orochford/Brim and NetworkX First steps Notebook Final Basic (1).ipynb

## Brim and NetworkX First steps Notebook Final Basic (1).ipynb
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "import zqd as zqd\n",
    "import pandas as pd\n",
    "import networkx as nx\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "#space = 'tzng'\n",
    "space='2020-09-01-Emotet-epoch-3-infection-with-Trickbot-gtag-mor119.pcap'\n",
    "\n",
    "zql = '_path=conn | cut id.orig_h, id.resp_h, proto | sort id.orig_h, id.resp_h'\n",
    "\n",
    "# Create ZQD client instance\n",
    "c = zqd.Client()  \n",
    "\n",
    "# Send ZQL query to ZQD\n",
    "s = c.search(space, zql)\n",
    "\n",
    "# Create dataframe and flatten json/dictionary\n",
    "df = pd.json_normalize(s)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Validating our data\n",
    "Now that we've imported our data into a Pandas Dataframe, we should conduct some validation to make sure everything worked out as expected"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "167"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# How many records does our dataframe contain?\n",
    "len(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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>proto</th>\n",
       "      <th>id.orig_h</th>\n",
       "      <th>id.resp_h</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>tcp</td>\n",
       "      <td>10.9.1.101</td>\n",
       "      <td>5.149.253.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>tcp</td>\n",
       "      <td>10.9.1.101</td>\n",
       "      <td>5.149.253.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>tcp</td>\n",
       "      <td>10.9.1.101</td>\n",
       "      <td>5.149.253.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>udp</td>\n",
       "      <td>10.9.1.101</td>\n",
       "      <td>10.9.1.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>udp</td>\n",
       "      <td>10.9.1.101</td>\n",
       "      <td>10.9.1.1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  proto   id.orig_h     id.resp_h\n",
       "0   tcp  10.9.1.101  5.149.253.99\n",
       "1   tcp  10.9.1.101  5.149.253.99\n",
       "2   tcp  10.9.1.101  5.149.253.99\n",
       "3   udp  10.9.1.101      10.9.1.1\n",
       "4   udp  10.9.1.101      10.9.1.1"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's take a look at the first 5 records\n",
    "df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>proto</th>\n",
       "      <th>id.orig_h</th>\n",
       "      <th>id.resp_h</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>162</th>\n",
       "      <td>udp</td>\n",
       "      <td>10.9.1.101</td>\n",
       "      <td>224.0.0.252</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>163</th>\n",
       "      <td>udp</td>\n",
       "      <td>10.9.1.101</td>\n",
       "      <td>239.255.255.250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>164</th>\n",
       "      <td>udp</td>\n",
       "      <td>10.9.1.101</td>\n",
       "      <td>239.255.255.250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>165</th>\n",
       "      <td>udp</td>\n",
       "      <td>10.9.1.101</td>\n",
       "      <td>239.255.255.250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>tcp</td>\n",
       "      <td>88.247.212.56</td>\n",
       "      <td>10.9.1.101</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    proto      id.orig_h        id.resp_h\n",
       "162   udp     10.9.1.101      224.0.0.252\n",
       "163   udp     10.9.1.101  239.255.255.250\n",
       "164   udp     10.9.1.101  239.255.255.250\n",
       "165   udp     10.9.1.101  239.255.255.250\n",
       "166   tcp  88.247.212.56       10.9.1.101"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# And the last 5\n",
    "df.tail(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "proto        object\n",
       "id.orig_h    object\n",
       "id.resp_h    object\n",
       "dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Which columns and data types are in our DataFrame?\n",
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "proto        0\n",
       "id.orig_h    0\n",
       "id.resp_h    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's check that there are no empty fields\n",
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# If there are, let's drop them\n",
    "df.dropna(axis=0, how='any', inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# How many unique source hosts are in our dataframe?\n",
    "df['id.orig_h'].nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "29"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# How many unique destination hosts are in our dataframe?\n",
    "df['id.resp_h'].nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "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>proto</th>\n",
       "      <th>id.orig_h</th>\n",
       "      <th>id.resp_h</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>167</td>\n",
       "      <td>167</td>\n",
       "      <td>167</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>tcp</td>\n",
       "      <td>10.9.1.101</td>\n",
       "      <td>10.9.1.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>109</td>\n",
       "      <td>166</td>\n",
       "      <td>41</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       proto   id.orig_h id.resp_h\n",
       "count    167         167       167\n",
       "unique     2           2        29\n",
       "top      tcp  10.9.1.101  10.9.1.1\n",
       "freq     109         166        41"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Describe our columns and associated metrics\n",
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Generating a Network Graph\n",
    "NetworkX is a Network Graph library that supports the generation, creation, manipulation and visualization of network graphs. Network Graphs are very useful to model and analyze data that represents flows, relationships or connections. This makes the especially useful to analyze data from social networks, email communications, or in our example, network data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Our data is now in a usable format to generate a network graph of the TCP/IP connections\n",
    "\n",
    "Network Graphs view the world through Nodes and Edges. Translating these to our network world, a Node is a host, and an Edge\n",
    "is a connection between two hosts. We can also dress the Edges (our connections) with data that desribe them. In our example \n",
    "we will distinguish between TCP, UDP and ICMP traffic\n",
    "\n",
    "\n",
    "Because our ZQL query already returned our data in a way we can directly use, we can use the networkX \"from_pandas_edglist\" \n",
    "function.\n",
    "Our Data:\n",
    "[(id.orig_h id.resp_h), proto]\n",
    "[(Source Node, Target Node), Edge Attribute]\n",
    " <----- EDGE ------------->\n",
    "\n",
    "networkx.from_pandas_edglist expects the input to be the Source and Target Nodes, followed by any additional attributes.\n",
    "In our example, setting \"edge_att=True\" means that any additional values in our pandas dataframe will be added as edge attributes.\n",
    " \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create our graph and create our edge and node lists\n",
    "G = nx.from_pandas_edgelist(df, source='id.orig_h', target='id.resp_h', edge_attr=True, create_using=nx.DiGraph())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Networkx suppports 4 basic Graph types (see https://networkx.org/documentation/stable/reference/classes/index.html). For our purposes we want to use what is called a Directed Graph, so that we can map the direction of our connections.\n",
    "\n",
    "Let's start investigting the graph we've just built"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "29"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# How many nodes are in our dataset?\n",
    "G.number_of_nodes()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "29"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# How many edges?\n",
    "G.number_of_edges()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DiDegreeView({IPv4Address('10.9.1.101'): 29, IPv4Address('5.149.253.99'): 1, IPv4Address('10.9.1.1'): 1, IPv4Address('10.9.1.255'): 1, IPv4Address('36.94.33.102'): 1, IPv4Address('40.90.22.184'): 1, IPv4Address('40.90.22.186'): 1, IPv4Address('45.127.222.8'): 1, IPv4Address('45.138.158.32'): 1, IPv4Address('45.230.228.26'): 1, IPv4Address('52.109.8.20'): 1, IPv4Address('52.114.158.50'): 1, IPv4Address('52.158.208.111'): 1, IPv4Address('54.221.234.156'): 1, IPv4Address('62.108.35.9'): 1, IPv4Address('81.169.145.161'): 1, IPv4Address('82.146.46.220'): 1, IPv4Address('86.104.194.116'): 1, IPv4Address('88.247.212.56'): 2, IPv4Address('118.110.236.121'): 1, IPv4Address('185.164.32.214'): 1, IPv4Address('195.123.240.252'): 1, IPv4Address('195.123.241.90'): 1, IPv4Address('195.123.242.119'): 1, IPv4Address('198.46.198.139'): 1, IPv4Address('203.176.135.102'): 1, IPv4Address('224.0.0.251'): 1, IPv4Address('224.0.0.252'): 1, IPv4Address('239.255.255.250'): 1})"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# How many degrees?\n",
    "G.degree()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check if the graph is directed\n",
    "G.is_directed()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visualizing our Network Graph\n",
    "Now we have created our network graph, we can visualize it using NetworkX’s default settings. With a nice small dataset, this works quite well, While it’s not pretty, we can clearly see the connections emanating from the two central nodes.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAV0AAADnCAYAAAC9roUQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOydd1hT1xvHv9kJCXuKTFFBcVVxVUShDqCOigsQpY4iTrRatYiKsypateJGa1VaacFViiJSRepPrANQEFRQkKWIMoVAQs7vjzRXYsJGa9t8nodHybn3nHMvyZtz3/c935dGCIEKFSpUqHg/0P/uCahQoULFfwmV0VWhQoWK94jK6KpQoULFe0RldFWoUKHiPaIyuipUqFDxHmE21Kinp0csLCze01RUqFCh4t/B7du3iwgh+sraGjS6FhYWuHXr1ruZlQoVKlT8S6HRaNn1tancCypUqFDxHlEZXRUqVKh4j6iMrgoVKlS8R1RGV4UKFSreIyqjq0KFChXvEZXRVaFChYr3iMroqlChQsV7RGV0VahQoeI90uDmCBUqPgSKKqoRfjsX6c/KUCYUQ4PLhI2RBib2MYGugPN3T0+FimahMroqPliSc0qw50oG4h6+AABUiyVUG5f5DDsuPcRQa33MHdIRPU21/q5pqlDRLFRGV8UHyYmELGyMSodQXAtlxU2Efxngi/ef4+rDIqx0tYHXAIv3O0kVKlqAyuiq+OCQGtw0VIkkjR5LCFAlqsXGqDQAUBleFR88KqOr4oMiOacEG6PSm2Rw61IlkmBjVDp6mGihh8k/z9Wg8lv/d1BlL/wDKaqoxv64TCwKS8SMH25iUVgi9sdl4mVFdbP6ycrKgqurK7S1tWFkZIT58+dDLBYDACorKzF37lzo6elBU1MTDg4O9fYTHBwMOzs7cDgcfP755wrtsbGxsLGxgZqaGhwdHZGdrSjAVFNTAxsbGwzqaQ2huFbpOKRWhBenNyF37wxkbx4FYfZdufbXFaWY6OEFAwMDGBgYIDAwUGk/cXFxoNFoCAgIqPeaLl++DEdHR2hqakKZvOmqVavQvXt3MJlMpeO8ePECnp6e0NLSgra2NqZMmaJ0nOScEvgcv4VBW37HjksPcSYpH7+nF+JMUj52XnqIj7f8jtknbiE5p6Teuar4Z6Fa6f6DaOvA0ty5c2FgYICCggKUlJRg+PDh2Lt3LxYuXAgfHx+IxWKkpaVBR0cHSUlJ9fZjbGyMgIAAREdHo6qqSq6tqKgIbm5uCAkJwejRo7Fq1SpMnjwZCQkJcscFBQVBW1cPmflFSn24MjgmtlC3G4uiM5sV2l5dCgFNLMT9lAeorSzFJ598AnNzc0yfPp06RiQSwc/PD/3792/w3vD5fMyYMQMeHh7YtGmTQnvHjh2xdetW7N+/X+n5bm5u6Nu3L7Kzs6GmpoaUlBSFY1R+6/8mqpXuP4QTCVlwP5SAmLTnqBZL5AwuIP2AVosluHj/OdwPJeBEQlajfT558gSTJk0Cl8uFkZERnJ2dkZqaigcPHuDcuXM4ePAg9PX1wWAw0KdPn3r7cXNzw2effQZdXV2FtlOnTsHW1hYTJ04El8tFYGAgkpOTkZ6eLjePEydOoM/YGQ3Ol8ZgQaPvWHBNbQG64lu3KuNP6AycgKj0V7CwsMDMmTNx5MgRuWO2b9+OESNGwMbGpsGx+vXrh6lTp6JDhw5K2729veHi4gJ1dXWFtosXLyInJwdBQUHQ1NQEi8XCRx99JHfMG7+1coNbl7p+66b8XVV82KiM7j+Ad/UB9fPzw8mTJ1FZWYm8vDycP38ezs7OuHHjBszNzbHMPwACTR3omXWC0/wtLXJjpKamomfPntTvfD4fVlZWSE1NpV5bsGABNm3ahGcVtWjk8hqlRlyL9IJyBAcHY8+ePfjjjz8ol0d2djaOHDkCMzMznDp1Clu3boWzszPy8/Op86urq+Hr6wtDQ0Po6Ohg1apVlMulIdauXQsajYZLly4hISEB1tbW8Pb2hqamJtTV1cHj8WBoaIhdu3Yp9Vs35jqRCCuQc3obPv+kF3T09BVcGklJSRg8eDA0NTVhYmKCdevW1TvXxlwnjo6O0NfXh4aGBnr27ImzZ8++mSch2LhxI8zMzKChoQF3d3eUlZU1en9UvEFldP9i6NCh4HK5EAgEEAgEsLa2BgAkJCRg+PDh0NHRgb6+PiZOnIiCgoJ6+2nIv5mVlQUajUaNIRAIsH79eqr97Q/86NGjcfHmfaWBpeq8dDw/GYCcne7I2eWJF6e/gbjiFdVeWVMLvy+/gpa2DnR1dbFs2TKQOhY7KSkJhw4dQmhoKPh8PkxMTGBnZ4fPPvsMN1MfISUlBb/cfQnjeUch6TwUl/f6Y9fUj7Fg7McKfkaZf3PTpk0KbojCwkJcunQJxsbGoNFoyMrKgqamJsrLywEAp0+fhlgsxrhx4/C6Rrkvt6nwOvRGaUI4XhaXgEajoba2FvQ6K+KFCxfCw8MD69atg6OjI5YsWQJLS0t4eHhQx+zatQvXr1/H3bt3kZ+fDz6fj1evXikbjuLVq1cIDw9Hu3btAAC5ubm4ePEi9T7w9vYGm83GjRs3MGLECOy5kqHUb80xsYXe6CVg8LUVx4gNARFVo/3cw3BZeRjHjx/H999/T7V7enrCwcEBr169QlxcHPbt24dz584pna/MdRIUFKS0fdeuXSgoKEBZWRkOHjwILy8v6j1/7NgxHD9+HNeuXUN+fj6qqqqwYMGCBu+PCnlURrcOwcHBqKioQEVFBR48eAAAKC4uho+PD7KyspCdnQ11dXU5H+HbyPybM2bU/6hcUlJCjbNq1Srq9bc/8FpaWpg9Z57SD6hEWAFBL2e0n3ME7eceAY3Nw8vfdlLtFUkXUPbgOkatPY67d+8iMjISBw4coNo9PDyQkZGBwMBApKamwsDAAGlpaRg11Rc/JxYCdCYEAyejhjDAad8FLH0LqFn1BSFQcGPI/JsdO3ZUmKdAIEC7du0QERFBvVZWVgZ1dXW8fv0ay5Ytw+7duwEAfDaj3nvWFLSHzQaNyUbEignYu3cvZs2aBQ0NDQDAr7/+ivLycrx+/RoTJ06EtrY2GAwGVq1ahatXryIzMxOA1NUxcuRIGBoagsvlwtHRESKRqMFxz58/jy1btoDNZgMAeDweLCwsUFhYiJEjRyI4OBhmZmZITk6GvmkHxD18ofDE0hTXicaA8aAxubj1igUPL28510lWVhamTJkCBoMBKysr2Nvbyz1N1KUx10mPHj3AZErDPTQaDSKRCDk5OdR9nDlzJkxNTSEQCLB8+XKEhYWhsrKywXuk4g0qo9sILi4umDhxIjQ0NKCmpob58+fj2rVr9R7fkH+zMd7+wLuMHY+8J4+UuhR4Vnbg29iDzlEDncWFep9RqM5Lo9pfp8RCo9843HxBB1dTD0uWLMHRo0ep9qysLJSVlWHhwoXo2rUrHBwcwNQ2xqWL0YCumdxYHGNrMNV1Qee98V/WdWMwrIfAxcWFMjp16du3L2pra9G3b18A0qyIzMxM2Nra4tGjR8jKysLgwYNhZGSE8zu/Qm1FMXJ2e0Fc8rzZ94/BU4ep23J8e+4GUlNTIZFIYGxsDECaQXHr1i3s27cP33//PcLCwrBz507qaUQW6Jo5cya1iqusrERsbCx4PF69Y2ZnZ4PBYMDV1ZV6rUePHqDRaEhISICOjg4+/vhjpKWlYcOGDTgY9Wezr4virzcCDcC9/FK54NyiRYtw7NgxiEQiPHjwANevX8ewYcNaPNSoUaPA5XLRv39/DB06FHZ2dn9Ngcg9MRFCUF1djUePHrV4rP8aKqNbh6+//hp6enoYNGgQrly5ovSYq1evwtbWtlXjmJubw8TEBNOnT0dRURH1+tsf+B37j4Df0a5JfVbnpIKl98ZY1hQ9BdvAEjQA4Xdy0bNnT7mVz+LFi6GpqYng4GCkpqbiytU/kJieCaa+Bbim3cDU0Efp9Z9BJLUQ5t6HMCcF7HadFMatEkmwITIVNzOeUR9IoVBI+UHHjRuHlJQUnDp1CgDw3XffoUePHrCxsUG3bt2Qk5ODpKQkJCUlYc++A2DwtWA8fTcYGnpKr5OIRSDiGun/JWIQcQ1lBETFBRBXlmFcz3Y4f/48Dh48CHt7ewDA+vXr8fDhQxw9ehRcLhcODg6YPn065faQrdQ6d+4MMzMztG/fHhoaGsjOzoaGhgaEQiFqamqoeYhEIhQVFSEpKQnDhg2DUCik2saNG4fi4mLcv38fP/zwA8aMGQN1dXX06tULwasWKARBm4LMdSKprkT5i1zEnftZbnU5atQohIeHg8fjwcbGBjNnzqS+6FpCZGQkysvLERUVhZEjR1JuGhcXF4SEhCArKwulpaXYsmULAKhWus1B9kFR9tOnTx/yXyEhIYGUlZURoVBIjh49SgQCAcnIyJA7Jjk5mWhra5OrV6822t/KlSuJt7e33Gvl5eXk5s2bRCQSkWfPnpHx48eTESNGUO2lpaXE3d2dACAMBoOwODwCOpPQWFxCY3EJU6c9MV8RSYymbiNci16EzhUQOk+DcM17ERqHTwynbCbmKyKJ+YpIAhqdGH+xj5iviCRDP19ObG1tCQAybdo0Qggh165dIyYmJgTAXz80AhqdsNt3Ie3nHCHtZu4hbGNrQmNyCI2jRmhsNULj8AmNwydaDtMIt0MfaixNe486/Uh/WCwW6dKlCzl9+jSJiYkh1tbWBADp378/efLkCREKhWTGjBnEzMyMCAQC0qtXL7J582bC1zYgFl9L+zVw30DAYBLQmYRj1p20n3OEMDQMFMZq73uYmK+IJPqfLSdqWnqEx+ORnj17kgsXLij9OwQHBxN1dXWipqZGNm3aRDQ0NMju3bsJn88n4ydNJj3th5PRS3cojDNkyBCqD29vb4V2XV1dEhMTQwgh5OrVq4TL5RImk0n69OlDrl69SoqKiggAYroojLp3yn4Y6rrE0GOT3Gsmfj8Rta5DCJ2vRVh6ZqTn6OmkQ4cOhBBCXr58SdTV1ckPP/xARCIRycnJIf379yd79uxp8D0aExNDzM3NG30vjxw5kpw9e5YQQkhtbS1ZvXo1MTc3J+3btyfffvstAUCePn3aaD//JQDcIvXYVdVK9y/69+8PdXV1KvAxaNAgREVFUe0ZGRlwcXHBrl27MHjw4BaNIRAIYGdnByaTCUNDQwQHB+PixYtU9HfOnDkQCoV4+fIlXr9+DY5ACwx1XZgtCYfZknC095H6ZOv6cw08NqI6Lw1MdT1wTbtRY9HYXEiqpasPukAH06dPB4vFAo1Gw6tXr+Ds7IyNGzeioKAAfIEALO120HaaCW77LnhxdgvY+uZoN2071LoMBs/iI5gsOAad4b4gNVVgCLRhOGktNZaW/RR0DojCp6PHgk6nIyoqCtXV1QgKCoKnpyd69OhBPQqfPHkSFhYWEIvFMDU1RVxcHEpLS7F+/Xps2LABP0fGgMtkoLayFC9Ob4Le6KUw+/JncIw64cXZLTCZewTmKyLlfphahgAA3e5Dcf3eI1RWViIpKQkjR45U+neYN28eysrK8Pr1a4wfPx5isRg9h4yC574r+PVyAl60G4C7zE4wXxEJ00UnAQBWX/4E61nbqODh0aNH0bNnT+jq6sLQ0BCGhoYoLi7GpEmTsGXLFgwePBgTJkzA1KlTcevWLQwePBg0Gu2vGTQ/R4PBU4f+mK9guuAEjGftBZtOQ79+/QAAjx8/BoPBwLRp08BkMmFiYgJ3d3e5929rEIvFlM+bTqdj7dq1yMrKQm5uLmxtbdG+fXu0b9++Tcb6L6AyuvVAo9Gox9bs7GwMGzYMq1atwtSpU9t0DADUOMnJyfj888+ho6MDDocDdV0D1JY+R21lqdx5Mn+uRFiBF+HroW43BuKyQrlj2HpmqCl8AgDoYT8C2tra0NfXByD/IT137hwMzTtBy24UhFlJ0LT3hKjwCUQvpYETWQCHzuKCIdAGjc1Dxd0YxWsB8OT5K6kv2sUFNBoNn376Kfh8PvWBrQufz0dgYCAsLCxAp9MxatQoWFpaoqrgEVa62kCcmQC2nhn4NvagMdkK83obHouOla421BZgsVgMoVCI2tpa1NbWUi4PoVCIlJQUEELw9OlT+Pj44JMJn8Pnl3TEpD0Hy6gTSpJjIRG+BqkVo/xOFBgCHYjZ6go50LGxsUhJSaHcI8bGxjhw4ADmzZsHAJg+fTpOnz6NpKQkiEQirF+/Hlbd7cATaCi9hsZcJ7VVZSCSWoizbuP+ldPUjrrOnTuDEIIff/wREokEz549Q1hYmFyqXl0kEgmEQiFEIhHlDpK5TtLT03H+/HlUVVVBJBLhxIkTuHr1KoYMGQJAmqmRmZkJQgju37+PL7/8EqtXr5bLElHRMKo7BWk2QXR0NPXBDA0NxdWrVzFy5Ejk5eXByckJ8+bNg6+vb6N91fdhB4AbN27gwYMHkEgkePnyJRYuXIihQ4dCU1MTgDTodOzYMZSWlkIkEqGm7CVAoyH/0Bw8O/6VXO6muLwIz3/yh3qfT8Hga8n5cwGA380JZTfPgFH5CkasSmzfvh09evQAIP8hTUlJAVunPUpT48AysASdzQVTywg1L55SfRFJrdQY1Eqvo6YwC6T2TUSf1IpRJRRCzFSDrq4uwsPDUVNTgzNnzoDD4aBz586orpbm9lZXV8v5P2U8f/4cDx8+hK2tLbwGWKAHvxw8ow6QLQ6VzQsAaDSAx2JgpWsXud1aGzZsAI/Hw+bNm3HixAnweDxs2LABQqEQnp6eEAgE6NevH9TNuuKhqQuVA63tNANgspB30Ac5301B1eNb0HdbKb1OAmTum41lW/biREIWdHV1YWRkRP0wGAxoa2tDIBAAAJycnLBp0yZ8+umnMDAwQEZGBiJ+/omaY37IXFSkXqZ+zzs4G0+3uaG2/CUKw1ZL/18q/TKteZaBgsPzkfPtJBRd/gHfHz1GxRY0NDRw6tQp7NixA9ra2ujVqxe6deuGlSul846Pj6fmBEjjEjweD66urnj69Cl4PB5GjBjx1zUSBAYGwsDAAPr6+ti1axfCwsLQu3dvANIdhq6uruDz+XBxccGMGTPg4+Oj8PdU0QD1+R3If8inW1hYSOzs7IhAICCampqkf//+5OLFi4QQQgIDAwkAwufz5X5kbNy4kTg7O1O/r1mzRsHXt2bNGkIIIT/++COxsLAgampqxMjIiEydOpUUFBRQ5xYVFRFPT0+ir69PNDU1Sddu3YmJ1zfEbOlpovvpYgIajWg5zfzLj+pJABAak039S2NxKR+g2fJfiUZ/N0LnCoiWtjb56quviL+/P+XfjI2NJXZ2doTFYhEmm0sEPUcQ0yXhxHxFJGHpmRMwWMR8RSTh2w4lbJOuCtfEMe1GjcXv9olCO41GIzwej0RGRiq0Sd92b6ipqSEDBw4kdDqdTJkyhRBCyIwZM4jzGDei1c6c0JgcwjPvQdhGHYmu6yJiviKSWAdEkc4BUWT28ZskOaeY3L9/nzg6OhINDQ1iZWVFTp06JTfGpUuXiLW1NeHxeGTo0KEkKyuLJD0tJjarzsv5Ts2Wnib8HsMJQ0Of0Ng8wjLoQAwmBlLtdf3p2jq6ZMKECSQ/P7/e99bu3btJnz59CJvNpu79F8duUn5rvbHLCVPXRDqWrinRd1spNx+jz3cSjoktobG4hK6mRXSGfUFmH7/ZvDe4ivcOGvDp0kgDW5zs7OzIrVu33o21V9EkfI7fQkzacxACPA9bDZ5VX2jYjQYAiIrz8Tx0BbSGfg5BNyeFc2k0YGRXQ+z3kmZABAQEIDc3Vy51zM/PD5fTClDWx5t6Lf/wPGgO8gTfZhBqq8rxKmY/hNnJYPA0wOs8EJX349DeN0RhvD6MHFzZtxLR0dHo3bs3bt++jTFjxuD8+fPo1auX0uuTSCTw9PTEpUuXYG1tDUtLS5w4cQI+Pj44evQoQkND8bHjCExfsBSXTx2HpcssfOoxCzbt1DGht1SBSywWo2vXrvD19YWfnx/i4uIwevRoJCYmonPnzigqKoKVlZWc/kN8fDx6zAum7i01nxohym5EQNB9GBia+qjKvIWic0EwnhEMppYhqjJvQSISQq1Dbwzr2g7k2hHk5+fjwoULSq/v1KlToNPplC7F0aNHkZxTAvdDCSh/9Rx5+2bBYHwAuB36SMc6sxnt5xwGg6+F2spS5IfMhfYns8C3tgepFYFZVYwzKyf9I5XU/kvQaLTbhBClqUcq90IjtJWiV0uZN7QjuMy/Ng3QaJAFYcSlhXj+UwA0B7krNbgAwGUyMHeo4oaFutja2uJ1QSY4TOlbQVIjhLj4Gdj6UnfF2wEcEAnY7TorGYsOvMqGg4MD7OzsQKfT0bdvX/Tv3x+XLl1SOjYhBDNnzsS9e/cwZMgQDB8+nGqrrKwEl8vFxIkT0V5PEyd2bYS4phqPzu7BGINizHawoiQP09PTkZ+fj8WLF4PBYMDJyQmDBg3C8ePHAdSv/xDzvzsKOdB0Nhdag6eAqWUIGo0OtY79wNQ0RPWzDABv/Ok0thr+yCqH1wyfZudt9zTVwkpXGzCrXoHO5YNnZQcajQa1jn1BY3EgLpHu/iq7eQY8y94Q2DqCxmSBLxBgnfcIlcH9h6MyuvXwd0vuyfzM1vpcrBjRETXpcajOSQHPsrecP1f9I1el59cNLDXkZx43bhxePM1AedofIOIalF77CSwDC7B0TQHIB3CqMm+hIikamh9PVhiPAPAe44T4+HhqK3BiYqJ0RfmXL/lt5syZg5SUFFRXV2Pnzp1ybTweD9XV1YiIiIBQKMS2bduotoULFyok6CvMhxAqY0KZ/oO2kSmqXyhKTL5N7etiiF7lUV9CdaEB2B8W2aK87fZVT8B5ngKOnimqMm6ASGpR+fA6aEwWWPqWAIDqvAegcwV4dnwpcr+bAu7v2+BgrPrI/tNRSTsq4UOQ3BOJRAgICEB6ejoYDAb0TCxhMmk1GHomKI7/EeKSZyj94yeU/vEmMGO2JBw0GlAcH4qKpzfhuugGAGlQae3aNyleJ06cwJo1axAYGAh9fX2ciojAhGmzUHZ2G9jtOkN/zDLq2JpnGSiOPQSJ8DWYOsbQG70EbH1zqj0/ZC40B06E8yR3jHG2Q2BgICZMmIDnz59DX18f/v7+VJBm06ZNiI+Px/nz55GdnY0DBw6AwWCAwWCgS5cuqKmpoRL6JRIJxo0bh5UrV8LLywtWVlZURsmTJ08QGRmJ0aOlbhYbGxsYGBggKCgIixcvxuXLlxEXFwdHR0cAQEVFBZW5QcFWQ01VJRT30L2B1IpRdG4bBN0/ob6E6lKWn4lzYbsRcz6yCX9RKS9fvsTixYsRGhoq1fTdvAMbA5ZDXFMNGoMFvc9WgM7mSu9BRRFeP8/EWP89+NpzJI5/twkeHh4NrqwbQyWW/vej8um+RXNKxciQriq7vHOt07u5Jdh7JQOXH7wADW+MPyB9vCcAHK31EbZmFkqf3AWPx8PSpUuxdOlSpRKEdZH5GatEzRed4bEYCPMZ0OzH3qSkJEyZMgWJiYlgs9kIDAxERkYGTpw4AT8/P4hEIuzduxcA0K1bN7kddR07dpTbenr37l0sWLAAKSkpsLOzg76+PjgcDg4fPqzQFwBom3YE024S+DaDlM6NEAmKzgVBUl0Jg/GrQGPIr09k/vRBHgsRd3BNo9caEBBAPQXI0rF0dXVBCEF0dDTMO9vi258u4LsVPhi+eCcsrW3xy0oPOAzoix9PHAMgNdh6enooKSmhMl6aSsNazNL3jqrIZ9vxj/HpPnr0CFwuF15eXgAaV+WqS3V1NWbOnAlzc3Ooq6vjo48+wvnz56n2+/fvw87ODtra2tDW1sawYcNw//59qp0Qgulz/ODt1AMPgyaj+PIRpY+tgKLC19OfN2Jt2P9wN1fqaggKCkK3bt2grq4OS0tLBTWn5sjw1e1r7OCPYFVwGf9b7oTFwztjXK/2+MTGABb5cSgK8UHutxMQt3EqOutxQAhBZWUlNm3ahIEDBzZ672V+Rh6reW+Jt/Njm8OVK1eQlZUFMzMzGBkZYdu2bYiIiEDv3r1ha2uL5ORk6tjJkydTIixr167F8uXL5frq0aMH4uLi8PLlS0RHR+Px48fU5oG3+3r9+jUqCpW7DADpe+Fl1HeofV0C/XH+Cga3rj+99ydjm3y9xcXFqK6upgR0eDwe5QPX1+Dhm9njMHzIINirFWDH5F5wHGgHLvvN2G/ndTeVd6HFrKLlfFBGd968eUr3i9enylUXZTucJk2ahKysLABS9a/w8HC8evUKRUVFGDNmDNzd3anzDx48iNNnzsB4xm60m7kbVRk3UZF0XulYyhS+cs9ux94r0mALIQTHjh1DcXExLly4gODgYJw8eZI6vzkyfMr6iok8jdkOVtgxuRcGipLxKvECrsZGo6KiApGRkXJVETQ1NXHs2LGGb/xfeA2wwErXLuCxGFR+bH3Ulx/bHHx8fJCZmUltLvD19cWnn36K6OhoSrNB5tOtqKhAnz59wOVysXTpUsyaNUuur7t370IoFKKyshLbtm1DQUEBJWbzdl/r1q2DiZU1BIbmSmYFvIreA9HLHBhMWA06S/6Ru64/Xb/vKNi0a/gJoq4/vWfPnpg5cyY4HA6YTCYsLS0b9IEr21xhb28PLa2mf8GpxNI/PD4Yo3vy5EloaWnhk08+adH59e1wun37NgBAS0sLFhYWlF+QwWAgIyODOv/wkaPg9B4LhroemOp6UO83DhX3YpWOVZ/C1+UHL/CyohrLli1D7969wWQyYW1tjbFjx8r54Zojw9dQXxKJBGvXrsWOHTvQtWtX0Gg0WFlZUUbXyckJDAaDUtpqCl4DLBDmMwAjuxqCw6RLsxLqwGXSwWbQMKKrIcJ8BrTKpaKmpia3uUAgEIDL5UJfXx/6+vqIiIjAypUroa2tjRs3buDkyZNgsVgQiUTYtGkTXFxcqL6OHz+Odu3awcDAALGxsYiJiQGHIzWYyvqK+CWMOrf0fz/j+c9SF4G4tBAVSRdQ8/wxcndPxdPtE/B0+wRqE0NF8kXKn/5wixuWuPaU23iwadMm6OjoUNrMampqckmTdOQAACAASURBVJs0ZC4ONpuNmpoaLF68GBMmTIC6ujrGjx8v5wO/f/8+NDQ08NFHH4HP5yMjIwM//vgjAGlNuQkTJlDvaWUCTck5Jdjw6z1k7PFB7h5vhXYZbwuoF2ckYWNUOvXkFhgYCBaLJffE+fjxY+r85jy5NdZXVlYWHB0doaamBhsbm3ozX/7JfBCBtLKyMqxevRqxsbE4fPiwQru5uTloNBqGDx+OoKAg6OkpV6CqS90dTnXR0tJCRUUFJBKJ3JvjXmoK9CdNon5nG1hCVCS/+6k+ZApfMkWv2Q5WVBshBPHx8Zg9ezb1mkyGb/369Xj8+DGuX7+OZcuWKelZnrf7ys3NRW5uLlJSUvD555+DyWRi2rRpWLJkCWJiYjBs2DCsWbMGU6dORXR0dJO3avYw0cJ+Lzu8rKhG+J1cpBeUo0woggaXBZt26ljqZo9HPbrAZpLy3NSW8nY1hGHDhsmV9QFAGV1/f3+514OCguoV5a6vryGdyxGT9hyaH0+CzEPK1DSA+Yr6A2Na9p7QsvdUyIGW4e/vj4sXL8LLy0tuNU4IwYABA2BhYYFDhw6ByWRi/vz5iI+Pl/vyr4uxsTF27doll+NbF3t7eyxatAgTJ05Uev6eKxl4/scvYKhpQlxapfQYGW/XnhOKa7H3SgZ1fZMnT8aJEyeUnuvp6Ylx48ZR7iJ7e3v06tULY8aMUXp8Q315eHhg4MCBiIqKQlRUFCZMmIBHjx4pBkL/wXwQK91Vq1ZRwsh10dPTw82bN5GdnY3bt2+jvLy83qqqdRGJRJgyZQq8vb0VamGVlJSgtLQUwcHBcnWrqisrUct8o5tK56iB1FQ16j+rKXyC0ms/QdtxOoRiCdILyuXaAwMDIZFI5ITPWyrD93Zfubm5AKQ1ue7du4fLly/jp59+QlhYGKWlumrVKlRVVcmlXDUVXQGHcmMc9u6LHZN7YbaDFYiwHFeuXMGAAQNQWFjYeEdtCJvNblRUvKnI5UA3k6bkQNclIiICFRUVOH78eJtoM7PZbCxatAj29vZgMBSvoaiiGpdu3ENF6mVoDlRulGUoE1AnBNSTW2M058mtIR4+fIg7d+5g7dq14PF4GD9+PLp37y4ngP9v4G83uklJSbh06RIWL16s0NaYKpcyJBIJpk6dCjabjeDgYKXH8Pl8+Pr6Ytq0aZTRYHJ5lCoXAEhqqkBj8+ooQykiKs5H4c9roD3Mh1L4KhO+MQjBwcE4duwYfvvtN+pRV6bwtXr1agiFQuTk5CA6Olousq4MZX3JxLWXLVtGuU9mz54tpy7FZDIRGhqKbdu24c8/WyGgXQfZdsa7d++iW7duSivdvitYLJacrm1reJfBw7razJGRkfDz88OBAwfkhN7bQpu5PsJv56Iweh+0HaaBxmwoMa5+ZE9ugLRihI6ODmxtbbFv3z6545oroF5fX6mpqejQoYNcps3bOtD/Bv52o9tQBPttGoveynY4PX/+HBEREWCxWPWOK5FIqIKMAKBnYkWpcgGA6PljBRGZutS3I0yDKx3zyJEj2Lx5M2JjY2FiYkK1t0SGr76+rK2twWazG/xiAKTumX379sHDw6NNigjWNXplZWWU3/x9IHMvtBXvIni4ZcsWPH78GHl5efDx8YGbmxscHBwoQXVAGvhbt25dgy6R1hB57gxqa2uhZv1xi/uQPblNmjQJaWlpePHiBQ4dOoR169bhp5/e5Ic358mtob4qKioUUuHq1tP7t/C3G92GItiNqXK9zZw5c5CWloZff/1VocRKTEwMEhMTUVtbi7KyMnz55ZfQ1tZGly5dAABDR01Axc2zEJcXQVz+EmU3z0DQXXlQr74dYVwmHTbt1BEaGgp/f3/ExMQo1KFqrgxfQ32pqalh8uTJ2Lp1K8rLy5Gbm4tDhw5h1KhRCv2MHz8ew4cPh6+vb7NTjupSW1sLsVgMTU1NMJlMJCYmwtu7/iBNW9PWRhd4Ezw0pb0Ciw6lwUMOk46RTQwe1tVm7tSpE+h0upz2RFtoMzfE69evcTV0F3SGz2784EYoE4rQtWtXGBsbg8Fg4OOPP4afnx/Cw8MBNP/JraG+BAKBwqJAVk/v38TfbnQbimA/fvwYzs7OUFdXR7du3cDhcOS+YetGsGU7nJKSkqh+BAIBQkNDAUh9uR4eHtDU1ISVlRUyMjJw4cIFcLnS3T+71n4Ffud+KDg8HwWH54FnZQdBrzfR8boyfHUj2LLo9tPtE0AATOhtgoCAALx8+RJ9+/al5iGThWyuDF9DfQFSt4NAIICxsTEGDhwIT0/Peotifvvtt0hOTm5yCpkyGAwGEhISUFhYiOnTp8ulwr0P2tKnW5drv/6E+E3T4Cq+LpcDPa5Xeywe3hn/W+6E/V52zcpHrqmpgY+PD2xsbKhFwLvSZq7Lo0eP8LqoAM9ClyNntxdenN7U4tpzsie3utTVmm6tgHrdvmxtbfH48WO5lW1ycvI7c8H8Xah2pNWhrqJXc6HRgP7GXPzwhT3lc/0QuXfvHpycnHDt2jV07qwoXNMcHjx4AAcHB2RlZTVYvLEt6dOnDw4cOEAVSmwLvv/+e8yZMwfV1dWYPn26XJXd5lJSUoIbN25gyJAh2Lp1K06dOoVHjx7hzp07EAgEcHBwgK+vL7766qtG+xKLxRCLxVi7di31FMNkMqlNItXV1SCEoGPHjjhy5AgcHBzA4XBQW1uL7edu4WB8JmrEBNV5aXgVsx/tPt8FupoGaHTFwBsRiwAQ5B34ArqufuCadgOXw8GXI6xhVJwCBwcHaGlp4ebNmxg3bhw2bdoEb29vlJWVwczMDHv37oW7uzsKCwsxbtw4ODk5YePGjQrjnD17tt6+AGDAgAGwt7fHhg0bcP78eUyfPv0fmb3wj9mR9nfTmmg2h0HH6Y2+4PF4aN++PYYPH46AgIA28aG2Jd27d8e6devg7u5OCYu3FGtra/Tt27fe9J93QVu7F06ePIm5c+dS96LuzrWWINPM0NPTQ2BgIGg0Gs6cOQNra2uEhITg8ePHWLt2rVyeqoy3c4/rE2KXYW1tDR6Ph7y8PIwcORI8Hg/Z2dlgMpmYOeIjMAU6YAi0QecKABpNWvnjL4PbFAF1UWkhJvQ2wcmTJ9GxY0eoq6tj2rRpWL58OWUkm/vk1lBfsvZbt25BW1sbK1asQHh4+D/O4DaGaqX7Fq3RXji7/StERERQj0s8Hg9ZWVkwMDB4V9NtEYQQuLm5wdLSEt9++22r+vr9998xf/58pKamNhrQawsGDx6MjRs3wsHBoU3627hxI7755htUVUnTAzU1NVFcXNyqPgkhGDZsGFxdXbFkyZI2mWdLaO2Tm7I8ZBVNQ7XSbQatiWbv2LFDzrWwYMGCD87gAlI/2uHDhxEeHt7q4oWOjo5gs9mIjo5uo9k1TFv7dFeuXInbt29DU1MTM2bMQIcOHVoVaASku+OKi4vh5+fXRrNsHlVVVTh37hzYGZffWx6yiqajMrpKaMpWWGXRbBMTE0yfPh10Oh0jR45EWFgYFi5cqLQm2N+Njo4OTpw4gZkzZ6KgoKDF/dBoNHz55ZetXjE3lbbM05Xx66+/YuLEiQgJCcHt27dbtWIvKirCsmXLcPDgQcr3+j7Iz89HQEAAevXqBU1NTYwdOxa/Hg1+7yJGKhrng9gG/CHS2FZYWamYtwkMDERJSQlCQkJQXV0NHx8f9O/fHydPnqTS0z4UHBwcMHv2bEybNq1Z24Tfxt3dHStWrMC9e/fQvXv3Np6lPO8iZezUqVNYs6ZxecamsGTJEnh4eLRpoK8ppKenywWuOBwOgoODMfqvBUFD+tAyaDTpCvdd6EOreMN/0qf7PoWcCSEICQmBv78/Nm/ejBkzZrwX32dTEYvFcHR0xKhRoxTkEpvDxo0bkZmZ2arIf1Nwc3PDlClTMH78+Dbpr6CgALa2tnj27JncbrGWEBsbixkzZiA1NVUuePS+8PLyolIk9fX1UVBQQG0RbqoW89yhHVUr3DagIZ/uf2ql27CQ8zPsuPSwzYWcaTQavvjiCwwaNAju7u64ePEiDhw40Cx5vneJbJtw3759MXToUDlZyOYwe/ZsdOrUCd988w0MDQ3beJZvaGuf7pkzZ+Dq6tpqg1tVVQVfX18qb/p9s2vXLsTGxsLFxQUXLlyg6sXJaOmTm4q25z9jdP/uEjxdu3bFn3/+ia+++gofffSRtMrtxy3fotmWmJmZYd++ffD09MSdO3eaXZUAkIoTubu7Y+/evXKlgdqatvbpnj59Wm6zSUvZuHEjevbsSZUQel/U1tZi8eLFuHTpEq5fvw4TExOsWbNGTtWuLjIRIxV/H/8J98KHVoLn7NmzmD17NhYsWIAVK1YoVYn6O5gzZw5KSkrw448/tsgF8j42S8yYMQODBg3CzJkzW93Xq1evYGlpifz8fPD5/Bb3k5KSAkdHRyQnJzdLu7i1VFRUwNPTE69fv0ZERMQH8/Sk4j2ljA0dOpQSbhYIBLC2tlY4Zu3ataDRaPUKEzdWcichIQHDhw+Hjo4O9PX1MXHiRLnI++XLl+Ho6AhNTU1YWFgAkLoUNkalKxjct0vuvDj9DcQVr6j25/87jRkuAyFQ14CxsTEWL15MVdCtS1xcnLTAYEBAvffm7XmNHTsWt27dQkxMDIYPHw5TU1PweDzq3slErGW8ePECnp6e0NLSgra2dpPkLVvCt99+i3v37uGHH35o0fmyzRIyv+K7oC0DaZGRkXBycmqVwZVIJJg9ezbWrVv3Xg1ufn4+hgwZAl1dXZw/f/69GNyiimrsj8vEorBEzPjhJhaFJWJ/XGaT5B9VvKFNU8aCg4OpsjoPHjyQa8vMzER4eDjatWtX7/mNldwpLi6Gj48PsrKykJ2dDXV1dTmdWj6fjxkzZsgpN+25kgGhWLHYorKSOy9/e1MGnNexH4ym74TXvt+RkpKC5ORkfPfdd3J9iEQi+Pn5NeoHVTYvExMTxMbGwsnJCfn5+fD396fu3cWLF+XOd3Nzg5GREbKzs1FYWIilS5c2OF5L4fF4OHnyJL766iuFv19TkaWPtTbXtT7a0qd7+vRpjBs3rlV9HDx4EISQeh/n3wX37t3DwIED4ebmhiNHjrTaH90YyTkl8Dl+C4O2/I4dlx7iTFI+fk8vxJmkfOy89BAfb/kds0/cQnJOyTsZ/99m7N+bT3f+/PnYsmUL5s6dW+8xspI7MuqW3LGwsJDbIinrc8iQIdTv/fr1Q79+/aiVdFFFNeIevlDqw+VZya/81fuMwvMfv6Z+Z2lLvxwuP3iBl4ONQafTFRT+t2/fjhEjRjQq5P32vGQwGAwEBARgz549CA4OxosXL7B161ZKhAeQCpTn5OTgypUrlBuirvh6W9OtWzesX78eHh4euH79erN1JBwdHcFisRAdHQ1nZ+c2n19b+XRfv35db6WSplJQUIBVq1bh8uXLLU63ay6yqhS7du2Ch4fHOx/v74yF/B2B7/dBm75T6go3163Z9Msvv4DNZsPV1bX+k5VQX8kdGY2JQIffzm3yWLKSO3V5nXoFGVvHo7NFeyQnJ8utZrKzs3HkyBGsXr26yWPUB4cjrd574MAB6Ovr4/Tp01RbQkICrK2t4e3tDV1dXfTt2xdxcXGtHrMhZs+eDQsLC6xYsaLZ577rzRJt5V6Ijo7GgAEDoKOj0+I+/Pz84OPjg27durV6Pk3h0KFDmDZtGiIiIt6jwf17ilr+mysYt5nRfVu4efTo0cjMzERFRQX8/f2xc+fOxjupQ0Mld4CmiUCnPytT+GMpo27JnbrwbYfC9Mtf4L3jDHx9feVSoRYuXIj169e3SXpQaGgosrOz8erVKwwfPhzjx4/H7t27QQhBbm4uLl68CEdHRzx79gxLlizB2LFjUVRU1Opx64NGoyEkJASnTp3Cb7/91uzz3d3dkZKS8k4qSrSV0T116lSrXAuRkZFITExs0JevjODgYNjZ2YHD4VDVimWEhISgY8eOEAgEcHZ2Rn5+PgCp39je3h4+Pj4oLy+Hi4uLQkHHujRWtDIoKAjdunWDuro6LC0tFT5Djo6O0NHVg/eQrsjcPxeVDxPqvZ7SGxHID5mLp99ORO6+mXj2xy9yRS1lKIt9/Pbbb1R1YyMjI3zxxRcoLy+v19iXXD2O/MPzkL1lDEripXEDmbFfG3YNvQcPg7GxMWg0GuWSlJGXl4exY8dCR0cHJiYm2L9/f73X9K5pM6NbV7jZ29sbgwYNQlRUFFUY0dLSssl9NVZyp6ki0GVCxcDX2ygrufM2DG1j2NraUq6RX3/9FeXl5Zg8eXITr6hhBg0aBB6PBz6fj1OnTsHCwgLbt2+Hu7s76HQ6LCwsMHPmTLBYLLi7u8PU1LTB2lptgWyb8KxZs5q9TZjD4WDevHnYsWNHm8+rLXy6NTU1iIqKwmeffdai8ysqKjBv3jzs37+/2VkaxsbGCAgIUNA8jouLg7+/P86ePUtlVXh4eKCqqgru7u54+vQpJkyYgNevX1O+/7dF7etib2+PEydOwMjISKGNEIJjx46huLgYFy5cQHBwsJwu8q5du+C2PRJmS36BrssCFEVulwsyv9UZdEd9CdNFJ2E4aS3Kb0ei6O7v2HvljSuuvthHaWkpAgICkJ+fj7S0NOTm5mLGnIVKA98AwNQ2hvbQ6eBZKValENYS5KvbYMu+o0qn6eXlBUtLSzx//hy//fYb/P39cfnyZaXHvmvemSNKJk4cGxuL7777jhIpz8nJwaRJk7Blyxal5zVWcqc5ItAa3IZd1vWV3FHshwWxWIzMzEwA0p1Ht27doq4pLCwMO3fuxNixYxscr6lwOBxs27YNBgYGCA8Pb3OtgaYyePBg+Pr6YurUqZBImp5uB0hdFKdOncLz580TzW6MtvDpXr58GV26dGkwqNsQq1evxpAhQ/DJJ8orizREfcUmZfoPtra2YLPZWLVqFa5evYpBgwZRIuFN9a83VrRy2bJl6N27N5hMJqytrTF27Fi5L3HjDtaIzywGIQCpFYOIhCj43g9Pv52I/CMLUZUpTSOtzkuHMCsJhScDkLt7KkquHgfXoheqc9Lkilpu2bIFOTk5uHfvntw8PD094ezsDDU1NWhra6N///44FRaKB998hmc/fg1xqXysRND9E/Cs7EDn8CARVaMwYgOebh+P3L3TIcxKBq+XC+JLNBSu98CBA7hy5QoOHz4MS0tLhIaGUkFIoOHMq8YyplpCmxjdkpISREdHQygUQiwWIzQ0FFevXsXIkSMRGxuLlJQUqhyPsbExDhw4gHnz5intq6GSO3l5eXBycsK8efOUJrRLJBIIhUKIRCIQQmClzQGbppi5ANRfckdGeXI0al+XgMukQ6P6Gb755hvqQ7Z+/Xo8fPiQuqYxY8bgiy++wPfff690rLfnJRQKKcPx9OlTXLt2DTU1NRAKhQgKCkJRUREcHR2xe/du7Ny5EwUFBRg/fjxqamoQHh6OvLw8DBo0qP4/SBuycuVK1NTUYOvWrc06T09PD5MnT2604GZzaQv3QmtcC7dv30ZoaCi2b9/eqjm8jazYpwxZ0NbKygqhoaFgMpkNFodszbjx8fFysZHw27nIO7kG2UHj8Dx0ORiahjCauhWmi8Og5eCFF2e3QFzyXGkGUGX6H2Dpm1FFLbOzs7Fz506lLsK6FBUVYdM334Bt1BGmi34Cx6gTXpxVvjADAOHjW6AxWDBZcAJ6o5fi5cW9qC7MxpWHim63ykppwdm0tDTcuHEDsbGxuHv3rpz7q77Mq8YyplpCm2QvyISb09PTwWAwYGNjQwk3vw2DwYC2tjblC920aRPi4+Nx/vx5quQOh8OReyw6cOAApkyZIicCXXfXU0VFBQBpYM3R0ZF6feFIW/DMusPA8xsAUuFmjYETIbB1lCu5U/rHmxJAZkuk9Zqqc9NQEnccRFSFTSDQ19NFfHw8evfuDQ8PDznlf5lrQBaUiY+Ph4uLS73z4vF4GDJkCK5cuYLy8nLMmTMHmZmZ4HK56NWrF86fP0+thLy8vMDj8eDt7Q01NTXY2tri7Nmz0NPTa8mfqtnItgnb2dlh6NChGDBgQJPPXbRoEYYMGYIVK1a02WaJ1hrd2tpanD17tkXuGbFYDB8fH2zdurXNhbVdXV0xefJk+Pr64tmzZxg7dixoNBrc3NxAp9MxadIk+Pj4wNDQEDdu3MD48eOhpaXV6oBaYGAgJBKJnCFJf1YGvQlroFsrhjArCaKXuWBpSZ8K1Dr2A1PTENXPMsC3kf/ip9EZICIhBN2HU0Utf1m3FBwOBwEBAZgwYUK989iwYQNqxbVoP3oxCJMNTXtPlH/nCdHLHLB0TeWOJZJaiF7mQt9tJehsHrimtlDr2B+vUy9D3VCxXt/ixYsRERGBLVu2ICgoCEOGDEFwcHCTXJ6NZUy1hDYxuvr6+rh582aTjn3bwe3v70/939zcvMH8zjVr1jSoBjV06FCF8+sKORvPerPq0rL3hJa9Z7196X26CDQaYEJe4o/N3igoKEBBQQHYbLZC8Ozo0aNyvw8ePJgyuPXNS4atrS3u3r1b7zwAaVHJzz77DN988w2Cg4NRUvJu8iHrw9TUFPv374enpycSExObvE3YxsaG2iwxa9asNplLa43u9evXYWhoCCur5m+F3b17N7S0tDBt2rQWj18fn3zyCdauXUulIE6fPh3h4eFU9eeuXbtSx9Yt6NgaoxscHIxjx44hPj5eznUhi4XQGEzwrOxQduscmNrtoNapP2pfF0P0Kg9sfflMn7Lbv+L1g2tgGViCxpS6BFOu/46kpCQcOnSowS/dhIQEHDhwAOa9PoZEU7rBhM7mgqllhJoXTxWMrqS6EqDRwNJpT73GMrBE9dN7ckI+dQkNDcW8efNgamoKsViM7t27y20o+frrr7FixQpYW1tj48aNGDp0qNJ+GsuYagr/ej3d1pTg4TIZ2DNvDKZOnUq9KUUiEUpLS+WM6vtAltMbERGBBQsWvHed3nHjxsHZ2RmzZ89u1saHxYsXY8eOHW22WYLNZrfKp3v69Gm4ubk1+7zs7Gxs3LgR+/fvfycqcYQQvHz5ElwuF/fu3cPy5cshFovrTUerW9CxJRw5cgSbN29GbGwsZdhlKMRCJLUQFxeA1IpRdG4bBN0/kTOEFckXUXrtJEAk0BnmQ72ecfUMSkpKMGfOHLi5uaGyslIh9pGYmIgxY8bA3t4eAiP5lSedwwepqVKcvKQWNAbrrWPVIFF27F+Ym5sjMjISW7duBZ/Ph4WFBfr16weg/syrt2lKxlRT+Ncb3Z6mWq0Wcj548CAsLS3BYDCwcOFCJCYmokOHDli3bh1evaonqvuOGDRoEBITE1FQUID+/fsjLS3tvY29fft2pKamKqzsG8LJyQlMJlNhl11Lac1KlxCCU6dONdvoEkIwb948LFq0CJ06dWrR2DLEYjGEQiFqa2tRW1sLoVCIyspKTJs2DT///DOuX78OdXV1+Pj4wM/PD9ra2gCkeh3FxcUghODPP//Ed99912Dgtrq6mvpSlsULZEY6NDQU/v7+iImJUciASE9Phzg7ESwiAqkVoyLlMoQ5qWCbdkVR5HaAwYTO8DfxlIrUy3h1RRrL0BnuS2UAsSU1qHiehatXryIpKQkhISHg8XhysY+UlBQ4Oztj9+7d0pW8SN5oSmoqQWO/WSGTWjGIuAag0UFqRSDiGhCJNGZDqitBY3H/KrApf/2A1J/7008/YcWKFZg3bx7i4uLw5ZdfAqg/86ouTc2YahIyB76ynz59+pB/C8evPyE2q84Ti68jifmK+n8svo4kNqvOk+PXn8idn5WVRZycnEh5eTkhhJD09HQyffp0oq2tTb766itSUFDwXq9HIpGQgwcPEj09PRISEkIkEsl7GTclJYXo6emR9PT0Jp9z9OhRMmLEiDYZPzQ0lLi7u7fo3Dt37hArK6tm36uff/6ZdO3alVRXV7do3LqsWbOGAJD7MTc3J66ursTW1paoqakRQ0NDsmLFCiIWi6nz3N3diY6ODuHz+cTa2prs2rVLrt+uXbuSEydOUL+bm5srjPPkyRNCCCEWFhaEyWQSPp9P+Hw+4fF4ZMKECSQxMZGEh4eTLrbdCI3NIzQOn7CNOhG9z74m/O7DCMesOzGYvJ7QWFzq80JX15P2T2cSGotLaCwuEfRyJmazdhMmk0kMDQ2JoaEh0dbWJjQajfD5fHL16lUSGRlJRo8eTb3GZrMJjUYnbD0zYr4ikph+GU5AoxM1G3tqLH63TxSuSdd1kbTN1lGhTWrepPj4+BAajUY4HA4ZNGgQuXnzZr1/I2dnZ7n7m5WVRczNzcm+ffua/HcGcIvUY1c/eJWxthQcfxdCzk+fPkVQUBBCQ0Ph4eGBZcuWwdzcvFnzag3379+Hu7s7unTp8t50eg8cOID9+/cjISGhSWlM1dXVsLCwQExMTKt3b/3yyy8ICwtDeHh4s89dvXo1hEJhszIxSkpKYGtri59//rnNM0aePHkCV1dXODs7Y9u2bX+L2tzatWuxYcMGqKmpQSQSoaqqCvr6+vhsexQVC3l5IRg1hU9g6L4B9DorT3F5EZ6HroDgIxdo9n8jKk+jAcOtdbFupAX12v/+9z/Mnz8fd+7cQUhICNauXQs1NTUqq8fExAQlpaUQDJ8PlqUdSuJDIcxJQbtpyrNEpJkNNOi6LERN4WMU/hIII68gqLezxP+WO8nZht9//x0TJ07E6dOnFQqalpSU4MaNGxgyZAiYTCbCwsLg4+ODO3fuwNraGnl5eXBwcICvr69c8LwxGlIZ+2BXuklPi8kXx26SzgFRpHNAlNxq1Pqv13yO3yRJT4ub3XdRuZDsj8sgi04mkhlH/ySLTiaS/XEZpKhc2OL5Pnv2jCxfvpzo6OgQb29vkpaW1uK+mktVVRWZP38+sbCwINeuXXvn40kkEjJ+/HjigO/ndQAAIABJREFU5+fX5HPWr19PZsyY0eqxz5w5Q0aPHt2ic21tbcn169ebdY6vry+ZPXt2i8ZriISEBNKuXTuye/fuNu+7OeTk5BA2m02tDDkcDklLSyNJT4uJzarzpP2cI9I2BotaydJYXKI7egnRtPckAORep7G4xGbVeZKcI/+5vHz5Mmnfvj0hhJBr164RJpNJjcliscgvv/xCYmJiiGY7c0JjsgnHtBtp73uY+sxrOUwj3A59qN9N/H4ivE4DCI3FIQwNfaI3eimx+DqSzD5+k2RnZxM+n0+ys7MJIYQMHTqUMBgMamXP5/OJs7MzIYSQwsJCYmdnRwQCAdHU1CT9+/cnFy9epOYdGBhIAMidy+fzG72v+KetdBsT2ZDxIdZ0Ki4uxp49e/Ddd99hyJAh+Prrr9G7d+/3Mvb71OktLi5Gr169sGfPHowaNarR44uKitCpUyekp6e3qrJEVFQUdu/eLSf52RQePnwIR0dH5OTkNFmc5tq1a5g0aRJSU1Pb9AkiIiICvr6++P7775t0794FhBD89ttvCAwMxJMnT1BWVgY2m419+/ZR2RltqUNdVVWFs2fP4ujRo7h58ybodDqKiorA4/Hw448/UrsDk3NK4H4oAVUi5fn1DY/NQJjPgA+i3NA/qgT73ymy0RZoa2sjICAAjx8/xscff4zRo0fDxcUFf/zxxzsf+22d3ry8vHc2lra2NpUKJtMIaAjZZonWJvW3NJB2+vRpfPbZZ002uDU1NfDx8cGOHTvazOASQrBt2zb4+fkhOjr6bzG4hBBERUWhf//+8Pf3h7+/P5KTk0Gj0TBmzBi5dDivARZY6doFPBYDjSVs0GhSo1fX4BJCkJCQAF9fX5iYmOD777+Ht7c3cnNzsW3bNgDAnj175LZjt0Xg+0OnwStLTEysV5AckEYfR44cCT09vQbTaB49egQulwsvLy+5198W+Ii5maZ03zURi1AUtQu5e6crbEUEgPIXBZg60BJqfAG1lW/9+vVU+86dO9GhQwdoaDQsSF7fvOoalZKSEnh7e8PAwAAGBgZyUpR1EQgEWLx4MR4/foxx48bB29sbDg4OiI6Ofmdas4C8Tm+fPn3w66+/vrOx7O3tMXfuXHh5eaG2tvGVyaJFi7Bv3z5UVdWf2tMYLTW6zd2FFhQUBEtLS0ycOLHZYylDLBZj7ty5OHbsGK5fv/7enn5kEEJw4cIFDBw4EMuWLcOyZcuQlJQENzc3mJiY4OrVq0plLr0GWCDMZwBGdjUEh0kHlylvMrhMOjhMOkZ2NUSYzwB4DbBAXl4eNm/ejC5dusDb2xvm5uZITk5GdHQ0PDw8wOPx4OHhgfj4eKW7u1pr7D946vM7kCb4dNPT00lISAg5c+aMXKTwbYYPH07s7e3JlClTqNeuXLlC9PX1SUpKCqmuria+vr7EyPojpdkFpl+GE81BHqS972Fitvwc0Z+wmtDYPMrn0973MAFAvjiq3F+XkZFB/s/edYdFcb3ds0vvvYlgpyqIoqhEihpbbFhQRBAVQbFhjI2okKgExa6xF2LvBQ02FBExYgWlKKCAFOkddim77/cHHxPXXaqYmPxynmceZebOnTu7cObOe9/3nKKiuhhTQUEB2dvb0+bNm0W2FTUuGxsb5ribmxtNnDiRKioqKCUlhTp37kyHDx9u9HMiIqqpqaETJ06Qqakp9erVi86fP088Hq/J8z4HDx48oA4dOtCCBQuIw+F8kWvU1taSjY0N+fv7N6v9yJEj6cCBA62+XmRkJPXr169F56Snp5OqqipVV1c3q31iYiKpqalRampqa4YohNLSUhoxYgQNGzaMSkpK2qTP5oLP59PNmzepX79+ZGJiQmfOnGn1711jayGVlZV06tQpGjZsGKmoqJCHhwc9fPjws7JqYtKLyPNY3bqOYQPrOp7HngjFj78GoJGYbpsspCUlJTVIuqdOnaJJkyaRr6+vAOkuWbKEvLy8mJ9fJb4jANTO80CjKV31m4RGR1Ift1KAdLv5XG1yMSw/P58GDx5Mc+fOFXn803FlZmYSAEpOTiYiIjU1NXr8+DFzfP369fTNN980/SH9P3g8Hl2+fJn69OlDxsbG9NtvvzWbDFqDwsJCmjhxIpmZmVF8fPwXuUZ6ejppamo2a5EqNDSUTExMWv3H+PjxY2rpAu/OnTtp+vTpzWrL5/MbfSi3FOnp6WRmZkYeHh5f9Hv+FHw+n27dukUDBgwgIyMjOnXqlEAKWltd448//iBPT09SVVWloUOH0smTJ6mysrJNr/MlFr6/NBoj3UbDC9HR0UKC5C1BaWkp1qxZI1IcpH4A9bgWU/cKX5OX1mS/DZUipux0Q9fOHTBjxgwhvdmTJ09CUVER6urqQoLkjY2r/v8fi2N8erwlurFsNhtjx45FVFQUduzYgaCgIBgYGGDPnj1fpMJMRUUFZ8+exfz582FjY4NDhw61eXijffv22LdvH6ZOndpkiXJ9scTNmzdbda3WhBdaYstz9OhRlJSUYOHCha0ZngBevHiB/v37Y9q0adi7d6+QYt6XAP2/sp+NjQ0WLFiAefPmITY2FlOmTGmzhdWPwweurq7Q19dHdHS0QPigLVHvYLx1ck8cmt4HWyf3hKdNl3+uZXxDbExEsLCwoKCgIJKXl2dmeqLQ0Ex34cKFFBAQQEQkNNMNDQ0lNTU1iomJocrKSuo+eDwBLFIfs7TRGa7+0ssk3cGc5HsO/yj8cI60p28l/WVXaPbeUJowYUKDyfiJiYm0atWqBosZPh1XfVL1yZMniYjI2dmZHBwcqLS0lJKSkqhz584kKSnZ4GfTHDx8+JBGjRpFOjo6FBgYSKWlpZ/VX0OIi4ujHj16kKOjIxNuaUt4eXnR5MmTm5zFHjlypNXFErGxsWRsbNzs9vn5+aSkpNSs2VdeXh5pamrS06dPWzW2j3Ht2jVSV1ens2fPfnZfzcXdu3dp4MCBZGBgQMePH2/TmS2Hw6HTp0/T8OHDSUVFhWbPnk2RkZF/WVHOPw1o7UyXzWY3WBbXFKKjoxEaGorFixeLPF4v8DFhwgR06NABUiraYEnJQExBTWT7ugcEX2QpIltSBlI63cBii4EnrYhdu3bh1q1bKC0tFeqjW7duAoLkTY2rY8eOUFBQYOrTd+zYARkZGXTr1g1jx46Fk5OTUO16S9G/f39cvXoV169fx9OnT9G5c2f4+fm1eYmxiYkJHj9+DE1NTVhYWODhw4dt2v+mTZsQHx/foMRlPZycnISk9ZqLloqYX716FUOGDGnW7GvJkiVwdnZG7969Wzyuj7F79264u7sjODi4zRbiGkN4eDjs7Ozg4eGB2bNnIy4uDs7Ozp89syUiREVFYe7cudDV1cWhQ4fg4uKCjIwM7N+/HwMGDPgiOhT/djQrL6M14hr37t1Damoq9PX1oa2tjU2bNuHChQsCq7bz5s1DUlIScnNzYTrgW4DPg4RGR5H9EREKQnaAV1EMDQcfsMREC6QpSIsjMTERQJ2HVffu3YXCGx8LkovCx+OaMGGCgPCIqqoqTpw4gezsbMTFxYHP5zPCGZ8Lc3NznD59GpGRkUhPT0fXrl2xdOnSzxZN/hjS0tKMTu/48eOxfv36ZmUeNAf1bsLLly/H69evG2xX7yzRUgsnoOUi5s3VWggNDcW9e/fw888/t3hM9eDxeFiyZAl27NiByMhI9O/fv9V9NQcREREYNGgQZs2ahRkzZiAhIQEuLi4QF/888cCsrCxs2LABJiYmcHFxgZ6eHqKjo3Hr1i1MnToVsrKybXQH/6NoaApMROjVqxcdP36cZGVlRdba8/l84nA4FBcXRwCIw+EQl1sX3K6oqKAPHz4w25IlS2jChAmUm5tLRHWvK69evSI+n09paWnUzbwvqQ5wbDCsIN9zOEm2MyS9788JHdN23UztZu8lgx+vUYchrnVVMiwWASBJSUlycXGhnJwcIqp7xTYxMaHFixeLfC34dFy2tra0cuVK5nhycjLl5+dTbW0thYSEkJqaGsXGxn7u24hIpKWl0cKFC0lFRYXmzp1L7969a9P+09PTyc7Ojuzt7SkjI6PN+t23bx+Zm5s3mjGRl5dHysrKlJ2d3aK+MzIySEdHp1ltS0tLSVFRkYqLixttV1lZSV26dKGrV6+2aCwfo6KighwcHMjW1pYKCgpa3U9zEBERQYMHD6ZOnTrR4cOH22SB7uPwgbKyMrm7u/8XPvgMoLXZC2JiYgJlcZ+W16WkpIgU7xCFT2O6RUVF1KNHD0bgY+H3P1A3n6siy/4aK0XssOIaqY9ZSmJKWsSSkCJ1DQ2SlZUlNpvNjElTU5Pk5eVJWlqaOnToQD/88IMAIXwsFvLpuD4VHjlz5gzp6OiQjIwMmZub040bN9rgK2ocOTk5tHLlSlJVVSUXF5c2zUKora2ldevWkZaWFgUHB7dJn/VlwgsXLmy0nYeHB/n6+rao75ycHFJXV29W27NnzzLlno3Bx8eHJk2a1KJxfIwPHz5Qnz59yMXFhZl0fAlERkbSkCFDqGPHjnTw4MHPJls+n09RUVE0d+5cUlVVpSFDhtDx48epoqKijUb8v4vGSPerKgP+WHC8pWCxgGEmWtg7zRKlpaUYPnw4nj17BmVlZezbtw+3b9/G7du3UVJSgsGDB+Pbb7/Ft99++9nx2L8SxcXFTInxN998Ax8fn8+OP9bj4cOHcHZ2xujRo7Fx40ZIS0t/Vn9FRUWwsLDAzp07MXr0aJFtEhISYG9vj9TU1GZfr6ioCJ06dWqWkLuTkxMGDRqE2bNnN9gmNjYW9vb2ePnyZas80+Lj4/Hdd9/Bzc0Na9as+SIxzkePHsHX1xdv3rzBqlWr4OrqCklJyVb3l5WVhePHjyMoKAg1NTVwc3ODi4sL9PX1mz75PzQLjZUBf1Wk25Z119XV1XB1dYWurq5ATDctLY0h4Dt37kBTU5MhYFtbWygoKLTZ/XwpVFRU4ODBg9i0aRNMTU3h4+MjpJ7UGhQXF8PDwwNv3rzB6dOnYWxs/Fn9RUZGYsKECXj+/DnatWsnss13332H8ePHY9asWc3qs6KiAhoaGozvVUOoqqqClpYW3rx506DWQ721uaurq0jPvaZw584dODk5YfPmzU2apLYGjx8/hq+vL+Lj4/Hjjz/Czc2t1WTL5XIRHByMoKAg/PHHH5g4cSLc3Nz+EYthbak0+FfhH0O6QNuKbDQFHo+HFy9eMCT85MkTWFhY4Ntvv8XQoUNhaWn5t8jtNRdVVVU4duwYAgICoKOjAx8fHwwfPvyz/oiICIcOHcLKlSsREBCAmTNnflZ/a9euRVhYGG7fvi3yswwNDcWiRYsQGxvbrOtUV1dDTk6uyQyGkJAQBAQE4P79+w222bNnD44fP46IiIhmazLU48iRI1ixYgXOnDnToLVLa/HkyRP4+fnh1atX8PHxwYwZM5rtBPwxiAhPnz7FkSNHcObMGVhYWMDNzQ3jx4//RyyGxaQX49d7yQhPzAMAVImQYrUz1ICXbVeY631dmgv/KNIF/j6VsYqKCkRERDAknJGRAXt7e2Ym3Bpfrb8CtbW1OHfuHPz9/SEhIQEfHx84ODh81gMjISEBU6ZMgaGhIfbv399q0Rcej4fBgwdj6NChAn549SAimJubIzAwEMOGDWuyPyICm80Gn89vlKTd3d3RvXt3eHt7izyelZUFc3NzhIWFtUjjl4iwevVqnDp1Cr///nuTLrctwbNnz+Dr64uYmBisXLkSs2bNahXZfvjwgQkfVFVVMeGDv1Ln+XPxT1YaBP6BpAt8GcHxluLDhw8IDQ1lSFhGRoYh4EGDBjHuv18L+Hw+rl27hvXr16O0tBQrVqzA1KlTW10JxeVysXTpUly9ehUnT57EgAEDWtVPRkYGevfujcuXL4tMowoKCsLp06dx48aNZvUnLi4ODofT4H3xeDzo6Ojg8ePH6Nixo8g2kyZNgqGhIdatW9fs+6iqqsKMGTOQkpKCK1euQFNTs9nnNobnz5/Dz88Pz58/x4oVK+Du7t7imDqXy8XVq1cRFBSEhw8fYsKECXBzc4O1tfVXHz74FH/l2+6Xwj+SdOtRUF6F888z8PpDGUq5NVCUloCRjgIm9vpr4zlEhLi4OIaAHzx4AGNjY4aE+/fv/1mLG20JIsLdu3fh7++Pt2/fYtmyZZgxY0aryzODg4Ph4eHxWTq9V65cgbe3N168eCE0a26ps4SsrCzy8/MbfEWu97969uyZyONXr17F999/j5cvXzb7MykoKMC4ceOgra2No0ePtkmpa3R0NPz8/PDkyRMsX74cHh4eLSLb+vBBUFAQzpw5g549e8LNzQ0ODg6Qk5P77PH9Hfhf0NP9ap0jvnZwuVwKCwujlStXkqWlJSkoKNDIkSNp69atFBsb+9XkN/7xxx80ZswY0tbWpg0bNrS6xDgjI4Ps7OzIzs6u1Tm98+bNI0dHR5Gfzc8//0yzZs1qVj+KioqNljEvXLiQ1q5dK/JYWVkZ6evrU2hoaPMGTXVl7t26daNly5a1iTJcdHQ0OTg4kI6ODm3btq3FAjFZWVm0ceNGMjExoc6dO9PPP//cpCLazp07qXfv3iQpKSkg/lNVVUUTJkxgPNXCwsIEzuNyueTp6UmampqkoqJCo0aNavD7b6qvu3fvkp2dHSkqKopMLU1JSSEd497EEpcicdX2pDllXYN5+8r2M0hCXZ9YkjIkpqRFyvYzGOcIojq3CHV1dVJQUCAzMzO6fPmywLVyc3PJycmJlJSUSFlZmaZOndrgZ7dq1Srq3r07iYmJCaU4Xrt2jaytrUlJSYm0tLTI3d2dSktLv7zK2H+oq/E/e/YszZ49mzp27Ejt2rUjV1dXOn78eIsLAL4EYmJiyMnJidTV1WnNmjWUn5/f4j4+zum9cuVKi8+vrKykHj160MGDB4WO5ebmkrKyMlPE0hjU1NSYIptPwefzSU9Pj+Li4kQe9/b2JldX12aPOSIigrS0tGjfvn3NPqchvHz5ksaPH0/a2tq0ZcuWFuXDcrlcOnv2LI0cOZKUlZVp5syZdP/+/WY/3C9cuECXLl2iOXPmCJHu1q1bKSIigrS1tYWIcsOGDWRmZkbZ2dnE4XBo2rRp5ODgIPIaTfUVFRVFR48epX379okkXcs+VqRsNY70llwg9XEriSUlR+0XnhBNunZupO22jfSXXaF2s/fWWfaMWUoGq0Iov4xLMTExVFNTQ0R11kjy8vKUlZXFXOubb76hxYsXU3FxMVVXV9Pz588b/OyCgoIoJCSExowZI0S6J06coOvXr1NFRQUVFhbS8OHDydPT8z/S/avB5/MpKSmJdu/eTePGjSNlZWUyMzOjJUuW0I0bN/7W5PPExERyd3cnFRUVWrJkCWVmZra4j8jISOrQoQPNnz+/xTq9cXFxpK6uLrLAw8PDg/z8/JrsQ1tbu8FxP3nyhAwMDESS0dOnT0lLS4vy8vKaNdZTp06Ruro6Xb9+vVntG8KrV69o4sSJpKWlRZs2bWr298/n8+nJkyc0b948UlNTo0GDBtHRo0epvLy81WP58ccfG5S51NXVFSLKOXPm0NKlS5mfr127RgYGBk1eR1Rf9bh9+7YQ6b5584bEJSSo69LzDLFKtTch1WFezZJ6Veg9mhR6jSLDVSG0N1xQnCsqKoqkpKQoKiqKiIhu3rxJHTp0aLEgkLOzc5PFPBcuXKDu3bu3XvDmP7QOLBYLXbt2xdy5c3Hp0iXk5eVh7969UFRUxLp166ClpYXBgwdjw4YNeP78Ofj85i8YfC66deuGAwcO4OXLl4ymxNy5c5GSktLsPgYMGIDo6Gjk5OTAysoKCQkJzT7XxMQE/v7+cHJyEpKy9Pb2xu7du5uUuGxM3vHSpUsYP3680OJRbW0tZs+ejY0bN0JdXb3R/okI/v7+WLZsGe7cuYPhw4c3486EER8fj8mTJ2Pw4MHo27cv3r59iyVLljSZrpWdnY1NmzahR48ecHR0hKamJp4+fYo7d+7AxcXlL43Xzpo1C5GRkcjKykJlZSVOnDiBESNGtPl14uLioKChixqxP2PakpqdUJP3vslziQjc9DhIaOiDW8vH6w9lAIBRo0ZBWloaVlZWsLOzg6VlXYj10aNHMDQ0xPTp06GmpoY+ffogPDy8Te7j/v37MDU1bbTNV0G6+eVV2Bv+Ft5nXmDmb0/gfeYF9oa/RUF51d89tDaBuLg4+vfvjzVr1iAiIgJZWVnw9vZGZmYmnJ2doaWlhSlTpuDQoUN4/77pX7K2QPv27bFt2za8efMGqqqqsLS0hIuLC+Lj45t1vrKyMs6cOYMFCxbAxsYGBw8ebLYokru7O7p164Zly5YJ7Dc2Nkbv3r1x4sSJRs9vTGmsIYGb7du3Q1VVtckihpqaGsyePRvnz5/Ho0ePYGZm1sTdCCMhIQFOTk6wt7dHr1698PbtWyxdurRRsqyqqsL58+cxatQoGBsbIz4+Hrt370ZycjLWrFnTYBbGl4aBgQH09fWhq6sLRUVFJCQkYM2aNZ/VZ1FRET58+IBVq1YhOjoaRITy8nKIS8sLtGNJyYFf3bS1U8mDkwDxId/jWwBAKbfud+PatWsoKytDSEgIhg0bxuRiZ2Rk4NatW7C3t0d2djaWLFmCsWPHCmlwtxS3b9/Gb7/91qRo0t9KujHpxfA49hTWG+5ia2giLkdn4e7rXFyOzsK20EQM2HAXnsefIia96ZLPfxIUFBQwevRo7NixAwkJCXj+/DmGDh2K0NBQ9O7dG4aGhpg/fz6Cg4NFylO2JTQ0NLB+/Xq8e/cOJiYmsLe3x/jx49GcrBUWiwV3d3fcv38fO3fuxOTJk5tVnstisbB//34EBwcLebh9//332Lp1a6ME3pDSWEJCAsrLy5kZTT1SU1Pxyy+/YM+ePY2mTxUXF2PEiBHIzs7G/fv3G6yiawivX7+Gs7MzbG1tYW5ujrdv32L58uWQl5cX2Z6I8OzZMyxYsADt27fH7t274ejoiPT0dBw+fBg2NjYtLtpoa8ydOxdcLhcFBQWoqKjA+PHjP3umW//9bdy4EQMGDICSkhL8/f1RW1Uh0I6qKsGWbDxLpPTZVZTH3oXmJD+wxOtSCBWl/0wllJCQwIgRI3Dz5k0EBwcDqFPD69ixI2bNmgUJCQlMmTIFenp6iIyMbPU9PXr0CFOnTsX58+dhYGDQaNu/7Rs9/igVUw48wu2EHFTV8gWqTYC6vNyqWj5uxedgyoFHX43b75eAnp4eZs6ciVOnTiEnJwenT5+Gvr4+du7cCV1dXXzzzTf46aef8PDhw0YNNT8HSkpKWLlyJVJSUmBnZwcHBwcMGzYM4eHhTc5gjY2NERUVBS0tLfTs2bNZOr31bsKzZ88WcC0ePHgw2Gw2bt++3eC5DYUX6h0iPiZWIsK8efOwePFidOvWrcE+09LS8M0338DIyAiXL19ukChFITExEdOmTcPAgQNhamqKt2/fYsWKFQ32kZ2djc2bN8PMzAyTJk2ChoYGnjx5grt378LV1bVF1/7SiImJgZubG1RVVSElJYUFCxbg8ePHLZoVcjgcvHjxAidOnMCPP/6IjRs3Aqh7q+BwOKioqEBNTQ3KcjMhwfsztFSdmwIJjYb1IMpjbqH00XloOa2HuGJdyEhanA0jHeFS/o/lXM3MzNo0d/nFixcYM2YMDh8+jMGDBzfZ/m8h3X+6zfqXBJvNhoWFBZYtW4bbt28jNzcXa9asQXl5Oby8vKCuro5x48bh119/RVJSUptb78jKymLhwoV4+/YtHB0d4e7ujoEDByIkJKTRa9Xr9O7YsaPZOr3W1taYP38+XFxcmLYsFguLFy/Gli1bGjyvIdIV5fh77tw5pKWlYenSpQ329/TpUwwYMADu7u7YuXNns/Vok5KS4OrqCmtraxgZGeHt27fw8fERqd9RVVWFCxcuYPTo0TAyMkJsbCx27dr1l4UPamtrweVywePxwOPxwOVymQd4VVUVE0evrq4Gl8tlvus+ffowFkY1NTXYvXs32rVrJzIuXllZiUePHuHQoUNMcU7nzp2hoqICV1dXBAcHg81mw97enilskZGRwb59+5CUlARz854oiDgJqq1G5ZuHqM5Lhayhtcj7KY8LQ9H9o9CavA4SytrMfgJgLleB69evg8PhoKamBsePH8f9+/dha2sLAHBwcEBRURF+++038Hg8nD9/HpmZmbC2Fn2tmpoacLlc8Pl8gc8RqBNMGj58eKPCTkJoaIWNiMBiscjOzq7RHMD4+Hiyt7cnRUVF6tKlC128eFHgeGhoKBkaGpKMjAzZ2dlRyMMYMlp9XdiG54dLJGf2LYkpahBLUoYkNDuT5iS/PzVzXTaRbCcLUlRSJnV1dZo4caJACsinaCgvsR5nzpwhIyMjkpeXJ2NjY7p06ZJQm6qqKjI0NCRdXd0Gr/NXIzs7m06cOEFubm6kq6tLHTp0IHd3dzpz5kyr0sCaQm1tLZ06dYp69OhBPXv2pLNnzza56tuSnN7a2lqytbWldevWMfu4XC5pa2s3qFNsZWVFDx8+FNiXlpZG6urqTJoQUZ0pp46ODkVGRjZ4/cuXL5O6urrI778hJCcn0/Tp00lNTY1++umnBvV6+Xw+PXv2jObPn0/q6upkZ2dHQUFBVFZW1uxrtRV8fX2FZFjrV+Lr82o/3lJSUoioLhVy6tSppKGhQUpKSmRtbU1hYWH05MkTCgoKIjU1NerZsyd16tSJpKWlSUJCQqivpKQkIiIKCwsTOtanTx9mjCkpKaRj1ItY4pIkrqorkKer5RxALAlp5mcxJS0CW0xA6lXeYjh5HntC8fHx1LdvX5KXlyclJSWytLQU4qX79+9T9+7dSU5Ojnr37k33799njnl6epKnpyfz8/Tp04XGfeTIESKqcwdnsVgkJyfHbCYmJq2XduzVqxcNHjwYERERePRri8+nAAAgAElEQVTokdDx2tpamJiYYM6cOVi0aBHCw8MxevRovHjxAgYGBsjPz0eXLl1w8OBBjB49GqtXr8bRSzcg6xggNMPlV3NRGnUB8j2GQExJA5y3T5EfHIh2M3dBXFkLnLdPQTVcjBo5DLuc+2L+/PnIyspqsHT04sWLYLPZuHnzJjgcDoKCgphjmZmZ6NSpE65cuYLhw4cjJCQEkyZNQmpqqkBp5/r163Hz5k28e/cOGRkZDX5OfxeICAkJCUyVXEREBLp168YI9gwYMKBVtfsNXau+xLi4uBgrVqyAs7Nzo6W4AQEB2LlzJ/bv348xY8Y02Hd9mfClS5eYUuO1a9fi/fv3OHDggFB7GxsbrF27lpm5AHULZTExMTh8+DCzz9PTE2w2G3v27BF5P9u3b0dgYCAuX76MPn36NPkZvHv3DuvWrUNwcDDmz58Pb29vkZoUOTk5OHHiBIKCglBWVgY3Nze4urqiU6dOTV7ja0JZWRkSEhIQHx+PuLg4xMfHIz4+Hjk5OTAwMICpqSlMTEyYfzt37tzst4Ta2lqw2WyhmPX/QkVak2XA4eHhUFdXx4sXL4TEPWJjY9GvXz+UlZUxMZKhQ4fCysoKa9euxf79+5lacABIyylEp/Y60JmxHRJqek0OPOvQfChZO0HO6M9pv5Q4Gw+XD0JaYhxsbW1RVlbWaB+rVq1CRkaGAOlGRUVh9OjRyM3NZfZpaGggODiY0QZISUnByJEjsWXLFsyePfurJN1PUV1djUePHjEkHB8fD2tra6ZUuXv37p8dyyIi3Lt3D+vXr0dSUhKWLVuGmTNnNlgW+/DhQ0ydOhWjR49GYGBgg2Wun5YJ5+XlwcDAAG/evBHSOBg8eDBWrlyJIUOGMPtsbW2xdOlSjBo1CgDw4MEDTJ48GXFxcULEyOPx4O3tjbt37+L3339v8tU+JSUF69evx6VLl5j4sIqKikCb6upqXLt2DUFBQYiIiMC4cePg5uaGgQMH/u2LYU2htLSUIdSPCTY/Px+GhoYMqdYTbKdOnb6o+t6/XXuhyceSnJwcunTpgri4OCHSFUXYRH9aksfFxcHc3Jw5dv11ESRUdFCd975J0m3IZp0F4PzzDHCe/5kPl5qaCh6P12wVMEtLSxgbGyM4OBjfffcdrl69CikpKYH0oAULFsDf37/N7aS/JCQlJWFjY8PMBIuKinD37l3cvn0bv/76KyorKzFkyBAMHToUQ4YMaZVoN4vFgr29Pezt7REVFYVffvkF69atg7e3N+bOnQtFRUWB9vU5vR4eHrCysmpQp3fs2LEIDQ2Fh4cHzpw5Aw0NDUyaNAl79uyBr6+vQNtPY7q5ubmIiYlhSLiqqgoeHh7Yvn27EOGWl5czOcKRkZGNqqelpqZi/fr1uHjxIry8vJCUlCQgckREiI6ORlBQEE6ePAlTU1O4ubnh5MmTX9ViWD2Ki4uRkJDAkGr9v4WFhTA2NmZI1cvLCyYmJujYsePfIm1aT5z/ZJWxxtCsdwElJSWRM0ojIyNoamoiMDAQixcvRlhYGMLDw2Fvbw+g7hdcQ0ODaf86uxQsSVlQE7l3xKtFfvAmyPcYLETO3Fo+Ih49Q0jAz/D29kb//v0RFRWFKVOm4OTJk825HYiJicHV1RVTp04Fl8uFpKQkzp07x+RRXrp0CbW1tXBwcMC9e/ea1efXCBUVFUyYMAETJkwAUPd6fPv2bVy5cgWLFi2Crq4uMwu2sbFpcdK9lZUVLl++jFevXiEgIACdO3eGl5cXFi1aBDW1P12d63N6Dx06BBsbG/zyyy+YNWuW0Kw7MDAQffv2xaFDh+Du7g5vb28MGjQIy5cvF5ghf0q6wcHBGDZsGNNm48aN6NKlC3Pf9cjKysKoUaNgYWGBvXv3Nhgaef/+PdavX4/z589jzpw5SExMFLif3NxcJnxQWlqK6dOnIyoqCp07d27R5/elUFRUJBQSiIuLQ0lJCYyNjZmZ6+DBg2FiYoIOHTp8dbPxaf06wqy98t+uNPgl0CzSLS0tFbkiKyEhgcuXL2PBggXYsGEDLC0t4ejoyMQR5eXlBfJMS7m14FdXgtVI7l1DNuv1qCnKwrlfl6O2ogTr1q1j/vgqKyvx+PFjaGlpQUtLq1G1ptDQUCxbtgz37t1Dr1698OzZM4wZMwbXr19nkvZbajn/T0Dnzp3h6ekJT09P8Hg8PH36FLdv30ZAQAAcHR1haWmJoUOH4ttvv4WFhUWzZzk9evTAiRMnkJycjI0bN6Jbt26YMWMGlixZwuS61uf0WltbY8qUKbh165aQTq+0tDROnz4NGxsbWFtbw8TEBL169cLJkycxc+ZMpt2nxREXL17E9OnTAdSlb23fvh3Pnz8XIPWXL19i1KhRmDt3LlasWCEyzJKeng5/f3+cPXuWcdCoX6Wvrq7G77//jqCgIISHh2PcuHHYvn3735pLW1BQIBQSiI+PR1lZmUCsdejQoTA1NYWent5XR66Nway9MvZOs/xqlAbbDA2tsNH/ay+Ul5eTjIwMJSQkNGuVtH///rR3714iqnOFHTBgAHPMKyiSWOJS1G72HpH10/rLr5JcjyEkpd+D9JZcEDquO/cwiSlqUr+pi8nY2JgkJSUJALHZbDI2NiZLS0vS09MjSUlJUlRUpG7dupGenh516NCBvLy86KeffqK9e/eSq6sr2djYUHJyMrOSPHbsWAoMDKQXL16QuLg4aWlpkZaWFqmoqBCbzSYtLS1mRfffiLKyMrp27RotWrSIjI2NSU1NjSZNmkT79+9v8X2np6eTt7c3qaiokKenJ719+1bgOIfDofnz51OHDh1EZhbs37+fzMzMiMPh0K1bt8jU1FRAS2Hy5Ml08uRJIiIqLi4mBQUFKikpIT6fT/b29rRlyxaB/m7cuEEaGhp06tSpBsfr5eVFKioqtGzZMgExnefPn9PChQtJQ0ODbG1t6ciRI61Wamst8vLy6N69e7R7926aP38+2dvbk5aWFikqKlK/fv1o5syZtHnzZrp+/TqlpaV9NQp3/8tAawVvLCwsaNmyZWRlZdVg5zExMcThcKiiooICAwOpY8eOjCNqbm4uKSoq0vnz54nD4dBQJw+S1jVslc267rwgElfWJo3BM2lveDLx+Xw6f/48qaqqkri4OB07dowZE5/Pp7y8PIqJiSFnZ2caOHAgbdmyhXx8fGj27Nk0YMAAEhcXp3bt2pGsrCxJS0sTm80mIyMjGj16NE2bNo0WL15M/v7+tGTJElJTU6OIiAjKz8//n/mFTk9PpyNHjtDUqVNJU1OTunbtSl5eXnTp0qUmLc3rkZubSz/++COpqanRtGnThFLArly5QpqamrR27VqBNDQ+n0+TJk2i+fPnE5/Pp+7du9PNmzeZ49OmTaPffvuNiIhOnjxJ3333HRERHTlyhHr37i2QNrZv3z7S0tKiiIgIofFlZGTQvHnzSEVFhX744QdG4SwnJ4e2bt1K5ubm1KFDB1qzZg0lJycLnd+W4PP5lJOTQ2FhYbRr1y7y8vIiOzs7JlWrf//+5O7uTlu2bKGbN29Senr6/8zv4j8RjZFuo9kLbDabbGxsEBQUxKzw+vv7IyIiAtevXwcALF26FAcPHkRNTQ0GDhyInTt3omvXrkwfoaGhmD9/PtLS0tDLsg8+9JwJvnxdnLfk4VlwM+Kg5fgTaktykblnJiAmARb7z9da1eHzIG9qj+IHJ1Hy4CRYEtKQlfzz+IcPH7Bp0yZUVlYiNjaWGZefnx9++ukngfvx9fWFn58fAGDXrl3Ytm0bcnJyoK6ujilTpmD06NHIyckR2GJjYxEVFQV9fX3k5OSguroampqaTBjj0+3jY6qqqv+o17mGwOfz8erVKyYr4uHDh+jRowcTD7aysmrUnaKkpAR79uzBtm3b0L9/f/j4+DApWpmZmZg2bRqICMePH2fcmYuLi9GzZ0/s2LEDBQUFOHv2LI6du4zzzzJw5NJNKKppwdSgM56GBsOxjx6cHEaje/fuuH79Onr16gU+n4+VK1fi0qVL+P333wWq0bKyshAQEIDjx49j5syZWLp0KVRUVBASEoKgoCDcu3cPY8eOhZubG2xtbdv0OyQi5OTkCIUF4uLiwOPxhNKwTExM0K5du3+c+8P/Or4q54i2sln/u8DhcJCbmytEzqK28vJyqKurN4ugNTQ0vmoTzI/B5XLx4MEDhoTfvXsHGxsbJh5sYGAgkiQqKytx6NAhBAYGwsjICD4+PrC1tQWfz0dAQAB27NiB/fv3Y+zYsQDq0s0cHBxwJPguPLdfhHSnXmCz2QIl41RTBSlpaSiUv4eZeDaObPIDh8OBq6srsrOzcfnyZWYR7MOHD9iwYQOOHj0KNzc3LFu2DDk5OThy5AhOnjwJIyMjzJgxAxMnTvxsV2giQnZ2tlCmQL2gkChy1dbW/o9c/yX4qkj335L83BxUV1cLEXRDhF1UVAQVFZUGCfpjktbU1PxqrIEAIC8vD3fu3MHt27dx69YtsFgsZhY8ePBggQwWoO5zOX78OAICAqChoQEfHx+MHDkSN+5FYu6GIOh274tuJmZQlpPCi5dxSKuRB8TEUZcw2AD4fEhLimORrR6Orp6NTp064fDhw5CWlkZOTg42bNiAoKAguLq6wt3dHXfu3EFQUBAKCwsxffp0uLq6CryhNRdEhKysLKFZa3x8PMTExGBqaipEsJqamv+R678cXxXpAv+O5Oe2Rm1tLfLz8xucNX9M1nl5eVBQUGiUoD/eWmpy+DkgIrx584aZBYeHh6NLly7MLNja2poZT33d+8+//obqLnYgHROIsdmo4n2GnkRtFfpKZOD0uvnIz8/Hxo0bcfjwYTg5OcHS0hLBwcEICwvDmDFj4ObmBjs7u2aFD4gIGRkZQrPW+Ph4SElJCc1aTU1NhR42/+GvQ355Fc4/y8Dr7FKUcmuhKC0OI21FTOr912Q8fHWkC/zzLZb/TvD5fBQWFjYrxJGbmwtpaelG49Afb22d1F9TU4OoqChmFhwbG4sBAwYwM+GXlUpYfz0BVTU8UGMz2RZAWpwNa+4TXDq0DUOHDoWCggKCg4NhaGgINzc3TJw4UaiIox5EhPfv34tMxZKVlRUZFmhKFP0//HWISS/Gr/eSEZ6YBwACoaj63F47Qw142XaFud6Xe2P+KkkX+Dps1v/tICKUlJQ0i6BzcnLAYrEajT1/vB07dgy//fYbXr16BScnJ4FS6zt37mDevHl4//49rKysEBQUhA4dOqC4uBhhYWG4ffs2brytAK/HWNSW5KLg1h5U5yRDTEYJKvYzIGso2u69Oi8VRXcPoTr7LficUnRYcU34nvl8yBYmQfzREaSkpEBKSgpFRUU4fPgw3NzcANQ9uOqLIE6fPo2qqiooKSmBw+FAUVERpqamqKmpQUpKCj58+IAJEybg1KlTX+Ir+g9thK9pIvfVkm49/nXJz18xUlNT4eXlhT/++ANSUlKYOHEitm3bBnFxcZw5cwZr1qxBZmYmNDQ04OjoiE6dOgkRc3Z2Nt6/f88UKIiLi0NJSQljx46FlpYW5OTksH79eixduhQ5OTnYt28fjIyMGFufESNGIPx+BLj/H9enGi7YcipoPy8I3PexyLvwM3Rm7ICEqi6qMl+jOOI4qrOTARYbktpdId3RAhIqOsi7uA5aTv4ojjyF6py3YEvJo71XneANi3jwNa/Czk0BePfuHUpLS6GiooK+ffsiLy8PCQkJkJaWRllZGSZPnoxevXohICAAeXl5TOk3j8fD1q1bERMTw4gmbd++Hdu2bUNubi709fVx5cqVJkWr/8OXx9cWsmyMdL+KfCY1eSl42nTB1sk9cWh6H2yd3BOeNl3+I9wvAC8vL2hqauLDhw+Ijo5GeHg4du/ejczMTLi4uGDbtm0oKyvDrl27sHPnTowfPx6+vr7YvXs3Lly4gAcPHiAmJgY+Pj5ISEjA27dvYWtri+LiYnTt2hWysrIIDQ2FrKwsrl+/jqCgILBYLLx+/RqampqwsLAAEcF49mbof38O2q6bABYLChYjwGKLQaajOaR0TVARexcAwOeWQ77ncOjOPQxdr8MQk1cFN/UFI27NkpCCvNm3ULGfKXijRFgbdA2vXr2CjIwMEwOPiIhAQEAAMjIyMHToUCxZsgRHjx6Ft7c3hg4dCklJSZSXl6O8vBwcDgdz5sxhsh8OHjyIQ4cO4ffff0d5eTmuXbv2PxVa2LVrFywtLSElJcW8MdTj7NmzMDY2hoKCAkxMTHD58mXmmJ+fHyQkJCAvL89s7969E3mN6upqTJw4ER07dgSLxRJZhv/8+XPY2NhAXl4eWlpaWOYXgPUhrwUIl/v+FdICRqHo/rEG7yfn4SXMHNEf8gqKaNeuHRYvXsxoDOfm5sLJyQnt2rWDkpISrK2tERUV1WBfgYGB6N69OxQUFJpUk/sqSPc//HVISUmBo6MjpKWloa2tjeHDhyMuLg4ZGRlQVlbGiBEjwGKx8N1330FOTo5R2/8YcnJy8PPzg5GRETp37ox+/fpBUVERBgYGWLVqFeOIoKamhosXL0JfXx/6+vpYt24dDh48iBlzFqBEVhdgsVBbWgAQQc7U/qMrEKrz0gAAMl0sIWf0DdhSsmBLSEOh9yhUZf5phCnVzhDy3QdB/CMhawAgtjj6fueEzMxMZGRkoHv37li6dClYLBaUlZWhrKwsJMikra3NWNN8CiLCTz/9hK1bt8LExAQsFgtdunQREMD5t6Ndu3ZYtWqVQEk28Geu9ZYtW1BaWorAwEBMnTpVQMVv8uTJzMOsvLy8UZ2Kb775BsePH4e2trbQsfz8fAwfPhyenp4oKChAcnIyUqS7gFv7ZzYU8WpRGLofku0MG70fma59oT1jG6btuYvY2FjExMRgx44dAOp0Y/r06YNnz54xGS7fffcdysvLRfZFRDh69CiKiooalJutR/PEL/9m/N0rkf8mLFq0CKdPn4adnR2Kiopw/fp1rF27tlnKaw2hvLwcJSUljOpbeXk5CgoKICkpiZEjRwKo0+GQlJRE9+7dcfeDGNjsLIBHqM56DYhJoPJNJBT7jAP3/Utw38dCukMPkdeqSo+DhHrDFi4f415kFHR/GMOEQR49egQej4chQ4ZAUlISBQUFWLhwIVavXg0JCQnGgkZLSwtSUlLQ19dHp06dkJycjMrKSmRmZmLFihVISEgAm82GkZERrK2tISkpCQkJCYFN1L6WbA2dLy4u/relm9Ubfj59+lRA6vTjBzYAgQf2p7KcTUFSUhLe3t4AIJC3npiYiJ9//hmysrIYNmwYnJ2dAQBlNcDLCnkQ/TnLLX18CTKdLMCrKGn0WhIqdSp7YW/yUDCwHdhsNpKTkwHU6ZR8//33TFsPDw/88MMPePPmDXr37i3U18cmq4aGjZP9V026ja9EZmNraOJfshL5b4KtrS0OHDgARUVF8Hg8TJ8+HePGjQOLxWpUee1j8Pl8lJaWorCwELm5uTh9+jQ0NTVx7949XLx4Ec+ePUN8fDzs7OxgZ2eHrKws8Hg8eHp6wsPDA5pjl0K8a91CWUXcPSgNcATn7VOUProASZ2ukDP+BhATrnCrzk1BSeQpaExY1ax7lZVgwWrkSHTr1g0XLlxAWVkZXF1dsXLlStTW1mLQoEGYO3cuhg4dipqaGjx58gQzZ87ExYsXkZaWBj8/P4wePRpycnJITk5GZmYmqqur4e/vj9LSUuzYsQMdOnRA7969UVNTw9i6VFdXMz+3dmuoDx6PB3Fx8VaTdlucFxcXh6KiIly5cgUSEhIQExNDu3btsGHDBtja2uKPP/6AmJgYZGRkkJKSgtLSUgQHB0NFRQXa2tqYO3cu5s2b16JioISEBJw9e5aRcO3duzfS09Oh3bU7aiynA3J1YZ7aklyUv7wNnRnbUXhrb5P9VsTdQ/rNX2GwjgN1dXVs3rxZZLvo6GhUV1c3K5e7sXUy4Csm3aZWIuszHW7F5+B+Yv5/KWXNAJ/Px7Bhw+Dp6YmHDx8iLy8Ps2bNwqxZs9CjRw/4+vri+++/h6KiIuLj4+Ho6IiBAweCiFBUVITCwkIUFRWhpKQE8vLyUFZWRmlpKbhcLjQ0NBAdHQ0VFRVUVFRAXl4ec+bMgaqqKpycnFBQUICHDx+iV69emHX0Ke6+zgU3PQ68iiIo9hkHZWsnZpzZx36AXHdBg7+aoizknvWFyhAPSOt1R01RVqP3KgY+HOz7or+yKRM+kZGRwdGjR3HgwAEYGBigsrISZ8+ehZqaGgwMDKCmpgYtLS3G5aKiogJPnjyBsbExuFwuoqOjsWPHDsaxQkZGBg8ePMCKFSva+JtqGPU+Xa0h7JYQPYfDQWlpqch2iYmJKC8vx6FDh5jzKisr4ePjAz6fDxaLBV1dXUyaNAk1NTWorKyEhIQEeDweUlNTsWjRIixatAhsNrtRcs/JyYG7uztUVFRQWloKPp8PPp+PpKQkAICLiwte5tUg6+IGaLsEAgAKb++Dss20Jl2E6yFnagc5UzvYadVCr+AptLS0hNqUlpbCxcUFvr6+UFJSarLPeqmBhvBVkm5LViI/Nq4E8D9HvDweD8XFxQKkWFhYKPD/+n9zc3ORnp6OnTt3Yt26dSAiyMrKIjw8HDo6OpCTk8P79++hqqqKTp06oWvXrlBTU4OLiwtUVFSgqqoKVVVVKCkpQUxMDG5ubkhNTUWfPn2Qk5PDZEFcvXoVxcXFmDVrFqSkpJCbmws2m81YzEtQ3et+RewdyBr0R21xNiRUdUHER9nzENSWF0G+x5+uELUlucg5tQpK1lMgZ2oPqq0G8eoWPKi2GqIq1YgIR1Z7IrJDOxQWFkJBQQH+/v6YPn06ysvL8fbtW5w/fx579uzB0aNHkZmZifj4eEhLS8PGxgYGBgbIyMhAYWEhVFVVISMjA0lJSfD5zV8d/xJgs9mQlJT8WysSP3VjCQ0NxeTJkxEVFSUglXru3Dn07NlT6PyAgAA8efIEZ86cafQhYGNjg+XLl8Pc3BwhISHYsGEDeDwe2Gw2TExM4OTkhNp34oi5MRR8bgW46bHgV3MgZ2zT4nsSU2kHU+06AfeLFy8y+zkcDkaPHo1+/fph5cqVTfaza9cuHD16tNE2Xx3pxqQXC61ENgecGj7Wh7yGWXvlf1xOLxGhsrJSJFE2RqKFhYUoLy+HgoIC1NTUGGL8+F9dXV306NGD2Td16lS4uLjAx8cHPB4PM2bMgKysLDw8PDBhwgR4e3ujZ8+eePHiBbZt24bAwEAMHTpUaMxz5szBnTt3kJmZifv37wMAjh8/Dl9fX4SHh+POnTvw8fFBRkYGJCQk4OzsjMTERBgZGSGzWhq1fBaqspOg4eCDitgwlMfcBPF5kNIzhdaUtWCJ14UXqjLfIPvYD1DsNxEKFiNRW5yDzL2zmHG83zQebAUNqA+fB4CQfXo1pHWNoGlggaB9u+Ds7MwI8M+ZMwdz5szBuXPnMHHiRFhZWUFHRwcbNmwAh8OBnZ0dNm3ahKKiIty6dQtHjx5lwg71GDVqFFxcXKCrq4v9+/dj/vz54PF4/xjdjC+B6Oho2NjYwNKyLkOqT58+sLKyQmhoqEjSZbFYICKIi4tDXFy8QXcWCQkJdOvWDX379sXbt29RVVWF9u3bw9LSEpcuXQIAXDl07/9bE7hpMajOTkL6zml1e6oqARYbNbmp0Jy4utF7UJSWQG1NrcDCcVVVFcaNGwddXV3s27evyc/h8OHDCAgIwP379xt1sWkW6VZVVcHLywuhoaEoLCxE165d4e/vjxEjRuDRo0dYvXo1nj17BjExMdjZ2WHHjh1CVjDV1dUwMzNDeXl5o35jPr+eRPKBX8ArzYNkOwOof7cY4kqig/E8ThkKQraDm/oCbBlFqNhNx+576kKCOHl5eTh//jwOHjyIpKQkKCoqYurUqfD392eM9Ozs7PDo0SPmZ11dXbx584YZ+9SpU/H06VOkpaUhLCwMdnZ2QuOpra1tkDQbI8+ioiKIiYkxM0lR5KmnpyfymJKSUotUsK5duwZvb2/o6+tDTEwM9vb22Lp1KzQ1NeHn54eJEyciJyeH0USoJ9yP1eXS0tKwb98+SElJCcR89+3bB2dnZ3z48AF8Ph9DhgzBvXv3kJSUhNevX8PR0RELFixAu86GMJ/uh7y7mZDuYAaZjuZQGfTninjWQS8o9p8EeVN7cFKeASCUPbuKsmdXAQAsCWnoLzkPAOCmvUTOKR/knvOr+50ozQObauE5ywFz585FWVkZpKSkIC4uDh6Ph9raWsyYMQM7d+5Er169sH//flRUVAAAnJycMGTIEOaPe9OmTVi4cCGAusq62NhYLFq0CEFBQRAXF4empiZ27twJPz8/dOnSBQYGBkKbhobGv0Znoba2FrW1tQI27uLi4ujTpw8CAgIQHR3NPLAjIiLg5eUFoM7/zsbGBsrKynjy5Al27NgBf3//Bq9TVVXFxEXrLeHHjRuH9PR0vHnzBhMmTEB0dDRMTU2RdOM3yOiZgi0tD+WB06DUbxLTT2HofojJq0LJeorI65TF3IRsVyvIKalCsSobv2z4BcOGDQNQ931PnDiRCUk19Td24sQJ+Pj4ICwsrEkHkWYVR1RUVCAwMBBubm7Q19dHSEgInJyc8OrVKyQkJKC8vBzDhg2DuLh4gy69zXHWfZOaCRMjA6iOWAjZrn1RfP84uBlx0HEVHdzOu7IRIILayIWoznmH3PM/Qd9tM55tmgE1eSlUVVVh06ZN+PnnnxkzQysrK+Tl5WHMmDGYNGkSE4+zs7PDtGnTMGvWLJSXlwuQYk5ODi5fvgxVVVUcO3YMdnZ2kJaWFiLPyspKKCsrC5CiKKL8dJ+Kispfqo/Q1sjOzkZ4eDju3buHe/fuITs7GzY2NrCzs4O9vT169OghNBOcuuceHqaVAaw2zlrkVcOwMg6/b1sBIsLBg7Ni6kAAACAASURBVAexdu1aDBw4EGvXroWBgQGqqqpw69YtnD17FteuXYO5uTkcHR0xfvx4kWlKTaGiogLJyclITEwU2N68eQM+ny+SjLt16/bZSmZ/NRqTS/1YKlVDQwPz5s3DkiVLANQ9zG7dusU8zLy8vJiHGVCnuObj48NkJHTs2BFpaWkC10lJSWHkZffs2YN169ahsrISffsNQFK3yeDLqeFT5F/bCjFFdajYuAAAuOmxyD3rxzyw83/f9v8u4xy019HCZEdHrF27FtLS0ggPD4ednR1kZGQECPf69esYOHAgIiIiMGLECCaFrFOnTsjIyGBccyoqKtq+Is3MzAy+vr5CPlTPnz8XcultrrOu8w/rcfHMCWhNqwuK86u5yNgxVaR7ML+ai/RtU9DO/VdIqOrWfYhXN0NKSR3+v/wC7aJYeHp6oqSkBFwuF99++y2mTZvGEOTdu3eRkpICc3NzFBYWIiYmBmJiYuByuZCWlm6QKPft24dZs2ahf//+QscUFBT+Ffq5TSEnJwfh4eEICwsTIlk7OzuYmZmJfN0mIkRGRiIwMBBRydmQG/MjeGir13ICamuwYrghLm7whqysLE6dOgUZGRlUVFRg+/bt2LJlCyZOnIg1a9YwNkJcLleAgC0sLBgCFrWo0lIUFBQIkXFiYiKSkpKgrKwskpA7d+78VanIfe34GuViP8sNWBRycnKQmJjI5GV+jPv37wvtb66zbnxcHMQ1OjI/syWlIa6sLdI9uLYwEyw2myFcAJDQ7ATO+1e4/jAGV1YKPgyio6OhpaXFEGVJSQl69uyJuXPnQkVFBd7e3nj79i2kpKRgaGiI9evXiwwhnDx5EmPGjBF57N+KepKtn8l++PABAwcOhJ2dHTw8PBok2XrweDwEBwdj48aNyM3NxZIlS3DqlBsuvsxtcenmp6CaKkjLyMDOUAOpv+9D8vVIXLt2Da6urhg+fDiCg4OhpKQEHx8feHp6IiAgAD169ICHhweWL18OZWVljBkzBmPGjAGHw8HNmzdx7tw5rFy5Er169WIIuKX5pvVQU1ND//790b9/f4H9fD4fmZmZAkQcFhaGxMREpKeno3379iIJuX379v8TD/aWYJ5dV0Qk5bdKLlZaXAxedi2X9PwctJh0a2pq4OzsjOnTpwtZsr98+RI///wzrly5wuxribNuRUU52FKCeaFsKTmR7sH8Gg5YUrKftJUFv5oDNR09PHnyBJs2bcKVK1fA4/HQuXNnHDtWVxJ45MgRZrZbX8a5c+dOmJiYQFJSEqdPn8bo0aMRHR3dbFv3fxNyc3MFZrIfk6y7uzvMzc2btXDE4XBw9OhRbN68GcrKyli2bBkcHByYc6f16wg+n/DT1Veo5bPAapRMCGLExxDTdrh9/Rr6WNuinboKbp49gg1zHDD6W0vkD++Inj17Yvjw4Th58iQWLVoEW1tb3LhxA9ra2lBTU0NgYCAWLlwIPz8/xoR0/vz5kJGRgYyMDMaNG4dx48aBw+Hgxo0bOHfuHFasWIHevXszBNwWko1sNht6enrQ09PD4MGC6XHV1dV49+4dkpKSkJiYiJiYGJw7dw6JiYkoKipC165dRRKympravyJ+3NJiKHM9Zfw40qiV2gtGf/nCe4tIl8/nw8XFBZKSkti1a5fAseTkZIwYMQLbt2/HwIEDAdTFulrirCsnJw9+jmAVSUPuwWwJGVCVIBlTVSXYkjJQlJaApWVPnD59GgUFBYydEABcvnwZK1asQGhoqEDdvJWVFfP/6dOn49SpUwgJCcGCBQuaNfZ/MupJtn4mm5mZ2SqSrUdhYSF2797N1OofOHAANjY2QoSQn5+P436e0JZSQ7dxC/BHakmDanO172Pw0xRrTBthifYrx2HThlnQ09PDmjglPAi9jtHf2kFdXR1BQUFwc3NjcmrXrVsHa2tr3Lp1i3mA6unp4dChQ0hISMCPP/6IHTt2wNfXF25ubsxCqoyMDBwcHODg4AAOh4Pr16/j7NmzWL58Ofr06YNJkybBwcHhi2jmSkpKwsjISGhSAwBlZWUC8eM7d+5gz549ePPmDdhsdoPxY1FFLl8bPqcYqj5V9GtRGWsMzSZdIsKsWbOQk5ODkJAQAU+stLQ0DBkyBKtXr4aLiwuzPykpCampqQwJV1dXo6SkBNra2nj06BETGK+HiakpXseeYH7mV3NRW5QNSQ3hsk9xVV0Qn4eawkwmxFCdmwIZrY4w0vlzgUJNTQ3Lly8HANy4cQOzZ8/G77//jh49RJeZ1qM+reXfiLy8PAGSzcjIYEh25syZ6NmzZ6tSoFJTU7F161YcO3YMY8eOxZ07d0SGoADg2bNnmDBhAiZPnoz169dDXFwcBeVVmBv4G15mF6C/zSAoy0rBSEcBZvKVcBzrgalH6koty8vLGd3fkSNHYvbs2diwYQMAYMiQIZgyZQrc3d1x6dIlrF69GhoaGhg4cCBCQkIEUpiMjY1x8eJFREVFYcWKFdi0aRPWr1+P8ePHCzwgZGRkMH78eIwfPx6VlZUMAS9duhRWVlYMAf8V4jcKCgqwsLCAhYWFwH4iQn5+vkC44syZM0hMTERycjJTAFK/GRoawsDAAB07dmzU3+6vQlsUQ03r1xFm7ZW/ernYZi+kzZkzB9HR0QgNDRUQus7MzISNjQ3mzJmDpUuXCpxf74ZQj4cPH2L+/Pl4/vy5SE+w1ykZMDU2xP+xd+ZxMe/fH39N+zZR0qZUClluaCFJdCVJiyRCZLkSkf1ariXiKm7Wrl22ZGtB6IaksoesSVEUJa3a9/P7o9vcpqZ1pizf3/PxmD9mPu9tPjNz5vM573NeR3r0Qohp6CE36hRKUl42Er3gCYCBTqNdUfYlEV/Ou7FFL9Tm5s2bsLOzQ1BQEIyM2IOnc3Nz8eDBAwwbNowlcejk5IQnT56w8qhrwlg0NDTg4+MDIyMjCAsL/xC3cxkZGYiMjGS5Cz5+/AhDQ0NWdEFrjWwNT548wbZt23Dt2jX89ttvcHV1RZcuXRpsf+TIEaxcuRL79+9n24gNCQnBb7/9hujoaNZGFwBs3LgR2dnZ2LlzJ4Dq+M3CwkIICQmhsrIScnJyePLkCbp2rf5zLi0thb6+PubOnQsnJycAgL+/P+bNm4fz58+zMspqQ0QIDQ3FqlWrICQkBA8PDxgbG9drV5vCwkKWAQ4NDYW+vj4mTJiAsWPHspTJvgeqqqqQkpLCcUPv06dPUFFR4XiF3F4FMdtClvFby8Vyraf74cMHqKqqsuIdazhw4ADevn0LNze3ercvnNR4bt26BQcHB7bohbrhImNW/I1rhz1QmfcFQgr/xul2rN5Frl09GOAcp2trNxH7HXSRnJyM3r17IzY2Fl27doWxsTGioqLYQrOGDh2KkJAQZGRkwNzcHHFxceDn54empibc3d0xcuRIVtumwli+J2qMbM2VbEpKCsvIDh8+HP3792f7HFsDEeHatWvYtm0b4uLisGjRIsyePbvRNMnS0lIsWLAAUVFRCAwMRK9evVjH3r17BwMDAwQEBMDQ0JCtn5aWFvbu3QtDQ0OUlZVBXFyc5S4CAAcHBwwdOhRz5sxhvfb69WsYGRkhKiqKdZseFhaGSZMm4eDBgxg7dizHNVZVVeHs2bNYs2YNNDQ04OHhUe+qkhOFhYW4evUqzp07h2vXrmHw4MEsA/w9K5GVlpYiMTGRo0HOz89H9+7dORpkKSmpFs1Tk0lW14j/rDUTGzO6HOuy1zx0dHR4UgO+JTxNziHNtSGksvJyix+aa0PoWUpOu6/5W5ORkUEBAQG0YMEC6tu3L0lKSpK5uTlt3bqVoqOjqby8nGdzlZWV0cmTJ6lfv37Up08fOnbsGJWWljbZ78OHD6Snp0e2traUl5fHdqygoIC0tLRoz5499frFxcWRgoICVVZWEhFRVlYWdezYka3NqVOnyNraul7fffv2kba2Ntv6Hj16RAoKCnT48OFG11taWkp///03ycvLk729PSUkJDT5HmvIz8+nM2fOkK2tLUlKSpKZmRn5+PhQdnZ2s8doL+Lj40lYWJimTJlCRERJSUkEgMTFxUlcXJxERUVp/Pjx5ObmRpMnTyZdXV1iMpkkIyNDBgYGNGjQIOrSpQsJCAiQlZUVFRUVscZ+9eoV6ejoUMeOHUlYWJjExMQoODiYdbykpIQ0jccRn1hH4hORIFF1Pericozjb7vr8iAS62lA/JKyBIDkJv1Jqqsu05yT0UREtH79ehIQEGCtW1xcnN69e8eaKyYmhgwNDUlSUpK6dOlCGzZsaPCc7Nixg9TU1IjJZJKCggItWrSI9RtKT08ne3t7UlBQIElJSTIwMKD79+/XGwPAI2rArn53sSc1O5Gigi1b2rfaifwWZGZmIjAwEK6urtDS0oK6ujqOHDkCZWVl+Pj4ICsrC1euXMHy5cuhq6vL9VUtUL2Bs2PHDtZcf/75J168eAFHR8cmY0rDwsIwaNAgTJgwAefPn2dLCiAizJ49G/3794eLi0u9vgEBAbC1tWWFSRUWFta7qxo1ahTCw8NRWlrK9vqcOXOgpKSEtWv/SwHV0dFBREQENm3aBA8Pjwb99kJCQpg3bx4SEhLQp08f6OvrY968efj8+XPjJwrVMpYTJ06Ev78/Pn36BEdHRwQHB0NVVRXm5uY4duwYcnJymhynPXBxcYGenl6913Nzc1FQUICioiKcP38e69evx6lTpxAdHY2vX7/i5cuX8PDwgLa2NgYOHAglJSVERERAWloaKioqGDlyJLZv3w5zc3OcOnUKffr0QVFREaysrLB7924QEf7c6oXEVzFQnLUHSvNPgE9EAtnXG063FVbqAxnLpeAXr77KJvpXlrGg+nNvTLN38uTJMDIyQnZ2NiIiIrBv3z5cunSJ4zyWlpZ48uQJ8vLyuNbZ5cR3Z3SBaof4H+a9ICrIj6ZcSgxG9W3Gz1wpOCsrC0FBQWxG9vDhw1BSUsLhw4fZjKyenh5PjGwNaWlpWLVqFdTU1HDv3j0EBAQgPDwc5ubmTfr7iAgeHh5wcHCAn58fli1bVq/Pzp078ebNG+zfv5/jeDU6CTVwMrqdOnVC7969ERUVxfY6g8HA4cOH4evri5s3b7Je7969O+7cuYNTp05hyZIljYrYSEhIYM2aNYiLi4OoqCj69OmDNWvW4OvXxrVaa/e3t7dHYGAgPn78iKlTp+LixYtQVVXFmDFjcPz4ceTm5jZrLF5z5swZdOzYsV7IWlPU1NEbOnQo9u7di8DAQEyZMgVjx45FQUEBwsPDsXTpUmhpabF88TExMQCqvxOLFy+Gqqoqbj58AXF1bfCLS4EhIASxXkYoz0zmPCe/ICT1rCGi3AeoFVrIAOD/pGFZgRrev3+PKVOmgJ+fH+rq6jA0NMSrV684tlVXV0fHjh1Z6+Wks6ugoAB+fn44OTmhrKyMJRnQHL5LowtUG96zTvoY1VsOwgJ8EBFgX6qIAB+EBfgwqrcczjrp/1QGt8bILly4EP369UO3bt1w6NAhNiN79epV/P777xg4cCBPjWwNcXFx+O2339C7d2/k5+fjwYMHOHfuHMerIk7k5eXB1tYWQUFBePjwIcdNqfDwcHh6eiIwMJBj4szbt2+RlpbG5uOtHblQG3Nzc46hiZ07d8bRo0fh6OjIVhFCUVERkZGRiI6OxrRp09h8xJyo0VqNiYlBamoqunfvDi8vL5SUlDTarzZMJhOTJk1CUFAQUlJSMGXKFAQFBaFr166wtLTEiRMnmm3MuSUvLw/r1q1rUD9WRUUFSkpKmDFjBttmeFPw8/OjW7duMDMzg6urK7y9vfHw4UPWHYWgoCDExcWhoaEBhUHmKEqORUV+FqrKS1AYewui3eoLhDdGSUUV4tKqs1+Dg4MhLS2NPn36YN++fWztFi1axBIwevPmDe7duwcTExNOQwKoToKSlJSEjIwMnj17xrZfUJuW6OzW8N0aXQDQUuqI/Q66uLviVywe2QM2/btghKYsbPp3weKRPXB3xa/Y76D7w7sUsrOzceHCBZaRVVNTw8GDB6GoqIiDBw8iMzOzzY0sUP2vfvv2bVhbW2PYsGFQVlZGQkICvL29W5QkEhsbCz09PcjKyiIyMhLKysr12qSkpGDy5Mnw9fWFiooKx3ECAgIwbtw4tsgKTle6QMNGFwBMTU1hZ2cHJycnNneClJQUrl27hq9fv8La2polfNMYXbt2hY+PD8LDwxEVFYUePXrAx8eHVVurudSILl24cAEfP36Evb09AgICoKysDCsrK/j6+iIvL69FY7aEtWvXYtasWfU+GxkZGURHR+PDhw94/Pgx8vPzWZvcrSUlJQV9+/bFiBEjsHXrVnz9+hVhYWEQklECv2RnfPrbESnbJ6A8MwUdaukqN5e8knJMmDABr1+/RkZGBg4dOoSNGzeyVW+2sLCAv78/REVFoampiVmzZjV6ATF58mTk5eUhPj4ezs7OPNHZZdGQs5e+0Uba/wJZWVkUFBRECxcupH79+hGTySQzMzPy8PCg+/fvU1lZWbuup6KiggIDA0lfX5+6detGe/fupcLCwlaNde7cOZKRkSEfH58G2xQXF5Ouri5t3bq10bF0dXUpLCyM7bXLly+TmZlZvbaVlZUkJyfHtnlSd04tLS2OG2hlZWXk6OhI+vr6lJWV1eia6nL37l0yMjKiXr16UWBgIFVVVbWof11yc3Pp5MmTZGlpSUwmk6ysrMjX15e+fv3K1bi1iYmJod69e7M2GNevX8/aSKtLWloaAWhy/j/++IMcHR0bbVNZWUnS0tKUnp5OREQ9h4wm0e76pLTwNHVdFkQdhk4hIYUeTW6Y8zM7kdykP1nPF52JqTfXli1baNy4cURU/XtjMpl0/PhxKi8vp5SUFBo0aBD9/fffTZ0qIiI6ffo02djYsL1WVFRERkZG9Ntvv3Hsgx9pI+1nJDs7GxcvXmRp1aqqqmL//v2Ql5fH/v37kZWVhZCQEKxYsQKDBg1qt2D14uJiHDhwAL169cKWLVuwdOlSxMfHY+7cuRATE2t6gFpUVFRg2bJl+P333xEaGooZM2ZwbEdEcHFxgZqaGpYtW9bgeElJSfjw4UO9mOqaqhR14ePjw+jRoxESEsJxPBEREfj5+WHlypWIj49nOyYoKIijR4/C0NAQQ4cObVR6tC6DBw/GrVu38Ndff8HNzQ0GBgaIiIhodv+6dOjQAQ4ODrh06RKSk5Nha2uLM2fOQElJCWPHjoWfnx+bmFRruHXrFt6/f4+uXbtCXl4ef/31FwICAqCtrV2vbY2fnXiQKFRVVcWqNQcAeZ/eQqr/SPCLMsEQEISkjiXK0uJRWdR8F4uIAB9bMlTtddesOTExEfz8/Jg2bRoEBASgpKQEe3v7ZmfKVlRwp7Nbl/83um1ATf2oxYsXY8CAAVBVVcW+ffvYjOw///yDlStXQl9fv90zgrKzs7Fp0yaoqakhODgYhw4dwoMHDzB+/PhWJUmkp6fDxMQEL1++xKNHjzj+eGs4cOAAHjx4AB8fn0Y34gICAjB27Nh6rpSG3AtA4y4GoDom3M3NDZMnT0ZZWRnbMQaDwZIvHTJkCOLi4hocpy4MBgPm5uaIiYnB/PnzMWPGDIwePRpPnz5t9hic6NixI6ZNm4bg4GAkJyfDxsYGfn5+6NKlC2xsbHD69OlWGWAnJye8e/cOT58+xdOnT+Hs7IwxY8YgNDQUDx48YElS1hTuHD58eIO3zxUVFSgpKWHT2K1xtVy/fh0xMTGorKxEXl4elixZAikpKVZ89rAh+sh7EYaqkkJQZQXyn1wFv4Q0+MU4z0UV5f9WCgGoqgJUUYYqIozXVsLFixeRk5MDIsLDhw+xe/duWFtbAwB69OgBIoKfnx+qqqrw+fNnnD17lq0SdG0OHz7MqmQcGxuLLVu2sDYbW6qzy/mN/ODuhYz8Etp36y0tPPOEZhx7SAvPPKF9t95SZn5Ju60hOzubLl68SIsWLaL+/fsTk8kkU1NT+vPPP+nu3bvt7i5oiKSkJHJ1dSUpKSmaPn06vXz5kusx7927R0pKSrR27VqqqKhotO3du3epc+fOFB8f3+S4gwYNomvXrtV7fffu3TRv3jyOfXJycojJZLLFitalqqqKxowZQytXrmywjY+PD8nJydGDBw+aXCcnSktLac+ePSQvL0+TJ09u0OXRWrKzs+no0aM0evRokpSUJBsbGzp9+jTl5+e3arza7gU/Pz9SVVUlMTExkpeXp6lTp1JaWhqr7ebNm9ncO+vXrycAbI/169cTUbWrqWfPniQuLk4yMjI0evRoevbsGatvZmYmqQ8eRXxiHYghLE7CSr1JfpoXy20gKNOVOlku/c+t8G+Mbu3H5O0XiYjI3t6epKWlSVxcnHr27Em7du1ie49hYWGkq6tLkpKSJCcnR7/99hvLhRYZGUni4uKsttOnTydZWVkSExMjFRUVWrZsGRUXFxMR0a1btwgAiYqKssUER0ZGss2HRtwLrdbT/dY0Lo5RnWPdVpWCc3JyEBUVxcr4evv2LQYPHszK+NLV1f0u8tlraGmabnMgIuzbtw9ubm44cuQILC0tG22flpYGPT097N+/HxYWFo22TU5Ohra2NtLS0uqdRw8PD+Tk5LC0FupiZGSEVatWscqBc+LLly/o378//Pz8GpTovHTpEmbNmgU/Pz+2zMSWUBPbvGvXLkyaNAlr167liUZvbWpcV+fOncPdu3dhYmKCCRMmYMyYMRzdMN8b/4sZaT+ke8H3/nvYH7qP66/TUVpRxWZwgeowktKKKlyLTYf9ofvwvf+eq/lyc3MRHByMJUuWQFtbG127doW3tzdkZGTg7e2NzMxMVt7+4MGDvwuDS/9qCZiYmMDKygo6OjpITEyEp6cn1wa3qKgI06dPx759+3D37t0mDW5ZWRns7Owwe/bsJg0uUO1asLa25ngeG3MvAE27GABAVlYWPj4+mDZtWoNJClZWVggMDISDgwPOnj3b5Jo5wWQysW7dOsTFxUFQUBC9e/fG2rVreRqVIC0tjRkzZiAkJARJSUkYM2YMjh49yqrGe+7cuWZFZXwr/heToX44o/ufOEbj8m0Ae6VgTob38OHDHCt31hjZpUuXQkdHB8rKytizZw/LyGZlZeHatWtYvXo1DAwMviuV//Lycvj6+qJ///5YtmwZpk6disTERCxbtqxlYS0NkJiYCAMDA1RUVOD+/fvNik9csmQJpKWl2TLDGsPf3x92dnYcjzUUp1tDjdFt7A4OAMzMzGBjY4M5c+Y02Hbo0KG4fv06li5dir///rtZa+dE586dsWPHDjx58gQpKSno3r07duzY0aIY3+YgLS2NmTNn4p9//kFiYiLMzMxw5MgRKCoqsrIBv0cD/D+XDNWQ34Ga4dNtKm9bXFycNm7c2GD/PXv2kI6ODgkJCdULN7l37x6ZmJiQlJQUycjI0Pjx4+l69GuWLoNINx1iCIqwHuATIMHOKhxDTOSn/kViagNIskNHkpGRIVtbW5o5cyYJCgpSr169aMOGDdS1a1cSFBQkISEhEhISIhMTE9q0aRMFBwfThAkTmsy1rqGkpITmzJlDsrKyJCUlRRYWFvTx48dGzyMvyMvLIy8vL1JWVqbhw4fT1atXuQ5fqsvVq1dJVlaWdu3a1eyxjx07Rt27d6fc3Nxmtf/48SNJS0s3qOcwe/Zs2r9/f4P9q6qqqEuXLvTmzZsm5youLqa+ffvS0aNHG22XmJhIGhoatG7dOp6c0xcvXpCVlRV17dqVjh492qQvnFsyMjLo0KFDNHLkSJKUlKQJEyaQv79/q8MC24pnKTk052Q09VhzlXquucr2G+655ir1WHOV5pyM/iH0VdCIT5crozty5EgyNDSsZ3SbK7ASEBBAQUFB5OzsXM/oXr16lc6dO0dfv36lwsJCmjFjBin9ok+qqzjH7gkr96UOhlM4HpO1c6POY1fSjIPhlJGRQQoKCsRgMAgAMRgMEhQUpIEDB9KGDRvIz8+PunbtSqdPnyYionfv3pGXlxelpqZSRUUFHThwgDp16tTgpoWnpydpaWnR58+fqbi4mBwcHOrF+PGS1NRUWrlyJXXq1IkmTJhA0dHRPJ+jsrKS3NzcSFFRkaKioprd7/HjxyQjI9OiDbtdu3Y1Gu85efJkOnnyZKNjzJ49m3bs2NGs+V68eEEyMjJNCtqkp6eTtrY2OTs788xI3r59mwwNDal379504cIFnv9JciIjI4MOHjxIJiYmJCkpSRMnTqSAgIBGNx/bm8z8Etof8ZYWnYmhmcce0qIzMbQ/on03x7mlTYzu6dOnyc7Ojm3ns6VGt4bmBFbfiLpHDCFRjka1i/MRAoOPFJ0PNxpU3WPNVerWS4tt97Ou8hER0YIFC2j+/PkNroXJZNKjR484HnN2dqbly5eznl++fJl69OjR/JPRTF6/fk2zZs0iKSkpcnFx4fkOeQ3Z2dk0ZswYMjQ0pNTU1Gb3y8jIIBUVFTp//nyL5hs6dGi9z6M2VlZWFBQU1OgYgYGBNHLkyGbPuXv3bho4cGCTUSZfv34lY2NjGj9+PJWU8MYAVFVV0eXLl+mXX34hAwODervgbUl6ejrt37+fRowYQR06dCB7e3sKDAz8rgzwj0pjRrdVPt22yttujP1nLkOYQwUJACh4eRPCSr0h2LHx8tkMANPW78XEiRMhIyMDNTU1FBcX4/nz56w2RISoqKgGKx40lWs9a9Ys3LlzB6mpqSgqKsKpU6ca3UlvCfRvmq6VlRWGDRuGrl27Ij4+Ht7e3myKSrzi2bNn0NXVhYaGBm7evAkFBYVm9auoqIC9vT3s7e3ZxGqaIi0tDS9evGg0WqCpjTQAGDFiBO7du9ds5af58+ejU6dO9cqL10VSUpLlLzY3N+c6SQGojvEdM2YMYmJi4OzsjGnTpsHCwoLtO9lWyMrKYs6cqaClkgAAIABJREFUObhx4wbi4+MxbNgweHt7Q0FBgZWizGu/8//Tyo209szbBqoLXgYf24MOwzlnORW+vAmJXxoWr6ihpKIKCR8+4dq1awgMDERiYiK+fv3Klhnl5uaGqqoqjhlVzcm17tGjB7p27YouXbpAUlISr1+/xrp165r5TjlTWVmJwMBAGBgYYPr06Rg9ejSSkpKwbt26NisR4+vrCxMTE7i7u2Pnzp0tishYvXo1+Pj4sHnz5hbNGRgYCAsLCwgLN6zsX1BQ0KTRlZSUxMCBA9mUxRqDwWDg6NGjOHLkCCIjIxttKyIigrNnz6J79+4wNjZmBdFzCz8/P6ZOnYq4uDiYmprC1NQUU6dORVJSEk/GbwpZWVk4OzsjLCwMb968wdChQ7Fr1y4oKCjAwcEBFy9e/H8DzCNabHRrSvYsXry43jEJCQmWfqucnBy8vb1x7do1rkJkagpeDpy8BCLKfesdL0l5hcrCHIhpDmlyrPKcVARtmc9WPJPJZLKiD7y9vXHixAlcuXKl3g+/uLgYlpaW0NfXx6pVqxqcY+7cuSgpKUFWVhYKCwsxbty4Vl/p1k7T9fT0xNKlS/HmzZtWpek2l7KyMsyfPx8bNmzAzZs3MXny5Bb1P3fuHPz9/XH69OkWZ7f5+/s3eWXcUBpwXczNzRtMCeaEnJwcDh8+jGnTpjUptcjPz499+/bB3NwchoaGeP/+fbPnaQphYWG4uroiISEBGhoa0NPTg6urK8+Me3OQk5PD3LlzER4ejtevX8PAwAA7duyAgoICpk6dikuXLtXTLuaGzIJS7I94h0VnYzDzeDQWnY3B/oh3LJ3cn40WG932zNuuXfBSe4QVxzaFL8Mg1mMw+DhUDK5NxdcvSD+9Bvq2s9mKZ9bg4+MDDw8PhIWFQUlJie1YS3Ktnz17hunTp0NaWhrCwsJYsGABHj582CI3S1ZWFtzd3VlpuocPH8b9+/dbnabbXFJTU2FsbIzk5GRER0c3WbyzLi9fvoSLiwsCAgJaXCMsPT0dMTExMDU1bbRdc9wLQPNDx2ozZswYWFpawtnZucl+DAYDGzduxIIFC2BoaIgXL140e57mwGQysX79esTGxoLBYKBXr15Yv359myqPcUJeXh7z5s3DrVu3EBsbC319fXh5eUFeXp6VotxaA/wsJRdOJx9hiOdN7LgRjwtPU3Ez7gsuPE3FzhvxMPC8iTm+j/As5dvoDbcVLTa67ZW3/enTJ/z6669wcXGBs7MzNOUlIVxHU7eqvBSFcXcg3oRroSI/E+mnV0NazwITps2sd/zUqVNYvXo1rl+/Xs832tJcaz09PZYuanl5Ofbu3QtFRcVmuQHev38PV1dXdO/eHUlJSQgLC8Ply5c5li/nNZGRkdDV1YW5uTkuXLjAEnFuLrm5ubCxscGOHTuaVVOsLhcuXIC5uTlHXd3aNMe9AACamprg4+NDbGxsi9axdetWvHjxAidPnmxW+wULFmDbtm0wMTHBnTt3WjRXc5CVlcWuXbvw+PFjJCUloUePHti1axdPrzSbi4KCAlxcXBAREYHY2FgMHDgQ27Ztg4KCAhwdHXHlyhU2TQtLS0vs2bOH41jtneD0XdHQDhs1U3uhrfK23dzc2GJ+xcTFiSEowhaNIGO1nPglO1PXFcH1IhVq5213MJxcHR4mKMIWQ1yDqqpqvfpKc+bMIaKmc63r5m1nZmbS5MmTqXPnztShQwcaMmRIkzn8jx8/ZuWO//777+0S11tDVVUVbd++nWRlZSkkJKRVY1RWVpK5uTm5urq2eh0jRoyggICAJtuJiYk1W2Ng7ty5TcpHcuLZs2ckIyNDb9++bXaff/75h2RkZBqNvOAFz549IwsLC1JRUaHjx4+3eYxvc/j06RPt3r2bDA0NSUpKihwdHen48eMkLCxMoqKi9WrfnbyXRJprrzYaaVS//uFVOnkv6du8wVaAn0V7wenkI1x/nd5kJhonGAxgVG857HfgXKCzvSGqrqa7detWvHnzBosXL8bs2bMhKSnZbmsoKCjAb7/9hvj4eAQEBEBNTa1V46xfvx63bt3CjRs3WpUCnZGRAQ0NDaSlpTXqq66qqoKAgAAqKiqape50+fJleHl5ITw8vMVr2rlzJ86ePYvIyMhmv6cHDx7A2toanp6ecHR0bPGcLSEqKgorV65EXl4e/vzzT1hYWPDsbsjb2xvHjh3DixcvMGnSJBw7dox1LCwsDC4uLkhOTsagQYNw7NgxNhH6T58+ISAgADt37mTbBJSRkcHBgwfRTdeYo9ZCWcZ75Nw8grLP71BVnAeVlZfrratGa0Gk6AuWL1+Ou3fvorKyEnp6eti9ezd69uwJADh27BhmzZrFdtd0+fJlls7G8OHDcf/+fZaCXZcuXVpUbqc5/DTaCy7DNSAi0DqfpogAP+YNb35JjbaivLwcJ0+eZKXpOjo6IjExEUuXLm1XgxsfHw99fX2IiYnhzp07rTa4ly5dgo+PD86dO9dqzYmLFy/CzMysyc3BoqIiiIiINFtOz9jYGI8ePWqVH9TV1RWSkpLYtGlTs/sMGjQI4eHhjYZT8oqhQ4fi9u3b+PPPP7Fq1SrWc16gqKiINWvWYOZMdldcZmYmxo0bB3d3d2RnZ0NXVxcTJ05ka9OlSxe4urrWcwFlZmbC3t4em0+HoaSivrgNg08AYppD0Wm0a4PrKqmoxN5bb5GbmwsrKyu8efMG6enpGDhwIEvGsYbBgwezFamsK2zk7e3NOsZrg9sUP5TR/ZHFMfLz87F9+3aoq6vj6NGj8PDwwPPnzzFt2rR21264ePEiDA0NsWDBAhw5cqRJP2pDvHnzBr/99hv8/f25Us9qTtQC0PzIhRrExcUxZMgQ3Lhxo8Vr4uPjw7Fjx3DgwIEWGbNevXrh9u3bOHLkCH7//XeeiH83BIPBgKWlJZ49e4bZs2djypQpsLS05HpTb9y4cRg7dmy9zdDAwED06dMHdnZ2EBERgZubG549e8ZRe5ifnx98fHyYM2cO9uzZA19fXwzUN0BYsD/HO1XBTkpg9jOFYAOx+MB/1X/Ve/fDrFmzIC0tDUFBQSxevBhv3rxhq4H3PfNDGV3gxxPHSEtLw8qVK6GmpoYHDx4gMDAQN2/exOjRo9t8c6wulZWVWL16NRYsWIDg4GDMmTOn1WvIz8+HjY0NNm/ejEGDBrV6TdnZ2bh3716zwuqaG7lQm+aojjWEgoICDh48CAcHhxZV7FVWVkZUVBQiIyMxc+bMFtdPayn8/PxwdHREfHw8RowYARMTEzg6OvI0lA0AXr16xSb8LS4uDnV1dY5VdU+ePAlRUVHs27cP8+fPx5QpU5BZWI7SjA9crYFT9d/IyEjIy8uz/UnExMRARkYGPXr0gLu7e73PYNWqVZCRkcGQIUNw69YtrtbUUn44owv8GJWCX79+jVmzZqF3794oLCzEw4cPcfbsWejqfhufcmZmJkaPHo379+/j0aNHXBlKIsKMGTNgaGiI2bNnc7WuixcvwsTEpFlXsE0pjHGiNaFjtbGysoK5uTlcXFxa1K9Tp04ICwtDWloaxo0bh+Li4lbN3xKEhYWxaNEiJCQkQFVVFTo6Oli0aBEyMjJ4Mn5BQUG9SKQOHTpwzMzT1NSErKwstm3bhvLycly7dg3xTx+gsoy7BIva1X8B4OPHj3BxccH27dtZrxkZGeHly5f48uULAgICcPr0aWzbto113NPTE4mJifj06ROcnJxgaWnJVo6nrfkhjS7wfVYKpn9TiK2srDB8+HCoqKggISEBe/bsaZM03eby6NEj6OrqYsCAAbh27RpkZWW5Gs/T0xMfP35sMByoJTTXtQC07kpXQ0MD4uLiXJXO+euvvxATEwNfX98W9RMXF8elS5fAZDJhamraoqtlbpCUlMSGDRsQGxuLqqoq9OrVCxs2bOA6bVlCQqKefzwvLw9MZv0aZYKCgrhw4QKuXLkCeXl5eHl5QXWgCfiZ3GdQ5pWUA6jegDU1NcW8efMwadJ/VYS7desGNTU18PHx4ZdffsG6devg7+/POj5o0CAwmUwICwvD0dERQ4YMafXdUGv4YY1uDZ0khDHHSB07JvbHEUc97JjYH3OM1NFJouFUUl5Tk6Y7ePBgzJgxA+bm5nj//n2bpuk2lyNHjmD06NHw8vKCp6cn1+Xbr127ht27d8Pf37/RdN3mkJubi6ioqGYJmwOtM7pAy7PT6iImJgY/Pz8sXry4xWm5QkJCOHnyJLS1tWFkZIS0tLRWr6OlyMnJYffu3Xj48CESEhLQvXt37N69u9Uxvn369MGzZ89YzwsLC/Hu3bsGdUq0tLQQERGBrKwshIaGojgzFcIKPVo1d20kRQSRk5MDU1NTWFlZ4Y8//mi0fe0ila05zmt+eKP7LSkuLsb+/fuhqakJT09PLF++HG/evIGzs3OrN6d4RUlJCZycnPDXX38hMjIStra2XI+ZlJSEqVOnsqrTcsulS5fw66+/crxS4kRr3AsAd37dGvr3749Vq1ZhypQpLfbR8vHxYefOnbC3t8eQIUOQkJDA1VpaSrdu3eDr64vQ0FCEhoZCU1MTvr6+qKqq4ti+oaQlGxsbvHz5EgEBASgpKcHGjRuhpaUFTU1NjuM8f/4cJSUlKCoqwl9//YWy/GxID+CccUhEoIoyUGX1uaWKMlBFeb12IgJ8UJEERo0ahSFDhsDDw6Nem5CQEKSnpwMA4uLi4O7uzopuyM3NRWhoKOs9nTp1CpGRkRg1alTTJ5JXNBTASz9IYcpvQWZmJm3cuJHk5OTIwsKCIiIi2kULtbl8+PCBdHV1ydbWlvLy8ngyZmFhIfXr169ewT9usLS0bFIbtza+vr40adKkFs9TXFxMTCaTsrKyWty3NpWVlTRy5Ehyc3Nr9RgHDx4kBQUFevz4MVdr4YaIiAjS19cnLS0tunz5cr3vbmNJS9evX6eePXuSiIgIDRs2jJKSklj96iY/LVu2jDp27Eji4uJkZmZGD56+oh7/ipN3metDDEER6jLX5z951jpz8kvKspIjRLrpUEejadRjzVXy3n+IJctaO2Hpw4cPRES0dOlSVmFJNTU1Wrt2LUu288uXL6Srq0sSEhLUoUOHBgugcgt+luSI1pJZUAr/xx8R9zkPeSUVkBQRgKa8JOx0lBp1Q5w9exbm5uasK7GkpCRs374dvr6+sLGxwbJly9C7d+/2ehvNIiwsDA4ODli6dCmWLl3KkwgJIsLUqVPBYDBw4sQJnoyZl5cHJSUlpKSkNLuM0MGDBxEdHY1Dhw61eD5LS0s4ODjUiyttKampqdDW1mapvrWGwMBAODs74+zZszA2NuZqPa2FiHDp0iWsXr0anTp1goeHR6vfT0v4mRKcGuOnSY5oKdwIahw9ehT29vbYvXs3Hj9+DHt7e+jq6kJcXByvXr2Cj4/Pd2VwiQgeHh5wcHCAn58fli1bxrOQtN27d+PVq1c4cOAAz8YMDg7GsGHDWlS3rbXuBYA3LgagOnHgwIEDcHBwaLX4zLhx43D27FlMnDgRgYGBXK+pNTAYDFhbW+P58+eYOXMmJk2aBGtra47hX7zkZ0hw4paf1uhyI6gRHR2N+fPnA6jW17W2toaenh6SkpLg4eEBRUXF9nwrTZKXlwdbW1sEBQXh4cOHPL16ioiIwJYtWxAUFMRTOcmWRC3U0NqNNAAYPXo0QkJCGvRjtgRra2uYmpq2OIysNsbGxggNDcX8+fNx8OBBrtfUWvj5+TF9+nS8efMGw4YNg7GxMaZPn44PH7iLp22IHznBiVf8lEaXm4rBHz9+xK+//oqioiIA1V/KtWvXtnuabnOJjY2Fnp4eZGVlERkZWU9Ynhs+fvyISZMm4eTJk1BVVeXZuPn5+bh58yasrDjLdTYEN0ZXVVUVMjIyePz4cav618XLywvR0dHw8/Nr9RgDBgxAZGQkPDw8sHnz5nbdQa+LiIgIlixZgoSEBCgrK0NbWxtLlizhWeWX2vxoCU685rs0ut7e3tDV1YWwsDCmT5/OdiwsLAyampoQExODsbFxvX/kZym52Hw1DsXlVSjPTMFnv9VI3jEBn/bPRtGbuw3O+TU1Ec5TbNFNXQMFBQXg4+ODkJAQKisrcfz48XrtnZyc0LNnT1a66Lfg/PnzGDZsGFauXIn9+/dzHcJVm9LSUtja2sLV1bXR8jmt4erVqxgyZAikpKRa1I8b9wLAOxcDUB2D6+fnh0WLFnGV+aWhoYE7d+7g3LlzWLRoEU+uxLmhQ4cOcHd3x6tXr1BWVgZNTU24u7s3u/RRc/kREpzaiu/S6HIjuPH3rbcoqagEVVXiS4A7xDT0oLzwNKTN5iPzshfKsz9xnJPBJwARTUP8Oq+6xExRURHS09ORnJzMMcazX79+2Lt3L0fx9ramoqICy5Ytw++//47Q0FCOpYW4ZcGCBVBWVsaKFSt4Pvb58+db7FoAuLvSBXhrdAFAW1sby5cvh4ODA1epvgoKCoiIiEBMTAwcHBzYNGm/FfLy8vD29saDBw/w+vVrdO/eHd7e3jxd2/eY4NQefJdGt7WCG5kFpYiIzwARUJ6VgsqCbDD1xoLBxw9R1X4Q7tIbhS85180S7KQECS1TvCmr/oCFhYXRsWNHKCgocNzscXFxwYgRIyAiIsLjd9846enpMDExwcuXL/Ho0aM2MfqHDh3CnTt3cPToUZ7rQxQWFuL69ev1VKGaQ3MFzBvC0NAQcXFxPEuLBYClS5dCWFgYW7Zs4Wqcjh07IjQ0FIWFhbCyskJhYSGPVsgd6urq8PPzQ0hICK5cuYJevXrBz8+Pp1fk30OCU3vyXRrdhmhKcMP/cS0hDI7uMUJZE4Ib7StB0zLu378PXV1dGBkZ4cqVKy0uidMcHjx4gD/++ANBQUHNTlpoCSEhIdDX12/V2luqMlYXISEhjBgxAqGhoa0eoy58fHw4ceIEvL29cf/+fa7GEhUVRUBAABQVFTFixIjvSjWrf//+CAkJwZEjR7B7925oa2sjJCTkm/qhf1R+KKPblOBG3Oc8VpSCYCcl8It1QN6DAFBlBYqTnqAk+SWoovEUyNLKb+tT4wQRYe/evbCyssLevXuxcePGNqmVlp6ejvHjx+Pw4cPo0YP7dE1OtNa1AHDvXgB472IAqjVk9+/fjylTpnBdw0xAQABHjhzB8OHDYWhoiOTkZB6tkjcMHz4c9+7dw/r167FkyRIYGxuz/myio6NhZGTUpLjP/1ohyrpwl4jfzjQluJFX8p9fjcEvgM62a5B9/QDy7gdASEED4r0MAf7WCW1/K4qLi+Hs7IwnT57g7t270NBomzjF8vJy2NnZYebMmS2OKmguRUVF+Oeff+Dt7d2q/ty6FwDAzMwMK1asQGVlJU//uGxsbHD16lW4urpyvbHKYDDg4eGBzp07w9DQEKGhoejVqxdvFsoDGAwGbGxsYGlpiRMnTsDOzg46OjpISEjAmzdvsHDhQo5hcM9ScvH3rbeIiK9279QO4xQR+IwdN+IxvGdnzBumgX7KP5cftzY/1JVuU4IbkiLs/yFCsmqQn+IB5UWnITfRHRW5n3kiuNFeJCYmwsDAABUVFbh//36bGVwAWLZsGSQlJbF+/fo2myM0NBS6urro3Llzq/pz614AACUlJSgpKeHBgwdcjcOJnTt34t69ezh79ixPxlu6dCk2bdoEY2PjNlkvtwgICGDmzJmIj4+HjIwMYmNjUVlZiZMnT9a7m/ifLkRZh+/S6LZWcKNuxeCyL0mgijJUlZfg64NAVBTkQKKBysH0r+CGEKq/DCUlJY2qMZWVlaGkpAREhPLycpSUlPB0cyEkJISlWubr68v1FV5j+Pr64urVq/D19W12KZzW4O/vDzs7u1b354V7AWgbFwNQvcdw6tQpLFiwgGdugWnTpuHIkSOwsLDgqS+al4iIiLAJgZeUlMDGxoalyMZN3PxPSUOiDPQNBW9aK7ixet0GElPXYYlkSA4cR3zC1VWERbrpkOKcg6xjzRHcUFFRYY1tZmZGmzdvZj0fNmxYvfbh4eFcv/fKykrasGEDKSoqUlRUFNfjNcWTJ09IRkaGXrx40abzFBcXU4cOHejz58+tHqNjx46UmZnJ9VoiIyNpwIABXI/TEB4eHjR06FCeVuq9ffs2ycrKkp+fH+3Zs4d0dHRISEiIHB0d2dodOnSI1NXVSVxcnEaNGkWfPn1iHVu/fn29qtfv3r3jOF9paSnZ2tqSiooKx+/21q1bqU+fPiQhIUGqqqo0aNAgsrKyIlNTU9LX1ychISFiMpkkLsEkYVk16jxuTYOVfjsazyBBma7EEBIl/g5y1NF4xr8VgEPoWUoOa86aytx//PEH21pOnTpFXbt2JTExMbK2tm5Q2Cg9PZ3s7e1JQUGBJCUlycDAgO7fv886Hh4eTgwGg+38HDt2jHV86dKlpKGhQRISEtSzZ086fvx4g58X/pcEb35kQY2cnBxMnToVX79+xblz56CgoNCm82VlZUFXVxeenp6YMGFCm8516dIlbN++navSKEJCQsjPz+c6CaSiogKysrJ49epVm5zjyspKmJiYYOTIkVi9ejXPxn358iVGjx4NU1NTWFpaVmvUFhezfMgRERGws7NDeHg4unfvjoULFyI2NhYREREAqlPa37592ywx9rKyMuzduxe6urqws7PD6dOn2Yo7bt26FSYmJtDS0sK7d+9gamoKT09P2NvbA6iWdezduzfmnX6Kyzci8fnMGig6HYCAhHS9ub7e94eIan8IyaqhIicN6WfXQmr4dEj0Gcb6PZaXl0NPTw8iIiIwMTFhFQx99eoV9PX1ceXKFWhra8PJyQlVVVU4c+ZMvXkSExNx4cIFTJo0CbKysjhy5AhWr16N9+/fQ0JCArdu3YKDgwM+fvxYry9QXfV60qRJ6NGjB6Kjo2FmZoYrV65wFAr6nxK8+VEFNZ4/fw49PT1oaGjg5s2bbW5wKysrMWnSJNjZ2bW5wQW4dy2UlZWhqqqKJ0U8BQQEMHLkSPzzzz9cj8UJfn5+nDhxArt27cLDhw95Nm7fvn0RFRWFqKgoPH78GNLS7AYsODgYdnZ26NOnD4SEhLB27VpERka2qhSNkJAQFi1aBENDQ44bjr///ju0tbUhICCAnj17wtraGnfu3GEd19LSQm5JZXXcPACqrEBlHuf46A764yEsrwEGHz8EOylBrLs+Sj++ZhWizCoohZeXF0xNTetp9546dQqWlpYwMjKChIQE3N3dERgYyLFKRrdu3bBkyRIoKCiAn58fTk5OKCsra3Y14A0bNkBTUxN8fHwYNGgQhg4dinv37jWrb21+OqP7Iwpq+Pr6YsSIEdi4cSN27tzZ6lLmLeGPP/5AVVUV/vzzzzafq7S0FJcvX4aNjU2rx6jx5/IqWaOt/Lo1KCsr4++//8aUKVN4mkKrqqqK27dvIyQkpF6cbM3ta+3nQPUVcg3BwcGQlpZGnz59sG/fPp6sif4tU1W3goTxyNFI2GKNzyeWQqTrLxBS6N6ssUpSXrGqAjMAHLj6AD4+Pli3bl299nVj99XV1SEkJIT4+Pgm53r69CnKysrYNqi/fPkCOTk5qKmpYfHixQ0mqRQXFyM6OrrBqhmN8dMZXeDHEdQoKyvDggULsGHDBty8eROTJ09ul3n9/f1x5swZnDlzhuvyPc3hxo0b6NOnD1fqbLyIXKiNmZkZbty4gfLy+tUJeMX48eNhZGQEV1dXno4rKyuL8PBw5OTk4NatWygpqS72aG5ujnPnzuH58+coLi7Gxo0bwWAwWOJNEyZMwOvXr5GRkYFDhw5h48aNOH36NNfrcXNzQ1VVVb109BGLvKC85Dxk7dwgqqYNBqNpc/P1th9AVZD4pVrvo6SiCke2roO7uzvHz78lxTJrk5eXh6lTp2L9+vWs/pqamnj69CnS0tJw8+ZNPH78GEuWLOHY39nZGf369WtVxYmf0ugC37+gRmpqKkuwJzo6Gr/88ku7zPvq1SvMnTsXgYGB7Va/rTUyjnXhVeRCDXJyclBXV8fduw2LIPGCXbt2ISoqCufPn+fpuEwmExMnTgSDwYC5uTny8vIwYsQIbNiwAba2tlBRUYGqqiqYTCartFLv3r2hqKgIfn5+GBgYYOHChWwFG1uDt7c3Tpw4gStXrtTzteeVVIDBLwBRdV0UJz1BUULjYW95j4NR8PImZO3cwBCovtsrSniA4qKCBsXnW1Iss4bi4mJYWlpCX18fq1atYr0uLy+P3r17g4+PD2pqati6dSvH87N8+XK8fPkS586da9Wd1w+VHNFSagQ1sgpK4f/kI+LS8pFXUg5JEUFoKjAxXrvxyhFtRWRkJCZNmoR58+Zh1apVbRqmVZvc3FzY2NjAy8ur3YR6ysrKcOnSJbi7u3M1Di8SI+pS42IYNmwYT8etjYSEBPz8/GBhYQF9fX2eSm8KCAhg2LBhEBcXx/DhwxESEgIXFxeWzm98fDw2bdqEvn37cuzPbUFGHx8feHh4IDIykmPNPLa4+apKVOQ0XJSz4Nk15N33h9wUTwhI/ncxUPLhGUrfx0FeXh4A8PXrV/Dz8+PFixe4ePFivdj9xMRElJaWNphRWVpairFjx6JLly44cOBAo++P0/lZv349QkJCEBER0Wqp15/2Src231pQY+vWrdi6dSuICDt37oSdnR18fHzwxx9/tJvBraqqwtSpUzFq1ChMmzatXeYEgPDwcPTs2ZPrQpa8di8Abe/XrUFPTw8LFy7E1KlTUVlZyfV4tePYq6qq4OXlBQsLCxgYGOCff/4BESE5ORlOTk5YuHAhS0Lz4sWLyMnJARHh4cOH2L17d6PCQ6WlpSzXRe24dKB6A2v16tW4fv06unXrxtYvLi4OISEh6CYlBCFGFQpehqMk5RWEu3I2/gWvwpETeQJyEzdBsKM82zF542lwP3UDT58+xdOnT2HH0ZpNAAAgAElEQVRlZYXZs2fj6NGjAIApU6YgODgYUVFRKCwsxLp16zBu3DiOV7rl5eUYP348REVFceLEiXq/vVu3biE5ORlEhJSUFKxcuZLt/GzZsgV+fn64fv06d7onDcWS0f8XpuQJubm5JC4uTiIiImRkZEQDBgygxMTEdl+Hm5sbGRoasgr0tRezZs0iLy8vrse5evUqjRo1igcr+o+KigqSkZGh5ORkno7b0FxGRka0ZcsWIqqOGS0pKWnVWA3FsW/dupUEBARIRESE5OTkaOXKlWyxwvb29iQtLU3i4uLUs2fPekVGe/fuTb6+vqznNTG6tR81cfGqqqr1Yn7nzJlDRESxsbE0cOBAEpeQID5hcRKS706dbVaz4nLlpngQQ1CE9Zy/gxyBj58YgiKsh0R/M1JZeZl6rLlKmfn/nSdHR0eOcbrKysokJiZGVlZWbHG6c+bMYa2rJs5XVFSUbd2RkZFEROTl5UWKiookKipKSkpKNH/+fLbCrgBISEiIrW/t2P3a4H8pTrc9aEmhy02bNmHz5s0oKSmBoKAgnj9/3mDJ6rbi8uXLmDt3LqKjo1m3ae1BeXk5FBQU8PjxY6ioqHA11vnz53H27FmufZB1cXBwgJGREZycnHg6LieSk5Oho6MDZ2dnbNu2DXv27MHs2bN5OsfZs2fh6uoKf39/DB06FO/fv0d5eTm6d286cqAt+JHj5rmhsTjdn9qny2taKthRXFyMP//8k3WLVllZiWnTpvE0drMh0tLSoKCggISEBMycORMXL15sV4MLVAfrq6urc2Vwv3z5gkuXLuHRo0fIzs5GWFgY+vfvzzNZy5od//YwuhISElBWVmaV5nn69CnP55g4cSKkpaUxbtw4eHh4YMWKFVBXV/9m2g0uwzUQlZCJ4vKWu1V+lkKUdfl/o9tMqvPH46qrUnD41y751wBfi01HZHwm/jDXxOvgQyguLoa4uDh0dHQwfPhwmJqatvlaY2Nj0bdvX6xatQpBQUFwd3fH4MGD23zeunAj41hDXFwcnJycICQkhKqqKpiZmWHDhg08y/QyNTXF3LlzUVpaytNyR5ywsLDA8+fPWX7RmJiYNpln5MiR8PPzg5mZGYgIhYWFSEpKgpqaWpvM1xg1cfPV2gvN1yb5mQpR1uX/3QvN4D/BjpZ9aZb82g3GSvxQV1fneQWGxvDx8YGLiwvKy8shLy+P2NjYdi+qWVFRAUVFRdy/f7/eRktLICKoq6uzxFOYTCaSk5PRsSPvfoyDBw+Gu7s7TEw4iyHxiqSkJCxfvhxXrlxBSUkJmEwm1/q7nCgvL8eAAQMQFxfHkrD8/fff6yXCtMRNxi1NXbTUwGBUX+H+Ya75Q9dF+yHSgBsrRnn48GFoaGhAQkICZmZmSE1NZR1zc3ODoKAgJCQkWI/ExESOc5SVlWH8+PFQVVUFg8GopwOwbds29O3bF0wmE2pqati2bRtbocvPfquQsmsykrfbIfXIfBTFN1wp4PPt85g/YRT69R+Abt26Ydu2bRzbRUREgMFgYM2aNazX0tLSYGVlBUVFRTAYjCYLH969excDBw4Ek8mElpYWzp8/z9rd/vz5MzQ1NaGiogJxcXGMHTsW2dnZjY7HC6KioqCsrMyVwQWqw3bWrl0LQUFBCAoKYuPGjTw1uED7RTGoqanB398fDx8+hK6uLvLz81m11Xgp7F1ZWQkdHR0wmUyIiYmhsrISO3bsYM31LCUXTicfYYjnTey4EY8LT1NxM+4LLjxNxc4b8TDwvIk5vo/wLCWXZ+/9e4+bb0++myvdwMBA8PHxfXciHhoWc5DYoR+IqqUiBWW6gsHHj9LUN0hvQsRDVK0/LIYNwlJ9qXqCIAAaFPFIT09HQEAABgwYAAMDAyQlJbFKoNe9OhGqKITvknHY7e0Nx8kTcfr0aUybNg1EBDExMcjJySEtLQ2hoaFNCoLwEhcXFygrK2PlypVcj1VaWgpJSUmIiIggIyODJ/oLtXn8+DGmTJnCqrXXXrx79w4FQp0a2SfgAwGtFvYmIrx48QL+/v7w8fHBkydPcC2x6JtfcX5vcfNtwQ+xkTZu3DgAwKNHj9hUfmqLeADA2rVr0aVLF7x79w7q6uotmqNGxANAgyIeNfTs2ROm5hbwf3gfHUyqc7uFZNl9YjUiHpyMbgf9al9mxNscbLEdwBIEqW10a0Q8vnz5wtZXTk4O8+bNY6sw29AmXtHbhygXYsIzXgoPTsdg7rAxICIoKCjg5MmTuHHjBj58+AAjIyMAgLu7O3r16oX8/Pw2qYEGVF9pBQQEICoqiifjCQsLw9XVFRoaGjw3uAAwYMAA5ObmIjExkesr85ZwL4Mfm6/eb9E+QUsMIIPBgJaWFrS0tLBx48YWuclq69oC4KnhrYmb/1/lu3EvNERNbFvt50D7iHj8cyMcQv8Kb9Tw5fwGfNhm02wRDwaA849T6gmCfPjwoUERj7oExXxsWHX/3/NTo7o/6dADdFZUxsSJEzFixAjExsa2WhCktdy5cwfy8vJchynVvuXO6jsBrzsObJNaWnx8fBg9ejRCQkJ4Oi4nHBwcoKCgAFFxJmaOGYIvj66yDG5VeQmyQvdWu7B2TMBn3xUAOAt7v379Gr/++is6dOgADQ0NBAUFcZxvw4YNYDAYOOB3geUmq0tm8F/4uGcqkrfb4dMBJ+Q/+08s/Wvae8weZwrJjh0hJSUFExMTxMbGNvj+GnMTAkBYWBg0NTUhJibGSoOvgZN772fkuze631LEo6SsAiJ92DdXZO3Wo2sLRDxKKqpwbM+2eoIgrq6uDYp41MU7/G2DqvvCSr1QUZCNwtgIVFVUIOPJNWSkfsSzpHQArRcE4QZuZRzbyuf4/v17mJubQ0pKCvLy8pg/fz6rFNLjx4+xePFidO7cGXZ2dkhLazhltSnDUkONwbtx4wbrtVWrVmHr/hNgyKiiIi8L2SHeyL55BACQ/Y83qkryoTh7H5QXnoaUyX8xvLm3/RDnbo7V3qfx5H0mrK2tYWFhgRs3bkBMTAzjxo2DjIwMdu3axerz7t07+Pv7Q0FBAcdDbuP9yVVI2WmPlF2TkRG0BRUF1b59SX07MHUsISDZGZUFWcj+529k36iucSYgIY1OY1fCYt1x9OvXD5GRkdDW1mZ7T7VRVFTEmjVrMHPmzHrHMjMzMW7cOLi7uyM7Oxu6urpsmgpEhBMnTiAnJ4dVS6+t3WDfgu/e6H5LEY9fF21nCW/UpqUiHq8igtkEQYKDg5Gfn9+giEcNNUaltJHbQX5RScjarkHewwv4uMcBxYmPIaLaHy9yBfD8Y26rBEFaAxGhuLgYVVVVCAgIaHWoWFvW0po3bx5kZWWRlpaGp0+fIiIiAnv37kVOTg4WL14MISEhxMXFgclk1lPMqk1jhqWG2gavNnJycnCaOhHi/UZBftpf4BPrAH4JaZRnfURRwgN0MlsAfrEOYPDxQ1i+Oka1PCcNRW/ugF9CGmWVVfA4fQOpqamYOnUqxowZgxUrVmDEiBGYOXMmW0ji/Pnz4enpCQFBQcR/zIBEfzN0meuDLvN8wBASRdaVnQAAoc4qAB8fOlksgfy07eATkUDhq1sojI0An4gEBDrIIWj7Smj2+QWenp4gIowfPx4ZGfX1cceNG4exY8dyjKMODAxEnz59YGdnBxEREbi5ueHZs2csX3pTGr0/C9+90QWqN2USEhLw5csX2NraoqKigisRj9LSUuTk5MDe3h5MJhMDBgxg3Vr6+PjAzc0NfHx8CFxph89+q1Dx9T+fa170RXzaNwvJ2+1QkvwceQ+DQFWcA7/zY0KQE34UqKqEsrIyK1oiLCwMjx49grCwMPj4+HD8+HFs3rwZfHx8bGpj+yLeAgA+n1qBZC9bfDrkjPLsT/XmEen6C6SMZ0BQVg3F7x6h5MMz8MtrYO+ttyxBEGNjY3Tu3BlMJhMFBQVISEhg9b916xb4+PjYIkCOHz/e4Plbu3YtfvnlFwgICMDNzQ1AtS9eQkICv/zyC4qKimBiYsIxWmLZsmXo3r07mEwmNDU1ceLECdaxtq6llZSUhAkTJkBERATy8vIwMzPDq1evMHr0aMyYMQPa2tq4d+8eDA0Ncfv27QbHacyw1FBj8Or6oDd5bEWloBiyQryR5rMAAsxOYPY3Q2nqGwh0kEVu1Cmk7JqM1CMuKIyrNjjZ1/dDavh0gE8ABODh++rzuX37dowaNQpTpkwBg8FAQkICq2rw+fPnISQkBHNzcxSWVkJEsSfENQ3BJywGPkERMHUsUPrpNWtdFV+/IN13BdKOuEBAsjPEeg5B6cfq4+XZn1DyKQ4H9+/F0qVLWZ9/QEBAs857DXW1b8XFxaGuro5Xr17Va0sNaPT+DHw3RrehYpQlJSV4+fIlT0U8CgoKwM/Pj61btyI9PR0bN27EhAkTsHPnTqxcuRKlpaXw8PDA9uDHEFPsgYyLnijPSkHxu0cQUe0P+WlekDadB1QRqLwU+Y8u1Zun4FU4cqJ8ITXQGs4bdrNlg7m7uyM+Ph4fPnxAamoqJkyYgEWLFsHAwIB1W/4x8ysunak2SNKj5kHJ1Q+y49eDT7R+vG3Z53cAvwDEew2DkIIGwMcPETUdhL/JwBgbOwQHB8PR0RFv376FtbU1TExMMHv2bLZbaEVFRRQUFLAejo6OrGNnzpxBr169WD+SyspKzJw5E1JSUvD09ETnzp3h5uYGAQEBxMbGIjc3F58+fcLu3bshJiaGefPmsW7Jd+zYgb59++Lr/7V33tFRlVsffqbPpE56pZqYAAIiiPQQEBNQlOKlk3xR6WGhoiIYISoCKqAgWMCWACIQENAbkKIxgMAVJSBVBEmB9D5JZjLlfH+MOTCkAN57kYvnWWvWymRm3vecKfu8e797/3Z5OUlJScyYMYMffviBVeu38eQjvTm7cGi9C51gMVO8cwXZy8eR/c4oCja9gqWyCIAas43XU89wPMfuFZw6dYouXbrg4eFRLwY5Y8YMZs+ejVKpxMnJiSVLlpCUlMTZs2dJTk6moKCAoUOH8tRTT4ldGZpKV2yMqw3etez4dh/Od3VG5dsSmcYZm9mItaoMa2Ux5sJM5BonguOT8BwwmeJ/vk3Fv7YikyvR3XW/OIbGqxk6N082bdqEXq+nbdu27Nmzh/3795OVlYXBYGDOnDm88459JWu22jDbHK9ipuyTqLyv7Fd4RU2l2bMb8Rv7BtrQbpgunxGFxM2FmSi9gpn6yX5WrFhBp06d6NixY4PGsiluJtTVmEbvncBtY3Tnz5+PTqdj0aJFrF27Fp1Ox/z58zEajYwZMwYXFxe6du0qJrLX8cUXXxASEoKrqysxMTHMmjXLwWC0a9eOdevWiffDwsLw9vamsrKS2NhYnJ2dad++Pa1atWLBggUUFxdTXV1NXFwcLw7rirWmAnPB75hL8yjb/zl5a57j0qpJVB7ZjtfA6cg1TphLczFmnyBryRWXuix9LYLRQNmPX/H+i0+Sn5/P0qVLAXuCv7+/v3jT6XSYzWYOHjzI+PHjAWjmo6fwG/umYGHKq2QvGY7KIwCFzpXinSso3rlCnKv88GYKNiVSmvYJ2GwonOxfbBlwosaNDz74gLlz5xIYGEhlZSUvvPACZrOZ7Ozs634uu3fvZtasWXz66adUVlaSnp7OtGnTCA8PJzw8nKeffprMzEx8fX1FQXCZTEZISAhDhw4V26d4eHiQkJDAxIkTcXd3d2h5smfPHuKfHIt773E0e3o9Gv9QCre9IR5DxZFtmC6dIfDJdwmOT0audaFk9xVZPqPFyntpdq8gMDCQlJQUSkpKKCoq4tFHHxUzRiIiIigsLMRms1FTU0NMTAw1NTUIgkBcXBxnz57FYrEgCALx8fF8//33zJkzh23btlFSUkKrVq0YPXp0k+/XtQbvWgpyL1N+fC+eAybRbPoaZHIF+V8kIFOqQa7EvecoZAoV2ubt0QS3pfzgRofYLoBJkBP19GIuX77MypUrcXNzY9SoUfj6+jJ69GjmzZvH+PHjxQq0a72G2oLfKT+wHo9IR4MmkyvQNmtHzblD2KrLRSFxm9mIXONMDUomT55MTEwMSqXypvcFbjTU1ZRG753AbWN0ExMT66nxJCYmotfrOX78OFVVVeTl5bFw4UKHdK/169dTXFyMwWDgzJkz9VT6T548ydixY8X7Fy9erDePTqfj119/JT09nfj4eCZOnIjBYKDKYGDkzAUo9f4IlloCYpfS/NlNeD00BXNJDsWp71Bb8Duu90ajbXYPzWdeiSUHT/mYlrO2MfGTfRgMBgIDAxtVof/ss8/w9fWld+/e4g8lbsU/AfDoPwGFqzcKdz/K9q1DEGx4RcfjFR0vvt7nsRdo/sxGmj+zEfeeo+CPzT2jxcaZ3ErGjBlDVlYWkZGRfPPNNzz00EP07duXLl2upBE21qZk3rx5zJ07l27duiGXywkKCiIoKIiBAwfSokULNBoNTk5OTJ8+XRzL09OTgwcP4unpKWZLhIeH13PJ61qe5OTmo/BqjlN4L2RKNe69xtgvdMX2i4KlPB9d6/tQOHsgU6pxatMHc9GVFudX99LS6/Vi8YsgCCgUCn777TdsNhtRUVGEh4czcuRIioqKKC0tZdasWWKYo+4HrlQqRcnAm+05dq3BuxaZSo3T3d3RBNyNTKlG7dsaa3k+Cn19XQxLySXU/qH15A4BNH6tCA0NJTY2lkOHDpGZmckTTzzBDz/8wK5du1i+fLl4Ua8qyado6yLKD6VgLr1MwcZ5eDw4EW2z+iG6ip++wlJyCW2r+8T9DLlKi2Cqxk2rwmazUV1dTV5e3k3vC1yrfVtVVcX58+cdQgh1Gr179+79t+VAb1duG6P7V2E2mxk7diyxsbGEh4fXc4Gm9Q1BqXVBqK0R/+fcri/Nn91E4MQPce00EIWzR4Nj34xgR3JyssNOeP4frr/x4lECn1yB/+gFVJ36HsOxXTd1fhXGK+1ovv76ayorK0lNTSUqKkrUE22sTYnVauXIkSMUFhYSEhJCcHAw8fHx1NTU1JsnPT0dtVqNUqnkxRdfdDCujbmQdS1PzhUY0FyVAy1Xa1Hq/akttBtWlw4PYco5jaWyGJvZSNWpNHStOzuMJQNSfr6S363X69FqtUyfPp05c+ZQUlJCdnY2Xbt2JTU1ldDQUH7++WexqKZXr144OTkhk8mQy+UEBgbeULritezdu9fB4GVnZzNixAjeeOMNCgoK0Dm5gM2KYLNSc+Enqn61d67QBoWjdPOh/OBGBJsVY84pLBUF1F4+Q/a748h+dxzWyiLReJryf6ddu3ZYrVYWL15Mbm6u2O5p27ZtnDhxQtSg1Xv74jdoOrqQruSvT8C95yhc7ukHgLWqzJ75UltDZcY3lO9fjyDYcArtBkDN70cBGZayPPyUVTz77LN4eHiQk5PTYLy1sTAhwNChQzlx4gSbN2/GaDTy6quv0qFDB1F1rymN3juJv7XRrRP2VqvVrFhhd9evdYE6NtPjpbaicXKq93qVZxAq7+YU73qv3mM3I9ixf/9+8vLyHHb83V3s87k9MNy+g6z3w/XeaGrO31yFoJvWMftCpVIxcOBAvvnmG7Zvt8eiG2tTkp+fj9lsJiUlhX379pGRkcHRo0eZP38+RQYT5/Ir2XkilyHzP+fFhHn84/k36RXRF5vNMeOgIRfy6pYnBSXlCGrH91eucRYvdCrPIBRuPlxaGUv20hGYi7Jx7+no5tet6usoKyujvLxcjEF6e3vTqlUrTCYTv/zyC+fOnaN169aUlpaycuVK+vXrx+zZs0U3va4NTkPpipWVlY0alr179zoYvMDAQD788EOmTZuGTCZDZq6h6uR3ZC0dQcm3H6MJaoMmuC0KZz0+wxOoOX+E7LdHULLjXbwGziBwwgcExr1rd/XlCjyj4/HpOpiCo7vZvn07a9as4csvvyQ1NZU333yTXr160bp1a4fwlYtOjWCzUpjyKq6dH8ZWYyB/4zz7GyWTUXl0B9nLx1Gy813kWhc8H5yI0912o2szVVH6fRKCzcIr4wZw9uxZ8bMbPnw4CxYsYODAgeL73liYEMDHx4fNmzfz0ksv4eHhweHDhx1SwhISEiguLub+++8XN3QnT558A9/y/y1um4q0W40gCDz5pD3WmpqaKnbgbdeuncPOfVVVFcW5WSQO78enp8z1qocEm82hDcmfKZ9MSkpi2LBhDjm73Tq15wuFEvsa7s+hVcoJD2jYBbRYLI26yXWuuU6nA2D69Oli6tOwmEksXPA6KfJe5OZVIpTaOPLNdPSRT/EjoRTWeJKz9VuiRk+kYzN9g+1TMjIysFgsYssTQaXFVu64ErbVViNT2+cv/mYlgqWW4Bnrkau0lB9OoWDjPAJilzq85upVPdh3xydPnoyPjw+nT59my5YtPP3003Ts2BGFQkFkZCQzZ85k5cqVXLhwgVdeeQWwq3Vrdc5M/mw/oQOfoGvPPliM1cx+6WVcXV3Zu3evGHsHezfnefPmkZiYWC+jQaFQ4OHhIRqRjGPHaDdiJsX71mOrLEbl7ofnw/YqSbVPC4TaGjyj43FpF+kwjkffWDGFS6bWsX71CrxcVvP+++8zf/58evToQa9evfj888/F17Rr1445c+aQlZlJ52GTyCvLo3z/lRz2rCWP03xmCv5jF5Hz/pNYK4uwGkoo3fsRpXs/wrldX7yi43Fp04sePlYubVtKeno6Fy9eJCUlBR8fn3pqb4mJiWJGS0M8+OCDjZZb14ka3en8bY3ulClTOH36NHv27BGNC9hdoOeff57Nmzfz8MMPiy7QC6P6E51TxvTExeS4tUPlrKci7yIVhzahbdVJrJOPDPNhat8QcYVrMplEt7Su5YlGoxFVx2pqati0aRNbtmxxOL4xPUNJaNuHisObUfu1xmaqpvLYLtweGNbg+QiCDawW+w0BwVKLTabg8fuCOXPmDL///jt9+/ZFqVSyYcMG0tPTefPNNwF7yljr1q1p1qwZOTk5YpsSDw8PgoODxWNde+giS/f8SoXRjLPRiMVYjfHXw+j7jMO5bQRGiw1NmwjOr3mOR1/+iJdjB5H28QKH9ikHDhzgwoULnD17VjRQAS1CuHDqyvnbao1YSvPEakBzwe/o+8Sg0NnHcOs8mPJ967BWl4ubhlB/VQ+IMchLly7RqVOneiJHb7zxBuHh4Zw6dapeqfXWjMsQHIF/fARapZy1BTlUG2t54tl5YruY63GtWJG3i4bHRv8fu+8d2GBaXOBT9b2mOoKnfoJMZv+O1WkUTJkyhSlTpjT4/KuzCz5Z9gaj7hnaqK5t8JSPG51Xq1Qw6x896fDMo40+R+LG+VuGFzIzM/nwww/JyMiwu19/rELWrVvXpAvUIVhPa+slKtc+ze+Lh2PY+hphXfoQO302zwy4mx9m9WPfwlh++f6f4lxhYWHodDouXbpEVFQUOp3OofRx69atuLu7ExnpuLLxdtEwLP5lZGotOStjyVvzHM5tI3Dp8Edr6muyJUxZJ8haPIyCTYlYKwrJWjwMw5ev4OWiETclfX198fHxYdmyZWzYsEFsTvnzzz/TvXt3nJ2d6dGjB/fccw/Lly8HIC4ujueee45eg4bz6uZ/UXzoSxAEshYPo+a3wwi11ZTuWUXVie8A+2rNK2oal758k4lR93E6K5/33ntPjPWlpaVRVVVFaGio+L6ra0owF2VSdeYAgqWW8gPrUfm2ROVlb+KoDribqhPfYjNWIVgtVP6cisLF08Hg1q3qd+/ezdGjR7FarVRUVIgxyLr81cZSDBsqyhAstdQW2jdeDcV55H69HOfOg5m46cxNFWVcy7S+IWiV9bU/boQ/K+xdp2urU93cT/5O1rX9q7htVMYk7KuiqVOncvDgQTQaDX2jB5MRPISaWjNF29/ClPsb1ooC/EYvQNuiQ6PjVPz0FTUnvsVanMmY0aNFxbY6qquree6559i4cSNms1ks7wR7LHTGjBliscikSZM4m3mZzRs3gFKFc3hvPCLjKD+UQvn+z+2ZEsIfMVyFihbP2zUAyn/YiDHnJC3Hzmft/91HVNe2FBcXOxyHu7s7JpMJuUJBjcmMPZQioA64G++Hn0Gp9wPAWlNB4dZFmLJPgs0KChX+YxehCQwD4PJHU/HqOZLpPfx4Z/EbFBXZc3j1ej3dunVj5syZLFu2jCNHjpCbm4u7uzsWi4Xg4GCmTp2KZ9dHRSGYyx9Nxa37P3BpF4nNaCBv3YtYynKRqXW4tH8QfZ/xyOSKP4xRmz8tBPNnNZr/nTmvzPv30bX9q2hKZUwyurcRgwYNwtfXlw8++ICysjIGDBjAvQOG8aOuMwWHv0btH0LR1kV4P/p8k0bX8ttBHu/SHNPFow4ymXWMGzcOi8XCu+++i6enJxkZGXTubM8GiIuLw2AwkJSUREFBAf379ye431iyfB6o9yMVrGYqf06td1yCxUzxrvcwXszAZjSgc3KmVZAfZWVl7Nq1i5iYGM6fP09FRQUdO3Zk7dq1vPNTNbtP52OtMVCyZxU1F34CwLXTIPS9x2K6fBZzySX7SviHjQRP/QTTpTOU7VtLbd5vKLChUyvZvn07ffr04cKFC6xatYqlS5eiVquxWCwoFApqampEqcyWLVuSl5dP7R92TxPUBr9RDbeKLz+8mapf9mKpKESuc8P1vkH49xrBhond6BBsT1PLz88X0xl79OjBrl32TJO0tDT69euH01WbsStXrkQRFlHPAFqryijZswpT9glsZiNq7xZ49n8K9xZteWlQOMHGiw2OVZebbjKZmDJlCikpKTg5OfHCCy/US1U8nlPGe2m/8d3ZQmRcUTMDGg2TSdwc/xPSjhL2jYT4+HiHMtWKijwSRnTgdYUao8UKTbRsF1cnM59iXLeWJCQkOMhkApw9e5bt27eTk5MjdpOoM7hg14XYsWMHTk5OtGzZklHjYm7/XAsAAAn3SURBVHn70434jn2g/nwKFW73/1H9d9VxCTYrSldv/McswiZYKfx8DufPn8fd3V0sXqjT0ejevTujRo1izT/T2XeuiOy9HyGYTQRN+RhbVTn5X7yE0t0Xlw4D0ASGUXPxSl8xm9GAy73R6EM7U7FmOp06dmThwoVERERw1113odPpGDlypJgWZrFYxA3TOvrPWMwpRcvrN04UBLweeRa1bysspbnkb3gZpZs376V5i40Tv/rqq0a7TwQGBtb7LMAesrraAFaajWgCQvHo/xTObh6UZeyidMurbDlygm5hwaSlXWx0LLBvZJ07d47MzEzy8vKIjIykbdu2REdHO8z5wbgufwtd29sRyejeRsyYMYMvvviCvn37Ulpayo4dO3jttdcY2q2l+OP8GFAr6qvu3+jq5PDhw7Ro0YJ58+axZs0aAgICSExMZPjw4eJzrvZ+Tlwqx1SY2dBQjSJXa9H3thekFGx6Bd+oydQeSMJsqkKv1zt0fkhOTsZgMPD8kyMYN/5p5v32L3xGJCJXaZHrtbh0eAjD8d1iLPtqdHd1QaeSM+k+N555K497xo5l6dKltGrVipiYmOsep00QOJZTjrL5dZ8q6iMDqLyCcQrthin7tFiU8WepbwADqOjW4YoBnD2AVoGfoTLkA9cvFkhOTubTTz8Vy6AnTJjAZ5995mB06/i769r+VUhG9zYiIiKC1atX4+bmhtVqJTY2liFDhgBXfpzbZ2l5vEswgn/Qn1qd5OTkiDmWly9f5uDBgzz88MO0bduWNm3aEB0dzaJFi0hKSiI/P5/vv9qIzWz8U+dTffYHBJsVeUAYJQW5eHtdEXvX6/UYDAZsNhtz585Fq9Wy7Pkn0KrkaBRyZLK68lUBcwNG/+qYY2ubXQ8hNTWVzp07s2nTJh566CHCwsJIT0/H09OTgICAerv8VSYr5dveQrDZUPvdhUdkHGq/6yflC4KAMfskrp2iHYoyxo4di81mo1OnTrz11lsO4i51FX9OTk4MGTKE+fPn4+zsLD7emAHMyMigtraWkJCQ645VWlrK5cuXHebt2LEjW7duve45Sdw6/pbZC7cjdWWqw4YNo6qqyqFM9WrkMni0YxBvj7yXj2Pv5+2R9zKpz1037A7qdDpUKhUJCQmo1WoiIiKIjIwU44/Lly9Hp9MRGhrKY489RosHBqB09b7586k1Upr2KR79n6Jo+2KC7unm4NpfXbzQtWtXZs+ejV6vp0unjtx1eQ+RrVyQVeRRdXw3NsuVlaRaLkMmw6GXVl3KX05ODkuXLqVly5ZMmjSJ6upqB63l119/3eEY+099jcDJHxM09RO0LdqTv3EuNqPhuudWvv9zEGy4tB8gFmWsW7eOixcvkpmZSWRkJFFRUZSV2UV4Gqv4ux4VFRWMHz+eefPmiVWSTY1lMNiP/eqKyv+2drLEzSMZ3duEujLV+Ph4NBoNXl5exMXF/ccbJnbo0PgGHNh1E9atW0deXh4nT55ELbenbN0sltLLWMryyf10Bsack+SfO0Zubi7+/v5i7mpd8UJMTAwFBQXIZDImTJiAv6cbqS+PRPPtEh4cPAx3L3/6h/sy9N4ghncOJsBdywfjuohhFKXS7rBNnz6d3r17i8fg5ubmoLV8tT4EgEuLe5CrNMhVWty7j0CuccGY3bRyVsVPX2E48S2+/0gUtQkqjGZ69uyJTqfDyclJvIDUtStqrOKvKWpqahg8eDDdunVj9uzZ4v+bGquuuObqisr/hnayxL+HZHRvE+rKVN9//30sFgtlZWUkJSWJrqLJZMJotLv5dUUWjWWeNFX/3qdPH5o3b87ChQuxWCwcOHCAtLQ0oqKiALv4dnFxMVarlR07dnD6u6349GlcWUuwmBEstfa/bRYESy2CIKD0bo5TWE80/iG0mrKKuNmL8PPzIyMjg2bNmpGVlcWBAwcwGo1UV1ezYMECioqKiI6OFo3+mdOnuDfYnYH9erF6fGcWPhZOVBsf+4670UhtbS2ZmZkMHjyYBx54gGPHjlFZWUlOTg6rV6/mkUceEY+z7v24+r10014TXbtO8Z/h2C4qDqXgN/p1lG5XVv8NFWU0pet8Pc1nk8nEkCFDCAoK4sMPP2z0edeO5eHhQUBAgIOozLFjx+5ITdr/ZSSjexuxZcsWdu7ciY+PDyEhISiVSt5++22g6SKLm6l/V6lUbNu2jdTUVNzd3ZkwYQLJycmi6MhPP/1E+/btcXV1Zfbs2XySlIzGp4U49uWPpmI4+Z14/9KqSWQtHoa1spiCDXPtf5cXULr7AywVBfiOfBWV3p+BnUOQy+X88ssvHD9+nLKyMlHm0WQykZGRwY4dOygrK6O4uJi0tDS0Wi2rVq0iISGB9PR0dDodgwYNIisrC51OR0REBP369WPatGns2rULFxcXAgMD6d69O2PGjMHLy0sshNDpdGI/uvDwcHuYpfAcapnVnoZ2eDO26go0wW0a/GwMJ7+jND0Zv5HzHVS/tEo5vvJKDhw4IF4M33rrLYqKiujZsydgTxnLyspCEASys7PFir+GMJvNPP744+h0OpKTk0VRojquN1ZMTAzz58+ntLSUM2fOsHr16iZbCkn8BVwrc3j1rXPnzoKExITkH4WWs78WWrx4Y7egKZ8IgIBCJchUWkGp0QnOzs7C2rVrhY0bNwphYWGCs7Oz4O3tLQwcOFA4duyYONeGDRuEgIAAQafTCR07dhR27tzpcCxt27YV1q5dKwiCICQmJgqA4Ozs7HCrY9SoUYKnp6fg7OwshIWFCcuWLRMfO3HihNC23T2CTKUR5FpXQduig+Af+7Z4Dn5jFwkylVa8r3D3E5ArBJlKK95c7o0W7k5IFfb/62ehffv2gpOTk+Dp6Sn069dP+PHHH8W5lixZIgQGBgo6nU4IDg4W4uPjhYqKCvHxSZMmCZMmTRIEQRDS0tIEQNDpdA7nlJ6efkNjGY1GIS4uTnB1dRV8fX2FJUuW/Ce+AhI3CXBEaMSuSsUREtflWHYZo1YfarRuvyl0KoVYQHA7MnHNEXafzr9+nm4D1G3o1eXpSkjU0VRxhBRekLgud3Ld/l+hgyDx90YyuhI3xLhuLXlpUBt0KgWy62w4yWT2Fe6/qxNwK7iTLygStydScYTEDTPuqsq4O6luv+7CIAnBSNwKpJiuxJ/iTqzbl4RgJP5TSCpjEhI3wZ14QZG4tUgqYxISN4EkBCPx30TaSJOQkJC4hUhGV0JCQuIWIhldCQkJiVuIZHQlJCQkbiGS0ZWQkJC4hUhGV0JCQuIWIhldCQkJiVuIZHQlJCQkbiFNVqTJZLJC4OZawUpISEhItBAEwaehB5o0uhISEhIS/1mk8IKEhITELUQyuhISEhK3EMnoSkhISNxCJKMrISEhcQuRjK6EhITELeT/AYi+LXe5mBIzAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Draw our connection network\n",
    "nx.draw_networkx(G)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "But if you try this with a larger data set, you get what's affectionately called the \"fuzzy hairball\" by data scientists.\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}