{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This tutorial was downloaded from https://www.ritchieng.com/machine-learning-evaluate-linear-regression-model/ and slightly modified to include the use of datascience (Berkeley) tables.\n",
    "\n",
    "Contents\n",
    "1.\tIntroduction\n",
    "2.\tLibraries\n",
    "3.\tExample: Advertising Data\n",
    "4.\tQuestions About the Advertising Data\n",
    "5.\tSimple Linear Regression\n",
    "6.\tEstimating (\"Learning\") Model Coefficients\n",
    "7.\tInterpreting Model Coefficients\n",
    "8.\tUsing the Model for Prediction\n",
    "9.\tPlotting the Least Squares Line\n",
    "10.\tConfidence in our Model\n",
    "11.\tHypothesis Testing and p-values\n",
    "12.\tHow Well Does the Model Fit the data?\n",
    "13.\tMultiple Linear Regression\n",
    "14.\tFeature Selection\n",
    "15.\tModel Evaluation Metrics for Regression\n",
    "16.\tModel Evaluation Using Train/Test Split\n",
    "17.\tHandling Categorical Features with Two Categories\n",
    "18.\tHandling Categorical Features with More than Two Categories\n",
    "This tutorial is derived from Kevin Markham's tutorial on Linear Regression but modified for compatibility with Python 3.\n",
    "\n",
    "\n",
    "1. Introduction\n",
    "•\tRegression problems are supervised learning problems in which the response is continuous\n",
    "o\tLinear regression is a technique that is useful for regression problems.\n",
    "•\tClassification problems are supervised learning problems in which the response is categorical\n",
    "Benefits of linear regression\n",
    "•\twidely used\n",
    "•\truns fast\n",
    "•\teasy to use (not a lot of tuning required)\n",
    "•\thighly interpretable\n",
    "•\tbasis for many other methods\n",
    "2. Libraries\n",
    "\n",
    "•\thttp://www.statsmodels.org/stable/index.html\n",
    "•\thttps://scikit-learn.org/stable/\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import statsmodels.formula.api as smf\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn import metrics\n",
    "from sklearn.model_selection import train_test_split\n",
    "import numpy as np\n",
    "\n",
    "# allow plots to appear directly in the notebook\n",
    "%matplotlib inline\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "3. Example: Advertising Data\n",
    "Let's take a look at some data, ask some questions about that data, and then use linear regression to answer those questions!\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>TV</th>\n",
       "      <th>radio</th>\n",
       "      <th>newspaper</th>\n",
       "      <th>sales</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>230.1</td>\n",
       "      <td>37.8</td>\n",
       "      <td>69.2</td>\n",
       "      <td>22.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>44.5</td>\n",
       "      <td>39.3</td>\n",
       "      <td>45.1</td>\n",
       "      <td>10.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>17.2</td>\n",
       "      <td>45.9</td>\n",
       "      <td>69.3</td>\n",
       "      <td>9.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>151.5</td>\n",
       "      <td>41.3</td>\n",
       "      <td>58.5</td>\n",
       "      <td>18.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>180.8</td>\n",
       "      <td>10.8</td>\n",
       "      <td>58.4</td>\n",
       "      <td>12.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      TV  radio  newspaper  sales\n",
       "1  230.1   37.8       69.2   22.1\n",
       "2   44.5   39.3       45.1   10.4\n",
       "3   17.2   45.9       69.3    9.3\n",
       "4  151.5   41.3       58.5   18.5\n",
       "5  180.8   10.8       58.4   12.9"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# read data into a DataFrame\n",
    "\n",
    "path_data = 'http://www.millerjw.com/dom/mgmt462/pfiles/'\n",
    "\n",
    "data = pd.read_csv(path_data + 'Advertising.csv', index_col=0)\n",
    "data.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(200, 4)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# shape of the DataFrame\n",
    "data.shape\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.PairGrid at 0x1a21a4c780>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1058.4x504 with 3 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# visualize the relationship between the features and the response using scatterplots\n",
    "sns.pairplot(data, x_vars=['TV','radio','newspaper'], y_vars='sales', height=7, aspect=0.7)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "4. Questions About the Advertising Data\n",
    "\n",
    "•\tLet's pretend you work for the company that manufactures and markets this widget\n",
    "\n",
    "•\tThe company might ask you the following: On the basis of this data, how should we spend our advertising money in the future?\n",
    "\n",
    "\n",
    "•\tThis general question might lead you to more specific questions:\n",
    "1.\tIs there a relationship between ads and sales?\n",
    "2.\tHow strong is that relationship?\n",
    "3.\tWhich ad types contribute to sales?\n",
    "4.\tWhat is the effect of each ad type of sales?\n",
    "5.\tGiven ad spending in a particular market, can sales be predicted?\n",
    "\n",
    "\n",
    "We will explore these questions below.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "5. Simple Linear Regression\n",
    "•\tSimple linear regression is an approach for predicting a quantitative response using a single feature (or \"predictor\" or \"input variable\")\n",
    "•\tIt takes the following form:\n",
    "•\ty=β0+β1x\n",
    "•\t\n",
    "\n",
    "\n",
    "What does each term represent?\n",
    "•\ty\n",
    "•  is the response \n",
    "\n",
    "•  x\n",
    "•  is the feature \n",
    "\n",
    "•  β0\n",
    "•  is the intercept \n",
    "\n",
    "•  β1\n",
    "•  is the coefficient for x\n",
    "\n",
    "•  β0\n",
    "and β1\n",
    "•\tare called the model coefficients\n",
    "\n",
    "To create your model, you must \"learn\" the values of these coefficients. Once we've learned these coefficients, we can use the model to predict Sales.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "6. Estimating (\"Learning\") Model Coefficients\n",
    "\n",
    "•\tCoefficients are estimated using the least squares criterion\n",
    "o\tIn other words, we find the line (mathematically) which minimizes the sum of squared residuals (or \"sum of squared errors\"):\n",
    " \n",
    "What elements are present in the diagram?\n",
    "•\tThe black dots are the observed values of x and y\n",
    "•\tThe blue line is our least squares line\n",
    "•\tThe red lines are the residuals, which are the distances between the observed values and the least squares line\n",
    "\n",
    "How do the model coefficients relate to the least squares line?\n",
    "•\tβ0 is the intercept (the value of y when x=0) \n",
    "•  β1 is the slope (the change in y divided by change in x)\n",
    "Here is a graphical depiction of those calculations:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Intercept    2.921100\n",
       "TV           0.045755\n",
       "radio        0.187994\n",
       "dtype: float64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "### STATSMODELS ###\n",
    "\n",
    "# create a fitted model\n",
    "lm1 = smf.ols(formula='sales ~ TV + radio', data=data).fit()\n",
    "\n",
    "\n",
    "# print the coefficients\n",
    "lm1.params\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.9210999124051362\n",
      "[0.04575482 0.18799423]\n"
     ]
    }
   ],
   "source": [
    "### SCIKIT-LEARN ###\n",
    "\n",
    "# create X and y\n",
    "feature_cols = ['TV','radio']\n",
    "X = data[feature_cols]\n",
    "y = data.sales\n",
    "\n",
    "# instantiate and fit\n",
    "lm2 = LinearRegression()\n",
    "lm2.fit(X, y)\n",
    "\n",
    "# print the coefficients\n",
    "print(lm2.intercept_)\n",
    "print(lm2.coef_)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "7. Interpreting Model Coefficients\n",
    "Interpreting the TV coefficient (β1)\n",
    "\n",
    "Let's do this again using just the feature or X variable TV.  We will ignore radio.\n",
    "\n",
    "•\tA \"unit\" increase in TV ad spending is associated with a 0.047537 \"unit\" increase in Sales\n",
    "\n",
    "•\tOr more clearly: An additional $1,000 spent on TV ads is associated with an increase in sales of 47.537 widgets\n",
    "\n",
    "•\tNote here that the coefficients represent associations, not causations\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7.032593549127693\n",
      "[0.04753664]\n"
     ]
    }
   ],
   "source": [
    "### SCIKIT-LEARN ###\n",
    "\n",
    "# create X and y\n",
    "feature_cols = ['TV']\n",
    "X = data[feature_cols]\n",
    "y = data.sales\n",
    "\n",
    "# instantiate and fit\n",
    "lm3 = LinearRegression()\n",
    "lm3.fit(X, y)\n",
    "\n",
    "# print the coefficients\n",
    "print(lm3.intercept_)\n",
    "print(lm3.coef_)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "8. Using the Model for Prediction\n",
    "\n",
    "Let's say that there was a new market where the TV advertising spend was $50,000. \n",
    "\n",
    "What would we predict for the Sales in that market?\n",
    "y=β0+β1x\n",
    "y=7.032594+0.047537×50\n",
    "\n",
    "We would use 50 instead of 50,000 because the original data consists of examples that are divided by 1000\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9.409444"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#8a.  Manual Prediction\n",
    "7.032594 + 0.047537*50"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   TV\n",
      "0  50\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0    9.409426\n",
       "dtype: float64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#8b. Statsmodels Prediction\n",
    "### STATSMODELS ###\n",
    "lm9 = smf.ols(formula='sales ~ TV', data=data).fit()\n",
    "# you have to create a DataFrame since the Statsmodels formula interface expects it\n",
    "X_TVSpending = pd.DataFrame({'TV': [50]})\n",
    "print (X_TVSpending)\n",
    "\n",
    "# predict for a new observation\n",
    "lm9.predict(X_TVSpending)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.PairGrid at 0x1a227755f8>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABBAAAAHsCAYAAABrDV41AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nOzdeXwb530n/s/gIsADPERCJ3XQlkRbseNDcuzYoSUlzaY5lKZNWmfrpGcsZ7uNt92+2m43sWv12CTdtj+3203kXG3Txkq3bmM5h5MmkizbsSLJZyyLsmTqoCiS4AESN2Yw8/z+gEgRFEBcM5gDn3dfebEGIXAGxHzn4fd5nu9XEkKAiIiIiIiIiGgpLrMPgIiIiIiIiIisjwkEIiIiIiIiIiqJCQQiIiIiIiIiKokJBCIiIiIiIiIqiQkEIiIiIiIiIirJY/YBlOM973mPeOqpp8w+DCIio0j1+CGMpUTkcHWJpQDjKRE5XtF4aosVCJOTk2YfAhGR7TGWEhHpg/GUiBqVLRIIRERERERERGQuJhCIiIiIiIiIqCQmEIiIiIiIiIioJCYQiIiIiIiIiKgkJhCIiIiIiIiIqCQmEIiIiIiIiIioJCYQiIiIiIiIiKgkJhCIiIiIiIiIqCQmEIiIiIiIiIioJCYQiIiIiIiIiKgkJhCIiIiIiIiIqCQmEIiIiIiIiIioJCYQiIiIiIiIiKgkJhCIiIiIiIiIqCQmEIiIiIiIiIioJCYQiIiIiIiIiKgkJhCIiIiIiIiIqCQmEIiIiIiIiIioJCYQiIiIiIiIiKgkj9kHQERkhkODYew9PIThSBK9nc3YPdCH7f0hsw+LiKhhMA6TVfCzSFQ+rkAgooZzaDCMB/efQDiWRkfAi3AsjQf3n8ChwbDZh0ZE1BAYh8kq+FkkqgwTCETUcPYeHoLXLaHZ54Ek5b563RL2Hh4y+9CIiBoC4zBZBT+LRJVhAoGIGs5wJImA1533WMDrxsVI0qQjIiJqLIzDZBX8LBJVhgkEImo4vZ3NSClq3mMpRcWazmaTjoiIqLEwDpNV8LNIVBkmEIio4ewe6IOiCiTlLITIfVVUgd0DfWYfGhFRQ2AcJqvgZ5GoMkwgEFHD2d4fwp5dWxBq82M2pSDU5seeXVtYcZmIqE4Yh8kq+FkkqgzbOBJRQ9reH+LggIjIRIzDZBX8LBKVjysQiIiIiIiIiKgkJhCIiIiIiIiIqCQmEIiIiIiIiIioJCYQiIiIiIiIiKgkFlEkIlrCocEw9h4ewnAkid7OZuwe6GOhJSKyNcY1IqoW4wdxBQIRURGHBsN4cP8JhGNpdAS8CMfSeHD/CRwaDJt9aEREVWFcI6JqMX4QwAQCEVFRew8PweuW0OzzQJJyX71uCXsPD5l9aEREVWFcI6JqMX4QwAQCEVFRw5EkAl533mMBrxsXI0mTjoiIqDaMa0RULcYPAphAICIqqrezGSlFzXsspahY09ls0hEREdWGcY2IqsX4QQATCERERe0e6IOiCiTlLITIfVVUgd0DfWYfGhFRVRjXiKhajB8EMIFARFTU9v4Q9uzaglCbH7MpBaE2P/bs2sJqw0RkW4xrRFQtxg8C2MaRiGhJ2/tDvDESkaMwrhFRtRg/iCsQiIiIiIiIiKgkJhCIiIiIiIiIqCQmEIiIiIiIiIioJNZAICJa4NBgGHsPD2E4kkRvZzN2D/Rxrx8R2RZjGhEVwthA1eIKBCKiyw4NhvHg/hMIx9LoCHgRjqXx4P4TODQYNvvQiIgqxphGRIUwNlAtuAKBiOrOyKx3La+99/AQvG4Jzb5caGz2eZCUs9h7eGj++8zUE5FdzMU0VRM4O5mArGpwSxI+99TgVfHLrNlIzoIWxvfFGvT6PVjt97nUeIefMyqFKxCIqK6MzHrX+trDkSQCXnfeYwGvG6fDMWbqich2hiNJZFUNl2bSyGoCbpcETQi8EY7nxS+zZiM5C1oY3xdr0Ov3YMXfZ7HxzsVI0qQjIjthAoGI6mph1luScl+9bml+lt/M1+7tbEZKUfMeSykq5Kxm2DETERmlt7MZ49EMJAlwSRLm/m9x/DIyLi/FrJ9rdXxfrEGv34MVf5/FxjtrOptNOiKyEyYQiKiujMx61/rauwf6oKgCSTkLIXJfFVXA65aYqSci29k90AdF0yCEgBACmiagQWB5W1Ne/DJrNpKzoIXxfbEGvX4PVvx9Fhvv7B7oM+2YyD6YQCCiujIy613ra2/vD2HPri0Itfkxm1IQavNjz64t2LQ8yEw9EdnO9v4QNva0wuWSoAoBj1vCqvYAPG5XXvwyazaSs6CF8X2xBr1+D1b8fRYb77D+AZWDCQQiqisjs956vPb2/hAeu+92PPMHO/HYfbdje3+ImXoisq0//NnrEGrzY21XMzZ0t8Djlq6KX2bFOMbWwvi+WINevwer/j4LjXeIymFYAkGSpF5Jkg5KknRSkqQTkiQ9cPnxP5YkaUSSpJcv/++9Rh0DEVmPkVlvo16bmXoisqty4pdZMY6xtTC+L9ag1++Bv09yGkkIYcwLS9JKACuFEC9KktQG4AUAPwfgFwHEhRD/u9zX2rp1qzh+/Lghx0lEZAFSPX4IYykROVxdYinAeEpEjlc0nnqM+olCiFEAo5f//5gkSScBrDbq5xERERERERGRcepSA0GSpPUAbgbwk8sP/VdJkl6VJOmrkiR1Fvk390mSdFySpOMTExP1OEwiIsdhLCUi0gfjKRFRHRIIkiS1AngcwH8TQkQBfAHANQBuQm6Fwl8W+ndCiEeFEFuFEFt7enqMPkwiIkdiLCUi0gfjKRGRgVsYAECSJC9yyYN/FkL8GwAIIcYXfP9LAL5t5DEQUfUODYax9/AQhiNJ9HY2Y/dAH4v+EBGRbnifyeH7QER2YWQXBgnAVwCcFEL81YLHVy542ocAvGbUMRBR9Q4NhvHg/hMIx9LoCHgRjqXx4P4TODQYNvvQiIjIAXifyeH7QER2YuQWhjsBfAzAzkUtGz8vSdJPJUl6FcAOAL9j4DEQUZX2Hh6C1y2h2eeBJOW+et0S9h4eMvvQiIjIAXifyeH7QER2YmQXhmdRuP3Dd436mUSkn+FIEh0Bb95jAa8bFyNJk46IiIichPeZHL4PRGQndenCQET209vZjJSi5j2WUlSs6Ww26YiIiMhJeJ/J4ftARHbCBAIRFbR7oA+KKpCUsxAi91VRBXYP9Jl9aIY4NBjGRx89grs+dwAfffQI954SkaU4MUY12n2mGL4PtJATr3VyFiYQiKig7f0h7Nm1BaE2P2ZTCkJtfuzZtcWRVaFZwIqIrMypMaqR7jNL4ftAc5x6rZOzGNrGkYjsbXt/qCEGMAsLWAFAs8+DpJzF3sNDDXH+RGRtTo5RjXKfKYXvAwHOvtbJOZhAICLb0qtvNgtYEZGV6Rmj9IqbRKSfuevy6Llp+D0udLc2IXj5mud4hKyGWxiIyJb0XObHAlZEZGV6xSgujyaynoXXZZNbgqxquDSbQjSlAOB4hKyHCQQisiU9+2azgBURWZleMUrPuElE+lh4XYaCfkiQAACT8QzHI2RJTCAQkS0NR5IIeN15j1W7zI8FrIjIyvSKUXrGTSLSx8Lrss3vxaoOP7wuCemsxvEIWRJrIBCRLfV2NiMcS88XGgJqW+bHAlZEZGV6xCi94yYR1W7xddnm98LtkhBq8+Ox+243+eiIrsYVCERkS9x2QERUGcZNIuvhdUl2wxUIRA3K7pW4t/eHsAe5vYMXI0msMfEc7P5eEpExrBYbrBQ3C7Ha+0X2Z4fPlNWvS6qcHT53tZCEEGYfQ0lbt24Vx48fN/swiBxjruKv1y0h4HUjpahQVMF9dlXQ6b2UjDzGOYylRPXDOFsZO8VSgPHUDngNkhkc9LkrGk+5hYHIQQ4NhvHRR4/grs8dwEcfPVK0NRcrceuH7yURFcLYUJnPPTWIcDSNC9NJnJ1MQNUE3y+qSSNcg+WO+6h+GuFzxwQCkUNU0t+blbj1w/eSiAphbCjfocEw3gjHoQkBt0tCVhO4NJNGVtX4flHVnH4NVjLuo/px+ucOYAKByDEqyXj2djYjpah5j7ESd3X4XhJRIYwN5Zu7f839n0uSIEnAeDTD94uq5vRrsBFmuu3I6Z87gAkEIseoJOPJir/64XtJRIUwNpRvOJLE8rYmaBDQNAEhcv9TNI3vF1XN6ddgI8x025HTP3cAEwhEjlFJxnN7fwh7dm1BqM2P2ZSCUJvfjsVdLIHvJREVwthQvt7OZnjcLqxqD8DjlqAKAZdLwsaeVr5fVDWnX4ONMNNtR07/3AHswkDkGA6q+tqI2IWBiBqWjvcvdmGghsFxHxmMXRiInK4RMp5EROQ8vH8RVY7XDZnFY/YBEJF+tveHeOMgIiLb4f2LqHK8bsgMTCAQUV0cGgxj7+EhDEeS6O1sxu6BPt70iIgMwHhLeuFniYgW4xYGIjIcexUTEdUH4y3phZ8lIiqECQQiMhx7FRMR1QfjLemFnyUiKoQJBCIyHHsVExHVB+Mt6YWfJSIqhAkEIjIcexUTEdUH4y3phZ8lIiqECQQiMtzugT4oqkBSzkKI3FdFFdg90Gf2oREROQrjLemFnyUiKoQJBCIyHHsVFyaEwExSNvswiMhBGG9JL/wsEVEhbONIRHXBXsX5NE1gPJZGVhXoaPaZfThE5CCMt6QXfpaIaDEmEIiI6iyrahidTUNRNXjdXAhGRERERPbABAJRAzg0GMbew0MYjiTR29mM3QN9RWcUKnkuVS6tqBiPpqFqwuxDISIH0zOW875AgHM+B045DyKzcOqLyOEODYbx4P4TCMfS6Ah4EY6l8eD+Ezg0GK7puVS5RCaL0VkmD4jIWHrGct4XCHDO58Ap50FkJiYQiBxu7+EheN0Smn0eSFLuq9ctYe/hoZqeS5WZScoYj6YhBJMHRGQsPWM57wsEOOdz4JTzIDITtzAQ2Vg5y/CGI0l0BLx5jwW8blyMJK96vUqeS+URQmAyLiOWVsw+FCJqEHrG8lpfi8vFncEp4wOrnAevC7IzrkAgsqlyl+H1djYjpah5j6UUFWs6m696zUqeS6VpmsBYNM3kARHVlZ6xvJbX4nJx53DK+MAK58HrguyOCQQimyp3Gd7ugT4oqkBSzkKI3FdFFdg90HfVa+4e6MNsSsHpcAyDY1GcDscwm1IKPpeWpqgaRmZSSMlq6ScTEemokrg/59BgGB999Aju+twBfPTRI/N/zFTzWnO4XNw5avkcFFLs82Y0vc+jGrwuyOoUVVvy+9zCQGRT5S7D294fwh7kblgXI0msKbFUTgIAkVt6DyHl/rvO7L60j50WiGiOGfGs0rg/NyPqdUt5M6J7qnithayyXJxqV8vnYLFSnzcj6Xke1XLCdWH3cRoVpmkCkaSMeCaLdctaij6PCQQim+rtbEY4lkaz78plXGwZ3vb+UFmBfe/hIQQDXqxoD8w/lpSz2Ht4qG43BjMHFnpIZLIIxzIslkhEpv+hVO7PWDgjCgDNPk9e7K/ktRaq5D5F1lft52CxUp83o+l1HtWy+3Vh93EaFRZNK4gkZKiagEtaevqQWxiIbMqIZXjDkSQCXnfeY+VkxfVcimjnpX2zSYWdFohoXql4ZtYy7sWqjf2lWGG5OFmPUZ83u7DLdVEsPtl5nEZXS8kqLkaSmIxlyl45ywQCkU1t7w9hz64tCLX5MZtSEGrzY8+uLTVlf6spLqR3MSC7DiwmYhlMJTJmHwYRWchS8cxKhdSMKixnxH2K7M8KhQzNZIfrYqn4ZNdxGuVTVA3j0TRGZ1OQs0vXPFiMWxiIbEzvZXi7B/rw4P4TSMpZBLxupBS1ZFZc76WIdlvap2kC4VgGSTlr9qEQkcUsFc/MXsa9UDWxv1xmLxcn6zHy82YXVr8ulopPdhunUb65OgfRdLbqFbNcgUBE86rJiuudibbL0j4AyKoaLs2mmDwgooKWimdWmsWzw4woOQc/b9a3VHyy0ziN8kXTCoYjScymlJq223IFAhHlqTQrrncm2goVksuRVlSEoxlktcqWfRFR41gqnvUettYsntVnRMlZ+HmztqXGdnYZp9EVKVnFVCJT8VaFYphAIKKaVLoUsZzWP1YfWOjZaSFbotcuEdlbsXi2MHZmVQ3jsQwUVcDnduHQYNjSMZCoGLb3c4ZSYzurj9MoR1E1TCdkJDL6rpRlAoGIarrhV5KJdkLrn9mkoluxxOmEjD/59ut44r/epcvrEZF9zMXOz37vJM5NpeB1ubCmww9Z1QyPi/wjj4xQz3s8P8PG4ioDe9M0gZmUUvNWhWKYQCBqcHrc8MvNRFupaFg1JmIZxNKKLq/104uz2PPt1zGVkHV5PSKyn+39Iew9PIT1mshbKmxkXHRCIpesqV73eH6G64OrDOwpnsliOi4busWWRRSJGlw9+/laqWhYJTRNYGw2rUvyQAiBx1+8iN/9f69gKiGjxecu/Y+IyLHqHRfZw52MUq/PMj/DRFfLZFVcmkkhHE0bXp+LCQSiBlfPwasdez/r2WkhJav40++cxN8dfBOqJrChuwVf+vhWHY6SiOyq3nHRrolcsr56fZb5GSa6QtMEJuMZjERSSC+6/ozCLQxEDa6WLgqV7kG0W+9nPTstXJhO4qH9J3B+KjfAeWd/CL/77k0I+r01vzYR2dOhwTAiiQzOTSXgdbmwPNgEj9tlaFxkD3cyipH3+IXjjWhKgapp6G71z3+fn2FqRNG0gkhChqrpX+dgKUwgEDW4am/41exBtFNRnqU6LRwdmsa+Y8MYjaawMhjAPdt6cVtfV9HXeub0JD731CCSsgq3S8Jvbb8GH7xpFSRJMvIUiBzDiQXTFsbQNR0BjMcyuDiTxqZQKz7zvn7Dzs9uiVyyD6Pu8YvHG1lVQziWqx+0rKXJkM+wE2MOOYfebRkrxQQCUYOr9oZfbbEkOxTlWarTwtGhaTxy4DQ8LglBvwdTiQweOXAaD2DjVUkEVRP4yrNnse/YMABgWasPD73/erxldbvh50DkFE4tmLY4hgYDPiTlLDqafYael50SueWSsxom4xms6giYfSgNz4h7/OJrpactt/IgkVHhcSm6f4adGnPI/uRsri2jHttqa8EEAhFVdcMfjiTREchffm/3PYhCCEwlZERTxYsl7js2DI9Lmt9/OTeDt+/YcF4CIZKU8SffPomXh2cAAG9d047PvP96dLX4jD0JIoexe/eWYsyMoXZI5JZDCIHZlIJI0phWZWQNha6V7tYmzKYUPPMHO3X/eU6NOWRfqiYQScqIpbOWiHVMIBBZiJ2WzDltH62mCYRjmZJZ3dFoCkF/fuj0e10Yi6bm//vEpVk8/OTrmIznllj+0tY1+M139MHt4pYFoko5MVkJOCeGmnXfymRVTMTMW8JL9VPva8XKMcdO40Sq3VySdCapQLNA4mAOuzAQWcTckrlwLJ23ZO7QYNjsQyto90AfFFUgKeeyoUk5a9t9tIqqYWSmvE4LK4MBpJX8AWta0bAiGIAQAv/+0gh+55uvYDIuI+B146EPXI/dd1/D5AFRlezYvaUcToihZty3hBCYTsi4NJNm8qBB1PtasWrMsds4kWoTz2RxMZLCdEK2VPIAYAKByDLs1td4e38Ie3ZtQajNj9mUglCbH3t2bbFdJjyt5PrmKmp5A9F7tvUiqwmkFBUCua9ZTeDnb16N//W9QfztgTPIagLruprxhV++BXdv6jH4DIiczQl/aBfihBha7/tWJqtiZCaFmaRsiWW8VB/1vlasGnPsNk6k6qSVXJwLR9Nlj03rjVsYiCzCykvmirH7Ptp4JouJIp0WirmtrwsPYCP2HRvGWDSFFcEA3nVdCH///DkMTSYAADs29+D33r0ZAZ976RcjopKcWPRvjt1jaL3uW0IIzCQVzKRY66BR1fNasWrMseM4kcqnqLkCiYmMuQUSy8EEApFFOGU/rF3MJGVMJ+Sq/u1tfV3zBROfOzOJzz41iEQm16Jx90AffuGW1WzRSKQju/+h7VT1uG/JWQ0T8Qwyi5aUExnJijGH40Rn0i4XSIxapEBiObiFgcgirLpkzmmEEJiIZapOHsyZa9H4mSdOIJFR0dXiw1995K348K1rmDwgooZg9H1rNqlgZCbF5AEROE50omhawXAkiVmbra7iCgQii7Dqkjkn0TSB8VgaKbm2wehsUsGffud1vHAh16LxhtXtePD912FZa5Meh0lEZAtG3bcUVcNELIM0EwdE8zhOdI60omIqIds2OcoEApGFWHHJnFNkVQ3femkE/3TkAkajKawMBnDPtt75rQjlOjkaxcNPvo5wLAMA+PCtq3HfO/rgcXNBF1E9sI2Zteh935pNKZhOsEgiUSELr7e5WPjpJ15jLLSJ7OU6B3Eb1DlYChMIRBbktAGy2eeTyap44qUR/PUPT8PjkhD0ezCVyOCRA6fxADaWlUQQQuDbr47i/xw8A0UV8LldWNnuxzOnJ3FmPFFVMoKIiisUNwDgwf0n4HVLeW3M9gB1iSlmxzIjmX1ujbbq4G9++Aa+/OxZJGQVLT43fvOuDfjUuzblPcfs3wlZ11xLR7NiIVVG0wRmUorttioUwykzIotxWp9fs88nKWcxOpPGN34yDI9LQsDrhoTcV49Lwr5jwyVfI6Oo+Pz3T+Gvf3gaiirQ09qEYMADTYi8ZMTRoek6nBGR8xWLG597atC0NmZmxzIjmX1u0bSCkUiqoZIHjxw4g5SiwuPKFcJ75MAZ/M0P35h/jtm/E7I2tnS0j1hawcWIs9rPMoFAZDFOuymYeT6zKQVjs2loQmA0moLfmx/y/F4XxqKpJV/j0kwKv/3Yy/j+iXEAwMDGbqwI+hHwuqtKRhBRacXixtBkAgFvfnvUerUxc1psXsisc8uqGsZm05iMZaA5ZGBdji8/exYuCfC4XHBJrstfc4/PcfLnjWo3HEmaFgupPHJWw6WZFCZiGWQ1zezD0RUTCEQW47SbglnnMxXPYCqemf/vlcEA0kp+AE8rGlYEA0Vf48jQFO7/pxdxZiIOlwTcN9CHhz5wPcLxdFXJCCIqT7G4AeRmaxeqVxszp8Xmhcw4t3gmi5GZFJKyvfcCVyMhq3AtatbjknKPz3Hy541q19vZbFospKUJITCdkDEy49xVVUwgEFmM024K9T4fIQTGo2nMppS8x+/Z1ousJpBSVAjkvmY1gXu29V71Gqom8PfPncMf/ftriGey6Ah48RcfvhH3bOuFJElVJSOIqHzF4saGZc2mtTFzWmxeqJ7npmoC4Wga4WgaqtY4qw4WavG5sfjUNZF7fI6TP29UO7Z0tKa0ojpuu0IhTCAQWYzTbgr1PB9VE7g0m0aiQHXb2/q68MDOjVjW0oRYOotlLU14YOfVBRRnUwr+57//FP945DwA4PqVQez92K24eW3n/HMqSUYQUeWKxY0//NnrsGfXFoTa/JhNKQi1+bFn15a6FA1zWmxeqF7nlpSzGImkbF+BvFa/edcGaALIaho0oV3+mnt8jpM/b1S77f0h02IhXU3OahiPpnFpJgVFddZ2hUIkO2RHtm7dKo4fP272YRDVzVzlZaf0+a3H+cwF71oC9xvjMTy0/wTGo7mtDx+6eTXuv7sP3gItGo8OTWPfsWGMRVNYUWVLyIDPje7WJnjdixezGoOxlOzEinHQisekFyPPTdMEphIyYmml9JNr0NfTWpdYCtQeTyvpwuDEzxuRE6iaQCQpI5bOOmrFgUuSsL67pWg8ZQKBiGwvJasYj6ZrKsL13Z+O4pEf5bos+D0u/O67N+Fd1y3X8SivkCQJXS0+tAe88w8Z8oMWYSwlonpLKyomYpm6zMrZKYFARPYlhMBsSsFMUnFkAdhSCQRPPQ+GiKiYavtdf/fVS3j0mbMYnU1hZRUrAeSshr85cBrf/ekYAGB1RwAP77oefT2tVZ/LUpq8bvS0NsHn4Q4yomqUihXVxhLS11whscX1aMh6KrlmeH1Ro4ulFUQSiuM6K1SCI1giMl21/a73vzyCP/nOSUzFMwj6PZhKZPDIgdM4OjRd1s8dm03jU/temk8evP2aZfjCvbcYkjyYW3WwuiPA5AFRlUrFimpjCelrrpAYkwfWV8k1w+uLGllSzuJiJOnItoyV4goEIlpSPWYbFva7BoBmnwdJOYu9h4cK/ixNEwjHMvjqs+fgcUnzra4CXjdSiop9x4ZLrkI4dm4af/adk4ims3BJwK/fuQH33NYLl6T/Clifx4WetiY0edyln0xERZWKFZXGkmI4y1odIQRmkgpmUoqj9gM7WSXXjF7XVz3xWqZaZbIqphMyUrIzWzJWw7BpMEmSeiVJOihJ0klJkk5IkvTA5ce7JEn6D0mSTl/+2lnqtYjIHPWabaik33VW1XBpNtc7fDSagt+bH8b8XhfGoqmiP0sTAl9//jz+8PGfIprOoj3gxed/4Ub857et1T15IEkSOptzqw6YPCCqXalYUUksKYazrNWRsxpGZlKIOLx9mdNUcs3ocX3VE69lqkVW1RCOpTESSTF5sIiR62izAP67EOI6ALcD+C1Jkq4H8IcAfiSE2AjgR5f/m4gsaOFsgyTlvnrdEvYeHtL155Tb7zqTVXFpJg05m1s6tjIYQFrJX0aWVjSsCAYK/pxYWsGnv/UavvbjcxAA+le0Ye+9t+CWdfrnMb1uF1a2+9HZ4oNkwKoGokZUKlaUG0uWUq+45ySzSQUjM6n52Ez2Uck1o8f1VU+8lqkampar3zIcSSGebuyWs8UYlkAQQowKIV68/P/HAJwEsBrABwH8w+Wn/QOAnzPqGIioNvWabSin33VSzmJ0Jp237+yebb3IagIpRYVA7mtWE7hnW+9VP+NMOI77/+lFHLlcH2HXW1fh//ulmxAK+nU9FwAIBrxY0xmA38tVB0R6KhUryoklpdhtltVMiqrh0kwKU4kMVx3YVCXXjB7XVz3xWqZKRdMKhiNJzHAl1ZLqUgNBkqT1AG4G8BMAy4UQo0AuySBJUsGNSJIk3QfgPgBYu3ZtPQ6TiBbp7WxGOJae3+8IGDPbsL0/hD1A0X7X33nlEr70zFmMRvM7LdzW14UHsBH7jg1jLJrCihbSHJIAACAASURBVCJdGH5wYgx/9cPTkLMafB4XfvddG/HuLSt0PQcA8LhytQ4CPuskDhhLyQ7K3adcKlaU+n456hX37C6aVjAdlx3ZwqyYesfTeuzfr+Sa0eP6qidey1SulKxiKpHhKqoySUZnVyRJagXwNIA/E0L8myRJM0KIjgXfjwghllw/zF67ROaY2z/odUvzBQoVVWDPri11GzDsf2kE/+upQXhcEvxeF9KKhqwm8MDOjSULJcpZDX936AyefGUUALCy3Y+Hd23BtSH9uyy0+j3obmmCy1XVdoW67HFgLCUrskKcsfLxWE1W1TAZl5GUrbO0V9UEvvfaKD71zk112y9mdDzl57B2fA+pFEXVMJ2QkchYJ55ZgUuSsL67pWg8NXQFgiRJXgCPA/hnIcS/XX54XJKklZdXH6wEwEomRBZVzmyDUTMk850Wnquu00I4msYfP/k6BsdiAIDb+7rwP362H21+b83HtpDbJaG7tQktTWxqQ1QNsyu7F4phe3Ztsc0saz3FM1lMxTNQNWusOhBC4Oi5aXzx6SGcn0riU+/cZPYh6cbs68IJ7LZiwu7s1PFC0wQiSRnRdJZbFapg2IhXylUN+wqAk0KIv1rwrf0AfgXAZy9/fcKoYyAyg50CaCmlzmVhdn9hheM9QE3nnFU1jEVzxRJHoykE/fmhqlSnhRfPR/An3zmJ2ZQCCcCv3rkev2xAl4Vmnwc9bU1wV7fqgIiQ26fcEchP7NVrn3LRGLZrCx677/b5GPjpJ15D72F7xnM97kmqJjAVzyBuoVm6N8NxfPHpN/HChRkAdVrGZbCFv6uJWAYrgk153+f+/cpt7w/pcs06aWxnBKPGg0aIphVEErJlEqF2ZGQXhjsBfAzATkmSXr78v/cilzj4GUmSTgP4mcv/TeQITmoZVM65GFHhuJZOC5oQ+MZPLuD3H38VsykFQb8Hn/2FG/Cx29fpmjxwSRK625qwot3P5AFRjcys7L5UDHNCPNfjHJJyFiORlGWSB5PxDP7i+6dw39dfmE8e3LK2A3s/dqvJR1abxb8rCcDITBrRlDL/HO7fN4cTYoHR7NDxIiWruBhJYjJmnVVUdmVkF4ZnhRCSEOJGIcRNl//3XSHElBDinUKIjZe/Tht1DET1ZocAWq5yzkXvCseJTPWdFuKZLB564gS+/OxZaALYtLwVX7z3Vmxbv3SdhEr5vW6s7gwgqPNWCKJGZWZl96VimBPieS3noGkCE7EMxmbzY7JZUrKKv3/uHD7+laP43mtjEADWdTXjzz/0FvzFh280pLZNPS3+Xa1oz3UIGo+lbdHxwMmcEAuMZuWOF3JWw3g0jdFZtprVCzftEunIzKW4eivnXPSscDybVDCVyFz1eDmdFoYm4nho/+sYmclta3jvDSvwqZ0b4fPolyOVJAldzT60NzNxQKQnM/cpLxXDnBDPqz2HlKxiMp6Bopo/2FY1gadeG8PXfnwO0wkZANDZ7MWvvH093nfDSsesAlv8u2rze7G6Q2AsmsFsSuH+fRM5IRYYzYodL1RNYIZ1DgzBBAKRjqwYQKtxaDCMaErB6GwKfo8bPW1NaPN7rzqX3QN9eHD/CSTlbF6F40pmSIQQmIzLiKWVos+Za9lYyI9OjuMvf/AG0lkNXreEB965Ee+9YWX5J1sGn8eFUJtf14QEEV2h1z7lSi0Vw/YeHsK5qTiiqSxkVYPP7UIw4MH6ZfaZ6a70nqRpAtNJOW/ZvJmOnZvG3qeHMDSZAJCLxR+5dQ3u2dbruMK1hX5XHrcLt6ztxGP33W7ikZHVxnZWrMegx3hQL0IIzKYUzCSVhmozW08cDRPpyMyluHqZ2+vX7HPDJUmQVQ0jkRQm4+mrzmV7fwh7dm1BqM2P2ZSCUJu/ovZImiYwHs0smTwoRlE1/M2PTuPPvjuIdFbDiqAff/vRm3VNHkiShM5mH1Z3BJg8IHKgpWLYHX1dCMdkyKoGlwTIqoZwTMYdJdrHWkkl96SknMXITMoSyYOzkwn8weOv4g8e/+l88uBnrl+Of/y1bfiNuzY4LnkAOGP84FRW+t1YtR5DreNBvcTSCoanU5hOyEweGMh5EZjIRE5oGTS316894EeTx43JeAaZrIZERsXf3HPjVedS7czhwk4LlZqIZbDn26/jxKUoAOC29Z34H++9Du0B/bYXeN0u9LQ1wb9oTx8ROUuxGPb80DR6Wn2Ipa+sQGjze/D80DQ+ZcJxVqOce5KVOixMJ2R87blz+N5ro5ircXZTbzvuv/sabFreZu7BGcwJ4wenstLvxsrtPc1aSQbkEqDTCZk1DuqECQRyvHov9apXADXqvBbu9QsGvAgGvPPLwfQ6r0xWxfhspqrCXC8Pz+BPvv06IsncLNnH71iHj92+Ttd9sB3NPnQ2eyHp3PaRiOxjOJJEd2sTetr8848JIYrue7bismJg6XtSLK1gWod2ZkeHprHv2DBGoymsLFCnppS0ouL/Hb+Ix45dmO+609sZwH0DfXj7NcsaJhab+QcYLc0qv5vhSBJuKVf7aS6x2d3qs2Q9hnrExLSiIpKUkZLV0k8m3TCBQI5mp760lTDyvIze65eUswhHMxUvLRNC4JvHL+LLzwxBE0Brkwd/9N5+3N63TJfjArjqgIiuqCQW2u1eo6gaJuMZXQbdR4em8ciB0/C4JAT9HkwlMnjkwGk8gI0lkwiaEPjBiXF85bmzmIrnCiS2B7z4+B3r8IEbV8Lj5tYxooVafW6cmUjALUlwSxKyqsDITBrX9rSYfWh5jI6JiqohkpAtsXKqETEyk6M5tfWOkedl5F6/2ZSCsdl0xcmDRCaLh598HY8eziUPru1pxRfvvUXX5EFHsw9rOgNMHhARgMpioZ3uNdG0gpFISrcZu33HhuFxSQh43ZCQ++pxSdh3bHjJf/fi+Qju//qL+Pz3T2EqLsPrlnDPtl58/Tduw4duXs3kAVEB86txpAX/W/i4RRgVE7XLW64uRlJMHpiIKxDI0azQeseIJVyVnFelP9+ovX5T8Vwrqkqdm0rgoSdOYDiSa9H4n7Ysx39750Y06fSHPlcdENGcxfHyw7esxvND0yVjYT3uNbXeS1RNYDKeQULnQfdoNIWgP3846fe6MBZNFXz++akE9h4ewpGh6fnHdmzuwSfe0YcV7f6C/4aoWkaMwczcrhTLZLG6w4/JuDy/hWFFsMlyf0wbEROjaQURHbZcUe2YQCBHM7v1jlFLuMo9r2p/vp57/TRNYKLKQeuhU2F8/vunkFZyLRp/a8e1+MCNK3XLtLcHvOhq8Vkuc09E9VcoXv7riyNlVRI3+l5T670kKWcxEcsYMvBeGQxgKpFBYEESNq1oWBEM5D0vkpTxDz8+j2+/emm+QOJbVgXxye3X4LqVQd2Pi8iIMZjZ25XmYk1fz5V2skk5i1CbtZJvesbEtKJiKiEjo7DOgVUwgUCOZnZfWqOq5ZZ7XmZX682qGr710gj+6ciFsoprzRXiujSbhBASJuIZAECorQkPfeB63QaZXHVAZD1zs3pvjEehqAI+jwsbQ211m92rJV4afa+p9tg0TWAqIVfVKrdc92zrxSMHTiOlqPB7XUgrGrKawD3begEAGUXF4y+O4BtHLyB5edvEqg4/7hvowzuu7WYC1wBmzZBbrZCoEWMgs8dVZo9ry6XHcWqawHRStkRrWcrHDWbkaGb3pR2OJPNmZQB9lrWWe15G/fxyZLIq/u3Fi/jL/3gDU4lMXnGtowuWrs6ZK8QVjqURTWfnkwfX9rRi77236pY8aA94WeuAyGLmZvXOTsYRTWeRUlTMJhWcm4rXrcd5LfHS6HtNNceWVlSMzKQMTR4AwG19XXhg50Ysa2lCLJ3FspYmPLBzI7Zu6MR/vD6OX/naMXz52bNIyiqCfg9+a8c1+NqvbsPAxh4mDwwwdy2FY+m8GXKjryGzfu5SjBgDmTmuAswf15ar1uOMpRUMR5JMHphgJJLC14+cX/I5XIFAjmdm6x0jl7WWc15mbeGY67TwjZ9cKa4FYD4Lve/Y8FWrEPYdG4aqaZhKKPPLbIN+D1p8brQ3e6/6GZXiqgMi65qb1ZuKZ+GCBJdLgiYEoqksVrR76jK7V2u8NPJeU8mxCSEwnZCrqjlTrdv6uvJi+isXZ/Bb//wSTo3HAAAel4QP3bwa996+Fm3+2uM5FWfWDLnZM/OFGDEGMntrLGCdlpKlVHOc3K5gjolYBgdPhXFwcGI+bn/m/dcXfT5XIBAZyMiOBlb9+bPJK50WRqMp+L35YaZQcS0hBM5MxBCO5YrjuCRgVbsfy4NNGI+laz4mrjogsra5WT1Z1TBfZFwCZFWr2+ye2fFaj2NLKyouRlJ1TR4sNDydxGeeeA2/881X5gehd2/qwd//2jZ8cvs1TB7UgVkz5GbPzBdixDVt5ThhZ4qqIRxN49JMismDOokkZTzx8gge2PcyfunRI/ji00Pzcbu71bfkv+UKBCIDGdXRwIo/XwiByXj+XttyimulZBX/+wenEM/kbhg+twur2v3weVxIKepVhbgqwVUHRPYwN6vnc7uQVQUkCRAiFw/qNbtndryu5dhUTWAqkUE8bU4l9tmkgn88ch77X7k0v4Ls+pVtuP/ua/CW1e2mHFOjMmuG3Aoz84sZcU1bOU7YkaoJzCRlRNO5hAwZK57O4pkzkzgwGMZLFyJYWFc36Pfg7k092Nkfwlt7O5Z8HSYQiAxm9lKzevx8TRMYj6Wv6iteqrjWhekkHtp/AuencjMUAa8LXS0+eD0SUoqa99xKBQNeLGOHBSJbmCu41eb3YCohQ9MEIIBgi7eus3tmx+ulFDs2M1ubyVkN//bSCP75J+eRuJwEXtnuxyfesQF3b2KNAzOYVWTPqsX9jLimrRwn7EJc3qI2k2JbRqOlFBXPvzmFA4NhHDs3DUW98n63+Ny4a2M3dmwO4Za1HfC4c6uGXSViNxMIRAVYrZKwlSmqhrHZNBRVu+p7t/V14QFsxL5jwxiLprBiQReGw29M4PPfP4WkrMLjkvDJ7ddgVdCPbx6/eNVzK+F1u9Dd2oSAj6sOiOxi4axeVo1CvtyFYf2yVsbfIhRVw2Q8c1Xidq6bTTmdb6olhMDBUxP48jNnMRbNbTNrbfLg3tvX4uduWg2fhztkzWLWDDln5uvDCePTeCaLSEIuOG4kfchZDcfOTePAYBjPvzmFdPbKe93kceGOvmXY2R/CbRu6qorXkh2Wi2zdulUcP37c7MOgBrGwx+/CLLoVq9zWQo+bUFpRMR5NV5Q9VjWBLz8zhG8evwgAWNbqwx9/4HpsWVX7MtdWvwfdLU1wuWw361WXA2YsJSdywoC6UrNJBdNJ+aolv3PdbDwuKW/V1wM7N+qWRHhtZBZfePpNnBzN7ZV1uyR88KZV+Njt69AeMLfGQV9Pa92Cv5XiaSNeA43I7uNTFkg0lqoJvHghgoODE3jmzMT8qjAgV8j2tg1d2LE5hLdfs6zkJJtLkrC+u6VoPOUKBKJFrFhJWG8Lb0IL2y3tAco+x0Qmi3AsU9GetemEjD/9zkm8PDwDALiptx2fft/16GpZulhLKW6XhGWtTWhtYkgjaiR6xDI7UVQNE7EM0kUG4PuOld/5plIjMyl86fAQDp+enH/srmu7cd/ABlP3uTe6RrsGGpldx6dyVkMkKSORMadGi5NpQuC1kVkcHJzA029MYGZBAV2XBNzc24Gd/SHctbFb1yK2HG0TLTIcSaJj0SyK2ZWEy1XuLEStN6HZpIKpRKaiYztxaRYPP/k6JuMygFx9hN+4awPcNa4WCPjc6Gltmt+3RUSNY6lYNvd9p8zKRtMKpuMytCWStqPRFIL+/KFdoc43Ff3clIKvHzmPJ16+hOzl1Wabl7fh/u19eOuapQttkfHs+kdlvTlhlYbdxqeqJhBJyoixQKKuhBB4YzyOA4NhHDo1gYl4/nj8htVB7NgcwsCmnpon6IphAoFoEStWEi5HJbMQ1d6ECnVaKEUIgW+9fAlfOPQmsppAs8+N33/PZgxs7Cn7NQqRJAmdzV50NBsTHInI+orFstPjUcfMymZVDZNxGUm59OxdOZ1vyqWoGr718iX805HziF3u7hBqa8In3rEBO/pDJYtsUX3Y7Y9KMzhllYZdxqdCCMymFMwklSUTnlSZs5MJHBgM4+CpMC7N5Lc437S8FTs2h7B9cw+WB/2GHwsTCESLWLWScCmVzEJUcxPSNIFwLFPWIHbha/71f7yBH54MAwDWLWvGw7u2YG1XbTc7tmckIqB4LJNVgXYHzMrG0gqmK+iwUKrzTTmEEHjm9CQefWZofpDa4nPjo7etxS/cshpNjLuWYpc/Ks3klFUadhifxtIKIgkFWY0FEvUwMpPCoVNhHBicwNnJRN731i1rxs7+EHZs7qn79c4EAtEidq0kXMksRKU3oayqYSyahpwt/4ZwMZLEQ/tfnw94Ozb34Pfevbnm7gjtAS+62J6RiFA8lvk8rrxZeMBes7LFOiyUslTnm3K8fimKLzz9Jk5cigLI7aH9wI2r8CtvX2f51V4L/4BuJHb4o9JsTlmlYeXxaUpWMZXIVDROpMImYplc0uDUBE6NxfK+t7Ldjx2be7CzP4QN3S2mjYUbM9oSlWDHHr+VzEJUchPKZFWMz2YqyiY/d2YSn/3eIBKyCrdLwv139+Hnb15dU6DjqgMiWqxYLNt7eMiWs7JzS38jSaXqPcO39XVVXDBxdDaFLz9zFgdPTcw/dkffMuwe6MPaZdZ9zyRJQkuTG+0BL5o8jXlvsPIflVbhpFUaVhufylkN04nytlhRcTNJGYdPT+LAYBg/vTiLhdF/WYsPd2/uwTv7Q+hf0WaJCTQmEMgxzCyQY4XiPJXOQpS6CR0aDOP/HnoTF6YTZc9iqZrA1547i28cHQYAdLX48OD7r8ONNRbaCga86Gr22bE9IxFVqdy4WiyWWW1WttT5pBUVk3HjZ/CODk1j37FhjEZT6GltQlezD8+fnYKi5oas14Za8cm7+3Dz2k5Dj6MWbpeENr8XQb+n4QroFvscWemPymoYOY6y6ioNK4wdq6VqAtOJympiUb54JotnT0/i4KkwXjgfwcKdakG/BwObcisNbljdXnPBcb1JdqiKaaVeu2RNZvbGtVJf3rmbUa2zEIcGw/j0t16DJKHsXuIzSRl/9p2TeOFCrkXjDavb8eD7r8Oy1qaqz8frdqG7tanmbQ82UJc7A2Mp2YUecVWveKiHpc5nYFMPppMyoinjB+JHh6bxyIHTcEtAJqthKiHPD1q7W334zbs24F3XL7dsgUSv24VgwIu2Jk+xhHLdDtyMeGql8Yae6nFeVooHc8djx9+lEAIzSQWzKRZIrEZaUXFkaAo/Ggzj6Nnp+cQtADT73Ljr2m7s6O/BrWs7TU2OuiQJ67tbisZTrkAgRzCzQI6VivPoNQvxtwfOQJJQdi/xk6NRPPzk6wjHcq1kPnzratz3jr6agl+b34tlLVx1QNSI9IirVpqVLXY+//fQm+jraa1bwbHHjl6AnNUQTSvzA1cJwPKgH1/91a2W3SLW5HWjI+BFS1NjD1utNN7QUz3Oy0rxALDn7zKaVjDDAokVk7Majp2bxsFTE/jxm5NIK1feP5/HhTv6lmFHfw9u37AMPo89VlQ1diQmxzCzQI5TivMAVzotXJxJltVLXAiBJ18dxd8dPANFFfB7Xfj9/7QZ2zdXf/PzuFzobvM1bEEsInJWXAWuPh8hBDwuCRemE3UbjJ8ai+H1sWjejFe734OuFi9SimbJ5EFLkwftAa8lj80MTrsu5jj1vJZip3OOZ7KIJGQoKhMH5VI1gZcuRHDw1ASeOT2JeOZKjQiPS8LW9Z14Z38Id1yzzJbjXfsdMVEBZhbIcUpxnoWdFsrpJZ5WVDzyo9P4/olxAEBvZwAPf3AL1i9rqfoYWpo86G5tstxeLyKqL6fE1TkLz0fVBLKahpSs5sVUo4xH0/jKs2fn2+kCuaWyPa0+NHlyq8vqcRzlkiQJbf5c4sDbYPUNSnHadTHHqee1FDucc1LOYjohs7NCmTQhcGIkigODYTz9xgRmFmxLc0nAzb0d2NEfwl3XdiO4KHlkN4zM5Ai7B/qgqAJJOQshcl/rVSDHzJ+tl0xWxaWZK20a79nWi6wmkFJUCOS+Luwlfmkmhd9+7KX55MHApm584d5bqk4euCQJPW1NWB70M3lARI6IqwvtHujLbR1IyVBUFSk5P6YaIZHJ4kvPDOHjXz06nzxYEfSjqzm3PczncV0V283kdknoavFhbVczulubmDwowGnXxRynntdSrHzOaUXFpZkUxmYra9/diIQQeGM8hi8+/Sb+85d+gge++TKeeOXSfPJgy6ogfnvntfiX3XfgLz7yVrz3hpW2Tx4ALKJIDmJmgRyrFeepRFLOIhzNXFUMZ65S9+Je4keGpvDn3x1EPJOFSwLuG+jDR25dU3VbGb/XjZ624oNFO1cprgCLKJKprHid2TmuLhZNK/jeq6N47OjVMVVvqibw7VdH8Q8/Pjc/iF3W4sOv37UB775+OV44FykY283idbvQ3pwrjKhDezJHF1EEnHVdLLTwvFp8bkiShFgma5l4ZASr/S7ZkrF856YSODAYxsHBCYzM5G/vvTbUip39IezY3IPlQb9JR1ibUkUUmUAgamDRtILJy4UPS1E1ga8/fx7/eOQ8AKCz2YvPvP963NRbXYtGSZLQEfCis8VX9Dl2rVJcBSYQyDQNdJ3VXVbVMBHPICWrhv8sIQSODE1j7+EhXJjO7aP2e1y457ZefGRrb96WNCswqDCi4xMITsd4VH+qJhBJyoilc6shqLCRmRQOncolDYYmE3nfW9vVjJ39PdixOYTeLutsQ6kWuzAQUUFT8Qxmy2wbNptS8OffPYlj5yIAckuyHnz/9ehpq65Fo9ftQk9bU8nCWHasUkxkN7zOjBFNK5iOy3VpdXZ6PIYvHh7CS5fb6Lok4D1vWYFfe/v6mlrpGqHZ50FHMwsjUmGMR/UVSyuYTshQNSYOCpmIZXDojQkcHAxjcCyW970VQT929PdgZ38Ifd0teqygsg0mEIgajBC5TguJTP4StbktC6PRFFYuWNb6xngMD+0/gfFobqXCh25ejfvv7qt6f2p7wIuuFl9ZgbbSKsVWXIZNZAVLXRu1VgPndZevnqsOJmIZfPW5s/jBiXHMDf9vXdeJ++/uwzU9rYb//HJJkoTWyx0V7NKmTG/lXieNfj3ZqTuBnWWyKqbiMtKK8XHKbmaSMg6fnsTBwTBevTiLhamVZS0+3L0plzS4bmVbQyUNFmICgaiBqJrAWDSNzKIbxtGhaTxy4DQ8LglBvwdTiQweOXAabz+3DPtfvZRr0ehx4b+/ezPeeV11AxmPK7fqIOArf9apkirFC5c9dgS8CMfSeHD/CewBGmrwRbRYqWujlmrgvO7yxdIKpuqw6iApZ/HNY8P4l+MXkblc5Gz9smbcf/c1uG2DefUMFnNJEoIBL4J+DzwNXBSx3OuE15M9uhPYmaJqiCRlxNOsc7BQPJPFs6cncfBUGC+cj2Dhgoyg34OBTT3YsbkHN67pYLFvMIFAdBUrZ/9rOTY5q2E8mi7Yx3ffsWF4XNL8HtkmjwvTs2k8/tIIAGBNZwAP79qCDd3VdVlo9XvQ3dIEV4VBd/dAHx7cfwJJOZu3F7JQlWIueyQqrNS1Ucl1Vulr682q8VnVBCbjGRw8GS64kkvPn/O918bwtefOIpLMbUHrbPbi1+5cj599y0rLDGw9LhfaA160+T0Vx30nKvc6Kfa8z37vpCmfezOut1riERWnagIzSRlR1jmYl1ZUHBmawo8Gwzh6dhqKeuV9afa5cee13dixuQdb13U2dAK0ECYQyLGqufFZOftfy7GlZBXj0XTRWbHRaApBfy4cKKqGS7Pp+VmtO69Zhj/42X60VlHoyu2SsKy1qap/C+TOaw9QVpViLnskKqzUtVHJdVbpa+vJqvF5bg/x82emCq7kegAbdUkiHD2bK5B49nLxriaPCx/Zugb3bOvNm62df36RbWlG8nlyiYNWfToqOEa510mh52VVDeemUlivibp+7s263mqJR/Vg1SRmMZomMJNSEE0pdanHYnWKquHYuWkcHJzAc29OIq1cmVTzeVy4o28ZdvT34G3ru9DEOi1FMYFAjlTtjc/Ks9jVHlv08pLapTLOK4MBTCUy0DSB0Wh6funWyqAfD39wC1xVDAQDPjd6Wptqztpu7w+V9d5z2SNRYeVcG+VeZ9W8tl6sFp+zqobJ+JWWZ4tXcs3Nnu47NlzTH+5vTsSx9+khHD+fK2IrAXj3luX49Ts3FC1kW2xbml7JjMUCPjc6Ar6Ktqg1knKvk0LPG49l4HW56v65N/N6qzYeGc2qScxiZlMKZpIskKhqAi8Pz+DgYBiHT08ivqAGmMclYev6TuzYHMKd1y4rmIylq/FdIkeq9sZX79m0SrLY1RxbuZ0WfnHrGvz59wbzgqrbBbxny/KKkweSJKGr2Yf2Zm/pJ+uIyx6JCjPq2jg0GMZMUsa5qSS8bgnL23IJQ6Ouu3qvMloqRhfqsLBwJdccv9eFsWh+j/ByTcUz+Npz5/DUibH5pO5NvR345N192Li8bcl/a1QyY6G5wojBgAdNHiYOllLuNVjseWs68nvJ12N1ndNW9emxcsDMpEolx5+Us5iKywW3rDYKTQi8fimKHw2GcfiNifktX0CuS81NvR3YsTmEd2zsRjBQ3/GqEzCBQI5U7Y2vXrNp1WSxKzm2Yp0WComlFex/9VJe8qDJDQQDXjz1+jg2rwiWPeD0eVwItflNqbJt9WWPRGYx4tpYGMPWdPgxHs3g4kwKG3ta8Zn3XW/IdVfP1Q7FYvRDmsD1q4MFOyzMreQKLFj2mlY0rAgGKvrZKUXFvxwbxjePD88vr13blfud3d7XW5yaWAAAIABJREFUVdbWAL2TGQu5XRKCfi+CAa9lai5YXbnXYKHn+dwuyIv+EKzH6jonrerTa+WAWUmVco8/kcliJqVcVSi7UQghcDocx4HBMA6dmkA4lsn7/pZVQezYHML2zT3oavGZdJTOwAQCOVK1N756zWJXk8Uu99iKdVoo5Ew4jof2n8DobHr+Mb8nV7egxeepaMaqo9mHzmavqfterbrskchsel8bi2NYMOBDUs6isyW3pP6jjx7RfY9wPVcZFYrRsbSCvz14Bn/1i28t+G/u2daLRw6cRkpR4fe6kFY0ZDWBe7b1lvUzVU3gB6+P46vPncVUXAaQa3v7q29fh/fdsLKi7WB6JTMW8rpd8x0VWN+gcuVeg4ufN/fHY62f+0pn4J20qk+vlQNmJVVKHX9KVjGVyEDONuaKg3NTCRwcDOPgqQlcjOQnSa8NtWLn5h5s7w9hRdBf5BWoUkwgkCNVe+OrdqauHtsRyjm2pTotLPb9E2P46x+enr/hSAA8bkAVQDiaQSiYq0JbasbK53Ghu7UJfhabIWoYxWLY6XDMsD3Ceq2kKCdeLzw/IQSymoDXLWFstng8vK2vCw9gI/YdG8ZYNIUVFRQufOF8BF98+k28OZErkOh1S/jIrWtwz21rqypCW2syYyGfx4WOZl/VxXCpNnp87quZgXfSqj69Vg7omVSpZNxY7PiHpxMYm03P12FpJKOzKRwcnMCBU2EMXY6bc3o7A9jZH8KO/hDWdtlvxYwd8G5AjlTLja/SmTqjtyOUe2ylOi3MkbMa/u7QGTz5yigAwOd2obPZi2haQVYVcLkkaBCYTshwSU1FZ6wkKXe+HSavOiCi+isWw+SshvaAcXuEa11JUW68nju/Jo8bWU0DRHkz+Lf1dVVUY+DsZAJ7Dw/h6Nnp+cfedV0Iv3HXBiyvYbaslmTGHL/XjY5mL4uKWUCtn/tqZ+CdsqpPr5UDeiYxKxk3Lj5+IQRimSy6W/0NlTyYiGXw9BsTOHgqjJOjsbzvrQj6saO/Bzs3h9DX08JxqcF4VyDHqteNz8jtCOUqp9MCAIxH03j4ydcxOJYLvLf3deHNiTiCAQ/cLgnhWBqaBkASyGRF0RmrJq8b3a0+Fs4ialDFYpjXLeUtmwesVXit3Hj9ibs24NP7X4Oc1WqewS9kOiHj7398Dt/96eh8gcQbVrfjk9v70L8iqMvPqDSZMafZ50FHs5eryhzEaQURK6XnmEuPsWWl48a5409kFPg8biTlLBRVv3hkZbNJBU+fnsDBwTBevTiLhaPcZS0+3L25Bzs29+D6lUEmDeqICQQyhd366C7FqO0I5ZqMZxAto9PCC+cj+NPvnMRsSoEE4FfvXI9fftta/N6/vIqpROby8lQ/IkkZclYg4HXjgZ35Lb/M6rBARNZSLIbtPTxk6cJr5cTreCaLa5a34lM7apvBLyStqPjXFy7isaPDSF2uU7OmM4BPvKMPd127zLQBsCRJaGlyoz3gNSQx7KR7vh05qSBiNaywHWPhNTARy2BFML8F61Ljxu39IfyRomLv4SGMzuoXj6wqkcniuTOTODAYxvHzESzsQhn0e/COjT3Y2d+DG9d0sJCrSZhAoLqzWx/dUozYjlAOTct1Wii1fE0TAo8dvYCvPXcOmsgF3//5vuuwbX3uxrNwr2xLkxtuVxOymrgqedDkdaOntcmUDgtEZD3FYpiVC68tFa+zqobJuDwfU6udwS9EEwI/PBnGV545i4l4rjJ40O/Bx+9Yhw+8dRW8FRRI1JNLktDq96A94DXsGJx2z7cjJxVErJaZ2zEWXwOT8QxGZtKQJAlt/lxCs9i4Uc5qmE7I2LSiDX9ZpICrE6QVFUeGpnHwVBhHhqagqFeyBgGvG3dt7MaOzT24dV2nafGSrmACgerOzD66RjDjxqyoGsZm84slHh2axr5jwxiNprAyGMDNve04fn4Gb4RjyFwulLhpeSv+eNeWvEq0pfbKztU66GTLG6KGU2jmGEDR2WQrzPQtpVi8vvdta3ExkipZQ6YaL12I4AtPD+FMOA4gVyDx529ejV9+2zq0+s0ZhrldEtoDXrT5jW/F6LR7vh0tvi5bfG743C58+onX0HvYWtdoIXZfwbL4Glje5sfITApjs2m0NnkKjhs1TSCSlBFNZ0tuT7UrRdVw/FwEB0+F8dyZqflVWUCueOvtfV3YsTmE2zd0oYlbqiyFCQSqO6ftxav3gDmt5IolqgvWdB0dmsYjB07D45IQ9HswMpPAKxdnIEmYX/oV8LrxsbetK9jGpthMm9ftQk8bOywQNaJCM8e/96+vQAIQDHiLziZbufDa4ni9qj2AX9y6BtetCuqePLgwlcTew0N4fmhq/rEdm3vwm+/YgJXt1bdTrIXH5UJ7c31bMTrtnm9Xc9el3VaE2O14C1l8DQQDXgACY9EMZlNK3rhRCIFoOouZpJw3znMKVRN4ZXgGBwbDeObMJGLpK6to3S4J29Z3YsfmEO68dhkLuFoYfzNUd07ci1evAXMsrWCyQLHEfceG4XFdKV42k8pCABAi154x1JbbevD4iyO4c2N3WT+r1e9Bd0sTXNxfRtSQCs0cj8ykAAGsuPwHsB1nk7f3hzCwqQdTCRmxdOn6MZWaScr4hx+fx5OvXppP4G5ZFcR/2X4NrlupT4HESnnducRBW1P9EgdznHjPtzO7rQix2/EWUuga8LhduGVtJx677/b5x+KZLCIJuaxW3HaiCYHXL0VxYDCMp9+YQCR5Je5KAG5a24Edm0MY2Nh9OblCVscEAtUd9+JVJ5KQEUnKBb83Gk0h6PdACIGJuJy3d6y3MwC/1w0BgbFo8R7mc1yShO62Jvb8JmpwhWaOVU1clcC022xyPJPFdFzOtWfUkZzV8PiLF/GNn1xAQs4txV3Z7sd9A30Y2NhtSoFEr9uFzhafqfGc93xrsduKELsdbyGlroG0omIqISOzYAm/3QkhcDocx8HBMA6emkA4lsn7/pZVQezYHMLdm7qxrLWpyKuQVfEvBKo7q++RtZpcUiCDeLp4scSVwQDGY2lEEjLSl+sdSACaPNL89oNyepj7vW6E2prgYYEaooZXaNbM7ZIAkf+HsF1mkxcXSdSLJgQODobxpWfOzg+S2/we3Hv7OnzwratMKTzb5HWjI+BFiwUSwbznW4vdVoTY7XgLKXYNvP3aboxH00hk9I1JZjo/lcDBwQkcOBXGxUj+pNW1oVbs2NyDHZtDWNF+9XZasg/z7yzUkKy8R9ZKNE1gPJZGSl46K71tfSe+8tzZ+eWyzV4XUoqG1iYPBETJHuaSJKGz2YuOZhZKJKKcQrNmrU0eSIDtZpNnUwoiCVn3OgevXpzBF54ewqmxGADA45Lwczevwr1vW2fKUly/142OZq/l9g7znm8ddlsRYrfjLWbhNaBeLpA4MpNyRIHE0dnUfNJgaCKR9701nQG8sz+EHf0hrO2yT9KHlmatOwwRzSvUaWExIQS+efzifPLALUkI+t1Yt6wVN/e246Xh2ZI9zFkokYgKKTRr9pn3XQ/APrPJclbDZDyDtM5Lgy9Gknj08Fk8e2Zy/rGBTd34xF19WN1Z/wKJAZ8bnc3/P3vvHR7Xcd39f+eW7Yu+ywqQBAsgUhIlUaSoShK2Yye2mSbbokucxEXSz/nZiVKcvK9jFSeOHceK5cSxSblbtiW3WJJ7AZsKRVKUKIsUSJBgAUGCC2ABbL913j/u7nIX2L57twDzeR49ELfcO3vvzJm5Z875Hguz44y8NFpESKO1NxeUUgSiKiYjlXdmVpvxkIS9J8ewe8CH45eCae953Vb09XrR1+vFSo+zJulbDHNhDgQGow6JKRp8ASlnjm5YUvHvvzyB/YPGAnaVx4UHtq/F4pYri9f35DmP2yaiw2Vhxp3BYGQk285xvS/eKaVG1EFEqegO33RUwbeeP4cnj15MKqT3LnTj3i0rcc3S5oqdp1AcFgEtDpE5DhhF0WgRIY3W3kyEJRX+BhdInI4q2D84hv6BMRwdnkKqZW11iNja40VfrwdrFzWxdeUchzkQGIw6IyKr8AWknN7pM+NhPPDUMQzH88veuG4B/vp1qwuuk8tzBB0ua13kx9YLjV5nmlF/sD5VGyRVw1hQgqxWbqEuqzp+/PIIHjtwHqF4vvKCJis+cHs3tvV4qr5YZo4DBiM39WJ/JVWDPyznTUWtV8KSimdPT2D3gA+Hz02mlZZ02wTcsdqDbb0erF/aYmjkMOYF7OmBUTPqxbjXE9NRBRMhKedndg/48JlfnUBM0SHyBP9/3yq8+ZpFBS9gHRYBHreVGfoU5kKdaUZ9wfpU9aGUYjKiYDpauagDSin2nhzDo/vP4NJ0DADgtPJ4103L8CfXL6m6QKLLKqDZIcIqXHEcsLmUwUinHuyvqunwR+ScAtjV4OCQH48fGsalQBSLcqSzpiIpGg6c8aN/wIcDQxNplb3sIo9bV7Wjr9eLDctaITLR7XkJcyAwakI9GPd6YyIkYTqavSa5qunYuW8IPzwyAsDIMXtg+1r0LiysrjghBG1OC5pZjd1ZzIU604z6gvWp6hJTjKiDSoYHH7s4jS/uGcLxSwEARuTWW69dhPfevBzNjurZUUKI4Tiwi7McFmwuZTBmU0v7q+lG+lQgqtRc5+DgkB+P9A9C4AiabAImwhIe6R/ER7B6lhNB0XS8eG4S/QM+PHtqAtEU3RiRJ9jcbTgNNq9oKzjalTF3YQ4ERk0ox7jPtd0WTafw5am0MBGS8NBPjuN3I8ZCdkNXCz725rUFL2ItAgev25ZcfNbiGtbzfctWZ3rwcgA7dh2oyzYz6pvhyQh4AgyNhSBrOiw8hw6Xpeja5WaNm3oej8Wg6xT+iIxADudrsVyciuLR/Wew9+RY8rVbV7XjA7d3l6UiXuxOIEcI3DbDcZCttC5zVM0tKjEuazm268WuZJvTi7W/xaBquuE4iKl1U1nh8UPDEDgCe/yBP1HF4vFDw9jU3QZNpzh6YQr9Az7sHxxHMCVagucIblzWim29Xty6st20lNdSIiQYtYc5EBg1oVTjPtd2WyTVEEvMtWv2yoUpPPST1+APywCAd27qxF/cuqLgFIRmu4g25xWhxFpcw3q/b5nqTI+HJAQlDb5grC7bzKhvXBYep8bC4AkBTwhUjWJkKoZVHmfBxzBr3NT7eCyUiKxiPCjnFJsthmBMwWMHzuPHL48kQ3bXLHDh3i0rsb6zpaxjF7MTKHAcmuwCmmwiuDx2vhYPSgxzqMS4rOXYrie7kmlOjyoalrZWvoygoumYiigISfXjOEhwKRBFky39Uc8qEJz3h/Ff/aew54QPk5ErzlcCYH1nC/p6vbh9dYfpEavF2EVGfcESVxg1obPVkRYeBRRm3FN3Wwgx/oo8wc59Q2Y21xQisopLU9nLNFJK8f0XL+C+7x2FPyzDaeHxiT9ch/ff3l2Q80DkOSxusaPdZU3TR6jFNaz3+3b3Hd1QNIqIbCwAIrKKyYiCNqdYt21m1DfJMUdS/kt9vQDMGjf1Ph7zoekUvkAMo9OxijgPFE3HD49cwHu+chDff/ECFI3C67bin36/F//zrhvKdh4A6TuBBMZfgSN4/NBw8jMWwSip29lmR4vDktd5AJQ+lzLqj0qMy1qO7XqyK5nmdEWjuPuO7oqdQ1Z1+IIxDPsjCMYqW+2lUixqsiOm6KCUGmleIQlnJqLwRxT870sjSefB2kVN+NC2lfje3Zvx8NvX4y3XLqpKumshdpFRn7AIBEZNuPuObnz8qWOIyGoypKoQ4z5XdlvyiSVGZQ2f+eUJ7ImH0HZ3OPHg9nUF1xd320S0OzMvQGtxDSsVzm0WmepMT0cVtDutaZ9rxL7GqA1BScWSFhvGQ3Kyzy9ssiYV/FPJFvZr1lhtZDsaklRMhKQ0JfBSoZRi/+A4du0fwsUpQyDRYeHxzk1d+NMbllQ0zzfTTqBN5DAaiMJu4dFit8BuKf58pc6ljPqjEuOylmO72HObme6QaU6v1PElVcNUREE4gy2vN/p6Pdi1fwgxRYc6w2au9DjR1+vFth4vFjbbatK+XHaRUd8wBwKjJpRq3KsZlmYW+cQSz/sjuP/JYzjnNybd11/lxX1vWFNQuS6eI/C4rWnXZya1uIaVCOc2m5l1pnfsOtDwfY1ROxLjrNvjSr4WkVV43ekLtVxhv2aN1Ua0o6qmYzwkIyJXZtH+2qUAvrT3dFJXhiPAW65djPfesgytDktFzpHKoiY7JsJSMhcZMHYwl7U7sai5MMdwJsx8UGJUl0qMy1qO7WLOXY10h5lzernEFMNxUCkbZBaj0zHsPuFD/4APp8fCae9ZBQ63rerAuzd3YVl77ddfmexiTNGxsKl0m8ioDsyBwKgZpRj3Rt5tKUQscd/JMXz6FycQVTQIHMGHtq3EQrcN/+dHr+YVmLFbeHhc1qxiWwlqcQ1nhXMDAC0unLvaNHJfY9SeQvtPLhE8s/rgzOOOh6Rk+cMduw7U3QNoIKbAH5Iromg+Oh3Do/uHsPvEFYHEzd1t+OAd3Vhu4oL6ro2deKR/EDFVg0PkIWs6KAju3bKy7GNX+kGJURvKGe+J3fxBXxDBmIpWh4gOl7Wq81Yx7W8k8c+orGEqKudcu9Wa8ZCEvSfHsHvAh+OXgmnved1WbOvxoK/Xi1VeV12tuxJ2MaposIlcMlLiro2dtW4aIw/MgcBoKMrdbamVQnA+sURNp3h0/xC+d/gCAKDJJmCB24ZvPHcWYVlDi11Ai8OSUWCm2PKMldyxKvR6FhPOXS+wnT1GORTaf3KF/SaO8elfDGDQFwIArGgvfycxtW2vjkwhJGkgBIhIKs5OhKoufJbNjiiajrGghJhS/sI9JKn4zgvn8cMjF5ICias8LtyzpRs3LGst+/j5uHV1B9w2Ad86cA4jU1FmTxizKHXOSd3NX9hkg8hL8IcVqJqO1QuaqlplKSKrkFUdFp5kPHficwfP+mHlCbxNNrhthv2rtzSqhBaSlMH+1EPlgOmogv2DY+gfGMPR4SmkuldbHSK29nixrceDtYubwNWR0yCVTd1t+AhW4/FDwxgNRLGQVWFoGEg9in7M5MYbb6SHDx+udTMYDU7qJJvqHX9o+zpTJ9eQpGIsKGUV2PGHZfzLT4/j5eFpAIbeQUhSYRU4jIcMpwMBgbfJCqdFQFTR0O604uF3rIdVNKIOZtYGrwbFXM9M6QCJcO7vfnBztZtej1Rldme2tP7INzbMtFt7Bny4+7EXoVMKniOgFKAUaHeJWN7uqsrYzPb7PvrGHqxd0ly2MJmq6fjJK5fwjefPJVPHOlwWvO+2FXjD2gWmL6ztFh7NdjFnWhmjolTtSale7Gmt59dCbVTq50anY5Dja5vFLYYToV7WBDFFgz8sZ3VcplYOSN01/0if+ZUDIrKKZ05NYPeAD4fPTaZpwbhtAm5f3YG+Hi/Wd7YUXKmLwcgERwiWdzizdiI2ozHmDbUImcund3Ds4jQeePo4JkJGica7NnbitYsBKJoOu8hD0XRwhIAC8UoMQlJgptVhQYtDrFk4WjHXk6UDMBiZyTc2zLRbO/cNQdMpBI6AgIAQQAfFdETBBa46O4Ezf59N5KFoCh7dfwYPv2N9ycellOK50xPYtW8Iw5PR+LE57NjYhbfduLQgTZlSIYTAaTUcB1bBvPMwGEDtRVELtVGpn+twWXFxOgoKo6IKz5GarwkUTcdkWM4bGZlaOQBA0m4/fmjYFAeCpGh44Ywf/QM+HDjjh6xeiWS1iRxuXdmBvl4vblzeCjFPCiuDMROOEIgCB5EjEHkOAm/8zdeXmAOBUTK1SgcolWpOsvn0Diil+PHLF/HFPaeh6hQOC49/eFMP7ljtwY5HDyRVaUWeg6pREA7J9AdJ1bGszYlWZ+WFvoqhmOvJ0gEYjMzkGxtm2q3hyQisQtzGJMtMApKmV01QMfH7KKXQdAqNUliF8lS4T14O4kt7TyejujgC/ME1i/DntyxHm4l2kxACt01Ai13Mq0VTTzTaXM5Ip9aiqIXaqNTPNcX/jockxFQdXretZv2OUoqpiIKpaGGlGIutHFBKuoOi6Xjx3CT6B3x49tREWqlWkSfY3N2Ovl4vblrRZqozlDE34AiBwBNYeA4Cz0FMcRKUGqnCHAiMkqiGgm6lqdYkK6s6LgdiWfUOooqG//z1SfzmNR8AYHm7Aw9sX4euNqMdqaq0rQ4LfMEYqA4IHIGk6aAUuHdr+cJb5VLs9WRCXwxGZnKNDTPtVmerA6qmYyIsA7rhPNAohcBxVdsJ7Gx1YDQQhYXnk4v3UlW4fYEYvvLsWfz6+OXkaxuXt+KeLSuxosM8gcRGdRwAjTmXM9KpdYRfoTZq5uea7CIEntQ0bSEkqZgMy1nXa5kopnJAarpDk03IqGOVQNMpXrkwhf6BMewfHEMgdiUSgucINixrRV+vF7eubIfTyh7fGOmY4STIBeuBjJKoRTpAubsk1ZhkI7IKX0DKqhZ+YTKC+586jjPjRmmdbT0e/N3v9aTV/05VpXVaebSoIgIxFU6rgMXN9mR7d+w6UNMdo1ovWhiM+UAh46xU25g4drvTgmBMhaTq4DmCD21dWRV7QinFjk2d+LefD0DVaMkq3BFZxXcPDuP7L15Ihvd2dzhx95ZubFxuTk7ywSE/njg8jNFADMvaHLhnS3WuWaVpJDV8RmYKifAzM8qk0LVAvawZKKUIxFQEokpRjoMExVQOyJfuQCnF8UsB7B4Yw56TY/CH5eR3CYD1nS3o6/Xg9lUeNDsKE8oulHoQgmQUh8Bx4HliOAe4K+kGAkeq7rxmIoqMkrjt0/1osafn31NKDVXYj/ZV/HyVEhJLTKJmhNFPRxRMhKWs7z97ahyf+vkAwrIGniO4d0s3/vj6JRk1DBKGfTQQxeIWOz60dRVet3ZB8jfUQgwyE2Zez3kGE1FkZCXXOCvXHtRqDEdlLSkSm2rvilHh1nSKn/3uEr7+3FlMRgytmTanBX9563K8cd1C00TEjpybxOd+MwiLYDx419IGl0u15/IqMO9EFPNRjTVDoXak1muGQEzBVFiBqhfvOEilUJuVSEklKd1SpzomIwresHYhdp/w4XIgfd3Yu9CNvl4vtvZ40OGyltXOXO2vlRAkIzuJKAKBMyIIBI6DKFz5dw00z7KekDkQGCVRbdXfWqsM54JSivGQjGAss1iiplN89dkz+O7BYQDGAvf+t6zFNUubcx43W3nGer4WjJJhDgRGSTSaPdB0iomwhFCs9BKulFK8cMaPnfuGcG7CyLO2CRzevrET77ixMy2iq5I4LAJaHCL+4muHGuqa56LR+k8BMAfCDObgPS6asKTCX2SqQiW474mjyXQHWdURiCkIxFSoevqzV3eHE329Xmzr9WBRc/HpW+W0K0FqhS+GOaQ6CIR4FAHPEwhxAcM6rJxR/SoMhJCvAngLAB+l9Or4aw8A+ACAsfjH/g+l9GdmtYFhHtUORau0kFilwvl0neJyDrHEqYiMf/npazhyfgoAcM2SZnz8LVehPY9X2Sby8LitGVVQa624PB9gomLzm0a6/41kD8KSiomQXNbu32lfCF/aexovxm0qAdDqsIDjgFeGp7F2YVPFd9BcVgHNjisVFRrpmuejXsLKGfkp1S4NT0bAE2BoLARZ02HhOXS4LA3ZX4slKmvwR2RIWUoyms0b1y3A/+w9jdFADIqW7jRY2mpHX48XW3s9WN5unkZLJooVgmQUBh9PJRA4kkwrMP4azgKu/hwEJWOmBsLXAfw3gG/OeP0/KaX/YeJ5GVWg2qr6lRQSq5RoVD6xxNcuBfDAU8cxFjLC0+7csAQfvL07Z54SIQStDhEtjuxK4bVWXJ7rMFGx+U2j3f9GsAeViDoYD0n46jNn8ctjo0gsw1d5nJiKKrCLPGwil1OgrFgIIXBZjYiDmY7cRrjmhcIq5DQG5dglt1XAoC8EniPgOQJVpxiZimG111WdxteAiKxiOqpk3dwxE39Yxp4TPvQPjOH4pUDaeyJPcHN3O955UxdWe101K8NdjBAk4wqJyIHUKALDWVCzFIOaYZoDgVK6jxCy3KzjM2pPNVX1K7lLUgnRqFxiiZRSPP3KJfx3/ymouiEM9g9v7MHWHuPY2YRrLAIHj9uasW546s6D2ypgOmqkS7Ado8rDRMXmN412/2/ubsMX9pyGphvlD902ARaBr6g9KCciIyKrGA+WHnUQlTU8cWgY3zs8jFhcIHFZu9GGJw4OQ1L1itZjL6SiwlzbtWcVcuqfcuxSMlU5sVyhM16vEqXakUK/p+sUQal0ccRyCEQV7B8cR/8JH44OTyE1Q6HVIeKONR68rteLtYubwNXBQ2YxQpDzBUJIMlqA566IFKY6CuaTgyAftajC8FeEkD8DcBjA31JKJzN9iBDyQQAfBICurq4qNo9Rj1Ryl6Tc8NPJsIzJiJzxvZii4XO/GcSv4mXEutoceGD72mR4WraSPv9k7cVb1y/OaJxm7jxEFQ0EgMgRTEeVmu0YNVKYdz5Sf8tYUMLCpvQUk0YNTwaYLS2URB84eNYPK0/gbbLBbTPsRDXufynjac+ADz84MoI2p4jpiIKYqkGNUHxoa1dFxdFK2fksN+pA0yl+eWwUX3v2rFFmEsZC/M9vWY4/uGYReI7gkd8OVjQM12UT0OqwZEwdS4Xt2s9famVPy1m3hGQNS1psGA/JyRSGhS4rwhXYnS/UbpVqRwr5nqrpCMRUBGMKNL16TpGIrOK50xPoH/Dh0NnJtHO7rAJ6F7oxGZYRlBScG48gIml14TwAgE3dbfgIVpckXttopDkGCAHHEXDE+P+Es6AWVQwanaIdCIQQDoCLUhrI++HZfBHAJ2D4Pz8B4LMA/jLTBymluwDsAgyhmhLOxZhjVGqXpNTwU12nGAtJCEuZF8QjU1E88NQxnB4zSjTesaYD//ArwVgaAAAgAElEQVTGnrTzzCzp47AIkDUN3z04jO3XLcl43Ew7DwDQ6rTiF39TGwGkRgvzzsXM3zIekjAyFYvvRBoLtkYNTwaYLS2E1D5gEzjImo6LUzEsbgHcNtH0+1/qeErYhma7DR0uGwBjUfv8kB8frlDbStn5DMYU+MNyyYv5Q2f92Ll3CEPxcrcWgcPbNizFXRs70+qfVyoMd6bGQSGwXfv5Sa3saTlpM4nvdnuupCwkRBTLoRi7VWoERa7vbV7ZjkBUQVjWqhZNISkaXjjjR/8JHw4M+ZNlYwHDeXnryg709XpBKcUX9pyGwBE028WKpldVik3dbXXTlkqQqFgg8hxEnoOFj1cyYI4BUyjIgUAI+Q6AewBoAF4E0EwIeZhS+pliTkYpvZxyzEcB/KSY7zPKZy7tGpdKKeGn+fQODgxN4JM/G0BIUsER4xx3blg6K6IgVbiG4xLKq0LOXYRBXxARSYWiU1h4I83BZc39HbNptDDvXMz8LQvcNoxMRTE6HYPLKjR8eDIjP6l9oMNlxcXpKCgofIEYeI6Yfv8LGU+ZbHc1xPyKOYes6pgISyXnHZ8ZD2Pn3tM4ePZKYOIb1i7A+25dDm/T7IedcsJwOULgzKJxwKgNbH2SnXLSZkr9br77Ucw6oFRbNfN7lBrroLMTIVycqo7gn6rpOHxuErtPjOHZU+OIpNg3AmDt4ib86Q1Lsbm7Dba4M/O+J46mbRZVIr1qviPEKxaICXHCeaw/UA8UGoGwllIaIIS8C8DPAHwUhiOhKAcCIWQRpfRS/J9/DODVYr7PKI9M3uK/+8FReFxWBCV13kzYmcJPb+5uw859Q/jYk6/Oug659A40neKbz5/Ftw6cB2CE2H78LWuxvrMl47kXNdnhj0hwWcVkuZaIrGbdRdgz4EMwpkKnNCl+dHEqhnaXiOXttRNAmksq5DN/S5NdBEAxGpBqmiLCqB6pfaAp/nc8JCGm6vC6babf/3zjKdtOnzvu4DJTzK+Qnc/dr13GF/acxvBkJE3XpVD8YRlfffYMfvHqaDJ3+LrOZtyzZSXWLHBn/V4pYbg2kYfbJsBpEeaUIna9UE6e+1yJajODctJmSvnuzPtxdiKEux97ES4rjzULmop2YJYaQZH4nl3koekUGqWIyhoWuK9EGWXTlSoHTad45cIUdp8Yw76TYwjMSMWyCRya7QIEnoM/LMMh8knnAcCqHJQDHy9paBU42EQeFoFj+gN1SKEOBJEQIgL4IwD/TSlVCCE544UIId8FsBVAByHkAoD7AWwlhFwHI4XhLIC7S204o3hmeotVjWIqoiAUU7HK65pXE3Zq+Gmuhct1XS3whzPrHUxHFXzyZ6/hUHy3bN3iJtz/1rXoyFGi8T2bu/C53w5CUrWCdgJ27htCq0PERFgG1QFCAB0U/rCCf/vj2u2IzyUV8ky/ReA53NDVOm9qZM93ZvaBJrsIgSdVq5Oebzxl2+mjlELRqKlifvl2L3/16igeePoY+Bm6LoWE6sYUDd8/fAHfPXQeMUWPXws7PnhHN25Z2V7QgrGQMFyeM9KRXFYBFoFFG5hFOU6AuRTVZhblpM0U+93U+xGMKZgIKaCgiCl6SQ7MUqIgKKV4783L8NBPj0NW9YxRRtl0pUpJFaCU4rVLQfSf8GHvibGk9gpgRBpcu7QZEyEZOqVwWdN/88zIAlblIDsCx8EqGikGCZHCRIUQnjl1G4ZCHQg7YTzwHwWwjxCyDEBODQRK6Y4ML3+lqNYxKspMb/F4SAJHAI1SEELm7YSdaeESlhT8V/8pfOZt12b8zsnLQdz/1DFcDhglGv/4+iXY0NWCT/50IKsXvNVhwZ9sWIp2l7XgnYDhyQg6XEZlhvGQlBRAsotcTe/RXFIhn0u/hVEate4D+c6fbadvOqrgE394dVlifvl2jLPtXm7p8WAiJOF/9pwGX2SorqZT/Pr4ZXzl2TOYCBmL9Ga7iD+/ZRnefM2iiuWs2i083DYRTgvPdq+qQDlOgLkU1TYXSL0fY0EJhAAcCGRNL8mBWUwUhKrpCMZUBGMq1ix048PbskcZzdSVKjZVgFKKobEw+k/4sHtgDKOBWNr7vQvd6Ov1YmuPBx0uK3Y8emBWZIGm6zh2aRo7Hj2QXPvN9yoHhCQEC+MOAyHVacCcuHOBghwIlNLPA/h8ykvnCCHbzGkSwyxm7nLJmg4CwJIymOfjhJ0px07gOYxMZb4OP33lEj7fPwhFo7AJHP7293rgtgpZveC3ru6Ax21NhrcVsxOQuGdNdjEZWl0J8aNymUsq5HPptzBKo9Z9IN/5c0UolLMrWeiO8cxzRGUNFyajUDS96FDdI+cm8aW9Qzg1FgJg1EX/0xuW4p03daXt6pUKIcQQRbSLLNqgypTjBJhLUW1zgdT7IWs6eI6A6lfWi6U4MPPZqoisIhRTZ4ki5ooyKjVV4Lw/gt0DPuw+MYbz/vT+2e1xoq/HcBosbkmPGJgZWRCSVFwOSLMjsPpW4yN9c6fKAR+vXJBayUDg0isacBzAEyOKgDls5z6FiiguAPBJAIsppb9PCFkL4GawiIKGYuYuF88RqBqFx30l5H4+TtipE2XCox6VtVmhZrKq4/O/HcTPXh0FACxttePB7euwosOZVTDn+y9ewNs3dmLfybGS8kJrvTOai7mkQj6XfgujNGrdB3KdP5cdKEd4rtgdY02n8IdlBGNK8rVCQ3XPToSxa98QDgz5k6/19Xrx/ttWYGFz+Q5RYwFvOFpZGGxtKMcJUM9z3Xwk9X6IHIESFydJVHuphAMTMNKYwpKKkKTOqtpSiLZBMakCo4EY9gz40H9iDKd8obT3lrbasa3Hg2293mTZ7UzMjCwYDxtRqB63FQQkLQLi4XesbyiHQaLcoUXg4pUMjP+38BxzCDBmUai7/+sAvgbg/8b/fRLAE2AOhIZi5i7X8jYHJsKy4VmmdN5O2ImJMiQpEDgOMUWbFWo2Oh3D/U8dw2B80rl1VTs++qbe5I7ZLC84MUqD+YIx7Ds5VnJeaK13RhkMRu3JZgcAlCU8V8yOcUhSMRGSZi3y84XqTkZkfP25s/jpK5eSAonXLGnCPVtW4qpFTcVfjBnw8TJpTTaRiSLWmHKcAGyuqy9S78d0VEEwpqLVIcJtM5yM5awVFU1HWDJSFLJVtipU2yCf/fGHZew5MYbdJ3w4djE989rrtmJrjwd9vV6s9roK1lxJFW6lFFjQZIUzxWlW72KJCUeBNe4osKT8ZTAKhRRSO5UQcohSupEQ8hKl9Pr4ay9TSq8zvYUwau0ePny4GqeadyR2r+b7hP3z313Czn1DGJ2eHWp26Kwf//rT1xCIGSUa33fbCty1sTNtsrnviaNJLziJh3nFFC2ZajBzVyaRhsBE+hhxqvLkw2zp3GLHrgNl2ZZCvq9qOsZDMiKymu0wyZ3C1FDd9Z3N+OGREXzn4Plk2bMlLYZA4m2rChNIzAVzHNQndbCmqFpnmE/2tNz7qusUoXiKQkzJX+Y1dU2VIKpoaHda8fA71qd9dqb92b5+ESKKhv4BH14enkKqz7PVIeKONR709XixbkkTuDLtUDHtrDZ8vNyhGK9qIArxqAIWUcAonKwdpdAIhDAhpB1G9QQQQjYDmK5Awxg1ptZhu/moRl3oqYiMnoVuPPz2dGOvU4pvHziPrz93FhRAi13Ex958FW5Y1jrrGAkvuKRpcFkExFJ2Xj725KtMHIrBYFSccoXn8u0YT0cVTIbljCVsU0nNUdYpxW9f8+G9XzsEX9AI722yCXjPzcuwff1iiGUIaB0c8uOJw8O4HIihq82Be7asrOv5az5S72sKhkGxa6tS7qui6YhIGiKKipiio5ANywTFaBts6m7DNUub8dzpcfx2wIdP/nwAaorXwGUVcMfqDmzr9eK6zpaKpjjVg1giISSZbmDl+aRYIXOsMsykUAfCfQCeArCSEPIsAA+AO01rFYMB8+tCU0oxFpIQis3eWQvGFPzbzweS+bq9C9144K1r4W3KnKt708p2/LNdwLcOnJ/loe/cNzsvdCIsISxpuO3T/aY5RhgMRv1TjpO0XOG5bGHjt6zqwMhUFFIBO4WpHB2ewhf3nsbJy1cEEv/ouiV49+YuuG1inm/n5vAZP/5r9ylYBYI2pwVjIWnelB1mzG2qsVEy83xmra1UTUdY0hCS1aLtRyqFaBvIqo4DZyawe2AMB4YmIKlX0iFsIodbVnagr9eDG5e1mRaePzOlwWyxRIEzUg2S/8W1ClhEAaPaFJTCAACEEAFAD4xwhhOUUiXPVyrGfAoTY1yh3PDcXOg6xeVgDFF59gQ3eDmIB54+jkvTRjmfP1y/GPduXZl1AhJ5DguabFnfT52s7SKPibAEX1CGx2VBh8ua3PV7aPs6thCev7AUhnnITNtQrC0o9/szoZRiKqJgKqoUtVs47I9g174hPHt6IvnaljUefOD2FbNUzIslkapwz7dexFhIYqlgjHw0VApDpcdwIVRibUUphazpkFUdikYhqRpkVZ+lkVIqqRoIqTv7f7V1FTge2D0whmdOjSfTowDDYXnTinb09XpwU3d7mvOhEUhUOgAAQhAXMuQgxNMOWFQBowaUlsJACPmTLG+tIYSAUvqjsprFmNOU61U3qy60oukYnY5lFO/5xauj+NxvByGrOiwCh/tevxq/t25h1mO5bSI6XJac3t+Zu3xhSYPHZYEnro9QTK1sBoMxdyi2CsJMKik8F1M0jAWlrKJmmZiOKPjG82fx9CuXkg8Oaxe5cc+Wlbh6SXPRbUhlpsbBhalo1vmg2ju4DEalKNcGlNL3S11bSaqGqKwhImuQ1OJSEooldWf/0nQELquIxc1WfPqXAwikRI1yBLhxWSu29Xpx66qOipSCNRuBM5wCqZUOrALPqscwGop8I+2tOd6jAJgDgZGRSoTImVEXOipr8AVjs7zksqrjC7tP4elXLgEAFjXb8OD2dVjldWU8DkcI2l2WgsNyU/MHb/t0P9NEYDAYFXGSlptzTinFZETBVEQu+DuyquNHL43g2y+cQ1gydgAXNdvwgdu7sWVNR1nhtBwxHAfN9nRxxGzzgcsqmJrqxmCYSTk2oNR1VqFrK0nVEFN0SIqGqKJVLLqgECilcNsFdHudGJ6M4PR4GKfHwwCMLdFrlzZjW68XW1Z70OwoLz3KLAgxoidsgqFLIHAs3YAxd8jpQKCU/kW1GsKYW5TrVQcqXxd6OqLAH5Fnec0vB2J44OnjODEaBABs7m7DP/1+b1bngEXg4HVnT1nIhxmOEQaD0XjU2hYUG3VAKcXuE2P48v4zGA0YKV4uq4B3b+7CH123pKw842yOgwTZ5gORo2XPNQxGrSjHBpS6zkodSzaBQ1TRIGsU776pC+MhCbKqmx5hkAlKKYbGw+gf8GHPibFkGmmCnoVu9PV6sXWNBx63taptKwSOENhE3nAaiDysAqt2wJi7FBzrQwh5M4B1AJIqcpTSh8xoFKPxqdTOWiXCc3OJJb54bhKf+MlxBGIqCIA/v2U53rW5K2tpnya7iHZn7pSFfFTaMcJgMBqTWtkCXaeYCMsIxgqXMnp1ZBr/s+c0BuKOVp4j+MPrFuM9m5eh2V76DmA+x0GCbPMBq3LDaGTKsQHFrrMSOgXXdrbgb16/Gt98/hwupZSuvmpxEwLRqsmbJRn2R7D7hA+7B8Zwzp/e9u4Op+E06PGUradSaThCYBU52EWeOQwY846CHAiEkC8BcADYBuDLMCowHDSxXYwGp1I7a+WG5yqajsuBGGQ1fYdNpxTfPXgeX3v2LHRqlBn7v2++ChuXZ1bO5QhBh9takfy6SuYtMxiMxqUWtiAkqfCHZKh6YVEHI1NRPLpvCPsGx5Ov3baqAx+8Y0VZkRIzNQ4KIdN8kKnKDYvoYjQK5diAXOssSikkVUdMMdIQYoqWVo51fWcLPtvZYsZPKojLgRh2nxjD7gEfBn2htPcWt9jQ1+vFth4vVnQ4a9TC2SRSEpjDgMEoPALhFkrptYSQVyilDxJCPgumf8DIQT3ssmfTOwjFVHzqFwN4Lq4Y3rPAjfu3r8XCLCUabSIPj9taVv3ymbBa2QwGA6ieLYgpGvxhGbECS6sFogq+deAcnnz5YrKmes9CN+7d0o1rl5b+4CHyHJodItxWoSKL73qYaxiMcijVBiT6flhSYBN5RGUjFeHODUtwdiJS9RSEfPjDMvaeHEP/gA/HLgbS3vO4rNja48HrrvJitddV8wdzniMQ4pUPLLxRMtEmMocBg5GgUAdCIhEpQghZDMAPYIU5TWJUglqrUtd6l306omAiLM16fWgshPufOo6RqSgA4C3XLsJfbVuVMXeXEIJWh4gWh8X09jIYDIYZaDrFRDhzClcmZFXHk0cv4rED5xCMf2dBkxXvv60b23o9WdO78mEVeTTbxYqrpNd6rpnL1HodwciMoulQNYr1nS3469etxjcPnMNoSirC9V2tdeM8CMYU7B8cx+4BH14ankLqfk6LXcSWNR5s6/Xg6iXNJduWVA4O+Y3KDYEoFsWvx6buzJGlCUQ+rlkgGs4CkedYRQQGIw+FzuRPE0JaAHwGwBEYFRgeNa1VjLKoRAWESlCLXfZcege/Pn4ZD//6JCRVh8gT/PXr1+D3r85colHkOXibrLAKjVVHmMFgMADDFgaiKiYjclrocq7P7xscx659Q0nxMqeFxztv6sKf3rC0ZIFEm8ij1WGB3WKeLWURXZWnXtYR8xldN9IQZFWHpBn6BYpG05wD13W14Lqu2qUiZCIqa3ju9Dj6B8Zw6Kw/GcEEAE4rjztWe7Ctx4Pru1or+qB+cMiPR/oHIXAETTYBE2EJj/QP4iNYPcuJYBN5OK0CXFaBOQsYjBIo1IEwAECjlP6QELIWwA0AfmxesxjlUIkKCI2IplOMBmKQZoToKpqOL+45jR+/fBEAsLDJhge2r8WaBe6Mx6mEUCKDwWDUipiiJdXUC+H4xQC+uPd0MqyYI8Bb1y/Ge29eVnIElt1iOA5sInPCNiLzdR1RSxRNT9Et0Aoev/WArOp44Ywfuwd8eH5oAlJK220Ch1tWdWBbjwcbl7eVVa0lF48fGobAEdjjNieR0vT44WFs7fXCKnCwihysAs+cBgxGmRTqQPhnSun3CSG3AXgDgM8C+CKAm0xrGaNkKlEBodGQVUMscWY5srGghAefPo7jl4yFsdsqQKM6vrRnaFZoG88ReNzWNEEiRmayhbaykFdGPZHojycvB6BoFBaBw2qvu2b90uzxQSnFZETBVEQu6POXpqN4dN8Z7Dk5lnztlpXt+OAd3ehqK02E0GER0OIQmeOgwZmP64hqQSmFrOnJiAJF0yEpesHCpqnMDNm/vrMZLw1PFxXCXyqqpuPI+SnsPuHDM4PjCMtXNm9EnmDTijb09XixeWV78qHeTC4FomiyGes3Qgg4Yqz5xoMxLGzOrHFV77A1FaNeKfRJKWEV3gzgS5TSJwkhD5jTJEa51Lq2eLWJyhouB2KzwnRfOj+Jf/npa5iMKCAwQuea7QLsFn5WaJvdwsPjskKooFDiXCVbaOudF6bwgyMjLOSVURck+qmsagjEU5qisoazE6Ga9EuzQ8JjioaxoDTLiZqJUEzFYy+cw/++NAJFM+zmaq8L92zpxvVdrSWd32kV0GxnjoO5wnxbR5hFohqCHHcSJBwHldAomBmyPzIVxisjU2hziGh1WnKG8JeKplO8OjKN/gEf9p4cS9pWwIhc2rCsFX29Xty6qqPieie5IIRgSYsd/rAMl5VPRpBGZBWdbfVTyaEYWBoRo54pdHSPEEJ2Ang9gE8TQqwA2JNWnVIpVepG8HwGYgomQnLaZEwpxROHhvHlZ85Ap4DbJsDjtELR9YyhbW+6ZiETSiyCbKGtX37mTFoEBwt5ZdSSRD+dCKngQMBxBHpcF2Bhs1D1fmlWSLiuU0yEZQRj+eu3K5qOp49exDefP5dc+HtcVrzv9hV4/VXeokXMCCFwxR0HZoUlNyKNMHfmg1W3KB5dp9AohapRxBQNUUWDVCFnQSZmhuyHJA0cAcKyhjYnubLOOTRclgOBUoqB0SD6B3zYc3IME6ErEU4EwDVLm9HX68UdqzuqupZKiB/aLTwcIo8P963Gx586hqii1bzPVsIGsDQiRj1TqAPh7QDeBOA/KKVThJBFAP7evGYxyqESqtT14vnMZYTHQxIC0fRFc1hS8e+/PIH98Zrli5ptaLGLOHE5CAtP0O6ywhk3xnaRx3gwxpwHRZIttDUsa+iasfuYGvI6FxbVjPplZv86eTmARc12yJoOPv5gTAgga3pNQrHNCAkPxBRMhuVZpWqBK6HN5/xhQxeGAJqOZG6yXeTxzps68ac3LC06aoDnCNw2Ec12keUSz6Be5s5yYdUt8qNoFCNTUcNxoNOCxEoryaVAFDwBhieNyCNVBwSCtCgkTddx7NI0djx6oKCUhoTduDgdQavdikUtNpy4HEwKqyboWehGX68XW9d44HFbTfuNM7FbeLisAhyW2eKH9dJnK2UDWBoRo54pyIFAKY0A+FHKvy8BuGRWoxjlU64qdT14PrMZ4QcoxVWLmxCV08USz4yHcf9Tx3Bh0ijRuKGrFSNTEYQkFVaBg6Lp8AUkeJsAt02ErGoNG9pWS7KFtjothsc/U8jrXFlUM+qTTP0rJBlCghaeg6pREAJQClh4riah2JUMCc8nkpgIbVY1DYGIAm3G+zctb8Pfv6kHbc7inKcCx6HZLsJtE8Axx0FG6mHurBSsukVudEpniTZXE6dFwLmJMDjOiLCCTqFSQIyPzbCs4nJAAs/nr0oAGHbjs78+kRRy9AVlnPAFk++v6HCir9eDrT1eLGmxV+13ijwHl1WAyyZAzJNmWg99tlI2gKURMeoZFnPIyMjwZGSW6E21PZ+pRpgQ46/AAf/Vf2qW82D3gA8f+s4RXJiMQuQJ7nvDGqiaDpHnYI+XEQMACgp/6Iq3noVjFs/dd3RD0SgisgpKjb+KRvH+21ZkfP3uO7oz3kuRJ9i5b6jWP4cxB8jUv9qcIiYjCtw2ATooVF2HrlM02YWahLVmGzfFtEPVdPgCMVyciuZUaH/80DBAKfzhdOcBR4CFTVZIql6U88AicPC4rehss6PZITLnQQ7qYe5kzBMSEQ/U+I+PD0uqU1BQjAUlAECH0woCI6VB4IhhH1K4HIjhiUPDePAnxzEWkhGIqZDj2igCR7DAbcVX3nsjvvLeG/Gum5ZVxXmQcFYuabWjs82BVqclr/OgXqiUDajEnMFgmAWTm2dkpB48nzPDtzSdguc4XJqOJl9TNR1f2jeEHx0ZAQB43VY8sH0tehc24dsvnEsq8rqsAgixYTIsQ9IovG4bC8cskVxhgtcubcn4+seefJWF4jFMI1OoZ7vTCkWjWNHhgqoFIMerMCxvd9Vk7JcTXqvrFNNRBVNRJW8+dVhScdIXRFTWkPgkAZBYe7ttAkYD0WxfT4MJIxZPPcydjPlBWNGwoMmKyYgCRdNhETjYRA4hSUMwpoICWNBkTRMztIkcRgNR+MMy9p0cQ/+AD6/Gy7cmEDgCt1WA2ybAIhCEJA0rOsyP1hQ4LpmiYLc0rs2plA2ol5QMBiMTzIHAyEg9CCilGmFV06HphjDRwibD+z0RkvDQT47jdyPG5LdhWSs+9gdXodlhPEgsarJjIizBbuEhcBzanFbYRB5etw3f/eDmqv2OuUi2MMFsr7NFNcNMsvWv1V53XY31YsNraVz0cSqaWecgFU2n+MkrF/GN584hkhKhxRNDs4BSQOAJYoqetKGZSAgjtjjEhtnxqyfqYe5kzA8Sa5zOlHk0qmhY1ubCw+9Yj/ueOIqJsJR8T9Mp/BEZqkbx9p3PI9WktNhFCJxR+rDZLiarGERT1lxmIPIc3DbDYWAVGtdpkEolbUA9pGQwGJlgDgRGRlI9n4O+IGRVTws5r4ZBu/uObvzzk69C1WRYBA4xRYeqU9y1sRNHL0zhoaePYzJiiCi+66YurFvUhAefPp5WD/mXxy9D1XRYeK6uw7+qJTBYKyFDtqhmmEmu/lVqn6+l6CelFIGYiumIkrc2PKUU33zuHB4/PJwUSBQ4ApvIwyYAUxE1Ke7mtAhJGzoTsx0H80VEle0aMqrFXRs78Uj/IKKKBpuYvkZKvP+fvz2JsKxCUnSEZ6R+Oq08bl/lwbZeD27oasWLZyfxSP8gYqqe8XiV4uCQH997cRijgRiWtTnLHh/1ZlvMtgH19nvrtU0McyFmlZepJDfeeCM9fPhwrZsxL0kVJ0tdmD+0fZ3pxkFWdTz50gi+/cJ5jAaiWNhkxztuXIrzU1Hs3HsaOjUmwH98Uy9EjkvWQ05MfDoF3r5hCQ6cmazrhVy1rnEt72Xi/GxRnZWqJJXPZVuaqX8BKKnP13KsBGMKpuIhyfkYvBzEv//yBE6PhZOvOS08nFYBb756IV4ansY5fxiyqsPCEyxrd81SYSfEEFhrtosQTIo4qLXtYcwrqibQcc11N9Anf72vWqfLSKJqQmKNdNfGTlzX1YKDZ/zoH/Dh2dPjULQr63yRJ7htVQf6er3YuLxtVvnVTMcrpwRkKhwhODo8hf/41QlYBK4itmC+2ZZ6/L312CZGxchqT5kDgZGTHbsOzAoNjsiq6WkAEVmFLyCllUWKyCo+88uT2HtyDADQ7XHiwbeuw5JWezJUzy7yADFy6SRVq+t0hcQDz5HzkyAEWOC2oSmex23GNa7VvZxLmOhln5cOBLN3LbL1eZEjaHVas563FmMlpmiYCMsFqbqPBSV89dkz+NWxy0mdA4eFh8dlgVUwFnDtTisefsf6rMdIOA5aHBbTSzEy28OoInPWgZB4uE9EWSYiAxJlF11WES0OESdGg2nRBiJPsGl5G/p6vdi8sn2WwJ+Z8ByB3cLDYRHgEHm868svVNQWzDfbUo+/t2VG0OcAACAASURBVB7bxKgYWe0pS2Fg5KQWdWinI0pa3h4AnJ+I4P6njuGc3zjvG9YuwN+8fnVS3OtSIIomm6HALvAEHCF1LdKX6rHVdB0cIbgYF4dssoumtH0+1BQ284GUlaIsjWz3pBrXM1OfVzUdZyeiWK7TrOet5ljRdIqJsIRQTM372Yis4vFDw/j+4QvJdAWeI1jgtsBlvdLehFBaJgghcNsEI+e5ShoH88H2MBhmkijNKnBXSjJ+6hevQdUpKEWy7GICjgA3dLWir9eL21Z1wGWr7nLfJvJocYhpD5VA5W2BWbalXkPy69GW1mObGObDFJIYOelsdSA6Y0fMLPE7So2yQzOdB/tOjuHebx/BOX8EAkfwkdetxj++qSdNGXxRkx2yRiHGnQdmtrMSpJadswo8CCHgQDAeMn67GW2v5r2sBYkHUl8wlvZguGfAV5Hjs1KUxZPrnlTjembq85eDEkSOy3neaowVXaeYDMsY9kfyOg8MgcRLeM9XDuKxA+chqTpaHSLue8MaXL2oCTyXPpVnE0p02QQsbbWjw2WtmvMAmPu2h8Ewm8cPDRspmnE9qGBMxVRURUjSEJY1JLIUrAKHpS12fP+em/Hvd16LN129sKrOA4dFwOIWOxa32Gc5D4DK2wIzbIvZa4lyqEdbWo9tYpgPcyDMQ/YM+LBj1wHc9ul+7Nh1IKdRrFYdWlXTcXE6hmBMSb6m6RRf2nsaDzx9HFFFg8dlxefecR3+8LrFSYVgwMiru3tLNyg1jFYt6+UWem1T6wR73FZQClBQyJpuWtvnek1hsx9IWX334sl1T6pxPbP1+QVN1rTPqZqOI+cnk+P25u4208YKpUZJxuHJCCYjclqaVqbPHjzjxwe+eRgP//okJiMKrAKHd2/uwrfetwlvuXYRdmzqgqpTw/bB+DtT+Mxu4bGk1Q6v21aTygpz2fYUM58yGKVyfjKMkKTi7EQEw5NRTEWvrJWsAocOlwUr2h3oarND1XW0Oixln/PgkB/3PXEUOx49gPueOIqDQ/6MnxN5Du1OK7raHFjYbMtZ9rXStsAM21IN53apdqMebWk9tolhPiyFYY5SqbDhaihKR2UNvmAsrUyZPyzjEz85jqMXpgEA13e14GNvvmrWpGgTeXjcVizvcMIu8jUV6Svm2qaWnXPbRCxuAUanY6AAvG6bKW2vlTp4tUIBzQ6jY6UoiyfXPcl1PSvVZzL1eQvPQU4RKAzGFIxMxSCkjNsfHBnBnTcswfND/oqOlYisYiIkFySQeHoshC/tHcKL5yYBGImIv7duAf7y1hXwuK84QDZ1t+EjWJ1R+EzkObQ5LXBaazvVz9XKBMXY/HoNiWbULyOTUfSf8GH3gA/+sJL2noXnjPRHDljWll7GsRJlFzOlTDzSP4iPYHXStjitApzW2eUXc/X1StsCM2yL2WuJctL36tGW1mObGAZmzjtMRHEOkksRdee+oboSO5mKyPCH5bTXXh2ZxoM/OY6JkPH6jk2d+MtbV6QJfRFC0OoQ0VIBL3ulKEZIZr6o1lbzd5ot5GPyb5mTIoq57kmi9OLM63nnDUvwgyMjpvWZmffxlC8EVadY0mI3TcRUUjX4wzKicn6BxImQhK89exY/f3U0KZB4XWcL7t3SjdUL3AWdj+cImu1iWj13RuUp1ObMF3tfJzS0iKIvEMOek2PoH/Dh5OVQ2ns8R+Cw8Gh1iKAUCElG6pPLKqSVXfxI3+qyKyekCVPHiSqGMPVj778JdkvmKIO50NfNXksw0UFGNajQWGQiivOJ1PArwMhJi8hq0gtVD2In/a9dxhd2n8aFqUhSTXjjilb8+OWL+J89p6HpFA4Lj4++qRe3r+5I+67Ic/C4rTnD5GpBMdd2vnhsc/XFSv/WxANpRFbTjGWlwujmyz2rJLnuSbbraXafmXleCmBJy5UKKEDlbKKq6fBHZIRiakYF9dRFflTR8L1Dw3ji0DBicYHErjbjmmzubivIESBwHJodYlJQlmEuhdr8atpBRuMxGZGxL+40+N1IIO29dpcF23o86Ov1Yjqs4InDF5KRRh/augoATCm7mBCmBgAQgI9XbfEFY1mdB4B5fb2aETxmryXqZR3OmNuYPe8wB8IcpNSw4Wrxm2Oj+PhTx8CnhMb9529PYlGzHS8PTwEAlrc78OD2dehsS2+XwyLA67aCM7nsWCkUe2239nrn/OKxmhNlNR7w58M9qyT57kmm6/mxJ181vc+knjexG5RKuTZR0ymmIjICMSMnNFc48IblrfjVsVF89dmzmIhHY7XYRbz3luV48zULCxI75DmCFoeFOQ6qTKE2nz0wMGYSiqnYf2oc/QM+vHR+EikZnGi2i9iyxoNtvR5cs6Q5KQwNADetbJ91rEo4DGayqMkOf0SCyyqCI0bUZ0RW89pFM/p6tSsgmb2WqId1OGPuY/a8wxwIc5Bcxslsz2o+QpKK/95z2qgNHI8g4AmBPyTjcsCoQNDX68XfvmHNLC93q8OCVmf9pCzMpNbXth5J7YuBqILxkARJ1eGw8Ngz4DNF54E94NcXue5Jpl2lai+uKjludd0QSJyOKmniiAkF9YTNS5zn0f1D2PUMMDQWBmDUa3/bhqW4a1MXXAXoFnDkSqpCPTpV5zqF9h32wMAAjHv+/OkJ9A/4cOisH4p2xUY4LTxuW92Bvl4vbuhqTUvZrCaEEDgtPO7d2o1//dkAJFWDXeQLFsYzo6+XupNaTtSCmWsJtlZkVAOz5x3mQJiDlBI2XI2HLn9YxlRExqXpK6FxIUnFaCCW9L5/aNtK/Mn1S2ZVWfC4rWUJgVUj/K3eQ9yLvQaVuGaJvjgWjCV3VwkAp5U3dQeBUf9k21VKaCCMBWOYDMuQNQoKQFZ105xO5Y5bSikCURVTUTlNDDbBpUAUPAGGJyUomp58OJDUK599/VVevO+2FVjQZMt7PhIPJ25xWGr2oMEovO+wB4b5i6zqOHTWj/4BH54/PZFMTwKM6gm3rGxHX68XG5e3wSLUrjCaEREqwm0TIPAc3nj1IliFdGHqm7vbsHPfED725KtZ1wS5+vrMNcXN3W14fsifd41Ryk5qtaMWiqHe14qMuYHZ8w4TUZyjJAx1PRgnXafwBSVEZEPw574njmI8FENY1jAZMZSFOQJ0d7iw6882pH1X5DksaLKVNbHOBVGfcin2GlTymu0Z8OHDj7+EsKzCJhhVM9w2kYkGpTMnRRRzkUtI6ubuNny+fxCqblwYI4rfEE79zJ3r62rcBmMKJsMKVD17ZYX3f/0QzvkjIAB0IC1c+dqlzbh3y0r0LCxMINFlE9DqsNSkHCOjdOppTp7j1FxEUdMpjpyfRP+AD8+cGkdYuiKeKvIEm5a3YVuvFzd3t+fUE6gGIs+hxSHCZc2d/lTMmiBTXweQ9v3xkISxkAyv24J2pzXn8UoRHWRChQxGReYdJqI436iXUG5Z1XE5EEsrW/aWaxfh3395IllKzSpwaLaLeP9tK9K+67QK8LjK1ztgAlbFX4NKXrOtvV402UV0tTnSFigsB3h+k2tX6fkhQOA58ATJ8a9TimCsfsZtTNEwEZYhKfkrKyScBjPd9QvcVvzn29cXpFvgsglosVtqukvJKJ16mZMZ5qBTit+NTGP3wBj2nhzDdPRK2UWOADd0tWJbrxe3rWqH2ybmOFJ1EHkOrU5LQalSQHFrgkx9fceuA2nfD8ZUcAQIRFV0uGw5j1fKTirTHWEwzJ13mANhnlKNkP6wpGIsKKXlAr92KYCd+4aSzgOHhcdqjws7NnUlhYAIIWhzWtBsr8wkyyaS4q9Bpa+ZmblYrL56Y5G4X2NBCeNBCQubbckFdaJPDE9GoOkUfMqDNSFGVYNaj9uYomE6qiAcL6GWC51S/Ob4ZZz3R9KcByJH0OESQYGczgNCCFxWAc12cV45DtiYZjQKA6MB7B4Yw+4TPoyH0ktSX7OkCdt6vNjS40FrnZSczuU4yDXuhicj4AkwNBaCrOmw8Bw6XJaC7fHMNYWs6eAIkmtBoLJVq5juCINhLsyBMA8xOzeMUoqJsIxAigeeUoqnX7mE/+4/BVWnsIkc/uGNvdja40n7rkXg4HWXl7IwEzaRFH8NKn3NzMrFquc8R8ZsUu/XwiYrRqZiuDAZxZIWCoHnkn1i574hjIckUN1wHAAApUaZwlqN26isYSoqIyrnjzgAgJfOT+KLe4dwynellnurQ0RbXLcgqmhod1ozfpcQArdNQItdLKgKw1yCjWlGo3BmPIz/79svpb22ZoELW3u82NbjKUjPpFokUhWyRT/kG3duq4BBXwg8R8BzBKpOMTIVw2qvq6Dzz1xTWHgu6YhIUMmqVUx3hMEwF+ZAmIeYGdKvaEbKgpwiFBRTNHzuN4P41fHLAIza5g9uX4tl7U4ASNZHvxyMYVmbA7esbC9IWKdQ2ERS/DUo95pl2sl4aPu6iucAs/SUxuJTP38NvmAMmk5h4Tm0OkQEJRWjAQk3dLWm9Ym/+8FRTEUU0LhggE6NB/Bqj9uQpGIqIqfZtFycn4hg574hPD80kXxt/dJmXJyOwibwiCoqxsMyVI1C5DkcHPKnRV+5rAJaHdkdB3N9d56NaUajkEjNXNbuQF+PF9t6PRV3cCbWR5cCUSxqsuOujZ1FlW20ijxa7GJeEep84y6pl5YIpUr8s0AdtZlrCrdNwFhIRpNdAKW04uuyTFELhYhAMhqHuT4X1jvMgTAPMSukPyKr8AXSUxZGpqK4/6ljyTJlW9Z48PdvXJOcpBL10W0Ch3anBWcnwjh0bjIprFOJ3SemeFv8NSjnmmXdydi+ruLiRSw9pXHYM+DD4FgIPCHgCYGqUUxFFSxutkGnSOsbW3u9+I871+NTP38NZyaMe7na48RH39RbtXEbjCmYiihp+i25mIrI+MZz5/D0KxeTIolXL27CvVtX4qpFTTg45MeufacxMiVB4IwIDEXT8Uj/ID6C1dh2lRdtztziiPNhd56NaUaj0Oa04Mt/tgErOpwF6ZgUS2J9JHBG1ZWJsJS0F/mcCHYLjxa7pWCRxnzjLiRrWNJiw3hITkYOLHRZES4wImvmmmJFhwvv3GRUYTBrXZYatTAfbOd8gt3P2sMcCA1GJTxuna0OnJ0IIRBVkxNBk13A8vbCQtEyMRmWMRlJz/97/vQEPvnz1xCWNHDE8EDfuWFp2kT7vcPDsIscnFZj4ipGWKcYmIBV8deg1GtWzR3EclItmPfaPDJd2537hiByXDLvn8RLElwOSri+s3XWMWo1ZkOSismwXLDjQFZ1/PDIBXznhfPJxfTiFhs+eHs3bl/dkbR3m7rb8PihYSxpobCLVxb1MVXDj14awV03deU911zdnU/tL4GoAk3X0eG6Ev5dzZQzZhcYhdLhsqLbU/q6KR+PHxqGwJGkvUhEAz5+aDirA8FlFdDsEGEViqvukG8uTbyf+nsTVQ2A9HHjtgoIRmWMhY001u6OK87fmWPpw0W1snTmqu2cr7D7WXuYA6GBqJTH7ebuNhw86wdHkBSx8QVl7NhYeFhcAl2nGAtJaYJimk7xjefP4rED5wEYYccff8tarO9sSftuk13E5WAsTVyoGGGdemfPgC9tBzV1EjXrfGYtfIs5djV3EEtNtWDea/PIdm3DkoIFcd0DmepAvCoB0Yzd+9s+3V9Svy21tvhMiqmqABgCibsHfHh0/xn4ghIAwG0T8O7Ny/BH1y3OGElwKRBFky0+7RJD06FJ4HBpOlrQOefi7vzM/qLG5yMAaeXdqpG6wuwCo55I2IuwrMIfd2oKHEEog4CryyqgxZG7SkuueTzfXJrr/dRxwxPgxGgQOgCBAzhCMOgL4e9/cNT0Erz5RCCrbTuZM9I85uJc2GjML3WmBifV40aI8VfkCXbuGyrqOM8P+eFxWWDhOejUELPxuCx4fshf1HFkVcfIVDTNeTAdVfBPP/pd0nlw9eIm7HzPhjTnAUcIFjTZ0OGyoqvNiWjKgj21TQkaUfBwz4APf/eDozg1FgalFJTS5CS6Z8Bnyvk+/tQx+IKxtIVvJc5V7LE7Wx1p9xQw7x5u7fXioe3r4HXbMB1V4HXbMtaRnkmlxhJjNtmuraLRK45Bmp5KOxWVS+q3M/vmmfEQHuk/hbMToYKPp2g6fIEYLk5FC3YevHJhCh/6zkv4158NwBc0UhLu3LAE3/rLTXjbhqVZ0xAWNdkRU3TwHIGF55JiioWOjWqOrWoxs7943DZ4XBaEJa2oMW1GW5hdYNSSRU12TEVk+AISVJ2Ci4sXhiQVB4f8cbFVEUtbHfA25RafzjeP55tLc72fOm7GQzJoPMhUpwDPGXYuUYLXLPL9vmrbTjPXZIy5ORc2GiwCoY7I562slMdteDKCDpcVHveVEFFKaVHHyaR3cGI0iAeePobLAWM37k+uX4K7t3SnLaatIg+v25p8rRBhnUBUgciRkncoa8HOfUMISSp4QpJ17ImJdezNDOdKPXYgqmA8JEFSdXz48Zfw+buur0jN5nIoJdSdea/NI3FtgzEFY0EJsqZD5AgEnoM/rIAQwCpwoNSINCJlpCzN7PeZUqDGQzF8+PGX0GQX0+yHrlNMRmQEYmrBQmAXJiPYte8Mnjk1nnztjjUd+MBt3VjSas/7/T+/ZTk+++sTkDUddo5HRFaLGhtzURA201jscFkxHVWw/6N9NW8LswvFw3ZeK8NdGzvxz0+9CgoKDgQ07n9ttgn4wZELuPPGpXhmcLyga51vjVDIPcs216aOG1nTkdRbjP+tRgnefL+vWrYzcR2PnJ8EIcACtw3EQliIfYWZi3Nho8EcCHVCIaGTlSqtV+5x/GEZUzP0Dn76yiV8vn8QikZhEzj87e/14HVXpRvJJruI3w1P4e++dyarOv9MYR2XVQAFoOi0oUJKq13H3syFb6L+88nLQUiqDgKA54CwrGa8F40gWslKe5pHQmNlImQ4C3iOQNEpNKoD0KHpgEIpOGJEH1h4UnLKUr7a4sGYgvGgDAqj+osvGMM/P/kq/lHqxdVLm6HphTkOpqMKvvX8OTx59GLyO1ctcuPeLStx9ZLmnN89OOTH91+8gNFAFF1tTrxtw9KShcMaYWwVSz2NxXpqS6PC0kAqx6buNjgtPCRVh6LpEHkO7U4bmu0CLgdieGZwPOu1BpDmEBj0BeG08BgaCyW1rzpcFlyYjJR9z1LHjYXnoOoaKK1uCd58a6Bq2M7U66jpOjhCcDGentZkF5kzsoLMxbmw0WAOhDqhkB3kSnncSj2OqukYC0lpddAlRcPn+0/h56+OAgCWttrx4PZ1WNHhTH6GIwQdbisOn/Hj/qePF6TOnxDW2bHrAGRNbzihlM5WR1Xr2Ju58HVZeJwaCycfnCgAVQesPEmG9xa6U1EvMO+1edx9RzfufuzFWbtmdpHDdFSHwBNYCElGIChauqhgsSH9uWqLjwUlgABWngMhBFaBh6LpeHT/GTz8jvV5jy+rOv73pRE89sI5hCXD7i1ssuEDt6/A1h5PXuX1l89P4Qt7TsEicGh1WOALxvCDIyNlheTX+9gqlnoai/XUlkaFiZtVluXtLkyEJTitAniOgCMEEVnF0lZH1mv96V8MICxraWutqYiMybCxBklUwRmZimGVx1n2PUsdNx0uC4b9UdD/x969R7l11XfD/+5z0V1zH/k6jj2Jk4kTEuI4hkBwTAqUlGKel1KIaXrhLSuG0oY+faHQlhpw+zwllLes8ELBhodeEoppQ7twaRMKNY6TFtd2HEzjxLGTsZPxdTxXaXQ9Ome/f5yRLGmk0ZkZ3fX9rJU1yUQaHWn2+Z09v/Pb+wd7jy3TsmrSgtfJHKjasTP3c3RrKtKWhJDA2EwSHV6dycgKa7VrYbPhHggNYmQyljeJBubeiVvseu9Ci/k58ZSJC1OJvOTBxek4Htz702zywK0p6Pa6cGV2CQMA6KqClV1eBNzaotaXOvlcGtGOLYMIuDWYUsK0rNl/JIIerSoX0R1bBmGYErFUGuF4CqcvR3B2PIrJaHLJa+4yfyRJAGL2n8z3m+F3UUylziWaa+tQCAG3CpeqwJQSmiqwstOLuGHZ1USmRDJt2QkGYa+TzSxZWkxJf2bcS2mfX7k/L5E2IaVEj8+FVNpC2rTg1hRcCs+/aaGUEgdeHMUH/voIdh8cRjRpwu9W8cCWQfz1B+7Am4dC8yYPdFXB8k4P/uGZc3BpypyY97nHX8D2PYdw10P7sX3PobZeF9tI52IjHUuzatZrdqP6jTdcA8Deq0UAeTGy1Gc9PBadM9dShICZexGfDV9CiCX/znLPG0sCNywPYnWnG6piJ27XhwJV3UDxwMlRTEaTODsexenLEYTjqZLXkgMnR6sWe3M/x/6gG1ICEvbePwu9thE1OlYgNAind5AXknErtaZtoesTp2IpTETzlyz815lx/O9/PYlIwt5AsdOroT/gwlQ8le1TfM+NIfQF3Nk9ABZTZt+sJaW17mOfKed66ImTODseg64KrO7ywrDkkstHI8k0VnV5MDIZhyXtuwqaEDBn96ho9N9FKcxeV8/1yzryzttIwkAybZciuFR7SUPKlHCrAn5dxdreQEVK+nOXQI1MROHVVXh0FV6Xmt3nIGFYWN5Rer+CExem8dUDw3j+YhiAvQTjnbeswK/fuRadPr3k8zKP7fK50OHRshPzwpiXNi2cHY9jbZ2WZR04OYqHnjiJ4bEoAGBdrw+fvPfGup4LjXQuNtKxNKNmvWY3ElWxN0cMejQM9gfQ5XMVLdUeOFj8swYwJyEgAagC0BSRrdJa3uHGTDI97+/M6XyxVudNsa47jx07n53zXI4kcW4qgetDAfzxO/LnW9VeXpP7OQY9OlZ2AZemE5AAQkEPS+yppTCB0CAqXTpZKlC+59xUNtiWC6CmJXElkkQsdbXLgiUlHvnJK/jbn7wCCfti1O3Ts60Yvbp94fnusXNz+povZmLRzCWltZ6IZnZDXtvry/uMl1o+mvm9renx4cJUAkLYd2gVRTTN74Jqq/C8vTSdmN07Q8zuym3HEgHgppWdc5YwLUTheWZaEvffaSAcN3Do5XE8vP804oYJj64gYVhIWxL33TEw5+ecn4rjG0+dwZOnrmS/98brevHAmwYx0FP+j5+gR0eP3wVVuVqZUCzmXY4koStKXUq8D5wcxccfO47JmIHMYb50JYqPPXYcX6hyizVqD818za43RQh0+XR0evW8CqdSc4lSn/W6XnuH+ty4oyoCqhAY7A9kvxdLpbN/2Bb7OXcO9jTUfhbF5rVfOfAyun06Or32puAdXhdiqTS6fK45x1jt5TWFn6OqCIQ6WMVErYlLGBpEpUsnSy0X+MbTZxwtI0gYJs5PxvOSB+G4gT/8p+fwN7PJgxtXBNHl09GVe1dO2L3QL4UTc46psNzYSUnXYj+XapapNbJqlI9mfm+qIrCi0w0BwJQSa3t8vDBSUYXnrQTQF9AhBGBZMtva1LCsipWYWpbEZDSFkYkYpmIpWFJi82APPnrPevT63Ygk0uj1u/HRe9Zj82BP9nmRhIGvHngZH/irI9nkwQ3Lgvjie2/Fn7zr5rLJA7euYmWXF/1Bd17yACgd85Z1uPMeV6sS790HhxFJpHMSOfZ66JlkdVusUfvgMpCFy7RjHOjxocvnKru3SkbuZ30pnMCVSBLRpAHAnq/lxp2AW0PQoxWdf5X6nf1keKKh2poWm9emLStbCZtRKp5We3kNxz61E1YgNJBK3rEutVwgmjKxpkwAnY4ZmIil8lqbnb4cwaf3PZ9NDGy7dSV+a+u1+OR3/xvj0SS8ugoh7E31SlUVLHbX1IV+Lu28C3Q1ykcLf2+3relmKR6VlXvebt9zaHZc6hibsVs7qorAYI9/ySWmUkpMxw1Mx42iXRU2D/bkJQwyDNPC9356AY8ceiU7AQ0F3fjgm9bhnqEQlDKTeFUR6Pa70OEpvayhWMzLbPSYq1Yl3iOTMaQtC1pOa10h7KoNrlGnSuEyEGfsxIGGTq+e1+56ITKf8859J9DpFdkKArvDjYLpuIHV3T788Ts2ACg9/yr2O/vU955rqLamxea1blXJLo/LKBVPa7G8hmOf2gUTCC2qVKD0u9Q5pW2ZAGpZEqMFSxYA4PHnLuHhfz+NVNregOx/vvV6vG3DMgB2n+KH959G0jQRcGllyxVrEVzbeRfoapWP8qJIS5EZl7oqsK7Pnx2Xn7z3xrzHLeTclVIinEhjOmYgbeVPIOcjpcRTp8ew56lhXJhKzL6OivdvXoNf2rgK7oIEazHFliuUUnjuZJIk9SjxHuj2YSySnNNiTVUE16gT1YgQAp1ee6mCkxhSTrG4CQBdPhce/90teY9dyHW80fazKHY8nT4dE1HDUTzl8hqiymECoUWVCpQfvGsdHjt2fs73P/CGtTg/FYeRc2cslbbw5R+/hO//7CIAYEWnXY51bejqGrrXXduLT3k0PPpfr1akF+tCN3gs9pzToxEs7/DkPaZddoFmb1xqRE7HZalNB4+9Oom7HtqfjQm3r+3GVMzIi1cZh4cnsPfICC6G41jR4cV9dwxkKxBeuBjG1558Gf993t4gURHAO29ZiV97wzXZfVzm49IU9AXc8DhIMpRSz3N0x5bB7B4IUtjVGpYEutzVbbFGRFcrDrq8el4V0FItZoNqJxbzB/di5nDlZH7mqcthzCRN9Ph19PrdiBsmdFXFR7auwU+GJ8rGU86PiCpH5JapN6pNmzbJo0eP1vswmk4m6BYGysLv3/+6NdiwqjNvycLlcAKf+efn8eKlCADg9YM9+IN7hxDMKdfVFAWhjqVNpguPN3OXMvdiNd8asmLPOTcZR49fR1/gahIhs1nQUjZrI6qipd+GcqDRY+nVpQ5Xuzecm4xDUwWu6w8gmkojaVh4sGAfg4zDwxN4eP9paIrI2zTxV193DY68MoEfv3h1g8TX5Dib0AAAIABJREFUD/Zgx5ZBXNPrL3tcQgj0+FxluzA0g0bswkBUQTWJpQDwmtdulN/74UFHj/W7NfT4XYteqjCfwrgJVG7OU2oeWeqxC53DOXn93J85NpPEZMxA0KNhfSjIBABRdZWMp6xAqIFqZGSdKFY6u33PoexxfPadN2HDqs7spjoZR89O4E//5QWEE2kIAB9441q8/3Vr8tYEe10qQkFPRcrvMhaz9KDYc7pnS9p8Lo1lakRNpFj3BgDoD7hhmBK6oiCtSOw9MlI0gbD3yAg0RWQ3ynKpCqZiSfz5v72ITIS7LhTAh+4exMY13Y6OyetS0RdwV2Xi71QlryFcjtQ66jW3IOd01a5a8roqc6OlmPkqBXLHSNCtQUqJmZTpeLwsJF5UY/lo4c/sD3rgd2u8IURUZ0wgVNmXfnQKXznwMtKWBRXAaDiB3/zbCVwfCuATbx+q2cW+cHOyS+E4/uh7z+XtSG5JiW8ffhV/9R9nYUmgw6Phj95xI+5Ymz9R7/K50OMvX+67UIspwyv2nL6AG2nTQijoYZkaURMpLDG1pN2xwKur2SSnR1dwKRwv+vyL4Tg6PFp2Y8WxaAqZfRX7Ai785l3r8NYNy8pukAjY+wL0+F15VVf10M6bwrYrJ4mBYuPiY48dR3/AjUgyzYRCnemqgi6fXpH4UW48lCrNB5AdI6oATo/OAABWdXmqEkeqsZSiWssziAlIWhomEKrowMlRfOXAy7CkhAIgZQGAhKYAZ8aiNZ0EZrK4Xl1F2pp7J28mkcafPX4SPxkeB2C3Mfv0tg15ewkoQiDU4c4rk6ukxWzYU+o565d1MDtN1ITuvqEfm9b1YDpu4COPHsN4NJn3/xOGheUd3qLPXR704PxUHNMJA4ZpZw4EgGUdHnzzNzY5Xm7V4dXR43NBqWCF1WK186aw7chpwqhwXKRNiamYgZlEGteFAkw01YmqCHT5XOjwaI7bMc7H6XgoVimwfc+h7BgZvjJjV4xKYGwmhcH+QMXjSDU2XWy0jRxbBRPTtFT1q8lsA7sPDsO0JFQhMDuXhYC9aZUpZU376Y5MxuDWFBimhGXl38l7+coMPvStZ7LJg1+8ZQUevu+1eckDl6ZgVbfXUfJgsX3cS/VMn2/pwWKeQ0SNx7IkpmMGRibiGA0nkDRM3HfHANKWnG1LZn9NWxL33TEw5/mnLkcQTqYxFk1lkwd+l4r+oBu/+3PriyYPDg9P4Pe+cxzbv34Iv/ed43j21Ums6vaiL+BuiOQBUP3e5dRYivW6LzZXKBwXYzNJKMKeW8z3PKoOIezEwUC3D51efdHJg8L500NPnHQ0HorJHSMp04IQdveVTBvZSseRaszHOMerDqdxhqgUViBUUeaP9rQpkd1iQNgJBK+q1HQSuKLDg0vhRN6EI2FYcKkqfvvvnkUybUFXBX73Ldfj3puXZx9zeHgC//DMOVwKx9Hh0cuun1tKVnMxO+RyV925WJZGjcLJWDQtiXDcQDhhwLTyN/XdPNiDj2I99h4ZwaVwHMsLuioA9rKwbzx9Bj964WqiMujW4NIEBrr9cx6fkbvhoiqAFy5O4/e/+zN8/eBwyU0F63Fu8Q5ce3Fasl04LlKmBQF734/5nkeVF5jdIHGpnRWKzZ/OjsewumtxXaVyx4hLVZC2JCCvjpFKxJHCmPiejatKdkRYTPxc6ByP8x9nuDSElooJhCoa6PYhbVoYj6auflPaVQj9QXdNJoFp08KVmSR+aeNqPLz/NOKGCY+uIJ4yMREzEEuZAIDlHR58ZtsGXL8smH3u4TMT+PKBl+DWFGiKcLR+bqnltovZ4Iubgl3FsjRqFOXGomnZ+xSE4waseboBbR7sKZoAiCbT+PbhV/HYsfNIpe07aoN9fuy4e3DOvi3FZDZclACuRFJQFAEVwNmJWNFzpl7nFnuXtxenCaPCcaEqAmlToj/onvd5VDmKAFZ2eSvWiarY/ElXBS6Hk+jwXt13yunvNXeM9AVcOD9lb0q7POCuyJ38YjHxsWPni3ZdWOrNJScxlvMf55iYpqXiEoYq2rFlEC5NRa/fBZdql7NJAP0BF1RFVH0SGEul8Y/PnMOHHzmGL/77KXg1BbqqYCpm5CUPNq/rwdfu35iXPNBVBf/07Hm4NQU+l4axmRRURUAVAmMzKcdllUDrZDUXuzSjlliWRo1i98FhpNImLk0n8OLlCC5NJ5BKm/jqky9jbCaJVydimIql5k0eFGNaEvuOX8CvffMw/u7wCFJpCz1+Fz72tuux+1dvd5Q8AIBL4TiCbg2TUTt5oAj7H9MqvrysFudWsRizdSiEXdtuQijowXTcQCjoWVJbNGpsTku2C8fF2h4fun06VEWw1LtGdFWpWPIAKD5/WhZ0w7CsouOh3Jwkd4xYElgfCuC6fj8siYrEkYXExFrEz8W+RjPM7SqNS0NoqViBUEW5pVe6GoPfpUIIgZmk3Z+3mqVVk9EUfvDcpWyJbodHQ8KwEE0ZSBoWYikTAsCv3XkNfvXOa/J2Jfe7NfQH3Dg/Fc+WOKVMK9uycb71c62a1WyWzDbL0qhRnLocRjiRhgI78WikLYzNJJE0TITjxoJ/npQS/3VmArufHMYrE/Z49mgK3nvHAN63acBxmzQh7HN4ba8fV2aSebFNzpb3Fjtnqn1ulYsxjRRnqHoWUrJdrFUzl/M1r2LzJ01VsL4/gG6/u2SHhYVurlgpC4mJtZibLOY1mmVuV2lc/ktLxQRClc0XvDNZz0qu1bIsidFIErFUOq8nupTSXrYQtSfuQY+GP/yFIbxuXW/e83v8LnT57FK5xayfK1ZuOx034FIV3PXQ/qZdk9YsO6G3agKHmk+2C8JsblIo9gYwKXNhFQeHhyfwV/9xFmfGZ7LPFQB+/qbl+MAb1+aVbJfjdano9bvh0hR86O5rsXPfCahCwLKkvcEtJPoCnqLnTLXPrWaJMVR9xRIDTuYKTDQ1t1LLlf74HRvm7bAA1CdeLCQmVjN+ZhJnVyJJjM0ksSzoQcdsIqHcaywk7rba/gqMF7QUXMJQJ5ms52gkkZf1XErpVMIwcX4qjlgqDcDuie7RFZiWxMVwAmOzezFoisDX7t+YlzxQFYEVnd5s8gDIL3HqC7hgWhKmlOgLuByXVeqKgIBdtVCp97lYX/rRKdzymR/g2j/8V9zymR/gSz865fi5zbI0g2VpVE8HTo7i7V98Ejd86nGEE/bYM0wLFqS9VEHaHV2c+uGJy/js95/Hi6ORbPLApSn4nXuuw++//QbHyQNNURDq8GBFpzf7+plYta7PD1MCQgFWdnqgqcWXl1X73GqWGEO1VY25AjWmhSxXyo0XkYSB4SszeGU8imOvTtZsbCwkJuY+NhxP4fRoBGfH7WVsSzne3PNjeYcbaVPi/FQc4XjKUYx2Gnd5HhLlYwVCnVTybpOUEpMxA1OxVN73V3R4cSkcx3hBW7Nr+wNY0Xm1j7pbV7Es6J6zg3BhidP6UABSSkRT5rxLMHKzmtv3HIJhybrfVfvSj07h4f0vQRGApthZ6Yf3vwQAePAt15d9frPc2WdZGtXLgZOj+Nhjx+09BXI6mJkSsNISHl1BwKthVZe/7M+Kp0x858gIHv2vV5BpzOBSFfQFXFAEcPDUGP7HbascHVenV0e3z1W0LWMmVuWWfpeKbdU+t5olxlBtsTKlvTi9K5yJF6YlcWEqASEARQgIgZqV4C90uc0uAJ97/AWcHY9DVxSs7vIgZVpLOt7C80MIgUvTCVwKJ7FxTXfZGO007vI8JMrHBEKdVGo9mGFaGI3Y64oLDS0P4vi5KUjYJb9dPh0eXcX7N6/JPibo0dEXcJXsWbzUEqdGWZP/jafPzCYP7CSJIoC0ZeEbT59xlEBopp3QWZZGtSalxFcOvIRwwrA3I1QEdEgYs3/9e3QFfQE30pbEfXcMlPw5piXxxHOX8Ff/eRYTsxVTqgB6A250euyNsSQkLoXjZY/JravoC7jg1srvjeD0nKnmudVMMYZqp1GuodRYMvFiNJwAIAFpd5RZFrSrqGr1h+1CYuLWoRB2HxzG2pybSgCW9Id44fkR9OgIuDVMxw18+4HXl32+07jL85AoHxMIdRJwqXjpyky2/ZgQAroqsLbH+d2mmWQaY5HknF3MDdPC7ieH8Y/PngcA6Kq9iWJuT3QhBHoDLnR49GI/umIa5a5aNGWisHJaEfb3C5Va58Y7+0T59j9/GX/55Ms4NxnDeDQF05LQZu/0X00iAMm0hV6/Oxt/ijlydgJfe3IYZ8aiAOylCt1eHZoq4M+JHwnDwvIOb9GfAdh34br9LnR6qxvbKq1dYkyx+AqgpdYWV1KjXEOpsWTixY5Hn4GEPc/rC9hr/6WUVf/D1sl+AMUeU+k/xHMrMa5EZjfFFQLr+spXugHO4y7PQ6J8TCDUwYGToxiPppAyLFiZb0oJSInxaCrbuqsUKSXGZlKIJObuZD42k8Suf34ez10IAwA2XdONP/qFG9HpuxqwdVVBf9Bd0fZDpTTKXTW/y37t3CpmS9rfz8Wd0InKS5sW/vW/L+LPHj8JTREIejRMRFOwpF1FoKmZnRMFXCqwYUUn/uJ9txb9WcNXZvC1J4dx9JXJ7PfetmEZ/u83rsXZsRge3n8accOER1eQMKx5qxj8bg29ftec5VjNotVjTLH4+vHHjkPCXmrSTrugO9Uo11BqPFuHQti4prvmf9g66VxQ6jFBt4a4YVbseHdsGcTHHzuOyZgBRdjVtmlL4spMsuxcOsNJ3OV5SJSvarMsIcQ3hRCjQojncr7XI4T4oRDi9OzX7mq9fiPbfXAYHV4dLk2BALL/6KqCDq8+b89aw7RwfipeNHlw/NwUdjzyTDZ58CuvW4M/e/dr8pIHPpeGlV3emiQPgIVtClRNH7xrHSxpL1uwpDX71f5+rlr0KiZqVsm0idFIAiOTcXzz6bPZLi8CAv1BNwRm9zywrNl/JPxuregf/OMzSXzh317EA488k00evHagE1+7fyM+ee8QQh0ebB7swUfvWY9evxuRRBq9fjc+es/6OVUMuqpgeacHyzo8TZs8aAfF4mskkcZMMs2YW0KjXEOpMdVj42Qn86RSj5FSVvR4tw6FZpPGYrYSQ8GqLi86y8ylF/M6PA+JrqpmBcJfA/gygL/N+d4nAfy7lPJzQohPzv73J6p4DA0pU8JlSgm3pmTX9ZqWnLeUK5pM40qRJQtSSjz2zDnsPjhs31V3q/iDe4fwhmv78h7X7XOh2+9CrTXCXbXMPgffePoMoikTfpeKD961bs7+B1znRjRXKm1hMpZCNJnOfu9iOI4Oz9VLiN+lYUWnG5fDyWzvxmt6fHjgTYN5f/DHDRP/cHQEe4+MIGHYNVgD3V7suHsQdw72ztmPZfNgT8llD0KI2U0S9ZL7uFDjKBZf05Y153fHmJuvEa6h1JjqsfTJyTyp1GOm4wb+5F03V/R4Z1ImrusP5MWRaizj4HlIdFXVEghSyoNCiLUF334XgK2z//43AA6gDRMImbVULlVB2pQQwl7B4FKVoqVcUkpMRFOYjs+tOoil0vj8D17EwVNjAIDBfj8++86bsKr76hphRdh3B/1u+9fdar1snXrwLdeX3TCR69yIrkqlLUzFUpjJSRxkrOjwYjyazGuBpSoKXrOqq+hyBdOS+OHzl/F//uMMxmfsDRI7vTp+4w3X4B2vWbHgygGPrqLX4SaJi9GucbKaisVXTVHsErwcjLlE+eaLR7X+w9bJPGm+x1T6eDlvI6q9Wtd6LpNSXgSA2a8lI4gQ4gEhxFEhxNErV67U7ABrIVNyFvRosCDtcnpLosOrzSnlSpsWLkwniiYPXhmP4re+9Ww2efDWDcvw5e235SUPdFXByi5vXvKAvWxLq0c5IFE1LSaW2t1dEjg3GSuaPACA++4YQNqSiBsmJOyvpfYnOPbKJD706DP4/A9exPhMCroqsH3zAB75zc1412tXLSh5oCn2Hi4ru7xVTR4wTlZesfga9GgIuDXGXGoK9ZibNlo8cjJPquVcivM2otoTsqAcvqI/3K5A+L6U8ubZ/56SUnbl/P9JKWXZfRA2bdokjx49WrXjrIdMNvn05TBSpoRLU7A+FMzLKkeTaYzNJGFac39HT566gs8/8SLihglNEfjIm6/DtltX5JVw+Vwa+oNuqDk7B27fc2hOpjaWSiMU9DhqedMOcnvCt+pO6NRwalJ/Xy6WJgwT4biBaMqEk2vD4eEJ7D0ygkvhOJZ3eOd0WTg7HsWeg8M4NDyR/d7PDYXwm29ah+UdngUduxB2N5lunwuKUt2Pi3GyeorFV6D1u09QzdRsLVOt5qaNGI+czJNqOZfivI2oKkrG01onEF4EsFVKeVEIsQLAASnlDeV+TismEOYzX5cF05L4+lPD+Puj5wDYS43dqgKPrmBtbyB79++xY+dwKZyYU+p210P70eXV56wVm44beOoT9yzoOHNL6oJuDVJKzKRMlvsSLVzdEghSSkSSaYTjRrat7FJNxlL4m/98Bd//2QVk8p+vWdWJD28dxNDyjnmfm0lKXAzHsWI2KfGmG/rR52C5QqWWHZSKk5fCCawPBXHqchjGbOK3P+Bm7CNqHC2XQCiMR5GEgdFwAnHDQtCjFb0BVSnNvJRrKcfezO+bqIJKxtNat3HcB+DXAXxu9uv3avz6DaNUcEoYJq5EkjDMuRP5iWgKf/L953H83DQAu++vZdpLIGaSFs5NRvHQD05CFUCnz1W0vU6l1orltuhRBXDqcgSmBBRht5L82GPH8YX33MqAS9SgLEsinDAQjqeRthafOMj9g39Z0IMVnR489dIYYikTALCqy4sHtgziruvmbpBY7Gc9vP80NMWuNhiPJvHlH7+E5Z0erCoTS5y0FnOqWJwcjyYRSaRxZmwG4YS9rCOaTGMymoIQAqu6PGxB6AAn5kQLkxuPIgkDF6YS2ZgdN0zEUybOjs9UPPbMF1MBVPU8XmqcWMr1oJLXEqJWVc02jt8G8BMANwghzgkhfhN24uCtQojTAN46+99tp9R6tu8fv4CL04miyYPnzk9jx6PPZJMHQY8GVQCKKqAqCgQEoikTsVQaM0mzZHudSq0Vy23RczmchJlTyCItYCpm4HOPv7D4D4mIqsK07E1ZX52IYSKaWnLy4OH9pzE2kwAAnLgQxg+ev4xYykSHR8Nvv/lafPM3NuFN6/scdUnYe2Qk2xpSEXZbW7euOGrHVckWrMXi5ETUQLdPRySRhgIBTVFgScACoAqBsZkUWxCW0WhruYmaQW48Gg0nICEhJaAqdhxSFIFwPF3x2FMqpn7u8Reqeh5XIk4s5XrAdt5E5VWzC8P2Ev/r56r1mrVSKjPqNGOaG5wAu7VN2jTwjafOzNm9XEqJf3r2PL765DBMS8LvUqGpAqGgG2fGotm1wIqwNz4TQkDK/D8IctvrVKrlT26LnkRO2bMlAUtKKAI4M842XESNxJISIxOxOa1gF2vvkRHEkgbCSRO5P7I/4MY3fv12BD166ScXkWkNqalKdu8Wpy39KtmCtVicnIql0BdwYzyagjqbDJEAhLSXkqVmE79sQVj6Gll47fO57M0Tdx8c5p29Ilit0fqc/I5z49HZ8Rg0xW79nbYkLGnvg5VMS1yciuPseAzb9xyqyFgpFVNPj85gdbe3audxJeLEUq4HbOdNVF6tlzA0vVKlTe85N4XHjp13VPKUG5xMy16C4NIUXArH8x4XN0z8v/92Cvtns65re3347Lab8MUfnsZ4NAldVZC27D/WJQTcmgJTSkCKOT8nd4lC5ngyF61MVnUhgT9TUldsg0fDklAFoKnsy07USDIJvqXILFkYmYxiPJq/T4uAncxMm+aCkweAvdxhKpaCR78aO5wusap0K6/CVmOZjcxy2+8KAMhpw7vU12wF85X/cmLuHMuoW99CfseZePT2Lz6Jl65EIWAnMKUEUqaEAGAIwKMpCy7XL5XAKBVTAeS17838d6XO40rEiaVcD9gWkqi8WrdxbHqlSpu+8fQZxyVPA92+2aUDFtKmBUggYVhY3nG1/eLIRAwf+daxbPLgnqEQvvIrGzHQ48u2Twu4VUhLwpQSFmS2HVbQM39LrEqUh2VK6i5NJ4r+f0sCg31+xz+PiBrf4eEJfPFHp/DSlcic5IGuCrg0ZfZu/MKSFIoQ6A248eA965G2sKglVtVu5VWs/a4i7IuoKSX6Ai62D8P85b8D3b7sHyAZnJgXxzLq1reY33FmKVim820m0ma+9gXcjsdKublgqZg62Oev6nlciTixlOsB20ISlccKhCLmy8iWyoxGUybWOMzI/vqd1+Cz338ehinh0RUkDCuvf/rTp8fwuSdOIpYyoSoCH757EP/XbauyF47Ngz34n8p6fPeZ83gZM0ilLbhUgXV9gbyWWLktInOrDCpRHpYpqdvx6DNQFQHLksj9k0EI4BNvH3L0s4io8aXSFr60/zRGZ5IoVsQgxGx1gwRcmvPctM+loTfggq4qS1pitZDnLqY0PPfnp82rsTXThSGaMhEKetq+zHy+u4d/8q6bsXPfCcRSaXh1FXHD5MS8hGao1uASi8XJfG6Hz07ArQqEOjzZiq1yv+NIMo1VXR6MzaRgzf6RbUm7GmplpxcdXmc/Byi/VKBUTAVQ1fN4x5bBJf/8Wl1LWh3PcSqFCYQC5UrKSpU2+V12kJuv5MmyJMaiSVy/PIiP3rN+Tv/029d2Y8/BYew9MgIA6PW78Ol3bsDNqzrzjtGlKXj3xtV47x1r5n0vO/edQKdqb0hWjTLSrUMhbFzTnV3KcCWSRMq0oAqBdX1+BhmiFiClxI9fvIJvPHUGl8J2xZEi7PgUSRgwTAlT2vFNVxUEvBpWdZWvPtIUBb0BF/zu/MtQ4dKBhXDy3KWUhi/l2NrFfOW/nJg71+hl1FxisTi5n5tHU5AyLVyYSmBlFxD06GV/x5lxMdgfyH7v9GgEkMgmDwBnY8XJXLBUzKvmeVypOFHta0mr4zlO82ECocB8GVkAmIwmcXY8Cl1RsKzDDU1VYJgSH7xrHR47dr5kxrSwPePmwR5sHuzJvu5ULIXf/+7P8OyrUwCAW1Z3YucvbkCP35V3fH63hlDQXXZH8/neRyUnJplMsa7aSYPM+2b1AVHze+78NP7ywMs4eSmS/V7ArWJZ0ANVsZcsXJpOwKUJXNPjm1NNVYwQ9mSk06tnN4GtJW7kV13l7h624sS8GnfpKnEXtpp4Hi1O7ufWF3DjwnQcEhKj4QRURZT9HRcbFwG3BgEseKwsZS5Y7fO4FeNEoykXt3iO03y4B0KBkclY0c1hTl8OY+e+EzAsidVdXkAA56bsDbV2bbsJD77leuzadhNCQQ+m4wZCQQ92bbsJd9/Qj/GZJC5MxYu2ZwSAFy6GseORY9nkwS/fvhpfeM8tc5IHXT4XlnV4HLVDK/U+zk3GKrq+a+tQqOj7ZnAhal7np+L4zL4TeHDvT7PJgzet78PH3no9gh4dKdOChIQiBDq8OlZ3ehFJpNHrd+Oj96zPS47mCnp0DHR70e131SV5AMwfG2np2u2aUK3WlI3+OfI8Wpzcz63Dq2NlpxcuVUHSlI5+x8XGxRfecyv+/D23LniscK1/+3ISt3iO03xYgVCgVEY2ZUp05mTiOrz2hlldPlc2SBdmTJNpE+en4kiliycOpJTYd/wCvvLjl5G2JLy6io///A3YekN/3uOEEOgLuBa0q3kty0iZKSZqDeG4gUcOvYLv/fQC0rMdVm5YHsSH7x7ELau7ANibdOUuv/rI1utKJgwydFVBf9ANT8FkpB4avTS8FbTTNaGad+ka+XPkebQ4hZ9bh1efbc3twbcfeL2jn1FqXCymxJ9LitqTk7jFc5zmwwRCgVJlgy5NWVAmbiqWwmTMgCzRMi1hmPjij07jh89fBgBc02O3aFzTm39iqorAsg7Pgife7VhGSkSLk0pb+N5Pz+ORQ69iJpkGACzrcOODdw3izUP9UHKqngqXX81HCIFOr45un+6ocqoWGr00nJpLM2x2WA08jxan0T43zgXbk5O41WhjlRoLEwgFSmVkdx8cdpSJM0wLo5EkkgUtaHKdn4rj0/tOYPhKFABw9/X9+PjPX5/3swH7rt3yTg90deErTZhZJqJypJR48tQYvv7UMC7OtmT1u1T8yuvW4N0bVy+om0Ihl2ZXHbi1+lcd5GJspEpq17t0PI8Wh58bNQIncYtjleYjSt0hbySbNm2SR48eresx5O5GmpuJy11nNh03MBlN2a3MSvjPl8fwZ4+fRDRpQhF2hu89t6+ec3fOo6tY1mFvVEZELa8mJ/prN94u//EHTwIATlyYxlcPDOP5i2EAdmeFbbeuxK/deQ26fK75fsy8hBDo9tmbJDZK1QFRtTiZG1BN1SzoNMLclGgxGLfIoZLxlBUIDhVm4vwuFS5Vwae+9xxWP+nF+zYN4NY1XSWfb1oSf/2fZ/Gt/3oVANDt07HznRtw6+q5zwm4NfQ76LRQSez1StQeLk7H8fWDZ3Dg1JXs995wbS8e2DKINT1z75oeHp7A3iMjuBiOY8Vsy9lSSxh8Lg09fteSKheI6m0h10PepaNGUIs5HOeJrYNxi5aKFQhFlAuSuZk7l6ogOrtzbandx6djBv70X1/AM69MAgBuXtmBne/cgL6Ae85ju30udPuL3/2rVvB2monkxYOoamqSLVx53U3S/74/h2HacX99KIAPb70Wrx0onvw8PDyBh/efRto0EUmkkTIlVEXg/s1r8KtvWJt9nK4q6PG74HdXPifNuEO11K535lroPGu7CoRajNmFvMZSx1ILjUVqEBxTi1YynvI2UQEnrU12HxyGptiTZtOS8GgqNEVg75GROT/vxUsR7Hj0mWzy4N23rcJfvPfWOckDIQT6g+55kwfVaBWVeT+Z3ViFsL/qqsDug8M1eX0iqo33TEfUAAAgAElEQVTxaAqGKREKuvEH9w7hq/dvLJk8AIC9R0aQNk1MxdIwJaCpAlJKPHr4VRwengBgt2Zc1eWtWvKAcYdqycn1sNXwPGtutRizTl9jqWOJY5EqjWOqOphAKOAkSL46EYWmKLCsq9UbHl3BpXA8+99SSnz/Zxfx4N5nMRpJwqMp+NQ7bsRv33MdtIJNEVVFYEWnZ942jQsJ3tv3HMJdD+3H9j2HHJ0gTnq9tuOkiqjVKELgg3etw9984A68dcOyvO4KxVwMxxFJpAFhP1dAQBECliXxnaMjWNbhQX/QDaVKe7Vk4o5pSZwZi+LViRhGwwk89MTJqrweUTv2Puf1vbnVYsw6fY3csTSTTOPSdALnp2J4cO+zjuajHItUaRxT1cEEQoFyQTKaTKM/6EG8oMtCwrCwvMMLAEgaJr7wb6fwFz88BcOUWN3txVd+ZSPuKVIuo6sKVnZ5y7ZpdBK8F5tlG+j2zXk/hbuxtuOkiqjVXBcK4P2vWwO3w7awKzq8SJkSuXkGKe0OC1ciiapUHeQamYwhbVq4MJVA2rKXT1hS4tToDO8eUFU4uR62Gl7fm1stxqzT18iMpUjCyMZtTRGIpUxH81GORao0jqnqYAKhQKkguarLi4loCpfDCdy2uhOXwgm8dGUGr05EMRlLIm1J3HfHAC5Ox/E7e3+Kx5+7BAC467o+/OWvbMS6Pv+c1/K6VKzq8jpq0+gkeC82y7ZjyyAMUyKWSkNK+2thr9d2nFQRtZqFdnW5744B+492S0JKCWlJSEh0enUM9MyNaZU20O3D5XASIqcCQkDw7kGTWkyFXK05uR62Gl7fm1stxqzT18iMpSuRq3EbUsCtKY7idiONxWaIV1ReI42pVsIEQoFiQTKVtvDLt6/GVCyFw8MTeOL5y+j0aHBrCgxTYiqexts3LIMUEh969BheGp2BIoAHtgzis9s2IFDkLl3Qo2N5h6do6W+xoOUkeC82y7Z1KIRd225CKOjBdNxAKOiZszFOO06qiNrd5sEe3L95DYSwlxFoqkBfwA2Xptbk3N+xZRCGZdnJCylhWRIWJJYF3TW/e8DJ5NI0yzpUJ9fDVsPre3Or9pjNbEAXS6VxJZLEpel4ydfIjKVE2gRwNWb3BdyO5qONMhabJV5ReY0yploNuzAUkQmW5yZjWN7pwXs2rsYd6+zuCr/3neMYjybz/lCPpdJIW8DlcAISQJdXx6d+8UZsXNM952cLIdDjd6HTW3y/g/l2ugXmb7myfc8hjEYS8LmuJixiqTRCQQ++/cDrK/q5sOULUUXVZOfw1268Xf7jD55c0HNUReD5C2H87U9eqcu5//YvPomzEzGYloRLVdAXcENTRcXimhPtujN/JVX7+kRL00LX97brwlBNi4l9B06O4sG9zyKWMuHW7Jjd4dUdn++NMBYZr1pLI4ypJlUynlZ3AWuT2joUwl3r+3BlJol4Kr/s5WI4jg7P1Y/NtCQmYgZis4/bsCKIT7/zJvQH57ZoVBV70ut1lV5/nLsMAbD7qsdSaew+OIxvP/D6eQf8ji2D2LnvBGKpdF6gr1SWbetQiCccURsJuDX0Bty4ptePe1+zoi7H8Ml7byw6ga3l3YP54jJjojMjkzF0FSTOuQ61cfD6TsUsJvZtHQrhS/fdlhe3F3LXtxHGIuNVa2mEMdVquIShiHDCwLnJ+JzkAWBvKpYwLABAwjDx6kQsmzx412tX4ovve23R5EFms8T5kgfA0jb7aMfSSyKqPE1RsKzDg1CHZ8H7JlRaI8Q1bsK0dFyHStR8qrk0tpExXhHNjxUIOSxLYmwmiZlkuuRj7rtjAA/vP40rM0lMxQxkFoC8b9Nq7Lj72qLP8bpULAsW3++g0EC3b07Z1EKCFrNsRLQUAY+GXr+77omDXPWOa0uNy1T9CjkiqrylxL56x+2lYLwimh8rEGYl0ybOT8XnTR4AwGvXdGGg24fJ2eSBS1Xw0XuuK5k8CHi0kpslFlO42cfYTALnJuM4dTnMjbuIqGo0RcHyTg9CwcVXHbTqRoPchGnpmv2OJFE7Khf7WjXmM14RzY+bKAKYjhuYiKaQ+1kcHp7A3iMjuBiOY0WHF/fdMYBr+nz4zD8/jxcvRQAAdw724g/uHULAU7yQo8fvQpfPteDjyWz2cXo0gkgijW6fjr6Amxt3EbWuum6iGPTo6PW7HCc6i2n1jQa5CRNVWmZMjUzGMMAxVSncRLHCSsW+TMxPpU1EEmkk0xZUReAjW6/Fg2+5vt6HTURLVzKetnUCwZxdshAtqDo4PDyBh/efhqYIeHQFCcNCNJlGIm0hljIhAHzgjWvx/tetsXvcFhBCoD/oLtq+cSG4CyxR26hLAkGf7WpQbm8WJxiviJxr9YRbHTGBUCPb9xzCmbEZjEdTUCAgBGBKCUUI7L7/do5jouZXMp627RKGhGHi/GR8TvIAAPYeGYGm2Bd1SCCWMrOdFjo8Gh76pdfg/tdfUzR5oCoCKzo9S04eANy4i4iqp9OrY3V3+Y1dnWK8InIud3d7Ieyvuiqw++BwvQ+NyJGRyRgiiTQUCCiKgBACqiKQtiyOY6IW13abKEopMRFNYTpulHxMplWjaUlcCicQne2yoCkCu3/1dizr8BR9nltXsSzohqZWJi/DjbuIqNJ0VUF/0A2PXpnEQQbjFZFzbBNHzW6g24dL0wloOUvfpATcqsJxTNTi2qoCIbNR4nzJA8Bu1RiOp/HqZCybPPC7VGxY0VEyeRBwa1jZ6alY8gDgxl1EVFmqEFjd7a148gBgvCJaCLaJo2a3Y8sgVEXAlBISEpaUkBLo9Okcx0Qtrm0SCFOxFC5MJZBKW2Ufe/2yAC5HkjBMCQGgx6ejw6vj/ZvXFH18j9+FUIcHosiShqXgLrBEVElCoOJxKoPxisg5Jtyo2W0dCuEjW6+FIgQM04IqgN6ADl1VOY6JWlzLL2FIpS1cmUkiWZDpL8YwLfzlj1/G945fAGC3aAx6VAx0+3HfHQPYPNiT93ghBEJBN/wV2O+glGbuo0tE7YXxisiZrUMh7ALY2YOa2oNvuR63rO7iOCZqMy2dQJiOGZiI5bdnLOVKJInP/PMJvHDRbtH4unU9+PkNy7Hv+AVcDMex98gIAGSTCJqiYFmnG26tfCkwWzUREV3FmFgf/NwbCxNuVA/l4sBC4wTHMVH7acklDIZp4cJUHOPRpKPkwbFXJ7HjkWfwwsUIBIDfeMM1eNetK/H1p4cxHk2iw6NhPJrEw/tP4/DwBFyagpVdHsfJg537TmA0kkCXV8doJIGd+07gwMnRCrxTIqLmwphYH/zciahcHGCcICInWi6BEEkYOD8ZR8LBkgUpJfYefhW//9jPMBU3EPRo+N/vvhm/duda/P3Rc9lWjgL2V00R+PtnRrCy0+t4s0S2aiIiuooxsT74uRNRuTjAOEFETrTMEgbLkhibSWImmXb0+JlkGp9/4kU8/dIYAOC6UACf3bYBKzq9AK62cszld6kYDSegKM43IWOrJiKiqxgT64OfOxGViwOME0TkREtUIMRTJs5Nxh0nD86MRfFb3zqWTR7ce/NyfHn7bdnkAWC3ckwYVzs2aKoCw5IY6PEv6NjYqomI6CrGxPrg505E5eIA4wQROdHUCQQpJcZnkrg4HUfaKt+eEQD+/YVRfORbx3BuMg5dFXj3batwcSqBX/+rw/i97xzH4eEJAMB9dwwgbUnEDROqIpBMm0VbLB04OYrtew7hrof2Y/ueQ3PWibFVExG1snIxsBBjYn3wc6+/hZ4rRJVWLg40Q5yo53nEc5jIJpxsMlhvmzZtkkePHs37XjJt4kokiVTaWeIgbVr42sFh/OOx8wAAXRVwawqSaQtdXg1dPhcShoW0JfHRe9Zj82APjp6ZwHePnceF6Xhea5rMDrWnRyOIJNLo9unoC7gRN+wkQ2Hv88zj2eKGiEpwvi5qCYrF0qXIbLilq/Y+MaViYLHnNUNMbLWuBc3yubeixZ4rra4K51hNYilQ+XhaK+XiQL3jxHxjop7nEc9h51rt2tnGSsbTpkwgLKQ9IwCMzSSx65+fx3MXwgAAl6agz+/CZCwFw7QgIBDqcMPv0hA3TPT63fj/3n8blnd6oBdslpgbQC5OxWFY9jGs7PSiw6sjlkojFPTg2w+8vkLvnojaQFMmELbvOYTRSAI+19X9YlolBnKySJXUyufKYlXpHGMCoYmVGxP1PI94DjvDa2dLKRlPm2oJQ3qB7RkB4PjIFHY88kw2ebAs6EYo4ELArcEwLShCAAKYiKYAAB5dweVIHCu7vHOSB0D+DrWGJaEqAgoExmaSALjZDBG1j5HJGLx6fjvbVomB3I2cKqmVz5XF4jlGhcqNiXqeRzyHneF53R6apgvDTDKNsUgSlsPEgZQSjz1zDrsPDsOSgN+t4g/vvRFf2n8aXpcdAHRVQdqUEApgmPZSiFTawjU9fqiKKFqCk7tDrUtVkLYkhABSs8/nZjNE1C4Gun1z7si0Sgxs193IWXpaHa18rixWu55jVFq5MVHP82ixr91uMZXndXtoigqEtCUxGk44Th7EUml89vvP46tP2smDwX4/vnb/7bjz2t687grdPhckJCxLQlMEUqYFCYEP3X1ttgRnNJJAl1fHaCSBnftOIOBSszvU9gfdkBIwpYRLVRpysxkiompphg23FqsddyMvdd3jRmFL18rnymK14zlG8ys3Jup5Hi3mtdsxpvK8bg9NkUAwLef7NLwyHsVvfetZHDxlt2h824Zl+PL227Cqy27RmNtdwe9W0eXV7RIbt4YVnd7sGp1SJThCiLwAAkgYpkQybcKlKlzjQ0RtY+tQCLu23QSXquD06AzOTcbh05vislJWO/7Bx9LT6smcK6GgB9NxA6Ggp+3nC+14jrWKanUjKDcm6nkeLea12zGm8rxuD02zhMGJJ09dweefeBFxw4SmCPz2PdfhnbesgBBX94DYPNiDj2I99h4ZwaVwHKt7/PjTLYN4+2tW5P2sUiU403EDf/Kum/HQEydxdjwGXRW4ptMDTVUQTeVn3IiI2kE0ZWJ1tze7YdLOfSewC2jqP462DoWwC2irrgUsPa2urUOhlh4/C9WO51gryN0kL/eueiVivpMxUc/zaKGv3Y4xled1e2iJBIJpSew5OIx/eOYcAKA/4MZntm3AjSs6ij5+82APNg/2QFUElnV44CnYFAWYf61TpkJhba9vzm6suw8O8yQhoraRe4cFAHwurWViYbv9wcd1+lRr7XaOtYJqx/xWGhPtGlNb6XdIxTV9AmEimsKu7z+Pn52bBgDctqYLf/yOG9Hlc837PF1VirZpzLhzsAdfOfAyTEvCrSkIejS4NDVbgtOOWUUiokLtGAtbdVOsHVsGsXPfCcRS6bz2Wyw9JaKMcjG/VePjYjCmUqtq6sWqz52fxo5HnskmD7ZvHsDnf+mWsskDj66WbNMI2MHvsWPn0ePX4VIFEmkTkzED79m4KhsEuUkIEVH7xcJW3hSL6/SJqJz5Yn4rx8fFYEylVtWUFQhSSvzTs+fx1SeHYVoSfpeKT947hDde11f2uT8bmcLeIyM4NxUvmRnNlGcpQoUQaShCQAB4/LlLePAt1wNgVpGICGi/WFjN8t1GuHPH0tPG0QjjgahQsZg/HTfgUhXsePQZCADLOz3ZTQNbZUnbUjnfDp6o8TVdBUI8ZeJP/+UFfPnH9vKCdX1+fPX+jY6SByfOT+MvfnQaV2aS82ZGRyZjSJsWLkwlkLYkVEXAkhKnRmeyj2VWkYio/WLhyGQM3oJ9cyqxZIN37igXxwM1qsKYryv2TbaUacGSEpaUuDCVQCRhAGj9JW3z4XlMraqpKhBGJmL49L4TODtuB6J7hkL4f952/ZzJXCEhBPoCLvzd4RFHd44Gun149tVJCAEosx0cBABdRd5jeaeGiKi9YmG1NsVq5c0oaeE4HqiR5cb87XsOwbAkfC4NLlVB2pSAAK5Ekgh69JZe0lYOz2NqVU1TgfDU6TF8+FvHcHY8BlUR+O03X4c/+oWhsskDVRFY0elB0KM7vnO0Y8sgDMuClBJSSliWhAWJZUF322ZRiYioej2uq1XZQM2J44GaRe5Y7Qu4YcGeOyfTZsXiY7PieUytqikSCGMzSXx63wnEUiZ6Ay588b234t0bV0HMVgeUoqsKVnZ5s20anW72tXUohPX9ASiKgCklNFVgZacXmqq0bRaViIiqt2Sj3TajpPlxPFCzyB2rHV4dKzu9UBQBVVFafklbOTyPqVU1RQJhIpoCANy6uhO7778dN6/qLPscn0vDqoJOCwu5c/TJe29EKOjBmh4f1vX5oamirbOoRERk2zoUwrcfeD2e+sQ9+PYDr6/I5LhalQ3UnDgeqFkUjlVNFQgFPdh9/+0Vi4/NiucxtaqmSCAAwHs3rcYXfvlW9Pjnb9EI2BnQ5Z0eKEp+hcJC7hy128ZgRERUP7zmUC6OB2oWHKul8bOhViWkbPzGImuHXiP3P/UTR4/tDbjR6dWrfERERBU1/3qsCtm0aZM8evRoLV6KiKgeahJLAcZTImp5JeNpU3RhCHrKJwQUIRDqcOftjE1EREREREREldESf21rioJlnW64tfk7MhARERERERHR4jR9AsGlKVje4YGmNs12DkRERERERERNp6kTCH63hv6Ae85miUt14OQodh8cxshkDAPdPuzYMsgNT4iIKoyxloiIyuG1gqixNO1t+06vjmUdczstLNWBk6PYue8ERiMJdHl1jEYS2LnvBA6cHK3o6xARtTPGWiIiKofXCqLG03QJBCEE+oJu9AbcVfn5uw8OQ1cFfC4NQthfdVVg98HhqrweEVE7YqwlIqJyeK0gajxNtYRBVQRCQQ+8rqVtljhfKdTIZAxdBW0gvbqKc5OxJb0mERFdxVhLxbBUmdoJx3t5vFYQNZ6mSSDoqoJlHR64tKUVTWRKoXRVZEuhPv7YcfT6XZhJmQjHDZiWhb6AJ/ucuGFidbdvqW+BiIhmDXT7MBpJ5LXebfdY2+5/TBS7Pu/cdwK7gLb6HKg9cLw706zXinaP59TammIJgyKAlV3eJScPgLmlUKYlMRkzcHbCznD6XCpGIymMzSQgpUQslYZhSuzYMliBd0JERACwY8sgDNOOsYy1XOcLsFSZ2gvHuzPNeK1gPKdW1xQVCLqqQK3QZomnRyOIJdMwLAmXqsC0JBQBmJaEEAL9QbvyIJo0oSkGVjNrSERUcVuHQtgFexJ9bjLW9rE2948JAPC5NMRSaew+ONw2n0mpUuXToxFs33OId/KopbA035laXCsqXS3AeE6trikSCJVy4OQoIok0LCmhKgJpSyKZtqApgFu7uq9CX8CN6biBpz5xTx2PloiotW0dCnEyNYt/TBQvVR6PJhFJpOfcyWOZNzW7Zi3Nr4dqXiuqsZSE8ZxaXVMsYaiU3QeH0e2zT2hpAZmahrRlJw0yGMCJiKiWBrp9iBtm3vfa7VpUrFR5Imqg26ezzJtaTjOW5reiaiwlYTynVtc2FQgHTo7i2KuTsKS0syYCMKWEW1OQTFu4HEngwnQcqiIQcGv443dsqPchExE1DG4IVV07tgxi574TiKXS8Ooq4obZdn9MFCtVnoql8hL8QOk7eRyj1EwqWZrfDGO/UY+xGtUCjOfU6toigZApTxLIVB0IWFJiZacXybSJ8WgKkICUEpACldltgYioNXC38OrjnhC2wlLl7XsOOSrz5hilZlSJ0vxmGPuNfIzVWErCeE6tri0SCJnypOWdHlyYSgACEBK4HElASqAv4Mpr28iNToiIruKGULXBPSHmcnonj2OU2lUzjP1GPsZqVQswnlMra4s9EEYmY/DqKoIeHSu7PNAUuwJBSiDo0dDrd1YeSUTUjjIxNBfjJNXC1qEQdm27CaGgB9NxA6GgB7u23TRnYs4xSu2qGcZ+Ix+j0xhDRFe1RQVCbnlS0KMj6NERS6URmm3ZyF1wiYhK427hVE9O7uRxjFK7aoax3+jHyGoBooWpSwWCEOKsEOK/hRA/FUIcrfbrzbfTLXfBJSKaH+MkNTqOUWpXzTD2m+EYici5elYgvFlKOVaLFyq3mQk3OiEiKo0bQlGj4xildtUMY78ZjpGInBNSytq/qBBnAWxymkDYtGmTPHq06oUKRET1UpPmL4ylRNTiatZIi/GUiFpcyXharwoECeDfhBASwG4p5Z7CBwghHgDwAACsWbOmoi/eqL1oiYgqrZqxtBjGVyJqVZWIp4yRRNTs6lWBsFJKeUEIEQLwQwC/I6U8WOrxlczy5vaizW3Xwh1XiaiOWqICgfGViOqsoSsQGCOJqImUjKd12URRSnlh9usogH8CsLlWr53bi1YI+6uuCuw+OFyrQyAiakmMr0REpTFGElErqHkCQQjhF0IEM/8O4G0AnqvV6zdyL1oiombG+EpEVBpjJBG1gnpUICwD8LQQ4jiAwwD+RUr5RK1efKDbh7hh5n2vkXrREhE1K8ZXIqLSGCOJqBXUPIEgpRyWUt46+89NUsr/VcvXZy9aIqLqYHwlIiqNMZKIWkFd9kCop61DIezadhNCQQ+m4wZCQQ83ryEiqgDGVyKi0hgjiagV1KuNY11tHQoxWBMRVQHjKxFRaYyRRNTs2q4CgYiIiIiIiIgWjgkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqiwkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqiwkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqiwkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqiwkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqiwkEIiIiIiIiIipLq/cBVNuBk6PYfXAYI5MxDHT7sGPLILYOhep9WERE1ER4LSGiemDsIaJG09IVCAdOjmLnvhMYjSTQ5dUxGklg574TOHBytN6HRkRETYLXEiKqB8YeImpELZ1A2H1wGLoq4HNpEML+qqsCuw8O1/vQiIioSfBaQkT1wNhDRI2opRMII5MxeHU173teXcW5yVidjoiIiJoNryVEVA+MPUTUiFo6gTDQ7UPcMPO+FzdMrO721emIiIio2fBaQkT1wNhDRI2opRMIO7YMwjAlYqk0pLS/GqbEji2D9T40IiJqEryWEFE9MPYQUSNq6QTC1qEQdm27CaGgB9NxA6GgB7u23cTda4mIyDFeS4ioHhh7iKgRtXwbx61DIQZaIiJaEl5LiKgeGHuIqNG0dAUCEREREREREVUGEwhEREREREREVBYTCERERERERERUFhMIRERERERERFQWEwhEREREREREVBYTCERERERERERUFhMIRERERERERFQWEwhEREREREREVBYTCERERERERERUFhMIRERERERERFQWEwhEREREREREVBYTCERERERERERUFhMIRERERERERFQWEwhEREREREREVBYTCERERERERERUFhMIRERERERERFQWEwhEREREREREVJZW7wOohgMnR7H74DBGJmMY6PZhx5ZBbB0K1fuwiIiIiBaFcxsqxDFBRPXQchUIB06OYue+ExiNJNDl1TEaSWDnvhM4cHK03odGREREtGCc21AhjgkiqpeWSyDsPjgMXRXwuTQIYX/VVYHdB4frfWhEREREC8a5DRXimCCiemm5BMLIZAxeXc37nldXcW4yVqcjIiIiIlo8zm2oEMcEEdVLyyUQBrp9iBtm3vfihonV3b46HRERERHR4nFuQ4U4JoioXlougbBjyyAMUyKWSkNK+6thSuzYMljvQyMiIiJaMM5tqBDHBBHVS8slELYOhbBr200IBT2YjhsIBT3Yte0m7kpLRERETYlzGyrEMUFE9dKSbRy3DoUYQImIiKhlcG5DhTgmiKgeWq4CgYiIiIiIiIgqjwkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqiwkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqiwkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqiwkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqiwkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqiwkEIiIiIiIiIiqLCQQiIiIiIiIiKosJBCIiIiIiIiIqS0gp630MZQkhrgB4ZRFP7QMwVuHDqSUef33x+OurnY5/TEr59moeDLCkWAo0/+/DCb7H1tEO75Pvca6axFKgreemGXwfjYXvo7G0wvsoGU+bIoGwWEKIo1LKTfU+jsXi8dcXj7++ePyNpdXeTzF8j62jHd4n32NzapX3xPfRWPg+GkurvI9SuISBiIiIiIiIiMpiAoGIiIiIiIiIymr1BMKeeh/AEvH464vHX188/sbSau+nGL7H1tEO75PvsTm1ynvi+2gsfB+NpVXeR1EtvQcCEREREREREVVGq1cgEBEREREREVEFMIFARERERERERGW1ZAJBCPF2IcSLQoiXhBCfrPfxOCGEOCuE+G8hxE+FEEdnv9cjhPihEOL07Nfueh9nhhDim0KIUSHEcznfK3q8wval2d/Hz8T/3969xkpVnWEc/z8FBbRYWmOtii0XibcWEJGAF7RqKlArvdiKNa1tSGwTLWq0jcbE6Kdq0nppVKy3otaiES8l2hoa1IhWQbkKgkpFK4pirWA1ihfefthrYDzOnDkDB2bW9vklO7P3mj2Hd887+z3rrFl7I41oXeSbYq0V/0WSXkk5WCRpQtVz56f4n5V0XGui3kzS3pIekrRc0jJJZ6b2LHLQSfxZ5EBSb0nzJC1O8V+c2gdKmpve/zsk7Zjae6Xtlen5Aa2Mvxk51tOuaKaG5arZOpGjZs/FnEnqIWmhpPvSdhmPMau+UPmeOyMAAAn3SURBVDNyraVlqyNlOI8k9ZM0Q9KKlJcxOeZD0tnpM7VU0vRUz9s+H830H1Rom/53dyndAIKkHsDVwHjgAOBkSQe0Nqou+2ZEDK/6f0PPA2ZHxBBgdtpuF9OAcR3a6sU7HhiSltOAqdspxs5M49PxA1yecjA8Iv4GkD4/k4AD02uuSZ+zVvoIOCci9gdGA6enOHPJQb34IY8cbACOjohhwHBgnKTRwKUU8Q8B3gImp/0nA29FxD7A5Wm/tpd5PW1kGl2vYblqtk7kqNlzMWdnAsurtst4jJBXX6hLMq+lZasjZTiPrgQeiIj9gGEUx5NVPiTtBUwBRkbE14EeFP28HPIxjbz/BtpqpRtAAEYBKyPihYj4ALgdmNjimLbURODmtH4z8N0WxvIJEfEI8N8OzfXinQjcEoUngH6S9tg+kdZWJ/56JgK3R8SGiFgFrKT4nLVMRKyJiAVp/X8Uvzz2IpMcdBJ/PW2Vg/Q+vpM2d0hLAEcDM1J7x/e/kpcZwDGStJ3C3Rplqqef0GQNy9IW1InsbMG5mCVJ/YFvAzekbVGyY+xEGT6v2dbSMtWRMpxHknYBxgI3AkTEBxGxjgzzAfQE+kjqCewErCGDfOT+N1B3KOMAwl7Ay1Xbq+n8D5N2EcAsSfMlnZbado+INVAUcODLLYuua+rFm1NOzkhTjG6qmv7V1vGrmA5/EDCXDHPQIX7IJAdpGuQiYC3wD+BfwLqI+CjtUh3jpvjT8+uBXbdvxFuk7d73bSy3mttlXawTWWryXMzVFcBvgI1pe1fKd4xQjr5QLaWopSWoI2U4jwYBbwB/Spdi3CBpZzLLR0S8AvwO+DfFwMF6YD755aMiu/731ijjAEKtb/Vy+L8qD4uIERRTXU6XNLbVAXWjXHIyFRhMMQ12DfD71N628Uv6PHAXcFZEvN3ZrjXaWn4MNeLPJgcR8XFEDAf6U3y7tH+t3dJj28XfRbnGbVWaqBNZavJczI6k44G1ETG/urnGrtkeY5Wy9oWyz1fudaRE51FPYAQwNSIOAt6lzS9XqCV9QTQRGAjsCexMcd531O75aCTHz1hDZRxAWA3sXbXdH3i1RbF0WUS8mh7XAvdQdIJer0xzSY9rWxdhl9SLN4ucRMTrqSO6EbiezVPk2zJ+STtQ/DK/LSLuTs3Z5KBW/LnlACBNHXyY4trQfmkqHnwyxk3xp+e/QNcvoWmltn3ft5Hcam5DTdaJrHXxXMzRYcAJkl6kmPp+NMU3qWU6RqA0faFasq6lJakjZTmPVgOrI6Iya3MGxYBCbvk4FlgVEW9ExIfA3cCh5JePimz6392hjAMITwJD0l08d6S4IcfMFsfUKUk7S+pbWQe+BSyliPvUtNupwF9bE2GX1Yt3JvDTdCfS0cD6yjSfdtLhmqTvUeQAivgnqbiT/kCKG6HM297xVUvX7d0ILI+Iy6qeyiIH9eLPJQeSdpPUL633ofhFuBx4CDgx7dbx/a/k5UTgwYjIYQQ6u3q6lXKruZ3agjqRnS04F7MTEedHRP+IGEBxDj4YEadQomOEUvWFasm2lpaljpTlPIqI14CXJe2bmo4BniGzfFBcujBa0k7pM1Y5jqzyUSWL/ne3iYjSLcAE4DmK6yAvaHU8XYh3ELA4LcsqMVNcmzUbeD49fqnVsVbFPJ1iivmHFKNrk+vFSzF95+qUj6cp7rjajvHfmuJbQnHC71G1/wUp/meB8W0Q/+EUU6CWAIvSMiGXHHQSfxY5AIYCC1OcS4ELU/sgioGNlcCdQK/U3jttr0zPD2r1Z6iJY82qnjZxXF2uYbkuzdaJHJdmz8XcF+Ao4L4yHiMZ9oWaPL4sa2kZ60ju5xHFZZ5PpZzcC3wxx3wAFwMrUu2+FeiVQz6a6T/QZv3v7lqUDs7MzMzMzMzMrK4yXsJgZmZmZmZmZt3MAwhmZmZmZmZm1pAHEMzMzMzMzMysIQ8gmJmZmZmZmVlDHkAwMzMzMzMzs4Y8gGCfWZJ2lbQoLa9JeqVq+7gO+54l6ZpWxWpmlitJR0m6L62fIOm8VsdkZmZmW8YDCPaZFRFvRsTwiBgOXAtcntanApM67D6J4v99NTMzQIWm+hERMTMiLtlWMZmZ2daR1LPVMVh78wCC2afNAI6X1AtA0gBgT+DRFsZkZtZykgZIWp5mZC0AbpT0lKRlki6u2m+cpBWSHgW+X9X+M0lXpfWvSZotaUl6/Op2PyAzs61QVROvT3VwlqQ+kgZLekDSfElzJO0nqYekF9Lgaz9JGyWNTT9njqR9JB1ZNRt2oaS+aRbXI5LukfSMpGsrg7eSptapwS9KulTSvLTsk9p3k3SXpCfTclhqv0jSdZJmAbe04K20jHgAwayDiHgTmAeMS02TgDsiIloXlZlZ29gXuCUiDgLOiYiRwFDgSElDJfUGrge+AxwBfKXOz7kq/ZyhwG3AH7Z96GZm3W4IcHVEHAisA34AXAf8KiIOBs4FromIj4HngAOAw4H5wBHpC6v+EbEy7Xt6mhF7BPBe+jdGAecA3wAGs3lg9oKONbgqrrcjYhRFrb0itV1JMeP2kBTnDVX7HwxMjIgfd8ebYuXlAQSz2qaz+TIGX75gZrbZSxHxRFr/kaQFwELgQIqO8X7Aqoh4Pg28/rnOzxkD/CWt30rRoTYzy82qiFiU1ucDA4BDgTslLQL+COyRnp8DjE3Lbynq3iHAk+n5x4DLJE0B+kXER6l9XkS8kAYhprO5XtaqwRXTqx7HpPVjgatSXDOBXST1Tc/NjIj3MGvA17iY1XYvRQEfAfSJiAWtDsjMrE28CyBpIMW3ZYdExFuSpgG90z5bMmPLs7zMLEcbqtY/BnYH1qVZBB3NAX5JcWnshcCvgaOARwAi4hJJ9wMTgCckHZte17E+RoMa3PE1lfXPAWM6DhRIglTbzRrxDASzGiLiHeBh4CY8+8DMrJZdKDqc6yXtDoxP7SuAgZIGp+2T67z+n2ye6XUKvs+MmZXD28AqST+ETTecHZaem0sxO2FjRLwPLAJ+QTGwgKTBEfF0RFwKPEUxowtglKSB6d4HJ1HUy3o1uOKkqsfH0/os4IzKDpJqDXKYdcoDCGb1TQeGAbe3OhAzs3YTEYspps0uoxhsfSy1vw+cBtyfbqL4Up0fMQX4uaQlwE+AM7d50GZm28cpwGRJiylq5ESAiNgAvAxULgObA/QFnk7bZ0laml73HvD31P44cAmwFFgF3FOvBlfpJWkuRW09O7VNAUamm9c+QzEbwqwp8n3hzMzMzMzM2o+ko4BzI+L4Jl7zIjAyIv6zreKyzy7PQDAzMzMzMzOzhjwDwczMzMzMzMwa8gwEMzMzMzMzM2vIAwhmZmZmZmZm1pAHEMzMzMzMzMysIQ8gmJmZmZmZmVlDHkAwMzMzMzMzs4b+D8GbWVmrJ6i8AAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 1058.4x504 with 3 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Plotting the Least Squares\n",
    "sns.pairplot(data, x_vars=['TV','radio','newspaper'], y_vars='sales', height=7, aspect=0.7, kind='reg')\n",
    "\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}
