{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "47f1d548",
   "metadata": {},
   "source": [
    "**In this workshop we will analyze the data on 10k customers regarding their risk profile, products and demographic information using the `pandas` and `sklearn` libraries.** \n",
    " \n",
    "# Clustering\n",
    "\n",
    "Clustering is a type of __unsupervised machine learning__, where different data points are grouped together into two or more clusters. Data points in the same cluster are more similar to each other than those in other clusters. This similarity can be measured in some specified way and the strength of similarity between data points is used to assign data points to its cluster. \n",
    "\n",
    "There are hard clustering and soft clustering methods. Hard clustering is when each data point belongs to a cluster completely. Soft clustering is when each data point can belong to more than one cluster with some probability. The number of clusters can be defined by the user. However, in some cases even the users do not know how many clusters should the data be grouped into. Therefore, figuring out the best number of cluster is also a part of the clustering task.  \n",
    "\n",
    "## K-Means Clustering\n",
    "* Hard clustering method.\n",
    "* A centroid-based clustering method. \n",
    "* Given a cluster, a __centroid__ is its central data point. \n",
    "* Centroid can be real of imaginary. \n",
    "* In K-Means an iterative algorithm is employed to derive similarity based on the distance of that data point from the centroid of the cluster. \n",
    "\n",
    "Refer [here](https://jakevdp.github.io/PythonDataScienceHandbook/05.11-k-means.html) for an in-depth study of K-Means Clustering.\n",
    "\n",
    "### A. Data Loading and Pre-processing\n",
    "\n",
    "Let's begin by importing required libraries, methods and data. Then, we will perform some basic data pre-processing."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "bc3397b2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# import required libraries\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from matplotlib import pyplot as plt\n",
    "\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "from sklearn.cluster import KMeans\n",
    "from sklearn.metrics import silhouette_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "3a47f022",
   "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>CustomerID</th>\n",
       "      <th>CreditScore</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Married</th>\n",
       "      <th>Age</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>NumBankAccts</th>\n",
       "      <th>HasCrCard</th>\n",
       "      <th>EmergingMarketFund</th>\n",
       "      <th>RealEstate</th>\n",
       "      <th>PrivateEquity</th>\n",
       "      <th>GovtBonds</th>\n",
       "      <th>CorpBonds</th>\n",
       "      <th>ETF Tech</th>\n",
       "      <th>ETF Health</th>\n",
       "      <th>ETF Med</th>\n",
       "      <th>EstimatedSalary</th>\n",
       "      <th>Mortgage</th>\n",
       "      <th>Risk Profile</th>\n",
       "      <th>Debt</th>\n",
       "      <th>Net Assets</th>\n",
       "      <th>Portfolio Return</th>\n",
       "      <th>Diversification</th>\n",
       "      <th>BusinessOwner</th>\n",
       "      <th>Revenue</th>\n",
       "      <th>Margin</th>\n",
       "      <th>LifeInsurance</th>\n",
       "      <th>NumTransactions</th>\n",
       "      <th>LastTransactionAmt</th>\n",
       "      <th>ForeignAssets</th>\n",
       "      <th>NumProducts</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>15634602.0</td>\n",
       "      <td>619.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>1.0</td>\n",
       "      <td>42.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>101349.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.16</td>\n",
       "      <td>0.0</td>\n",
       "      <td>75615.0</td>\n",
       "      <td>0.1232</td>\n",
       "      <td>0.3623</td>\n",
       "      <td>0.0</td>\n",
       "      <td>65424.71</td>\n",
       "      <td>0.08</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2095.3</td>\n",
       "      <td>0.39</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>15647311.0</td>\n",
       "      <td>608.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>1.0</td>\n",
       "      <td>41.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>112543.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.48</td>\n",
       "      <td>33658.0</td>\n",
       "      <td>21131.0</td>\n",
       "      <td>0.1262</td>\n",
       "      <td>0.4050</td>\n",
       "      <td>1.0</td>\n",
       "      <td>23130.27</td>\n",
       "      <td>0.04</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>9955.2</td>\n",
       "      <td>0.21</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>15619304.0</td>\n",
       "      <td>502.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>1.0</td>\n",
       "      <td>42.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>113932.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.0</td>\n",
       "      <td>86608.0</td>\n",
       "      <td>0.0997</td>\n",
       "      <td>0.4239</td>\n",
       "      <td>0.0</td>\n",
       "      <td>19497.81</td>\n",
       "      <td>0.10</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>9123.1</td>\n",
       "      <td>0.00</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>15701354.0</td>\n",
       "      <td>699.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>1.0</td>\n",
       "      <td>39.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>93827.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.21</td>\n",
       "      <td>1431.0</td>\n",
       "      <td>54767.0</td>\n",
       "      <td>0.0932</td>\n",
       "      <td>0.1576</td>\n",
       "      <td>0.0</td>\n",
       "      <td>63760.01</td>\n",
       "      <td>0.08</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5973.3</td>\n",
       "      <td>0.40</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>15737888.0</td>\n",
       "      <td>850.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>1.0</td>\n",
       "      <td>43.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>79084.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.03</td>\n",
       "      <td>40265.0</td>\n",
       "      <td>28374.0</td>\n",
       "      <td>0.1289</td>\n",
       "      <td>0.1568</td>\n",
       "      <td>0.0</td>\n",
       "      <td>14422.97</td>\n",
       "      <td>0.04</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>9834.4</td>\n",
       "      <td>0.13</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   CustomerID  CreditScore  Gender  Married   Age  Dependents  NumBankAccts  \\\n",
       "0  15634602.0        619.0  Female      1.0  42.0         3.0           1.0   \n",
       "1  15647311.0        608.0  Female      1.0  41.0         2.0           1.0   \n",
       "2  15619304.0        502.0  Female      1.0  42.0         2.0           3.0   \n",
       "3  15701354.0        699.0  Female      1.0  39.0         0.0           2.0   \n",
       "4  15737888.0        850.0  Female      1.0  43.0         0.0           1.0   \n",
       "\n",
       "   HasCrCard  EmergingMarketFund  RealEstate  PrivateEquity  GovtBonds  \\\n",
       "0        1.0                 1.0         0.0            1.0        0.0   \n",
       "1        0.0                 1.0         0.0            0.0        1.0   \n",
       "2        1.0                 1.0         0.0            0.0        1.0   \n",
       "3        0.0                 1.0         0.0            0.0        0.0   \n",
       "4        1.0                 1.0         1.0            1.0        0.0   \n",
       "\n",
       "   CorpBonds  ETF Tech  ETF Health  ETF Med  EstimatedSalary  Mortgage  \\\n",
       "0        1.0       1.0         1.0        0         101349.0       1.0   \n",
       "1        0.0       0.0         1.0        1         112543.0       0.0   \n",
       "2        0.0       1.0         1.0        1         113932.0       1.0   \n",
       "3        0.0       1.0         0.0        0          93827.0       0.0   \n",
       "4        0.0       0.0         1.0        0          79084.0       0.0   \n",
       "\n",
       "   Risk Profile     Debt  Net Assets  Portfolio Return  Diversification  \\\n",
       "0          0.16      0.0     75615.0            0.1232           0.3623   \n",
       "1          0.48  33658.0     21131.0            0.1262           0.4050   \n",
       "2          0.13      0.0     86608.0            0.0997           0.4239   \n",
       "3          0.21   1431.0     54767.0            0.0932           0.1576   \n",
       "4          0.03  40265.0     28374.0            0.1289           0.1568   \n",
       "\n",
       "   BusinessOwner   Revenue  Margin  LifeInsurance  NumTransactions  \\\n",
       "0            0.0  65424.71    0.08            1.0              5.0   \n",
       "1            1.0  23130.27    0.04            1.0              8.0   \n",
       "2            0.0  19497.81    0.10            0.0              3.0   \n",
       "3            0.0  63760.01    0.08            0.0              5.0   \n",
       "4            0.0  14422.97    0.04            1.0              2.0   \n",
       "\n",
       "   LastTransactionAmt  ForeignAssets  NumProducts  \n",
       "0              2095.3           0.39          4.0  \n",
       "1              9955.2           0.21          1.0  \n",
       "2              9123.1           0.00          5.0  \n",
       "3              5973.3           0.40          5.0  \n",
       "4              9834.4           0.13          4.0  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bankcx_data = pd.read_csv('Bank_Customers.csv', sep=\",\", header=0, index_col=None)\n",
    "pd.set_option(\"display.max_columns\", None)\n",
    "bankcx_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1fe41c25",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 10001 entries, 0 to 10000\n",
      "Data columns (total 31 columns):\n",
      " #   Column              Non-Null Count  Dtype  \n",
      "---  ------              --------------  -----  \n",
      " 0   CustomerID          10000 non-null  float64\n",
      " 1   CreditScore         10000 non-null  float64\n",
      " 2   Gender              10000 non-null  object \n",
      " 3   Married             10000 non-null  float64\n",
      " 4   Age                 10000 non-null  float64\n",
      " 5   Dependents          10000 non-null  float64\n",
      " 6   NumBankAccts        10000 non-null  float64\n",
      " 7   HasCrCard           10000 non-null  float64\n",
      " 8   EmergingMarketFund  10000 non-null  float64\n",
      " 9   RealEstate          10000 non-null  float64\n",
      " 10  PrivateEquity       10000 non-null  float64\n",
      " 11  GovtBonds           10000 non-null  float64\n",
      " 12  CorpBonds           10000 non-null  float64\n",
      " 13  ETF Tech            10000 non-null  float64\n",
      " 14  ETF Health          10000 non-null  float64\n",
      " 15  ETF Med             10001 non-null  int64  \n",
      " 16  EstimatedSalary     10000 non-null  float64\n",
      " 17  Mortgage            10000 non-null  float64\n",
      " 18  Risk Profile        10000 non-null  float64\n",
      " 19  Debt                10000 non-null  float64\n",
      " 20  Net Assets          10000 non-null  float64\n",
      " 21  Portfolio Return    10000 non-null  float64\n",
      " 22  Diversification     10000 non-null  float64\n",
      " 23  BusinessOwner       10000 non-null  float64\n",
      " 24  Revenue             10000 non-null  float64\n",
      " 25  Margin              10000 non-null  float64\n",
      " 26  LifeInsurance       10000 non-null  float64\n",
      " 27  NumTransactions     10000 non-null  float64\n",
      " 28  LastTransactionAmt  10000 non-null  float64\n",
      " 29  ForeignAssets       10000 non-null  float64\n",
      " 30  NumProducts         10000 non-null  float64\n",
      "dtypes: float64(29), int64(1), object(1)\n",
      "memory usage: 2.4+ MB\n"
     ]
    }
   ],
   "source": [
    "bankcx_data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "9248d9ff",
   "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>Net Assets</th>\n",
       "      <th>EstimatedSalary</th>\n",
       "      <th>CreditScore</th>\n",
       "      <th>Debt</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>Mortgage</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Married</th>\n",
       "      <th>HasCrCard</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>75615.0</td>\n",
       "      <td>101349.0</td>\n",
       "      <td>619.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>21131.0</td>\n",
       "      <td>112543.0</td>\n",
       "      <td>608.0</td>\n",
       "      <td>33658.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>86608.0</td>\n",
       "      <td>113932.0</td>\n",
       "      <td>502.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>54767.0</td>\n",
       "      <td>93827.0</td>\n",
       "      <td>699.0</td>\n",
       "      <td>1431.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>28374.0</td>\n",
       "      <td>79084.0</td>\n",
       "      <td>850.0</td>\n",
       "      <td>40265.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Net Assets  EstimatedSalary  CreditScore     Debt  Dependents  Mortgage  \\\n",
       "0     75615.0         101349.0        619.0      0.0         3.0       1.0   \n",
       "1     21131.0         112543.0        608.0  33658.0         2.0       0.0   \n",
       "2     86608.0         113932.0        502.0      0.0         2.0       1.0   \n",
       "3     54767.0          93827.0        699.0   1431.0         0.0       0.0   \n",
       "4     28374.0          79084.0        850.0  40265.0         0.0       0.0   \n",
       "\n",
       "   Gender  Married  HasCrCard  \n",
       "0  Female      1.0        1.0  \n",
       "1  Female      1.0        0.0  \n",
       "2  Female      1.0        1.0  \n",
       "3  Female      1.0        0.0  \n",
       "4  Female      1.0        1.0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# remove na from data\n",
    "bankcx_data.dropna(inplace=True)\n",
    "\n",
    "# select columns to work with\n",
    "select_cols = ['Net Assets', 'EstimatedSalary', 'CreditScore', 'Debt', 'Dependents',  \n",
    "               'Mortgage',  'Gender', 'Married', 'HasCrCard']\n",
    "df = bankcx_data[select_cols]\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a6de6181",
   "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>Net Assets</th>\n",
       "      <th>EstimatedSalary</th>\n",
       "      <th>CreditScore</th>\n",
       "      <th>Debt</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>Gender_Female</th>\n",
       "      <th>Gender_Male</th>\n",
       "      <th>Married_0.0</th>\n",
       "      <th>Married_1.0</th>\n",
       "      <th>HasCrCard_0.0</th>\n",
       "      <th>HasCrCard_1.0</th>\n",
       "      <th>Mortgage_0.0</th>\n",
       "      <th>Mortgage_1.0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>75615.0</td>\n",
       "      <td>101349.0</td>\n",
       "      <td>619.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>21131.0</td>\n",
       "      <td>112543.0</td>\n",
       "      <td>608.0</td>\n",
       "      <td>33658.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>86608.0</td>\n",
       "      <td>113932.0</td>\n",
       "      <td>502.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>54767.0</td>\n",
       "      <td>93827.0</td>\n",
       "      <td>699.0</td>\n",
       "      <td>1431.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>28374.0</td>\n",
       "      <td>79084.0</td>\n",
       "      <td>850.0</td>\n",
       "      <td>40265.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Net Assets  EstimatedSalary  CreditScore     Debt  Dependents  \\\n",
       "0     75615.0         101349.0        619.0      0.0         3.0   \n",
       "1     21131.0         112543.0        608.0  33658.0         2.0   \n",
       "2     86608.0         113932.0        502.0      0.0         2.0   \n",
       "3     54767.0          93827.0        699.0   1431.0         0.0   \n",
       "4     28374.0          79084.0        850.0  40265.0         0.0   \n",
       "\n",
       "   Gender_Female  Gender_Male  Married_0.0  Married_1.0  HasCrCard_0.0  \\\n",
       "0            1.0          0.0          0.0          1.0            0.0   \n",
       "1            1.0          0.0          0.0          1.0            1.0   \n",
       "2            1.0          0.0          0.0          1.0            0.0   \n",
       "3            1.0          0.0          0.0          1.0            1.0   \n",
       "4            1.0          0.0          0.0          1.0            0.0   \n",
       "\n",
       "   HasCrCard_1.0  Mortgage_0.0  Mortgage_1.0  \n",
       "0            1.0           0.0           1.0  \n",
       "1            0.0           1.0           0.0  \n",
       "2            1.0           0.0           1.0  \n",
       "3            0.0           1.0           0.0  \n",
       "4            1.0           1.0           0.0  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# obtain a list of categorical columns\n",
    "cat_cols = ['Gender', 'Married', 'HasCrCard','Mortgage']\n",
    "\n",
    "# transform all categorical columns using one hot encoder including primary key\n",
    "ohe = OneHotEncoder()\n",
    "cat_data = ohe.fit_transform(df[cat_cols]).toarray() # do not include primary key\n",
    "cat_data = pd.DataFrame(cat_data, columns=ohe.get_feature_names_out(cat_cols))\n",
    "cat_data.index = df.index\n",
    "\n",
    "# drop original categorical columns and combine the numeric features with the transformed ones instead\n",
    "df_transformed = pd.concat([df.drop(cat_cols, axis=1), cat_data], axis=1)\n",
    "df_transformed.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9b2ccd8e",
   "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>Net Assets</th>\n",
       "      <th>EstimatedSalary</th>\n",
       "      <th>CreditScore</th>\n",
       "      <th>Debt</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>Gender_Female</th>\n",
       "      <th>Gender_Male</th>\n",
       "      <th>Married_0.0</th>\n",
       "      <th>Married_1.0</th>\n",
       "      <th>HasCrCard_0.0</th>\n",
       "      <th>HasCrCard_1.0</th>\n",
       "      <th>Mortgage_0.0</th>\n",
       "      <th>Mortgage_1.0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Net Assets</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.000231</td>\n",
       "      <td>0.007089</td>\n",
       "      <td>0.011798</td>\n",
       "      <td>0.016954</td>\n",
       "      <td>0.002194</td>\n",
       "      <td>-0.002194</td>\n",
       "      <td>0.003811</td>\n",
       "      <td>-0.003811</td>\n",
       "      <td>-0.000522</td>\n",
       "      <td>0.000522</td>\n",
       "      <td>0.003818</td>\n",
       "      <td>-0.003818</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>EstimatedSalary</th>\n",
       "      <td>-0.000231</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.001384</td>\n",
       "      <td>0.006228</td>\n",
       "      <td>0.751885</td>\n",
       "      <td>0.008081</td>\n",
       "      <td>-0.008081</td>\n",
       "      <td>-0.789411</td>\n",
       "      <td>0.789411</td>\n",
       "      <td>0.009912</td>\n",
       "      <td>-0.009912</td>\n",
       "      <td>-0.012166</td>\n",
       "      <td>0.012166</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CreditScore</th>\n",
       "      <td>0.007089</td>\n",
       "      <td>-0.001384</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.010247</td>\n",
       "      <td>-0.005009</td>\n",
       "      <td>0.002857</td>\n",
       "      <td>-0.002857</td>\n",
       "      <td>0.007989</td>\n",
       "      <td>-0.007989</td>\n",
       "      <td>0.005458</td>\n",
       "      <td>-0.005458</td>\n",
       "      <td>0.027094</td>\n",
       "      <td>-0.027094</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Debt</th>\n",
       "      <td>0.011798</td>\n",
       "      <td>0.006228</td>\n",
       "      <td>-0.010247</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.015529</td>\n",
       "      <td>-0.003869</td>\n",
       "      <td>0.003869</td>\n",
       "      <td>0.000155</td>\n",
       "      <td>-0.000155</td>\n",
       "      <td>-0.009788</td>\n",
       "      <td>0.009788</td>\n",
       "      <td>-0.004460</td>\n",
       "      <td>0.004460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Dependents</th>\n",
       "      <td>0.016954</td>\n",
       "      <td>0.751885</td>\n",
       "      <td>-0.005009</td>\n",
       "      <td>0.015529</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.017204</td>\n",
       "      <td>-0.017204</td>\n",
       "      <td>-0.565735</td>\n",
       "      <td>0.565735</td>\n",
       "      <td>0.004661</td>\n",
       "      <td>-0.004661</td>\n",
       "      <td>-0.012344</td>\n",
       "      <td>0.012344</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gender_Female</th>\n",
       "      <td>0.002194</td>\n",
       "      <td>0.008081</td>\n",
       "      <td>0.002857</td>\n",
       "      <td>-0.003869</td>\n",
       "      <td>0.017204</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-0.009759</td>\n",
       "      <td>0.009759</td>\n",
       "      <td>0.005766</td>\n",
       "      <td>-0.005766</td>\n",
       "      <td>-0.106512</td>\n",
       "      <td>0.106512</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gender_Male</th>\n",
       "      <td>-0.002194</td>\n",
       "      <td>-0.008081</td>\n",
       "      <td>-0.002857</td>\n",
       "      <td>0.003869</td>\n",
       "      <td>-0.017204</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.009759</td>\n",
       "      <td>-0.009759</td>\n",
       "      <td>-0.005766</td>\n",
       "      <td>0.005766</td>\n",
       "      <td>0.106512</td>\n",
       "      <td>-0.106512</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Married_0.0</th>\n",
       "      <td>0.003811</td>\n",
       "      <td>-0.789411</td>\n",
       "      <td>0.007989</td>\n",
       "      <td>0.000155</td>\n",
       "      <td>-0.565735</td>\n",
       "      <td>-0.009759</td>\n",
       "      <td>0.009759</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-0.012501</td>\n",
       "      <td>0.012501</td>\n",
       "      <td>0.009874</td>\n",
       "      <td>-0.009874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Married_1.0</th>\n",
       "      <td>-0.003811</td>\n",
       "      <td>0.789411</td>\n",
       "      <td>-0.007989</td>\n",
       "      <td>-0.000155</td>\n",
       "      <td>0.565735</td>\n",
       "      <td>0.009759</td>\n",
       "      <td>-0.009759</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.012501</td>\n",
       "      <td>-0.012501</td>\n",
       "      <td>-0.009874</td>\n",
       "      <td>0.009874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HasCrCard_0.0</th>\n",
       "      <td>-0.000522</td>\n",
       "      <td>0.009912</td>\n",
       "      <td>0.005458</td>\n",
       "      <td>-0.009788</td>\n",
       "      <td>0.004661</td>\n",
       "      <td>0.005766</td>\n",
       "      <td>-0.005766</td>\n",
       "      <td>-0.012501</td>\n",
       "      <td>0.012501</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-0.007138</td>\n",
       "      <td>0.007138</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HasCrCard_1.0</th>\n",
       "      <td>0.000522</td>\n",
       "      <td>-0.009912</td>\n",
       "      <td>-0.005458</td>\n",
       "      <td>0.009788</td>\n",
       "      <td>-0.004661</td>\n",
       "      <td>-0.005766</td>\n",
       "      <td>0.005766</td>\n",
       "      <td>0.012501</td>\n",
       "      <td>-0.012501</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.007138</td>\n",
       "      <td>-0.007138</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mortgage_0.0</th>\n",
       "      <td>0.003818</td>\n",
       "      <td>-0.012166</td>\n",
       "      <td>0.027094</td>\n",
       "      <td>-0.004460</td>\n",
       "      <td>-0.012344</td>\n",
       "      <td>-0.106512</td>\n",
       "      <td>0.106512</td>\n",
       "      <td>0.009874</td>\n",
       "      <td>-0.009874</td>\n",
       "      <td>-0.007138</td>\n",
       "      <td>0.007138</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mortgage_1.0</th>\n",
       "      <td>-0.003818</td>\n",
       "      <td>0.012166</td>\n",
       "      <td>-0.027094</td>\n",
       "      <td>0.004460</td>\n",
       "      <td>0.012344</td>\n",
       "      <td>0.106512</td>\n",
       "      <td>-0.106512</td>\n",
       "      <td>-0.009874</td>\n",
       "      <td>0.009874</td>\n",
       "      <td>0.007138</td>\n",
       "      <td>-0.007138</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 Net Assets  EstimatedSalary  CreditScore      Debt  \\\n",
       "Net Assets         1.000000        -0.000231     0.007089  0.011798   \n",
       "EstimatedSalary   -0.000231         1.000000    -0.001384  0.006228   \n",
       "CreditScore        0.007089        -0.001384     1.000000 -0.010247   \n",
       "Debt               0.011798         0.006228    -0.010247  1.000000   \n",
       "Dependents         0.016954         0.751885    -0.005009  0.015529   \n",
       "Gender_Female      0.002194         0.008081     0.002857 -0.003869   \n",
       "Gender_Male       -0.002194        -0.008081    -0.002857  0.003869   \n",
       "Married_0.0        0.003811        -0.789411     0.007989  0.000155   \n",
       "Married_1.0       -0.003811         0.789411    -0.007989 -0.000155   \n",
       "HasCrCard_0.0     -0.000522         0.009912     0.005458 -0.009788   \n",
       "HasCrCard_1.0      0.000522        -0.009912    -0.005458  0.009788   \n",
       "Mortgage_0.0       0.003818        -0.012166     0.027094 -0.004460   \n",
       "Mortgage_1.0      -0.003818         0.012166    -0.027094  0.004460   \n",
       "\n",
       "                 Dependents  Gender_Female  Gender_Male  Married_0.0  \\\n",
       "Net Assets         0.016954       0.002194    -0.002194     0.003811   \n",
       "EstimatedSalary    0.751885       0.008081    -0.008081    -0.789411   \n",
       "CreditScore       -0.005009       0.002857    -0.002857     0.007989   \n",
       "Debt               0.015529      -0.003869     0.003869     0.000155   \n",
       "Dependents         1.000000       0.017204    -0.017204    -0.565735   \n",
       "Gender_Female      0.017204       1.000000    -1.000000    -0.009759   \n",
       "Gender_Male       -0.017204      -1.000000     1.000000     0.009759   \n",
       "Married_0.0       -0.565735      -0.009759     0.009759     1.000000   \n",
       "Married_1.0        0.565735       0.009759    -0.009759    -1.000000   \n",
       "HasCrCard_0.0      0.004661       0.005766    -0.005766    -0.012501   \n",
       "HasCrCard_1.0     -0.004661      -0.005766     0.005766     0.012501   \n",
       "Mortgage_0.0      -0.012344      -0.106512     0.106512     0.009874   \n",
       "Mortgage_1.0       0.012344       0.106512    -0.106512    -0.009874   \n",
       "\n",
       "                 Married_1.0  HasCrCard_0.0  HasCrCard_1.0  Mortgage_0.0  \\\n",
       "Net Assets         -0.003811      -0.000522       0.000522      0.003818   \n",
       "EstimatedSalary     0.789411       0.009912      -0.009912     -0.012166   \n",
       "CreditScore        -0.007989       0.005458      -0.005458      0.027094   \n",
       "Debt               -0.000155      -0.009788       0.009788     -0.004460   \n",
       "Dependents          0.565735       0.004661      -0.004661     -0.012344   \n",
       "Gender_Female       0.009759       0.005766      -0.005766     -0.106512   \n",
       "Gender_Male        -0.009759      -0.005766       0.005766      0.106512   \n",
       "Married_0.0        -1.000000      -0.012501       0.012501      0.009874   \n",
       "Married_1.0         1.000000       0.012501      -0.012501     -0.009874   \n",
       "HasCrCard_0.0       0.012501       1.000000      -1.000000     -0.007138   \n",
       "HasCrCard_1.0      -0.012501      -1.000000       1.000000      0.007138   \n",
       "Mortgage_0.0       -0.009874      -0.007138       0.007138      1.000000   \n",
       "Mortgage_1.0        0.009874       0.007138      -0.007138     -1.000000   \n",
       "\n",
       "                 Mortgage_1.0  \n",
       "Net Assets          -0.003818  \n",
       "EstimatedSalary      0.012166  \n",
       "CreditScore         -0.027094  \n",
       "Debt                 0.004460  \n",
       "Dependents           0.012344  \n",
       "Gender_Female        0.106512  \n",
       "Gender_Male         -0.106512  \n",
       "Married_0.0         -0.009874  \n",
       "Married_1.0          0.009874  \n",
       "HasCrCard_0.0        0.007138  \n",
       "HasCrCard_1.0       -0.007138  \n",
       "Mortgage_0.0        -1.000000  \n",
       "Mortgage_1.0         1.000000  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_transformed.corr()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4ddfa338",
   "metadata": {},
   "source": [
    "### B. Data Modelling\n",
    "\n",
    "Now we can use the `.fit` framework of sklearn to implement the [K-Means](https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html) clustering algorithm in this data. This framework will train the model using the provided data and then obtain subsequent predictions. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "2b6b8d0c",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df_transformed\n",
    "\n",
    "kmeans = KMeans(n_clusters=4, init='random', random_state=0)\n",
    "kmeans.fit(X)\n",
    "y_pred = kmeans.predict(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "257a7489",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 2, 3])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.unique(y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "47ed726d",
   "metadata": {},
   "source": [
    "The parameter `n_cluster` takes the value of the number of clusters we wish to have. Here we have asked the data to be grouped into two clusters. The parameter `init` refers to the method to be used for initialization. We also specify the `random_state` parameter to replicate the result during future runs. We also have a choice of selecting either Lloyd's or Elkan's algorithm. \n",
    "\n",
    "The `KMeans` object has attributes such as `cluster_centers_`, `labels_`, `inertia_` and `n_iter`. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "32522381",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 5.88120898e+04,  1.75578497e+05,  6.51800410e+02,\n",
       "         1.81307357e+04,  3.51311475e+00,  4.51229508e-01,\n",
       "         5.48770492e-01,  4.99600361e-16,  1.00000000e+00,\n",
       "         2.99590164e-01,  7.00409836e-01,  7.86475410e-01,\n",
       "         2.13524590e-01],\n",
       "       [ 6.21337705e+04,  1.25702812e+05,  6.48426629e+02,\n",
       "         1.86848800e+04,  3.49140344e+00,  4.77808876e-01,\n",
       "         5.22191124e-01,  6.10622664e-16,  1.00000000e+00,\n",
       "         3.00679728e-01,  6.99320272e-01,  7.95281887e-01,\n",
       "         2.04718113e-01],\n",
       "       [ 6.06198909e+04,  2.54666924e+04,  6.53045945e+02,\n",
       "         1.82707020e+04,  4.94206952e-01,  4.50659209e-01,\n",
       "         5.49340791e-01,  1.00000000e+00, -2.77555756e-15,\n",
       "         2.87654814e-01,  7.12345186e-01,  7.99840192e-01,\n",
       "         2.00159808e-01],\n",
       "       [ 5.78799636e+04,  7.60504765e+04,  6.48906886e+02,\n",
       "         1.75436948e+04,  6.20109546e-01,  4.37793427e-01,\n",
       "         5.62206573e-01,  1.79186228e-01,  8.20813772e-01,\n",
       "         2.90297340e-01,  7.09702660e-01,  8.03208138e-01,\n",
       "         1.96791862e-01]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "centers = kmeans.cluster_centers_\n",
    "centers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "59721475",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, ..., 2, 3, 2])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kmeans.labels_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "a0d35968",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9572086199393.164"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kmeans.inertia_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "9b197323",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x2d212e76108>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# relationship between Net Asset and Estimated Salary among different clusters\n",
    "plt.scatter(X.iloc[:, 0], X.iloc[:, 1], c=y_pred, s=50, cmap='viridis')\n",
    "plt.scatter(centers[:, 0], centers[:, 1], c='black', s=200, alpha=0.5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "bb289887",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x2d224f88c48>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXsAAAD4CAYAAAANbUbJAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOy9d5hdVb3//1q7nH6m95lMJr0XQjqhhV6kIyggRVDBgoIKKIJiQUW5YqWIIkqv0msIIZDee51kei+nn93W7489mXomcO/lPt8f9+b9PIE5++yz99prr/Ven/WpQkrJERzBERzBEfzvhvL/ugFHcARHcARH8D+PI2R/BEdwBEfwfwBHyP4IjuAIjuD/AI6Q/REcwREcwf8BHCH7IziCIziC/wPQ/l83AKCgoEBWVVX9v27GERzBERzBZwrr1q1rk1IWfpJz/39B9lVVVaxdu/b/dTOO4AiO4Ag+UxBCHPyk5x5R4xzBERzBEfwfwBGyP4IjOIIj+D+AI2R/BEdwBEfwfwBHyP4IjuAIjuD/AP5/YaD9r8Kxu9jXdDsYq9GFxeaOQv65cjqJoIISj2I9F0XsMwnneDCmFBEtzSfp6KRU0Pzd+LY14xRr2LOCKLYge4dCvn80UV0nPyfIJcfP5KSjxlG95SBP3/MSm1fsIqErOEcVMGpuF2Mn17FsaYjuFwycoIZ5Vi7qJC9+YaLsimOsMHA2pJAxG/wKQhc4YQ1ZGSCrQSHH1imsyKe+oZ3OjihKRQ4LLwtxzefeJC8QYf8eH/94ezRj5kmErRPwqtSvHM17j7ZixdKo2X6cMkHinCycKg8ex8/49gQz96xl41saCBi92KJVy+Gco+oYOyEBSjlLXp7Hs/ftJpFMIXWwynwIqZNvRDnn6laOOTuGN+QjHCwh7I2CGkb4L6WxcR7P3vs6m5ZuJ5QbZNGXF7JtRowPO3YRtw0EENJ8zAqNoWNLF9tb92EWS9S4jX9ZBLnbQr+4GO9sD2FflBP89RRFdSaUwKjCdoTioa3b4L0nFN5/NhfHCbHoLJtzrmoku6iEGnEx/6xtZ0vnTnLUCCeGGji41GbJ7/w4EdCriplz3UnYXpVlW/aTNiwCnRH8WV0UTU9xxeIGTszejxCpnhGkI5Uiqncfxe/uV9k1SSAn+Ahn+4gmoyRNgd4mKNocoW2jByaXI3QVbWMdyu5WHCkRxWGKF0/GrOug9cM92CqofoEuwcz2kJhUii9lEdrdRCqZRJulM+vcBOEVSbZ0TGTvKWAXa2BKCrZ18o3Re8j3KjzybjE7xhZgFHiQCY0TC1q4cuYWdM3hg44ynt95FAmvDyu7Gw8mpZ4ElQ6wO5+ttSp+j0HV+BbW5OQQxc8E1cMFbeuZMrYOQ9HZ1FhMWUkXU7JbaejM5tHlR7G1vhiPR1CU5+PmU3ZT5NlOS63D26+P5l0xiyaPgqopHD97FLeefipZfj8Ar2zewv073qFD78aveDk6lseGD9voigq0thghJ01WIAcxqpX2xR7SukZQmIxIJNgRz8UKCMb6LH57tEBPreHZtcU8u2ESXXEfeUYn1y3YzDGzO/EHKlDVL/DUfRHe27aJ9pM9aGODTCst5IYREYLGG0S6I7z/chavPFJAOuZjZFkJCEEimqT0KIvW3Y2kIzbl0yWJaROx8+Zz2UlHs2DyyIwcs3LHQf6+dBV7PTXY3e2Ip1thXxon6MGYmMf0sMGdt6coLD1Ai6nyTMsoVq4oYWKsCO+YEO9lV2N82ELwpTayu5NMnhHnnGsjNDRrPHFvPvX7vHhKdS7/7ll8/sufR9P/5yhZ/P8hEdrs2bPlf9Ybx7FaqK77HCV6BL9qA2BJMB2V256fyfbv22BIRM/jSU0hNbGYxDGj0JoihFbtJn5vOdKvgLdng5OWSEPFXpYLloLXozE6btD++FqstDXwWhMKSSyoIvDRftTcJMmbi0EXoArUrUmCP6ofeH9AMPTv/pACUBXss0fz8F3v8HpkBO+/NYm6jmwAzBQ4JoTf2IneHMU4I0zyK0XufRWBaDcJf7sWNWbhpN07eHw22fk2v39lN1l5NrddOoZdG/2kk2pvWwAKSgzuf2c3voCDx+celRJET0O3rcnlB1+sxDRUbNPtb7tSJ/bbERBQ+k7svagEG9B6jqcdUAU4Ejxuf/uExUhflPvHvodfdYhHFL55xjjamvTe9uleh0DI5sv/7uLu6FxMqWD3bEh9isV0Xysnd+zn/i8VYqUEEoXuS49CpCzCr21HmDZIyC02ueibLZx/WSuaIgc0d1c0i6/sX0zaUpCKAg4ItedRbBAOaCvDGJ063jX1+Dc1gOUggGkLYnz5h42Mn5ng+QcLeeTuEixTAMLtBgEoIOxDYwfQBck/VGCWet2Dom9khF5px7YVkqflgK9nXNoSDYfbqtZxVn4NaUch4WhcvfMkGs0gQkBRIk3X+0UYlorluI336SaVRZ3Y8yM8MPF9/MLCqzq97xZg+Z6R3PbsKZiWgi3d3/l1kxMm7OeuC5YgBCTSGu/vruTO1cdBgQmWQGv38/rNX+fed97hTXUVUpEgwFkeRjbroPd0oO2A4xCe20iy0jto5EvG+zpRkfxh3AcIR/Ktf36OXU0FSCmoKugkZam0HVA5U12JmjKYMDPJqpwK3ikZAx5Blm7yt/Hvkq+lenkgnRLEIyrfOGscbY0ehANF40266xTSCbddquag6TD7Zi9vdS/gkhNmcuP5x/afjvzhxeU8vmoN1oI29Pe7CfyxBayBnGJOLeTLP2zk8mO2AJBMKKz7IMTtz88gdXUB/j+3oi+PIVLujxTVQffArX86yKzjotx51Sg2Lg8jNRg7t4w/vvfb/xThCyHWSSlnf6JzP6tk39x4OSFnXe8L7o/uDpVLp0/BcQZSqtQUuj83hfBbu0h9Nx9rdgDUQZosC5yDfpytITBt8h5dg7CcIfeQmkLk7ClYRX6009rB33MdRxL+UjVKx9B2IWQPox8ejlel4AcjkbZGdWsuds/k7YVhk/3qRuIPVPQtVID/l43oH8Z6ieUQVM3h5Is6mXh0gvvvKOsl0v4oKDH4x+odaBnGmZRwxZxJtDZ4BhyP/bwce7rfJfFPgv6rRw+8wuLLJTv4UvEu7r+zjJf/kY9lDHwnQneIPzka069nuiheYWOZAvXFCN5H2rBKstDaE4i0RVauxffuq2Hmoige75DbA5B2FC7deRqNRhDpgBis3JRQLBL8ufIDOvY4vPhQActfy2beyVF+8MABfH5Je5PGlQsmYaY/XjPqBBWij43qXfR6n7PTIvCTBuK/GvheD8GDzWvTXiakWliOYHWsiJv2uwRV+IGHxo4sBosRPt3kihPWc+389UOGumEpnPKbq4invUPu5ddNfnvp68wdXU+z4efa3YtpT/twVIF0AAeyurLp7khDUCKK08gWD87KEKgDx5coTqPO7x7SNheSH41Ywxl5NTy3dgq/f3s+VyzcyOULN+E4Ak3YNB/U+fWNlezdFMAbsEnpOrHfjMAp9/Dd8g2ck78fjzKQx2wLVr6dxV1fHgVC4vE5GBnGfV6xSfzKmbQn8nn0li8wrrwAgH0NbVz+yycw57UiPGmyr6hGGEO5UqoKiQsn8cJPX6QwnACgKeLjgt1nIranCP64oZfoB/RvyObpzdtIxBS+MLOHqzzwnT9+jTOvPSlDP2XGf4bsP5M6eykdEuntGYkeQNMlU+fFh35hO/g21gM21qzgUKIH0ECMcLf5nprO4bnZdvDubEYUmwMOq3vSiOTQxcFtuMAXyNzmAXBAbUhS15GNImBKWTNji9rplcMVSJ5X0ieWA9gS/aOhRA9gWwrvvZjLK//Iz0j0ANFulYbqoZPe/b37/YBHCSjYUz8Z0YsmE3VHEhEd2i9pqfFC+2gA3n46dwjRA5iTgthDGLj36qSlhq2pGGdnk/5qIXpDBGHZKKrkN69UM+v4GF5fZqJ3ryA5NafG/TvTbQR0CQ8iaDNtXpzv3lfDd35byzd/WYvP776E91/O+bhu6IW1IOjuegZBXx7DOCmrbzc0CNKSvN9dDoCmSGaHWvEpFqGkRUckQCYyTZk6r6+dgJLhkqv3VwzbxqSp8cL6yQD88MA8OiwvTs+7FgoIDSI53cguHWdDCPuNfJwdgSFED+CZGMvYNheCF9pHowh4ds0Urlq0gSsWbiLgsQj5THxeh5Hj09zzzD6KR6RdyTziELirAaTkjLyDQ4geQNVg7klRdI875jIRPUAipjAvsAvTsnl5xbbe4y+v3IGlmogcC8/q+PDttx30nW28vW1s76GPjDI01cHzejekMwvTAlj3fhjdK5k8p4erDHjhT/8epp/++/iM6uxtdDEMofYgmD10NgkJStJE+pSefewwL1BzX5BIWwMJddC1RNIEjxywZIq4ja46WP2uLTVXfSEcyC2yaDyQeeD1h+FoXDp3M1cfuwEpQREQS+vc9dKJrNxXiVPgBa1fH1gSDtMlRkoQ6x7+vqoG0a7M39tSIYVG/86Q/h6VzLCTGJRGA/8vm1APGkhNIEyJeWyI5DeLBkiuCdsdhqlEZkKXQeWQUuTw8CkYp2XheawdJQmTb8unsGwHun7433oUSbZmHPYcTUiitgdI4A9KTjyva8D3iYiKmf5kOxwZVCFDV4uYg1OsDbuA2kIQs/t2NxIIKBY4CqbqkLYy36+uM5uz/uMK7jj3PeaPqes9Hk15kcNKM4KuuI+GdIDdydxe1dmAMzQQo1LIRp97IDbMtTyHn6sRy90xmo7CZQs249OHPojucbjoa6386YcV7jxutVD2G/hmHl548vgkljn86FEV8FgGjpR0RhO9x7tiSWzFQZXue3HH+lAIwEnYRJN9u96YrWMJBS1i96p8BsOREIuoSAmhflwV7cwgpH5K+ExK9kLopGUYw8ncfF2X7NnkH3JcegTWIj9KxHJf4DCQ3S75WMXh4V+WpmBW5CDbB85ae4wXerZ75jEhog+NJPLCGCIvjCV5WzGTTktSVD6UWPrfRjgOx89r4MvHrSfoNQn5TAJek6KsBPd8/k0mFzehVJtg9vuVV0EWDr92V45PM21+HEXN/NyWIaiamMr43bZYLnJQk0WnjUgdZhInbILfqUPdm0YYEiXhIEyJvjxG8Af1KPvSICUCydRgOwBjpiQzXkrdk8bJtAvLgKDP4rzfRDGOr2TWtDaCXvNjfxO3NTbF3e27HOaRbCkY6Yv2ftY9ElXr6/8JsxL4g4cntUNQd6YyLszWRB/ajiQMszNUhWRKoKP3c8zW6bS8dHp1LPtwAoSgJRriu0+dzo6Ggt6jUyuasYeZQ17NZM7oOlpMP3qm7eKhKw/eqWYgRaPGjxz2EpK54WYATpu6B8vOvGDoHjj6hL7+l4pAaTPZl8watm1dbSrxiIJQQNEy92l2gYl/pIdRhUnmTKzsPT57fAU+xwuOwJ7gG5YpHU1BqQwybURz77EJegeq5WDNDCA9mZ/HsQUTj0qgeyS7NwXcZxIw84Rpwz7PfxefSbIHqMi/HiuDVJJyFD5cmUtry0D9shQg/QrmF8KYJ4bxPNEOGchKWiB3BAGw84OYRSHkoD2wBNAUjDH5qAcNd/IaPYavbI1jzo3gnBUicXMxTrnHldR0gbEwzHvnTsNTPOieHoFTqjHv5Ai/eXUfj+/YzldP34DfM1TC8WoWX128Ft8bzSgNJph9z5C6Mh/pHdonXr/D1bc2csk3WtA9mVevEWNTKOrQ71K2yoPtUzFOCg+4tnDA+1hHxj4E8LwdQaSdIYulMCTqjhS+n7Yi/qJhvZLH3teqeGbNFC7/fjNe/8DrVU1McuF5DXzR3Ea5HuXjIBHMWRjBGF9E3PRiDkMe/ZF0VFZ1F/U0cOj3PmHx+cI9+JQ+xlJUBtiEjj4+SkGpiTqIVDL1tnIgjYjYfVbSHtgz/Kg7U+4iag/6peng12z8wh0TSVvlocbJSAQjg1FuOPtDvjh/E8VZw/dR2lR5YOmc3s8j8iLMGVWHRxs8ziS66nDB0Tuo8MYxZeaFREqQkf4ChsjIKPJAABwx+HEBiYKkwhsjaaucMX0PSgaVzCEk430XF5bEKffwl8apJAfbtIBUQvCPX5fg8UlmnxDBM2jcZ+dZ/PrZvTz43m6uPGkL//rKPzlz3C+QdhsApxw9npDXi9wdwBrjxa7yDOUBAegKuUf7mD+mtvf4VK0d0WBinhR2yX7QmPJ4HaYviFFUbvDha9l0NLu7NcUDX7z14mGf/7+LzyzZe8NfJOn9Ei2Gj6StErU00o7CkrpS7npnOgh3ovX+84JxWhhsSeobRWCB9xDhx233X1LibAghW/q2ytHTJ7kSvCpwPCpSU7Dz/HSfNxXybEIf7SLwq0a0DQkwHETMZuatNqnrCvu8KQ5BFSSExv4pRUgdnICC1AXmohCX/6qd2x44yLSjYhSEDLRhBr2iwIzyRnLMKDk/qaGoLYpH2AQVA+e4EMFrg/iCDoGwTSBs4wvanHlFK7NPjJJXbPKjhw6QnW8ielj4UP/s3ebn6T8WkUoIYhGFeEyh29T5Sc1sNsYLSd1QhHFiGKkLZEBB+gRqUAev29Gy/z8btJUJxDD6SgSkJ5RiluYibY369mzue3sBDx84ka//qo5glk041+SuR/fz+1f3cM0PmrjuqN08PuFtbijdgleYDKdf04XDeF83DoK3to4dVnLta69ANRyKmiPu+0vbYLuLvmJJPMLm/IJ9fK1024DfJ+OCJf/OJZUQve/lnuf2MenoBLrXcXdaqoKd48fxq0h/T795BM4ZYc6pqHZVb/0ZUBEkflZO4KEW1Jq0OzZjtrugOxB1dK7Zs5gV3UX8rXES/64dxS9GruCR8e9y0bSdfP2klTz/zSf49ikfZuwficLGmlJiKQ3TFtgO3H3R2xw77gAe1SLoTeNRTEqzY/z5ipdQdZuAYjLd35ZZjWGDszcw4A7kmAjHBKvfYpZWsD/MhrjiClOmACnxCYspvjZ+d/AonmsdTVFOFGWYrXQqIXj9X/luN2kS3wQFbYTKlng+99bNIOUo2Larg08mBE/cV8TSf+cy74wIZ/xHgjPuTaPlqEjd9b6754W9TJkbR/dIwj4Dr2ajWBuQHV9EShuvrnFeMBuxHpx9AeI/LseaFhjEAwHCl5fzl6texbR9JE2VxloPt3xhLN7vNaDUmMR/UY5TriN8EAjb6B6HOYsj3Prng7z/bi6/vWkEUgFyFX716o+onFie8fk/DXxmvXEOwXHSNHU9SX1bI3dfuJ7oNjnEtfHQZ+kBqatEbxyLU+EhEO5m2p93sCORBxZkJ73UnToNu4cJRNpCqgqhkMWi4t3odpSmoiAb/COQQYkIOCiOpOCAyhX20fjzN7Gtdj0dSY01C8eQcDJ5jwBSouw3EFEbp8pDcU6ap6a8iVf/ZGoAy4QtK0OMnpwkO9+mIR2gNh1CpCQy5qEk1EVkv3vu28UTeaF5NPm1bVTmJ+h+36TxIXuIACuF62HkDTpMnBTDNgWrfzgV2ztINRSzUfemUQo9iBE+DGegVChtkG0a/t80493WkVGj72gK8RPHYYzOH3DcqwtmnyCpkrWMP/ARJ13Q2WsAPYRkQmG/+hVu399NSzrdq0sWOHiEwy+qVrIgq4mTfn010ZSPb538ERfN2Uag3y4pbSqoqsPDNZM48EOD8kln8tGLW2g3o5gVHiInTCIYMimc1sHNo9cyq6gVbz+J3XYganr40i+PZ3JpOzdcuJOyXFcFtaqxiF/9bRGtNR7ssBcn2w9SorVGEcE0oy9qQ89W2JnM5XD2Dr0xhdPu4JToyIJB4ygtYHk+Pzh7A6eMWovfM1BHkjA0fvXasby6aeLQ6/pN7r7AJidvJNlhQXVHDWp7lIDMIxkcRZddSVVJCU9ueY3u3JVE8LInmY10+kmottt0Z2sIeaCfutS2CW7ah39TGx1XL8ygqZKQZaPoFiX19aQfb8Ys9hP/cQmiTCOkGpydd4DrS7eiIVF7BJ5UQlCz18dNF4zFMDVGjY3zq6f3EfX72NsaZmRulNFZrq5bSqje7qWj3cMrWWNZIqrQhUPc0JGGgFc1FhQ28PPrPyTozWDkEEFE9r1YyiLOKr6K9vNnIr0aaA4ix0J0GCg1JopP4c6rPiI79FvmH1ME1kZM8vlgJzxx5+/Yv8mLmRUkNbcIWaqRZ7RTVtxM3liHdJ6XfYksOk0fxGw8HQ5PXnEbFaH8oe35GPxnvHE+owbaPiiKl7K8KynLg5HH/4Ut25YMmUKHPgsDMGyC99fSfel0YjLEaT/ayb2TN2E643hp33e497kP8OxtJbCqBiVhcOxZnXzv9locoeDRLNKOSpe9kW/uPJE2JczM/Cp+dvKl5HgCVG+ZRXHO2ZhVO1hbv2P4RguBM6bH88WRnJxVi/hPLLqaDkcdG+v9XOZNUOZNQBbQo42gCGKWxlu7xmP6TJpzs2jb54OwRcDTAoN18BKEaWN2CbasCCH9SkajHCEVe2YAULBtawhfCRVEroneHgGP6LVfDDgHMEbkDDmeNiXpgxXo21ay+LauIUQP4A84lMVepN04gQpvFBDEbZ1pwXauKt7JhEAXAJcv2MTfl8/m9+8sYFNtKVces4HSnCj1nWGShs68MXVMCHfxdPtIgo+s5PjPL6RhXzO71+zFqEiRmOal1uvntrYF3OFfzfE5jSg90rJjC+64qorU6lbWpyXX3j0en9+m6w8jMfJ92BP9SIJ9enlFYhWHIMvP7s1hlKoU5JvDegcBGMU+RGnm76QqQTU5qWr9EKIHCHgsrlm0fijZKxIqLRKVczkh61VIvc2oYqAkAMGvIILnIXoa9ZuDBrsjRag7kmhmAmuiD4KuusRJC5yl2ZBUQAccV+3k296Ed00bqfEFw/gKCIhoOIage6XEZ4JWnyT8ozpiD44khocnW8ezKlrMVcU7OSrYSsLSeW7JFF55pgRzuoNe7uV3v3mOZ/9YwAsPFWKkFQSFHH9uJ9ff1UAg7DB6SpqnaqfwXkclhlQxpOp62WkSeb7JVCMyYPEf2LlxpLGWNXvzSYzMw+OxmTGqCSEkm2pLSDkhnAoQpoWta9QkXmB++8sgk+jAwsrTiP7c4ZePjMJM+EEq0AbtViFdx+kIRfYZslUgW0XN81ESyBl+MHxK+MyTfX9cdOpstj+8DGc4twRcolEjKZT2NE6On7tfPYGJowxyCr/Cn19+Cm1nM6Hl+xGWQ/noNN/7XQ0+n+TQzNVUG59I8Oi0LSTznqXYn0PDvia+e97tNFW3oOkqhmWS+mcV+IZphI0rghgSkXLI2tCOdvV/f4e1prqMv74/m+uOX8tRVc20yvGkEg7+Xzegr04gdVfXjiKQHukufgC4xkbb6mOf9Pk5wyr5BGCnJWT21ATDwclTUdqtobssAbEFVX1BN4MQT7YhZFuvmikTAr42LGnTbAZ5fcrLGV1wv7BwC+taJ7FhR5CV+ypYtb8CRwo+P2crN56yAiFgbLILK3sS6UQ7S5/8kKcaHiLWFWfb9hru2PUupgIpRyVHMzAd8PU0+QeXjmbvWi/ikIE8LUmlFYwct0PUcUlksYFzwOfqtDt7JPNuHdmtYTd5EaMSKJMTmQnfkQgTV0WWAaqQhIJJNGX4nWBpTnRgXIciIWDjHxdjkXoHMtWFoGeeSANif0A6zYisHwJgfthC1q/2AxKJQFiS9Pk5pL+Uj/CCOqcdz++TWIVZKAkT345mRuW0s+CbEcyZCm/s6aKuM5uMuxdF4KntBHo85LostHUJrLmuraw6lc2dB+chHZBNHpx12eB655ICfvGt0axpyCN6awH2GC8i7vDK652sOj6bm+9po3J+hNc6Rma2NSiQKLcwpII3o0efDkoWm1N1nHNxIzdc/i6OVKBnp3H/e3N4bOVMpKZS3ZrHiLz1ILsB6LZ0rt1h0pKuwDkpgdJqIg94IS4R41PufBrywgXIFO83fchJZccN+z4/DfyvIntd1/B5dRLDkL1dpKG2WK4lP2Hg5PixHJ3HV80g7N+OkTYJrzjQG0R1ztWtaNpQ0lE1CNFKWKsjnfTz7UW309UaQTqSNK46xFrjgQUGon8PO+CVHrTdBs7yVkStibY+wbaFflKXKARCQwef6QgitgdTKpR4kthO5vAAyxYcaMtl3cFytj1RxC2fa+aoBV9Hu/unKOsSCLOHQHrQZ9uWaLpk0ZldfPh6DqbhfmGckgX6MGwvBTKmIjJtgwF0gdpuu+ujwgDPE6mrGOOLMv5MUwTHjK1lXE4U5TDWpI56Bd9d9SRvKOQveVO5vnTrAMI3HIV228P2cXG00hQjutNcULif48YfpCirz7Wt9YCKqJM4Ph3dq1O9pYZpx06ipKqIxCSFu3e+wNRgExMDnagIVu0vo7Hez7YdWb1RxAP7pe9PkWWjTItjv50HA4L7hGsTqPbDmKTrljjYCd6QaOvjWHNDGX3udc1mnrL/sM6onZYXMTKFbPGAIhGVKZRRSRZl17C6w0uOLxdVODzfNoYmI8CUQAcXFrxAoe9q9qzopPvu3b3eVoccF70vdiGDCukL8xBFKtZNPjxPN+F9v5tv/7SWky7oRNFAKE1ctngrV/39Ag625kB/u4lp49vehJLoG4wiKfHsSPWSfS8ccPa4NgFNUcjLCuBNmCyPl5D8YVGvTUyGVVJfKKBhXpifXe/Dk+eBu23IG0r2QoF3YiP4KtuGfHfo/QjfWWTlPcAVl2/D7x34nr924ho64n7e3jKGkuwo6fokHOV+d1/9DBrTfixUhABRZEKRCZbjrnnDxIokHY31zW8dIfv/DKYdNwk7Q7QrgPQK0hfkoG9Ioq1NYOe4ukbbkextaKMrlkR2xN0taQ9GT06hDaN2t5Ck48u5c+nbHPx9PlLJR6kxIKTiFOlgWji1XpR8C8Iu8cl6L/G9fnzdLQRejfRG5G1cHqKh2kvlxBSefj7hhqNQkw5x3e4T+cPYD1i2cRQnTjpAfigxhB8sR+HZNVMAN5Dm169U8dhIH+r6OJgS6VeQWQqi3UZYsh8xCSxTsOKtbPKKTdqbvVgGrgpmOJgS9cM4zhledxvfH7ZERG3MBSE8L3cxWHhSDBvvrhbS4wsHSveOxOfzcPG8BsKym9VLwsw9KYrHO5DSUgnBk9urSNxaApbk6ZaxtFs+vlqyjQpvDEu6qQQKtBSPTXiLp1rH8Ur7SNqLGED0ybjgufsL8dR0kppUQqC6g1BOgGQ8RVdLNycUTuS+/R4WZjXy4c6R/PzlE5AIbAtSF2l4d7YQ/HB/r7eRALR1caw5wT7y7tTAHC4YR+BsCaGVtPe5zDpuQIX/Dy1oO5Ik5gSwBznk+xSLLxbu5rLP7+S9t4s46ZQWPINsPamE4Nm6MXhmJLDpU/dhS5bEKvgwUUraUbBQXFsWgh2JXF5sH83Rjb/A/lE2dmroQi7SEu9TnRjn54IqkHka6a8Ucs4pTZx4eifefmq3sGry8NUvcOvrJ7F2WyWYAhE38K+vw7ejecB1da9GYXERtYrbHkUI0paF9pqFs7IBb1U+l15zMtecMY9XH36bX5xQM9T5wadgj/ISWZQLHT7sxxTk5Roid+hztJgB/to0mWuKd+BVbBTRP4WJjUz8kxODb+DXhy7ofo/F9Seu4fXtY+nMVnj2K4XkproIzwryymszcLo00CViZAplbMIV9rSeRWloALl73Ibt++K9i8b/FP5Xkb0/6OOyn13Ew7c9PsATROrgFGmYp2XjjPPhtPqQAdc1UwioLMzhYFc7CDHAVbBuv5fJc+IZUwioMoUWv4+fz5Usj5Tyk4NzMCb2hWkKr4PiSyObPTjv5dCztIPqQFwdFHot+P7FY7j5P2qYfVIUU1HRFYfVkWLuq5vP3aPXUWAZ/O7tY3hx/RTuv/LfaKpDwGNhWAqOFPzurQXsa+0z8KRiKe649k9o+V66r8nFmhPojdr0vNaF75H2AVGc6aRKS51CTqFJtNOHd2ua1EI1Y4CPNGyCD9VgOAUYZ2S70uehvDcCZIFO6sp81C1JtH3pIb8PfrgfYdmkJpe4M0BRKPbr/OEbOvn+A+CAmRbU7/dQPMIkEHJwbEinFNa+H+bFdRXwOQV6vGvf7RrBu10juLJoB1cV7ySnJ0CqXE1wfelW5oWbuePgHK4r2Y60wTQFr/4znzVLwkiPguPXyS7M4pnfvsz7T69AUQWOI5n3jbk0npTDAy9PJ231W9VUSI8vRJgWwVU1vYd9f2sjeVQIW3dftTxs6gSBjKsEf9kEUmJP9EHCQV8TRyTdsfF9exVPhKbSaATQhMQBLi/azTXFO0hEFVY852f2vBKygq14fSaOA+mkwsE9ZZww7h6WLH2Tmn1xFBVkRQJRlsJSFax+kvahUWihYklY2R0ivHn/sK3WbIe7Ah+yKljBW50jMNOCLxxXgz84dJ+R4zX43efe5OczZ3OgIUDzF7syphwQQnDfd79NJNtkc1cNG17exJrbl6J6BWNPd5hz7F5maK+RbruamkAooyOWlOBszSYxqhAqe8bscgkFJuq8yBCh+p8tE/EIm2tKdvS8jUOwIfF3ig7DjMXZMfwLOvlrZBLWeTn86qk8ErtG4BwaIzbIPQHsJg/qsV1uniXZo1IbZu3fvrqEztOT5IaGxgd9WvhfRfYAs788jwc7liEebUapNcAvME7JJnV5HngV7Aov6RP63Ju8usax8yt5N7YRO+LD8WqolksWL/2tgMUXdA5R5Rxaob09qoNJ/g4kYsiyLTSg2IA8Gzp6BoIAp9yL9IveSQ3QrYW55f7jyX7GpGCMpCG/kM64nwp/mPk3vM7DyyYjpWB3cwFn/+4Kzpi2m6kVLTRHgry8YRL1XQODSyRQW9tM8qfFOIW6myytB8ZZOTj5OsFfNw16LkFni47Xb3JUjcnaYzXMwXH9KQffP9tRbfA/2Ib+TgRjcRbmqVluQrRDUq1XwTw5jFpnDHHBFBICKw/iX1eLWp5FfjDJHb/ewlPfLWTlO3k4dh6KAkZaYe5JEeafEsFIC5a+mMv2tQE8+V2kz84d0N85apprSnbgHaTH9qs2R4VamRropCOqU7/Vw/13lLF/e6D3ZaqKwBfwsvSpjzDTfeqFjX9YhZ2YjGFl0P3qKqkppQTW1fWq/QJtab7rrOfdgrNY0dGMk+1gSaVPiyUlSiwNEpwsD1qejd/rwdgZRT0wNNBuvLeLf4x7l42thai6w9S8Nnz9n8+SfPOSaXzv8TlM8W0mljCJeBbjP2oh1/32eeIpC2lq7hvsDMEBP+qirt4kb5kggdT8AN63IplPsCTrto+mqizGfROWc0vtcRTlDR997FUcbh2xDmUE1K3wc+cFlbTV6K5DgACP38NVP72Uwop80rsb2P2zVax6cjnJqUWk542gyyNZtwnYBLeJFxk10Q8Hxw25j7PXj2z2uAbRQ8TuCGjz4OwMoE5OMNiAdEpu3bDZPg5nPLcR2PkO0hJQadFpjwJr0A8cATEVWedFjOx55we8KJVpNzHeoSB+G5zdAXyGzvrddZw0a+izfVr4X0f2/qRKYo4XuXBkxu+F7QVdRVMVVEXwtbMWUOtpQoxKwEEP8eNHE35zN8J2qN7h56G7yvjKnQ3uwPTKjFuxldHSXk+NIVBAKU/h9JC9IsFeqCP/pkDSJdL48WNIjykAVSEloNkEmt2b1MWSGMpktnUUYvZESSYMD8+tm8pz6w7TEUJgj5M4OdoAogfAp2AtCGKX6KhNQyNME3qAD5WRaMsd5PQEImi7CcJMie8fbXhe7u49V9tvgBrFPCN7iO7ZOC0b7yvdKM0mst9uWvc7nHFHlOUvZtG+qosrflvDrZeMJhFT6ZuN7sxc+VY2K9/KHvhoXW5MBIG++x2T3Yg9TOi/X7G5pmQ7eUGT0EyLq25p4o4rR7n30lUu++LxvPbDpwcQPYCRMumMetzMqJm6WErsLB/eSAxVg8/f0MxJc9oI7X+Dxdk/YsqM8fy24X1WbD+IWttJ8IN9KHH3Ho5Pw5hYSHpndNgMqH94axFbXq9ECIlpq8wY0ciPz3uPkuwYmkeyfW2QLqeLG//ZAdOzEUUGurKB2Ae7kDEd0ZXC0xJFelTM8hyQGs5eP+qEzJHKAAoSZ0EIfVkSMzWwP6QAoySL57ZOw7fThPfgtksNNL0YnMbMfSQg2CMUjSqO8+s3D3DVF6czMpZD5aQKLr75c0xdNImHb3uM53//GkbKAAmebS1o1V10nzsN2ZMA72evnsA9l7+B4hNDUgvJvQGwM7wnRyCqfYw5qoEaI9xrtD055yAjvR8fpDcYpiN4t6scB+F606SGl9axFZy9AZTiFGV2mpbREk24AoDXsYm2BpB7Ash2D/h0NO1/Nuzpfx3Zv3f/EipHdFJfmo01SN8pLVD2+zhuSj4TRo7lc/MnU1GYwx93vYHjcVCP78QqDhLxTiSwohatNcbLTxey3CrjpOujzClqZWqgA32Qp4gpFVeyzwChADEDtT2OJ1/huxd8yJTCRjZ9y8eK17PYsz+LVHMUNT+IXRga8nuPrvK5LVOISYchogmAYePd04LWGsfO9WLMyMdRPIRf24F5VdCVtjNBgj3Tj/qGOfgw0RPH4vh0jHYB7/nAb4MqoQvUDxuGPmmZF92rD90F+BSi/zGCwB+b0Ze5umPdI7npnhq8Acmbm0MEQ7D6nSwSMdX1+ujrucztBndR6fFU0YXN4px6zs47MGy+JCFgarADRYAvIJm+IM60hXE2rwkx49unIWo6ScYyp4ogbUHGbJugegWnnN1CaV6Mky/qpMYp5pR7rsKRAvgIW65mfEUhamM34Td3Dsiemu+Pc8q8Wko+b3Bgh493n8sjEXXHq6ZrRI8dxUazGMPu+836g2V86aELefyaJ/nguTCRLg1zXBhzXhsE3GhlI+ngNAvCb+1Ar+saEPUZO3EcpicHDkP2CNCPzkGO6EbWWL27MukRSJ8g/p0i2OuQ8gswBXc/6WXxDybgJzPZ94emSHKDBj97+lgWjr6u9/hrT3zAM797FbvfYitMByWaIrRkN9GzXFtU2lR59qOpnL+omn+3jsUU/dI1G8OPF+EIHhq9lJtqjmF7Io9jshq4vXL9YaX3TEg6Kt2Wh983zEAaAntFNnR9DIXGFEp8Bq1Sw6mzMACnXEWoCtlZSTrbXUHGdiRzJ1Qe/lr/TfyvIHtbOrzbtIVnDq7k8lF/44/z49xYfzwH4ll9KVklyIM+jFovq/Umvn/WWjzmj/jrbf9ixYsrCMsIqVPDmCfbVM2NMfl7KSJdIVbGSkiGbJ6IObTZPqo/ECx5OhczLVhwWoRzv9zGnFBLxkRdosUk+JsmPLuT6LrEsWFzXZq/LqnCSCk9LjESX0sLvt2tpMcWED9h7ICtg1OWoCuWwt6VO/TBpQRVkB5fhOPrJLBiH4H1daTOyUFvi2KlA71Gv6G/ZYAPvATskJfU9FKkV0PpSiIDOtKnw6GMgcIhNbWU0LJ9Ay7laXewNQXTyeCh4hOYM4Poy1zjqGnAb79TyajJKdJJlfxSg6U7q9C0SMZU0kOarYK5MAiqoNQT58Gx7xFQLYKqlSEcvw+qcPPbqELiDTiceH4nW3YVc9d3L+Jfv3+B9KV5GItCICX6e1G8r0cQSYfAjmZSC0dhDbq4EDChrINbr3X74mB7Nt974DRSZv+FwWb7wWaCqw4OeLaFp3dxyx9rXFWgX5KMK1z2vRZu/NYcDtaFmHfMRD7wOZj2wP5wpEIirfPzv81lx390gyJIn1oAXrtPJ20Jgkv3odd1I2yJ6Jd2IbxkD7HcyUzwt7Mj6QYS6kujeF7rRsRt7KP8aBdmsfioebx1r8R6px3P2xFIS6yFQdJn5iBDCur4dldNoUisiMpLW5q5ZNrwBsj+8CoWs3L77DjPLtvMn7/3CGp66A5TOKA3RhBxAxn0IFHY3lDIPeVvkKVn80RzNiCxHAXTa2OlM9OZTzfxeSz+Y/RyflM/g+tKdgxIffFxiFoaNekwL3VU8Wp7FRYqMq0gckzXtdYZ/qFHjGun+6Mkvj93IBKOy0MhheTXi7AW+PAWJxGdWXznguPwe4fxBvmU8Jkne0c63LLhMda072Wkp5nZx3TjDzj8LH8Nly87DyfPRloCWe+FmPu4tiN4+Olu1v3yW2TnGpx6YTMlI0z27PCz9Rdh7v7XXnQfyBECVThICbXdQX59YRkra0p60wTXV3t55dF87ntlD0eHWlkRLemT8BMOoe/UonTb2I7A7pE8Vr2T3ZMdcZAM60i8+9qxSrJIT3KT56iKgzI6hbnHD6bCEGlXCFDAu6mewJZGRMoGAb5nXR9mfWkUc1EI/BkGowrq2rgbOaur2Dl+ImdNdv06VVehqLbGIJrGzu/xMFEF5vFeIl+uQuZriKiN/7Uo5+fM4iN/jIPx1qHBNBZ4X+rq32gsE/Zvcw1RdaWjEJE0eqaaAYrAzvUjbInSlex9/NTFBdjbfPzq9HfJ09K9kZYfRzSqkMRtlaBq49ElsjPBr26+n1WXJEjNyO3NxGmM8GCenUPwxhpCe9uoungOe1s6SRk9uijFARXOOGln77UfXzEd85AaQUqU7hTCsrFzA2jNfeqCvCKTW/5UMyBgbENjObc9ewpysiAxUmWpbg1LIClLZ19WBd94oY5dr0heHmeQ6nGRlabA+cCHd3/HAJLvhe1QtKOaP41dxUcdxdx9xQjU3em+whqNJrweZfXY1zCuCGGflo152kAVGocIvSePksy2GVfVipRgSUF1MotCPUmOZmR8H4al8crSg3z+c7XU1r3EAy9HoHuYXRUgVQU1lsYKutb4nEAKRcBXit/jqkKFJjNAlmrw79hkHnx/9kBDOoDicNHsrSjCtd/8qHJ9f4e7T4S0VPnO3kVEHK+7txaghG3klDhUpbA/yIVhcjDlRhuJ3xMfYLcSaZvAr5qI31nKlJkxrhr7RRZNHfWfa9R/AZ95sl/avJ017ftI2iaLvQ14vO6b3NeSj96uYjQOtW6btsaKP1ocf0oz3/pVPUJx9fHHJrqw7UZefTSfky/qJLfQQghXYlnxcIDmAx7SaQVjdD6paaU4fh2tNcaPb9e59E8H+DDiepfkaimOba4mfG6EzcuD1O7ti65yi1tkFkGF7eDb3NBL9pricNHIbTy2Yt7w0oMt8e1rR0lZhzYK7rUAbUMCbUsSa7p/oKtaysH7eAdqxEHqAkyb2InjwOMOB/1Ah6tfTvdcU1WJL6jCutiPGGEie/xRZbZG6qJcdhcp/Hbql7jmo/tJOd2kpIYwHaQDvvtbMxgfBbYtccIayc8V4q1pwzI8aDXueRJITS0lOWeE+1kRCNPC429BTvPjbM1lVH4nI8LRXqLvj8NJmClHwy/cvEH5hQbvlddgOaEBKZelR0EtkeTfmc3xB+Zx5fcu5vwnfk9qjw2OgihOo1Sl+H3rOBJ2mmvG7mFLXQm2o7pV0N7bi5IwkKLfC+nBqZd2DGhbbUcW33+6345A7wlLOMw2pSqvm7PnVrP4KI1rU3V8tW4xB9JZOOvCqAeSSFVB2MOk+K6JsumdIImmNME9CdKp/snF3N6PtccJ3B0h+a1irGPCA68xqF89qs20YDtPto7lr01TkECRluAfE9/NGLSkIplU8RFG/Uvko/LStyTXvz2Z+s3D2EVsBzvsBqv5dZNL5m7pu7fiUOl11YOXL9zEjsZCPthdRfqQQV2VqAUG5yzcPuCanzR80TTc9PwbogVEpQ6D1PNCAxmyEWMSyN3BjNdo/3s8Y44okZb4ftdF100jyZkxXPTlp4vPPNk/V7OKpO2SxKG4muodPqINzrAvVYmnyNdjfOtX9QN8g30B9++Lr2/rHdSH5twbj+eTTivEThyHMSqv10fcCHvZ4OSx4e8mxL2cP3M7N5/+IXKcRJzmlr/buDzEz77ao7r5GChx91k8msWZM3Zx/YitPM684QeolNijdVK3VWBP8oEEbX2CspcaKCNO/R9raF2YT/rcHGS2hlJv4HuiA32lq1YRpuyJqO3RFzd0E357F6In8ZUAsCxC7+8lMa8Ea9TAye/osDVSy6PLVxN5O0hgdIqzpu2n9j2ovs9C6Rw44e2wFyegw2xB4rpiFBHHmuXHOmcE2pYkgZ83khpbTGJu5QA/fKmppJUKlG0OjlQpyYkPcCE8BNMBGwVfBqJxpBu7gAZzFkd4cOlOrq0t56A1tHctVJqn5nD9DRN5sWkj3bntaIsG3s9B5aH2aZxfVkdhOM7enQGyXt3eq7Lpb2o+ZG0pq0rj9fXd74mV07EyGRaHgV83OG+W6y4Y0C0cDX47ejkXrD8L2epBeu3ed5cJiW7Br79ZSSqp4AwjjYpuG3NuEP+fW4kuCGVWAx46F3iubQwPNE0l5bh0csDI5k8N07ihbCs6NqoCliOwpMKBZIhJZW1oqsTTE8F73fdquPPqUW78Rz9IRWCW5yADHjyayayqBs6euStjO1RF8suL32ZrQyFf++BU0o6KUmLgyUuT73V3DlFL5w/10zg7/0CvDac/LAldcR9+3SaS9PLmw2HOuqyVX7XMQg4TTi5UUKpS2JnI3nZI1Q7/LtSWBF23ruDbP1jJ2EVjuPNv36Z0dPGw5/938YnIXgjxHeBa3DG7BbgaCABPAVXAAeDzUsrOnvNvA76M68n9LSnlm592ww+h2+wrOPD2sgJe+/wkYt0qQgNrdhdZO1pQoinsbD+pmeWYFTl4pcGZl7UNm061v/Ry6O9kXMEszx5A9ICb7lABIgqzqhq56bSP8On2gGCjmYtifOMXddx708cbYJwsLz7dZEp5Czef9iGWFJRWdtKwJ59MZbNEdprUDwoGSO7W7ABt86r4Sel7jAlH+eiNbO79RsWwVapQBHpdF8b4IgIrD2QkCyHB/8dmoseFhoh3KdtgnfMGvpM8RC0Pr3SPZGS4A6WrnXCuxfnXtnL8+d3IoM67O8bw6NaxxOe60cV9V1KwpvlJfKOIdNuIzOkUHHB6Jl1tRzZYDrbtSl+WrfDyxgk8vWYqZx+9gwtm7hgSFCOAUm8SKcHjBU1z+MHI9Xx134kZuyVpq2za9gD3r56Bo/kRJWmEPkjotiT3vDmXzy9MsfWhOjdL2uC+6/f3gZ0+UgnRK1hsqy/qrRn7cfBqJpPLWzluwoHeY4qAHNWgMpmkWpHYuQHsgI4aSWf28pGix+tpeEhVYM3wo6+Joxw0cEb15MXI5B8gVR5qmtJL9IfwdNs4NsYLuLhgL5XeGHtT2TzdOpbuLp3X57864FxrdoDksaX4l/UYeW3pZpXMDRBdPA6B5JYzPuDsmbsz7uT6Y0JxG+rIJGpPgaKpShteyyZqanxp50k0WgG2J/N4YNxSvMLuzS5rOIKo7eHy1z9H2/YCSFuE3t/OvzeUkb5JBSHRVsTxPt+J0mphV3pIfz4Xe1qgt9iR+zCOm0Ax6GFyeQtt6sA0JP3Re9SR7P1gL9fP/h4PbvwtRZWFh33G/yo+luyFEOXAt4DJUsqkEOJp4FJgMvCulPKXQohbgVuBW4QQk3u+nwKUAe8IIcZLOXz5gv8O5uSPoTrWgr0vQcNdMUS6L499aMne3g5VY4ZbpHt2KWdf00G5SKMPl9slA8ZNT/Khv6g3Gm4IhOCaY9fhzVBlx+uXnHBeFw/8uJx4REVRyKg3VD0w/4oUF3/xJaaUtyAExEydUZOaaNjvGtQGzDbbQZvYjfQNeo1CkHRUHo1N5u7ClSw4vZuf5FvcesmYYZreV0RZax2+Uo6IS2i1oGigXlRKidgZ54T3t1F4oYfRR6dRxzhsSvi46uyDhHPsnkjYNF/I3cK6kizWxDNIMF4Fc1YO8t3hSxAC6Ac7iDx1kIt/NRlFgbknR6ifOYkdsXJSps7vXz8GDw7nHLULG4FfddVxh9aoQ/9XVJgU7CRbTdNtDxwM0hBoK8J8I55L0haQ5UMtMZCO7DWGShukorF2a5C7v/Yf+Bu/1FtPxslVkWEVrdFA9isy8/YzeXzpe80cUiYUZ8fY3lA4rOTYr0WMLWrnj5e/MiT9tbSgfGsTHd48zpu9k1kLdtFSo/H6Y/kc3NWnxgxlW1RNTBHrVjmw85DqIIMAkXIQLZbbxgHjNAPbQ8Z88gC7k7n8vHbOwIPC4R/PVHDV592KWRFL57aVx5GakEO6rATP/g7skAezMte1HQk3H9WsqsaPJXrHgY01pcTfLUQ9phNFGOz9epzLmEzkhBy6Lgug1KTZW5nFVbtO4uqSHSzMasKWgrc7R/Boy0Q6snrmkk8l+ZsyUj63A3x/acXzTqTXviFaLbStSZJXF5CeX9iXDG5rI76tTUS/OJP7Ln+d360oYdU7WW7W0MNASEhEk/zrZ89x04NfO+y5/1V8UjWOBviFECauRN8A3Aac0PP9P4ClwC3AucCTUso0UC2E2AvMBVZ8es3uw6UjF/LCvpV47mkaUu9xcPcKyyG4vo4r/7iDmj0e0kkxQI1zOFzyjWaWP6YNlGqlRBg2UldBEYwtGro1PATLEJRUpqnb5yO7xKL5gGeA8lBR4eKvNnP19wcGOvkUi4YthejhJiwnHxnx9OoFlHgCWTpMYQkUPoqUAOD1SSbNiVPxTZV9e4PoK+IoXX1rr4qDWeEa4mRIIX1eDsbiLFBBXxXH+4wrzQBoO1NYg8hepBy6nk5z7vfbGT8j2Vux6firBZqQA7rMqzkcNMPDelZKTQyfkwfw7GkhtMxNVCdxc7KveDMbubSF9MVlEHDLKP7qteO5/725HD2qnrsvfHvY4JmDrdmIfV4cx4coMVACNrNDLYxtTtFZFWTJ9jHgCNQZMVeCSynYe/zIpp7FoSxFpMrHO48tw4ylkH5B4qYS1JhJ8IFWbLPPGC8USSKqcseXRvGTR6pBwEVHb+WjvZWkzI8je8GeloKM36jCoWhnMy/9diOqcPD5HCwTzrisg3/9tpjnHyzi+rvqOfXSDsy0QNWgs0Xj7htG9lZJGnAnB3zPdbopPvL7ja8BNog+JZVzODfZwbAlLzxezJcuqkNR4Oma8aRW5YBUcEI+UtPLhvzEtFW+/PD5/OOqpygt7DPm2rZA7TEUW7Ygaer88tVjEQmL8FoV7f5qZAK60YjNzUZ/L4K2JUnyG0XUGmHuqpk74D5S4qa3EECuifC7i5uyN9VTjKefkRUgLfE/3IYVyUZraMO3vQm9JYajKUyM7MbvMfnaTxpYuSIHmZQ9NpHhlkxXePjwxdX/78heSlkvhPgNUAMkgbeklG8JIYqllI095zQKIQ5ltyoHVva7RF3PsQEQQnwF+ApAZeV/3b80Gx8lD8ZpzlGR7cphyw2695W8+1wOO9cHmDy7lsHmmuGMe9Pnxwnd10FncRZoCr6N9fg3NSBMG4QgPaGQ+suDFIQTQ38M6F5JyUgT5/gK1qbH4znYidbQjZI0sQpDiAnZfP7Gx4a0RUr41xf+zb9en8g/n+sk+eUCpK7ifBTG0XwoZL4fMND3XxdM/ILNtqZCUl8txPvPDnzPdeL1O5x8cQdPhRXSikPszyORWQp4ejxTTsvGODFM6KZalHpzaGIuKVEOGHxx4QEmHJUY4GWiDyOJFehJWsyhJAOgBGyyQ0k6Y34GTwmPMAn2S1TX70HBsPFtaiC5oKr3cHfSz4q9I9lSV8LMyoGLqGUr3PLMKXy0dyS2BAeB2BbkrKN3cPMpK/BUOZi2wi1nLOf2lxezPJwFCQX7/Vw3WvKQSm1/AEt3uOfuh0FC/M4y7HFe8q6pH2D8BFzpTnM4YBVx2jdnkl0mmRBsoEDtoE4p7DHCH4Y4JcTTHnICfYRnScGezT5uuKuBoL9vAdd02NlSSO3kiVz/5EFOntWJ1yd77QX+UQa/emYf1502gdZaDwzKVi1sNxjV90AryVv651oeIkL1vYNPwvmqwN5t0taoU1Ru8voHEzOqJwffo6PbyyVXnsCERDVX3d7M7OMjvLh+MidMrEZVJEt3VvH3P1Wird5JYUwiFMnC0yJUTUzy5B+KwZb4/9YOtiR543DODiDrfOCxUY/u86DyLIlmTNXt/kaS9fjeAYcUy6E8Uo9Xs0kUBUn/pQKeirjux4Zwa1cPh09qPf4v4JOocXJxpfVRQBfwjBDi8sP9JMOxIY8gpXwQeBDc4iWfpLGDsa59P99b8Sixq3RwSkETeN6K4PtL67DjzkwLHr2nBNsS3PEljR8/Uo0AdK+Dabi61J50Lb1IJwWr382CDW2IiZUElu/Hu7+9H+lIvDtb+PEXR/Do0k7C/qGqHI9X8s7oxSQML6hgjM4fULxDWDavvVDKBZfWoyjugnMgHeajSCkgWXRiLRU5XWwoiLAkPYLIYskk0UmzGaAjQ65hgcOCrD6Cs1GIC0+vbj99WR5Z7QnOGFNLVoGNf2Uj1nlZyBx1IKHrAlTXLzj4owbXs6c/bAj+oJ5zV7eDV9Bl6WSpxuFsenyhcA8/r8kmJQcOPwWHKeEObv7iUr7yyLmkTRW7J+LRo1kUpdpJDqMNFI7Eu799ANm7kMTTQ/2X739vNiv3jeiNSnbPhLc2jmdmaTPnHLULvadgyc/OWcJlO0+mZnVZT2Kz/rs7AYZC9KgK/AcPYo/3kdWYQMlg9JUCOhdPprU8C6lpJIGmdCHoEmVWN7LF57oID2OwtRXQPBZxW0MXNpYU2FJhzdthxnxzoPviH9+Zy5Orp+PTDX7wuQ8yFsbRdYezH0nxt8/5UCIZbA0O6B/FSTQryIjXDfMvTffUnR3sBjxIUMokNaUcPC93IRMSX8C9X2N9bt+1FMf9O5PKQ1dJnFjBrm6DH387SHLBWFIV+dzzxrEA+NfUkLWtllSvW7Pgw9ez2Lk+wJ1/q+bmJ7PdnXha4vtji1utziP6jM8GyDYPsl1DObkD0W9KidjwhcMzxvEJKCpMIYSb0VIpUElcX0TiWnDezCPn0Y2osaE5oxQVFp77ieqQ/JfwSdQ4JwPVUspWACHE88BCoFkIUdoj1ZcCLT3n1wEj+v2+Alft86lib6SZb615BFOzBujRjVOyUPal8L6VORRaIkhnh3ACOhu2+rh0RoAFp3VTWGow75QIE49KontkrxHOsWHZy9ncd8sIFMMm+/nNKHFjiBFTOJJYk+TRf47h6qv24dOsIWl6s/1pl+wztUsINrzl49yLAA/8+MBclnWXudGYAgRTOKmyjptLNvJtbTO/rjmKG0dsZn8qm2/vW0R6AHFK/IrN10q39h5RhcMH3f22yD6F9CW5vH5TAstUUGQ94use0DLlABfYk/2kLsuDUL/vTYm+JIIMKfy8ew4rG0oQuBkPry3Zxvn51Rl3SSfn1PFGy0iWJ1yJ8dA5DoKx/i4mlLTx+Fef4e/Lj2LF3ko8usXJ0/YyM7yPux6r/M8oDTBNlSnlrQOOWbbC02umDfXJxs0Y+vflszjnqD6vD02xOT93P/e1VpFZlhGkR+Wh+90pMMIXpS3DWalJxZhl2QP7WFXAkTgHA2gLI9j5JnJzaCjhqw5qWYpv71vEjFAbZ+cdYKQvRnebQlerzrbVQdcGcXScPZ1FPLl6OilTZ8aIJgxbxZshg6PuhdkV7fw9mT3kO3ANtZHTJmGvzqI3idf2IGJUEmVKPHMGR1NAWqBsSyNH444XR7qC2Cvd+B9tY8LRCbJy3faYZs+41RyUGVGcTeHh3Yx1MM7PxTg1G//3akmV54EQiLRFYHM91iBDqG0pRDpVDu72MfVgM3uS7m7SuySK2miSvjQXe7QP0WWhvZMkMXIM6kmdQzK5WkcF0D+MDchldTh4vDDxEovv7jyGda0lJIPCjWfZGAYpiB87mvBbuxD9jPlCSPyhAJfdftEnusd/BZ+E7GuA+UKIAK4a5yRgLRAHrgR+2fP/f/ec/xLwuBDiXlwD7Thg9afZ6LRpcf0rj2LmWEMLbPgUUl8pxPN2dMhqbOX4iZ42ESfoQTgSqQrijRHee303l99Qz/gZSTw929ydiRxWREpwLEnLQavHPx7UaHp4l07T4Zl/lbPXO5JrF6xm4pguVNVdMDpaNC4+egsPfjB3UJQlKNicMLma27+3H90D/2iewAfdZX0Efsj9s6mS5b/3M3F7Exd+fR+bnWKOHVPHbyuX8/v66ey1cpHArGALN1VsYpQviiPdoJB762YSH1QmMZrtR/R46Ajk0Bw6/SHAGuHB+692ZK6KPD6AsCTHtVXz0V8n81FM6/WU6bBUfl8/g27Lw9UlQ13lUqbGnoZ8CDMw3z+C1zurODrUxsl5dfzonPcBSFoqDzRNoSzXBJ+AVAapWRGkxwws66ZKC191G6v3l3H8hINYjoKmOLTFAgMk+sFo6g4TtzUSjkaelkJXJePFMInBem+muBGSjsQc6UX3SFKDbN2paWXDFG0RKO06Jwfq+GBkCYmoitwfcK120v1elKZZtGgPe41snmwdxxOt4wmqFhPeOMi+ZyXLXslBUcAyBd5FOaRGqyAgntaHresKEI35cEp11Jqhyczi86uwisN9+eh7LiOrfTjZFuqIodKpbPTgbMjCtmy8rzfiSbah2BZqtYFuWXiDkm/fU9d7vle3SJk6ytgEFA2fUA3VQVSk3VDosELqzkLE+wYy4EVrjKDpEitDeYVUQuWj17NZfG4He/vZJ4IH4py+tYGSiEFDjZe32qagnJoAjxySIdNcFHKzxBoW4uPcTASU3pHPL5TRGAkVwrhFWNp1N1Gbo2BW5hI9fSKBlQdQO1w17JjjRnH7gzdRUpW51sOngU+is18lhHgWWI/rD7IBV/0SAp4WQnwZd0G4uOf8bT0eO9t7zv/6p+2J84+31tLtiwxbSUlbn3CfzHTHp1USxgl5iS8a3WtMPTT8zbJsoqdP5IKvbMIXkJiO4NYDC1gXLcKUPQR/ioMkjv93LR+jU5N497ax/Tb4YbACVSvnF4/vZ+eGAA//rAwHSd4X2ukI5pM2VSQKft2gKBzn9nPfJ+B3dxRPNI3D3GSgJVLYE3zIPPc1Sa9C7Ox8dj8R4d4bK5h+nsOTXTOpe99COq3kqG0Yi0Jk3WqT3OfQnOthdyCPf7ZNZHN8qHFPtA2cHerOFPaMzLp0mVYw6irwLtmJ3tmJ8pDku/ce5OCNxXzQrvRU8+lDSmr8o3kS52fvRZUCpcdCajkKv35zIc0jPEOyL0oL4jUhfrL8JJ4JdnD6pN2cMHYfj91XzMpdCl97NIb8eh78pn1gCmvFNSwri/LwYqKpDpat4tnVgpFWuOv+eajlx3P8xIOEvAYba0sOS/bC43Da1s+hIvEpNtcUb+e4QKMbNTqMG53aHkc0uTaN3UYut/5kC3+7pYR0sl+w1mCvqX7waRaXZe/htjFruTlwDBtGF/eQA4hiAxF0+ChWOiDfU2Kdxe4/CYQNqXjf8fT7MXzxJlLTy9hWX0zS0Al6MyS8MzSeWzaNxPg8Qg17B9hCpKqQnliUeafnKMj1YWxDoIxODfBykp6ea2gq6ZnlGLKMwuoDFMYOMv/UCBd9rZXCsr62nD1jF8+vm4yoTCM8ICfHkdtCAyNShQSPRBmZ6r2RLNURIy1kq9dVIQ3bs7gu1v22IVPmxvjpP91dpz/okIwr3KA2cWP1IrYbeUMvoCtEfzOCwC+a0PamwO4Xg9IfAubfuIils1owHNnLT0IBp9Y74JnMihy6L5rpuuoKwcKLjqNi3DB1KD8lfCYLjp9yywN0HlWPkjN0KVc3JAj+pAFhSMyiENFTJyI1BRFLI3P8eL0OVQUdpC2NmvYcHKkgLJt/fPU5Jle086eGqTzdOnaQWgRIOnj/0Yb+bhwlbn1iVUIoxyI7z6J+v+vqpnkcsmf5mXilH9NWOX7iAU6YcABNdSfJR+9k8eMbxrgDSggwJeaxIZI3FruSt5Rknb23Z9cikYNy8Esd7CovqavzCf6kkcQPS7FmBIZK7UkH/x9a8CztU3dZE33Ef1E+pDCEtMDZFELW+cGwyPvXWoTp4PU5hP5dzH47J+OzBxWDr6Q24mw0qSmpYktjGXuaC7D9EvXEjgFSvUwL1/hpKL2TQnEslM4UWS9uxaNZXPL1FvQrwjzwymjUv3WhVKdBBfOYEPLaXP66cBlqTFDfEOBPX82nvVZFaipCutWooqdPdFM/gFtXwOlnaD0E1UGZEEcZ16cD19oUsvdqNDdl9czwwW9fokyNoJSn3K88Ap9icXPDCl74eS71+72AoPtzU7DKMqtMfLrJO997BJ9ukbA1PrftrCE7sSH9e1Mt2s7MqQYcr0bnl+aAIji6qp7ffeE1dNVG6/FeSdoqmw6UcuNjZ2F7wLutnsDSOoRwBSEn6HHJ6HCZGFWJGJNAneRKp1KCPOhzVTGDnu2XF7/FonF9uf9r9nh59J4S1i4Nk7Q8dD9aBSH3Xk6DB2dbEBKqayeoSKFMjiMGFbJxOjScD3LBtMl/dLUbFTW4XwM2197VyEvTprJjVYDcfzTy1GubCYQdLFuhJRok5E2T5TeIWjpnbztryNxXcViY1cTkpjht62w+etpD44SxWMXZCNvBu7cV36Z6rBMDTP/hQtZ17scetPzYa8PI+uEjZW+99EQ+f/zM4ft6GPyvLzgeTaTx1auQk8bokXSK9AQXF+xljqee7r8qPPdYOUvK5iGQZL+yDWtuGbdd9xGnTtnbu8gbtsKf353LYx9MY9PBEiaUt/Nc25ihRA/gVzAuzMX7Uvd/SmecjCnEuvpesmUoJLYkONm3k4WnDVQNVO/w8cuvjkQk+wy/APqHMaQuSHypDLnJQ/eFM8C08e5pxbe71S171gNh4uaQtyBxSwnev7Vi/6gMmaOBX3EXEVOiL4uiLx1o19B2pgj8vJHkt4qQ2Zob7i8FzragS/TgGspmVhBcU4NtQ6RVhQzCkNt6wcixSebObiWVaKa5M8C1T1xEt+EdwpfO5hD0JofrOaZoODkBEkdXIFbV8OJfC3jmO9uwzxL8bfZkLFviCIE/bXKluQl/U4q6vV5++/V8EjHVNdP1lA9UYmmyXtpK1xdmucndHIE3K41MaBimBjjomoOTb8GYfu59NV6szWFSthjG20SizIgiKo0BVv2UrfHL4mM4+7JttP3GIZ1U8a+vI1oYGqLK8Wom58/ajq8nRkMgOTW3hhfaxwy4j+j9rwu1eqga5RCE5aAkDZygl3UHyrn8wYu4YuFGZo1uIKKrPFc3jtfenArHd6GGbKyTfUSuG4PnxW6UVpP00bnQ/TEj3RbIvQHk2CRClwjDwfeveixPHumxBb31M1OmzoNrjiJdaJOjGoT2x/j+RWNIJ5Ue/3MbfUMcc2HIrYCVVCCpoJzajvDJjLYBANGTGgVdJT5nJNnrq7HSfSfrHoeiCpPwyTpbGgpgFixcLJAq3L9kNv9aORPHEUgEs0bWc/OZy1mcU89rNaNx9vuRXRpF+REeuvB1cvQ0wdEW6aMF3/qawu/f8fHU6nw3tce0UlJzilEXd7G6Y1/GcSKKDGSTJ6PxXddUZo8fMfRHnzI+k2RfVZLH9XNf4nFZxc5ULqN9Ef4w5gM0YeMpljAZlqdzUNaC/939qB0J7rlxKUdNaRvi833jKSsRtsPu7SE6Zvl6VTeZIPO1T0z0ZVVpTjivk1C2zdZVIVa+ndUbnp6Mqyx7LZcZJyQIeKzeNj39pyLMQWrL2SdEuOKWZqompYkbHl5UJ/L3xNGkTJ1EQZDU9DKyX9iCSFs4+RpKhwVJibY6TvhbIS44O8r6Vd1sjhSRNi30ujied7tRd2SWCPV1CbQrD2CN8hI5fxok9IHSrxCkZpTh3dMKXUmK1nQQO90/xLPmEGbltKMoEAg5VHhi/OLkV/j6SxdBnYYcYblFHGxcv/VMLniqQnpiMcFVNSRiKt3tKqc51RRXt1J8LGQFLPLSCb79uXE8Xj9+2ChhAUjb9Zpa9MUkN532IXnBJCv2juD93VWowmHx1P28pxTzYodLstIGuWWQSmEwig1EeXpoeVFFYFsKbz+XiyftphT21HcTWFFN4uRKtJEp14+7Q+e4nDpuPKXPW9mv2lT5+hbick+Mb5Vt5Mc180j2k/alX0Gkh9OQSqTfdfVEQk1XNg+umoUqxtJqeNDeiiBO7e5LFb0s4qopLekmr3u3CydYS2zxOKyy3OGfX5HITg0RTuN5O4Lvow4crQvflga6z50GfoEyJ8LufJ2f17gCqBEFb1UT2ra+Meh9rANzThDZrSN3hEAK5M4AYmbmID/pgGxTULqSOGEvqellOCEP5dt3EW0AX8Dh1Es7uPx7zewWeYRUkxgeRoZifPeZM1lzoIL+rLx6fwVf+/t5XHDmeneH6QBS8OsLl1LkSaD37Ii8XgnYfOOk1WyrL2ZrfQmggAFOtQ91bMJN1d1z6SI9wXUl2zhxWj3q6bC6upw/L5nHvhbXvqSrCvMnVjK6dKC96X8Cn0myv/Gc8czMrWeBWstbnRXMD7cQUF2pyLIV/vDuPJ5cNx3SDt7qdsZNjjN9YltGCUFR4GunrOO0e77EGU01aEiG84IVncMU2B6Ey77TxCXfaEFRJbrHDW7pbte46dyxdLTo2BUa7yZGsOmlGXx//kqmlbWiqZId6wI4/Vb+0y5t54af1feG1vs8SS5bsJljxtVy9cMXYKLihLwk5o0kuHwf1iw/6S8V4H2oFXRBNOLln68tJJ72YDsKAokFOIubCV3QhfabNqzk0MVNAGq9CREtY1lChCAxewTBXY3kJU1iSpo2R/QWhgDwCYvvlG/E06+yku6BmZPbmfTVpYS2OGz+0RQ3MOow+nOgN2+Pokh+cf1ItqwIIaXgqOOi3PHwAQLZDn96Yw9vPpnLM38ppK3Bg8ywcCi2wzVnbOYL59X2plI4dkINx07oUy/MdJpYHimjzfIj2w+vRgn5UiRyLcRwp2kC59ocTltbx2mXdqJ7HP64U2XN6DCo4AgF3+gE2zUP7baXYtVdFJK2Sm062HMJh/vHLSWspFEHqQaM07LwPt/l5jfq318KWDP8KOd2I1s8iDScUFnDT2d8hAT+tGsyz+eX93qdqDuT+O9tGVIyUI1bZL2yg64r5+AMl37XAXVPCv+bTWhrXXWOYjmIriT+DfWkb8xC5JugQuLQQhUC665ywl89iNJjN1JrDII/rCd6zsTecpmyJoCsTEOeNXTu2hC+dz/qAROJIDW9lMBkPwWNKZJtXqSEd5/NpXSkwZlXt/ODwCrufGUmK0pKhxA9uEGIkaSXlR+NdRf3LIuqEW2MLW7vJfr+8GgWly3YxG3PlvT0g4Ks9cG4vriXIj3BoxPeIaQarjezCovGHWTumDqu33wi22uL8X1kcfXMUzP37aeMzyTZz5/gId3qpaFDZ+m7k/j5ntOREuaNqUNKWFtdjlQEiieFna8zc1EM9TB8ogiHiWXtvLpxIqdMP8hrkSqswdbDlIP3kfaPaZlk5qIYF9/QMiAyNxBy8HgNfvDQQb625TjsKX6wJVFF4Rstx/KLwEcck9NEVq5F40HXNdPjc7j+roZeoj8En25TmdfFqVP38Oqmia7kO66Q4LJ9qA0mMl8j9Z1iaLWwPiroyUUvelrXYyS1CvnD+e/zp9fy2Lkuc7Y+J+TNHF3mdhjm6Hy6R+SwTneQr0NoWjd2uUHK0RipRfh65VYWZjUN+amZFkydH+eKn7YQCu1ndbSY1d3FvKpnk87gDw8wuqiTz/+ogb/8eQzL/ROwLs9G+nTeFxa/W7KLr5+8muxAmnOvaaeg1OQ3N1ZmzP+SXWBy2ZU1GX3O18cK+EvDVDfP+yFS/ZgQd188QdkH1VR7i5HlHvQPY6hbEsgsFfOkLDyVCg+es5IR50bx+x02xvLZJCsHGLNTUsM0FW6pXsAjE5b0Hn+zcyQAx2fXE1AsfKrkupJt/KVxWu8uKv35PPRVcZRGc2CREb9C8ptFCAVEiYFXWHxl/ObehfeGqm1sWVjADlzduveJjmGDhoQE34aDpBeM6o15GPB9yiF8d/VQV2Rb4ulux8j3Zy6DqEL6c9n4/943p7QdKcRUCXn9VHkf5aAcHXHLe0o4lNpVedZE25PGrtBJXVmAPUJBu2k3+xM+QPQKbH+/u4Sl/85m754g3tIOVi2Y3LubGQzLUdnRVIBybCciy6IiqxVTKPiG1MVyNVRVBV19z2tYKC1JRMTG7g6iFBlcV76tj+j7/c6v2Hxvwjqu4SSS5zvceNuvuf83P2DS3P+5koTwGSV71DIau/x86aHzSBgasmfyfLDbnSCiIoUyvQsBxM8cQUqNwmEq6eiq5IvzN/PnN4+mfnU51rwEFDvuoJCAKdHWxt1IusNA0yUXXd+aMQWDpsP4o5IU6Q6N/dyIbODOunk8GnqHs69q58BtftJJhenzY8Pm3Q54LT43c5dL9uDqOVWwR/TkBfIqSH9gANH3h+0oPLJ8FvNP3sS+rf5et9IBfWKbh4+IFALp0UhZgAXWmjwqq7uZdOZ+zmvZyayszH2leyUNc0eSG27Ar9qcnFvPybn1jDrB5E/vziM1yPfdp5tcv3gN80d18H5wNiv2F/QuQiY6L22cxMr9lTz+tacJeU3mLo5w8301VI5N01zr4fkHC1m/zCW1OSfHsKXCoIQvfNBdyu0H5pGWGkp1GnVPCi2kYk4PgjOwtm8vLJv4mghiW4rwyzW9gWgiKZEqeF/o4gsPdlE5NdpbN/aJ1nGkMxCmjUJ1KovqZJgR3ig/qJ5P1Hbf5aRAB8GeXevnC/ehKpKHGqdgSBU7IPD8oZDoWwaet6PQpWAu9mOcng0FKrqwEcB3yjcyxt9nH9I9kktL93Jno+uhpe4ZmDRNUSQzj41RUGpQt9fH1g2tGONLEdk+ZH+pybQJLN8/bJZNp1x1uzoT2XuUIQF6UoCwDdyMLIeCLwTOmmwI2IhcEyyBbNHRqpuwR3iI/ccI8Al8f2rBMWDwoE0nVXZsDhF5bLT7VcSAdf5hVXN2UKLmuOrFBjuIrmSehLYDB9py3A+GRe6ja5CaQDwpMcuyiB03lhN/2jAk4PwQxvu7ydINooqH5E3F3HXFvTyx6y+ZT/6U8Nkke6WQ3789n0RaG5RAqkeCbXSjEMWcCAiFRaNbM1+nB7G0n9ueOQPDAXzA+gDkmgTT9XjNNPY7SbQ9wxvDABTVYfzpJqXThwZTHYKBSmkoSWNsoLeCKRWeahnLTRduZNnLOWxZEUTVD+8lpfertKNE0whNYJ2bzaKsBo7NbiCdrfN27SQ2HCxjKGsL3ltXwfZnG/F4HWyLAeojr9/mrEtaeDU/QkNHJu+RobHxtlSp7sihZt8Y4gcNJk3dgj8wcKKYBmxeHeaM0w/iGeSwfOm8LbTFAm7K35TrtSRUwdcXr+LESdVYjmBrYykIQW4gQXF2nKbuEF0JP03RIP9aNZ2vHbcO3QvHnBZBKFA5Ls3UeTFefLiAv99bjpzpQwzqV0fCL2tnkY4Jgj+pQ92dgh47cQCIXWRj+IoHhlQ7DsKw8e1sxrFd10dp9plOhQ3YknNm1A0oEF6bDg9bvlIXDk1mgCpflDtGruHm6mM4mMoiYnlI2Qp71/pZ+u8cjLTB7ScvY8RxFromeap1HE+fMQ7jtBzkHg+eJ7rxP9JG3gV+zphXyzmF1RR5BtpnVBVG2t1uPmhdcdNj9ORKGjM1wc/+VY3P7yAUCVLQ1qRz6+UmB4tHYUwqBq+K0hLHv7YWT313xucBEF22ayDPFFsgJU6VF+kVfW60HoEojyGKPSgTU+B3wBA41X7k7gAy0efokJ5QAottN+5CEehrEzjDuMWiCUKtSconm3SG0zSsy2K4QH8xMtlrf6lJh9mXzGK8v6s39Ucs5aG2Iwu/x+SxFTPc53TkgKpgek032S9uRf3p8HNY4qrowHVz3X9qLjv31DNx3JDMMp8aPpNkL9OrWL6nAomC2h5Ha44iPRpGZS54VLAVZIuObPIwfnQLE4NdmaP9enLP3PHciS7RH4KqQkRFlcWca77DS3sOpRw9dJGhZKd7QF6SRbWWQ5lMZkwX4FFs6tND68zaKGxN5KOq8JNHqlnxZjZLXshG92YeLElDY8mO0e4Hy8a/oRb7hjwePuUDKrxxgqqFkwdnl1ezprqc7z91eo9E2wd/tuTRtTvpblX58+3lbF4RQtVkT+HsFi75ZgvGtu3849/ze3Sowz97X4cKZLfGhxPH8OQ/Wvni1Y0IIdF0SMUVWhp17lhxDA/OXXbIUaMXQsA3T17FhdM2c9stM4m0Kzz23CoCHleq3dlQSMBj8JPz3mXemDoMS8Wj2azYO4Kf/Hsxz22dxFePXedmt+x3bX9Qcv51bby1qZKPsidzoxiYx2R/KouEoxH4ZRPqriSiZ/9/6AlDTx0gNk9gji1AehSwQW+IEFy2F8XoW7Ay9UggOHCxq/JGqE6FM2a4NKVCudeNSs3VDR4a9x7Lukp5qWUUd/+oko3vh1zvFSlY9lIOxSMM7n5+P293uV4cQgFVRAiurnOJZHYRl529B79nqJ3JsgU1qzVE2EFmgXFODr6/tBL02/z6mX2Esvu3W1JaleaeJ/dwzTEqck0t/jzH9XYapPpxclSs2QFQBOrGBNq2JJjDEF5PUjXj+DCedyM4Izwkv1aImjCRU+NuKgMAr0QZm0DmmTgrsvt6WkrMomwUxRXCpEegex3mLo6QU2Cxd6ufXRsCqBp89Y46TjtnMxYKmnDYNyKH2x8/ldq2/oZnie6xkYMCxW6pXsgD45YSsCz+vGQer26egK7aJA3dVcc5Dnpt18BHkyBSJpt25jF3WktGLmg2/XRaPdH0AqzyIFf99mle+uV1FOUM5YhPA59NsjdWIw2b8Ovb0VtiICVSEYQkxI4bjTGuyCX8PV78Gzr4QWoCYwujXHFZA1l5/SaogA+3lfLB3pGZ77OyiZc2F5JpKquaxOt3SxZquuSqe1u5O28RyRY/s0Mt+NWBkqvpCDbH82keJgFYge4a51QVFp3ZzaIzM0tMli2IpT38e8NEkBJd7cD4UYjvTt9AlS+Kt0eSVAR0xP2sP1BGeW43NR0DB/YvLnyLte+GWf1uFqJEI3BXDvUlOSgFKtvyAtSl4myL5qMd14G9M4Rs1d0gEZ/tGm4z0ZsiwSshoPDA9Hm88csGTgnXEtQtNuwt5gNnOvZp0GH5GEFmL4u8cAp9fwelPqeX6AGqCjp54Mp/U5QVx6M5eDW3fxeOreGBK//NU5smY0glY3UkTZOcMbuW15+AFRNHMG90Xa+B1pEC0WSibekj+v4QtuS84rUEZus80T0F368b0boOk8iqH/Zu8TNtQd9zXla0m48ipaQGLbwqDhMCXb1Vl8Dt6mOzGrn3L2Ow3svG6SecJ+Mqdfu9fPM7U+m8sUfadSRK+6GyiYJ9XYVUt+UyrrhtiIHRdFSeqxtN8K+1GOfnYB4bRns3yuJ5tagZGEHTICff4qjjYqx/P0yqSyBVOWD5T1+RR/rCnjF2KKbDArEvhcxSM9t/vArWvCDWDD/WsSFIOOBT+4i+B0ID8kxEgYls61FVCgZ4b824weSui7a5/alKpBTU7/dSX60z75QoPlVySH03MaeDv1/3PJf87WLam7PcJ1Alx529lfetgTvhNsvPxTtOJ2uVl86WELajYliHItvdWBj/pvohj3bpdY3Mmpg5R1fKUfld/YwB95HdOobj8KfnlvGTL5+Z4Vf/fXwmyT7uQNnKrSSaUn0VlXq2UKFl++nOCWCXBlBGxNlcXgWGZIVH8MQbKX6Qv4YzT3PVOrYD9enMbmW+DXXom1sYLhdK+Zgkl3+vhWDYobk8j/+IzkNFsilewP1NU7mhdAsCiS4kaUel3ghy+4H5me8lLC4u2JfxO+jZgQBSCrbUF/PYiumYY1OoVVGkBh4hODW3tpfoAV5cP5F7Xj8W2xFDimNUBtv58xU5RNrzScZVd868FMU7xyF5SwlLuitY0loJK8KIxRHUuX36XhlR+1zThjQUREmPZBRUOXhOBY8+EUDuDJKc3SOBRuI81TyWcf4uAoMWRMeBxhoPUsJvXxjYHyGfSdBrDi2LpzlU5ndxzqwdqMOkBdB0yMkzqf/QxtPcycGEh8opBooiGeGNIg6arr41k5HSdguO3HvvPkr2WjwYHyaoIAP+8dsSfvHY/p5c/jAl2Mk3yjfz+/oZCCRpqRJQLAr0FHdXDcwALoSb2td5Jj6A6A/BMhRalwBfdcDn+quLDT0VshyJSFnc9M9T+cqIJVgRh3FTY0yY49brveethWw6phC9uxvfvzrw/a0dLMmEb6V601MPhu51GDUxyfr3w+69nJ4xmaWSujofc3F4aGpqHeR4HwKZWX3lSEg4BP7UgvPXNqLfGgtHD5MwWQVRlu5H9gItEsVBp9QT52df2opfHbgjqZqYZPSU5BC1qirAp9rccP6H/PSZkxBlaXyVCb48YivvVw9NsWzHVdpasoYa7IUAy8YsyUJr7/PCWXB6N5fd1IzHM8hLSkLM1vlxzRw+jLj3kTZu0fIuHVRYsnEvP8n0/J8CPpNk//h2P+aeBCKTt4Tt4N9YR+K8YkS27Q7AnvFhjffxs86FzGl7jcICE0OqvFY/qicHSd+1hGERWFd7WPvkwV1+frH7LDzC4Wulq3ht2quowqHFDPBA4xS+te9Y/jBmGULA96sXsCZWPIy+VnJSTi3zws3uJwkpR7AvlYuDIKQYvNoxki7LS4U3xtmlB/nNJW+xOlrI96uPwXIEIdUc4JRX15HFPa8fS9rK/Hq1tw/Q1qBhW+4sEBJISfTVcay3IpinZyM0iVNpMLkmiTIhyc5ULjYKIstGTIwjdwV7fZHd4qagzI0M9LwQYFyci+zQYa10Q/+9DksiFZwQaeBYfz1ej4OiQCohMA2Fn3+lii/f3oDXnyELo+i38OFKv0KAV7OZkt+W0Q4IkIgpbPowhFQUliyrYPPTEE3rZGeZ2BYoM+LDGhkloGRp+DSHs8fX8/dZxZjrjQy7gKHqrc3rwry3u5BjR7UhAF/Q4aKC/ZyYXc87XSOI2jpT/B3My2oestVPWwpPrZ6K2X4YO7kCRGykpiBrfKRHhvGM70LdkyawfD92bSd/oQRFOqgaeLMF0XMn0j1FRxVJzLNyMM/IRnTZSAEt+5oxTIEng73INBQ6W3UQkvxik+5OjdRIP/FflbtzbLg0p/1SkwxBWuLtKQhijCnE8fpQROaU3T3xfQMOeJ9sJzGthAvL9qFm2tENrirWDz7VZmFuE9qibnzC4tTcGsZlR7lv9DK+e2ARthQ4KKgHkijvK6TDNk7GbY9K8tRyjKvDaMsS+F5v4rJvNw/xojv0DKq0WX0gHxkSoEpku46zts8J4H8yocFnkuxfe7sa4QEy5E0SErTOOCLHGpp7XVNwQpIHlo3npnN38l5XBTtzg+6k6Sdkag0Rt8i1PXzPax5J5dwm/jhvCSiy91alngS3VKznQCqMIwW/qZ3B6lgxw01ZBcl3Kzb0EtmSzjJ+XjcHS7pl1UxUVBwsVDzC5h8tk/hV1QrmZTXz5MQ3eKJhPGvaS3Ac0ZuL44X1k7CHcxuUkpZEGK81tPNEWuJ9sRPz9GwkUDKyjd9NXoLaE1f1+/0zeDk5EnVcElloYu/3oSUFMttCjkojPBLHAiEFaBIhhOuJETBQpnWDD0SBCUJwx46jOfbNEGcd3UBWjs26ZWHeeCqPaERn7uLosEZuITKYm0Xfqx6cWde23Cjm91/OAWDNYxrpqBuU0xl1PX+Ut+JIn8hsjdAUNhdMpaGrDtvnIG8pwPl+G4GGFFZaoHkcbFuQlWuTjCmkUwqOpiAlJK8r4D/W5PPAJY2MmZRm+sIoF1/fQkAaXJS7l3RKQVFlRp6UUvDMmmnY4b1oncnMnQE4sQDO7gC06yiqQ/x3I1AOGoS+XjMg/a5tQTwtkS/sRzlnRN+TKsLNvZR2eKV6BBdbzUOyPh7q45VvhwmGbe56tJpQts23LhiP8VEc88RhPJb6fo3AGWCrUJIW2rNdqJvcZ0tNL0O2aTBMfQZpuknW+h7cwdKysD/KZvLYTjwfU8UqE2K2Rlg1+GLhbkZ3J/ny386jpi2bqtJuyo9qZvezEH80Qbo8F+d4MnsVISFHIieBOS6AcfZ4SsdsHL4nDBj5g33UZRUTO3EMGP0625EcM63qP/0cnxSfObKPRxJ013ShG26QUCY4uVqPpJZhFvlVNjkF/Mdz43nnwTz8uY0Yx6YwEsVguWXQDkmqw0Ny9HERrivciSqGhnP7VZuJgS7uqZvJax1VmdsBCBzmhFt6t58SN9AmMSgnyqHkV4ZUQcKtB+bzI99G/vz2fGrbc0DAMs8oTpmyF1WB+s6s4euaKhIn7Mn8HSA6LDzPduJ9poNU0uFybSKLL+jkK3c2cPOYDSzY10ZngcIfxTTyR3fx92Pe5ryXL6R7ae7AJGGaRO9qI/T8PtfbQoBTpJH+Qh7m8WGCdzayabeHzQ9V9f7EyVKI/6YMRds4bPs+DocWzVRcQSiS2n1e7rp2FInRAUS3g9lhZSwRZwd8KI6BtCWK3VOsXlNITSzCKM/mydVTWVKWR5fPy4SHQny9fSf71vkJhG0WndVNToHF5hVBtqwNsVPJ591p45HZGslH2pBdOptX6GxeEeL5B4s49uwucvIt9m3z44zV+dmPdwOuesF0BLatcM9ri2iOhPEcXUHog70DEr+B68GRGl+MsyWnr8u9Ng4C/f2oS0yDhF0hQY0aaLtS2JMG1SUAmjoC3P/jMr724wZUD2iqxDQFjgX3fa+CE8/v4tJvtlBUbmKZcPMvavjh7f5PQPbu4qX0rD4lkW6sb7SSahO9M8Px6xBXkQ1eKE0PzJtkg4xpyJZ+41ZTccI+RKOg/kAuM6a3fWzZwv5IxgXpgw5vTH2JB9+bww9XLurNRttVHWDf+gChF7YjTImnpmv4mBNVIkb2JIPTgRKLZ9rGc3VwZ+bTNUmsXcFT30k4upfo6ZN6OkCiK4JvXnzcJ36G/yw+c2S/ZdkOAhvSpMp11APGkDTG0iuwTvC7+sBMJGtLmrdpLH3Yh8eKIQHPuijm/HYS11YgbQVnoYVYMtzAcYlr4/Iw8biGUDKnZe22dF7pGOUSdAYIHEKqxXcrNvQeUwQcl92AV9g9/tiZn8F2FH740fGYbcHeJv34xRPw6RbHjT/A2OI2Ptg9MmO+doRA6RwoPUkBZmUuVl4AgYX3qTaUuDsxDUvh3Wdz2bk+wJ/e3M34onYKc+JMCXSwKZLH795YRHJHlrtQ9m+vJTC9+cTnQXip6wGjNlr4/tCGXO0lOn0y8mgFrSlKYF0tWnsCJeIQuq2BbUdlMXVMJOP82p8M827XCL5QtJuQmjmiOZ2GN57I5ZVHC6jb53O3/1Mg/pdKUtuTBH7RiBIdyIR2fpDImZPx7mlDb+jG8eukJ5VglYTBgRW1FcRLDJwU6C918vDyEqKdKuOmJ5k8O05uocWMhXFmLIyzKiJ5Z/9k98J+BanRW5IuEVV58wk3NF7THb44vwW1Z4GyHKhPBbn572dysM09x17sx8rLQnuhJ8trTx1isyKbxLx+jgWKg1WVRqRB3ZvOaGx2XzYoNUZGstfWxHm1qYCVJ47hgsJqKtMRJk2OkpXjcOufawaeq8NRx8XITqboNSsPV+YNQAgcBAoObR0+/G0DR7bancQuCOGsDyPGqyhjkm4ZSAdkjQ9ne4gBv7AdlM4E3qTBs2umcPLk/Rk9j6IJDY9i4fH2ec8m44LNK0L84QcVHP9rH498OAvbGSjd6VvaehOrCcsh8FE1iePGDHw+1UEUmYjCvs4WGjzeOoFLS/cOaY9pwKq3s0jGVdeeV9eF2pXAzvJTFfTzm+9eTEVhTub++xTwcYUv/38HIcCz38Se7EOGVGRPVj4JSF3BOD6McU7W8E9mSjzvRFF6kocJQKQk+so4nq1dKIUmIlchdUkuMkOknVRd9zcjpSAPkz1hbyoH/TDJr8OqyWMT3mKEd6BXikQQVA8NnswTx3BUrEFZLC1H5/tPn8aflszjqPH1WM4wHeBAclEpssfjwc7y0XnZ0UQXj8OsyEF0W1hZQaysviIrpqHQXOvhw9ezKctxPX5GeKJs6yzg9U3jXe8EkWFh0lWMMfnYPdeSqkLknKmkJpThZPmQfg/myDy6z52GUe7684uEw++/XIqRFkP0lylH5dd1s/hnywSu2nUScTuzrOKYChs/DFO3z/VUEdKNzsSS2JP9xH9ePmRPKBIm0qeTmllO9MzJxE8c5xI97sIccXQS3RoXv7eeu7+6lfte3svfP9zFaZd28POvjWT9slDPexA0GH1Rycbx4WH12UKBk87rcP8WboLJCn+cE07axaEo3tzJERJXFRF9uIrUlwtIXVlA92WTiZ41oSfRmHQzeOZb+MfG0Hf5sYI+hkvxJBRQ8wd9mXLQl8VQmk3MBSGaHnN46KJ87rio6rAVxyxTEK7sl4Sv0YTU4cuCOigYJV7sUQOL+PjX14HpVsCSu4PYr+e7/17Nx8mQn8jrtfnZrzZTOV+yrb6Yvy+fScpUsXp2bUlDJZby8P2rJ/L9C8ex6u0s2po09m/3cf+d5fz46lG0NPn424tTsP0OytQoysIulOlRCFso0dRAQVII16MD3AEVtlCmx1DmDBVKIo6H9QfLSBhab2BkIqawdP0Ibn/+JLrPnkzi6ApkSOfH819m3tgWHvrxlxhdlrnG8KeFz5xkP+24ydimjffVJN3nTkRtT6PXdSN9GsbibJyzehbfNhPCuG5gh0Zs0kF/N4K6b2iAlEhJPP/uwjyuZ4J/IYsxI7qJPJKkrdHjFscYW0BidiXCdgi/tYv3ns9h1OQk/gzGmKBqHbYQc6U3OiTYBdyaot3Woe2q60LmHPAh9/nd9L9BG2V0HLqH7hgcHZ7bPoH3S3JwjopBxuARgZ2dQ3pBHp4VHUTOnoz0ewisPIBvRzNYbqvTo/KInTQeJ9uPSBgkNzfw/stRFp0dIZ5SiBs+aPa4Az/bgu5hcqdIMEfkom5rIjWxCDvbPzBHuiJAUYmdOJbcf61DADV7fHzrzHF89ccNzFgUByHZkcjj9w3Te/Pyt5gBnmgZx7WlO4b2oSVYvSIbJ091A3t6qt0JQyL9Ck65B3uqD21r6lATUVJu4YoMkfFIBB0tIZTGENFpVWQX1PSmCp59QpQJM/dxy+dH8cCSPZiOwrPNY3qFXFmik7ogF9/znQO8fbx+h4uvb6ZkxEARXBOSGyZs4qPyseypL8IfMOhoCODsysZUiiHbQVSlEL4YapOGUCV2hStdelWLG4//gOLJ3dyxcgR2euj4cxSFVHkOyJ6isxLQBY6QpD+Xgzk1i9A9tb1qo5o9PibPzqxHVxRJ/ezC3s/60igiamN8Ps8tbzmclO9I7AoPanXfrthb3YGdU0/y6Ap3EZO4JSBTpvtZdY3Auvb/sfffUXJVx/o//NkndO7JOUmjnLMQUQQJRM7RgLGxwQGwr21wDjhzbTA2OOAAGDDBYKLJGSRQQkI5jkaaGU3OnbtP2O8fpyf0dI+M7/Vd75e1frWWDUx3n7DPPrVrVz31PBYe3eSuK19gZ2sZTZbTaHff6qW8u3cSFyzaRWlelG0tFfxzywzE1p2oYZVbP12f/Vx1gXQbiCoF5VAc31vtqPvi4FYwJviQrQw7fKvIB5qKRzf4xDFbufDYHfhUk52xIv7SMYudsVFEZqbgKxtPZOm2Hs71fYjHjPOHNUdzQJ+ArHXuwywPkphXxaDWzV2XPM0/1h/FFademHu8/kP2sXP2vqCXa350GQ/84HGswjzMCo3k7ErwWw5H+tD8KtHBkoiQhXQJRI+JsknD80DfuMdW+k38SgpDqpxZ1MxXv7iFGwPn0HioFAN9ePJKKQmdO4eXn45xwXU9aFUp9FGBiiVhhrcfv2JksBQOmUcxubCkMevvKVvweNcUrPS2REqBvSEP2e0aiWwGFOwteeh7ejCmljrXVJxCnRuBgEVCgcNmAJFSkGNQRiMXKIidVUvy7CLsBh2tLYRnd+eweEVsYTXxhTXDnY/SrRE7tp73rEJu/NsctjZXIYTEtBUsDchLweA42HtIp9QgObN8HKUmkLqGVewbhrAd2uPlG1+eTuyeWoRHcQrWo8dKqjzfN5FryveAdCgvEjGBLQW3vLOE/r/VOOdNSdyP9aGviTidogCawJztRduRwDjBT/wzpcgiDcXuQ7Z4kAeGqCaGdisCaapYwOu7puB1m3zjzDXOoXTwBS2O/XycJ7fXcVApYd+7dYgpcQhYyJhCfFo9xopyvFtbUUIJfPWSW76+nxNWDOYcC1XAry9/iQt/8wlK2yxaNuSNUOMaCnKvDwpNXMf1UuaKczgVxCUsfjtlNZO9gwxUOXoG2n39zjtggXQ5t2JNcuG//RDmXC+pcwqQxRqoYK7Ix1oJ7nu6M3hyHr6znO/9+VAWuiQRF7z4ahnhs0Y5OUvifnYQ97ODxL5WjnlSMDeRHmKYAG20ebccRlg2sWMmQsoi8OZ+EJLYMfXY+R4QYOigLo7yhqjg5ffnkbRG3q+GrhFNWoB8b5xlpwzw4QvuYeRZxlVIiekJor8RJvha43CgQ8TGFU7XPYZaF0IJ3CLFvdc+w4TiATzpPo1lwU4WBnr43qFlrA5VARLhtWBGnA9sPx++dRTuJwYJnzYhc+5rDq3d/QeXcwkPMqHsHuD/c/ZZdsnXzqWospBvv7lumPBIqYtn+xpVODzuho3yoY2ZKkRYB3MeUwpYMDfE1ZMOUu8JE9QMGjqL2NFahjGW1lAIpCIYnFDJl84y+fS32ll5cT+6R9KSDPByfx2fq9zFLTUf8o1DxzL6wjzCZLavj9MKW3JcheCF/om4hUlSasgWpxM4C99rKxiTSlA7I1gzPahHD2bJ+zm/GW9nIcAUzgukCDw7O4Y58W2vTnxRbbZoha7SqxXRe7Ao47iiJIGoSGK3ubO22kNjpTf3O2N8BCEMISVyjCqSdClYlsJ4OYkuw8sV61dy0c5tVJQk2L/bz5PHLWCw1pt2MgLckLy6mNRpeSORpgbmbC+JzymYZ+UjNRXrsBu5dXTnYu6aTcLUee7DmXzxlA0EPU5k6vZIjjs7xCf3rESqCmJRCHtTHvS4oDYOCYFRV4AxoQBRmYR5fcxbvHXcsbAskP0GXz73De58dmU2B7ql4BkUfN+9ldLaEH/qmE2tGmKCO4wq4LX+Wszz8kksDqK/MojSZaB0mKhNKad5DFAbErifGyD6sxqsGZ50Q6uElI3tdyMMCyVp8sFbefz1vyv49Dc7iCZ03jlQT1NfIYpp8ffByci6ESEf1/ro8L97nh0gclwg29nbTgCWk2JbUUhOKwXDIu/FXUhdJbxqxoiTlEBCI7GuiH+o00nNtGB97jGcUNzP/Z95ikgnfOH1aVhj1hahC2Jzq0BoBN4+kKHSBeldoEsgdYnUBO7mHlbcFKGuaHDY0YOzMfUIi+/UfsCZO892pDlFeqopYJ2kE2upJqtlPG1xQ2drSyXzalpY37OfZSX/d2RoH0tnnzRMHu/Y6eTUhwqxHjubUzxtUhOkZhYhd7tJ1hfjPtiXIfYLgC7YWzsT1VqDS7GIWRpbWsuxckXGALrqSBpua+eub9Tym1triTw6Cdul4utPMHdXKy/VOxC3Ca5BTFTy1BQXlRxgVWFzFl0tgEuxeWD66zzVM4mX+ydweHsRMVPkrj/YNupgHDnLHOPoHRPFhtPRmssBqzaiLJWOXCzUvtjwS5qaWDQ+2Dcn54SAEgMKTegbszAZFu7dnahRxym6mvtJzHLnnPhSEWi9mfULpc0Rdh8PAe+NJonf0M3jsVJMQ+D6bJCQ35PtYDwKcoJ79E9hiQex1I0lVUcfdEvwyLz1o0xXLRq7C5lf2zn8N0soyPR9KR4Qy0LYjR6UqYlhhBA4QxhB56ydZ3NmYRNfrdkyzJ8jJTx3fzEP3VFBKqFgGAJfyW7CyydjF2Z2XicMnZe3TuP2ma9wR/179IR03GlUV6/pISU1qIbktaWoG2LoD8exqvzo7SFEwnQKuIbE99M2wg9MZJa/n8SuIA0TZxKtc9Ioak+U4Bv7ePrPZbzwai19p89F6IKEoePWnDBrfn0TOwa9uP7ei9I4kpZRG5K4H+ol+clixyPqAuI2wpD4b21DAGaxj/jcKqxCnzOXbRsr30Nh42FEb5TB8+fm3glagsSOPLRjB7HzzHRHd6b99KLXCbhT5E2EX/7jAL+4qY6uwy5UTWLZgtDsGuILa1F7omDmrq2JlMSa4CJxdTHKgMV5iz7MWQQG0BWbmb7+zHQOzqJiTvbCwDh1GyHpi3oxpcKDje/+f85+rN311EtsOxjGtIcu3xFQkFXJnI4PBPQ40Xn0xMkoKRO9NeRkOIRASEnsS6WEqoP8pXUWn6jZw65oIfeum4EZZ7gpK8NsiRI3nKBTF8S+VoHtUsGyMbak+NHdE0kudzPtm/38cdrbeJXMCSWlg/X+++9Kee7+EsL9GtWTklz51U4+edY+Plm+j2tcZ7HTHKdjUwiklIji3JNPFJpQYEL/GAds2SjhJIo3hv52GO/9fZCGGgpAqjmA7Ecw2aWjqKAeM4i9z4c86IWkQIkk8Ww+jGdPl/M9wLOtneT0Mucco07iVg2mxBrpGBtdWZD/VBeJa0pziKMIzIDOzCe8XB/fQkGRybdjx9MaOwLmIK3SJV63MXxFWMtDoIG1x/eRHT04Orr53pG6T9xSeaFvDOWGCsqQ4pUtEYOWI7uX7jI1pcqLnRPZ313E7+e+jddl8sTvS/nbr8ozBFjUjjD5z2xn8NIF2P7MomYsDRX0qBZVeSPza7p3AJ9iELN1rEYPZmsxqeNsZ74rCp6dHfjWHUIASszm54l32D04iUd2T8aW6lDmCqvMz8Al8yl49EO6TpmLhYuhrfQQ0mvn6gmc2v0Oa9/2ZU0bz9MD6OujpFbmIYtU1N0JXO+EEQlJYkYZ0WPrnYVZUbBKfShIzqnZwv43InRoHqyi3PTbAPTpCCHJrxtkcHtRRiBSXRBiYkn/MPpm2vw4f3l3L22HXMQjCi2UcevzSyEp0kHfEZ69ITGPdXZ8bs/4iAwJuHO84/TpjBRHss9jWiqTy3p5faCGlljP+NfxH7CPnbM3LItn3t8/pjtUkNcriUknn54rApXd6VSMphI+YxbKQBy9M4zUVVIT81CXD2Ct8fJ+wyy2rCwlrioE72wkduk4FXJpo/f3YZwcJHlhIfYQusAA9xP9yATo74a54jtduHJU/YSAVFKw9pV8ejuc1eTgbi+//FItrQfcXP6lLlbMa2TX6iqknit0B+nVHRDyeBDgowextwUc7UshwQC9ZQD/Ow2IpyyHsGmMbqfeFhovg5HbLAV7jw9lZgx1RgxmxJzc7YO9uA8OgK5ge4AL8/Cd6aGQw0S2FDEY8oEtMZIC1+bD9G7rxuOXGcLZLo/Nl07azes9Om/smOKgXquTKBMTCF2SlBqb4mU01xYzrfAwA7vG7x/AtNHeCMNuF0awCLtGG2nQGvx3XgNJRX5kmMs8ZSt0G16e78ssAAoBqKALi1V5TZw79RBu1ebdwUqeODyN/k3FmN0utiulrHi5nrNn7WLdnaEMgXJIX59p49nWRuyYkXN4dIOTpo+kJE3TaQLUXQ4H/q9b5xNt8zri3YpAukdx6M8qR8RT+La24dVMZJ/N37YuGOF8GX12l0LogqnoXoGVq3gtBSWn5SEed0REsjKpbQaeB3szeHRsXRA9blJmqlAo2MDzLQvIb980LCc5rqUzldNmtrPnbUk4v3B4F1Dgi2NYaka6BaBqorPzULpDw4LzZrEfMc5OVgowF4/sqNZEKigkwpuPF/D2s4UIASsu6mPV5f1oHgdEMPxbC6x1+dCvHSGQkJi2YM3OWh4vrKM2/6NTcfxP7GPn7CPxFFYODP1g2Melyb2s9hbTbXozPhcCB2kxChJvF3hJFngBCdUJCt0JLluyiXvXLCJyIIjncDsiahN8cz/hFdOGI5AhQLQe6SNxW4mTRkrYKAkLl9vmxvIddP2wkB27ymh6y2QiDeOl6zAMQXF5JhojGVf5253lnHL5ANWLw4h3LKSlZKY+TAu9PYRRU4DSEYaKVHYKS0qEJlAXRZBTwuhvx/E+2ImSdKKTcboQ0Ppi6G0hjOq8TNQMOIXgRSEY4us3BPYOP/KAD7s85VDi5jvl5VM/N8AlXz/I/uYgv/MvICY1wuno3LM8Sv7AIPJbPdjNDr+RgYKRTK8zCljTPdzwrWZ+v3sVnaEApB2RiCgUNAseuO5JFI/NI91TebJnEhM9ITpSmamOo4IdfL5iJ4ktBj+9bgJJQyVlKWC0YZb6ic2tgCpAl4wrTzZmpBQhufb4TRiWQlyqvNA3kXs7ZxK3s18lt7C4Z+pbTHCHh3mAKrUIzz2+CDnocryJLSgrDLOsrpmvbj+MIuDDNQHu/3klB3c7WHhhS1yH+oedvSosAu4UZ83fN3wuwxYIS6BoNroi+cPUt7nk1ctzC7DoKomFNXi3tZGIKvziSxMJpDZiFXiJLa3DmDjK6dgCuyiQlfMespSl0R4poLymjZbaQvRNsWyOIbfA9giUQYdSOX5qBeNFFPr+HpSU6cBl2wYxq/Ozgzdbojf3EbzoAPumuLDEAGJR/nBNaH9zHoocf7GYUDxAVUGIgz2FaU3lanxbWjPy9jL9f8qeJOq2GNZMD08eqOOVmxXC/QqphPNuNO118/SfS7n28T5GM27Yu33ZaU0Y04sgsGyVu14/FtU1yLd+cAL/l/axw9kHvC7UHODfoCeFLyn5Tfl7fLv2A44NtuEe6mTpsiEx/lZN85l8u24Tn1i2jb9c8yxav4L+pkP+5WrqJ/+pbbj3dqP2RNGb+wm+uhfPHqfAqm6OMu3NFn4yaR3XJRv51SOn8ND6hWwYmELf0ikciFaOS12gqJL2ZnfW320Utrzj57G+KYgzB1FTEQfja1iOo28dxCgJgKo4zSaWQI7OgFgSTFBaUmgbIvh/2YbvntZhR/+vLPjaHtx7u51cpmk7C0dZEvW4QYTP6RgWAoRLoiyMIKZFkWsLsN8rxH6+BPP5UrbuqaOsIMkLJZPot90ZIu4JqdHvcxFb5c9WOEJizvUSvaOWX3ecTMdgMCPitC2VgaiHX79yLGWuOJ+r2Mk15Xt4tHMq1iinvKqgif+uX0vJQIQfXjORyICGERWIhERYNlpXBN/32yBpIybEnPrGGBPYTCzpZ1Z1J6pioSkWtlT4/nMrOOZn13PqB+fzm9Z5RKwxOwpLgpRcXrqPek84g/DtvT31DEQ9wyipmsJBHrr+H5y04DAer8TlkSw9JcydzzUwZe4I5FGqCppioasWi+vbeOC6J/G7R1YozQ1femEpO7pKSZkqxSSxIuPLKkpVIL0aUgpkwkbYEq0vRvCNfbi3t2V+2QZdy+08XarJxJJ+kijEb6kgflMZdoGKdAukLrDqXERvrSR5cRG2pmDUBUmeUpK7YCklvg0tw3BH//sH09j70V5UIgwL/9omJx2UX0Vsab0jIp+emCnp4rq7zyIey7HDl/DBoWq6w0OBgSSxqIbY0lpsl4rURmgzBKDvTxD4Ziv55x0geWUHve3asKMHJzjradf58Lc6iwPdeBQTpEQ2eXMvtLmyDpqKmcxnbee+7O//B+1jF9nrqsr5x0zlyff2pJ2AZPn0g/z0wtfRVQtNhUkMclrBYfotN5/cs4L4sxZmgQ2uXGubYGI0Qa07wj0ds9hzqBy/2yBWWo2nqhutLYQ2ECfw7ggLowRoB/v3XaROzeenJ28nIf18741lGY7JMDUeWTefFbMP4lUyHa1lQdtBN407szsZTVuhoy9AW8qPCAi4PAm7JOJDF9KrYtQXgC3QNRPdsDFWBylZ3EOkUGBaCvaOBJ7fdqO1Os7ALlRJXlKIXetCaU7iei3s5JDHMWFJAmsa8b/XiNRUkpMKSX07n1wVcCFAmRbHavBnbFcP7qjka8Hl7CoNknMPoSukVubh/ePYPKVA2+fkusNNQWdXM8YsqfLO3npMS8GrWiwK9HDXofnD3CsqNjfXbMGrWDx8fylWDlELYUtcHRHO3rCZjXPraWifhAxrw8gXt2bgdZn8+hMvUlMYJmUqvLVnEttaynklVk28ysKSNkRxio9DaZK4jXogieeuDpY/3oxnTB53zf464sbI4nDjynX4XEZGq7+igNdv88Uft/LV86ciVUFyeiluzeSB656kpjA0jPMHp2bwzmAVN53VwBxfH6Yt2HSo+sikWkIgDDsrwBamjX9DM8kZo2CytsjghXFrBted+AEXLt5FwJMiZSp0fXcGTbaNsSIP4+QgotN0WC9LnAXHLnFh7/KTPKcAJd/A0rLBA0o0hZIctYD1xyl4ahuxpbWk6ovAAtehPnwbm1HDSaw8t3OdOZBj+0MVPPzUZK6+vBFDOjoEQgh+9vxyXtkxbeS7UgJJrKk6ZpuOVP1Oc6Fp4drfg94dGXXg3EGbaSi8+WQRD/9sPbvjhbzdXcMTdsm/lQ1FwNN7NnPl5BOo8hX+O7/8yPaxc/YAN503i7e2fEhXyMdtF7/G8umHUJVMjpoOw8t3Dx1N3NZIneaD7cqYhhmJIiS2VFA0m3sPz+S1F+ZiDb3wk4Ok6krQO0IEX9mTEYEKAAvcL4XwrE1Q8J7Br9+eO5wHHG37Oku545VjuPmM98F2NGRTpsPr4w3YfPqb7Tz9lxIGejIJkTbaM6jWo/SaXuxuHRrzHKY8ABsuWLSDE6Y1k7JU5lR3UZHvTMq4pXJn3jxejJej/qQdc4mf2DcrnIt2C+brCSb9l83erxm0rs/Gxo9OWggJwrDw7O3BanVjlebm4keAqI85lAkJBdnppCi2NVehBUO4Xh7A9WoIUhJjmZ/UBQWOE/Dk3lgqLrhv2utc89xluc9HOntmqgRUG13YLCzsoqk3iIXCbH8fIh0e7t7kx0jlPo/Ha7OoboD/Wv4W0YWreeS1Gfz1tbmgKVx9wW6uOG7ncCHWpdmsmtPAqjkNXGe6uK1lERt+7UJ5I4xxaj7mUX5ISFyvDqKviYAFv/hENfev2ZNB6qbatnPx6d3pCdOaxuV0mb4ohssviWseErMqIKVy49/O4bvnvsWiie1YUmBKhTcHqllV1DyM6lEVybFTm5lW0cOhnsKsXLwqbDz9/Y6zz2FSB5e/nZSvDAacZ+kp6kPrL0ACv7/qeSaX9eFO58Q9us3XztpLeafk3q7ZTo2gMnNXYQc8aIuD/Pb05+jT3fxy9wpCUUcvdvi8Q81Uo691MEHw9f3O52TO1tSEIsZLB0lV4f7nZvPsjCnM9g8S3VzIxsYaTFth+bSDXHnMNsryIjR0FvPAW3Mp37iHDactIy49WKoGtk1iRjnuAz343znwLzELybjCz5oWE4+5yO+x8ekG0WT2rn1cUwRChTXde7h0wjEf/Xf/hn0snb1Lk8RTGhcv2cUxU1oyohxwFuv98QIOJPKdolGNBTuczwLuJDesWMfZ8/fh0U3aBoJ0RXw8v3UGajiN6wYnZHWpGJV5xOdU4NuWrWErLAmhFO88V0iLmZ8hJD3antk6izWuUs4qP8inpu3ArVvomqRqQooLP9fNGVf2ctOZU+lscWNrCqlJxaztmsLxLfvwlJpE9uZnRUHXn7iJ0rzszkavanFt7R6eW1BP4pJCUpcVpZ2qM0YR1cXRhZ1s2JuJlx++J7JfKgH/MuGnzIgxzD0sBdb6fOiCwJ9bUDqM4Tyu8s8B3K+EiPyqZrhhJeM4quSsi3uY4R1gUkk/B7qLs78EFPnj+F0jUeDNNVv5dMUeXuqbwMLACCSypMJACKcTOZcVlBgoCgTzTa49dwf57Z08/ttyjr7iUAbiZrS5EibHv7uf7c9WYaYU1L/3w9/7s77X26nz4ZoAi5ePRIfLyht5aetUpOIEBso4HPxDlpxfweD0kYacjsEgNz5xFgVndhBQDLoND4/NfDUDvrm1pYIXtk3jJxe+zq3PrOBgdyHxIeSObpDnTTJx6w4O5KK3BBASkW+gHjWIvSWIjCoYq7spuyXCJ9wHmVLei0vLXCi8qsUnK/byRO8UQtYYJ2eCelhjdnUn72yexulz91Hqi6WdfdqkRGoKtt+FGs7R4a6ln+HogG0on5jzHsCa6qVb03lrIA+rsQhswS1nvMs5C/YOC+NUFYQ4ZkozX89bRfygF2uIQFBRQIHk5BL0tkHc+4+MlLGKPLz2+AJIKfhdSS5espPHNszNwU81TrXMK5H+9G7x/8g+ls6e+MskDI2rjtmK12Vi2oK1DXW09udRXeg8vOX5bbiERVJqCBXEvAiunV7++pmnqCoMDU/W6sIwVQVh3t9fm5u0TFexio8AATMk/3y8lClf6GVLc2Vuhy8F/S4X29x5rI5WEpE607wDzPf34nJLVNXicz9t59s/WUpqUjFGrbONW/PeNPQZoSwcsa5aFAdyt7ADlOlxVA+kLip0RNNHTbADiQK+37wMfV4n6rvjHyNrGFZHsKZ5xo3GM3jskahHD6DfE0FpNxCjpOmECdKy8d3ZiVLqMFMOsVBquo3LI/nEjR0oAr5wyga++9TKYTbCIfPoBl84ef3wez70zxI9yVVlTt7TTDv3sz/Vy9pX80nGs18wt9dm7tEj2H7dBZfe0M0bTxbm5NMHaGlw89Xzp5BKCMxxdgxDZqQUulozr/3E+S247u8nVVOI1FQ+OFjFssmHc3LQNPYU0Td/krMTUCXUJGBAQ1QmiVguIpaLMj1GWVrlzJbwvadW8O7eehKGyrfOfJd7r32aN3ZN5vmt0zAslRUzD3DW/H28lpfHHzfVpEW6M02YYM31IjRQFofxtCX54qVtnFd+CAU5rMc61kypsCzYyav9dSM+2AIZVZHNXj5I5bHpUBWPb5wzdCaGtEG1lgECb+7PkHoEsPNVzGU+VJ9EfTMKoZFz64cHYGntOKNvYy8XToziscFlM6uoh3MX7sWrj0QZqgLhhM4Hh6pzM8XqKvF51Ud29rogtngCpBRUxeLSo7Zz3fJNHOotZH1jDYapgpBoikQRNoaljMDGbQkqqEvDqEJw9P+Hsx8xKW2I/YUZladRFIixv7OIGx46h4ShYVgKumrj0U3u+MSL5Gkpug3nFtXaJGdO3k9ZfiQjKmlL+vh163zeK6pEO7sHGVaxd/mRnSPRidTHZ6AEOBDL5/q5DTy1eTb22GhVSPBZiPwUu5NFHGgrwJCOFmalK8bdk99lz6FyvrXxVOIna2mBk5HzGHvyYIwwg2EpJE1t3AaPhK06xUpf7sgnKTVSnysnuPpgFmvoeOZ6I0TykkKkLjKalsYlOhSglDkRmjnLA6Z02BhtZ0iUhhSD02fhmdSJ+3A/ef4UBUUpPvvdNorKnRf+pBmH+Mqq9/jNq8cOp2UsW+G6Ez/g3IW5i1lD16IiMWzB3GVRzr6mh+cfKHbI66TA5bZRNckP7juEqmb//pbftDB5TjaHvJRw66cnEu5Xx90pjDZ/nsXyswYzxiiQb/OZGe/iP6GYB9cv4rdvHM2CumeynmXCVPl1aA7qWT2QVLD3eh1epLkREBIVi0IthS0Fd7XO4+LSA+zYU8U7e+tJGDorZ+1HCKfZ5/S5+zl97v6M4592WT8P3VVNpFdkUCFLtyB5XgEE1eHxSFW7+H3XPGbkDTLP33vEe1aFhJiC1KXTpd3k0E9Y6Z1plv5uOjo3q/Ix6wpxN4w41cQlhSSvdHL1KKBPCuP9bffwLlHri6E3D2DUFWQix0wLdTCO0OKABgYoC8KcM2kHLjW7VtUT9qFrNqlxyli2f6TG4vQqCKSiIITEpVj0L5lEalIxqrC5+6rnmVvdiUu3uePyl9nbUcyafRNQFcny6YcoDUb53dtL+cfGOc7BPDaUGOiawvGlU6kPlB1xfP839rFz9sgwEOcLp2zgUE8+Nzx0LoPxkdyfYUEspfPlv51NauVARvphVe3BDF3THsPDp/etIGzpI23OeRbKkhD2h0FkW5o1sciN5pKYqRyVdLcgtTzIz3cdxRdPWctdbxwHpItPmgSXRD12AHDyq6ZUWFlwmE+U7qPMFacz5eOJjbOIpcZixCWiOIU6PYa7KEkyomM1+JGH3YDguQ9ncP6iXbj1zIUgaSs811vPcNQ0jikBgajXoPGjIXREQhK8pYXETypJ1TrjouDUPHKtgUIDc5mf0DmFw9chLPDc3YXrvYjTFOZzk1w5iSp/F/kv7uLgbh/KmBD3osW7OXv+Pra1VBBNqNRX91IbiNKd8lCiJ8bdxSuCdE0GPvu9do49fZAXHiqmr1Nn1tIoZ3+yl+Ly7HsXAibNypayA2jc6aGnXf9Ijh7gtMv7SNoavjEqO5+6pRNF6eSUuYc47zdX8vkHzuWWM9YwvdJxdE2JAHe2zmdzrMypiXttlDlR7BZ3egclkSj0m24sVJ7uncTzfRPxrg6kd0GSm1auH3dsACxVpfe8efBmK67mfhAS6VNJXl5I6tyCjO9KBAmpcWvTUp6c+fK4x9Ww2fyYG70hSiqvDDvPk/uLo8200mRsKvF5VcPO3jjKT/KKogxQhbEyH+lS8Py5F6XfeXbuXe0YlWmYcBoW7d7XhW9jE/GqYoxVBaCBUm6QXxzLWR+pyI9g5AACDJkyGEcqAqvAS/TYesyyAHpnGJdmYtW4SZoOeeKpcxqYU92F1zWqwa2il+kVIwtkNKkR0FP4XAaxlA4pFdoUkh0eSrVqWPivh+x/ah8/Zy98gGDJxDb++NZiUqZKtrcRxE0Nq9WHMkotfqzYyd86pxG1NMfRj/61BsrcCFabGyyJuqcHs9qFbLMyRCSk6mwzU6fm0Rxzcdcbx0BxClGeAkOgyDhqJIqdcCPdKgL4Zs1mVhU2DwuSl+gJfn7Ja/zhzaN4ZN2CkWuYkECdEwFNkkSFfBt1fhi7PIW9KehQGU9op7Z4YFg8O2VDa9LHHzvmOLS1toXhy52XdblsSqoMIh02iVj29jXXPsYTTfHYslewClQsqbA7VsiPW5Zmia0MHcGucWeohUkg/rVylIiFsjvFSYub+fKp6ygvjNL+eR9vbijjtffLWHB8ZFi3FRzZwaX1rcQsjX7TxRV7T+OTZXs4q7g5x3kzbWjtmL00xuylsSM6wCEzbAUzbuMZU4/u6dCRR+D8HRozW1eInDSF++Uy7r8byoJRblyxnlVzHV7/oWsoDcZYNvkw6w7U8Kl7L8LnSqFOiBGbZmR1ggsNlLqhuaxk6JLYKCSlQjTiXLDPZVCWl1vQHRyfeOE9VxBRfXDqDERNBLU+AgXK+PKCOELxh5IB6j2RrM/iCYUXHy4m8fswPjuCj1aS08uIHj8p59ZP7Yngf+8gWmcYcFglYwtrhj9PXlGUM2VoLg8SPiaA/WwBEnUEMWRYeDe14N3ejrAldpmGeXKec+r06TdGyjk+vz1L+zjgSbFydgOv75ySo7HM0Tro/+RSpHsU0q6mAMOwEInEsBc9Z8Ee9rSXIiXMru7EMyYQW9tQy9cfXwVIUpaKsIc8kgOd/vvbWzl+dj1HzajLuob/hH3snL0QOtJ1FDK1jpSlZcDYRpthaDCooqRTelJCczLIokDP8Nx7c7BmWAVqrKm6jRW0YFB1iMFswG/gebTPgS0qAuM4P4nPlToCFYMCbAvRrCB7XATf24++K4zUBLEfV2EVaEz39mc4+iHz6hY3rNjAS9um0R/zgWY723UVMlyuBlpVgmnGIEaXmwfem88PznsbW8Jgj8Y7z+cTCWvMrT7M1sEazjrxEM+FJ+W8R49qce+D23nnmQL+8L1q4qM6VxEgXZqzTbKlk5LxwLfub6aozGSoslqsJ1APj7N7kCL37PIoxD9ZzKInG/nRhR+S1HX+69AJbIuW4Cq2MM5W2Ns4kdsmraXK7dQULOmwXL41UMnjPdM4nAzw+kAtZxQ1H5FvfbSN9jdH0tgAUHRIGgqeMVJPhRMtEik1K2gYul0k2G6VgcsWIt1pLUcJ7YN5/PifJxFOuLh46S7e21/HX9cs5FBvIUX+OGXBCL0Rv9PwVS4dx96Wwv1YH9oHMdAEqZODJM8vhMLxlHZBBCxkn5oTFZZxrRL6QyONh7LDh5yTgHFUkofMsBWu338yZVqc79VtZLpvEBsIRXUe+1Upz9xTMnREANx7utCb+xGmjR1wE59fTWpyMWpfjPxnd2Q0MWm9MYJvjqSa1B0xtK0xzJkezHo/ssPjdFCXpcBvIfMVGApSbNvpMt7VOYyaS52alxWtvNpfy+crd+AWVgbMP2kr3LBqHT0hP9sOV2DZCqpikzJVZ+eq52CyMi08O9swLvNi7fOBFNz82Bko6UK5LQU3rVzHpUt3AtAZ8nPL46uy6k8Z42taPPrWh///c/ZCiOnA30f9aRLwfeDB9N8nAoeAS6WU/enffAv4DE627UtSylf+o1edfxeptmMpDUYYV7keCU1ezH4dUZNgwpQeVhU2ZbzkR5rYLs2isrifpnApKCrJpQUolSmMM/MhLsElhqNWcSBJ8BdtaK0xx1EWqqSO8mH3aaiHDZR2A2uGh9MLm3ApuRODti04acYhnt48C1GRchaXHO+srUBiRpKC2SH87giHjQDbHtC59ydVIBxBCZc7wZmXbefySzt4I1ZH2BIZuxe3MPlK5RaEhMZdnkxHD1hBD1fc3MmLz1Yz2Aq4ktTe5WXu4syCrq5Ifln/Pl9pPI6EqSGVdHNXOsQdl858spuf/2Uvbo/kur0ncDCRh4k6XCBvSObz2f0n86v6NRS7kuyKFvLXzplM9IQ4lHDglevCFVhS/Es0Sy4bLVyeJfRtK7zXV8Hjd5by6+9sQ1HB5ZaYBmzwVWNNd6PuTgwrT40MhsCc7sFwlzj0FmMOnDB07n7jaMIJnXtXLx2RwIt58egGCye0s6T+MI+76+hvhMAtLZCUw+Ua9zP9qAeSxH5cNe7Aiukx5DoNw1J5v6GW46c2Z6UtpISOUICM/KapYK0uRF0yiMyzxn12FoKw5SZsubm+4RTKtQiGrRK9qAMlkqMpzZaokTRFQcIk8E4DiY4QajgxzLI69vtD5nmwz6Hd0BSsoIfQubOcBXSvH3xm2tGnHyICxbAc3qE0zYJdrmf11SSlxmf3n8JPJ6xjkjuEYaq4dIt14TLm+Hv5/SefZ3dbCS9sm45lC86cu48H187nrd1TyNjrSgc6a87WsRpG4J/xMY78rteO5uLFO1EUeOqDWY5O9L+wtt7Qv/zO/9T+pbOXUu4FFgAIIVSgFXga+CbwhpTyNiHEN9P//Q0hxCzgcmA2TjP660KIaVIeoX/537RDXRaf+uVVPPyFf/CrV44fJ4cqHE3UPhdlZor7zngLr5I5wVYUtPBE9xSMHF7Vrxp8bvE2vn1olXO0PGvkDfCNnE85nHJezMTIkiN6TNyvh4l9pQztgxiu5wcwjg8QUI3c9N6Aqtj4hqCEqjzCSiQ4lHRESbbFSnh1TRn+n7ZhjhKqSMRUJlSGqQtE+ev0N5wC9GAlNoIJ7jA3Vm1jghnhv2+s44O3gyPXoEoUTXL8V23klGLue3wjXzhzFl09KjsO1nLF2joiCTdTy3u47sRNLK1vZUGgh58WbeDL757qiLzHVOwWN+qJA+PdAKppo2qwJVrC4VQwa+dho9BnevjU/lOR9kgvV7fhcQqA0olBt0eLWBTMXTAczTKZyyzpdPL6FRNLCizp6P/ujhXyk4ZFyAMDXH3RUk79usW0il4mlffyl20LSH7XxPfdVqplmONXDeL22WxbF2DjcROptSLsbyrObvIZdU1/emdZVuSdMHQ+bK7kk8dvhkgN3ru6IZ4ZwggDJ5pNSvDkvimlOAVVIez2fG5/9Tjm1Xbic6VwpwEJSVshZah844lTyUrURVWsd4qgJIl2dGgcce2R76ekSrsRgJiNL/7RFlxh2g4xnjzyDsK53/QxUzZqf5zAaw2Ez5rlhI/hUf0h6TSN7XcRWjWDvLd3oWExzdXPXtOPOYbyoz3l59O7VlC1V1BspuidbbC4vJMTC9rZ1lLON544jWjShSIkz26eSV3xQNa9DxeVlfLcvDeutKSnoQ3/bG9HCalxlNWGTUpm1P6/U6BdARyQUjYJIc4DTkr//QHgbeAbwHnAY1LKJHBQCNEAHAWs/Y9cMfD2e7tIJlUq8yN8+dT3+f2bRztU3OMM5ieP/RCvbmS9+FeW7eOlvgkM5oh8b67+kLnawPDfZFxFBLKjEfdDvZDKnrwiJfHe30v4njqC1zbhfrSP9TeWc0pBK/4c2qmWrbC5ucI514B65G1H+kMbBeUfIYxkNgFVV4tOPCao9MX47/q1WBIsqeBSbOIplcbuIr7x22ZefLiYlx4uIhFVWHBChAs/103N5JGC4n99/wD/9dg5WHuCtKfHaHNTNV95tIyvn7GaM+bv460tU2CHC7UjCcLGrvQ6xHOlRnbTbcqmbGsf7mU2O3qKMMaTTxz9MuOkNSLPRtAaEnjLdVLnFnJ/YBYzfe9npcUShspL26ZSYvaxYW8VW0MT8QUtTp/bwOlz9+HRLVQBgXRXs5LeHd5xeD7P9U0CRaIEyjg4rZQ/vaswqbSXuqndxPJAeBWu/vsgV5TsR+DA6RJfUjmU6KE54ucnd0wlB1M74DAcinF2IklD5Ucvn8TZp27h+F80ER1QeemRYta/ljcczCid5hHmRRqhUh7BmmfS2e7iirfO4hNzd3JKeQtWSuHlTdN4fOMcBmPZXdvDo96jE9ziInhMH32mB4F0eH9sUHbGUcI21jQ3skTHREW40ztc6yPusKT9L+Z2drVI2BK9fRAlksQOuLM+B0BVsCr8hO+ejFZkknSF0E07C04pbcBQaDlYQOe8CBdU7OIrNVtpHwhww9/OJj4GKHGg+98gJytOoc6LgD89H2MqzzRP4cIJDZQWRBDCRo6nFwlgSZYf+3+TwoF/39lfDjya/vdyKWU7gJSyXQgxtCRVA+tG/eZw+m//MUv0hh1ki61w+bLtrJx9gOc+nMmbu+vZ31kCCEQ8hbuhBxEzOOnGA+hq9mQs1pM8MP0N7m6by1uD1VhSYYpngBurdrAsr5OD3QXD31UaXI4i0xhdWm1zbCwyctjEgIXoszBODOJ5op9Nm1SiL6l4AmZWhN+YyGOPN4ioTkChMc4Lkf0iKM3ZousAbz9byPU/aGfICajC6ZwEJzCZWt6DS5Oc8Yk+wv0qLz1czLvPFdB60M01t3Qw7xinwNdfVAZVfoa3/boNmiSR0PjvF0+gO+7ilT8GKdzyATINYRFSEj1Yi/klN1KTwxh8xbAI2il+e+l6VNXR4dWEnaVClTGGAtT1Efy3dYDpqC4pe5Loa6NsvayQ394wl5uqt2FJBbewMC2Fdftq+N1/lRJesgzb73ags72wvaWc371xFKfN2c/s6m5WzGrErVnDyJ1ryvfwbFc9ssODWZsHgFs3+OTJm/hJeCFCl5xc0MalpQ3D3PEAPiwme0NM8wzwTv0BXuuaCzm60BRFYo+D5JEozCnu5tMT9uKZ7Bx7/rFRtrwX4EefmYhtC9RdiXGUnwAEStRA3Z1AVunICUkGEPy+bw6/a1iA9X5Bjih09HyS+FwGBb44v7vgeWoKQxxKBmmI5/Poe3Usb2xEF5LN7wXY9Qsflcsh9LVKDqtBUqvycL0UyuinAAfAMFaGWdgglSMBmccZH1VBCSXSzn4cU8BO6JhIGlKFuIVJUE2lO42FE2knFCYcMrj2k69ybPVh8jQTKeHR9XMzEDkiYSBM00kHRf9FQIIEr50tIhS0+GXvfKTH4vWC0uG6TvbNSTBsAm/uo/C2C8a/v/+lfWQiNCGECzgXeOJffTXH37JuUQhxvRDiAyHEB93d3R/1MgA4ceFUpFR4faej9VkWjHHdiZv40zXPoQiJa38XhQ9vwre+Cd+WVmRs/AxSmSvOjyduYPW8p1kz/0kemvEGy/I6iac0/vHB7PTVS/xhcL8yAEl7JIpJHindkr5rj4KdLqpZrTY//3Idg11aFiry3UgF7jkh1CVh1MmJMRGxRCX3imJX5F6voyGVH32unnhKJWE4508aKklD5cl7y2jZ42KwV+G/zpnC339XRl+XTjyqsmNdgO9eNYm3nymgx/Bw/+apqO3NBFZvR5/WhrqqF/WUPtQzeknVp7jvV5PwbG1HWBLFsFAMC2HaBNc0M/fFTvLbIWAYTPIM8sW6HTy19BWqix1UyUn5rUfU6QWwewT+n3ciknLYcQgJIinxPNbPc5truHDn6XwYKUHa8OLWafzoyhrilSVYAU+6R8KxpKXTH/Py9w3zue2F5Zz5q6tp6ByJ3CpdMc5TW1B3Onn0fF+c45bv4w5jDjLNs3V12Z4sNAeAW7HRVJh5Shd4JGNXYI9ucOa8vU6DTQ7z6AbLpx/CM6oHxBuwWXB8hFMuSnfnKnKc9AoOamxTHN+fuvB97TDux/oQoXT++oA3p7YuQ/3SLhNRmeTM07fxh889Q22RI6Jd7wlzjNrG71es5aovdHDFDZ385N6D3PZII4MbbRbcs5dpngGsTxdiTXYj0+klKXD+PcfCJHEcfq5l50iIVmHJIzv69EGEb2T8DKmwNNDJjyes56bK7ZyVaEM+7aPjwTi/u7iU71w+lZf/WU7XoItNB6sxLQ0RSuDa3YkSSiCwnPrAv6wLCbDJqaUhFcHtrYtI+ARibtR5hkPHU22QNt51TRQ9uBFXcz8z8v6jcXGG/TuR/RnAZinlUC96pxCiMh3VVwJd6b8fBka3tdUAY2j0QEr5J+BPAEuWLPm3qmyzlk6h6jsD/Oa1Y1hcf5iyoNMAE/CkyE8MIN5pdKgM0vbmUwVc/LluXJ7xTyPEyHtk27C/o4in183ApRgU5Sf40aqX+OUdE2g65MGe4oGkjfphnFRNEe59PTmje7tSRw3C6Yvbibcn2LCxgJ1v+Lli4SzqZ8X52SONFJU5b+FFJQf5R88UTFth9KvgxuTUwmbmB3q5s3XBCMzRlugvD6IeSuWMkqQQrNtRybm/OZ5zF+xhUlk/R9W3UOCJU10Z44unzRh3LBJJhR82Lia1PR9ruoRpYPoCyF4Na13AoW5VJVQm8G0/nCXpBiANiXink2e/8z4tPUEmFPbjHpU9MA2QIZtPFu3iob6ZpKSSbrhxUmK2LbA2B3C9E3HQM7memSWZ824T3zr9IHVuBw5Yb7ei9nkcebucuXPnSE5fg+SGv53Ni195CFWRKAK+tWADZ1cf5Lo9p2AELdYrRZTrcQaEJGS5qHaPD2kE2KmXop7Uj7XTD61usGFaRS/nLdjD3W8cPS6YoMgfZ+XsbF1ir9/mvGt7eP2JItwuiS7s7BqTYeP/VitqYxISoO1Loh5K4Xqmn+idtZijc9xjR6MiibI4DFLwnF3Hi3trWBro5MRoD17VZPnUQ7hdI++N128zY2GMa77ewZ9+VMVvv/8+P1OXse+OCuSHMZT3Ypi2gmi10HflGCsFrAoNpdN0tHHTj8Sa6SG1PID3/t4MeDM4c9ks8Y3g9nPCqZzomvyRFKmNwoZwOT+rd7QL32lNsPqJONg2KRv2tbrYt7EC3VNG5c1xSKTArZGaOmru9EhUYVNdGKIzFMimP3DZzm43MX7cbAsnzapOTCDLUtjNHogpUGCiJQbw/akNCRQsqcCn/xt8Ov+m/TvO/gpGUjgAzwHXALel//nsqL8/IoT4FU6Bdiqw4X9/qSMmhOCPf/giV/zwz4TjHor9CTTVIUKb3b2LXWPywE/9qZTTLu0nv9hAH5WS6zY8PNE9mbWhSvyqwfnFjawsPIwqJJZU+Mb571HiCrP69yrf/U01pmoTeL0V4zg/8RvLsZb50Gt05Jf6IWUNO3wJ4BYkbiwhz2Nwcn4rP3tnAiSG4ljBwV1ePrt8Bg+s20OwwKLMFedPU9/mR81LOZjIQ0sf7MqyvVxbvgcLwV86ZpGwFMR+A/dfutH2JsdsnR23L3UF260TOXUadszNA+8vAiQTS/r4+xee4NhVIfx5FtFQ7jAx8aliUsfmO/wgaay53aVh7/cjPBYyX0C/hmjQEdHxd02HG9x4XSb15QPEBlXAwjQVdJdk+zo/f7ujnB8/vJ9lhd082j2VxkQe5VqMuS1tPPbiTAY8hSgJM4sGedgsqIkMDjt6gMN7dCdCPILe7YgJ4imddQdqOW6qg9kXAuaWduNqT3FT1TbOLT6EJQW6sNkYLqPH8FCg5eAYAFKmwocbq7HCAWh3D9Mm5wUTvLG7noSR+3ULuFPcfdU/0dXcu7eCEpOqiUlu+EUrDwQK2BQpzagxuZ4bRD2QzHCSIiXBkHjv6MS4tAQZztGPEjBRFofTEanERpCSKu8NVPF+Zx3/OOYF3K4cdSqv5LTL+vjbr8rp3avyp5PeZn88n711BbxVP4k1703BqhIE4gdwHep1uk0tC2uWh+g3K8DjzDvX0/1YtS6spX7wOvej9Fu4nx4YJZSuYLs0IqdOY3jVH+vnVRs0UJcNZq0BajqKNkyF9nVmdmBigKJJeLcNpaIc26dmIqmkQNdsLli8i0uW7uTZzTO589VjMT2gLAw5inD/QuxqtAmf7Yj8DFm76sxXXXDHX7/+0Q7yP7SP5OyFED7gVOBzo/58G/C4EOIzQDNwCYCUcqcQ4nFgFw4g+4b/JBInfQ4qK9/mhZ++hCoy6V49oShCBjO+H+7X+OJpU/nMt9s47fIBhICGeB6f238SKalipCF/e+OFPNtbz12TV7NwQgcL6jr40llTOLjLi5USw/hqfU0EdUccc7EPa5Kb1PdqCfx9ALl3EGww53jg04VUzLL51aR3+eY1daQSCtPmx1h+7gBuj83GN/P44K0AT/+5hKtv7nS2ze4QX6zczqv9tSRslfOKG1kadPoCNCQ/C6zh5iunYbWYkDOtL5ACYotrScypHMMZLjjUU8Qda47ihmUbKakziO7I0UzlFqTOLshoaJESRMBGPSqEs1cGEirWmmDW70eb1++8WLoqceXDTftPZG9TkMA/ejFfiHHr/Qfx+Wzmqn3MDazn/Zfy+MWX6mjCjzA64JO1mCX+dBSX7fDdXovZR2VGj3HV4+jMhJMfqYPTtBVa+4NZweIjM16lVIvhGQVdPCrYSdjSSdhqFnWxlGBYKsmDQUimi4hpqN0HDTUjIew4VjFOE5SUECwwufqFEF9vOQUZHdr7jOzn3C8MZEXD4GQL1P1J1OIQZldJVirHP2OQZK41UQW73ER4jkCDLcAXtMgrspASJumD1PkHqQoOsL6rEtvlQSl1U1WpMmVWlIIL4WWqiY5qwEtdXOh4oFHzNHlNCcYpeehvhhBhC2OuD6O+EPvD0RHvmALutBjK5PgYfibQsDi1sIV4VOGhO8p4+k+5kS7JuEpcFdhePWdTWcLQefbDmVx97DbOW7Sb0vwI3xpcCrp00q1Deug5NhxHpJm2JGpDAuPYANY1pZRPrzjCl//39pGcvZQyBhSP+VsvDjon1/d/Cvz0f311411P6FZIPIMdS+IvyFyp66Yl2LbWj2VmzuLBXp0/fL+GqQsSTJqZ4AdNy9ITb+TpxG2NHdFinump55KyRra+F6BlvyeLIleYoPRYuF8JUzu7h4s/18WMvyfxqzYbOytYnfBycd1GFgV6aNrnJhZW+PrdTRx3xiC6W6KqsPKSftqbXNz+5Vo+eUsnCVvlpoYTaIjnE5caAsnbgzUcFezkl5PeJxES3P6JKmhOIY7Q2u1cnz2umv0TDTN4paAccW0CcUsnipWZBLLLdBgbSUvAa2c2Jvks1BNDpF4owtXYm5XW1F02q64YgUV6FIvbp7zPj1xLWfOZStwFfSxdsZU0+SMHdnq47YYJJIe2wx4BEszyIGaVD/M4HfP4oJO+eiOM+5UBdJfktEv7Rq7dgsmTBtHUErwfNBM9YXJuwepRpik2VQXhzP4LATWuaNaLqysSt7SIWSpuYWX9RldNrj9xE3e+etyY8RuvMudYJOnmha3TOGPevoxW+yHrUvz8sPmoDAGY9IFRkCS/UIL++ADazhw4IA0UPYWYHkXu8YOEyaV9/PC8N/he/xJajHEWbEvwYX8ZVd5DOT+W6SR7ZFDliT+XsfmNAKF+lf37gihTeija14WuWLSnFPo3ayiPwc8ffYcnCmfz6kAaceIeYWMdbXati+RVxbieHMDzt37ERJVkvQ85zYZOtwOpHn0tLR5kfRyUEWerYhPUDK4s2MNXzp1CS4P7iDj31oEgTAC8FqLEABuHqjvtR8JxJ3Dw6BbHTmmhbs90WszMsRMCZ0fSZSArXcOOXvZoEEjhfjOE/moIkUxTfZ9XgHlCEPME5zjPHf7g/4zeGD6GHbTSbIL4U+zcoKLpbqYvzCSsOvdTPbz0cHGWjJoQkvxik/oZCQ4n/RxO+skVaRmo3NM4l2nRMK+9FCA+TiVeAIXlKX777F40XaKlA5aTXC0sjHdSGXS2agfCeZx86QDHnjGIxzcysX0Bm9rJSa76mlMC+V3bHPbGC0ilX2jplIfYGC7nwdZpzGtopb9Lx/4Xjt4R+bSpKxrgnAV7KAlG2dZSwcvbpxE3dOQhN9F5OpSreK+vJvjQYYyYTXKOH2NVHrZbZIu8iOyIRSggNZvYBdVo94SddEt6i+zxWpTVGsP35ow/5GkGP5m4nq/Zx7HtymJC0kVRmjfm8d+VYYzKjoiEiTBMZEAl+usqhGINX1ey2oV5bj53THgTb0AOR1SKCrOOinPNf/fyl68IbL+L+OJaZ/HS1Zx5XpdmcsyUluznO45f8KsWXsXK+blLk5y7YE+2sx8axCPYL146Aa/L5JSZjcOoECFAUywOJPL4Ru0m9sSKeKl/AuFhZSzhpF4WB0jN9eN+qBfP0wNjbxG7QkOVUZTWPkq7Utx77Vv4XCaJFheMlyJWJO9sm8QpJYezSNqSCcHrTxQSiyrceu1ETFNBSImqSVRh4dnbBZYjNQkM03H86OqJ3L/pA7bHimlPHYFJFkABqYHansTt6cHV00f0hBqsjhy7tYiG/VIJYlEItSZJQDFYWdjCZyt2s+lJL+1NLkxj/PdGAmaNQFkcQVSntTGlcw32Tj8c9DCrumvk+wKW5HfR0ptjoUzYeO7rAQtiN1eAR0G2agT/2IjakRregSntKVwvDRL9VS12jfM83/s/5LKHj6GzJ/k6Ukp+8aU6jj9zkAnTExlOtGZyiq/c3sKdNzs14lRCweu38Phsbn3oEEJA2HI5qIhxgr6IdPOZey/At+0wHtE6bjE+HlZxeWQGaZbPZeLRTCwL9iYL+bFyLH+77iW8vuyDuDySZStDmBL+2Vc/7OhHm4nCPwamUrCvF8P414lB3SM5+9NtXH/uK6iKja5KVsxs5IYV67nu/vM52JaH7/utThSoCxJJBXOWm/g3ypEFGgiBwHaikrRHG5daQAOqYOCShXj2d5DX3MmMil5Ou7SPky/ox+3NvmePYnFj1Ta+2HAir/fXcGmZU5Tct8WHParWIgDvpsMk/qvI0Q8ePcgeBatY5wljOnPkJgb7NJ78UwnvvZSPqkpOvGCQY7+t8/6P2/Ds6sSszMMoD5KYW8kQ6RaGBX7Bb6/+57jiIblsvGLxkHlHcez/O2baKt97eiV3vx5hbk0H0ZSL0kCE7533Dsfnt+NSJCfnt3FecSNX7T0ts9CrCPAIktcU41odQelJ6wy7BcnzCyBmk3fVQZIXFHLZtw/j0h24aWRPHnJ2MgtF4og3Kby5firHlbeyak4DmmKjCEcgvqdD4+E7yxnsGV34FRiGRJmgIA7nrj0YKcGWd4KcO++gw990JBNgnhAgdGqes8tTBUJKBCHk5jyynoIEuTXIj5e9w6mlrcN/fv0fVTm5n8aaPceDqE5mpYKUWVHUJHxm+aaM8UnmokMe+k3URt2ZwPvnbuI3lON5qxu1PZWhzSsMwLTx/qqT6K8cX+XKBef5D9rHz9lLm2fuLaCj2cVLjxRz0ee60V0m6qg7OeXCARadGObtpwvp69KYPCfO0aeG2JoqIRH14DVT4+OdbZB9miPKPKUMz6bWnN8D56Hv/sDH7KOyeeHffzmP7yWPITFJp6hq/NynpSiEDQ3rCLizAdNNQYmJrkvM3LVB53pUwcQzTK4/ZycefeScPreJx3Yk9q4+dS5ad9yZbOnirrY7gf+WViL3TADNSQ4g5Dioh9EXDzKpQJFN6lMBeoMeJqckJ55wCJc+vgOd7h0A4MX+iZxT0oRXsSgsNWg7lBlmuvd1kqoI5Cbn0gXvUcODbyb4/atHYfnccKKNZ08nbb87RH5+lMTUSjz7e3A19eNq6se7tY3UlBKsPBfWUh37VIXy4iOja8aaEBCxNAKqSWvSz7O9E2lNBZjuHeCc4oN0dud9xCPlRpp3hf28vaee8vwot1/2MooAVzra8KoW74cqUbFzczoJSK0M4npuAGFA6rQ8Uivz8H+tBWuKm+SVRRxbuAlXenFTujRkEVA54vClBdgCa2MeoPDj507h4bULOHlmI5V5IU6eeZA/PjyDwcHsa49fV4q6LY7rUO4xtUzoa9WoXRr+COMjkCVDF8XwHBA2SFXm6BkQkLDp3RqAlaPP+REqp7rAmu/LcvTgwCmrj+pkzqjIXgXW9FWOu+qrO+IIE/S3wsQuqUDdn8gJfRUSp7A+YCIL1P9TJA58DJ29qRzDQ3e8BAiiIZWbzpzKl247zKITI4BE05wUQ0GxxfmfzRQcSMUUvnjdbNRdBvb3PYhJiWxsrA32PmeLaRd4kR4NkchNA6yqEMmBaFEUyCu2SGgO1rDd8jOZ3JwXUgiu33cyOjkgdWkr1WMce3qI34xbrJdIVSE5o5Szv7Uvpzi0okChN87cum72tGXSOQoLlH4TbX0U87jA0F//NcJAgDIpjpjvvNwyIbj/zcV8cLCae699+ghUBQqmFOzaUsXK5z9FgZZk/rJduHcYJOOjonu3GJcjCCBq6ty95njwDzV8qSRmVmBU5SP/uQUmqRjVeeidYachyzCdBWRVHuaqUoSAp3vr+UTZvmGlp+FrtEFKkaWCBvD7vfOYUtzPbzrmOw07qKwZrOS+jpnUN5ocqWUoc/jsDH53TbEoCsQIx12cv2hXTt6fkOUal7wPXcGa5SFl5JM6pwBZpkPSJvrbCai746AL4qMi0hOmNvPih1OxD3sQE+LgtpHdLuQhL6Mrt43dRTR2FyGEze/fPJrEux14kx2Z4zXZTer0fNxRG7kpltVgBc77UlZvsCVeAUg0JKapDHshFZtj8zqodEU5nArw/kC6YDlqsZchfVgnOPsECs++UMv5x+4b3u2fcPYgDdu9JOMj923nKZjLAki3QNsed/pljmB9YsQJx1Ma97y9lAHVj5JvjnhQW0JK4r27C2FCqjqfyMlTkBt1IicXAALv5ha8W9syZ4YKImIh8xTe7dyFYZvoyv+NW/7ITVX/r1h7c2FG8bWn3cX3r5nExbNm8+0rJpFK5n7J4qbKpg/y0TdEUPqTyA/dyGYP0gJpCOd/SYG9MQ/lUHKYqCk5tXTcZg8jJZg6L1vkIhEXfPj+SD7vr50ziOdgIkzYCs/3TaDNDFDljuDOYtcCzbI4of8QHp/Nt+9pwu210NLUqUKx0d02R11l0PfpZURPmkSlPzpebRZNWJSV594aiLhE25x22uPM/eGC01DQr4IIpp2kJVH3JsGw2N5Sxur9E7By7OZNCe8MVmI3e7D3BUhGXHQOBHnNXEK4rgSpjirZRewjCqPLkEoWH0OaOCtWU4K7sYfYb8uJ/LyGxFXFJD5ZTOR3tSS+WDa8Y3mgcybNiUBGTXooVfPndxazraWcUNxFPKUOf/bkW/O5o20hSakNO96k1EhIjV01XqhMQr7hQALHKcy6dRPdb4BiOyGvaUFrBOXxfcTjOrVFoSzpP4C5/l68Su5UkYhZ6C+FcL84SPALTWgfRJ0iqFfBmu8DVfBcb/3wXPzs8k1OQbhLw96Yj72mELnXT26IDkip0BfzYftdyDENU6mVQdAFqTPyc3sVIQkUWMw7PsrrA9VURyOY7+dj9ziFzKneAf45+wVunbCBG6q2c3P1ZhRk9q7Oaw9DWrPMsmnbrnLPrVXEoirhhM5x54cJ5I+MY+KCAsIP1hP/fCmJz5QQ+XUt8RtLM6i4x5pfGITiLra1lPPNJ07j4bULsN8vwNrjh5jALU307TF8321F2WmTmF5KeNUMpN8NKODSwKUSH0LJjTZF4C+VXNa9Awk0R48sf/i/sY9dZO/xu7EtFcZ0lCZiKlvXB9m52c/so2MZ7ey2hL42lde/6EKkfZ33g8PE1Amw148oMJGmgD7NaVte20D1hARLrlPZWxLkwB4FxogzS2DGoij+vGwInm0JXryvGGVCEnuyh9cGapnuHeCSUofPXEFiSoWt0RLuap0PCA7F8ihoDJGszXc6D9Oe1W5I8cITBbx1zVx+8MeD/Omtffzzr8Xs2+ZFIjjx+hT//cEqMBSQkgOpPGZbvTnpIRRF0tGUm2JVKiCHIuRxAlMhwIvByuLDLAt28MZALW8NVjtfNiS+P3fg7e8iMbuC3zwwj4XfasPnMYaL14YtiFg6v3l3Gckt+RknkVIldvIUZpyyj7ZHQhByxtv9SA+J68uyuM2lCfbuADnNpZKcUoqrqRfhBnu2h9TsUQ05o8yQShZufkja9OrjtnLOr68mktBZPu0gP73gZboiechSw2kcyhVgC4l2lJOmkDZYrxWlG27EqOPbpDygHNVH3jd7sC0VrT+BGkpgAHpTH3vbijhh2qGMdBzAcXntFGlJ2lNqpg6DKRH9Fvr66HC/h++n7YT/OMGJ8BXn3l/om8i5xQep94SpKQpx37VP8d8vnsDWlkpsy7l+qYzARjMngkRTbLzzA/BB5m3LgAqqQBZpxL5Xie8nac3mlAS3wB+wue2xA/g0iydmvsq6hmpu6p4EhoqvLMbvJr9DnjayiAkhkAZZBWSlJoG1e5ziribwmxGe3DSbR287FcWtowhQy5vxdHRgLvaRvLo4C4BgzfY6WzltFJxn6L5MaN9eyilPfSbzXLZAHvBhHvCxoK6F4MYW3ll4FLZLc97fnKlHlfiSWjw7250sqVuQuKCI82PdXLOkkWdaF+FV/99oqvp/wspqS6ieUsjBHdlsh6mTAnxzw1K+p2/lqAX9pGwVj8vCSMDXzp1CalSKwLOzA+lSiS+sQYYVJ2thm/hXN+I6PMhgj81n7t2FcqLC2kn5/PKz1WlHMdQWBfu3edm+zs/iEyMZeqjJhCDUr+L9YzexH1cj3Qq/bZ/HP3omO9q4itOgszdeOHw9qiKRd/YRsEOkzsgjtSrfSSlN8RD/QhnW6x7+dHuK41YMMufUGN1JL3vq5/LDtU6k4NEN8qYP8NjBSZxV0ISeo6Uf4ODucUiwNIFxcp7zgglyRmfShNIO+M4Cp1h1bF4HC3p7uHPvPHy/aHc6OIHAmoNE18AXXpnC5V/u5JSLBonHVN56vZSH3p5Le2mJQ0c7xiyp0aBO5bNvvctf3p6Kui3uRKaGDW6BsIQTgUuBvd2P7MqtZTD0gORkF4sDXaRshV2xIiyyX+bj89oo1hMoAmxbkkpJXC6BogiENFlYuJYnXrR59N02XnrEjW2niNWvpkCfgLeuBDF2GzUajqmAsjiEvS4/nXeWjpMoNFGXhHA9H0I7HMko3AEE39rPS4Fqrj0x22EowD1T3uY7TUezN1aAMCUJU0VtSOL7WXtmJ7clcT0/SPLakuH7TkmVz+8/mYtLGji/pJHCwhhXnrqByX8O8P7SqfRUebFsBTslnJP1aNiNPlxhuPPyl5ld1c0Nfzub/SdMJrC6EaSNsMG1I4pxrB+8KuYiP6GHJ6G/F0HpNVEnqvz4ig+oyXMWVSFgwYROppb3sL+zhBWDvcO8TUNWpsccahL3GNizRyLmh5Bbgs6CNPp5apJTb4nz8LrZDjFaOq9fcKAPASQvL8qtoexWHII0mwz4pjRB9urIg+MTx4GDnIsdVYfd9K8dtVQEZpkPrT9OYnkpsYJ6+vsPkJdnUdVXRJWv8F8e439qHztnD3DzfTfxtZO/TyIqGP12qU0GvB/lJ7+spbiigjknRLj5l82sfq6QeGRMdAX4PmzFu70dszQAtkTrCo/QVqiSgS6N2ilJBprB5bZIJcZQ08Y0fnhtPfe8sZfq+pHo0O2WzFkWZfs6ge97rRT9PI9WNciA6ebxntyCwklUqr4bpOtncVIr8oYnudKWYtpdDdz6m0bKa5JYpsDllni9NqttAzWSpMg2+OQJm3lXFLL/hgT/PaeG7/+5KTvDocPVX+vg4TsrMnLj0i1InZaHNkmDfuGwM47OR4KzPTIVBvePFCB9qsV5xQd55U4/rZvIsp52F3d/q5a7vzthGJYZLG3l5hu2cPKlITRNsmb/BO57dzGtA85xU6ZGczIPOdVNakbmS5a/Q6cn7Id+jSMSqaQsvIe6+ckP9zJroqNOZUmFn7Ys4t1BRw1JSudlPtF1iE1bErz1XpS9DSORZXW5SmuHRVNvlFRkIqqnmEHpqCdYbQN0PLkBvdBH2TlL0At8CE1FjIrmFGxUKUm5QDu7FxlRkTEF4bcQfhsM28kXp7J3YMKSGK+28fXXl/DL0zbiSS/cQ04oT0nxBXsbv/phNR2mD3enAS3Zi7swQW0Yg72XkqSp8HDbNB5un06+SHHfzNfZ/pkSBvrcWFIBFZQ0kkpWGWjlg7g0k658jWWeFAF3itT0WvrLg8xSD5FMqEws72eLxyBEmkHWq2CszEMXFtO8/czJ68+4DF21OGFaE/s7S5jsHsQ/JjhRBVS82kn72ZVZDlotS+D+oJXowpmZGw8h+MfqWc73Ry0CIr0rH4I45jQLrLV5KDUpZHkKBjVkkycdUGQ2sY02r25w6twD3PnKR4RMagrR4yZiz9UgqKCFU0yr6KFjwMMP5l380Y7xP7SPpbP31FVz8s/y2XBbHz2DbsyZHpTDKdTG5LCz7u3QKS40QQo+XB0YF34lTBu9Pbt4ahqC/GInh75ldTDL0Q+Zokh2bfRnOHuAonLHcai7kph3pPjHHc/zrJzKo93ThkU6hq8hnddtqizBvoOMNG/xb1r5zSN7CRZY6QYk58NZsyL8snM9NwZP5wcnvsWCmjYeWzgbdVDl/ZYCetpbKa3OrgFcdmM3tbNS/PTbk0m1STylcM43+lk/P5+GAZPl+e2s/kMNYmEEc7HPcUaaQGlJ4fpziLILSjKOp2Gz4oweHlxXknUu0pc75Ojziw1+//I+8oqsYdnBs+btZeWsA1x77wUc6C6mpDzEGwO12DkKD0sLO3i1eeoRkUuYNlo0wS1f2Mqy5ZnP9UcTNnJTg4etXSVE34jSt2En17ZvJ88VwaVBdZXGlHodlw7PvhLFMAFdQ+gqQghHDWlfN7ZfIb5EI7yjhf61+/FNKkPx6HhrSihcMpGqyQEWB3pxbwrzfM0sQEEELERgiPrW6RmIf7eKRI+J5y/duNaORbBI9nYHHNKwUW+pEODWbGZNGiRcuRTxdAfjOSKpgF0xJm0nBCJsInfonDS7m+8ftwa3y+SZ/kk5mrbSPlODBBq3H15IkZbkgsW7+LCpglSBh0Z9MklTo00z8bxpMvGkDlo1L7qwSdoqywId3DpxY/ZzkiDThZL2wSCJhILHkxndf2nJbn7yhE704pK0YppAJG08v+3GNPPHpEokIj9FMuHP2r0ZlXm4DvUh+k1k/jjFbQWI6ti7dIc+wWMjbeEIgnts8FrQ5cooDquKRUkwSmN3AUlzzEIyHn9P0ILzDBQ73QJvw5PuKmZry1mSX8P/pX3snL1tS75415O0982h5OtNhCZ6wZQEP9eUhYf3+i00TZJXaCEU6Ty8j2CabrNweZi8QgvbBpfHYrwXSihO2/hoU1TJoX0eLL+L+MJq4v0J1j2fx1XX7OWtwWo6U77hF0vDwqXYzPH1siFSAaPmjNKWYtWyDlwee7jTdMhcLsnk8gEqjQRffvhMqpUewvZhlBIbJWTxzj8LOO/angwuoCGbPjuK0WcjgwrhCi/nnbmX6wOH2POhl1sunILfPoB43sYuVLGrdESfhdpuIDWFhYmujGNpqsRdpWOrCgX5KZafM0BBicmBnV7WvpzHaKb9q77aSX6xmXFNmipRFINvnv0u1z14PnOWtLBJFGUtiACB6SH0nTaWMfaz9IM3bDz7u3j81y9RVZnM+r1LWJyW3MHzP3eTHOgn0deBovmYXpdAETaDYYu1Gy16+i1KihSKC1X2tmpE4o0EKifhbQpjx2OE4r0oG2xEsRvNr2H0hsifW4fS08vU17YycatkcvFE/rptIXx27KVKJ/JMOypZqRP/egXJfQlkndvpEF4dwfVsPyu0znEhwgjJmYsbePKZwPi7HC1NfTHGfLZJpLeUbx3zHD63yaCpk8wx3mMtKTX+0D6H26vXpnnixbAsaCzlIp7ScK0u5aHPP02f6SUYiVEVjOPNUT8yDVi9rQZMm1c2TOSmk97P+s5J5w2wZ/N+nr50EFGiIHQBXSbGhGLiJ43hfRcg+1w5mTbji2txHR7A/fQA8c+XDvPwDJm0QfbokO6Ulwe8+E7pwShLDtdFpAS72YPc43NqMArMnd5G7eZ9PN53SuYJpUTEDaRLdYTQnT+CKlGXOoyiw4AqBTpMHz/oiPLCzCMO///aPnZonA/2tTAQicPkGH1T/E66w68iItnIhW1rAyTiCqde2p8hYD3ahCJHOXPw+C1Kqwy+9qvDvPZEAVcunsX61/LHvR5pw5KTRnDDhinY31PC5qUnMHDZQpRoCu/WdkrKDYIuk79Oe4PPVuxiojtEpSvC+SUHuX/a69SNFnFOFxFFv8WC4yN4/eNDw+bWdGGh0ZwqJbG4jsEz59H/o7k8aM0mGlazOol3DRbwiR0rCT0ymfADk4h/t5rzHr+Eq/90EXZ5gKtv6RiOxJV+C21nArXd2aUI06b13UwkSCyisL5tAiddPMjfNu7iuu+1MfdiQfy0qQhPpgM5+YKBnIuPImBOdRclR3Vx/rT9GOPw2/8zOYHrz1qLW0sx0uYomVLYTeWj71N033omN+2hMC83WqW9w+T3v+zCSiYxooMougtFd3OgqxgpFTxuFV2HZNKmu9cmkZLErQAIQaz9EHYozADd5BWlmDstwcLiQSbnJykyQywVB7mkrp2dsp5Hd9Xwnb/FMHb1Z8cHozDjw+ZWsOd4kfkqslAjdWY+kXsmUKSbuPXcsF+3ZlOlD+QE+wyNDKZE3ZOJFvMIk8CATllBDFc6deJXTQf58hHsQCKfZzfPRFOy3zeJQijupqOtgAWBHurLYri9MgvdZZmw4fUgvXc3E3htD8qfd3LbDXUk4oJUwhmbZELw7j/zee6+UofBttNC6zIIBizOv6EPn8fA50qhqJaDaJI4mp05AjKrxE9o1QzUNTG0DVFI2k6OHgeJR1zB/nBUf0SXZMa7LSyTbcMIOSFAnZBAW9WHenYPvnM6uHnFuyi9SSfXP+om9cMDFDyxBe/GZtT+GMJOIeriqKf0O4p3Y00IuhMhfv7Bcx/pGfxP7WMX2Td3D2BKG2VaJvGRXeMaLhAO2fZ1floa3NTPTLDqil5efaxoOJ0jhMTlkXzhJ4epnZTi3p9W0LTXw0XfCbPNM52z/nAcqbjANa0X7+bDqMaQg3Emk6LY6G740u2tGELDTtpgSw43uPn+F+rID+9B7Ysh0vjD3Zt9HLUyhM9ncXX5Pq4u3zd8nTFL5UA8e0Gxa1yEWlUsy8EojzVLCsKJdFFIU5l+kslpqRf587YTaZ9Wz6fWa3zJ3MQJpw+i6pI1AxV8s+lY7CKR7pQFNBs5L8qebUGu/+t5fK78lYxC9FgbTR9hpKC3U2fvPSH+vrYJt0vy+zeX8si6+SQNlWB+HD0xshDqORgUh+9VwKzJ7SxUupgY7me/uxj09FgjuaD4ABcWNPK7F47FliqKkI4YNNDQXYy+TCXvtb3EIiqqliOSNCV3/aWftoFJDoWAkUJ1OwidcMLF9sPllAajpCIDuFxOjra13aSiYJDWgQKsSIR+BlERTJxmDrchFGhJXF6bcKuFr8rLlPIwHwbKsAJRDsnDTNhejT3XP1JoVIQzvGmnhsdha80sNAqQsJdiEoaO3529eMUSKgd25i4cDh/JBu+fe7CneLCmefAIk8pEmK5v9CEun4madtiakJxV1MTzfRNz7qhGm0cxaegqHlcVzrIFTb0FLK1vHW56tkc9diGc3fCrfy/CI5IozY4zXftyAZ853seqK/qom5Jg1yYfz95bOvpuMFICs1+w/hcpXnn/r+zpLOUXLx7P/o4SVMWmLBglmnQRSmRTKpjlQaTfjfcXHQRuL6LdW4mtCmSnC9nuHkEfSYnWFeXQAybSbSEetqgIJPhs9W6W5zsY+TX9Fby8r5opBSGqpvhhDPras6MDodl4Orrx7mwn/PAkZN6/2DkJeLp1A5dUHsOU6tIjf/d/aB87Z19ZGETxWlhjcjaJK4vw/rIDa6GP5Bn5yKCK9mGMW76gcPMvmvjMrR3MPiHG838uprPVxeSZcS6/sYsZi2J0pryc+dcEj/6hhLsPHoMlVEc+zA3J6WWk6ovJf3IratRx+L6gxZKTw1x2QzcfRCfz478WUdV0kIatHvZt8QImKpEMd/n6Pwq58uvdOESgI2bagl2xQj6Mjsp5R22ELpBewfO7azgl2Y+ag25BFZLV+yYM/3co5eWiz3ZxXOtzXPn4J2ifVMSP/zKLZF8xhXNNdA+OWMiYXKLQQJkdJdlSyN82LUJyKDfruirQpviJhhya4i3vB7j9S3WQMDm4zU2yIshD7dOxljn3HsuvIvjbBpSYhV2msbW/mKXenpyotHCPCrf28v3YRNr2hAj+0Y/p0ohLjZ9NXMuyYCc/fOoU1h+oydJwRVMx6gowC7yE+uLs3eZn1uJIRr/Brn0pOrosUPwkBzsQY1ZP01boDPnR4wMEfI4nTyQkfi2KpuRhCjBIUFbiyRobr0fQdAjizfkkEhK1OAbTvSQHQyT2deEfKIWVfkwUrH4N4baZU9RDhStGcyiPvf1FKIVjJZ0Ea0vLCcXdeHQzg9LBlmCYKu+/9BG6dVMS1z8GKP6OH/3pfvruS6AIjfiWAbYfLmNBXQeqAjdVbeODcCnNqSDjLfQaFmcUNuEtdqOpJmYOh68pksr88PB1HuouoKGrmOJAjIUT2pHSCVKmXR9k424/sj0+fLaedhcP/+rIzI8yTb62e52X2gUhGjqKuebYD/nU8R8iFJv1B2p58L2F7OssceaJLSGSpGhdA/MW9xMJ5nFiQQv7DYtXtk3L4qd3ayZqpIfUCQG0bTFqf9zI75/Zi9dlDkPxTytuYfm8Vg41etmyYGpaly/9odcieVOA+NQip2vWkuD7aAkUqdv89oX3+PX153+k7/+79rFz9stmTkC1VcbSxJjHBIj8tg5ZqA3n5FL1LrrOyedH39UpiMYp/mUezd8t4r7Jb1EZjGLYgu8fOoq3B6vRhU38dA1pD8LmAAwRLqkK0g2xpXUE324ABL6gzXfuaSZlKrzyjo/Vq0vROz24GnpQ0n3RAof+1O21mL0kxjEXR/nSo2fzy8tewa2ZKIrEEPDD5qN4P1zJ8GSREn19lF+evIGn2ifRvjCP118qZsXpfcOUwaYlMCyVW589mURa0V4RNnOqu3B5JGVVSS5auIlHInMoPEvj1ovWMDswwNk7z2K8FxmXRBwdpm9LMf76EK6WgQzubwlIVWGddx43Xxqjr01joMc5t9dvsb85wK85Fnt6gqEGQHkChOfVE/h6M5Hbq7knlMe8ynfxjtGqS8QEf/5BJTve9IJLUHyRxl+XvsRf/j6Rd//g5/aOYgI1pRxcWY81XveoIjBq8kFT+MHqM/nrnGdwq+YwH/sLr8aQKZ3UwRimGUF15YiKpURTR4TlVRX6+y2CniTx/iQ2Nv09GqF+jYISk/LaFJomad7vpa/fxpAuFBS07jjavgTm0ToDrk5ustqZY0b5jXUMyRLBndPWUKQl083BkpZkgK9uXU6PNxO6J/PgC0+fyF3nrqEkEHXy0lIQTeqs21dNYly5vBETEtQ9Jv67umh/TRKfXU18SS0g+ckzfv762WfxaAYet0VCHkHkxLYpcSX4XOVOIgEPj62fR64Ek0szOXpKC/1xN7f8/XT2tJWiKdIhTnUZfP3Cd1hU0cHWtmpMIzSuAzpSD7JlQUujm/uajuaLp2zg8mXbcesm33riNN5vqCNu6CNHEVDTeoBJX/Tx/sHj0VSbnR86mbTpZd3s3ZeH4hYIv45tC752xhruXjmFWMRP3meb+NyNLfi0TBlRVXHouzVps7FvVO1At1FP7MfW3ZmpuvH0GHLc9Mbd2aR8/yn72Dl7TVU4qbiSl/p6oNjMgBfKqjEJYZcCmiR2cyXKdYdQvxsmfNYMzOsch3H74YW8M1hFSqrO9lUFoUqUxWGsNSoMpieNopCaVAxvO01RWjpNIKXgpW1TSU3LI1VfTHTZRPKf2oo2mEBRneYqEOzf7uO6H7QTG9zP2b++kkUTOijLi/J+fj6D+WPYGIVAWeHDU6Pwi0WbSSUFa18J8PMbJnDup7opnirY3V3OQ+sWpvV207eqWVx93BYAPF7J2UsOEO5x8a2pG1HTSDR9PLFc0pdQaiBOMYhEpuDd7MBSpQBhS8wiP5FTpmJ7Xew/WIAaHkmZSeCtCZOJK0rmraggCwThX9Qj/Da7k8Xc3Hgc367dRJGeGCaU+sutFbz9bKHzcicl0ScT/N6q4s2ng1hpkFNnqgA7JTMK2GNvQFNt4mdOYzDs5eLfXcFlS7dxSsVuElF49gmVvqZihB1D5Dmpk9GvoCIktUVhejsZ9jSaBvGETaV/kK6YxZCigWUJ+jo1Qn0q5bUpQv0KUsqRYrQN2BLvZoOop4/zf58i4LZp3+TnHzNeIF9LZfiCSZ4Qf1jwFpfuXZWlZNWtSa7bejJnWR1oqoUiJEdPbuHcJftRf1DEH2+tzoDRjrV0WwKdr9skJ5QQX1yLsCW+1Y1ED/ZyzeZ5XLy0hbpTLAaN8aGJMmwT+F4T2vMW1YVhvnH2O9z2/IkgIWVpePUUmiq5+6oXUIXkqw+fyZ7OEkxLY2imxFIuvvHI6QRO62LGxBBmgRe1N5qbaFBxrnushi04Qcfbsp499S5uP2YbHtXijV2TeL+hdpSjh6Fc2+EpM+g6KElZGikLkBLP1jZaPjxMgWIiLSidbPPt3zYyeWacX2+bgf52FGybZaeFc6ZQFQVqJyXRfzGIWe0HRSAmxh0Ft7FbV0WMg84ZoswQSFsg29xoOTv1/jP2sXP2ADPygrywKYC6csCZEEcC2SgCu0THnOIldDCO3W3ywrZpXHLsdl7qn5A7R6mAMjWG/UF+xnEAVM1mxcX9DkfGW0vpCKW30rqKMhhHjThT2043dCSiKsmY5HtX1fPHtXvIq4vw/adWIps11NN7c157CoXHwtNYULIOl1sijw2w9quFrH81D6kphFdMxaorwOtOoaS39z++4A2mlI1wu3t9NrdM25Qh2HRaYTN/7546LNYy2jzCJKFoDrAjIIgfNYH4ohrUUBLbrSH9aUcgbSe0SpsQkmCRxSatIicqRCggC0dERzdFyrho9+lUu6Jowqalz4dnTyc6I2RypiF47fHiDG8skuY4kn6OzanpILFpkAPaRAD6oj7+8PbR/HFwPv4XtnM4EsYrVFyahTseo6DUpj/uw7IVvC6DqoIw+b4E8ZBCImmj68Lp4kTScsCFJAaIYYcuEZgmdB52YUobHXcG8ghASYE7ksKrm1iKxn/PWY3LtnjrqQJ2bvBTUGpy6iX9VE5IUeRKsDTQ6SCyhkwVmLO8DErBObN3Uu/NJBA76+o+CkoMfvedGno7HJnFXPHwsSf2s/UFF31LakFTyHt6W7qeJOmdV8SDvzax/+4i+QsxrEyW9RyTkoEWlX/cV8ZlX+qmelI/vpVdLB4cJJiymVzWx8q5DZR4EmzcVcqethLMXO7FFkQbA2yfKrCu13F/u2+YmmTIpACrwI0aSY3oPQ99BqRcGhvn1bCkoBszfb+Pb5gzjAzKMk0hNYo4zbOpBd/WNoRpD/++c6/C7Z+v5VsPNvGVwGYaJrhZ7XKh5kASDY+JgMId7cQrKp1mrMpUTh3a4S+PuZPJ7gEuLjnAoOniDwcXYG/3c+qyaeOe739rHzs0DsCKMxbhaoxh7/aOYk0Y/6FIIQhfMJNkUYC6eAuPrZ/DzoFi9FxhA46DEoWjNqlSorc5mG0h4KiLkvzXI2fw8LoFGb/z7OjIuWUbyjPu3+DhlPIWqk9oQ9THR7Wkj/k+TscnQGM8j1tblxH+Qj22y3HSea/spfi5Ldxy2mp+euHrvHbzX1k+vWn496mUICL1YWnDIbuqbB8FWhItg4JP4hEmP69/n69Xb0II6UQoigRNxSryjTh6IaHEJPGdMmdb7rfIKzK59aFDmOMgaHKboDUVoCmZh43IJs2ys5+m1hVBSeVGpoAkaer86p6tKDLznu18L6HLF5OqLkCZ7GflxQNMmqMRiTs7gaJAjIkl/eT7nOajogJluKAopXS0cE0FiUQZk0KSUmCmnAXBR3YLv0Qyy9+HyyVwqzZLgj0opmTJSWG2vh/g73eXcf1J03niD6W4FZPZvj40MYIMA7D3+rBDGj9vXEQiLjKKnYYpmHGcQf+Zc0gsrEDRHXQZo4+gCFo3Q7w4iJ3vQWsdROmPD2s0mwu9SJeC0pwc/xUynNSikVR45L5art5+KjccOJGIW+edshI21AfYVebj9tYF3HzpFL52y5Lx2SZtAX06lqIgZ1pEl9chVUGqMo/QadPpv2whoTNmETprDpFV9UiXQLqGitkCERREf1KJqWqkRs25gdi/ViVz7sUadvSjbeXF/fz21X3UVCY5f3IzX7yokb9t2sPB3eMfVwIPPL+FyZFDDmX2+BvnLNNMi2sr93BB6SEuLz2A730vWgw+d9bRH/0g/6Z9LCP7iollnJffxsoTdrFgQjeWFHzlwPFsiZY4LfFjTQV8CpHvTaQg2QZJk+8/dhLWidkkZkMmUwrTK7r50qlrWTyhDWnBxjeDvPxoIf/cPYtNTTUQNHHXR6kpH2C+r4dda1N0j/PCSAmdzW6mHp1gYX4P0TkaCVsbl+kyX0liGIKX+2odMe5lCv3dC3E39aP2xlC7I3S9FubUL3XgGoU+sS1IKhpxqWZxOxVoKR6Y9gb3dc7klf46DFthXqCHz1fuZJavnw/DxQgkypQ4docbwipyqIlESet8LgpjCQ9Lbk6xYkI7J5zlqG8FdhijRDXGWFIgNTlu1KOOUViyFYe7fLQJwLf6AJHTZ+aIkgSH+/JoGCjj6BltvNc4MfNTRcVdVYNfO8SOwRpaUxqReAuqWyNpaPRHvUws6afQl8DnVdB1h5sdIBgQxBOSWExBzfGsLCxUVPQcKiC+/CgnLpUoo7b1Xr+N2wM/fvAgnz5uBiB46PYKpi2Nc9n8Bs4pPsi9rbN4fqAeGVOQB/zIA7DdTPJfm6dy7X+1M++YCAYar2yfwp9XH0Wv7oNFhZg+D/73nOL60BmFLWk95MGsc9IbeutghqNTG5LEvlWB/9Y23H/rJXlNSWbHqi0hZeN+0umAtZKCg2/VoJ44MPwYugwfrw3UoexPEHg/jlobRyoKBE2UWVFEmZOLk9069i6/06QEYAtSy4tIzS9ARj3OVQuBne842JSnjLwvKpyif0CkB1yVLh5fPAfb6zyHbaNADfPrOjjUW4CVi2d+NNCpJ4oUmXuwqvokN952GLdnZM75XBa2BqVVkIiBx+egtg735VEciFOWF0VVIb/Q5PYb3+HK620SVeXIo8zxo/tRZkqVxr4gKwqcYvuckk4WlZ9MacE4fE//AftYOvud7z7Ml3/yLh63M2lUIflq9Yd8Zv8Kp917lEkTMATK4jCokjZRgpsIZoOJ3SSgVsnKsUkTZobD3PPpV3DrpvOxCkefGmLJyWGe2ehBmxNCTEwgVUkTPrqUStzTelB3hXNGNUJA1aQkIEhJBQuFKneU5mQgg+YWHHjbZWUNqKrkitL9PNozDVsxCbzTQGTFdLRgmLw9nTxxdynJiOCqr3Xi9tioKuzZ6uPHrmO5qPogs3396IrEtke0P4r0JDfXbOHmmi1Z19iUykNFclpJEzd+/nnW7J7IS1unEUvppMoNmircCJdE2grdswtZsWr38G/PLjrIo93TGJtGkCbYOwIok+OQZ2bSFSdsPL/rQpgjL5kjvqw6W/sxtJnS704TVmW/0HFD5+39k5ie1857ckLWgpBXN4Oe3S30GoXgEii6C9s0UDQdKQUJQ0eSRCiS6gqN5sMGSUNSWabgcyWINHiQY0JfCxPbr1AUL0bk2KVVTYpx+inZeRFFhcJSk+kLY+z90E8qKXjhviK+/ftmFEPnlX/Ow4q6nK7NdNJdNGoc2Obne1dPIra4hviC6sxx0FQ8u7tyJ7ps0FsGESkrTfbFcBTvfrSP6G01hP8wAddzA7ie6cc4PR/pUUAVqA0JvHd1oXSZSEWQmlgEERXZoyNKR0FCEzbuh50FQY0kIc9EXT4Iqhx5FGUGavEADHezS6TXhk5vVt1qyIrLUlx9eRvfefJUNveWY2nh4Xs0pcJtLYv4bt0mrjpmKy9um5bt7BXp7EgtAJHF1glw1lU9OdM1igKqLnnw15W0TJvBG3unoKsWhqUyq6qLn1z4BhX5EUoqDea5mth3Ww+RO2qw61xZnD5ZZtjs/adO9NMKwiVJ2TptlePk0P5D9rFM4+R77hx29EM22Rfmtvr38WMgDadZQlogI6ojDKyNTLokGladCxkYmvhjHrQKt5y0Fq/LzFgHFBU0XVI6PQwTkkhVDHfYxW2d8JlFWDkmkxCSghKTOUdFUYVkbagCAXy2YhdB1cigNvYqBosDXZxR1ISigFuxODm/FbwKejRM4d8+wL+mMZ3nFDx3fymXz5vNZ0+cwRULZ/HtKyfR/q7CP1onYaWJwwZiHg5GgvSk3MP0xAApUyE1ii66SEtwUv5hvlmzmVJ3ggsW7OFP1zzH3657kgfPfoElRWmZQUXQ2Z4Zxd9UtR2fYjjdiEOU0SbYu/zIVg/WewXQ4IGIDXEbdXsM/w/acL8dGWmP0hSsfC+DF8zFqMlHjqFMUHV5hPqMIGWohA8Y2c8T8BSWY6hFJKJxhBD4y+pASmzTcVglgRgiXSl0uwWlJSoet0IkZmMrJhXeQjQ0TAwsTEwMhKISOG4i9kmFwz0BQ5YiSU2NYO7M3LsdW0J5jXNuaQtaG92ETZ2b3l1JIuxyWExD+nAdJFWdj3Q7sVliZnnOBU+Jjq9sIxWBEkuRnFSc4UyVFhvlrxZmYyGxo+pIrixGfytM8KZmglc1EvjaYdSm1PDzScyvAktgd+mQkBBznqfrkRDWoOO0bZ+OMiuS6ehJY+w1hhuLVE0SCGR3Oo8epC0b81l1+6dY31iDHVE5o6SJH9at5+s1m5nj6+X1gVq+cuB4elw6P7/sFfJ9cXTdBM2hQhYVSZRjB4YPaZUEyChk4ajbDTX7Hdrr5o+3VvGzz9fxzL3FJAyFvqoqXt89hZSpEU26SZka21oq+NRfLiSe0rAtKK9JIUxJ4OuHcT/ZR4kWx6sYiJy5HYlISXbfBZcvmM0rjxSwpbWSZ9fvIp78nymdfRT72EX20u6jtDK30s3ReV08NeslVvz5KoQGckBDPak/97bKpYAf3L/tJHlDeUZA6lNNZgT6c/zIWe2PK+6AHAJWVoWb1M2l+O/oRCAdScSAjS9g8dNHGknYKne3zSVm6/gUgxPz2zgq2MVDDVPYoZYSUA3OLT7I8Xntw4uMT7OY7unnVauWxBVFeP/UgzYwJu1hC7pbndmqe2xEn0nn45JfDtaw/GaTbzcdj8y3cAmLOf5eLss/QDBhs7WlnLd2T+Kvn30agGOCHUz2hPDmYMz0KBZfrNzOZ/afwvHuNj5/ytbMcRHwxylvc/XO07C2BMAUyF7XiKKQBKvdReHXd2Tl6AUOj0tiUhGxk6aCEIRPnY53QzPeXR24VGcxPHpWE6+5JjqIijHmc6VYPu0gv/tFEZwus8IYoaiUzjmBjm2vYXkH0Ca5CdZVEd3VjhWOk0ia6KqD3ojFbCwLjl7kJhhQqarQ2LAhyuBGP1GrHw0XgUAJ4oRCyNfQ3g5n1GpSafzJ8hm1QO65qqqSw43u9LVJOn0BTt92Nql9hWPEOdJFV6/OwGWLCL66e1wRdSvPg9IdyfmZsKXDQ+/SMCqC6G0hzOp8QqtmOA+gSwXbxmr0ITYMUDNH4fBqHFUoCUZ5kOjyydj+dLqqwUOZEqMrFIQujXiwmEB4D9gSZTCBKDfHX5ilxCUsvla7hdaBUu6zF+f+nqqgdYZJ5XspKYlz37VPk+dP4NdNLAlnFDbx5kANP25ZwhcPnAgI5MoI9OoohkAUmAhv2tkuG8TekA8KRE6aQvC1vWDaCKBxl4dFy8M8+cdSHv1NOaYhsCzButfyePCXFeRfXYxhZzoRWypEky5e2j6VM2fu4XCjG6FIbF2BsOTa5F7OnneALYlSvnHwWEAStzW8woQUcHc3oRsqMed4uSM6EREexBoooLmzn+l1ZeMM3P/OPnbOHmmnURm5k+OaakO/CznkZFxHwLhqAtfaKPb0EMZpI8gbMW6l6l9/rp7g45vndbLxNzqN+3ys+PQgy1f102zl8d8HZ7EhUo5HmHyhcgcuxcalpDjOaOczk/Y6QhJjbM82Hy99y0veVgf2aRepKOliUK53yTYFrmcGSHyhlBcWL+X5fgF5NkIIEmh8EC1nY6gc2atjry2gNDjiHExToULPllgcspm+fm4s28ql5Y241DGFUBt27fBDxESZEMbaXOAgKVTpRKfFKVx6B1LPUZAFhA16b2wk6lQV4sdMJH5ULWoyxYpFTVx83E6M9Y28uWcypjni8HTVpDI/xHu/BytlUlveQ+tASVr3YMgkbr+H6i8vofOlDaT6B1A8OsGjajEH4qi9MTp7YpiGxOMRnLfKzyXn5TFrmgtLapx15yeomu3CHBige+9akkYURRh4dhoo3SbSkhiksDFx4aGWqaz+h+CyGxrGFMQdXpjWRjeN6Q5Y2xaE1tn4zz+ENjtCdHH9KIc+OuGsED5tBmpXGKsyPytVFV9Yjfbm/qzio1QFycklTKvrx+sy2L+8GvlklNBpMzIXjnSuL7pkEq2v7STyyZmYUQmagnQNuQrJ/4+9/46So7j6//FXdZi4szlHSaucUBYIBIgsggGbjDE2YMAJnI3DY+OMAw44YwM2xgEbY3LOSKCAEsp5d7U5706e7q76/dGzYTSzMn4evuf8OOdzz+GInenprqquunXr3vd93+kVfQS8KYq1GP+47hEiCQ8H3zK4541KmvG5sNxjIeQE/KRxLUtCPaytlRjKxhY56izoEs1M4mnq51sffZOyUHS0cpgu3DKNqwpb2TBUzjO7pkFlCg0wShPpYufjTjCVFuLUAeSeAJbIZ/iMGQTfPIw+lOCpB0qYuzzC3+6qIJkY22iTcZ1kXDH8xwG4Ohs6GbdM1uxtYK7RRNMe910KW5H0VPPz5xtZUNfLvGAvT8x5gpcGa2mLBsgbSvDAD0oZ/EItmLh5PADVFlp4iI3dh/6fsh8VrYRkogiPmc1n7yh4c7gSbdkQckMaEhnXIDBBmDwuEUMS778HM5R9TJociuczPTCU82cHEwUcXVJuRFJKpyE/wr7ifPZtDLCnJZ8f9yxGLvGja4oyM8bNlTs4r6Rl9DebmqqYNTObebNpr5cvvX8KidhYQEnvddA8YOgOVkJDjYM7mh6Jo2lEflHvZu3pLpj8aAtL6ECxhVGQ5NSph0glBUrTeOCpGXz4gt0TpS1hScGl5dmKHtxnTBWD+P7cR+KGUvST+iBhomwdke8gAhJ2ZgdeM+5Rogj6E6QsHcfR8Zk2FfkRfnvtY5TkucH0irK1vGBVox3yI6RrwM8o7yF82OZZ3wlwX9LFLe9NwCH/GOIpaCMaE3iq8qj7yKnEW3oZ2nSIeEsvSBgMVXLtmf2cudLLcXO8eNIFLuIpg9+8tIzBeB6aCZ6ycqpLzicx0EnYvwX7+UM4aWRLkHxKqCBIPprQaDkA3zm8iK9N2YxULhFbKq4x0GPwtQ9PQemAM04l2RLv9h7svADJOVW5McWGxpKlA2zuyMuyNq3JJcTnR/FvSx87pauofbUmv//7OkqLkkglMD/ocFnnqeQ+u7qSKCtgutXMoYIG4pb7nAX17Xz74hcp8CdxlMBr2HgMic+0iVT5OOfKfh76TRk9ohDVayDKcqOn5gT6WRLqAeCEqS34nCQR4+iELgVeReoTASoejDK/titniciA7nC57zBPbloChkQW2aDZhI4fIHxUUobId9DnDxH8ZxvGOFBAT7uHOz7eMEGVO4GwbIyeYezygqO+kWiOzTc+PHnss4TiYv96rv9EJ4d7Cnl5xyTmBI5QHu1n58OSx58qYOie6mxefa+G0G3etg8B/98gct5zyl4IQbD6eyT7P4bXzKxGlZAGd3fOQYQcxOQ4qttEKZVT4ZGSeP89gFAgBrIn5U/bFvDTxjX4tGxrW0fiEZLkUcFgE4fFed2U6gme/dskALQum+I7jnDdNztZdcUQIc0aDZYC7Nni57l782m2TuarF7yGJhQeQ5KyNf7w3eqc1MwyBaF6CPqTdLV40A3lTtQqP5GzQ4iUwnxmAHuWHzl34sILKt/CJ/oYxsu3/3Eaaw/VMXPBMCvq2zLS8wFsG1oPe5ncmMh5LyFg+oIEpbf4aRW6u2zzZIbP0pnpcy37eOa9vX7J9d/o4Kwr+jGM9SQcgz2tpThSsHxKOwrY0VrOQNLLE04t0xd0ULQoyf7BInrXlbOjowp8QKGDoaUQgD4rhpoZA0uAoZA7A4haK52EpxGYXE5gcjlKKpTtoGyDgSNDTJvxGikpSSbA1CX3r13AX9fPz+yrpuMvqcZfU0yRVYRCoqG5NMjjrwNePFDNungVpxW0UWgk2RstYPPrIbQTE3gfHsgygIVUKNOYMHlEF5Jlszr5wIl7+e7jpxBOeEc5ggDiS+tJzqrAc7gfHIey2fDXbzyN35M5x8+9bpAnt0f4wNJdTK/oo7mvkIfemkNzX5ELuc3zUXt4Nx/6ykH+tHYBjhTcdfWTBI66j1LwxtP53PHJBhcIIEDYcTx/D2N9zJ/lQvUKm1tr3h79WxNw/oJNPNh6PGrYM1rghQJ7lCGy8BSJ5Wh4zdxQ6bJQ+jRqa6geDxYe5HqH4AlhLKmRYqSkpML75GCGoh+Rvq6JE8qErjCm9eH4fKiuMdSVjqTz0WH6u8ZzUCuKg3FKQzFKQzHm1nbzk2dP4NGXp1D46FacqV6UL/e7FQYcSnXm/O7dkPecsgcwgqv41f4PsFo8xeTyGArYGinlJ20LaGorHq0MJOriCO8EQT0Jpc/3cNlXu1l12RB64S7eGK7kj12zaEvlsSVaxqcPnsQXazcz5ahklmmBYT5bs5U72xaiC4klNUxNMck7zDfqNvDPu8oYHDDRdIVvVhDzzCp+2bGEv/wuzhXL3+bChXsQStF22MtXrpzCkG3z7I7pvH2kmg8s2UFjeT+He4rY+LLGRO6q3iMGfZ88jlqjl4Eegx5Vjszz4ZnWSujmZrAV8RvLkLN9uUukKWB6nAfzZvPagUnMCcZBavz48ZO5/6aH8Gv2aA3UlNQYtjzsiNfTqO3LvteI6HBd/R5eH67m9eHqbOy9Loh/rpLA9zogpdyNVih+8M+DTJkTx5t2uZmaxbyaLt56OcQFN55I/4oZCK+G1NyTykWLdnHT6RvwGw5rtGq+/szZJB3TzQ8YJ0Iw6sYT1QlExAGvOMqqEqhdhagjPl6Wpby2dwqza7rxGA4HewsZjvs52ifhNSw+tGIL+7YF2C5EFv4+Y5hbPYTLFI/1j1l/LAKzx0HpYhTvPl6MngipxpKcQViP6TC5dICTZzRz8owmHtk0izueOTkjZ0PmeUnMcyuYffSiF0arlsUcHUtp5OsWJ81s4cOnbB01LpZOaeXixbv4wVMreXzjdDyDEaafGmOaOcjqVJSK+WKUJfPoMV6yKoyuq9GaDwJF4Pl2wkWNOOcaiEJ3gyiTSb41/Q3mBzNP5RXHW+jtg6iUgYrqiICDyBsxEjQ6QiE8xsS1iA91Fx096iSHPXzVt40fH1xCKl321S8c2GFPxP4/0qPsB0iQDR60umGcl4ohruMzLVZMbub2z73FYK/Bd25s4OCOAD6/ZMXZYx4Bv8emrngIWejHLg8hAvYx8fj6MTNE/2/ynlT2AI/0ePhL6hyCLUlSHhNL6SgH5Pr80aCgqIxjvh1FaQJnti+j9mSRnuC3L+2jIN8epT9eXdzMaYVt3Lh/FQcTBWyNlvHVpuP526zns55/YWkTpxa28epQDRHHZF6wj7mBfoSAy27t5a/2Kj540tv85rU5JGKuP3Iw5uenz53I81sn0/uzZsL9BlJA+LK5SEfQNpjPXS+sSD9BUcy6iV2fSpF8tI3YJYVce8Ueqou2sKO1jL/foqOibuDJ88Iw1qoQ5LAkhJT4f9KBUILhlMOuqX4IObR1B7n64TO56rS9nJbfjgSeG6jjb13TOW54mPOc/TmP0+CyJ55d3MKpBW1oQnEgUcCOaAkP9U6lNeXih+2lQSI/rsP7YD/GjhhLlg3RMD2B16vot7zsiRcR1CzmBvsommnQdeIclK6nSaXc5zy+ZRZ+w+aWM9dz0tw27hx+iFueuxCtYBjvfUPoexOocoPUeQU4M/yYzw3hu78PMezewF4QIP6JclSFidyeh2odYz10lGB7ayWgOG3mQVbNPsyPnl5J0tIxNJdr5VOnr+OSpTtJnKDx3c31bHihIMdouCpF7gvClASEHISZTniycIt6y9yxJ+/+HmLHN+S8p2XrVBe6Lj9DU1yydBe/G5jFwKZSV4nY41H2sGhSO0esPH54aCHbo6UIoaj3hrl/xovo43gKTF1h6g63nfs6G/ZWoTV10bzPyyfOno5tC+5ds3vC925bgoYZCfZsHkssE7Yk8FQrQ6GF6IbNyhnNXL54Bwvyst2v1cEYPtMhYWpuFa9xoinF6hkHMTSZASEekXjK4N41IwFehZgcR5sRwzIUt4eXQIk7Gj7N5sS8dtYFJuTbyPmp0sFp8CAnexE2aJPiqD0BLl+2nU+cvh5NgC+Q4kcPHeTmM6ZTOyXJ7KWZca/Hts4CJYicPp3qVzcT9eR+loHD8SUVE7Tv/y7vSWUfs5OklM2sgS6Gnrdov7gGvArV4wGvBAv8G4/gv6893UMBUhG/oRTr3EIArq/dTWGhjWmOTWBDgKbZfLF2MzcdWOUWuyhyiYkcB578cwn//kMZHd5y/FN9nLiyjxvev5M8bxJdc08Q8ZTBX9fP4wPzd/DrV1dkseolLJMd3dUUlA9DfxirpjAnVBAEqZpCPEcGcnKHCMDbOoB6oJtVN+wjv1Di7x/ikfBkEmlLU9+dwHw1jHVyaKxgg1RgKXy/6cZcFxud4sM7khR6tjB0/myiPxvmrknzucu3YPR5Kqrx6ppK+hdspCwUy3laEiKdv2Y4SAXTPMNM9w9wUelhvtG8lFfTJQFlo5f4p8oJ3dTMitOG8AQV32lZzHMD9ZjCQSHwaQ61h+2cp5KEZfLghnl89JRN+H02C1cMM/NHb9H5Dw84CmG5MWHz1Qj2TC/GviQiOe49b46Rd2sL4bsmoVp8E2YyG7pi9bwDnDnnIHvay5BKMLOqZ/TE4/NJ/uf3zVwyew7JeNpVAKNtFhL0rhjWq0WIKgtRkwShUO0+EtEQftWV87ki5ZD/5C6Gz5nlBlBHx0BgS41r7r6E6ZV93Hnl05TmxTlv9n7+WSaxun3I9QUZ+8fhaD5fa15GTBousEHB7MAASakRyFmnWHFJcA175xusf6EA23LnTSysA7lhgZqu0t9nih5O4DVsfnvtozSWDRBIUzUrBUml8/JgDa3JPAq1hIuPzwEENzTJ3JY2PnTpTO5buwctratTthuvuuuF49nUVOOOzswYWmMs03WURhMl4gYvWvUE249MaEBJXXMzkNOxFHS30lfs9up0Y4ACG48uqciPjL4WTQPTo/jcT44wZ5m7NpSCzZEytkZL6a8Aog4SL9/8exv3HPbyVn410swEEHg0yZXVR59S3j15Tyr727b+FbknRu9Xhlx444FOEreWIyosjNJ+PI8M4NvW5xZfTsHI7Pf/vhdVbGAvD3JWSWuGoh8RTcDsQD8FegKVgpntHchy+OZHJvHWthJ6zzrOpS0wdf6+dxIP/Wgxkyv6mVPTzWfPfoMH3jiOP7y2mAtnvZ3l9x6RhGWgzqrFlzqI5/Agnn+9jdIF8fnVJBbVjvprY8c3YHYMgSUnTJaJDms89/diLrm5l4PbfFipsSsF4P95N+ZbMZIXFyLLTRzbj2djP55XXBpipYMz14/ya2h7E+StOYwIJrMWntwXQFk6H7z7Uu67/l9UF7ooHiFcYjAtvdkN2B4e7p3ChnAFAWGzwuziA/UH+GbDRs7bUUFUupuf56khREyiHPjRkYU8P1A3RkiHGyTvrwa1T0IkWwsYuqKpt5BZ1b04tmDWlAhd28YWilCApTC2J3L4xXGx4f8awq4vn0DZC/Z2uhmahqaYW9ud4xp3kZ/6eck/189G742ifAZOUYD8Z/YAEv/WNqy6QlSXd9Tfu3zKEb74hdf5fVsxG1/KpBQecTGYnWGK799IalIxiVkV5E33Mr+2k0jSy9aWSnZ3lPHR+y7inx//G9dU7OXpgQaGC1NZh4W7mhYQD+gZvEIlZgJvjlhUxDHYGitjsMHP5g2BDNTUE38q4abb2/HloNru7zZp2Z+dQSz9JteeuIVpFX340v72nW1l/O6NxazvrEYrsJBTkuh+xy01mU64EIZr5WrAGYf2ctdnKrBS+qiBYTkaP3zqJF7a3TjGXW9ItKkxsnnEXDit8rhzVVYZqH3kNqB0iNxZi96SQoQlTqPX9QikH6wkENUxNElFQWYZSY9PMe8EN6s2bJt88uDJtCTzSEgDMcVGn9yP3BegNxHizlPX8+vOeTzc24ghJI7SqPDE+GrFW4T3r6JyaXbb3g15zyn75mgvm3sO47+jh1RMw6nzEP98Jfg1dzrr4H10kFwEjyKp8N3TC/f14XnZnpBBUSIIvDaEfc8w3xmsxxtSJAYFvRfPRQbMsbOkoWMD+ztLOSDzeeKxOpyohskR2gLBDKRMhlgS/98PokVS7qRzJMKBwNY2tLhF7KQpbjsK/QxfPJ/gy/sxeqI5FX4qofPog1XkFzn87vbqrOxdAZhrIxhrI0i/ydClx+F7+AAipbCWB4l9blyOgSkwXwoj2gXoAtVv4OwOwqAx6h7ojwa48K5rWDL5CBcv3I1pOGxuquayZTuwA3DjgVOxpDZadvEtVc4mWcr/1G3gtIIjPD7g9s1cE0GkFC+9UMLmRRMQ0gnQpsaQW7N5221HI+RLp+EriA79d2yBwgLPpjCxuomv8XktBmwPRcZYslJfl4F0BKVV1qjymbxUYnWXYM0qRNQmEaYkaRXhebEPsydC8LWDRE9uBKVY2tjOnVc8g64kW9fUc7T7YPxfQiq8h/oItPbyx2/vIVDoaqiUbfDlh85kV3sZbx6q4/gprfyh8UV+sH8h6wJFmLsjGO3DKI9O60ITWZ+5WR6IF5CQBsF0/oJS8PvO2TzQPQNDSKwqgfVXDd+9PXifdF1Gzz1YzBmXDDBlTny0cpolBVZScMenGrL6gSFwFlRwydIXRhX9n9Yu4O5XlpC0XeSNM+CBliBywTBEddRhv1saMOBQFOqCe1tZ16GPzumn/1LMBR/up3s4yJNvz8Aax6cvSizSnNG533e6eakLizDfjEIyU9srQJboyCleZKMvN0mlBNnkx9AtTpzawtGyYWs5rRsl68+cxqFE/ijhoErnbmrTYvxu13GsmNrCrTXbuaFyN4cT+YT0FHVmhCMHvfztd/v4yl/Ozd2J/6O855T97qFWnC0GWo8bUU9cUwzjfWBxiRicOJijtbmFfnduCLLw5EiWDxBguFMj9t0h0q8IKwF2eR4yz5vtNMS9TPklTE2iS4WcHyCuLJytuZW992A3WtxCmQap+nyEVKOcJb49XcQX1aICriniFAWIL20g77k9WfjpEekYyONnX6qbmHxqpCdxi/wndqElLJypXmJfqsyCgFmnhtD2JZDdHuSmgtE086NlS1MNJcEEFy7czer5+ykIJLi5+RSijplhRVpCZ324kteHayjVk2Meq/Si3N5ThOZIsorsgsskWJzLdaCoLRqitnh45E+2vJ6bU+SY4S4TTK+DlnI477h9rJ63DyHguR1TeXz7dJoqPbxv53lM8w9ySd8u/vXFQrpaPQigqNzi499pY/kZYfq3JdErBmBpuoSdDonJxaSuCBG4rQ3fgV48Lf2k6ov53A3r8ZkO618IZZzCjiWGIdn8Uh7nXDXCamrxs6ue4srfXsre9nJWTjtCXSDGN2s28Il/DtPXYSCsNDRmK2gXF7qcN2l5Y7iKsGPi01ye9od6G/lrz/QMqm/8kLi+DK3XwVwfxbY0vnhpI2dcOsB51/bhm6azcbicreuqae6Io0yJsKR7MjEFS08d5ryvbqbA7yaYNfcVcPcrS9OKfuQ1CnBAbcpPZ9alxyNq0DNcRTAQw2f3jF7+6/+ppXFugknz49kFbBTviA/AmeEjcVUxvr/0g6OYMj1O3ewk3b0eNl41c1TDC9ya1UIDlVYncneAQFLy82uecvN5xkksZfD3nYvYf283A0uqUEZ2Y4QBTYVe/rj2OD5y0lY8msPcYD+xiMZQROf2j0wmUJbbtfduyHtO2eebfuyDxugqthcGMosMe7T/sMLdI9wff1DFnGUHso6liZjgnu+MKyaS/j+Z75vAt56+IpqefGlH3m4nn8VT2th6qDrTby8U5uF+oosbSM6udK163HT2wJuH8R7oxWwfJjV1bHFaVaEJu6QMDTsUQO+Lcyzmz5F+6MMJnKCP5BWFmZvkiPg05Gw/8qUQImojEjYy6MlIvjE0h19/6HFmVvWMQvEOx0N0JIM5aYjj0uDBnmkUGsmxo/jpIfTmFCIiSSR1mAAhKmLKZRRMP9/UXZTQt97/IrblBgfv+ETDqG85a3yYIPlM10hUV7Kwtp3bzlpLWSg6Ck+cUdnLB0/aykeaVjEkveyKFvNttYK8cAta0r2m64iX7900ia/e3cQr6woQ16cYXxpLmCDLTeSPqln+r11UV8U4/rwDTGlw3V+Hdr1DlkZc90EykdkLQ3f44IqtSDn2zJ99toZwB2jWCNGYghR4HxnEmenDXu5uiBLBxw6cyl1TXqPISHBP5ywSMocq8GkkPlSCud51WdiWxtMPlfJIYip8tJBv16/ni2euZ+esMv79cC07XvETtn2kppbyepVB6ZNvMv9GjWDQ4bEtM3GkgICDNjOKqEy58YtuD3J3ACJHJVXpGtETp+A92Ddq5EhH8P0fNHLiT2z0uWFkrxfV6QHS2drviPxFkbq0iPxTDX484w0mVcRwEGAIhu02Pnf4RA4l3IQ1YUlC8l+XrwAA4dZJREFUiRThVBCn0wtByazpHTSW92M7YjRgHUsarNnfwBt7aglMst1TwwSaVQQc/vkxH28VTePMS/ooKrXZsT6PVx8rJJHUmTYn9E468b+Sd6TshRCFwB+Aubjr5zpgL/AgMAloAi5TSg2kr/8ycD2uXXiLUurZd6vBS0sacbzmaBarcI5ScYYgtSAfz6bhLL+cEmO+un3bAnz92sl85setFJVZKCVwbPjt16t5+ZHirOdqYZfELLcoRN7RpwlBIn+I8+aFeXL7DKRwq0tRbJGaX0yqvNzl6DDGSj3HTpiMlrBdTpGGGNrkBColUD0m0dU1BJ9uy6wepQmckBcn5Mni/Z5QpCLZWIK1MDBKh5tLgpsO4n2jD6UJhITEzHJiJ0wCXeOSJTuZVdWTgd0ecjzoIgc3cVr6bS9742M+9dSZBXgeH0K0ptAGbKQ/h08tLvH9uRvVNkhyVgXK1KjVuzl7RTPrt1WwpqOQN+8zOJLDXzwqmkgXwRhrmNIEKmCSnFnJqqlrqSwIjwZdwYXLGUaUW2u28a0jy0AIlEcjeVkR/l+OWZrJhMavv1bD4Wsqc26cQgNZrnHDzzup97pKfsReaJydO18htwgWrsykQTB1xXF1XaPJZsMDOmdcMsBHbuuk9ZCXh39Xxu5NLjpGJBW+hwaILB87/XSnfFy550xmBIYYciYeP1nvcZUyArwCe7qPJR+0+frsJwnqNl/6x9msP1RL0tLheHeBKUeg7erijYMmq64rYI4aoCccxPaBfsoAGGqs6FBlCqMkif+b3YguSMyuIDWl1C0GIhVWdQGeFjf9K/7hEvZfWMj+LoFoTKLVJyGh46wpdN0/x0qgHDeWoPjFyjep80RdhFVa/JrNb6a+wsW7ziUmTfBohHsMZEJHJTWEDpsj5Xzw7ku45oStzK/roj/q5x8b5/Ly7ikoHESfjTIntjZVXAdDcOSAj/u+V535pSEoWzo59w/fBXmnlv3PgWeUUpcIITy4JQ6+AryolLpDCHEbcBvwJSHEbOAKYA5QDbwghJiulJrYt/JfiKkZVANJ3U1qMNeGcVbnZ1Abxy+swdidQCRttLRyVIbmEmul7FGFv21tiA+fMJOqhhT+oIPuVezfks1LDmB0hdHiKaSRA7eugTblKLpkQ7CzupIDCZv3XbiBCk+K+wZmkTB1Un3lbmQ0q3M68YU1cGkMLS+K0NNTs9TGmuonbE8nsOEI+kAMZeokZpQTX1yH2TaIMjX36P4fRGlpCtmU5rIq5hKpCLX1c9ZVPVQscDjSG2Dj3y26XkgROXsmly7bkZWkM9kXzlkUxR0eyaDtISPM7NOI/LQO71/68N/ZRfTbNS6ZWHqhKOUepc01YbRUGN/ebuwiP82rZ/PbLWlHuxBoC5Lkd+xCpFIQ0BERByXS8ENDJ3zOTEg55G9qgu44ytBITisjvqQO5TE477h9GYp+9FVoijOKWvnOkaVuuw2BtTSIn56M6zpbPMhSPSdqCNzqYO3J4KiyH0FqLDoljOlR/9GV4/FJFp0cpn5aNmFYOOHhmrsv4bJl2/nkaes56bwhdB0mzUiw7LRh7v9RJf/6nZt6r7db+ISNg2C2p5+D4XwiHi87YyXHfH7IY/GV3zdTOddhSk2URErnmY0V/PWvVYjyYtYfqh0tjQm4FpWUMFnS8flpfKZ5Ku8vPcic2i6e91Ugxyt63A0RE1JXhMi7rQ2jJ4K1p5vwubNRwp2vANayIKkLCjPYJIUJSnfQFg8j3yxE7vejzY3mCNJmysJgLxVmPEPRg/sKTSE5u6iFf/c1omLg7CtFXxRGb4ik3UyKVlvjO6+thOGj1KcQePYNYm/z4yzyZxH5KRtUh5fU5ZPg700YPVHcVBQ3RhY+fTp5vRPTlfxf5T8qeyFEPnAy8GEApVQKSAkhLgROTV/2J+AV4EvAhcDflVJJ4LAQ4gCwDHjz3Wr0yUXlPOe4c2pFWzNbtRmEpWdU4atKjaEr5uPd0YP3UC9KCJLTyrBq8in819tHWcGCjmYvaBBbVodPb3N9yDkk9Oxuhs+fC6aGMg005aAbigUnNLElP58sy18Ikn6Tf0emgoA8wyIRN90ZPoEF7JQGMQoSR98G4VHYS4IM1c/Peo5ozCewSRLvm8hpMb634BT48f2lleR1xdlp20oR6E3w80f28YPeJTyULHYRAycLarb3cmBzjJAvW/EUGCnOKmrhuYE6Uupo0ihBkhzcJ0Gd5EfL4E99hG5qJnZLGc7idIk3Afh1UqsL8D4zDI5g+H1zXebHcZEzWehj+IK55O3ZRezbtWjNKbRDSVSRQcouQ3UEOKGxhS//aDsX/ewqZIYmUPjNiQqiuNTZpnBGg83k4PQBgdZpI6epnArfUi6VdcYvBOgGfP6nLfzwlnqcccRno0/wueiUlZcO8elvZdcljaUM/vLmAgr8ST5x2gY847LJNR18AcW1X+rk9ScK6W7zYFWbyKjEf1ULTSlF9O/FRwEUsueORzhcUHyYk+cOjQ656be58KR2OpYG+cgTs7EHopBXmNm4Yomz0kQaYEl4oHsmft1GVVgZin6swQJntj/NmyQxu8J493WTnFqG2TmMIh2b82f/WGhAiQU+G9XmhalxVEAes3rd9MBgVmGfEQnoDvOCffy7rxG5M4i+ZBiCMt3udJ6EIdFPHMR5vhhGWGMth+DaQwhHUfSbdtRvqomaHuLS9UIoQBiC8gW9PHTZM2x8Xy3fvO944m0Oym9ileXh29OFlZdNm/JuyTux7KcAPcB9QojjgE3ArUCFUqoDQCnVIYQYYe+pIV1vPS2t6c8yRAhxI3AjQH19/dFfH1OWzpvK8xokq4upOC3CPVNf4v7embw4WIutNBZM7WDrjhlEFtSQWJD56NiyBgIbW1xfuRrDRUdWTMaaVIx/Y2vuh3oFhV/1cv/pD/Dqjsm0xoupKIqxet5+QsEEv+qYx0O9U3P/1qchbMmtDdu498gcjpDtJhq7dmLXirYgjPNqER5HkUoHuvymRX3JIN97dB9fvqQhXZ4u90zXTIiuaiD0/F5EPIVzgh97pn9sESXdIsrfP249n+pclbbGtVGkTNu8UoLeAXa3l3NCY0tWrPqLtVuI2zov99diCAddh7gyjomSADDeioKlkA1esFWGSyR5Yxmq2EDt8rhc5EevYk1D+gzkgB/RZyMne5GT3THQZJTA6/DDy55lOOpxS0VmzHhBS18BDaVDOdvVa/lIjpxWkhLPi5kL0Z074H1sEHt5MCt5TUMyzT9IvTfCno7SUUy4QLFkchufO3st3/v7If54RyUHtgcw/IrwGcVE31eIlgJZYrC3uAjLaEdJiVdzFVQsafDavkm8tncSly9/G13Lrbg0TfGZO1vo6/awq7qCJ0IVJC8uxPvIINqBBM6CALLPg9zvR18YQZhydHx8wqbaG+X6yt1ZQ+7RFOWeOOcu7+ChCj+8YoEa28y1abEs/3lcM9KntWNI+jfClvh2dIDloIoEke80oCpyGAuMXK8Qk2OIQglZin5sE9P3JTBfHia2IIH9EYEnh+fQkoK+lA8Zk5DSwSezNighcIvx1ERQB4MYfTH8b7XgaR1CMxQBw2HYFASERRw3v8HAwdQkd0x+E7/H4YTGFu753ACX/+py1FCKvLWHyGvrZe4HzzjWCP2f5J0oewNYBHxKKbVeCPFzXJfNRJLrfWZpMKXU3cDdAEuWLHmHDmdXTnjfEqxp5YSXT6Y5cYQC7W2+XL+ZL9dvHr1m9zV7+fif30c0aWZwhyTmV2NVhvBt70AfjCMsh8hp03DK3cBIbGENga2ZZcuUV2AtDnDjOYepLExy1el7stp0Y/kuHm5vRJrkwGy5bqQt0XIeXvA0N+64gK2Hq1FH0wloClE/sS9X+BX66QN8MH6Yjfvr8OgOFyzYy7y8Zu78VC393RPze5geyaIrHNa8HUMkLTQJgf9px16RR/LsfAhqGG9FOTdwmH0fLSLmGKNc/SOSVAZ6o+QP6xawuK4Vny9TyZhC8t0pG2ip2snWaCnrWkt4SUxxq1yp3OOCAmemn9R0L6rIyOKF1/ckMHYn0PaHMY9Eic+vxqovyryXoeGUBDA3REmdV8jIFBRCccbKPYAi35Nw3XChzMDob15exjcufDnLLRV3dO7unO3eK+XSRnsfHdsUlAZ4BdGvVoGpoaUcpFe4BoQmEDZUBWLcMXkdu9rLuPGPF5Kwxsi+1h2s44rfXs6fbniInzx6EE1zM5XvONII0hzNqN8ZK+GKPWdxaekBTgx2EDskuGfbCaw5NBkQrJjaMmE+h+mB41ZE0Y0oK51hPib20XuHl8cmlfDvRzwMlBUitxWAI3BeMhF1CbSaJIYmuXnGTi6uPDi6wRwtft1hdUkLD3U0YhYOYA2MMTWKwtwW/LGsba0llZH4poWTBNY1EfnjZFTxxG4y98YKT6wfp95PtTfGkrwebCVYO1xFoZ5gqm+Iklf7OfyoYO9bfjY8byKukTmh1w6Cx/smIV8KICY5EwZ9hQbacQm8W9rwPTPoUnprglRdIambChgQJmJfkpCRoGZ6nCUFPVxaup8Kj7u+TVNRHohw7pHneeOZApQAI19yxmXHiD/9H+WdKPtWoFUptT7990O4yr5LCFGVtuqrgO5x149HL9cC7e9WgwF0j0HqlOlgO2y73yF1hkJ6MlGRs6p7efqz93PjA+eza7jELZjgc1CtfpzyENHTQ5Cy8W9rR5SOKYDE4npkURD/5la04TgqaJK6Mp/UuQUsDW1if1eIJ58pZ2irYkp1jNVX91FRa2EoSXWzQ+skLUthjYitNISAL573Oh+790IiMQ922kXg1S3MwhTx6RP77JQEZ0OIe3uXEPBYXLRoF8trDvOJVdMYHtRRE2SCAlgpwZZ/aBip7lHudSFdvLu5Ziz41/DlGGviM0mo3FND1xT9wN9+WsZln+jB9CpMj5tQNbKY6/1RKr0xKjxxrtQPczBewM/bjyMuc1hnmsBaHsQ5zp81bubTQ/jv7hnl0dFJYXRHSMysIHbiuECWo1wo61EhCENIOr0eWp08Gv1DVO45QPvCWRmcMy/smkppIMInT1uPLdzkI1N3uK9lBk92NaClbMq39xH8Vx+9MdO1WnSwTs4jeXUJWlsK3x+60ZpTyHKD1IeKmbcqhjHk5UyzhRIjwReeXp3p13ZHH0fCx++/gDsufY55lZ1M9w6Qklom6Cus02Xl83trNlalxrRAlI2tdYwEGufVdh1Tieojlno6W7baG+fmW1u5+uZ2zv/5HKIjVOC2hjocwDkcQNMduuwSvNX7J75xenzxaqhJkvEUmiqpjeO2eQeSkPh/PxYLUQKE5WAdH0QFxDEVvYnDFKufnm/1c8uTvaya0YVULnzjy2ITQkAqpaFdIVGXwZEDPr569RR+8Ml6bvtlC7qpME1wpCBl6/x+0wKaYoVoM0Al+A/YfUHqI6Ukry6GN7zInjyUxyDa4iBnDKDtLuBS7WWuO68dI/0elIJ+20PMManLi7L4jDBrXylEFencfv9+/N7NwKp3Pnb/hfxHZa+U6hRCHBFCzFBK7QVOB3al/7sWuCP976PpnzwG/FUI8RPcAO00YMO72ejthzvQTQPv1jbMXT3cdvkU7nz4AHmFmUe4XclCmhcKDHsIjDRednocuS0PdcSPcBT+wSEcvSrj7JGaUkJqSjpwVZbCWOFadDdvXUmLzEdMV6g5As+GCA+d1clnv9PCigvCxFuDyIBEq8nGhvs1i+PzO7nt8PG80VKO9x+7MEuKoa7E5alp6mLF5CZeOem4NEvfBBj9siRXztzB+cftxaNLfvezKSTi4piK3hVBKqEfk4vfMCV5+Q5+bWI/tgIKCyQfuebYeGCPpliQ18sPjizkpILOYx7fnQX+TPgsIMIO/t/2ZBc6SeciJGeUuVWHAAwNaWrYCzOtIhuNTckybtx/Knm6zeqb9/DvH2sMLZ6CDHjcuFhflBe+CUvJx5pUzONbZ7KlrQJnRZivedZy5qJOrEUC43pFW5OX735nKrs/Ng0V0jFfHcb/s+5Ri1TvsvH9uJv9vxb8+vmt/OrNkxjKh13tE/GTC4bjPr5ww2zsS+bhy1M481yLZWQeq5CDcCC1tYCLrjyEv0iOAgwCHuuYMYdjSe9wPo6dW4tZjs5zO6Zy65nrcicXAQmp8eKgS3+BFAgl3U1KKugzUMW5ipe4Dc/TLBLKwLFBdNj4ftODsW0M4KAMEEogJ3uzY0rjRMdhsn+Yn858g4HHNWqnWjlPIoZ3zAqYPCvO7fce5rMXTeNjZ/q58PpeJi+XtA3m8/cdi9jVWQ5CoZ8xgBow/jOcUyqER0OdbMFGGzrdDFtxZxjf+i7m/C6CPm6YhYCQbhFxPHxoz2ksmd5G9NvVHH9cHwvmxED8f1ea8J2icT4F/CWNxDkEfAR3GP4hhLgeaAEuBVBK7RRC/AN3M7CBT7xbSJwRkcrNq/ZvbUXYkua9fq49YRZ/37ZrlNQsKTW+cGgFSfTRXo7E5rTjIjgdOqFn96L6Im6qdi7RJVpD2q2iFC0i37Vk0joltSyPgfxafvp5RcG0DrqG82GzRC/sQQXHZokpHKrMGAmps264AuMn3YiOFIHWTtg2Rmm6+VAeCz7QzobK3GmdQsAHlu7khtrto1mJQzstkvF35+inGy5KJK+wmQ3RirHA5DixlEZe5J1ZbVIJtkbKuKFy18RjDGBqGZWeAIw3I65FlSunypZ49/UQKwkycqSIL22AFge9ZmicC0EghSAuNeLS5C+V87niuq08981+RNBASAVJmxv/p51TzhskaYX54dMriVkevjN7PacWdOHV1Wgh6skzE/zs/r1cunsyQ5aG0gT2PD/GW2McQ0KBiipuPa2RG36zG+U/NjRECIVvTw/qDoj8oDbL2yUE7vydFCdPc/CaDh895S1+89IyEpaBLTWMnBw3xxapxGgZxom+VwrCjoEpVEb1MltB1DF5pK/RpZ14vB/VEcfrl6w+v5lFpw1yb+9sDiQKRwDSI70BFPdOf4l8PYntCL53/xR27PSiggIk2IU+lGZitg2j9acx6/7suaMjOb+4idvqtiAEFM0+tptoREwPNM6NUz8tQct+H7/+Wo2bFGloKM8RtPPzkYU+1xCoSSEHdShwMu+dkJivhDHeiiLC0uXd+lwFLAmjDts4O70QKkSd62PJqm25Yx5mnOn+IR5JzmSq2U30CwPwtI7wrf7PnfhfyjtLQ1Bqq1JqiVJqvlLqIqXUgFKqTyl1ulJqWvrf/nHXf1cp1aiUmqGUevpdb3WhRTSRQIuNaYLosMHDd5eSiLlden2oOmeCD4BQCn+iGSMcIXp7FWpx1CVMGm/1ahIKbURVGnnikFW7Eo+GM92H1eDlez+c5/5MwYrUAHlaClO4pQDPLmrh7ukvs7qohS8UbKK0dZjzruzj/Tf2MG3+mNvGSmi8/RsfaoJMWAPJmaUto4oeIFTwv7PsRsdCU/gCDl6/5Iu/aKZ6ksWfOmekg7LjlYFyTwWWYPXsg+/o3gqISYM+28/narfgE8doqyYynidicsLcAQGIhJ25unUdBgxU28RxC0fTOHhiNf/cvpPbf7mfr911kA9+tpN//6GMKxfM5vsfq2O+/xCV83tYVdiG76gsSU0Djya5qOQQaAJ7ZYjY5ytRAS1jpARgJwT33lLIGaEWppZnMz2OjNCsMnezVw7I6b6JNVaBQzgdlD933j5K82JIJXj67ekk7exlfIwaMQBMKh3EOwFtsKE5nDbrEELAUNLLz9qOozfhJSU1LClYO1TFh/edznDUQN+fwPfsAIGtbXg2tLH113D3mUXM/uU+Th06nHWSnOEfpNSMU2halPpS/OTne/jLxl18+Ge9fPov7QQ/1IjRH3dpPl6PTBjRNYTko1XZweN3Io7tsnRCei4pNxFNi6YoeHwHSFAdHpQErTBzjES3ReiGJvx39+B5I4qxPY6xM0Hoxma0AQsxOY4VAqumgPknJyaEI/s0hyn+IWKWTrLYS1+/h5bWDyCMSf99h96hvOcyaG3p8OXtf6ViQRjL1FxsV1r+eEcV9uxSLjl5H63xPCw5wV5mCOwTAgyfPwW8GhopRGAQuTeAGjBBl1CVQmuMjiVmGRPMKgGJ6QHi+w2Y6lpEM0SYH857mYjjIaBZmOMCaMsCnZyxtg0l3TqkjiPYuzXA1z80mURMx3g7guqvgWIrk73PhoX5PcwL9Wc8/uwr+9n0aihnkZP/JEqDK2/poqrO4qTzBwmGJNujxexOFJO9ytLL1oAz5x7I+CYhNXxHHZ8Tjs6/+6YQlwYlRoJ5Jf3UeqN8/MApOe7tihvztBBAcpYvawMYEWlq2DUF2TdwNESHB+omSIDTBDuiJfgCknnHR/nCBxo5tMtPMu7Ok3XP5CNeGKbx+/EJeY18msMJ+Z38qXsWAOaWGELmNissS7Dm8QI+f85aPvXAeSSOYkD1mTbWY21jeJH/oLjWRys423uEG/54ET3DfszWIX75uQpeL3c4/vRBVl0+SLNegOYojsvvPdozliG6pvjcOWv47uOnZsQThJD4PRYfOnErAN2DIR7tn8Kj/ZPJlwlSQ4KEz4MYcvD9uxfP00OjPFSOI+hOb7avPVqIespB+24SZ9ZYenSZGXczVsdJWZnFVee18lZTNUMxH2bARItbiKjE/6NO4l+odE95pgaWwmM6fKluM6Xmf5OYNiZCQF9XdvxIAMpyMFsGsAIF6LVJF3UzTo0EftSJGHRG+zzSE2WD7xfdxL5Rg1aTRIbzXNROjuf3WV4+efBk2pNBMDSaikvQflnMs7313PS/6tE7k3dk2f//k6zvO4AlHX5+1ovMOys1mnQBYOf7+dnLKznnzmt5bt10bGeC7kmFqvZkJmgU22gzYmAosDQ44kO+VIq9IR8ZznYzjN0LSIJd6iZj+Uyb+tJ+NFzsuXkUUqK0zMbrU/gCCtPr4qFnLYpx6w9dyKcs8CPXF6AO+1GWe7TVkg7ygI/vNazjaFl6WpgFJ0bwjU+QEgpNV6PpwrlargRYdUWcdl2cs6/sJxhyZ+9DPY25+zkimkKMwyjbCprjeSSlRkLqo/+uC1fw2/Y5TPUPUe11Ty+L8nrximPwFqF4Ys4T/KRxLdeuPISa4hmP6HPbrYEydZKNuZOBxKAxIYYaQLdd3/KLDxVxaLdvVNEDKCmQKTh0u0MqOfHSCDtjpwftSAoSueeGSsDBXX4WNnTwiw8+yayqbnQh0YXkuLoOfnD5U0T2JUetS/qOfUprSYR4fe8kBiI+/C8cJPTsHvR9A+xc4+eeO6q4esUcPr92GZ86eAqf2HsqkZRJPKVPaOWvnneA77z/BeqKB9GFxNAcVjQe4c8f/RcV+VFiKYO/bp6bvlowrPlJFPlAh7wvtuJ9fIjMw9q4/AdHQyXAf2dXxjGjKZGPOcH7OdxThCNd9tcRbhnPm1FCH2vG8+ggxltRqjb18MDMFzi3eIyIzHIEUv3n0wy4uTmRYZ1dG3P7xoUt0Qdjbmbuq0WodhMGbJStEF0W+r5kbpJF0hu/BqTZdDc1VWPmKOH5pcMraEmExtykmkCaGn9mHwfD/48bZ1R6k2FKzDC13ggrL+1j+1MVo5aRDHhAKiJJL/u2V6NX9ufEyeayoFRMw3mjAI7eIHo8yM35iBMHJ0gIAWNDjOjFMwCFJTU85YkJOVlyHTs9PsWJ5w6RVyJpX1wHUiB35cGuAMtL97H/+31El09m99IylkxpzwAnaBp8/d4mXvhHMf++p5TeXg8Nc5Nc87F2knGNr39oMjLPh0hYCNvNYZUeDeU3iZzSyA+eDvLTq54erSvbY2dXZjpavtZ8PN+bvI57OmfxYM80UlKjSE9wamE7uqZYN1xJl+UnZNh8u2F9xm9PK2jj2cG6LFinhuSE/A6ChsOCvF4W5PUy/f4KvvXJKRib46MJTc4UL+Flc3JWcQKQCY1iO0m38GejOJIS56kIqVmCJx8oJjnBachOwMHtfhYuzw4YxBydx/rGkECyxHDx9TkUvuGV+Csh6WgsbOjgzzf+i4RlIIRCCti7zUeKstHrPa9HSF1cmBu66wgCCYtNTVXYO4cJNg9kEuMlAUui/6CHxE/r2Zos5dzt53NKbz8XTNvPsim5AXGnzmzi1JlNRJMGUglCPgtHQjyh89JTpWz6k4V+dQJnehqxlpIY2+Jove/Mfaj12WjtFrLG3SBbU3nsjJZQ0jXMk38soWmPj/nHR7j6s92U57v0BdFppcT9YdQCDZWnYWyO4vn3EMIRfPLxI5RqYxZ9PGXgNe2sV62Uq9gR7onU0BTxlI5tC756xyyUIcjlVVSG5uoRWxJ4vgXfL9KblSaw5nomSKxLiwRlgep1+xpJern39UV85KQto9Dew4kQ++MFGRn/I2Ih+HvTC3x13tXvaGz/W3nPKfvGvAr8moNUGpF8H3hAJF3fsz4YG0dGJXDWFqKvGER50pWppXCt+kEDrSLTwpTji1OPFyVg0EQd8UFtAjFiaUoFKYX33j4iq2aiPO5QKq/Di2tmcfJFHWjHCIAdLXZKkH9mMc0FReOeDds7a4l9ZDoI+M2LS/lN/RMZPntw3dVnX9nP2Vf20zYQ4uL7L6PMu4NbF2xk2elhXu2twZqUh7e/E+E4WMtCWCcFEcko6zfU8Knnz+TLp6ylwRdhdmCAbZHSnJNxZFxfG67mtkPL2RCpGk246nGC/LNzCnW+KHWBCJeV7ue0glb6h4IkCpOYuqQ/4kftDpBfYxFTxuhvTeEQ0Gw+U7Mt40lO0IBvlpN4YBjfg/0IC1LnFyAdM12nIFskgvbXq9BXDLkByBE4Z1Ki9djwWJjLn5pLnjoW4kjw2+cW87OFr+MxnFEce8zR2RgpZ81w1ei11so8Fx6aQzQBl17eia4pHAUppaVPRoq3IyXcv7EG5Yw6yPD+c4DU+QW5eXak4tnrTJZ81sa/o32UBiTzGtAPpxDdFqrcJKnpPCuqeeuRep7+7J8n7C+A37R5q6ma6KBGfE+cZ/9ezJ63AnjEIJ5tQyQ/UEjy0mL0Q0kCPzy6TurEmdu6rvAmLOJpULtA8j9/nIP+0z4cW+DYgnhU4/039bJiagua7qAtTpA6P98FVAhwZvtJXlXKAr2Xr0VPZOmjMc6ZfhBTl1QVDTOrqidX8jqW1Lj5/vdx7sm7KCuNsHVLHY/1TSI6S6Pwkd3kOvMKIDWpmNAzuzE7h8c4lRyFuX1it5ECZJkBSS1NzubKva8vpmc4yM2nb6AsL8bBeP6EeDiFYH84d92Ed0Pec8p+TkEtaHXYSjBnTgQKiqHb4ZT3DdLdZqCmN7O+uc7luo7pOC8UI8osyHMgkX4RSqFmR9Gnjb081WOOUaxmiUK+nYfo8SCmxNA8NqJLobYaRCtnjm4wmnCo9MY4efphtrZUsrC+MyPhJVdZtREx/IL26kkwklnvsxGFNrGUB/oFINjeUc1dzx/P51evnRB6LKVADnp46JkF5EUlZ12+jzXfGCb5tRBxf8Xo6USknxFc1cuV9TsYdLwcGQpyfvFBHuppxDk64WucaCjWhGvIWmGmzpFIHk2vV/N2ZBp3xL1I3ECvqUssR6coEONvq/7OowOTeWawAakEpxW2ckXZfkrMZAbUbyTsaexPINJGtv93vSRuqUKlAtnPB9fyGjJxXinGRwvOfC8iJdF3xLHn+YncPYkICt9d3Xjaw7lPX1KyOT6VG+4r4cMnbmFObRfDcS9HrCBlRRHunvoSm6Ll/LNnKn15fqJfriL4/Q4Xhme5CWyaBl/8ZTMFJe7GnHA01gxXsSlcTmsyj4PRfAZnmPjndWG8HXNL3g05+H/URfzz6RoDHg1dSTQU5nc66Ttg8PSXQbMn2OkAZQi0QQen3HTHschmOJ6b/jmjzwL2tpXw52tMRGrMmBAK16h5cABjbQSjJfO0IzRFqNAmMqhnMHCOjSXklWpocYekplE2FCP1k/4MN1nTHj9CuAXer3n/Ru4enJWpmTwClGLQ5+ULZVv5/taTeeORSYDgmc/9EX2CqWqjYS2N8pPofNQwyLagW4IypRE5ZSp5rx4Epdwi7+ns7PBZMzEG4phd4az6wMfCFwCkzi7AeSn/KD0ieHzLDJ58dRJT2rfSdmYF1qLcVbmUhOrA/ytLOCpCCG6bcwl/2PMGN9ftxPuV40je1kcyJfjc3Z38aUMNvjab1fP2g1A8tW0Gdo+HTP4qgdqdh6qKI/LSL8bzH6xwn4OoTiIKHFAC5fVhF+S5THuALhwcpdEzHOJ7T5yKUgKfaXPHpc+xqKEDpeDIER9VlclReOiIKAXtg3lEEyZoEm3hEKLKHjtpOOBsLIB+k4femssNp2yiOJhtZSQtnae3T0//RuPPry9k7rJDMEm5qfBHp31roHkddL9kQV4fCaljK8HNFW9zV+eCLFfLiHiEzJl0pVIClMGSFU18tnIbH/vayah13ejDCWTAJD6/Gu/xQYKaw/VVe7i+KjsT2XI0krZBnjfFJCIkHANvgTHKWCriktC9Bxi+aF62m0YpRMJGFZgQ10n1V1Dwi204s3zEvlU9DrMtSF5bgueNCCqeGVxVAhIzK1Beg72dZXz5X2dRXzzIfdc/zBTPwChp2tzgAB8q38vjvZP4wdJFhO+ZRP5z/awcaKZheoJzruynrHpMMfp0yaK8Xn54ZBFh6aFIT6IKdGJfriT4jXaCh924hn/bEMFPRVn4Y1DlXhp9Q5xb1MxVYiUQpdQ3jF7ho/vtCdyEtsKpGhfosAXVRcMMWSb5hjUhekUIqB1sxWfUkkzlVtpHK3pw4xzD/WNzIa/AJhiS9HUZWMpgeH4tiVdGKEsEPbva8Ts6WjpHWAmInFrIfS3TOXdyG2/I8txaSQg6UwHmBPq4dMU2yqYpwjEfidTEKszQJRHdRHaZyD0B6B8ZF0FqWhmDlfl493ShD8WxiwOkzgnBDIX/8TaYgB/r6DPMyEpWfvDf34dRkSR8ziw3lpiO0GqxJPlP7qIvpeF/ux/nx15klZk9fyVc0XDShP35v8p7TtkD/GzXk/TEqjg13saDH3iFLaeUsP0xPzc8cAm1RUM8/ukH0ITiu0+cgj0RIicl0R+z4ESFLDHQ6uPIAXO0WPl4ESkb7ZxBSHOYAaiKFCKagIM+cAS6tNCaowgJsaoQyu8hlvJwy1/O5SsffpFXElV0xP186PAuTp/hJhmNX3hFIkLDv9fS/NEG7Mqgm2Q0UuDZBP2EQZyXipFxnTuePJlvXvQifs+YBWY5gqG4lwc3zBv9zNAkj6yZSvL9hRNW5York53RYlYWdODT3NqxF5c1UeRN8d2WJVmkZgAB3aJQJOm03KC0imo4W0IwYIJQbNUL+IVj43/5EKmRzXA4SXBdM9H2QmI3mln0BOCurzcP1PG5B89Nk0cJzOlhOCcIr4ZHqwuZPVEC65qJLat3B1HXIOUgpCT0wj6Gr5oFMQi9tB8hFfJTpZxY3olHSLZFS+m3fahSk8iP6gjc0YXWlnI3CgAFiXlVGcew77z/BfJ8yQwLUgh30a8ubiEmDX4uFlB4rY/PTG8brQB1tJSYSZ6f/zjSdQGzcbiMgG6z4YFyVvS0sP3tELtqKmmqLKJXdzg/v5kzC4+go0gsqeWmi/dw/IIe2mJ+vn9VPaSOMho8AuuUPAilKyQ5IJu9HJlkc+HOc7l7+itM9Q/l9G8LAfFhccwopzOCksm6RFBWk+LTd7Yyf3kExxZICX99bBp3H6hmRD0a3WG8O7oyYg2xz1Rgn5LHn1Pl/G3vbOxjxIsMIYk4Jp9u3IpnuiJla2hCYdkC08hslFTQnAjRfqgItS2Uc13LkJf4UpeXS9TF0eZHXAScB9cwyoUl0MCe5ME45J6uistTzF4cZWjAZMeGIDLoJRgN46kwqC8ZZGFxMwf/mWBnxF0rQ6dPQ384DtdK18Xo10Yzv8UOmH/+f8cT9t/Ie07Z9ycjGM4W/jL7dQwh8WiKEyu6eaNmBfFeg59e9TR5PtcCcSFlEwF1NdQRL3mfPojyKsK/mgSlPug208QnuNpHKoy6PpSpje7EKqbhvFrkpoxJDe/uLoJvHE5T67puADelfxL2rATf7VyEo7mumG9aJ/DgvgGuDeynRE9S4E9SUxRmf08Jh06eh1wqc1O0CtAmx5G78nhpdyORiMEtK19jWmOElG3w3I6p/Oql5QzFx3G/KIhWBVz89lGSzkvDozsUjCu7pwkwNckZha28MFDPW5Fy4unCFjoSU5P8T8VG/nB1MUMlJSSuLMPZWQ4pkR5rgeVovGHNxj+7jcCmMWI5YUvMlkF+/a/j+PyVb2Up/JRt8LtXlqWb7o7l7HiESy7cya9fqSH5XAKRDoQGd7WR19XH1GsCbN9RTCg6iL21nzPe18eF1+7kiz8/kfBQnNOui3LLuc+Mcs2YQvJkfwM/almE5RQy+IEqtM4kel8M78FevIf7yX9iF8PnzkIGvVQVhZlS3j+hq8CjSy4uO8zdXXPoTAXRJvTIjsmIsl2a7x43p/qH6C30ca9YRtQxSCbc8d4dL+IfPY3cZO4jKT2sYQEfWvAY5bZDxRe8DP0k5sJ3pSBh6ziL/cQ/4WbrKhu3oI6hoNoigclH96/iuvJdXFZ6EF8aYx9zdDyagymgcU4cIeD4s4a45nOd1E1LEhnSefL+Eh78XQXx+iK8B3uzqLQDIYe7nthPfont0gKkT64fvPQgjQeTlOdHmVrWT3xY8Lvbq3j54SJA4DR6sU8NjcKaxxR97hhASulM8obxpI2gkVOWlJCMC7z+sYTKlNL45uFlqLfzcir6zBeixhQ9YB2fR8Hjvaw6d4BJM+N0tXh46eFihvpd7qb4J8spv6+db31zH7MWx1AKEjGdzz20mu2tldjCABsivQEODlbwqzsfYdujQ/zx+9XkrW1i6P1zUesVospBhGyIC8QOqN7bfWzWsf+jvOeU/WAyzHcnv0ngqKzB53dN45SZTWjjcFGnzDjMhkM1xK0cZq0Aa0opA1NKAQUbJNQkCGxoJVVTivSZmB1D+HZ1Ev1jTcaRSzkgauOoFj9m8yDBNw6PIl1GxLe3G1msYZ0fxBnnqLfR2REv5fNDZahni/Dokvm1nWxtqcSe6aDJyJhFP765OqiSsWP0hpZ6vnJ1I223zMLTEszdRwSJxaaLTz76G+H6CFPDBj2lR9EMSA0hJN9peJPXhmv4+9ZJ9PzdwtydoL4qSuyyFG27PHiI4KQKYYHCOppAxNSJL6hBzxtGKImxNYY2LMGWPH9/PqLoRD55+jo8uo2mQXc4j28/dir7utIVupRiZnUPnzx9HXOLujjnN0fY8GKIf/++jL5Ok2nzY1zysR6qJyfRNDdRRjqglCKvQHFFwwY2nhDi019rGuWFGZHVRS0MNof49Z4TQGrIwgCyMIBVX4RT7G5Qhf/Yil0RonKFdUyKCXe8BPVGmANbfDyxoZgLru7NqoA2Ee0AgFeT/KB10SjL6IgkpMnhRAHf2nc8INjaUkVrfz61xcNce14HkWV++g4oakQvdYtTvBZs4PXhPJSEg50liBIbfepY35PK4Ddd8/nV3oVohu1WpdAEK/Pb+PakDdTPS/LBz3VywbV9o+33+mwu/2Q3S04L89E/zIYDvVntP+fKPgIhZ5T/ZUT8HptTZzSNxql8pXDLHa1sfT3EQI9B8rTQBLwz2QPlFTanFrRR4smm1wboaPFQVGbRYxfwRriSf0Sn0N2WIxcj19NKrYxY7fTZUX6xcRcGEn9QkYgLPvzlTu64tZ5Xo7XIqV6+fc8hZlVEMdKeocffnsbu7gpX0acl5RhYjsatj51H+RkdONUGiT02+kn9rkWvCRgWmI9ECLzQwaKrV7yj9v5v5T2n7MvYh9Kyz1e21KgpGh4tkwdw1twD3P3qUlLDRmbA0ZFoQ3G31GCegpSOeWCYwF+a0ftj+DePYV2VT2TNPS0kUbNiMCVB4OFWlp40yLIzhrEtwetPFLJ7UwBhS/wbO7HUFHKeLgSoUodEt4eNh2tdS9Y6Kov3aBmP/VaKhqsKGPrZQfI+NI2uIR1bjq0cr2FxwtQj7AmY7gkkl0hwdoT4V/5UTszvYnGoZ/Tz3bEipuYNU7ZzkJ4bBrEtQdLW2HUgyN43/aNcPMmaYpxcJe0AfILYVdVoJSnQBZ5HBvH9qQ/vgR4eXbeEF3/lYYrVyuD8BppD9elcBjczdiaH+MoVm2iygkyWJoVGiuVnhFl+Rnj8ELioOI1Ra3JESkpTfPAzHfi82XPFrztcMW8Xf3h6OanxcQlTJ76gFt+uLrS4hdEfobNZPyY9M4CpJNaXuglu0rlXryI/ZLPqInfMlALdUDzw5jyuOmkXPtPOCtJHHIMt0bKcMZKU0kmWjn3+j42z2dxcQ1Nv0Sjay++x+OnJT/Ox6p18rHonjhSckroIe4KGiwLHdYmlG/L6cA0X71rNhcWHuOGm3VlFPbx+xaQ5KU5a1cem53U4Cgl04uqhrM1tRGyp4RmXcBfIU9zx4AE+c+F0olXZiU2Z4mZtm0KxPNTFbXWbcl6ladAwPcm2tUFufPr9SI8HTOmeanJko3t0m7riISJJL13DeW62fFoMIfnZ5NcJjXOR+tInhtt+3sJbO2dRkzfMtKpwBvr3Hxvn5SC7A4XGwECQ4f5iRKOEKWO7vgAoVtg3+lF7Tc696tT/MB7/N3nPKfugGSMiRdYCnFrXQ9tAPrGUQdDrarfOgyaVz2+hv3ouTlXhCPDWdbusb8YxBeEfzMB8NEnw9aacBb1FQkFMjvpBRz83wKen+NU9W6mfmsAXcGl8z/1gP5teCfHdmxpQUqH12xNzcXvSQaqRzaAvHTMwsxeOskE1jSvUqmnsU/XYBd387KLH+MXak1h3sA5DlzhScOHCPXz6rDf45KGV9NoTFHjVgIhOvMvPM4V1LA71uBaoBtODw7zcV8XvbyokGc/suzM+Pd8+ttUrAgIC7u9T7ytE67HwPD2Mf0Mz5r5eWm0P7OmgMNiHXZkPtoM8XnDwskI+2XQyMWlw6nAbtzdsxDduk3eU2/yJ0E0nnO1uvhOJUoLKgggt/YVHf0FqahHePT1YK/MY/kQ5T/T3c3HJ4ZwIKCmheZeXvk26m8PgCH7y2Xr+9MMq5h0fIZnQ2Lw2RP/sBh7dPo+/3vRPQv5MNE3EMdFROWmAAFdxAVJpPLZlFvGUiTMuDT+W8vCx+y/g0Vv+QmEgmcaYi4npeVFZBGMDto+mZAEJpZOXwzoI+GzOO24fr518PKHn9yHGBTCTx0hAyyWTZqa4/b7D3PLPUrcOwARi4nBr1dsc5+mhIRCecM8dCTPMWJzg3rJ/cfOD7ydheV1epXEk+gLFDSe/xTUrtiIRmJrkUE8R3/vLUvYrP6BxYn4HpuXkjHEJARcN7KW9rDgrwzp8LH4qLZ2oiZwg0Uagbqhi0RnzJ77HuyDvOWUfl9MwkRzoKuauF45n/aFaQGGeOMjODeV8YfUaAHraTT5z4VRiYY3Qlj1Ir4HyGmjR1OhEVfP8oBSBNbkVPaTt7AmY9z5dt43JoTjecValPyhZsmqYC6/v5eF7yyEwgcLRXLx/pgicjQXoJwyCYNR3r2xQ7V5Ud+amMTjsJXnCJJ7/126+d9OzpITJYMxPeX4Un2mjFFxdvo/dTcVZbhblgOr2QFIj37L5VM32UVeDqUtMoGTPMKnUMQqtAN693cSKAxkFyTOkaJzi8GskrinFmeQFQ2GF/Jgb3aC2Hk2hH+wlcU0xqYuLwKcRS59UXhmq5dMHvdxUtZNZgQHiUkdHkm9MjIXzB+UxMypN3WEo1wL1CeIfKiM5OQQB971vGijloqLDWQaGUpCIavzwUyNBtTFfc1+nySuPjOVM6EMJOoZqeXXfJM6Zu3+0WDVAqZlws34naK8aGpknbsJgrpOi7Wg8tnUmHzx+GxsO15LaVAA9HrAE+CViWgxtUsJFh3RaqFIDPJnz2hAyR/B1TDy6g9VQzPD5s/FvbMHsiqAMjafemMKs5bsIeLPfh5EjgxTA41V4HhkkeU1J7iRHBYk9+dz19CpqWg8Tf7mXb997kFmLx1wnIzKiP/1+h2mTh7l19Tp+8OTJjPJupyf2J05fx+VHldScUdnLb256lg/97gQ6Tq6gyg5nBXtHxOtTTE4Nsc+pyFL2c2q66NkTQOXaYR2BbPfAIR/kO2j1CcR49J8uiC30ok1kubxL8p6jS1i3T/H42ql85J6LefNAHY7UcQJg5Svs42N86pFzCCc8/OO35aSSI0FD0JI2+nAiwyIxdsTxNA2Qc7aNiE7OY7wpHM4pbslQ9CPiCyjef2MPkxdb+AtyWOkOqH4TIjn22n4T56Vi1GE/csBAthnIjQXILaHMdjoS2T2EVhvlb9saeOnlEjzKorZwCG9aCQoBpxR2cGXZPkzhgJN2fVhARGfxwBB3Xfkk/zrzUfL0bFheclgck3oAwLevh6AVy4iVpHvpNjdx1BTL17DOLcA6p4D4FyqI/LTOdZXhusySaUV/tGyNlvGxA6dy6tsXs3rH++i2JjitjJORdZ7RKgVv7q/mk38+j6F4jnsogZhkjyp6UHy8dmcGTe34+zft9dJ60EtBiYVngipj0hQ4Re6z/rRmoVt4fpwYQnF16R5Mme1yUjaoPSPW79h8PlqStsnbLRXEUiZ3PnMitHvT1qSAuI7aGcTZHgRH4Pt9b86NZXOkDGOCYiWxlMGLu6cAYFfmEz5/Dv03HM/Ah5fxhHU8B7pLSFiZ/bJsbfQ01DYQ4gdPruTiX1zJlb+5lN8+cRxI8DzQNyECSPgtYgmT/eUz6Fw5l+/c3EDnEQ+xyMRqy+uRnH/cvsxNRgiCngRXLN+eBQrQNHfjuSK4D8/f+uk4EsSeoC5wIi44vNNH665S7KPI564/eTNeMxd8J21YHgygjrhJhc5zxajeo3csyf5wx4T9ejfkPafspVTc+cJK4pY5touOHNMKbXbqBaz+2TU8/2Q5dg68cIYkFL4H+9xj1gSiI8mLZgeFQvqxA3dFZTafv6uJu6a8htdyXL+5lVb0vSZyQ/64q4/y1cd15M485OYQ2j4H1XcUqkhKtMXDqOsU2tIE8U+U863yU7jylyuwLJGltD9es5P7p77AwsQAap8fubGAa51D3HnJsxw/pZUCTyqni2LacbFjukIAfB6b9y/ZicxKSBNgCZyMfuJqyJGHBXRkg4f4R92grNPgmZDpckT8msWCYA+HE/l0Dge497VFfPmhM7n7lUU56YvGK/yecIBLfnk5t/z1Aja3ZFXKBMtBVCURwTFFkWclqTDj2demZfqCBNY5Ifp+OZmEmfugLIQgOculRTjcW8znHzyHwZSHiGMQcQySUqPCG6dMRdAciYhLVMrdlOWmgJvw9x9EE5LksOK6W0+iuaeArE3B0aDJj/N6AQjw3tsLCTmGJ7cV/VEPT7xQTjyW+VvLFgzGfOkcjvRcHW93OBo3/+l9/OG1xXQOBYkmDLZvzeelh/KJRwW720u58reX8e/NszjSX8j+7lLWMp/hjy5wM4aPnrARB/+POij81C6Kf/8mBQ9tRe+P0SuDXP3wyXytbfmEVFXglmMMejNdZRcs3Dshy6fHq1h62jDefw+RbM4jmdBcj+/RouCVNVU0b6vii/84m3jKIJVW+tMqevnGhS/hNSx8pkXAk0onhgg3mWAkZ0Zq4Gg46/NHIZcmDguCPXTGByfu1Lsg7zk3zsKp1VjmUZM/rLtHpR4TtTdIwhGELT/GaDpqbhG43B0TWUumV/K+W/tZU1bGvkTm8XnI9hyTo73L8bMvWMLeN6uxNhRhhzSEV6KG3czeMVHoQqZ9sGpM5+dJ9JMHQZeItjBqVxBSmrvOjgsj6q2xRZKmN+w8rYIXBmo5ryq7QPXkYJgvTN/E5S9PpSoU5vqVE1kiY1JZZ7Hk1DCbXgnlIAZTVDcmyTu3nL/tmUXuMRQQNlARHZE3wbM8GtZp+cjf9CB67OyFf9Qz49Jga7SM3dFikmET7c0QqYSHldN0YklzFHab0Qrh+tY/+efzae4vyt1WpRC2g7bIDQArqWC3SXJPASwSTORjSUmd8NmT0QoScPV0QvcdACldeKKhgYDh1TNQMyxocuft+kO1rH75YhZM6SRPt9gVK6LP9oMOnn/2o+9LIGIKWhWpKeUk5vgmdpOlRVqKnT+PkJxbCVUTjKECUZkieWUxeV9sxdgVJ/aZCtQk7+iOeKdxAnse3setF+x2K5BpsO6NIr575HQSQQVhlc0fJQSppMaf/9nIox91EIkREKXisftidJy3xM0EzxANBy9iIIRePJYgKPpt8j7ejIjIUcIxoy9GYHsLkV/WoQoN3ogX0pEKUOPNXdXNcjQiiTEXXcib5NYz3jjm1ErEdFIzSvnSRW/yxhP5nHTuEKZH4QtKknH3RPW9j9UTOL4QU3N4q6mWS399BZct3c682i66hvP458a5JAccghta0LwC33llJMIFuaeOAtXpxVMbo9hI8IXazRiB0okb+C7Ie07ZF+blYqsTyB1BV5GmMbWJmRUE103six8RZWpYJwbxvBbJqIGpNLACBvcuXoqKG1xQcpgXBuvQ029OInh5sIbTC1uzeM97U16+0HQiR1J52KU66vQIYq8/HWDNYQGP6hKBv3+AKcPN7LugFqm72Td6XRJVm0QlBHJdPtrkVO5yrobGPX1zcip7gIaSQb50zmtoHok+gS/1aLntV838+NZ61r2Qj8crkY4gmO/w6Z+28IeSpbz5eKNrrRxDVFxDBI+hyAUQ0BBDzoQlHY/GXifRUQGJPTsBmz1IpU1YvwDcalHtg/lMtLEjBMqX5jbxSeTaAlSXQdzU2dxcxZJJbVlYe8sRPLdjKnJfHtQkkaKIgQ8uwdPUhz6YQOZ5SDaWgqkhYkm0M/tRbV6IKwhbbAuXIMf7aR2F9x8DaNFxrKKVqf+4AWJL/JuOYA7ESI5kbuYSDYRP4kzyEfngJHQVcdlftbHTlvTCY/mzePnCfEojYWIDMHhlOan3OeixKM6a3HBGLZ6i4Kk9R603wd7mEga78yHX4cTR3DXRGGfkvXgfGkDEZBazZOqcfFRIH8Xk3981k0/XbMsoqgKQSOn8c+PcDPRd3DY40F3CrOrcdQWkhPXPh/jHg2soK4yz+mr44x2V9LSbNExP0ttpsO65fG68vYPU5EN867FJAHQOhbjrhXFwSaUw+vox+qIon4mzxYIpE7wLKQgmHT5Qtp9ryveSp9sYviEYR4z3bst7TtkbusZxU6rYdijTv6Va/YyPLiVnlOPb04U+EB8LyJJD1VqK5OVFyBoT3yODiIhESbAXBoh/qhzydKq9Ub5Qu4XP127l7ahLrTs/2MeaoUo2RcpZHOpBRyIRWFJw7b4z6LN9jChy4ZNoc6KooETuzOYpccYpy+Un9HP7ueu5oKmc+Dh+XyEUgbgiXpg6Juq70564rJmuwfsX7z5m7eYRkWnggNev+Nrvm+ntMDi820+wyKF+Xoqk1Hl7VwmiwULtm7hgCAoCsQhJZY4mnWWJpRARiV0XcgPUy4dd19pobb7cIHWhA9VJ2KbY2lKFOUHFJqXgQPexA82AuxosgRrwoAY8oxvPD59ayR9veBifaWGmA6spW2M44eU3Ly9z512n122zoZGamr1g1bCJ8EmMVD+++/oR7UliX6uCUd5+ICwRR2XF6oPxNIos14aq0AajhF48iNHrnmI9h/tJTikBzwQupYoUcmM+TsBEP9PIrJkw+lAIf7+W2O9tvDv6sFYVuMHcYTGhm827rT0nxYDy6MfMyh2BRupp37ZnTTgnB411SiiDkvzR7kkYb0So7RukoibF8jPD6Ca8ebCO3768NPMRjs7tj57Ogx/7R+42KLjgw70UpStSCQHXfaWTyJDGni1BZi+V3PzNdoQu0MQQd72QIJbKkbCpKewpBQzVzWfF5BbmTj7Mn9YWkrSzd7qAafGtuW+ysrrZbaMSkHgJ8qZOPFb/R3nPKXuAT1+8kut+8PdRzutRGT+nDI2hC+fi29GJb3cnIuUgknbGNcoAe54PVe0l9X4P+ktJ4p+rRE0FUTB277mBPmylEdRtloXGWOlOKWjn2n1nYHRIluV3YyvBM/31DNreLOUkDGByHPYHXHdM5rcA+M0UFy/ZQ16BHGftK64s28+1FXsICpu4o7N61wXHYKWEuKNnWTwjIpUYjTXkPB0oV7esO1jHlr8obvqfdgxdIkp1Hpkym1eHqmGHQBcShUD4JEqTE1j3imBpDKvaQE2ENEhIvI8NInRIXRrEa0lCW0yMmVG6Ta97UvPLiW12BZiSaMLDPa8t5rqVmzOCcJYjEEBZKPafWUgF+PKS+Pf76R3nomvuK+LK317Gh0/czKkzm3Ck4NkdU/nzGwsYiAXASGO6j1UH2OdgvjaM/6fdowXUAz/sIH5LOc68gLuxBLPHyGwdRKQclKFnJPaJuIUxECHwykGM8Jh/2jwygD4YxykOZNJA6wpRnYCUhurxQL7t+pJzMT8KUD6Fc71J+MXZ6P5+BBIK0nxNOV5lYnEdQil8u7oy3pU+GD/GiU4hSixAUOsNc25xM4/qHqK5HjBu39c2SPJ+1MxzdhBh+zE8oOngvaKeZqM256Na+wvoGMyjqjCS9V1kSBDIk1kw3rwCyZJTXbeeLQW2FKQw+O6lz/Hx+99H3DLS8z6NA1YCpM7M2l5+cPULpBydB95ckKMrElN3yPMmcKRA1xRKQcROEMo9Uu+KvCeVfWA4SfFrBym6oohDPcUoBB7dxqPbJGzTZbwEMHQSC2qwF1VSn9dNV8ugS1X6RgSt38Gp9RD/kktXqzRB+OzZ0KJBu4aoT6DNiyA0iEsjpzVtaoqvqTf50vrlPDBrmus7V2piV4QEUZ5CtWbTF6BJ9PIUA8VubtEJ+Z28PFjDp2u28b7iplHlbeqSVQWtvDJUk5k0E3PRNjKk890ji/l41Q7KPXE0VIYlP5IwM5KQNH4djhhgKUfjdy8upvn1KOsuLOXanw3y8/Aswq/b6J1DOJM9JBcHXZRSfQKREKhDATi6PJ6hUEvCOLn8zcqNT+j7E+Q/3EPRPPj2tW+Q77fY11HCL15aTkd/EfqqATf5q9mHOuR3ESYFNvqMGJOr+/hI3W6WfqKHpG3w+NYZ/OKlZXx45RaKvQmkglc6qvl513EUeFOoYwTiQeKvj1Dti3I4UZT1bedQiDueOoU7njolR18EoiYJTX4YNMiy+HSJKErBPw2SU8rxHOrDmWkS/Xq1O4YeDRyXeTG1IoR/7RAybfEKBQVP7GT4gjnIgAEKgmsP4d3bi9I1hHVU2TwFBY/vJLq8geSMcjA1vB6bOfNbmX/cER5/czZ9Dq5FfYzNTwhQHomoTKHavTA5jjAVZqQfy1+UFUNQfpPY8ZNQAQ+Bt8bciMKW+Ha1k1hQA0czqWqgTY8hHElN3yBTjnSx9Iwi1vwjD9vKvNZ8LUyiwsRZV0j+L7aNiwuAk3BpbJJ/boMPVuWMb+iaJJoVN3Cn4c6NeRx/VjjruxFxJAxbHr7YdAI+3aEjGSR5fAR2B9x370/DfNt8oAQ3nrIRr2Hj99jcdfWTfPqv5yKVIGXreAyHeMrEsnVu/ev5eAyHr7/vZZZNayWsLf9/yv5oEUJQYg9x/40v8OV/ncUb++sJ+VLc/9GH+NZjq9jWUkk8zYvj96SQHkXXiRrJU0tAQvLaUhiwocQY03YJDbT0QpWgWrxIodDnR9kQrshpR29fH+SrV00mleglX/SCVxD/fAXWCcd4ZSOkNIyzqgIO2vQY8fokP25bxFuRcm6q3Mn+WAEXlRzGexQc7ot1W9gbL6I9FYQ9SXy/7kE/7CKGZI2Hl28u44UFqwlqFo/PeTKLWsIdQzcfajwzQzxdaSrfsFi98AC/emYSnS06t781m8DXO/BKhVPrIfm+WpQEuSfg+lxHLNpRC18hNEXe4j7ingks+jSTmJzuZe7PDb566tvkBdx+Lp3cxu8//BiXv3YenbqJXF8A/cZYYLDHRPbnc/n5mzmjqHWURvraE7fSHQ7y0ZOnkbiokMgZxTh+A0zokwGMpWGMdTpCkjYI0gFxqTDjvdgzJIdTBThlNvS7fQn5kly4cDcrprYQTnh5dMtM3jhQz6hCtx304iGEAfqSYZzXi9yBddIWn+4G4OUhP/EF9eBIoismQ0UKNmmIoIM2OYEodJVX8mMlNLT1MtihE/N6SJ1bgJzvo9xuYqi8BP2eXjz7BxCOQji5T2/ClgTXNREcGuDzPxvi9Jlb0YTbVU+Zjz9QjAzrbka2MXHsRpiglaQwm03sehC6QiyOo79q4FTlQNGYOvHjavC93Y42jibZt7+dxMXF0BRwXV0KMBXa4jAi30El4O3PSHa0NXDvur1seqqR6BAZlMmhFwZwllSjbxkGJ/dJT0iF90AvyVnZNMGWo1NXPDhq4IwYNjs2BVn7VCGLTo6McuuMF6Vg+0AxX9m6hMEDOqm+GpAGOKAtH0arTFHjifD+RCvTV/XT2l/Agvr20VPCgvpOnv38n3ht7yS6hvKoKhjmVy8tp6XfNShiKfjyQ2dy0yXr+eDKJRO+i3dD3pPKfvL8elad08empmrWHagnaZvcdvprFAfj3HX1k2w4VMvT26eTSOlEyhXb8/NIaumujmz6pWN+NGWD3BkkE96ooZr9qIYIqYDGt1sW8/WGt/AIZ9SA/9GtdaNl7YQC4grj1QjWggD4c1izGqhOM00LoNCGE5jlXS4Z1EhgWRq8MlTLJaWH+PXU13LWQs03LP468zm+/9Jc1nxZzwgs6y0pgt9sJ3p7NZ7FGvoxrDelBNfsO40FwV5ak3kUmilub9gIuAgGuzKE71Qv+tcPQtS9T/zWcvBryA35blLWeJIpgavwGxIsP64JT9DijUj1hM8HUF6dNTWTSZm7ccstudhnv2ZjlzvQHMDcNIzRHUf6DVJTSlF+E+UIfvL0SayecwA9nVnrNR3Kg2E+cGMPv14wNcPHC2AXK8SqARY1RzFtiddwWD6phaUzWrni0Nk4aTC9NimBcyBAfeEA917/77SV5j7jhMYW3jhQx5cfOgsSDr5NR/Dv70KWlBObHcJ7ZjdTe+Ls3VfJpLJBUv1emnsLXZiwBmg6K6Y2c8PJm5hUOsBAzM/f18/jXx2TENMTaPkax/3JpGTvIHcXL0ZpIA2dPvwYw0k8bw0gclRLGv1EczdRe2aAGV8TLJmyezSwLICTZzTzh+3z0WbFwTOWeJbTpSfBq2xW1TZR2hvmaVFL/zQvbDNy/wBASqzqArxN/a4hbwriX6xEnxmD6TEK4g4JTUflOxiaRCnBrBeaONjmhteD+Q6/fGYfv/tGNetfKEBKqJ+a5Ib/aecrmxeSHBjKImIbEWFL9P6JEDo61/7+A9xy5ps0lvXTH/Hzt19UsP5+A19A8vHvto0fxQzpe0XifKqTPK9G5MQAqWll7mgakpX57Xxr0np0pfDokoX1HWhH000YDmfOOQhA0tb54TMrM75P2gaPbziXD5/y39eR/m/kPansdV3nzA/O4f63w67fDDhj9qHRrMTjG1s5vrGVhNQ4e/v7ctL0Aq7SjUn89/YidvYQXdmIDHnRhGR+XScFgQSHX7RpOyufl4fqaN+fx7UVe5gVGGD3niA93dkZmObaCMlLilANwmXKTIvhOGiPh3F2WKAJfLu73ai9oRE+UIA1qQhMiZgVJdkgeWagns/Xbp0wtmVqitafOZl8OWkRSYX/9z1EFtQcK12MQdtLRypISzKf84qb+GzNVgCGYh6e2TkNu7qQU3iJ5x2/C5tfFUI2eF1GxXxrjN5hRFTafGz2EZwhOb66gy3RcuITjX9adBSvDVdzUcnhzH50WeR/fj8i7iAsidI1gm82ETllKqlpZWhCsfFwLSunN4/+xutVnHVpP78+OEHP/ZL2eVDnjbGquInTC1t5YbAO7/4Y6tEIWreNM91H4kyH75/0CqGjqI0DXpsVU49wzrz9PL1lGvHlk0DXmPynFv7w9G5MIbEdjW0zK8jzJ7n+D+/P4Ly5Ytk2PnH6htG4Qr4/xS1nrOP4w0f43D/PRjYk2be0kINVkzIoERQa8pDtolpy8CqM977LPA/Rm2rZUWDx8cOncO/0F0dPd28OFqIdH85Ax0w0x4QA3+Z+3vxLNH1iayPP0IicMcMlUcslpkCW6zgxA3uen9Slxch6DwL4aOVOrizdx4FkIXtihRQaKVbmtyNmKL64YSq7duXz752zmV3RyylfFHz0zoOUBWOYnrRP+w0Pep7XhbTmQNkpXUPme0FIRFUKUZ8AHVSHiWrxcaDAx2eePwnfgz3oIgLFOlptikSrxbeub+B7fzuc5bcXAlacM8ziU8Js3FKE3jCMdpIJliCQdPhWw3r842g8RnRQLkyBlHCgq5i+yNEUEYK+ztwEb++mvCeVPcDkhWfR8dzTjFjjpu4wYHtISIMKM4YmXL4PMTFEGixF/pWHEG49EvJe3s+UTxRzx2XP4TPdAJb5foc3j9Tw9eFF7AkXcdveU1FhAy2aIOQ9gJ7IhA4Ixy3GnLimGOu8QpTpBgjlUw4JZzJihkuMFZ1TxlK5i95HB3A2HmGovhiSOmp7CNsRxIoM4ikNU1cZqfUjEotoNG8xJlTmWnMKLS6JOgYeLXdlI0M4/GzKGib5woQMV4O8tHsS33r0NLdWKooHh07Fs7wHcWIUZ4nLsy8AbVocpiRw1hRCePw0EiAFa16YyS2f2kJQt0jZ2jEDyg6CpDzKB6zA+41OrPCYa3kEVZX36kEGS4OoCoOElT2FPaZ0F7klUG1eVFRH5NuI2iQg6LCCdFhBNvSU8aP+ucx4qgnjqa7RwKm+P8Hk3V1MvTA3tXHAa3PF8u08vX0GAPHFdbQ+m06IMsE0XAtv7f4GTF2STE+RkC/JJ89Yn1VW0u+xWTqpjWX1HWxoqmFztBHv8YNZz1VBDSb2urhzQSq0cIrgfUeIfbeGjlSAf/dN4ery/cQcnXsT87JgkO4aSbtXRmi8JZhrw/DX7oyThOY4ePf3YFeEcmP/lSD51SJSZuHY/cMOnoTFlfP2EdAd5ht9zA+OwSClgCu/1Mtn/rGYX79QgN+0XZ56qXHy9CZuv+gl1u6vx1ECZ0oJwbWHs5+bHoDkjBK0E4cQBfYo0kgVWjAtjvNaIdLWSX4lH0IFrrFnCPQDSaKPHSAZ1/AHswfY65csvSHOS54F4BFoaVqI0wqamAg6oAB7HM++lRIkpMk3Hz0t5/VB3zG4dd4lec8qe7ynYe38J4RsKIWrd51FuwygoQjoNh+r2s6Zha05MjvHRLSlECOFAxT4Gj388OKnKM7LNJ2Or2vjo3tC/Pypk9zF5mg4mo/BSxYTem4vniODmfdNKPy/78N3Tx8yqBH5VCNWshJMF6U/sj1s8czia396iV1/buGvHOd+6AjYHeDME1pd+HM6Uj/eSkjGBS37fBNvYrgL/3uN6ygyJy5h177V4I/fKyIRK6FhZoJFl0q+8eqZJO1x00IIUtPLEIEQum8sSU3ooDTl+qlfzg1rfO7tafxh2Uvc3ryMrZFSRnMKcrR1YTCzjuu+bX7sLonIVR5RSvw7OrDKGlhQnwnBdWzY8lY+MmYgtxS6d3cEYtlghjIDwK8RLQvwdmUDgVTH2KZiQ0HIJhHVCObn1q5FwXFZtYZG/Lia0XfUZ3kpNFJUFYYziuecNK05DbPN9rX7PDbnHreXDYdrkb1eUkMel51yfLenelF5OiKRA5s4ToRUGDviiD6bZInBE32TuLp8PxvCFW4fczq8BaIrhQoZ7ok0IjA2xbI2FwF4D/SSmF+NU+B3rewRsRz8b7Vgn+hFlZuIDovAz7vQd8Wpm56EExTkqJCoaVBQpbCLCgCRjre58tLeybx5z9XEe/0opYEpCJ89k9Cze9xEuHRgW9cV+ZeVMTDbzlD04CLhlKbQFkQQBTbKo4/57QcNrDwf1nWV2Pb+nOOpafCXsgUuAGHc/Cn2JvGI3HETTcDOQ4X4nSQ+j826Fwu4r+8MulKFWdcaOnxg5bzsm7zL8p6jSxgRIUzkTh+amUI/aYBmOw9L6SSVwYDt4yetC3l6oJ5TCtpGMbwZv++xyPtia+ZnG3v4zOpGhvszLRZdU/zx6WUuEmQkSCg1MHQiZ81A+nKnswsJWlTie7A3pxWUsE3+sGYpH/92G43lrqWjCcldlz/FkrJuvKZktLqZBOlAeEDn378v4wuXNDJhghAwZ3GEE8smLl780G9L+fIVU9mxPsiB7QFe+lcR//OHE0lauWINGqrNjzqKOkEIIOBAXrbySdoG+zpK2LCzjtr9EuewbwJ3gSJfTzI9MJTxadNBH84E/RMKjIEYp88+SFko00ergH/+qAy5qdB9V45wYYfl1miVsQzxCKwzQwxcsxSraoza4cgBL+YEpSodCXvax2HphUCWBlC64Hsti7h891lIBdMq+qkpGkakM4Q8hu0WQc8hmnCx14ALEOjOTbsY+1IFyvufEyWUKdA73eBhvu5u+CmlY8mJ/cKqxACPQHhAFCsSN5URubM263lCKgoe3Y5vZ4cLZ5YKbSBG3isH8L/dgffhfsSgTd5nWtB3xBE2xHo1jAkIxgD+tv64cYOhIGiDRyIdnWhXAOkI9IEYvk1HsCrzGbj0OGILa0lMLSU5vZiBuydxsKbeDXbnMGGFhstbryt3PUU1nJeKcNYWIHeE2LRxJtc9cCkdg9m70cFYiE4nkFVGcF+8gJTKPZ6xpMETa6fw8dOncf3KWfz++zX0teZwMwhJY6XOlactnHBs3i15zyp7gLrGWrx5nekq9JkvIqEMft0+j6R0UeW+dKaGUAoSEv+PO92U9HFiJwW9HSZ/+G5Vxuev7Z2EdXSKeFp0QyHnl0zYRiHBc3hwQsdoc18Rhglnz9kHwJlzDnJcfSfm0SgJAR3NHi6ZM4f77qgiNY5gbPydhVD4Ag4f/3Z7xs/HP76zxcOfflCVDi6PHNsFTlnexIE3TUEkx8SWYpSqOUMch9f2TuJHT6/kkY1zUTtCOM8Xo+JH319kUBePtLW5sAhrgsxcJcCuM8lb1M+wbRKzdJJxQX+Pu8qDq0vStQHScgwlA4CpUH6T4dWzcPLc43RkyODVxwtxchjRKdvgvjWLMj6rLI3x6/a5PDtQT0R6WReuxFZw5xVPUxyME/Ck2NRUMyHWP5o0eXXfpJEhmXBlOnMChH9eh/oPp37dltx70qs8MON5fjn1NZSC4wI9E6cCOMoFL5iZJx9Z7yH5gcKjLlYISxJc10zxHzdQ8vs3KfrHVryH+hCAsS2O58khREKNZsL2RgI8/No0+sL+rKWQSAjW76t2D34zo+ire9FPGUA/qw/txAHXoECQ9+I+AptaKXrgLYIbjmAMJfC0D+E92I+5Meqe8nPQg48XYbiGk/N6oTufHQ1sDeVoNPUWcsN9F2EfNUj9KT9OjvW/MVxBv+3Nul4qNyD81JH5pBpd3ZDnt1h8VQeiNAmG4+YYaJIpZQPc8r7F+D3/mf/o/yrvWWW/ofcAB852sBf5J+xFxDF5rasaaWloKcVCfzfvLzpA8TeaMbcnctqNtqXx8sNFGROybSCflJ17B7cxOOEqC4TCMCVX3tLJ37bu5Mnmbdy7djdnXNrnzq4JJGBa6Lri4c1zAbhs2faMAiwjIgQUV9hMmpldaDytrjE9kuVnDvPzJw4wdV4meZdlCaLDbjWnJ+4vxspBcCYSEzKqT6zUdXWUzz4tmls4fLSClhKQ0HFeKEEdxVpYbGQGp6LSYEdDFbLILTSeJabA+nAe/x6YyuodF3DdzlVc98F5PPGnEjQBF55zhNsuXMPqefvw6DYkxbFL04XT71YIEnMrRz/+7TeqMhgWo0mTaNLk9kdWsbujfOz3SvGxczfwr95Gkulg9A9bFzJkeynNj/L4rQ/w5fNeY9nkIxzqKiSROood0hEMxXw8v2Mse1JUZb/n0ccVGziTXW2fU7XpMHdJhOkNUfy6g6m51myZmaCwX2bVrsWWExcH8GokVxdmfGSYI/Dho0SkUWbtNubrYURKoYDISVOIf2g+q5a3URBIZOV2xG0PQ8Mm2rwIWmMMYbiwT6GDKLbRTx5ES8TRB901qyVtt4Tk/h60mIVIKTyPDMMRH2r4GIgW5S5F1eFNZ+5mn1Tz/QnWHaglmjSIJEyG417+8OSynJukQvDx/afQFHHraIzMj+6hPG7+2ZkYTxzEc7gfUNROTvDRvM1cN+dtPCg0FEpqHO4u5nP3bOZ3T745cbvfJXlP+uyfa9/Gt3c8TLLRgugx9isb5A4/MhogJobYckIpWzzlmKcP4d/ePaETxLIEtiVGj/G1xUOYupNRCWpEvIbFtJp+mqc4fOa7zcxeEh2t2lMzOcUnv9dO7WLJnU1krQ9Tt7lgwR52tpXRF3HhDYX+iRe5LQWhcgf25PpWUFGXpO2Ql8fuK3FL9k1yj++2465jr1+h6RAeNEYrTY0X345OoidOzuFyUpDnZLBBAq67oXWESjdXk3KuEOShAPp8N5PRr9lcWnYg4xJDSHbGSol/SxH8QiskJCKhUKZ7z/jNZchJXqo9ERbm9ZK0Nd6aXcDUuU0IDU5sbEHXYPW8/dxy5ptcf+/FdOwPoE+LgCezTcoGOUIhbGhYla4rRzcUlfUWocKxPqdsjct/cxn90RE0hftCRWOc21OLkN0m6qAfFdPpzA/x/v7zWVjVyfL8LmY29FHwYIQf31HClZ92WHn+MI7QMA3JhkO1fOuxVaQcw3UzNMQxAw72RFaMR+AdTLHsnCE6uvw0bfeilHKBBj5BZWWSr/6mOedPv9rwFrc9vQC5bAyKrO9N4EzzgW+CFZE/1g6v32HOsihhy8veLXnotoWpS4rKbW7+djuNs2Lc9fU61u904zjxxbUkp5dx8cI9hHzJLLCBEG7Au3RKit4GK6v+stBA6QoxJY7SBBO4yNESNmJqDLU3iFo2lOXKUTbIFh9aQwI1MC5nIy1nz93HZ89+A79pIYQiYZn8dd187n9jAY7U0YJhRG0iS2N2WwGu+OMHmOUboqF0kK6hPLZvzCP/iV2Yo6VKBbu35PGFCwsYumQeMjR2E4UgkbL547NvcdbiGUyufAe0Hv9Lec8pe1s6/HD3YySlhbMjCB6J1hjPWaRbIVAeA7p1zENhrGWuQrXOKsD3pz7EQO6ZU1ZtjSr6lK2xuKGN1EQl3gScMesAAzc1MmtxLKs8mz8oef/Vnfz5d8MMDQRGeTJ8pkVVQZibV21kzd467LTlue1IJdVFw6McLOPF44NdoanIkh5EX7ZHu/Wgm5nb3uTlxX8V8Z2/HGbaojgeXaKNu99xKyK88mghiWhmn7z7uklOK8GuLRjLdtTSiUGLh7M7nxDIt//LnD8lUGl3kE/YzJK9rDDHXE7xpMGDzZOJxnRUqc7A9QvwbBvCsAZhisJalY9epvGd+nWsLGjHUQKFwPyGg5n2x6ZJQAl6LXymzZ1XPM2Vv70MqdlojQmXME0IEAq5M4jqSvtElEKLuRukU21y+e86SUgdR4EpFF6fzerLtvHg1tlo/7KwTgugNSYReRJnV8DNInYAj0KbGiPhF7w5XMW6SBVIRcG2I9z/4BYeuaeEX9xWS3GVTXdDDf8/9t46vK4qbf//rC3H49JY0zZ1d4O2lJYWh+Lu7jAwgw0yOAMMIwwwuDsUh1JKhVJa6q6pJGka9+N77/X7Y58mOc1JKTPl931537mvK1eSc7bLs571yH1XDSwCUwWPgVLUQk6vBi7O38iTZcMI7/uKRi0m1e/i3vlr7NY8XaGiROejFzL57t1UXE6LZ7/ZhMfX8flRFBjVvRxWjMX3j2JIVRDNJsJv0fReUee3TFNoPrE3Xddt47RzKjjp0ho+W9kX57Y0rh+zEJfTIC3X4NWqfvypphdN1zvQIgbKSw2EMuyO1kl9dyYUNwEww5JexiZqjaK2m9cOQgOrt0Qk5B2OhfX6uVF6BzG/8mCt8aEMabG/EBIEyBIXcq0PK6TYyl+KbG0GPLxfMX88fn4czYbbYXLxxBWs2JXH6tJclI0ppGYImpP8MZZaxc4pGQIaHWysz2ZLRSZF2XWkLd6KtU9pqAA7gb20DP+U3h3OwTBNPl+8getmTOj0Pvyn+M0Z+01N5RiWiWxU7e5NISE/jHRZbcpOe6sqdFAGBmBAEPlPgVIexSq0Ca5Cl2bi/ntVXEMS2A+2MiGbBZsDpHuDrNiVy7s/DbGjALrVWo3j0KIoAh44aTZ7GpMpGhjC6U78MGqKxfuXvcvMZf35dkNvFCE5YdhmpvTfhi4MFr7mRLol6PDaouFMG1iMrsa/GKGoyqx1vanq3h1HD52kf5Z2Wo1jGgLTULn7wh7c/1EpA/rGJz8nHNPIc/flEQ4q8R6+AO/KbTSf0AerxA1RgegStpNe7UVapARLYlW691sKmAiKYpGe1ky/pD0cn7KD105K5qzdAzn6ghqKrlR5Zl1/KiNuFH+EaE06tDiI9MwmkpaGekgDQoMb8lYyIbm8Q2dxIqiKpCCtiQm9dzG57w765FexvCWbH4sLWb6sG7J96aZh4VpfAUDTfQX8ob4H3QJN9HQ1UWc4We3PtAeW/DCOsnIcc3RCfbORTTqy2NNqPJRxDZBixieEFUHLPfmEfes46dJaZj6XzZ7tTtheQ8bcGszuDpQeGv1rm/jryesRAmqibl7a3d/uwdMEBCU9gnXcN2lFqy4qWBT1Mbj+vjImHdnAn68rRN8PL13UVIl0S8ezaCfKnkhrBZJSHsXq1UkIxARjjJfqHsOZcNZWUCBoatxy9I/kpgaREq4vnsgaf0ZrGCvq0OGiDERpELleJxjpPCYtJdBs2OEkZ2e6uRbhyek459ch9pXCdAjCZ6bZXbmjGrHWJmF+lYno14IoDCE3epGlblClPSD3bJ/Ul9ww/ccOoiZgl8ReM2UJN7xzGkVZTVw24Du2Rny0WA76e2rJdwa4dtthNOWHOC5zBzcesZhQC1z8cJ+EesJCgmNnLX46GnvTktQ1JW4IO1g4IGMvhNgJNGP7LYaUcpQQIh14F+gO7AROl1LWx5a/Hbgktvz1UspZB+uALWkhhMAqccUq2BTM+WkovQNQGLK7VOs0m4cmN2onZKTEuMiF78pdBP+Yi9nLSXSMF/WMNJLfr0GNJfD8QZ3AqK6sT8nnd+8MiN+xIlGm1EGtjmhRmJBTxmUDV/H1mt6UNyZzzZQlneqhKoBXN6nuqrDDYXFIeiUNbosXa/ozu6qAQF0zqi+EmeNkp+bmlg+O5IET56DHxBZ0xeK7DUU88sUksCyyPywhmDCYHV9X529USdFDHY7L4ZI8+ck2/nheD3aXuDBVBWFJzG4OAnfnoaRHUAoiHbYp6g1cL9WgL2gBQ2Ll6/gHdydakBlfqRA1EVHTpgzeZ+e6YvL8kV/TNb2JQLPC4gE6C4qdvCf6Ed6VipVhv+zSkijdA1jr7E5m6jVkvY47M8jxGTtxHYChb73+QvLn02ehCLtnYUCXOk7puo11PbO57s3jMS0BhoVzazX6bntgFI0mMltnVziZXeF4ARahwTHnNTLrbjdKdTktRxW1DXrJBiLJSFj5I1T4MtCDK/PXc9YNlbz11y4IYc/+jD0hRvZt5ra7S1qjX+dnbWKYqOIv7/ZhT5UT15Yg5520JRYz73hPhx7agsdnUbzOTZ9hgQ73PWoIZq3tBapC04mDSP58A0pTLA6+O4rVKwFnUwwSgT+s8+L3I/nd9EUs25nPmWPXA7CsJZt1gfRWQ98Kp4LoEYbtJl+s7suE3rsSeveqJtn1FpC4BN2+dgLCN6YhtCiO75pj/SsSqQiCN3fB6umyn9LcKGpWPebcNGjQUXoF6Tu+jOOO3kmKEmFZIItvGgvxuy3kWh9JjhBdkjrXvRjStYp7zlV5vmkPd+0ehSUFqpB8WteDB7v9yO/yV/Gjrwt/6Loct25CUN1fkVyndEQep86I3gkEdQ4ifolnf7iUsqbd/7cBc6SUjwghbov9f6sQYgBwJjAQyAO+FUL0kVJ2Em37ZeibnIeUMsYcGbuqUQVrgw82xMqmFIkywM/eVkMhAB1kdwfe35dh5etYXR2otVHeXL6eTSu8SAm3/XgSIbMTAWQJQpeIwjBOYbB8cxd+evkkXrjoY3JTm/E6o1hW4hyXELA9mMTHtUWEVY25jQXMbYyx86nAlS48N22h+ZwBUOVgSUUhRz5xAcMKK/C5Q/ilyj1HLeDO4+exel0KS1o6LZbu8N+uLU7ye4RR9nGYcrtFeHreVk79bAotW3SsbipWn31edilJViOELJVIA/gu34nwt7HGq2VRkqq34Z8QJtwjz75G4SieJSW4ahuoP3oIerJC2NJimriCP834jq7pTXs3TzioYHZ3EJyeFq+JqgiEAsrgFsyYxJ61OIWc8c02HewvQCKRFo/DYFBeJcd0XcPXcwtwb6hAK29qPTfnJw0Er7GpIeKvqUWRq4kbzt/Mwg3H0bK4kaGinpWk2N+nGJ3OuAxFZV3Ajsme//tKWhpVvnwjg5T0KL/7ayl9hwYwLcGypkyKw6m4TJOHlo9l6FEV9Jzjp/SNCP3+FETr5K01DSjsE+JvtxbwxMxtOFxW67KRqEJz2MmLC+wqIivJRTQnCWeTnSPSF7VgjPa2k2OMO2lktQPTUvluQ08m9N5F3y5tZb3fNeQTtDo3JSInzKJthawsyWVEtz1xXnQoIHjuvjyCDQrup6oIXt8lXpayfZOJKgjd0IXw+Rmom0NIl4I5yN3KcQ+xGL8mUQ+vQzgkN+as4sSsnTbNiQITzHKuzFvPZRxG0FHP+HBzp+WwAKrq5MWWzZRFvG2NgbHFb9g+iSGeau7rvtQ29EByukmXggi7t3ccOCUQzU9JsBcLt1Nh2si+nR7HwcB/EsY5EZgc+/tVYB5wa+zzd6SUYWCHEGIbMAY4KOlmp6pzZe9pPLF9DuYeR0fVHLBLuNL2qSwRAitLZeShzUw7rR6Xx+KnOcmsXexj7BFNVPu9JK2P0lSfyJBKSDVaRYLDhoZ/ewr3HDWXwowGHJrFmtJsPA6DrhmNCeXPPq4tIrpvg5ApUbeGIWgRPikL6vVWqmBLKqzYFeOVUS0aAi6OGrSVIV6dn0Sf/Vyh+OP/4JlsRk1u7pBLiFiC1S2ZVHdLhRwLbWELVlcHOIXtpYcsMCS93yqm27mCb25xxRn61ssalngWl2FNAccrAfRd9TisKGOmNuEOz6akJoeBx0uyUwNMG1iM9Jus+dFLWpZBZm6UlQt9RM5O7pwpVILIC9vevSWoW5WBPvlnSikPEB63yWmDV7Pozrbp896rp89tJjreizHC22rwXcLAqZg2F4qQ/OuPcyitS6asPoXNX+fZakyhvU5IgmO0LDIVu0pKCLjmwXJOubKa2gqdVx7NYd0SH1JCz8FBApdnsq17DnQxWF2TTsrjDYgoVO3WKRqQOInv9kp0p8X29W6uPaoPZ99UyajpfgxUfizuyvDCPSS5I7SEDQxTMLBrNc4UP1vXuJGLWgiflY6Vr0M7mg9pEBNcsb0F0xS8dUcSJUstDvvUTZ+hwZhiW2clu4BDIlXJ794+hlNGreeswctJTYqwc5OTt/6aw4oFdt7HMa8FpdogdHYGZi+nXcPoUTo8GzJNwxjXsR5eSqBWxypxQlQwoe92Tuy7A3c7oR6PauIUJo+k/cC2dU6mnVYXxwS97/bqDZOKiJ6wA1wi2BhMI61dNZkQcNX95dx3Sfe48mgANIXAmMIOW0nxhPj7WR/S1HI8rvSuiQ/mIOBAjb0EvhH2EPgvKeVzQBcp5R4AKeUeIcTeWrR8YHG7dctinx00nNn9UCoPbeLVjRtiYgrt487SrrdN20dYGMmfLt3A6JGNON02d/Woyc0EWhT2VLm56M1TaQi4SGjoNYk6LEaBKiXWJg8Ow2L6wGIcmk0mdffMI6j3u/ndkT9w5OCtMVJHiapYqAo0mY64OJ7+XROuZ6sRMTEIaQnEaJXwwFw6wBTM3NiPO/MWUlAUwe21CAU6PqGqJlFVi0i47buNy70896c8rvhTOdICzSGJSI0yw8sfd40F7M98z1YSnd1E5KhkrBQNbVUAx6xGtjbprG/04djT0unsVFgWQrfwn9wdYXbDXb2TJZ+pnHppFSdeuIXeKY1EgoInb+rKolkpOJwWRkRBc1hEQgoySUmYmLM3TlydfJ3fw5qSHIZ3K+9Q2dGJxsl+4U1OIPIds13uhyvRTkmj/1VhoprK+OQ9HJ++q5VaIjs5QHZygEEF1Tw7dwyhqIZVrXeex4hA782VBLsI3F772EMBhTvOLiLkb5upblvtwXlLC+77W4gOSEGb38bB/uWbGYw9ornT8xx7dAuLvkqlbKeT+58aRWBtDzw7qigq2cKbdV1JydtA/5N83HzuCnQMMGzpwdce68JHtygErsgkOiXmfZoCq9iN3GIXNggs2FJPyU8KlinYvt5Fn6FBJqeWM7uhK0GrY1xeCFB6BbCcFuYeJ++V9OGT5al4Xy5DhDoOiNr6EL47dwNgZWs0P9ct8YkGLZQtIayh9rFJCdbyJGTFXnI+wRlTtuFOkEdTFeiaFaTLCRG0/ZS3CwFLmrITkhGKJhNtUQsiYLIp4mbwKH/rPRl9eDP3vLSTZ+/Jo3yHE8NUMLK9+A8twkzvyIvj0Q26ZdTz0cIHOOf4ZxG/9CE+QByosT9USlkeM+izhRAJi/9i6CyYHL+QEJcDlwMUFu472v08bhh0NHmXp/Pnp+ZiRjW7bVpTIDuKOjb+ZRA1EQZ9vZMvS9NY0dXLsefX0ntIELfPQnda7NyYSlPA2SZgvs/ZKJPqEUkxtauwgrXNh8/b5g3urEmlpsVDKKpz/2eH8/AXk/A6o2QnN/PyJTNRFZPRSVXMb8wjaOloS/24/xGfHBZIvIt3IR1ajFVvnwu4N5GmwFX37+aJmwpbGTft62k3UwWjWgdFri9ez2ThF6lMOL4BZ083K3r1YFVKMkIIfIS5PmMVxh+CvPhALtqaQOvae3uatC3h/VGf28ZNgNIriPBYRLyp6Ed5OHn8RpL1MKqAB6/oxuqFSUTDCtEYeVs45vloa4JEJyYlDiFIkHXxb+Q9H0/hlUs/xOcI43GZWBaEQ4JISMHjM9H0AzP60QisXBDvIQr2GnsF/+SenH1CKVf2/ikhP9FeODWTly6eyR/eO5Lt1WmoK91ERgUQih1TxpIQkTjfr+f1d9LYcxqccnk1WfkRXnool3CgXUgyhnBQIeX5SpqeTEGpMVr5aeorNZtzJUHcXggYenjQ5qPTVYIj8vDMLca5o47yWBVY194t3Hnuug4zvQtvrSDQrDLrSYvA1xbBKT1j+gSx45ISiUBbV4UVqxxradKQFoxLqqCHq4ltwZQ40kEVCxPFpn/uEUIWhpBVOkY/D+bXDtTSSMdkazsoVQb6d81EJyfFh3YiFsruCJ5H9tDyhl3BI8ucMUPftlxOWuex+Cgays812wFJms3T096C6V824H6uxr40huSON4vo0TfIw29vt4WHsB3JZ+Zs5b2F/Xjy2wk/qyHs0k3652xh7Y4KhhQlcPgOAg6oqUpKWR77XQXMxA7LVAohcgFiv/cG8cqA9nORAiC+ndPe1nNSylFSylFZWf+e7uJpA8ZyQ34vUj9aQ9LszaS+s4LkbzYiDNMW84haqCv8JF1WQvkHkpXfJzHr3TR+N6MXrz5uc15rOgwaUE+SpxMOGVUiYg+QNEGW2rG4xoCrtcPTH3GgtksYGpZKY9DF1sos3l48GH9YZWpqKV7FQMGyyz7DCV5Ww8LzU0nHbltVctKAtvF10vGN3PHMLgp6hlBUiapJhk9q5pSHQ9RP7o90dXywGus0Pn8jm5fWHMLyhUVYq32c5N7KlwM/J3V1Ey8/lBsTjNjbohVLJikCUbd/LhakwOrjQuRFEGkGOBSO6LEbp2qgCpt6YPUPiUTLbejfNyNi4itxiFoo5QbUKLR/26qafZz81Nn89dvxLFqSzoJPU3j4ym6cN6o/1xzVO2HXayJEIwofPZfd4XNhgTAtfPOLqS1T4vht2sOy2m5VbmoLr1/+IW9e8QGPT5/Dyz2+Y1p6iX1+hsG079dzQcZGRh7WzLfvp3HlEX157a+5rJiflNBzBGgpBgImVjcHlksQHe9l1yE5fF7XHb+Z2E/zG04iQ1NonDEYJRDFuaMuThf2wj/saTX0flOjeW8psEdy4W0VuDwGZn5afE4M7JFEgn9A2yT9x1nJhEMKioB/9lzAiRk7cCkGGhZJaqSVpkFGBOYGD+acdKzlyZjzM2icPIxw72ykqtgDYjsoiiQl3UB3WLj/UYXzrVpEk2nrBIQsHN804ftDGa6ogbYjbBMNFrs7hHS3VmTYyfcEcGgmP2wrbC157gwjXRXIdt3Y6sYg7udrEBGJCNu9DdGgwvb1bh65tm0WEo4q1AXcvLJ09H4Nva6YTB1g0x+3hBxsr0isk3sw8LOevRDCCyhSyubY39OB+4BPgQuAR2K/P4mt8inwlhDiL9gJ2t7AT7/CsSONnQweE8IbMQnV21UU6rIIyWdvJ3qID5ms4Pi80b4hsXHNMhUiJrz59zxWaf2494rFqIpFmidIQ8CdeD9hgbXBg6zVWykDTKnwt1njuenIRfTKrovTkW2Pf343jlcXDef6yQv515DvuLt0HKU7OqczVfxhiFrgiD0gikXfwioG5rXlxqWEIYf5eXH6ZkIBhZChURf2cvHzJ2LkOAgekoPnx3IwQESl7akqCoFRXTEzvGCC2OnknGOL0VTJM3fndzDEIrYfS1cQQROpkrChRQLBc9Mhxu65F2OTqlppdTet9HTg+G6PtNQo4yr28LVSZCc4LYEQEscqP65HqzCSa/CP746ZHfPChSRkaHxc3o05j0YYNrUJo8FgxqU1jDuykUhIJKxYsSwItigoKtRXazxydTcqy/ZTp2hZ/LQItPMTx2UipoJlKXEVJt0zG+ie2UDAVAk06hyRWsIfC5chRwgcwiQcVGio0fj9KT0pGhAA0XkTjT2QCIxRHlqe6450CgJOhb9WZPL3yqE81P1HxidXti4fjKjMXDGAlrEDAIF7wdYOVMC9hwRZ50/n8bLhbAulgISuzmZuLljF8PRqDjm6iffTMjrwwACgCKLd01pnjut/8rJhmYeBY/y43SY3F6zmxvzVNESdLG/J4u6Scbahn5dmU3G3N7wOFf+knvgnFNmC6XtqSZ6zhTOvq+Kky6txxPJjcz9N4x/fuKnfbNMV6/OaccxvQUQlmldyT4+lzE7uxbxQeofo2WuLhjGh7y7cSvzoHzYUftqez1PfjmN8z1KSXJHO6fkjgr5v7mD1ab1AFzjfr+/YgYzdeb/i+yQ2lCSRmm0y+5NM3lh7CPU4EZZhRx2EiLuuirDwOCOce8hqAmGNL9cM5MQpCZjiDhIOJIzTBZgZiyNpwFtSyq+FEEuB94QQlwAlwGkAUsr1Qoj3gA3YBI/XHKxKnL2QZi1W/bV8WdXAG1pval4rgPIoznfqcSxqJj0lSnhFPS2N+zk902LVpzoXqSfzyqUfUNHYeXOQtTTZnttbexNv9s2euXIgC7b25dHTvubM0Wt4Z+kQQtF9g4CClpCLJ2Yfxr3e73hx0FyOdw0mEkw8OAgFcNl17IpuMXXEVu6fPq/1+2BE44OlA1i6s4CjB29h6oBiHv1yInNLCpHhFlLeX09wZFeani1Cfz2Iui2E5XMS7t/F1iWNQdctVu7OR/HvoLmhk2MBlIiJdKoQNjuEhyRgDHIRPbWjwWo0HTbdigCvz+xQpSSBSK9MgsPyaUxzUFNu2N6Z20S4DbJW7ML6phopBXqgmdSZa5FA8jAHh53aQH5qE1vmOel7vp/JFzajRi2Wf+vjLzcVcuWfyhl1uJ1jiVqCesNJshbBpViU73Hyjye7s+kzPdZ0Yx9MwtomC0LFFk+XD+KynA04FbP1XQ2YKh9s7M/qDQU8eMpsHFrbd0FTZWlLF8rCXl7p+51dJho7f4/PwuGK8MAb28nrEWbxlyks/iY5cVy4yGGHtqREpqqtsamwtOUJb98xnvcHfE2WHiIY0dhencbM5QNa75IId2y8W9uYzs0VEwm1C7fsCKdw8/ZDeaLoBzSHldjQtx6UbbCkAjJF5a5Lizjv2gpOuLgGTxKELAfv1xbxemU/AKytbjtp3VkFlSLAoaL2SeHP1++gZx9/XIjp8FPq6XnsBi7YegQmCmZ/N5FT0/DdXIbDFWXKsEpG1tayaFcBoS5pcfG7jXuyefizSdxx/HxMS0FTLCwp2FyRyb1Pj8X6oZTrP+7Fvc9vp1uvUEKDLwSUzQTfV7uIHpuEsrPzkKahq1w2fxLmYDfef5agbttISpoH6VRR6wIYOckExnbDTHOjCMlhfXdw81GL8DiiLNlewIqSPjzU75eHtA8UP2vspZTbYS//btzntcDUTtZ5EHjwPz66xNtG1p/HQ9tTmd0wmJClgRvoqRK+NZvjUpu4pmAjqir58Pl8Xn4oMyE1jZBAS4TqZg9/mTUhjla1Z3YtZ41ZQ7eMem545zgC4fbeX/wTUduicd2bJ3J9rxWcNW41ry4cjiUTxGBNnfs+PZzJ/XYy9aR6Zr+f1kFnEwXGTmvknjufJ2Do+PQopXUpRA2VkCXQVMm7Pw3in3PGIREs35lP98x6Zq/vA1gIw4cSMYh2T4edJsahKdAzce20IqT9o4C5r3ZsO+i6hWdyGjW7NfQNNUhLxvjQBZHpyYSuSByC+6S4kPSl9SR5DYYc2mI3BrWD/5DuhPt1aZ3iNgbt66+EBGmqwQ3HryLzwjC6Lln4ZQrfvJvO9DPquPSPe2x5PaeEk2J3JFZaO+m4BsZOa+KNZ3LpMzbAy/UD+bi2CEvalRNTU0u5rPsGll05AOsyUDcFUdcEcb1TH0+cFoMUYOU5eKu6K5uCaZyfvYlurmb2RLy8UdGHYJWP309djCosmwYCQVjk8UxFTz6ozuLmgpVoouPDp2mQXxTBNOHiO/aw6gcfIb8SZ/B1l0XTFVlomJimsD3DfRC1FN4o68txnlJmLh/Axyv625QLe78vTEcvbUBpp+z06KahhFI6hhXCUuPRnSOZXFiMWhywZ4AJoDQGCF6eSXR6rPdAwNPzc3jqxmTmfHA7M374C81G28xVlro6N/Tt3IfMJD/9h7Z0GGccqiTXFWBiyh7mNebb5Gw5OqGLM5hurkMIePnhHJzLywhNT4k9T7HqObfFlzt7Mv/xHhzWbwc+Z4Q1ZTls/x5887ehGRZ70LnxmF48M2czmTnRuIa0UEDwwv25RMMKStjE+VYDVtZ+TGZUIqqiaD+aWBkq6jabnbX1XErqcZTUI90K5/y5mWlTK6htcfPs3HHM39Kfp6+fgdpZs85BwG+ug5bIYjY3tzC7flCcdwJgaiof+3txllJMrh5g+CF1vOlMj0tk7oVUBUZ2EsGogy/Wt3W0nTBsA3845gc0xbRLHw+gys8wJWutftx7+Et8uGwQTcHEBjYY1bnpnaN54PavWTQ3hYZaFRGbEkpdIL0Kx/+xEQQkOeyKj9+/Nx3DVPE5I2yvTo8blDTV5Ms1e8swFaTQCfXLwb2yjICzu60m1aoLGw/TUhjfq5Q0TwRdtwibnRC9RQUnDd/A1ot78lVjdxR/FCEFZlcdvAnWMSWuZ6oon93MY85CNGya5mPPreXz1zKJhiGS7LV1QhPUvFkInjz3C/pm1hJTCaTPsABn31iJ22vhcO2nJloBj9viqKvq+f3HI9n2kwvL1Uh0UhJWroNvG7qyvLknHlUj8uEe3G/UETg3EytVtZOg+25aE4SPtStTVrRks6KlLb4/1FnD3w6bs48QiURYFWwO9MJC0MvViNaJGyhVe9ZT2DvM37/YyvP35bFsXhJSwsAxfqbc7GdHD4kStXi9MnH9tSkU3l4/gDeXjbc/2Mc1NXunkbohir9WtLI2lvjS6KxMsjTq483mqXjWFtOciCMpaiKOCBHNSonjGIpOSUYZ68Dp9ODRXHHGPjYOJoYCSIlAMmPExk4nFF7VYHJKmW3sARwKkSnJfHx2Fl+8nkGgWUWjBe+iHfiPLEQd3wweq5UuIdik8eVPve1QkmmRvuCnuDxG0K9y/TF9uPjOPUw7rR5VlZRuc/LKIzn88FVq/ME0mUin6Nh5rwCGxPNMlX19I1bCClwJWEka/1h7BE+vV3A7dS46cjS3nDeEZG/nTW0HA789Yx9dw7f12UQSiVrEML8hjzOzt9FnWJCuvUNsW+fpWA4nBKEBNsOhTDGhViXDG+DWYxa2NuHU+RPH8Dsckmmxrd72SrT9dnYKlu3MZ1FLIQNedTD3rVT0uS1gSaITfUSOT+ORUDbPGXNxKSZe1eDSScv40ydT2bVPeMipR5nYeyfv/TSk7UNdJdI3m5SZa7CcOqFBOSTpKs2m2UFk4tCMTSQ7gggBmXlRdm/vOBvZi669QvQw1vPDdUEwJUZ/F4E/5iEtOyeAhv3iCoHzlVocc5oRUUk0KojGOIU+ezWTo+9uYscPOuuDeZ2GChQkb37cF2NOBcEWhTFHNHPc+bUkpxsHVGHTVK9yz8nd2L0rghoKo6rgfLue8IxUwhdmUhuI0PeTCOWfhmmYNgBDJBGZEiD5kw1gmTZTowYogsBR2Zg93LZBardvacHpXbaysCWXFC3CcF91q1F3KSbX5a3l0q1TKA37GOSpTah2ZSlKjO7YorB3mPtf32GLRUmIoPJmZR/S1DCuUMSWgUyUWohK9A1NKEvqGXl8mFOmFpPuC7JiVx7v/jSYO46bR4/LqvjLDV3ZuMKD7pA0WrLTMleJHY42Du8FTSGEJVuTpyJqouQ02kFdbZ/1NVBTLJbVbeekrmN4uXguPZxV3N51OX/fMIElW7uS8NlSJeSEyW6yCQE7gyXB2Pd91wQRQyUabKvxd+6oJjzWBz4l9nzFLG2qgXpIA+bcNPTdDQklDZvqNP56c1fmvJ8KwNrFicO6IiyxsjWUBjthLCxsvv9wrAcl0Bbm3XeQkwBeBc8ZY8jOzuDE8QOZMWHQ/y/0xvBbNPZKCiFLT8g9AWBKQbidoMCDb27nllN6UbLdQyzfBYpC85H9kF4HqBZKjyCWX+HIwVvjblCfnNpOs/n7IjWmXDRt4Dbe+2lQ4jJOwJCCB5ePh9wAqmiyjfyUZGSOfcN3R3ycvOEYjkgrZZirCv+GEOkbd1HevYdds6+BiYLXEeHrdX3Y9yWSmoIwLNyrd6OP7c7nj1zOg//8lDmbd2FqClpNC8kbqthRVUvdSTrJ6UZrIjARFBV8SRb9R/lbvRltbYjk83YSGpCB3tyEdELwgQIkEufnDQkrjSJhhbLZCo+9uY2n5qTzysIeCfdnWYIfvknD+aNdNrdjo5uZz2fyzuoNnYqJtMfjN3SlYrveJqVnAqbE+WkDZn8Xxlgf+ReUsFkZiNVsoQSjmKk+6s8eibO4ioxoJb26NdC/bzObNwT58fkijIt8SF3a6lzCdqD/WDIuJj4vcQiLB7svZmSSrbY1wFOHisX7Nb04Iq2MUJOkrkonIyeKx2dhSWgxdDYFUxmdVNVK/SCELdFYH3XyalU/BBKzSXbuGlsSz9t7+P2dO5lwfFNrorh3l1pOGbmeuz+eyu3H1vLYh8XUVmjUV+s840xiUSAXy1RsycYGDdwWSkHYpp62hO0XJbns3VoWjugerOkKMr1zcxHF4IfqzVzdZzqb6hZwd94CPKrBsJElLNle0JFiWpWIAX6U7Aje5AY2RFIZ56pKOKCHLJVvGuKbjUS9GQu9tZthTEpqawpsv6wCeExEWhjn15UJY+4SsJKdNJkmF15dwubV3g55NSnATHKhNBlYDoHs5sDK01Eqoqhbwh3uU3vHXnoEKf0yeG3u4/iSOunS/5Xx2zP2riMZn/w8n9cVJGzi0IXFKF9bK3dqhsndz+/kjPeORdkAlsthtyyris18l2wiMiPg8JLmCcZNy4uy6hmQV826si77VfhxaVFOHbUOgIsmrmDm8v5EzDaPY19EhYLiVDGPTiHpsp0436sndHY6kdPtRGfYUviiOJ+5f3egL/EDVaQ5aol2TUN1q4QO60OdP1EIxcKxqw4AYUl+d+gwlny0hON6dmVgCN5//FOCzXb3ZTM6Fx3ajxMvriEt06B8x77pVxs21W8E02j7TgBELNyr2qQET96+innJ3eiUTlxC8VpbuGJnksv26hKUvQnDZHD2Hi56p5iUDIN1S7x8/EImG5d7GDzOn9AYWNJ+vxtqNFZ8n4SVkKvfrnM3x3rY8pEDz1trEFG7dtJMchGYVMQdt21gSv/tOFR7FhGKaBRX13PVm8cRndCC9Fit+5eI1kRpALixeALP95hHv5R6JAILwebqZC67fxD1P1homsQ0BYedUM81D5bjdUXJ1oPMru/KtNRSkBpCMVjZksX9JaNsBSRLoq1sxrXIT/i6LihOBVMDwvbg4P5bJWMH1jPh2EY8zrbn1qFZODSL245dwF++PoQHT51DRo5BRo7BDeG1LF+aS8v3GbGB0H4PzE1ecCSoo1AE0a6ZqBlNnTzNseuLQFdUXKqDh3rWQdjeVlZGM87Daons9CIrYx3GCoj+ftTu9rNYYiRz045JXJu7kTOzt6GJtjBQyFRZH0hnaXOXtp2FLJxv13Y4HmOAqwO9RdsBSjzabtSUUCsZZuvmemUSGN8ddJXVOjyxdRAjz1/Hjy/bHcTCsqvSpEun6cRBSLdOclU13TdsoDAtyLLNqYlSPq2IHOolelo6juwUPqlZyYnuUfi0Xzdkkwi/OWMvlDTG5l9FfvlcdoVtKcK9cAiDAd46BnrrWz8LBwWz30tDzQwQOSsda7MX/AJ0C9EjiNI7gCIkpl9l454s/GEdr7ONauGJM7/i5neOZkN5lm0AWlkS7UdNVw0G5Fcxud8OADJ9QR44eQ63fzi9k1mBQOREbOukCSKHJeH6tBHX23WYA9yYvZ2o64N4/1huEz0hiI7zELqmCzJFxe2PcCgFLFq0m1CkXUlZrODbcmqEe6Tj3FXPcxc9g6qphAJhO7G6D4yIwofPdqwz3wtVlfQeEiArL8K3H6bt975cdNxOzvSXcKHZv7XMdV/4UkxmN3RlqTMdkkxoEvHleFh0TW7g0dtW4fHZBq2wd4jpZ9Tz2mPZDBrb0dgblmBzQzJrGtMZ1VyB7pBEO6lsVSqieOY20vRsM+012LWGIKlfr6fHlbvjeFs8LoM+ObVMn76BL6yCxLKGMUSjCpf/bST9ttRy+CXVuJ4qR/8xQCUgUFqPaf4naVSWOvnzB8V0dzWzPZjMVcUXEbFKqY06aTBjdMuWxP1IBfoyPyIkcSz1Y0xJwezpRNQZaF82oNSZHPdaDR534mI3t25Q4/cSNRX0GGVAgaMF11IvLZF2zsjeexBKZA4EsmY/5akxOBWNI3LskKISXQRC8nltIU/uHobpkah9mqG/gDoTma4i2vPZIBmXVIFHDeM3hxD0byTD66e5TuXDZV15NXMocm+SWRM4Z9bj+Kqp45Hu9fYTUW8oEB7lIzzMiwhKvPeUo24PE+qZgX9Sz9b8hImtHlepj+OqV+by3MyusFkn2iWVSLd09sbkQvnpuMb35N7zPue6o3uxpaITb90hiJyRjtXLRS1h/rV1Nu/s+oFXx19DuvPXK7NMhN+csQfQvafy7JhePLTubRbWWwgkFjA9tZRbuq5qXc6IQm2lzuevZuLMr8N42NOOzdGGUxiM0ar5UaQxf3N3WkIOXLqBGqsLT3ZH+NeFn7G5Mp0tFekoQrKxPIuVu/LRFJOtlZmkeYKEolqrwtTh/XdwaO9d/LS9IL4UU7UHGLG3hdulYA5ww6eNdoflB3UYI7y4XqhpFT0QgL4yiLmgmchJaQRTnCxRVtNvTE82/lBHJGLYcdWYWG2kTzaOHbVIAZFQlL1kcHshASPbh5nmQQlE0Msa2oS2hd2gZUQV3F6TlAyD25/eRaBZ5Y3Hc9gf3F4Lb7JF0YAgW1Z5OpQSOt0Wx19YwxtVwwhLDfWQRqzVPls1SEiQgi6FDTx/wiethh5Ad4DusDjj2mq++zaNiUc0IpA4FIk/oNBcq/HAmQXU7tZZM1Vp7cpNBJmj4XqpBiNB/5wVldz5QD+c92cwxFvDOdlb6OZqwamblPuciJ9jn9UFRl8XO5+zeOW7DHQCCT3hSFhhy2o3m1d66DciwOZgGsWhFiJWPLOmttjfaugBRFCif9HAvnPZ1IzOO8ikhGRXiHBUQ481OK3YlUcg5KBTLptEUGxjnulMpqevCz/VbSNktj1XLlVnYlZ/+qfYCVTL0ljtz+SxshH27EelLU+QrNika2O94FTI01v4R68FZOohnIqFROBwq8zb0J0njk9BRiUe3y6MYR6kAG1VAKU5cV7MMaeJyEmpic9NCDup7ADpgZZH8km5bDvBmEe/L8JRlSW7+yKP6EIgvaMXHjE01pTmsGlPJidcXMs/bnMRDsZvRwJWFy2OTTRkRYmGm/nb5i/505DT93fVDzp+k8YeINkzjEfGDGPdqi18+tXfuO687/DuQ0CmarBsgQ9/SEXdHMb1ZCWhG7qAqtjZcwWSmyWDHM1Ee5Txw9buXPryDP529pfkpDZjSYHPqaFoefQv7EpO8o8oQnLskK2U1qVw3nOnYFgq323sybSBxRzSqwSP0w4B3H/SbF75bhivrxhpd2B6TJS+ARSXH/fjNegLWyAqsTLtWyAkaEsD6D8F2JfMTIQlrldriRyZAh6FsBVlS9Y2Xrv3Sm6/4Dm2F/jswKQA4Y/gKG1o5dxpDwlEuqXRMjVWwSMlwpQkfb0RvaoFiSB/bBZFPWo49LAKxk/3s/ALHy/cn0t1+f69u5KtTrr3C3PrP0q44fjehINKKxGUy2PRZ2iIY8+r45nNMZ4VXaKOakZGW+wqCafFnb0WkJGWuJPZ4ZJ8srkb/8zuwpGZpWTOq2H9fDdLZqVgGjbd7Ypvk7AUFU2PdgzluAQTTmti+aM6CRvHpcC/0mRPOJnSsI9vGgp5rMciRidVdSSwSwRLotQZrdUn+zOl0bDCqh98pA+SfFjbk2iCNpS9Gq4/h3WLvRQNDuPYV7MY0FWLysYkvE6LihIHLz6Yy5ziXgTGqokTvgmgKoKpI3tzw8RDyXGlIqOb+HzHYl4rV6iIeMjQ4dzu4zilx3Gt6xRvHsSLqkXYSkD361Iwxnrp+n6U02/bwckZ6/bm9pESVrRkcOuO8fgtB973osh/1uGY24RY2MLeCLjukFhWx5JhdXcU55t1hM9Otw27IjonTNIE2Vd5aG5SibRefgk+06ZJb1FZuSuPzNRMAjQmvDamJVi2I5+zTl7N95+lsHqRr42zSgWcCoHb2qgPsvQAV+euZUrqbjTxPlbN+4jk3yMcYw7sZvyH+M0ae4Di1Tu5feL9PPXVyg6GHux7fNx5dWw8vJCZtb1sabJSJ/hV+4aWOamoMfi6rBpRXMpg5y76HmHypw8mYmoOencJcO/Fl4I2EOl/hjTPIsA2RpYlYvX0dvz29g+mM7HPTk4ZtQHhj/DM77tQtckkyb2c5le7gVtBNBj4ri5BNJmtQsxqdZtnJiQIRTL2iCY2LPfQVNvmx0nN9mqMQ9qmfssCO4hMzENZV4teXgOKsGOLqoIwE1wPQG0IxnkyEmg6dgBpb61AhA3KdJXccRn8KDKYN6s3R6fNpKleQwiZsPHHTHYSzU/lgX96efDeleQXBXlxwSa+eD2DJd8m4/bCUZcczsSjtqFaW8l3+mkMtKllC11CLE+S6kgcf5ESNizzENoiqVYFb4YKcD/l6GgMoxKhmEST3OihMFbYQtHsByFzopsbTl7HuQ/3T7gPsMtfwU6Am5bCXTvH8sWgz5iYVM765oz9vy1hiePzxtbrvD8omsThtPihKQelk+xr8MZswiURXB/Wo60KJlwG4OOXsjjmgnoc+xxbKKqyeGsBA5N6UV07g2uO3IK/WUBW593bbao/9hmoqoLPqeNWHVz1yMe4dJMTh8zmxOFrOK7/3udLgJiFMPqBbjsRK38cz6bhGzonKDIlE3LXcWrmnrhrJQQM8NQzLa2MmbU9aXE6cPwuk6LDI7jeryO3W4TDTmjAMgXNDQp/+0PHKh/XB/Voa4OYp6ajDEsi6DUTX2GXwi41iVYe14wI6vBmcFptfQHFLvZs6xgu2gtFSByagarCva/s5MdZyXz2eiZltR6c4wax4bBQa1I7XQvxap9vSVYjbYVxxmpk3aWQ9neEc3Kn+zlY+E0b+2d/9wohf6hVazURFAHjkyr4pLYnliZQe4Rtjps9DkSFoMtnK2mKSIxYLL6mzCIjdws9rs9idf14hG4LgeM+FdnybOt2u2c2kOYJsqfRNsgSwYItPViwsRup76xE8YcRUqK0GHge2UPg9lwc79cjWtoMfSK4PBZnXFfJinlJvP5Em1cggPadSZa0WLRnIw2vLSe1uB4pRNsy+3LrtIP0JHDphCDUN5uzx67i4jvXYkglFhWaT0VDEk98vJVX/5zLuiU2738kJDAthZYpvYl0TwcJqySc8I9BXH3ECi6YuImzbwpw9o1N4LsC4b0aWXsiWHB+9ibuLRljN8O1gy5M6gwnlkkc935thcbtZxZRWebAsFQ8X1VCxEJ0Fr2wpB2HzUlG29MEmoLol8pTN31BUrpJ974htq31dFhNahA9PD6UEpEKSxuzUcocSEsBxWqL2+/NClsSwhJ9bhPaygNTGhLYamELSKUzeiqZpWNm6fgHunG+V2c3fiVA9W4Hd57VgztfKsHtk1gSHKrFj1sLePCu/hyW18Cb6wsItBQjLQutshklGMHSnB3FF0yJo7wRIzcZX4qHsf0K+WH9Tr5YshHDtB/af1SO5JOVPXnp4o9x6QY2U10A2fwoIv1FAHoMGUqwZgtkdnIBNMHZ55Qh9gkxmpZg6bYC6tZlYDb6EHkRwl1g84h8Pj9vJckxttGmOpVHru2801TbHKLwHZNzrj6Nh9bNJGB2tA8qghmnTGL1F6Wsb4yijmuvWxvLf/UNI1pMtBUKRrqnQ7gnYmqMKSqnJaSDhDHT/PSZdgjJXR7BrXs4dcFfKAnYNCcXyLUkyQgde+NCyMZ7IGver8Z2uRe/XrvWrwzTMFmzYCMAhrH/izQuuYpnes3DgWnzczdqWKuTyPpxM9EAcZ2s4ZBC9W6d3M3FhHvtImLZVkWo2Yi0f2C367oRAv5wzE8o+1hux/ZaRDgal+3XlwbwXV2CY3ZT50YqBiEkO9a7aajdV3sUzMFtRkoVCmseXoZjez3ClCiGhTAshN0umtCbsRvJfLjW7kEvbWgbFHSVQ49r4qJbK3E6LLxOA7fDwKWb5KQ203twlAde38HHW9bx5rINeHwWgXHd7ISVptovgUPFFCrPfz+eBWX3IlKeQGQvQvFdYz/Ewu5ZmJxazumZW3EIE12YCCRuxaCfu44xSZVxSVAp4Y6ziygtdhEKqBghExGwDf3+AhzuNeUQNYl2TQMJWfO2kuo5ChDc+FgZLq+J0q4fQmp263/4zI5J6E27M3lp7qEoCzOQlQ7bUTBBGgJlQxDthxa895Xjfqr6gKLgutNixmXVZBdEGZNUgfy5rj2XQviMdKyczv2y9cu8nHHJCG7aMp77Fo3mvDNH89DRGaiL9+BMdfH9zJ+wYsZaAMlfbkAEohAx7YscNcEw8c7dSm+Xm16F2bidDn7cuItAONpq6AFChs6umlTeXjI4/iAii5CxVvVRRw3Ds0yxNRH2gWwUiIVuMrrEG/pQVOPil07ijx8dwZx1vZGlbqxlSZjfp6JaFktjDW2BFoVrj+7NqoU+OpYdQ+jkVJqfLWTHgyn8VFOM1cn11RSVU3tN5o/nn4feP5jQEprCgn5BfLM2kP7qUtxLdsU5UlIKzrtxMn+6uDt/vrYr54ztzzl9avjqlfnI0DdcWejApViIiihTs3Z3LhdpNYC5q5MvDx5+s569lNJWrALmrShg+vjSTmeNDsWir6uBix1beOr7cVCnI6IG1u5AwtBENKIw5/00Drt4FztbqumTbHvYwnkYZP8AoS/BquKVxRqKEm59kQD00vq49vS9UCuiHT7bF4pqEQ6qPHdfHkbUJgMTisRUFcLHpyBjbe4OS0dZmIr+9eaEFLECeyYqhbAbY1ovGjg3VNjxfFVgOXWajhuISNW57uzVuDwdj9suRVWxORJ0fClBHv5wB+e8cyitLa7tEIoYvPBNM5NHngCAZVkUr9pJsHYyPXtuxu0JcHXeemZk7GBuYz5hS2WEr5qhXpvtr/093LzSQ0WJo5VS90AgAGFIkmdvaf2sRcCyhYcx6vBVdB+4mae+2sqbT3Zh2bwkIopKy+RUgqdmtF7fvQiGVT77fTaz117P5tJqLn/yfSLSAM2CsIK2vgLP4vK4bszYZU5o+N1ek+seKWPqKQ0AFDpbODzWGdpB0q89FIFxRCqed+uxLAtr33yMQxA6Po3NLwVxfmzPLsIXZhA9KoWZ7nLEtC7o79XhnGkn49WmMGlvLSfaLR0j3YMSjKIX1xCY3ItNWS7MPftnXgwbOh+v6M9FE1buc9Y2VFXl6auv5rxvnoJ8q7UcUparmMtTMQ0ZV9AA8PR3Y9hamUHEaHcdTAUaBeGNSVjd7Ss66+10Gmq0xBQfiiB8WhqkaISQfFG+Ak0oKFLBsiz7MbbsQ+3eXEhXTyaqT8FXoNDcCXuXVARkKojSKO51ewAIju1mX/YtVbgX7GCN2eaECaK8eMML5PsqmHJ4PXW5hTz7r3zE8M6vpyUl6i8Vc/438Jv17DVdo//Y3jjdFv9afigNAdf+ohe4NJNTirZCgw6aRPRusuO5nSAcFLiVMB4tfjgWig/hOZ31NaeyZXe81wMgHVqnVCCqJlE64UW3DbstFh4KqBhRmytF02HUdBP10i7oiopHdZK9qSuh0s5DV2CXTYqY37i3yE5Ydvu9sCQiaqG0hEn+fB2aYpKT2tL5xoQL0l61fwOeXBWXq/OHc2elHXJY8e0azi68kpsn38Ndp/3IGYN788oj+UgJec4A52Rv5eKcTQzz1SOE6DBY79rceS1y+4aVn4WENx/4AFf2M5TWpZLe1eSWv5fy+srNPL2kmPBFmR0MPWEL7YcWeuTk4tQ1BvfIIS3JbfcGhFVAEB6Yi398d2T7jlQBZpITI81tD7jtNvnQ29tbDf1e3NVtGadlbtv/2eiCUaeO5I2dz/DQl3fSbWABqq6iair9xvbm9OuPJ+PhWlzv1kNU4n+4gMixKUi3gkRiJauEz80geG0bj5Etfl2HZ0UZro2VmF2SiOSnJmp9SAh/2IHRvmxWH4VoNy3r26eAq3qdhOOtENoPLSjL/Vg/+mzqDkXl4xX9CccMtpQwc/mAeEO/F5YgssPLqCS7d2bux6kdql5aoYK6o+29MKVF2DSwakxYDlalhlXiwliQRvHCIK/MWgqAZ38K7apdCQXYzYrr9pCX7MG7ZBe+udsSFkJEQgovPZgGGJyatZ3Bu/fw46wUjE78vWjECWr3zo/hIOE369kDXPHEBcx65lpm+j2c9vSZXDxhOWeNW9uph+9zRbjoiv7Mql5DVdAEl4DECm/0HhJkx/Mu3jPeo7qsjr6jijjuqiPJzLMbn1YVl3cw9ACRPlm4NlclbMlWFInDZRFoUZHtXhSHyyI1M0pVmbPDOpGQwro5Fv+6uZZGx9V069eNEz99BUNT6MAu1g6WSadsjnshACVscGL60oQt/a2QUbCqgDAgSXWH41/0fZDm9bN14bXcPaOWcCA+bvXRC9loTi/n/q4GHMPAeynIMDRcBzJ+wEnPie6XIuGXRDirS2vZsynIHu0N/vrBc/TLraQhoDNvc28MRaAMqUP6YsOiCuqKMCnPNnDWu5fa+xKCP5x+OLe//ylGQQt4TGS9hvPTqvgciQS1JYzl1gmMKMCzsqyVqiMzt+PbrgnJNXnr+LS2O01W4sFNIDhx3KFkZKeRkZvGC2ufpKXBj6Iq1KtBPihZTOaUsTQsrSC4pgHZ3RnHXQOASyE6JRnr3XqUqo6xxFD/Lm202lKiVLdgZfo6obWQNAacHPbwJRw/bDPXT1uGN+NWpNWEDH4E4R+QIpWhwybT7cICtlfVI7eYSIfSei2e+W4sI7qV0zW9CU21CBv7EfcwBDoWzYaOtb+OdiE6jpkCSJF4n9mFWmvSPK0vVqFGCIPXv13O6YcNoyiaT5XVhExAw62UR1Fq2q6X1+Nk2M4Wfli3Z7/P346NrlZN6pyuYd59KovJJ9bj8VlxOalQUDB72bEc37Wjs3Ow8Zs29gPG9SE7bSg1c3Yxa10v/vLNoRw1ZCvp3sQWXChduKL/NFZurKTK20jgrAx8L1d30IpUFMnwiU289piX9XwHwOp56/nwr19w/6e30X9CP75ZtploAmNvZCcR7pmBc2uNHT+Pwek2ufiOPYyZ2szTd+XHRCsgtzDKpXeV89j13To9T6FIdLmQR0+sJZLZBXVqbyIOjUhhGo6Sug4JX6HIhEyfiaBh0kuztWUSV6lp4DgEYVUgpe01+VwRDulVyg9bCzH26Sx26VHOGrOEt//cTCSUwr4mORyw+OCZNM7800c4XLZHJY1t7MuCbVqCuYHB+M0wCokTHYqmYCUYVBPBMi12bShj2nmH0bvgTt5fsIaKuhqOGp3G2D4F3PzPjzGSDYRHIBtVzACkXNqfkdOGtm6jPKUCdVI9Rc5aLsnZwDBXDaFD4as30vn4hcxWj1NIm0tGqw3EcTLt3OgiMzfaIS8qBNyQt4b7S8ckHMEynT4OzYonQ/OlevmuYh33rHkfU1oY0kQbrWCNSu00Tq0oCuYYH8rnDR2+kzFDr+1pwvftFpSoQWBoHqEh+Qnq0IXdQWwofLqyH+sqRvDa7z0o1UeADCNlkD+XDeeT6oVYQkAuyCwF1WrAXJgKzRrBqM4FL5zC5H47mT5wKx5HlJZwR2cHAJfFJVunkKUH2TpVxT/NgTncA4ZE/7YZ18x6RIsFlsTsn2DANEFotmeeNHszDWcMx/I58YcinHTvywTMMNY4xabX3msRDQlRiefJyvhNGSbLPlveIXTX4XrqgsXNXTgkpZITL6rlhy9TuO6YPlx1325GTGoGAXt2OvnXY4XM65bORmMut501Zb/b/E/xmw3j7EV6wUCumLwGtyOKQPLqwuEEI4nGMCd4r+D+N2azfvdunG/UoL9cGxPtkLR3CaSE1x7LJY53Ixwl5A9z78mPcefzX7ClbB+Prh38h/RApLhI6ZJCWnaU4RObue/Vncy4pJa87hEeeH0Hn2xby7ur13PPe4dx6HlfkJbTuRSZaQg8SSYFPVrwl9YRDNkeon9STyyfs5X+VgKWpmBpKgfq9zocFhk5MY9TKEQtZ9tpCQ+oXRApD4HSBUTbdPePx8+jS3ILHsfeabPErUcZ2X03p45ez7qfvHGzl/YIWwZXf/g0b+9cSEs0BGpPUOOpkv8xZyyfrh5A85H9sXS1NVTSPjTStU8eTo8DJeZ9/lxYJzPfnpXlZaRww0kTeerak7jl9Mm88M1SLF2DgNPuFo2qSF2lJBrhy6Ubaa5v4bOv5/P05lkM9ZbzfO+5TEopJ80VIbdrhHNurOSvn23D2U7vVIlaiKiJbCfe/e5T2URCia/JMRklKFs8rTHlvSfTw5vFa4dci7pP+25TNMg9a94nbEUxYgOlIa1ODT2Aw6lz9V8v4qklD+NL8+Ly2MZVURXcFc3ojUGSv9yAGoggohaeZWW4V++GqIlmRRNe4YipUVItWfjT/SAbgSCLm7vweU0PLEW0WhihAbpEHdPYuh3TUpmzoSe3vjOdQFXUptDYB4oKoneAXeFklrV0oXFqBsZhScg0DZmlEzklleZ/FCIzdULnZcbLF+6FKVH25swsiXNDRexPSUNLiFDAwlyQirXFY/MDNUkcc1vwXVuCui2+VNWX6kXbt841DhKpQmRiEnfsHM+bVb3pNyLA6VdXUbtH554Le3Bir8GcPmQQFx8xkNmOcYSiJh8vWkdVw35CqQcBv2nPHgDXsRSk/5lvb3mFqKWwvSqVlSU5jOpe3ir2bcNBbeREZq94GefcnTi2NSJaw3v7ZPU75d8G07RY/MVyIoVpiKaQXcq4V4UGIGri3FIN9UHCuQ7eXLgFn7ujZ6o7JKbL4o83b+GWf0Q55abj+NctzxMOxu9b0y3GTGkiKdUi0Kyg+iNoNS0YXZKQbp2G04fj2F6LY2cdUlOI9M5C31mHa2PFfks8W89cgfHT7Vpi4TwG3XMqBD8BGUS4JoPrWIRwIl1HQNNdreuleUO8f807fLuhJ/M39cTlMDhmyEbG9NiNEODxmtR36PeMXUPDZK2xmy1b6nll+3xeGncVeSmPI+svBBkkEFF5/6dBhA0dcnQazhqBc1MlWlULlteB5XWQsa6S466cTubAAl57bwFl9XW0rCjBsa0hsRCJQ2Ho5IGt/weag8x/bxHbt5RTvGozVmEa+9bFBSNR/v7atzzz8mL8F6UTPdrHXYXLcKvxsxCnW5LXPczRZ9fy8Yv2oCUFmEU6xpFZ6Isa0TaFWPeTj3/dm8eV99ni7053G5umEBofnXUuu3Y9SoVWgqlrjEmupMCdhlBnAPEsjN/uWdP5cN5JhthCMja1J5sWbODYy4+gZncd/qYgmXlpTDxnIr+/6hloN1sVgGd5Ge7V5RjZPgJH98bQOnrfgXCU79Z5mNTLNtbvV/cimoBbQgiQLgtSDGhs92xYEi2jhmiBiixxIYTAqWpYlmTsiAJW5K/eSwdkb6T9RMOhINMFvZ4az4bUGrD2CZWFLJxv17WqrAlLotX60VUFU0qsvbNvQ0Fu9WJu9YJp4f2oHLWubVuKquBw6Vz++Pn85dJ/dHLhwZurUHrUaMiNojQE+ReDODZ9F+feXMX4o5r46q10avY4+CnUh4ZuhUiXfR1URWHxxl2cMH5gp9v+T/GbNvZSSmi6D1DQNQMdi0EFNa3hCCmhrC6JktpUCjNC7IxswNkUQt/clDCxciAwoiZayDbeatDAtXA74cG5Nv1ASwT3mnL0nTYZWSASZc3GDMYNq+wwdQcIBRR2b7W49qmZvHP7OYya9RXLvy0hHLSTs26vSXp2lBsfK6OxVmXnJnuK6puzheaTh2B6dFBtA99epNxMcuHaVElCktVYqY7DZaEokj+9sqONIz48B8wdiPTXEEq8cRHCCWnPIusvt2sPCSMUjcweAab3yKGv+T4FqW0Cz0efW8trj+UQCSVoIc/TkV10QlaUSMTgnjXv8cK4KyHjY2TNSeyo9sTiuLF13Dqh4QWt21Bawiibqinp4uGRj+YiNUk0zQdH9EMdEiD58/UosbbIvVfgkL9MRYndhBVz1nLvSX9GSknIH8alKzgVhabjBmJmxnOc1DX4SQtFiaQJevmaSFITZ9lcHslRZ9e1GnscAuM0D1ZPJ9Hjk1A3Bkl7pIzZ76fTUKtxy99K2oXMVHBOJ8e8kZyuW6B92MqsR9aeCVlzEUpb1UdtpIXQvoat9WZh00+3e+Y0CWPI46Kb7yM8xIl0GvhKgrjXRPjzrLvoO7oXuQGTygSvhTAs1Bo/Wo0fIydRqEW20osAVEX3Qw0uBcJhISMmCFACETxrdxC6PwPV1YLsHUCpcnF1v6M5YkgfuqT5eHKTg49WLyKSJBPTM+uCXd5mnhh6Pvet/YD6UAvRQBQJON+xq5Da7R6R5iE/M4XqRj/+UIJCB1Wh6ch+ZLy7DKfLbiZ0Jzn5y/xHye/dhdfveoyy4o5JXafb5ORL6vhrtQa1Kub3LqzxtXzfmMfxGTvpOTDEtQ+WEzZUpj02FRlpN+AJWmeovxZ+08ae6DKILGBvV+teiFivyzn/OpXd9SkIITFMlV55Kxki17FFWP92oZOiCKyYQTCyvOhVLTi/6sjFLVWFUE4Krz6Ry4jnq+Kk1sBWwXnp0VwimUkYhsnb81Zx90ePsuiNU/jx6wBGRDB2WjNjj2gEBI9c0I297praEiFp/loG3HwIi9aH2NeNUxsC+9h5+5+UzChTTmqgvkqnaGCQI8+qIzWjvZcaBGMrsvE2RNo/O5yTcIyBrO+QgfeZX7WF+4tdSDSikQBo0zmqaRd/6LoSTUhOuLCWeR+nUbrN2RrLlhqgCQI3tTEYWkg2NZVTFWok29UdqSShCIOo2XmEUTUlZ750Bf+Yv4KI0e74pYKZ5aH52D4kz9xoV8YU6oT/1JVVhQ0cNvtechwpBJ5axxGnlpGdF2HXZhfff5FKJKSQ/MV66s8d1Up2hSXxLNqBFKBuDuGcLPb73OwN40iXIHxkMlavmGF0CsRQH9zYlb+M/45ufUM4W0VYnKAkg/t4aLwZOuQnpB0HD36O8LZxqfRKysGjOhI2DMkoyBodPTuMoQoytRCTnaV8UGnCjCRw2ufXMNRDywo/tx71AO+W/Yu0zGQqt1d12B6AIiU4E5sLt24wbWBbqesATx3bgimJO2gViWwUJH+1ARE1MMbphO7JROoKssyJbNRQPDBuUAE56bbDcay/P7PvfJ/aJ3I75eIPWwajM3ry6WF/YGvTHn5/9H34l9fRu5+fC16vYNBYP5GQ4NuPMhDDL2LIIcO54L73Em4LKZnSYyt3rV/fegq6U9IUeAjkfdz6VBl/OLUbkbBoLQF1uk2KBoQ49aIK/vpnsB8+CK9IJTi4zeGJGArzNnUnEIkfLEzT4pD+3RMfz0HCb9rYy+AnIBMnY0NRjf65NWytbPN4t+xuISetAE3bTGQ/Unxgsy326B+ktlJn/U/e1tCOJ9lNICsJTBNUBf+hPfAt2I5oN/2VisByqLg3V7JjveSeC3vwuydKSU43kRaYpuCVR3P46r1swmd1QZoWy7eWoShORp3yDqsWns7Uk3fjTTKZ80E6HzybxZ5dbR6VdApSL/YQ7roeZXMRVvumsqhJ0rdb4pLDeweDYIvGUWfX0b3vflrmiUB4PtKqQygdtWWFks5G81ju3lZO2IoRramAVJlVX4hbNbgpfw1Ot+TJT7bxzbvpfPxSJqW7XBCFzLwwV/iXMCArRI3Py4c1vVgbLKQhEkCEVO576xh+2qaR7Apx6oSVjO9ZSkvYwcwVA5i7sQeaonHTZUfx9bIt8ayfrVAwclJp/Kg3uss2zqpQ2BNqAGBHsBrXlRnI1HrO6LaOQIvClfeVc+tpPdm21YdjVz2Rogz7XA0DR0m9Xab4TRPbzilA7SQmbhgKG1Z0QR2RTNMJPozR8V26hrBoPiSZbod9izPyPoQ+ByS4j0V4zoXgJ0jZWcddAKJLgDZjPzGrH17NRdCMxjVmSQlYgiFVAf4x9QucumErhS0+2tazbe89uhWMEV78YyJ8/+ESjr/qSHauLyXk7/h8uFIUJh+xiy/W9Isj93NqUQbmVzG8qB4THZUoZ2Vt5Yva7uyrgCtNkFU6SrWJf3wP1BY/5vkaSIH5TWor5XJUkZy38T3+dMF0po3ow32nPk60LIAIWcgEMXmBYGR6kf23EPRJyePxp/7Aq3f8jjueKcbhtFAU8PjgxEtrqInewWWrjkY5UkPf6ia6yUV7h6l/diV/umgRLnf80J6ifYes20mfoS08O2cLHzybxYr5PjxJFkefU8u00+tpisQniGVYISdiX0+Jh6pmH09+c3j8tXVonDNlBOnJHTu7DyZ+08YeGaSztJwiZKvi1F5ETZUq0vCleCCUeJBITje496Ud9BwUxDRtCgJ/s8q9F3Vn21oPgcYAae+vJnJcf8JOlUifbJpdGp4Vu1CrgqArJE/0Mn1ECVlJfras8vL9FymcP7Y/BT3D6E7Jrq0uDFWn+dj+SLf94qT67Kmvy+vj2Ouf5Y6jH6S2tgEr1Nb5CLahD9yQjTrOgVAjiOQoNDhaaWodu+pbdbT3hREVzHo7gyvuLd//dRUOMPdAAmMP8FLxXCIJQghhqfFxTREXJG3EpZi4vRbjpjfy0sM5EIUhY1u4//UdqLqFwwHQzEhfNd81lJOm3Mx5D79NbZOL7hk1vHDxxzhUs/UeDulawUkjcnl58SWcPHEIL3z1U6eH79BUDkkeREa2i6/LV8cGpTaEpMYHDb05M7eYbF8Qy4KH3inmrBEDcfoj6C4HUcOEzVX4x3dHqw/i2FaDdlslr7/cm/MKt8bF7SWg6W6mXfEa9/d6DqOT8IoAmiydLklXQ9LVcd9JJRn7dUzUP6GCEs89oCkq/xp7GdctfZn6SAtSSsJREzMM5uIUrjjpi1a65h2hJBo0V+IySrdCy3QPe4orOfvOk5nz5vds+HFzq8HXdBU0hayzsrh26rf0za3l5e9HUNnkI9kd5rTRa7lowkpWNtusqEN9lcxpKEQR0q4+bl+VWqthLUuCJAVSBGaGB+ZhJ2aje7tBAEsQtgzuefUb3LUBmutaEBY4X6kldGVWhySsU9G4vHe8HHav4T2499UGlH3K0nTFIlMPclL6ep6vHITSO4CmW+ibUzEiBtGowS2T5uFM0EeiqybS2AoCcgojXPvQ7rjvgxGVt5cMiftMVRRyvFPBHUBxHk522gROOGQZH3y/lpZgmLyMZC47ZizHjRvQ8d4cZPymjb1wHo4MzwGZmJNk6Y78Dp8pisXAEyTb3jDjmjMkgAIPvLWdov5BdL31UzxJFn9+v5gLxvenud6O24/fHSLl3LHMWrmJ0NmClqsKQIUT0rdzS8EihCFxOCWBlnouv2c3t5zci7Jie9SXmkL9eaNbXz63Q+f0SW0lfj0GFfLmrmf4y9vv8vn8hVhbAmg7wkivinqej7tP3MBhqeUYUiFSpHDzzKNYsy0PFIkaCneaj7BMQc2eA7jlMgJK55TGGxrLWt9hURnFOdMmn7KSVYxpSTzeXIS7LMTVD5Tx0XNZhIO2BN8fn9+J2xv/EnlUk+npZXy6ZDbNgRCmJXnwlNl4nZE42+RxGAzLL+fsrOU0Vh1FbkYytc2dcNFYgrtGz+Dlsu9a6S4SnCTzG/M4LasYRbEFzA85qomkMSNxDc7n1VnLMIoyQFcJR03847qR/OVGPpjogPvzOeeM3YBEc4HD0RuR8ihCzSfTmcTuYF0ne5SkOLxIKVnfWEaJv4YcdyrD0rohnNOAezo5Vh3hPqXDpwWeDD6adDOr6ndSGqhld0kLr7+7FjNi0DenpnW5RsOJhoVJJ7XsqRpd0rNQNZWHvryDue/8wOf/+oaWej/Dpw7mC8PPmmiEqKVy8siNnDxyY9zqAVPlneoe/NicS4GjmfKIFwvFzhnEZpiyXsVanAJSaasBVGN191bijLJlWXy1YB1KLKzm/KYJBHYTnG5X+jibBH879kJ6J+1TzWbuRJGJ+YR0RXJBl818WNuLOsOF3jPM9UMPgQYDZc0tDBlQ32nNe0LxHAtChsayHfm8sWhY3HduzUHP3tejxPSWXcC1MyZw7YwJiXfwK+I3bexxTYeWv4JZTvtYZ9TUWVycz86ajlwnioAZZ1cS7N/E23/rQtVuB6SqtByXSs9jTAoHRNATXBVVkxx5Zh0fPJONZVqsn7eejz68BWtgI1+U7wEVilyN3Nx1NU7Faq0Y8PgsXG64//UdXHRIP+zsGW2G3qlzSP9uHD6sV/xxKgpXnD6Db3N30BDxEwyD3OThtRM/pSi5EYdi4cTCq8IzZ3zOyrosbt10KElvlhDtpNnK6TYZOMaf8Ls26HZdvZrR6RLJupuacLMtsnLXbluL07BPWdscYpnlRkRcuH0q65c4MKIKQw9txtGJrKAuIsxdtZFgxEPX9AYK0psSOqEul0l+7rdcOrCGM16+guLyWoKReC9ac8Og/pnoboXwPiGO9rCkiKMu1nVJQY8Qw87O5vq/rcSQsq2+PPa7+ej+pL2+jA/vTOPjh1PJuMFN9xkjeHDkTa3bOa/HRP66+cs4vncAh6JyVN4wGiJ+blj2ChWhtqqhZN3DkyMvoEfKw9B4O7Z3b2EbQBd4L0TofUgEIQTD03swPL0HZp7FltWN/LS5lJaQk2S3PUvo4WpqLc/tANNC3xZh4h3jAFA1lSPOncQR505qXeTVa/+GZSnc/v50njz7SzTFaqVUDpoKCxpz+THm2ZdF9tFujd1Iq8xDp63lnSm6mRYNLpVouO1aOmc14ZjdhJWvo1oKx594GMPP69FxZRlBxvQgEkEVkj91W8J1xYfhUDXyeruZkO4hOrQGa5+Cn5+DYanc/M6JLN2RFXcuqqIw45BB6FrHrcnoGmTwS5Ahm4bFOQkhfslefzl+23X2xk7ssbK9t6jRaB7Dnz49JuEqQkjG9yrlyDPreeXHTXxZspkhX45DnpFNX73ebqZIAJdHMnB0m6FUFEFzUwtzqte2PhmnZW5DE2aHdRUVUjMNBowOgICsIV3pU5DF2H6F3HfBkTx62XEJM/FJupuXx1/FYG93zHlpjFZr6OprxrGPqLlTsRiSVsOQnCqMls5SiBJNl0w7Ld7biSPJFF5QuyFSHwVgZ0Udnyxaz7crthBs98KdVjgOl9DwPLwHEZJx5G4iJBERidvnYsDk3+Hw2ARWSalmp3QWAhDSvrYp7tB+k7NJqQb+xgBz7v6QUyYNxqlrqIoAp4V+SBMcUcO27ls4+ruH2B2ow60mboVXhWR0UlsyMhoVTD21jnmrfkio6gW2rQoXpSOdguCIJEoPLeLiPmfFLTOj62imdhmEU9FRYi++W3XQJymPG/oew5U/Pc8ufzVBM0Ig9lMRauDKn54nrE9DZLwP7hNB6wfOqYi051CS2gaTHS1V3L/2Q07//kmuXPIccyrWYsVCFaqi8MQVJ3Df+UeyZNchhGNMrilahGlppegJePOJAvkONoX3dHrNs1LsgoTlu/I565kz+H5LNyKGghmrehufXMmM9O2drg/YcoS/qOcZdFWh78CujDl6BA5XW55AWKCWRnE1wKk3HZ9w3e9q/LR0xk+AfdxDvLVk6XYxg0PRIPwtmiZoNHSC5oEbXodmcsMxfnrlZcWdoWlZvL9gNfe8OquVx0tKC6vhFmTtuRB4BYJvIRtvQtbOQFrNB7zPfwe/Wc9emhXIurNiLfbtX06NzNRsjh8/jJkL1xKMJfE0xURTLR4+dXarRJvdHTqau4ZeyeW3PUR4WzPW49jjxz4wDKirbHvgXF4XSoojroml0NmM1snzLCV0KYhQvD6d+1+4hl7DE3gjCZDrTmNE/UDWGEsZ22M3bjVxWMKlmAz31RDoC2XrE3ciXnhnBY52VUGWhEhUxS9OJSPFg3CMA+ckQlGLW5+fydLNZShC2BVIluSuc4/gqNH9OLFgNF98+wMlwc7LV/uM7slxV0wn2BLi1bvfpXidGy2BZ798no8XH8qjeP1W0pViqoamoF+QeMAyDdi4wk5iVRRX8OBwD5cduhaXtRCEyaqWTJ4qH8zGYIzSon4nmqKiKypRq83QOYXBSF81vd2NANRWalTudpBTGKZ2i0bYSGAUAXSVyNhUope70Ltk8vqEy+jui5d1VITCPUNO46zuE/iuYi0RaXJIZh9GphfxY80WGiL+hI1PEcvgm4o1nFgwCpHyaMLd/1i9hVtXvklUmpjSYqe/mo1N5cypWMeDQ89ExO7V1BG9kfJxZN15EN0MBLm16wpCUmdBQw7RqGhXiy8JFen8bsVrfHX4HbjUjr0R508bxd9nfk8wYuBx2t3Tez17VVi4FIsb8tdgIfi0rijxtcuMQrVuk5sdIBRF4dSJQ8g4cgwPnvVXVsxejaYLwEDT4c7Xp5NblNVhvcpQI/eu/ZijUwfxh64rEzM+ABFLJUcPUBz2MiytGwSjrGpJ4+nd/bg0byODPHV4YrmZUFQlYqh8srIfp43eEKN3bkPvnGYykz1s3xPfaxmOmny7Ygsj+xRwwviByMAHEJpNHE+LDICxA9l0DyL1Lwd8fX4pfrvG3v9qrBJn3xcnBIHXufmUq5g0uIh356+mqr6ZgQXVnD3iXQrS7Rcc4QUlF5H6OGXLyqj9+2aWakn77qYVRkTw5Zu2EXF6VE6//UQ+2Pk2phVh7wSpOJTCEG8teiKODQWkWsjJb53MQ6GvaZjvZ1BqV84vOoxeSfuX/Ptq6SaihkUoqmJZIiGZmiEFKVqYK26r4YHLuxMO7qPi44J+E6K0pxBTYjkxjycLJfn61mXvf30WP20qjS9rBO57fTaF2akM6JbD5TmTeUBbSZjElT3NtXY34HFXTOPLF+ZQuVOyaqGPYRNaWssO53+awhM3FbYeqzAtjJX1zHo3nemn1+HeRwA7GhG8+w+7bDO/KEq66zJUQhCb6YxMqubp3vO5fttE1gYyiUgTLMHojJ4sq9tOJGJTGx+dUcJVXdbRVKfy8HXdWPuDF90piUYEuSOrcA3qSsJG16iJY0kDyiY3T7xxfgdD3x59knNb2VL3YkvTHsJmYm8zaEZY31DKiQWjEn5vWCZ/XPEOIRntsN4P1ZtZVLMljlJBCCekvwmhr5CBD3AQ4pS8XFa0SOrbT+hjtl1KybzK9RyVN6zDvk+bNJT1uyqZvXwLV0xeikPr6HC4VZOr8tbxeV0PrAQevFIYwtzsATM+Pq+pCj1y0qhtChKKRAmEozh1uwP8vguOJD8zBYD7Pr6ZPauvYMuyTSSlhBgyvhlV34ys/RDS30Qovth5RFm150VOSN/K1mAyO0M+ityJO1Mdiklt1MUNuUtZsv1kVkeO472yQwhLjRuLszispZoT84rxOqIs3NKND5cPJBDR+XZDL168eCZa7D2fta4/f/5qKI2BkoT7CUYMXpu9zG6YCrwIJBKjiUBoNtJqaT2Xg43frLEnPJ999VVbIXSIrmNMv3GM6dcmciCNU+yHXzYjHKPAMYHi1bu4+bB7kKYkaio8eHk37n5xJ6om0R02oVgkLPjkpUz27HLicFmcfGkNA2f8nSJXOc3+QXxS14OI1PigphcnZOxEJ95ISang8BbSdPsUvqlZSrDRPu7yYD3zKjfw4LCzmJjdr9NTtWKuwrcbenH+oavQ1ESep+DI1HJ8U8Nc+afd/OvePBQVTCkIhzXGXS0pyAug7yNf59JNrOhzSOsChJJCfXOA71Zt62DoAcKGwcuzlvLY5cfTZ0QRViSxB67pGkMOs6sL3D43Ty15mHcf/Zin73Fxzf3rGD6hGYmTp+7o2mFQEhKe/WMeWhcnR0zeQzQMQkpMQ/DY9YVs32BXLZ11QwmKEoJ9Kt/disktBau4YMsR9vYETMjux0PDzmLDnj088OJ3zAt4Ufs5+emeAM0VdklgNFYEU75sD65t9YRmDLZXViQiP4zIjkBI4tmh8OjTNzK0pwMZWQlqHkLtwoEg3enDoeoEE9TG60Ily9UmniKNErBqkWp3Pnn6R15/6ANEZTPJHoXwMcmEz8lorZcPmhFmlvzUgT9HCB3cJyDcNt30rD0zqTeWJjy2sBmlItiQ8DtFsQ3v+UeMJF++2ClpnkuYFDojVEZ9GNKKk1sUukQZ34BcnIKICoRQ0BTJoIIy/nz6iyR7s1hbdQbfbxtGVqqPo0b1ba1QA5D+V8jJWUrOcft6xMXI5ocQKQ8hIyuQ9Vcw0RliQq6BRNBs6oRMBZca/5xELMGWYAp3FC5nVFI1IUvl6d1rCUt7cDHDCrPnDmC21bGjdUd1Ggs2d2dK/x18v6UH9386gVB0/02arVQIVuI+htiVBqsO/mvs94HYT5ceVuv3lmVhBH5Ei7wExjZQcxHei8AxESEEj57/VFwCaPn8ZC4/vC8nXlxDn2EBqnc7qKtS6TkoxK1P7WLwWD94BaqQuBSL6/LXUhpJYlVLJmVhLw+UjOSPhctQUHEoURBehJLESnkni2vmEmzn2VlIQlaUe9a8x6wpd6B3wrk8eUhP3luwmu3V6Xy2qh/HDt0cxwVu4cLhPRVHdDmYuzjm3Homnhhk4zIPlnYsheOupLT0HDzOxCGgoGkRbPqa7NQz2FlZj0NXExp7KWFTif2wpuekMenUcXz/0RIiwXjjpTk0TrmpTZPUm+zh4gfP5uIHz7a3Y+5m29LviUY+I1GpoRWBJ6/L5++XTmHMlkWE6yRrl3hbee2dHgfjpzfTWYtTkauRJDVCs+lAEQouRcejORmYnU+/gmy+W9XMZzO74qraGtcfAWBEDNwtEYyaAEaRj+j4WtAshG4PRMHbMvik5S8MrpqDUBx2ItAxGpH6eMK+BMO0+GLJRt6Zt5L6YIDweCNhpkwIwbF5I5DGLmTDDWBsB6FjRAL4lDRCDbkIFAhYOD9tQFsfwv9YQWsCtCH6c4l36OnLxqXoCTtvnapOobczaSkbvfIzsao8YCWugtIUOL374UzLn8LfNn/J17tXYVh20EpIGJJVzV9u+pAte7JpCTsoymqgMKPBXtkqZUjmUwwpmALGLgjUYUWHIHxXIfQBEHiVxBS1EQh+huW7AeovAemPq8x0CJMWS0dY9qxWFzFRc0Uy2NuWv9KExcTkcraHbGMvqxz2QSeYpQQiDmat7cOU/mX87dsphKI/b0a7ZqXaf6gFYGzuZCnZgSPqYOK3a+zdp0HzNhJOiYSLpqZuPPf7f+LRP+Ki28pQXNKmLLD2IBs3gutHKuuvpry4Im7VlHSDw05oILdbhO3r3Hz3URqnXVPNqMltyROzXde2Q7H4a8+FbAyksbipCxURD7eWXsbfB+fao7TWD5yTeXfF2wk9OrCn0MtqtzM+K3HFxfnTR/H5kg20BCM8+uVEVpfmcMGhK8lJacEkn7QuN4DraAC+W/Yl//h0C2W1tkd22JCe3OJzMqJ3Hpg7Eu8fmL1nFeeknkFGspfofhj9MlLa6AR+98JVACz4YDEOl45lWXiTPdz5zk3kdO88xCHUfCxtNEJ82ekyIKn1e/leHYdjxSaEauFy61iGyfQLJqM51tLZzM6uwoiRbUmLCdm27uzvnv2Uldt2Y5gWjpImRAKRGYBIMMKFA3rx5cQKSg3ZWkQiBYQsgzl1DsZ5s5iWVhZbYbGdcMv8PI7T3bQsbnrmE1ZsLWvNHSnLfCgjm1BVBRMLFYGmaNzQ72hyXSqy+vQYoZgFMoSmw4RjanF5Itx3iZ3nERFQd4TRlgcwRntxKBpjMuKruRLhmPwRPLt1dsLvHKrOpOzO9Xlb4Z4B/tdINEjrel9OzbUH+bsHn8q53Sfy+IJvWFlcwp8nz2Zsxh40VTKqR2d9HiFbGGgvwpXI8HxI/Yv9Lu0P/rdjNB7x0BSJQ1r8adcYsh0hMrUgZ2VvSbABGR/b/xk2FcsxiWjaQ5TUvPizC7scGhcfaYuKC++VyKY7Yj1C7eEE9wzEfp3Y/wy/WWMvPCcjg++DsZW2EV8ATkLa/Vw35o+EWyp4ZXFZu9b0GGQQgh9hBiegtitJ6zvcz8PvbEdVJS6PxIjCUefUoevx68sE0hn9PfX099RTG3XyWPVxCM/Zcd83G52LRkskfrPzrtbsVB+v3Xo2j7wzh2VbypizoR+rykZy3YwJHD2mLfzz2Y/refid7eyl+7BMydxVxazYupv3/nA4TnNxa8KpPXRh8Xa5yTn9oTA7lR456Wwpq24NH+2F26Fz9pThrf87nDq3vX49lz92HttW7iQp3Uff0T1bOWj2h55Du7XWT3e4HorA7JXF70+bTGF2Kr7HHKgVTQRbQvQd3YvkjCSs+hUQ/o5EL1pZ2EuT6cSl6FzZZxqpDg9bd9ewqri8dcYiHardfJbgPdUdGmRoVMg6ZIIFQpbGW1V92ow9BljlEFkIzraSxXmri1mxbXeroQew9jixvktH7R1h5PAsCr1ZnN5tHD2TcrD8L8eMwD7VVm7JqMObye0Wbu2kFiGJ/n0zxmgvuqJycuHY+GsoJevnvsybD31J8TqLtCyNk66fxhMzzuOW1W/YvEBmFJeq41B0nh59CZry8xUowns5MvQVmNW0GXwVhBOR8mDcskVJXXj62PMINX2M2vJeHH/OgcHC1mi9FZRcsBLHxBEamMV0Jk6hCIscp8HXDYP4Z89vEjIuRC2VRU1tuTORFe20VNTj1Jk2cjCa7rWLF/bDs6WrCudMGcHUEb3tD1zHQHQDBF6LLWFilzsPRyTf2el2DgZ+u8ZeOCDjTaT/TQi+A1YzOEYgfNcw54Uy6ioaOHxGXWzqn+hmROjSZVFr5lxRJPe9ugNvUtuLpumg6R3X7axlHqDBcHNCgiTbmIyebGgsS9jkY0iLQSld93u+hdmpPH39KQQjUSJRk2SPM06gOGqaPPHB/A4UApaU+EMR3lzUkxOGuskRgbjSzaCp8mFNTxrMthKkRy49lgsfe4dQJEooYtjV3g6dKcN6Mm1Ex9lHek4aY47u2NOwP2i6xuWPn8c/r3+JcKDNS5QCcKicf/vJnNVuYKFXfIOcSLoZGfmxQ0Nd2FJ4bs9AhntruLBbD8Z1PRQpJd/OX2tL0+1drlcW7lXlcSyPrdsWgr5H9UUvXd9pU1bNvmRfMoCMLEW0M/YfLVwbV7LaioCKtjmFCycfydh2OSXC39OZwTINwYBR/jjaDBWFrp4MHh52FpnO+OKCb/51Lf+4uSLGoqpSXyV56savGfn5ar788C/Mr9pARbCBQm8mk7L7H5ChBxBKqk1Y538ZgjOBCDgm2eEWrXvCdRxyKSidOzs/DwmuIyDwNh1n8i5wn2PXY4Z1Es32FOFgat4RXDP0AtTG7chIE6JdYUHQVFnWks3mYNszLNwWolsQWRJTJ4tB11Ry0pOYOrw3qqIwaXAR89YUt7Fn7l0f6Ns1m79ceUIrxw/Yz5ZI/j3Sew6EvgUZBud4hD7oP7g+B4bfrLEHEMKF8F0CvkviPp/7zruEA2HcHgu1ExlAsFAUP6ffcgLv/vkTBo6uQXceiOehIoTEknQQGw+aKstCEzmje0eDeErhWN7a+QNRy4gbKpyKxsTs/uS4Uw9g37Z37XZ0LI/bWlaDYXUSljBM5iwvZU32mZyQPJtpaaWoQtJkOHi5sh8f1PTmsOy2Yy7MTuXT+y7i0x83sGTjLpI9LmYcOogRvfPjBpj/FEdfPBWPz80Lt79JdWkNEug7sT+3PHsFhb075/cHEFovSH8b2fQgRJeyd0B3KhaPFC2OLbSE7Uvzuf+8ZZQ6wBhb2NogZaW6CQ7Mwb2hIk6IwulxcsYfTmRQj55Ed3VSgomkR6xssw06QsQbXH8wcdhuLwL7Mi4qyYkXxM6XBPxtBtnhdXDJZWdw0sQjOtyTQP3SmKGPnzmFgwor5pSzbvYSjjp64n6PbX8QSgoi6UZIurHTZYLhKHNWbqWyvoWpvQ26+pROcywHBH0YeIDAG7RVlAlwTkYk3QDmbqT/9YSrOhSdQdnnIYSGTHsemp8k6n8TCBO2VN6v7skLFXYiVhMqmc4kqsNNKEOC5GWlU7deEghFURXB0aP7c9Opk1obpW4+7TBWbC3DH4q0ihnpqkKSx8Vfrz6R7NTEyVah5oH3/H//evwbOGBjL+z2rmXAbinlcUKIdOBdoDuwEzhdSrs/WQhxO3AJ9hzleinlrIN83Ps/1ljwbf1SL2Zn76vwIpyHcu5dx2MYJvU7X05IQ9wGFyip4JwIrlNQGm/EtBpQCdn16lKnXozg9L6PoiTg8k5z+Hh+7OXcueodyoP1aIpKxDKYljOE2wbN+A/PeG8b9/4MseDqvqdy4zI/D5eGcSomAUsDBB7VwVV9psct7XM7OXvK8Liwza+Bw04/hEmnjSfkD6E5NPQEA1lnEHp/SH8JWTmKRB5xQ02Em6d/ir9JgENFjiuM+z44rhtGbjLe1eWkmtCtXz5n3jqDsceMAGBKl0F8V7mug3fvEiYXdtmX6VSxp+jtMH5ANzaXVRGOdnwIo4bJoB7xJbfCfRoyNJdEeShFgRXz7cHE4dIpGljIiSdPSTj4Lv387U6dnFBAYdZLMxn9Hxj7n8NPm0r43bOfIoFwxGBBgYtnzlNw6f+msZcRhGMYwn0U0nsBhOYAJjgPtQd9AK07Muk2aH7E/g4DcIJQEWnP2JEA7IiASL4V3XcLb+34hhe2/4gQKk5V4lId/HHQyUzI7kfQiKAqCg5FQ0oZKwnV0PYJPeamJ/PeXefz+rfLmb1iCwKYPqov500d+asTm/1S/BLP/gZgI7DX/bgNmCOlfEQIcVvs/1uFEAOAM4GBQB7wrRCij9xXd+5XxJSzJrBlWTFbVsO2dW76DA3Gxe0lKkIkg+sohBBcdN+ZhJr6oLVcAAnrxh3gvRilnScjs2ahBb9EhuehKD7c7pPI10fv1/PtmZTDOxNvZGdLFfURPz18XUh1HJwHond+FnonMXCHpnLUqL6MSC/i76Mv4u+bvmJ9YxkKMCqjiJv6HUuP/dSM/9oQQuD2/ZuJKau206++eC2DaMT2AJWIiff77fgnFNmcLIoAIdD6dGHSWRO457zpHe7dHYNmUBdpYXX9LiQSVSiYMsK1eRsZ4bO5Z+Y25PFK5QB2R9LIdL3PuT0mclz+CBShcNqkobz13UoiUTN+NqdrTBvRm6yUfbw+xyHgPBwic9sl8ASGofGvP/UkGlZxeZ0cc9lULnrgLFQ1cegl5A/uR55Y4G/sRHj5IKC+JchNz3waR2OxtjSVmcv7M2PEJtyO9mEWldYQq8gG2cBeneM2uMA1HaHaA6NQc8F7bsJ9K95zkM7xyMC7YJaBPhDhPh2hdqwyUhSVc3sezandj2BzUzkORaNvcm6ro+bW2jqvhRB4XZ2LkmemeLnplEncdMqkTpf5nwAhO+thb7+QEAXAq8CDwO9inv1mYLKUco8QIheYJ6XsG/PqkVI+HFt3FnCvlPLHzrY/atQouWzZsoNwOjZCgTBXjfgDlTur0PQwv/tLKeOmNRGNKLg8AtU9DJH6l9YHaC+smhPB2AL71Mkj3IjMWR2W/5+Gr37axH1vzCYcbfNEVUWQ5nPz3l3nx9UtG7GO0gON1f5PhZRBZOUYEg3Svz+liDU/xodWol18BIcVYGV6KchL5+rTJ3PEiN77HaS3Nu9hVd1O3KqDSV0GkGQtQ/pf4LkSi7eq8glZbYOsS9GZkjOQe4fYdMTb99Ry+4tfUlrVgKYpRA2T48cP5PenT0ZPYKyltCD0BTLwKpg1tsHyXQHaYKIRA92h/WworXzDW1w68kOi4Y6Dv8tjcfGDx3LSDRfvdxv/Ll79ZhnPfv5j3DNoQzJ9UCm3Hr+TFFc9aL0QvstBHwUYCOGwtYgbfmfToAjdJuRzn4RI/mOrZ/5fxEMIsVxKmbgTb99lD9DYfwA8jK2NdkvM2DdIKVPbLVMvpUwTQjwFLJZSvhH7/EXgKynlB/ts83LgcoDCwsKRu3btOrCzO0C0NPh56c63+ObV+YQDYfqOTOOCew5l1NHTbe8gAaRZjay/GMwSO0gqVEBBpP4T4Rx3UI/v18LCdTv4+8zvKS6vRdNUjhjemxtPmdjRi/xfBKvh9xD6in3LAe+/rIiFXyTuivYku7nz7ZsYc/S/F6aqDDVyyoInEiZwXYrOs2MvY0BKm7pWSVUDjf4g3XPSSXJ3Iqx9kCBlhPtPPJWfvtUJh9oMvqJIkjMEr257DU/Sr1Pid9fLX/HFTx3FfMCOZV87YwLnHTFyv9uwG8rqQeuB2E8e47/4Zcb+Z8M4QojjgCop5XIhxOQD2X+CzzqMKFLK54DnwPbsD2C7CSGlBGMdGCWgdQVtMEIIfKlerv/nZVz/z8uwLOuAygGFmgUZn0J0NRibQMkA52G/Ka9iwqAeTBjUA8uy9U0PZkL1fypE8t1IYxOYpbHqHJst8piLurJsXjChGIcQguFT//0KiPmVGzrNkIQtg1l7VscZ+8LsVCD1397fL4EQDm5951mevuZ3fPtuFE2XGBFBr6EubnvroV/N0AMUdknDoSVuytN1jdz0xINvewitECj82eX+i1+GA4nZHwqcIIQ4BpsiLFkI8QZQKYTIbRfG2dsHXAa0ryMsAH5GLePfgzRKbU1UsxybPFvaPOxpz8UeGBsHYuj3QggBjmH2z28YP6dnWdPoJxCOkJuRnDCc8FuCUJIg42MIz0OG5wIOhPs4Rs4YxoST/8nCj5a0GnxVU9AcOre/ecMvSgbvi4hlYHYyK5ZIQsb+K3F+bTg9edz08jtc9sQu9hRvI6VLEdmFB0a+959gxiGDeOnrxJQMmiKYNLgTorT/4lfHAYVxWhe2Pfu9YZzHgNp2Cdp0KeUfhBADgbeAMdgJ2jlA7/0laP+dmL2UUWT11BjXRPssvwJKFiLrO5sb5L+IQ3F5Dfe89g3bdtegqgqqIrjkqDGcP23U/8hZwK4NpXzwxGdsXlZMVtdMZlx3NKOmDz3gY5VSsuiTpXz81FfUVTQwYGxvTr3lBLr1L/j5lfeDTY27uXzJcwmpBzyqgz8NOZ3Duvz66kP/E/Htii3c9coswFbPcjk0VEXhn9edzJCi/ZfU/he/DAc1jLMfPAK8J4S4BCgBTgOQUq4XQrwHbMCuf7rmV6nECX8Hspl9uw3tNvMWCM8B11EHfbe/ZVTWN3PR4+/iD0bsuFpsqv2vLxYTMSwuO2bsftf//xuLPlnKQ+f8FSNiYBoWO9aWsGb+eo666HCu+fslP78B7JnaoTPGcOiMMQf12Pql5DMkrRur63cSbhe314VKF1cqE/ZDbPe/HUeM6MOwnvl8vmQD5TVN9MrP4Jgx/fH9yrmK/2L/+EXiJVLKeVLK42J/10opp0ope8d+17Vb7kEpZU8pZV8p5VcH+6ABZHQdyE7In6QfGVn7a+z2N43XZy8nHDE6JFBCEYNXZv3UQfXpP0UoEOb7Dxfz9ctzKdm0++dXaIdwMMwj5/2dcCCC2a7pKeQP89VLc9m4ZOtBPdZ/B4+POI+j8objVDQ8qgNHrEHuubGXoybotfi/hMwUL5MGFzGgexcykr1ov/FQ4f8G/GY7aIWSgcRJZ3XxiWpr/69j4fodrV1++0JRFDaXVjGsZ0fd3n8H899bxOOXPI2iKFiWhbQkQw4bwN0f3ILL8/Me3k9fruw0VBMJRfjy+dn0H9v7oBzrvwuXqnPnoJO4qd8xVIebyXD48OkJlG/+jyEQinDzvz5jVXF5TPzGFsq574IjmTr817ln0moBcxeIFIT2n4Xo/rfit+t+uI7bz5fiZ77/vwlHInHdGKSUOPfz/S/B1hXbeezifxLyhwk029Uw4WCE1fPW8/glTx/QNprr/ZidDEzSkjRUNR2UYz0Y8GhOunkz/2voY7jrla9ZuW034ahBMBLFH4oSDEe565Wv2bq75uc38AsgpYHV9CCy6hBk3XnImqOxamYgjeKDup//DfjNGnuhZkLyvdgFQnuniKr9f/I9dhnlfxGHGeMH4urEoHucDvoWHJwu2nf//DGRUMeQUCQUZdHHS6mvbPjZbfQb0yte360dnB4nQyd3FJX4L/7fo6qhhR/W70xYehkxTF775uA1TwLIprsh8C4QikmUhsHYiKw9A/lztMj/x/CbNfYAiucURMYH4D4F9BHgPhmR8QGK59T/14f2PxInTRxMflZKTPbNhs1oqXHP+dN/tlzzQLF1+fZORbsdLp3SzT9fiVs0pBt9R/dCd8YPTkKA7tQ46uIpB+VY/4v/DFJKpAy1Cmrv2FOLQ08cn7csyYaSyoO3b7Magp/SkRdJggwjA2/FfRpsCfLeY59wcf8bOLfoav5+zfNU7NyfctT/LvxmY/Z7IfQ+iJQH/l8fxm8CbofOq78/kzfmrGDmD+sIhiMMLcrjiuPGMaDbwaOCyMhLp7w48UttRA3Sc1IPaDv3fXorD571V1bPXYfu1DENk4y8dO796Pf4UttEVKRRbHPkqD0RasbBOIX/4mcgZRDZ/CQE37O1oEUK0nspGcknYnQSfgPIanff/mNEV4Ow1cI6Igyh+eC7FoBAc5Brx95O5a7qVmW1L1+Yw7dvfM9fv7+foiHdDt5x/Q/Fb97Y/xe/DB6Xg8uPHcflx/569A8n3XAsW1ds79C5KoQgv1cuBX3yDmg73mQPD31xB5W7qtm1oYz0nFR6DuvemriVxnZkw/V297TQbW/ONQ2R8tCvqvjzfx1SWsi6CyC6kdYCCVkPLf+gyLed3PR+7Kyo61D15XbonHX4QWRR/bl73E7L9f0nPqViR1WcBKkZNQlGgzx+8T95etmfD95x/Q/Ff439/0BU1DWzs7KOrBQvPfN+e1VFE04aw+LPxrPggx8JB8JICS6PE4fbwV3v3/yLt9elWxZdusXnYKTViKw9MybhJ23vEiD0LVL6EWnPHYQzsVFe28T7C1azpayarlmpnH7YUIpy/w/PICLfxwgD962EC0Hwc568/CzOf/wHIoZhi98IcOkaR43pd3A7aB2j6ZTWW3gQntNb//36pe/iDH177FxfRu2eejJyf5kAz28N/zX2/4PQEgxz5//X3plHR1Vle/jbNSYVyGAgmMgMAmJEiN00g4LNKD5RfEI/HBBRX3frW8sWcT3BodHnslfboM/1VtsqKvZgA+LQzdQ22AFtB0YbGQKJOEQikACRAAlkqjrvj3sxlaEqVaSSe5M631q16tapO/xyc2rfc/bdd++l77I1/yAet5Naf4Cs9BSe+dlUenVrPx1RRHhw6b1MnvNj3n01l9Ol5eRMHMLkO64mKSU203h15i3TwDccP1ZB1WZUbWHIyknR8M89XzH/5XX4A4oav59tjoOs+iSPeTPGMv2qIS3ef3tEVW5oVCEsmB7Ju1jz5Bz++kke2/MPktopkRuvvIyh/bJi+pS2iAdSfo0qm0f91MiJRrETb12NhuBqaA1xuhycLW+9tM92QRt7G3H/71axp7CYmlr/99EMXxeXMmfRClY/eWe7egJRRBgyZjBDxrRSyoDqjwlVwg9xQs1OaKGxr6isZv4r66gMStfrDyj8gVqeefN9Rg3uRVZ6SouO0T4JXyQHhM6+BGZNuKLZDJctVpIwEdKXocpfMHz4jlRIvA3x3YRRb8kge/Qgtqzd0WSAl8vt4sLeHT96r11H49iNQCBA6ZETlJeFeLI3DAVFR9n3TQk1DULWlIKqmlrWbd0fK5ltSln5WUpPVRBNDqZznK2o5PihUvxNhPHhSA2zpYA0n13xHP5AgGNl5ZSfre+W2LjzQMiRaCAAqzfvi/gYHQlJmAwSquiOAu/VMT3e8UOlvPPcOv74xEp2bNhVr5YwgLizcaQ9jyPjIxxd1uJImtkoL9ashTPwJDbOXuv1eZm1cDquoJDkkxWV591n7Ywe2ceI9b/fxNKHl1FeVkHAH2DQiIu5/8WfRZxwa09hccgy5mera9mWf5D/uHpozPS2Nnu+PsKvlufy5eFSRISMlE48+JOxjB3Sr9ltT5SU8dw9S9j+t504nA5cHhfTH7iOWx656fsMppI4A1WVG1TRKRhllI9sBqUUyzft5JW/beVsdS2BQIArBnTn0VsnkJWeQumpM1Q3KsJhUOP3U3LidLPH6JB4RoPrUqjZTX2/fSIkTovpE6xvPbuG1x5djlJQU1VDYqcEMnp2YfGmx0ntGvms6uKcvvzPqvksvvN5Tn9XgcMpqIDi1semc+N9/wZAXmExTy3L5YvDx3GI0CUliXnTx/Ljof1j9vdYSVRZL1uLWFeqamvWvLielx78E1Vn6jq+CPiSfSzZtZiMns1PEdfvKODJ19/jTBM3kRwiTBudzaO3Toip7tbi82+PcceiFVRW1zeUXreLX999bViDf7aikrsvnUvp4RP1RvRen5dJs8dy3/P/CZjx3Scfgsr11NVsdQAeSFmEI3FyszqXrNvC7zdsr6fT4RCSfQm8vXA2+74p4aGX1zb5P0n0uJl701VMH3N5s8fpiChVhSr/LZxZZiQkdGRA0k8R36yY+eX3fLifBVOeqve7AnC6nVx25SUsyl14HroVhXlFVJ+tps9lPfGY5QYPHDrO7N8sb7LPPjXnGsa1UpqHlhJN1kvtxmkhtTW1vPrwskYdUikjEdgbi1ZHtJ+rsvsQCHHh9bidTBt9/oU22prnV39MVXXjEXFVTS3PvPlB2Olx7usfcqr0dCPXTdWZKv6+dBPfFZ8AjHsCkvI0kvq0UdrO2QsSpiDpKyIy9BWV1by2fnujH3cgoDhTWc1bH+xixCU9Se2UiKMJ4+VyOpgy/JJmj9NREfHi6DwPR7dPkW75hgsl6faY3oBduWgV1Wcb577y1/jZt7mAkm+ORb1PEaFPdk8G/rD/94Ye4Hdh+uyzb/+zQ7h0tLFvIYV5RQRCPETir/GzeXXThRwa4kvw8Pjtk0hwu+oZl0SPi2mjssnube/6t8FsLygK6ZI6WlbOidNNuV4MPvrL1iYrSwG4PE52vV/nJxcRJOEaHOnLcHR9D0fq/yLuyG4I7y0sDlmgvbrWT+7OAzgdDpbMnUGPjFR8XjeJHjc+r5uuKUm8/MCMsEWo4wlppQyfRQWHQmXMwO11c+Sr2D2Nuy1Mnz1+soLSU6Gjj9oL2mffQlxuV8jUAAAuT+SneNIVA+nd7QL+sGEH+UVHuTCtM7eMG8aoS3vHQGnb4QxTGUwphSuEkQUapUcIRhBcIR7FjxaX0xHyxw3gdhnHyUpP5p2Fs9n91REKS05wYVonfjiwZ8xSS2hCk9U/k0MHipv8rqa6ttGzFy3BGeb/2VyfbS9oY99Ceg3uTqfUpCZHo+4ENxNnjY1qfwO6d+WpO6fESp4ljB/Wn3Vb9+Nv4iI4oHtXkpNCZ4ecOGssn23Mo7KicVhlba2fnImxiW0f0iezSfcMGLmCrh9Zl2hNRLi8XxaX94vsyV9NbJgxbyq7P9jX2GfvcnBxTh8y+3aL2bEmDBvAmi15TfbZflldSO3U/p/Ibv+XK4sREeYu+TleX/0pvcvjIi0jhRvvu9YiZdZxz9RRdE701hstiRhGdMHN4ROYjZ42nL6X98KTUD90zuvzctevbiEpOVTIX3S4XU7mzxzXKAuox+UkKz2Z60bGZ0lBOzFs3GXMfOgGPAnu72d0iZ0TyOjRhcdWRv8kdjh+PnVk4z6L0WcfvmV8TI9lFToaJ0bs21zAa4+tYP+Wz/EkeBh/61XM+uUMktMjj/fuSJScOM2LazaTu/MA/oDiR5f05N6po+h/UfPpH6orq1m5eDVrX9jA6bIKeg66iNsf/wkjp0YUdBAV2/IP8sKaT8gvOobP6+aGUdncNWW49sfbiMNfFrNx+UeUl1WQPXoQI6f+AKcr9pWvSk6c5qW1W/jHzs/x+xXDB/XgnqmjGNDdvg9cRRONo429RqPRtFN06KVGo9Fo6qGNvUaj0cQB2thrNBpNHKCNvUaj0cQB2thrNBpNHGCLaBwROQZ8c56bdwGOx1BOrLCrLrCvNq0rOrSu6OiIunoppSKKDbWFsW8JIrIj0tCjtsSuusC+2rSu6NC6oiPedWk3jkaj0cQB2thrNBpNHNARjP0SqwWEwK66wL7atK7o0LqiI651tXufvUaj0WiapyOM7DUajUbTDNrYazQaTTyglLL8BfQANgH7gTzgF2b7BcB7wAHzPS1omwXAF0ABMDmo/Qpgj/nd/1HnqvICb5jtW4HeEehKALYBu0xdT9hBV9A+ncBOYK1ddAGF5v4+A3bYSFcq8BaQb/azkTbRNdA8V+dep4D7baJtLka/3wssx/g92EHXL0xNecD9VvUxYClwFNgb1NYmOoDZ5jEOALMjOm+RGpbWfAGZQI653Bn4HBgM/AaYb7bPB542lwdjGGAv0Af4EnCa323D+CEL8C4wxWy/F3jRXJ4JvBGBLgE6mctu84SPsFpXkL4HgGXUGXvLdWEY+y4N2uyg6w/A3eayB8P4W66rgUYnUAz0slobcBHwNZBofl4J3GEDXdkYht6HUWnvH8DFVugCxgA51Df2ra4D44LylfmeZi6nNXvuou2QbfECVgETMa6AmWZbJlBgLi8AFgStv948WZlAflD7zcBLweuYyy6MJ9YkCk0+4F/Aj+ygC+gO5ALjqDP2dtBVSGNjb6kuIBnDcImddDWhcxLwsR20YRj7IgyD4gLWmvqs1jUDeCXo82PAf1ulC+hNfWPf6jqC1zG/ewm4ubn+ZTufvYj0BoZhjKK7KaWOAJjvGeZq5zriOb412y4ylxu219tGKVULnATSI9DjFJHPMKZr7ymlbKELeA6jkweC2uygSwEbRORTEfmpTXT1BY4Br4nIThF5RUSSbKCrITMx3CVYrU0pdQhYDBwEjgAnlVIbrNaFMaofIyLpIuIDrsVwA1ut6xxtoSPUvsJiK2MvIp2AtzH8cKfCrdpEmwrTHm6bsCil/EqpoRgj6eEikm21LhG5DjiqlPo03HptrctktFIqB5gC/JeIjLGBLhfGdPsFpdQwoAJjim21rroDiniA64E3m1u1LbSJSBpwA4bLIQtIEpHbrNallNoPPI3hD/87hmuk1mpdERBLHeelzzbGXkTcGIb+z0qpd8zmEhHJNL/PxBhdg3El6xG0eXfgsNnevYn2etuIiAtIAb6LVJ9Sqgx4H7jGBrpGA9eLSCGwAhgnIq/bQBdKqcPm+1HgL8BwG+j6FvjWnJWBcaM2xwa6gpkC/EspVWJ+tlrbBOBrpdQxpVQN8A4wyga6UEq9qpTKUUqNMdc/YAddJm2hI9S+wmILYy8iArwK7FdKPRv01WqMu86Y76uC2meKiFdE+mDcoNlmTptOi8gIc5+3N9jm3L6mAxuV6fAKo6uriKSay4kYP4B8q3UppRYopborpXpjTP03KqVus1qXiCSJSOdzyxg+3r1W61JKFQNFIjLQbBoP7LNaVwNups6F03B/Vmg7CIwQEZ+5v/EYUUxW60JEMsz3nsC/Y5w3y3U1sW1r6VgPTBKRNHMGNslsC09zTv22eAFXYkxDdlMXgnYthn8qF+PKnQtcELTNIxh3tAsw716b7T/AMDBfAr+lLowpAWOK/AXG3e++EegaghHauNvc5y/Ndkt1NdB4NXU3aK0+X30xptXnQlUfsYMuc7uhwA7zf/lXjCgGy3WZ2/qAUiAlqM1ybcATGIObvcCfMCJJ7KDrQ4yL9S5gvFXnC+MicwSowRht39VWOoA7zfYvgDmRnDedLkGj0WjiAFu4cTQajUbTumhjr9FoNHGANvYajUYTB2hjr9FoNHGANvYajUYTB2hjr9FoNHGANvYajUYTB/w/VFkObubEBrAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# relationship between Net Asset and credit score among different clusters\n",
    "plt.scatter(X.iloc[:, 0], X.iloc[:, 2], c=y_pred, s=50, cmap='viridis')\n",
    "plt.scatter(centers[:, 0], centers[:, 2], c='black', s=200, alpha=0.5)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2e804171",
   "metadata": {},
   "source": [
    "#### Steps in K-Means Algorithm\n",
    "\n",
    "1. Choose the number of clusters *k*\n",
    "2. Randomly initialize *k* centroids\n",
    "3. Assign each point to its closest centroid\n",
    "4. Compute mean of each cluster and call it the new centroid\n",
    "5. Repeat steps 3 and 4 until the centroid positions do not change\n",
    "\n",
    "\n",
    "### C. Evaluation\n",
    "\n",
    "1. __Silhouette coefficient__\n",
    "* A measure of cluster cohesion and separation. \n",
    "* Quantifies how well a data point fits into its assigned cluster based on two factors:\n",
    "    * How close the data point is to other points in the __same__ cluster\n",
    "    * How far away the data point is from points in __other__ clusters\n",
    "* Values range between -1 and 1; larger numbers indicate that samples are closer to their assigned clusters than they are to other clusters.\n",
    "\n",
    "[`Silhouette_score` function](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.silhouette_score.html) is available in sklearn's `metric` module.\n",
    "\n",
    "2. __Elbow Method__\n",
    "* A technique to evaluate the best number of cluster *k*.\n",
    "* Run K-Means on same data with multiple values of *k* and choose *k* that minimized the squared sum of errors (`.interia_`)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "49a91178",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.3684423242481178"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "silhouette_score(X,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "865d396f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running k-means with 2 clusters\n",
      "Running k-means with 3 clusters\n",
      "Running k-means with 4 clusters\n",
      "Running k-means with 5 clusters\n",
      "Running k-means with 6 clusters\n",
      "Running k-means with 7 clusters\n",
      "Running k-means with 8 clusters\n",
      "Running k-means with 9 clusters\n",
      "Running k-means with 10 clusters\n"
     ]
    }
   ],
   "source": [
    "no_k = range(2, 11)\n",
    "\n",
    "inertias = []\n",
    "silhouettes = []\n",
    "for i in no_k:\n",
    "    print(f'Running k-means with {i} clusters')\n",
    "    model = KMeans(n_clusters=i).fit(X)\n",
    "    inertias.append(model.inertia_)\n",
    "    pred = model.predict(X)\n",
    "    silhouettes.append(silhouette_score(X,pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "65bc4f01",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax1 = plt.subplots() \n",
    "ax1.plot(no_k, inertias, '-bo')\n",
    "ax1.set_xlabel('Number of clusters')\n",
    "ax1.set_ylabel('Inertia')\n",
    "\n",
    "ax2 = ax1.twinx()\n",
    "ax2.plot(no_k, silhouettes, '-*')\n",
    "ax2.set_ylabel('Sihouettes score')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ea44c0b6",
   "metadata": {},
   "source": [
    "### D. Final Model with Optimal K"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "20ab7aa6",
   "metadata": {},
   "outputs": [],
   "source": [
    "kmeans = KMeans(n_clusters=3).fit(X)\n",
    "inertia = kmeans.inertia_\n",
    "y_pred = kmeans.predict(X)\n",
    "silhouette = silhouette_score(X, y_pred)\n",
    "centers = kmeans.cluster_centers_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "0f2f3bb4",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\niti.mishra\\AppData\\Local\\Continuum\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    },
    {
     "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"2\" halign=\"left\">Net Assets</th>\n",
       "      <th colspan=\"2\" halign=\"left\">EstimatedSalary</th>\n",
       "      <th colspan=\"2\" halign=\"left\">CreditScore</th>\n",
       "      <th colspan=\"2\" halign=\"left\">Debt</th>\n",
       "      <th colspan=\"2\" halign=\"left\">Dependents</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cx_segment</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>59887.45</td>\n",
       "      <td>23055.17</td>\n",
       "      <td>33799.96</td>\n",
       "      <td>19555.71</td>\n",
       "      <td>652.08</td>\n",
       "      <td>95.50</td>\n",
       "      <td>18087.04</td>\n",
       "      <td>14486.58</td>\n",
       "      <td>0.50</td>\n",
       "      <td>0.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>59695.53</td>\n",
       "      <td>23081.26</td>\n",
       "      <td>100313.84</td>\n",
       "      <td>19139.12</td>\n",
       "      <td>648.01</td>\n",
       "      <td>96.90</td>\n",
       "      <td>18060.73</td>\n",
       "      <td>14646.84</td>\n",
       "      <td>2.03</td>\n",
       "      <td>1.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>59992.14</td>\n",
       "      <td>23267.69</td>\n",
       "      <td>166922.35</td>\n",
       "      <td>19256.99</td>\n",
       "      <td>651.54</td>\n",
       "      <td>97.53</td>\n",
       "      <td>18318.39</td>\n",
       "      <td>14788.50</td>\n",
       "      <td>3.52</td>\n",
       "      <td>1.13</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Net Assets           EstimatedSalary           CreditScore         \\\n",
       "                 mean       std            mean       std        mean    std   \n",
       "cx_segment                                                                     \n",
       "0            59887.45  23055.17        33799.96  19555.71      652.08  95.50   \n",
       "1            59695.53  23081.26       100313.84  19139.12      648.01  96.90   \n",
       "2            59992.14  23267.69       166922.35  19256.99      651.54  97.53   \n",
       "\n",
       "                Debt           Dependents        \n",
       "                mean       std       mean   std  \n",
       "cx_segment                                       \n",
       "0           18087.04  14486.58       0.50  0.50  \n",
       "1           18060.73  14646.84       2.03  1.72  \n",
       "2           18318.39  14788.50       3.52  1.13  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['cx_segment'] = y_pred\n",
    "df[[i for i in df.columns if i not in cat_cols]].groupby('cx_segment').agg(['mean','std']).round(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "c83a81f9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Gender\n",
      "cx_segment  Gender\n",
      "0           Male      1839\n",
      "            Female    1491\n",
      "1           Male      1820\n",
      "            Female    1558\n",
      "2           Male      1798\n",
      "            Female    1494\n",
      "Name: Gender, dtype: int64\n",
      "-------------\n",
      "Married\n",
      "cx_segment  Married\n",
      "0           0.0        2961\n",
      "            1.0         369\n",
      "1           1.0        3378\n",
      "2           1.0        3292\n",
      "Name: Married, dtype: int64\n",
      "-------------\n",
      "HasCrCard\n",
      "cx_segment  HasCrCard\n",
      "0           1.0          2386\n",
      "            0.0           944\n",
      "1           1.0          2371\n",
      "            0.0          1007\n",
      "2           1.0          2298\n",
      "            0.0           994\n",
      "Name: HasCrCard, dtype: int64\n",
      "-------------\n",
      "Mortgage\n",
      "cx_segment  Mortgage\n",
      "0           0.0         2661\n",
      "            1.0          669\n",
      "1           0.0         2709\n",
      "            1.0          669\n",
      "2           0.0         2593\n",
      "            1.0          699\n",
      "Name: Mortgage, dtype: int64\n",
      "-------------\n"
     ]
    }
   ],
   "source": [
    "for i in df[cat_cols]:\n",
    "    print(i)\n",
    "    print(df.groupby('cx_segment')[i].value_counts())\n",
    "    print('-'*13)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0d4f833f",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}