breast-cancer-detection/neural_network_CM.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/moritzvonsiemens/Library/Python/3.9/lib/python/site-packages/urllib3/__init__.py:35: NotOpenSSLWarning: urllib3 v2 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "import numpy as np \n",
    "import pandas as pd\n",
    "import tensorflow as tf\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Age        BMI  Glucose  Insulin      HOMA   Leptin  Adiponectin  Resistin  \\\n",
      "0   48  23.500000       70    2.707  0.467409   8.8071     9.702400   7.99585   \n",
      "1   83  20.690495       92    3.115  0.706897   8.8438     5.429285   4.06405   \n",
      "2   82  23.124670       91    4.498  1.009651  17.9393    22.432040   9.27715   \n",
      "3   68  21.367521       77    3.226  0.612725   9.8827     7.169560  12.76600   \n",
      "4   86  21.111111       92    3.549  0.805386   6.6994     4.819240  10.57635   \n",
      "\n",
      "     MCP.1  Classification  \n",
      "0  417.114               1  \n",
      "1  468.786               1  \n",
      "2  554.697               1  \n",
      "3  928.220               1  \n",
      "4  773.920               1  \n",
      "              Age         BMI     Glucose     Insulin        HOMA      Leptin  \\\n",
      "count  116.000000  116.000000  116.000000  116.000000  116.000000  116.000000   \n",
      "mean    57.301724   27.582111   97.793103   10.012086    2.694988   26.615080   \n",
      "std     16.112766    5.020136   22.525162   10.067768    3.642043   19.183294   \n",
      "min     24.000000   18.370000   60.000000    2.432000    0.467409    4.311000   \n",
      "25%     45.000000   22.973205   85.750000    4.359250    0.917966   12.313675   \n",
      "50%     56.000000   27.662416   92.000000    5.924500    1.380939   20.271000   \n",
      "75%     71.000000   31.241442  102.000000   11.189250    2.857787   37.378300   \n",
      "max     89.000000   38.578759  201.000000   58.460000   25.050342   90.280000   \n",
      "\n",
      "       Adiponectin    Resistin        MCP.1  Classification  \n",
      "count   116.000000  116.000000   116.000000      116.000000  \n",
      "mean     10.180874   14.725966   534.647000        1.551724  \n",
      "std       6.843341   12.390646   345.912663        0.499475  \n",
      "min       1.656020    3.210000    45.843000        1.000000  \n",
      "25%       5.474283    6.881763   269.978250        1.000000  \n",
      "50%       8.352692   10.827740   471.322500        2.000000  \n",
      "75%      11.815970   17.755207   700.085000        2.000000  \n",
      "max      38.040000   82.100000  1698.440000        2.000000  \n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 116 entries, 0 to 115\n",
      "Data columns (total 10 columns):\n",
      " #   Column          Non-Null Count  Dtype  \n",
      "---  ------          --------------  -----  \n",
      " 0   Age             116 non-null    int64  \n",
      " 1   BMI             116 non-null    float64\n",
      " 2   Glucose         116 non-null    int64  \n",
      " 3   Insulin         116 non-null    float64\n",
      " 4   HOMA            116 non-null    float64\n",
      " 5   Leptin          116 non-null    float64\n",
      " 6   Adiponectin     116 non-null    float64\n",
      " 7   Resistin        116 non-null    float64\n",
      " 8   MCP.1           116 non-null    float64\n",
      " 9   Classification  116 non-null    int64  \n",
      "dtypes: float64(7), int64(3)\n",
      "memory usage: 9.2 KB\n",
      "None\n",
      "Age               0\n",
      "BMI               0\n",
      "Glucose           0\n",
      "Insulin           0\n",
      "HOMA              0\n",
      "Leptin            0\n",
      "Adiponectin       0\n",
      "Resistin          0\n",
      "MCP.1             0\n",
      "Classification    0\n",
      "dtype: int64\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[<Axes: title={'center': 'Age'}>, <Axes: title={'center': 'BMI'}>,\n",
       "        <Axes: title={'center': 'Glucose'}>],\n",
       "       [<Axes: title={'center': 'Insulin'}>,\n",
       "        <Axes: title={'center': 'HOMA'}>,\n",
       "        <Axes: title={'center': 'Leptin'}>],\n",
       "       [<Axes: title={'center': 'Adiponectin'}>,\n",
       "        <Axes: title={'center': 'Resistin'}>,\n",
       "        <Axes: title={'center': 'MCP.1'}>],\n",
       "       [<Axes: title={'center': 'Classification'}>, <Axes: >, <Axes: >]],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzgAAANECAYAAAB8bIo4AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAC7ZUlEQVR4nOzde1wU9f4/8NeiywJyE5RbgpJ6wrsFiqTHvCDkQZPE8tYJzbIMTOR0kUpT0zDPKc1CTDOsE2h5v182VPxaiEpZ2YWkMC0FM+MiyLqxn98f/pjjyoIsLOzs8Ho+HvuA+czszPvz2d3Pzntn5jMqIYQAERERERGRAthZOwAiIiIiIiJLYYJDRERERESKwQSHiIiIiIgUgwkOEREREREpBhMcIiIiIiJSDCY4RERERESkGExwiIiIiIhIMZjgEBERERGRYjDBISIiIiIixWCCQ0RERESyN3/+fKhUKmuHQTaACQ7VsHLlSqhUKoSGhlo7FCJSiHXr1kGlUhk9vLy8MHToUOzdu9do2er5jz/+uMl1vfTSS9Iyly9flsqnTJkCZ2fnJq0HEVleQUEB4uPj8be//Q1OTk5wcnJC9+7dERcXh6+//tra4ZENam3tAEh+0tPT0alTJxw/fhz5+fno0qWLtUMiIoVYuHAhAgMDIYRAUVER1q1bh3/84x/YuXMnRo0aJS3n4OCAzZs3Y+XKlbC3tzdax/r16+Hg4IDKysrmDp+ILGzXrl0YP348WrdujcmTJ6NPnz6ws7PDDz/8gC1btiA1NRUFBQXo2LGjtUMlG8IEh4wUFBTg888/x5YtW/Dkk08iPT0dr7zyirXDIiKFGDlyJEJCQqTpadOmwdvbG+vXrzdKcO6//37s2LEDe/fuxZgxY6Tyzz//HAUFBYiJicHmzZubNXYisqyffvoJEyZMQMeOHZGZmQlfX1+j+a+//jpWrlwJOzuecETm4TuGjKSnp6Nt27aIiorCuHHjkJ6eXmOZP/74A//85z/h6uoKd3d3xMbG4quvvoJKpcK6deuMlv3hhx8wbtw4eHh4wMHBASEhIdixY0cz1YaI5M7d3R2Ojo5o3dr497Y77rgDgwcPRkZGhlF5eno6evXqhZ49ezZnmETUBJYuXYry8nKkpaXVSG4AoHXr1njmmWfg7+9v8vlnz541ue8B3DjVdf78+UZlv/32G6ZNmwY/Pz9oNBoEBgZixowZuH79urTMzz//jIceeggeHh5wcnLCgAEDsHv37hrrf/vtt9GjRw84OTmhbdu2CAkJqdFf/fbbb3jsscfg7e0NjUaDHj164P33369Hy1Bj8QgOGUlPT8fYsWNhb2+PiRMnIjU1FSdOnEC/fv0AAAaDAaNHj8bx48cxY8YMBAUFYfv27YiNja2xrm+//RYDBw7EHXfcgTlz5qBNmzb45JNPEB0djc2bN+PBBx9s7uoRkZWVlJTg8uXLEELg0qVLePvtt3H16lU88sgjNZadNGkSZs2ahatXr8LZ2Rl//fUXNm7ciMTERJ6eRqQAu3btQpcuXZrlmt8LFy6gf//+KC4uxvTp0xEUFITffvsNmzZtQkVFBezt7VFUVIR7770XFRUVeOaZZ+Dp6YkPPvgADzzwADZt2iTtt6xZswbPPPMMxo0bh1mzZqGyshJff/01cnJyMGnSJABAUVERBgwYAJVKhfj4eLRv3x579+7FtGnTUFpaioSEhCavc4smiP6/kydPCgBCq9UKIYQwGAyiQ4cOYtasWdIymzdvFgDE8uXLpbKqqioxbNgwAUCkpaVJ5cOHDxe9evUSlZWVUpnBYBD33nuv6Nq1a5PXh4jkIy0tTQCo8dBoNGLdunVGywIQcXFx4sqVK8Le3l7897//FUIIsXv3bqFSqcTZs2fFK6+8IgCI33//XXpebGysaNOmTbPWi4gapqSkRAAQ0dHRNeb9+eef4vfff5ceFRUVQgghfe6rFRQU1Nj3qAZAvPLKK9L0o48+Kuzs7MSJEydqLGswGIQQQiQkJAgA4v/+7/+keWVlZSIwMFB06tRJVFVVCSGEGDNmjOjRo0ed9Zs2bZrw9fUVly9fNiqfMGGCcHNzk+pETYOnqJEkPT0d3t7eGDp0KIAbh3fHjx+PDRs2oKqqCgCwb98+qNVqPPHEE9Lz7OzsEBcXZ7SuK1eu4ODBg3j44YdRVlaGy5cv4/Lly/jjjz8QGRmJM2fO4Lfffmu+yhGRLKSkpECr1UKr1eKjjz7C0KFD8fjjj2PLli01lm3bti3uv/9+rF+/HgCQkZGBe++9lxcbEylAaWkpAJgc+XDIkCFo37699EhJSWnUtgwGA7Zt24bRo0cbXQNYrXro6T179qB///4YNGiQNM/Z2RnTp0/H2bNn8d133wG4cWrtr7/+ihMnTpjcnhACmzdvxujRoyGEkPaBLl++jMjISJSUlOCLL75oVJ2obkxwCABQVVWFDRs2YOjQoSgoKEB+fj7y8/MRGhqKoqIiZGZmAgB++eUX+Pr6wsnJyej5t460lp+fDyEE5s6da9RJtW/fXhq04NKlS81TOSKSjf79+yM8PBzh4eGYPHkydu/eje7duyM+Pt7oPPhqkyZNglarxblz57Bt2zbp9A8ism0uLi4AgKtXr9aY9+6770o/gljC77//jtLS0tteu/fLL7/grrvuqlHerVs3aT4AvPDCC3B2dkb//v3RtWtXxMXF4bPPPjPaXnFxMVavXl1jH2jq1KkAuA/U1HgNDgEADh48iIsXL2LDhg3YsGFDjfnp6emIiIio9/oMBgMA4Nlnn0VkZKTJZTj8NBHZ2dlh6NCheOutt3DmzBn06NHDaP4DDzwAjUaD2NhY6HQ6PPzww1aKlIgsyc3NDb6+vjh9+nSNedXX5Jw9e7bOddR208/qs06aSrdu3ZCXl4ddu3Zh37590pD28+bNw4IFC6R9oEceecTkNcoA0Lt37yaNsaVjgkMAbiQwXl5eJg8Db9myBVu3bsWqVavQsWNHHDp0CBUVFUZHcfLz842ec+eddwIA1Go1wsPDmzZ4IrJpf/31FwDTv+Q6OjoiOjoaH330EUaOHIl27do1d3hE1ESioqLw3nvv4fjx4+jfv7/Zz2/bti0AoLi42Ki8+khLtfbt28PV1dVkMnWzjh07Ii8vr0b5Dz/8IM2v1qZNG4wfPx7jx4/H9evXMXbsWCxevBhJSUlo3749XFxcUFVVxX0gK+EpaoRr165hy5YtGDVqFMaNG1fjER8fj7KyMuzYsQORkZHQ6/VYs2aN9HyDwVAjMfLy8sKQIUPw7rvv4uLFizW2+fvvvzd5vYhI/vR6PQ4cOAB7e3vpNJBbPfvss3jllVcwd+7cZo6OiJrS888/DycnJzz22GMoKiqqMV8IUefzXV1d0a5dOxw5csSofOXKlUbTdnZ2iI6Oxs6dO3Hy5Mlat/OPf/wDx48fR3Z2tjSvvLwcq1evRqdOndC9e3cAN26XcTN7e3t0794dQgjo9Xq0atVKuleXqaSK+0BNj0dwCDt27EBZWRkeeOABk/MHDBiA9u3bIz09HVu3bkX//v3xr3/9C/n5+QgKCsKOHTtw5coVAMaHi1NSUjBo0CD06tULTzzxBO68804UFRUhOzsbv/76K7766qtmqR8RycfevXulX0MvXbqEjIwMnDlzBnPmzIGrq6vJ5/Tp0wd9+vRpzjCJqBl07doVGRkZmDhxIu666y5MnjwZffr0gRACBQUFyMjIgJ2dHTp06FDrOh5//HEsWbIEjz/+OEJCQnDkyBH8+OOPNZZ77bXXcODAAdx3332YPn06unXrhosXL2Ljxo04evQo3N3dMWfOHKxfvx4jR47EM888Aw8PD3zwwQcoKCjA5s2bpRuORkREwMfHBwMHDoS3tze+//57vPPOO4iKipKuLVqyZAkOHTqE0NBQPPHEE+jevTuuXLmCL774Ap9++qm030RNxIojuJFMjB49Wjg4OIjy8vJal5kyZYpQq9Xi8uXL4vfffxeTJk0SLi4uws3NTUyZMkV89tlnAoDYsGGD0fN++ukn8eijjwofHx+hVqvFHXfcIUaNGiU2bdrU1NUiIhkxNUy0g4OD6Nu3r0hNTZWGaRXif8NE14XDRBMpR35+vpgxY4bo0qWLcHBwEI6OjiIoKEg89dRT4tSpU9Jytw4TLYQQFRUVYtq0acLNzU24uLiIhx9+WFy6dKnGMNFCCPHLL7+IRx99VLRv315oNBpx5513iri4OKHT6aRlfvrpJzFu3Djh7u4uHBwcRP/+/cWuXbuM1vPuu++KwYMHC09PT6HRaETnzp3Fc889J0pKSoyWKyoqEnFxccLf31+o1Wrh4+Mjhg8fLlavXm2hlqPaqIS4zfE/onrYtm0bHnzwQRw9ehQDBw60djhERERE1EIxwSGzXbt2DY6OjtJ0VVUVIiIicPLkSRQWFhrNIyIiIiJqTrwGh8w2c+ZMXLt2DWFhYdDpdNiyZQs+//xzvPbaa0xuiIiIiMiqeASHzJaRkYE33ngD+fn5qKysRJcuXTBjxgzEx8dbOzQiIiIiauGY4BARERERkWLwPjhERERERKQYTHCIiIiIiEgxZDfIgMFgwIULF+Di4mJ000giajwhBMrKyuDn5yfdsKwlYf9C1DRaet8CsH8haioN6V9kl+BcuHAB/v7+1g6DSNHOnz9f552hlYr9C1HTaql9C8D+haipmdO/yC7BcXFxAXCjEq6urlaOpuno9XocOHAAERERUKvV1g6nWbS0OsuxvqWlpfD395c+Zy1Nc/UvcnztzWHr8QO2Xwdbi7+l9y1Ay9l/qYutvW+bC9ulJnPapCH9i+wSnOrDuq6uroruIPR6PZycnODq6tpi3uwtrc5yrm9LPX2iufoXOb/29WHr8QO2Xwdbjb+l9i1Ay9l/qYutvm+bGtulpoa0iTn9S8s8UZaIiIiIiBSJCQ4RERERESkGExwiIiIiIlIMJjhERERERKQYTHCIiIiIiEgxZDeKGpnWac5ui63r7JIoi62LiOhmluyrAPZXRM2tMZ9hTSuBpf2BnvP3Q1d1Y8QrfobJGngEh4iIiIiIFIMJDhERERERKQYTHCIiIiIiUgwmOEREREREpBhMcIiIiIiISDGY4BARERERkWIwwSEiIiIiIsXgfXCIiKhF4D16iIhaBh7BISIiIiIixWCCQ0REREREisEEh4iIiIiIFIMJDhERERERKQYTHCIiIiIiUgwmOEREREREpBhMcIiIiIiISDF4HxwiomZg6XuwWBLv50JERErCIzhERERERKQYTHCIiIiIiEgxmOAQEREREZFimJXgJCcno1+/fnBxcYGXlxeio6ORl5dntExlZSXi4uLg6ekJZ2dnxMTEoKioyKJBExERETXUkiVLoFKpkJCQIJVx/4VIOcxKcLKyshAXF4djx45Bq9VCr9cjIiIC5eXl0jKzZ8/Gzp07sXHjRmRlZeHChQsYO3asxQMnIiIiMteJEyfw7rvvonfv3kbl3H8hUg6zRlHbt2+f0fS6devg5eWF3NxcDB48GCUlJVi7di0yMjIwbNgwAEBaWhq6deuGY8eOYcCAAZaLnIiIiMgMV69exeTJk7FmzRosWrRIKuf+C5GyNGqY6JKSEgCAh4cHACA3Nxd6vR7h4eHSMkFBQQgICEB2djY7CCIiMktDh9fWtBJY2h/oOX8/dFUqC0dFtiouLg5RUVEIDw83SnC4/0KkLA1OcAwGAxISEjBw4ED07NkTAFBYWAh7e3u4u7sbLevt7Y3CwkKT69HpdNDpdNJ0aWkpAECv10Ov1zc0PNmrrlt966hpJSy+7eZmbp1tnRzrK6dYiIia04YNG/DFF1/gxIkTNeZx/+V/GrO/obETRn8Bfu8A8twfsDZz2qQh7dbgBCcuLg6nT5/G0aNHG7oKADcGLliwYEGN8gMHDsDJyalR67YFWq22Xsst7W+5be7Zs8dyK2uA+tZZKeRU34qKCmuHQETU7M6fP49Zs2ZBq9XCwcHBIutU6v6LJfY3Xg0xSP9be59DTuS0PyAX9WmThuy7NCjBiY+Px65du3DkyBF06NBBKvfx8cH169dRXFxs9CtIUVERfHx8TK4rKSkJiYmJ0nRpaSn8/f0REREBV1fXhoRnE/R6PbRaLUaMGAG1Wn3b5XvO32+xbZ+eH2mxdZnD3DrbOjnWt/oXRiKiliQ3NxeXLl3CPffcI5VVVVXhyJEjeOedd7B//37uv/x/jdnf0NgJvBpiwNyTdtAZbpwaaq19DjmR4/6AtZnTJg3ZdzErwRFCYObMmdi6dSsOHz6MwMBAo/nBwcFQq9XIzMxETEwMACAvLw/nzp1DWFiYyXVqNBpoNJoa5Wq1ukW8CepbT0ueQ27tdm0pr201OdVXLnGYcuTIEfz73/9Gbm4uLl68iK1btyI6OlqaP2XKFHzwwQdGz4mMjKwx+AkR0a2GDx+Ob775xqhs6tSpCAoKwgsvvAB/f3/uv/x/ltjf0BlU0npsuS0szdbfG02hPm3SkDYzK8GJi4tDRkYGtm/fDhcXF+m8VDc3Nzg6OsLNzQ3Tpk1DYmIiPDw84OrqipkzZyIsLIwX6BFRncrLy9GnTx889thjtQ7Nev/99yMtLU2aNrVzQUR0KxcXF+l64Wpt2rSBp6enVM79FyLlMCvBSU1NBQAMGTLEqDwtLQ1TpkwBACxbtgx2dnaIiYmBTqdDZGQkVq5caZFgiUi5Ro4ciZEjR9a5jEajqfV0ESKixuD+C5FymH2K2u04ODggJSUFKSkpDQ6KiMiUw4cPw8vLC23btsWwYcOwaNEieHp61rq8tUY5MjU6jCVHQrS0W9uiMSP+yKWepkZzsrTmfg/Jma3EebPDhw8bTXP/hUg5GnUfHKKm0ND7XphydkmUxdZF1nX//fdj7NixCAwMxE8//YQXX3wRI0eORHZ2Nlq1amXyOdYe5ejm0WEsORKipdU2ylFDRvyRWz1vHs3J0ppjdChbGXWJIzQSkZwwwSEimzBhwgTp/169eqF3797o3LkzDh8+jOHDh5t8jrVGOTI1OowlR0K0tFtHOWrMiD9yqaep0ZwsrSlHh7K1UZc4QiMRyQkTHCKySXfeeSfatWuH/Pz8WhMca49ydPN2LDkSoqXV1hYNaSe51fPm0ZwsrbnfQ3JmCzESUcthZ+0AiIga4tdff8Uff/wBX19fa4dCREREMsIjOEQkC1evXkV+fr40XVBQgFOnTsHDwwMeHh5YsGABYmJi4OPjg59++gnPP/88unTpgshI3kSOiIiI/ocJDhHJwsmTJzF06FBpuvramdjYWKSmpuLrr7/GBx98gOLiYvj5+SEiIgKvvvoq74VDRERERpjgEJEsDBkypM6h6Pfvl8fF60REcmLJkUeJlILX4BARERERkWIwwSEiIiIiIsVggkNERERERIrBBIeIiIiIiBSDCQ4RERERESkGExwiIiIiIlIMJjhERERERKQYTHCIiIiIiEgxmOAQEREREZFiMMEhIiIiIiLFYIJDRERERESKwQSHiIiIiIgUgwkOEREREREpBhMcIiIiIiJSDCY4RERERESkGExwiIiIiIhIMZjgEBERERGRYjDBISIiIiIixWCCQ0REREREisEEh4iIiIiIFIMJDhERERERKQYTHCIiIiIiUgwmOEREREREpBhMcIiIiIiISDGY4BARERERkWIwwSEiIiIiIsVggkNERERERIrBBIeIiIiIiBSDCQ4RycKRI0cwevRo+Pn5QaVSYdu2bUbzhRCYN28efH194ejoiPDwcJw5c8Y6wRIREZFsMcEhIlkoLy9Hnz59kJKSYnL+0qVLsWLFCqxatQo5OTlo06YNIiMjUVlZ2cyREhERkZy1tnYARE2p05zdFl3f2SVRFl0f/c/IkSMxcuRIk/OEEFi+fDlefvlljBkzBgDw4YcfwtvbG9u2bcOECROaM1QiIiKSMR7BISLZKygoQGFhIcLDw6UyNzc3hIaGIjs724qRERERkdzwCA4RyV5hYSEAwNvb26jc29tbmmeKTqeDTqeTpktLSwEAer0eer2+CSKFtP6b/wKAppVosu011q1tYSr++pJLPTV2wuhvU2ju95Cc2UqcRNQyMMEhIsVKTk7GggULapQfOHAATk5OTb59rVYr/b+0f5NvrsH27Nljsvzm+OtLbvV8NcTQZOuurd0sqSGvgTVUVFRYOwQiIgkTHCKSPR8fHwBAUVERfH19pfKioiL07du31uclJSUhMTFRmi4tLYW/vz8iIiLg6uraZPHq9XpotVqMGDECarUaANBz/v4m215jnZ4faTRtKv76kks9NXYCr4YYMPekHXQGVZNs49Z2s6TGvAbWUH10lIhIDpjgEJHsBQYGwsfHB5mZmVJCU1paipycHMyYMaPW52k0Gmg0mhrlarW6WXYab96OrqppdrItoba2aEg7ya2eOoOqyWJq7veQnNlCjETUcjDBISJZuHr1KvLz86XpgoICnDp1Ch4eHggICEBCQgIWLVqErl27IjAwEHPnzoWfnx+io6OtFzQRERHJDhMcIpKFkydPYujQodJ09allsbGxWLduHZ5//nmUl5dj+vTpKC4uxqBBg7Bv3z44ODhYK2QiIiKSISY4RCQLQ4YMgRC1j3ilUqmwcOFCLFy4sBmjIiIiIlvD++AQEREREZFiMMEhIiIiIiLF4ClqREREMtBpzm7pf00rgaX9bwy73ZBR4M4uibJkaERENoVHcIiIiIiISDF4BKcFuvlXQkvgL4VEREREJBc8gkNERERERIphdoJz5MgRjB49Gn5+flCpVNi2bZvRfCEE5s2bB19fXzg6OiI8PBxnzpyxVLxEREREZklOTka/fv3g4uICLy8vREdHIy8vz2iZyspKxMXFwdPTE87OzoiJiUFRUZGVIiaixjA7wSkvL0efPn2QkpJicv7SpUuxYsUKrFq1Cjk5OWjTpg0iIyNRWVnZ6GCJiIiIzJWVlYW4uDgcO3YMWq0Wer0eERERKC8vl5aZPXs2du7ciY0bNyIrKwsXLlzA2LFjrRg1ETWU2dfgjBw5EiNHjjQ5TwiB5cuX4+WXX8aYMWMAAB9++CG8vb2xbds2TJgwoXHREhEREZlp3759RtPr1q2Dl5cXcnNzMXjwYJSUlGDt2rXIyMjAsGHDAABpaWno1q0bjh07hgEDBlgjbCJqIIsOMlBQUIDCwkKEh4dLZW5ubggNDUV2drbJBEen00Gn00nTpaWlAAC9Xg+9Xm/J8GSlum71raOmVe13eLe2+tahvnVWQl1vXlZO72M5xUJEZC0lJSUAAA8PDwBAbm4u9Hq90f5LUFAQAgICkJ2dbTLBkcv+i5y+MzV2wugvwO8dQJ77A9ZmTps0pN0smuAUFhYCALy9vY3Kvb29pXm3Sk5OxoIFC2qUHzhwAE5OTpYMT5a0Wm29llvav4kDaYQ9e/aYtfzt6qykugL1f42bQ0VFhbVDICKyKoPBgISEBAwcOBA9e/YEcGP/xd7eHu7u7kbL2sL+ixy/M18NMUj/N+R7U6nktD8gF/Vpk4bsu1h9mOikpCQkJiZK06WlpfD390dERARcXV2tGFnj9Jy/v875GjuBV0MMmHvSDjqD+Tdxk5PT8yPrtZxer4dWq8WIESOgVqtrXe52bWcrbvca17fdLKn6F0YiopYqLi4Op0+fxtGjRxu1Hrnsv8jpO9PU9541vuvkpr77Py2JOW3SkH0XiyY4Pj4+AICioiL4+vpK5UVFRejbt6/J52g0Gmg0mhrlarXapt8E9b3ztM6gatBdquXE3Nfpdq+trbfHrWp7ja3x/rblzxQRUWPFx8dj165dOHLkCDp06CCV+/j44Pr16yguLjY6ilNUVCTt29xKLvsvcvzOvPl7j987/2Pr+7ZNoT5t0pA2s+h9cAIDA+Hj44PMzEyprLS0FDk5OQgLC7PkpoiIiIjqRQiB+Ph4bN26FQcPHkRgYKDR/ODgYKjVaqP9l7y8PJw7d477L0Q2yOwjOFevXkV+fr40XVBQgFOnTsHDwwMBAQFISEjAokWL0LVrVwQGBmLu3Lnw8/NDdHS0JeMmIiIiqpe4uDhkZGRg+/btcHFxka6rcXNzg6OjI9zc3DBt2jQkJibCw8MDrq6umDlzJsLCwjiCGpENMjvBOXnyJIYOHSpNV59/Ghsbi3Xr1uH5559HeXk5pk+fjuLiYgwaNAj79u2Dg4OD5aImIiIiqqfU1FQAwJAhQ4zK09LSMGXKFADAsmXLYGdnh5iYGOh0OkRGRmLlypXNHCkRWYLZCc6QIUMgRO1DEqpUKixcuBALFy5sVGBkOzrN2V2v5TStBJb2v3FBpBzPGSYiImWqa7+lmoODA1JSUmq9kTkR2Q6rj6JGRETWdeuPFPwxgoiIbJlFBxkgIiIiIiKyJiY4RERERESkGExwiIiIiIhIMZjgEBERERGRYjDBISIiIiIixeAoajep73DHREREREQkTzyCQ0REREREisEEh4iIiIiIFIOnqBERERFRk7Dk6f9nl0RZbF2kbDyCQ0REREREisEEh4iIiIiIFIOnqBFZiaVH7WsJh+7nz5+PBQsWGJXddddd+OGHH6wUEREREckNExwisik9evTAp59+Kk23bs1ujIiIiP6HewZEZFNat24NHx8fa4dBREREMsUEh4hsypkzZ+Dn5wcHBweEhYUhOTkZAQEBJpfV6XTQ6XTSdGlpKQBAr9dDr9c3WYzV6755G5pWosm2Z2kaO2H01xY1Rx0s/R66+T3S2Pib8v0th+0REdWFCQ4R2YzQ0FCsW7cOd911Fy5evIgFCxbg73//O06fPg0XF5cayycnJ9e4ZgcADhw4ACcnpyaPV6vVSv8v7d/km7O4V0MM1g6h0ZqyDnv27LHo+ky9Rxoav6Vju52Kiopm3R4RUV2Y4BCRzRg5cqT0f+/evREaGoqOHTvik08+wbRp02osn5SUhMTERGm6tLQU/v7+iIiIgKura53b6jl/f4Pj1NgJvBpiwNyTdtAZVA1ej7XYevxA89Th9PxIi67v5vdcY+O3dGy3U310lIhIDpjgEJHNcnd3x9/+9jfk5+ebnK/RaKDRaGqUq9VqqNXqOtetq2r8TrHOoLLIeqzF1uMHmrYOt3sPmctUnA2N39KxyW17RER14X1wiMhmXb16FT/99BN8fX2tHQoRERHJBBMcIrIZzz77LLKysnD27Fl8/vnnePDBB9GqVStMnDjR2qERERGRTPAUNSKyGb/++ismTpyIP/74A+3bt8egQYNw7NgxtG/f3tqhERERkUwwwSEim7FhwwZrh0BEREQyx1PUiIiIiIhIMWz6CE6nObutHQIREbVQcv4OsnRsZ5dEWXR9RERNiUdwiIiIiIhIMZjgEBERERGRYjDBISIiIiIixWCCQ0REREREisEEh4iIiIiIFIMJDhERERERKQYTHCIiIiIiUgwmOEREREREpBhMcIiIiIiISDGY4BARERERkWIwwSEiIiIiIsVggkNERERERIrR2toBEBERERE1t05zdltsXWeXRFlsXdR4PIJDRERERESKwQSHiIiIiIgUgwkOEREREREpBhMcIiIiIiJSDCY4RERERESkGBxFjYiIiKgZWXL0LiKqiUdwiIiIiIhIMZjgEBERERGRYvAUNSIiIiKSPZ7aJw+WeB00rQSW9gd6zt+PvMWjLBCVMR7BISIiIiIixWCCQ0REREREisEEh4iIiIiIFIMJDhERERERKUaTJTgpKSno1KkTHBwcEBoaiuPHjzfVpoiohWH/QkRNgX0LkTI0yShqH3/8MRITE7Fq1SqEhoZi+fLliIyMRF5eHry8vJpik0TUQrB/IaKmwL6FGqOukcVuHjFMV6Wq1/rOLomyVGgtUpMcwXnzzTfxxBNPYOrUqejevTtWrVoFJycnvP/++02xOSJqQdi/EFFTYN9CpBwWP4Jz/fp15ObmIikpSSqzs7NDeHg4srOzayyv0+mg0+mk6ZKSEgDAlStXoNfr69xW67/KLRR182ttEKioMKC13g5Vhvpl87aupdW5uev7xx9/3HaZsrIyAIAQoqnDaRK20r/Y+nvd1uMHbL8Ocov/dv1LS+tbgJa7/1IXub1v5aIh7VKf73RrscT79+Y2aZL+RVjYb7/9JgCIzz//3Kj8ueeeE/3796+x/CuvvCIA8MEHH834OH/+vKU/+s2C/QsffMj70VL6FiHYv/DBR3M/zOlfmuQaHHMkJSUhMTFRmjYYDLhy5Qo8PT2hUik3+y8tLYW/vz/Onz8PV1dXa4fTLFpaneVYXyEEysrK4OfnZ+1QmoW1+hc5vvbmsPX4Aduvg63F39L6FqDl7r/Uxdbet82F7VKTOW3SkP7F4glOu3bt0KpVKxQVFRmVFxUVwcfHp8byGo0GGo3GqMzd3d3SYcmWq6tri3uzt7Q6y62+bm5u1g6hwWytf5Hba28uW48fsP062FL8LalvAazfv8iZLb1vmxPbpab6tom5/YvFBxmwt7dHcHAwMjMzpTKDwYDMzEyEhYVZenNE1IKwfyGipsC+hUhZmuQUtcTERMTGxiIkJAT9+/fH8uXLUV5ejqlTpzbF5oioBWH/QkRNgX0LkXI0SYIzfvx4/P7775g3bx4KCwvRt29f7Nu3D97e3k2xOZuk0Wjwyiuv1Di8rWQtrc4trb7NxRb6F1t/7W09fsD262Dr8dsiW+hb5I7vW9PYLjU1dZuohLDRMR2JiIiIiIhu0SQ3+iQiIiIiIrIGJjhERERERKQYTHCIiIiIiEgxmOAQEREREZFiMMFpRkuWLIFKpUJCQoJUVllZibi4OHh6esLZ2RkxMTE1bjRma3777Tc88sgj8PT0hKOjI3r16oWTJ09K84UQmDdvHnx9feHo6Ijw8HCcOXPGihE3XFVVFebOnYvAwEA4Ojqic+fOePXVV3Hz2B1Kqi/9T3JyMvr16wcXFxd4eXkhOjoaeXl5RsvI+fNdn/iHDBkClUpl9HjqqaesFHFNqamp6N27t3SjuLCwMOzdu1eaL+f2B24fv9zbn1qOI0eOYPTo0fDz84NKpcK2bduM5tfne+7KlSuYPHkyXF1d4e7ujmnTpuHq1avNWAvLul2bTJkypcbn9/777zdaRmltYqnvxXPnziEqKgpOTk7w8vLCc889h7/++susWJjgNJMTJ07g3XffRe/evY3KZ8+ejZ07d2Ljxo3IysrChQsXMHbsWCtF2Xh//vknBg4cCLVajb179+K7777DG2+8gbZt20rLLF26FCtWrMCqVauQk5ODNm3aIDIyEpWVlVaMvGFef/11pKam4p133sH333+P119/HUuXLsXbb78tLaOk+tL/ZGVlIS4uDseOHYNWq4Ver0dERATKy8ulZeT8+a5P/ADwxBNP4OLFi9Jj6dKlVoq4pg4dOmDJkiXIzc3FyZMnMWzYMIwZMwbffvstAHm3P3D7+AF5tz+1HOXl5ejTpw9SUlJMzq/P99zkyZPx7bffQqvVYteuXThy5AimT5/eXFWwuNu1CQDcf//9Rp/f9evXG81XWptY4nuxqqoKUVFRuH79Oj7//HN88MEHWLduHebNm2deMIKaXFlZmejatavQarXivvvuE7NmzRJCCFFcXCzUarXYuHGjtOz3338vAIjs7GwrRds4L7zwghg0aFCt8w0Gg/Dx8RH//ve/pbLi4mKh0WjE+vXrmyNEi4qKihKPPfaYUdnYsWPF5MmThRDKqy/V7tKlSwKAyMrKEkLY3uf71viFEEb9la1o27ateO+992yu/atVxy+EbbY/KR8AsXXrVmm6Pt9z3333nQAgTpw4IS2zd+9eoVKpxG+//dZssTeVW9tECCFiY2PFmDFjan2O0ttEiIZ9L+7Zs0fY2dmJwsJCaZnU1FTh6uoqdDpdvbfNIzjNIC4uDlFRUQgPDzcqz83NhV6vNyoPCgpCQEAAsrOzmztMi9ixYwdCQkLw0EMPwcvLC3fffTfWrFkjzS8oKEBhYaFRnd3c3BAaGmqTdb733nuRmZmJH3/8EQDw1Vdf4ejRoxg5ciQA5dWXaldSUgIA8PDwAGB7n+9b46+Wnp6Odu3aoWfPnkhKSkJFRYU1wrutqqoqbNiwAeXl5QgLC7O59r81/mq20v7UctXney47Oxvu7u4ICQmRlgkPD4ednR1ycnKaPebmcvjwYXh5eeGuu+7CjBkz8Mcff0jzWkKbNOR7MTs7G7169TK6wW5kZCRKS0uNjm7fTmtLVIBqt2HDBnzxxRc4ceJEjXmFhYWwt7eHu7u7Ubm3tzcKCwubKULL+vnnn5GamorExES8+OKLOHHiBJ555hnY29sjNjZWqtetd4a21TrPmTMHpaWlCAoKQqtWrVBVVYXFixdj8uTJAKC4+pJpBoMBCQkJGDhwIHr27AnAtj7fpuIHgEmTJqFjx47w8/PD119/jRdeeAF5eXnYsmWLFaM19s033yAsLAyVlZVwdnbG1q1b0b17d5w6dcom2r+2+AHbaH+i+nzPFRYWwsvLy2h+69at4eHhIavPoyXdf//9GDt2LAIDA/HTTz/hxRdfxMiRI5GdnY1WrVopvk0a+r1YWFho8r1UPa++mOA0ofPnz2PWrFnQarVwcHCwdjjNwmAwICQkBK+99hoA4O6778bp06exatUqxMbGWjk6y/vkk0+Qnp6OjIwM9OjRA6dOnUJCQgL8/PwUWV8yLS4uDqdPn8bRo0etHUqD1Bb/zeeC9+rVC76+vhg+fDh++ukndO7cubnDNOmuu+7CqVOnUFJSgk2bNiE2NhZZWVnWDqveaou/e/fuNtH+RGTahAkTpP979eqF3r17o3Pnzjh8+DCGDx9uxciah7W/F3mKWhPKzc3FpUuXcM8996B169Zo3bo1srKysGLFCrRu3Rre3t64fv06iouLjZ5XVFQEHx8f6wTdSL6+vtKvj9W6deuGc+fOAYBUr1tHzLDVOj/33HOYM2cOJkyYgF69euGf//wnZs+ejeTkZADKqy/VFB8fj127duHQoUPo0KGDVO7j42MTn+/a4jclNDQUAJCfn98codWLvb09unTpguDgYCQnJ6NPnz546623bKb9a4vfFDm2P1F9vud8fHxw6dIlo/l//fUXrly5IqvPY1O688470a5dO+nzq+Q2acz3oo+Pj8n3UvW8+mKC04SGDx+Ob775BqdOnZIeISEhmDx5svS/Wq1GZmam9Jy8vDycO3fO6BxsWzJw4MAaQwL++OOP6NixIwAgMDAQPj4+RnUuLS1FTk6OTda5oqICdnbGH6NWrVrBYDAAUF596X+EEIiPj8fWrVtx8OBBBAYGGs0PDg6W9ef7dvGbcurUKQA3fsiQK4PBAJ1OJ/v2r011/KbYQvtTy1Of77mwsDAUFxcjNzdXWubgwYMwGAxS4q50v/76K/744w/p86vENrHE92JYWBi++eYbo+RPq9XC1dW1xg/otwuGmtGto+I89dRTIiAgQBw8eFCcPHlShIWFibCwMOsF2EjHjx8XrVu3FosXLxZnzpwR6enpwsnJSXz00UfSMkuWLBHu7u5i+/bt4uuvvxZjxowRgYGB4tq1a1aMvGFiY2PFHXfcIXbt2iUKCgrEli1bRLt27cTzzz8vLaOk+tL/zJgxQ7i5uYnDhw+LixcvSo+KigppGTl/vm8Xf35+vli4cKE4efKkKCgoENu3bxd33nmnGDx4sJUj/585c+aIrKwsUVBQIL7++msxZ84coVKpxIEDB4QQ8m5/IeqO3xban1qOsrIy8eWXX4ovv/xSABBvvvmm+PLLL8Uvv/wihKjf99z9998v7r77bpGTkyOOHj0qunbtKiZOnGitKjVaXW1SVlYmnn32WZGdnS0KCgrEp59+Ku655x7RtWtXUVlZKa1DaW1iie/Fv/76S/Ts2VNERESIU6dOiX379on27duLpKQks2JhgtPMbk1wrl27Jp5++mnRtm1b4eTkJB588EFx8eJF6wVoATt37hQ9e/YUGo1GBAUFidWrVxvNNxgMYu7cucLb21toNBoxfPhwkZeXZ6VoG6e0tFTMmjVLBAQECAcHB3HnnXeKl156yWgoQyXVl/4HgMlHWlqatIycP9+3i//cuXNi8ODBwsPDQ2g0GtGlSxfx3HPPiZKSEusGfpPHHntMdOzYUdjb24v27duL4cOHS8mNEPJufyHqjt8W2p9ajkOHDpnsL2JjY4UQ9fue++OPP8TEiROFs7OzcHV1FVOnThVlZWVWqI1l1NUmFRUVIiIiQrRv316o1WrRsWNH8cQTTxgNfSyE8trEUt+LZ8+eFSNHjhSOjo6iXbt24l//+pfQ6/VmxaL6/wERERERERHZPF6DQ0REREREisEEh4iIiIiIFIMJDhERERERKQYTHGpyQ4YMwZAhQ6Tps2fPQqVSYd26dVaLiYiIiKi+uO9iW5jgKNi6deugUqlw8uRJa4dCRAp1u35myJAh6Nmzp1GZXq/HihUr0K9fP7i4uMDZ2Rn9+vXDihUroNfra6yjU6dOUKlUCA8PN7mNNWvWQKVS1RnH888/D5VKhfHjx5tZQyKyFmvsx2RkZGD58uXNtj1qGq2tHQC1PB07dsS1a9egVqutHQoRNbPy8nJERUUhKysLo0aNwpQpU2BnZ4d9+/Zh1qxZ2LJlC3bv3o02bdoYPc/BwQGHDh1CYWFhjbtZp6enw8HBAZWVlSa3KYTA+vXr0alTJ+zcuRNlZWVwcXFpsjoSke3KyMjA6dOnkZCQYFTOfRfbwiM41OxUKhUcHBzQqlUra4dCRM0sMTERWVlZePvtt7Fz507ExcVhxowZ2L59O9555x1kZWXh2WefrfG8gQMHwtnZGR9//LFR+a+//or/+7//Q1RUVK3bPHz4MH799Ve8//77+Ouvv7BlyxaL14uIlI37LraFCU4LMmXKFDg7O+O3335DdHQ0nJ2d0b59ezz77LOoqqoyWnbDhg0IDg6Gi4sLXF1d0atXL7z11lvS/Pnz50OlUtXYRvXh5LNnz9Yah6nzWM2JjYhs06+//oq1a9di2LBhiI+PrzE/Li4OQ4cOxXvvvYdff/3VaJ6DgwPGjh2LjIwMo/L169ejbdu2iIyMrHW76enp6N69O4YOHYrw8HCkp6dbpkJEZHW//fYbHnvsMXh7e0Oj0aBHjx54//33jZY5fPgwVCoVPv74Y7z44ovw8fFBmzZt8MADD+D8+fPSckOGDMHu3bvxyy+/SKe9durUCQD3XWwNE5wWpqqqCpGRkfD09MR//vMf3HfffXjjjTewevVqaRmtVouJEyeibdu2eP3117FkyRIMGTIEn332mdVjIyJ5KikpweXLl2s8br6mZu/evaiqqsKjjz5a63oeffRR/PXXX9i3b1+NeZMmTcLx48fx008/SWUZGRkYN25craeN6HQ6bN68GRMnTgQATJw4EQcPHkRhYWFDq0pEMlFUVIQBAwbg008/RXx8PN566y106dIF06ZNM3kdzeLFi7F792688MILeOaZZ6DVahEeHo5r164BAF566SX07dsX7dq1w3//+1/897//ve31ONx3kSdeg9PCVFZWYvz48Zg7dy4A4KmnnsI999yDtWvXYsaMGQCA3bt3w9XVFfv372/WQ7H1iY2I5Km2AQAAoEePHgCA7777DgDQp0+fWpetnvf999/XmDds2DD4+Phg/fr1ePnll/H999/j1KlTeOutt/Dzzz+bXN+uXbtQXFyMCRMmAACio6Mxffp0bNiwocY59kRkW1566SVUVVXhm2++gaenJ4Ab+w4TJ07E/Pnz8eSTT8LR0VFa/sqVK/j++++la/DuuecePPzww1izZg2eeeYZjBgxAnfccQf+/PNPPPLII/WKgfsu8sQjOC3QU089ZTT997//3WjnwN3dHeXl5dBqtc0d2m1jIyJ5SklJgVarrfHo3bu3tExZWRkA1HmBf/W80tLSGvNatWqFhx9+GOvXrwdw49Qzf39//P3vf691fenp6QgJCUGXLl2k9UdFRfE0NSIbJ4TA5s2bMXr0aAghjI4cR0ZGoqSkBF988YXRcx599FGj/mfcuHHw9fXFnj17GhUL913kh0dwWhgHBwe0b9/eqKxt27b4888/pemnn34an3zyCUaOHIk77rgDERERePjhh3H//fdbPTYikqf+/fsjJCSkRnnbtm1x+fJlAP9LXqoTHVNulwRNmjQJK1aswFdffYWMjAxMmDDB5PWAAFBcXIw9e/YgPj4e+fn5UvnAgQOxefNm/Pjjj/jb3/5WvwoSkaz8/vvvKC4uxurVq2s9HezSpUtG0127djWaVqlU6NKlS53XDd8O913kiQlOC1OfU868vLxw6tQp7N+/H3v37sXevXuRlpaGRx99FB988AEA1LpD0ZiL6jgyCZGydevWDQDw9ddfo2/fviaX+frrrwEA3bt3Nzk/NDQUnTt3RkJCAgoKCjBp0qRat7dx40bodDq88cYbeOONN2rMT09Px4IFC8ysBRHJgcFgAAA88sgjiI2NNbnMzUeQmwr3XeSJCQ6ZZG9vj9GjR2P06NEwGAx4+umn8e6772Lu3Lno0qUL2rZtC+DGL6Tu7u7S83755RcrRUxEcjdy5Ei0atUK//3vf2sdaODDDz9E69at6zxiPHHiRCxatAjdunWrNVECbiQwPXv2xCuvvFJj3rvvvouMjAwmOEQ2qn379nBxcUFVVVWd1wDe7MyZM0bTQgjk5+cbJUK1/YBLtoXX4FANf/zxh9G0nZ2d9OHX6XQAgM6dOwMAjhw5Ii1XXl4uHeEhIrqVv78/pk6dik8//RSpqak15q9atQoHDx7EtGnT0KFDh1rX8/jjj+OVV14xeVSm2vnz53HkyBE8/PDDGDduXI3H1KlTkZ+fj5ycHIvUjYiaV6tWrRATE4PNmzfj9OnTNeb//vvvNco+/PBDo1NkN23ahIsXL2LkyJFSWZs2bVBSUtI0QVOz4REcquHxxx/HlStXMGzYMHTo0AG//PIL3n77bfTt21c6xSQiIgIBAQGYNm0annvuObRq1Qrvv/8+2rdvj3Pnzlm5BkQkV8uWLcMPP/yAp59+Gvv27ZOO1Ozfvx/bt2+XhlitS8eOHTF//vw6l8nIyIAQAg888IDJ+f/4xz/QunVrpKenIzQ0tEF1IaLm8f7775scOn7+/Pk4dOgQQkND8cQTT6B79+64cuUKvvjiC3z66ae4cuWK0fIeHh4YNGgQpk6diqKiIixfvhxdunTBE088IS0THByMjz/+GImJiejXrx+cnZ0xevToJq8jWRYTHKrhkUcewerVq7Fy5UoUFxfDx8cH48ePx/z582Fnd+Ogn1qtxtatW/H0009j7ty58PHxQUJCAtq2bYupU6dauQZEJFfOzs7IzMzEypUr8dFHH+G5556DEAJBQUFYvnw5nn766VrvaWOO9PR0BAQE1Doktbu7OwYNGoSPP/4Yb775Jlq35tchkVyZOuIL3LjR5vHjx7Fw4UJs2bIFK1euhKenJ3r06IHXX3+9xvIvvvgivv76ayQnJ6OsrAzDhw/HypUr4eTkJC3z9NNP49SpU0hLS8OyZcvQsWNHJjg2SCWEENYOgoiIiIioKRw+fBhDhw7Fxo0bMW7cOGuHQ82A1+AQEREREZFiMMEhIiIiIiLFYIJDRERERESKwWtwiIiIiIhIMXgEh4iIiIiIFIMJDhERERERKQYTHCIiIiIiUgzZ3dnMYDDgwoULcHFxgUqlsnY4RIoihEBZWRn8/Pykm7a2JOxfiJpGS+9bAPYvRE2lIf2L7BKcCxcuwN/f39phECna+fPn0aFDB2uH0ezYvxA1rZbatwDsX4iamjn9i+wSHBcXFwBAQUEBsrOzERERAbVabeWo5EGv1+PAgQNsk1uwXUwz1S6lpaXw9/eXPmctTXW9z58/D1dXV6mc76HGYfs1nFLarqX3LUDt/Yvc2eJ70BZjBmwzbjnE3JD+RXYJTvVhXRcXFzg5OcHV1dVm3gRNTa/Xs01MYLuYVle7tNTTJ6rr7erqWiPB4Xuo4dh+Dae0tmupfQtQe/8id7b4HrTFmAHbjFtOMZvTv7TME2WJiIiIiEiRmOAQEREREZFiMMEhIiIiIiLFYIJDRERERESKIbtBBszRac5ui67v7JIoi66PiGwX+xciaiqW7F/YtxDVxCM4RERERESkGExwiIiIiIhIMZjgEBERERGRYjDBISIiIiIixWCCQ0REREREisEEh4iIiIiIFIMJDhERERERKQYTHCIiIiIiUgwmOEQkC1VVVZg7dy4CAwPh6OiIzp0749VXX4UQQlpGCIF58+bB19cXjo6OCA8Px5kzZ6wYNRHZgtTUVPTu3Ruurq5wdXVFWFgY9u7dK82vrKxEXFwcPD094ezsjJiYGBQVFVkxYiJqDCY4RCQLr7/+OlJTU/HOO+/g+++/x+uvv46lS5fi7bfflpZZunQpVqxYgVWrViEnJwdt2rRBZGQkKisrrRg5Ecldhw4dsGTJEuTm5uLkyZMYNmwYxowZg2+//RYAMHv2bOzcuRMbN25EVlYWLly4gLFjx1o5aiJqqNbWDoCICAA+//xzjBkzBlFRUQCATp06Yf369Th+/DiAG0dvli9fjpdffhljxowBAHz44Yfw9vbGtm3bMGHCBKvFTkTyNnr0aKPpxYsXIzU1FceOHUOHDh2wdu1aZGRkYNiwYQCAtLQ0dOvWDceOHcOAAQOsETIRNQKP4BCRLNx7773IzMzEjz/+CAD46quvcPToUYwcORIAUFBQgMLCQoSHh0vPcXNzQ2hoKLKzs60SMxHZnqqqKmzYsAHl5eUICwtDbm4u9Hq9Ud8SFBSEgIAA9i1ENopHcIhIFubMmYPS0lIEBQWhVatWqKqqwuLFizF58mQAQGFhIQDA29vb6Hne3t7SvFvpdDrodDppurS0FACg1+uh1+ul8ur/by7TtPrftT+WcPO6lcZU+1H9KKXtbCH+b775BmFhYaisrISzszO2bt2K7t2749SpU7C3t4e7u7vR8nX1LUD9+xdTLNm/NLbtbfE9aIsxA7YZtxxibsi2meAQkSx88sknSE9PR0ZGBnr06IFTp04hISEBfn5+iI2NbdA6k5OTsWDBghrlBw4cgJOTU41yrVYr/b+0f4M2Was9e/ZYdoUydHP7kXlsve0qKiqsHcJt3XXXXTh16hRKSkqwadMmxMbGIisrq8HrM7d/uZkl+xdL9S22+B60xZgB24zbmjE3pH9hgkNEsvDcc89hzpw50rU0vXr1wi+//ILk5GTExsbCx8cHAFBUVARfX1/peUVFRejbt6/JdSYlJSExMVGaLi0thb+/PyIiIuDq6iqV6/V6aLVajBgxAmq1GgDQc/5+i9bv9PxIi65PTky1H9WPUtqu+uiFnNnb26NLly4AgODgYJw4cQJvvfUWxo8fj+vXr6O4uNjoKE5RUZHU75hS3/7FFEv2L43tW2zxPWiLMQO2GbccYm5I/8IEh4hkoaKiAnZ2xpcFtmrVCgaDAQAQGBgIHx8fZGZmSglNaWkpcnJyMGPGDJPr1Gg00Gg0NcrVarXJjvrmcl2VqjHVMblupautXen2bL3tbDF2g8EAnU6H4OBgqNVqZGZmIiYmBgCQl5eHc+fOISwsrNbnm9u/3MyS/Yul2t4W34O2GDNgm3FbM+aGbJcJDhHJwujRo7F48WIEBASgR48e+PLLL/Hmm2/iscceAwCoVCokJCRg0aJF6Nq1KwIDAzF37lz4+fkhOjrausETkawlJSVh5MiRCAgIQFlZGTIyMnD48GHs378fbm5umDZtGhITE+Hh4QFXV1fMnDkTYWFhHEGNyEYxwSEiWXj77bcxd+5cPP3007h06RL8/Pzw5JNPYt68edIyzz//PMrLyzF9+nQUFxdj0KBB2LdvHxwcHKwYORHJ3aVLl/Doo4/i4sWLcHNzQ+/evbF//36MGDECALBs2TLY2dkhJiYGOp0OkZGRWLlypZWjJqKGYoJDRLLg4uKC5cuXY/ny5bUuo1KpsHDhQixcuLD5AiMim7d27do65zs4OCAlJQUpKSnNFBERNSXeB4eIiIiIiBTD7ATnt99+wyOPPAJPT084OjqiV69eOHnypDRfCIF58+bB19cXjo6OCA8Px5kzZywaNBERERERkSlmJTh//vknBg4cCLVajb179+K7777DG2+8gbZt20rLLF26FCtWrMCqVauQk5ODNm3aIDIyEpWVlRYPnoiIiIiI6GZmXYPz+uuvw9/fH2lpaVJZYGCg9L8QAsuXL8fLL7+MMWPGAAA+/PBDeHt7Y9u2bdL9LYiIiIiIiJqCWQnOjh07EBkZiYceeghZWVm444478PTTT+OJJ54AABQUFKCwsBDh4eHSc9zc3BAaGors7GyTCY5Op4NOp5Omq2/mo9frjf6aomklzAn/turalhzUp01aIraLaabahW1ERERESmdWgvPzzz8jNTUViYmJePHFF3HixAk888wzsLe3R2xsLAoLCwEA3t7eRs/z9vaW5t0qOTkZCxYsqFF+6NAhODk5QavV1hrP0v7mRH97e/bssewKm0hdbdKSsV1Mu7ldKioqrBgJERERUdMzK8ExGAwICQnBa6+9BgC4++67cfr0aaxatQqxsbENCiApKQmJiYnSdGlpKfz9/TF06FDk5ORgxIgRtd7BtOf8/Q3aZm1Oz4+06PosTa/XQ6vV1tkmLRHbxTRT7VJ9hJSIiIhIqcxKcHx9fdG9e3ejsm7dumHz5s0AAB8fHwBAUVERfH19pWWKiorQt29fk+vUaDTQaDQ1yqt3yNRqda07rboqlTnh35at7BzX1SYtGdvFtJvbhe1DRKQsnebsbtTzNa0Elva/8aOxrkqFs0uiLBQZkfWYNYrawIEDkZeXZ1T2448/omPHjgBuDDjg4+ODzMxMaX5paSlycnIQFhZmgXCJiIiIiIhqZ9YRnNmzZ+Pee+/Fa6+9hocffhjHjx/H6tWrsXr1agA37jKekJCARYsWoWvXrggMDMTcuXPh5+eH6OjopoifiIiIiIhIYlaC069fP2zduhVJSUlYuHAhAgMDsXz5ckyePFla5vnnn0d5eTmmT5+O4uJiDBo0CPv27YODg4PFgyciIiIiIrqZWQkOAIwaNQqjRo2qdb5KpcLChQuxcOHCRgVGRERERERkLrOuwSEiIiIiIpIzJjhERERERKQYTHCIiIiIiEgxmOAQEREREZFiMMEhIiIiIiLFYIJDRERERESKwQSHiIiIiIgUgwkOEREREREpBhMcIiIiIiJSDCY4RERERESkGExwiIiIiIhIMZjgEJFs/Pbbb3jkkUfg6ekJR0dH9OrVCydPnpTmCyEwb948+Pr6wtHREeHh4Thz5owVIyYiIiK5YYJDRLLw559/YuDAgVCr1di7dy++++47vPHGG2jbtq20zNKlS7FixQqsWrUKOTk5aNOmDSIjI1FZWWnFyImIiEhOWls7ACIiAHj99dfh7++PtLQ0qSwwMFD6XwiB5cuX4+WXX8aYMWMAAB9++CG8vb2xbds2TJgwodljJiIiIvnhERwikoUdO3YgJCQEDz30ELy8vHD33XdjzZo10vyCggIUFhYiPDxcKnNzc0NoaCiys7OtETIRERHJEI/gEJEs/Pzzz0hNTUViYiJefPFFnDhxAs888wzs7e0RGxuLwsJCAIC3t7fR87y9vaV5t9LpdNDpdNJ0aWkpAECv10Ov10vl1f/fXKZpJSxTsVu2oUSm2o/qRyltZ+vxE5GyMMEhIlkwGAwICQnBa6+9BgC4++67cfr0aaxatQqxsbENWmdycjIWLFhQo/zAgQNwcnKqUa7VaqX/l/Zv0CZrtWfPHsuuUIZubj8yj623XUVFhbVDICKSMMEhIlnw9fVF9+7djcq6deuGzZs3AwB8fHwAAEVFRfD19ZWWKSoqQt++fU2uMykpCYmJidJ0aWkp/P39ERERAVdXV6lcr9dDq9VixIgRUKvVAICe8/dbpF7VTs+PtOj65MRU+1H9KKXtqo+OEhHJARMcIpKFgQMHIi8vz6jsxx9/RMeOHQHcGHDAx8cHmZmZUkJTWlqKnJwczJgxw+Q6NRoNNBpNjXK1Wm1yZ/Lmcl2VqjHVMblupautXen2bL3tbDl2IlIeJjhEJAuzZ8/Gvffei9deew0PP/wwjh8/jtWrV2P16tUAAJVKhYSEBCxatAhdu3ZFYGAg5s6dCz8/P0RHR1s3eCIiIpINJjhEJAv9+vXD1q1bkZSUhIULFyIwMBDLly/H5MmTpWWef/55lJeXY/r06SguLsagQYOwb98+ODg4WDFyIiIikhMmOEQkG6NGjcKoUaNqna9SqbBw4UIsXLiwGaMiIiIiW8L74BARERERkWIwwSEiIiJFS05ORr9+/eDi4gIvLy9ER0fXGNSksrIScXFx8PT0hLOzM2JiYlBUVGSliImoMZjgEBERkaJlZWUhLi4Ox44dg1arhV6vR0REBMrLy6VlZs+ejZ07d2Ljxo3IysrChQsXMHbsWCtGTUQNxWtwiIiISNH27dtnNL1u3Tp4eXkhNzcXgwcPRklJCdauXYuMjAwMGzYMAJCWloZu3brh2LFjGDBggDXCJqIGYoJDRERELUpJSQkAwMPDAwCQm5sLvV6P8PBwaZmgoCAEBAQgOzvbZIKj0+mg0+mk6eqbner1euj1+jq3r2klGl0HS9HYCaO/t4tdDqpjtIVYb2aLccsh5oZsmwkOERERtRgGgwEJCQkYOHAgevbsCQAoLCyEvb093N3djZb19vZGYWGhyfUkJydjwYIFNcoPHDgAJyenOmNY2r9hsTelV0MMAIA9e/ZYOZL602q11g6hQWwxbmvGXFFRYfZzmOAQERFRixEXF4fTp0/j6NGjjVpPUlISEhMTpenS0lL4+/sjIiICrq6udT635/z9jdq2JWnsBF4NMWDuSTvoDCqcnh9p7ZBuS6/XQ6vVYsSIEVCr1dYOp95sMW45xFx9dNQcTHCIiIioRYiPj8euXbtw5MgRdOjQQSr38fHB9evXUVxcbHQUp6ioCD4+PibXpdFooNFoapSr1erb7gjqqlQNq0AT0hlU0FWpbGbHG6hfW8uRLcZtzZgbst1GjaK2ZMkSqFQqJCQkSGUcZpGIiIjkRAiB+Ph4bN26FQcPHkRgYKDR/ODgYKjVamRmZkpleXl5OHfuHMLCwpo7XCJqpAYfwTlx4gTeffdd9O7d26h89uzZ2L17NzZu3Ag3NzfEx8dj7Nix+OyzzxodLBEREZG54uLikJGRge3bt8PFxUW6rsbNzQ2Ojo5wc3PDtGnTkJiYCA8PD7i6umLmzJkICwvjCGpENqhBR3CuXr2KyZMnY82aNWjbtq1UXj3M4ptvvolhw4YhODgYaWlp+Pzzz3Hs2DGLBU1ERERUX6mpqSgpKcGQIUPg6+srPT7++GNpmWXLlmHUqFGIiYnB4MGD4ePjgy1btlgxaiJqqAYlOHFxcYiKijIaThG4/TCLRERERM1NCGHyMWXKFGkZBwcHpKSk4MqVKygvL8eWLVtqvf6GiOTN7FPUNmzYgC+++AInTpyoMa8hwyzWNY78zX9NsfQ48nIfl1wOY5HLEdvFNFPtwjYiIiIipTMrwTl//jxmzZoFrVYLBwcHiwRQ2zjyhw4dgpOTU53jblt6HHlbGfvdFsdPbw5sF9NubpeGjCVPREREZEvMSnByc3Nx6dIl3HPPPVJZVVUVjhw5gnfeeQf79+83e5jF2saRHzp0KHJycuocd9vS48jLfex3OYxFLkdsF9NMtUtDxpInIiIisiVmJTjDhw/HN998Y1Q2depUBAUF4YUXXoC/v780zGJMTAyA2w+zWNc48tV/a9tptfQ48rayc2yL46c3B7aLaTe3C9uHiIiIlM6sBMfFxQU9e/Y0KmvTpg08PT2lcg6zSERERERE1tLg++DUZtmyZbCzs0NMTAx0Oh0iIyOxcuVKS2+GiIiIiIiohkYnOIcPHzaarh5mMSUlpbGrJiIiIiIiMovFj+AQERERkW3qNGe3Rdd3dkmURddHVB8NutEnERERERGRHDHBISIiIiIixWCCQ0REREREisEEh4hkacmSJVCpVEhISJDKKisrERcXB09PTzg7OyMmJgZFRUXWC5KIiIhkhwkOEcnOiRMn8O6776J3795G5bNnz8bOnTuxceNGZGVl4cKFCxg7dqyVoiQiIiI5YoJDRLJy9epVTJ48GWvWrEHbtm2l8pKSEqxduxZvvvkmhg0bhuDgYKSlpeHzzz/HsWPHrBgxERERyQkTHCKSlbi4OERFRSE8PNyoPDc3F3q93qg8KCgIAQEByM7Obu4wiYiISKZ4Hxwiko0NGzbgiy++wIkTJ2rMKywshL29Pdzd3Y3Kvb29UVhYaHJ9Op0OOp1Omi4tLQUA6PV66PV6qbz6/5vLNK1Eg+thys3rVhpT7Uf1o5S2s/X4iUhZmOAQkSycP38es2bNglarhYODg0XWmZycjAULFtQoP3DgAJycnGqUa7Va6f+l/S0SgmTPnj2WXaEM3dx+ZB5bb7uKigprh0BEJGGCQ0SykJubi0uXLuGee+6RyqqqqnDkyBG888472L9/P65fv47i4mKjozhFRUXw8fExuc6kpCQkJiZK06WlpfD390dERARcXV2lcr1eD61WixEjRkCtVgMAes7fb9H6nZ4fadH1yYmp9qP6UUrbVR8dJSKSAyY4RCQLw4cPxzfffGNUNnXqVAQFBeGFF16Av78/1Go1MjMzERMTAwDIy8vDuXPnEBYWZnKdGo0GGo2mRrlarTa5M3lzua5K1dgq1Vi30tXWrnR7tt52thw7ESkPExwikgUXFxf07NnTqKxNmzbw9PSUyqdNm4bExER4eHjA1dUVM2fORFhYGAYMGGCNkImIiEiGmOAQkc1YtmwZ7OzsEBMTA51Oh8jISKxcudLaYREREZGMMMEhItk6fPiw0bSDgwNSUlKQkpJinYCIiIhI9ngfHCIiIiIiUgwmOEREREREpBhMcIiIiIiISDGY4BARERERkWIwwSEiIiIiIsVggkNERERERIrBBIeIiIiIiBSD98EhIiIiItnrNGc3AEDTSmBpf6Dn/P3QVakavL6zS6IsFRrJDI/gEBERERGRYjDBISIiIiIixWCCQ0REREREisEEh4iIiIiIFIODDBAREZGiHTlyBP/+97+Rm5uLixcvYuvWrYiOjpbmCyHwyiuvYM2aNSguLsbAgQORmpqKrl27Wi9ohageGICoOfEIDhERESlaeXk5+vTpg5SUFJPzly5dihUrVmDVqlXIyclBmzZtEBkZicrKymaOlIgsgUdwiIiISNFGjhyJkSNHmpwnhMDy5cvx8ssvY8yYMQCADz/8EN7e3ti2bRsmTJjQnKESkQUwwSEiIqIWq6CgAIWFhQgPD5fK3NzcEBoaiuzs7FoTHJ1OB51OJ02XlpYCAPR6PfR6fZ3b1LQSFojcMjR2wuivLbBUzLd7nSytenvNvd3GkEPMDdm2WQlOcnIytmzZgh9++AGOjo6499578frrr+Ouu+6SlqmsrMS//vUvbNiwATqdDpGRkVi5ciW8vb3NDo6IiIioKRUWFgJAjf0Ub29vaZ4pycnJWLBgQY3yAwcOwMnJqc5tLu3fgECb2KshBmuHYLbGxrxnzx4LRWIerVZrle02hjVjrqioMPs5ZiU4WVlZiIuLQ79+/fDXX3/hxRdfREREBL777ju0adMGADB79mzs3r0bGzduhJubG+Lj4zF27Fh89tlnZgdHREREJEdJSUlITEyUpktLS+Hv74+IiAi4urrW+dye8/c3dXj1prETeDXEgLkn7aAzqKwdTr1YKubT8yMtGNXt6fV6aLVajBgxAmq1ulm33VByiLn66Kg5zEpw9u3bZzS9bt06eHl5ITc3F4MHD0ZJSQnWrl2LjIwMDBs2DACQlpaGbt264dixYxgwYIDZARIRERE1FR8fHwBAUVERfH19pfKioiL07du31udpNBpoNJoa5Wq1+rY7groq+SUSOoNKlnHVpbExW2uHvT7vEbmxZswN2W6jrsEpKSkBAHh4eAAAcnNzodfrjc5jDQoKQkBAALKzs00mOHWdw3rzX1MsfQ6r3M+JlMN5kHLEdjHNVLuwjYiIjAUGBsLHxweZmZlSQlNaWoqcnBzMmDHDusERUYM0OMExGAxISEjAwIED0bNnTwA3zmO1t7eHu7u70bJ1ncda2zmshw4dgpOTU53n/Fn6HFZrnYtpLls8d7M5sF1Mu7ldGnIeKxGRrbt69Sry8/Ol6YKCApw6dQoeHh4ICAhAQkICFi1ahK5duyIwMBBz586Fn5+f0b1yiMh2NDjBiYuLw+nTp3H06NFGBVDbOaxDhw5FTk5Onef8Wfoc1uY+F9NccjgPUo7YLqaZapeGnMdKRGTrTp48iaFDh0rT1fsdsbGxWLduHZ5//nmUl5dj+vTpKC4uxqBBg7Bv3z44ODhYK2QiaoQGJTjx8fHYtWsXjhw5gg4dOkjlPj4+uH79OoqLi42O4hQVFUnnuN6qrnNYq//WttNq6XNFu849YLF1nV0SZbF13coWz91sDmwX025uF7YPEbVEQ4YMgRC1n9auUqmwcOFCLFy4sBmjIqKmYmfOwkIIxMfHY+vWrTh48CACAwON5gcHB0OtViMzM1Mqy8vLw7lz5xAWFmaZiIlIkZKTk9GvXz+4uLjAy8sL0dHRyMvLM1qmsrIScXFx8PT0hLOzM2JiYlBUVGSliImIiEiOzEpw4uLi8NFHHyEjIwMuLi4oLCxEYWEhrl27BuDGjbGmTZuGxMREHDp0CLm5uZg6dSrCwsI4ghoR1al6GPpjx45Bq9VCr9cjIiIC5eXl0jKzZ8/Gzp07sXHjRmRlZeHChQsYO3asFaMmIiIiuTHrFLXU1FQANw713iwtLQ1TpkwBACxbtgx2dnaIiYkxutEnEVFdOAw9ERERWYJZCU5d569Wc3BwQEpKClJSUhocFBGRJYahJyIiopanUffBISJqCpYahr6u+2yZuj/QzWUt7T5bjcF7UTWcUtrO1uMnImVhgkNEsmOpYehru8/WgQMH4OTkVKP85nsGtdT7bDUG70XVcLbedrzHFhHJCRMcIpIVSw5DX9t9tiIiIuDq6iqVm7pnUEu7z1Zj8F5UDaeUtuM9tohITpjgEJEsCCEwc+ZMbN26FYcPH65zGPqYmBgAtx+Gvq77bJnamby53NL32bLlndf64r2oGs7W286WY6eWq9Oc3RZbV1Pe/5DMxwSHiGQhLi4OGRkZ2L59uzQMPXBj+HlHR0ejYeg9PDzg6uqKmTNnchh6IiIiMsIEh4hkgcPQExERkSUwwSEiWeAw9ERERGQJdtYOgIiIiIiIyFKY4BARERERkWLwFDUiombA0XqIiIiaB4/gEBERERGRYjDBISIiIiIixeApak3EkqejADwlhYiIiIioPngEh4iIiIiIFIMJDhERERERKQYTHCIiIiIiUgwmOEREREREpBhMcIiIiIiISDGY4BARERERkWIwwSEiIiIiIsVggkNERERERIrBG30SEREREcmIJW8Yb+mbxdvCzex5BIeIiIiIiBSDR3CIiGyMLfx6RkREZC1McFog7hwRERERkVLxFDUiIiIiIlIMHsGxEZ3m7IamlcDS/kDP+fuhq1JZOyQiIiIiQv3OjuF+XPPhERwiIiIiIlIMJjhERERERKQYTHCIiIiIiEgxmuwanJSUFPz73/9GYWEh+vTpg7fffhv9+/dvqs0RUQvC/oWImgL7FlKixoyea6vXDTVJgvPxxx8jMTERq1atQmhoKJYvX47IyEjk5eXBy8urKTZJCmLuB7GuDx+HsFYe9i+W19ih42/+DOYtHmWhqIiaF/sWIuVoklPU3nzzTTzxxBOYOnUqunfvjlWrVsHJyQnvv/9+U2yOiFoQ9i9E1BTYtxAph8WP4Fy/fh25ublISkqSyuzs7BAeHo7s7GxLb46oTpa+qamctYSjVexfWh45f4Yt/ZlrSXWVG/YtRMpi8QTn8uXLqKqqgre3t1G5t7c3fvjhhxrL63Q66HQ6abqkpAQAcOXKFVRUVOCPP/6AWq02ua3Wf5VbMHL5a20QqKgwoLXeDlUG+ZwH+ccff1h0fea+rnJtl+Z26+ug1+trfIbKysoAAEKIZo/PEizZv+j1eqncVFu1tP6lMW7+DFq7P2hOlqjrze89W65rS+tbgPr3L6bI6bW2xe9QW4wZsM24myPmpuhfrH6jz+TkZCxYsKBG+d/+9jcrRCN/k6wdgAnt3rB2BPJsl+ZmzutQVlYGNze3pgtGJmrrXwIDA60QjbJVfwbb/duqYTQrOfR9zaW+dW0pfQugrP7FFr9DbTFmwDbjbuqYm6J/sXiC065dO7Rq1QpFRUVG5UVFRfDx8amxfFJSEhITE6Vpg8GAK1euQK1WIyAgAOfPn4erq6ulw7RJpaWl8Pf3Z5vcgu1imql2EUKgrKwMfn5+Vo6uYSzVv3h6ekKl+t8vUXwPNQ7br+GU0nYtrW8B6t+/yJ0tvgdtMWbANuOWQ8wN6V8snuDY29sjODgYmZmZiI6OBnDjQ5+ZmYn4+Pgay2s0Gmg0GqMyd3d3lJaWAgBcXV1t5k3QXNgmprFdTLu1XWz511VL9S+14Xuocdh+DaeEtmtJfQtgfv8id7b4HrTFmAHbjNvaMZvbvzTJKWqJiYmIjY1FSEgI+vfvj+XLl6O8vBxTp05tis0RUQvC/oWImgL7FiLlaJIEZ/z48fj9998xb948FBYWom/fvti3b1+Ni/eIiMzF/oWImgL7FiLlaLJBBuLj42s9rFsfGo0Gr7zySo3Dvy0Z28Q0totpSm6XxvYvt1JyWzUHtl/Dse3kxdJ9iy2wxfegLcYM2GbcthgzAKiErY7pSEREREREdAs7awdARERERERkKUxwiIiIiIhIMZjgEBERERGRYsgywUlJSUGnTp3g4OCA0NBQHD9+3NohNavk5GT069cPLi4u8PLyQnR0NPLy8oyWqaysRFxcHDw9PeHs7IyYmJgaNyhTsiVLlkClUiEhIUEqa6lt8ttvv+GRRx6Bp6cnHB0d0atXL5w8eVKaL4TAvHnz4OvrC0dHR4SHh+PMmTNWjFh+WnqfU19HjhzB6NGj4efnB5VKhW3bthnN53utduzXyZqU8P6zpe99W/terqqqwty5cxEYGAhHR0d07twZr776Km6+TF9uMd+WkJkNGzYIe3t78f7774tvv/1WPPHEE8Ld3V0UFRVZO7RmExkZKdLS0sTp06fFqVOnxD/+8Q8REBAgrl69Ki3z1FNPCX9/f5GZmSlOnjwpBgwYIO69914rRt18jh8/Ljp16iR69+4tZs2aJZW3xDa5cuWK6Nixo5gyZYrIyckRP//8s9i/f7/Iz8+XllmyZIlwc3MT27ZtE1999ZV44IEHRGBgoLh27ZoVI5cP9jn1t2fPHvHSSy+JLVu2CABi69atRvP5Xqsd+3WyJlt//9nS974tfi8vXrxYeHp6il27domCggKxceNG4ezsLN566y3Zxnw7sktw+vfvL+Li4qTpqqoq4efnJ5KTk60YlXVdunRJABBZWVlCCCGKi4uFWq0WGzdulJb5/vvvBQCRnZ1trTCbRVlZmejatavQarXivvvukzq6ltomL7zwghg0aFCt8w0Gg/Dx8RH//ve/pbLi4mKh0WjE+vXrmyNE2WOf0zC3Jjh8r5mH/TpZky29/2zte98Wv5ejoqLEY489ZlQ2duxYMXnyZCGEPGO+HVmdonb9+nXk5uYiPDxcKrOzs0N4eDiys7OtGJl1lZSUAAA8PDwAALm5udDr9UbtFBQUhICAAMW3U1xcHKKioozqDrTcNtmxYwdCQkLw0EMPwcvLC3fffTfWrFkjzS8oKEBhYaFRu7i5uSE0NFTR7VJf7HMsh+8187BfJ2uypfefrX3v2+L38r333ovMzEz8+OOPAICvvvoKR48exciRI2Ub8+002Y0+G+Ly5cuoqqqqcddgb29v/PDDD1aKyroMBgMSEhIwcOBA9OzZEwBQWFgIe3t7uLu7Gy3r7e2NwsJCK0TZPDZs2IAvvvgCJ06cqDGvpbbJzz//jNTUVCQmJuLFF1/EiRMn8Mwzz8De3h6xsbFS3U19ppTcLvXFPsdy+F6rP/brZE229P6zxe99W/xenjNnDkpLSxEUFIRWrVqhqqoKixcvxuTJkwHYZv8uqwSHaoqLi8Pp06dx9OhRa4diVefPn8esWbOg1Wrh4OBg7XBkw2AwICQkBK+99hoA4O6778bp06exatUqxMbGWjk6IjKF/TpZk628/2z1e98Wv5c/+eQTpKenIyMjAz169MCpU6eQkJAAPz8/2cZ8O7I6Ra1du3Zo1apVjREwioqK4OPjY6WorCc+Ph67du3CoUOH0KFDB6ncx8cH169fR3FxsdHySm6n3NxcXLp0Cffccw9at26N1q1bIysrCytWrEDr1q3h7e3d4toEAHx9fdG9e3ejsm7duuHcuXMAINWdnynT2OdYDt9r9cN+nazJlt5/tvq9b4vfy8899xzmzJmDCRMmoFevXvjnP/+J2bNnIzk5GYA8Y74dWSU49vb2CA4ORmZmplRmMBiQmZmJsLAwK0bWvIQQiI+Px9atW3Hw4EEEBgYazQ8ODoZarTZqp7y8PJw7d06x7TR8+HB88803OHXqlPQICQnB5MmTpf9bWpsAwMCBA2sM9fnjjz+iY8eOAIDAwED4+PgYtUtpaSlycnIU3S71xT7Hcvheqxv7dbImW3z/2er3vi1+L1dUVMDOzjglaNWqFQwGAwB5xnxbVh7koIYNGzYIjUYj1q1bJ7777jsxffp04e7uLgoLC60dWrOZMWOGcHNzE4cPHxYXL16UHhUVFdIyTz31lAgICBAHDx4UJ0+eFGFhYSIsLMyKUTe/m0dTEaJltsnx48dF69atxeLFi8WZM2dEenq6cHJyEh999JG0zJIlS4S7u7vYvn27+Prrr8WYMWNkPbRjc2OfU39lZWXiyy+/FF9++aUAIN58803x5Zdfil9++UUIwfdaXdivkzUp5f1nC9/7tvi9HBsbK+644w5pmOgtW7aIdu3aieeff162Md+O7BIcIYR4++23RUBAgLC3txf9+/cXx44ds3ZIzQqAyUdaWpq0zLVr18TTTz8t2rZtK5ycnMSDDz4oLl68aL2greDWjq6ltsnOnTtFz549hUajEUFBQWL16tVG8w0Gg5g7d67w9vYWGo1GDB8+XOTl5VkpWnlq6X1OfR06dMhk3xQbGyuE4HutLuzXyZqU8v6zle99W/teLi0tFbNmzRIBAQHCwcFB3HnnneKll14SOp1OtjHfjkqIm25TSkREREREZMNkdQ0OERERERFRYzDBISIiIiIixWCCQ0REREREisEEh4iIiIiIFIMJjgKsW7cOKpUKZ8+elcqGDBmCIUOGWC0mazh79ixUKhXWrVtn7VCIqJHmz58PlUplsfVNmTIFnTp1stj6iIhIvpjgyMzKlSuhUqkQGhpq7VBkKyMjA8uXL7d2GEQtRvWPKNWP1q1b44477sCUKVPw22+/WTs8yYULFzB//nycOnXK2qEQkYXc3P8cPXq0xnwhBPz9/aFSqTBq1CijeZWVlVi2bBlCQ0Ph5uYGBwcH/O1vf0N8fDx+/PFHabnqH1SqH05OTujevTtefvlllJaWmozr+PHjePrpp6WbpFryBxlqvNbWDoCMpaeno1OnTjh+/Djy8/PRpUuXBq3nwIEDFo5MPjIyMnD69GkkJCQYlXfs2BHXrl2DWq22TmBECrdw4UIEBgaisrISx44dw7p163D06FGcPn0aDg4OFt3Wyy+/jDlz5pj1nAsXLmDBggXo1KkT+vbtazRvzZo10l25icj2ODg4ICMjA4MGDTIqz8rKwq+//gqNRmNUfvnyZdx///3Izc3FqFGjMGnSJDg7OyMvLw8bNmzA6tWrcf36daPnpKamwtnZGVevXsWBAwewePFiHDx4EJ999lmNBGbPnj1477330Lt3b9x5551GCRNZH4/gyEhBQQE+//xzvPnmm2jfvj3S09MbvC57e3vY29tbMDr5U6lUcHBwQKtWrawdCpEijRw5Eo888ggef/xxvPfee3j22Wfx008/YceOHRbfVuvWrS2aNKnV6ho7QERkO/7xj39g48aN+Ouvv4zKMzIyEBwcDB8fH6PyKVOm4Msvv8SmTZuwc+dOzJo1C9OmTcPSpUtx5swZPPPMMzW2MW7cODzyyCN46qmnsGXLFowdOxbZ2dk4duxYjWVnzJiBkpISnDx5EiNGjLBsZanRmODISHp6Otq2bYuoqCiMGzfOZILz7bffYtiwYXB0dESHDh2waNEik79K3noNzuHDh6FSqfDxxx/jxRdfhI+PD9q0aYMHHngA58+fr/H8jRs3Ijg4GI6OjmjXrh0eeeSRGqeiTJkyBc7Ozvjtt98QHR0NZ2dntG/fHs8++yyqqqqMljUYDFi+fDl69OgBBwcHeHt748knn8Sff/5ZY9t79+7FfffdBxcXF7i6uqJfv37IyMiQ6rV792788ssv0qHk6vPqTV2DY06MRGSev//97wCAn376SSr74YcfMG7cOHh4eMDBwQEhISE1EiC9Xo8FCxaga9eucHBwgKenJwYNGgStVistY+oaHK1Wi0GDBsHd3R3Ozs6466678OKLLwK40cf169cPADB16lSpf6juD269Bqe6v/jPf/6D1atXo3PnztBoNOjXrx9OnDhhsTYiIsuYOHEi/vjjD6N+4vr169i0aRMmTZpktGxOTg52796NadOmISYmpsa6NBoN/vOf/9x2m8OGDQNw4wfoW3l7e8PR0dHcalAz4SlqMpKeno6xY8fC3t4eEydORGpqKk6cOCF9aRcWFmLo0KH466+/MGfOHLRp0warV6826wO2ePFiqFQqvPDCC7h06RKWL1+O8PBwnDp1SlrPunXrMHXqVPTr1w/JyckoKirCW2+9hc8++wxffvkl3N3dpfVVVVUhMjISoaGh+M9//oNPP/0Ub7zxBjp37owZM2ZIyz355JPSep955hkUFBTgnXfewZdffonPPvtMOq1s3bp1eOyxx9CjRw8kJSXB3d0dX375Jfbt24dJkybhpZdeQklJCX799VcsW7YMAODs7FxnnesbIxGZp3pgk7Zt2wK48QPMwIEDcccdd0h91CeffILo6Ghs3rwZDz74IIAbyUtycjIef/xx9O/fH6WlpTh58iS++OKLWn8J/fbbbzFq1Cj07t0bCxcuhEajQX5+Pj777DMAQLdu3bBw4ULMmzcP06dPl5Kve++9t846ZGRkoKysDE8++SRUKhWWLl2KsWPH4ueff+bprkQy0qlTJ4SFhWH9+vUYOXIkgBs/iJaUlGDChAlYsWKFtGz1jyr//Oc/G7XN6h9vPD09G7UesgJBsnDy5EkBQGi1WiGEEAaDQXTo0EHMmjVLWiYhIUEAEDk5OVLZpUuXhJubmwAgCgoKpPL77rtP3HfffdL0oUOHBABxxx13iNLSUqn8k08+EQDEW2+9JYQQ4vr168LLy0v07NlTXLt2TVpu165dAoCYN2+eVBYbGysAiIULFxrV5e677xbBwcHS9P/93/8JACI9Pd1ouX379hmVFxcXCxcXFxEaGmq07er2qBYVFSU6duxYow0LCgoEAJGWlmZ2jERUu7S0NAFAfPrpp+L3338X58+fF5s2bRLt27cXGo1GnD9/XgghxPDhw0WvXr1EZWWl9FyDwSDuvfde0bVrV6msT58+Iioqqs5tvvLKK+Lmr6hly5YJAOL333+v9TknTpyo0QdUi42NNeo3qvsLT09PceXKFal8+/btAoDYuXNnnfERUfOo7n9OnDgh3nnnHeHi4iIqKiqEEEI89NBDYujQoUIIITp27Cj1Kw8++KAAIP788896baO6v8nLyxO///67KCgoEO+++67QaDTC29tblJeX1/n8uLg4wV1qeeEpajKRnp4Ob29vDB06FMCN60nGjx+PDRs2SKdS7dmzBwMGDED//v2l57Vv3x6TJ0+u93YeffRRuLi4SNPjxo2Dr68v9uzZAwA4efIkLl26hKefftro/PeoqCgEBQVh9+7dNdb51FNPGU3//e9/x88//yxNb9y4EW5ubhgxYgQuX74sPYKDg+Hs7IxDhw4BuHH6SVlZGebMmVPj3PvGjk5yuxiJ6PbCw8PRvn17+Pv7Y9y4cWjTpg127NiBDh064MqVKzh48CAefvhhlJWVSZ/zP/74A5GRkThz5ox0mqu7uzu+/fZbnDlzpt7brj5yvH37dosOFjB+/HjpCBTwv9Pu2D8Qyc/DDz+Ma9euYdeuXSgrK8OuXbtqnJ4GQBr57Ob9nfq466670L59ewQGBuLJJ59Ely5dsHv3bjg5OVkkfmo+THBkoKqqChs2bMDQoUNRUFCA/Px85OfnIzQ0FEVFRcjMzAQA/PLLL+jatWuN599111313tatz1epVOjSpYt0qskvv/xS6zqDgoKk+dUcHBzQvn17o7K2bdsaXVtz5swZlJSUwMvLC+3btzd6XL16FZcuXQLwv0PBPXv2rHd96qM+MRLR7aWkpECr1WLTpk34xz/+gcuXL0sX7ufn50MIgblz59b4nL/yyisAIH3WFy5ciOLiYvztb39Dr1698Nxzz+Hrr7+uc9vjx4/HwIED8fjjj8Pb2xsTJkzAJ5980uhkJyAgwGi6Otlh/0AkP+3bt0d4eDgyMjKwZcsWVFVVYdy4cTWWc3V1BQCUlZWZtf7NmzdDq9Xi8OHDyM/Px+nTpxEcHGyR2Kl58RocGTh48CAuXryIDRs2YMOGDTXmp6enIyIiwgqR3V59RiwzGAzw8vKqdVS4W5MPS+OoakSW0b9/f4SEhAAAoqOjMWjQIEyaNAl5eXlSovHss88iMjLS5POrh70fPHgwfvrpJ2zfvh0HDhzAe++9h2XLlmHVqlV4/PHHTT7X0dERR44cwaFDh7B7927s27cPH3/8MYYNG4YDBw40+HNe2/OEEA1aHxE1rUmTJuGJJ55AYWEhRo4caXRdcLWgoCAAwDfffCMdla2PwYMHo127dpYKlayICY4MpKenw8vLCykpKTXmbdmyBVu3bsWqVavQsWNHk6d05OXl1Xtbtz5fCIH8/Hz07t0bwI17yVSvs3r0kJu3Uz3fHJ07d8ann36KgQMH1jkgQufOnQEAp0+frvP+P7yZFpH1tWrVCsnJyRg6dCjeeecdPPbYYwBuDMccHh5+2+d7eHhg6tSpmDp1Kq5evYrBgwdj/vz5tSY4AGBnZ4fhw4dj+PDhePPNN/Haa6/hpZdewqFDhxAeHs6+gagFePDBB/Hkk0/i2LFj+Pjjj00uM3r0aCQnJ+Ojjz4yK8Eh5eApalZ27do1bNmyBaNGjcK4ceNqPOLj41FWVoYdO3bgH//4B44dO4bjx49Lz//999/Nul/Ohx9+aHTIdtOmTbh48aI0IklISAi8vLywatUq6HQ6abm9e/fi+++/R1RUlNl1fPjhh1FVVYVXX321xry//voLxcXFAICIiAi4uLggOTkZlZWVRsvd/GtqmzZtUFJSYnYcRGRZQ4YMQf/+/bF8+XK4urpiyJAhePfdd3Hx4sUay/7+++/S/3/88YfRPGdnZ3Tp0sWoz7nVlStXapRV38yz+nlt2rQBAKlPISLlcXZ2RmpqKubPn4/Ro0ebXCYsLAz3338/3nvvPWzbtq3G/OvXr+PZZ5+t9zZ/+ukno+HwSf54BMfKduzYgbKyMjzwwAMm5w8YMEC66ee7776L//73v7j//vsxa9YsaZjojh073vb89WoeHh4YNGgQpk6diqKiIixfvhxdunTBE088AeDGr6+vv/46pk6divvuuw8TJ06Uhonu1KkTZs+ebXYd77vvPjz55JNITk7GqVOnEBERAbVajTNnzmDjxo146623MG7cOLi6umLZsmV4/PHH0a9fP0yaNAlt27bFV199hYqKCnzwwQcAgODgYHz88cdITExEv3794OzsXGsnR0RN67nnnsNDDz2EdevWISUlBYMGDUKvXr3wxBNP4M4770RRURGys7Px66+/4quvvgIAdO/eHUOGDEFwcDA8PDxw8uRJbNq0CfHx8bVuZ+HChThy5AiioqLQsWNHXLp0CStXrkSHDh2kO5t37twZ7u7uWLVqFVxcXNCmTRuEhoYiMDCwWdqCiJpHbGzsbZf58MMPERERgbFjx2L06NEYPnw42rRpgzNnzmDDhg24ePFive6FAwDDhw8H8L+h8YEb1yz/97//BXBjgCYAWLRoEYAbZ8M0dohqaiTrDuJGo0ePFg4ODnUOQThlyhShVqvF5cuXxddffy3uu+8+4eDgIO644w7x6quvirVr19Z7mOj169eLpKQk4eXlJRwdHUVUVJT45Zdfamzz448/FnfffbfQaDTCw8NDTJ48Wfz6669Gy8TGxoo2bdrUeO6tw7tWW716tQgODhaOjo7CxcVF9OrVSzz//PPiwoULRsvt2LFD3HvvvcLR0VG4urqK/v37i/Xr10vzr169KiZNmiTc3d0FAGno19qGiTYnRiKq6eZhWm9VVVUlOnfuLDp37iz++usv8dNPP4lHH31U+Pj4CLVaLe644w4xatQosWnTJuk5ixYtEv379xfu7u7C0dFRBAUFicWLF4vr169Ly9z6Gc3MzBRjxowRfn5+wt7eXvj5+YmJEyeKH3/80Sie7du3i+7du4vWrVsb9Qe1DRP973//u0adAIhXXnmlga1FRJZUV/9zs5uHia5WUVEh/vOf/4h+/foJZ2dnYW9vL7p27Spmzpwp8vPzpeWq+5vahqHv2LFjjdtTVO9XmXrcvP9F1qESgldStgSHDx/G0KFDsXHjRpMjjhARERERKQGvwSEiIiIiIsVggkNERERERIrBBIeIiIiIiBSD1+AQEREREZFi8AgOEREREREpBhMcIiIiIiJSDNnd6NNgMODChQtwcXGBSqWydjhEiiKEQFlZGfz8/GBn1/J+32D/QtQ0WnrfArB/IWoqDepfrHgPHpPOnz9f642T+OCDD8s8zp8/b+2Pukm//vqrmDx5svDw8BAODg6iZ8+eRjd3MxgMYu7cucLHx0c4ODiI4cOH17jRY13Yv/DBR9M+5Nq3NAf2L3zw0bQPc/oX2R3BcXFxAQC89957iI6OhlqttnJElqPX63HgwAFERESwXjZAifUqLS2Fv7+/9DmTkz///BMDBw7E0KFDsXfvXrRv3x5nzpxB27ZtpWWWLl2KFStW4IMPPkBgYCDmzp2LyMhIfPfdd3BwcLjtNqrrXVBQgOzsbJt/bZXwHlVCHQBl1KMxdZBz39Jcqut+/vx5uLq6KuI9YY6WVF/WtXk1pH+RXYJTfVjXyckJrq6uinrj6PV61suGKLVeAGR5+sTrr78Of39/pKWlSWWBgYHS/0IILF++HC+//DLGjBkDAPjwww/h7e2Nbdu2YcKECbfdRnW9XVxcFPHaKuE9qoQ6AMqohyXqIMe+pblU193V1VVKcGz9PWGOllRf1tU6zOlfWuaJskQkOzt27EBISAgeeugheHl54e6778aaNWuk+QUFBSgsLER4eLhU5ubmhtDQUGRnZ1sjZCIiIpIh2R3BIaKW6eeff0ZqaioSExPx4osv4sSJE3jmmWdgb2+P2NhYFBYWAgC8vb2Nnuft7S3Nu5VOp4NOp5OmS0tLAdz4Rermv7ZKCfVQQh0AZdSjMXWw5XoTkfIwwSEiWTAYDAgJCcFrr70GALj77rtx+vRprFq1CrGxsQ1aZ3JyMhYsWFCj/NChQ3BycoJWq21UzHKhhHoooQ6AMurRkDpUVFQ0QSRERA3DBIeIZMHX1xfdu3c3KuvWrRs2b94MAPDx8QEAFBUVwdfXV1qmqKgIffv2NbnOpKQkJCYmStPVFyoOHToUOTk5GDFihNXPKW4MvV4PrVZr0/VQQh0AZdSjMXWoPjpKRCQHTHBu0mnObout6+ySKIuti6glGDhwIPLy8ozKfvzxR3Ts2BHAjQEHfHx8kJmZKSU0paWlyMnJwYwZM0yuU6PRQKPR1Civ3nlTq9W17shZsj8AmrZPqKsetkIJdQCUUY+G1MHW62zLbKmvImouTHCISBZmz56Ne++9F6+99hoefvhhHD9+HKtXr8bq1asB3Bg9JSEhAYsWLULXrl2lYaL9/PwQHR1t3eCJiIhINpjgEJEs9OvXD1u3bkVSUhIWLlyIwMBALF++HJMnT5aWef7551FeXo7p06ejuLgYgwYNwr59++p1DxwiIiJqGZjgEJFsjBo1CqNGjap1vkqlwsKFC7Fw4cJmjIqIiIhsCe+DQ0REREREisEEh4iIiIiIFIMJDhERERERKQYTHCIiIiIiUgwmOEREREREpBhMcIiIiIiISDGY4BARERERkWIwwSEiIiIiIsVggkNERERERIrBBIeIiIiIiBSDCQ4RERERESkGExwiIiIiIlIMJjhERERERKQYTHCIiIiIiEgxmOAQEREREZFiMMEhIiIiIiLFYIJDRERERESKwQSHiIiIiIgUgwkOEREREREpBhMcIiIiIiJSDCY4RERERESkGExwiIiIiIhIMZjgEBERERGRYpiV4KSmpqJ3795wdXWFq6srwsLCsHfvXml+ZWUl4uLi4OnpCWdnZ8TExKCoqMjiQRMREREREZliVoLToUMHLFmyBLm5uTh58iSGDRuGMWPG4NtvvwUAzJ49Gzt37sTGjRuRlZWFCxcuYOzYsU0SOBERERER0a1am7Pw6NGjjaYXL16M1NRUHDt2DB06dMDatWuRkZGBYcOGAQDS0tLQrVs3HDt2DAMGDLBc1ERERERERCY0+BqcqqoqbNiwAeXl5QgLC0Nubi70ej3Cw8OlZYKCghAQEIDs7GyLBEtERERERFQXs47gAMA333yDsLAwVFZWwtnZGVu3bkX37t1x6tQp2Nvbw93d3Wh5b29vFBYW1ro+nU4HnU4nTZeWlkr/6/V6c8NrFE0rYbF1mYq9uqy569XUWC/boaS6EBEREZlidoJz11134dSpUygpKcGmTZsQGxuLrKysBgeQnJyMBQsWmJyn1WobvN6GWNrfcuvas2dPrfOau17NhfWSv4qKCmuHQERELUinObsttq6zS6Isti5SNrMTHHt7e3Tp0gUAEBwcjBMnTuCtt97C+PHjcf36dRQXFxsdxSkqKoKPj0+t60tKSkJiYqI0XVpaCn9/fwDAiBEjoFarzQ2xwXrO32+xdZ2eH1mjTK/XQ6vVNnu9mhrrZTtuPkJKREREpERmJzi3MhgM0Ol0CA4OhlqtRmZmJmJiYgAAeXl5OHfuHMLCwmp9vkajgUajMTlPrVY3646lrkplsXXVFXdz16u5sF7yp5R6EBEREdXGrAQnKSkJI0eOREBAAMrKypCRkYHDhw9j//79cHNzw7Rp05CYmAgPDw+4urpi5syZCAsL4whqRERERETULMxKcC5duoRHH30UFy9ehJubG3r37o39+/djxIgRAIBly5bBzs4OMTEx0Ol0iIyMxMqVK5skcCIiIiIioluZleCsXbu2zvkODg5ISUlBSkpKo4IiIiIiIiJqiEZfg0NEREREytDQUc80rQSW9r8xYJMlr2kmaogG3+iTiIiIyBYkJyejX79+cHFxgZeXF6Kjo5GXl2e0TGVlJeLi4uDp6QlnZ2fExMSgqKjIShETUWMwwSEiIiJFy8rKQlxcHI4dOwatVgu9Xo+IiAiUl5dLy8yePRs7d+7Exo0bkZWVhQsXLmDs2LFWjJqIGoqnqBEREZGi7du3z2h63bp18PLyQm5uLgYPHoySkhKsXbsWGRkZGDZsGAAgLS0N3bp1w7FjxzgaLJGNYYJDRERELUpJSQkAwMPDAwCQm5sLvV6P8PBwaZmgoCAEBAQgOzvbZIKj0+mg0+mk6eobKev1eulRPd2UNK1Ek66/vjR2wuhvU2jqtqyv5npt5UAOdW3ItpngEBERUYthMBiQkJCAgQMHomfPngCAwsJC2Nvbw93d3WhZb29vFBYWmlxPcnIyFixYUKP8wIEDcHJykqa1Wq3lgjdhaf8mXb3ZXg0xNNm69+zZ02Trboimfm3lxJp1raioMPs5THCISJaWLFmCpKQkzJo1C8uXLwdw4yLgf/3rX9iwYYPRvba8vb2tGywR2Yy4uDicPn0aR48ebdR6kpKSkJiYKE2XlpbC398fERERcHV1hV6vh1arxYgRI6BWqxsbdq16zt/fZOs2h8ZO4NUQA+aetIPO0DSjqJ2eH9kk6zVXc722ciCHulYfHTUHExwikp0TJ07g3XffRe/evY3KZ8+ejd27d2Pjxo1wc3NDfHw8xo4di88++8xKkRKRLYmPj8euXbtw5MgRdOjQQSr38fHB9evXUVxcbHQUp6ioCD4+PibXpdFooNFoapSr1WqjHcFbpy1NbkMy6wyqJotJbslEU7+2cmLNujZkuxxFjYhk5erVq5g8eTLWrFmDtm3bSuXVFwG/+eabGDZsGIKDg5GWlobPP/8cx44ds2LERCR3QgjEx8dj69atOHjwIAIDA43mBwcHQ61WIzMzUyrLy8vDuXPnEBYW1tzhElEjMcEhIlmJi4tDVFSU0cW+wO0vAiYiqk1cXBw++ugjZGRkwMXFBYWFhSgsLMS1a9cAAG5ubpg2bRoSExNx6NAh5ObmYurUqQgLC+MIakQ2yKZPUWvo3XaJSJ42bNiAL774AidOnKgxryEXAdc1ytHNf02x9MhETTECjRxGt2ksJdQBUEY9GlMHudc7NTUVADBkyBCj8rS0NEyZMgUAsGzZMtjZ2SEmJsboGj8isj02neAQkXKcP38es2bNglarhYODg0XWWdsoR4cOHYKTk1Odo8JYemSiphz9Rwkj+SihDoAy6tGQOjRklKPmJMTtf7BwcHBASkoKUlJSmiEiImpKTHCISBZyc3Nx6dIl3HPPPVJZVVUVjhw5gnfeeQf79+83+yLg2kY5Gjp0KHJycuocFcbSIxM1xeg/chjdprGUUAdAGfVoTB0aMsoREVFTYYJDRLIwfPhwfPPNN0ZlU6dORVBQEF544QX4+/tLFwHHxMQAuP1FwHWNclT9t7YdOUuPAtSUO71KGMlHCXUAlFGPhtTB1utMRMrCBKeJmLo+SNNKYGn/G78Mm7vzdHZJlKVCI5IlFxcX6aZ71dq0aQNPT0+pvPoiYA8PD7i6umLmzJm8CJiIiIiMMMEhIpvBi4CJiIjodpjgEJFsHT582GiaFwETERHR7fA+OEREREREpBhMcIiIiIiISDGY4BARERERkWIwwSEiIiIiIsXgIANEREREzcjUrSSIyHJ4BIeIiIiIiBSDCQ4RERERESkGExwiIiIiIlIMJjhERERERKQYTHCIiIiIiEgxmOAQEREREZFiMMEhIiIiIiLFMCvBSU5ORr9+/eDi4gIvLy9ER0cjLy/PaJnKykrExcXB09MTzs7OiImJQVFRkUWDJiIiIiIiMsWsBCcrKwtxcXE4duwYtFot9Ho9IiIiUF5eLi0ze/Zs7Ny5Exs3bkRWVhYuXLiAsWPHWjxwIiIiIiKiW7U2Z+F9+/YZTa9btw5eXl7Izc3F4MGDUVJSgrVr1yIjIwPDhg0DAKSlpaFbt244duwYBgwYYLnIiYiIiIiIbmFWgnOrkpISAICHhwcAIDc3F3q9HuHh4dIyQUFBCAgIQHZ2tskER6fTQafTSdOlpaXS/3q9vs7ta1qJxoTf7DR2wuivOW7XFtZUHZucY2wIJdZLSXUhIiIiMqXBCY7BYEBCQgIGDhyInj17AgAKCwthb28Pd3d3o2W9vb1RWFhocj3JyclYsGCByXlarbbOGJb2Nz9uOXg1xGD2c/bs2dMEkVjW7V4vW6WkelVUVFg7BCIiIqIm1eAEJy4uDqdPn8bRo0cbFUBSUhISExOl6dLSUvj7+wMARowYAbVaXetze87f36htNzeNncCrIQbMPWkHnUFl1nNPz49soqgaT6/XQ6vV3vb1sjVKrNfNR0iJiIiIlKhBCU58fDx27dqFI0eOoEOHDlK5j48Prl+/juLiYqOjOEVFRfDx8TG5Lo1GA41GY3KeWq2uc8dSV2VekiAXOoPK7NhtYQf7dq+XrVJSvZRSDyIiIqLamDWKmhAC8fHx2Lp1Kw4ePIjAwECj+cHBwVCr1cjMzJTK8vLycO7cOYSFhVkmYiIiIiIiolqYdQQnLi4OGRkZ2L59O1xcXKTratzc3ODo6Ag3NzdMmzYNiYmJ8PDwgKurK2bOnImwsDCOoEZERERERE3OrAQnNTUVADBkyBCj8rS0NEyZMgUAsGzZMtjZ2SEmJgY6nQ6RkZFYuXKlRYIlIrJVnebstti6zi6Jsti6iIiIlMasBEeI2w9v7ODggJSUFKSkpDQ4KCIiIiIiooYw6xocIiIiIiIiOWOCQ0REREREisEEh4iIiIiIFIMJDhERERERKQYTHCIiIiIiUgwmOEREREREpBhMcIiIiIiISDGY4BARERERkWKYdaNPIiIiIiJr6DRnt0XXd3ZJlEXXR/LBIzhERERERKQYTHCIiIiIiEgxmOAQEREREZFiMMEhIiIiIiLFYIJDRERERESKwQSHiIiIFO3IkSMYPXo0/Pz8oFKpsG3bNqP5QgjMmzcPvr6+cHR0RHh4OM6cOWOdYImo0ZjgEBERkaKVl5ejT58+SElJMTl/6dKlWLFiBVatWoWcnBy0adMGkZGRqKysbOZIicgSeB8cIiIiUrSRI0di5MiRJucJIbB8+XK8/PLLGDNmDADgww8/hLe3N7Zt24YJEyY0Z6hEZAE8gkNEspCcnIx+/frBxcUFXl5eiI6ORl5entEylZWViIuLg6enJ5ydnRETE4OioiIrRUxESlBQUIDCwkKEh4dLZW5ubggNDUV2drYVIyOihuIRHCKShaysLMTFxaFfv37466+/8OKLLyIiIgLfffcd2rRpAwCYPXs2du/ejY0bN8LNzQ3x8fEYO3YsPvvsMytHT0S2qrCwEADg7e1tVO7t7S3NM0Wn00Gn00nTpaWlAAC9Xi89qqdvpWklGh233GjshNFfW2DqtTHneQ19vi2RQ10bsm0mOEQkC/v27TOaXrduHby8vJCbm4vBgwejpKQEa9euRUZGBoYNGwYASEtLQ7du3XDs2DEMGDDAGmETUQuVnJyMBQsW1Cg/cOAAnJycpGmtVltjmaX9mzQ0q3o1xGDtEOptz549jXq+qddWqaxZ14qKCrOfwwSHiGSppKQEAODh4QEAyM3NhV6vNzqNJCgoCAEBAcjOzjaZ4NT1C+vNf02R8y+st8Zvy78iKqEOgDLq0Zg62HK9fXx8AABFRUXw9fWVyouKitC3b99an5eUlITExERpurS0FP7+/oiIiICrqyv0ej20Wi1GjBgBtVpt9Nye8/dbthIyoLETeDXEgLkn7aAzqKwdTr2cnh/ZoOfV9doqjRzqWv3dbQ4mOEQkOwaDAQkJCRg4cCB69uwJ4MZpJPb29nB3dzdatq7TSGr7hfXQoUNwcnKq8xcpOf/Ceuuvjkr4FVEJdQCUUY+G1KEhv7DKRWBgIHx8fJCZmSklNKWlpcjJycGMGTNqfZ5Go4FGo6lRrlarjXYEb50GAF2VbSQADaEzqGymfo3dYTf12iqVNevakO0ywSEi2YmLi8Pp06dx9OjRRq2ntl9Yhw4dipycnDp/kZLzL6zVvzrK4Ze1xlJCHQBl1KMxdWjIL6zN6erVq8jPz5emCwoKcOrUKXh4eCAgIAAJCQlYtGgRunbtisDAQMydOxd+fn6Ijo62XtBE1GBMcIhIVuLj47Fr1y4cOXIEHTp0kMp9fHxw/fp1FBcXGx3FKSoqkk4xuVVdv7BW/61tR07Ov0DeGrMSfkVUQh0AZdSjIXWQe51PnjyJoUOHStPVP3zExsZi3bp1eP7551FeXo7p06ejuLgYgwYNwr59++Dg4GCtkImoEZjgEJEsCCEwc+ZMbN26FYcPH0ZgYKDR/ODgYKjVamRmZiImJgYAkJeXh3PnziEsLMwaIRORjRgyZAiEqP26OpVKhYULF2LhwoXNGBURNRUmOEQkC3FxccjIyMD27dvh4uIiXVfj5uYGR0dHuLm5Ydq0aUhMTISHhwdcXV0xc+ZMhIWFcQQ1IiIikjDBISJZSE1NBXDjl9abpaWlYcqUKQCAZcuWwc7ODjExMdDpdIiMjMTKlSubOVIiIiKSMyY4RCQL/6+9u4+Lqs7///8cEAZIAQXlIhGxXK8vVg0iLW1DybU2V1etdVs0u8aS2N3Sdr3cNVrbSnNNc7e02sy00rY0k/Dqa6KpZea6kRqmm4GlcaEGTsz790c/5tMEyoUDzBwf99uNW877vOec94sz5908OWfOnO/ykUpBQUFasGCBFixY0AgjAgAAvsivrk/YsmWLbrzxRsXGxspms2n16tVuy40xmjZtmmJiYhQcHKyUlBQdOHDAU+MFAAAAgHOq8xmc06dPq1evXrrttts0YsSIKsvnzJmjp556Ss8//7zrVoupqanav38/dyMBAA9oP3mNpO+/jHRO4ve3tL6Qu74dfnSYp4YGAECTq3PAGTp0qIYOHVrtMmOM5s6dqz/96U+66aabJEkvvPCCoqKitHr1at18880XNloAAAAAOI86X6J2Pvn5+SooKFBKSoqrLSwsTElJScrNzfXkpgAAAACgCo/eZKDytq5RUVFu7VFRUa5lP1ZeXq7y8nLX4x9+G7LD4Tjv9uz+NX8o2ZvY/Yzbf+uipt9FU6ocmzePsT6sWJeVagEAAKhOk99FLSsrSzNnzqx2WXZ29nmfOyexIUbU8P7cz1nn56xdu7YBRuJZNe0vX2Wlus6cOdPUQwAAAGhQHg040dHRkqTCwkLFxMS42gsLC9W7d+9qnzNlyhRlZma6HpeUlCguLk6SNHjwYAUEBJxze91nvOOBUTceu5/Rn/s5NXWXn8qddftA8L4ZqQ00qgvncDiUnZ1d4/7yNVas64dnSAEAAKzIowEnISFB0dHRysnJcQWakpIS7dixQ/fcc0+1z7Hb7bLb7dUuCwgIOO8bywu5a1BTKnfa6jx2X3iDXdP+8lVWqssqdQAAcKEq70hZV9XdwZK7UXqXOgecU6dO6eDBg67H+fn52rNnj1q1aqV27dopIyNDf/nLX9SxY0fXbaJjY2M1fPhwT44bAAAAAKqoc8DZtWuXrr32WtfjysvL0tLStHTpUj344IM6ffq07rzzThUVFWnAgAFat24d34FjYd1nvOOR7+KoxF9BAAAAUF91DjiDBg2SMee+C5jNZtOsWbM0a9asCxoYAAAAANSVR78HBwAAAACaUpPfJhq1U98PwlWHS8AAAABgVZzBAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAltGsqQcAAAAAwDe0n7zGo+s7/Ogwj65PIuBclDz9wrT7e3R1AAAAQL1xiRoAAAAAyyDgAAAAALAMAg4AAAAAy+AzOAAAAMAF8IUP3l9MOIMDAAAAwDIIOAAAAAAsg4ADAAAAwDIIOAAAAAAsg5sMAAAAAF7EkzctuBhvWEDAAYCLHP8jBQBYCZeoAQAAALAMzuDA61wsf03mnvlA4+KYA4CLA2dwAAAAAFgGAQcAAACAZXCJGgDAa3n6sjIAgPU1WMBZsGCBHnvsMRUUFKhXr16aP3++EhMTG2pzQKPgzZZ3YH4B0BCYWwBraJCA88orrygzM1OLFi1SUlKS5s6dq9TUVOXl5alNmzYNsUkAFwnmF+9W1z8C2P2N5iRK3We8o/IKWwON6uJTnz/GnG9fXAw3VGBuAayjQT6D88QTT+iOO+7Q+PHj1bVrVy1atEghISF67rnnGmJzAC4izC8AGgJzC2AdHj+Dc/bsWe3evVtTpkxxtfn5+SklJUW5ublV+peXl6u8vNz1uLi4WJJ05swZnThxQgEBAefcVrPvTntw5A2vmdPozBmnmjn8VOG0zl8qvbmuEydO1Pu5DoejyuvQm19ztam1tLRUkmSMaejhNAhPzS8nT56scY7x5n1dyZuPvdry5Rp+eMxVN180pfq8fs+3L2qaXy62uUU6//zicDjO+5rwhfmlrnz5WK4rX6vV298LNcj8Yjzsiy++MJLMtm3b3Nr/8Ic/mMTExCr9p0+fbiTxww8/jfhz9OhRTx/6jYL5hR9+vPvnYplbjGF+4Yefxv6py/zS5HdRmzJlijIzM12PnU6nPv/8c/Xu3VtHjx5VaGhoE47Os0pKShQXF0ddPsKKdRljVFpaqtjY2KYeSqOobn45efKkAgIC1K5dO5/ft1Z4jVqhBskadVxIDRfb3CKde36JiIiQzWazxGuiLi6meqm1cdVnfvF4wImMjJS/v78KCwvd2gsLCxUdHV2lv91ul91ud2vz8/v+o0GhoaGWfOFQl2+xWl1hYWFNPYR688T8Eh4erpKSEknW2bdWqMMKNUjWqKO+NVxMc4t07vnlx6zwmqiLi6leam08dZ1fPH6TgcDAQPXt21c5OTmuNqfTqZycHCUnJ3t6cwAuIswvABoCcwtgLQ1yiVpmZqbS0tLUr18/JSYmau7cuTp9+rTGjx/fEJsDcBFhfgHQEJhbAOtokIAzZswYffXVV5o2bZoKCgrUu3dvrVu3TlFRUbV6vt1u1/Tp06uc+vV11OVbrFqXr7vQ+UWyzr61Qh1WqEGyRh1WqOFCeGJu+aGL7fd5MdVLrd7PZoyP3tMRAAAAAH6kQb7oEwAAAACaAgEHAAAAgGUQcAAAAABYBgEHAAAAgGV4ZcBZsGCB2rdvr6CgICUlJen9999v6iHVyZYtW3TjjTcqNjZWNptNq1evdltujNG0adMUExOj4OBgpaSk6MCBA00z2FrKysrSFVdcoRYtWqhNmzYaPny48vLy3PqUlZUpPT1dERERat68uUaOHFnlS9O8zcKFC9WzZ0/XF1glJyfr7bffdi33xZpQM1+aY6x47D366KOy2WzKyMhwtflKDV988YV+85vfKCIiQsHBwerRo4d27drlWu4L83tFRYWmTp2qhIQEBQcH67LLLtOf//xn/fCeQ75Qh7fzpXnmXGbMmCGbzeb207lzZ9fy2hy3R44c0bBhwxQSEqI2bdroD3/4g7777rvGLqUKT7xXO3nypMaOHavQ0FCFh4drwoQJOnXqlFufvXv36uqrr1ZQUJDi4uI0Z86chi6tippqHTduXJX9fP3117v18ZVaXYyXWb58uQkMDDTPPfec+c9//mPuuOMOEx4ebgoLC5t6aLW2du1a88c//tG8/vrrRpJZtWqV2/JHH33UhIWFmdWrV5uPPvrI/OIXvzAJCQnm22+/bZoB10JqaqpZsmSJ2bdvn9mzZ4/5+c9/btq1a2dOnTrl6nP33XebuLg4k5OTY3bt2mWuvPJKc9VVVzXhqGv273//26xZs8Z8+umnJi8vzzz88MMmICDA7Nu3zxjjmzXh/HxtjrHasff++++b9u3bm549e5pJkya52n2hhpMnT5r4+Hgzbtw4s2PHDvPZZ5+Zd955xxw8eNDVxxfm99mzZ5uIiAjz1ltvmfz8fLNy5UrTvHlzM2/ePFcfX6jDm/naPHMu06dPN926dTNffvml6+err75yLa/puP3uu+9M9+7dTUpKivnwww/N2rVrTWRkpJkyZUpTlOPGE+/Vrr/+etOrVy+zfft28//+3/8zl19+ubnllltcy4uLi01UVJQZO3as2bdvn3n55ZdNcHCweeaZZxqrTGNMzbWmpaWZ66+/3m0/nzx50q2Pr9RayesCTmJioklPT3c9rqioMLGxsSYrK6sJR1V/P34hOZ1OEx0dbR577DFXW1FRkbHb7ebll19ughHWz/Hjx40ks3nzZmPM9zUEBASYlStXuvr897//NZJMbm5uUw2zXlq2bGn++c9/Wqom/B9fn2N8+dgrLS01HTt2NNnZ2WbgwIGugOMrNTz00ENmwIAB51zuK/P7sGHDzG233ebWNmLECDN27FhjjO/U4c18fZ6pNH36dNOrV69ql9XmuF27dq3x8/MzBQUFrj4LFy40oaGhpry8vEHHXhf1ea+2f/9+I8ns3LnT1eftt982NpvNfPHFF8YYY55++mnTsmVLt1ofeugh06lTpwau6NzOFXBuuummcz7HF2v1qkvUzp49q927dyslJcXV5ufnp5SUFOXm5jbhyDwnPz9fBQUFbjWGhYUpKSnJp2osLi6WJLVq1UqStHv3bjkcDre6OnfurHbt2vlMXRUVFVq+fLlOnz6t5ORkS9QEd1aYY3z52EtPT9ewYcPcxir5Tg3//ve/1a9fP40aNUpt2rTRT3/6U/3jH/9wLfeV+f2qq65STk6OPv30U0nSRx99pK1bt2ro0KGSfKcOb2WFeeaHDhw4oNjYWHXo0EFjx47VkSNHJNXuuM3NzVWPHj3cviw1NTVVJSUl+s9//tO4hdRBbY6B3NxchYeHq1+/fq4+KSkp8vPz044dO1x9rrnmGgUGBrr6pKamKi8vT998800jVVM7mzZtUps2bdSpUyfdc889OnHihGuZL9barNG3eB5ff/21KioqqnxrcFRUlD755JMmGpVnFRQUSFK1NVYu83ZOp1MZGRnq37+/unfvLun7ugIDAxUeHu7W1xfq+vjjj5WcnKyysjI1b95cq1atUteuXbVnzx6frQnV8/U5xpePveXLl+uDDz7Qzp07qyzzlRo+++wzLVy4UJmZmXr44Ye1c+dO3X///QoMDFRaWprPzO+TJ09WSUmJOnfuLH9/f1VUVGj27NkaO3asJGv8f6op+fo880NJSUlaunSpOnXqpC+//FIzZ87U1VdfrX379tXquC0oKKj291C5zFvV5hgoKChQmzZt3JY3a9ZMrVq1cuuTkJBQZR2Vy1q2bNkg46+r66+/XiNGjFBCQoIOHTqkhx9+WEOHDlVubq78/f19slavCjjwDenp6dq3b5+2bt3a1EPxiE6dOmnPnj0qLi7Wq6++qrS0NG3evLmphwVU4avH3tGjRzVp0iRlZ2crKCioqYdTb06nU/369dMjjzwiSfrpT3+qffv2adGiRUpLS2vi0dXeihUr9NJLL2nZsmXq1q2b9uzZo4yMDMXGxvpUHWh4lWf1JKlnz55KSkpSfHy8VqxYoeDg4CYcGTzp5ptvdv27R48e6tmzpy677DJt2rRJ1113XROOrP686hK1yMhI+fv7V7kDR2FhoaKjo5toVJ5VWYev1jhx4kS99dZb2rhxo9q2betqj46O1tmzZ1VUVOTW3xfqCgwM1OWXX66+ffsqKytLvXr10rx583y6JlTPl+cYXz72du/erePHj6tPnz5q1qyZmjVrps2bN+upp55Ss2bNFBUV5fU1SFJMTIy6du3q1talSxfXJTu+Mr//4Q9/0OTJk3XzzTerR48euvXWW/XAAw8oKytLku/U4a18eZ6pSXh4uH7yk5/o4MGDtZp7oqOjq/09VC7zVrU5BqKjo3X8+HG35d99951Onjzp8/V36NBBkZGROnjwoCTfrNWrAk5gYKD69u2rnJwcV5vT6VROTo6Sk5ObcGSek5CQoOjoaLcaS0pKtGPHDq+u0RijiRMnatWqVdqwYUOV05B9+/ZVQECAW115eXk6cuSIV9dVHafTqfLyckvVhO/54hxjhWPvuuuu08cff6w9e/a4fvr166exY8e6/u3tNUhS//79q9yi+9NPP1V8fLwk35nfz5w5Iz8/9//9+/v7y+l0SvKdOryVL84ztXXq1CkdOnRIMTExtZp7kpOT9fHHH7u9Oc7OzlZoaGiVPxZ4k9ocA8nJySoqKtLu3btdfTZs2CCn06mkpCRXny1btsjhcLj6ZGdnq1OnTl5zeVp1/ve//+nEiROKiYmR5KO1NsmtDc5j+fLlxm63m6VLl5r9+/ebO++804SHh7vdgcPblZaWmg8//NB8+OGHRpJ54oknzIcffmg+//xzY8z3tx4MDw83b7zxhtm7d6+56aabvP72m/fcc48JCwszmzZtcruN4JkzZ1x97r77btOuXTuzYcMGs2vXLpOcnGySk5ObcNQ1mzx5stm8ebPJz883e/fuNZMnTzY2m82sX7/eGOObNeH8fG2Oseqx98O7qBnjGzW8//77plmzZmb27NnmwIED5qWXXjIhISHmX//6l6uPL8zvaWlp5tJLL3XdJvr11183kZGR5sEHH3T18YU6vJmvzTPn8rvf/c5s2rTJ5Ofnm/fee8+kpKSYyMhIc/z4cWNMzcdt5W2ihwwZYvbs2WPWrVtnWrdu7RW3ifbEe7Xrr7/e/PSnPzU7duwwW7duNR07dnS7dXJRUZGJiooyt956q9m3b59Zvny5CQkJafRbJ5+v1tLSUvP73//e5Obmmvz8fPPuu++aPn36mI4dO5qysjKfq7WS1wUcY4yZP3++adeunQkMDDSJiYlm+/btTT2kOtm4caORVOUnLS3NGPP97QenTp1qoqKijN1uN9ddd53Jy8tr2kHXoLp6JJklS5a4+nz77bfm3nvvNS1btjQhISHml7/8pfnyyy+bbtC1cNttt5n4+HgTGBhoWrduba677jpXuDHGN2tCzXxpjrHqsffjgOMrNbz55pume/fuxm63m86dO5vFixe7LfeF+b2kpMRMmjTJtGvXzgQFBZkOHTqYP/7xj263d/WFOrydL80z5zJmzBgTExNjAgMDzaWXXmrGjBnj9r1PtTluDx8+bIYOHWqCg4NNZGSk+d3vfmccDkdjl1KFJ96rnThxwtxyyy2mefPmJjQ01IwfP96Ulpa69fnoo4/MgAEDjN1uN5deeql59NFHG6tEl/PVeubMGTNkyBDTunVrExAQYOLj480dd9xRJYz7Sq2VbMb84KuLAQAAAMCHedVncAAAAADgQhBwAAAAAFgGAQcAAACAZRBwvFj79u01bty4Jtv+uHHj1L59e7e2U6dO6fbbb1d0dLRsNpsyMjJ0+PBh2Ww2LV26tNHHOGjQIA0aNKjRtwsAAADvRMBpIocOHdJdd92lDh06KCgoSKGhoerfv7/mzZunb7/9tqmHd06PPPKIli5dqnvuuUcvvviibr311gbf5v79+zVjxgwdPny4wbcFAAAA38Zd1JrAmjVrNGrUKNntdv32t79V9+7ddfbsWW3dulWvvfaaxo0bp8WLF6t9+/YaNGhQk5wZkSSHwyGn0ym73e5qu/LKK9WsWTNt3brV1WaMUXl5uQICAuTv7+/xcbz66qsaNWqUNm7cWOVszdmzZyV9/8VqAAAAQLOmHsDFJj8/XzfffLPi4+O1YcMG17fESlJ6eroOHjyoNWvWNOEI/09AQECVtuPHj1f59mGbzaagoKDGGpYbgg0AAAB+iEvUGtmcOXN06tQpPfvss27hptLll1+uSZMmVfvckydP6ve//7169Oih5s2bKzQ0VEOHDtVHH31Upe/8+fPVrVs3hYSEqGXLlurXr5+WLVvmWl5aWqqMjAy1b99edrtdbdq00eDBg/XBBx+4+vzwMzibNm2SzWZTfn6+1qxZI5vNJpvNpsOHD5/zMziffPKJRo8erdatWys4OFidOnXSH//4R9fyzz//XPfee686deqk4OBgRUREaNSoUW6Xoi1dulSjRo2SJF177bWu7W7atElS9Z/BOX78uCZMmKCoqCgFBQWpV69eev755936VI75b3/7mxYvXqzLLrtMdrtdV1xxhXbu3Fnt7x8AAADejzM4jezNN99Uhw4ddNVVV9X5uZ999plWr16tUaNGKSEhQYWFhXrmmWc0cOBA7d+/X7GxsZKkf/zjH7r//vv1q1/9SpMmTVJZWZn27t2rHTt26Ne//rUk6e6779arr76qiRMnqmvXrjpx4oS2bt2q//73v+rTp0+VbXfp0kUvvviiHnjgAbVt21a/+93vJEmtW7fWV199VaX/3r17dfXVVysgIEB33nmn2rdvr0OHDunNN9/U7NmzJUk7d+7Utm3bdPPNN6tt27Y6fPiwFi5cqEGDBmn//v0KCQnRNddco/vvv19PPfWUHn74YXXp0sU1nup8++23GjRokA4ePKiJEycqISFBK1eu1Lhx41RUVFQlPC5btkylpaW66667ZLPZNGfOHI0YMUKfffZZtWewAAAA4OUMGk1xcbGRZG666aZa9Y+PjzdpaWmux2VlZaaiosKtT35+vrHb7WbWrFmutptuusl069btvOsOCwsz6enp5+2TlpZm4uPjq4xp2LBhVcYgySxZssTVds0115gWLVqYzz//3K2v0+l0/fvMmTNVtpmbm2skmRdeeMHVtnLlSiPJbNy4sUr/gQMHmoEDB7oez50710gy//rXv1xtZ8+eNcnJyaZ58+ampKTEbcwRERHm5MmTrr5vvPGGkWTefPPNqr8QAAAAeD0uUWtEJSUlkqQWLVrU6/l2u11+ft/vsoqKCp04cULNmzdXp06d3C4tCw8P1//+97/zXmoVHh6uHTt26NixY/Uay/l89dVX2rJli2677Ta1a9fObZnNZnP9Ozg42PVvh8OhEydO6PLLL1d4eLhbPXWxdu1aRUdH65ZbbnG1BQQE6P7779epU6e0efNmt/5jxoxRy5YtXY+vvvpqSd+fLQMAAIDvIeA0otDQUEnff/6lPpxOp5588kl17NhRdrtdkZGRat26tfbu3avi4mJXv4ceekjNmzdXYmKiOnbsqPT0dL333ntu65ozZ4727dunuLg4JSYmasaMGR57U1+5nu7du5+337fffqtp06YpLi7OrZ6ioiK3euri888/V8eOHV1BsFLlJW2ff/65W/uPA1hl2Pnmm2/qtX0AAAA0LQJOIwoNDVVsbKz27dtXr+c/8sgjyszM1DXXXKN//etfeuedd5Sdna1u3brJ6XS6+nXp0kV5eXlavny5BgwYoNdee00DBgzQ9OnTXX1Gjx6tzz77TPPnz1dsbKwee+wxdevWTW+//fYF11lb9913n2bPnq3Ro0drxYoVWr9+vbKzsxUREeFWT0M6122tDXdPBwAA8EncZKCR3XDDDVq8eLFyc3OVnJxcp+e++uqruvbaa/Xss8+6tRcVFSkyMtKt7ZJLLtGYMWM0ZswYnT17ViNGjNDs2bM1ZcoU1y2dY2JidO+99+ree+/V8ePH1adPH82ePVtDhw69oBo7dOggSTUGuVdffVVpaWl6/PHHXW1lZWUqKipy6/fDy9pqEh8fr71798rpdLqdxfnkk09cywEAAGBdnMFpZA8++KAuueQS3X777SosLKyy/NChQ5o3b161z/X3969yZmHlypX64osv3NpOnDjh9jgwMFBdu3aVMUYOh0MVFRVVLgFr06aNYmNjVV5eXp+y3LRu3VrXXHONnnvuOR05csRt2Q/HX1098+fPV0VFhVvbJZdcIklVgk91fv7zn6ugoECvvPKKq+27777T/Pnz1bx5cw0cOLCu5QAAAMCHcAankV122WVatmyZxowZoy5duui3v/2tunfvrrNnz2rbtm2uWxpX54YbbtCsWbM0fvx4XXXVVfr444/10ksvuc6YVBoyZIiio6PVv39/RUVF6b///a/+/ve/a9iwYWrRooWKiorUtm1b/epXv1KvXr3UvHlzvfvuu9q5c6fb2ZQL8dRTT2nAgAHq06eP7rzzTiUkJOjw4cNas2aN9uzZ46rnxRdfVFhYmLp27arc3Fy9++67ioiIcFtX79695e/vr7/+9a8qLi6W3W7Xz372M7Vp06bKdu+8804988wzGjdunHbv3q327dvr1Vdf1Xvvvae5c+fW+wYPAAAA8A0EnCbwi1/8Qnv37tVjjz2mN954QwsXLpTdblfPnj31+OOP64477qj2eQ8//LBOnz6tZcuW6ZVXXlGfPn20Zs0aTZ482a3fXXfdpZdeeklPPPGETp06pbZt2+r+++/Xn/70J0lSSEiI7r33Xq1fv16vv/66nE6nLr/8cj399NO65557PFJjr169tH37dk2dOlULFy5UWVmZ4uPjNXr0aFefefPmyd/fXy+99JLKysrUv39/vfvuu0pNTXVbV3R0tBYtWqSsrCxNmDBBFRUV2rhxY7UBJzg4WJs2bdLkyZP1/PPPq6SkRJ06ddKSJUvOGRwBAABgHTbDp6kBAAAAWASfwQEAAABgGQQcAAAAAJZBwAEAAABgGQQcAAAAAJZBwAEAAABgGQQcAAAAAJbhdd+D43Q6dezYMbVo0UI2m62phwNYijFGpaWlio2NlZ8ff98AAADW43UB59ixY4qLi2vqYQCWdvToUbVt27aphwEAAOBxXhdwWrRoIen7N2ChoaHn7OdwOLR+/XoNGTJEAQEBjTU8j6IG73Ax1VBSUqK4uDjXcQYAAGA1XhdwKi9LCw0NrTHghISEKDQ01KfflFJD07sYa+DyTwAAYFVchA8AAADAMgg4AAAAACyDgAMAAADAMgg4AAAAACyDgAMAAADAMrzuLmrAxaL95DUeW5fd32hOosdWBwAA4LM4gwMAAADAMgg4AAAAACyDgAMAAADAMgg4AAAAACyjzgHniy++0G9+8xtFREQoODhYPXr00K5du1zLjTGaNm2aYmJiFBwcrJSUFB04cMCjgwYAAACA6tQp4HzzzTfq37+/AgIC9Pbbb2v//v16/PHH1bJlS1efOXPm6KmnntKiRYu0Y8cOXXLJJUpNTVVZWZnHBw8AAAAAP1Sn20T/9a9/VVxcnJYsWeJqS0hIcP3bGKO5c+fqT3/6k2666SZJ0gsvvKCoqCitXr1aN998s4eGDQAAAABV1Sng/Pvf/1ZqaqpGjRqlzZs369JLL9W9996rO+64Q5KUn5+vgoICpaSkuJ4TFhampKQk5ebmVhtwysvLVV5e7npcUlIiSXI4HHI4HOccS+Wy8/XxdtTgHZqqBru/8dy6/L5fV001+PJ+AgAAqA2bMabW77KCgoIkSZmZmRo1apR27typSZMmadGiRUpLS9O2bdvUv39/HTt2TDExMa7njR49WjabTa+88kqVdc6YMUMzZ86s0r5s2TKFhITUpyYA53DmzBn9+te/VnFxsUJDQ5t6OAAAAB5Xp4ATGBiofv36adu2ba62+++/Xzt37lRubm69Ak51Z3Di4uL09ddfn/cNmMPhUHZ2tgYPHqyAgIDaluBVqME7NFUN3We847F12f2M/tzPWWMNJSUlioyMJOAAAADLqtMlajExMeratatbW5cuXfTaa69JkqKjoyVJhYWFbgGnsLBQvXv3rnaddrtddru9SntAQECt3mzWtp83owbv0Ng1lFfYPL7Ommrw9X0EAABQkzrdRa1///7Ky8tza/v0008VHx8v6fsbDkRHRysnJ8e1vKSkRDt27FBycrIHhgsAAAAA51anMzgPPPCArrrqKj3yyCMaPXq03n//fS1evFiLFy+WJNlsNmVkZOgvf/mLOnbsqISEBE2dOlWxsbEaPnx4Q4wfAAAAAFzqFHCuuOIKrVq1SlOmTNGsWbOUkJCguXPnauzYsa4+Dz74oE6fPq0777xTRUVFGjBggNatW+e6QQEAAAAANJQ6BRxJuuGGG3TDDTecc7nNZtOsWbM0a9asCxoYAAAAANRVnT6DAwAAAADejIADAAAAwDIIOAAAAAAsg4ADAAAAwDIIOAAAAAAsg4ADAAAAwDIIOAAAAAAsg4ADAAAAwDIIOAAAAAAsg4ADAAAAwDIIOAAAAAAsg4ADAAAAwDKaNfUALlT3Ge+ovMLmkXUdfnSYR9YDAAAAoGlwBgcAAACAZRBwAAAAAFgGAQcAAACAZRBwAAAAAFgGAQcAAACAZRBwAAAAAFgGAQcAAACAZRBwAAAAAFgGAQcAAACAZRBwAAAAAFgGAQcAAACAZRBwAAAAAFgGAQcAAACAZRBwAAAAAFgGAQcAAACAZRBwAAAAAFgGAQcAAACAZRBwAAAAAFgGAQcAAACAZRBwAAAAAFgGAQcAAACAZRBwAAAAAFjGBQWcRx99VDabTRkZGa62srIypaenKyIiQs2bN9fIkSNVWFh4oeMEAAAAgBrVO+Ds3LlTzzzzjHr27OnW/sADD+jNN9/UypUrtXnzZh07dkwjRoy44IECAAAAQE3qFXBOnTqlsWPH6h//+Idatmzpai8uLtazzz6rJ554Qj/72c/Ut29fLVmyRNu2bdP27ds9NmgAAAAAqE69Ak56erqGDRumlJQUt/bdu3fL4XC4tXfu3Fnt2rVTbm7uhY0UAAAAAGrQrK5PWL58uT744APt3LmzyrKCggIFBgYqPDzcrT0qKkoFBQXVrq+8vFzl5eWuxyUlJZIkh8Mhh8NxznFULrP7mbqWUOM6G0vl9hp7u55EDfVn9/fca7fyOKipBl/eTwAAALVRp4Bz9OhRTZo0SdnZ2QoKCvLIALKysjRz5swq7evXr1dISEiNz/9zP6dHxiFJa9eu9di66iI7O7tJtutJ1FB3cxI9v86aajhz5oznNwoAAOBFbMaYWv8ZefXq1frlL38pf39/V1tFRYVsNpv8/Pz0zjvvKCUlRd98843bWZz4+HhlZGTogQceqLLO6s7gxMXF6euvv1ZoaOg5x+JwOJSdna2pu/xU7rTVtoTz2jcj1SPrqa3KGgYPHqyAgIBG3banUEP9dZ/xjsfWZfcz+nM/Z401lJSUKDIyUsXFxec9vgAAAHxVnc7gXHfddfr444/d2saPH6/OnTvroYceUlxcnAICApSTk6ORI0dKkvLy8nTkyBElJydXu0673S673V6lPSAgoFZvNsudNpVXeCbgNNUb9NrW6s2ooe489br9oZpq8PV9BAAAUJM6BZwWLVqoe/fubm2XXHKJIiIiXO0TJkxQZmamWrVqpdDQUN13331KTk7WlVde6blRAwAAAEA16nyTgZo8+eST8vPz08iRI1VeXq7U1FQ9/fTTnt4MAAAAAFRxwQFn06ZNbo+DgoK0YMECLViw4EJXDQAAAAB1Uq/vwQEAAAAAb0TAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZBBwAAAAAlkHAAQAAAGAZdQo4WVlZuuKKK9SiRQu1adNGw4cPV15enlufsrIypaenKyIiQs2bN9fIkSNVWFjo0UEDAAAAQHXqFHA2b96s9PR0bd++XdnZ2XI4HBoyZIhOnz7t6vPAAw/ozTff1MqVK7V582YdO3ZMI0aM8PjAAQAAAODHmtWl87p169weL126VG3atNHu3bt1zTXXqLi4WM8++6yWLVumn/3sZ5KkJUuWqEuXLtq+fbuuvPJKz40cAAAAAH7kgj6DU1xcLElq1aqVJGn37t1yOBxKSUlx9encubPatWun3NzcC9kUAAAAANSoTmdwfsjpdCojI0P9+/dX9+7dJUkFBQUKDAxUeHi4W9+oqCgVFBRUu57y8nKVl5e7HpeUlEiSHA6HHA7HObdfuczuZ+pbwjnX2Vgqt9fY2/Ukaqg/u7/nXruVx0FNNfjyfgIAAKiNegec9PR07du3T1u3br2gAWRlZWnmzJlV2tevX6+QkJAan//nfs4L2v4PrV271mPrqovs7Owm2a4nUUPdzUn0/DprquHMmTOe3ygAAIAXqVfAmThxot566y1t2bJFbdu2dbVHR0fr7NmzKioqcjuLU1hYqOjo6GrXNWXKFGVmZroel5SUKC4uTkOGDFFoaOg5x+BwOJSdna2pu/xU7rTVp4wq9s1I9ch6aquyhsGDBysgIKBRt+0p1FB/3We847F12f2M/tzPWWMNlWdIAQAArKpOAccYo/vuu0+rVq3Spk2blJCQ4La8b9++CggIUE5OjkaOHClJysvL05EjR5ScnFztOu12u+x2e5X2gICAWr3ZLHfaVF7hmYDTVG/Qa1urN6OGuvPU6/aHaqrB1/cRAABATeoUcNLT07Vs2TK98cYbatGihetzNWFhYQoODlZYWJgmTJigzMxMtWrVSqGhobrvvvuUnJzMHdQAAAAANLg6BZyFCxdKkgYNGuTWvmTJEo0bN06S9OSTT8rPz08jR45UeXm5UlNT9fTTT3tksAAAAABwPnW+RK0mQUFBWrBggRYsWFDvQQEAAABAfVzQ9+AAAAAAgDch4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwDAIOAAAAAMsg4AAAAACwjAYLOAsWLFD79u0VFBSkpKQkvf/++w21KQAAAACQ1EAB55VXXlFmZqamT5+uDz74QL169VJqaqqOHz/eEJsDAAAAAEkNFHCeeOIJ3XHHHRo/fry6du2qRYsWKSQkRM8991xDbA4AAAAAJEnNPL3Cs2fPavfu3ZoyZYqrzc/PTykpKcrNza3Sv7y8XOXl5a7HxcXFkqSTJ0/K4XCcczsOh0NnzpxRM4efKpw2j4z9xIkTHllPbVXWcOLECQUEBDTqtj2FGuqv2XenPbcup9GZM84aaygtLZUkGWM8tm0AAABv4vGA8/XXX6uiokJRUVFu7VFRUfrkk0+q9M/KytLMmTOrtCckJHh6aDWKfLzRNwl4zK/r0Le0tFRhYWENNhYAAICm4vGAU1dTpkxRZmam67HT6dTJkycVEREhm+3cZ2ZKSkoUFxeno0ePKjQ0tDGG6nHU4B0uphqMMSotLVVsbGwjjg4AAKDxeDzgREZGyt/fX4WFhW7thYWFio6OrtLfbrfLbre7tYWHh9d6e6GhoT77prQSNXiHi6UGztwAAAAr8/hNBgIDA9W3b1/l5OS42pxOp3JycpScnOzpzQEAAACAS4NcopaZmam0tDT169dPiYmJmjt3rk6fPq3x48c3xOYAAAAAQFIDBZwxY8boq6++0rRp01RQUKDevXtr3bp1VW48cCHsdrumT59e5fI2X0IN3oEaAAAArMNmuF8sAAAAAItokC/6BAAAAICmQMABAAAAYBkEHAAAAACWQcABAAAAYBleEXC2bNmiG2+8UbGxsbLZbFq9enWNz9m0aZP69Okju92uyy+/XEuXLq3SZ8GCBWrfvr2CgoKUlJSk999/3/OD///VtYbXX39dgwcPVuvWrRUaGqrk5GS98847bn1mzJghm83m9tO5c2evqWHTpk1Vxmez2VRQUODWz5v3w7hx46qtoVu3bq4+jb0fsrKydMUVV6hFixZq06aNhg8frry8vBqft3LlSnXu3FlBQUHq0aOH1q5d67bcGKNp06YpJiZGwcHBSklJ0YEDBxqqDAAAgCbhFQHn9OnT6tWrlxYsWFCr/vn5+Ro2bJiuvfZa7dmzRxkZGbr99tvdAsIrr7yizMxMTZ8+XR988IF69eql1NRUHT9+3Ctq2LJliwYPHqy1a9dq9+7duvbaa3XjjTfqww8/dOvXrVs3ffnll66frVu3NsTwJdW9hkp5eXluY2zTpo1rmbfvh3nz5rmN/ejRo2rVqpVGjRrl1q8x98PmzZuVnp6u7du3Kzs7Ww6HQ0OGDNHp06fP+Zxt27bplltu0YQJE/Thhx9q+PDhGj58uPbt2+fqM2fOHD311FNatGiRduzYoUsuuUSpqakqKytrsFoAAAAanfEyksyqVavO2+fBBx803bp1c2sbM2aMSU1NdT1OTEw06enprscVFRUmNjbWZGVleXS81alNDdXp2rWrmTlzpuvx9OnTTa9evTw3sDqoTQ0bN240ksw333xzzj6+th9WrVplbDabOXz4sKutKfeDMcYcP37cSDKbN28+Z5/Ro0ebYcOGubUlJSWZu+66yxhjjNPpNNHR0eaxxx5zLS8qKjJ2u928/PLLDTNwAACAJuAVZ3DqKjc3VykpKW5tqampys3NlSSdPXtWu3fvduvj5+enlJQUVx9v43Q6VVpaqlatWrm1HzhwQLGxserQoYPGjh2rI0eONNEIz613796KiYnR4MGD9d5777nafXE/PPvss0pJSVF8fLxbe1Puh+LiYkmq8tr4oZqOifz8fBUUFLj1CQsLU1JSktfuCwAAgPrwyYBTUFCgqKgot7aoqCiVlJTo22+/1ddff62Kiopq+/z48yHe4m9/+5tOnTql0aNHu9qSkpK0dOlSrVu3TgsXLlR+fr6uvvpqlZaWNuFI/09MTIwWLVqk1157Ta+99pri4uI0aNAgffDBB5Lkc/vh2LFjevvtt3X77be7tTflfnA6ncrIyFD//v3VvXv3c/Y71zFR+Xuu/K+v7AsAAID6atbUA4C0bNkyzZw5U2+88Ybb51eGDh3q+nfPnj2VlJSk+Ph4rVixQhMmTGiKobrp1KmTOnXq5Hp81VVX6dChQ3ryySf14osvNuHI6uf5559XeHi4hg8f7tbelPshPT1d+/bta9DP/AAAAFiJT57BiY6OVmFhoVtbYWGhQkNDFRwcrMjISPn7+1fbJzo6ujGHWqPly5fr9ttv14oVK6pcYvRj4eHh+slPfqKDBw820ujqLjEx0TU+X9oPxhg999xzuvXWWxUYGHjevo21HyZOnKi33npLGzduVNu2bc/b91zHROXvufK/vrAvAAAALoRPBpzk5GTl5OS4tWVnZys5OVmSFBgYqL59+7r1cTqdysnJcfXxBi+//LLGjx+vl19+WcOGDaux/6lTp3To0CHFxMQ0wujqZ8+ePa7x+cp+kL6/c9nBgwdrdUamofeDMUYTJ07UqlWrtGHDBiUkJNT4nJqOiYSEBEVHR7v1KSkp0Y4dO7xuXwAAAFwIr7hE7dSpU25/Dc/Pz9eePXvUqlUrtWvXTlOmTNEXX3yhF154QZJ099136+9//7sefPBB3XbbbdqwYYNWrFihNWvWuNaRmZmptLQ09evXT4mJiZo7d65Onz6t8ePHe0UNy5YtU1pamubNm6ekpCTX5yCCg4MVFhYmSfr973+vG2+8UfHx8Tp27JimT58uf39/3XLLLV5Rw9y5c5WQkKBu3bqprKxM//znP7VhwwatX7/etQ5v3w+Vnn32WSUlJVX7OZfG3g/p6elatmyZ3njjDbVo0cL12ggLC1NwcLAk6be//a0uvfRSZWVlSZImTZqkgQMH6vHHH9ewYcO0fPly7dq1S4sXL5Yk2Ww2ZWRk6C9/+Ys6duyohIQETZ06VbGxsVUuyQMAAPBpTX0bN2P+73bDP/5JS0szxhiTlpZmBg4cWOU5vXv3NoGBgaZDhw5myZIlVdY7f/58065dOxMYGGgSExPN9u3bvaaGgQMHnre/Md/f+jomJsYEBgaaSy+91IwZM8YcPHjQa2r461//ai677DITFBRkWrVqZQYNGmQ2bNhQZb3evB+M+f52ycHBwWbx4sXVrrOx90N145fk9hofOHCg22vFGGNWrFhhfvKTn5jAwEDTrVs3s2bNGrflTqfTTJ061URFRRm73W6uu+46k5eX12B1AAAANAWbMcY0Qo4CAAAAgAbnk5/BAQAAAIDqEHAAAAAAWAYBBwAAAIBlEHAAAAAAWAYBBwAAAIBlEHAAAAAAWAYBBwAAAIBlEHAAAAAAWAYBBwAAAIBlEHAAAAAAWAYBBwAAAIBlEHAAAAAAWMb/B3GAHRomFEmmAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 1000x1000 with 12 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "breast_cancer = pd.read_csv(\"dataR2.csv\")\n",
    "print(breast_cancer.head())\n",
    "\n",
    "print(breast_cancer.describe())\n",
    "\n",
    "print(breast_cancer.info())\n",
    "\n",
    "print(breast_cancer.isnull().sum())\n",
    "\n",
    "breast_cancer.hist(figsize=(10, 10))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classification\n",
      "1    64\n",
      "0    52\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "X = breast_cancer.drop(columns=[\"Classification\"])\n",
    "y = breast_cancer[\"Classification\"].replace({1: 0, 2: 1})\n",
    "\n",
    "print(y.value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of samples: 116\n",
      "Number of features: 9\n",
      "Number of classes: 2\n"
     ]
    }
   ],
   "source": [
    "print(\"Number of samples:\", X.shape[0])\n",
    "print(\"Number of features:\", X.shape[1])\n",
    "print(\"Number of classes:\", len(np.unique(y)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def build_model():\n",
    "    model = tf.keras.models.Sequential([\n",
    "        tf.keras.layers.Dense(16, activation='relu', input_shape=(X.shape[1],), kernel_regularizer=tf.keras.regularizers.l2(0.01)),\n",
    "        tf.keras.layers.Dense(8, activation='relu', kernel_regularizer=tf.keras.regularizers.l2(0.01)),\n",
    "        tf.keras.layers.Dense(1, activation='sigmoid')\n",
    "    ])\n",
    "    model.compile(\n",
    "        optimizer='adam',\n",
    "        loss='binary_crossentropy',\n",
    "        metrics=['accuracy']\n",
    "    )\n",
    "    return model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "train test split and scaling of the features "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.metrics import f1_score, classification_report, confusion_matrix\n",
    "import tensorflow as tf\n",
    "import numpy as np\n",
    "\n",
    "# Splitting the dataset into training and testing sets\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)\n",
    "\n",
    "# Scaling the features\n",
    "scaler = StandardScaler()\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Cross validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/moritzvonsiemens/Library/Python/3.9/lib/python/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step\n",
      "Fold 1 - F1-score : 0.7407\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/moritzvonsiemens/Library/Python/3.9/lib/python/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step\n",
      "Fold 2 - F1-score : 0.8182\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/moritzvonsiemens/Library/Python/3.9/lib/python/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 113ms/step\n",
      "Fold 3 - F1-score : 0.6667\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/moritzvonsiemens/Library/Python/3.9/lib/python/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step\n",
      "Fold 4 - F1-score : 0.7368\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/moritzvonsiemens/Library/Python/3.9/lib/python/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:5 out of the last 5 calls to <function TensorFlowTrainer.make_predict_function.<locals>.one_step_on_data_distributed at 0x14bd8b790> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step\n",
      "Fold 5 - F1-score : 0.6000\n",
      "\n",
      "F1-score moyen sur 5 folds : 0.7125\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import f1_score\n",
    "from sklearn.model_selection import StratifiedKFold\n",
    "from keras.callbacks import EarlyStopping\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "\n",
    "skf = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)\n",
    "f1_scores = []\n",
    "histories = []\n",
    "\n",
    "early_stopping = EarlyStopping(\n",
    "    monitor='val_loss',\n",
    "    patience=10,\n",
    "    restore_best_weights=True,\n",
    "    verbose=1\n",
    ")\n",
    "\n",
    "for fold, (train_idx, val_idx) in enumerate(skf.split(X_train_scaled, y_train), 1):\n",
    "    X_cv_train, X_cv_val = X_train.iloc[train_idx], X_train.iloc[val_idx]\n",
    "    y_cv_train, y_cv_val = y_train.iloc[train_idx], y_train.iloc[val_idx]\n",
    "    \n",
    "    model = build_model()\n",
    "\n",
    "    model.compile(\n",
    "        optimizer='adam',\n",
    "        loss='binary_crossentropy',\n",
    "        metrics=[\"f1_score\"]\n",
    "    )\n",
    "\n",
    "    # EarlyStopping\n",
    "    callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True)\n",
    "\n",
    "    # Entraînement\n",
    "    history = model.fit(\n",
    "        X_cv_train, y_cv_train,\n",
    "        epochs=50,\n",
    "        batch_size=8,\n",
    "        validation_data=(X_cv_val, y_cv_val),\n",
    "        callbacks=[callback],\n",
    "        verbose=0,\n",
    "        class_weight={0: 1.0, 1: 2.0}\n",
    "    )\n",
    "    \n",
    "    histories.append(history.history)\n",
    "\n",
    "    # Prédiction & F1\n",
    "    y_pred_val = (model.predict(X_cv_val) > 0.5).astype(int)\n",
    "    score = f1_score(y_cv_val, y_pred_val)\n",
    "    f1_scores.append(score)\n",
    "    print(f\"Fold {fold} - F1-score : {score:.4f}\")\n",
    "\n",
    "print(f\"\\nF1-score moyen sur 5 folds : {np.mean(f1_scores):.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x1200 with 5 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(3, 2, figsize=(12, 12), sharey=True)  # 3 rows, 2 columns\n",
    "axes = axes.flatten()  # Flatten to easily iterate\n",
    "\n",
    "for i, (hist, ax) in enumerate(zip(histories, axes)):\n",
    "    ax.plot(hist['loss'], label='Train loss', alpha=0.6)\n",
    "    ax.plot(hist['val_loss'], label='Val loss', linestyle='--', alpha=0.6)\n",
    "    ax.set_title(f\"Fold {i+1}\")\n",
    "    ax.set_xlabel(\"Epochs\")\n",
    "    if i % 2 == 0:\n",
    "        ax.set_ylabel(\"Binary Crossentropy\")\n",
    "    ax.legend(fontsize=8)\n",
    "    ax.grid(True)\n",
    "\n",
    "# Hide any unused subplots if histories < 6\n",
    "for j in range(len(histories), len(axes)):\n",
    "    fig.delaxes(axes[j])\n",
    "\n",
    "plt.suptitle(\"Evolution of the loss on each fold\")\n",
    "plt.tight_layout(rect=[0, 0, 1, 0.96])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In the context of binary classification using the Breast Cancer Coimbra dataset, preserving the class distribution during data splitting is essential for ensuring the validity of experimental results.\n",
    "\n",
    "1. Use of stratify=y in train_test_split\n",
    "When splitting the dataset into a training set and a test set, we use the train_test_split function from the scikit-learn library. To ensure that the proportions of the target classes are preserved in both subsets, the argument stratify=y is used.\n",
    "\n",
    "This precaution is particularly important when working with imbalanced datasets, as is the case here, where the two classes of the target variable (\"Classification\") are not equally represented. Simple random sampling could introduce a significant class imbalance in the test set, making performance metrics unreliable and potentially favoring one class over the other. The stratify=y option therefore ensures statistical representativeness of the classes in each subset.\n",
    "\n",
    "2. Use of StratifiedKFold for cross-validation\n",
    "Similarly, for model evaluation through cross-validation, we chose to use the StratifiedKFold method. Unlike standard cross-validation (KFold), this method ensures that the class proportions are maintained in each of the k folds.\n",
    "\n",
    "The goal is to obtain a more robust and stable estimate of model performance, particularly in the presence of class imbalance. Preserving the structure of the original dataset within each fold reduces the risk of overfitting or underfitting on certain folds dominated by a single class.\n",
    "\n",
    "3. Statistical Justification\n",
    "Maintaining class distribution during sampling procedures is a classic requirement in statistics, based on the principle of sample representativeness. In supervised classification, systematically using stratified methods improves the external validity of results (the model’s ability to generalize) while reducing the variance of estimates obtained during cross-validation."
]

  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/moritzvonsiemens/Library/Python/3.9/lib/python/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:6 out of the last 6 calls to <function TensorFlowTrainer.make_predict_function.<locals>.one_step_on_data_distributed at 0x14ca5d3a0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "     Healthy       0.50      0.09      0.15        11\n",
      "      Cancer       0.55      0.92      0.69        13\n",
      "\n",
      "    accuracy                           0.54        24\n",
      "   macro avg       0.52      0.51      0.42        24\n",
      "weighted avg       0.52      0.54      0.44        24\n",
      "\n",
      "0.6857142857142857\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model = build_model()\n",
    "\n",
    "model.compile(\n",
    "    optimizer='adam',\n",
    "    loss='binary_crossentropy'\n",
    ")\n",
    "\n",
    "callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True)\n",
    "\n",
    "history = model.fit(\n",
    "    X_train_scaled, y_train,\n",
    "    epochs=50,\n",
    "    batch_size=8,\n",
    "    validation_split=0.2,\n",
    "    callbacks=[callback],\n",
    "    verbose=0,\n",
    "    class_weight={0: 1.0, 1: 2.0}\n",
    ")\n",
    "\n",
    "\n",
    "y_pred_test = (model.predict(X_test_scaled) > 0.5).astype(int)\n",
    "\n",
    "print(classification_report(y_test, y_pred_test, target_names=[\"Healthy\", \"Cancer\"]))\n",
    "print(f1_score(y_test, y_pred_test))\n",
    "\n",
    "## Confusion matrix\n",
    "conf = sns.heatmap(confusion_matrix(y_true=y_test, y_pred=y_pred_test), annot=True, cmap=\"Blues\", xticklabels=[\"Negatives\", \"Positives\"], yticklabels=[\"Negatives\", \"Positives\"])\n",
    "conf.set_xlabel(\"Predictions\")\n",
    "conf.set_ylabel(\"Test data\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(8, 5))\n",
    "plt.plot(history.history['loss'], label='Loss (train)')\n",
    "plt.plot(history.history['val_loss'], label='Loss (val)', linestyle='--')\n",
    "plt.xlabel('Epochs')\n",
    "plt.ylabel('Binary Cross-Entropy Loss')\n",
    "plt.title('Learning curve')\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "While training my neural network on the Breast Cancer Coimbra dataset, I obtained an F1 score of 0.75, indicating a good ability of the model to detect positive cases (sick patients) while limiting false positives.\n",
    "\n",
    "A particular behavior observed during training is that the val_loss is consistently lower than the train_loss. This phenomenon is mainly explained by the use of L2 regularization, which penalizes the weights only during the training phase, and not during evaluation on the validation data.\n",
    "Additionally, the small size of the dataset, the use of class_weights to compensate for the slight class imbalance, and the use of early stopping can accentuate this gap.\n",
    "\n",
    "This behavior is not problematic as long as the validation performance remains stable and satisfactory, which is the case here with a high F1 score — a priority metric in a medical context where recall is crucial."
]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}