tzV++N1BHr+rB96t21nFtKaqEI2HJy2H349XyzZ4BIZhcQHFu3+mYNNS1HIdim8ALW99EEN1JVlLX6S6MJvoSa/TOnkap5e94jhGPVehlrf6PSJue5zIu2aStfhZ1HKd+TpHg6aEEI3LlZ6Gp794mehJr17klTmXl5eHh4cHrVqdH2qi1Wp54okn6NmzJ926Gb9PPv74YwBeffVVc3IMICAggPnz53PTTTexZs0annnmGaKioli5ciVlZWXcd9995uQYgLe3N1OnTuX48eOcOXPGZj05OTlMmjSJ/Px85syZw9/+9jer81999RVnz57l3nvvNSfHADQaDVOmTOHnn39mz5497Nmzh+7du9OlSxe6dOnCoUOHOHDgAF27dgWMScBVq1bh5+fH0KFDAWM13cmTJ7nllluskmNg3Iq5YcMG1q5dy7p16xg5cmR9ft0OSYLsCmEzqtoOtVxHUcoKfOK6mp9oGVQ91WdzCbpuOIqHp93qKL92ibR54E2q8jLtJqxM/bP2H8tn/c6TFJZUMqxvHP0To+1+OdlUtGWkGp/imZ7+dUvCL76b0+SYvfcMCfRmcK8Yru0Ubrenl6Mvy7qasgb1GIpncITd5JhJ5V9HyV02j+hJrzK8bzzL1h+xuWZQz1jpNSaEEEKIZqWumM2VGNYkIGEg+YWlbN6bxT23XkULH+ND3Yq/jlKa9htV2X+i9W9xLpZMRK2q4MzPn1CVc/xcXDuQoB5D8I1PJPvzOQRc3c8mxnMao9aqUKspzOb0sleInvQqQT2GUpSy4vzndnPnhRDiwrnc07AJVnn27NmTX3/9ldtvv53Ro0czcOBArrnmGmJiYhg/fjxgrAbLysqidevWdO/e3eYegYGB3Hjjjfzwww/s3LmT0aNH89tvvwGYt2xa6tChAz///LPN8bNnz3Lfffdx6tQpRo4cyR133GFzzY4dOwDo06eP3c/Tv39/Dhw4wM6dO81rHTt2LHPnzuXbb781J8h+/fVX8vLyGDNmDH5+fi7de8CAAaxdu5bffvtNEmTCvtqjqh2pvW1Ro2jxjohHrSwja8lMp2Wo3hFt7SbHyiqqmb1oO2mZxkBAUTQ8cWcipen7HK7FsqItuN9YqzWZn/45SY7Vfk+TTbtPmadC+vl4mpNRzr4s1coywMHTS41CUI8hlKXvde2LNn0fo/p34o+MfHTl57dYdo4NsRpxLoQQQghxpXMWs/1+OIe3n76JAF9P12PYdols2XacTjHBeHpoMeiryFr8ouP4NXkaQdcNM1Z3HddZHY+8ayYaDw+bGK+mMJusj6cSM+UdfKI7WcWoNWfzKNj0X4p/X4taYawWM8V/Qd1voWjrN+ZBVxdz0JQQwsidnoZNrcpzzpw5/O///i+HDh3irbfe4q233iIsLIybbrqJcePG0a1bN3JzcwHsNprdIOsAACAASURBVLk3MVWV5efnA5h7l9Vu8u/MH3/8ARgr2H766ScyMjKIj4+3uiY727itfMqUKU7vZboOYOTIkbz22mv88MMPTJ06Fa1Wa95eaVmhZnrN3LlzmTt3rsN7nz592uXP5CpJkF1BTE1LHZWUOtq2qFG09S5D1Soam6AnNiKQsGB/cjdvcrpeU0VbTfEZwv/nEYv1OM/i23tPS2mZhcxetJ35j50vIXX2ZVmVd5Ka4nwCEgbaPL30ahWDR1BLCjYudbomE93+zYSPTuSVhwYAkFdUzq4/cuh/bZRUjwkhhBCiWXEWsw3vF09YC19eeH8rD93ejfDk6eQuq7v1xrC+bRnWty0AWYtnOY9f7VR3WR4HKNjwmc1rPQJC0Pr4k/vdW1TlHEfx9kOtLKMq76TNpHcwxX+P4tUqxjzR0jRoqqlUpwjRXLja07CpVXlGRUXx9ddfs2PHDtavX8+2bds4duwYX331FStWrGDmzJlcc801dd5HrzcOITH15qqpqanXekz9xd5++21eeOEFPv30UzSa8/+WNb3P4MGDzZVf9lx11VXm/x0SEsLgwYP58ccfSUlJoUePHmzYsIGYmBh69eplvk49VzDTr18/8yRMezp06FCvz+aMJMiuIJajql3dtmhQ9ZQft6is0ih4tYqxCQTOl6FeYx6Nq1dV9h/Ltwl6/HyMf6xc/nLSFbj8GR29Z21pmYXsPZJHQoeW5qSUw/UYVIp3ryM0abzN08u6tl/arO/cF+2ilfspLq1iUK8Yhvdre67PhiTHhBBCCNE8OIvZFEXDsL5t2ZOWy54jecz8YDtzHrjefuP9czFsZWU1n33/Byeyi3nm7z3Q5qS5XN0fdN0wKk4eQq0opSrvpPm4b9sE9KVnbddniv9KCs0JL6ef9Vz8Z3pdYwyaEkK4xt2ehk2Joij07duXvn37AsY+YEuWLGHRokXMnz+f77//HoBTp045vIdpcqQpsdSqVSsyMjI4ffq0eUKkpeXLlxMaGsqgQYPMx6677jomT55MVVUVq1at4rfffmP58uUkJyebrwkPD+f48ePcd9999OzZ0+XPOGbMGH788UfWrVuHTqejoqKC2267zSr5ZurDdttttzF69GiX790Q5JHGFcaU/PKNu4bw0Y8SOX4W4aMfxTeuq9X589dr0e3fhOIbQPANY4l9+F3a3P8GUXfPpc39bxD78LsE3zAWxTfg3Ihsrfm1WkVh/c6TNmsoqzBmqRvjy8nRe9qzYVemVVLK2XqKd6+lujCH1snTrMaGO91+aW995z5L6rF8Nu0+xQvvb+PpN7dQVlGD/tw0SyGEEEKIK52zmC02IpBWwb5s2GU8n51fyhMLtrBk9SHKQjpYxbA+sdewZmsG9875iZWb/6SwpJJAfx90+zc5fX9TbOvdOh6PwFCiJs6xim1LD+9Aoyh4Rba3eW194z+1ssyq2k0IcXGZehq6wlTl2RQcP36cUaNGcf/991sdj4iI4OmnnyYkJISysjJ8fHyIjo4mJyeHPXv22NynpKSElJQUFEUxV2T16NEDgC1bbPs8ZmVl8fzzz/PGG29YJahM1WdeXl688MILAPzf//2febsmYE6K2bsvwLRp0xg7dizr16+3Ot6/f38iIiLYsGED69atQ6PRcNttt1ldU9e9FyxYwOjRo1m2bJnd8xdCEmRXKMtElvFnJ/+pNQrR971OaNJ4qvJPkfvtm2QvnU3ut29SlX+K0KTxRE96HexUQBWWVNocy8wp4UxRKf4JSS6t1d0vJ3vvWdd1dX1ZmgYHqFUVRE96ldbjZxHQdSDagGD0ZcUEuPpZzjWPzcwpMR8zbfmUCjIhhBBCNCeOYjbTbgPL8yVl1Sxbf4R/zFvPI/M3snb7cQCmLkzh/61IRVdebfVaZ9X9HiGR5ti28nS63dg2ZMDtAPh37m3zesv2G64ISBiIvqyY0JvvJXrSqyje/rK1UohLwLIvtzOmKs+m8v/TmJgYCgoK+PXXX22a5qekpFBYWEh0dDRhYWHcc889AEydOtWqkqy0tJRnnnkGnU7HkCFDzFVYt99+O15eXixZsoSdO3ear6+oqOCll14C4H/+538cru2GG25gxIgRFBcXM2fOHPPxcePG4evry3/+8x9++uknq9d8/fXXfPPNNxw5coTExESrc1qtlttuu40zZ86wdu1aevXqZTWNE+DWW2+lVatWfP/99yxdat3q6JdffuGjjz4iLS2NhIQEh+uuL9liKQgdPBENGrtTGi2bmYYOmmjz2pBAb5tjqmpg9bZMJg53f2iAKyzfU1E0xEYE4ufjQVnF+ab4ta9zZYhBTWE2+WveJ3L8C/jGXWO1Lr92rjePXbH6kHkNJva2fAohhBBCXMnsxYlwfreBozgyM6eEHldFcPh4ARpFQ9vIIHOMV9dOBcUviKi/z0bj4ek8th03HYOq4hPV0TbGc9J+ozZT/Ac43LEhhLh46tuX+1LSarXMnj2bhx9+mIceeoiuXbsSHR1NXl4ee/bsQavVMnPmTAAmTpzInj17WLNmDSNGjKBXr174+vqya9cuCgsLufrqq3nxxRfN946JiWHWrFnMnDmTu+++m+uuu44WLVqQmppKbm4uvXv35h//+IfT9U2bNo0tW7awdu1a1q9fz+DBg2ndujWvvPIKzzzzDA8//DCdOnWibdu2nDhxgrS0NBRF4fXXX6dly5Y29xszZgzvv/8+qqoyZswYm/O+vr4sWLCAyZMn89JLL/HJJ5/QsWNH8vPz2bt3L2BMEHbp0uUCfuv2NY0/EeKiMqh6q5+1voGUpu2gujDb7vWmZqYe/sFWlV56VWVwL9t9zABrtmaQc0ZHePJ0hxn8+pSgm94z0M+T5Js78Z8Zg3n76Zt47eEBvP30TfxnxmCSb+5EoJ8ng3rGWm1rNH1ZOltP+N+ewKCqqFgnsQyqvu7XJk8n54yO1Vsz7F5Te8unEEIIIcSVylmcmJlTQl5ROYN62p4P9PPk/tFdaRnkxVVtQ21ivMKSCrs7FUxbKmOmvINHUBinv7Tf8B/OxbZfzkOjKOjLdTYtNsCi/cY412PZpvKPbSGaM8u+3KZdQb7x3QjoOpDW42c12SrPm2++mQ8//JABAwZw6tQp1q9fT2ZmJkOGDGHZsmXcdNNNgLFP2b///W9eeeUVrr76anbv3k1KSgqRkZE899xzfPnll4SEWLcwuv3221myZAkDBw7k6NGjbN68GV9fXx566CEWLVqEh4fzuqnw8HAee+wxAF566SV0OuMU3+HDh7N8+XJGjhxJYWEhGzdupKSkhKFDh7J8+XKGDx9u935t27alZcuW+Pn5MXToULvX9OzZk5UrV3LHHXdQVVXF5s2b+euvv7jxxhv5+OOPmTRpklu/X1dJBVkzYsqSl584YGzgrytCGxBMQEISQT2G4BufSPbnc6ixkyg736S/q/mYVlG4tlM4nWNDbBqwlpRVWzdcdXFoQF1M77nw6SRCWvhRmr6P3M3nP4t/QhIThydya784QltYT9NwbYiBHo2isP9ILut3nqSwpJKQQG+G92tLl7gQ+69NSMKvXTdyzuiY+cF28xaA2lzdGiqEEEIIcblzFieqqoEftx1n4vAuVucjW/ozd/L1hIcGUJaxzypeNcV4Q3rH8Mu+bG4beL663yMkksjxM/EMjkCtrqQsfZ9rDfwzUvFuHY/G09tujFejK8SnRasGjWWFEI3Psi+35a6gpp7M7t+/P/3796/zOo1Gw5gxY+xWXznSs2fPOpvp9+nTh7S0NLvn7r77bu6++26b4126dOFf//qXy+sA2LVrF/n5+dxxxx1OJ2DGxMQwd+5ct+59oSRB1kwYVBW1stRuqanlNsrIu2aStfhZ1HKdzT10qZtstkPqVQOz7r/e7gjv7PxSFn6VyoxJvRv0y8mg6gny0jsvm79zxrlk1/lebMZJko6/LFXVQGmFntmLUmw+y6bdp+jeqZXdz1Kiq2DJ6kOs3prhMDkGjrcZCCGEEEJciZzFiWu2ZjC8b1tm/fN6Zn+4nb/ydcydfD0h3qrTGC88eTo3JESSW2DcqZD/7QJajpiM4ulDzso3ibjtsTob+JvveS62NcWl9uLDy/Uf2kIIN/tyi0ZVVVWFh4cHRUVFvPLKKwCMHz/+Eq/KliTImgmNojjchw3nt1FGT3qVoB5DKUpZYXONaYS1Ja2iwc/Hk/mP3cjeI3ls2JVprroa1DOWazu1Qq8a0NTaWnghX04aRVv3Z/niZaInvcqve7P4cfsJQgK9Gdwrhms7haNXDWjtfFlqwG4AZ7LnSB4z3t3K/MduNB/Tqyp//lXMsvVH6ly3acunbLMUQgghRHNxPk7MZcOuk1ZxYstgX/SqyvzHbiQ7v5TwUH+7yTGTyr+OkrtsHtGTXmXl5mP07dqayPHGCWtZi6ei0dbdwN+SKbY1xaXO/jEt/9AWQoj627FjB1OmTEGv16OqKiNGjODqq6++1MuyIQmyZsCg6ik/ccC1UvP0fQR1v4Wird+Awbo3mGmEdW2mhE9ChzCu7dTKfNzU/6shE0Lufpar4jrwf0t/R1UNbNp9is6xIcy6/3r8fDyt1qVXVfYfy3eYHDOp3Wzf2fYBS51jQ6x+N0IIIYQQVzK9aqCsopr/W7KLjjEhDOsbx5PjrzOfLyyuoLKqBg8PY+KpdagPZRkubo1M30f/bh148q1f+OC5QajZh6j86yhe4XGA4wb+tTmKbYUQQjSsuLg4goKCqKio4Oabb7YaJNCUSIKsGdAoWnSpm1y6Vrd/M+GjH8WrVQxVuSeszgV0S3LaZ0Fb63hjVEq5/1kSiY0I5Hh2MWBMcM1etN2qCgyMa1+/86RL992wK9MmEeho+wBgTspJ9ZgQQlyZVv1r9AXfY9RT3zbASoRoOrSKxhwb7TmSx1cbj9pMHu/YJtgck9UnxhvcMxYfHy9yz72uKu8kNcX5BCQMRHdgS533qSu2FUII0TBiY2PZunXrpV5GnSRB1ky4W2queFs3y/OO6mjTf+xScfez+PlY/zGvXQVm4moT/drXubrNVJJjQgghhGgO7FXmq6rB/MDSpHZM5m6Md8+txu055tcZVIp3ryM0aby5gb8jTSm2FUII0TRIgqyZcLfUXK0sMx+zHGHdGE/YLJvn2/vZZo1ufpayihqbc7WrwMD1Jvr2rruY20yFEBdH+stj6/3adjNWNNg9RNN2If+NQf47iyuDvdhNV15NoJ8nJWWOBxiBdUxW362Rlq8r3r2WwMTBtE6exullr9hNknlHdaT1uOkY9DWgUaSCTAghBCAJsmbBoOoJ6Jbkcqm5vqwYbUAwAeFtG3WEtamqav+xfNbvPN+01bqZvnViyd3PUlpWSWZOic252lVgelVlcK8YNu0+Ved9nTXbvxjbTIUQQgghmgJnsVz/xGg6tAnmhQ+2kZ1f6vAeppjMrRgvIYmqqmq0Hh4oqFavU8t1ZH8+h8i7ZhI96VXK0veh278ZfWkhWv8Qc2xbXZhD3pr3aT32mYb5ZQghhLjsSYKsGdAoWvziE90qNY+8yzgRqLFGWJsat9rr22XZTN/fxxMNqsXkII1bn6W0vMru+dpVYNJsXwghhBDCda7EcjP/0YeXHujLkws2260kC/TzZNj1cecq0NyIV9sZ41WDqrcb59YUZpO1+FmCegwlqPsthI9+9Py6y3UUbPovxb+vRa3QUZaRim9cV6kiE0IIgfxN0EwYVJXWd87AO6qj3fOW2ygtNVawYNm41Z7isipqqmtQFA3lJw6Q++2b5P3wHhpFoaa0iNbJ05x/luRp1JQW4e/rRWxEoM01piowS6Zm+51j7U80smy2L4QQQgjRnNUVy6VlFjLnox20DvNneN94m/ORLf359+MDuSExmv3H8lm4fC9FxeV1xqsR42ZgUPUAlJ84QN7q96kpKaD1uOlWr1PLdRSlrCBz4f+Ss3IB+nId1cVnOPnuIxSlrECt0AGgS90kyTEhhBCAVJA1GxpFQfH2N5aaZ6SiS91kU2p+sab42GvcainQz5O5k68nwKOGrMVTzU8DfWK6AFCwfgkhA5Ltl80nDMSvXSLVhTkU/rqM8FGP2DTpd1QFJs32hRBCCCHqVlcsZ2KcYJnLsL5xfLXxKOq5h4yBfp7MeaAvPt4ePP3mFvN99h3LZ96Dfe3HqwlJ+LXrhkHVo1aVc/rzueYYsfz4fustlQe2oPHwxCOwJT7xCfi26Ux1YQ7Zn89BLbceFGBq+C+EEEJIgqwZMSW/fOOusZra01jbKC2ZSuDBuJ2xfXQQyTd3Ys3WDJuS++H94gkPDbBKjoHF4ACD6rBsvuZsnrls3q/DdYB1k37LKjD7PcSk2b4QQgghhDNaRWH9zpMuXbtx10meHH8dsRGB5imWw/vFExHmb5UcA8jOL+XRNzYzemB7RvbrTPho63hVVQ0oitYqOQbnt1S26D2KoF4j8G3b1aI9h3Fbpe7gr6gVtn1pazf8F0II0Xw1ywRZVlYWCxcu5Ndff6WgoICQkBCSkpJ49NFHadXKurIoIyODt99+m99//52ioiJiY2NJTk5mwoQJKJdpObZlwGD8uTETY8aqtPITB4xPAXVFxgEACUlMHJ7IkN4xzPxgu7l5q6JoGNE3ltL0fTb9J6ryTlJTnE9AwkB0B7ZQlLKCoq3f4NUqBsXbD7WyjKq8k2AwJvwCuiVRUlpBaJA38VFt3KoCk2b7QgghhBCO1R54VNd1/ROjCA70JjTIm+TBHdl7JNduBVpJWTWfrTnMf9emERcZxFN39aBNRKAxNlP1lGUcsNujTPEJJKDrALTefpRl7KsVdw4kpP9YAq7pT/bnc6gpzDa/LqBb0kXbRSGEEKJpa3YJsv379zNp0iRKSkro1KkTCQkJHDhwgGXLlrF9+3a++uorWrRoAcDhw4eZMGECOp2OHj16kJCQwI4dO5g7dy779u1j/vz5l/jTNG0GVUWtLOX0Fy/bBDK6A1vwjupIePJ05jxwPU8s2EJJWTWxEYGEBfuTu3mTvRtSvHsdoUnjzzdiNahU5Z6wudRy4MDsB/oBUgUmhBBCCNFQag88quu6cbd0ZpzF8boq0FTVQEbWWVZsPMqT4427AjSKFl3qJptrFd8AIsfPRPH0sdmBAOfjztbJ04i8ayZZi59FLddZxYtCCCFEs3pUUlVVxdNPP01JSQnPP/88q1atYuHChaxbt46hQ4eSmZnJ22+/DYDBYODZZ59Fp9Px+uuv8/nnn/POO++wdu1aOnfuzKpVq1i7du0l/kRNm0ZR7CbHTCr/OkrusnlEhAWYm7ea+oXpdUV2X1O8ey3VhTl1N+m3M3BAEmNCCCGEEBdOr6oM7hXj0rX2BiOB+xVo5ve2EyMG9RiKZ3AEp5e94jTuPL3sFTxDIgjqMdRhvCiEEKL5alYJstWrV3P8+HFGjRrFxIkTzce9vb2ZNm0aLVu2JCMjA4CUlBTS0tLo3bs3o0ePNl8bGhrKiy++CMCSJUsu6vovJwZVT1mG7TbJ2ir/OkpZ+j6G941FUTTmfmHagODzF2kUvMLj8InpgkdgGNlfvIxaVUH0pFdpfdcLBHQdiG98NwK6DqT1+FlET3oVxdtfSuWFEEIIIRqBVlG4tlO4w8nfJqbBSPYeUrpbgWZ+78AQc1zoFR4HigdBPYZQlr7X5bgz+IaxEi8KIYSw0ay2WK5btw6ASZMm2ZyLjIwkJSXF/PMvv/wCwM0332xzbY8ePQgLC+P3339Hp9MREBDQSCuuP8um+PZ+bujX1eaoBN4e3f7NhI9OJDYikMycEs4UleKfkETZn7uNjfh7DMEjqKX5+prifEr2bwaDgRa9R+HXLtFivY0/cEAIIYQQornTqwZm3X89sxdtt9tLzNlgJFMF2qbdp+p8H1MFmlbRYFBVWg6fjOJ5PmlWoyvEIyCEgo1LXVq3bv9mc+xoihcbKv4VQghxeWtWCbI//vgDT09PrrrqKrKzs1m1ahWZmZkEBwczZMgQunU734Pg2LFjAHTq1MnuveLj4zlz5gx//vkniYmJdq+5FBw2xe+WhF98osMmpPV9nTOOtknaXHduvHZix5bERwVRVQNh7RLxvv/feASGUpa+l4KNS60brd4wlpriMyhe1k8VJTEmhBBCCNH4tIoGPx9P5j92I3uP5LFhVyaFJZWEBHrXORjJsgLNXnLNxFSBBpax6mGrWDWo1wg8AkLcjjut79lw8a8QQojLV7NJkFVVVZGdnU3r1q358ccfmTFjBuXl5ebzixYt4h//+AfPPvssALm5uQA2Uy1NTMfz8/PrfO+vv/6ab775xqV1Hjp0yKXr7HGlKX7rO2fYlJPX93V1sdom6ey6c+O1/zk6ATA+kTSoejQens4brd45Q57wCXEFu1jfnUIIcSW5mN+dpuRXQocwcyILXBuM5E4FmoLBYaxalXuCNve/4Xbc2VjxrxBCiMtXs0mQ6XQ6AM6ePctzzz3HsGHDeOihhwgLC+PXX39l9uzZfPTRR8TFxTFu3Dhz8szHx8fu/UzHy8rK6nzvrKwsfvvttwb6JI650hT/9BcvEz3p1QZ5nTMGVU9AtyR0B7bUeW3t8drGYErb4GsSQlxeLtZ3pxBCXEkuxXentlYCyZXBSO5VoGkcxoVVeSepKc4nIGGg23GnxJpCCCEsNZsEWVVVFQDl5eX079+f+fPnm8+NGDECPz8/Jk+ezMKFC0lOTkarNVYlaTTO/4JXXZh8Ex0dTe/evV1a56FDhygpKXHpWksGVU/5iQOuNSfNSMU3risaRan36+qiUbT4xSfiHdXR6b3tjddurDUJIS4vF+O7UwghrjSX03enKxVodcaFBpXi3esITRrvctzp1jApiTWFEKLZaDYJMstKsLvuusvmfFJSEhEREeTk5HD8+HF8fX0BqKiosHs/03F/f/8633vMmDGMGTPGpXVOnDixXk/93GqKn7rJnJSq7+tcYVBVWt85w+HTOcvx2pZBR2OuSQhx+bgY351CCHGluRy/O51VoLkSFxbvXktg4mBaj5vO6S/nOY47x00/F3dKrCmEEMJWs0mQBQYG4unpSXV1NW3atLF7TVRUFDk5ORQWFhIeHs6hQ4fIz8+nffv2Ntfm5eUBjnuUXQr1aU56Ia+ri0ZRULz9iZ70KmUZqcbmp6WFaP1DzjU/7eaw+WljrUkIIYQQQlxe6ooL1XId2Z/PIWriS8a4M30fuv2bz8edCQPxa5dITUmBOe6UWFMIIURtzSZBptVqad++PYcPHyYnJ4errrrK5hpTw/2wsDA6duzI5s2bOXbsGH369LG6zmAwkJ6ebr5nU+Fuc9ILfZ0r/j979x4dVXnvf/wze8iFXJSACQgmMQiJqRIikAg9BSJIUVc59KByRA4FtGj7q0tbRT2KLKUKWg70nGI5baVejvRYi7d6qJaqYAS5BpBbhSQIEhIhBBMgQyDA7Pn9QWckZDKZTOaSzH6/1nItZz/P7Hlmo1/2851nfx/3TUjXzGua/Prm+sejqS0tVw/lmAAAANB5+HNfeK7ukOrWvKnUW+5RbGq60sbf/03b8RrVFr8mZ0O9Um+51+9zStxrAoCVWOph+hEjRkiSVqxY0axt3759qqqqUlpamtLT0zV8+HBJ0sqVK5v13bp1q2prazV48GAlJSWFdtB+chfF94e7OGl73tdWF+806auOQ7jGBAAAgI6tLfeFiVdfr3PHa1Tx6x+rcsmD+urVJ1S55EFVLP5/Orb2LSXmDpPLNLnXBAB4ZakE2R133KGEhAT9+c9/1vLlyz3Hjx8/rieeeEKmaWry5MkyDEOFhYXq37+/1q5dq2XLlnn61tbWas6cOZKk6dOnh/07tOTCovi+uIuTuhNUgb4vlDrimAAAABB+bbov7DtQJz77UDLP6cyRAzp9cLfOHDkgucwm943cawIAvLFUtO/Tp4/mzp0rwzA0c+ZMTZgwQT/60Y80duxYbdmyRUOHDtXdd98tSTIMQ/PmzVNCQoJmz56tiRMn6r777tNNN92k0tJSTZw4UaNGjYrwN2rKXRS/pb/sLyyKH4z3hVJHHBMAAADCz9/7wnMnvtaJLX9rsf3C+0buNQEAF7NMDTK3W265RVlZWfrNb36jkpIS7d27V+np6brrrrs0ffp0xcTEePrm5eXpjTfe0KJFi7Rx40aVl5crMzNTDz74oG6//fYIfgvvAi2K355i+h3tuwAA0BktXzg+0kMAOiz/7gudsnVNVtqEh/y6b+ReEwBwMcslyCQpNzdXixYt8qtvv379/O7bEQRaFD/Q94VSRxwTAAAAwq/1+0J7K+3N7xu51wQAXMiSCTIraEtR/GC8L5Q64pgAAAimfXNvDfi9fWe9JUka99C7zdo6y8o0b2MPRGf5vghca/eFgdw3cq8JAJAsVoMMAAAAAAAAuBgJMgAAAAAAAFgaCTIAAAAAAABYGgkyAAAAAAAAWBoJMgAAAAAAAFgaCTIAAAAAAABYGgkyAAAAAAAAWBoJMgAAAAAAAFgaCTIAAAAAAABYGgkyAAAAAAAAWBoJMgAAAAAAAFgaCTIAAAAAAABYGgkyAAAAAAAAWBoJMgtymU6frwEAAICOhPtXAECodYn0ABA+LtOUzTB06sAuOXYUy+k4JntSNyXlFSkha6CnHQAAAOgIuH8FAIQLCTKLcJmmzMaTOvz6XDV+Vd6kzbFrteJ691evO2bJiEvkJgMAAAARx/0rACCc+JvEImyG4fXmwq3xq3Idfn0uNxcAAADoELh/BQCEE3+bWIDLdKph//YWby7cGr8qV8P+HXKZZphGBgAAADTH/SsAINxIkEWpCwuX2gy7HDuK/XqfY0cxv8IBAAAgpForus/9KwAg3KhBFmVcplM2w65TX+6SY2exjK6X6LLvTpfTccyv9ztP1oV4hAAAALCqthTd5/4VABBOJMiiiMt0ymxsaFKrITYtut4bPQAAIABJREFUU5JkT+rm1znsiSkhGx8AAACsq61F99t6/8qOlgCA9uBvkChiM+zNbjjO1BzUuRNHlTRgpF/nSMorooYDAAAAgq4tRfddplNJeUV+nTdpwEidc9SRHAMAtAt/i0QJl+lUwz4vhUxdpk5s/UAJffMV17u/z3PE9e6vhKw8bi4AAAAQVG0tui/ZlJA10L/7174DdWLzXynWDwBoFzIhUcJm2OXYWey17cTWv+lsXbV6TXysxZsM95J2bioAAAAQbIEU3XeZpnrdMcv3/evEx3S2rlontvyNYv0AgHahBlkUaamQqXnKoUN/fFqXT5qtPtOfU8O+7XLs/ETOk3WyJ6b8oyhqHnUbAAAAEDJtLbpvMwwZcYne718HjFRC34E6W1etQ398WuZpB8X6AQDtQoIsivgqZHqu7pCqXn5Elwwaq0sLv6eEvgM9be5VYyTHAAAAECqBbBplMww5dq9TfO/+Sht/v+f4ueM1qi1+TSe2/E3maUez9wEA0FYkyKKEy3QqaUCRHLtWt9jHPOXQsbVvKT7zWnXNvEY2wy6JxBgAAABCy11039e9qpt70yh3sX4jPlEVi/+fYlPTZcQlyGxs0Jmag5LLbPF9AAC0FQmyKGEz7Eroe76Qqa/ip+5C/AAAAEC42Ay7p+h+W+5VPe+7/CrucQEAIcXPK1HEZTpbL2R6xyy5TGeYRwYAAACr86vovpdNowJ9HwAAbcEKsihiM+wy4hLOFzLdv0OOHcVeCvE7PY9WAgAAAOHSpOh+i/eqzR+RDPR9AAC0BQmyKONOfnXNvKbJMnP3qjGSYwAAAIgUdxKr+b2q702jAn0fAAD+smSC7M9//rMeffTRFtt/9KMf6Wc/+5nn9c6dO7V48WLt3LlTDQ0N6tevn37wgx9o3Lhx4RhuQC5OhJEYAwAAQEfR/F7VvwRXoO8DAKA1lkyQ7d69W5L0T//0T+revXuz9tzcXM+/r127Vvfee69M01RBQYG6du2q9evXa+bMmdq7d2+TRBoAAAAAAAA6H0smyD7//HNJ0rPPPquePXu22O/06dN6+OGHJUkvvfSShg4dKkmqqKjQlClT9Nvf/lZjxozRtddeG/pBAwAAAAAAICQsuSZ5z549uuyyy3wmxyTp3Xff1ddff61x48Z5kmOSlJGRoZkzZ0qSli5dGtKxAgAAAAAAILQslyA7ePCgTpw4oWuuuabVvmvWrJEkjR49ulnbDTfcILvdrtWrVwd9jAAAAAAAAAgfyyXI3PXHevTooaefflpjxozRgAEDNHbsWC1evFiNjY2evuXl5ZKk7OzsZudJSkpSWlqaamtrdfTo0fAMHgAAAAAAAEFnuRpk7vpjb7/9trp166ZBgwapZ8+e2rVrlxYtWqQ1a9bolVdeUXx8vGpqaiRJqampXs+VmpqqQ4cO6ejRo7rsssta/My3335b77zzjl/jcyfwAMDqiJ0A0HbETgAAAmO5BJn7RuDmm2/WvHnzlJCQIEmqrKzUT37yE3322Wf6r//6L/37v/+7Tp06JUmKj4/3ei738YaGBp+fWVVVpU2bNgXrKwCAJRA7AaDtiJ0AAATGcgmyRYsW6eDBg8rIyFBsbKzn+BVXXKHnnntO//Iv/6I//elPeuihh2S32+VyuWSz2Xye0zRNn+19+vRRYWGhX+PbvXu36uvr/eoLANGM2AkAbUfsBAAgMJZLkMXFxalfv35e23Jzc9WrVy8dOnRIX375pbp27aoTJ06osbFRcXFxzfqfPn1akpSYmOjzMydMmKAJEyb4Nb4pU6bwqx8AiNgJAIEgdgIAEBjLFelvjbuW2KlTp5SWliZJnlpkF2utRhkAAAAAAAA6PpvL5XJFehDh4nA49Itf/ELHjx/XL3/5S3Xp0nwB3dChQ1VXV6c1a9Zo3rx5+utf/6oXXnhBI0eObHauwsJCXXrppVq/fn3QxjhixAhVV1crOTlZubm5QTsvAFx99dWaNWtWpIcREsGMnUuXLg3SqABEypQpU4J2LmInALRdNMdORC9LPWKZmJioDz/8UHV1dSopKdGwYcOatH/yySeqq6tTdna20tLSNHz4cP31r3/VRx991CxBtmrVKjmdzmbH28td8L++vp4l7wDgp2DGzpycnGAMCQA6PO47AQD4hqUSZDabTRMnTtTvfvc7Pf3003r55ZfVs2dPSVJFRYV+/vOfS5J+/OMfS5LGjh2rhQsX6p133tGNN97oSYYdPHhQCxculM1m07Rp04I6xiuuuEKVlZVKSEhQZmZmUM8dDu5ir/wS2TKukW9cn9YFeo2uvvrqEI4qsjp77LwY/x9EHn8GkdWRrj+x01o60n970YDrGTyd7VpGc+xE9LLUI5bS+cL6d911l7Zs2aKEhAQNHjxYkrRx40adOXNGd911lx599FFP/5UrV+r++++X0+lUQUGBEhMTtWHDBp06dUo/+9nP9KMf/ShSX6VDchd7LSws5DGlFnCNfOP6tI5rFP34M448/gwii+uPSOG/veDiegYP1xIIPUutIJOk+Ph4vfLKK3rllVe0fPlybdy4UbGxscrPz9eUKVP03e9+t0n/0aNHa+nSpVq8eLG2b98ul8ulnJwcTZs2TTfffHOEvgUAAAAAAACCxXIJMkmKjY3VPffco3vuucev/oMGDdKLL74Y4lEBAAAAAAAgEoxIDwAAAAAAAACIJBJkAAAAAAAAsDQSZAAAAAAAALA0EmQAAAAAAACwNBJkAAAAAAAAsDQSZAAAAAAAALA0EmQAAAAAAACwNPtTTz31VKQHgeiSm5urwsJC5ebmRnooHRbXyDeuT+u4RtGPP+PI488gsrj+iBT+2wsurmfwcC2B0LK5XC5XpAcBAAAAAAAARAqPWAIAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0kiQAQAAAAAAwNJIkAEAAAAAAMDSSJABAAAAAADA0rpEegBoau7cudqzZ4+uvvpqzZo1K9LDAYBOgdgJAG1H7AQA4BskyDqYPXv2aNOmTZEeBgB0KsROAGg7YicAAN/gEUsAAAAAAABYGgkyAAAAAAAAWBoJMgAAAAAAAFgaCTIAAAAAAABYGgkyAAAAAAAAWBoJMgAAAAAAAFgaCTIAAAAAAABYGgkyAAAAAAAAWBoJMgAAAAAAAFgaCTIAAAAAAABYGgkyAAAAAAAAWBoJMgCIAKdp+nwNAPgGMRMAAIRal0gPAACsxGm6ZDds2rn3qFaWHFRdfaNSkuM0uiBd+dlpnnYAADETAACEDwkyAAgTp+lSw+mzmrNkg0or6pq0FW+tVE5Gip6cMVQJ8TFM+ABYHjET3ox76N2QnHf5wvEhOS8AoPPgEUsACBO7YfM60XMrrajTnCUbmOgBgIiZAAAgvEiQAUAYOE1T28qOtDjRcyutqNO2sho5TVeYRgYAHQ8xEwAAhBsJMgAIA7thaGXJQb/6rtpcwYoIAJZGzAQAAOFmyRpk7777rv73f/9XZWVlMk1TWVlZmjBhgv7t3/5Ndru9Sd/9+/fr+eef15YtW3Ts2DFlZGRo4sSJmjx5sgyD/CIA/9XVNwa1HwBEM2ImAAAIJ8slyObPn68XX3xRsbGxKigokN1u1+bNmzVv3jxt2rRJv/71r2Wznf8Vcs+ePZo8ebIcDocGDRqkAQMGaOPGjXrmmWe0fft2LViwIMLfBkBnkpIcF9R+ABDNiJkAACCcLJUg27Nnj1566SV1795dr732mrKysiRJ1dXVmjRpkj766CN98MEHGjt2rFwulx555BE5HA7Nnz9f48ef39mmtrZW06ZN0/LlyzVmzBiNHTs2kl8JQCfhNE2NLkhX8dbKVvuOGpIhp+nikSEAlkXMBAAA4WapZwTXr18vl8ulf/7nf/YkxySpZ8+euvPOOyVJJSUlkqS1a9eqtLRUhYWFnuSYJHXv3l1PPfWUJGnp0qXhGzyATs1uGMrPTlNORorPfjkZKcrPTmWiB8DSiJkAACDcLJUgcz86WV1d3aytru78LkndunWTJK1Zs0aSdOONNzbrO2jQIPXo0UNbtmyRw+EI1XABRBmn6dKTM4a2OOHLyUjRkzOGshsbAIiYCQAAwstSj1gOHz5czz33nFasWKEXXnhBt912m7p06aIPPvhAr776qi699FLdeuutkqS9e/dKkrKzs72eKysrS19//bW++OILDRw4MGzfAUDnZTdsSoiP0YIHRmhbWY1Wba5QXX2jUpLjNGpIhvKzU3lMCAD+gZgJAADCyVIJsquuukpPP/205s6dq4ULF2rhwoWetuuuu07PPvusLr/8cknSkSNHJEmpqalez+U+fvTo0VY/9+2339Y777zj1xh3797tVz8AnZN7IjegXw/lZ38TX9wrIJjofYPYCYCY2XbETgAAAmOpBJl0/vHIYcOGacOGDcrLy5NhGNq+fbt27typ1157TY8//rhsNptOnTolSYqPj/d6HvfxhoaGVj+zqqpKmzZtCt6XANDp2Q3jotdM8i5G7ATgRsz0H7ETAIDAWCpBtm3bNt11113q06eP/vKXv6hPnz6Sztcku++++/Tqq68qKSlJDzzwgOx2u6Rv6pa1xDTNVj+3T58+Kiws9GuMu3fvVn19vV99AXRcTtNsMqG7+DVaR+wEOh9iX+QROwEACIylEmTz5s3TyZMnNXfuXE9yTDq/i+Uvf/lL3XTTTXrllVd0zz33qGvXrpKk06dPez2X+3hiYmKrnzthwgRNmDDBrzFOmTKFX/2ATsxdD2fn3qNaWXLQUy9ndEG68rPTqJfTBsROoPMg9nUcxE4AAAJjmQTZ6dOntWPHDl1yySXKy8tr1p6enq6srCyVl5frwIEDSktL0+7du3X06FFdddVVzfrX1NRIarlGGQDrcZouNZw+qzlLNqi0oq5JW/HWSs+OawnxMUwUAUQNYh8AAIgGllnzXl9fL5fLJcPHMn/3Y5Vnz55V//79JX2zm+WFXC6X9u3bJ7vd7jV5BsCa7IbN6wTRrbSiTnOWbGCCCCCqEPsAAEA0sEyCrEePHurWrZuOHTumHTt2NGuvrq7WF198oZiYGPXt21fDhw+XJK1cubJZ361bt6q2tlaDBw9WUlJSyMcOoONzmqa2lR1pcYLoVlpRp21lNZ4d2ACgMyP2AQCAaGGZBJlhGLrtttskSbNmzVJ1dbWnrba2VjNnztTZs2d16623KjExUYWFherfv7/Wrl2rZcuWNek7Z84cSdL06dPD+yUAdFh2w9DKkoN+9V21uYKVFACiArEPAABEC8vUIJOk+++/Xzt27NCmTZs0ZswYFRQUyGazafv27Tpx4oTy8/P16KOPSjqfUJs3b56mTp2q2bNn680331RaWpo2bdqk48ePa+LEiRo1alSEvxGAjqSuvjGo/QCgMyD2AQCAaGCpBFlcXJxeeuklvfbaa3r33Xe1ZcsWmaapK6+8UjNmzNC0adMUGxvr6Z+Xl6c33nhDixYt0saNG1VeXq7MzEw9+OCDuv322yP4TQB0RCnJcUHtBwCdAbEPAABEA0slyCQpJiZGU6dO1dSpU/3q369fPy1atCjEowLQ2TlNU6ML0lW8tbLVvqOGZMhpunjUCECnR+xDR7J84fg29R/30LshGgkAoDOyTA0yAAglu2EoPztNORkpPvvlZKQoPzuVCSKAqEDsAwAA0cJyK8gAIFScpktPzhiqOUs2eN3RLScjRU/OGMoKCgBRhdiHC4VqVVZbVoftm3urz/a+s95q73AAAFGIBBkABIndsCkhPkYLHhihbWU1WrW5QnX1jUpJjtOoIRnKz05lgggg6hD7AABANCBBBgBB5J4ADujXQ/nZqZ7jTtPVpB0AogmxDwAAdHbUIAOAELAbxkWvmRwCiH7EPgAA0FmRIAMAAAAAAIClkSADAAAAAACApZEgAwAAAAAAgKWRIAOAEHCaps/XABAMxBoAAIDgYBdLAAgip+mS3bBp596jWllyUHX1jUpJjtPognTlZ6d52gGgPYg1AAAAwUWCDACCxGm61HD6rOYs2aDSirombcVbK5WTkaInZwxVQnwME1cAASPWAAAABB+PWAJAkNgNm9cJq1tpRZ3mLNnAhBVAuxBrAAAAgo8EGQAEgdM0ta3sSIsTVrfSijptK6uR03SFaWQAogmxBgAAIDRIkAFAENgNQytLDvrVd9XmCp8rOyi6DaAlbYk163ZUyW7YiCkAAAB+oAYZAARJXX1ju/pRdBuAP/yJNZdflqg7vnu1JBFTAAAA/ECCDACCJCU5LuB+FN0G4K/WYk1yQoyevmeYuthtmvmr1cQUAAAAP/CIJQAEgdM0Nbog3a++o4ZkNKsLRNFtAP7wJ9bc/O0s9eyRqJ//fiMxBQAAwE8kyAAgCOyGofzsNOVkpPjsl5ORovzs1CaTUopuA/BXa7HGMGy6adiV+qyUmAIAANAWJMgAIEicpktPzhja4sTV/UhT89VjwSvwDyD6+Yo1GT2Tldqtq1ZtJqYAAAC0BTXIACBI7IZNCfExWvDACG0rq9GqzRWeotijhmQoPzu1xaLY7S3wD8A6fMWaccOvkkRMAQAAaCsSZAAQRO7k14B+PZSfneo57l411tJKjfYU+AdgPa3FGmIKAABA2/CIJQCEgN0wLnrd8iNM7S3wD8C6vMUaYgoAAEDbkSADgAhrT4F/ALgYMQUAAKDtSJABQAcQaIF/APCGmAIAANA21CADgA6gPQX+AeBixBQAAIC2IUEGAB1EoAX+AcAbYgoAAID/eMQSADqYthT4B4DWEFMAAABaR4IMAAAAAAAAlkaCDIDlOU3T52sAQHARdwEAQEdDDTIAluUuUL1z71GtLDnoKWA9uiBd+dlpFLAGgCAj7gIAgI6KBBkAS3KaLjWcPqs5SzaotKKuSVvx1krlZKToyRlDlRAfw2QNAIKAuAsAADoyHrEEYEl2w+Z1kuZWWlGnOUs2MEkDgCAh7gIAgI6MBBkAy3GapraVHWlxkuZWWlGnbWU1cpquMI0MAKITcRcAAHR0JMgAWI7dMLSy5KBffVdtrmA1AwC0E3EXAAB0dCTIAFhSXX1ju/uxCxsAKwo09gUj7gIAAIQKRfoBWFJKclzA/diFDYAVtTf2tSfuAgAAhBoJMgCW4zRNjS5IV/HWylb7jhqS0WTSxy5sAKyovbGvPXEXAAAgHHjEEoDl2A1D+dlpyslI8dkvJyNF+dmpTSZp7MIGwIraG/vaE3cBAADCgQQZAEtymi49OWNoi5M192qIC3dSYxc2AFYUrNgXSNwFAAAIFx6xBGBJdsOmhPgYLXhghLaV1WjV5gpPPZ1RQzKUn53a7BGftu7Clp+dGqrhA0DYBCv2BRJ3AQAAwoUEGQDLck/CBvTr0WRC51694G2Sxi5sAKwoWLEvkLgLAAAQDjxiCcDy7IZx0Wt2YQOACwU79rUl7gIAAIQDCTIA8JN7FzZ/uHdhA4DOjtgHAACsgAQZAPjgNE3PvwdzF7YLz+vtNYDo11niQGfZgbKzXE8AANAxUYMMALxwF4reufeoVpYcVF19oy7vkaC7//laPTljqOYs2eB1R7cLd2HzNkn0dt6U5DiNLkhXfnYaBaoBC+iMccC9A2WgsS/UY+ts1xMAAHQ8JMgA4CJO06WG02ebTQS3l0vb9x7VvB//U0C7sLV0Xkkq3lrpmWAmxMcwmQOiVGeNAx11B8rOej0BAEDHQ4IMAC5iN2wtrpI4dPSk7l/4sabcnKvvDs1s0y5svs4rSaUVdZqzZIMWPDAiCN8CQEfUmeNAR9yBsjNfT0SffXNvbbGt76y3wjgSAEAgqEEGABdwmqa2lR1pcbIlSfUNZ/Xfb+3Qzr1fNylG3VrNsdbOK52fzG0rq6HINRCFoiUOdJQdKKPlegIAgI6BBBkAXMBuGFpZctCvvqs2V/g9MQzVeQF0HsSB4OJ6AgCAYCJBBiAqBHP3srr6xqD2C/V5AXQe0RoHIrWDZLReTwAAEH7UIAPQqYVi97KU5Lig9gv1eQF0HtEWByK9g2S0XU8AABA5lkyQVVVVafHixfr0009VW1urlJQUFRUV6f7771dqamqTvvv379fzzz+vLVu26NixY8rIyNDEiRM1efJkGQYL8IBICsXuZU7T1OiCdBVvrWy176ghGX5P/kJ1XgCdR7TFgUjvIBlt1xMAAESW5TI8O3fu1Pjx4/XWW2/p0ksv1ciRI2UYhpYtW6Y777xTx48f9/Tds2ePbrvtNr333nvq3bu3hg8frsOHD+uZZ57RI488EsFvAUDyf/eytkyI7Iah/Ow05WSk+OyXk5Gi/OzUNtUgC8V5AXQe0RYHQhGD2/b50XU9AQBAZFkqQXbmzBnNnDlT9fX1euKJJ7R8+XItXrxYH3zwgcaOHauKigo9//zzkiSXy6VHHnlEDodD8+fP1x//+Ef9+te/1t/+9jfl5ORo+fLl+tvf/hbhbwRYVyh3L3OaLj05Y2iLky73qoi27ogWqvMC6DyiJQ50lB0ko+V6AgCAyLPUI5bvv/++vvzyS40bN05TpkzxHI+Li9Njjz2mLVu2aP/+/ZKktWvXqrS0VIWFhRo/frynb/fu3fXUU09p0qRJWrp0qcaOHRv27wGg7buX5Wentt7Rc26bEuJjtOCBEdpWVqNVmys8dXVGDclQfnZqQI/qhOq8ADqPaIkDoYzBbRtHdFxPAAAQeZZKkH3wwQeSpOnTpzdru/zyy7V27VrP6zVr1kiSbrzxxmZ9Bw0apB49emjLli1yOBxKSkoK0YgB+BLK3cvck6kB/Xo0mdi5VyEEOtkK1XkBdB7REgc6yg6S0XI9AQBAZFkqQfb5558rJiZGV199tQ4dOqTly5eroqJC3bp103e/+13l5eV5+u7du1eSlJ2d7fVcWVlZ+vrrr/XFF19o4MCBYRk/gKbCsXuZ/aLNOII10QrVeQF0Hp09DnS0HSQ7+/UEAACRZZkE2ZkzZ3To0CH16tVLK1as0KxZs3Tq1ClP+5IlS3T33Xd7iu8fOXJEkprtaunmPn706NFWP/vtt9/WO++849c4d+/e7Vc/wOrYvSz6ETuBjosY3HEROwEACIxlEmQOh0OSdPz4cT366KO66aab9JOf/EQ9evTQp59+qjlz5ujFF19UZmam/vVf/9WTPIuPj/d6PvfxhoaGVj+7qqpKmzZtCtI3ASA13b3MV5Fo9+5l6HyInUDHRQzuuIidAAAExjIJsjNnzkiSTp06pe985ztasGCBp+2WW25RQkKC7r33Xi1evFgTJ06U3W6XJNlsvn/tNE2z1c/u06ePCgsL/Rrn7t27VV9f71dfwOrcu5fNWbLB6wTtwt3LWLnQ+RA7gY6NGNwxETsBAAiMZRJkF64EmzRpUrP2oqIi9ezZU9XV1fryyy/VtWtXSdLp06e9ns99PDExsdXPnjBhgiZMmODXOKdMmcKvfoCf2L0suhE7gY6NGNwxETsBAAiMZRJkycnJiomJ0dmzZ3XFFVd47dO7d29VV1errq5OaWlp2r17t44ePaqrrrqqWd+amhpJLdcoAxAe7F4GAJFDDAYAANHCaL1LdLDb7Z5EV3V1tdc+7oL7PXr0UP/+/SV9s5vlhVwul/bt29fknAAii93LACByiMEAAKCzs0yCTJJGjBghSVqxYkWztn379qmqqkppaWlKT0/X8OHDJUkrV65s1nfr1q2qra3V4MGDlZSUFNpBAwAAAAAAIKQslSC74447lJCQoD//+c9avny55/jx48f1xBNPyDRNTZ48WYZhqLCwUP3799fatWu1bNkyT9/a2lrNmTNHkjR9+vSwfwcAAAAAAAAEl2VqkEnnd/WZO3euHn74Yc2cOVMvv/yy0tLStG3bNtXV1Wno0KG6++67JUmGYWjevHmaOnWqZs+erTfffFNpaWnatGmTjh8/rokTJ2rUqFER/kYAAAAAAABoL0slyCTplltuUVZWln7zm9+opKREe/fuVXp6uu666y5Nnz5dMTExnr55eXl64403tGjRIm3cuFHl5eXKzMzUgw8+qNtvvz2C3wIAAAAAAADBYrkEmSTl5uZq0aJFfvXt16+f330BAAAAAADQ+ViqBhkAAAAAAABwMUuuIAMAAAAAf+ybe6vP9r6z3grTSAAAocQKMgAAAAAAAFgaCTIAAAAAAABYGgkyAFHPaZo+XwOAL8QQAACA6EcNMgBRy2m6ZDds2rn3qFaWHFRdfaNSkuM0uiBd+dlpnnYA8IYYAgAAYB2dJkHmcDhUUVGhb33rW5EeCoBOwGm61HD6rOYs2aDSirombcVbK5WTkaInZwxVYnyMXHLJbhgXvNds8hqA9fgbQxLiY/xKkl0cV4gzAAAAHUtEE2S5ubkaPHiw/vCHP7Ta9wc/+IGOHDmiTz/9NAwjA9DZ2Q2b14mt24mGMzpz1qnkhFhtK6thdQiAJlqLIaUVdZqzZIMWPDDC53lYhQYAANA5RDRB5nK55HK5Wu1XX1+vI0eO6MSJE2EYFYDOzmma2rn3aIsT2+SEGD19zzB1sRua+avVQVkdAiB6tBZD3Eor6rStrEYD+l3mNU4EexUaAACzS+i8AAAgAElEQVQAQidsCbIvvvhCU6dOldPpbHJ8+/btGjZsWIvvc7lccjgccjqd6tevX6iHCSAK2A1DK0sOtth+87ez1LNHotfkmJu/q0MARJ/WYsiFVm2uUH52agvnCc4qNAAAAIRe2BJkV111lW688Ua9/vrrnmM2m03nzp1TXZ3vX2glKT4+XjNnzgzlEAFEkbr6Rq/HDcOmm4Zdqc9Kj7R7dQiA6NVSDPG3X7BWoQEAACA8wvqI5cMPP6xbbrlF0vmVYVOnTlV2draeeOKJFt9jGIYSEhKUkZGhpKSkcA0VQCeXkhzn9XhGz2SlduuqV9/73K/z+FodAiB6tRRD/O0XrFVoAAAACI+wJsgSExNVWFjoeV1QUKCcnJwmxwCgvZymqdEF6SreWtmsLSH+fNhr7+oQANHLVwy52KghGS0W2ifOAAAAdB4RLdK/dOnSSH48gChlNwzlZ6cpJyOl2eNNDafPSWr/6hAA0ctXDLlQTkaKz5VfxBkAAIDOI6IJMjen06ny8nLV1dXpzJkzPvuOHDkyTKMC0Jk5TZeenDG0WYHsiup61Rw7pVFD2r86BED0aimGuLl3oGwpPgRrFRoAAADCI+IJsldeeUW//vWvdfLkyVb72mw2ff65f3WDAFib3bApIT5GCx4YoW1lNVq1uUJ19Y1KSY7TuXOmrstp/+oQANHLVwwZNSRD+dmpPpNawVqFBgAAgPCIaIJsxYoVeu655zyvu3XrpoSEhAiOCEA0cU9cB/Tr0WQC6jRd7V4dAiD6+YohF7a3hDgDAADQeUQ0QfY///M/kqRx48bpscceU/fu3SM5HABRym4YF70+PxFtz+oQANbRUgxp/X3tW4UGAACA8IlogqysrEyXXnqp5s2bp5iYmEgOBYAFtXd1CAC0hjgDAADQORitdwmtPn36kBwDEFGBrg7xxWmaPl8DsJZQxJlgIV4BAABEeAVZbm6uysrK1NjYqLg4tjgH0Pm5H5faufeoVpYc9DxONbogXfnZaTxOBaDDIF4BAAB8I6IJsmnTpum+++7T888/r5kzZ0ZyKADQbk7TpYbTZ70W5C7eWukpyJ0QH8OkE0BEEa/QmSxfON7rvwMAEExhS5B98sknzY7FxMRo0KBBevHFF/X5559r9OjRSktLU2xsbIvnGTlyZCiHCQABsxu2Fnerk6TSijrNWbJBCx4YEeaRAUBTxCsAAICmwpYgu/fee2Wzef8F0uVyaf369Vq/fr3Pc9hsNn3++eehGB4AtIvTNLVz79EWJ5tupRV12lZWowH9LmNVBoCIIF6hs9o391af7X1nvdXuzxj30Luef2e1GgBYS9gSZL179w7XRwFAE07TbFIg++LXwWA3DK0sOehX31WbK5rsZgcAodBS7CNeAQAANBe2BNmqVavC9VEAICn8Bajr6huD2g8AAuFP7DP8jH3EKwAAYBURLdIPAKESiQLUKcn+7cbrbz8AaCt/Y9+0731LJZ8fVn3DWZ/nI14BAACrCO4zRgDQQfhbgDpYyTGnaWp0QbpffUcNyZDTdAXlcwHgQv7GvpTkeN08LKvV8xGvAACAVUR0Bdno0aP97tulSxfFxcUpNTVVubm5mjBhgvr27RvC0QHorCJRgNpuGMrPTlNORorPz83JSKGeD4CQaGvs+953svTmx+UyW0iAEa8AAICVRDRBVlVV1eb3lJWVad26dVq6dKnmzJmj73//+yEYGYDOLFIFqJ2mS0/OGNri6g33o03Brn0GAFLbY9+Ddw7WiPw+Kt5a2aydeAUAAKwmogmylStXau7cuVq1apUGDBigO+64Q9/61reUmJiokydPqqysTG+++aZKSko0YMAATZs2TSdOnNDq1av18ccfa/bs2crJyVFubm4kvwaADigSBfPthk0J8TFa8MAIbSur0arNFZ7i2KOGZCg/O5XJJoCQamvse2jyYI0uyCBeAQAAy4togmzjxo36+OOPdeutt+qZZ56Rzdb0Jiw3N1fjx4/Xs88+q1dffVU2m02TJk3SpEmT9MILL+iXv/ylli5dqnnz5kXoGwDoqCJVMN89mRzQr0eTlWnuGj5MNgGEUiCxj3gFAAAQ4SL9f/jDH5SYmKjZs2c3S45d6KGHHlJycrJefvllz7Hp06frkksu0aZNm8IxVACdSEcomG83jIteM9EEEFqBxj7iFQAAQIQTZF988YWysrIUHx/vs19sbKwyMzNVXl7uORYTE6MrrrhCNTU1oR4mgE7mwoL5vrgLUDMZBBANiH0AAACBi2iC7NJLL1VVVZVM0/TZzzRNVVVVKS6u6WMDp0+fVnJyciiHCKCTchfMb2mieGEBagCIFsQ+AACAwES0Bll+fr4+/PBD/fd//7fuu+++Fvv97ne/U21trYqKijzHqqqqdODAAQ0YMCAMIwXQ2VAwH4AVEfsAAAACE9EE2b333qtVq1Zp8eLFKisr08SJE5WTk6OuXbt6drF8++23tWLFCtntdt17772SpOLiYi1cuFCmaWr8+PGR/AoAOjAK5gOwImIfAABA20U0QXbNNddo/vz5evzxx/XBBx/oww8/bNbH5XIpPj5eP//5z3XddddJkhYtWqTy8nJdffXVuvXWW8M9bACdDAWoAVgRsQ8AAMB/EU2QSdItt9yiQYMG6fe//72Ki4tVWVnpaevZs6dGjRqlu+66S+np3+zKlJOTo+9973uaNGmSYmNjIzFsAAAAAAAARImIJ8gkqVevXnriiSf0xBNP6MyZMzp27JgSEhKUlJTktf+zzz4b5hECAAAAAAAgWnWIBNmFYmNjlZaWFulhAAAAAAAAwCLCliCbP3++bDabfvjDHyolJcVzrC1sNpsefvjhUAwPsCSX6ZTNsLf4GgAQXsRlAACAyAhbguyll16SzWbTbbfd5kmQuY/5w+VykSADgsRlmrIZhk4d2CXHjmI5HcdkT+qmpLwiJWQN9LQDAMKDuAwAABBZYUuQff/735fNZlNycnKzYwDCx2WaMhtP6vDrc9X4VXmTNseu1Yrr3V+97pglIy6RyRgAhAFxGQAAIPLCliB77rnn/DoGILRshuF1EubW+FW5Dr8+V32m8/8nAIQDcRmIjOULx/t1DABgDfwMCViIy3SqYf/2Fidhbo1flath/w65TDNMIwMAayIuAwAAdAwdZhfL0tJSrV69Wvv375fD4dCiRYt08uRJrVixQuPGjVNsbGykhwh0ejbDLseOYr/6OnYUKyErL7QDAgCLIy4DkbNv7q0+2/vOeitMIwEAdAQRT5AdP35cs2bN0sqVKyV9U4xfkg4ePKhZs2Zp0aJFeuGFF5STkxPJoQJRwek45l+/k3UhHgkAQCIuAwAAdAQRfcTyzJkzuuuuu/TRRx+pa9euGjVqlNLS0jztLpdLl1xyiaqrqzVlyhR99dVXERwtEB3sSd3865eYEuKRAAAk4jIAAEBHENEE2R/+8Af9/e9/V0FBgT766CMtXrxYV1xxhac9NzdXq1atUkFBgerr67VkyZIIjhbo/FymU0l5RX71TcorotYNAIQYcRkAAKBjiGiC7C9/+Yu6dOmiBQsWqHv37l77JCUlacGCBerSpYvWrFkT5hEC0cVm2JWQNVBxvfv77BfXu78SsvJkM9jHA4A1uEynz9ehQlwGAADoGCJ6l7V//37169dPPXv29NmvZ8+e6tu3r6qrq4M+hmPHjmn48OEt1jfbv3+/HnzwQY0cOVIDBw7UuHHjtHTpUpn8gotOymWa6nXHrBYnY3G9+6vXHbNYpQDAEtyx7tSBXTry7q906H/n6Mi7v9KpA7uatId6DMRlAACAyIpokX6bzaZTp0751dc0zZDsZDlnzhwdOXLEa9uePXs0efJkORwODRo0SAMGDNDGjRv1zDPPaPv27VqwYEHQxwOEgxHbVX2mP6eGfdvl2PmJnCfrZE9MUdKAkUroO1Au57lIDxEAQs5lmjIbT+rw63PV+FV5kzbHrtWexJQRlxjSlVs2w5ARl3g+Lu/fIceO4m/icl6RErLy5DJNVo8BAACEUEQTZFlZWdqzZ48qKyub1B67WEVFhfbu3atrr702qJ//l7/8Re+//77XNpfLpUceeUQOh0Pz58/X+PHjJUm1tbWaNm2ali9frjFjxmjs2LFBHRMQajbD0KHXnlFc73665LoxSht/v6ft3PEa1Ra/ptNV5eo9+cmwj81pmrJfMAG8+DUABJPNMLwmx9wavyrX4dfnqs/058IyFknqmnmNErLyPMfdq8aClRwjzgIAAHgX0QTZuHHj9Pe//12PPvqoFi9erG7dmu/idOzYMc2cOVOSdPPNNwfts6urq/Xzn/9c1113nXbs2CGns2mtkbVr16q0tFSFhYWe5Jgkde/eXU899ZQmTZqkpUuXkiBDp+IynTp1YJdO7d+uU/u369i6dxSbmi4jLkFmY4PO1ByUXOcnYw37d6hr5rWeSVkoJ1FO0yW7YdPOvUe1suSg6uoblZIcp9EF6crPTvO0A0Br/E0AueNhS8kxt8avypvFw1CyGfaLXgcrMUacBQAA8CWiCbI777xT7733nrZs2aJbbrlFw4YNU2VlpSTp5Zdf1r59+/TBBx/o+PHj6t+/vyZPnhy0z541a5bOnDmjX/ziF14Tb+4NAW688cZmbYMGDVKPHj20ZcsWORwOJSUlBW1cQCjZDLscO4q/OeAydebIAa99HTuKlZCVp+eXbdOZs86QTaKcpksNp89qzpINKq2oa9JWvLVSORkpenLGUCXExzB5A9CitiaAmsVDH9zxsLMizgIAALQuomvqY2Nj9fvf/15FRUWqra3Ve++9pyNHjsjlcmn+/Pl64403dPz4cRUUFOjFF19UXFxcUD73tdde05o1azRz5kxlZmZ67bN3715JUnZ2ttf2rKwsmaapL774IihjAsLF6TjmX7+T5ydRlUfqVby1UrN/t14zf7VaDafPymm6gjYeu2HzOmlzK62o05wlG5i0AWiROwE081erNft361W8tVLby2tajV1tjYedFXEWAACgdRFdQXbmzBldeuml+u1vf6tdu3bpo48+0r59++RwONS1a1dlZmaqqKhIhYWFQfvMAwcO6D/+4z80bNgwnyvS3IX7U1NTvba7jx89erTVz3z77bf1zjvv+DW+3bt3+9UPCJQ9qfmjzF77JaZIkhpOf1Ow3z2JWvDAiKCMxWma2rn3aIuTtgs/d1tZjQb0u4wJnIUQO+EvfxNAF8eutsbDzog4az3ETgAAAhPRBNn111+v73znOyoqKtLIkSP105/+NKSf53Q69eijj8owDM2bN082W8s3gO7dNePj4722u483NDS0+rlVVVXatGlTACMG2s9lOj01bVymU0l5RXLsWt3q+5IGjNTRupOqqK5vcjyYkyi7YWhlyUG/+q7aXKH8bO8Ja0QnYif8EWgCqE3xMK+ow+4ieWGM9/aaOGs9xE4AAAIT0QRZY2OjPvzwQ3300Uey2WwaMGCAioqKdMMNN+jqq68O+uf9/ve/12effaZnnnlGvXv39tnXbj9/c+kriSZJ5j92l/KlT58+fq+C2717t+rr61vvCLTCPZk7dWCXHDuK5XQcU/KgMUrK/bbievf3WZg6rnd/JfQdqLfe3y3Ty+OUwZxE1dU3BrUfogexE/4INAFkM+xKyBroXzzsgPXHvMV4e1I3JeUVKSFrYJOEHnHWWoidAAAEJqIJso0bN2rt2rVavXq1Pv30U23fvl3bt2/XokWL1LNnT91www0qKirSsGHDFBsb267P2rNnj55//nkVFRXp9ttvb7V/165dJUmnT5/22u4+npiY2Oq5JkyYoAkTJvg1zilTpvCrH9rNZZoyG0/q8Otzm0z8Gqv3Ka7XVer1r4/r8J/meZ0UxvXur7SJj6v6a4feX7ff6/mDOYlKSfavtqC//RA9iJ3wV6AJIJdpqtcds5rFSre43v3V645ZHW71WEsxXpIcu1Z7xm3EJcpmGMRZiyF2AgAQmIgmyJKTk3XTTTfppptukiSVlpZq9erVWr16tT777DP98Y9/1Ouvv674+HgNGzZMN9xwg1/JLW/+8z//U2fPntXZs2c1c+bMJm3uVWDu448//rjS0tK0e/duHT16VFdddVWz89XU1EhquUYZEEk2w/A6cTJPOXToj0/r8kmz1Wf6c2rYv+P8yoOTdbInpihpQJES+uap+muHZr+wQY5TZ72eP1iTKKdpanRBuoq3Vrbad9SQjKDvoAkgOgSaALIZhoy4RO/xMK9ICVl5HS45JrUc490avyrX4dfnqs/052QSZwEAAPwS0QTZxXJycpSTk6MZM2bo5MmTWr9+vZYtW6bVq1fr448/VnFxccAJMnetsLVr17bYZ/ny5ZKkn/70p+rfv78++eQT7d27V9dff32Tfi6XS/v27ZPdbveaPAMiyWU6derArhYnTufqDqnq5Ud0yaCx6vbtW5s8OnTmzFktfX+33l+3v8XkmBS8SZTdMJSfnaacjBSf9YNyMlKoiwPAq/Ym2t3Jr66Z1zSJh65//HjW0ZJjrcV4t8avytWwf4e6Zl5LnAUAAPBDx7rrk3T48GH93//9n5599lnNnz9fa9askXQ+KeVyNa+F5K+lS5eqtLTU6z/uemPu11dccYWGDx8uSVq5cmWzc23dulW1tbUaPHiwkpKSAh4TEAo2wy7HjmKffcxTDh1b+5aOrnihyfHY2BhtL6/xmRxzT6J8JcecF9Xmu/h10zaXnpwxVDkZ3neJy8lI0ZMzhsrppRYaAOtoKa5cmGj3pbXYdWFh+/OvO9wtkiT/YrybY0exbIZBnAUAAPBDxFeQVVZWqqSkRJs2bVJJSYmqqqokyZMM69evn4YOHarrr7/e74KjwVBYWKj+/ftr7dq1WrZsmSZOnChJqq2t1Zw5cyRJ06dPD9t4gLZwOo752a+26et/TKLmLNngdaXBhZMob5NM9/Gde49qZclB1dU3KiU5TqML0pWfneb1fXbDpoT4GC14YIS2ldVo1eYKz/tGDclQfnYqj/wAFuZPXJHUrtgViNZ2jwwlv2P8yfPXgjgLAADQuogmyG644QYdPnxY0jcJsSuvvFLXX3+9558ePXpEZGyGYWjevHmaOnWqZs+erTfffFNpaWnatGmTjh8/rokTJ2rUqFERGRvQGntSN//6JTZdTdCeSZTTdKnh9FmvE9TirZWeCWpCfIzXJJkkDejXo8kjPu6JL5M2wJraElfClQBqy+6RoRJIjCfOAgAA+BbRBNmhQ4ckSTabTYMHD9YPf/hDjRgxwvPIY6Tl5eXpjTfe0KJFi7Rx40aVl5crMzNTDz74YMC10IBQc5lOJeUVybFrdat9k/KKmk3mAp1E2Q1bi6s3JKm0ok5zlmzQggdGtDge+0WTSiZsgLUFEldCmQBq6+6RodD+GE+cBQAA8CaiCbK7775bGzZs0O7du7VlyxZt3bpVXbt21ZAhQ1RQUKDrr79e1157rYwQ/xL7+eeft9jWr18/LVq0KKSfDwSTzbArIWug4nr391nEOa53/yYFqS/WlkmU0zS1c+9RnwWgpfOT2W1lNRrQ7zImZQB88ieuGIZNjWedKj94TH37XCq7YQtpAqgtu0eGSrBiPAAAAJqKaILs4YcfliSdOHFCGzdu1Lp167Rx40atXr1aq1evls1mU2JiooYMGeKpQXbNNddEcshAh+cynXKdO6teEx/T4WXPep1AxfXur14TH5N55rRsXWK9rnRwmmaTiebFry9kNwytLDno1/hWba5gpzQArfIVV5ITYnTzt7N007Arldqtq+e4rzjVXoHsHhm6VWSmet0xq8VknXslWzge9wTQNuMeejck512+cHxIzhttuP4AfIl4kX5JuuSSSzRmzBiNGTNGknTkyBFt2LBBJSUl2rx5sz755BN98sknstlsPld7ATi/uqB29R90yeCb1Gf6c2rYt12OnZ/IebJO9sQUJQ0YqYS+A3W2rlon1v9ZPW6c2uT9gRTal6S6+ka/xudvPwDwFi8uvyxRT98zTD17JOqz0iN69b3P/Y5T7dHW3SNDuXrLZhgy4hLPx/j9O87XQnPH+LwiJWTlkRwDAABoow6RILvYZZddpvT0dFVWVqpHjx46ePCgzp07F+lhAZ3GmeovVfXyI7pk0Fhdct0YpY2/39N27niNaotf04ktf1Pc5X2bvK89hfZTkuP8Gpu//QDg4niRnBCjp+8Zpvi4Lpr5q9VtjlPt1dbdI4PtwhVyNsOQaZrqmnlNk2ScyzQ97QAAAPBfh0mQ7d27V+vWrdO6deu0efNmnTx5UtL53S0zMzM1cuRIFRUVRXaQQCdhT+om80uHjq19S8fWvaPY1HQZcQkyGxt0puag5Do/gfK2i2UghfadpqnRBekq3lrZ6thGDckIeHVHWx77BNC5eYsrN387Sz17JHpNjrn5syFIoALdIVhqX/xqy8peEmMAAACBiWiC7J133tG6deu0fv16ff3115LOJ8RiYmI0bNgwjRgxQkVFRbryyisjOUygU2m2w5nL1JkjB7z2vXCHs/YU2rcbhvKz05STkeLz/TkZKQHVHwv0sU8AndfFccUwbLpp2JX6rPRIRDYECXT3SHd82ld1XOt3HNLeymO6NMn/+NWelb0AAADwX0QTZI899pjn39PS0jwJsW9/+9tKSEiI4MiA8HOZTtkMe4uv/RXoDmftLbTvNF2afff1evrFjV4nrzkZKZp99/VtTmYxOQSsy2m69OSMoZqzZIMazzqV2q2rXn3Pv1qkwd4QJJDYapou2VymJLv6p6eof3qKvj52Uu+vr9D8pZvV+7KkVuNXoCt7AQAA0DYRTZANHDhQRUVFKioqUm5ubiSHAkSMe5XBqQO7zhdadhyTPanbPwotDwyo0HKgO5wFWmjfaZoqPVCn7pfEa8EDI/RZ2RF9vPmblV43DEnXddlpOvz1SVXVnFROZorfySwmh4B12Q2bEuJjtOCBESo/eL7+VyQ3BGlLbJUkwzB0ct8undz5TWxPHFCkKTcP1HcL0zX7hQ0+41d7VvYCAACgbSKaIPvTn/4UyY8HIs5lmjIbT3qdbDl2rfZMtoy4xDYlyQLd4SzQQvt2w9Bf132pLXuqdfOwLN00LFMP3jnY015T16Cl7+/W++v2q+BbPfWtrO5+fQ6TQwDu/6f79rlEUmQ3BPE3tkpqNbanTXxcT98zVD/7r9Utxq/2ruwFAACA/zpMkX7AimyG0eJKBElq/Kpch1+fqz7Tnwvo3JL83uGsvYX26+obVd9wVstWlunNj8uV0TNZCfFd1HD6nCqq62WaLk8/fzE5BOBm/0etxHBsCOKLv7G1tdh+ZNk89Zn+nG4eluUzfkVyxRwAAICVsNURECEu06mG/dt91rKRzk+kGvbv8Ey+2uriOmYtrUS7sCC2L+5C+xdPOi9crWGaLn156IQ+31+rLw+d8CTHLu7nDyaHANzaG6eCqaXY2qbYvm+7bh6WoeOOluNXJFfMAQDw/9m798Co6jNv4N85k+tkEpKQTAgxgWCYgBASwkWCCgEKGFuktS0oFresF7a2hdW6tsKLN1rq9sVdL9VtsdatrFJZLHV9RXELBCoX5ZoERQImEIi5Z0Iymdxmznn/mJzJ3OecyZXk+/nLzJyZczLqM/k95/k9D9FIwgQZ0SDRCFqYiwsVHWsuLlTdhywYckNsX4tPuSG+zSnhZX+dvapDCbmqQykuDonIWbBxaqCoiu0lB5EQF4Ubb4j1+nx/xlYiIiIicsUtlkSDyGZuUnacRdlxveXcEPtMaR32n6hwNNpfODMNOcZEr1uWnKs6/PULk6s6lBoK26mIaGgJNk75YhNFaJ1uQLj/HAzFsb3VHi/zssYOaGwlIiIiIk9MkBENIq3ee9WATIjUIyZ3KUbN/pbL45Jo89je02fX1L1Ay8oY7bLgkisTfC065aoOXxMnnas6lE+w5OKQiDwFG6ecybGo5GI99h3vmbq7aFYqcoyGgLHKPQ47/xwotjt+jyh7FdzEVN/H90dsJSIiIiJPTJARDRJJtEE/LR/ms4fsD2gEhCWmQgjXQeywQLRakXzPRoTGJsFSVgRzSSFs5iZo9bHd09KyvU6i7CvuFRSBFl59XdUh4+KQiHxRG6dkNlGCpb3La1wpPHXVEVd0EaEe7ynH3bbLZ+1TLD3isg3RuUt6Yrsf+qx8iDYbJI3g89r7K7YSERERkSsmyIgGiUbQQpeejcj0bISPzUBM7hKExCQ4npesXZBEG6refhZt5UUurzWfPYTwsRMx5u6NEMKjBqQ/mRJ9UdXh7T25OCQaWfxVZ/UFraDBtt0l0Go1GJ8c4zJpFwDOV5jwzGvHsHX9PLfrEiF2tKJ+7x9ha66D2GFBZ90VQBJd4nJESiYi07M9Yrez8LEToZswDaJT/PK1vbM/YisRERERuWKCjIYtfwus3iy++up9baIIm9WGpJUbIGhDYCk7g8YDb3lUIyQUrEXVjs2wmqpcXt/x9QVU//lXSFnznKLrHkjBVnX4fj8uDolGgsDVWfbnexPDRVGEzSbiZ/fOcDzW0NSKPUcr8OGRcrRYugDYk2RnSuuQlZHgiDEaQYBksyHp2+sdr7U216P51MdoPrXXJS4nff/nqPqvp7xOs5QTaTarFe8dKsOZC/UYpQ+8vbOvYysRERER9WCCjIYdxwLKZnVdQHX/LIki2itL0XLqY1VbFpUs3NS8r1YQYOnqhNbWhco//8pjEeWoRljxBJLv2YTKNx6H2GZ2Oabj6wuwlBcjctzUPq8i64/G1b3FxSHR8CVXZ1X7i4fdVbNtV87BfGaf6m3nkmiDIGghdB9ja72GtorPEREZg9UFU7Fkdio2bTuGqvpWAMD+ExWOpLychOusvYTGfQd7zp01H/H5qxCdvQhVOzY7xeUpSFnzHCzlxfbvjFYTtFFx3dc6zXGtdy004rbcVESz8XwAACAASURBVHx09BJ+s/0ExibofW7vJCIiIqL+wwQZDSuSKAKSCEBA+5VzMJe4LmJ0E3IASURITCIsX51yJJwCbVlUtHBbuQEh+nhV7xsdFYHKN572WmEAdFeJ7fw1UtY8h5jcpWg6/K7HMebiQujSpwX7kXnobeNqIqJgaATBa4yVOVdntZcXu/T4UhLDvd7gyJoP/eS56DLVoPrd/4vRt6/F5ofm4JEXDqHF0gVTS0f3620QOyz266v6ytEvsrP2Mqr//CuEJ9/ocjPDOS5HjpviEqMlUcTXdWbsLryIqgZL93bxVKwumIzFs9Pw5LajXrd3EhEREVH/YoKMhh2xw4Lqd7b4T2RFx2PU7GUwHdzheN7flkVFC7d3tnhNZHV8fQG1u/8dyaue9NgGJHZ1IDJ9GrpMVR7VYc6vt5QVIWb6YjQd2d2dAOxha/U93VGt3jSuJiIKliTa0Hb5rM8YK/MXD33FcEU3OFY8gdEL70P9ey8gedWTKMhLx859pYiLDgdg7xlZu/vfEZk+DUnffcylX6S8xbL2vReRvOpJxOQudTmPHPNtooT2Diueee0ozl32Hl833X8znn0oD4++cNBjeycRERER9a+h0dmbqA/IFQLekmMyOZGlEQTEzCwANILH85byYnslmuN9bbCUF6lauDm/b0hcMhLuWAsAaLt8FrXvvYiqt55B7Xsvov3Kl4jPX4WUNb9BSFyyz/c2lxxEyKhEhCWmejynjYrze11qaAWNz2mRQE/jai7YiKgvaQQtzMWFio71Fw+9xXBFNzh2/hqhcUkIH5sBS1kRCvLSIAgaLJiZak/eVZxDwh1rEZ+/Cp31V13ieGf9VcTnr0JCwVq0VZxDzPTF0OrjPc6jFTR4aptnckx2vsKEza9/ijGjo1CQl479JyoYa4mIiIgGEBNkNIxIsJQpT2QJYZEIM4zzeN5cXOiyPcdj4aYREGYYh4jUyfbXOyXD3BduQqQeyas2QQiNQOUbv0D128/CfPYQ2i7ZtwdV73gWlW/8AkJYBJLv2QQhUu/1muUqMSFc5/Gcflq+y2JQDZvb6zo6rcg2JiJaF+rzNXLjapvTxDciot6ymZv8xlfHcX7iIeAaw4O5wWE+ewgJcVGYl5OC6UYDNIIWoaOTe+L4js1ucXyzI46Hjk5GyKhEROcudYnLNlHEmdJanzcfZOcrTDhdWovb88bhmrnD77FERERE1Le4xZKGDY2ghbmkUNGx5pKD0E3IRphhHDpryl2e87Zl0WZughCpR0zuUsTkLvG6vab51F6PhVtM7lKExiah8o1f9KrPmFwlJnZYXB4PHzsxqP5jvvqMuffBkRtVu3NuXE1E1BeicxcjcdmPfcZXeRu6r3goc47haivTDMvXQRNi/9No7XeycM3cgVH6cIRExSqO4wAQeYPR5XmtIGDf8SuKruPAiSt4dNUM3HhDrKLjiYiIiKhvMEFGw4rN3KTsOHkB5WX3ircti2FJ45HwzX9CaGwSLGVn0HjgLa8TzJpPfgSge+GmERCTuwSWsjO96qsDAPqs+bBeq0NnXc8CS25IHWhqm8fvrqDPmHMfnBZLl8d7yI2riWhkcu+n6P5zMO+nnzzXb3yt2rEZVlOV13joTI7h8o0Atd8LIdH25H97pxV/KbyIB++cgrZLyvujRY7PAgCPuKw0bsrH5WWN5VAUIiIiogHEBBkNK1q9sjvu8gKqs/qSx3PylkXnLTpx81ZC6uqwVxD4mWAWN28lrM316Ky7grDEVITEJKDxwFuKrkmuXghLTEVn7WXH4+FjJ0I3IRvmc0cQOX4qtFFx0E/Lhy59murkGKCsz9jm1z/F1vXzHI2q3cmNq4loZPE5DXJaPnTp2UHFJHsTfUvAJvrJ92xC/Ye/h25CNhoL3/a4kSDTZ81HU3MbYmMiAaj/XohIn4ZWSweef+sUxibq7VVoZw8qeg+5OtkbpXFTPm5iKivIiIiIiAYSE2R0XXOuWpBEG/TT8mE+eyjg6/TT8mFrM6OzrsLlcXnLomuDZy00YVpU7fqNoglm7VfPA5Lo2GaptnrBua9OT5WYvbpCP3lu9+8qdl+buoWoTRRRcrFeVR+cXQcuQHTrN7ZgZqrfygabKELrdG3uPxPR0KCmEkzRNMi7N0IIj/Ibm9zPobSJfsqa55D0vcfRZapB88m9Xo+Vbyi8u+ccsjISkJ0Rr/x7IWs+rOYmRN5ghKWtA7/+8a2O50Yv+geExCS4bPX0xtdUYZsoYtGsVBSeuhrwOhbMTIXVJkKj0bB6jIiIiGgAMUFG1yVvVQzRuYuhnzwX4WMn+t0KIyfBTJ/scqlAcN6y2HblC5jP7IOt9RoM33kEnfVXkXDHWr9bLLtMNWi78iXCElIAjeDoj6O2eiE0IQUhowxOVWKeC1a1iTHHOYLog5OWFI1LVc2OxzPT4jDdaPD6Gl+9zRbNSkWO0cDtQkRDRDCVYIoSWX/+laMPV8Bztl6D4dv/jI7qcmXbF8uLETluChoObIfY7pmkCh87EYYVG1DTYMaeI+Woa7Igx5gIXXq2su+FCdmQbDb7tVZ9idoSp88lK99jq6c3vqYKawUBOUYDMtPi/N6gkOOrKEoQGCuJiIiIBhQTZHTd8VXF0FFThvAxN2LMyg2ofmeL18WQnAQTOztgbW5AZPo01y2LNitqdj8Py5fHAABhhnHQRkYjND4ZGmi8Nml23gIUGj8GIVGxiM5ZCMlqhdjVoaqqTRJFJN7xo+7f075Q601fH2/U9sHRRfSECbk/WXuHFaGhWpdkl5LeZk89OAe6iFAmyYgGUTCVYJJoQ9tlhX24yosROW6qS4LN2znDDOOg1cUoH65SXAhd+jSMuesxWMqLu5NsJpcYXtfYik3bjsLc1uWIYY3XLDCs2IDanX6+F1baK3XFTmVbPSvfeNxrJZn7Fn1nNlHCUw/O8bnFXY6RvJFARERENDiYIKPrjq8qBrHNjKodm5F8zyakrHnO5wLK1tYCydaFxDvW9ry2qx0AYGttRmdNT/8vebuj2glmPUkuUXn1gts0yr5OjMnU9sFJTYpGUrwOC2amYrrRgPqmNozSe76Hkt5mz7x2DFvXzwv+4omo14KpBFM1DbI7kRXonMFuQweAiBSjyznETnsMl9CzHVyOYb/972Ks/c5U+/dCWRHMJQc9vhfkpJbSrZ7eJg4HmiqsFTTQRYRi6/p5OFNah/0nKpwmCKchx5jI5BgRERHRIGKCjK4rgaoYrKYqVL7xOGJylyJ27l0uixXrtTo0Fr6N5pN7ET72RiTf8yTqP3oN7VfOobPuiqPRvnN1gNjZbj+nyglmPdUDEiRRxJi7N/pceAU7jTIYavrgLJyZBpso4SffzwEA1Jks+PBIOW7NSfFYxKnpbXamtA5ZGQlcBBINAkcMrfoKYYZxEMJ1EDss9omQTlvOvVWCBZPIcjmn+02NILeh1/z1BbR+cdgxLEW+/vDkG2FYsQGbH5qDR144hAUzU1FnsuDk+Vo88sIhFOSloyAvA4blPU30e/pNSrCUFwU9cVhpHJfjXlbGaOQYEx2P27r7PDIuEhEREQ0eJsjouqKkikFsM6Pp8LuwNjfAcOdPUfv+y+isLndZAGp19gVZ+5VzjomRvqoDNIJW+Rag7glmdXt+B6l7e6UuPRtCuM5vVVt/JsecG+Sr6YOTY0zE6fO1OPllDcJCtZiWkYiCueleKxzU9Dbbf6LCZWFIRANHI2ghtrci7Sf/4XXYiHMTevdKMLWJLOdzeovbnXVXYG2uhz5rvuJt6FazCa1fHAYk0WXaL2CP4bU7tyBlzXNYXTAZ040GbN9zDqIoocXShZ37SrHrwAWkJUXj1uyxWLk4ExpB6I6/KirkuicOR+cshNTV1UdxXALA5BgRERHRYGKCjK47iqsYzI0AAKupxmMhpc+aD+u1OnvSzIl7dYAQFqHunN2VE131V9F+5ZxHP5/IcVNcFpzBTqNUdC1eGuYnj9bh/junKuyDI2J6pgHTMw2O9wN8Vzio7W1GRANPEkXoJ8/1OWzEuQm9cyWY2inB7skirzFUEtF86mPE569SvA29sfBtl0o3d/YYXoylN09BdUMr9hwpd3leFCVcqmpGbHQ4VnZ/HmJXO7ThOtVx3nkrPaAsjnOQCREREdHQxQQZXXfUVjHI23hk8rQyXwstuTogLDE16C1Azud07ucjiqJLjYAIoD86jflqmF90ASi6WI8tP7pFdR+cQIs2tb3NiGhgKWrO373NvPb9lxGROqXntdAE3U8R8B1Dm0/tRXT2IoxZ8QSqd/7a7zZ0a2sTmk/uDfh7mksKoZswDb/fXQJzW5fXY+Q4pBEE1H/4GpK+vb4XFXLKbnBwkAkRERHR0MYEGQ06SbS5NKR3/9n9WJcqBo3g0YdGTnp5qxKTF4BdphqfCy25OkAI16H96nnY2syqKidsbWbvlWnlxQhJmYzf7jqNxub+rRrw1zC/qr4V654/gNUFk7Fkzrg+6YMTTG8zLgCJBlagJvRdpiq0nv8U0TmLkHLfLx2PS6INtaZ26MIEGFZuRO076vop+qs+UzpcRRJF1P2/VyC2e06OdCfHcEu7Z3JMEDRIS4rGsttudPRGa/3iE1gX3qtqq2cw2yk5yISIiIhoaGOCjAaNvMBou3zWviCSt/p09+3ytgDRCFro0rMRmZ6N8LEZiMld4rWPTsfXF6GbkA3zuSOIHD/VvtDKmg/dhGx0mWpQtWOzz4WWRxWYRl3lhK291evz5uJCGNKnofzrZlyqagbQP1UDShrmt1i68Oq7xUhO0Ls0zA/2/Gp7mxHRwAo04CQkLhnJqzYhNDape9JjT0yOysrHmAnZqDe1otMqKJoG6XxeOW77iqHycJW4+asQM/0bvreh+9la6UyO4ZZ2q+OxaF0oCuam4468NIyOjXI8Hp6Ujti530FLcSHibv1e0BVygXCQCREREdHQxwQZDQpFW326+3a5J8kkUcSYlRug0Yb47KMj2az2qoXJc6GfPBcAIHa1O6ZY+qtCcK48C0tMhTYiCtbWpsBbgFY8AWtrE0KiYhGWmOrR90yuatBFuP5v19dVA4PVMN8mSgp7m7F6jGig+WtCL0TqkbxqE4TQCFS+8QufMdmwYgOaOrR4539LsWim92mQcrx2vgHSeu4Y4m77Psas3IDqd7Z4jaGhccnQ3zQX7o3qe95PXQ+0puY2VNS0AACSE6Lwy7VzYIjXo7WsCLUHCz2+M7qaatF1rV7RVs/gqsc4yISIiIhoqGOCjAZFoK0+zn27vBE72xQl15wJoRFoKy/2mxyT+5N1NlZDP+U2CLpoAEDjvu2Iu22F98oJp8o00yc7YVj2UwjhOo/39lbVIOvrqoHBaJivFTTQRYSq7m1GRAPDVxP6mNylCI1N8pockzlPiOzssuH+LfuQlhQNXUQI1nxrCiamxTn6KXq7AdJ2qaRnG6XC6jNngarQZHKFlw7AMw/m4UhxJVYtyYQ+xOo3+TdmxRMQrV0Quzr8xvneTKrkIBMiIiKioY0JMhpwgbb6yOS+XZHjprosSIJNrkmiiDF3b/T5WufqgNDYRBiWr3N+MSrfeBwxuUsRM32xy3PWa3WOyjTdxJkAgJC4JIR56YlWb2p1VDW468uqgcFqmC8nv7IyRvdJbzMi6jtem9BrBMTkLoGl7IyymFxWjGW3TsRfDl50bBXfc6Qcj46Pd3pLzxgtb6P0FkOVToFUE8M1guAShwIl/6p3/hopa56D6ZNdkKydHtcodnX0KjkGcJAJERER0VDHBBkNOH9bfdyZiwvd+tEEn1zTCAKEcF2ARtA2L1s6bdBn2bf2NB1+F01HdnsMBhAidIiZsRSxt3wXAGBY9lMAnj3R3t1zDmJ3sshdX1UNDIWG+Vq3z5CJMaLB5WuLYlhiKkJiEtB44C1F72MuKYRh+TS8sXER3j98GR8eKXeJXf5itNhmdomhCd98GOFjJihOOtljeFTAZv7y+2kFQd13RlkRorPmo+KVh13ivDYmAUnf/mdF1+jLUIjLREREROQfE2Q0KHxt9fE4rtW1l1XvkmsixA4LzF8cQVRGrkcV2LWTe6G/aa5H3zONoIVugtPWHkl06S/m0ty6vMh14EB3fxvRZkW9qRV7jpT7vN6+qhpgw3yi65Oaib5q+dqiKG8HVxuTw81f2yfhzk7FB0cuuZwnYIzujqHNx/e4VuoGOrcoOpLvkeOm+G7m70TVd0bJQRiWr3P0kOysvYzwsRORsPT+XlePMS4TERERDX1MkNGg8LrVx9tx3X27Gg68BamrEwlL1vQiudaz7adBI3hUgUESYS4+4LXvmbWl0WvzZkdz67BI//1t7t4IQIDGT0FAX1YNsGE+0fUjmIm+wZ7HvVG+PK1XdUz+4FVoQsJgWLEB9y7JdIklwcZon8d1v3fJxXrsO34FppYOxMeE44654zFp/Oju531/PmqvJ2J8FsIM4xX1RlODcZmIiIhoaGOCjAacqmlk3RMlrx39K8ISUwGoX8jJ53TZZuNWBSbz1ffs2qfvI2bG7R7Nm6OnL1HU3FruiVaQl46d+0o9junrqgE2zCe6PvRmoq+689jQXlmKEH28axyzNMFmaXZsIw/EecovJNHRuN9ZMDHaF5sowdLe5TWpdODkVUw3JmLjmtlAiOCSJHOuNlN7PQmL1wBQ3htNKcZlIiIioqGNCTIaEM5bhVRNI5uQjcbCt+0JrborsDbXQ581X9lCblq+485/b/ueRd6Y47XBtCTaYCkvUtzcuiDvRuw6cMGlD1l/VQ2wYT7R0Nfbib7Kz6NFy6mPYfnqlNdG+S7byH1wj8ny9TnfVFB1A8QpRvuiFTQ+K66SE6Lw4+9lIzwsBGdKax3VZcmjdbhrQQbGxEc6zhPM9fRVYswZ4zIRERHR0MUEGfUrb1uHQuLGYPQ3/iHwNLIVT6DLVIPmk3vlN0PzqY8Rn79K2ULOKckF9K7vmS49G6FxyS4NpsPGTIBh2U9U9LexN7f+7oIMXLjSNGBVA2yYTzQ09Xair1o2c5NHo3y5B1nisp963UYu8xqTuznfVFB1A8QtRntcryii5GK91+RYtC4Umx/KQ0R4CB578ZDjmOSEKKxbMQ2GeD1ay4ogdbRCP3lun1xPX2JcJiIiIhp6mCCjfuNz69ClYrRdKsHYHzzjdxpZl6kGVTs2Q2w3O17afGovorMXBV7I3b3RozKhN9t+JFGEYeVG1L5j/106ay8H3dz6vjtu6nmMVQNEI1ZvKluD4RID3baZV+3YjOR7NnXH5CKYiw/2xOSs+dBNyPYakwHPmwqSKAa+AeIlRntcryBg3/ErXp8rmJuOpNFRLsmxaF0ofrl2DuLCRce2dyFSj/AxNwb1nUFE/e/955cP9iUQERE5MEFG/cbf1iGrqQpX//Ao4uavQsz0b3hMI2s5sx8N+/7ksRAT28yuCzmnfmDOyTX3hU5vtv3YRBHnL5swOibc5Zya0DAAvUu8MTFGNLL1dUN7XwLFQKupyrGNPPaW70KXnt3z3LU6NBa+jeaTez1iMuAZ2zSCACE8yvsNkKx86CZMQ2dnF7SCELB61tTS4fGYIGhwe954nD5f61JdVjA3HYZ4vUtPyGC/M4iIiIho5GGCjPqFkq1DYpsZDR9tQ2h8ssvWIfuWzBKvCzHAdSE3ava3oJvQs5CTRJvjPdz7nkWOm4qEgrVoLHwLYpv39/a2zUYrCPjwyCWc/LIGBXnpKMjLgGF5tuN8fdlvxxfnhtPefiai61NfNrT3R8nWR7HNjLbyYsTnr4Ik2tBRXY76D151NOT3xVts0wgCRFFCRNoUl5jaaumApb0TuojuGwyCxhGrnWO2HOOSR+tQ5Ha5aUnRSIyNxJsffOF4TBA0uCMvDa1lnj0hnb8z3Huv9XUjfiIKTtmvvuv3+Qkb3x2gKyEiopGMCTLqF71tih8o6ST30YkYN9UluSbZrN0LLRHtlaVoOfUxbOYmaPWx0E/LR0zuEugyZuDr/3oKVlOVy3v622ZjaulAi6ULO/eVYteBC0hLioYuIgRrlk3BJBX9dkRRgpqaMbm6ouRivaMBdVx0OBbNSkWO0cCJZ0TXsd4m2J0TSt5+dj+XZO1S1GdM7GyHJiQMEWMzoAkJ85sc89e7SxA0ePylw2jrtCE1KRr333kTRo/SwVJehNrunpRafWz3Fs4cSNYuaMK0uNbShsp6C25KH43775yKoov1qKpvdbyvLsL+p4tzdVlaUjRGx0ah9mCh12tx770WNWku4m77HhNjREREROTABBm5ULPgCqS3TfGVJp3M546g5dT/uiy0IIkIiUmE5atTjmox89lDjiTYDQ9sRcPf3oS1qUrRNpu46HDHP4uihEtVzRAEDRJiI9HR0QXDig2o3bnF56LTsGIDOjq6EBKq/H85myjB0t7ldYJb4amrjumXuohQJsmIrkPBNrT3NvxEvgmgS8/uroqSPGJ3+5VzCDWMQ8qa59B29Xz3DYRGjz5jzUf/itHf+Ide9RKTG+yfu2xCtC4Um/5xFmJCbC7bH2WO2LziCVjbW6HThmF0TDie/P0R/Mvqmdjyo1uw7vkDaLF0AQAs7VYArnFZTpoF/N7p7r2mjRoF4Hv+jyUiIiKiEYUJMgKgbMGl9k57b5viB1yYrdyALlMN6vf83rEd07HQWrkBIdHxGDV7GUwHdzhe1/H1BVT/+VdIWfMcEu94yOV8gPdtNjZRxKJZqSg8dRWAvSoiLSkaN6aMQsKoSPzx/bP45tzx3vvbdC86axrM+ODIefzjsqmKPhPAvvXIW3JMdr7ChGdeO4at6+cpfk8iGlrUJqF8Dj8B0F55AWNXP4uQ6PjuRvtusfzG6Y5YF3lDpr1CrDuJ5txnLDx5AoAAvcQC3FRwbrDvrTeYu46vL6B656+RsuY5XDu5F0kzlmJiapwjxq0umIxX3y0GAFTUtKCuqQ0LZ6bi0JlKpCVFI3l0lP28A7RllYiIiIiGHybIyO+Cy7nqSgiPUpwkk0Qb9FkKtw5lzffavybQwszXRLWOry+g+p0tSFnzHGJmFsB06B2XLUIdX1+ApbzYo++ZL1pBQI7RgOnGRExMi8PteeORGBvpeP6u/InY++llABIWzejpTwYA9aZWvLvnHPYcKUdGqrKFG9BTfeErOSY7X2HCmdI6ZGUksIqM6DqkNgnla/iJEKlH8qpN0Aha/1VaKzdAsllh+vt/I2rSzdBNyIG1uR5fv/0srI1fA3BNHsnnjRw3xaOKzfl5b0wtHX57g7nr+PoCLGVFiMrIhaWsCAV5Gdh14ALOlNZhyZzxSE7QY/+JCphaOlB2tQk3T03Gfz65BHHREd3XNDA9IYmIiIhoeGKCjPxOmwRcq65UvCt0ExRuHXJqsg/0bOv0tTATO9t7Jqp1WBBmGAchXAexw+JoJi0vtCLHZyHMMA6dNeUu53DvexaITZTw5ANzEKIVcPp8Ld784AtHP7CFM1Ox8htGVDe04v/8/hhCQwToIkJgabeioqYFoigBcN0OFIhz9UUg+09UIMeYqPi9iWho8ZeEck/iiF0diEyfhi5TlcuwkZjcpQiNTQpcpdV980Cri0b1js2OrY3Jd/8fVL7xOMQ2s4+m+67bNZUkluKiwwP2BnNnLjkIw/J1uHbqYyRMyEZaUjQOnLTHuKyM0Y5YZ+uOq5ermvHH//kcppYO3J43Drdmq9+ySkREREQEjMAEmc1mw44dO7B7926UlZXBZrMhNTUVd9xxBx544AGEh7smMUpKSvDKK6+gpKQEFosFGRkZuO+++7Bs2bJB+g36lpJpk4D3qit/5K1ASrYOiZ3taPjbf8JqqvG6rdN9YVb/0TZYLp5EzIyliMldgpCYBMdz1uZ6NJ/6GM2n9sJcchC6CdleE2Tufc+UaOuw+u0Htun+m/H0g3Pw6AsHcamqy+P1C2emqWqq79yAui+OI6Lrhxz/PLZKZuUjPn8VorMXoWrHZvuwEY2AmBlLYVFRpRUzfTGajux22doYk7sUbeXFfZI8krem7/j4vP1nlT0pJWsnAOBbt6bj5inJAOCY3GsTRVjaPeNxWWUTJqXFBt03jYiIiIhGthGVILPZbHj44YdRWFgInU6H7OxshISEoKioCC+99BIOHjyIP/3pT4iMtG+fO3z4MNauXQtRFDFr1ixERkbi6NGjeOyxx3Dx4kU88sgjg/wb9V5vpk0GJkEIi/Tem6t765C1uQGVbzzhMlEy8LZODVL+8TcIjU2CpewMGg+85TINTV48mj7ZKR/uQW3/GSX9wDa//im2rp+Hgrx07NxX6vJ8Zlqc6iovpRVnairTiGjoce4B2XruGOJuWwGNVovqdzwHfzg3tE++ZxMq33gc4SmTEBI9Go37/0vR+eQqrbDEVHTWXnYkzUbN/hZG5X27T5JH8tZ0uRJWbW8wTUgYAGDpnPHo7HS94SBAwidnvsbX9WaP12s0gMbX9053T0jJZu3Nr0ZEREREw9SISpD993//NwoLC5GZmYnXXnsNSUlJAIDGxkY8/PDDOH36NF599VX87Gc/Q3t7O/7lX/4FAPDHP/4Rc+bMAQBUVFRg9erV+N3vfofFixdj6lTlTdeHqmCnTQaiEbSoevtZhI/NQMz0xTAsX+d4ThJFXDu5F6bCtz16iAH+t3XGL1oNDTQBp6HFL1wNAOisvuTxHmr6z6jpB3a6tBa3543DrgMXHFsr5WmTaqrH3AcD+KO2Mo2Ihg73HpCxt3wXIdFxihvaj5q9DNHZCwGoj+VCRJTjMbnitue6gp9g7DiPKOGh72ThWksbolT0pLReq4MuY4bjGrqufoGmEtcquoK52cjNTMCmbcdQVd8KwD4MYHRslM/vHXkQQXvlBYy996le/W5ERERENPyMqATZ7t27AQAbNmxwJMcAID4+Hk8//TSWL1+ODz74AD/72c/w3nvvoaGhAXfddZcjhTCHDAAAIABJREFUOQYAaWlpeOyxx/DYY49h+/bt+Nd//dcB/z36Wn9M/ZK3braVF6GtvAhNR3YjLDEVQkQUDN95FJ21l9Hw0Ta/79GzrXOKY6EmiSJComIVLx7Frg501lW4PK+2/4yafmAHTlzBo6tmYPHsNHR22bBwZhpyjImqE1hy9UVmWpzfxFwwlWlENHS49IDUCIjJXQJL2RnlWyVn3A5tpB6A+lhu+M6jaD7xIZpP7XUkzeo/fgNiW3OvJhg7ziNooIsIhVYIA6KV96RsPrMf0dPyAw6PMazYgM0PzcEjLxxCa7vVMQzA43vHrUclAFUtA4iIiIhoZBhRfxnGxcVhwoQJmDbNMzkyfvx4AEBtbS0A4O9//zsAYNGiRR7HLliwAFqtFocOBb4bPtTJ0yaVsFdd2RQd67F1UxLRWXsZYnsrQvRxMJccVPQ+5uJCaAQt/ufQV/jDeyWwWm2wlCvss1Ne7LGVxrn/jD82t+fV9gP7yfdz8OiqGcjKsPdHC6a6yyZKeOrBOchM856YdK5MI6LrjyS6xrOwxFSExCQoj48lB6GN1KPt6pewNtdDnzVf0ev0WfNhszSjs/Yy4vNXIWXNbxBmGA8AaL9cAvPZQ6h++1lU/ucGiJ1tAeOlN3IMlWOfJNow5u6NCB870evxcuWvtbkB+im3KBoeU7tzC5JG61GQl+4YBtBaUthzUPf3TvuVc+isvewyzdj+3TKi/gQiIiIiogBGVAXZ7373O5/PlZSUAADGjBkDALhwwf5HudFo9DhWr9fDYDCgqqoK9fX1SEhI8DhmKHPeOqMRtIgcPxUJBWvRWPgWxHaL1zvuwUz98rbdRwjX+XzO63t0VzXcOe9Gx2MmlT3TonMWQurqcvQ981cRIVd6lVysx77jVxAepsVPvp8TdD+w3mx7lKsvtq6fhzOlddh/osJpcmZwlWlENHS430gINj62l5egzdaF+PxViqu0GgvfRtPhdx2Jqbh5K2Ftrkdn3RUIkXrE5NqHoGidtmEq2XYpx6QLFU3Yc6Qcjc32mFUwdzwmj4uz9wYrL7YPHnDrDSZ2tkMbNQo2qxWtKgYOFORl4ItLDUF9dkREREREshGVIPNFkiS8+OKLAIAlS5YAAOrq6gAAiYnet68lJiZedwky50bQLlPRpuUjJncJom66BZK1AyH6eMdrrM31sFw8hajMObC2NCIkOt7PGVx52+4jdlh8Puf1Pbq3AjV99gGsTbVIWLJG9QIo8Y4fAYCjCsJfcszS3uXSjF8QNFi5OBMLZyrrB7ZgZmqfJq3k98nKGO2ylVKuGmNyjOj65hzPgo2P1uZ6tJ4/hujsRRiz4glU7/y13wmO1pYGNJ/cC8B1S3r71fMIiU1C8qpN3oegBNh2KYk2aLsTaJPGxyMxNhx7jlbgwyPlKDx1FdONidi4ZjYix01xueHiiM0hYfjkTCVuzUlxrQTzwz5wIBujosKC+uyIiIiIiGRMkAH4t3/7Nxw/fhwJCQl44IEHAABtbW0AgIiICK+vkR+3WCwB3/8vf/mLo/9ZIOfOnVN0nFrujaCduUyNDNOhbs/vYTVVO5ohx+QugWjtQvOn7yPulrsUns8G/TTPpsyddVccW4GUNmyWRBGW8586mvkHuwAKtJ3G26RKUZTw0dFLWF0wWVE/sOlGg6JrU0vrdu1MjNFIMBRiZ39zjmed9ZWwmk3K42P3sBHJ1gWxzYyqHZuRfM8m/xMcRRE1//Oyy3AUeUt6WOINSF61CUJohP8hKG4Thn3dfInKysfqgmwsmZ2KTduO4XRpHTb+xxFsXT/P5X01guAYhvL+J2W4NSdF9Y2Qa+YONDS1Kh8GoGJQC9H1ZiTETiIiov4w4hNkL774IrZt24awsDC88MILiI+3V0hptVpIkgSNxn8iQlTQm6WyshKfffZZn1yvUu5bYZT0c5GnRmp10Wg5/TEApwXRyicwatYdihcUGkELXbqXpsySiOZTH6vaCgQAYrtZfXKtjyZVfnikHItnp2HT/Tdj8+ufej0mMy0Om+6/Ge0dVoSGapnAIuoDQyF29sU0R3/n0k/Lh+WrU44tjSH6OITo45TFx/RpEDvb7TGx5CCspipUvvG4/b28THDsbKyCEBIKy1enPd7PXFzoOD7gEBSnCcNKbr44N9M/X2HCmdI6ZGUkuMRJeRiKpd3eN1LtjRBzmxV7jlZgdYHCYQAqWwYQXU8GI3YSERENByM2QWa1WvHss8/inXfeQXh4OF5++WXMmjXL8XxkZCSam5vR0dGB8HDP/lPt7e0AgKioKI/n3KWkpGD27NmKruvcuXNoaWlR+Ft4khdzbZfOwlxSCFvrNRi+/c/oqC5XPhVt+mI0HdntaGjc8fUFVL/za8eCSPm1iBhz90aPhVPzqb32rUArN6D6nS2+twKteAJiZ7sjOaY6udZHkypbLF14cttRPPtQXnc/sFrsP3HF0Q9swcxUTDcaUN/UhlF6Zb3KiCiwgY2dvreg93aaoy/yjYQbHvx3hETHw1J2BqZP3kXcbd9XFB+7TDUwf/53xN36PUdMFNvMaDr8rscER01oBFJ+uAWNhW+7NKuX2SxN9unDl0oUD0GRp0AqaaafsuY5FOSlY+e+Uuw/UeF1+q6ppQMVNS2qK8FaWtsRHxOOltYOdHR0ef3ecfnsuge1sHqMhquBjJ1ERETDyYhMkLW2tmL9+vX4+9//jpiYGLz66qsuyTEAMBgMaG5uRl1dHW644QaP9wjUo8zZXXfdhbvuUrY1cfXq1UHf9ZNEG8QOi8vCIMwwDlpdDMyq+rmsQ1hiqn3qVzf3BZESGkGAEB7ltSmz1WxCxKhEv1uBrM0N0EaNQtORvzgWdI7kmoI+O2oXQP4mVVbVt+LRFw6iIC8dy25Lx6OrZjieqzNZ8LfPLuO2nBTYRNFlO6T7z0Sk3MDFTu9VUEKkHiGjEhGWOA4hThVNfVlVJok2aEJCXaq22i6VBNwq2WWqQdWOzRDbWxA9/RueSaHuCY5Ad0z8/s/RZapx9B5zFz4mwz40QMWEYV36NLRdPa+qmf6uAxd8xtq46HCIohRUJdgzD80FADRea0NYSGj3Z1fcfaOo+7NTMKiFaDgYqNhJREQ03Iy4BNm1a9ewZs0afP7550hOTsa2bdu8TqqcOHEiLl68iK+++sojQWY2m1FbW4v4+Pgh1aBfI2g9F3hBTkWTX+dMXhCpuyb7IsSzKbMNorULrV8chi49y2Mr0LWTe6GflOexoAvYZ8exALKpXgAFmlTZYunCzn2lqL9mwSP3zMC7By6gta0LMyePwYKZadAKGpwprcW+4z3VZYtmpSLHaOC0SaIhzFsVVEhcsmuz+n0H+6WqzFvcDrRVsrHwbTSf3OvoI9a4fzsSv/lj7xMiu2NiT0LN7HENAKDLtFebqJ+gWazoeLmZflpStNdYaxNFLJplH4by4ZFyLJmdCsOKDajd6aeK7u6NaLxmwb9uPwkAsLRbUVHTgqiIEBTkpaMg70YYlnsZBsDkGBERERF5MaISZJ2dnXjooYfw+eefIyMjA6+//jrGjBnj9djbbrsNH374If72t79h/vz5Ls/t378fNpvN4/HBZN8ac9ZjIRHsVDT5dc7kBVEwnKstbKKI85ebMDomHEk5C2EpK8K1Ux9DsnZCExKGyPFZGDVjqc8FnfPicdTsbzn6lAFAvakVB4+U49acFOgiBMVJKefFWSALZqTBJkr47oKJjte6T7+UFZ66isy0ODz14BzoIkKZJCMaYiTRhrbLZz0qx4JpVt8X55a5b5VM+ObDCImOR8WrPwFEq9vBkp+bESKundwLU+HbPpNj4WMnImJsBoDgJmgqIX9/6CJCsHBmmsdNA60gIMdocAxD2bTtGDY/NMfvjZCOji784tWDqKpvdTmXfDNj14ELSEuKxrqV0zEhZRSreYmIiIjIrxH11+JLL72EM2fOIDk5Gdu3b/eZHAOApUuXYvTo0di9ezcOHuzZcnLlyhU8//zz0Gg0+OEPfzgAV62MfWtMocfjzo3tldBnzbc3c67z7MflPhUyWFpBwIdHLuGRFw5h+55zsMRlYPSCe5GweA1GL7gX4ak3obOxCpV/fBxWU5XX95AXjx01l3CtuQ1PvPoJfrr1AO7fsg+vvluMZ147pioZ5bw48yczLQ45xkSPhZ235JjsfIVJ9fUQ0cDQCFqYiwtdHovJXYrQ2CSf27iBnmb1valG8nZuD91bJZuP70FIdDzCElI8DpEHkgCAiJ448+ePv0StyQLdpDyExid7fXs50Sd2tsPW1qLiu6JngqYS8veHIU7nEUNlNlHCUw/OQWZaHKrqW12+IwzL1yF51VMwLF+HyHFTAAB/+J/PPZJjzkRRwqWqZrz/968Yf4mIiIgooBFTQWYymbB9+3YAQHx8PLZs2eLz2K1bt0Kv12Pz5s1Yt24d1q5di1mzZiEqKgrHjh1DW1sbHnnkEUyaNGmgLl8Rr1tjgpga6auJs5qpkIFcM3d43OXXRYTA0m7FzVPH4Ae3T0ZofLKi/jPb95zD2a8aXJ7zNSnNH3lx5ivZJVeCOVc++Jt+2dvrIaKB4RI7NQJicpfAUnZGdbP6Xp/b33E+tr87plmKEjQAbFYbtGH2a7l7ySSYmtvQoQn1289MtNnQZO5A/Kho6CbkKPyumAZLWyeips5X1LdMnzUfTc1teOg7WT63nGsFDXQRod3DUOqw/0QFSq+YUH/NgoK8dEwaH9/9WntFclWDZ6WzN/76SxIRERERyUZMguz48eOOyZOff/45Pv/8c5/Hbt26FQCwaNEibN++Ha+88gqKioogSRIyMzPxwx/+EAUFBQNy3Wr42hrTfGovoqcvCTzZq3sqmrcmzmqnQrpzb1b/2A9m4L1DZfjwSDlaLF24VNXseK7hWhsWz0qFYcVG1O70fb2GFRtR02DGniPlXs/pa1KaP5HhIdi6fh5Ol9bigJdJlVaba+LQ3/TLvrgeIup/zrEzLDEVITEJaDzwlqLXBtOb0de5/R7nZft7z0ASGyABgBZdV79AU0nPFM6orHxETciGubUdnaMnwrDcdUv6qaJK3Jqdgs2vH8e4sdH4x2/dhKSVG1HzTuDYW3i6Eiu/obCZ/oRs6ICA/Rjl57IyRrvES5souTwPBO4bqfY4IqKB8P7zyxUdt+xn7/XzlRARkbsRkyBbsmQJzp8/r/p1ubm5eP311/vhivqWJNqgz8qH+ewh7wdoACEs0m8/F2tzg9eeX8FOhQR6FkMlF+tdmtcvnJWK1QWTsXh2Gp7cdtRlm0yLpcu1/4x70+msfOgmTENNgxmbth2Duc37Fh+1VQNaQYMnf38UE1PjcHveOI9Jldv3nENphQmb/2luUOdhFQPR0COJNuin9cTOYAeb9MW5/dFPy4fN0mwfEmAY7zKREQBsHa2o8pLUkvulGVZsgMUq4Oe//TuAnob2N08Zg1uzU/D0g7MxKjqy+7rC/Db8t1qteHn7pyirvIb86SmKmunLkz+VVtC69wtzf52avpHeep4REREREbkbMQmy4U4jaKGb4P1OfkzuUoTGJKDq7WcRPjbDcypaSyNsbWaExIxGQsFDXhdEwSbHAjWv33T/zXj2oTw8+sJBtFh6El1V9a14ZVcxnl0716PpdIu5Hdv3nMOeI+U+k2OAuqoBeavk6dI6nC6t89j2WVHTArG7gsF9qySrGIiuXxpBC116T+wMdrBJX5zbF+cK3uR7ngTQM5FRAiAIAmp9VHwB9q2gtTu3IGXNc5g6IQE795Xa3yshCj/5nv19Q+pKUbvfXnkWEjcGo+bc6RF75SEot0wbi598PwePvnBQUTP9vtqa78y9qb8vct9IIqKhouxX3/X7/ISN7/bq/d0rz+SKNaXn9VW5Jr9Pf1W2DdT79zd+PkTXNybIhhFJtHluo3Tqp9NWXoS28iLHVDQhXAexw4LOuisQInSIyV2K2Lnf9ZiAZn8b9YsbraAJ2Lx+8+ufYuv6eSjIS3cs2gD7ouZfVs906TcD2BNZX33d7HKsL2qqBty3SsrNnb1x3ippE0UsnKm0iiGVVQxEQ5Akij2xs+orx2ATpZVdvUkAuZzbbwWW6znkf9ZAgqWsSFm/tLIiFORlYNeBC4iKCMEv186BTuhC5RtPu77+UjFaTn+M8JRMGFZsQEuXgH/dfhJfXjZBFCXsO37FJW4/8sIhFOSloyAvw2ULZ2++P5QIpm8kEREREZEvTJANIxpBC6mr0+VOviY0zLOfTvdUNGfyVEhrcwMMd/7U6T2DbDytsnn9nfMm4OJVE0bpw7FwZhpyjIleFzUaQFXVgFz1pUQwWyU1AKZnKr0eg6rrIaKBoREECOFRjm2F7ZUXoJ+cp6qyq6/OrbaC19cEY2/MJQdhWJ6NtKRozJ4yBoZ4PSrf+IXvyrPK86h955eOyrMvyhsB2OP26dJa3J43DrsOXHAZuDIvJwU/u3eG43frT96a+ju28fv5HiEiIiIi8oYJsmFCEm1ou3wWtbv/DTG5Sz22USrup2Nu7JPrUdu8/tFVM/DMQ/beXu7NmJ0b/AuCAKtNxFMPzMEzf/BTNfDAHDS3diAmSvm2xmC2SgqCAJsoYdP9N2Pz65/6vJ5N99/MhRrRECYncyLHTbHfbAiysqu35/ZVwes+6MT5Z7X90vS6UNx563hYytVXnslJ/gMnruDRVTOQlhTtqLadeEOs3ymV/UFNU38iIiIiIn+YIBsmNIIW5uJCRyWYvI0ybMwEGJb9ZED66bgv4IJtXt+TGPNs8J88WocHlk9FZESAaZNWES1++pN5u/beNHyOigxVNf2SiIYmTfeW7t5WdvXm3D0/Cz4HnSyalYocowGA+n5pDy3PwqjoSNTuL1T0OufKMzkZJsft7IkJSB8b44h17rHRX2KvLwVq6k9EREREFAgTZMOISxVB9zbKzroriJ9/d7/203FfwIWHafGT7+f0qnm9rwb/meOMCA8LwZO/P6J62qQ/vWn4rBU0kPNfk8fHY3r3ohUA2jutAACNRsMFG9F1QJ62CNgTVJIo+q3s6k+BBp1MHheH5358i6pJmJIoIi7GHnPVVp7pInr+ZJDj9gPLswDYY+8nRZW4NTvFce3+EnusqCUiIiKioYYJsmHEaxWBJKL51MeIz1/VL/10vC3gBEGDlYszVTSv96zI8tbgXxA0uD1vPE6fr1UxbXK04mqF3jR8ln8ODXE9V2iI1uV5Ihqa5BsDbZfP2qvFzE3Q6mO7q8WyXW4c9HdiTBZo0Mm5yyYcOFmJRbOVT8J8/+9l+NvxCrz4aL7qyjNLu9Xx2IKZqWhsbsf/3X4c5jZ77H3mwTzH1sZAE4yfenAOdBGhjI1ERERENGQMzF/51O8k0Qb9tHyvzzWf2osuUw3GrHgC4WMnej3GuZ+OGt4WcKIo4aOjlxzN6/2RK7Lct+ScKa31WFilJUUjMTYS+094Tpv8orwRl6qaXZrg7z9RoWorj3PD581r52LBjBuQY0zEghk3YPPaudi6fl7ABR23+RBdfyRRhNjRiso3foHqt5+F+ewhtF0qhvnsIVS//Swq3/gFxI5W1fGxN3zFQXevv38WnZ1dGHP3Rr/x3bBiA2oazHh775e4VNWMhqZWRGXlK7oWfdZ81JtaUVHTAsAet6cbDfjgk3KcLbPH3ok3xDpiuZIJxs+8dozxkYiIiIiGFFaQDRMaQQtduvcqArHNjKodm5F8z6Y+7afjPqlSEDSOaq6zX9WjuqE1YPN6bxVZvhr8y9t7gu1tpgQbPhONPBpB8NmMH7A3qq/+86+Qsua5AbsmpYNOWixd+K+957Hmmzd5j+9Z+dBNmIaaBjM2bTsGc3dvxj1HK7C6QGHl2YRsvLvnHERRcgwdqW5oxZ4j5QBcYzkgqZpgnJWRwLhKREREREMCE2TDhCTaIFm7MGbFE6je+WuPBY/VVIX6D3+PpO89jsi0vumnIy/gonWhKJibjtvzxiMxNtLxfGNzOzQaDbaun4czpbXY79S8fuHMNOQYE332ofGW3JK39/Smt5lSrAQjGhnkCcCKpjmWFyNy3NQB22KpNMlf/nWzz0mYLeZ2bN9zDnuOlDuSYwDw4ZFyLJmdCsOKDajducXnpM6klRtharagxdKBzWvnIseYiKaWduz4+Dxm3ZTkJZZrVE0wdu/pSEREREQ0WJggGyY0ghaNh/4LMTNut1cRlBXBXHLQqYpgPnQTstFlqkHzqb0Yveg+p9cGv9gTBA3+/Z/nI2l0FE6fr8WbH3zhlARLxfRMA1osnUgfOwqPruppXh+oIstbcquipgV1TW1B9zbrr+lpRHT9kicAK2EuLlTdp7E3grkZIA8YsHXf+Pjq62bs3Ffq8ZoWSxc2bTuGzQ/NCVhZHCcIePh7ObCJEkRRRGx0BB65J7f7PJ6xvD+rfImIiIiI+gsTZMNIZ80lVL7xOGJylyJm+mIYlq9zPGe9VofGwrfRfHIvwpMn9Nk513xrCjQa4LEXD/lsxrzp/pshSZLLc+49x5wTVzZRxKJZnkkwubfZ6oLJiqdNfnKmEh8du8zpaUTkk9ppjgPBVxz0ZuHMNLR3WvHqriI0NrtOi/Q3nbeqvhWPvHAIqwsm4/Y5gSuL5QoxZ95i6UBU+Xr73uANECIiIiLqDSbIhhGtPhbiJTOaDr+LpiO7EZaYCiFcB7HDgs66K4BkX/DIE8l6y15JEO41OSY7X2HC5tc/xdb181wet4kiNNBAEDQouViPfcd7tl+uWprpc1H34ZFyLJ6dFrC3mdwj55VdRY5tRZyeRkTeqJ3mOBC0guA3uSWTbwZs33MOB072JNMKT13F+pXTsWBmqt94OTZBj7nTxkKEAK3T474qiwMlptQm9tTesJCPd//e4A0QIiIiIuotJsiGCXmKpfnsIfkBdNZe9nqsflq+6ob8Xs8JKJqyJjdjTh8bg+ffOolR+p7FTH1TG159txhV9a2O409+WYOXfrYATz0wB8/8wXUSWoulC09uO4otP7qlu7dZHfafqPDobVbd0Iontx116bkjX8szrx3zSNgR0cjkETv96KvYqZRNlPDUg3N8ToT01jBfJggaZBsTcf5SI+JHRWDr+nk4XVqLA069IBfMTMV0owHVDa2orGtF5rg4n8klpYkptYk9tZ+Hpb3L6+fBGyBERERE1FtMkA0T/qZYOgsfO7HPeugonbIG2JsxP7pqBkwtHThdWuey/fLZh/Lw6AsH0WKxJ7NaLF3Y8B+H/SbBEmIjIYqSx7TJ9k6r14bUzjg9jYhkgxE7ldIKGugiQoO6GZCWFI3E2Ei8+cEXOPllDQry0nF73jg8umqG45g6k8URL2fdlISb0uO9XofaxJSSxJ63CcZKPg9f7wnwBggRERER9Q4TZMOIJIoYc/dGVP/5Vz4nko25e2OfVkCobcasi+j5T855+2VBXrpLI+mq+lase/4Anl8/3yMJJjeFFrz0w3l1V5HLNiNfOD2NiGSDETuVkhNI3uLgJ2cqXbaRO5NjramlAy2WLuzcV4pdBy4gLSkauogQWNqtqKhpgdgdT/3FcrWJKSWJPfVbK0WUXKxXXLHMGyBEREREpBYTZMOIRhAghEcFnEjWlws8tc2YLe1Wl8fPV5hwurQWt+eNw64DFxyLNcBeSbbj4y9dKh4A35MvAaCxmdPTiEidwYidark3oNcKGnx07LLPSlk51jrHaFGUcKmq2evxvmJ5sIkpf4k9+frVUFuxzBsgRERERKQWE2TDjLyAixwXeCJZb6lpxrxgZirqTBZU1LR4PHfgxBU8umoG0pKiPRZvahNZAzE9jYiGn4GMnX3FXxyrqGlBXVMbFs7sXcP83iamvCX2gqW2YpmIiIiISI2h9xc/9QmNoHX7ue//VTs3Y/YnMy0O040GfHT0skuFmOya2b6YuSk9HuOTY7q3TtqpSWTJCTsl5MUgEZGzgYidfcEmirhz3gSPmCkTRQkfHb2E6ZnKYnSOMdFn8mqoJKZ4A4SIiIiI+tPQ/MufrhtyM2ZfCzB/U9aidaFY8Q0jfnavfQvlj76bjZcfW4A/bFyMFd8wIloXqiqRpSZh528xSEQ0lNlEEVpBwMTUOI+Y6ezDI+Wob2oLGKPlhvm+DIXEFG+AEBEREVF/4xZL6pVgp6wlJ0Rh80N5SBodhdOltdh//IrT61KxumAyCvLGIyE2UtX19Nf0NCKiwSbHrZKL9djnJWYunp2GJ7cdRVV9KwBgbIIeEeFaRIaHBN0wX81Wel/bNPuC8w0Qf/3Q5BsgRETXu/efXz6gryMiIibIqA/4a8b84ZFyvLnnnEtyLFoXis0P5SEiPASPvXjIY7FTeOqqPZH1wBxHpYSaa+nr6WlERIPNJkqwtHd5Tf7LMfPJB27Grx++Fe/875eYOy3FI94F0zB/KCWmeAOEiIiIiPoTE2TUZ7wlsm7NScG+41dcFjMFc9ORNDrKa3JMdr7ChGf+cAxb188L4jr6dnoaEdFg0woan4khwB4zn/3Dp9i6fh4e/l6O13gXbMP8oZKY4g0QIhpJyn71Xb/PT9j4rqrjiIgoMCbIqN94W8xcM3dg+bwJOF1a67caAbAv+M6U1iErIyGoBU9fTk8jIhosNlFEycX6fo+ZvgylxBRvgBARERFRf2GCjPqVr8XM/uNXFL1+/4kK9pMhohFNKwjYN8gxc6glpngDhIiIiIj6GqdY0oBwX8yYWjoUvU7pcUREw9lQiZlMTBERERHRcMUEGQ2KuOjwPj2OiGg4Y8wkIiIiIupfTJDRgLOJIhbNSlV07MKZaY4tPEREIxFjJhERERFR/2OCjAacVhCQYzQgMy3O73GZaXHIMSZyCw8RjWiMmURERERE/Y8JMhoUNlHCUw/O8bngy0yLw1MPzmElBBERGDOJiIiIiPobp1jSoNAKGugiQrF1/TycKa3D/hMVMLV0IC46HAtnpiHHmAgemb6CAAAgAElEQVSbKLESgogIjJlERERERP2NCTIaNPJCLitjNHKMiY7H5QoILvSIiHowZhIRERER9R9usaRBpxUEt5+5yCMi8oUxk4iIiIio7zFBRkREREREREREIxoTZERERERERERENKIxQUZERERERERERCMaE2RERERERERERDSiMUFGREREREREREQjGhNkREREREREREQ0ojFBRkREREREREREIxoTZERERERERERENKIxQUZERERERERERCMaE2RERERERERERDSiaSRJkgb7IqjHvHnzUFNTg+joaEyePHmwL4eIhpFJkyZh48aNg30Z/YKxk4j6C2OnMtu3b++jqyKiwbJ69eo+e6/hHDtp+AoZ7AsgVxaLBQDQ0tKCzz77bJCvhojo+sDYSUSkXl/GzszMzL64JCIiokHDBNkQc8MNN+Dq1avQ6XQYN27cYF+OaufOnUNLSwurOPzgZ+QfP5/Agv2MJk2a1I9XNbiu99jpjv8fDD7+OxhcQ+nzZ+wcWYbSf3vDAT/PvnO9fZbDOXbS8MUtltSnVq9ejc8++wyzZ89mqb0P/Iz84+cTGD+j4Y//jgcf/x0MLn7+NFj4317f4ufZd/hZEvU/NuknIiIiIiIiIqIRjQkyIiIiIiIiIiIa0ZggIyIiIiIiIiKiEY0JMiIiIiIiIiIiGtGYICMiIiIiIiIiohGNCTIiIiIiIiIiIhrRmCAjIiIiIiIiIqIRjQkyIiIiIiIiIiIa0ZggIyIiIiIiIiKiEU379NNPPz3YF0HDy+TJkzF79mxMnjx5sC9lyOJn5B8/n8D4GQ1//Hc8+PjvYHDx86fBwv/2+hY/z77Dz5Kof2kkSZIG+yKIiIiIiIiIiIgGC7dYEhERERERERHRiMYEGRERERERERERjWhMkBERERERERER0YjGBBkREREREREREY1oTJAREREREREREdGIFjLYF0DXD5vNhh07dmD37t0oKyuDzWZDamoq7rjjDjzwwAMIDw93Ob6kpASvvPIKSkpKYLFYkJGRgfvuuw/Lli0bpN+g/6n5jE6cOIF7773X53stW7YMW7duHYjLHlA2mw1vvfUWdu3ahfLyckRGRmLq1Km47777kJ+f73F8eXk5Xn75ZZw8eRJNTU1IS0vDihUrcO+990IQhmeOX81nVFVV5fVzk+Xm5mLHjh39e8EUlMrKSrzyyiv45JNP0NjYiLi4OOTn52PdunVITEx0OXYk/n/Q39577z289dZbKC0thSiKSE9Px1133YUf/OAH0Gq1Lsfy8+8bf/nLX/DEE0/grbfewsyZMz2eV/s519TU4JVXXsHhw4dRV1eH5ORk3HnnnXjwwQcRFhY2EL8SXYf4t1rf+etf/4qf//znPp//p3/6JzzyyCOOn0fi2kCJzMxMRce9+eabuPnmmwHw7z+i/sIEGSlis9nw8MMPo7CwEDqdDtnZ2QgJCUFRURFeeuklHDx4EH/6058QGRkJADh8+DDWrl0LURQxa9YsREZG4ujRo3jsscdw8eJFly/L4ULtZ/TFF18AAKZPn44bbrjB4/1yc3MH9PoHyhNPPIH33nsPer0eeXl56OrqwmeffYbDhw9j3bp1+PGPf+w49ssvv8S9994Ls9mM3NxcZGVl4dNPP8Uvf/lLFBUVDds/StV8RvJ/R5mZmTAajR7vlZ6ePmDXTcqVlJRgzZo1aGlpgdFoRFZWFs6ePYudO3fi2LFj2LVrF0aNGgVg5P5/0J9+85vf4PXXX0dYWBhmzZoFrVaLEydOYMuWLfjss8/w29/+FhqNBgA//75y+vRpbN682efzaj/n6upqrFy5EtXV1bjpppswZcoUnDp1Ci+99BKOHTuGP/7xjwgNDe3vX4uuM/xbrW+dO3cOAHDLLbcgPj7e4/nJkyc7/nkkrg2U8pcgrKioQFFREaKjo5Gamup4nH//EfUTiUiBHTt2SEajUVq2bJlUXV3teLyhoUFauXKlZDQapa1bt0qSJEltbW1SXl6eNGXKFOno0aOOYy9fvizNmzdPMhqNUklJyYD/Dv1NzWckSZL0i1/8QjIajdKJEycG43IHxQcffCAZjUZp6dKlUl1dnePx0tJSacaMGdKkSZOk8vJySZIkSRRFadmyZZLRaJT++te/Oo5taGhwPP7RRx8N9K/Q79R8RpIkSS+//LJkNBql9957bxCuloLR0dEhLVmyRDIajdKbb77peLy9vV366U9/KhmNRmnz5s2SJI3c/w/607lz56TMzExpzpw5UllZmePx6upqacGCBS6fKT//vvHRRx9J06dPl4xGo2Q0GqXjx4+7PB/M57x27VrJaDRKr7zyiuOx1tZW6Yc//KFkNBql119/vX9/Kbou8W+1vvWDH/xAMhqNLp+lNyN1bdBbra2t0tKlS6XMzMz/396dB0RV9Y8ff7MJDqi4gUguKAzuCymoj0qa1UPpk+aaTyamWU8+0pNfcyst17QkhcfUeDTcsszcMvddc0NTXFBRARGXXABlk/3+/uA3N8YZkmHX+bz+0nvO3HvumTuHc88953OV/fv366VJ/0+I0iHrAkShbNiwAYBJkybh7Oysbq9Rowaff/45AFu2bAHylq3Ex8fTq1cvOnTooOatX78+Y8eOBWDlypVlVPKyY0odQd6TH0tLS72na8+6X375BYCxY8dSq1YtdbuHhwe9evUiNzeXw4cPA3lPGiMjI/H29ub1119X8+avz2fxOjKljuDPJ4jNmzcv24KKItu6dSvXrl2jV69eDBkyRN1ua2vLxIkTqVWrFjExMYD5/g5K09GjR1EUhX/84x96T9idnZ0ZPHgwACdOnACk/ovrjz/+YNy4cQQEBJCbm6vXpuVnaj1HR0ezf/9+6tevz/vvv69u12g0zJw5EysrK1atWlU6JyWeatJXK1mXLl2iVq1aenVpjLneGxTXrFmziImJ4a233sLX11cvTfp/QpQOGSAThVK9enUaNWpEq1atDNIaNmwIwN27dwE4dOgQAC+++KJB3m7dumFlZcXBgwdLr7DlxJQ6yszMJCoqikaNGqHRaMqymOUqODiYzZs307VrV4O01NRUADX2j+466tGjh0FeLy8vatasye+//05KSkoplrjsmVJHkLe8QaPRyFT6p8jOnTsBGDZsmEGai4sLhw8fZunSpYD5/g5Kk27p5J07dwzSEhMTAXB0dASk/otr/vz5bNq0iRYtWrBmzRoaNWpkNJ+p9fzbb7+hKArdunUziE1Wt25dmjVrxs2bN7l69WoJn5F42klfreTExcWRlJRUqAEac703KI6zZ8/y888/4+LiwpgxYwzSpf8nROmQATJRKIsXL2bbtm1GOwjnzp0DoE6dOgBcuXIFwOh6eAcHB5ycnEhISOD+/fulWOKyZ2odZWVl4erqyrx58/Dz86NVq1Z0796dOXPmkJSUVKZlLyuVKlVCq9UaBE/et28f27dvR6PRqDdIuhsbY9cR5MVWyM3NJSoqqnQLXcZMqaMHDx5w69Yt3NzcCA0N5R//+AetW7emc+fOTJ482egAgCh/Fy5cwMbGhiZNmnD79m1CQkL49NNPmTt3LmfPntXLa66/g9LUpUsXLCws2L59OyEhISQkJJCUlMTPP//MihUrqFatGn379gWk/ourUaNGzJkzh7Vr1/5lEGpT61mX38PDo8DjAly+fLnIZRfPJumrlRxd/LGaNWsyffp0XnrpJVq2bMkrr7zCN998Q0ZGhprXXO8NimPWrFkoisLYsWMNrlfp/wlReiRIvygWRVEICgoC4OWXXwbg3r17AAZvYdOpXbs2t2/f5v79+wUut3iWGKsj3bToAwcOcOLECdq3b0+dOnU4d+4c3333HXv37uWHH34wGvD0WZGens64ceO4evUqUVFR1K1bly+//FK9JnRPcP/qOgKe6c7Uk+pI1zmNiIjg8uXLetfRTz/9xL59+1ixYkWBszZE2cvMzOT27dvUqVOH7du388knn/Do0SM1/X//+x/Dhw9n3LhxgPwOSkPjxo2ZPn06M2fOJDAwkMDAQDWtbdu2fPHFF7i4uABS/8U1cuTIQuUztZ51+Z2cnAqVX4gnkb6a6XT1s379ehwdHfHy8sLZ2Znz588THBzMoUOHWLZsGXZ2dnJvYKKDBw9y+vRp3N3dee211wzSpf8nROmRGWSiWL7++mtOnDhBrVq1GDFiBIB6s2dnZ2f0M7rtaWlpZVPIcmasjnR/2Ly9vdmzZw8hISGEhoayc+dOOnbsyLVr1/jss8/Ks9il7tatW+zYsUNv5kVkZKT6b7mOnlxHus6pVqtl27ZthIaGEhISwp49e+jZsyf37t1TY3uIikG3ROzhw4eMHz+eHj16sH37dk6cOMG8efNwdHRk6dKlrFmzBpDfQWnx8vKiY8eOaDQaOnToQKdOnbC3t+fcuXOsXr0aRVEAqf+yYmo9y/ciSpr01Uynqx8/Pz/27dvHokWLWLVqFb/++itNmjTh9OnTzJ8/H5DfrKmWL18O5D1k0IUFyE/6f0KUHhkgE0UWFBRESEgIlSpVYv78+eoTNCsrKywsLIw26Pnl5uaWRTHLVUF1NHHiRLZv386iRYv0njzWqFGDOXPmoNFo2LVrl/qU/FlUp04djh07RlhYGPPnzycrK4vp06cTEhIC/Blny5yvoyfVkb+/P7t372b58uV6r/7WaDTMmDEDZ2dnIiIiCA8PL69TEI/JzMwE8m4WfHx8mDt3Lm5ublStWpVXX32VOXPmAPDNN9+gKIr8DkpBeHg4/fv358aNG/z6668sX76c0NBQtm3bRrNmzVixYgXBwcGAtENlxdR6lu9FlCTpqxVNcHAwW7Zs4csvv9RbAvjcc88xe/ZsLCwsWLNmDVlZWXJvYILo6GgOHz5M3bp16dmzp9E80v8TovTIAJkwWXZ2NlOmTGHhwoXY2tqyYMEC2rdvr6ZXrlwZRVH0Yg/kl56eDoC9vX2ZlLc8PKmObGxscHNzw8HBweCzzs7ONGvWDEVR1CdEzyKNRkP16tWpVq0afn5+LFiwAAsLC7799lsyMjKoXLky8Of18jhzuI6eVEdWVlbUq1fP6PKOypUrq2+KioiIKOuiiwLkf3r+5ptvGqS/8MILODs7c+fOHa5duya/g1Iwa9YsUlNTmTlzJq6urup2Z2dnvv76a6ytrVm2bBmPHj2S+i8jptZzYfNLYHXxV6SvVjy2tra4u7sbxEwFaNq0KXXq1CEtLU39W2bu9waFtX37dhRFoVevXnovZcpP+n9ClB4ZIBMmSU1N5f3332fNmjVUrVqVpUuXGrx2WBcTRBdv4HFPikPwtCtMHT2JLv5C/thEz7o2bdpQv359UlJSiIuLU6+jgmLIPOvXkTGP19GTmON1VNFVqVIFGxsbIO8puzF169YF8t6oKL+DkpWens7Zs2epWrWq0bfY1atXDzc3N9LS0oiNjZX6LyOm1nNh8xcUo0wI6auVvvz1Y+73BqbYvXs3gNHYY4Ul16YQRScDZKLQHj58yJAhQzh06BAuLi58//33ek/adHRvlTL2Vq+UlBTu3r1LjRo1nskgnIWto+nTpzNq1Cji4+ON7ufGjRvAn29SehYoisKXX37JRx99RHZ2ttE8uqeQ2dnZ6nWke1vZ4/uKjo7GysqKxo0bl16hy5ipdbRgwQICAgL04pLl9yxeR0+7/NdsQW+Z0t3016xZ0yx/B6UpOTkZRVGwtCy4+6N7Yp+VlSX1X0ZMree/yg9/9j8KeiumMG/SVyu+lJQUJk+eTEBAQIH9lfz1Y873BqaIj48nIiKChg0b/uWbf6X/J0TpkQEyUSiZmZmMHDmSiIgI3N3d+fHHHwvseHbp0gX48wlIfnv37iUnJ8fkp3RPA1Pq6PTp0+zevZu9e/capF2+fJmLFy/i6OhI8+bNS7vYZcbCwoI9e/awdetWDh8+bJAeFxdHTEwMGo0GNzc39Tras2ePQd5Tp06RkJDA888/b3Tpw9PK1DqKjIxkx44dbNu2zSBvfHw8hw8fxsbGBh8fn7Ioviikrl27AnnLKB4XHR3NzZs3cXJyol69emb5OyhNNWvWxNHRkQcPHnD27FmD9Dt37hAVFYWNjQ2NGjWS+i8jptazLv++ffsMYhbdunWLixcv4urqiru7eymXXDxtpK9WMuzt7dm1axc7duzgxIkTBukHDhwgMTERrVaLk5OT2d4bmEr3d6lt27Z/mU/6f0KUHhkgE4USHBxMeHg4Li4urFy58i+fSLzyyivUrFmTDRs2cODAAXV7XFwcgYGBWFhY4O/vXwalLlum1NHAgQMBmDdvnt7TtISEBCZOnEhOTg4jRowwGtfhaTZgwAAAZsyYwR9//KFuv3PnDmPGjCE7O5vBgwdja2uLt7c3Hh4eHD58mJ9++knNm5CQwNSpUwEYNmxY2Z5AGTCljnTXUWhoKL///ruaNzU1lUmTJpGSkkK/fv1kyUIFM2jQIDQaDRs3bmTz5s3q9ocPH/Lpp5+Sm5vLP//5TywtLc32d1BaLC0t6devHwCffPKJ3iy+hIQExo4dS1ZWFn379sXe3l7qv4yYWs+6wePo6GiCgoLU7WlpaXz66afk5OTI9yKMkr5aybCwsFD7K9OnT9drS69fv860adMA+Ne//gWY772Bqc6fPw9AixYt/jKf9P+EKD0Wiu5d5kIUIDExkRdeeIH09HSaN29Oo0aNCsw7d+5cIO8pcEBAADk5ObRv3x57e3uOHTvGo0eP+Oijj3j//ffLqvhlwtQ6ys3N5T//+Q87duzAxsaGdu3aUblyZY4fP05qaip+fn4EBgYWGJzzaZWVlcWoUaM4cOAAGo0GLy8vcnJyOHPmDGlpafj6+rJgwQK1s3n27FmGDh1KWloarVu3xsnJibCwMB4+fMiAAQOYPn16OZ9RyTO1jmbPnk1oaCiWlpZ4eXlRvXp1Tp48SWJiIu3atWPJkiVqQGtRcWzdupWPP/6Y7OxsmjdvjpOTE+Hh4SQmJtKhQweWLFmixiozx99BacrIyGDEiBGEhYVha2tL+/btsbCw4MyZMyQlJdGmTRtCQ0PVAO9S/yVnyJAhhIWF8f3339OuXTu9NFPrOS4ujjfffJN79+6h1Wpxc3Pj1KlT3Lt3j65du7Jo0SKsra3L8vREBSd9tZKVnp7OO++8w++//45Go+H5558H4Pjx42RmZvLOO+8wfvx4Nb+53RsUxfjx49m4cSNBQUH8/e9//8u80v8TonTIAJl4op07dzJ69OhC5c2/Fv7UqVN88803nDlzBkVRcHd3x9/fHz8/v9IqarkpSh0pisKaNWtYu3YtV69exdLSEnd3dwYMGEC/fv2e+Crsp1VOTg6rV69m/fr1REVFYWlpiVar5Y033mDAgAEGsYGuXr1KcHCw2uFq0KABgwYNon///s9sp9TUOtq2bRurVq3iwoUL5ObmUr9+fV5//XWGDh2qDrKIiufixYssWrSIEydOkJqaSr169Xj99dcZNmyYwfdmjr+D0pSVlcXq1avZtGkT0dHR5Obm0rBhQ3r27Im/v7/BjBCp/5LxVwNkYHo93759m+DgYA4ePEhycrL6Gxo6dCi2trZlcUriKSJ9tZKXmZnJsmXL2Lx5M9euXaNSpUo0a9aMIUOG8PLLLxvkN6d7g6J49913OXjwIKGhoXTq1OmJ+aX/J0TJkwEyIYQQQgghhBBCCGHWJAaZEEIIIYQQQgghhDBrMkAmhBBCCCGEEEIIIcyaDJAJIYQQQgghhBBCCLMmA2RCCCGEEEIIIYQQwqzJAJkQQgghhBBCCCGEMGsyQCaEEEIIIYQQQgghzJoMkAkhhBBCCCGEEEIIsyYDZEIIIYQQQgghhBDCrMkAmRBCCCGEEEIIIYQwazJAJoQQQgghhBBCCCHMmgyQCSGEEEIIIYQQQgizJgNk4qm3fv16PD09eeONN8q7KGUiPT2dGTNm0KVLF1q0aEGXLl04evRoeRdLCCFM8t///hdPT08CAgLKuygmyc3NJSYmRm/b8ePH8fT0xMfHp5xKJYQQpWPChAl4enoyZ86cYu+re/fueHp6sm/fPpM/GxUVVezjCyHEk8gAmRBPmWnTprFy5Uru379P48aNqVq1Kq6uruVdLCGEeOadO3eOfv368dNPP5V3UYQQwiykpKTw+eefM2TIkPIuihDCDFiXdwGEKK6XXnqJ1q1bY2dnV95FKRPbtm0DYOrUqQwYMKCcSyOEEObj+++/JyIiQmaKCSHMxpgxY3j33XepXr16uRw/IiKCH374AUdHx3I5vhDCvMgAmXjqValShSpVqpR3McpERkYGaWlpALRr166cSyOEEEIIIZ5lTk5OODk5lXcxhBCiTMgSSyGeItnZ2eq/K1WqVI4lEUIIIYQQQgghnh0yQCYqtMjISCZNmkT37t1p0aIFHTt25N///jdnz55V8xgL0n/jxg08PT3p2bMnV69eZeDAgbRs2ZLOnTuzatUqNV9KSgohISH06dMHLy8v2rRpQ9++fVm9ejW5ubkG+/P09CQ1NdWgnJcvX1bT89MFNt29ezfnzp3j/fffx9vbm7Zt2/Lmm2/y22+/AZCWlsZXX32lnmf37t2ZN28eWVlZ6r66d++Ol5eX+v8XX3wRT09P/vvf/+odc/fu3QwfPhwfHx9atmxJjx49mDFjBnfv3jUoty5I9tKlS1m9ejVdunShVatW9OzZk9jYWDVfXFwcU6ZMUcvn4+PDe++9V+DLATw9PWnbti2KorB27VreeOMN2rRpw/PPP8+wYcM4fPiw0c8B7N+/n/fee4/OnTurdfHZZ58ZLT/AiRMnGDVqFJ06daJFixb4+voyadIkvfILIZ4emZmZLFu2jL59+9K2bVvatGlDnz59WLp0KRkZGQb5de3s9u3buXTpEqNHj6ZDhw60bNmSV199lcWLF5OZmWn0WOfPnycgIEBt+/r06cO6devUNr979+7An38DNmzYAMB3332Hp6cnEyZMMNhnamoqQUFBvPLKK+rfnY8//pjr16+XYC0JIczJwIED8fT0ZN26dQZpX331FZ6envj6+hqkJSUl0axZM9q0aaO2n0VtY40F6S9sG2rM7t27eeutt/Dy8sLLy4tBgwapYUR0hgwZwttvvw3AgwcPjPa1hRCiJMkSS1Fhbdy4kcmTJ5OZmUnVqlXRarXcunWLXbt2sW/fPr799ls6d+78l/tITk5m+PDhJCUl4e7uTnR0NI0bNwbg5s2bvPvuu0RFRWFlZUXjxo3Jysri/PnznD9/njNnzpTIG3sgb9Bn48aN2NjY0LBhQ+Li4jh16hQjR45k0aJFBAYGcuXKFerXr4+LiwvXr19n8eLF3L9/n5kzZwLQokULnJycOH36tPr/SpUq4eLiAoCiKEyZMkUNHl27dm08PDyIiYlh5cqVbNmyhZCQEFq2bGlQvp07dxIeHo6rqyuurq6kpaVRr149AA4dOkRAQABpaWlUrlwZDw8PEhIS2L9/P/v372f06NH8+9//NnrekydPZu3atVSrVo1GjRoRExPDkSNHOHr0KMHBwbz88st6+adOncrq1asBqFOnjlr+H3/8kb1797J27Vrq1Kmj5l+4cCFBQUEAVK9eHa1WS1xcHOvWrWPr1q0EBQUZ7TAKISqmBw8e8O6773L27FksLS2pV68ednZ2REZGcuHCBbZs2cLSpUuNxsI5duwYY8eOBcDNzY3KlSsTFRXFvHnzOHPmDIsWLdLLv3XrVsaNG0dWVhbVq1dX2xvdQ5n8bG1t8fLyIjY2lvj4eJydnXF1daVhw4Z6+TIzMxk8eDCXLl1S02NiYvjll1/Yt28fGzZsUNtWIYQoLF9fX8LDwzly5Ah9+/bVS9M9rPzjjz+Ii4vTa2MOHz5MTk4OnTp1wtbWtlht7ONMaUMfFxISwqlTp6hSpQoNGjTg5s2bnD59mtOnT/PHH38wbNgwALRaLQ8ePODy5ctYW1vTqlUrU6tOCCFMowhRAUVFRSktWrRQtFqtEhQUpGRmZiqKoiiZmZnKF198oWi1WqVdu3ZKamqqsm7dOkWr1Sp9+vRRPx8XF6dotVpFq9UqL7/8snL//n1FURQlMTFRyc3NVRRFUd566y1Fq9UqAwYMUG7cuKF+9vjx40qbNm0UrVarbNq0yWB/KSkpBuWNjIxU0/MbP368un306NFKcnKyoiiKkpycrPTu3VvRarVKkyZNlG7duikRERHq55YuXapotVqladOmSmJioro9JSVF3V9cXJzesb777jtFq9UqnTt3Vo4cOaJuT01NVT7//HNFq9Uqvr6+ahkURVGCg4PV/c2cOVOtm/j4ePW8vby8FK1Wq8yfP1/JyMhQP7t79241bdeuXXpl0e2zadOmysqVK5WcnBz1vHX17ufnp/cZ3ffYpk0bZceOHer2+Ph4ZciQIYpWq1X8/f3V7Tt27FC0Wq3i5eWlbNmyRd2emZmpfPPNN2razZs3Db4vIUT507U/o0ePVre99957ilarVQYOHKjExsaq22/duqUMHjxY0Wq1yr/+9S+9/eRvZ0eOHKncu3dPTVu+fLmadubMGb39tWrVSm3bsrKyFEXJay8nTJigfqZbt25GjzV79my97ceOHVM/4+3trRw4cEBNi4qKUv72t78pWq1WmTJlSjFqTAhhriIiIhStVqt06tRJb/uDBw+UJk2aqO3Pzz//rJc+ceJERavVKj/99JOiKMVrY/O3e0VtQ7t166amzZ49W0lLS1MURVEyMjKUMWPGKFqtVmnbtq3a71eUP9tXb2/volafEEIUmiyxFBVSaGgomZmZ+Pn5ERAQgI2NDQA2NjaMHz8erVZLUlIS+/bte+K+3nnnHWrWrAmAo6MjFhYWnDp1irCwMDQaDQsXLsTV1VXN7+3trc6I2rRpU4mcT7Vq1Zg1axYODg4AODg48OabbwKQm5vL559/TrNmzdT8b4H8oM0AAA2RSURBVL/9NpUqVSInJ4crV648cf8ZGRksXrwYyJtq37FjRzVNo9Hw2Wef0bp1a27fvm10er6NjQ0ffvghFhYWANSoUQPIW0aUkpJC7969+fDDD/Xinr344ov83//9HwALFiwwWq7+/fvz1ltvYWlpqZ73hx9+CEBUVBQpKSlq3m+//RaAjz/+WG9mWY0aNZg7dy7W1tYcO3aMO3fuABAcHAzApEmTePXVV/XO5YMPPsDPz4+UlBSWLVv2xPoTQpS/c+fOsW/fPqpXr87ChQupX7++mubi4kJwcDAajYY9e/Zw6dIlg887OjoSFBRErVq11G1vv/22up/w8HB1+9KlS0lPT+ell17iww8/xNo6b0K9RqNh5syZRmfaFtbEiRPp2rWr+v9GjRoxdOhQAHUGsBBCmKJZs2Y4OTlx//59Ll++rG4/fvw4ubm5agiOEydO6H3u0KFDWFhY4OvrW+w2Nr/itqEdOnRg/PjxVK5cGciLqztp0iQgb5l6Yfq+QghRGmSATFRI+/fvBzCYRg5gYWHBwoULOXDgAK+99toT99WmTRuDbQcOHACgW7du6uBZfgMHDmTLli0GS3KKysvLSx0c06lbty4A1tbWdOjQQS/N2tpafZ21sZhnjzt16hQPHjygVq1aBvvS0Q0iHTx40CBNq9Vib29vsH3v3r0ABdbza6+9hoWFBRcvXuTevXsG6caWNzZq1Ej9t26A7Nq1a1y7dg1ra2t69+5t8BknJyc2bNjA0aNHcXZ25vr161y5cgVLS0u9wbH8evbsCRg/XyFExbNnzx4AOnbsqA7S51ezZk118N/Y79rb2xs7OzuD7W5ubgB6A/K6hysDBgwwyG9pacmgQYOKcAZ5evToYbDN3d0dyFtCKoQQRaEbeD9y5Ii6Tbe8csSIEQCEhYWpaZcuXeLu3btqiI7itrH5FbcNNdZO1qxZU+37SlsphCgvEoNMVDgZGRlqQHatVms0jykxXGrXrm2wTRcs2cPDw+hnHBwc1BuakuDs7GywTTcrzsHBwegbKXXpiqI8cf9Xr14F8oL962amPe7hw4cAxMTEGKQZq6OUlBRu374NwLx58wocLLSysiI7O5uYmBiD/Rg7b1tbW/XfOTk5wJ/fh6urKxqNxuhx8l8LuvO1tLTknXfeMZo/PT0dgNjYWBRFUWfHCSEqpqioKABOnjxZYDt248YNwHg7Zqy9AdRBM92LVzIzM9X9FBTsOf+MXlNoNBqDhyG67YDRANhCCFEYL7zwAj///DNHjx7F398fyIu9qNFo6Nq1Kw0bNuTatWvcunWLunXrcujQIfVzUPw2Vqck2lAnJyej2+3t7Xnw4IG0lUKIciMDZKLCyf/UqKDBElPkH5B5/Bglsf/CKO3j6GZGpKWlcerUqULlzc9YHeWfuXbhwoUnliE5Odlgm26QryC6wT9Tvw/dOWRnZz/xfHNzc0lNTTV60yqEqDh0v+u7d+8W+NZaneK0N4mJieq2gtocYzNqC8PYww4hhCgJnTp1wsbGhhMnTpCdnU18fDzR0dF07twZGxsbfHx8uHbtGmFhYfTu3VudBaYLmF/cNlanJNpQaSuFEBWVDJCJCif/Epm0tDSqVKlSasd49OiRyZ81NqNLN1upvOhiOLzwwgtqLK+S2ifkTeE3Nh2/pOiOVdjvQ9ch8/Dw4Ndffy21cgkhyo6uHRg3bhzDhw8vtePkv6FLTU01+jemMEvbhRCiLNnb29O+fXuOHDnCmTNn1FlcPj4+QF5crzVr1hAWFkaPHj04ffo0zs7O6myukmpjpQ0VQjzLJAaZqHCqVaumvl5aNx38cWvWrGHo0KH88MMPRTpGw4YNgT+X6j0uPj6efv36MWbMGLKzs9Xgo5A3tfxxT3oSV9p05xMdHV1gnhs3bhAeHk58fHyh9lm1alV1UKyg/ebk5HDkyBFiY2PV5ZJFoSv/zZs3CxxsnDJlCiNHjiQsLIwGDRoAeedk7PsAuH//PidPnlSD+gshKjbd7/qv2rELFy5w8eJFozNhC6tKlSrqcszIyEijefIHwRZCiIpCF9v16NGjakB+3QCZt7c3kBeH7NixY2RlZanLK6Hk2lhpQ4UQzzIZIBMVUufOnQHYuHGjQZqiKGzYsIFjx44VOUZBly5dgLyXAehic+W3a9cuzp07R1RUFNbW1lStWlVNMxaXQRfMvry0a9cOjUbD9evX9YK35vfJJ58wcOBAZs+eXej96jpiP/74o9H0zZs3M2zYMHr37k1aWprpBf//3N3dcXFxISsry+iMsMTERDZv3syBAweoUqUK7u7uuLq68ujRowLfNBoYGMg///lPPvrooyKXSwhRdnQ3cjt37iQhIcEgPTk5GX9/f3r37s22bduKdSzdkqP169cbTTf2tl9AjWVYmNiQQghR0vIPkJ08eRJ7e3uaN28OQK1atXB3dycuLo41a9YAf7Z1ULJtbFHb0KLQvQldCCHKgrQ4okIaMWIENjY2/PLLLyxZskSdnZSVlUVgYCCnT5/G0dHR6BsPC6Njx460bt2a5ORkRo8erfcGxrCwMAIDAwEYNmwYkDedXBeI9Ouvv1ZjM2RnZ7NixQo2bNhQ5HMtCQ4ODmrA1rFjx+oNkqWnpzNr1iyOHTuGlZUVQ4cOLfR+R4wYga2tLZs3b2bevHl6A5KHDh1i2rRpAPTv379YS2EtLCwYOXIkALNnz+a3335T0xISEhg7dixpaWn4+PjQtGlTLCws+OCDDwCYNWsWW7ZsUfNnZ2ezZMkStdNWUBB/IUTF4uPjQ/v27UlKSuK9994jNjZWTbtz5w4ffPABDx8+pHbt2vTq1atYxxo+fDh2dnZs376dhQsXqn9jMjMz+eKLL/TeBJefLq7OrVu3inV8IYQoCjc3Nxo0aEB4eDgxMTG0a9dOb5WD7k3mBw8exM7OTu/N5iXZxha1DS0K3ZLOlJQUow+1hRCiJEkMMlEhNWnShGnTpvHpp5/y1VdfsWTJElxdXYmLi+Phw4fY2dkRGBiovg7aVBYWFsybNw9/f3+OHz9Ot27d8PDwIDk5mbi4OAD69eunNwAXEBDA6NGjOXnyJL6+vjRs2JDbt2+TkJDA0KFDWb9+/V8GNS1to0aNIjo6mu3btzNs2DBcXV1xdHQkNjZWnSo/depUWrRoUeh9uru7M2fOHMaNG8fixYtZuXIlbm5uJCYmcvPmTSAvaOzYsWOLXf7Bgwdz4cIF1q5dy/Dhw3nuuedwcHAgJiaGjIwMXF1d9Wa/9evXjytXrrBs2TLGjBnDF198gbOzMzdu3FCD/o8aNcroq8SFEBVTYGAgw4cP5+zZs7zyyiu4u7tjaWlJdHQ0WVlZODg48L///U8vVmVR1KtXj2nTpjFhwgSCgoJYuXIlrq6uxMbGkpSURIsWLTh//jxWVlZ6n9M9KNmxYwe9evXC29ubyZMnF6ssQghhCl9fX1asWAH8ubxSx8fHh1WrVgF5D4MfbytLqo0tahtaFA0aNMDOzo709HReffVVnJ2dWbZsmd7qDiGEKCkyg0xUWG+88QZr167ltddew9ramsjISCpVqkSvXr1Yv369ugyzqFxdXVm/fj2jRo2iQYMGREVFER8fj5eXF3PnzmXmzJl6+Xv06MHy5cvp0qWL2pl47rnn+PLLL5k0aVKxylISrK2tmT9/PvPmzeNvf/sbqampREZGYmtry0svvcT3339P//79Td6vn58fGzdupF+/fjg6OhIZGUliYiItW7Zk0qRJhISElNjbiGbMmEFwcDAdO3YkKSmJqKgonJ2dGT58OBs2bKBu3bp6+SdOnMjSpUvp3r07ubm5XLp0Cchbortw4UICAgJKpFxCiLLh7OzM2rVr+fjjj2nevDk3b94kOjoaJycnBg4cyKZNm2jatGmJHOv1119n1apV+Pr6kpOTw+XLl6lXrx5z585VZw8/fpPYp08f/P39qVmzJteuXVPbHCGEKCv544rp4o7l/79uKXi3bt0MPluSbWxR2tCicHBwYP78+Xh4ePDw4UNu377N9evXi71fIYQwxkKRQBpCCCGEEKrVq1czdepUOnXqRGhoaHkXRwghnirShgohnlYyg0wIIYQQZmXChAn06dOnwBesHDp0CKDEZqsJIcSzRNpQIcSzSgbIhBBCCGFWPDw8uHDhAoGBgdy4cUPdnpmZSUhICHv37qVSpUr07du3HEsphBAVk7ShQohnlSyxFEIIIYRZSUtLY9CgQURGRmJlZUWDBg2oXLkycXFxJCUlYWNjw9SpU+XmTgghjJA2VAjxrJIBMiGEEEKYnfT0dNatW8cvv/xCXFwcycnJ1K5dG29vb4YMGULz5s3Lu4hCCFFhSRsqhHgWyQCZEEIIIYQQQgghhDBrEoNMCCGEEEIIIYQQQpg1GSATQgghhBBCCCGEEGZNBsiEEEIIIYQQQgghhFmTATIhhBBCCCGEEEIIYdZkgEwIIYQQQgghhBBCmDUZIBNCCCGEEEIIIYQQZk0GyIQQQgghhBBCCCGEWZMBMiGEEEIIIYQQQghh1mSATAghhBBCCCGEEEKYNRkgE0IIIYQQQgghhBBmTQbIhBBCCCGEEEIIIYRZkwEyIYQQQgghhBBCCGHWZIBMCCGEEEIIIYQQQpi1/wf6s4KL4TufcQAAAABJRU5ErkJggg==\n",
          "text/plain": [
           "<Figure size 619.85x540 with 12 Axes>"
          ]
         },
         "metadata": {
          "image/png": {
           "height": 526,
           "width": 612
          }
         },
         "output_type": "display_data"
        }
       ],
       "source": [
        "import seaborn as sns\n",
        "sns.set(style=\"ticks\")\n",
        "\n",
        "sns.pairplot(df, hue=\"kind\", diag_kind=\"hist\");"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
    
    schmittu's avatar
    schmittu committed
        "In contrast to our previous examples, our data set contains a non-numerical text column `kind`.\n",
        "\n",
    
        "<code>sklearn.preprocessing.LabelEncoder</code> is a preprocessor which encodes text values to according numbers:\n",
    
    schmittu's avatar
    schmittu committed
        "\n"
    
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 5,
    
       "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>circumference</th>\n",
           "      <th>length</th>\n",
    
           "      <th>is_atlantic</th>\n",
           "      <th>is_sockeye</th>\n",
    
           "    </tr>\n",
           "  </thead>\n",
           "  <tbody>\n",
           "    <tr>\n",
           "      <th>0</th>\n",
           "      <td>25.5</td>\n",
           "      <td>85.5</td>\n",
    
           "      <td>1.0</td>\n",
           "      <td>0.0</td>\n",
    
           "    </tr>\n",
           "    <tr>\n",
           "      <th>1</th>\n",
           "      <td>22.5</td>\n",
           "      <td>62.5</td>\n",
    
           "      <td>1.0</td>\n",
           "      <td>0.0</td>\n",
    
           "    </tr>\n",
           "    <tr>\n",
           "      <th>2</th>\n",
           "      <td>29.0</td>\n",
           "      <td>88.0</td>\n",
    
           "      <td>1.0</td>\n",
           "      <td>0.0</td>\n",
    
           "    </tr>\n",
           "    <tr>\n",
           "      <th>3</th>\n",
           "      <td>32.5</td>\n",
           "      <td>85.5</td>\n",
    
           "      <td>1.0</td>\n",
           "      <td>0.0</td>\n",
    
           "    </tr>\n",
           "    <tr>\n",
           "      <th>4</th>\n",
           "      <td>24.5</td>\n",
           "      <td>74.5</td>\n",
    
           "      <td>1.0</td>\n",
           "      <td>0.0</td>\n",
    
           "    </tr>\n",
           "  </tbody>\n",
           "</table>\n",
           "</div>"
          ],
          "text/plain": [
    
           "   circumference  length  is_atlantic  is_sockeye\n",
           "0           25.5    85.5          1.0         0.0\n",
           "1           22.5    62.5          1.0         0.0\n",
           "2           29.0    88.0          1.0         0.0\n",
           "3           32.5    85.5          1.0         0.0\n",
           "4           24.5    74.5          1.0         0.0"
    
         "execution_count": 5,
    
         "metadata": {},
         "output_type": "execute_result"
        }
       ],
       "source": [
    
        "from sklearn.preprocessing import OneHotEncoder\n",
    
        "features = df.iloc[:, :-1]\n",
        "values = df.iloc[:, -1]\n",
        "\n",
        "x = OneHotEncoder(sparse=False).fit_transform(features.iloc[:, 2:3])\n",
        "features[\"is_atlantic\"] = x[:, 0]\n",
        "features[\"is_sockeye\"] = x[:, 1]\n",
        "del features[\"kind\"]\n",
        "\n",
        "features.head()"
    
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 6,
    
       "metadata": {},
    
    schmittu's avatar
    schmittu committed
       "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>circumference</th>\n",
           "      <th>length</th>\n",
    
           "      <th>is_atlantic</th>\n",
           "      <th>is_sockeye</th>\n",
    
    schmittu's avatar
    schmittu committed
           "    </tr>\n",
           "  </thead>\n",
           "  <tbody>\n",
           "    <tr>\n",
           "      <th>95</th>\n",
           "      <td>19.0</td>\n",
           "      <td>69.5</td>\n",
    
           "      <td>0.0</td>\n",
           "      <td>1.0</td>\n",
    
    schmittu's avatar
    schmittu committed
           "    </tr>\n",
           "    <tr>\n",
           "      <th>96</th>\n",
           "      <td>18.5</td>\n",
           "      <td>67.0</td>\n",
    
           "      <td>0.0</td>\n",
           "      <td>1.0</td>\n",
    
    schmittu's avatar
    schmittu committed
           "    </tr>\n",
           "    <tr>\n",
           "      <th>97</th>\n",
           "      <td>24.5</td>\n",
           "      <td>67.5</td>\n",
    
           "      <td>0.0</td>\n",
           "      <td>1.0</td>\n",
    
    schmittu's avatar
    schmittu committed
           "    </tr>\n",
           "    <tr>\n",
           "      <th>98</th>\n",
           "      <td>21.0</td>\n",
           "      <td>66.5</td>\n",
    
           "      <td>0.0</td>\n",
           "      <td>1.0</td>\n",
    
    schmittu's avatar
    schmittu committed
           "    </tr>\n",
           "    <tr>\n",
           "      <th>99</th>\n",
           "      <td>27.5</td>\n",
           "      <td>86.5</td>\n",
    
           "      <td>0.0</td>\n",
           "      <td>1.0</td>\n",
    
    schmittu's avatar
    schmittu committed
           "    </tr>\n",
           "  </tbody>\n",
           "</table>\n",
           "</div>"
          ],
          "text/plain": [
    
           "    circumference  length  is_atlantic  is_sockeye\n",
           "95           19.0    69.5          0.0         1.0\n",
           "96           18.5    67.0          0.0         1.0\n",
           "97           24.5    67.5          0.0         1.0\n",
           "98           21.0    66.5          0.0         1.0\n",
           "99           27.5    86.5          0.0         1.0"
    
    schmittu's avatar
    schmittu committed
          ]
         },
    
         "execution_count": 6,
    
    schmittu's avatar
    schmittu committed
         "metadata": {},
         "output_type": "execute_result"
        }
       ],
    
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "Now we prepare the data for training and testing:"
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 7,
    
       "metadata": {},
       "outputs": [],
       "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "\n",
        "(features_train, features_test, \n",
        " values_train, \n",
        " values_test) = train_test_split(features, values, random_state=42)"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "Without further explanation we pick a regression algorithm, more about regrssion algorithms will be discussed later:"
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 8,
    
       "metadata": {},
       "outputs": [],
       "source": [
        "from sklearn.kernel_ridge import KernelRidge\n",
        "kr = KernelRidge(alpha=.1, kernel=\"rbf\", gamma=.1)"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
    
    schmittu's avatar
    schmittu committed
        "<div class=\"alert alert-block alert-warning\">\n",
    
    schmittu's avatar
    schmittu committed
        "    <i class=\"fa fa-info-circle\"></i>&nbsp; Regression methods in <code>scikit-learn</code> also have <code>fit</code> and <code>predict</code> methods. Thus cross validation, pipelines and hyperparameter-optimization will be available.\n",
        "    \n",
        "</div>"
    
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 9,
    
       "metadata": {},
       "outputs": [],
       "source": [
        "kr.fit(features_train, values_train)\n",
        "predicted = kr.predict(features_test)"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "Let us plot how good given and predicted values match on the training data set (sic !)."
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 10,
    
       "metadata": {},
       "outputs": [
        {
         "data": {
    
          "image/png": "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\n",
    
          "text/plain": [
           "<Figure size 1152x288 with 3 Axes>"
          ]
         },
         "metadata": {
          "image/png": {
           "height": 269,
           "width": 947
          }
         },
         "output_type": "display_data"
        }
       ],
       "source": [
        "def plot_fit_quality(values_test, predicted):\n",
        "\n",
        "    mi, ma = min(values_test), max(values_test)\n",
        "\n",
        "    plt.figure(figsize=(16, 4))\n",
        "    plt.subplot(1, 3, 1)\n",
        "\n",
        "    sns.scatterplot(values_test, predicted) \n",
        "\n",
        "    plt.plot([mi, ma], [mi, ma], \"k:\")\n",
        "    plt.xlabel(\"measured\")\n",
        "    plt.ylabel(\"predicted\");\n",
        "\n",
        "    plt.subplot(1, 3, 2)\n",
        "\n",
        "    sns.scatterplot(values_test, predicted - values_test) \n",
        "    plt.plot([mi, ma], [0, 0], \"k:\")\n",
        "    plt.xlabel(\"predicted\")\n",
        "    plt.ylabel(\"deviation\");\n",
        "    \n",
        "    plt.subplot(1, 3, 3)\n",
        "\n",
        "    sns.scatterplot(values_test, (predicted - values_test) / values_test) \n",
        "    plt.plot([mi, ma], [0, 0], \"k:\")\n",
        "    plt.xlabel(\"predicted\")\n",
        "    plt.ylabel(\"rel deviation\");\n",
        "    \n",
        "    \n",
        "plot_fit_quality(values_test, predicted)"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "For assessing the quality of the predictions of a regression method, we can use multiple methods which we will discuss later in this script.\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "For our current example we compute the average absolute difference between given values $y_i$ and predicted values  $\\hat{y}_i$:\n",
    
    schmittu's avatar
    schmittu committed
        "\\frac{1}{n} \\left(\\, |y_1 - \\hat{y}_1| \\, + \\, |y_2 - \\hat{y}_2| \\, + \\, \\ldots \\,+ \\,|y_n - \\hat{y}_n| \\,\\right)\n",
    
    schmittu's avatar
    schmittu committed
        "$$\n"
    
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 11,
    
       "metadata": {},
    
       "outputs": [
        {
         "name": "stdout",
         "output_type": "stream",
         "text": [
          "5.26365376785908\n"
         ]
        }
       ],
    
       "source": [
        "import numpy as np\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "error = np.sum(np.abs(predicted - values_test)) / len(values_test)\n",
        "print(error)"
    
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "## Metrics / error measures"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "When we used classification metrics (like accuracy, precision, recall, F1) high values indicated good classification performance. \n",
        "\n",
        "Most regression metrics turn this upside down. E.g. smaller values indicate a better regression model.\n",
        "\n",
        "The hyperparameter optimization functions from `scikit-learn` select configurations which yield a large score. To make regression functions work in this framework, we have to flip the sign of the error value to achieva a usable score.\n",
        "\n",
        "E.g.\n",
        "\n",
        "- an average absolute error of 0.1 is scored as -0.1\n",
        "- an average absolute error of 0.2 is scored as -0.2\n",
        "\n",
        "In this situation the first case would be prefered: higher score indicates lower error.\n",
        "   \n",
        "\n",
        "`scikit-learn` offers the following metrics for measuring regression quality:\n",
        "\n",
        "### 1. Mean absolute error\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "This is the metric we used before. Taking absolute values before adding up the deviatons assures that deviations with different signs can not cancel out.\n",
        "\n",
    
        "<div class=\"alert alert-block alert-warning\">\n",
    
    schmittu's avatar
    schmittu committed
        "    <i class=\"fa fa-info-circle\"></i>&nbsp; <strong>mean absolute error</strong> is defined as \n",
    
    schmittu's avatar
    schmittu committed
        "\n",
    
    schmittu's avatar
    schmittu committed
        "\\frac{1}{n} \\left(\\, |y_1 - \\hat{y}_1| \\, + \\, |y_2 - \\hat{y}_2| \\, + \\, \\ldots \\,+ \\,|y_n - \\hat{y}_n| \\,\\right)\n",
    
    schmittu's avatar
    schmittu committed
        "\n",
        "</div>\n",
        "\n",
        "\n",
    
        "The name of the corresponding score in `scikit-learn` is `neg_mean_absolute_error`.\n",
        "\n",
        "\n",
        "### 2. Mean squared error\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "Here we replace the absolute difference by its squared difference. Squaring also insures positive differeces.\n",
    
    schmittu's avatar
    schmittu committed
        "\n",
    
        "<div class=\"alert alert-block alert-warning\">\n",
    
    schmittu's avatar
    schmittu committed
        "    <i class=\"fa fa-info-circle\"></i>&nbsp; <strong>mean squared error</strong> is defined as \n",
        "\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "\n",
    
    schmittu's avatar
    schmittu committed
        "\\frac{1}{n} \\left(\\, (y_1 - \\hat{y}_1)^2 \\, + \\, (y_2 - \\hat{y}_2)^2 \\, \\, \\ldots \\,+ \\,(y_n - \\hat{y}_n)^2 \\,\\right)\n",
    
    schmittu's avatar
    schmittu committed
        "\n",
        "</div>\n",
        "\n",
        "\n",
        "\n",
    
        "This measure is more sensitive to outliers: A few larger differences contribute more significantly to a larger mean squared error. The name of the corresponding score in `scikit-learn` is `neg_mean_squared_error`.\n",
        "\n",
        "\n",
        "### 3. Median absolute error\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "Here we replace mean calculation by median. \n",
    
        "<div class=\"alert alert-block alert-warning\">\n",
    
    schmittu's avatar
    schmittu committed
        "    <i class=\"fa fa-info-circle\"></i>&nbsp; <strong>median absolute error</strong> is defined as \n",
        "\n",
        "\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "\\text{median}\\left(\\,|y_1 - \\hat{y}_1|, \\,|y_2 - \\hat{y}_2|, \\,\\ldots, \\,|y_n - \\hat{y}_n| \\, \\right)\n",
    
    schmittu's avatar
    schmittu committed
        "\n",
        "</div>\n",
        "\n",
        "\n",
    
        "This measure is less sensitive to outliers than the metrics we discussed before: A few larger differences will not contribute significantly to a larger error value. The name of the corresponding score in `scikit-learn` is `neg_median_absolute_error`.\n",
        "\n",
        "### 4. Mean squared log error\n",
        "\n",
        "The formula for this metric can be found [here](https://scikit-learn.org/stable/modules/model_evaluation.html#mean-squared-log-error). \n",
        "\n",
        "This metric is recommended when your target values are distributed over a huge range of values, like popoluation numbers. \n",
        "The previous error metrics would put a larger weight on large target values. One could consider relative deviations to compensate such effects but relative deviations come with other problems like division by zero.\n",
        "\n",
        "\n",
        "The name is `neg_mean_squared_log_error`\n",
        "\n",
        "\n",
        "### 5. Explained variance and $r^2$-score\n",
        "\n",
        "Two other scores to mention are *explained variance* and $r^2$-score. For both larger values indicate better regression results.\n",
        "\n",
        "The formula for [r2 can be found here](https://scikit-learn.org/stable/modules/model_evaluation.html#r2-score), the score takes values in the range $0 .. 1$. The name within `scikit-learn` is `r2`.\n",
        "\n",
        "The formula for [explained variance](https://scikit-learn.org/stable/modules/model_evaluation.html#explained-variance-score), the score takes values up to $1$. The name within `scikit-learn` is `explained_variance`.\n"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "## Some algorithms from sklearn\n",
        "\n",
        "- `sklearn.linear_model.LinearRegression` is a linear regression method, which only works well for target values which can be described as a linear combination of feature values.\n",
        "\n",
        "\n",
        "- `sklearn.kernel_ridge.KernelRidge` is [documented here](https://scikit-learn.org/stable/modules/kernel_ridge.html#kernel-ridge). It combines the kernel trick from SVMs with classical least squares regression.\n",
        "\n",
        "\n",
        "- `sklearn.svm.SVR` is an extension of support vector classification concept to regression, [you find examples here](https://scikit-learn.org/stable/modules/svm.html#svm-regression)\n",
        "\n",
        "\n",
        "- `sklearn.neighbors.KNeighborsRegressor` extends the idea of nearest neighbour classification to regression: Search for similar data points in the learning data set and compute the predicted value from the values from the neighbourhood, e.g. by averaging or by linear interpolation. [Documentation is available here](https://scikit-learn.org/stable/modules/neighbors.html#regression)\n",
        "\n",
        "\n",
        "- `sklearn.tree.DecisionTreeRegressor` expands the concept of decision trees to regression [is documented here](https://scikit-learn.org/stable/modules/tree.html#regression).\n",
        "\n",
        "\n"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "## A full pipeline\n",
        "\n",
        "Let us now try to find a good regressor using `scikit-learn`s hyper-parameter tuning:"
       ]
      },
      {
       "cell_type": "code",
    
    schmittu's avatar
    schmittu committed
       "execution_count": 12,
    
       "metadata": {},
       "outputs": [
        {
         "name": "stdout",
         "output_type": "stream",
         "text": [
    
          "cross val score: -5.984226118859981\n"
    
          "image/png": "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\n",
    
          "text/plain": [
           "<Figure size 1152x288 with 3 Axes>"
          ]
         },
         "metadata": {
          "image/png": {
    
         },
         "output_type": "display_data"
        }
       ],
       "source": [
        "from sklearn.pipeline import make_pipeline\n",
        "from sklearn.preprocessing import StandardScaler, PolynomialFeatures\n",
        "from sklearn.kernel_ridge import KernelRidge\n",
        "from sklearn.linear_model import LinearRegression\n",
        "from sklearn.model_selection import cross_val_score\n",
        "from sklearn.decomposition import PCA\n",
        "\n",
        "\n",
        "def eval_regression(p):\n",
    
    schmittu's avatar
    schmittu committed
        "    score = cross_val_score(p, features, values, scoring=\"neg_median_absolute_error\", cv=4).mean()\n",
    
        "    print(\"cross val score:\", score)\n",
        "  \n",
        "    predicted = p.fit(features_train, values_train).predict(features_test)\n",
        "    plot_fit_quality(values_test, predicted)\n",
        "\n",
        "    \n",
        "p = make_pipeline(PolynomialFeatures(2), PCA(2), LinearRegression())\n",
        "eval_regression(p)"
       ]
      },
      {
       "cell_type": "code",
    
    schmittu's avatar
    schmittu committed
       "execution_count": 13,
    
       "metadata": {},
       "outputs": [],
       "source": [
        "p = make_pipeline(PolynomialFeatures(), PCA(), LinearRegression())\n",
        "\n",
        "param_grid = {'polynomialfeatures__degree': range(3, 6),\n",
        "              'pca__n_components': range(3, 13),\n",
        "             }"
       ]
      },
      {
       "cell_type": "code",
    
       "execution_count": 14,
    
       "metadata": {},
       "outputs": [
        {
         "name": "stdout",
         "output_type": "stream",
         "text": [
    
    schmittu's avatar
    schmittu committed
          "{'pca__n_components': 12, 'polynomialfeatures__degree': 3}\n",
    
          "cross val score: -2.4152028203917557\n"
    
          "image/png": "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\n",
    
          "text/plain": [
           "<Figure size 1152x288 with 3 Axes>"
          ]
         },
         "metadata": {
          "image/png": {
           "height": 269,
           "width": 947
    
         },
         "output_type": "display_data"
        }
       ],
       "source": [
    
    schmittu's avatar
    schmittu committed
        "from sklearn.model_selection import GridSearchCV\n",
        "\n",
        "search = GridSearchCV(p, param_grid, scoring=\"neg_median_absolute_error\", cv=4, n_jobs=4)\n",
        "\n",
        "search.fit(features, values)\n",
        "\n",
        "\n",
        "print(search.best_params_)\n",
    
        "eval_regression(search)"
       ]
      },
      {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
        "# Exercise section\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "- Play with the examples above and try different algorithms, metrics and pipelines.\n",
    
        "\n",
        "\n",
        "## Optional exercise\n",
        "\n",
    
    schmittu's avatar
    schmittu committed
        "- Split the dataset into one with `kind=\"sockeye\"` and one with `kind=\"atlantic\"` and build individual regression models for both. How does this approach compare to the results we got before ?"
    
       ]
      },
      {
       "cell_type": "code",
    
    schmittu's avatar
    schmittu committed
       "execution_count": 16,
    
    schmittu's avatar
    schmittu committed
       "metadata": {
    
    schmittu's avatar
    schmittu committed
        "scrolled": true,