{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "9558248a",
   "metadata": {},
   "source": [
    "OLS Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "47ec4ef9",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>    <td>Average Daily Milk Production (litres)</td> <th>  R-squared:         </th> <td>   0.585</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                              <td>OLS</td>                  <th>  Adj. R-squared:    </th> <td>   0.546</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>                        <td>Least Squares</td>             <th>  F-statistic:       </th> <td>   15.03</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>                        <td>Wed, 29 Nov 2023</td>            <th>  Prob (F-statistic):</th> <td>1.02e-37</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                            <td>19:45:10</td>                <th>  Log-Likelihood:    </th> <td> -2251.7</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>                 <td>   292</td>                 <th>  AIC:               </th> <td>   4555.</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>                     <td>   266</td>                 <th>  BIC:               </th> <td>   4651.</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>                         <td>    25</td>                 <th>                     </th>     <td> </td>   \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>                 <td>nonrobust</td>               <th>                     </th>     <td> </td>   \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "                             <td></td>                               <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>const</th>                                                  <td>  214.0502</td> <td>  219.627</td> <td>    0.975</td> <td> 0.331</td> <td> -218.378</td> <td>  646.479</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Number of Cows</th>                                         <td>    3.0344</td> <td>    0.336</td> <td>    9.041</td> <td> 0.000</td> <td>    2.374</td> <td>    3.695</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Number of Buffaloes</th>                                    <td>    2.5291</td> <td>    0.435</td> <td>    5.811</td> <td> 0.000</td> <td>    1.672</td> <td>    3.386</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Number of Family Members/Employees Working at the Farm</th> <td>    1.2873</td> <td>    2.701</td> <td>    0.477</td> <td> 0.634</td> <td>   -4.032</td> <td>    6.606</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>ahmedabad</th>                                              <td> -234.7569</td> <td>  108.585</td> <td>   -2.162</td> <td> 0.032</td> <td> -448.553</td> <td>  -20.961</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>jamnagar</th>                                               <td> -117.4678</td> <td>  109.095</td> <td>   -1.077</td> <td> 0.283</td> <td> -332.267</td> <td>   97.331</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>rajkot</th>                                                 <td> -211.7515</td> <td>  114.266</td> <td>   -1.853</td> <td> 0.065</td> <td> -436.733</td> <td>   13.230</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>surat</th>                                                  <td> -138.1897</td> <td>  111.133</td> <td>   -1.243</td> <td> 0.215</td> <td> -357.001</td> <td>   80.622</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>aavin</th>                                                  <td>   72.1190</td> <td>  138.588</td> <td>    0.520</td> <td> 0.603</td> <td> -200.750</td> <td>  344.988</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>amul</th>                                                   <td>   51.8319</td> <td>  152.322</td> <td>    0.340</td> <td> 0.734</td> <td> -248.079</td> <td>  351.743</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>dudhsagar dairy</th>                                        <td>   77.5287</td> <td>  153.446</td> <td>    0.505</td> <td> 0.614</td> <td> -224.595</td> <td>  379.652</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>dynamix dairy</th>                                          <td> -315.0179</td> <td>  175.057</td> <td>   -1.800</td> <td> 0.073</td> <td> -659.691</td> <td>   29.655</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>karnataka co-operative milk federation</th>                 <td>  124.3128</td> <td>  161.807</td> <td>    0.768</td> <td> 0.443</td> <td> -194.273</td> <td>  442.899</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>mother dairy</th>                                           <td>  -39.6507</td> <td>  147.564</td> <td>   -0.269</td> <td> 0.788</td> <td> -330.193</td> <td>  250.892</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>orissa state cooperative milk producers federation</th>     <td>  191.7776</td> <td>  144.317</td> <td>    1.329</td> <td> 0.185</td> <td>  -92.371</td> <td>  475.926</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>parag milk foods ltd</th>                                   <td>    9.9635</td> <td>  147.334</td> <td>    0.068</td> <td> 0.946</td> <td> -280.125</td> <td>  300.052</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>selling privately to consumers</th>                         <td>  125.1362</td> <td>  152.651</td> <td>    0.820</td> <td> 0.413</td> <td> -175.422</td> <td>  425.694</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>verka</th>                                                  <td>   79.0992</td> <td>  183.174</td> <td>    0.432</td> <td> 0.666</td> <td> -281.555</td> <td>  439.754</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>natural plants</th>                                         <td>   93.5826</td> <td>   69.847</td> <td>    1.340</td> <td> 0.181</td> <td>  -43.942</td> <td>  231.107</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Use_of_Automation</th>                                      <td>  -45.6629</td> <td>   76.078</td> <td>   -0.600</td> <td> 0.549</td> <td> -195.454</td> <td>  104.129</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Daily Expenditure on Animal Health (INR)</th>               <td>    1.5998</td> <td>    0.550</td> <td>    2.911</td> <td> 0.004</td> <td>    0.518</td> <td>    2.682</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Daily Income from Selling Manure (INR)</th>                 <td>   -2.6758</td> <td>    1.070</td> <td>   -2.501</td> <td> 0.013</td> <td>   -4.783</td> <td>   -0.569</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Daily Operating Costs (INR)</th>                            <td>    0.0238</td> <td>    0.019</td> <td>    1.231</td> <td> 0.219</td> <td>   -0.014</td> <td>    0.062</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Daily Revenue (INR)</th>                                    <td>    0.1577</td> <td>    0.054</td> <td>    2.933</td> <td> 0.004</td> <td>    0.052</td> <td>    0.264</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Satisfaction_5_7</th>                                       <td>  -42.5378</td> <td>   87.484</td> <td>   -0.486</td> <td> 0.627</td> <td> -214.788</td> <td>  129.712</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Satisfaction_8_10</th>                                      <td>   53.4249</td> <td>   85.203</td> <td>    0.627</td> <td> 0.531</td> <td> -114.334</td> <td>  221.184</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>35.382</td> <th>  Durbin-Watson:     </th> <td>   2.017</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td> 166.690</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td>-0.307</td> <th>  Prob(JB):          </th> <td>6.36e-37</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 6.650</td> <th>  Cond. No.          </th> <td>5.19e+04</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 5.19e+04. This might indicate that there are<br/>strong multicollinearity or other numerical problems."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                                      OLS Regression Results                                      \n",
       "==================================================================================================\n",
       "Dep. Variable:     Average Daily Milk Production (litres)   R-squared:                       0.585\n",
       "Model:                                                OLS   Adj. R-squared:                  0.546\n",
       "Method:                                     Least Squares   F-statistic:                     15.03\n",
       "Date:                                    Wed, 29 Nov 2023   Prob (F-statistic):           1.02e-37\n",
       "Time:                                            19:45:10   Log-Likelihood:                -2251.7\n",
       "No. Observations:                                     292   AIC:                             4555.\n",
       "Df Residuals:                                         266   BIC:                             4651.\n",
       "Df Model:                                              25                                         \n",
       "Covariance Type:                                nonrobust                                         \n",
       "==========================================================================================================================\n",
       "                                                             coef    std err          t      P>|t|      [0.025      0.975]\n",
       "--------------------------------------------------------------------------------------------------------------------------\n",
       "const                                                    214.0502    219.627      0.975      0.331    -218.378     646.479\n",
       "Number of Cows                                             3.0344      0.336      9.041      0.000       2.374       3.695\n",
       "Number of Buffaloes                                        2.5291      0.435      5.811      0.000       1.672       3.386\n",
       "Number of Family Members/Employees Working at the Farm     1.2873      2.701      0.477      0.634      -4.032       6.606\n",
       "ahmedabad                                               -234.7569    108.585     -2.162      0.032    -448.553     -20.961\n",
       "jamnagar                                                -117.4678    109.095     -1.077      0.283    -332.267      97.331\n",
       "rajkot                                                  -211.7515    114.266     -1.853      0.065    -436.733      13.230\n",
       "surat                                                   -138.1897    111.133     -1.243      0.215    -357.001      80.622\n",
       "aavin                                                     72.1190    138.588      0.520      0.603    -200.750     344.988\n",
       "amul                                                      51.8319    152.322      0.340      0.734    -248.079     351.743\n",
       "dudhsagar dairy                                           77.5287    153.446      0.505      0.614    -224.595     379.652\n",
       "dynamix dairy                                           -315.0179    175.057     -1.800      0.073    -659.691      29.655\n",
       "karnataka co-operative milk federation                   124.3128    161.807      0.768      0.443    -194.273     442.899\n",
       "mother dairy                                             -39.6507    147.564     -0.269      0.788    -330.193     250.892\n",
       "orissa state cooperative milk producers federation       191.7776    144.317      1.329      0.185     -92.371     475.926\n",
       "parag milk foods ltd                                       9.9635    147.334      0.068      0.946    -280.125     300.052\n",
       "selling privately to consumers                           125.1362    152.651      0.820      0.413    -175.422     425.694\n",
       "verka                                                     79.0992    183.174      0.432      0.666    -281.555     439.754\n",
       "natural plants                                            93.5826     69.847      1.340      0.181     -43.942     231.107\n",
       "Use_of_Automation                                        -45.6629     76.078     -0.600      0.549    -195.454     104.129\n",
       "Daily Expenditure on Animal Health (INR)                   1.5998      0.550      2.911      0.004       0.518       2.682\n",
       "Daily Income from Selling Manure (INR)                    -2.6758      1.070     -2.501      0.013      -4.783      -0.569\n",
       "Daily Operating Costs (INR)                                0.0238      0.019      1.231      0.219      -0.014       0.062\n",
       "Daily Revenue (INR)                                        0.1577      0.054      2.933      0.004       0.052       0.264\n",
       "Satisfaction_5_7                                         -42.5378     87.484     -0.486      0.627    -214.788     129.712\n",
       "Satisfaction_8_10                                         53.4249     85.203      0.627      0.531    -114.334     221.184\n",
       "==============================================================================\n",
       "Omnibus:                       35.382   Durbin-Watson:                   2.017\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              166.690\n",
       "Skew:                          -0.307   Prob(JB):                     6.36e-37\n",
       "Kurtosis:                       6.650   Cond. No.                     5.19e+04\n",
       "==============================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "[2] The condition number is large, 5.19e+04. This might indicate that there are\n",
       "strong multicollinearity or other numerical problems.\n",
       "\"\"\""
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import statsmodels.api as sm\n",
    "import pandas as pd\n",
    "\n",
    "\n",
    "# Dataset for OLS regression\n",
    "final_transformed_data_path = '/Users/dhruvtrivedi/Downloads/Final Project Stat 371/Final_Transformed_Farm_Data_Gujarat_v2.csv'\n",
    "df = pd.read_csv(final_transformed_data_path)\n",
    "\n",
    "# Preparing the data for OLS regression\n",
    "# Defining the target variable\n",
    "target = 'Average Daily Milk Production (litres)'\n",
    "\n",
    "# Defining the predictor variables (all other columns)\n",
    "predictors = df.drop(target, axis=1)\n",
    "\n",
    "# Adding a constant to the model (for intercept)\n",
    "predictors_with_constant = sm.add_constant(predictors)\n",
    "\n",
    "# Performing OLS regression\n",
    "model = sm.OLS(df[target], predictors_with_constant)\n",
    "results = model.fit()\n",
    "\n",
    "# Summary statistics of the model\n",
    "results.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "4647d384",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x360 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(ShapiroResult(statistic=0.9831531643867493, pvalue=0.0016427095979452133),\n",
       " ShapiroResult(statistic=0.9701030850410461, pvalue=9.163556569546927e-06),\n",
       " ShapiroResult(statistic=0.9117769598960876, pvalue=4.5161092747381115e-12),\n",
       " ShapiroResult(statistic=0.6394598484039307, pvalue=2.22295244406673e-24))"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import scipy.stats as stats\n",
    "\n",
    "# Response variable - \"Average Daily Milk Production per day (in litres)\"\n",
    "response_var = 'Average Daily Milk Production (litres)'\n",
    "\n",
    "# Applying transformations\n",
    "df['sqrt_transformation'] = np.sqrt(df[response_var])\n",
    "df['log_transformation'] = np.log(df[response_var] + 1)  # Adding 1 to avoid log(0)\n",
    "df['inverse_transformation'] = 1 / (df[response_var] + 1)  # Adding 1 to avoid division by 0\n",
    "\n",
    "# Plotting histograms\n",
    "plt.figure(figsize=(20, 5))\n",
    "\n",
    "# Original data histogram\n",
    "plt.subplot(1, 4, 1)\n",
    "plt.hist(df[response_var], bins=20, color='skyblue', edgecolor='black')\n",
    "plt.title('Original Data')\n",
    "\n",
    "# Square root transformation histogram\n",
    "plt.subplot(1, 4, 2)\n",
    "plt.hist(df['sqrt_transformation'], bins=20, color='lightgreen', edgecolor='black')\n",
    "plt.title('Square Root Transformation')\n",
    "\n",
    "# Logarithmic transformation histogram\n",
    "plt.subplot(1, 4, 3)\n",
    "plt.hist(df['log_transformation'], bins=20, color='salmon', edgecolor='black')\n",
    "plt.title('Logarithmic Transformation')\n",
    "\n",
    "# Inverse transformation histogram\n",
    "plt.subplot(1, 4, 4)\n",
    "plt.hist(df['inverse_transformation'], bins=20, color='lightcoral', edgecolor='black')\n",
    "plt.title('Inverse Transformation')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "# Shapiro-Wilk test for normality\n",
    "sw_original = stats.shapiro(df[response_var])\n",
    "sw_sqrt = stats.shapiro(df['sqrt_transformation'])\n",
    "sw_log = stats.shapiro(df['log_transformation'])\n",
    "sw_inverse = stats.shapiro(df['inverse_transformation'])\n",
    "\n",
    "sw_original, sw_sqrt, sw_log, sw_inverse\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "fdaaaf76",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsgAAAI4CAYAAAB3OR9vAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAACOK0lEQVR4nOzdeZyNdf/H8deHsWRLiOyEbMk2pKhGUlpupQ23ulu4pdJyt/zS3d12S9r3RdoXke4WKkTLKC2KkiwVFRkUKZVk//z++F7DMWbGYM6cMzPv5+NxHub6nmv5XOecy3zmez7X92vujoiIiIiIBCUSHYCIiIiISDJRgiwiIiIiEkMJsoiIiIhIDCXIIiIiIiIxlCCLiIiIiMRQgiwiIiIiEkMJsogkDTPrZ2aTd3PbuWaWlr8R5XgsM7MnzexXM/tkN/dRz8zWmFnJaLmGmb1nZn+Y2Z35cYyizsxuMrOfzezHRMeSVdb3V0QKFyXIIpJnZtbFzD40s9/M7Bcz+8DMOkTPnW1m03ZhXw3MzM0sJbPN3Ue5+9F52PYpM7spts3dW7p7+i6czp7oAnQH6rh7x2ziO9vMNkcJ0hoz+z5Kdg+IifcHd6/g7pujpoHAz0Ald798Z8eIp+zemyzPj4g5tw1mtjFmeWIBxVgXuBxo4e77FcQxdxLPIjM7KnM5m/dXRAoRJcgikidmVgl4HbgfqALUBm4E1icyrgSpDyxy9z9zWecjd68A7A0cBfwFzDSzA3PZ5zzfNntTXo6RrZwS2/zi7oOi5K8CcDPwQuayux9bQHHUB1a5+4pd3TDer4+IFH5KkEUkrw4AcPfR7r7Z3f9y98nuPtvMmgMjgEOiXsTVAGZ2vJl9bma/m9kSM7shZn/vRf+ujrY5JLYXOioxuNvMVkQ91rPN7EAzGwj0A/4v2u61aP2tPXhmVtLM/m1m30YlCzPNrG5O+8zuZM2slpmNj3rKF5rZP6P2/sBjMed6Y24vWvRafevuFwBTgRui/WztpTWzp4CzYs7pvOyOYWYnmNksM1sd9eQfFBPvIjO7ysxmA39G++0UrbfazL6wmBIUM0s3s6HRtwB/mNlkM6uW03uT2zlmed2yi2NIzHsxz8x6xax/tplNM7M7LJSTfG9mx2Z5/rto2+8tlOEcBUwBakXxPRWt29NCqc3q6Pya5xJX4+j1Pyf6bP5qZoPMrEP0uVhtZg/EbN/IzN4xs1UWyjpGmVnl6LlngXrAa1E8/2dZeuFz+jxFz91gZmPN7JnoPOeaWWrM81eZ2dLoua/NrFte3w8R2U3uroceeuix0wdQCVgFPA0cC+yT5fmzgWlZ2tKAVoQ/xg8CfgJOip5rADiQkt0+gGOAmUBlwIDmQM3ouaeAm7IcaxFwVPTzlcCXQNNo29ZA1dz2mc35TgUeAsoCbYCVQLecznVnr0XUfi7wU3bnn/Wcsu4DaAesAA4GShIS6kVAmZjznwXUBfYi9PCvAo6LXv/u0fK+0frpwLeEP3z2ipZvyem9yeVcbwCey/I+bI0jajsNqBXF0Rv4M+a9PBvYCPwzOq/zgWXR+1Me+B1oGq1bE2gZ89nKiDnuAdF+uwOlgP8DFgKlc3h9Ms9xRPQeHw2sA14Fqkev3wrgiGj7xtG+ywD7Ev6IuCe7z18O729un6cbomMfF70Gw4GPo+eaAkuAWjH7bZTo/w/00KOoP9SDLCJ54u6/E+piHXgUWBn1iNXIZZt0d//S3be4+2xgNHBEHg+5EagINAPM3ee7+/I8bjsA+I+7f+3BF+6+Kq/7tFDf2gW4yt3XufssQo/umXk8fk6WEcpTdsc/gUfcfbqHXumnCeUtnWLWuc/dl7j7X8AZwAR3nxC9/lOAGYQkLNOT7v5NtP5YQuKWH2LjwN1fdPdlURwvAAuA2Lrqxe7+qId63acJiXDm52oLcKCZ7eXuy919bg7H7A284e5T3H0jcAchET40p7giQ6P3eDIhwR7t7ivcfSnwPtA2OoeF0b7Xu/tK4C7y+FnO4+dpWvRebQaeJfxRB7CZkJS3MLNS7r7I3b/Ny3FFZPcpQRaRPIsSyrPdvQ5wIKFX8J6c1jezg83sXTNbaWa/AYOAajmtn+VY7wAPAA8CP5nZSAt10HlRl9A7urv7rAX84u5/xLQtJvQq7onawC+7uW194PLoq//VFspY6hJizbQky/qnZVm/CyH5zBQ7+sNaoMJuxpZVbByY2T9iSkNWEz47sZ+DrXG4+9roxwoe6q97Ez43y83sDTNrlsMxaxHeo8z9bIniiH3PlmTdiPCtRqa/slmuEJ1DdTMbE5U6/A48Rx4/y+Tt85T1vShrZinuvhC4lNDLvCKKIfY9F5E4UIIsIrvF3b8ilAVk1vB6Nqs9D4wH6rr73oSvsy2X9bMe4z53bw+0JHyFfmUet10CNNrFfcZaBlQxs4oxbfWApTuLeSd6EXold8cSYJi7V455lHP30THreJb1n82yfnl3vyUPx9rpe5PX7c2sPuEbh8FAVXevDMxh2+cg9x25v+nu3QmJ/VfRvrKzjPBHQeZxjfAHROx7tifnNTza/iB3r0TooY89h9z2vUefJ3d/3t27EM7PgVt3JXAR2XVKkEUkT8ysmZldbmZ1ouW6QF/g42iVn4A6ZlY6ZrOKhJ6zdWbWEfh7zHMrCV+f75/D8TpEPdClCF99ryN83Zx5rGy3izwGDDWzJhYcZGZVd7LPrdx9CfAhMNzMylq4Ga4/MCqXY2bLwg2DDc3sfkLdbK439eXiUWBQFL+ZWXkLN0FWzGH954C/mdkxUQxlzSwt8/3biVzfm11UnpDUrQQws3PY9kdVriyMDd3TzMoTyknWkM37FRkLHG9m3aL39/Jomw/3MP5MFaPjrzaz2uz4h1WOn8k9+TyZWVMzO9LMyhA+r3+R82sgIvlECbKI5NUfhBvEppvZn4TEeA4hEQF4B5gL/GhmP0dtFwD/NbM/gOsISQyw9av0YcAH0VfvsbW0EG4KfBT4lfB19CpCXSnA44SazNVm9mo2sd4VHWsy4Savxwn1qLntM6u+hBuilgGvANdHdbx5dYiZrYmOnx4du4O7f7kL+9jK3WcQ6pAfiOJfSLjBLaf1lwAnAv8mJKdLCEndTv/fz8N7sytxzwPuBD4iJJGtgA/yuHkJwudrGaE05QjCZyq743xN6NW9nzCe9N+Av7n7ht2NPYsbCTdK/ga8Abyc5fnhwH+i1+uKbLbf3c9TGeAWwjn9SLiB8N+7cwIiknfmvqffpImIiIiIFB3qQRYRERERiaEEWUREREQkhhJkEREREZEYSpBFRERERGKkJDqAglCtWjVv0KBBgR/3zz//pHz58gV+XJFkpOtBZHu6JkS2SdT1MHPmzJ/dfd+s7cUiQW7QoAEzZswo8OOmp6eTlpZW4McVSUa6HkS2p2tCZJtEXQ9mtji7dpVYiIiIiIjEUIIsIiIiIhJDCbKIiIiISAwlyCIiIiIiMZQgi4iIiIjEUIIsIiIiIhJDCXIuJk2aRNOmTWncuDG33HLLDs//+uuv9OrVi4MOOoiOHTsyZ86crc/dfffdnH322Rx44IH07duXdevWAdC7d2/atGlDmzZtaNCgAW3atAFg1apVdO3alQoVKjB48OACOT8RERER2ZES5Bxs3ryZCy+8kIkTJzJv3jxGjx7NvHnztlvn5ptvpk2bNsyePZtnnnmGSy65BIClS5dy33338cgjjzBnzhw2b97MmDFjAHjhhReYNWsWs2bN4pRTTuHkk08GoGzZsgwdOpQ77rijYE9URERERLajBDkHn3zyCY0bN2b//fendOnS9OnTh3Hjxm23zrx58+jWrRsAzZo1Y9GiRfz0008AbNq0ifXr17Np0ybWrl1LrVq1ttvW3Rk7dix9+/YFoHz58nTp0oWyZcsWwNmJiIiISE6UIOdg6dKl1K1bd+tynTp1WLp06XbrtG7dmpdffhkICfXixYvJyMigdu3aXHHFFfTu3ZuaNWuy9957c/TRR2+37fvvv0+NGjVo0qRJ/E9GJB/sbsnR119/TZs2bRgwYABt2rShUqVK3HPPPQD88ssvdO/enSZNmtC9e3d+/fVXAKZMmUL79u1p1aoV7du355133imw8xQREVGCnAN336HNzLZbHjJkCL/++itt2rTh/vvvp23btqSkpPDrr78ybtw4Ro8ezbJly/jzzz957rnnttt29OjRW3uPRZLdnpQcNW3alFmzZvHYY48xc+ZMypUrR69evQC45ZZb6NatGwsWLKBbt25bE+9q1arx2muv8eWXX/L0009z5plnFuwJi4hIsaYEOQd16tRhyZIlW5czMjJ2KJOoVKkSTz75JLNmzeKZZ55h5cqVNGzYkLfeeouGDRtSuXJlSpUqxcknn8yHH364dbtNmzbx8ssv07t37wI7H5E9saclR5nefvttGjVqRP369QEYN24cZ511FgBnnXUWr776KgBt27bder21bNmSdevWsX79+nieooiIyFZKkHPQoUMHFixYwPfff8+GDRsYM2YMPXv23G6d1atXs2HDBgAee+wxDj/8cCpVqkS9evX4+OOPWbduHe7O22+/TfPmzbdu99Zbb9GsWTPq1KlToOcksrv2pOQo1pgxY7b75uSnn36iZs2aANSsWZMVK1bscOyXXnqJtm3bUqZMmXw7HxERkdykJDqAZJWSksIDDzzAMcccw+bNmzn33HNp2bIlI0aMAGDQoEHMnz+ff/zjH5QsWZIWLVrw+OOPA3DwwQdz6qmnMnDgQCpVqkTbtm0ZOHDg1n1nTRIyNWjQgN9//50NGzbw6quvMnnyZFq0aFEwJyySi7yWHF1yySW0adOGVq1abS05yrRx40bGjx/P8OHD83zcuXPnctVVVzF58uTdD15ERGQXKUHOxXHHHcdxxx23XdugQYO2/nzIIYewYMGCbLe98cYb6dq1K2lpaTs899RTT2W7zaJFi3Y3VJG42pWSIwgJdcOGDWnYsOHW56dPn067du2oUaPG1rYaNWqwfPlyatasyfLly6levfp2x+jVqxfPPPMMjRo1itepiYiI7EAlFiKyU3tScpTpnXfe2eGbk549e/L0008D8PTTT3PiiSdu3dfxxx/P8OHD6dy5czxPTUREZAdKkEVkp2JLjpo3b87pp5++teQos+xo/vz5tGzZkmbNmjFx4kTuvfferduvXbuWmTNnbp0YJ9OQIUOYMmUKTZo0YcqUKQwZMgSABx54gIULFzJ06NCtM09mV58sIiISD5ZdbWGimNkTwAnACnc/MJvnDbgXOA5YC5zt7p/tbL+pqak+Y8aM/A53p9LT07MtsRApjnQ9iGxP14TINom6HsxsprunZm1Pth7kp4AeuTx/LNAkegwEHi6AmERERESkGEmqBNnd3wN+yWWVE4FnPPgYqGxmNQsmOhEREREpDgrbKBa1gSUxyxlR2/KsK5rZQEIvMzVq1CA9Pb0g4gPgrbeq89hj+7NixRFUr76OAQO+46ijVD8pxduaNWsK9DoUSXa6JkS2SbbrobAlyJZNW7ZF1O4+EhgJoQa5oOpaRo2Cu++GtWvD8k8/leXuu1vQvHkL+vUrkBBEkpLqLUW2p2tCZJtkux4KW4KcAdSNWa4DLEtQLNm65pptyXGmtWvh3HPhkUegVKnwSEnZ9nNObfm1zq5sV7JkYl43ERERkWRR2BLk8cBgMxsDHAz85u47lFck0g8/ZN++YUNIPtevhzVrYNMm2Lhx2yPrcmzbli0FF79Z/JLvRCX/KSnhvERERETyIqkSZDMbDaQB1cwsA7geKAXg7iOACYQh3hYShnk7JzGR5qxePVi8eMf2+vXh3Xd3b59btuScSOeWWOfWll/rZLb9+eeu77sglSwZ3573ROy7sPT2jxoVvln54YcjqFcPhg1D5UYiIpLUkipBdve+O3negQsLKJzdMmwYDBy4fZlFuXKhfXeVKAFlyoRHUeEOmzcnZ7Kf+fP69dsn/sna25+oBD0vbe++C7feCuvWARiLF4frA5Qki4hI8kqqBLkoyPylH3rMnHr1TD1m2TALSVRKCuy1V6KjyT+Zvf3xTPb39I+ERPf2r10Ll10GvXqFPx5FRESSjRLkOOjXLzzS06cm1R2ZEn/q7d9++aijwvZZrVgBVarAEUfAscdCjx7QtKlqxUVEJDkoQRaRXO1Jb39ONfnVq8Pf/w6TJsG//hUeDRqERLlHDzjySKhYMV/CFxER2WVJNZOeiBQtw4btWEZRrhzcdVcYL3z+fPjuO3j4YWjdGp57Dk46CapWDUnybbfB7NnZ90KLiIjEixJkEYmbfv1g5MgwiouZU79+WI6tyW/YEAYNgldfhVWr4J13Qo/yzz/DVVeFxLlOHejfH158EVavTtTZiIhIcaEEWUTiql8/WLQI3nlnKosW5X7DaunS0LVrGPli9mzIyIDHH4dDD4WXXoLTT4dq1aBLF7jpJpg5s2BHDhERkeJBCbKIJK3atcMslC++GHqUp02DIUPCsHHXXgupqbDffnDmmfD882EdERGRPaWb9ESkUEhJgc6dw+Omm8JIGG++GW70mzgx1C+bhaQ5c2SMjh0Lz4QqIiKSPNSDLCKFUvXqoed41Cj46SeYPh1uuCEk0jfdFMoy9t0X+vSBp56C5Uk1Kb2IiCQz9SCLSKFXsmToLe7YEa67Ltzs99ZboXd50iR44YWwXps224aSO/TQMNufiIhIVupBFpEip2pV6N0bnnwSli6Fzz+H4cOhUiW44w5ISwvrnHxyGFXjhx8SHbGIiCQT9SCLSJFWokToOW7TJtzg99tvYSi5iRND7/Irr4T1WrTYVrt82GFFazZEERHZNepBFpFiZe+9oVev0HO8eDHMnRt6lWvVgvvvh+7dwzTYf/sbPPggfPttoiMWEZGCph5kESm2zELPcYsWcPnlsGYNpKdvGxnj9dfDek2abKtdTkvbcXZAEREpWpQgi4hEKlSAE04ID3dYuHBbsvzoo6GHuUwZOOKIkCwfeyw0bRoSbRERKTpUYiEikg2z0HN80UUwYQL88ksYd/n888NNfZddBs2bb5sqe9w4+OOPREctIiL5QQmyiEge7LUXHH003H03zJ8P338PDz8cbv4bNQpOOimMjNG1K9x2W5gq2z3RUYuIyO5QgiwishsaNAg9x6++GsZdfucd+Ne/Qk/zVVdB69ZQpw707x+myv7110RHLCIieaUEWURkD5UuHXqOb70VvvgCMjLg8cfDtNgvvQSnnx5m9evSJczyN2MGbNmS6KhFRCQnSpBFRPJZ7dpw7rkwdiz8/DNMmwZXXw3r1sG110KHDrDfftumyl65MtERi4hILI1iISISRykpoSe5c2cYOhRWrIDJk8PIGBMnwnPPhRsCU1O3jYzRsWOYPltERBJDPcgiIgWoenU444zQc/zTT/DJJ3DDDSGRHjYMDj00lGP07g1PPQXLlyc6YhGR4kc9yCIiCVKyZCi36NABrrsu3OA3ZUoYe3nSpFCiAeGGv8xpsA89FEqVSmzcIiJFnXqQRUSSRJUqoef4ySdh2TL4/HMYPhwqVw7TYaelhaHkTj45TJX9ww+JjlhEpGhSD7KISBIyC2Mst2kDQ4bAb7+FoeQyZ/Z75ZWwXosW22qXDzsszPQnIiJ7Rj3IIiKFwN57Q69e8MgjsHgxzJ0Ld94JtWrBAw9A9+6hB/qEE+DBB+HbbxMdsYhI4aUeZBGRQsYs9By3aBGmvP7zT0hP3zYyxhtvhPUaN95Wu5yWBuXKJTJqEZHCQwmyiEghV748HH98eAAsXBgS5UmT4LHH4P77Q+nFEUeEZLlHD2jWLCTaIiKyI5VYiIgUMY0bw0UXhZ7kX36BN9+ECy4IN/VddlnoeW7YcNtU2X/8keiIRUSSixJkEZEirGxZOPpouOsumD8fvv8eRowIN/+NGhXqmqtUCVNl33YbzJ4N7omOWkQksZQgi4gUIw0awHnnhZ7jVavg3XdDr/Ivv8BVV4Uxl+vUgf794cUX4ddfEx2xiEjBU4IsIlJMlS4dbt679Vb44gvIyIDHHw/TYr/8Mpx+OlSrBl26wE03wYwZsGVLoqMWEYk/JcgiIgJA7dpw7rlhBr+VK2HaNPj3v2H9erj22jDj3377wZlnhvKMlSsTHbGISHxoFAsREdlBSkroSe7cGYYOhRUrYPLkbdNgP/dcGAUjNXXbRCUdO4bps0VECruk60E2sx5m9rWZLTSzIdk8v7eZvWZmX5jZXDM7JxFxiogUJ9WrwxlnhMT4xx/hk0/gxhtDIj1sGBx6KOy7b5gq+6mnYPnyREcsIrL7kqoH2cxKAg8C3YEM4FMzG+/u82JWuxCY5+5/M7N9ga/NbJS7b0hAyCIixU7JkqHcokOHUHrxyy/w1lvbxl4eOzas17r1tolKDj0USpVKbNwiInmVbD3IHYGF7v5dlPCOAU7Mso4DFc3MgArAL8Cmgg1TREQyVakSbuh78klYtgxmzYLhw6FyZbjjjnAjYNWqcPLJMHJkGI9ZRCSZJVUPMlAbWBKznAEcnGWdB4DxwDKgItDb3XVftYhIEjALPcetW8OQIfD77/D226FneeJEeOWVsF6LFttqlw87LMz0JyKSLMyTaER4MzsNOMbdB0TLZwId3f2imHVOBToDlwGNgClAa3f/Pcu+BgIDAWrUqNF+zJgxBXMSMdasWUOFChUK/LgiyUjXg7jD4sXl+OSTKnz6aRW++KIyGzeWoGzZzbRps5qOHVfRseMv1K69LtGhFghdEyLbJOp66Nq160x3T83anmw9yBlA3ZjlOoSe4ljnALd4yOwXmtn3QDPgk9iV3H0kMBIgNTXV09LS4hVzjtLT00nEcUWSka4HyXT22eHfP/+E9HSYNKkkEydW5b77qgJhquzM2uW0NChXLlGR5m7SpElccsklbN68mQEDBjBkyPb3ld9+++2MGjUKgE2bNjF//nxWrlxJlSpVOPfcc3nllVeoXbs2c+bM2WHfd9xxB1deeSUrV66kWrVqLFq0iObNm9O0aVMAOnXqxIgRI+J/kiIFJNl+RyRbgvwp0MTMGgJLgT7A37Os8wPQDXjfzGoATYHvCjRKERHZY+XLw/HHhwfAwoXbSjEeewzuvz+UXhxxREiWe/SAZs1CGUeibd68mQsvvJApU6ZQp04dOnToQM+ePWnRosXWda688kquvPJKAF577TXuvvtuqlSpAsDZZ59Np06duO+++3bY95IlS5gyZQr16tXbrr1Ro0bMmjUrficlIlsl1U167r4JGAy8CcwHxrr7XDMbZGaDotWGAoea2ZfA28BV7v5zYiIWEZH80rgxDB4Mb7wRRsaYPBkuuACWLAnTYbdoAQ0bwqBBYarsP/5IXKyffPIJjRs3Zv/996d06dL06dOHcePG5bj+6NGj6du379blww8/nEqVKmW77r/+9S9uu+02LBn+EhApppIqQQZw9wnufoC7N3L3YVHbCHcfEf28zN2PdvdW7n6guz+X2IhFRCS/lS0L3bvDXXfBvHmwaBGMGAFt24ZZ/Hr1CqNndO0apsqePTvUOBeUpUuXUrfutorAOnXqsHTp0mzXXbt2LZMmTeKUU07Z6X7Hjx9P7dq1ad269Q7Pff/997Rt25YjjjiC999/f/eDF5GdSrYSCxERkR3Urw/nnRceGzbAhx9um9VvyJDwqFlz28gYRx0F++wTv3iyu8E9px7f1157jc6dO28tr8jJ2rVrGTZsGJMnT97huZo1a/LDDz9QtWpVZs6cyUknncTcuXNz7IUWkT2TdD3IIiIiuSldOty8d8stYczlpUvhiSegS5cwjNzpp0O1amGa7JtughkzYEs+DwZap04dlizZNippRkYGtWrVynbdMWPGbFdekZNvv/2W77//ntatW9OgQQMyMjJo164dP/74I2XKlKFq1XATY/v27WnUqBHffPNN/pyMiOxACbKIiBRqtWrBOeeEGfxWroQPPoB//zv0NF97bZjxb7/94MwzQ3nGypV7fswOHTqwYMECvv/+ezZs2MCYMWPo2bPnDuv99ttvTJ06lRNPzDrn1Y5atWrFihUrWLRoEYsWLaJOnTp89tln7LfffqxcuZLNmzcD8N1337FgwQL233//PT8REcmWSixERKTISEkJ01ofeigMHQorVoSb/TLLMZ57LoyCkZq6bWSMjh3Ddrt2nBQeeOABjjnmGDZv3sy5555Ly5Yttw69NmhQuK/8lVde4eijj6Z8+fLbbd+3b18mT57M77//Tp06dbjxxhvp379/jsd77733uO6660hJSaFkyZKMGDFipyUbIrL7kmqikHhJTU31GTNmFPhxk21MP5FE0vUgibZlC8ycuS1Z/vjj0LbPPuGGwMyEuWbNgolH14TINom6HsysUEwUIiIiEhclSoRyiw4dQunFL7/AW29tS5jHjg3rtW69baKSQw+FUqUSG7eIFDzVIIuISLFUpUq4oe+JJ8KNfrNmhRv/KleGO+4INwJWrQonnwwjR8IPPyQ4YBEpMOpBFhGRYs8s9By3bg1XXQW//w7vvBNm9Zs4MYyOAWGyksxSjMMOC+M1i0jRox5kERGRLCpVgpNOgkcegcWLw2Qld94JtWvDAw/A0UeH3uUTTgjL336b6IhFJD+pB1lERCQXZtC8eXhcdhn8+Sekp4e65YkTw9TYEKbKzpyoJC0NypVLZNQisifUgywiIrILypeH44+H+++HhQthwYLw8wEHwOOPh+eqVAm9zHffDfPnbz8N9qhR0KABHHnkETRoEJZFJLmoB1lERGQPNG4MgweHx7p18P77oWd50qTQ43zZZWGq7B49YK+9QtnGX38BGIsXw8CBYT/9+iXyLEQklhJkERGRfFK2bBhTuXt3uOuuUL+cOYzcqFGwZs2O26xdC9dcowRZJJmoxEJERCRO6teH884Lo2CsWhXqmbOjIeREkosSZBERkQJQujTUq5f9c7VrF2wsIpI7JcgiIiIFZNiw7Ee3+P13ePfdgo9HRLKnBFlERKSA9OsXZuWrXx/MnPr1YfhwqFkTjjoKhg6FzZsTHaWIKEEWEREpQP36waJF8M47U1m0CIYMgRkzoG9fuO66MNrFihWJjlKkeFOCLCIikmAVKsCzz8Kjj8K0adCmTZiMREQSQwmyiIhIEjCDAQNg+nSoWBG6dYObboItWxIdmUjxowRZREQkiRx0UCi56N0brr1WJRciiaAEWUREJMlUrBgmFnnkEXjvvVByMXVqoqMSKT6UIIuIiCQhszAN9fTpoUb5yCPh5ptVciFSEJQgi4iIJLHWrWHmTDj99DAl9bHHwsqViY5KpGhTgiwiIpLkKlaE55+HESNCqUWbNvD++4mOSqToUoIsIiJSCJjBeefBxx+H2fi6dg2TjKjkQiT/KUEWEREpRNq0CSUXp54K//43HH+8Si5E8psSZBERkUKmUiUYPRoefhjefRfatg0TjIhI/lCCLCIiUgiZwaBB8NFHULYspKXBrbeq5EIkPyhBFhERKcTatoXPPoOTT4YhQ+CEE+DnnxMdlUjhpgRZRESkkKtUCV54AR56CN5+O9Qpf/BBoqMSKbyUIIuIiBQBZnD++aHkokwZOOIIuO02lVyI7I64Jchm9rSZVY5Z3sfMnojX8URERATatQslF716wVVXQc+esGpVoqMSKVzi2YN8kLuvzlxw91+BtnE8noiIiAB77w1jx8IDD8CUKaHk4sMPEx2VSOERzwS5hJntk7lgZlWAlDgeT0RERCJmcOGFITEuXRoOPxxuv10lFyJ5Ec8E+U7gQzMbamZDgQ+B23a2kZn1MLOvzWyhmQ3JYZ00M5tlZnPNbGo+xy0iIlJktG8fSi5OOgn+7//gxBNVciGyM3FLkN39GeAU4CdgBXCyuz+b2zZmVhJ4EDgWaAH0NbMWWdapDDwE9HT3lsBp+R+9iIhI0bH33vDii3D//fDmm2FouI8+SnRUIskr3xNkM6sU/VsF+BF4HhgF/Bi15aYjsNDdv3P3DcAY4MQs6/wdeNndfwBw9xX5Gb+IiEhRZAaDB4eSi5SUUHJx553gnujIRJKPeT5fGWb2urufYGbfA7E7N8Ddff9ctj0V6OHuA6LlM4GD3X1wzDr3AKWAlkBF4N6otzrrvgYCAwFq1KjRfsyYMXt8brtqzZo1VKhQocCPK5KMdD2IbC+R18SaNSncdltT3n9/Xw499GeuuuorKlXalJBYRCBx10PXrl1nuntq1vZ8v2nO3U+I/m24G5tbdrvMspwCtAe6AXsBH5nZx+7+TZY4RgIjAVJTUz0tLW03wtkz6enpJOK4IslI14PI9hJ9TRx/fCi5uOKKalx0URdeeAE6dUpYOFLMJfp6yCqe4yC/nZe2LDKAujHLdYBl2awzyd3/dPefgfeA1nsSq4iISHFjBhdfHGbcK1ECDjsM7rpLJRciEJ8a5LJRrXG1aHKQKtGjAVBrJ5t/CjQxs4ZmVhroA4zPss444DAzSzGzcsDBwPx8Pg0REZFioUMH+Pxz+Nvf4PLLw2gXv/6a6KhEEisePcjnATOBZtG/mY9xhBEqcuTum4DBwJuEpHesu881s0FmNihaZz4wCZgNfAI85u5z4nAeIiIixULlyvDSS3DPPTBxYhjlYvr0REclkjjxqEG+F7jXzC5y9/t3Y/sJwIQsbSOyLN8O3L5HgYqIiMhWZnDJJXDIIXD66aHk4rbbQptld4eQSBEWz4lCfjSzigBm9h8ze9nM2sXxeCIiIrKHOnYMJRfHHQf/+hf06qWSCyl+4pkgX+vuf5hZF+AY4Gng4TgeT0RERPLBPvvAK6+Em/beeAPatYNPPkl0VCIFJ54J8ubo3+OBh919HFA6jscTERGRfGIWepCnTYMtW6BLF7j3Xo1yIcVDPBPkpWb2CHA6MMHMysT5eCIiIpLPDj44lFwceyxceimcfLJKLqToi2fCejphNIoe7r4aqAJcGcfjiYiISBxUqQKvvhqmpn799VBy8emniY5KJH7iMQ5ypejHskA6sCoaF3k9MCO/jyciIiLxZwaXXQbvvx9KLjp3DjPxqeRCiqJ49CA/H/07k5AQx46FrARZRESkEOvUKZRcHHNMmInv1FNh9epERyWSv/I9QXb3E6J/G7r7/tG/mY/98/t4IiIiUrCqVIHx4+GOO8K/7drBDHWBSREStxpkM3s7L20iIiJS+JiFqanfew82bQolFw88oJILKRriUYNcNqo5rmZm+5hZlejRAKiV38cTERGRxDnkkFBy0b07XHQRnHYa/PZboqMS2TPx6EE+j1Bv3Izt64/HAQ/G4XgiIiKSQFWrhlKL224Lo120awczZyY6KpHdF48a5HvdvSFwRZYa5Nbu/kB+H09EREQSr0QJuPLKUHKxYQMceig8+KBKLqRwSonXjt39fjM7EGhBGPIts/2ZeB1TREREEuvQQ0PJxVlnweDBMHUqPPoo7L13oiMTybt43qR3PXB/9OgK3Ab0jNfxREREJDlUqwavvQa33govvwzt28NnnyU6KpG8i+dMeqcC3YAf3f0coDVQJo7HExERkSRRogT83/+FHuR168LNfA89pJILKRzimSD/5e5bgE3R7HorAI2DLCIiUox07gyzZsGRR8KFF0KfPvD774mOSiR38UyQZ5hZZeBRwigWnwGfxPF4IiIikoSqVYM33oDhw+Gll0LJxeefJzoqkZzFLUF29wvcfbW7jwC6A2dFpRYiIiJSzJQoAUOGwLvvwl9/hZKLESNUciHJqUBm0nP3Re4+WzPpiYiIFG+HHRZ6j9PS4PzzoW9flVxI8tFMeiIiIlKg9t0XJkyAm2+GF1+E1NRQpyySLApiJr0Z0UMz6YmIiAgQSi6uvjqUXPz5J3TqBI88opILSQ7xSJA/BA4lmkkPuBGYA0wFno/D8URERKSQOvzwUHJxxBEwaBD06wd//JHoqKS4i0eC/AiwPppJ73BgOPA08BswMg7HExERkUKsenWYOBFuugleeCGUXMyeneiopDiLR4Jc0t1/iX7uDYx095fc/VqgcRyOJyIiIoVciRJwzTXwzjuhB/ngg8MU1Sq5kESIS4JsZinRz92Ad2KeS8lmfREREREglFrMmhVGuxg4EM44A9asSXRUUtzEI0EeDUw1s3HAX8D7AGbWmFBmISIiIpKj6tVh0iQYOhTGjFHJhRS8fE+Q3X0YcDnwFNDFfeuXIyWAi/L7eCIiIlL0lCgB//kPvP02/PZbKLl47DGVXEjBiMtEIe7+sbu/4u5/xrR94+6fxeN4IiIiUjSlpYWSiy5d4J//hH/8QyUXEn9xm0lPREREJD/UqBFKLv77X3j++VBy8eWXiY5KijIlyCIiIpL0SpaEa6+Ft96C1atDycUTT6jkQuJDCbKIiIgUGl27hpKLQw+F/v3hrLNUciH5TwmyiIiIFCr77Qdvvgk33gjPPQcdOsCcOYmOSooSJcgiIiJS6JQsCdddF0oufv0VOnaEJ59MdFRSVChBFhERkULryCNDyUWnTnDuuXD22fDnnzvbSiR3SZcgm1kPM/vazBaa2ZBc1utgZpvN7NSCjE9ERESSy377wZQpcP318MwzoeRi7txERyWFWVIlyGZWEngQOBZoAfQ1sxY5rHcr8GbBRigiIiLJqGRJuOGGkCivWhWS5KeeSnRUUlglVYIMdAQWuvt37r4BGAOcmM16FwEvASsKMjgRERFJbt26hZKLgw+Gc84JD5VcyK5KSXQAWdQGlsQsZwAHx65gZrWBXsCRQIecdmRmA4GBADVq1CA9PT2/Y92pNWvWJOS4IslI14PI9nRNxNd//gP16jXg6afr8+67a7nhhrk0aLA20WFJDpLteki2BNmyacs6BPg9wFXuvtksu9WjjdxHAiMBUlNTPS0tLZ9CzLv09HQScVyRZKTrQWR7uibir1s3OOMM6NevPBde2JGHHw5TVUvySbbrIdlKLDKAujHLdYBlWdZJBcaY2SLgVOAhMzupQKITERGRQqV791By0aFDmFSkf39Yq45k2YlkS5A/BZqYWUMzKw30AcbHruDuDd29gbs3AP4HXODurxZ4pCIiIlIo1KoVxkv+z3/CWMkdO8L8+YmOSpJZUiXI7r4JGEwYnWI+MNbd55rZIDMblNjoREREpLBKSYGhQ2HSJFixAlJT4dlnEx2VJKtkq0HG3ScAE7K0jchh3bMLIiYREREpGo4+OpRc9O0b6pGnToX77oNy5RIdmSSTpOpBFhEREYm3WrXg7bfhmmvg8cfDkHBffZXoqCSZKEEWERGRYiclBW66KZRc/PhjKLkYNSrRUUmyUIIsIiIixdYxx4SSi3btwpBw//wn/PVXoqOSRFOCLCIiIsVa7drwzjtw9dXw2GOh5OLrrxMdlSSSEmQREREp9lJS4OabYeJEWLYM2reH559PdFSSKEqQRURERCI9eoSSi7ZtoV8/GDhQJRfFkRJkERERkRh16sC778KQIfDoo9CpE3zzTaKjkoKkBFlEREQki5QUGD4c3ngDli4NJRejRyc6KikoSpBFREREcnDccfD553DQQfD3v8OgQSq5KA6UIIuIiIjkom5dSE+Hq66CRx6BQw6BBQsSHZXEkxJkERERkZ0oVQpuuQVefx2WLAnjJr/wQqKjknhRgiwiIiKSR8cfH0a5aNUK+vSB88+HdesSHZXkNyXIIiIiIrugbl2YOhWuvBJGjAglFwsXJjoqyU9KkEVERER2UalScNtt8NprsHhxKLkYOzbRUUl+UYIsIiIisptOOCGUXLRsCb17w4UXquSiKFCCLCIiIrIH6tWD996DK66Ahx6CQw9VyUVhpwRZREREZA+VKgW33w7jx8OiRaHk4sUXEx2V7C4lyCIiIiL55G9/CxOLtGgBp58OgwfD+vWJjkp2lRJkERERkXxUv34oubjsMnjwwVBy8e23iY5KdoUSZBEREZF8Vro03HknvPoqfPddKLl46aVERyV5pQRZREREJE5OPDGUXDRrBqeeChdfrJKLwkAJsoiIiEgcNWgA778P//oX3H8/dO4cepUleSlBFhEREYmz0qXhrrvglVdCPXK7dvDyy4mOSnKiBFlERESkgJx0Enz2GRxwAJxyClxyiUoukpESZBEREZEC1LAhTJsWkuP77oPDDoPvv090VBJLCbKIiIhIAStdGu65J5RZfPMNtG0byi8kOShBFhEREUmQXr3CKBdNmsDJJ8Oll8KGDYmOSpQgi4iIiCRQZsnFxRfDvfdCly5humpJHCXIIiIiIglWpkxIjl96aVvJxauvJjqq4ksJsoiIiEiSOPnkMMpFo0ah/OKyy1RykQhKkEVERESSyP77wwcfwODBcPfdcPjhsHhxoqMqXpQgi4iIiCSZMmXCrHsvvgjz50ObNjB+fKKjKj6UIIuIiIgkqVNPDSUX++8PJ54Il1+ukouCoARZREREJIk1agQffhhKLu66SyUXBUEJsoiIiEiSyyy5GDsW5s0Lo1y89lqioyq6ki5BNrMeZva1mS00syHZPN/PzGZHjw/NrHUi4hQREREpaKedFkouGjSAnj3hyith48ZER1X0JFWCbGYlgQeBY4EWQF8za5Flte+BI9z9IGAoMLJgoxQRERFJnMaNQ8nFBRfAHXeEkosffkh0VEVLUiXIQEdgobt/5+4bgDHAibEruPuH7v5rtPgxUKeAYxQRERFJqLJl4cEHYcwYmDs3lFy8/nqioyo6zN0THcNWZnYq0MPdB0TLZwIHu/vgHNa/AmiWuX6W5wYCAwFq1KjRfsyYMfELPAdr1qyhQoUKBX5ckWSk60Fke7omJL9kZOzFjTe2YOHCivTu/QMDBnxPSkry5Hd5kajroWvXrjPdPTVre0qBR5I7y6Yt23fYzLoC/YEu2T3v7iOJyi9SU1M9LS0tn0LMu/T0dBJxXJFkpOtBZHu6JiQ/nXpqmHXv4YfrsWRJPcaMgbp1Ex1V3iXb9ZBsJRYZQOzbWQdYlnUlMzsIeAw40d1XFVBsIiIiIkmpbFl46CEYPRpmzw4Ti0yYkOioCq9kS5A/BZqYWUMzKw30AbabN8bM6gEvA2e6+zcJiFFEREQkKfXpE0a5qFsXjj8ehgzRKBe7I6kSZHffBAwG3gTmA2Pdfa6ZDTKzQdFq1wFVgYfMbJaZzUhQuCIiIiJJp0kT+OgjOO88uPVW6NoVlixJdFSFS7LVIOPuE4AJWdpGxPw8ANjhpjwRERERCfbaC0aMgCOOgIEDwygXzz4Lxx6b6MgKh6TqQRYRERGR/NO3L8yYAbVrw3HHwdVXw6ZNiY4q+SlBFhERESnCmjaFjz8OPcm33BJKLjIyEh1VclOCLCIiIlLE7bUXPPIIPPccfP55KLmYNCnRUSUvJcgiIiIixUS/fjBzJtSsGeqRr7lGJRfZUYIsIiIiUow0bQrTp8OAAXDzzXDkkbB0aaKjSi5KkEVERESKmb32gkcfDSNbfPZZmFjkzTcTHVXyUIIsIiIiUkydcUYY5WK//aBHD5VcZFKCLCIiIlKMNWsWSi769w8lF926wbJliY4qsZQgi4iIiBRz5crBY4/B00+HHuU2bWDy5ERHlThKkEVEREQEgH/8IyTI1auHkotrr4XNmxMdVcFTgiwiIiIiWzVvDp98AmefDTfdBEcdBcuXJzqqgqUEWURERES2U64cPPEEPPVUSJbbtIEpUxIdVcFRgiwiIiIi2TrrLPj0U6hWDY45Bq67LvuSi0mTJtG0aVMaN27MLbfcssPz7s7FF19M48aNOeigg/jss88AWLduHR07dqR///60bNmS66+/fodt77jjDsyMn3/+eWvb7NmzOeSQQ2jZsiWtWrVi3bp1+XfSKEEWERERkVy0aBF6kc86C4YO3bHkYvPmzVx44YVMnDiRefPmMXr0aObNm7fdPiZOnMiCBQtYsGABI0eO5PzzzwegTJkyvPPOOzz++OPMmjWLSZMm8fHHH2/dbsmSJUyZMoV69eptbdu0aRNnnHEGI0aMYO7cuaSnp1OqVKl8PWclyCIiIiKSq/Ll4cknw2P6dGjbFt5+Ozz3ySef0LhxY/bff39Kly5Nnz59GDdu3Hbbjxs3jn/84x+YGZ06dWL16tUsX74cM6NChQoAbNy4kY0bN2JmW7f717/+xW233bZd2+TJkznooINo3bo1AFWrVqVkyZL5er5KkEVEREQkT84+O5RcVKkC3bvDDTfAkiVLqVu37tZ16tSpw9Isc1cvXZrzOps3b2bAgAFUr16d7t27c/DBBwMwfvx4ateuvTURzvTNN99gZhxzzDG0a9eO2267Ld/PMyXf9ygiIiIiRVbLliFJvuACuPFGOPBA56CDtl8ntscXQg1yVpnrlCxZkscee4w2bdrQq1cv5syZw/7778+wYcOYnM1gzJs2bWLatGl8+umnlCtXjm7dutG+fXu6deuWb+eoHmQRERER2SXly4dJRZ54Ar75pg7/+98S3nknPJeRkUGtWrW2W79OnTosWbJk63J261SuXJm0tDQmTZrEt99+y/fff0/r1q1p0KABGRkZtGvXjh9//JE6depwxBFHUK1aNcqVK8dxxx239aa//KIEWURERER2yznnwPTpHXBfQLdu33PttRsYM2YMPXv23G69nj178swzz+DufPzxx+y9997UrFmTlStXsnr1agD++usv3nrrLZo1a0arVq1YsWIFixYtYtGiRdSpU4fPPvuM/fbbj2OOOYbZs2ezdu1aNm3axNSpU2nRokW+npdKLERERERkt7Vpk8Lo0Q9wzjnHcNNNm9l//3OpVq0lI0aMAGDQoEEcd9xxTJgwgcaNG1OuXDmefPJJAJYvX85ZZ53F77//zl577cXpp5/OCSeckOvx9tlnHy677DI6dOiAmXHcccdx/PHH5+s5WXY1IUVNamqqz5gxo8CPm56eTlpaWoEfVyQZ6XoQ2Z6uCSlq3MMoFxdeCJUrw/PPQ9eueds2UdeDmc1099Ss7SqxEBEREZE9ZgbnnhvGTN577zBe8tCh2U8skuyUIIuIiIhIvmnVCmbMgL59w8x7PXrATz8lOqpdowRZRERERPJVhQrw7LPw2GMwbRq0aQPp6YmOKu+UIIuIiIhIvjOD/v3DzHuVKkG3bnDTTbBlS6Ij2zklyCIiIiISNwcdFEoueveGa68NJRcrViQ6qtwpQRYRERGRuKpYEUaNgpEj4b33QsnF1KmJjipnSpBFREREJO7M4J//DCUXFSvCkUfC6adD/fpw5JFH0KBBSKKTgSYKEREREZEC07p1KLk4+mh48cXMVmPxYhg4MCz165eo6AL1IIuIiIhIgapYEZYt27F97Vq45pqCjycrJcgiIiIiUuCWLMm+/YcfCjaO7ChBFhEREZECV6/errUXJCXIIiIiIlLghg2DcuW2bytXLrQnmhJkERERESlw/fqFYd/q1wczp379sJzoG/QgCRNkM+thZl+b2UIzG5LN82Zm90XPzzazdomIU0RERET2TL9+sGgRvPPOVBYtSo7kGJIsQTazksCDwLFAC6CvmbXIstqxQJPoMRB4uECDFBEREZEiLakSZKAjsNDdv3P3DcAY4MQs65wIPOPBx0BlM6tZ0IGKiIiISNGUbBOF1AZiB/3IAA7Owzq1geWxK5nZQEIPM8AaM/s6f0PNk2rAzwk4rkgy0vUgsj1dEyLbJOp6qJ9dY7IlyJZNm+/GOrj7SGBkfgS1u8xshrunJjIGkWSh60Fke7omRLZJtush2UosMoC6Mct1gKzzrORlHRERERGR3ZJsCfKnQBMza2hmpYE+wPgs64wH/hGNZtEJ+M3dl2fdkYiIiIjI7kiqEgt332Rmg4E3gZLAE+4+18wGRc+PACYAxwELgbXAOYmKNw8SWuIhkmR0PYhsT9eEyDZJdT2Y+w7luyIiIiIixVaylViIiIiIiCSUEmQRERERkRhKkLNhZnXMbJyZLTCzb83s3uimwazr1TKz/+VhfxPMrPJuxnKDmV2xO9uK5MTMrjGzudF07bPMLOt44wlhZunRVPNfmNmnZtZmN/eTZmaH5nN4UoSZ2ZoCPt6H0b8NzOzvMe1nm9kDe7DfVDO7Lz9iFMmrgr5+CoIS5CzMzICXgVfdvQlwAFABGJZlvRR3X+bup+5sn+5+nLuvjke8IrvKzA4BTgDauftBwFFsP/lOPI5ZchdW7+furYGHgNt385BpgBJkSTqZ14K7Z34+GwB/z3GDXeTuM9z94vzan0gy2MXfIflCCfKOjgTWufuTAO6+GfgXcK6ZXWBmL5rZa8Dk6C//OQBmVs7MxkY9ci+Y2XQzS42eW2Rm1aL155vZo1Hv3WQz2yta559Rj9kXZvaSmZVLzOlLMVAT+Nnd1wO4+8/uvgzAzHqY2VdmNs3M7jOz16P27b7JMLM5ZtYg+vlVM5sZfaYHxqyzxsz+a2bTgUPM7Awz+yTqsX4kD//hfUSYJRMzqxIdZ7aZfWxmB+XUHsU1CPhXdKzD8udlk+LGzNpEn6vZZvaKme0TtXeI2j4ys9tjfg80MLP3zeyz6HFo1J5mZu+a2fPAl1FbZo/bLcBh0Wf1X1FbLTObFH2LeVtMPGvM7NboenvLzDpG37p8Z2Y9Y46Ved1WMLMnzezLKN5TCuJ1k+Ir+vylm9n/ot8loyw41szGZlnvtejno6Nr6bMox6oQtS8ys+vMbBpwmpldbGbzos/ymGid8mb2RJQ/fW5mJ+bXuShB3lFLYGZsg7v/DvxAGBbvEOAsdz8yy3YXAL9GPXJDgfY57L8J8KC7twRWA5n/Yb3s7h2inrP5QP98OBeR7EwG6prZN2b2kJkdAWBmZYFHgb8BhwH75XF/57p7eyAVuNjMqkbt5YE57n4wsAroDXR29zbAZqDfTvbbA3g1+vlG4PPo+vo38ExO7e6+CBgB3O3ubdz9/Tyeh0hWzwBXRZ+vL4Hro/YngUHufgjhs5xpBdDd3dsRPu+xpQ4dgWvcvUWWYwwB3o8+q3dHbW2i7VsBvc0sc3Ks8kB6dL39AdwEdAd6Af/NJv5rCXMFtIrO4Z1dOnuR3dMWuBRoAewPdAamAJ3MrHy0Tm/gBTOrBvwHOCq6bmYAl8Xsa527d3H3MYRrpW30WR4UPX8N8I67dwC6ArfHHGOPJNU4yEnCyGbq6pj2Ke7+SzbPdwHuBXD3OWY2O4f9f+/us6KfZxK+XgM40MxuAioTSjre3J3gRXbG3deYWXtCEtyV8J/UEGAW4fO5AMDMngMG5rijbS42s17Rz3UJfwSuIiQOL0Xt3Qh/NH5qZgB7EZKJ7IyK/oMrCbSL2roQ/THp7u+YWVUz2zuXdpE9En2OKrv71KjpaeBFC/eTVHT3D6P25wklSwClgAcs1M5vJpToZfrE3b/P4+HfdvffojjmAfUJZVAbgEnROl8C6919o5l9ybbfJbGOIky4BYC7/5rH44vsiU/cPQPAzGYBDdx9mplNAv5m4d6t44H/A44gJNIfRL8bShO+Pcz0QszPswm/H15lW+fJ0UBP2/YNZ1mgHqGjcY8oQd7RXLb16gJgZpUIv/g3A3/msJ3lcf/rY37eTEgUAJ4CTnL3L8zsbEINpUhcRKVD6UB69Mv1LEKCnNPA6JvY/hunshC+JiP8Ej7E3deaWXrmc4S//DN71wx42t2vzkN4/YAvCF89PwicTPbXl+fSLhIvuf1f/y/gJ6A14XpZF/NcTr87spP190Tm7+qNvm3ygi2Z67n7FjPL7vd5Th0+IvGU0+f3BeBC4BfgU3f/w0JWPMXd++awr9jr5njgcKAncK2ZtSR8xk9x96/z8wRAJRbZeRsoZ2b/gK2F4XcSEti1uWw3DTg92qYF4auxXVERWG5mpdj5V88iu83MmppZk5imNsBi4CugoZk1itpj/8NaRNSba2btgIZR+96E0qK1ZtYM6JTDYd8GTjWz6tE+qphZ/ZxidPeNhK/dOplZc+A9ousiSsp/jkqfcmr/g3BNieyWqAf315ga9jOBqVEv7B9mlvlZ7xOz2d7AcnffEq2flxuL4vlZnQwMzlzIrKEWSZB0wu+Rf7KtZ/hjoLOZNYat93MdkHVDMysB1HX3dwk9z5XZ9m37RVGijZm1za9glSBnEf113otQEL4A+IbQC/DvnWz6ELBvVFpxFeGrgN924dDXAtMJdTpf7WrcIrugAvB05s0OhK+3bnD3dYSSijeimyIWx2zzElAl+rrsfMJ1AeHr3pRoP0MJ/9ntwN3nERLeydG6Uwg3C+bI3f8i/HF6BXADkBptewuhx5tc2l8Deplu0pO8K2dmGTGPywifp9ujz1cbttX59gdGmtlHhB6szP/rHwLOMrOPCeUVeek1ng1ssnCD9r92uvauuQnYx8JNtV8QSqpEEiL6RvF14NjoX9x9JXA2MDq6zj4GmmWzeUnguegbz88J95isJvzeKQXMtnCz7ND8ildTTeeTqKe5lLuvi3rg3gYOcPcNCQ5NZLdEPbJXuPsJO1lVpFgxswruvib6eQhQ090vSXBYIpKPVIOcf8oB70YlEgacr+RYRKRIOt7Mrib8Dl1M6AETkSJEPcgiIiIiIjFUgywiIiIiEkMJsoiIiIhIDCXIIiIiIiIxlCCLiIiIiMRQgiwiIiIiEkMJsoiIiIhIDCXIIiIiIiIxlCCLiIiIiMRQgiwiIiIiEkMJsoiIiIhIDCXIIpK0zOxsM5uW6DgyWfCkmf1qZp/s5j7qmdkaMysZLdcws/fM7A8zuzM/jlHUmdlNZvazmf2Y6Fiyyvr+ikjhpARZRHaLmS0ys7+iZOCnKKmrkOi44qwL0B2o4+4dsz4ZJfSbo9dkjZl9H70uB2Su4+4/uHsFd98cNQ0EfgYqufvlOztGPJlZAzNzM0vJ4fkRMee2wcw2xixPLKAY6wKXAy3cfb+COOZO4llkZkdlLmfz/opIIaQEWUT2xN/cvQLQDugA/CfB8cRbfWCRu/+ZyzofRa/J3sBRwF/ATDM7MJd9znN334VjZCunxDa/uPugKPmrANwMvJC57O7HFlAc9YFV7r5iVzeM9+sjIkWHEmQR2WPuvhSYCOyQBEa9jndkaRtnZpdFPw8xs2+jEoN5ZtYru2Nk17tpZulmNiBm+Vwzmx+VJ7xpZvWjdjOzu81shZn9Zmazc0pYzayWmY03s1/MbKGZ/TNq7w88BhwS9ZjeuJPXZLO7f+vuFwBTgRuynoeZPQWcBfxftM/zsjuGmZ1gZrPMbLWZfWhmB8XEu8jMrjKz2cCf0X47ReutNrMvzCwty2s21Mw+iF7zyWZWLXr6vejf1dHxD8ntHLO8btnFkeN7G/W2TzOzO6L363szOzbL899F235vZv2intopQK0ovqeidXua2dzofNPNrHkucTWOXv9zzGxJdOxBZtYh+lysNrMHYrZvZGbvmNkqC2Udo8yscvTcs0A94LUonv/L+jnN6fMUPXeDmY01s2ei85xrZqkxz19lZkuj5742s255fT9EZA+5ux566KHHLj+ARcBR0c91gbnA0GzWOxxYAli0vA+hV7VWtHwaUIvwB3tv4E+gZvTc2cC06OcGgAMpMftOBwZEP58ELASaAymE3uwPo+eOAWYClQGL1qmZw3lNBR4CygJtgJVAt6zx5LBtts8D5wI/ZXcewFPATTntg9A7vwI4GChJSKgXAWVi3odZ0XuwF1AbWAUcF72m3aPlfWNes2+BA6L104FbcnqNcznXG4DnsnwetsaRx/d2I/DP6LzOB5ZF70954HegabRuTaBl9HMakBFz3AOi/XYHSgH/F30OSufw+mSe44joPT4aWAe8ClSPXr8VwBHR9o2jfZcB9iX8EXFPdtdBDu9vbp+nG6JjHxe9BsOBj6PnmhKum1ox+22U6OteDz2Ky0M9yCKyJ141s9XANEIicHM267xPSBgOi5ZPJZQhLANw9xfdfZm7b3H3F4AFwO7U3p4HDHf3+e6+KYqlTdSLvBGoCDQjJOrz3X151h1YqG/tAlzl7uvcfRahR/fM3Ygn1jKgym5u+0/gEXef7qFX+mlgPdApZp373H2Ju/8FnAFMcPcJ0Ws6BZhBSMIyPenu30TrjyUkbvkhNo68vLeL3f1RD/W6TxMS4RrRc1uAA81sL3df7u5zczhmb+ANd5/i7huBOwiJ8KE5xRUZGr3HkwkJ9mh3X+Hh25D3gbbROSyM9r3e3VcCdwFH5OXFyOPnaVr0Xm0GngVaR+2bCUl5CzMr5e6L3P3bvBxXRPacEmQR2RMnuXtld6/v7he4+19m9m/bduPWCHd3YAzQN9rm78CozB2Y2T9iygdWE8o0qu1wpJ2rD9wbs59fCL2Rtd39HeAB4EHgJzMbaWaVstlHLeAXd/8jpm0xoVdxT9SO4tkd9YHLM88rOre6hFgzLcmy/mlZ1u9CSD4zxY7+sBbIr5srY+PIy3u7NQ53Xxv9WMFD/XVvYBCw3MzeMLNmORyzFuE9ytzPliiO2PdsSdaNgJ9ifv4rm+UK0TlUN7MxUanD78Bz5P3zmZfPU9b3oqyZpbj7QuBSQi/ziiiG2PdcROJICbKI5Ct3v9m33bg1KGoeDZwa9eYeDLwEEC0/CgwGqrp7ZWAOIbHNKvOmtXIxbbGjGCwBzosS9szHXu7+YRTXfe7eHmhJ+Fr+ymyOsQyoYmYVY9rqAUvzev456EXoldwdS4BhWc6rnLuPjlnHs6z/bJb1y7v7LXk4lu98lbxtv4vv7Y47cn/T3bsTEvuvon1lZxnhj4LM4xrhD4jY92xPzmt4tP1B7l6J0EMfew657XuPPk/u/ry7dyGcnwO37krgIrL7lCCLSNy5++eE2svHgDfdfXX0VHnCL/6VAGZ2Dtnc6BftYyUhsTjDzEqa2blAo5hVRgBXm1nLaF97m9lp0c8dzOxgMytFSLTXEb7CznqMJcCHwHAzK2vhZrj+xPR451UUY0Mzu59QN5vrTX25eBQYFMVvZlbezI7PknTFeg74m5kdE8VQ1szSzKxOHo61klDasP9uxhorz+9tVhbGhu5pZuUJ5SRryOb9iowFjjezbtH7e3m0zYd7GH+mitHxV5tZbXb8w+oncni99uTzZGZNzexIMytD+Lz+Rc6vgYjkMyXIETO7xMzmRHcRX5rN82Zm90V3Ic82s3Yxz/WI7jBeaGZDduPY7c3sy2j7+6IeECzcWf1l9BXlNDNrsUcnKZJYownDnj2f2eDu84A7gY8IiUYr4INc9vFPQoKyitATvDUJcvdXCD1sY6KvwucAmaMiVCIkmr8SvuJeRahVzU5fwg1Ry4BXgOujOt68OsTM1hBuMkuPjt3B3b/chX1s5e4zCOf9QBT/QsINbjmtvwQ4Efg3ITldQnjNdvr/fVTmMAz4ICqL6LSzbXLZ166+t7FKEBLdZYTSlCOAC3I4zteEXt37CeNJ/40w/OCG3Y09ixsJN0r+BrwBvJzl+eHAf6LX64pstt/dz1MZ4BbCOf1IuIHw37tzAiKy6zLvKi/WLAz3NIZw88gGYBJwvrsviFnnOOAiwo0uBwP3uvvBFmZL+oZwl3MG8CnQN/rlkNfjfwJcAnwMTCDcUDLRzCq5++/ROj2BC9y9xx6fsIiIiIjkSD3IQXPC0Dpro7vfpxJqBmOdCDzjwcdAZTOrSUiqF7r7d1GPxZho3czxMyeZ2Uwzez+7m0yifVRy94+im5meIQxXRWZyHMn8ulJERERE4kgJcjAHONzMqppZOUIvcd0s69Rm+zuhM6K2nNoBRgIXRTcGXUEYCzOr2tE22W2PmV1oZt8CtwEX7+J5iYiIiMgu0rSbgLvPN7NbCTM0rQG+ADZlWS27O689p3Yzq0AYh/PFqKQYQk1ZVjntNzO2B4EHzezvhIkPzsrlVERERERkDylBjrj748DjAGZ2M9v36hItx/Yq1yHcdFE6h/YSwGp3bxO7k6hmeWa0OB54ONom6/ZZjYnWFREREZE4KhY36VWrVs0bNGiQ6zobN26kVKlSbNiwgW+++YZmzZqRkrLt74fffvuNFStW0LhxY/7880+WLFlC8+bNcXfmzJnDAQccQKlSpfjqq69o2LAhe+21F/PmzaNmzZrss88+uDt//fUX5cqV2+HY8+fPp27dupQvX56FCxdSvXp19t57b9atW0fZsmUBWL16NcuXL6d58+b5+tqIFJQ///yT8uXLJzoMkaSha0Jkm0RdDzNnzvzZ3ffN2l4sepAbNGjAjBkzcl3nsMMOY9WqVZQqVYo33niDbt26MWLECAAGDRqEuzN48GAmTZpEuXLlmDp1KqmpqQBMmDCBSy+9lLVr13LNNddwzTXXADB69Giefvppli9fzsaNG+nTpw/XXXfdDseeMWMGZ599NqtXr+bMM8/k/vvvx8y45JJLeOuttyhVqhR169Zl3LhxtGzZMp9fHZGCkZ6eTlpaWqLDEEkauiZEtknU9WBmi7NtLw49yKmpqb6zBDke9J+fyDa6HkS2p2tCZJsEJsgz3T01a7tGsRARERERiaEEWUREREQkhhJkEREREZEYSpBFRERERGIoQRYRERERiaEEOR5GjYIGDTjiyCOhQYOwLCIiIiKFQrEYB7lAjRoFAwfC2rVhDunFi8MyQL9+iYxMRERERPJACXJ+u+YaWLt2+7a1a+GCC+DXX6F2bahVKzz22w9KlUpMnCIiIiKSLSXI+e2HH7Jv//13uOii7dvMoHr1kCzHJs6ZP2f+W7UqlFA1jIiIiEhBUIKc3+rVC2UV2bV/8gksWwZLl4Z/Y3/OyIDp02Hlyh23LVVqW/KcUzJdqxZUqhT/8xMREREp4pQg57dhw7bWIG9VrhzcfDPUqBEebdvmvP2GDfDjj9kn0cuWwdy5MGVK6JHOqkKFnSfRtWpBmTL5f94iIiIiRUShTJDNrDlwCVANeNvdH05wSNtk3oh3zTX4Dz9g9eqFpDmvN+iVLh16m+vVy329NWu2Jc3Z9Up/+GH4ef36HbetWjX3JLp27VD6UbLkrp27FBlff/01vXv33rr83Xff8d///pdLL710a5u7c8kllzBhwgTKlSvHU089Rbt27QCYNGkSl1xyCZs3b2bAgAEMGTJkl44/c+ZMzj77bP766y+OO+447r33XswMgLFjx3LDDTdgZrRu3Zrnn39+z09YREQkRoEnyGb2BHACsMLdD4xp7wHcC5QEHnP3W3Lah7vPBwaZWQng0TiHvOv69YN+/Ziank5aWlp8jlGhAhxwQHjkxB1++SXnJHrZMpg9O/RYb9my/bYlSoSbCHNLomvVgn32CbXUUqQ0bdqUWbNmAbB582Zq165Nr169tltn4sSJLFiwgAULFjB9+nTOP/98pk+fzubNm7nwwguZMmUKderUoUOHDvTs2XOXjn/++eczcuRIOnXqxHHHHcekSZM49thjWbBgAcOHD+eDDz5gn332YcWKFfl1yiIiIlslogf5KeAB4JnMBjMrCTwIdAcygE/NbDwhWR6eZftz3X2FmfUEhkT7kuyYhd7iqlWhVauc19u0CVasyDmJ/vZbeP/9kGxnVbZs3so6ypeP33lKXL399ts0atSI+vXrb9c+btw4/vGPf2BmdOrUidWrV7N8+XIWLVpE48aN2X///QHo06cP48aN45BDDuHbb7/lwgsvZOXKlZQrV45HH32UZs2abbff5cuX8/vvv3PIIYcA8I9//INXX32VY489lkcffZQLL7yQffbZB4Dq1asXwCsgIiLFTYEnyO7+npk1yNLcEVjo7t8BmNkY4ER3H07obc5uP+OB8Wb2BrDDd6xmNhAYCFCjRg3S09Pz7Rzyas2aNQk57h7Ze+/waN58h6dKbNhA6Z9/psyqVeHfn3+m9KpVlMn8+YMPKPPzz5Rct26HbTeVL8/6atVYX60aG6pWDf9Wq8b6qlXDv9WqsaFKFTylUFb9FGl33303qampO3yWZ8+ezYEHHri1vXz58owfP54ff/yRlJSUre1//PEH8+fPp1WrVpx22mlcdtll1KlTh3nz5vH3v/+du+66a7v9fv3115QvX37r9itXrmT27Nmkp6fz4Ycf8sMPP3DPPfewZcsWzj77bDp27BjnV0AkPgrl7wiROEm26yFZspHawJKY5Qzg4JxWNrM04GSgDDAhu3XcfSQwEiA1NdXjVuqQi/R4llgkK/dwA2GWXuiUZctIWbqU8suWwVdfhec2bdp+WzPYd9+dl3VUq6Zh7wrIhg0b+PTTT3nqqaeoUaPGds9VqVKFtm3b0qVLFwD22WcfUlNT+e6771iyZMnWz/6SJUv4448/KFmyJPPnz+eOO+7Yuo/169fvcI2UL1+effbZZ2t7yZIlmTJlCmlpaVSuXJn169fz+eefk5GRwWGHHcacOXOoXLlyvF4Ckbgplr8jRHKQbNdDsiTI2RWxek4ru3s6kB6vYGQPmOXaC73Vli3w8885l3UsWwaffhpKP7IqVQpq1szbsHeqj94jEydOpF27djskxwB16tRhyZJtf9dmZGRQq1YtNmzYkG37li1bqFy58tba5kybN2+mffv2APTs2ZPzzz+fjIyMHbbPPGanTp0oVaoUDRs2pGnTpixYsIAOHTrk52mLiEgxlywJcgZQN2a5DrAsQbFIQShRIoyUUb06tGmT83obNsBPP+WcRM+fD2+/Db/9tuO25cvnnkTXrh0S7bJl43aahd3o0aPp27dvts/17NmTBx54gD59+jB9+nT23ntvatasyb777suCBQv4/vvvqV27NmPGjOH5559n5cqVNGzYkBdffJHTTjsNd2f27Nm0bt16h6S5YsWKfPzxxxx88ME888wzXBRNsnPSSScxevRozj77bH7++We++eabrbXOIiIi+SVZEuRPgSZm1hBYCvQB/p7YkCQplC4NdeuGR27+/DP3Ye8+/jj8m92wd1Wq7Lyso3p1KGb10WvXrmXKlCk88sgjW9tGjBgBwKBBgzjuuOOYMGECjRs3ply5cjz55JMApKSk8MADD3DMMcewefNmzj33XFq2bEl6ejqjRo3i/PPP56abbmLjxo306dOH1q1b73Dshx9+eOswb8ceeyzHHnssAMcccwyTJ0+mRYsWlCxZkttvv52qVasWwKshIiLFibnnWMkQnwOajQbSCGMY/wRc7+6Pm9lxwD2EkSuecPdh+XXM1NRUnzFjRn7tLs+SrZ6m2HOHX3/Nfdi7pUtzH/ZuZ2UdVaqorCMHuh5EtqdrQmSbRF0PZjbT3VOztidiFItsv6919wnkcMOdSL4wCwlslSpw4IE5r7d5c6h9zqms4/vv4YMPYNWqHbctU2bnSXTt2hr2TkREJIkVr++MRfKiZMlQm1yzZu7rrVsHy5fn3CM9axa88UYo/8iqUqWdJ9H77RdKTERERKRAKUEW2V1ly0LDhuGRm2yGvdvu5/feC/9u3LjjtrHD3uWUTO+7r4a9ExERyUdKkEXirVKl8MgyY9x2tmwJJRu5DXs3c2Yo/ch630BKyrZh73LrkdawdyIiInmiBFkkGZQoEXqC990XshnVYauNG7cf9i5rMv3VV/DOO7B69Y7bliu38yS6Zk3Ya6+4naaIiEhhoARZpDApVQrq1AmP3Pz557b66Ox6pD/5JPyczbTg7LPPzoe9q1Ej78PejRoF11zDET/8APXqwbBh0K/frp+7iIhIAVGCLFIUlS8PjRuHR07cQ09zbmUdc+eGYe82b95+2xIlQpK8sxE73nwTBg6EtWvDdJmLF4dlUJIsIiJJSwmySHFlFnqL99kHWrbMeb3Nm2HlypyT6MWL4aOPwtThebF2LVxzjRJkERFJWkqQRSR3JUuGIef22w/at895vfXrdxz27tJLs1/3hx/iEqqIiEh+0NhQIpI/ypSBBg3g0EPh1FPhkkugfv2c17/ppuzHiBYREUkwJcgiEj/DhoXRM2KVLQvt2sG110KTJvDoo7BpU2LiExERyYYSZBGJn379YORIqF8fNws9yo89BjNmwLRpocd54EBo1QrGjdtxjGcREZEEUIIsIvHVrx8sWsTUd96BRYu23ZzXuTN88AG8/HJIjE86CQ47LNzwJyIikkBKkEUkccygVy+YMwdGjIBvvw01zCefDF9/nejoRESkmFKCLCKJl5IC550HCxbAf/8LU6aEoecGDQojY4iIiBQgJcgikjwqVAg37337LZx/Pjz+eJjs5Lrr4I8/Eh2diIgUE0qQRST5VK8O998P8+fD8cfD0KHQqBE8+CBs3Jjo6EREpIhTgiwiyatxYxg7FqZPhxYtYPDg8O+LL2rECxERiRslyCKS/Dp2hHffhddfDxOSnH46dOoEU6cmOjIRESmClCCLSOFgFsotvvgCnngiTGWdlgYnnBBGwRAREcknSpBFpHApWRLOOSeMeDF8eJhwpHVr6N8fMjISHZ2IiBQBSpBFpHDaay8YMiSMeHHJJfDcc2Hq6quvhtWrEx2diIgUYkqQRaRwq1oV7rorTCxyyilwyy1hxIu774b16xMdnYiIFEKFMkE2s3pmNt7MnjCzIYmOR0SSQIMGoRf5s8+gfXu47DJo1gxGjYItWxIdnYiIFCIFniBHSe0KM5uTpb2HmX1tZgvzkPQeALzh7ucCLeIWrIgUPm3bwuTJ8OabULkynHEGpKbCW28lOjIRESkkEtGD/BTQI7bBzEoCDwLHEhLevmbWwsxamdnrWR7Vgc+BPmb2DvBuAccvIoXB0UfDzJnw7LPwyy/QvTsccwzMmpXoyEREJMkVeILs7u8Bv2Rp7ggsdPfv3H0DMAY40d2/dPcTsjxWAOcA17v7kcDxBXsGIlJolCgRepC/+gruvBM+/RTatYMzz4TFixMdnYiIJCnzBMxGZWYNgNfd/cBo+VSgh7sPiJbPBA5298E5bH8gcAPwM7DG3a/IZp2BwECAGjVqtB8zZkwcziR3a9asoUKFCgV+XJFklAzXQ8qaNdR7/nlqv/QS5s7Sk05i8RlnsKlSpYTGJcVTMlwTIskiUddD165dZ7p7atb2lAKPJHuWTVuOmbu7zwFOzW2H7j4SGAmQmprqaWlpexLfbklPTycRxxVJRklzPZxwAixZAtddR92nn6bulClhaLiLLgpDx4kUkKS5JkSSQLJdD8kyikUGUDdmuQ6wLEGxiEhRV7cuPPlkmJXv0EPhqqvggAPgqadg8+ZERyciIgmWLAnyp0ATM2toZqWBPsD4BMckIkVdq1bwxhvw7rtQs2aYoa9tW5gwARJQfiYiIskhEcO8jQY+ApqaWYaZ9Xf3TcBg4E1gPjDW3ecWdGwiUkylpcH06fDCC7B2LRx/PBx5ZLipT0REip1EjGLR191runspd6/j7o9H7RPc/QB3b+Tuwwo6LhEp5szg9NNh3jy47z6YMwc6doQ+fcJ01iIiUmwkS4mFiEhyKF063LD37bfwn//Aa69B8+Zw8cWwcmWioxMRkQKgBFlEJDuVKsHQobBwYahNfughaNQIbroJ/vwz0dGJiEgcKUEWEclNzZrwyCOh5KJbN7j2WmjSBEaOhE2bEh2diIjEgRJkEZG8aNYMXnkFpk2Dhg3hvPPCKBivvqoRL0REihglyCIiu6Jz55Akv/JKSIx79YLDDoMPP0x0ZCIikk+UIIuI7CozOOmkUHYxYkS4oa9zZzj5ZPj660RHJyIie0gJsojI7kpJCaUWCxfCf/8LU6ZAy5YwaBAsX57o6EREZDcpQRYR2VPly4eb9779Fs4/Hx5/HBo3huuugz/+SHR0IiKyi5Qgi4jkl+rV4f77Yf78MBvf0KFhaLgHH4SNGxMdnYiI5JESZBGR/Na4MYwdG6avbtECBg8O/774oka8EBEpBJQgi4jES8eO8O678PrrUKZMmMq6UyeYOjXRkYmISC6UIIuIxJNZKLf44gt44glYuhTS0uCEE8IoGCIiknSUIIuIFISSJcOU1QsWwPDhYSzl1q2hf3/IyEh0dCIiEkMJsohIQdprLxgyJIx4cckl8NxzYerqq6+G1asTHZ2IiKAEWUQkMapWhbvuChOLnHIK3HJLGPHi7rth/fpERyciUqwpQRYRSaQGDUIv8mefQfv2cNll0KwZjBoFW7YkOjoRkWJJCbKISDJo2xYmT4Y334TKleGMMyA1Fd56K9GRiYgUO0qQRUSSydFHw8yZ8Oyz8Msv0L07HHMMzJqV6MhERIoNJcgiIsmmRInQg/zVV3DnnfDpp9CuHZx5JixenOjoRESKPCXIIiLJqmzZUJP83Xfwf/8H//sfHHAAXH45rFqV6OhERIqsXBNkM6tjZleY2Tgz+9TM3jOzh8zseDNTci0iUhAqVw6jXHzzDfTrF0a6aNQIbr0V/vor0dGJiBQ5OSa5ZvYk8ASwAbgV6AtcALwF9ACmmdnhBRGkiIgAdeuG2fhmz4YuXcJ4ygccAE8+CZs3Jzo6EZEiI7de4Dvd/Wh3v8/dP3T3he4+x91fdveLgDRgWcGEKSIiWx14ILz+Orz7LtSsCeeeC23awIQJ4J7o6ERECr0cE2R3n5P5s5ntZWZNszy/wd0XxjO46Nj7m9njZva/mLbmZjbCzP5nZufHOwYRkaSUlgbTp8MLL4RSi+OPhyOPDDf1iYjIbttpHbGZ9QRmAZOi5TZmNj4vOzezJ8xshZnNydLew8y+NrOFZjYkt324+3fu3j9L23x3HwScDqTmJRYRkSLJDE4/HebNg/vvh7lzoWNH6N07TGctIiK7LC832l0PdARWA7j7LKBBHvf/FKFeeSszKwk8CBwLtAD6mlkLM2tlZq9neVTPacdR4j4NeDuPsYiIFF2lS8PgwbBwIVx7bSjBaNYMLroIVqxIdHQiIoWK+U7q1cxsursfbGafu3vbqG22ux+UpwOYNQBed/cDo+VDgBvc/Zho+WoAdx++k/38z91Pzab9DXc/Ppv2gcBAgBo1arQfM2ZMXsLNV2vWrKFChQoFflyRZKTroWCVXrWKBk89Rc0JE9hctixL+vRhyamnsmWvvRIdmkR0TYhsk6jroWvXrjPdfYdqhJQ8bDvHzP4OlDSzJsDFwId7EEttYEnMcgZwcE4rm1lVYBjQ1syudvfhZpYGnAyUASZkt527jwRGAqSmpnpaWtoehLx70tPTScRxRZKRrocEOOUU+OorUq6+moZPPEHDiRPhhhvCTX0pefnvX+JJ14TINsl2PeSlxOIioCWwHhgN/A5cugfHtGzacuzGdvdV7j7I3Rtl9jK7e7q7X+zu57n7g3sQi4hI0dasGbzyCkybBg0bwnnnQatW8OqrGvFCRCQHO02Q3X2tu1/j7h3cPTX6ed0eHDMDqBuzXAcNFyciEl+dO4ck+ZVXQmLcqxccdhh8uCdfCIqIFE25TRTympmNz+mxB8f8FGhiZg3NrDTQB9iT/YmISF6YwUknwZw5MGJEGOWic2c4+WT4+utERycikjRyK0K7Y093bmajCROKVDOzDOB6d3/czAYDbwIlgSfcfe6eHktERPIoJSWUWpxxBtx1F9x2G4wfDwMGwPXXh8lHRESKsRwTZHefuqc7d/e+ObRPIIeb60REpICULx+GhDvvPBg6NPQqP/ssXH45XHklVKyY6AhFRBIiLxOFNIlmrJtnZt9lPgoiOBERKQDVq4dJRubPD7PxDR0KjRrBgw/Cxo2Jjk5EpMDlZRSLJ4GHgU1AV+AZ4Nl4BiUiIgnQuDGMHRumr27RIkw80qIFvPiiRrwQkWIlLwnyXu7+NmFSkcXufgNwZHzDEhGRhOnYEd59N8zGV6ZMmMq6UyeYuseVdyIihUJeEuR1ZlYCWGBmg82sF5DjFNAiIlIEmIVyiy++gCeegKVLIS0NTjghjIIhIlKE5SVBvhQoR5hBrz1wBnBWHGMSEZFkUbIknHMOLFgAw4eHsZRbt4b+/SEjI9HRiYjERV4mCvnU3de4e4a7n+Pup7j7xwURnIiIJIm99oIhQ8LYyZdeCs89B02awNVXw+rViY5ORCRf5WUUiylmVjlmeR8zezOuUYmISHKqWhXuvDNMLHLKKXDLLWHEi7vvhvXrEx2diEi+yEuJRTV3X5254O6/ohpkEZHirUGD0Iv82WfQvj1cdhk0awajRsGWLYmOTkRkj+QlQd5iZvUyF8ysPqDxfkREBNq2hcmTw6Ny5TA7X2oqTJmS6MhERHZbXhLka4BpZvasmT0LvAdcHd+wRESkUOneHWbODL3Kv/wCRx8dHp9/nujIRER2WV5u0psEtANeAMYC7d1dNcgiIrK9EiWgX79Qn3znnSFhbtcOzjwTFi1KdHQiInmWl5v0OgN/ufvrwN7Av6MyCxERkR2VKRNqkr/9Fq66Cv73P2jaFC6/HFatSnR0IiI7lZcSi4eBtWbWGrgSWEyYblpERCRnlSuHUS6++Sb0LN99dxjx4tZb4a+/Eh2diEiO8pIgb3J3B04E7nP3e4GK8Q1LRESKjLp1w2x8s2dDly5hPOUDDoAnn4TNmxMdnYjIDvKSIP9hZlcTZtB7w8xKAqXiG5aIiBQ5Bx4Ir78O774LNWvCuedCmzYwYQK4BkcSkeSRlwS5N7Ae6O/uPwK1gdvjGpWIiBRdaWkwfTq88EIotTj+eDjySPj000RHJiIC5G0Uix/d/S53fz9a/sHdVYMsIiK7zwxOPx3mzYP774e5c6FjR+jdO9zcJyKSQHnpQRYREYmP0qVh8GBYuBCuvTaUYDRrBhddBCtWJDo6ESmmlCCLiEjiVaoE//1vSJTPPRcefhgaN4abboI//0x0dCJSzChBFhGR5FGzJjzyCMyZA926hV7lJk1g5EjYtCnR0YlIMZGXiUK+NLPZWR7vm9ndZla1IIIUEZFiplkzeOUVmDYNGjaE886DVq3g1Vc14oWIxF1eepAnAm8A/aLHa8B7wI/AU3GLTEREpHPnkCS/8kpIjHv1gsMOgw8/THRkIlKE5SVB7uzuV7v7l9HjGiDN3W8FGsQ3PDCz/c3scTP7X0xbPTMbb2ZPmNmQeMcgIiIJZAYnnRTKLkaMCKNcdO4MJ58MX3+d6OhEpAjKS4JcwcwOzlwws45AhWgx14KwKIFdYWZzsrT3MLOvzWzhzhJcd//O3ftnaT4AeMPdzwVa5OEcRESksEtJCaUWCxeGG/qmTIGWLWHQIFi+PNHRiUgRkpcEeQDwmJl9b2aLgMeAAWZWHhi+k22fAnrENkQz8T0IHEtIbvuaWQsza2Vmr2d5VM9hv58DfczsHeDdPJyDiIgUFeXLh5v3vv0Wzj8fHn88jHhx3XXwxx+Jjk5EioC8TBTyqbu3AtoAbdz9oKjtT3cfu5Nt3wN+ydLcEVgY9QxvAMYAJ0blGydkeeQ0COY5wPXufiRw/M7OQUREiqDq1cMkI/PnwwknwNCh0KgRPPAAbNiQ6OhEpBAz38ndwGa2N3A9cHjUNBX4r7v/lqcDmDUAXnf3A6PlU4Ee7j4gWj4TONjdB+ewfVVgGNAdeMzdh5vZgcANwM/AGne/IpvtBgIDAWrUqNF+zJgxeQk3X61Zs4YKFSrsfEWRYkDXg8Rbxa++Yv9HHmGfWbP4q1YtvhswgJVpaaGGOQnpmhDZJlHXQ9euXWe6e2rW9rwkyC8Bc4Cno6YzgdbufnJeDpxNgnwacEyWBLmju1+Ux3PZZampqT5jxox47T5H6enppKWlFfhxRZKRrgcpEO4wcSJcdVW4qa9DB7jtNkjCz56uCZFtEnU9mFm2CXJeapAbufv1UUnEd+5+I7D/HsSSAdSNWa4DLNuD/YmIiARmcNxxMGsWPPFEuHmva9dQgjFnzk43FxGBvCXIf5lZl8wFM+sM/LUHx/wUaGJmDc2sNNAHGL8H+xMREdleyZJwzjnwzTdwyy1hLOXWrcM01hkZiY5ORJJcXhLk84EHzWyRmS0GHgAG5WXnZjYa+AhoamYZZtbf3TcBg4E3gfnAWHefu3vhi4iI5GKvvUK5xbffwqWXwqhRYerqIUNg9epERyciSSovo1jMcvfWwEFAK3dv6+5f5GXn7t7X3Wu6eyl3r+Puj0ftE9z9AHdv5O7D9uwUREREdqJqVbjzzjCxyCmnwK23hhEv7r4b1q9PdHQikmRyTJDN7LLYB2E85AExyyIiIoVLgwbw3HPw2WfQvj1cdhk0axZ6lrdsyXaTJUuW0LVrV5o3b07Lli259957s10vPT2dNm3a0LJlS4444ojtntu8eTNt27blhBNO2KVw165dy/HHH0+zZs1o2bIlQ4Zsm1vrrrvuokWLFhx00EF069aNxYsX79K+RSRnufUgV9zJQ0REpHBq2xYmTw6PypXhjDMgNTXMzpdFSkoKd955J/Pnz+fjjz/mwQcfZN68eduts3r1ai644ALGjx/P3LlzefHFF7d7/t5776V58+a7FeoVV1zBV199xeeff84HH3zAxIkTo1Noy4wZM5g9ezannnoq//d//7db+xeRHeWYILv7jbk9CjJIERGRuOjeHWbODL3Kv/wCRx8dHp9/vnWVmjVr0q5dOwAqVqxI8+bNWbp06Xa7ef755zn55JOpV68eANWrb5sINiMjgzfeeIMBAwZst83SpUvp0aMH7du357DDDuOrr77aIbxy5crRtWtXAEqXLk27du3IiG4y7Nq1K+XKlQOgU6dOW9tFZM/lVmLxHzPbJ5fnjzSzXfuuSEREJNmUKAH9+oX65DvvDAlzu3Zw5pmwaNF2qy5atIjPP/+cgw8+eLv2b775hl9//ZW0tDTat2/PM888s/W5Sy+9lNtuu40SJbb/lXvnnXdy//33M3PmTO644w4uuOCCXMNcvXo1r732Gt26ddvhuccff5xjjz12F09cRHKSkstzXwKvm9k64DNgJVAWaEKYdvot4OZ4BygiIlIgypQJNcnnnhuGhrv3Xhg7FgYPhn//mzVlynDKKadwzz33UKlSpe023bRpEzNnzuTtt9/mr7/+4pBDDqFTp0588803VK9enfbt25Oenr51/TVr1jB37lxOO+20rW3rc7lZcNOmTfTt25eLL76Y/ffffiqC5557jhkzZjB16tT8eR1EJOcE2d3HAePMrAnQGagJ/A48Bwx09z0ZC1lERCQ5Va4cEuQLL4Trr4e772bjY49xSo0a9Ovfn5NP3nEi2Tp16lCtWjXKly9P+fLlOfzww/niiy/47LPPGD9+PBMmTGDdunX8/vvvnHHGGTz00ENUqFCBWbNmbbefzZs30759ewB69uzJf//7XwAGDhxIkyZNuPTSS7db/6233mLYsGFMnTqVMmXKxOPVECmW8jLM2wJ3f8rdh7v7Pe7+ppJjEREp8urWhSeewL/4gv4VK9J8wQIue+ABePJJ2Lx5u1VPPPFE3n//fTZt2sTatWuZPn06zZs3Z/jw4WRkZLBo0SLGjBnDkUceyXPPPUelSpWoWbPm1pv53J0vvviCkiVLMmvWLGbNmrU1Of7Pf/7Db7/9xj333LPdMT///HPOO+88xo8fv13Ns4jsubxMFCIiIlJsffDbbzy7dCnv7L8/bVatos255zKhUSNGDB7MiIcfBqB58+b06NGDgw46iI4dOzJgwAAOPPDAXPd7zTXX8Pjjj9O6dWtatmzJuHHjdlgnIyODYcOGMW/ePNq1a0ebNm147LHHALjyyitZs2YNp512Gm3atKFnz575f/IixVRuNcgiIiLFXpcuXXD3sOAOL74I//43PPggpKWF4eE6dODKK6/kyiuvzHE/aWlppKWlbV2uWbMmkyZNyvXYderU2XbsLN56661dPRURySP1IIuIiOSVGZx+OsybB/ffD3PnQseO0Lt3mM5aRIqEnSbIZnaAmb1tZnOi5YPM7D/xD01ERCRJlS4dRrdYuBCuvRZefz3MyHfRRbBiRaKjE5E9lJce5EeBq4GNAO4+G+gTz6BEREQKhUqV4L//DYly//7w8MPQuDEMHQp//pno6ERkN+UlQS7n7p9kadsUj2BEREQKpZo1YcQImDMHjjoKrrsuJMqPPAKb9CtTpLDJS4L8s5k1AhzAzE4Flsc1KhERkcKoWTN4+WWYNg323x8GDYJWreDVV8MNfiJSKOQlQb4QeARoZmZLgUuB8+MZlIiISKHWuXNIkl95JSTGvXpBly7w4YcwahQ0aMARRx4JDRqEZRFJKjsd5s3dvwOOMrPyQAl3/yP+YYmIiBRyZnDSSXDCCfDEE2FWvs6doWRJ2LwZA1i8GAYODOv365fAYEUk1k4TZDO7LssyAO7+3zjFJCIiUnSkpIQkuF8/qF0bfvtt++fXroVrrlGCLJJE8jJRSOxtuGWBE4D58QlHRESkiCpfHn7/PfvnfvghlGJEnVAiklg7rUF29ztjHsOANKB23CMTEREpaurVy77dHTp0gBde0KgXIklgd2bSKwfsn9+BiIiIFHnDhkG5ctu3lSsXxlD+4w/o0wcOOAAeeEDjKIskUF5m0vvSzGZHj7nA18C98Q9NRESkiOnXD0aOhPr1cTOoXz8sP/YYzJ8fRr3Yb78wI1+9euHGvpUrEx21SLGTlx7kE4C/RY+jgVru/kBcoxIRESmq+vWDRYuY+s47sGjRtpvzSpQIo158+GEYIu6ww8IsffXqwQUXhNn6RKRA5Jggm1kVM6sC/BHz+AuoFLWLiIhIPHTuHCYXmT8fzjgDHn88lF6cdhp8knVyWxHJb7n1IM8EZkT/Zn3MiH9ogZmdZGaPmtk4Mzs6amtuZiPM7H9mpklLRESkaGrWDB59NPQ0DxkCU6bAwQfDEUfAG2/Ali2JjlCkSMoxQXb3hu6+f/Rv1keebtIzsyfMbIWZzcnS3sPMvjazhWY2JLd9uPur7v5P4Gygd9Q2390HAacDqXmJRUREpNCqWRNuvhmWLIG77oLvvw8TkLRqBU89BRs2JDpCkSIlT6NYmNk+ZtbRzA7PfORx/08BPbLsqyTwIHAs0ALoa2YtzKyVmb2e5VE9ZtP/RNtl7qcnMA14O4+xiIiIFG4VK8K//gXffgvPPhsmITnnHGjYEG6/fcdJSERkt5i7576C2QDgEqAOMAvoBHzk7kfm6QBmDYDX3f3AaPkQ4AZ3PyZavhrA3YfnsL0BtwBT3P2tbJ5/w92Pz6Z9IDAQoEaNGu3HjBmTl3Dz1Zo1a6hQoUKBH1ckGel6ENlevlwT7uzz6afUe+EF9vnsMzaVK8eyv/2NjFNOYcO+++ZPoCIFIFG/I7p27TrT3XeoRshLgvwl0AH42N3bmFkz4EZ3752XA2eTIJ8K9HD3AdHymcDB7j44h+0vBs4CPgVmufsIM0sDTgbKALPd/cHsts2UmprqM2YUWNn0Vunp6aSlpRX4cUWSka4Hke3l+zXx2WehF3nsWChZEv7+d7jiCjjwwPw7hkicJOp3hJllmyDnpcRinbuvi3ZSxt2/ApruSSzZtOWYpbv7fe7e3t0HufuIqC3d3S929/N2lhyLiIgUC+3awejRYTi4QYPgxRdDjfLxx8PUqWG2PhHJk7wkyBlmVhl4FZhiZuOAZXtwzAygbsxynT3cn4iIiGRq2BDuuw9++CGMo/zpp5CWFka/+N//YPPmREcokvR2miC7ey93X+3uNwDXAo8DJ+3BMT8FmphZQzMrDfQBxu/B/kRERCSrqlXh2mth8WJ4+GH49dcwjnLTpmH5r78SHaFI0srLVNP3mtmhAO4+1d3Hu3uexpMxs9HAR0BTM8sws/7uvgkYDLwJzAfGuvvc3T8FERERydFee4WSi6++Cj3IVauGmfnq1Qs9zD//nOgIRZJOXkosPgP+E41ZfLuZ5XncYXfv6+413b2Uu9dx98ej9gnufoC7N3L3YbsbvIiIiORRyZJwyinw8cehJrlTJ7j++pAoDx4M332X6AhFkkZeSiyedvfjgI7AN8CtZrYg7pGJiIhI/jODww+H116DuXOhTx8YORKaNIHevSEBoz6JJJs8TRQSaQw0AxoAX8UlGhERESk4LVrAE0+EmfmuuAImTYIOHeDII8PPGvlCiqm81CBn9hj/F5gLtHf3v8U9MhERESkYtWvDrbeGqaxvvx2++QaOPRZatw4z9m3cmOgIRQpUXnqQvwcOcfce7v6Eu6+Oc0wiIiKSCJUqhZ7k776Dp56CLVvgH/+A/feHO++E339PdIQiBSIvNcgj3P1nADN7Pf4hiYiISEKVLg1nnQVffglvvAGNG4fEuV49GDIEli9PdIQicbUrNcgAteMShYiIiCQfMzjuOHj3XfjkEzj66FCC0aAB9O8P8+cnOkKRuNjVBPnzuEQhIiIiya1DBxg7NtQnDxgQprVu0QJ69oRp03RDnxQpOSbIZlbWzC41swfM7DwzS3H3cwsyOBEREUkyjRrBgw+GGfquvx4+/BAOOwwOPRRefllTWUuRkFsP8tNAKvAlcCxwZ4FEJCIiIslv333hhhvghx/ggQdgxYowEUnz5vDII5rKWgq13BLkFu5+hrs/ApwKHFZAMYmIiEhhUa4cXHghfP01vPAC7L13mNq6QQO46Sb45ZdERyiyy3JLkLcOeujumwogFhERESmsUlLg9NPDzXzvvgvt28O114aRLy65BBYtSnSEInmWW4Lc2sx+jx5/AAdl/mxmGghRREREdmQGaWkwYQLMnh3KLh56KAwV9/e/w+e631+SX44JsruXdPdK0aOiu6fE/FypIIMUERGRQqhVK3j66TDxyKWXwuuvQ7t20L07TJ6skS8kae3qMG8iIiIiu6ZuXbjjjnBD3y23wNy5cMwx0LYtjBqlqawl6ShBFhERkYJRuTJcdRV8/z088QRs2ABnnBHKL+65B9asSXSEIoASZBERESloZcrAOefAnDnw2mtQvz7861/hhr5rroEff0x0hFLMKUEWERGRxChRAk44Ad57Dz76CLp2heHDwxBxAweGoeNEEkAJsoiIiCRep07w0kshKT77bHjmmTDpSK9eYbY+kQKkBFlERESSR5MmMGJEmMr6mmtg6lTo3Bm6dIFx42DLlkRHKMWAEmQRERFJPjVqwNChsGQJ3HcfZGTASSdBixbw2GOwbl2iI5QiTAmyiIiIJK/y5eGii2DhQhg9Okxt/c9/QsOGoV75118THaEUQUqQRUREJPmlpECfPjBzJrz1Fhx0EPz732Hki8suC2Msi+STpE+QzewkM3vUzMaZ2dFRWz0zG29mT5jZkETHKCIiIgXEDLp1gzffhFmz4MQTQwlGo0Zw5plhemuRPRTXBDlKYFeY2Zws7T3M7GszW7izBNfdX3X3fwJnA72j5gOAN9z9XKBFPGIXERGRJNe6NTz3XJjK+qKL4JVXQluPHvD225rKWnZbvHuQnwJ6xDaYWUngQeBYQnLb18xamFkrM3s9y6N6zKb/ibYD+BzoY2bvAO/G+RxEREQkmdWrB3fdFW7ou/nm0LN81FGQmgpjxsCmTYmOUAqZuCbI7v4e8EuW5o7AQnf/zt03AGOAE939S3c/IctjhQW3AhPd/bNoH+cA17v7kcDx8TwHERERKST22QeuvhoWLYJHHw1TV/ftG4aOu/9++PPPREcohYR5nL9+MLMGwOvufmC0fCrQw90HRMtnAge7++Actr8YOAv4FJjl7iPM7EDgBuBnYI27X5HNdgOBgQA1atRoP2bMmPw+tZ1as2YNFSpUKPDjiiQjXQ8i29M1UQC2bKHqhx9Sb8wY9p47l42VKrH0xBNZ2qsXG/fZJ9HRSYxEXQ9du3ad6e6pWdsTkSCfBhyTJUHu6O4XxSuG1NRUnzFjRrx2n6P09HTS0tIK/LgiyUjXg8j2dE0UsA8/hNtvD5ONlCkTZuu7/HJo3DjRkQmJux7MLNsEORGjWGQAdWOW6wDLEhCHiIiIFBeHHhpu4ps/P4x28cQTcMABcOqpMH16oqOTJJOIBPlToImZNTSz0kAfYHwC4hAREZHipmlTGDkyTGV99dVhtItOneCII+D11zWVtQDxH+ZtNPAR0NTMMsysv7tvAgYDbwLzgbHuPjeecYiIiIhsZ7/9YNiwMMHI3XfD99/D3/4GBx4ITz4J69cnOkJJoHiPYtHX3Wu6eyl3r+Puj0ftE9z9AHdv5O7D4hmDiIiISI4qVoRLL4Vvvw1jKpcqBeeeG6ayvu02+O23REcoCZD0M+mJiIiIxF2pUtCvXxhD+c03oWVLuOoqqFsXrrwSMjISHaEUICXIIiIiIpnM4OijYcoUmDkTTjghlGA0bBhGvpgzZ6e7kMJPCbKIiIhIdtq1g+efh4UL4YIL4MUX/7+9e4+Oqjr7OP59RKgEUCgYXn25BKxcEoQoCCIIgYpGRVBUKKClRUREoS/WpVasoOBSxEttFamIF5SKIFarIKBALLaCgoablKBtVBbYgoWWyEUCz/vHPgkTSCAJSSbg77NWVmb2nHP2M7POnvPMPvucDWedBZdeChkZmsr6OKYEWURERORwkpLg8cfDBX3jxsHy5dCtG7RvH5LmffviHaGUMSXIIiIiIsVRty7cfXe4RdzkyeECvr59w/2UJ02CnTvjHaGUESXIIiIiIiVRvTrceGOYdGT2bDj1VLj5ZmjcGO69F7ZujXeEcpSUIIuIiIiURpUq0KcPfPAB/PnP0LEjjB0LjRqFhPnzz+MdoZSSEmQRERGRo2EGF1wAf/oTrF0L/fvDlClh6EXfvvDRR/GOUEpICbKIiIhIWUlOhqlTITs73D95wYJwMV+3bvD227rzxTFCCbKIiIhIWTv9dHjwwXDni4cfDreKu/RSaN0apk2D776Ld4RyGEqQRURERMrLySfDL38ZxiO/8EIoGzQImjaFRx6B//43vvFJoZQgi4iIiJS3atXgpz+FVatg7twwPvm228JU1nfcAZs2xTtCiaEEWURERKSimMEll8CiReHivfT0MAQjKQkGD4ZPP413hIISZBEREZH4aNcOXnkFNmyAoUNhxgxISYHLL4clS3RBXxwpQRYRERGJp6ZN4YknwgV9Y8fC0qXQpUu4r/Jrr2kq6zhQgiwiIiJSGdSrB2PGhKmsn3wStmyBq66CFi3C1Na7dsU7wu8NJcgiIiIilUlCAgwfDllZMHMm1KkDN90UprIeNw6++SbeER73lCCLiIiIVEZVqsA118CyZbB4MZx7LtxzT5jKeuTIMBmJlAslyCIiIiKVmRmkpcGcObB6dUiaJ0+GH/0oTGv98cfxjvC4owRZRERE5FjRqhU8/zz8/e8walRImtu2hQsvhPnzdeeLMqIEWURERORY06ABTJwIX30FEybAunXhnspnnw0vvQR798Y7wmOaEmQRERGRY9Upp8Dtt4ce5WefDYnxddfBGWfAY4/Bjh3xjvCYpARZRERE5Fj3gx/Az38exii/9RY0aQK33hou6LvrLvj663hHeEyp9AmymbU0s8lm9qqZ3VRUmYiIiMj33gknwGWXwXvvhQlHfvxjePDBcIu4G26A9evjHeExoVwTZDN71sz+ZWZrDipPN7P1ZvaZmd15uG24+zp3Hwb0BdoVVSYiIiIiMTp0gFdfDUnx4MFhbHLLlnDFFfCXv8Q7ukqtvHuQnwfSYwvMrArwJHAJkAz0N7NkMzvLzN466C8xWqcX8D6wMGY7h5SJiIiIyEHOPBOeeirM0Hf33bBkCXTuDJ06weuvw/79xd7U7t27ad++PW3atCElJYUxY8YUulxGRgapqamkpKTQtWvX/PLBgweTmJhIq1atSvVW0tPT8+seNmwY+2Km4Z45cybJycmkpKQwYMCAUm0/j3k53w7EzJKAt9y9VfS8IzDW3S+Onv8KwN0fKMa25rj7ZUcqi8qHAkMB6tev33bGjBlH+1ZKLCcnh5o1a1Z4vSKVkdqDSEFqExIvJ+zaxWlvv02DWbOo/vXX7GzYkK/69uWfF13E/mrVDruuu7N7926qV69Obm4uI0aMYMSIESQnJ+cvk5OTwy233MKECROoX78+27Zto06dOgCsXLmS6tWr88ADD/Dcc88VWKc47eHbb7+lRo0auDtjxowhLS2N7t27s3HjRu69914effRRatWqVaDOw+nWrdsKdz9kNEI8EuSrgXR3HxI9vw7o4O63FLF+GtAH+AGwyt2fLKzscDG0a9fOly9fXhZvp0QyMjJIS0ur8HpFKiO1B5GC1CYk7nJzYfZseOihMNlI/fphhr6bbgrTWx/Bzp076dy5M0899RQdOnTIL580aRKbNm1i/Pjxha6XnZ1Nz549WbPmwAjc6dOn8+KLL7JlyxYSEhKYMmUKLVq0KLLuvXv30qdPH6699lr69evH7bffTrNmzRgyZEgJPgAws0IT5HhcpGeFlBWZpbt7hruPdPcb8xLhwspEREREpAROPBH69YPly2HhQkhNhdGjoWHDMAnJl18Wutq+fftITU0lMTGRHj16FEiOAbKysti2bRtpaWm0bduWadOmHTGURx55hN/97nesWLGChx9+mOHDhxe57MUXX0xiYiK1atXi6quvzq8zKyuLTp06cd555zFv3rzifw6FiEeCvBFoGPO8AbApDnGIiIiIiBl07w7z5kFmJlx5JTzxBDRtCtdeCytXFli8SpUqZGZmsnHjRj788MMCPcEAubm5rFixgjlz5jB//nzGjRtHVlZWkdXn5OSwdu1arrnmGlJTU7nxxhvZvHlzkcvPnz+fzZs3s2fPHhYtWpRf54YNG8jIyODll19myJAhbN++vdQfSTwS5I+AM82siZlVA34C/CkOcYiIiIhIrDZt4MUX4fPPw3CLN94IPcsXXwzvvltgKuvatWuTlpZ2SG9tgwYNSE9Pp0aNGtSrV48uXbqw8qAkO9b+/fupWbMmmZmZ+X/r1q3L76lOTU3lnnvuKbDOSSedRK9evXjjjTfy6+zduzdVq1alSZMmNG/enA0bNpT6Yyjv27y9DHwANDezjWZ2vbvnArcA84F1wEx3X1uecYiIiIhICTRqBI8+GoZZPPAArFoFPXqwpXVrtj/zDOTmsmvXLt59991Dxgr37t2bJUuWkJuby86dO1m2bBktW7YssqqTTz6Z0047jVmzZgHhQsCVK1fm91RnZmZy3333kZOTk9+znJuby9y5c/PrvuKKK1i8eDEAW7duJSsri6ZNm5b67Zdrguzu/d39NHev6u4N3H1qVD7X3Zu5+xnufn95xiAiIiIipVSnDtx5J2RnwzPPsHnHDrrdcAOtExI4t2lTenTtSs+ePZk8eTKTJ08GoGXLlqSnp9O6dWvat2/PkCFD8m/r1r9/fzp27Mj69etp0KABU6dOBWD06NFMnTo1/xZueT3Dsb799lt69epF69atadOmDYmJiQwbNgwI45Lr1q1LcnIy3bp1Y+LEidStW7fUb7vc72JRGeguFiLxp/YgUpDahByT9u8PU1k/9FCYbKROHbj5ZhgxAhITS73ZeLWHynQXCxERERE5Fp1wAvTqBe+/HxLkrl3h/vvDkIxhw+Aoxv1WJkqQRURERKTkzj8f/vhHWLcOBg2C55+H5s3hqqtg6dJ4R3dUlCCLiIiISOk1bw6//32Yyvquu2DRIujYEbp0gTffLNFU1pWFEmQREREROXr168P48fDVV/Cb34SEuVcvaNUKnn0W9uyJd4TFpgRZRERERMpOzZrwi1/AZ5/B9OlQrRpcfz00aQITJsBRTOBRUZQgi4iIiEjZq1oVBgyATz6BBQsgJSXcMq5RI7jtNti4MSTQSUl07d4dkpLC80pACbKIiIiIlB8z6NED3nkHPv4YLr88DMFo1Chc3PfFF5h7GJIxdGilSJKVIIuIiIhIxTj77JAAf/ZZGIqxb1/B13fuhNGj4xNbDCXIIiIiIlKxkpIgJ6fw1778skJDKYwSZBERERGpeI0alay8AilBFhEREZGKd//9kJBQsCwhIZTHmRJkEREREal4AwfC009D48a4GTRuHJ4PHBjvyJQgi4iIiEicDBwI2dm8t2gRZGdXiuQYlCCLiIiIiBSgBFlEREREJIYSZBERERGRGEqQRURERERiKEEWEREREYmhBFlEREREJIa5e7xjKHdmtgX4Ig5V1wO2xqFekcpI7UGkILUJkQPi1R4au/upBxd+LxLkeDGz5e7eLt5xiFQGag8iBalNiBxQ2dqDhliIiIiIiMRQgiwiIiIiEkMJcvl6Ot4BiFQiag8iBalNiBxQqdqDxiCLiIiIiMRQD7KIiIiISAwlyCIiIiIiMZQgF8LMGpjZG2a2wcw+N7PHzaxaIcudbmavFmN7c82sdiljGWtmt5VmXZGimNloM1trZqvMLNPMOsQ7JgAzyzCz9Wa20sw+MrPUUm4nzczOL+Pw5DhmZjkVXN9fo/9JZjYgpvxnZvbEUWy3nZn9tixiFCmuim4/FUEJ8kHMzIDXgNfd/UygGVATuP+g5U50903ufvWRtunul7r79vKIV6SkzKwj0BM4x91bAxcCX5VznVVKsPhAd28DTAImlrLKNEAJslQ6eW3B3fP2zyRgQJErlJC7L3f3kWW1PZHKoITHkDKhBPlQ3YHd7v4cgLvvA0YBg81suJnNMrM3gQXRL/81AGaWYGYzox65V8xsmZm1i17LNrN60fLrzGxK1Hu3wMyqR8vcEPWYrTSz2WaWEJ+3L98DpwFb3X0PgLtvdfdNAGaWbmZ/M7P3zey3ZvZWVF7gTIaZrTGzpOjx62a2Itqnh8Ysk2Nm95nZMqCjmV1rZh9GPda/L8YX3gfA/0bb+mFUzyozW2pmrYsqj+IaBoyK6rqgbD42+b4xs9Rov1plZn80szpR+blR2QdmNjHmOJBkZkvM7OPo7/yoPM3MFpvZH4DVUVlej9uDwAXRvjoqKjvdzOZFZzEfioknx8wmRO3tXTNrH511+buZ9YqpK6/d1jSz58xsdRTvVRXxucn3V7T/ZZjZq9GxZLoFl5jZzIOWezN6fFHUlj6OcqyaUXm2md1jZu8D15jZSDP7NNqXZ0TL1DCzZ6P86RMz611W70UJ8qFSgBWxBe7+X+BL4ESgIzDI3bsftN5wYFvUIzcOaFvE9s8EnnT3FGA7kPeF9Zq7nxv1nK0Dri+D9yJSmAVAQzPLMrNJZtYVwMxOAqYAlwMXAP9TzO0Ndve2QDtgpJnVjcprAGvcvQPwDdAP6OTuqcA+YOARtpsOvB49vhf4JGpfdwHTiip392xgMvCYu6e6+5Jivg+Rg00D7oj2r9XAmKj8OWCYu3ck7Mt5/gX0cPdzCPt77FCH9sBod08+qI47gSXRvvpYVJYarX8W0M/MGkblNYCMqL3tAMYDPYArgfsKif/XwH/c/azoPSwq0bsXKZ2zgf8DkoGmQCfgHeA8M6sRLdMPeMXM6gF3AxdG7WY5cGvMtna7e2d3n0FoK2dH+/Kw6PXRwCJ3PxfoBkyMqeOonFgWGznOGFDYve/yyt9x938X8npn4HEAd19jZquK2P4/3D0zeryCcHoNoJWZjQdqE4Z0zC9N8CJH4u45ZtaWkAR3I3xJ3QlkEvbPDQBm9hIwtMgNHTDSzK6MHjck/Aj8hpA4zI7Kf0z40fiRmQFUJyQThZkefcFVAc6JyjoT/Zh090VmVtfMTjlMuchRifaj2u7+XlT0AjDLwvUktdz9r1H5HwhDlgCqAk9YGDu/jzBEL8+H7v6PYla/0N3/E8XxKdCYMAzqO2BetMxqYI+77zWz1Rw4lsS6EPhJ3hN331bM+kWOxofuvhHAzDKBJHd/38zmAZdbuHbrMuB2oCshkf5LdGyoRjh7mOeVmMerCMeH1znQeXIR0MsOnOE8CWhE6Gg8KkqQD7WWA726AJjZyYQD/z7g2yLWs2Juf0/M432ERAHgeeAKd19pZj8jjKEUKRfR0KEMICM6uA4iJMhF3Rg9l4JnnE6CcJqMcBDu6O47zSwj7zXCL/+83jUDXnD3XxUjvIHASsKp5yeBPhTevvww5SLl5XDf9aOAfwJtCO1ld8xrRR07CnPwcSLvWL3XD0xesD9vOXffb2aFHc+L6vARKU9F7b+vADcD/wY+cvcdFrLid9y9fxHbim03lwFdgF7Ar80shbCPX+Xu68vyDYCGWBRmIZBgZj+F/IHhjxAS2J2HWe99oG+0TjLh1FhJ1AI2m1lVjnzqWaTUzKy5mZ0ZU5QKfAH8DWhiZmdE5bFfWNlEvblmdg7QJCo/hTC0aKeZtQDOK6LahcDVZpYYbeOHZta4qBjdfS/htNt5ZtYS+DNRu4iS8q3R0KeiyncQ2pRIqUQ9uNtixrBfB7wX9cLuMLO8ff0nMaudAmx29/3R8sW5sKg899UFwC15T/LGUIvESQbhOHIDB3qGlwKdzOxHkH89V7ODVzSzE4CG7r6Y0PNcmwNn20dEiTZmdnZZBasE+SDRr/MrCQPCNwBZhF6Au46w6iTg1GhoxR2EUwH/KUHVvwaWEcbp/K2kcYuUQE3ghbyLHQint8a6+27CkIo50UURX8SsMxv4YXS67CZCu4BwuvfEaDvjCF92h3D3TwkJ74Jo2XcIFwsWyd13EX6c3gaMBdpF6z5I6PHmMOVvAleaLtKT4ksws40xf7cS9qeJ0f6VyoFxvtcDT5vZB4QerLzv+knAIDNbShheUZxe41VAroULtEcdcemSGQ/UsXBR7UrCkCqRuIjOKL4FXBL9x923AD8DXo7a2VKgRSGrVwFeis54fkK4xmQ74bhTFVhl4WLZcWUVr6aaLiNRT3NVd98d9cAtBJq5+3dxDk2kVKIe2dvcvecRFhX5XjGzmu6eEz2+EzjN3X8R57BEpAxpDHLZSQAWR0MkDLhJybGIyHHpMjP7FeEY+gWhB0xEjiPqQRYRERERiaExyCIiIiIiMZQgi4iIiIjEUIIsIiIiIhJDCbKIiIiISAwlyCIiIiIiMf4fnl/aYJ93MncAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 720x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Data to plot\n",
    "transformations = ['Original', 'Square Root', 'Logarithmic', 'Inverse']\n",
    "statistics = [0.9871, 0.9702, 0.7145, 0.0346]\n",
    "p_values = [0.0090, 0.000007, 2.64e-22, 3.61e-36]\n",
    "\n",
    "# Creating subplots\n",
    "fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(10, 8))\n",
    "\n",
    "# Plotting statistics\n",
    "ax1.plot(transformations, statistics, 'o-', color='blue', label='Statistic')\n",
    "ax1.set_title('Statistics of Different Transformations')\n",
    "ax1.set_ylabel('Statistic')\n",
    "ax1.set_ylim(0, 1.1)\n",
    "ax1.grid(True)\n",
    "\n",
    "# Adding annotations for statistics\n",
    "for i, txt in enumerate(statistics):\n",
    "    ax1.annotate(f'{txt:.4f}', (transformations[i], statistics[i]), textcoords=\"offset points\", xytext=(0,10), ha='center')\n",
    "\n",
    "# Plotting p-values\n",
    "ax2.plot(transformations, p_values, 'o-', color='red', label='P-value')\n",
    "ax2.set_yscale('log')  # Log scale for better visualization of small p-values\n",
    "ax2.set_title('P-values of Different Transformations')\n",
    "ax2.set_ylabel('P-value (log scale)')\n",
    "ax2.grid(True)\n",
    "\n",
    "# Adding annotations for p-values\n",
    "for i, txt in enumerate(p_values):\n",
    "    ax2.annotate(f'{txt:.2e}', (transformations[i], p_values[i]), textcoords=\"offset points\", xytext=(0,10), ha='center')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "fd2f6cdf",
   "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>variable</th>\n",
       "      <th>VIF</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>Daily Revenue (INR)</td>\n",
       "      <td>22.626124</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Number of Cows</td>\n",
       "      <td>8.568805</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>Daily Income from Selling Manure (INR)</td>\n",
       "      <td>6.150645</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Number of Buffaloes</td>\n",
       "      <td>5.952573</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Daily Expenditure on Animal Health (INR)</td>\n",
       "      <td>5.561436</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>Daily Operating Costs (INR)</td>\n",
       "      <td>5.468870</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Number of Family Members/Employees Working at ...</td>\n",
       "      <td>4.499684</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>jamnagar</td>\n",
       "      <td>2.141800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>surat</td>\n",
       "      <td>2.062678</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Use_of_Automation</td>\n",
       "      <td>1.964859</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>rajkot</td>\n",
       "      <td>1.954350</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>amul</td>\n",
       "      <td>1.908705</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>mother dairy</td>\n",
       "      <td>1.897252</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>selling privately to consumers</td>\n",
       "      <td>1.894949</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>natural plants</td>\n",
       "      <td>1.887057</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>parag milk foods ltd</td>\n",
       "      <td>1.864444</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ahmedabad</td>\n",
       "      <td>1.761126</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>aavin</td>\n",
       "      <td>1.747232</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>Satisfaction_8_10</td>\n",
       "      <td>1.734666</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>Satisfaction_5_7</td>\n",
       "      <td>1.664132</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>orissa state cooperative milk producers federa...</td>\n",
       "      <td>1.646243</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>dudhsagar dairy</td>\n",
       "      <td>1.599509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>karnataka co-operative milk federation</td>\n",
       "      <td>1.546725</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>dynamix dairy</td>\n",
       "      <td>1.471665</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>verka</td>\n",
       "      <td>1.389482</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             variable        VIF\n",
       "22                                Daily Revenue (INR)  22.626124\n",
       "0                                      Number of Cows   8.568805\n",
       "20             Daily Income from Selling Manure (INR)   6.150645\n",
       "1                                 Number of Buffaloes   5.952573\n",
       "19           Daily Expenditure on Animal Health (INR)   5.561436\n",
       "21                        Daily Operating Costs (INR)   5.468870\n",
       "2   Number of Family Members/Employees Working at ...   4.499684\n",
       "4                                            jamnagar   2.141800\n",
       "6                                               surat   2.062678\n",
       "18                                  Use_of_Automation   1.964859\n",
       "5                                              rajkot   1.954350\n",
       "8                                                amul   1.908705\n",
       "12                                       mother dairy   1.897252\n",
       "15                     selling privately to consumers   1.894949\n",
       "17                                     natural plants   1.887057\n",
       "14                               parag milk foods ltd   1.864444\n",
       "3                                           ahmedabad   1.761126\n",
       "7                                               aavin   1.747232\n",
       "24                                  Satisfaction_8_10   1.734666\n",
       "23                                   Satisfaction_5_7   1.664132\n",
       "13  orissa state cooperative milk producers federa...   1.646243\n",
       "9                                     dudhsagar dairy   1.599509\n",
       "11             karnataka co-operative milk federation   1.546725\n",
       "10                                      dynamix dairy   1.471665\n",
       "16                                              verka   1.389482"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from statsmodels.stats.outliers_influence import variance_inflation_factor\n",
    "\n",
    "# Calculating VIF for each predictor variable\n",
    "vif_data = pd.DataFrame()\n",
    "vif_data['variable'] = predictors.columns\n",
    "vif_data['VIF'] = [variance_inflation_factor(predictors.values, i) for i in range(predictors.shape[1])]\n",
    "\n",
    "# Displaying the VIF for each variable\n",
    "vif_data.sort_values(by='VIF', ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "6496c7e6",
   "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>variable</th>\n",
       "      <th>VIF</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Number of Buffaloes</td>\n",
       "      <td>5.020027</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Number of Family Members/Employees Working at ...</td>\n",
       "      <td>4.327009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Number of Cows</td>\n",
       "      <td>4.175240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>jamnagar</td>\n",
       "      <td>2.054555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>surat</td>\n",
       "      <td>2.051606</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Use_of_Automation</td>\n",
       "      <td>1.935643</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>amul</td>\n",
       "      <td>1.866011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>mother dairy</td>\n",
       "      <td>1.861064</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>parag milk foods ltd</td>\n",
       "      <td>1.841169</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>natural plants</td>\n",
       "      <td>1.839625</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>selling privately to consumers</td>\n",
       "      <td>1.832080</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>rajkot</td>\n",
       "      <td>1.822925</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>aavin</td>\n",
       "      <td>1.666620</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Satisfaction_5_7</td>\n",
       "      <td>1.659979</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ahmedabad</td>\n",
       "      <td>1.639754</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>orissa state cooperative milk producers federa...</td>\n",
       "      <td>1.602578</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>Satisfaction_8_10</td>\n",
       "      <td>1.564728</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>dudhsagar dairy</td>\n",
       "      <td>1.507802</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>karnataka co-operative milk federation</td>\n",
       "      <td>1.492250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>dynamix dairy</td>\n",
       "      <td>1.454973</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>Balance Money per Day</td>\n",
       "      <td>1.407452</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>verka</td>\n",
       "      <td>1.383112</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             variable       VIF\n",
       "1                                 Number of Buffaloes  5.020027\n",
       "2   Number of Family Members/Employees Working at ...  4.327009\n",
       "0                                      Number of Cows  4.175240\n",
       "4                                            jamnagar  2.054555\n",
       "6                                               surat  2.051606\n",
       "18                                  Use_of_Automation  1.935643\n",
       "8                                                amul  1.866011\n",
       "12                                       mother dairy  1.861064\n",
       "14                               parag milk foods ltd  1.841169\n",
       "17                                     natural plants  1.839625\n",
       "15                     selling privately to consumers  1.832080\n",
       "5                                              rajkot  1.822925\n",
       "7                                               aavin  1.666620\n",
       "19                                   Satisfaction_5_7  1.659979\n",
       "3                                           ahmedabad  1.639754\n",
       "13  orissa state cooperative milk producers federa...  1.602578\n",
       "20                                  Satisfaction_8_10  1.564728\n",
       "9                                     dudhsagar dairy  1.507802\n",
       "11             karnataka co-operative milk federation  1.492250\n",
       "10                                      dynamix dairy  1.454973\n",
       "21                              Balance Money per Day  1.407452\n",
       "16                                              verka  1.383112"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "\n",
    "# Dataset for OLS regression\n",
    "final_transformed_data_path = '/Users/dhruvtrivedi/Downloads/Final Project Stat 371/Final_Transformed_Farm_Data_Gujarat_v2.csv'\n",
    "df = pd.read_csv(final_transformed_data_path)\n",
    "\n",
    "# Creating the 'Balance Money per Day' variable in the dataset\n",
    "df['Balance Money per Day'] = df['Daily Revenue (INR)'] + df['Daily Income from Selling Manure (INR)'] - df['Daily Operating Costs (INR)'] - df['Daily Expenditure on Animal Health (INR)']\n",
    "\n",
    "# Dropping the original components of the 'Balance Money per Day' variable\n",
    "predictors_full_model = df.drop(['Daily Revenue (INR)', 'Daily Income from Selling Manure (INR)', 'Daily Operating Costs (INR)', 'Daily Expenditure on Animal Health (INR)', target], axis=1)\n",
    "\n",
    "# Calculating VIF for the full model with the new 'Balance Money per Day' variable\n",
    "vif_data_full_model = pd.DataFrame()\n",
    "vif_data_full_model['variable'] = predictors_full_model.columns\n",
    "vif_data_full_model['VIF'] = [variance_inflation_factor(predictors_full_model.values, i) for i in range(predictors_full_model.shape[1])]\n",
    "\n",
    "# Displaying the VIF for each variable in the full model\n",
    "vif_data_full_model.sort_values(by='VIF', ascending=False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "aedf193b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>    <td>Average Daily Milk Production (litres)</td> <th>  R-squared:         </th> <td>   0.557</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                              <td>OLS</td>                  <th>  Adj. R-squared:    </th> <td>   0.521</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>                        <td>Least Squares</td>             <th>  F-statistic:       </th> <td>   15.40</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>                        <td>Wed, 29 Nov 2023</td>            <th>  Prob (F-statistic):</th> <td>5.84e-36</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                            <td>19:49:46</td>                <th>  Log-Likelihood:    </th> <td> -2261.2</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>                 <td>   292</td>                 <th>  AIC:               </th> <td>   4568.</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>                     <td>   269</td>                 <th>  BIC:               </th> <td>   4653.</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>                         <td>    22</td>                 <th>                     </th>     <td> </td>   \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>                 <td>nonrobust</td>               <th>                     </th>     <td> </td>   \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "                             <td></td>                               <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>const</th>                                                  <td>  604.0985</td> <td>  155.899</td> <td>    3.875</td> <td> 0.000</td> <td>  297.161</td> <td>  911.036</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Number of Cows</th>                                         <td>    3.6081</td> <td>    0.272</td> <td>   13.264</td> <td> 0.000</td> <td>    3.072</td> <td>    4.144</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Number of Buffaloes</th>                                    <td>    3.0491</td> <td>    0.420</td> <td>    7.262</td> <td> 0.000</td> <td>    2.222</td> <td>    3.876</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Number of Family Members/Employees Working at the Farm</th> <td>   -0.3954</td> <td>    2.680</td> <td>   -0.148</td> <td> 0.883</td> <td>   -5.671</td> <td>    4.880</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>ahmedabad</th>                                              <td> -217.1711</td> <td>  110.876</td> <td>   -1.959</td> <td> 0.051</td> <td> -435.466</td> <td>    1.124</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>jamnagar</th>                                               <td>  -80.2231</td> <td>  111.180</td> <td>   -0.722</td> <td> 0.471</td> <td> -299.116</td> <td>  138.670</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>rajkot</th>                                                 <td> -119.8591</td> <td>  114.794</td> <td>   -1.044</td> <td> 0.297</td> <td> -345.868</td> <td>  106.150</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>surat</th>                                                  <td> -131.0674</td> <td>  113.736</td> <td>   -1.152</td> <td> 0.250</td> <td> -354.992</td> <td>   92.858</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>aavin</th>                                                  <td>   81.2378</td> <td>  140.827</td> <td>    0.577</td> <td> 0.565</td> <td> -196.025</td> <td>  358.500</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>amul</th>                                                   <td>   92.5566</td> <td>  155.491</td> <td>    0.595</td> <td> 0.552</td> <td> -213.577</td> <td>  398.691</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>dudhsagar dairy</th>                                        <td>   74.9999</td> <td>  155.184</td> <td>    0.483</td> <td> 0.629</td> <td> -230.530</td> <td>  380.530</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>dynamix dairy</th>                                          <td> -313.8279</td> <td>  178.809</td> <td>   -1.755</td> <td> 0.080</td> <td> -665.872</td> <td>   38.216</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>karnataka co-operative milk federation</th>                 <td>  108.1122</td> <td>  165.295</td> <td>    0.654</td> <td> 0.514</td> <td> -217.325</td> <td>  433.549</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>mother dairy</th>                                           <td>  -54.2924</td> <td>  150.642</td> <td>   -0.360</td> <td> 0.719</td> <td> -350.880</td> <td>  242.295</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>orissa state cooperative milk producers federation</th>     <td>  178.8274</td> <td>  144.984</td> <td>    1.233</td> <td> 0.218</td> <td> -106.620</td> <td>  464.274</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>parag milk foods ltd</th>                                   <td>  -43.2276</td> <td>  145.355</td> <td>   -0.297</td> <td> 0.766</td> <td> -329.405</td> <td>  242.950</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>selling privately to consumers</th>                         <td>   19.1168</td> <td>  154.320</td> <td>    0.124</td> <td> 0.902</td> <td> -284.713</td> <td>  322.946</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>verka</th>                                                  <td>  -20.0783</td> <td>  185.814</td> <td>   -0.108</td> <td> 0.914</td> <td> -385.914</td> <td>  345.757</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>natural plants</th>                                         <td>   93.0422</td> <td>   71.692</td> <td>    1.298</td> <td> 0.195</td> <td>  -48.107</td> <td>  234.191</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Use_of_Automation</th>                                      <td>  -45.9189</td> <td>   77.912</td> <td>   -0.589</td> <td> 0.556</td> <td> -199.313</td> <td>  107.475</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Satisfaction_5_7</th>                                       <td>  -43.1317</td> <td>   89.870</td> <td>   -0.480</td> <td> 0.632</td> <td> -220.069</td> <td>  133.806</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Satisfaction_8_10</th>                                      <td>   78.8190</td> <td>   86.265</td> <td>    0.914</td> <td> 0.362</td> <td>  -91.022</td> <td>  248.660</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Balance Money per Day</th>                                  <td>   -0.0129</td> <td>    0.019</td> <td>   -0.687</td> <td> 0.492</td> <td>   -0.050</td> <td>    0.024</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>35.882</td> <th>  Durbin-Watson:     </th> <td>   2.057</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td> 128.226</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td>-0.442</td> <th>  Prob(JB):          </th> <td>1.43e-28</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 6.124</td> <th>  Cond. No.          </th> <td>2.21e+04</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 2.21e+04. This might indicate that there are<br/>strong multicollinearity or other numerical problems."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                                      OLS Regression Results                                      \n",
       "==================================================================================================\n",
       "Dep. Variable:     Average Daily Milk Production (litres)   R-squared:                       0.557\n",
       "Model:                                                OLS   Adj. R-squared:                  0.521\n",
       "Method:                                     Least Squares   F-statistic:                     15.40\n",
       "Date:                                    Wed, 29 Nov 2023   Prob (F-statistic):           5.84e-36\n",
       "Time:                                            19:49:46   Log-Likelihood:                -2261.2\n",
       "No. Observations:                                     292   AIC:                             4568.\n",
       "Df Residuals:                                         269   BIC:                             4653.\n",
       "Df Model:                                              22                                         \n",
       "Covariance Type:                                nonrobust                                         \n",
       "==========================================================================================================================\n",
       "                                                             coef    std err          t      P>|t|      [0.025      0.975]\n",
       "--------------------------------------------------------------------------------------------------------------------------\n",
       "const                                                    604.0985    155.899      3.875      0.000     297.161     911.036\n",
       "Number of Cows                                             3.6081      0.272     13.264      0.000       3.072       4.144\n",
       "Number of Buffaloes                                        3.0491      0.420      7.262      0.000       2.222       3.876\n",
       "Number of Family Members/Employees Working at the Farm    -0.3954      2.680     -0.148      0.883      -5.671       4.880\n",
       "ahmedabad                                               -217.1711    110.876     -1.959      0.051    -435.466       1.124\n",
       "jamnagar                                                 -80.2231    111.180     -0.722      0.471    -299.116     138.670\n",
       "rajkot                                                  -119.8591    114.794     -1.044      0.297    -345.868     106.150\n",
       "surat                                                   -131.0674    113.736     -1.152      0.250    -354.992      92.858\n",
       "aavin                                                     81.2378    140.827      0.577      0.565    -196.025     358.500\n",
       "amul                                                      92.5566    155.491      0.595      0.552    -213.577     398.691\n",
       "dudhsagar dairy                                           74.9999    155.184      0.483      0.629    -230.530     380.530\n",
       "dynamix dairy                                           -313.8279    178.809     -1.755      0.080    -665.872      38.216\n",
       "karnataka co-operative milk federation                   108.1122    165.295      0.654      0.514    -217.325     433.549\n",
       "mother dairy                                             -54.2924    150.642     -0.360      0.719    -350.880     242.295\n",
       "orissa state cooperative milk producers federation       178.8274    144.984      1.233      0.218    -106.620     464.274\n",
       "parag milk foods ltd                                     -43.2276    145.355     -0.297      0.766    -329.405     242.950\n",
       "selling privately to consumers                            19.1168    154.320      0.124      0.902    -284.713     322.946\n",
       "verka                                                    -20.0783    185.814     -0.108      0.914    -385.914     345.757\n",
       "natural plants                                            93.0422     71.692      1.298      0.195     -48.107     234.191\n",
       "Use_of_Automation                                        -45.9189     77.912     -0.589      0.556    -199.313     107.475\n",
       "Satisfaction_5_7                                         -43.1317     89.870     -0.480      0.632    -220.069     133.806\n",
       "Satisfaction_8_10                                         78.8190     86.265      0.914      0.362     -91.022     248.660\n",
       "Balance Money per Day                                     -0.0129      0.019     -0.687      0.492      -0.050       0.024\n",
       "==============================================================================\n",
       "Omnibus:                       35.882   Durbin-Watson:                   2.057\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              128.226\n",
       "Skew:                          -0.442   Prob(JB):                     1.43e-28\n",
       "Kurtosis:                       6.124   Cond. No.                     2.21e+04\n",
       "==============================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "[2] The condition number is large, 2.21e+04. This might indicate that there are\n",
       "strong multicollinearity or other numerical problems.\n",
       "\"\"\""
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Dropping the individual fiscal variables used in the 'Balance Money per Day' calculation\n",
    "predictors_ols = df.drop(['Daily Revenue (INR)', 'Daily Income from Selling Manure (INR)', \n",
    "                          'Daily Operating Costs (INR)', 'Daily Expenditure on Animal Health (INR)', \n",
    "                          target], axis=1)\n",
    "\n",
    "# Adding a constant to the model (for intercept)\n",
    "predictors_ols_with_constant = sm.add_constant(predictors_ols)\n",
    "\n",
    "# Performing OLS regression with the new model\n",
    "ols_model = sm.OLS(df[target], predictors_ols_with_constant)\n",
    "ols_results = ols_model.fit()\n",
    "\n",
    "# Outputting the summary statistics of the model\n",
    "ols_results.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "5137942b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1gAAAKmCAYAAABQcD91AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAAC65UlEQVR4nOzdd3xUZfbH8c9JCKEpJQkdQZogqKg0KyiKYFndXXtv64q9/+x17V2KtLX33gsuCFhAEwUEFbAgLbSE3kNyfn/cmzBJJiE4k4bf9+s1L2bu89x7n3tnmMyZc+4z5u6IiIiIiIhI7BIqewAiIiIiIiI7CgVYIiIiIiIicaIAS0REREREJE4UYImIiIiIiMSJAiwREREREZE4UYAlIiIiIiISJwqwREQkJmZ2tpl9GcP6H5vZWfEcU0Uzs13MbK2ZJcZ5u2ZmT5vZCjP7Ns7bvt3MXojnNv/kOP4ws8MqaF9lfq2VNi4z62tmC+I7OhHZUSjAEhHZAZjZqWaWEX7IXxR+kDywssdVVLQP9e4+0N2fLYd9PWNmbmZ/K7L8sXD52WXczjYDAHef5+713D03hiFHcyBwONDS3XtGGVtNM3vYzBaEz/0cM3s0zmMoUXkGGmZ2g5lNjLI81cw2m1nX7d1meb3WREQiKcASEanmzOwq4DHgHqAJsAswDDj2T2yrRlmWVSOzgYKMRXgsJwC/xWsH5Xx+WgN/uPu6EtpvALoDPYGdgEOAKeU4nor0PLC/me1aZPnJwHR3n1HWDYWZQH3mEZEKoTcbEZFqzMzqA3cCF7v7W+6+zt1z3P19d7827JMcZm0yw9tjZpYctvUNsx//Z2aLgafDLNMbZvaCma0Gzjaz+mb23zA7ttDM/lNSOZyZPW5m881stZl9Z2YHhcsHADcCJ4XZlmnh8vFmdn54P8HMbjazuWa21MyeC48RM2sTZp7OMrN5ZpZlZjdt4xS9DxxgZg3DxwOAH4DFEeNtZ2bjzCw73OaLZtYgbHueIGB9PxzzdRHjOM/M5gHjIpbVMLNG4Tk9JtxGPTP71czOLOF8NTez98xsedjvX+Hy84DRwH7hvu+IsnoP4G13z/TAH+7+XJFtv2lmy8Ls1mUlnSgz621mX5vZSjObZmZ9I9oaWVCqmGlBueI7ZlYX+BhoHo5vbbi/BDO73sx+C8/pa2bWKGJbZ4TPb3Zpz5+7LwDGAWcUaToTeNbMGprZB+GxrQjvt4zYz3gzu9vMvgLWA22LvNZKfN4jz6+Z/RRu/2kzq1XCuSvxPJtZTwuyy6vNbImZPVLSMYvIjkEBlohI9bYfUAt4u5Q+NwG9gW7AXgTZjpsj2psCjQiyJReEy44F3gAaAC8CzwJbgPbA3kB/4PwS9pce7qsR8BLwupnVcvdPCLJsr4bldHtFWffs8HYI0BaoBwwp0udAYDegH3CrmXUu5dg3Au8RZD0g+HD+XJE+BtwLNAc6A62A2wHc/QxgHnBMOOYHItbrE/Y/InJj7r4cOBcYZWaNgUeBqZGBTxEvAwvC/R8P3GNm/dz9v8CFwKRw37dFWXcycJWZXWRme5iZFRxUkLF5H5gGtCA4X1eY2RFFN2JmLYAPgf8QPG/XAG+aWVrY5XmgDtAFaAw8GmbVBgKZ4fjquXsmcBlwXHh+mgMrgKHhfnYHniQImpoDKUBBUBTFs0QEWGa2G8Fr62WCzzBPE7xudwE2UPy1cgbBa3onYG7Rw6aE5z3CaQTPbzugI4X/3+SPaVvn+XHgcXffOdzOa6Ucr4jsABRgiYhUbylAlrtvKaXPacCd7r7U3ZcBd1A4K5AH3Obum9x9Q7hskru/4+55wM4EH6SvCDNkSwmChpOJwt1fcPdsd9/i7g8DyQQBUVmcBjzi7r+7+1qCEriTrXAZ3h3uvsHdpxF8qI0WqEV6DjgzzIT1Ad4pMt5f3f2z8PiXAY+E/bbl9vB8bCja4O5jgNeBscBRwL+jbcDMWhEEjP/n7hvdfSpB1qpo1qYk9wL3E5y3DGChbZ3EoQeQ5u53uvtmd/8dGEX05+104CN3/8jd89z9s3B7R5pZM4Ln/0J3XxFmSCeUMqZ/Aze5+wJ330QQtBwfPofHAx+4+8Sw7RaC119J3gaamNn+4eMzgY/dfVn4GnvT3de7+xrgboo/b8+4+4/hazEnsqGMz/sQd58fBs13A6dEGeO2znMO0N7MUt19rbtPLuV4RWQHUJ3r6kVEBLKBVDOrUUqQ1ZzC397PDZflW+buG4usMz/ifmsgCVgUkSBJKNKngJldTZDdag44QYCWuu1DKXGsNQiuLcu3OOL+eoIsV4nc/cswE3MzwYf7DRHHQZhlegI4iCDTkUCQddmWqMcfYSRwCXCPu2eX0Kc5sDwMEPLNJbiuapvCSTWGAkPNrDZB5uwpC2YcbE1QvrcyYpVE4Isom2oNnJBf1hhKAj4nyOwsd/eynJP8bb1tZpGBUy7Bc9iciPPm7uvMrKRzg7uvN7PXCQLkSQSB5FUAZlaHINAfAOSXgO5kZokRk42U+ByV8XmPXL/o/5vI4y3tPJ9HUMY708zmEHxB8EFJ4xKR6k8ZLBGR6m0SQRnccaX0yST4EJhvl3BZPo+yTuSy+cAmINXdG4S3nd29S9GVLLje6v+AE4GG7t4AWEVQjlXSvrY11i3Akm2sty0vAFdTvDwQgiyQA3uGZVyns3W8UPKYSzwWC65PGxHub5CZtS+haybQyMx2ili2C7CwpG2XJMzqDSUIEnYneN7mRDxnDdx9J3c/Msrq84Hni/St6+73hW2NolyfBNHPwXxgYJFt1XL3hcAigoANKAiSUrZxaM8SvJ4OJwiE8oOTqwkyo73C5+3g/M1uY3z5tvW8EzlWiv+/yVfqeXb3X9z9FILSyvuBN8Lr10RkB6UAS0SkGnP3VcCtBBmM48ysjpklmdlAM8u/Xuhl4GYzSzOz1LB/mX//yN0XAWOAh81s53ASg3ZmFq2MbieCgGgZUMPMbiXIYOVbArSxkmd0exm40sx2NbN6bL1mq7QSyLJ4guADerFpv8MxrwVWhtciXVukfQnB9WDb48bw33OBh4DnLMqkIO4+H/gauNfMapnZngQZjxfLshMzu8KCiUpqWzDBxlnh8UwBvgVWWzCBSW0zSzSzrmbWI8qmXgCOMbMjwn61wu22DJ//j4Fh4cQSSWaWH8wsAVLC8st8w4G7zax1OMY0M8uf0fIN4GgzO9DMahJkdrb1WeQLYCVBRvAVd98cLt+J4LqrlRZMohHtGrXSbOt5B7jYzFqG278ReDVKn1LPs5mdbmZpYbntynCdeE/nLyJViAIsEZFqzt0fISibupkgsJlPUJr2TtjlPwTX0/wATAe+D5dtjzOBmsBPBBmSN4BmUfp9SvBhfDZBSdVGCpdZvR7+m21m30dZ/ymCCRUmAnPC9S/dzrEW4+7L3X2su0fLaNwB7EOQafsQeKtI+70EAepKM7tmW/sys30Jno8zw1K1+wkyJdeXsMopQBuC7MjbBNfDfbbtowKCAONhgrLJLOBi4J/hNWy5wDEEk0LMCdtHA/WLbiQM9I4lCCLyX0PXsvVzwhkE1xLNBJYCV4TrzSQIin8Pz09zgkkd3gPGmNkagok4eoX9fwzH+BJBNmsFwQQfJQqfs+cIMpuRGcjHgNrhcU0GPin1TBW3reedcJxjgN/DW7H/N2U4zwOAH81sLcG5OTlKSa6I7EAs+t8aERERERER2V7KYImIiIiIiMSJAiwREREREam2zOwpC36cfkYJ7WZmT1jwY+4/mNk+EW0DzGxW2FZSKfd2UYAlIiIiIiLV2TME1zuWZCDQIbxdQPCD5/kzvg4N23cHTgl/ED0mCrBERERERKTacveJwPJSuhwLPOeByUCD8EfUewK/hhMDbQZeCfvGRD80LFLBPkzaTTPLlLNDP7u9soeww1vcKtpM3xJvv65tte1OEpOD5oyo7CHs8LYsXlTZQ9jh1bvw3qK/4VYpyuszztFbZv+bIPOUb6S7j9yOTbSg8Iy2C8Jl0Zb3+rPjzKcAS0REREREqqwwmNqegKqoaAGol7I8JgqwREREREQkZpZUJRJp0SwAIksCWhL89mDNEpbHRNdgiYiIiIjIjuw94MxwNsHewCp3XwSkAx3MbFczqwmcHPaNiTJYIiIiIiISs4QalZPBMrOXgb5AqpktAG4DkgDcfTjwEXAk8CuwHjgnbNtiZpcAnwKJwFPu/mOs41GAJSIiIiIi1Za7n7KNdgcuLqHtI4IALG4UYImIiIiISMwsSVcfgQIsERERERGJg8oqEaxqFGaKiIiIiIjEiTJYIiIiIiISsyo8TXuFUgZLREREREQkTpTBEhERERGRmOkarIACLBERERERiZlKBAMqERQREREREYkTZbBERERERCRmKhEMKIMlIiIiIiISJ8pgiYiIiIhIzCxRGSxQgCUiIiIiInGQoAALUImgiIiIiIhI3CiDJSIiIiIiMbMEZbBAGSwREREREZG4UQZLRERERERiZonK3YAyWCIiIiIiInGjDJaIiIiIiMRMswgGFGCJiIiIiEjMNMlFQCWCIiIiIiIicaIMloiIiIiIxEwlggFlsEREREREROJEGSwREREREYmZKYMFKMASEREREZE4sAQVx4FKBEVEREREROJGGSwREREREYmZpmkPKMDagZhZLjAdSAK2AM8Cj7l7XinrNAeecPfjzawvcI27H13G/Z0NPAgsBGoBI9z90ViOoaKYmQFjgePcfbWZrXX3embWBpgDXObug8O+Q4AMd3/GzJ4B+gCrAAOucvexYb9XgFvc/ZeKP6Ltt+eoe2h8ZF82L81m4t7HRO2z+6M30XhAH3I3bGTaedezespPAKT1P4jdH7kJS0xg/lOv89uDoypy6NXKVzN+4YHXPiEvL4+/H7gP5w44qFD751NnMuy9cZgZNRISuPakAezdvnVBe25eHqfeM5LGDXZi8CWnVfTwq4WMjAyeHDGSvLw8BhzRn5NOPLFQu7vz5IgRpKdnkJyczNVXXUmH9u0BeOvtt/nk0zGYGW3atObqK6+kZs2alXEYVZ6788bT9/PjlC+omVyLMy66i1Ztdy/Wb8InL/P5hy+QtWQ+942eQL2dGwIw+8d0Rj5wOSmNWwDQrVc/Bh5/YYUeQ1X31ay53P/el+R5Hn/vsTvnHbJv1H4z5i/hjKFv8sCp/Tl8z/ZsytnCOcPfJic3ly25eRy+Rzsu6t+rgkdfPXz9x2IeGv8DuXnOcV3bcE7P3Qq1Z8xfxlXvTaJF/boAHNK+ORf07lzQnpvnnPHSONLq1ebx4/av0LFL9aEAa8eywd27AZhZY+AloD5wW0kruHsmcHwM+3zV3S8xsxRglpm94e7zY9heRTkSmObuq6O0LQUuN7MR7r45Svu17v6GmR0CjAQ6hMufBK4D/lUuI46zBc++xR/DXqDbU/dHbU8bcDB127dhfOf+NOi1F12H3M7XB5wICQl0eeJWvhl4DhsXLOHAyW+w5INxrP35two+gqovNy+Pe1/+iOFXnEGThjtz2r2j6LPnbrRr3rigT69Ou9J3r0GYGbMXLOa6ka/zzp2XFrS/NHYyuzZNZd3GTZVxCFVebm4uQ4c9yT13/4fU1FQuu+JKevfuTetddinok56RQebCTJ4aPYqZs2YxZMhQHn/sUbKysnj3vfcZOfxJkpOTufueexk/YQL9Dz+8Eo+o6vppypcsWzyX2574gD9++YFXRv+Ha+95qVi/trt1o+s+B/P4HecVa2vXeR8GXT+kIoZb7eTm5XHPOxMZcf7faFK/HqcOeZ2+u+9KuyaNivV77ONJ7N+xVcGymjUSGX3BsdRJrklObi5nP/kWB+7Wmj1bN63ow6jScvOc+8ZNY9g/DqTJTrU546XP6dOuGW1Tdi7Ub+8WqSUGTy9P+ZU2jXZi3eYtFTHkakfTtAd0DdYOyt2XAhcAl1igjZl9YWbfh7f9AcLlMyLXNbMEM/vFzNIiHv9qZqml7C8b+BVoFq5zupl9a2ZTzWyEmSWa2SAzeyBiP2eb2eCS+ofL15rZ3WY2zcwmm1mTcPkzZnZ8xLbWRty/1szSzewHM7ujhCGfBrxbQtsyguzWWSUdb2gS0CLi8RfAYWZWLb64WP5lBjnLV5XY3uRv/Vj4wjsArPxmGkn1dya5aRoNeu7J+t/msmHOAjwnh8xXP6TJMf0qaNTVy4w5C2nVuBEt0xqRVKMGR3Tvyvhpswr1qVMrmSChChs25RTcB1iyYhVfTP+Ffxy4T4WOuzqZNXs2zZo3p1mzZiQlJdHn4IOZNGlyoT6TJk+mX79DMTM6d+rE2nXryF6+HAgCtM2bN5Obm8umTZtISUmpjMOoFn7I+JyeBx+DmbFrx73YsG4Nq1YsK9av1a6dC7JUUnYz5i+lVUp9WqbUJ6lGIgP26sD4n+YU6/fyV9M5rGs7GtWrU7DMzKiTHGRet+TmsSU3L6ixkEJ+XLycVg3q0rJBXZISE+i/W0vG/7aozOsvWbOeL+cs5riubcpvkNWcJVi53KobBVg7MHf/neA5bkyQlTnc3fcBTgKeKGW9POAFgiAE4DCCbE9WSeuY2S4EZYI/mFnncB8HhBm13HBbbwD/iFjtJODVUvoD1AUmu/tewES2kR0ys/4EGaWeQDdgXzM7OErXA4DvStnUfcDV+YFeCQYA7+Q/CM/br8BepY2xuqjVvAkbFiwueLxx4WJqtWgSZfkSarVoUhlDrPKWrlxN04Zbvxlt0nBnlq4snjQdN+Vnjrt1MJcOeZHbzzy2YPmDr33CFf88vFDQJYVlZ2eTlrr1u5/U1FSys7ML98nKJi0treBxWmoq2VnZpKamcvw//sEZZ53NqaedTt26ddl3HwWzJVm5fCkNU7dmRBqkNGHl8qXbtY05s6dx77XHM+yeQSya/2u8h1itLV21lqYN6hU8bly/HktWrSvUZ8mqtYz78XdO6N2l2Pq5eXmc+NgrHHLXU/Tu0Io9d1H2qqilazfSZKfaBY+b1KvNsrUbivWbvmg5Jz8/lkvf/orfsra+Zz88/gcuP6grCXpPlm1QgLXjy38XSAJGmdl04HWgeOF8YU8BZ4b3zwWeLqHfSWb2I/A78Li7bwT6AfsC6WY2NXzc1t2XAb+bWe+wpHA34KuS+ofb3wx8EN7/DmizjXH3D29TgO+BTmwt4YvUyN3XlLQRd58DfAucGqX5QTP7nSAIvadI21Kg+TbGWC1E+1Dv7hDtD4t7BYyo+ol2VizK18qH7t2Zd+68lEcHncyw98YBMPGHWTTcqS67t94hXk7lxqO89oq+RD3KM2EGa9asYdLkyTzz9FO8+MLzbNy4kbHjxpXXUKu/qOe67B80W+3ambuGfcoND75BnwGnMvLBK+I4uOov6vtFkdP74PtfcsXA/UiMMhV2YkICr11xMmNuPJsZ85fyy+LsYn3+6kp6L4jUqXEDPjhvAK+c0Y+TurXj6vcnATDx90U0rJNM5yYNK2Ko1ZYlJJTLrbqpFqVM8ueYWVuCbNBSguuwlhBkVxKAjaWt6+7zzWyJmR0K9GJrRqmo/Guw9gM+NLOPCYK6Z939hmj9gROBmcDb7u7hhBMl9c/xrZ+gctn6mt0SHkf+hBX5V6UbcK+7jyjt+IAtZpZQ2gQgBMHTGwSZs0jXAm8BlxFMJBJ5FXItoNjXYWZ2AUHJJpckNGZAQoNtDK/ybVi4mNotm7IifFyrRVM2ZS4loWYStVtu/Wa0VosmbMzcvm+x/yqaNNiZxSu2fvu5ZMVq0hrsVGL/fTu2Yf4z77Bi7Tqm/jafCdNm8eWMX9ics4V1GzZx43/f5J7z/lkRQ682UlNTWZa1NbmelZVFo0Ypxfss21rKtiwri0YpKUyZOpUmTZvQoH59AA44YH9+/vln+h16aMUMvhqY8MkrfD32TQBat+vCiqyt2euV2Uuo3zCtpFWLqV1na3amyz4H8ep/72bt6hUFk2D81TWpX4/FKwuq3Vm6ai2Nd65bqM+PC5byfy+PAWDFug18MXMuiYkJHNqlbUGfnWsn06Ntc76eNY8OTVXyGqlJvdosWbP1T/SStRtIrVu7UJ96yUkF9w/ctSn3jZvKig2bmJaZzcTfF/HVH0vYvCWXtZu3cPPH6fxnYI8KG79UH9UvJJQyCa+fGg4MCQOU+sCiMKA4Ayit9C3faIIszWvunltaR3efBDwPXE5w/dLx4UQbmFkjM8ufFu0t4DjgFIJgi230L8kfbA1sjiXI0AF8CpxrZvXCbbXI324Rs9iaJSvpmGYCPwHFZlUMz+PjQIKZHRHR1BH4MUr/ke7e3d27V4fgCmDp++NocfpxADTotRdbVq9h0+JlrEqfTt32bajdpiWWlETzk45iyQf61j+aLm2aM29pNguzVpCzZQufZsygz16FZ6yatzS7IAvz87xMcnJzaVC3Dpf9/TDG3H81H99zJfedfzw9Ou2q4CqK3Tp2JDNzIYsXLyYnJ4cJEyfSu3fh2dN69+rF2LHjcHd+njmTunXrktKoEY3T0pg5cxYbN27E3Zk6dRqtWrUqYU9/TX0GnMwND77ODQ++zp49D+Xbie/j7syZPY3adXbargBr9cqsgtf6H79Ox/PyqLtTg3IaefXTpWVj5mWvYsHy1eRsyeWTab/Qp3ObQn0+vv7Mgtvhe7TnpuMO5tAubVm+dgOrNwQT4WzM2cLkXxfQprEC16J2b9qQ+SvWsnDVOnJy8xgzawF92jYr1Cdr3caC1+mMxcvJc6dBrZpcemBXPv7XkXxw3gDuObInPVqlKbiKQtdgBZTB2rHUDkvs8qdpfx54JGwbBrxpZicAnwProm6hsPcISgNLKg8s6n6Csrx7gJuBMWaWAOQAFwNz3X2Fmf0E7O7u3wK4+09mFrV/KfsaBbxrZt8SBGjrwm2NCa/pmhSWrqwFTifI4kX6EOhLcM1Uae4mKDcsJsy+/Ydg5sBPwwk4Nrh72a+YrUTdnn+YlD49qZnakEPnTOCXOwdjScFbwryRr7D04wmkDexD35mfkbthAz+cfyMAnpvLjMvvpOeHo7HERBY88yZrf9K1FNHUSEzk+pOPZNDjz5OX5xx7wN60b96Y1yekA3BCnx6M/f5n3p88jRqJCdRKSuKBfx2va662Q2JiIhcNGsRNN99CXl4e/fsfTpvWrfnww48AOOqoI+nZowfp6Rmce975JCcnc9WVVwLQqVMnDjrwAC657HISExNp17YtAwcOrMzDqdK67H0QP37/BXdcdhRJNWtx+kV3FbQNu/ciTv337TRo1JjxH73I/957mtUrs7nn2uPpsveBnHbhHUyZ/BlfjHmNxMREkmomc84VD+i1HqFGYgI3HHsQg/77Hnl5znE9OtO+aQqvTQ7moTqxd9cS181as46bXxtLXp6T507/PdsXC84EaiQkcN2h3bjkra/IdefYLq1pl7ozb0z7HYDj92rL2F8W8sa030lMSCC5RgL3HtlTr9PtoFkEAxatfl0EwMy6A4+6+0Hb7FzNmFkz4Dl3j9t8zGZ2JbDa3f9bWr8Pk3bTf7pyduhnt1f2EHZ4i1vpm9uK8OtaZdTK20FztlVRLrHasrhafO9YrdW78N4qEdn8eOyh5fIZp8u746rE8ZWVMlgSlZldDwyi5GuvqjV3X2Rmo8xs5xJ+C+vPWEmQNRQRERH5y6mO5XzlQQGWROXu9xFMVb7DcvfX4ry9spZSioiIiMgOSgGWiIiIiIjErDpOqV4edBZERERERETiRBksERERERGJma7BCijAEhERERGRmCnACqhEUEREREREJE6UwRIRERERkZgpgxVQBktERERERCROlMESEREREZGYaZr2gAIsERERERGJWUKiSgRBJYIiIiIiIiJxowyWiIiIiIjETJNcBJTBEhERERERiRNlsEREREREJGaVNcmFmQ0AHgcSgdHufl+R9muB08KHNYDOQJq7LzezP4A1QC6wxd27xzoeBVgiIiIiIhKzyigRNLNEYChwOLAASDez99z9p/w+7v4g8GDY/xjgSndfHrGZQ9w9K15jUomgiIiIiIhUVz2BX939d3ffDLwCHFtK/1OAl8tzQAqwREREREQkZpZg5XLbhhbA/IjHC8JlxcdnVgcYALwZsdiBMWb2nZldEMPhF1CJoIiIiIiIVFlh4BMZ/Ix095H5zVFW8RI2dQzwVZHywAPcPdPMGgOfmdlMd58Yy3gVYImIiIiISMzKa5KLMJgaWULzAqBVxOOWQGYJfU+mSHmgu2eG/y41s7cJSg5jCrBUIigiIiIiItVVOtDBzHY1s5oEQdR7RTuZWX2gD/BuxLK6ZrZT/n2gPzAj1gEpgyUiIiIiIjGrjFkE3X2LmV0CfEowTftT7v6jmV0Ytg8Pu/4dGOPu6yJWbwK8bWYQxEUvufsnsY5JAZaIiIiIiMSssn4Hy90/Aj4qsmx4kcfPAM8UWfY7sFe8x6MSQRERERERkThRBktERERERGJnFV8iWBUpgyUiIiIiIhInymCJiIiIiEjMKmOSi6pIAZaIiIiIiMSssia5qGp0FkREREREROJEGSwREREREYmZSgQDymCJiIiIiIjEiTJYIiIiIiISM12DFVCAJVLBDv3s9soewg5v3OG3V/YQdnh7/PROZQ/hL2HXepmVPYQd3pKuR1T2EHZ4q7o0rOwh7PD2rOwBhFQiGFCYKSIiIiIiEifKYImIiIiISMyUwQoogyUiIiIiIhInymCJiIiIiEjsNMkFoAyWiIiIiIhI3CiDJSIiIiIiMTPTNVigAEtEREREROJAv4MV0FkQERERERGJE2WwREREREQkZpqmPaAMloiIiIiISJwogyUiIiIiIrHTNViAAiwREREREYkDlQgGFGaKiIiIiIjEiTJYIiIiIiISMzPlbkAZLBERERERkbhRBktERERERGKna7AABVgiIiIiIhIHplkEAZUIioiIiIiIxI0yWCIiIiIiEjNN0x5QBktERERERCROlMESEREREZHYaZp2QBksERERERGRuFEGS0REREREYqZrsAIKsEREREREJHaaph1QiaCIiIiIiEjcKIMlIiIiIiIxM1OJICiDJSIiIiIiEjfKYImIiIiISOx0DRagAEtEREREROJAswgGFGaKiIiIiIjEiTJYIiIiIiISO1PuBuIYYJlZLjAdSAK2AM8Cj7l7XinrNAeecPfjzawvcI27H13G/Z0NdHf3S2Icerkws4OA4UAOsJ+7byin/ewGjAAaAMnAF+5+QSn92wAfuHvXyHNuZn8Ddnf3++IwpmeAE4Em7r4mXPY4cBmQ5u5Zse4jVmZWG/gEOBRoReFz8jnwN3d/P+z7AfCQu483s/FAM2AjsBn4l7tPDfv9DzjB3VdU7NH8eV/N+IUHXvuEvLw8/n7gPpw74KBC7Z9Pncmw98ZhZtRISODakwawd/vWBe25eXmces9IGjfYicGXnFbRw68W9hx1D42P7MvmpdlM3PuYqH12f/QmGg/oQ+6GjUw773pWT/kJgLT+B7H7IzdhiQnMf+p1fntwVEUOvdpI/+57ho0cTV5eHgP7H87JJ/yzUPu8+Qt46LHB/Prbb5xz5umc8I/jyryubJWRkcHIEU+Sl5dH/yMGcOKJJxVqd3dGjHiSjPR0kpOTufKqq2nfvgMA55x9JrVr1yEhMYHEhEQef2JwZRxClZee8R1PjhxNXl4uA/r35+QTjy/U7u4MGzGK9IwMkpOTuebKK+jQvh0Ab7/7Hh99OgbcGXhEf/5x3LGVcQhVnrvz9MjH+T5jMsnJyVx8xY20bb9bsX5LFmfy2AO3s3bNGnZt35FLr7qZpKQkvvh8DO+8+SIAtWrV4V8XXU2btu0r+jCkiotnmLnB3bu5exfgcOBI4LbSVnD3THc/vrQ+1dhpBB/Ku0UGV2aWGOf9PAE8Gu6nM/Cn/mq5+3vxCK4i/AocC2BmCcAhwMI4br+Y7Ty35wJvuXtulLYFwE2lrHuau+8FDAMejFj+PHDRdoyhUuXm5XHvyx8x9NLTeOv2i/kkfQa/ZS4t1KdXp1157ZZBvHbLIG4/61jueO69Qu0vjZ3Mrk1TK3LY1c6CZ9/i26PPL7E9bcDB1G3fhvGd+zN90C10HXJ70JCQQJcnbuXbY85nwp5H0fzko6nXuV3FDLoayc3NZfCTI7jnjlsZPWwwn0/4grnz5hfqs9NO9bj43+dzfERgVdZ1JZCbm8uTw4Zyx53/4cnhI5k4YTzz5s0t1CcjI53MhZmMGv0Ul152OUOHDCnUfu999zNkyDAFVyXIzc1lyJMjuPuO2xj15FDGT5zI3HnzCvVJz/iOhZmZPD1qBFdcejFPDH0SgDl/zOWjT8cw+JGHGT7kCb75NoOFCzMr4zCqvCkZk1mUuYDBI1/m35dcx6hhD0ft9+Izwzn62BMZPOpl6tXdiXGffQBA46bNuOO+ITw85FmOP/ksRgx5oCKHX/UlWPncqplyyeO5+1LgAuASC7Qxsy/M7Pvwtj8E2RQzmxG5rpklmNkvZpYW8fhXMyvxU5yZPWNmT5jZ12b2u5kdH9F2nZlNN7NpZnZfuKybmU02sx/M7G0zaxguH29mj5rZRDP72cx6mNlb4Xj+E7HN083sWzObamYjin6wN7PzCTI4t5rZi2bW18w+N7OXgOlmVsvMng7HNcXMDgnXO9vM3jGz981sjpldYmZXhX0mm1mjKIffjCAgyD/308NtJZrZg2aWHh7nv0t7zsJ9DyntfIbPxTAz+9HMPjCzjyLPdREvA/lfb/YFviLIbObv7x0z+y7c1gURy9ea2d3h8zXZzJpEjCnyeV0b/lv03Jb1uE8D3i2hbRqwyswOL+2cAZOAFhGP3wNO2cY6VcaMOQtp1bgRLdMakVSjBkd078r4abMK9alTK7ngNy02bMop9PsWS1as4ovpv/CPA/ep0HFXN8u/zCBn+aoS25v8rR8LX3gHgJXfTCOp/s4kN02jQc89Wf/bXDbMWYDn5JD56oc0OaZfBY26+pg1+xeaN2tGs6ZNSUpKou/BB/L15G8K9WnYoAG7dexAjcTE7V5XArNnz6J582Y0a9aMpKQkDj64D5MnTSrUZ/LkSRzarx9mRqdOnVm3bi3Ll2dX0oirn1mzfwnPcfB67HPwQcVej19P/obDDz0EM6Nzp06sW7eO7OXLmT9/Pp13241atZJJTExkjz268FWR50cC6d98SZ9DB2BmdOzUhXXr1rJieeHCGndnxg/f0/vAvgD06TeA9ElfALBb5z2oV28nADp06kJ21rIKHX9VZ5ZQLrfqptxG7O6/h9tvDCwFDnf3fQg+dD9Rynp5wAsEH4ABDgOmlaGsrBlwIHA0kB9IDQSOA3qFGYf8rxmeA/7P3fckKGuMzLRtdveDCcr73gUuBroCZ5tZipl1Do/hAHfvBuRGjDX/GEYTfNi+1t3z23oCN7n77uE2cfc9CD6QP2tmtcJ+XYFTw/53A+vdfW+CD/NnRjnuR4FxZvaxmV1pZg3C5ecBq9y9B9AD+JeZ7bqNcxip2PkE/gG0AfYAzgf2K2X9X4C0MHg9BXilSPu57r4v0B24zMxSwuV1gcnh8zUR+FcZxhp5brd53GZWE2jr7n+Uss3/ADdvY78DgHfyH4SlgckRx1KlLV25mqYNdy543KThzixdubpYv3FTfua4Wwdz6ZAXuf3MrSUnD772CVf883D9qGCMajVvwoYFiwseb1y4mFotmkRZvoRaLZpUxhCrtKzs5aSlbf3+LTU1hazs5eW+7l9NdnY2qalpBY9TU1PJzi4cPGVnZZOWFtknjeysoI+ZccvNN3LZZZfw8ccfVcygq5ms7GzSUre+HtOinePsouc4hezsbNq0bs30GT+yevVqNm7cRHrGdyxbVunV+FXS8uxlpKQ2LnickpLG8uzC52rN6lXUqVuPxMTgSpqU1OJ9AMaN+YC9u/cq3wFLtVTek1zkf/JKAoaYWTeCgKTjNtZ7iiC4eYyglOvpMuzrnTA4+yk/60EQnD3t7usB3H25mdUHGrj7hLDPs8DrEdvJr4GaDvzo7osAzOx3gmt1DgT2BdLDD5a1CQLIbfnW3eeE9w8kLOVz95lmNpet5+Tz8LqlNWa2Cng/Yjx7Ft2ouz9tZp8SfNg/Fvi3me0F9Af2jMj61Ac6ALPLMFaIfj4PBF4Ply82s8+3sY23gJOBXkDRTNJlZvb38H6rcGzZBNc1fRAu/46g3HRbIs9tScc9J6J/KrCytA26+xdmln8tXVEvmlldIBEomr5ZCjQPj6VAmKW7AGDwVedxXhXIRHiUZUbxYOnQvTtz6N6d+W72Hwx7bxwjrjyLiT/MouFOddm9dXPSZ82JsiUpq2gBqrtDtMDVoz1rf20e5ZVc1pg/lnX/ajzaa6/IyYp2PvP7PPjQI6SkpLBy5UpuvukGWrVsRdc99iiPoVZfUc5x0ffk6G8Bxi67tOLE4//B9TffSq1atWi7664kJMb7ioQdQ6yv5XwzfviecWM+5K4HhsZzeNVfNSznKw/lFmCZWVuCYGopQYZoCbAXQVZrY2nruvt8M1tiZocSfDgvy9XzmyJ3H/Hv9n4iyd9OXpFt5hGcLwOedfcbtnO766KMr7T9Fx1D/v6LcfdMgqD0KQtKLruG+7jU3T+N7GvBJBdlUdL53B6vAN8TnK+8/A+SFkwkcRjB5B/rLZg4Ij+Dl+Nb3/1y2XrMWwgzrhZsqGbEfoqe22LHXcSGiP2V5m6Ca7G2FFl+GkEZ4X3AUILMXr5a4fYLcfeRwEiADeNfrhKfkps02JnFK7ZmrJasWE1ag51K7L9vxzbMf+YdVqxdx9Tf5jNh2iy+nPELm3O2sG7DJm7875vcc54mCNheGxYupnbLpuTPjFKrRVM2ZS4loWYStVs2LehXq0UTNmaW5bucv5a0lJRC39RnZWWT0ihaNXV81/2rSU1NJSuiFCorK6vYuUpNTWXZssg+y0hJCfqkpASJ/QYNGrDffvsza/YsBVhFpKamsixr6+txWVYWjVKKnuOUIuc4u+AcDzyiPwOP6A/AU88+R2qKro/N98kHb/G/T4Pvq9t36ER21tb30uzsZTRqVLjwZOedG7B+3Vpyc7eQmFiD7KzCfebO+ZXhT9zPjXc8yE4716+Yg5BqpVxKBC24fmo4MCT8sFwfWBRmPs4g+OZ/W0YTlAq+VsJEBGUxBjjXzOqE42rk7quAFRGZiTOACSVtIIqxwPFm1jh/m2bWehvrFDWRMGg0s47ALsCsUtcogZkNMLOk8H5TIIVgMolPgUERbR3DrEssvgT+GV6L1YTg2qoSufs8ggBlWJGm+sCKMLjqBPQuw77/IMgcQpCpSyqh3zaPOyzlS4woyyxp/GOAhgRfDBRtyyEoIewdlo3mB35Nw7FWeV3aNGfe0mwWZq0gZ8sWPs2YQZ+9Cs+kNG9pdsG3fT/PyyQnN5cGdetw2d8PY8z9V/PxPVdy3/nH06PTrgqu/qSl74+jxenHAdCg115sWb2GTYuXsSp9OnXbt6F2m5ZYUhLNTzqKJR+Mq9zBVkG7dezAwsxFLFq8hJycHMZP/JL9evUs93X/ajp23I2FmZksXryYnJwcJk6cQK/ehd+6e/XqzbixY3F3Zs78mbp169KoUQobN25k/fr1AGzcuJHvp3xP69ZtKuEoqrbdOnZg4cJMFoXneMLEL9ivV+Hys/169eSzcZ/j7vw8cyZ169YpCHRXrFwJwNKly/jy60kc0ufgij6EKmvA0f/gocFP89Dgp+mx30FMGPcJ7s7smT9Sp049GjYqHIyaGV322JvJX44HYMLYT+jRO/jYuGzpEh6852YuvfpmmrfYpaIPpcqzhIRyuVU38cxg1TazqWydpv154JGwbRjwppmdQDAF9rqoWyjsPYLSwLKUB0bl7p+EZYkZZrYZ+Ai4ETgLGB4GXr8D52zHNn8ys5uBMRZcdZdDcE3V3NLXLGRYuP/pBOfqbHff9CevZekPPG5m+VnBa919sZmNJrhe6vvwg/8yguvRYvEm0A+YQVBq+A1Q8tX7gLuPiLL4E+BCM/uBILCcXIZ9jwLeNbNvCYLckl5DZT3uMQQlj//bxn7vpoTJMNx9g5k9DFxDcO3XvgTXjxXNeFVJNRITuf7kIxn0+PPk5TnHHrA37Zs35vUJ6QCc0KcHY7//mfcnT6NGYgK1kpJ44F/H65qr7dTt+YdJ6dOTmqkNOXTOBH65czCWFLz1zhv5Cks/nkDawD70nfkZuRs28MP5NwLgubnMuPxOen44GktMZMEzb7L2p18r81CqpMTERC658F/ccOsd5OXlcsThh9Gm9S68/9EnABxz5ACWr1jBxVdcw/r167EE461332f0k4OpW6dO1HWluMTERAYNuohbbr6JvLw8Du/fn9at2/DRhx8CcORRR9GjR08y0tM5/7xzg2nar7wKgBUrVnD3f+4Egpny+vQ9hO7du1fasVRViYmJXDLo39x4y+3k5eUVvB4/+OhjAI4+ciA9e3Tn24zvOPv8f4fTtF9WsP5d99zH6tVrqFEjkUsHXchOO9WrrEOp0vbpvh9TMiZz6b9OpmZyLS6+YmtB0j23XcuFl/0fjVJSOf2cQTx6/+28/MJodm3bgUP7HwXAG688zdrVqxg1LPiIm5iYyP2Pja6UY5Gqy6LWolYBZtadYPrxaNfASCUxs3ruvjacyOFbgsk+Fm9rvarGzPYGrnL3M+K4zceB99x9bGn9qkqJ4I5s3OG3V/YQdnh7/PROZQ/hL2FzQlmqmSUWSb65soeww1vlDSt7CDu8PTs0rhLffq5/6rZy+YxT59w7qsTxlVWVzLmZ2fUE2ZLtvc5Jyt8HYabyC+Cu6hhcAbj7FOBzi+/vks3YVnAlIiIissNKSCif2zaEl8zMsuCnna6P0t7XzFZZ8BNLU83s1rKu+2eU9yyCf0r4g7fx/NFbiRN371vZY4gXd38qztsbFc/tiYiIiEjpwi/LhxLMPL2AYKbv99z9pyJdv3D3o//kutulSmawRERERESkmjErn1vpegK/uvvv7r6ZYBbrY7exTjzWLZECLBERERERqbLM7AIzy4i4XRDR3AKYH/F4QbisqP3MbJqZfWxmXbZz3e1SJUsERURERESkeimvKdUjf0802m6jrVLk8fdA63CitiOBd4AOZVx3uymDJSIiIiIisbOE8rmVbgHQKuJxSyAzsoO7r3b3teH9j4AkM0sty7p/hgIsERERERGprtKBDma2q5nVBE4m+D3dAmbWNPx9VMysJ0EMlF2Wdf8MlQiKiIiIiEjsEir+56rcfYuZXQJ8CiQCT7n7j2Z2Ydg+HDgeGGRmW4ANwMke/Bhw1HVjHZMCLBERERERqbbCsr+PiiwbHnF/CDCkrOvGSgGWiIiIiIjEzLZ9vdRfggIsERERERGJXSWUCFZFCjNFRERERETiRBksERERERGJnUoEAWWwRERERERE4kYZLBERERERiZ3pGixQBktERERERCRulMESEREREZHYJSh3AwqwREREREQkHjTJBaASQRERERERkbhRBktERERERGKnHxoGlMESERERERGJG2WwREREREQkdroGC1CAJSIiIiIi8aDfwQJUIigiIiIiIhI3ymCJiIiIiEjs9DtYgDJYIiIiIiIicaMMloiIiIiIxE7XYAEKsEREREREJB40iyCgEkEREREREZG4UQZLRERERERip0kuAGWwRERERERE4kYZLJEKtrhVj8oewg5vj5/eqewh7PCm735cZQ/hL6HdzLGVPYQd3tlXzqvsIezwnn08qbKH8BfQuLIHENAkF4AyWCIiIiIiInGjDJaIiIiIiMROswgCCrBERERERCQeVCIIqERQREREREQkbpTBEhERERGR2GmadkAZLBERERERkbhRBktERERERGLmugYLUIAlIiIiIiLxoFkEAZUIioiIiIiIxI0yWCIiIiIiEjtlsABlsEREREREROJGGSwREREREYmZJrkIKMASEREREZHYqUQQUImgiIiIiIhI3CiDJSIiIiIisVOJIKAMloiIiIiISNwogyUiIiIiIrFLUO4GlMESERERERGJG2WwREREREQkZpqmPaAAS0REREREYqdp2gGVCIqIiIiIiMSNMlgiIiIiIhIzVwYLUAZLREREREQkbpTBEhERERGR2GmSC0ABloiIiIiIxIFKBAM6CyIiIiIiInGiAEtERERERGJnVj63be7WBpjZLDP71cyuj9J+mpn9EN6+NrO9Itr+MLPpZjbVzDLicRpUIigiIiIiItWSmSUCQ4HDgQVAupm95+4/RXSbA/Rx9xVmNhAYCfSKaD/E3bPiNSYFWCIiIiIiErvKuQarJ/Cru/8OYGavAMcCBQGWu38d0X8y0LI8B6QSQRERERERiZmblcvNzC4ws4yI2wURu20BzI94vCBcVpLzgI8jhw2MMbPvimz3T1MGS0REREREqix3H0lQ1hdNtIu0PGpHs0MIAqwDIxYf4O6ZZtYY+MzMZrr7xFjGqwDrTzKzXGA6kARsAZ4FHnP3vFLWaQ484e7Hm1lf4Bp3P3o79nkccCdQE8gBbnH3d/7kIZR1nw2AU919WPi44BjitP2BwF1AXYL/IB+4+zXbuY1uQHN3/2g71qkNfAIcCrQK99s1fF4+B/7m7u+HfT8AHnL38WY2HmgGbAQ2A/9y96lhv/8BJ7j7iu0Zf2XKyMjgyREjycvLY8AR/TnpxBMLtbs7T44YQXp6BsnJyVx91ZV0aN8egLfefptPPh2DmdGmTWuuvvJKatasWRmHUaWlf/c9w0aOJi8vj4H9D+fkE/5ZqH3e/AU89Nhgfv3tN84583RO+MdxZV5XAnuOuofGR/Zl89JsJu59TNQ+uz96E40H9CF3w0amnXc9q6cElSNp/Q9i90duwhITmP/U6/z24KiKHHq18n3Gt4waMZS8vDwOP+JIjj/xlELt7s6oEUP5Lv0bkpOTufyq62jXviObN2/mxuuuICcnh9zcXPY/8GBOPf3syjmIauDyC9qx374pbNyUyz2Pz2L2b2uL9dl3zwZcdG5bEszYsDGXux+bycJFGznl7y3p37cJAImJRuuWdTj69K9Zs3ZLRR9GlZWRkcGI4cPJy8vjiAEDODHK370Rw4eTnp5OcnIyV119Ne3Dv3tr167l8cceY+7cuZgZV1x5JZ07d66Mw6i6KqdEcAHBZ7l8LYHMop3MbE9gNDDQ3bPzl7t7ZvjvUjN7m6DkMKYASyWCf94Gd+/m7l0ILqo7ErittBXcPfPPBibhbCcPAce6eyfgb8BD4YslJmZWWqDdALgo/0EsxxBlv12BIcDp7t4Z6Ar8/ic21Y3g/G+Pc4G33D03StsC4KZS1j3N3fcChgEPRix/nohzVdXl5uYydNiT/OfOOxg5/EnGT5jI3HnzCvVJz8ggc2EmT40exeWXXcqQIUMByMrK4t333mfw448x4slh5OXmMX7ChMo4jCotNzeXwU+O4J47bmX0sMF8PuEL5s6bX6jPTjvV4+J/n8/xEYFVWdeVwIJn3+Lbo88vsT1twMHUbd+G8Z37M33QLXQdcnvQkJBAlydu5dtjzmfCnkfR/OSjqde5XcUMuprJzc1lxLAnuO3Oexky/Cm+mDCOefP+KNTnu4xvWbRwAcNHP8fFl13Fk0MeByApKYm77n2Yx4eO4rEhI/k+I51ZM3+KshfpvW8jWjWvw8n//pYHh87mmkEdova75qIO3PnQTM65/Ds+m7CUs05qDcDLby/gnMu/45zLv2PEs3OYOmOlgqsIubm5DBs6lDvvuovhI0YwYfx45s2dW6hPRno6CzMzGf3f/3LZZZcxZMiQgrYRw4ezb/fujBw1iiFDh9KqVauiu5DKkQ50MLNdzawmcDLwXmQHM9sFeAs4w91nRyyva2Y75d8H+gMzYh2QAqw4cPelwAXAJRZoY2ZfmNn34W1/gHB5oSfNzBLM7BczS4t4/KuZpRbZzTXAPe4+J9znHOBe4NpwvfFm9lg49eQMM+sZLq9rZk+ZWbqZTTGzY8PlZ5vZ62b2PkHdaT0zGxuOd3p+P+A+oF04deWDkccQbuMtM/skPIYHIo7rPDObHY5rlJltfYfa6jrgbnefGR7TlohMWetwPD+E/+4SLj8hPL5pZjYx/I90J3BSOMaTzKxPeH9qeMw7Rdn3acC7JTyl04BVZnZ4Ce35JlG4xvc94JQS+lY5s2bPplnz5jRr1oykpCT6HHwwkyZNLtRn0uTJ9Ot3KGZG506dWLtuHdnLlwPBH6rNmzeTm5vLpk2bSElJqYzDqNJmzf6F5s2a0axpU5KSkuh78IF8PfmbQn0aNmjAbh07UCMxcbvXlcDyLzPIWb6qxPYmf+vHwhfeAWDlN9NIqr8zyU3TaNBzT9b/NpcNcxbgOTlkvvohTY7pV0Gjrl5+mT2Tps1b0LRZc5KSkjjo4EP4dtLXhfp8O/krDunXHzNjt067s27dWpYvz8bMqF27NgC5W7aQm7uF6BU9clDvFD4ZtxiAH2etoV7dGqQ0LF4Z4A516wTvGXXrJJKVvblYn8P6pPG/iUvLd8DVzOzZs2ke8Xfv4D59mDS58N+9yZMn069fP8yMTp07s27tWpYvX876deuYMWMGRxxxBBB8cVCvXr3KOIwqzbFyuZW6T/ctwCXAp8DPwGvu/qOZXWhmF4bdbgVSgGFFpmNvAnxpZtOAb4EP3f2TWM+DSgTjxN1/N7MEoDGwFDjc3TeaWQfgZaB7CevlmdkLBB/4HwMOA6ZFmSqyC0EGK1IGcHHE47ruvr+ZHQw8RZARugkY5+7nhuV+34albAD7AXu6+/Iwi/V3d18dBneTzew94Hqgq7t3gyBILDKGbsDewCZglpkNBnKBW4B9gDXAOIKgpaiuwMPRzgtBZus5d3/WzM4FngCOI/gPcoS7LzSzBu6+2cxuBbq7+yXhGN8HLnb3r8ysHkE5X4EwKGvr7n+UsG+A/4S3z0rpMwB4J/9BOPVnspmlRKaeq6rs7GzSUrfG8ampqcyaNatwn6xs0tLSCh6npaaSnZVNx44dOP4f/+CMs84muWZN9tlnH/bdZ58KG3t1kZW9nLS0yHOcwsxZv5T7ulJYreZN2LBgccHjjQsXU6tFkyjLl9CgZ8xFATuk7OwsUlO3vhekpKYxe9bPhftkZZEa8X6RmppGdlYWjRqlkJuby9WXD2JR5kKOPPpYduuksqpoUlOSWZq1qeDx0uxNpKbUJHtF4QDqvsGzefC2Pdi0OY9167fw72umFGpPTk6g1z6NeGT4rxUy7uqi+Gu0+N+9rCh/G7OyskhMTKR+/fo8+sgj/P7777Tv0IELL7yQWrVqVdj4qwOvnBJBwstEPiqybHjE/fOBYqUO4cyDexVdHitlsOIrP8ROAkaZ2XTgdWD3baz3FHBmeP9c4OkStl30gr2iy14GCC/M2zkMqPoD15vZVGA8UAvYJez/mbsvj9jWPWb2A/A/gsxMk22MG2Csu69y940E02G2JqhdneDuy909h+AcbK/9gJfC+8+z9WLEr4BnzOxfQGK0FcM+j5jZZUCD8JuNSKnAytJ27u5fAJjZQVGaXzSzBcD/AYOLtC0Fmpe27arCvfj1n0V/y8+jXCNqBmvWrGHS5Mk88/RTvPjC82zcuJGx48aV11CrrZLOX3mvK4VZlBPn7tFPaJT/F0LUy8WLntdoZy6/T2JiIo8NGcl/n3uV2bNnMvePOeUwyOov6n/xKCf2pGNbcO0d0/nHOZP56H+LufT8wqWtB/RIYfrPq1UeWETU12ixTtHee43c3Fx+/fVXjjzqKIYMHUqtWrV47bXXymOYsgNQgBUnZtaWIHOzFLgSWEIQEXcnmJSiRO4+H1hiZocS/OjZx1G6/UjxLNg+RMzxT/H3Did47/hneL1YN3ffxd3zv3ZcF9H3NCAN2DfMVi0hCMa2ZVPE/VyCrGhZPwb+COxbxr4O4O4XAjcTXMw41cyK1aW5+30E31LUJsjEdSrSZQNlO7a7iX4t1mnArgQB4NAibbXC7RdiEdOLvvzKK2XYdflLTU1lWdbWRGlW+E1zsT7LlhU8XpaVRaOUFKZMnUqTpk1oUL8+NWrU4IAD9ufnnwt/my2QlpLCsmWR5ziblEaNyn1dKWzDwsXUbtm04HGtFk3ZlLmUjcWWN2FjpkqqoklJTSUra+t7QXbWsqjvF1kR7xdZWctoVKR0uF69euyxRze+/y69fAdcjfzjyOY8/fi+PP34vmQt30zj1OSCtsYpyWQtL5y9arBzEu13rcdPs9cAMO7LZXTttHOhPocd3FjlgVEUf41mFXuNRvvbmJKSQmpqKqmpqXTqFHykOPDAA/ntV2UIi7GE8rlVM9VvxFVQeP3UcGCIB2mB+sCicEbBMyg50xJpNPACQd1otIkXHgJuyC/RC/+9kcIldieFbQcCq9x9FUE96qUWfo1oZnuXsP/6wFJ3z7FgCsvW4fI1QLRrmErzLdDHzBqGpYclTX32IHCjmXUMx5ZgZleFbV8TXKQIQUDzZdinnbt/4+63AlkEgVahMYZ9prv7/QRllIUCrHCWv0QzKzXIcvcxQEOipI7DzNzNQG8z6xzu14CmwB9R+o909+7u3v2Uk08u2lwpduvYkczMhSxevJicnBwmTJxI7969CvXp3asXY8eOw935eeZM6tatS0qjRjROS2PmzFls3LgRd2fq1Gm62DeK3Tp2YGHmIhYtXkJOTg7jJ37Jfr16lvu6UtjS98fR4vTjAGjQay+2rF7DpsXLWJU+nbrt21C7TUssKYnmJx3Fkg+UiY2mQ8dOLMpcyJLFi8jJyeGLiZ/Ts/f+hfr07LU/n48dg7sza+ZP1K1bl0aNUli1aiVr1wYz4W3atIlpU7+jZUu9X+R766PMgokpvpicxYBDg6C/y247sXb9lmLlgWvW5lC3bg1aNQ+ua+verSFzF6wvaK9bJ5FuXevzxeSiVxpIx44dyczMLPi7N3HCBHr37l2oT6/evRk7dizuzsyffw5fx41o1KgRaWlpLFiwAICpU6eyyy67RNuNiK7BikHtsOwuf5r254FHwrZhwJtmdgLBlN/rom6hsPcISgOjlQfi7lPN7P+A980siWCa9uvypwgPrTCzr4GdCUoNIZgC/THghzAA+AOINjX8i+G2M4CpQP7EE9lm9lU4scXHFM/YRBvrQjO7B/iGYJrMn4BiV6C7+w9mdgXwspnVIchSfRg2XwY8ZWbXAsuAc8LlD4bXtRkwluDarnlsLYO8FzgwDBJzw31HywiOISg7/F+Utkh3U8JkGO6+wcweJpiA5DyCbNzkKCWJVVJiYiIXDRrETTffQl5eHv37H06b1q358MOghPmoo46kZ48epKdncO555wfT1V55JQCdOnXioAMP4JLLLicxMZF2bdsycODAyjycKikxMZFLLvwXN9x6B3l5uRxx+GG0ab0L738UXD97zJEDWL5iBRdfcQ3r16/HEoy33n2f0U8Opm6dOlHXleK6Pf8wKX16UjO1IYfOmcAvdw7GkoI/b/NGvsLSjyeQNrAPfWd+Ru6GDfxw/o0AeG4uMy6/k54fjsYSE1nwzJus/UnfSEeTmJjIBYMu5fab/4+8vDz69R/ILq3b8PGH7wMw8Khj2LdHLzLSv+HC884gObkWl155LQArlmfz2MMPkJeXi7tzwEF96NFrv8o8nCprUsZy9uveiFdH9iyYpj3fg7d15b7Bs8levpkHBs/iPzfsjjusWbuFeyP6HbxfKt9OWcHGTSX+asxfVmJiIoMGDeLmm28mLzeX/v3707p1az78MPjocdRRR9GjRw/S09M579xzSa5ViyvDv3sAFw4axAMPPMCWnByaNmtWqE0Crlp2ACzadRhS8cysO/Cou0e75qcs648n+F2tjG31rQhmVs/d14YZrLeBp9z97coeV74wk3eVu58Rx20+Drzn7mNL6zfnt1/1n66cJeblVPYQdnjTdz+usofwl9BuZqlvJxIH51/xW2UPYYf37OPKWJa3dm3bVonIZsW0CeXyGafhXn2qxPGVlTJYVYCZXQ8MIiiF21HcbmaHEVyTNIaI2faqAnefYmafm1liCSWZf8aMbQVXIiIiIjuqyppFsKpRgFUFhJMy3BfjNvrGZzTx4e7XVPYYtsXdn4rz9kbFc3siIiIi1YpKBAFNciEiIiIiIhI3ymCJiIiIiEjMVCIY0FkQERERERGJE2WwREREREQkZo6uwQIFWCIiIiIiEgcqEQzoLIiIiIiIiMSJMlgiIiIiIhI7TdMOKIMlIiIiIiISN8pgiYiIiIhIzFy5G0ABloiIiIiIxIGrRBBQiaCIiIiIiEjcKIMlIiIiIiIx0zTtAZ0FERERERGROFEGS0REREREYuboGixQBktERERERCRulMESEREREZGY6RqsgAIsERERERGJmaZpDyjMFBERERERiRNlsEREREREJGaa5CKgDJaIiIiIiEicKIMlIiIiIiIx0yQXAQVYIiIiIiISM5UIBhRmioiIiIiIxIkyWCIiIiIiEjOVCAZ0FkREREREROJEGSwREREREYmZrsEKKMASEREREZGYqUQwoLMgIiIiIiISJ8pgiYiIiIhIzFQiGFAGS0REREREJE6UwRKpYL+ubVXZQ9jh7Vovs7KHsMNrN3NsZQ/hL+G3Tv0qewg7vLu+n1rZQ9jhbfbllT0EqSBuymCBMlgiIiIiIiJxowyWiIiIiIjEzF0ZLFCAJSIiIiIiceAqjgNUIigiIiIiIhI3ymCJiIiIiEjMNE17QBksERERERGROFEGS0REREREYqYMVkABloiIiIiIxEwBVkAlgiIiIiIiInGiDJaIiIiIiMRMGayAMlgiIiIiIiJxogBLRERERERi5m7lctsWMxtgZrPM7Fczuz5Ku5nZE2H7D2a2T1nX/TMUYImIiIiISMwcK5dbacwsERgKDAR2B04xs92LdBsIdAhvFwBPbse6200BloiIiIiIVFc9gV/d/Xd33wy8AhxbpM+xwHMemAw0MLNmZVx3uynAEhERERGRmJVXBsvMLjCzjIjbBRG7bQHMj3i8IFxGGfqUZd3tplkERURERESkynL3kcDIEpqj1RB6GfuUZd3tpgBLRERERERiVknTtC8AWkU8bglklrFPzTKsu91UIigiIiIiItVVOtDBzHY1s5rAycB7Rfq8B5wZzibYG1jl7ovKuO52UwZLRERERERiVpYp1eO/T99iZpcAnwKJwFPu/qOZXRi2Dwc+Ao4EfgXWA+eUtm6sY1KAJSIiIiIiMcurnBJB3P0jgiAqctnwiPsOXFzWdWOlEkEREREREZE4UQZLRERERERiVkmTXFQ5ymCJiIiIiIjEiTJYIiIiIiISs8qY5KIqUoAlIiIiIiIxU4lgQCWCIiIiIiIicaIMloiIiIiIxEwlggFlsEREREREROJEGSwREREREYmZrsEKKMASEREREZGYqUQwoBJBERERERGRONlmBsvMcoHpQBKwBXgWeMzd80pZpznwhLsfb2Z9gWvc/eiyDMjMzgYeBBZGLD7V3X8qy/rxZGZr3b1ekePpBjR3948qejxlZWbvAo3dfb8y9C04tjjs93Zgrbs/tK3lZvYH0N3ds/7EfsYTvKYyzOxGd78nXN4G+MDdu5ZhG1cAy939OTN7JlzvjXDb9dy9e9ivO/CQu/cNX8vvAr8DtcN1rgn7HQ30cPfbtvd4KpO788bT9/PjlC+omVyLMy66i1Ztdy/Wb8InL/P5hy+QtWQ+942eQL2dGwIw+8d0Rj5wOSmNWwDQrVc/Bh5/YYUeQ1WXkZHByBFPkpeXR/8jBnDiiScVand3Rox4koz0dJKTk7nyqqtp374DAOecfSa1a9chITGBxIREHn9icGUcQpX3fca3jBoxlLy8PA4/4kiOP/GUQu3uzqgRQ/ku/RuSk5O5/KrraNe+I5s3b+bG664gJyeH3Nxc9j/wYE49/ezKOYgqbs9R99D4yL5sXprNxL2Pidpn90dvovGAPuRu2Mi0865n9ZTgz3Za/4PY/ZGbsMQE5j/1Or89OKoih16tuDuvPfUAM6Z8Sc2atTjrkjvZpW3nYv0+//gVxn34IssWz+ehpz4veE+e+u3nvP/KMCzBSEiowYnnXEv7zntX9GFUad9nfMvoEUMK3i/+eeKphdrdndEjhoTvF7W4LHy/WLZsKY8/fB8rVyzHzOg/4GiOOe6flXQUVVeJwcFfTFlKBDe4ezcAM2sMvATUB0r8IOnumUAsH9hfdfdLYlg/roocTzegO1DmAMvMDLDSgtJ4MbMGwD7AWjPb1d3nlNY/Ds9VZbsRuGd7VjCzGsC5BOcpmsZmNtDdP47S9oW7H21mtYEpZva2u38FfAjcZWb3u/v67RlPZfppypcsWzyX2574gD9++YFXRv+Ha+95qVi/trt1o+s+B/P4HecVa2vXeR8GXT+kIoZb7eTm5vLksKH85+57SE1N5corLqN3797sskvrgj4ZGelkLsxk1OinmDVrJkOHDOHRxx4vaL/3vvupX79+ZQy/WsjNzWXEsCe44+4HSElN45orLqJn7/3YZZc2BX2+y/iWRQsXMHz0c8ye9TNPDnmchx4bSlJSEnfd+zC1a9dmy5YtXH/N5ezbvSe7dSr+JcNf3YJn3+KPYS/Q7an7o7anDTiYuu3bML5zfxr02ouuQ27n6wNOhIQEujxxK98MPIeNC5Zw4OQ3WPLBONb+/FsFH0H1MGPKlyxdNI87B7/HnF+m89LIu7n+vheK9Wu3Wzf22PcgHrnt/ELLO+3Ri7169MXMWPDHbEY9ch13PPFOBY2+6gveLx7njrsfJCU1jWuvGETP3vvTqtD7xTcsWriQJ0c/z+xZPzN8yGM8+NgwEhMTOef8C2nXviMb1q/n6ssupNs++xZaVyTfdpUIuvtS4ALgEgu0MbMvzOz78LY/BJkEM5sRua6ZJZjZL2aWFvH4VzNLLcu+zezvZva/cL/NzGy2mTU1s7PN7F0z+8TMZpnZbRHrnG5m35rZVDMbYWaJ4fK1Zna3mU0zs8lm1iRcvquZTTKzdDO7K2I7bcxshpnVBO4ETgq3eZKZ3W5m10T0nRH2b2NmP5vZMOB7oJWZXRtu+wczu6OE4zzFzKaH27k/YnnUMUfxT+B94BXg5Ij1nzGzJ8zsazP73cyOL/pchefyHTN738zmmNklZnaVmU0J99ko7Pev8DimmdmbZlanLM9hSUp5np40swwz+zHa+TKz+4Da4XovhosTzWxUuM6YMBAq6lDge3ffUsKQHgRuLm3M7r4BmAq0CB87MB4oU6a2qvgh43N6HnwMZsauHfdiw7o1rFqxrFi/Vrt2LshSSdnNnj2L5s2b0axZM5KSkjj44D5MnjSpUJ/JkydxaL9+mBmdOnVm3bq1LF+eXUkjrn5+mT2Tps1b0LRZc5KSkjjo4EP4dtLXhfp8O/krDunXHzNjt067F5xjM6N27eAtInfLFnJzt4Au0I5q+ZcZ5CxfVWJ7k7/1Y+EL7wCw8ptpJNXfmeSmaTTouSfrf5vLhjkL8JwcMl/9kCbH9KugUVc/P6SPp3ffozEz2nbckw3ro78n79K2E6lR3pNr1a5D8J0ubN60oeC+BH6ZPZNmEe8XBx58KN8Ue7/4mr79Di/2ftGoUQrt2ncEoHadOrTcZReys7a7CGeH527lcqtutvsaLHf/PVyvMbAUONzd9wFOAp4oZb084AXgtHDRYcC0EkrE8gOY/Fttd38bWAxcDIwCbnP3xWH/nuF2uwEnmFl3M+scjumAMAOXG7HvusBkd98LmAj8K1z+OPCku/cI91X0GDYDtxJk2Lq5+6ulnStgN+A5d987vN8hHGs3YF8zOziyswXlevcTBADdgB5mdtw2xlzUKcDL4e2UIm3NgAMJgoD7Sli/K3BqOM67gfXh+CcBZ4Z93nL3HuFYfgaKpzWKuzLyOQWah8dc2vN0U1iqtyfQx8z2jNygu19PmGF19/x1OgBD3b0LsJIg4CzqAOC7UsY6CdhkZoeU1MHMGob7mhixOAM4qJTtVjkrly+lYWrTgscNUpqwcvnS7drGnNnTuPfa4xl2zyAWzf813kOs1rKzs0lNTSt4nJqaSnZ24eApOyubtLTIPmlkZwV9zIxbbr6Ryy67hI8/rrJVyZUqOzur0DlOSU0jO7vwn5XsrCxSi53joE9ubi5XXHIBZ576T7rtvS+7dSpejiXbVqt5EzYs2Ppnc+PCxdRq0STK8iXUalHS94OyMnspDVMi3pMbNWFl9va9J0/5Zhy3XXYcQ+69lDMvuj3OI6zelmdnkZrauOBxSmoqy7MLB7DLs7JITYvsk8byIoHUkiWL+f23X+mo9wspwZ+d5CI/lEwCRpnZdOB1YFt1FU+x9UP6ucDTJfTLD2DybxvC5ZcCNwCb3P3liP6fuXt22O8tgiCiH7AvkB5+oO8HtA37bwY+CO9/B7QJ7x9AEJgAPL+NYymLue4+ObzfP7xNIchodSL4gB6pBzDe3ZeF2ZUXgfwgrKQxFwizWu2BL919NrDFzCKvR3rH3fPC69lK+gv3ubuvcfdlwCqCbBgE1+Hl77OrBZnL6QTBUJdSzkG+RyOfUyAzXF7a83SimX1PcM66sO3XF8Acd58a3o96nggCzeJfCRb2H6JnsQ4ysx8IAvAPIoJ8CL5waB5tY2Z2QZiNy/jwjdHb2HUFci+2aHu+8Wy1a2fuGvYpNzz4Bn0GnMrIB6+I4+CqP49yfilyfp2S+zz40CM8MXgod975Hz784H1mTJ9eHsOs3qKevqLnuOQ+iYmJPDZkJP997lVmz57J3D9KraqWEkR733D3Yq/3sKECRlQ9lfZ+UFZ79zqUO554h0HXPcp7rwyL08h2DLG+JwNs2LCB++++jfMuuIg6derGe4jVnmPlcqtutnuadjNrS5BlWEpwHdYSYC+CYG1jaeu6+3wzW2JmhwK92JqpKKsWBNfPNTGzhIhrmor+b3CCIPBZd78hynZyfOv/slwKn4ftfeffQuFAtVbE/XUR9w24191HlLKt0l5BpY0530lAQ2BO+MduZ4IywfxAYVMZ9hXZJy/icV7EPp8BjnP3aRZMStK3lHFvS9Tnycx2Ba4hmDhihQUTUdSKsn5RkePPJZiMoqgN29qWu48Ly0R7F2nKvwarI/ClBddgTQ3baoXbjra9kcBIgM+mbarUTxcTPnmFr8e+CUDrdl1YkbU1RlyZvYT6DdNKWrWY2nXqFdzvss9BvPrfu1m7ekXBBdd/dampqWRlbY3ls7KySGnUqFifZcsi+ywjJSXok5KSAkCDBg3Yb7/9mTV7Fl332KMCRl59pBQ5x9lZy2jUKKVQn9TUVLKKnONGKYX71KtXjz326Mb336XTus2u5TvoHdCGhYup3bIpK8LHtVo0ZVPmUhJqJlG75daMTK0WTdiYuX0ZmR3d+I9f4cuxbwHhe3J2xHvy8iU0aFT29+RIHXbfl2VL5us9OUJKahpZWVtff9lZWTRqlFq8z7LIPlvfL7Zs2cL9d99Gn76Hsd8BhYqQJFQdy/nKw3ZlsCy4fmo4MCT8sF8fWBQGOmcAiWXYzGiCUsHX3D13O/ZdgyDjdSpBWdpVEc2Hm1mj8Hqb44CvgLHA8RZMzEHY3prSfcXW65ZKCv7WADtFPP6DcLIEM9sHKOkv86fAuWZWL+zbIn9sEb4hKIVLDa9DOgWYsI0xRzoFGODubdy9DUFm6OTSV/lTdgIWmVkS2x8kF1XS87QzQYC6KszMDSxh/ZxwHNvjZ4JM37bcDVwXrSHMEN4L/F/E4o7AjGj9q5I+A07mhgdf54YHX2fPnofy7cT3cXfmzJ5G7To7bVeAtXplVsE3gn/8Oh3Py6PuTg3KaeTVT8eOu7EwM5PFixeTk5PDxIkT6NW7cMzeq1dvxo0di7szc+bP1K1bl0aNUti4cSPr1wfzpWzcuJHvp3xP69ZtKuEoqrYOHTuxKHMhSxYvIicnhy8mfk7P3vsX6tOz1/58PnYM7s6smT8VnONVq1aydu1aADZt2sS0qd/RsmWryjiMam/p++NocfpxADTotRdbVq9h0+JlrEqfTt32bajdpiWWlETzk45iyQfjKnewVUzfgSdz80OvcfNDr9Gt5yFMHv8B7s7vs3+gVp162/WevHTRvIL35Hm//8yWLTl6T45Q9P3iy4nj6Nm78ITLPXvtz/ixnxV7v3B3hjz2IC1b7cKx/zihko5AqouyZLBqh6Vb+dO0Pw88ErYNA940sxOAzymcsSnJewSBUknlgRBcg3VgxOOLCK7Z+sLdvwjHk25mH4btX4bjag+85O4ZAGZ2MzDGzBKAHILrt+aWst/LgZfM7HLgzRL6fA5cH47h3rDfmfljAmZHW8ndx4TXG00Ks0trgdMJMoH5fRaZ2Q3hPgz4yN3fLWW8BSyYonwXIL8kEXefY2arzaxXWbaxHW4hCAbnEpQO7lR695K5+0/Rnid3n2xmU4AfCaZF/6qETYwEfghLCW8q424/pgwloO7+kZmVVko4HLjGts7WeAhBCWu10WXvg/jx+y+447KjSKpZi9MvKpjbhWH3XsSp/76dBo0aM/6jF/nfe0+zemU291x7PF32PpDTLryDKZM/44sxr5GYmEhSzWTOueIBXVQdITExkUGDLuKWm28KpgTu35/Wrdvw0YfBW9eRRx1Fjx49yUhP5/zzzg2mab8y+O5oxYoV3P2fO4HgOqE+fQ+he/fulXYsVVViYiIXDLqU22/+P/Ly8ujXfyC7tG7Dxx8G1c0DjzqGfXv0IiP9Gy487wySk2tx6ZXXArBieTaPPfwAeXm5uDsHHNSHHr22+esWf0ndnn+YlD49qZnakEPnTOCXOwdjScFHiHkjX2HpxxNIG9iHvjM/I3fDBn44/0YAPDeXGZffSc8PR2OJiSx45k3W/qRrNUvSdZ+DmPH9l9xyyTHUTK7FWRdtnd9p8N0Xc8ag22jQqDHjPnyJMe8+w+qV2dx19Yl03edAzhh0G1Mmj2XyhPdJrFGDpJq1+NeVek+OlJiYyL8GXcodN/8fuXm5HNZ/ILu03pVPPnwPgAFH/Y19e/Tiu/RvuPC804Np2q8Mvmf9+acZjB/3Ga3btOWKS4LL4E8/6zy69yha6PLXVh3L+cqDRa1HLc8dBr8r9Ki7x2UygLBErXtVmtZdqj4zexu4zt1/idP2mhAE99ucHquySwT/Cnatl7ntThKTLWxv4lj+jN86aca98lbn+6mVPYQdXtM6yyt7CDu8zu1aVInI5suf1pXLZ5wDd69bJY6vrLb7GqxYmNn1wCBiLysTidX1BJNdxCXAIsgeXh2nbYmIiIhUO3n6Chmo4ADL3e+j5OnB/+w2nyGYdEGkzNx9FjArjttLj9e2RERERKojlQgG/uw07SIiIiIiIlJEhWawRERERERkx6Rp2gPKYImIiIiIiMSJMlgiIiIiIhKzCp6cvMpSgCUiIiIiIjHL0yQXgEoERURERERE4kYZLBERERERiZkmuQgogyUiIiIiIhInymCJiIiIiEjMNMlFQBksERERERGROFEGS0REREREYuaaRRBQgCUiIiIiInGQpxJBQCWCIiIiIiIicaMMloiIiIiIxEzTtAeUwRIREREREYkTZbBERERERCRmmqY9oABLRERERERilqdZBAGVCIqIiIiIiMSNMlgiIiIiIhIzlQgGlMESERERERGJE2WwREREREQkZpqmPaAAS0REREREYpanEkFAJYIiIiIiIiJxowyWiIiIiIjETJNcBJTBEhERERERiRNlsEREREREJGauHxoGlMESERERERGJGwVYIiIiIiISszwvn1sszKyRmX1mZr+E/zaM0qeVmX1uZj+b2Y9mdnlE2+1mttDMpoa3I7e1TwVYIiIiIiISM/fyucXoemCsu3cAxoaPi9oCXO3unYHewMVmtntE+6Pu3i28fbStHeoaLJEKdtCcEZU9hB3ekq5HVPYQdnhnXzmvsofwl3DX91Mrewg7vPX7dKvsIezwmmaMrOwh/AW0qOwBVGXHAn3D+88C44H/i+zg7ouAReH9NWb2M8FJ/enP7FAZLBERERERiVkVzWA1CQOo/ECqcWmdzawNsDfwTcTiS8zsBzN7KlqJYVEKsEREREREpMoyswvMLCPidkGR9v+Z2Ywot2O3cz/1gDeBK9x9dbj4SaAd0I0gy/XwtrajEkEREREREYlZnpfPNO3uPhIosdbU3Q8rqc3MlphZM3dfZGbNgKUl9EsiCK5edPe3Ira9JKLPKOCDbY1XGSwREREREYlZFS0RfA84K7x/FvBu0Q5mZsB/gZ/d/ZEibc0iHv4dmLGtHSrAEhERERGRHdV9wOFm9gtwePgYM2tuZvkzAh4AnAEcGmU69gfMbLqZ/QAcAly5rR2qRFBERERERGIWh2xT3Ll7NtAvyvJM4Mjw/pdA1PpGdz9je/epDJaIiIiIiEicKIMlIiIiIiIxy6uCGazKoABLRERERERi5uU0i2B1oxJBERERERGROFEGS0REREREYlYVJ7moDMpgiYiIiIiIxIkyWCIiIiIiEjNNchFQgCUiIiIiIjFTiWBAJYIiIiIiIiJxogyWiIiIiIjETBmsgDJYIiIiIiIicaIMloiIiIiIxEyTXASUwRIREREREYkTZbBERERERCRmugYroABLRERERERilpdX2SOoGlQiKCIiIiIiEifKYImIiIiISMxUIhhQBktERERERCROlMESEREREZGYKYMVUIAlIiIiIiIx0+9gBVQiKCIiIiIiEifKYImIiIiISMy83GoErZy2Wz6UwRIREREREYkTZbBERERERCRmmuQioABLRERERERilpdX2SOoGhRgVTIzywWmExSX5gKXuPvX21hnrbvXq4jxFdnvH8B8dz8oYtlUoIa7d63o8cSTmbUBfgZmArWANcBQd3+2MsdV3r6aNZf73/uSPM/j7z1257xD9o3ab8b8JZwx9E0eOLU/h+/Znk05Wzhn+Nvk5OayJTePw/dox0X9e1Xw6KuH9IzveHLkaPLychnQvz8nn3h8oXZ3Z9iIUaRnZJCcnMw1V15Bh/btAHj73ff46NMx4M7AI/rzj+OOrYxDqBYuv6Ad++2bwsZNudzz+Cxm/7a2WJ9992zARee2JcGMDRtzufuxmSxctJFT/t6S/n2bAJCYaLRuWYejT/+aNWu3VPRhVGnuzmtPPcCMKV9Ss2YtzrrkTnZp27lYv88/foVxH77IssXzeeipz6m3c0MApn77Oe+/MgxLMBISanDiOdfSvvPeFX0YVdaeo+6h8ZF92bw0m4l7HxO1z+6P3kTjAX3I3bCRaeddz+opPwGQ1v8gdn/kJiwxgflPvc5vD46qyKFXK5OmzuDRp18lLy+Pv/U7kDOPG1io/ZMvvuH5dz8BoE6tZK47/zQ6tGkFwH+GPcNX30+nYf2deOnh2yt66FKN6BqsyrfB3bu5+17ADcC9lT2gbdjJzFoBmFnxv6zVhJlF+3LhN3ff2907AycDV5rZORU8tAqTm5fHPe9MZNi5R/P2VafyybRf+G3J8qj9Hvt4Evt3bFWwrGaNREZfcCyvX3Eyr11xEl/NnscPcxdX5PCrhdzcXIY8OYK777iNUU8OZfzEicydN69Qn/SM71iYmcnTo0ZwxaUX88TQJwGY88dcPvp0DIMfeZjhQ57gm28zWLgwszIOo8rrvW8jWjWvw8n//pYHh87mmkEdova75qIO3PnQTM65/Ds+m7CUs05qDcDLby/gnMu/45zLv2PEs3OYOmOlgqsoZkz5kqWL5nHn4Pc47cJbeGnk3VH7tdutG5ffOpxGac0KLe+0Ry9ufvg1bn7oNc686Haef/KOihh2tbHg2bf49ujzS2xPG3Awddu3YXzn/kwfdAtdh9weNCQk0OWJW/n2mPOZsOdRND/5aOp1blcxg65mcvPyeOi/L/HojZfx8qN3MOardOYsKPy+2rxxKk/efg0vPnQb5/zzKO4d+XxB21F99+fRGy+r6GFXK+7lc6tuFGBVLTsDKwDMrJ6ZjTWz781supkV++q6pD5m1sbMfjazUWb2o5mNMbPaYVt7M/ufmU0L12sXLr/WzNLN7AczK+2v3mvASeH9U4CXI8ZTy8yeDscyxcwOCZefbWZvmdknZvaLmT0QsU5/M5sUjuX18Jj6mdnbEX0ON7O3ohz/H2Z2v5l9G97ah8vTzOzN8HjSzeyAcPntZjbSzMYAz5X2RLj778BVwGXhuj3N7OvwuL42s93C5V+YWbeIMX1lZnuWtu2qYsb8pbRKqU/LlPok1UhkwF4dGP/TnGL9Xv5qOod1bUejenUKlpkZdZJrArAlN48tuXnVbYKfCjFr9i80b96MZs2akpSURJ+DD+Lryd8U6vP15G84/NBDMDM6d+rEunXryF6+nPnz59N5t92oVSuZxMRE9tijC19NmlRJR1K1HdQ7hU/GBQH+j7PWUK9uDVIa1izWzx3q1kkEgn+zsjcX63NYnzT+N3Fp+Q64mvohfTy9+x6NmdG2455sWL+GVSuWFeu3S9tOpDZuUWx5rdp1MAveKDZv2lBwXwLLv8wgZ/mqEtub/K0fC194B4CV30wjqf7OJDdNo0HPPVn/21w2zFmA5+SQ+eqHNDmmXwWNunr56dc5tGzamBZN0kiqUYPD9+/BxPRphfrsuVs7dq5XF4CuHdqyLHtlQdveu3csaBMpjQKsylfbzKaa2UxgNHBXuHwj8Hd33wc4BHjYiv81Kq1PB4ISty7ASuCf4fIXw+V7AfsDi8ysf9i/J9AN2NfMDi5hvG8A/wjvHwO8H9F2MYC770EQfD1rZrXCtm4EgdkewElm1srMUoGbgcPCY8ggCGrGAZ3NLC1c9xzg6RLGs9rdewJDgMfCZY8Dj7p7j/C4R0f03xc41t1PLWF7kb4HOoX3ZwIHu/vewK3APeHy0cDZAGbWEUh29x/KsO1Kt3TVWpo22Fpp2rh+PZasWleoz5JVaxn34++c0LtLsfVz8/I48bFXOOSup+jdoRV77tK03Mdc3WRlZ5OWmlrwOC01lezs7EJ9srOzSUtLK3icmppCdnY2bVq3ZvqMH1m9ejUbN24iPeM7li3LqrCxVyepKckszdpU8Hhp9iZSU4oHWPcNns2Dt+3BW0/35ohDmvDCG4WzicnJCfTapxHjv9Z5jmZl9lIapmz9f96gURNWZm9fMDrlm3HcdtlxDLn3Us686PY4j3DHVqt5EzYs2FopsHHhYmq1aBJl+RJqtWhSGUOs8pYtX0njlEYFjxunNGDZ8hUl9n9/3Ff03rtaXwFR4fK8fG7Vja7Bqnwb3L0bgJntBzxnZl0J8gH3hIFOHtACaAJE1mGV1AdgjrtPDe9/B7Qxs52AFu7+NoC7bwz32x/oD0wJ+9cjCLgmRhnvcmCFmZ1McM3S+oi2A4HB4bZnmtlcoGPYNtbdV4X7+wloDTQAdge+CuPCmsAkd3czex443cyeBvYDzizh/L0c8e+j4f3DgN0j4tGdw2MHeM/dN5SwraIiA9r6BAFjB8CBpHD568AtZnYtcC7wTBm3XemivV8VDeEffP9Lrhi4H4kJxb+LSUxI4LUrTmb1hk1c+dzH/LI4mw5NU8pnsNVVlLoGK5Lqi176YOyySytOPP4fXH/zrdSqVYu2u+5KQmJi+YyzmouaB4lyXk86tgXX3jGdn2av4ZS/t+TS89tx/+DZBe0H9Ehh+s+rVR5YAo92UrczC7V3r0PZu9eh/PLTd7z3yjCuuG1EnEa344uW8XP36M9BdaypqgBRf6OphNfwdzNm8t7nXzLyzuvKeVSyI1KAVYW4+6Qwq5MGHBn+u6+754QTTNQqsspppfTZFNEvF6hNyUVcBtzr7mX9S/cqMJQwc1NkOyUpOp4aYf/P3P2UKP2fJsiObQRed/eSPvF4lPsJwH5FA6nwj1PhFE3p9iYIIiHILH7u7n8PJ8QYD+Du683sM+BY4ESge7QNmdkFwAUAQwadxHn999+OYZSPJvXrsXjl1okAlq5aS+OdC5c+/LhgKf/38hgAVqzbwBcz55KYmMChXdoW9Nm5djI92jbn61nzFGAVkZqayrKsrdmQZVlZNIr49jTok8KyZVvLrLKyskkJ+ww8oj8Dj+gPwFPPPkdqSioS+MeRzTnmiOAan59/WUPj1OSCtsYpyWQtL1z+12DnJNrvWo+fZq8BYNyXy3jo9j0K9Tns4MYqDyxi/Mev8OXYoEK7dbsurMje+h3fyuVLaNAoraRVS9Vh931ZtmQ+a1evKJgEQ0q3YeFiardsSn6+pVaLpmzKXEpCzSRqt9yaWazVogkbM/U6jqZxSkOWZm+91nhp9krSGjYo1u+XuQu4Z8RzPHrD5dTfqcLnFKvWFNsHVCJYhZhZJyARyCbImCwNA6dDCDI+RZWlTwF3Xw0sMLPjwv0lm1kd4FPgXDOrFy5vYWaNS9nU28AD4XqRJhIEffnlcrsAs0rZzmTggIhrp+qE6+HumUAmQQnhM6Vs46SIf/MvUBkDXJLfIfIaqbIKg6iHCDNyBOd6YXj/7CLdRwNPAOnuXnyWCMDdR7p7d3fvXhWCK4AuLRszL3sVC5avJmdLLp9M+4U+ndsU6vPx9WcW3A7foz03HXcwh3Zpy/K1G1i9IYiZN+ZsYfKvC2jTWB+SitqtYwcWLsxk0eLF5OTkMGHiF+zXq/Bsi/v16sln4z7H3fl55kzq1q1DSqMgwFqxciUAS5cu48uvJ3FIn5Iqd/963voos2Biii8mZzHg0OADZpfddmLt+i1krygcYK1Zm0PdujVo1bw2AN27NWTugq0J+Lp1EunWtT5fTFZ5YKS+A0/m5oeCiSm69TyEyeM/wN35ffYP1KpTj/oNyx5gLV00ryCDMO/3n9myJYe6OzUop5HveJa+P44Wpx8HQINee7Fl9Ro2LV7GqvTp1G3fhtptWmJJSTQ/6SiWfDCucgdbRXVu14b5i5aSuTSLnC1b+OzrdA7qvlehPouzsrnhoSe57ZLz2KW5Si23l+d5udyqG2WwKl9tC6Y6hyCjc5a755rZi8D7ZpYBTCW4BqiosvQp6gxghJndCeQAJ7j7GAtmBJwUZnnWAqcDUb8Cc/c1wP1QrGRhGDDczKYDW4Cz3X1TSRcyu/syMzsbeNnM8r9+vhnIr9l5EUhz959KOZ5kM/uG4MuC/EzYZcBQM/uB4DU+EbiwlG3ka2dmU9g6Tftgd8+/9usBghLB/GvEIo/jOzNbTcnXiVVJNRITuOHYgxj03/fIy3OO69GZ9k1TeG3yDABO7F1y3XnWmnXc/NpY8vKcPHf679m+WHAmkJiYyCWD/s2Nt9xOXl4eRxx+GG1a78IHH30MwNFHDqRnj+58m/EdZ5//73Ca9q0zVN11z32sXr2GGjUSuXTQheykb1KjmpSxnP26N+LVkT0LpmnP9+BtXblv8Gyyl2/mgcGz+M8Nu+MOa9Zu4d6Ifgfvl8q3U1awcZN+xKUkXfc5iBnff8ktlxxDzeRanHXR1vmQBt99MWcMuo0GjRoz7sOXGPPuM6xemc1dV59I130O5IxBtzFl8lgmT3ifxBo1SKpZi39d+YAmuojQ7fmHSenTk5qpDTl0zgR+uXMwlhR8TJs38hWWfjyBtIF96DvzM3I3bOCH828EwHNzmXH5nfT8cDSWmMiCZ95k7U+/VuahVFk1EhO55txTuPzux8jLy+PoQw6gbavmvDVmAgD/6N+H/77xIavWruPB0S8Cwfv4M/fdBMAtj43i+59msXLNWo658Dr+deLf+NuhB1ba8UjVZVHrUUWqADMbAkxx9/+W0P4H0N3dK/UrZzNrTlAy2Mndt/npbOM7T+g/XTlb0vWIyh7CDu+0KzUtf0W4656elT2EHd76fbpV9hB2ePtnjKzsIezwGu7Vp0p8W/HAm+WTbrrunwlV4vjKSiWCUiWZ2XfAnsALlT2W0pjZmcA3wE1lCa5EREREZMemEkGpktx93zL0aVMBQ9nWGJ5jG7+pJSIiIvJXoMK4gAIsERERERGJWV41nJCiPKhEUEREREREJE6UwRIRERERkZipRDCgDJaIiIiIiEicKIMlIiIiIiIxUwYroABLRERERERilqcIC1CJoIiIiIiISNwogyUiIiIiIjHzvMoeQdWgDJaIiIiIiEicKIMlIiIiIiIxc12DBSiDJSIiIiIiEjfKYImIiIiISMzydA0WoABLRERERETiQCWCAZUIioiIiIiIxIkyWCIiIiIiErO8KpjAMrNGwKtAG+AP4ER3XxGl3x/AGiAX2OLu3bdn/UjKYImIiIiIyI7qemCsu3cAxoaPS3KIu3fLD67+xPqAAiwREREREYkDz/NyucXoWODZ8P6zwHHlvb4CLBERERERiZl7+dzM7AIzy4i4XbAdw2ri7ouC8fkioHFJwwfGmNl3RbZf1vUL6BosERERERGpstx9JDCypHYz+x/QNErTTduxmwPcPdPMGgOfmdlMd5+4nUMFFGCJiIiIiEgc5FXSLBfuflhJbWa2xMyaufsiM2sGLC1hG5nhv0vN7G2gJzARKNP6kVQiKCIiIiIiO6r3gLPC+2cB7xbtYGZ1zWyn/PtAf2BGWdcvShksERERERGJWRX9oeH7gNfM7DxgHnACgJk1B0a7+5FAE+BtM4MgPnrJ3T8pbf3SKMASEREREZGYeV5lj6A4d88G+kVZngkcGd7/Hdhre9YvjUoERURERERE4kQZLBERERERiVle1SwRrHDKYImIiIiIiMSJMlgiIiIiIhKzKjrJRYVTBktERERERCROlMESEREREZGYVdYPDVc1CrBERERERCRmqhAMKMASqWBbFi+q7CHs8FZ1aVjZQ9jhPft4UmUP4S9hsy+v7CHs8JpmjKzsIezwvu5+QWUPYYd3VM6syh6CRFCAJSIiIiIiMXOVCAKa5EJERERERCRulMESEREREZGY6YeGAwqwREREREQkZioRDKhEUEREREREJE6UwRIRERERkZgpgxVQBktERERERCROlMESEREREZGYKYEVUIAlIiIiIiIxU4lgQCWCIiIiIiIicaIMloiIiIiIxMz1O1iAMlgiIiIiIiJxowyWiIiIiIjELE/XYAHKYImIiIiIiMSNMlgiIiIiIhIzXYMVUIAlIiIiIiIx0zTtAZUIioiIiIiIxIkyWCIiIiIiEjNlsALKYImIiIiIiMSJMlgiIiIiIhKzPE1yASjAEhERERGROFCJYEAlgiIiIiIiInGiDJaIiIiIiMRMv4MVUAZLREREREQkTpTBEhERERGRmOXpGixAAZaIiIiIiMSBJrkIqERQREREREQkTpTBEhERERGRmGmSi4AyWCIiIiIiInGiDJaIiIiIiMTM8/IqewhVgjJYIiIiIiIicVKpGSwz+zvwFtDZ3WdW5li2xcz+ANaEDxMJxn2Xu2/axnpfu/v+ZtYG+MDdu5Zxf32Bz4Hz3f2/4bK9ge+Ba939ITO7E5jo7v8zs/HANe6eYWZr3b3eNrafC0wneA38DJzl7uvLMrYo2yrY93au1wA41d2HhY+bA0+4+/F/ZhxRtv8GcJ27/x4+f93dPavIc7K/u78Uh33VBP4HHOruW2LdXkX5+o/FPDT+B3LznOO6tuGcnrsVas+Yv4yr3ptEi/p1ATikfXMu6N25oD03zznjpXGk1avN48ftX6Fjry7cnadHPs73GZNJTk7m4itupG373Yr1W7I4k8ceuJ21a9awa/uOXHrVzSQlJfHF52N4580XAahVqw7/uuhq2rRtX9GHUaVlZGQwYvhw8vLyOGLAAE488cRC7e7OiOHDSU9PJzk5mauuvpr27YNzuHbtWh5/7DHmzp2LmXHFlVfSuXPnaLv5y/s+41tGjxhCXl4ehx9xJP888dRC7e7O6BFD+C79G5KTa3HZVdfRrn1Hli1byuMP38fKFcsxM/oPOJpjjvtnJR1F1TZp6gweffpV8vLy+Fu/AznzuIGF2j/54huef/cTAOrUSua680+jQ5tWAPxn2DN89f10GtbfiZcevr2ih15t7DnqHhof2ZfNS7OZuPcxUfvs/uhNNB7Qh9wNG5l23vWsnvITAGn9D2L3R27CEhOY/9Tr/PbgqIocerWgadoDlZ3BOgX4Ejg5Hhszs8R4bKcUh7j7HkBPoC0wclsruHssnzqnAydFPD4ZmBax7Vvd/X9/ctsb3L1bGPBtBi6MbKyAcwnQALgo/4G7Z8YxuOoCJLr770XbIp6TNsCpRdvD9bfrywd33wyMpfDzVaXl5jn3jZvGE8cdwBtnHc6nsxbwe/bqYv32bpHKy6f34+XT+xUKrgBenvIrbRrtVFFDrpamZExmUeYCBo98mX9fch2jhj0ctd+Lzwzn6GNPZPCol6lXdyfGffYBAI2bNuOO+4bw8JBnOf7ksxgx5IGKHH6Vl5uby7ChQ7nzrrsYPmIEE8aPZ97cuYX6ZKSnszAzk9H//S+XXXYZQ4YMKWgbMXw4+3bvzshRoxgydCitWrWq6EOoFnJzcxkx7HFuvfM+Bg9/mi8mjGP+vD8K9fku4xsWLVzIk6Of56LLrmL4kMcASExM5JzzL2TIiGd44JGhfPzBu8XWFcjNy+Oh/77EozdexsuP3sGYr9KZsyCzUJ/mjVN58vZrePGh2zjnn0dx78jnC9qO6rs/j954WUUPu9pZ8OxbfHv0+SW2pw04mLrt2zC+c3+mD7qFrkNuDxoSEujyxK18e8z5TNjzKJqffDT1OrermEFXI+5eLrfqptICLDOrBxwAnEcYYJnZQDN7LaJPXzN7P7zf38wmmdn3ZvZ6uD5m9oeZ3WpmXwInmNm/zCzdzKaZ2ZtmVifs187MJodtd5rZ2oj9XBsu/8HM7tjW2N19LUFAcpyZNTKzemY2NhzbdDM7NmLba4uub2ZfmFm3iMdfmdmeUXY1D6hlZk3MzIABwMcR6z1jZiUGJGaWGp6zo7ZxSF8A7cPz/bmZvQRMN7NaZvZ0eExTzOyQcLu1zeyV8Hy9CtSOdrxmdryZPRPeb2Jmb4fPyzQz2x+4D2hnZlPN7EEza2NmM8L+Je37bDN7y8w+MbNfzKykT5unAe+WcF7yx3gfcFC4/yvDbb8evubGmFldM3sqfG1MyX9ezayLmX0brveDmXUIt/dOuN9q4cfFy2nVoC4tG9QlKTGB/ru1ZPxvi8q8/pI16/lyzmKO69qm/Aa5A0j/5kv6HDoAM6Njpy6sW7eWFcuzCvVxd2b88D29D+wLQJ9+A0if9AUAu3Xeg3r1giC2Q6cuZGctq9DxV3WzZ8+mefPmNGvWjKSkJA7u04dJkycX6jN58mT69euHmdGpc2fWrV3L8uXLWb9uHTNmzOCII44AICkpiXr1Sk3+/2X9MnsmzZq3oGmz5iQlJXHgwYfyzaSvC/X5dvLX9O13OGbGbp12Z926tSxfnk2jRim0a98RgNp16tByl13IzsqKtpu/tJ9+nUPLpo1p0SSNpBo1OHz/HkxMn1aoz567tWPnekFFQdcObVmWvbKgbe/dOxa0ScmWf5lBzvJVJbY3+Vs/Fr7wDgArv5lGUv2dSW6aRoOee7L+t7lsmLMAz8kh89UPaXJMvwoatVQ3lZnBOg74xN1nA8vNbB/gM6C3meW/Q5wEvGpmqcDNwGHuvg+QAVwVsa2N7n6gu78CvOXuPdx9L4LSt/PCPo8Dj7t7D6DgKyEz6w90IMhKdQP2NbODtzV4d18NzAnX3Qj8PRzbIcDDYUBUktHA2eH+OwLJ7v5DCX3fAE4A9icoDyy1JDGfmTUBPgRudfcPS+lXAxhIkC2D4Dzc5O67AxcDhFm7U4BnzawWMAhY7+57AncD+5ZhSE8AE8LnZR/gR+B64Lcwk3Ztkf4l7RuC5+n/27vvOLuqev3jnychEHpJQodQBEGRJoEgqIDKFRVEVIqACAg/FRTQexUsF8UKdlFULAFRURCUdhEQkCK9hCKIIEWRQAhID5Dy/P7Ye8iZYTLJzJyZlbPzvF+v85qz9z6TeWZzOLPXXmt91x7Aa4A9JPV2y3kb4MZ5ZDoSuKL++d+u921NNVxyB+AzwCX1e2Z74Ov1e/NDVO+lTYEtgAfr770dmDCPn7nAmPrM86y09EttY1ZaanEefWb6y15325TH2fOUi/no7//CP6bN6eH65p9v5bDXb8SIPt/q8fhjjzJm7IovbY8ZM47HH+t+cfn0U0+yxJJLMXJk1XE6ZuzLXwNwyYXnstkWWw1t4A7z2LRpjB037qXtsWPH8thjj3V7zbTHHmPc2LHdXjNt2jSmPPwwyy67LN/+1rc49JBD+M53vsPzzz8/bNk7yeOPTWNs6/t47Fgef6x7Y//xadMYO671NeN4vEdD6pFHHubef9zD+htkGGZPjz7+BCuOWeGl7RXHLMejj/9nrq8/55K/MHGz+Zp1EP0wetWVmP7gwy9tP//vhxm92kq97H+E0autVCLiAs2zPSSPTlOygbUX8Jv6+W+Aveq5K38Edq4v/N9O1QsxEXgV8BdJk4H9gPEt/9ZvW55vVPcQ3UbVm/Dqev/WwOn189Y5NzvWj5upGjAbUDWa5odavn5F0q1U83BWA/r6v+504B2SRgEHACf18drTqBpYewGnzmeuUVTD1T5p+6K5vGbx+lzeQNVT9rN6/3W276ufbwucAlDPkXsAWB94A/DLev+twNwah612AH5Yf88s23O/fdT3zwa42PaTtp8H7qD7e6HLKsBAbvVfZPvx+vmOwJH1efozMBpYE7ga+LSkTwHjbU/v+r2AFyW9bMycpIMl3SDphp9fMXkAsdrPvPwDq2dbaYMVl+PcA9/Kb/Z9E3tsui6fOOdqAC6/dwrLL7EYG660/HBE7Wi9Dm3ocaJ7+2/R8zW333oTl1x4Hvt84MPtjNfxevuz+7Imfy//DSQxa9Ys7rnnHt729rfz/R/8gNGjR3Paaae97LXRnvfx9OnTOfbLR3PgwR9hiSXS09LT/JzjLjfe/jfOvvRKDt17tyFOtfDp7f647d7/W3Tg0LUYHkWKXEgaQ3XBvZEkUxWNsKRPUjWWDgEeB663/XTdG3SR7b3m8k8+2/L8JGBX27dI+gCw3bziAF+1/eN+/g5LU83h+TtVQ24c8FrbM1QVVBg9t++1/Zyki4B3ArtT9YLM7bUPS5oBvAU4jKona15mUvXe/Bdw2VxeM73ugWn9naD7ueyra2Junyqt++d6DuZDXz+7tRdvFr2/j6cP8Of3/P3fbfuuHq+5U9K1VDcALpD0QduX1McWo+rR7Mb2idRz9p750VELxCfySkstziNPz+mxeuSZ6YxdcvFur1lqsVEvPd927ZX52iWT+c/0F7jloce4/N4p/OX+R3hx5iyeeXEmnz3/er60U8d04A2pP557Jn+64BwAXrHeBjw2bepLxx577FFWWGFMt9cvs8xyPPfsM8yaNZORIxfhsWndX/PAfffwo+8dy6e/8HWWXmbZ4fklOsTYsWOZ9uiceynTpk1jhTFjXvaaR1t6UqZNm8aY+jVjx45lgw02AGDbbbfl9DSwejVm7Dimtb6Pp01jhRXGvvw1j7a+5tGX/lvMnDmTY798NG/c7s1svc08B4kslFYcszxTH3v8pe2pjz3BuOWXe9nr7n7gQb7y41/w7aMOY9mlM6S13ab/+2EWX31luvoOR6+2Mi88NJURi45i8dVXful1o1dbiecfmtr7P7IQ68TepqFQqgfrPcAvbI+3vZbtNaiG221L1VOwOXAQc3qmrgG2kfQKAElL1EPrerM0MKXuHWqdD3MN0FW2qLWoxgXAAZozp2s1SSvSh/q1JwB/sP0fYFlgat242p7ee1R6+inVsLnrW3pM5uZ/gU/VPSTzw1Q9YxtIOnI+v6c3l1Ofw/p8rwnc1WP/RkDr/LFHJG0oaQTwrpb9F1MNLUTSSEnLUFVlnFuFhLn97Pl1JzCvUmt9/Xyo3hsf7RruqaqKI5LWAe61/T3gbOrfv75x8KjtGf3IWcyrVl6ef/3nGf795LPMmDWbC+96kDeus0q310x79vmX7qre/vDjzLZZbvSifHTbjTj/oLdx7oFv5Stv25IJa4xL46rFW9+xG984fhLfOH4SE7Z+PZdd8kds8/e//ZUllliK5XtcmEri1a/ZjGuu/DMAl138RyZMfD0Aj059hK9/5bN89BOfZdXV1hzuX2WBt/766/PQQw/x8MMPM2PGDC6/7DImTpzY7TVbTZzIxRdfjG3+duedLLnkkqywwgqssMIKjBs3jgcfrEb5Tp48mTXXzDnuzXrrb8CUh/7NIw9PYcaMGVx5+SVsOXHrbq/ZcqvX8eeLL8I2d/3tjvo8j8E23//O11l9jTV5527vLfQbLPg2XHct/jVlKg9NncaMmTO56Krref0Wm3R7zcPTHuOob/yQow89kDVXzfC0oTD1nEtYbZ9dAVhuq02Y+dTTvPDwozx5/W0s+Yq1WHyt1dGoUay6x9t55NxL+v7HFkKzPXtIHp2mVJn2vagKDLQ6g6pk9xWSzqWao7QfgO1H696oUyUtVr/+s1S9Rz19DriWakjZbcy5gD4c+KWkT1DNTXqy/rcvlLQhcHV9Hf0MsA/Q222JS+uL7RHA74Ev1vt/BZwj6QZgMjDPkvO2b5T0FDBpPl571bxe08v3zJK0Z53rqa5S6P10AvCjerjlTOADtl+Q9ENgUj0kcjJwXcv3HAmcC/yLak5S1+21w4ATJR1I1ev0YdtXqyrwcTtV8Y4fzMfPnt/s51H1XvZVZfFWYKakW6h6PnsOdv8i8B3g1vq/+/3AO6jmf+1T9yw+DBxTv3574P/mN2Bpi4wYwSd32JRDz/wLs2ze+erxrDt2GX53S1V48T2brMPFd/+b391yLyNHjGCxRUbw1bdt2evwiZi7zbfYmptvuIaPHrQniy42mkMOP+qlY185+n/40Mc+xQpjxrLP/h/m28d+nlN/+VPWXmc9dtixqk3zu99M4pmnnuQnJ3wLqCqyHfudnxb5XRZEI0eO5MMf/jCf/exnmT1rFjvuuCPjx4/nvPOqqadvf/vbmTBhAtdffz0HHnAAi40ezRFHHPHS93/owx/muOOOY+aMGay8yirdjsUcI0eO5KAPf5QvfPZTzJo9izfvuBNrjl+bP553NgBvffsuvHbCVtx4/bV86MB9qjLtR3wSgDvvuJ0/X3IR49dah8MPPQiAffY7kC0mTJzrz1sYLTJyJP99wF4c9uXvMHv2bN6x/Tass8aqnHlhNRBltx3fyM9+dx5PPvMsX/9ptXTDyJEjOelrnwHgc9/5CTfdcRdPPP0MO3/okxy0+y7sssO2xX6fBdWmp3yTMW/ckkXHLs8O913G3cccj0ZVl8P/PPE3TD3/Msbt9Ea2+9tFzJo+nVs/+GkAPGsWtx92DFue91M0ciQPnnQGz9xxT8lfJRZg6sTShwOhqprgdNuuGx572X7nvL5vCPOsStVbt4HdgU3zBZykxanWEdumHz1/g/2ZZwJH9TKksJsFZYhgk937plwkD7UlR76sQGoMgRe92LxfFIOy8jO5SB5qV21xcOkIjff2GXctEHc/33Xo3UNyjfP776+3QPx+86v0OljD6bXA5LrX5SPAJ0oFkfR+ql62z6RxNTTqwhNHUxUcGXKqFhr+w7waVxERERHRbKWGCA4721cAm8zzhcPA9i+AX5TO0XS2LxjGn/Ui+W8aERERC7EFsciFpBWo6jqsRTXdY/e6hkLra15J96rk61AtdfQdSZ+nqg3RVVHp07b7nBKyMPVgRURERETEELE9JI9BOpJqiZ/1qIquvawAnO276nVRN6Ua9fYcVb2FLt/uOj6vxhWkgRUREREREc31TuDk+vnJwK7zeP2bgH/YfmCgPzANrIiIiIiIGLTZs2cPyUPSwZJuaHn0p3LKSranANRf+1yOiWo5p1N77DtU0q2Sfi5p+Xn9wIVmDlZERERERHQe2ycCJ87tuKQ/ASv3cugz/fk5ddGyXYCjWnb/kGrpHtdfv0m13uxcpYEVERERERGDVqrIhe03z+2YpEckrWJ7iqRV6H2t2y47ATfZfqTl337puaSfUK332qcMEYyIiIiIiKY6G9ivfr4fcFYfr92LHsMD60ZZl3cBt8/rB6YHKyIiIiIiBm0BXd71a8Bpkg4E/gm8F0DSqsBPbb+t3l4CeAvw/3p8/3GSNqUaInh/L8dfJg2siIiIiIgYtAVxHSzbj1FVBuy5/yHgbS3bzwFjenndvv39mRkiGBERERER0SbpwYqIiIiIiEFbEHuwSkgPVkRERERERJukBysiIiIiIgZt9oJZ5GLYpYEVERERERGDliGClQwRjIiIiIiIaJP0YEVERERExKB5doYIQnqwIiIiIiIi2iY9WBERERERMWiZg1VJAysiIiIiIgbNqSIIZIhgRERERERE26QHKyIiIiIiBm12hggC6cGKiIiIiIhom/RgRURERETEoKVMeyU9WBEREREREW2SHqyIiIiIiBi0lGmvpIEVERERERGDljLtlQwRjIiIiIiIaJP0YEVERERExKBliGAlPVgRERERERFtkh6siIiIiIgYtJRpr8hOV15EzJ2kg22fWDpH0+U8D72c46GXczz0co6HR85zDEaGCEbEvBxcOsBCIud56OUcD72c46GXczw8cp5jwNLAioiIiIiIaJM0sCIiIiIiItokDayImJeMQR8eOc9DL+d46OUcD72c4+GR8xwDliIXERERERERbZIerIiIiIiIiDZJAysiIiIiIqJN0sCKiIiIiIhok0VKB4iIBYukEcAmwKrAdOCvth8pm6qZJC3PnPN8v+3ZhSM1Ts5xdDpJG9m+vXSOhYWkJYHnbc8qnSU6V4pcRAQAktYFPgW8GbgbeBQYDawPPAf8GDg5F6iDI2lZ4BBgL2BR5pznlYBrgBNsX1ouYefLOR4ekkYD7wBez5xG7O3Aebb/WjJbk0i6kup9fBLwa9tPFA3UMPVNxT2BvYEJwAvAYlSfG/8HnGj77nIJoxOlgRURAEg6FfghcIV7fDBIWonqYvU/tk8uka8pJF0E/AI4p+eFkqTXAvsCt9n+WYF4jZBzPPQkfR7YGfgzcCMwlTk3ZLavn3/C9q2FIjaKpPWAA4D3AtcBk2xfVDZVM0i6DPgTcBZwe9dNREkrUL2X3wf83vYvy6WMTpMGVkRERPSLpLfbPq+P4ysCa9q+YRhjNZqkkcCuwPeApwABn7Z9ZslcnU7SKNszBvuaiFYpchERfZK0Y90jEENI0isl/aR0jibLOW6feTSuxtuemsZVe0jaWNK3gTuBHYCdbW9YP/920XAN0NVwkrSupMXq59tJ+pik5VpfEzG/0sCKCAAk7SDp75KekfRLSa+SdAPwVaqhg9EG9cXShZJul/QlSStJOgO4GLijdL4myDkeHpK2lvSeureq67z/GriycLSm+T5wE7CJ7UNs3wRg+yHgs0WTNcsZwCxJrwB+BqwN/LpspOhUaWBFRJdvAgcDY4DfURUDOMX2azMEpa1+QvVH+91Uk6hvAu4FXmE7d6PbI+d4iEn6OvBzqnN8nqSjgYuAa4H1SmZrGttvsH2K7em9HDulRKaGmm17JvAu4Du2jwBWKZwpOlTmYEUEAJJusr15y/Y/bK9bMlMTSZpse9OW7X8Ba6UkcPvkHA89SXcAm9t+vi6F/xCwcaqttV9d4OKrwKuoiocAYHudYqEaSNK1wHeAz1ANw7xP0u22NyqbLDpR1sGKiC7LSdqtZVut2+nFapvRkjajmqAO8AywsSQBdA3/iUHJOR56020/D2D7P5LuSuNqyEwCjqaab7U9sD9z3tvRPvsDHwK+XDeu1gZSOTAGJD1YEQGApEl9HLbtA4YtTINJ+jMwtw9e295hGOM0Us7x0JP0BHB5y643tG7b3mW4MzWVpBttv1bSbbZfU++7wvbrS2drGkmLU1W/vKt0luhsaWBFREREv0h6Y1/HbV82XFmaTtJfqBZz/h1wCfBv4Gu2X1k0WMNI2hn4BrCo7bUlbQock5sFMRBpYEUEAJLe38dhZzJ1e0h6Qx+HbfuKYQvTUDnH0SSSJlCVaF8O+CKwLHCc7WtK5moaSTdSlb7/s+3N6n0v9RpG9EfmYEVElwm97BOwM7AakAZWe/xPL/sMbAKsDowc3jiNlHM8xCRdSt/DMN80nHmazPb19dNnqOYJxdCYafvJeqpml/RCxICkgRURANj+aNfzuhjA3sCnqMq1f7lUrqaxvXPrtqRtqapWTQEOLRKqYXKOh8V/97JvIvBJYOowZ2ksSfsBhwFdwwHvBL5n+xflUjXW7ZLeB4ysKzd+DLiqcKboUGlgRcRLJC0CfAD4BNV6Nu/JZN+hIelNwOeo7pB+xfZFhSM1Ts7x0LF9Y9fzej7W54DFgA/ZPr9YsAaph20fDnycai03AZsDX5dEGllt91GqGzEvUK2jdwHwpaKJomNlDlZEACDpEKo7pRdTTaB+oHCkRpL0dqo/4k8CX7L9l8KRGifneHhI+i+qhtXzVKWtLy0cqVEkXQPsafv+HvvXAn5je2KJXE0kaSRwge03l84SzZAGVkQAIGk21dCeR+k+7lxUcyo2LhKsYerz/CBwC72M70/FqsHLOR56kq4HxgFfB67ueTxrjQ2epDtsv6q/x2JgJJ0N7Gv7ydJZovNliGBEdFm7dICFxPalAywEco6H3rNURRfeUz9amaoaWwzO9AEei4F5HrhN0kVU728AbH+sXKToVOnBioiIiFjASHoOuKe3Q8A6tpcc5kiNVhcU6cmZ6xYDkR6siABA0tP0XpK2a4jgMsMcqZEk3UYfpX8zFHPwco6HnqTd+jpu+8zhytJgG5YOsJBZzvZ3W3dIOqxUmOhs6cGKiBhGksb3dTzFRQYv53joSZrUx2HbPmDYwkS0gaSbbG/eY9/NXYsOR/RHGlgRAYCkpWw/M9jXRN8kyfP44J2f18Tc5RxHxPyStBfwPmBb4IqWQ0sDs1JZMAYiQwQjostZkiYDZwE32n4WQNI6VEUDdgd+AvyuWMJmuFTSGcBZtv/ZtVPSolR/4PcDLgVOKhOvEXKOh5ikfYBf2549l+PrAqvYvnJ4k0X021VUi5CPBb7Zsv9p4NYiiaLjpQcrIl4i6W3A3sA2wPLATOAu4DzgZ7YfLhivESSNBg6gOs9rA08Ao4GRwIXAD2xPLpWvCXKOh149N+UA4Mb68SjVOX4F8EZgGnCk7buLhWyAen2mk23vUzpLRMy/NLAiIgqRNIrqrul0208UjtNIOcdDp77434HqhswqVKXD7wTOb+05jMGRdAGws+0XS2dpIklX2t62l0JPKfAUA5YGVkRERMQCStKPgc2Bs+m+PtO3ioWKiD5lDlZERETEguuh+jGCqvBCtJGkFfo6bvvx4coSzZEerIiIiIgFnKQlu4oPRftIuo9qaKB6OWzb6wxzpGiAEaUDRMSCR9K2kvavn4+TtHbpTE0kabykN9fPF5eUu9NtJGlJSSPq5+tL2qWekxXRMSRtLekOqvltSNpE0gmFYzWG7bVtr1N/7flI4yoGJD1YEdGNpKOBLYBX2l5f0qrA6ba3KRytUSQdBBwMrGB7XUnrAT+y/abC0RpD0o3A66kqYl4D3AA8Z3vvosEaRNJiwLuBtWiZdmD7mFKZmkbStcB7gLO7Fr2VdLvtjcomawZJa9m+v4/jAlaz/eDwpYpOlzlYEdHTu4DNgJsAbD+UnpUhcQiwJXAtgO27Ja1YNlLjyPZzkg4Ejrd9nKSbS4dqmLOAJ6lKtb9QOEtj2f5XdZ3/klmlsjTQ1+ue7rN4+ZID2wNvAo4G0sCK+ZYGVkT09KJtSzJUw6xKB2qoF2y/2HXRJGkRupcIjsGTpK2p1sM6sN6Xv3vttbrtt5YO0XD/kvQ6wPVi2R+jHi4Yg2f7vZJeRfU5cQDVkgPPUZ3j/wO+bPv5ghGjA+UPTUT0dFpdFni5ehjbAcBPCmdqosskfRpYXNJbgI8A5xTO1DSHAUcBv7f9V0nrAJcWztQ0V0l6je3bSgdpsA8B3wVWA/4NXEDVAx5tYvsO4DOlc0RzZA5WRLxMfcG/I1VVpQtsX1Q4UuPU4/o/SMt5Bn7qfCi3jaT32j59Xvui/yTdRtXjugiwHnAv1RDBrsVZNy4YLyKiqDSwIiKGWT3e/9ZMUh9akm6yvfm89kX/SRrf13HbDwxXlqare16/C0ykatReDRxh+96iwSJirjJEMCK6kfQ0c+YCLQqMAp61vUy5VM1ie7akWyStafufpfM0jaSdgLcBq0n6XsuhZYCZZVI1S1cDStIptvdtPSbpFGDfXr8xBuLXwA+oChAB7AmcCmxVLFFE9CkNrIjoxna3ioGSdqWqdhfttQrwV0nXAS8tHmp7l3KRGuMhqpLsu1BVBevyNHBEkUTN9erWDUkjgdcWytJUsn1Ky/YvJR1aLE2DSVoNGE/3JQcuL5coOlWGCEbEPEm6xvbE0jmaRNIbe9tv+7LhztJUkkbZnlE/Xx5Yw/athWM1gqSjgE8Di1NVXINq/tWLwIm2jyqVrWkkfQ14AvgN1eiCPYDFqHq1sP14sXANIulYqnN7B3PK4Ds3vWIg0sCKiG4k7dayOYJq0eE32t66UKSIAZH0Z6perEWAyVTr21xm++MFYzWKpK+mMTW0JN3Xx2HbXmfYwjSYpLuAjW1nPbcYtAwRjIiedm55PhO4H3hnmSjNlbluw2JZ209J+iAwyfbRktKD1QaSugqFnN7y/CW2bxrmSI1le+3SGRYS91J9DqeBFYOWBlZEdGN7/9IZFgaZ6zYsFpG0CrA7WeOm3b7ZxzEDOwxXkIg2eQ6YLOliWhpZtj9WLlJ0qjSwIqIbSeOAg4C16D7R94BSmRYGtv8g6cjSORrmGKr1xf5i+/q63PXdhTM1gu3tS2eIaLOz60fEoGUOVkR0I+kq4Aqq6mtdE32xfUaxUA2UuW7RFJI2Al4FjO7aZ/sX5RJFDIykRYH16827uorkRPRXerAioqclbH+qdIiFQOa6DTFJqwPHA9tQDVu7EjjM9oNFgzWIpKOB7agaWP8H7ER1ntPAahNJZwA/B863Pbt0nqaStB1wMtVnsYA1JO2XMu0xEOnBiohuJH0JuMr2/5XOEjEYki6iWqS1aw2hfYC9bb+lXKpmkXQbsAlws+1NJK0E/NT2zvP41phPkt4M7A9MBE4HTrL9t7KpmkfSjcD7bN9Vb68PnGo767pFv6WBFRHd1NXtlqRaz+ZFqjt5TnW79spct6EnabLtTee1LwZO0nW2t6wvTrenWsz5dtuvnse3Rj9JWhbYi6pgy7+AnwC/zDC29pB0q+2N57UvYn5kiGBEdNOzul0MmbOo5rr9iZa5btFW0yTtA5xab+8FPFYwTxPdIGk5qov9G4FngOuKJmogSWOoemD3BW4GfgVsC+xHNUQzBu8GST9jTo/33lTv6Yh+Sw9WRHQjSVR/WNa2/UVJawCr2M5FUxulJ2XoSVoT+D6wNdUcrKuo5mA9UDRYQ0laC1jGdtYaayNJZwIbUF34n2R7SsuxG2xvUSxcg0haDDiEquEq4HLghCw8HAORBlZEdCPph8BsYAfbG0paHrjQ9oTC0Rolc92iCVpuyKxj+5i6Ubtybsi0j6QdbF9SOkdEzL80sCKiG0k32d5c0s22N6v33WJ7k9LZmqRlrtsLwAwy161tJB0H3Gv7Rz32H0F18Z8qmW2SGzJDT9ISwMeBNW0fLGk94JW2zy0crREknWZ797pgy8suijMHKwYic7AioqcZkkZS/6GpizGkNHCbZa7bkHoHsFEv+78L3AqkgdU+W3XdkAGw/Z96LaFon0lUc4FeV28/SFVNMA2s9jis/vqOoimiUUaUDhARC5zvAb8HVpT0Zao1bb5SNlIzSVpe0paS3tD1KJ2pIdzbekH1PhXI02S5ITP01rV9HFVPN7ank/dx27TMafuI7QdaH8BHSmaLzpUGVkR0Y/tXwCeBrwJTgF1tn142VfNI+iDVJOoLgC/UXz9fMlODPFcPo+qm3je9QJ4myw2ZofeipMWZ04hdl2pocbRXb+vj7TTsKaIRMkQwIrqR9F3gt7Z/UDpLwx0GTACusb29pA2oGloxeP8LnF8XEukqs7wFcBRweKlQTWT7V/UaWG+i6lXZ1fadhWM1zdHAH4E1JP0K2Ab4QNFEDSLpw1Q9VetKaq2AuTRV5dGIfkuRi4joRtJ+wB7A+lR3pn9r+4ayqZpH0vW2J0iaTDWP5YWUbm8fSRsB/8OcuVi3A9+wfVu5VM0haYW+jtt+fLiyLAzqdbAmUjVir7E9rXCkxqgXcF6eatTGkS2Hns77OAYqDayI6FV9AfVuYE+q6lUvG3IVAyfp98D+VD0qOwD/AUbZflvJXBHzQ9J9VEPWBKwCPNR1iGoO3DqlsjWRpNWA8bSMPLJ9eblEzSNpIvBX20/X20sDr7J9bdlk0YnSwIqIXknakqona1fgDts7l03UXJLeCCwL/NH2i6XzRPRH65IO0X6SjqX6LP4rcwqI2PYu5VI1T10Jc3PXF8aSRgA32N68bLLoRJmDFRHd1H/MdwP+AfwW+KLtJ4qGapC5DK3qGra2FJAhKdFpcqd2aO1Kte5VClsMLbml18H2bEm5To4ByRsnInq6D9g6Y/yHzDSqdWxm1tut5ZYNZGhVRLS6FxhFKgcOtXslfQz4Yb39EapzH9FvGSIYEd3UwyLeB6xj+xhJawIr276ucLRGqKs0bgf8BTgVuNL5IB4Skr7Xy+4nqYb9nDXceZpE0sdbNj8OfKv1uO1vEW0h6QxgE+BiWhpZtj9WLFQDSVqRatmBHahudl0MHG57atFg0ZHSwIqIbiT9kGqc/w62N5S0PHCh7QmFozWGJFE1svYCtgQuBH5o+76SuZpG0onABkDXOm7vpprHsgZwr+3DC0XreJKO7uu47Sw50CZ1ZdeXsX3ycGeJiPmTBlZEdCPpJtubt05cl3SL7U1KZ2saSctRVWn8IvBp2z8pm6hZJF0C7Gh7Zr29CFVj9i3AbbZfVTJfxPyStCjV0hkAd9meUTJPE0maRC/zCW0fUCBOdLjMwYqInmZIGkn9h0bSOOZUropBkrQk8E6qqmDjgDOpKlf9q2iwZloNWJJqWCD181Vtz5KU+SzRESRtB5wM3E81Z3MNSfulTHvbndvyfDTwLuYsPxDRL2lgRURP36NaYHhFSV8G3gN8rmykRpkK3E01/+oeqobsBEkTAGyfWTBb0xwHTJb0Z6oL0zcAX6kbuX8qGSyiH75J1RN7F4Ck9ak+P15bNFXD2D6jdVvSqeRzIgYoQwQj4mUkbQC8ieqi9GLgn7afLZuqGSSdxNzLWjvDUdpL0ipU89wEXGc7d6Sjo0i61fbG89oX7SXplcB5tl9ROkt0njSwIuIlklYDVgFutf1iXVXpcOADtlctGi5iAOr39HhaRmxkaNXg9agi+DKpItg+kn5OdVPmlHrX3sAitvcvl6p5JD1NdZ5Vf30YOKpnz1bE/MgQwYgAQNLhwGeohq0tVpcT/xbwCzIUJTpQvWj2HlSVA7vmERpIA2vwli4dYCHyYeAQ4GNUF/+XAycUTdRAtvOejrZJD1ZEACDpDmBb24/Xa1/dA7zB9jWFo0UMiKS7gI1tp6BFRPRK0uZ9Hbd903BlieZID1ZEdHne9uMAtv8p6e9pXEWHuxcYRcvirNFekkYDBwKvpqq8BqS0dTtIurWv45mD1TbfrL+OBrYAbqHqKdwYuBbYtlCu6GBpYEVEl9Ulfa9le8XWbdsfK5CpsSTt1svuJ6nWZ5o63Hka6jmqKoIX09LIynu5rU4B/gb8F3AM1fygO4smao7ZVENafw2cA0wvG6eZbG8PIOk3wMG2b6u3NwL+u2S26FwZIhgRAEjar6/jtk8eriwLA0nnAVsDl9a7tgOuoVpM9Bjbp8zlW2M+ze09nfdy+3QtSN5V1U7SKOAC2zuUztYEdUXXvYCdgTuoGlsXdi2eHe0jabLtTee1L2J+pIEVEVGApHOAD9p+pN5eCfgh8EHgctsblcwXMT8kXWd7S0mXAx+hqrx2ne11CkdrHEl7AD8AjrX99dJ5mqZe9+pZ4JdUPYf7AEvZ3qtosOhIGSIYEVHGWl2Nq9pUYP26yMiMUqGaQNJptneXdBu9rDmWuSttdaKk5akWIz8bWAr437KRmqNeZmBP4F3Af4AjqBaCj/bbn6pi42H19uVUN70i+i09WBERBUg6AVgTOL3e9W7gQeB/gHO75gVE/0laxfYUSeN7O277geHOFNFfki6jKod/GvA74PHW411FiaJ9JC0KvJLqxsxdtnOzKwYkDayI6EbSCvnDPfQkiapRtQ1VxaorgTOcD+W2kXSs7U/Na18MnKTlgPcDa9F9MecUEhkkSfczpwe29XNBgDMMs70kbQecDNxPdY7XAPbLwuQxEGlgRUQ3ku4GJgOTgPNzwR+dStJNtjfvse/WDBFsH0lXURVnuY05izmnkEh0HEk3Au+zfVe9vT5wqu3Xlk0WnShzsCKip/WBNwMHAMdL+i1wku2/l43VLHWZ9mOBFanulnbdlV6maLAGkPRhqoIL6/RYS2hp4C9lUjXWaNsfLx0iog1GdTWuAGz/va6KGdFv6cGKiLmStD1VRaUlqRZfPNL21WVTNYOke4CdbWfNoDaTtCywPPBV4MiWQ09n+Gt7SToCeAY4l+5rjeU8R0eRNImqF7ZriYy9gUVs718uVXSqNLAiohtJY6jK0+4LPAL8jKo62KbA6bbXLpeuOST9xfY2pXMsDCStCIzu2rb9z4JxGkXSIcCXgSdomS+U+UHRaSQtBhwCbEs1ouBy4ATbL/T5jRG9SAMrIrqR9HeqO3iTbD/Y49inbB9bJlmzSPousDLwB7rf+T+zVKamkbQz8C1gVaoy+OOBO22/umiwBpH0D2Ar29NKZ2kySdsC69meJGkc1fpM95XO1RSSRgC3Zv3BaJfMwYqInl45t8IWaVy11TLAc8COLfsMpIHVPl8CJgJ/sr1ZPeQ1i4a211+p3scxRCQdDWxBVT58EjCKauh2esDbxPZsSbdIWjM93NEOaWBFBACSzqEe4lNVEO/O9i7DnanJMq5/WMyw/ZikEZJG2L5UUm4StNcsYLKkS+neE5sy7e3zLmAz4CYA2w9JWrpspEZaBfirpOuAZ7t25m9fDEQaWBHR5RulAywMJH3S9nGSjqf72jZALkzb7AlJS1HNpfiVpKnAzMKZmuYP9SOGzou2LanrBtiSpQM11BdKB4jmSAMrIgCwfVnpDAuJrqqBNxRNsXB4JzAdOIKqItiywDFFEzVM1rsaFqdJ+jGwnKSDqJbQ+EnhTI0haTTwIeAVVOu5/cx2bsTEoKTIRUQAIOk027tLuo3ee1ayOGt0DEkjgQtsv7l0libK58XwkvQWqvmaonpfX1Q4UmPUaz3OAK4AdgIesH1Y2VTR6dLAiggAJK1ie4qk8b0dt/3AcGdqota5br3JeP/2kXQ2sK/tJ0tnaZp8XgwfSWsDU2w/X28vDqxk+/6iwRpC0m22X1M/XwS4zvbmhWNFh8sQwYgAwPaU+msujIZW5roNn+eB2yRdRPdJ65nnNkj5vBhWpwOva9meVe+bUCZO48zoemJ7Zm9FniL6Kw2siOhG0kTgeGBDYFFgJPCs7WWKBmuIzHUbVufVjxgiknYDjgVWpBq+JqqFhvN50T6L2H6xa8P2i5IWLRmoYTaR9FT9XMDi9XbeyzFgaWBFRE/fB/akukO6BfB+qsm/0QZzm7PCnD/mmbvSJrZProdTrWn7rtJ5Guo4YGfbd87zlTFQj0raxfbZAJLeCWRh5zaxPbJ0hmieNLAi4mVs3yNppO1ZwCRJV5XO1CDvKB1gYSFpZ6ohmYsCa0vaFDgm89za6pE0robch6iWGfg+1Y2Yf1Hd+IqIBVQaWBHR03P18JPJko4DpgBZd6VNWues1AUC1rP9p7qnJZ/J7fV5YEvgzwC2J9cFA6J9bqirsP2B7gsNn1ksUcPY/gcwsV7TTbafLp0pIvqWP+YR0dO+wAjgUKr1g9YA3l00UQPV69kcDKwArAusDvwIeFPJXA0z0/aTPSatp3Ruey0DPEdVQryLgTSw2kTSYlSfwWsBi3S9n21nTbeIBVQaWBHRje0HJI2rn2dl+6FzCFXvyrUAtu+WtGLZSI1zu6T3ASMlrQd8DMhw1zayvX/PfZJS3a69zgKeBG6kpZcw2kvSTrbP77HvQ7Z/VCpTdK40sCICAFW3RY+m6rkSMELSTOD43CkdEi/U1cCAl9ZfSe9Ke30U+AzVRempwAXAF4smaihJr6IqjrMXVWNgi7KJGmV1228tHWIh8DlJL9i+BEDSp4DtqEYWRPRLGlgR0eVwYBtggu37ACStA/xQ0hG2v10yXANdJunTVCWB3wJ8BDincKZGsf0c8BlJx1abmbvSTvUcwr3qx0xgPLBFFsBtu6skvcb2baWDNNwuwLmS/gd4K7BBvS+i32TnhmlEgKSbgbfYntZj/zjgQtublUnWTJJGAAdSzV0RVe/KT50P5baph6r9HFi63vUkcIDtG8ulaoa6suiywG+A39RDXO+znSIibSbpDqqlMu6j6o3Nkg5DpB6m/Seq4ZgH5PM4Bio9WBHRZVTPxhWA7UcljSoRqMlszwZ+Iulk4NXAv/PHvO1+BnzE9hUAkrYFJgG5MB28R6kKs6wEjAPuJkNch8pOpQM0maSnqd67qr8uCqwDvEdSFhqOARlROkBELDBeHOCx6AdJP5L06vr5ssBk4BfAzZL2KpmtgZ7ualwB2L4SyDDBNrD9TuA1wE3AFyTdBywvacuyyZrH9gP18g7TqRoAXY9oA9tL216m5eto20t1bZfOF50pQwQjAgBJs4BnezsEjLadXqw2kPRX210NrMOB7WzvKmll4PwMxWwfSd8GlqAqcGFgD+A/wBkAtm8ql65Z6qFVe1DNx1rD9hqFIzWGpF2AbwKrAlOp5rrd2fU5EoMjafO+judzIgYiDayIiGEk6eauRpSk84DTbZ/U81gMnqRL+zhs2zsMW5iFiKTxrQtqx+BIugXYAfiT7c0kbQ/sZfvgwtEaIZ8TMRQyBysiYng9IekdwL+pqjYeCC+VaV+8ZLCmsb196QwLozSu2m6G7cckjZA0wvaldWXMaIN8TsRQSAMrImJ4/T/ge8DKwOG2H673vwk4r1iqhpG0EfA/VAVEDNwBfCOlrqMDPSFpKeBy4FeSplKVxY82kLSD7Usk7dbbcdtnDnem6HwZIhgREY0i6Z3AN4CvAjdQzSN8LXAU8N+2zyoYL6JfJC0JPE/1Pt6bqjz+r2w/VjRYQ0j6gu2jJU3q5bBtHzDsoaLjpYEVERGNUs9ZeWfPBW8lrQWcZXuTErmaqF4n7yBgLVpGxeSiNCIWZhkiGBERTTOqZ+MKwPb9WdOt7c4CrqBanHVW4SyN0rI+08sOUfWspIR4G0j6eF/HbX9ruLJEc6SBFRERTTND0pq2/9m6U9J4Mnel3Zaw/anSIZrI9tKlMywkvkG1HuH5wAtUDdiIQUkDKyKiAEnLAe/n5UOrPlYoUpMcDfxJ0leAG6l6ASYARwJpDLTXuZLeZvv/SgdpunqtsdFd2z1vIMSAbQ7sCbyd6vPiVOBiZw5NDELmYEVEFCDpKuAa4DZgdtd+2ycXC9UgkjYBPkFVRVDA7cA3bd9SNFjD1MPYlgReBGbUuzN8rY2y0PDwkfQ6qsWy3wx8yvbZhSNFh0oPVkREGaNt9zn2Pwaubki9v3SOpsswtmHxRWAiPRYaLpypceqCLZsBrwEepGrMRgxIGlgREWWcIukg4Fyqcf8A2H68XKSI/qt7WN5Qb/7Z9rkl8zRQFhoeQpL2B/agGn75O2B322lcxaBkiGBERAGSDgG+DDzBnEphtr1OsVAR/STpa1Tz235V79oLuNH2keVSNYukPwG7Uq3rNpaqZ2WC7deVzNUUkmZTDdXumtPW7cLY9i7DHio6XhpYEREFSPoHsJXtaaWzNJWkFdIjOLQk3Qpsant2vT0SuNn2xmWTNUe90PB0YARZaLjtJL2xr+O2LxuuLNEcGSIYEVHGX4HnSodouGslTQYmAeenKtiQWQ7oasguWzBHI9l+tn46W9J5wGN5L7dPGlAxFNLAiogoYxYwWdKldJ+DlTLt7bM+VTWwA4DjJf0WOMn238vGapSvAjfX72NRzcU6qmykZpA0EfgaVeP1i8ApVEMER0h6v+0/lswXEXOXIYIREQVI2q+3/SnTPjTqymu/pCopfgtwpO2ry6ZqBkmrUM3DEnCt7YcLR2oESTcAn6bqFTwR2Mn2NZI2AE61vVnRgBExV2lgRUQUImlRql4WgLtsz+jr9dE/ksYA+wD7Ao8APwPOBjYFTre9drl0EX2TNNn2pvXzO21v2HLs5jSw2kvSRrZvL50jmiFDBCMiCpC0HXAycD/Vnf81JO1n+/KCsZrmaqphVbvafrBl/w2SflQoU8T8mt3yfHqPY7k73n4/qm96nQT82vYTZeNEJ0sPVkREAZJuBN5n+656e32qYT+vLZusOSQpxQCiU0maBTxLdQNmceYUxRHVQuWjSmVrKknrUc3ZfC9wHTDJ9kVlU0UnSgMrIqIASbf2LGXd277oP0nn0Mcd/qxr016StgXWsz1J0jhgKdv3lc4VMRD1UgO7At8DnqJq0H7a9pklc0VnSQMrIqIASZOohgCdUu/aG1jE9v7lUjVD1rUZPpKOBrYAXml7fUmrUs1v26ZwtIh+kbQxsD/wduAi4Ge2b6rf01fbHl80YHSUNLAiIgqQtBhwCLAt1R3Sy4ETbL/Q5zdGLEDqdcY2A27qKrqQntjoRJIuB35KdYNgeo9j+9o+pffvjHi5FLmIiBhmkkYAN9reCPhW6TxNI+k027tLuo1ehgrm4r+tXrRtSQaQtGTpQBEDYfsNfRxL4yr6JQ2siIhhZnu2pFskrWn7n6XzNNBh9dd3FE2xcDhN0o+B5SQdRFUg4CeFM0XMt7ndiKEaWeDckImByBDBiIgCJF1CtTjrdVSVwoAUYIjOIUnA6sAGwI5UF6QXpOpadBJJfc6tsv3AcGWJ5kgDKyJiGElazPYLcyvEkAIM7SNpInA8sCGwKDASeNb2MkWDNYikG7O0QEREdxkiGBExvK4GNgc+aHvf0mEa7vvAnsDpVJXu3g+8omii5rlG0gTb15cOEjEQkq60va2kp+k+VLBriGBuyES/pYEVETG8FpW0H/A6Sbv1PJi1VtrL9j2SRtqeBUySdFXpTA2zPfD/JD3AnEVxM28lOobtbeuvS5fOEs2RBlZExPD6ENWaV8sBO/c4ZiANrPZ5TtKiwGRJxwFTgFS5a6+dSgeIaCdJKwKju7ZTiCgGInOwIiIKkHSg7Z+VztFk9eT1R6jmXx0BLEu11tg9RYM1iKQ1e9ufi9LoNJJ2Ab4JrApMBcYDd9p+ddFg0ZHSwIqIiMaSNA7A9qOlszRRS4lrUd31Xxu4Kxel0Wkk3QLsAPzJ9maStgf2sn1w4WjRgUaUDhAREdFOqnxe0jTgb8DfJT0q6X9LZ2sa26+xvXH9dT1gS+DK0rkiBmCG7ceAEZJG2L4U2LRwpuhQaWBFRETTHA5sA0ywPcb28sBWwDaSjiiarOFs30S1vltEp3lC0lLAFcCvJH0XmFk4U3SoDBGMiCigXqR1b2Ad28fUc1lWtn1d4WgdT9LNwFtsT+uxfxxwoe3NyiRrHkkfb9kcQbUEwRjb/1UoUsSASFoSmE71Pt6bas7mr+perYh+SRXBiIgyTgBmU435PwZ4GjiD3P1vh1E9G1dQzcOSNKpEoAZrLW09EziP6n0c0WlGAa+qn//B9pMlw0RnSwMrIqKMrWxvXve2YPs/dUnxGLwXB3gs+u8O26e37pD0XqrFnSMWePXn7onArsB9VAVbxkv6PfAh2/nMiH7LHKyIiDJmSBpJVYGta/ja7LKRGmMTSU/18ngaeE3pcA1z1Hzui1hQfZaq92oN25vZ3hRYk6oT4nMlg0XnyhysiIgCJO0N7EE1Z+Vk4D3AZ3v2BkQsiCTtBLwN2B34bcuhZYBX2d6ySLCIfpJ0O7Cl7ed67F8KuMb2RmWSRSfLEMGIiAJs/0rSjcCbqIak7Gr7zsKxIubXQ8ANwC7AjS37n6Za1DmiU8zu2bgCsP2MpPRCxICkBysiohBJywNr0HKzqy5zHdERJC1iO6Wso2PVCwxvR3Wjq6dLbW8yvImiCdKDFRFRgKQvAh8A/kE9D6v+ukOpTBHzS9JptncHbu7tLr/tjQvEihiIZal6YXtrYKUXIgYkPVgREQVIugt4TSpURSeStIrtKZLG93bc9gPDnSkiYkGRHqyIiDJuB5YDphbOEdFvtqfUX9OQiojoIT1YEREFSNoCOIuqofVC137buxQLFTGf6pL3c72AsL3MMMaJiFigpAcrIqKMk4FjgdvI+lfRYWwvDSDpGOBh4BSqOSx7A0sXjBYRUVx6sCIiCpB0me03ls4RMRiSrrW91bz2RXQCSdsC69meVC/+vpTt+0rnis6THqyIiDJulPRV4Gy6DxFMmfboJLPqRbN/QzVkcC9gVtlIEf0n6WhgC+CVwCRgFPBLYJuSuaIzpQcrIqIASZf2stu2U6Y9OoaktYDvUl2EGvgLcLjt+wvGiug3SZOBzYCbbG9W77s1Sw7EQKQHKyKiANvbl84QMVh1Q+qdpXNEtMGLtt21rpukJUsHis6VBlZERAGSlgWOBt5Q77oMOMb2k+VSRfRPPU/lIGAtWq4pbB9QKlPEAJ0m6cfAcpIOAg4AflI4U3SoDBGMiChA0hlUJdpPrnftC2xie7dyqSL6R9JVwBXAjbTMvbJ9RrFQEQMk6S3AjlQVMS+wfVHhSNGh0sCKiChA0mTbm85rX8SCLO/ZiIiXG1E6QETEQmp6XRIYAEnbANML5okYiHMlva10iIjBkvS0pKd6PP4l6feS1imdLzpLerAiIgqQtCnV8MBl613/AT5g+5ZioSL6SdLTwJLAi/VDVNUwlykaLKKfJH0BeAj4NdX7eE9gZeAu4MO2tyuXLjpNGlgREQVJWgbA9lOls0RELKzmsmj2NbYnSrrF9ialskXnyRDBiIgCJH1F0nK2n7L9lKTlJX2pdK6I/lBlH0mfq7fXkLRl6VwRAzBb0u6SRtSP3VuOpTci+iUNrIiIMnay/UTXhu3/AJnLEp3mBGBr4H319jPAD8rFiRiwvamquU4FHqmf7yNpceDQksGi82QdrIiIMkZKWsz2CwD1H/HFCmeK6K+tbG8u6WaobhRIWrR0qIj+sn0vsPNcDl85nFmi86WBFRFRxi+BiyVNohp+cgBz1sSK6BQzJI2kHkJVLzw8u2ykiP6TNBo4EHg1MLprfxbNjoHIEMGIiAJsHwd8GdiQ6g/6F+t9EZ3ke8DvgZUkfZnqTv9XykaKGJBTqKoG/hdwGbA68HTRRNGxUkUwIiIiBkzSBsCb6s1LbN9ZMk/EQEi62fZmkm61vbGkUcAFtnconS06T3qwIiIKkLSbpLslPVkvaPm0pJRqj060BDCS6ppi8cJZIgZqRv31CUkbUa1RuFa5ONHJ0sCKiCjjOGAX28vaXsb20lmcNTqNpP+lmju4AjAWmCTps2VTRQzIiZKWBz4LnA3cARxbNlJ0qgwRjIgoQNJfbG9TOkfEYEi6E9jM9vP19uLATbY3LJssYv5JGgG8x/ZppbNEM6SKYEREGTdI+i3wB+CFrp22zyyWKKL/7qequPZ8vb0Y8I9iaSIGwPZsSYcCaWBFW6QHKyKigLo8e09OSeDoJJL+AEwALqIq1f4WqkqCUwFsf6xYuIh+kPQ5YDrwW+DZrv22Hy8WKjpWGlgRERExIJL26+u47aztFh1B0n297LbtdYY9THS8NLAiIoaRpOOpF2XtTe74RyeRtKLtqT32vdL2XaUyRUSUljlYERHD64bSASLa6ApJn+sqDiDpE8CBwKvKxoroH0lLAB8H1rR9sKT1gFfaPrdwtOhA6cGKiIiIAZG0CnAiVZGLlYA7gU/YfqZosIh+qosO3Qi83/ZGdUXMq21vWjZZdKKsgxUREREDYnsK8Edga6pFWX+RxlV0qHVtH0e94LDt6YDKRopOlSGCERERMSCSLgKmABsBqwM/l3S57f8umyyi316se60MIGldWpbQiOiP9GBFRBQgaYXSGSLa4Ae232/7Cdu3A68DniwdKmIAPk/VG7uGpF8BFwOfLJooOlbmYEVEFCDpbmAyMAk43/kwjg4iaQPbf6ufL2b7hZZjE21fUy5dxMBIGgNMpBoaeI3taYUjRYdKD1ZERBnrUxUH2Be4R9JXJK1fOFPE/Pp1y/Orexw7YTiDRLSDpLOBHYE/2z43jasYjDSwIiIKcOUi23sBHwT2A66TdJmkrQvHi5gXzeV5b9sRneCbwOuBOySdLuk9kkaXDhWdKUUuIiIKqIei7EPVg/UI8FHgbGBT4HRg7WLhIubNc3ne23bEAs/2ZcBlkkYCOwAHAT8HlikaLDpSGlgREWVcDZwC7Gr7wZb9N0j6UaFMEfNrdUnfo+qt6npOvb1auVgRA1dXEdwZ2APYHDi5bKLoVClyERFRgCSlsEV0Kkn79XXcdi5Mo6PUCw1vRVVJ8DSquVizy6aKTpUGVkTEMJJ0Dn0MobK9yzDGiYgIQNJbgYtsz6q3twHeZ/uQssmiE2WIYETE8PpG6QAREdGd7T9K2lTSXlRDBO8DziwcKzpUGlgREcOonkgdERELgHp5jD2BvYDHgN9SjfDavmiw6GgZIhgRMYwknWZ7d0m30ctQQdsbF4gVMSCSVrD9eOkcEQMlaTZwBXCg7XvqfffaXqdssuhk6cGKiBheh9Vf31E0RUR7XCtpMjAJOD+FW6IDvZuqB+tSSX8EfkPWcotBSg9WREREDIgkAW8GDgC2pBpedZLtvxcNFtFPkpYEdqUaKrgDVYn239u+sGSu6ExpYEVEFCBpInA8sCGwKDASeNZ2FrWMjiRpe+CXwJLALcCRtq8umyqi/yStALwX2MP2DqXzROdJAysiogBJN1ANSzkd2AJ4P/AK258pGiyiHySNAfYB9gUeAX4GnA1sCpxue+1y6SIiysgcrIiIQmzfI2lkve7KJElXlc4U0U9XA6cAu9p+sGX/DZJ+VChTRERRaWBFRJTxnKRFgcmSjgOmUA2tiugkr5xbYQvbxw53mIiIBUGGCEZEFCBpPNWQqkWBI4BlgRO6ygRHLMgknUMvywx0sb3LMMaJiFigpIEVEVGIpHEAth8tnSWiPyS9sa/jWVA7IhZmaWBFRAyjuqz10cChVGutjABmAsfbPqZktoiIiBi8EaUDREQsZA4HtgEm2B5je3lgK2AbSUcUTRYxnySdVn+9TdKtPR+l80VElJQerIiIYSTpZuAttqf12D8OuND2ZmWSRcw/SavYnlLPJXwZ2w8Md6aIiAVFqghGRAyvUT0bV1DNw5I0qkSgiP6yPaX+moZUREQPGSIYETG8XhzgsYgFjqSJkq6X9IykFyXNkvRU6VwRESWlBysiYnhtMpcLUAGjhztMxCB9H9gTOB3YAng/8IqiiSIiCksDKyJiGNkeWTpDRDvZvkfSSNuzgEmSriqdKSKipDSwIiIiYqCek7QoMFnSccAUYMnCmSIiisocrIiIiBiofamuJQ4FngXWAN5dNFFERGEp0x4REREDVi8xgO1HS2eJiFgQpAcrIiIi+kWVz0uaBvwN+LukRyX9b+lsERGlpYEVERER/XU4sA0wwfYY28sDWwHbSDqiaLKIiMIyRDAiIiL6RdLNwFt6LppdDxe80PZmZZJFRJSXHqyIiIjor1E9G1fw0jysUQXyREQsMNLAioiIiP56cYDHIiIaL0MEIyIiol8kzaIqy/6yQ8Bo2+nFioiFVhpYERERERERbZIhghEREREREW2SBlZERERERESbpIEVERERERHRJmlgRUREREREtEkaWBEREREREW3y/wEIfkI9P2/t7AAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 864x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Selecting variables for the correlation graph\n",
    "variables_for_correlation = ['Daily Revenue (INR)', 'Daily Income from Selling Manure (INR)', \n",
    "                             'Daily Operating Costs (INR)', 'Daily Expenditure on Animal Health (INR)',\n",
    "                             'Balance Money per Day', 'Average Daily Milk Production (litres)']\n",
    "correlation_data = df[variables_for_correlation]\n",
    "\n",
    "# Calculating the correlation matrix\n",
    "correlation_matrix = correlation_data.corr()\n",
    "\n",
    "# Plotting the correlation matrix\n",
    "plt.figure(figsize=(12, 8))\n",
    "sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt=\".2f\")\n",
    "plt.title(\"Correlation Matrix of Selected Variables\")\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "4151b7bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1.0328495120584136, 0.3906413159749041, 4.0)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Creating the full model including the location variables\n",
    "full_model = sm.OLS(df[target], predictors_ols_with_constant).fit()\n",
    "\n",
    "# Creating a reduced model that excludes the location variables: Ahmedabad, Rajkot, Surat, and Jamnagar\n",
    "predictors_reduced = predictors_ols_with_constant.drop(['ahmedabad', 'rajkot', 'surat', 'jamnagar'], axis=1)\n",
    "reduced_model = sm.OLS(df[target], predictors_reduced).fit()\n",
    "\n",
    "# Performing an F-test to compare the full model against the reduced model\n",
    "f_test_result = full_model.compare_f_test(reduced_model)\n",
    "\n",
    "# Outputting the F-test results\n",
    "f_test_result\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "817b25ad",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Selecting variables for correlation analysis: location variables, government satisfaction, and the target variable\n",
    "variables_for_correlation = ['ahmedabad', 'rajkot', 'surat', 'jamnagar', \n",
    "                             'Satisfaction_5_7', 'Satisfaction_8_10', \n",
    "                             'Average Daily Milk Production (litres)']\n",
    "correlation_data_places = df[variables_for_correlation]\n",
    "\n",
    "# Calculating the correlation matrix\n",
    "correlation_matrix_places = correlation_data_places.corr()\n",
    "\n",
    "# Plotting the correlation matrix\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.heatmap(correlation_matrix_places, annot=True, cmap='coolwarm', fmt=\".2f\")\n",
    "plt.title(\"Correlation Matrix for Location, Government Satisfaction, and Milk Production\")\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "8493bde8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(0.7485146408525016, 0.47405139609970803, 2.0)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Creating the full model including the location variables\n",
    "full_model = sm.OLS(df[target], predictors_ols_with_constant).fit()\n",
    "\n",
    "# Creating a reduced model that excludes the location variables: Ahmedabad, Rajkot, Surat, and Jamnagar\n",
    "predictors_reduced = predictors_ols_with_constant.drop(['Satisfaction_5_7', 'Satisfaction_8_10'], axis=1)\n",
    "reduced_model = sm.OLS(df[target], predictors_reduced).fit()\n",
    "\n",
    "# Performing an F-test to compare the full model against the reduced model\n",
    "f_test_result = full_model.compare_f_test(reduced_model)\n",
    "\n",
    "# Outputting the F-test results\n",
    "f_test_result\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "e4f3bc56",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n",
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  warnings.warn(\n",
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/graphics/gofplots.py:993: UserWarning: marker is redundantly defined by the 'marker' keyword argument and the fmt string \"bo\" (-> marker='o'). The keyword argument will take precedence.\n",
      "  ax.plot(x, y, fmt, **plot_style)\n",
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x864 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import statsmodels.api as sm\n",
    "from statsmodels.graphics.gofplots import ProbPlot\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# Load the dataset\n",
    "file_path = '/Users/dhruvtrivedi/Downloads/Final Project Stat 371/Final_Transformed_Farm_Data_Gujarat_v2.csv'\n",
    "data = pd.read_csv(file_path)\n",
    "\n",
    "# Prepare the data for the model\n",
    "X = data.drop('Average Daily Milk Production (litres)', axis=1)\n",
    "y = data['Average Daily Milk Production (litres)']\n",
    "X_encoded = pd.get_dummies(X, drop_first=True)\n",
    "\n",
    "# Split the data into training and testing sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_encoded, y, test_size=0.2, random_state=42)\n",
    "\n",
    "# Add a constant for the intercept\n",
    "X_train_sm = sm.add_constant(X_train)\n",
    "\n",
    "# Fit the OLS model with statsmodels\n",
    "model = sm.OLS(y_train, X_train_sm).fit()\n",
    "\n",
    "# Calculate residuals and leverage\n",
    "residuals = model.resid\n",
    "fitted_vals = model.predict(X_train_sm)\n",
    "leverage = model.get_influence().hat_matrix_diag\n",
    "studentized_residuals = model.get_influence().resid_studentized_internal\n",
    "\n",
    "# Create sequence of numbers for plotting\n",
    "sequence = np.arange(len(residuals))\n",
    "\n",
    "# Create the 4 plots\n",
    "fig, axs = plt.subplots(2, 2, figsize=(15, 12))\n",
    "\n",
    "# Residuals vs Fitted Values\n",
    "sns.residplot(fitted_vals, y_train, lowess=True, scatter_kws={'alpha': 0.5}, line_kws={'color': 'red', 'lw': 1}, ax=axs[0, 0])\n",
    "axs[0, 0].set_title('Residuals vs Fitted Values')\n",
    "axs[0, 0].set_xlabel('Fitted Values')\n",
    "axs[0, 0].set_ylabel('Residuals')\n",
    "\n",
    "# Normal Q-Q plot\n",
    "sm.qqplot(residuals, line='45', fit=True, ax=axs[0, 1])\n",
    "axs[0, 1].set_title('Normal Q-Q')\n",
    "axs[0, 1].set_xlabel('Theoretical Quantiles')\n",
    "axs[0, 1].set_ylabel('Standardized Residuals')\n",
    "\n",
    "# Leverage vs Sequence\n",
    "axs[1, 0].scatter(sequence, leverage, alpha=0.5)\n",
    "axs[1, 0].set_title('Leverage vs Sequence')\n",
    "axs[1, 0].set_xlabel('Sequence')\n",
    "axs[1, 0].set_ylabel('Leverage')\n",
    "\n",
    "# Studentized Residuals vs Fitted Values\n",
    "sns.scatterplot(fitted_vals, studentized_residuals, ax=axs[1, 1])\n",
    "axs[1, 1].axhline(y=0, color='red', linestyle='--')\n",
    "axs[1, 1].set_title('Studentized Residuals vs Fitted Values')\n",
    "axs[1, 1].set_xlabel('Fitted Values')\n",
    "axs[1, 1].set_ylabel('Studentized Residuals')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d9962897",
   "metadata": {},
   "source": [
    "Removing Outliers and Plotting again "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "86a03df9",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n",
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  warnings.warn(\n",
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/graphics/gofplots.py:993: UserWarning: marker is redundantly defined by the 'marker' keyword argument and the fmt string \"bo\" (-> marker='o'). The keyword argument will take precedence.\n",
      "  ax.plot(x, y, fmt, **plot_style)\n",
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x864 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import statsmodels.api as sm\n",
    "from statsmodels.graphics.gofplots import ProbPlot\n",
    "from sklearn.model_selection import train_test_split\n",
    "from statsmodels.stats.outliers_influence import OLSInfluence\n",
    "\n",
    "# Load the dataset\n",
    "file_path = '/Users/dhruvtrivedi/Downloads/Final Project Stat 371/Final_Transformed_Farm_Data_Gujarat_v2.csv'\n",
    "data = pd.read_csv(file_path)\n",
    "\n",
    "# Prepare the data for the model\n",
    "X = data.drop('Average Daily Milk Production (litres)', axis=1)\n",
    "y = data['Average Daily Milk Production (litres)']\n",
    "X_encoded = pd.get_dummies(X, drop_first=True)\n",
    "\n",
    "# Split the data into training and testing sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_encoded, y, test_size=0.2, random_state=42)\n",
    "\n",
    "# Add a constant for the intercept\n",
    "X_train_sm = sm.add_constant(X_train)\n",
    "\n",
    "# Fit the OLS model with statsmodels\n",
    "model = sm.OLS(y_train, X_train_sm).fit()\n",
    "\n",
    "# Calculate residuals and leverage\n",
    "residuals = model.resid\n",
    "fitted_vals = model.predict(X_train_sm)\n",
    "leverage = model.get_influence().hat_matrix_diag\n",
    "studentized_residuals = OLSInfluence(model).resid_studentized_internal\n",
    "\n",
    "# Redefine the function to remove outliers based on studentized residuals and QQ plot\n",
    "def remove_outliers(X, y):\n",
    "    # Fit the model\n",
    "    model = sm.OLS(y, X).fit()\n",
    "    \n",
    "    # Get influence measures\n",
    "    influence = model.get_influence()\n",
    "    \n",
    "    # Obtain standardized residuals\n",
    "    studentized_residuals = influence.resid_studentized_internal\n",
    "    \n",
    "    # Identify outliers in studentized residuals\n",
    "    outliers_studentized = np.abs(studentized_residuals) > 4\n",
    "    \n",
    "    # Get theoretical quantiles and sample quantiles for QQ plot\n",
    "    qq_plot = ProbPlot(studentized_residuals)\n",
    "    qq_outliers = np.abs(studentized_residuals) > np.percentile(np.abs(studentized_residuals), 99)  # Top 1%\n",
    "    \n",
    "    # Combine outliers\n",
    "    outliers_combined = outliers_studentized | qq_outliers\n",
    "    \n",
    "    # Remove outliers\n",
    "    X_clean = X.loc[~outliers_combined, :]\n",
    "    y_clean = y.loc[~outliers_combined]\n",
    "    \n",
    "    return X_clean, y_clean\n",
    "\n",
    "# Remove outliers from training set\n",
    "X_train_cleaned, y_train_cleaned = remove_outliers(X_train_sm, y_train)\n",
    "\n",
    "# Refit the model without outliers\n",
    "model_cleaned = sm.OLS(y_train_cleaned, X_train_cleaned).fit()\n",
    "\n",
    "# Recalculate the diagnostics for the cleaned data\n",
    "studentized_residuals_cleaned = OLSInfluence(model_cleaned).resid_studentized_internal\n",
    "leverage_cleaned = OLSInfluence(model_cleaned).hat_matrix_diag\n",
    "fitted_vals_cleaned = model_cleaned.predict(X_train_cleaned)\n",
    "residuals_cleaned = model_cleaned.resid\n",
    "\n",
    "# Diagnostic plots for the cleaned model\n",
    "fig, axs = plt.subplots(2, 2, figsize=(15, 12))\n",
    "\n",
    "# Residuals vs Fitted Values\n",
    "sns.residplot(fitted_vals_cleaned, y_train_cleaned, lowess=True, scatter_kws={'alpha': 0.5}, line_kws={'color': 'red', 'lw': 1}, ax=axs[0, 0])\n",
    "axs[0, 0].set_title('Residuals vs Fitted Values (Cleaned)')\n",
    "axs[0, 0].set_xlabel('Fitted Values')\n",
    "axs[0, 0].set_ylabel('Residuals')\n",
    "\n",
    "# Normal Q-Q plot\n",
    "sm.qqplot(residuals_cleaned, line='45', fit=True, ax=axs[0, 1])\n",
    "axs[0, 1].set_title('Normal Q-Q (Cleaned)')\n",
    "axs[0, 1].set_xlabel('Theoretical Quantiles')\n",
    "axs[0, 1].set_ylabel('Standardized Residuals')\n",
    "\n",
    "# Leverage vs Sequence\n",
    "sequence_cleaned = np.arange(len(leverage_cleaned))\n",
    "axs[1, 0].scatter(sequence_cleaned, leverage_cleaned, alpha=0.5)\n",
    "axs[1, 0].set_title('Leverage vs Sequence (Cleaned)')\n",
    "axs[1, 0].set_xlabel('Sequence')\n",
    "axs[1, 0].set_ylabel('Leverage')\n",
    "\n",
    "# Studentized Residuals vs Fitted Values\n",
    "sns.scatterplot(fitted_vals_cleaned, studentized_residuals_cleaned, ax=axs[1, 1])\n",
    "axs[1, 1].axhline(y=0, color='red', linestyle='--')\n",
    "axs[1, 1].set_title('Studentized Residuals vs Fitted Values (Cleaned)')\n",
    "axs[1, 1].set_xlabel('Fitted Values')\n",
    "axs[1, 1].set_ylabel('Studentized Residuals')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d7d8fd30",
   "metadata": {},
   "source": [
    "“Modern” Forward Selection with AIC"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "5cb4ab33",
   "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>Number of Cows</th>\n",
       "      <th>Number of Buffaloes</th>\n",
       "      <th>Average Daily Milk Production (litres)</th>\n",
       "      <th>Number of Family Members/Employees Working at the Farm</th>\n",
       "      <th>ahmedabad</th>\n",
       "      <th>jamnagar</th>\n",
       "      <th>rajkot</th>\n",
       "      <th>surat</th>\n",
       "      <th>aavin</th>\n",
       "      <th>amul</th>\n",
       "      <th>...</th>\n",
       "      <th>selling privately to consumers</th>\n",
       "      <th>verka</th>\n",
       "      <th>natural plants</th>\n",
       "      <th>Use_of_Automation</th>\n",
       "      <th>Daily Expenditure on Animal Health (INR)</th>\n",
       "      <th>Daily Income from Selling Manure (INR)</th>\n",
       "      <th>Daily Operating Costs (INR)</th>\n",
       "      <th>Daily Revenue (INR)</th>\n",
       "      <th>Satisfaction_5_7</th>\n",
       "      <th>Satisfaction_8_10</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>172</td>\n",
       "      <td>11</td>\n",
       "      <td>1075</td>\n",
       "      <td>38</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>138.745205</td>\n",
       "      <td>118.421918</td>\n",
       "      <td>3088.800000</td>\n",
       "      <td>2565.566667</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>47</td>\n",
       "      <td>23</td>\n",
       "      <td>350</td>\n",
       "      <td>39</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>273.260274</td>\n",
       "      <td>19.208219</td>\n",
       "      <td>1364.300000</td>\n",
       "      <td>1417.200000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>117</td>\n",
       "      <td>187</td>\n",
       "      <td>1520</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>260.575342</td>\n",
       "      <td>19.208219</td>\n",
       "      <td>2756.300000</td>\n",
       "      <td>2164.133333</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>192</td>\n",
       "      <td>130</td>\n",
       "      <td>1610</td>\n",
       "      <td>44</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>68.167123</td>\n",
       "      <td>111.246575</td>\n",
       "      <td>6399.766667</td>\n",
       "      <td>2963.500000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>323</td>\n",
       "      <td>98</td>\n",
       "      <td>2360</td>\n",
       "      <td>25</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>148.049315</td>\n",
       "      <td>53.482192</td>\n",
       "      <td>1567.266667</td>\n",
       "      <td>2755.700000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Number of Cows  Number of Buffaloes  \\\n",
       "0             172                   11   \n",
       "1              47                   23   \n",
       "2             117                  187   \n",
       "3             192                  130   \n",
       "4             323                   98   \n",
       "\n",
       "   Average Daily Milk Production (litres)  \\\n",
       "0                                    1075   \n",
       "1                                     350   \n",
       "2                                    1520   \n",
       "3                                    1610   \n",
       "4                                    2360   \n",
       "\n",
       "   Number of Family Members/Employees Working at the Farm  ahmedabad  \\\n",
       "0                                                 38               0   \n",
       "1                                                 39               0   \n",
       "2                                                 12               0   \n",
       "3                                                 44               0   \n",
       "4                                                 25               1   \n",
       "\n",
       "   jamnagar  rajkot  surat  aavin  amul  ...  selling privately to consumers  \\\n",
       "0         1       0      0      0     0  ...                               0   \n",
       "1         0       0      0      0     0  ...                               0   \n",
       "2         0       1      0      1     0  ...                               0   \n",
       "3         1       0      0      0     0  ...                               1   \n",
       "4         0       0      0      0     0  ...                               0   \n",
       "\n",
       "   verka  natural plants  Use_of_Automation  \\\n",
       "0      0               0                  0   \n",
       "1      0               0                  0   \n",
       "2      0               0                  1   \n",
       "3      0               0                  1   \n",
       "4      1               1                  1   \n",
       "\n",
       "   Daily Expenditure on Animal Health (INR)  \\\n",
       "0                                138.745205   \n",
       "1                                273.260274   \n",
       "2                                260.575342   \n",
       "3                                 68.167123   \n",
       "4                                148.049315   \n",
       "\n",
       "   Daily Income from Selling Manure (INR)  Daily Operating Costs (INR)  \\\n",
       "0                              118.421918                  3088.800000   \n",
       "1                               19.208219                  1364.300000   \n",
       "2                               19.208219                  2756.300000   \n",
       "3                              111.246575                  6399.766667   \n",
       "4                               53.482192                  1567.266667   \n",
       "\n",
       "   Daily Revenue (INR)  Satisfaction_5_7  Satisfaction_8_10  \n",
       "0          2565.566667                 1                  0  \n",
       "1          1417.200000                 0                  0  \n",
       "2          2164.133333                 0                  1  \n",
       "3          2963.500000                 0                  0  \n",
       "4          2755.700000                 1                  0  \n",
       "\n",
       "[5 rows x 26 columns]"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Load the dataset\n",
    "file_path = '/Users/dhruvtrivedi/Downloads/Final Project Stat 371/Final_Transformed_Farm_Data_Gujarat_v2.csv'\n",
    "farm_data = pd.read_csv(file_path)\n",
    "\n",
    "# Display the first few rows of the dataset\n",
    "farm_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "1ba5288a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4762.484478389892"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import statsmodels.api as sm\n",
    "\n",
    "# Dependent variable\n",
    "y = farm_data['Average Daily Milk Production (litres)']\n",
    "\n",
    "# Creating a null model\n",
    "X_null = sm.add_constant(pd.Series(1, index=farm_data.index))\n",
    "null_model = sm.OLS(y, X_null).fit()\n",
    "\n",
    "# AIC of the null model\n",
    "null_model_aic = null_model.aic\n",
    "null_model_aic\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "0f00d9c0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('Number of Cows', 4596.333084168103)"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Identifying the variable that reduces the AIC the most when added to the null model\n",
    "variables = farm_data.columns.drop('Average Daily Milk Production (litres)')  # All variables except the dependent variable\n",
    "aic_values = {}\n",
    "\n",
    "for var in variables:\n",
    "    # Model with the current variable and the intercept\n",
    "    X_current = sm.add_constant(farm_data[var])\n",
    "    model = sm.OLS(y, X_current).fit()\n",
    "    aic_values[var] = model.aic\n",
    "\n",
    "# Finding the variable with the minimum AIC\n",
    "min_aic_var = min(aic_values, key=aic_values.get)\n",
    "min_aic_value = aic_values[min_aic_var]\n",
    "\n",
    "min_aic_var, min_aic_value\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "ae55a147",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4596.333084168103,\n",
       " <class 'statsmodels.iolib.summary.Summary'>\n",
       " \"\"\"\n",
       "                                       OLS Regression Results                                      \n",
       " ==================================================================================================\n",
       " Dep. Variable:     Average Daily Milk Production (litres)   R-squared:                       0.438\n",
       " Model:                                                OLS   Adj. R-squared:                  0.436\n",
       " Method:                                     Least Squares   F-statistic:                     225.8\n",
       " Date:                                    Wed, 29 Nov 2023   Prob (F-statistic):           3.84e-38\n",
       " Time:                                            20:51:24   Log-Likelihood:                -2296.2\n",
       " No. Observations:                                     292   AIC:                             4596.\n",
       " Df Residuals:                                         290   BIC:                             4604.\n",
       " Df Model:                                               1                                         \n",
       " Covariance Type:                                nonrobust                                         \n",
       " ==================================================================================\n",
       "                      coef    std err          t      P>|t|      [0.025      0.975]\n",
       " ----------------------------------------------------------------------------------\n",
       " const           1005.4935     73.516     13.677      0.000     860.801    1150.186\n",
       " Number of Cows     3.8203      0.254     15.027      0.000       3.320       4.321\n",
       " ==============================================================================\n",
       " Omnibus:                       16.412   Durbin-Watson:                   2.046\n",
       " Prob(Omnibus):                  0.000   Jarque-Bera (JB):               27.557\n",
       " Skew:                          -0.345   Prob(JB):                     1.04e-06\n",
       " Kurtosis:                       4.337   Cond. No.                         575.\n",
       " ==============================================================================\n",
       " \n",
       " Notes:\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       " \"\"\")"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Model with \"Number of Cows\" as an independent variable\n",
    "X_cows = sm.add_constant(farm_data['Number of Cows'])\n",
    "model_cows = sm.OLS(y, X_cows).fit()\n",
    "\n",
    "# AIC of the model with \"Number of Cows\"\n",
    "model_cows_aic = model_cows.aic\n",
    "model_cows_aic, model_cows.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "4772fdb7",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "('Number of Buffaloes', 4548.9275276506205)"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remaining variables excluding 'Number of Cows'\n",
    "remaining_vars = variables.drop('Number of Cows')\n",
    "aic_values_with_cows = {}\n",
    "\n",
    "for var in remaining_vars:\n",
    "    # Model with \"Number of Cows\" and the current variable\n",
    "    X_current = sm.add_constant(farm_data[['Number of Cows', var]])\n",
    "    model = sm.OLS(y, X_current).fit()\n",
    "    aic_values_with_cows[var] = model.aic\n",
    "\n",
    "# Finding the variable with the minimum AIC when added to the model with \"Number of Cows\"\n",
    "min_aic_var_with_cows = min(aic_values_with_cows, key=aic_values_with_cows.get)\n",
    "min_aic_value_with_cows = aic_values_with_cows[min_aic_var_with_cows]\n",
    "\n",
    "min_aic_var_with_cows, min_aic_value_with_cows\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "ca02871c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4548.9275276506205,\n",
       " <class 'statsmodels.iolib.summary.Summary'>\n",
       " \"\"\"\n",
       "                                       OLS Regression Results                                      \n",
       " ==================================================================================================\n",
       " Dep. Variable:     Average Daily Milk Production (litres)   R-squared:                       0.525\n",
       " Model:                                                OLS   Adj. R-squared:                  0.522\n",
       " Method:                                     Least Squares   F-statistic:                     159.9\n",
       " Date:                                    Wed, 29 Nov 2023   Prob (F-statistic):           1.75e-47\n",
       " Time:                                            20:51:52   Log-Likelihood:                -2271.5\n",
       " No. Observations:                                     292   AIC:                             4549.\n",
       " Df Residuals:                                         289   BIC:                             4560.\n",
       " Df Model:                                               2                                         \n",
       " Covariance Type:                                nonrobust                                         \n",
       " =======================================================================================\n",
       "                           coef    std err          t      P>|t|      [0.025      0.975]\n",
       " ---------------------------------------------------------------------------------------\n",
       " const                 614.4806     86.306      7.120      0.000     444.612     784.349\n",
       " Number of Cows          3.6088      0.236     15.304      0.000       3.145       4.073\n",
       " Number of Buffaloes     2.7413      0.376      7.299      0.000       2.002       3.480\n",
       " ==============================================================================\n",
       " Omnibus:                       52.428   Durbin-Watson:                   2.030\n",
       " Prob(Omnibus):                  0.000   Jarque-Bera (JB):              223.319\n",
       " Skew:                          -0.655   Prob(JB):                     3.21e-49\n",
       " Kurtosis:                       7.079   Cond. No.                         833.\n",
       " ==============================================================================\n",
       " \n",
       " Notes:\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       " \"\"\")"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Model with \"Number of Cows\" and \"Number of Buffaloes\" as independent variables\n",
    "X_cows_buffaloes = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes']])\n",
    "model_cows_buffaloes = sm.OLS(y, X_cows_buffaloes).fit()\n",
    "\n",
    "# AIC of the model with both \"Number of Cows\" and \"Number of Buffaloes\"\n",
    "model_cows_buffaloes_aic = model_cows_buffaloes.aic\n",
    "model_cows_buffaloes_aic, model_cows_buffaloes.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "d17e3001",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "('Daily Expenditure on Animal Health (INR)', 4543.734658232791)"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remaining variables excluding 'Number of Cows' and 'Number of Buffaloes'\n",
    "remaining_vars_2 = remaining_vars.drop('Number of Buffaloes')\n",
    "aic_values_with_cows_buffaloes = {}\n",
    "\n",
    "for var in remaining_vars_2:\n",
    "    # Model with \"Number of Cows\", \"Number of Buffaloes\" and the current variable\n",
    "    X_current = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', var]])\n",
    "    model = sm.OLS(y, X_current).fit()\n",
    "    aic_values_with_cows_buffaloes[var] = model.aic\n",
    "\n",
    "# Finding the variable with the minimum AIC when added to the model with \"Number of Cows\" and \"Number of Buffaloes\"\n",
    "min_aic_var_with_cows_buffaloes = min(aic_values_with_cows_buffaloes, key=aic_values_with_cows_buffaloes.get)\n",
    "min_aic_value_with_cows_buffaloes = aic_values_with_cows_buffaloes[min_aic_var_with_cows_buffaloes]\n",
    "\n",
    "min_aic_var_with_cows_buffaloes, min_aic_value_with_cows_buffaloes\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "29939a93",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4543.734658232791,\n",
       " <class 'statsmodels.iolib.summary.Summary'>\n",
       " \"\"\"\n",
       "                                       OLS Regression Results                                      \n",
       " ==================================================================================================\n",
       " Dep. Variable:     Average Daily Milk Production (litres)   R-squared:                       0.537\n",
       " Model:                                                OLS   Adj. R-squared:                  0.532\n",
       " Method:                                     Least Squares   F-statistic:                     111.3\n",
       " Date:                                    Wed, 29 Nov 2023   Prob (F-statistic):           7.31e-48\n",
       " Time:                                            20:52:23   Log-Likelihood:                -2267.9\n",
       " No. Observations:                                     292   AIC:                             4544.\n",
       " Df Residuals:                                         288   BIC:                             4558.\n",
       " Df Model:                                               3                                         \n",
       " Covariance Type:                                nonrobust                                         \n",
       " ============================================================================================================\n",
       "                                                coef    std err          t      P>|t|      [0.025      0.975]\n",
       " ------------------------------------------------------------------------------------------------------------\n",
       " const                                      388.2929    120.066      3.234      0.001     151.975     624.611\n",
       " Number of Cows                               3.6876      0.235     15.681      0.000       3.225       4.150\n",
       " Number of Buffaloes                          2.7512      0.372      7.403      0.000       2.020       3.483\n",
       " Daily Expenditure on Animal Health (INR)     1.3503      0.504      2.680      0.008       0.359       2.342\n",
       " ==============================================================================\n",
       " Omnibus:                       47.506   Durbin-Watson:                   2.010\n",
       " Prob(Omnibus):                  0.000   Jarque-Bera (JB):              193.797\n",
       " Skew:                          -0.592   Prob(JB):                     8.27e-43\n",
       " Kurtosis:                       6.812   Cond. No.                     1.27e+03\n",
       " ==============================================================================\n",
       " \n",
       " Notes:\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       " [2] The condition number is large, 1.27e+03. This might indicate that there are\n",
       " strong multicollinearity or other numerical problems.\n",
       " \"\"\")"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Model with \"Number of Cows\", \"Number of Buffaloes\", and \"Daily Expenditure on Animal Health (INR)\" as independent variables\n",
    "X_cows_buffaloes_expense = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)']])\n",
    "model_cows_buffaloes_expense = sm.OLS(y, X_cows_buffaloes_expense).fit()\n",
    "\n",
    "# AIC of the model with these variables\n",
    "model_cows_buffaloes_expense_aic = model_cows_buffaloes_expense.aic\n",
    "model_cows_buffaloes_expense_aic, model_cows_buffaloes_expense.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "2c95d84c",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "('dynamix dairy', 4540.310875080921)"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remaining variables excluding 'Number of Cows', 'Number of Buffaloes', and 'Daily Expenditure on Animal Health (INR)'\n",
    "remaining_vars_3 = remaining_vars_2.drop('Daily Expenditure on Animal Health (INR)')\n",
    "aic_values_with_cows_buffaloes_expense = {}\n",
    "\n",
    "for var in remaining_vars_3:\n",
    "    # Model with current variables and the additional variable\n",
    "    X_current = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)', var]])\n",
    "    model = sm.OLS(y, X_current).fit()\n",
    "    aic_values_with_cows_buffaloes_expense[var] = model.aic\n",
    "\n",
    "# Finding the variable with the minimum AIC when added to the current model\n",
    "min_aic_var_with_cows_buffaloes_expense = min(aic_values_with_cows_buffaloes_expense, key=aic_values_with_cows_buffaloes_expense.get)\n",
    "min_aic_value_with_cows_buffaloes_expense = aic_values_with_cows_buffaloes_expense[min_aic_var_with_cows_buffaloes_expense]\n",
    "\n",
    "min_aic_var_with_cows_buffaloes_expense, min_aic_value_with_cows_buffaloes_expense\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "887cd3f7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4540.310875080921,\n",
       " <class 'statsmodels.iolib.summary.Summary'>\n",
       " \"\"\"\n",
       "                                       OLS Regression Results                                      \n",
       " ==================================================================================================\n",
       " Dep. Variable:     Average Daily Milk Production (litres)   R-squared:                       0.545\n",
       " Model:                                                OLS   Adj. R-squared:                  0.539\n",
       " Method:                                     Least Squares   F-statistic:                     86.07\n",
       " Date:                                    Wed, 29 Nov 2023   Prob (F-statistic):           5.93e-48\n",
       " Time:                                            20:52:53   Log-Likelihood:                -2265.2\n",
       " No. Observations:                                     292   AIC:                             4540.\n",
       " Df Residuals:                                         287   BIC:                             4559.\n",
       " Df Model:                                               4                                         \n",
       " Covariance Type:                                nonrobust                                         \n",
       " ============================================================================================================\n",
       "                                                coef    std err          t      P>|t|      [0.025      0.975]\n",
       " ------------------------------------------------------------------------------------------------------------\n",
       " const                                      399.2683    119.257      3.348      0.001     164.539     633.997\n",
       " Number of Cows                               3.6901      0.233     15.810      0.000       3.231       4.150\n",
       " Number of Buffaloes                          2.8421      0.371      7.663      0.000       2.112       3.572\n",
       " Daily Expenditure on Animal Health (INR)     1.3006      0.501      2.599      0.010       0.315       2.286\n",
       " dynamix dairy                             -342.8210    147.791     -2.320      0.021    -633.712     -51.930\n",
       " ==============================================================================\n",
       " Omnibus:                       36.614   Durbin-Watson:                   2.008\n",
       " Prob(Omnibus):                  0.000   Jarque-Bera (JB):              127.634\n",
       " Skew:                          -0.465   Prob(JB):                     1.93e-28\n",
       " Kurtosis:                       6.103   Cond. No.                     1.58e+03\n",
       " ==============================================================================\n",
       " \n",
       " Notes:\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       " [2] The condition number is large, 1.58e+03. This might indicate that there are\n",
       " strong multicollinearity or other numerical problems.\n",
       " \"\"\")"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Model with \"Number of Cows\", \"Number of Buffaloes\", \"Daily Expenditure on Animal Health (INR)\", and \"dynamix dairy\" as independent variables\n",
    "X_cows_buffaloes_expense_dynamix = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)', 'dynamix dairy']])\n",
    "model_cows_buffaloes_expense_dynamix = sm.OLS(y, X_cows_buffaloes_expense_dynamix).fit()\n",
    "\n",
    "# AIC of the model with these variables\n",
    "model_cows_buffaloes_expense_dynamix_aic = model_cows_buffaloes_expense_dynamix.aic\n",
    "model_cows_buffaloes_expense_dynamix_aic, model_cows_buffaloes_expense_dynamix.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "9989964f",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "('Daily Revenue (INR)', 4538.495387989797)"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remaining variables excluding the ones already in the model\n",
    "remaining_vars_4 = remaining_vars_3.drop('dynamix dairy')\n",
    "aic_values_with_cows_buffaloes_expense_dynamix = {}\n",
    "\n",
    "for var in remaining_vars_4:\n",
    "    # Model with current variables and the additional variable\n",
    "    X_current = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)', 'dynamix dairy', var]])\n",
    "    model = sm.OLS(y, X_current).fit()\n",
    "    aic_values_with_cows_buffaloes_expense_dynamix[var] = model.aic\n",
    "\n",
    "# Finding the variable with the minimum AIC when added to the current model\n",
    "min_aic_var_with_cows_buffaloes_expense_dynamix = min(aic_values_with_cows_buffaloes_expense_dynamix, key=aic_values_with_cows_buffaloes_expense_dynamix.get)\n",
    "min_aic_value_with_cows_buffaloes_expense_dynamix = aic_values_with_cows_buffaloes_expense_dynamix[min_aic_var_with_cows_buffaloes_expense_dynamix]\n",
    "\n",
    "min_aic_var_with_cows_buffaloes_expense_dynamix, min_aic_value_with_cows_buffaloes_expense_dynamix\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "9b51081f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4538.495387989797,\n",
       " <class 'statsmodels.iolib.summary.Summary'>\n",
       " \"\"\"\n",
       "                                       OLS Regression Results                                      \n",
       " ==================================================================================================\n",
       " Dep. Variable:     Average Daily Milk Production (litres)   R-squared:                       0.551\n",
       " Model:                                                OLS   Adj. R-squared:                  0.543\n",
       " Method:                                     Least Squares   F-statistic:                     70.27\n",
       " Date:                                    Wed, 29 Nov 2023   Prob (F-statistic):           9.22e-48\n",
       " Time:                                            20:53:40   Log-Likelihood:                -2263.2\n",
       " No. Observations:                                     292   AIC:                             4538.\n",
       " Df Residuals:                                         286   BIC:                             4561.\n",
       " Df Model:                                               5                                         \n",
       " Covariance Type:                                nonrobust                                         \n",
       " ============================================================================================================\n",
       "                                                coef    std err          t      P>|t|      [0.025      0.975]\n",
       " ------------------------------------------------------------------------------------------------------------\n",
       " const                                      254.6992    140.153      1.817      0.070     -21.163     530.561\n",
       " Number of Cows                               3.3132      0.303     10.940      0.000       2.717       3.909\n",
       " Number of Buffaloes                          2.6365      0.384      6.865      0.000       1.881       3.392\n",
       " Daily Expenditure on Animal Health (INR)     1.3938      0.500      2.785      0.006       0.409       2.379\n",
       " dynamix dairy                             -343.5163    147.085     -2.335      0.020    -633.023     -54.010\n",
       " Daily Revenue (INR)                          0.0894      0.046      1.939      0.053      -0.001       0.180\n",
       " ==============================================================================\n",
       " Omnibus:                       41.229   Durbin-Watson:                   2.039\n",
       " Prob(Omnibus):                  0.000   Jarque-Bera (JB):              169.691\n",
       " Skew:                          -0.482   Prob(JB):                     1.42e-37\n",
       " Kurtosis:                       6.608   Cond. No.                     1.37e+04\n",
       " ==============================================================================\n",
       " \n",
       " Notes:\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       " [2] The condition number is large, 1.37e+04. This might indicate that there are\n",
       " strong multicollinearity or other numerical problems.\n",
       " \"\"\")"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Model with \"Number of Cows\", \"Number of Buffaloes\", \"Daily Expenditure on Animal Health (INR)\", \"dynamix dairy\", and \"Daily Revenue (INR)\" as independent variables\n",
    "X_cows_buffaloes_expense_dynamix_revenue = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)', 'dynamix dairy', 'Daily Revenue (INR)']])\n",
    "model_cows_buffaloes_expense_dynamix_revenue = sm.OLS(y, X_cows_buffaloes_expense_dynamix_revenue).fit()\n",
    "\n",
    "# AIC of the model with these variables\n",
    "model_cows_buffaloes_expense_dynamix_revenue_aic = model_cows_buffaloes_expense_dynamix_revenue.aic\n",
    "model_cows_buffaloes_expense_dynamix_revenue_aic, model_cows_buffaloes_expense_dynamix_revenue.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "c3ebec29",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "('Daily Income from Selling Manure (INR)', 4534.675061447597)"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remaining variables excluding the ones already in the model\n",
    "remaining_vars_5 = remaining_vars_4.drop('Daily Revenue (INR)')\n",
    "aic_values_with_cows_buffaloes_expense_dynamix_revenue = {}\n",
    "\n",
    "for var in remaining_vars_5:\n",
    "    # Model with current variables and the additional variable\n",
    "    X_current = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)', 'dynamix dairy', 'Daily Revenue (INR)', var]])\n",
    "    model = sm.OLS(y, X_current).fit()\n",
    "    aic_values_with_cows_buffaloes_expense_dynamix_revenue[var] = model.aic\n",
    "\n",
    "# Finding the variable with the minimum AIC when added to the current model\n",
    "min_aic_var_with_cows_buffaloes_expense_dynamix_revenue = min(aic_values_with_cows_buffaloes_expense_dynamix_revenue, key=aic_values_with_cows_buffaloes_expense_dynamix_revenue.get)\n",
    "min_aic_value_with_cows_buffaloes_expense_dynamix_revenue = aic_values_with_cows_buffaloes_expense_dynamix_revenue[min_aic_var_with_cows_buffaloes_expense_dynamix_revenue]\n",
    "\n",
    "min_aic_var_with_cows_buffaloes_expense_dynamix_revenue, min_aic_value_with_cows_buffaloes_expense_dynamix_revenue\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "66ff45de",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4534.675061447597,\n",
       " <class 'statsmodels.iolib.summary.Summary'>\n",
       " \"\"\"\n",
       "                                       OLS Regression Results                                      \n",
       " ==================================================================================================\n",
       " Dep. Variable:     Average Daily Milk Production (litres)   R-squared:                       0.560\n",
       " Model:                                                OLS   Adj. R-squared:                  0.551\n",
       " Method:                                     Least Squares   F-statistic:                     60.49\n",
       " Date:                                    Wed, 29 Nov 2023   Prob (F-statistic):           4.91e-48\n",
       " Time:                                            20:54:15   Log-Likelihood:                -2260.3\n",
       " No. Observations:                                     292   AIC:                             4535.\n",
       " Df Residuals:                                         285   BIC:                             4560.\n",
       " Df Model:                                               6                                         \n",
       " Covariance Type:                                nonrobust                                         \n",
       " ============================================================================================================\n",
       "                                                coef    std err          t      P>|t|      [0.025      0.975]\n",
       " ------------------------------------------------------------------------------------------------------------\n",
       " const                                      324.8131    142.055      2.287      0.023      45.204     604.423\n",
       " Number of Cows                               3.1565      0.307     10.267      0.000       2.551       3.762\n",
       " Number of Buffaloes                          2.4193      0.392      6.179      0.000       1.649       3.190\n",
       " Daily Expenditure on Animal Health (INR)     1.5309      0.500      3.064      0.002       0.547       2.514\n",
       " dynamix dairy                             -354.3768    145.952     -2.428      0.016    -641.658     -67.096\n",
       " Daily Revenue (INR)                          0.1416      0.051      2.796      0.006       0.042       0.241\n",
       " Daily Income from Selling Manure (INR)      -2.3922      0.999     -2.395      0.017      -4.358      -0.426\n",
       " ==============================================================================\n",
       " Omnibus:                       41.608   Durbin-Watson:                   1.997\n",
       " Prob(Omnibus):                  0.000   Jarque-Bera (JB):              182.316\n",
       " Skew:                          -0.464   Prob(JB):                     2.57e-40\n",
       " Kurtosis:                       6.758   Cond. No.                     1.37e+04\n",
       " ==============================================================================\n",
       " \n",
       " Notes:\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       " [2] The condition number is large, 1.37e+04. This might indicate that there are\n",
       " strong multicollinearity or other numerical problems.\n",
       " \"\"\")"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Model with \"Number of Cows\", \"Number of Buffaloes\", \"Daily Expenditure on Animal Health (INR)\", \"dynamix dairy\", \"Daily Revenue (INR)\", and \"Daily Income from Selling Manure (INR)\" as independent variables\n",
    "X_cows_buffaloes_expense_dynamix_revenue_manure = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)', 'dynamix dairy', 'Daily Revenue (INR)', 'Daily Income from Selling Manure (INR)']])\n",
    "model_cows_buffaloes_expense_dynamix_revenue_manure = sm.OLS(y, X_cows_buffaloes_expense_dynamix_revenue_manure).fit()\n",
    "\n",
    "# AIC of the model with these variables\n",
    "model_cows_buffaloes_expense_dynamix_revenue_manure_aic = model_cows_buffaloes_expense_dynamix_revenue_manure.aic\n",
    "model_cows_buffaloes_expense_dynamix_revenue_manure_aic, model_cows_buffaloes_expense_dynamix_revenue_manure.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "01f3b55f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('natural plants', 4533.348318074137),\n",
       " ('ahmedabad', 4534.355307372128),\n",
       " ('orissa state cooperative milk producers federation', 4534.665866602294),\n",
       " ('Satisfaction_8_10', 4534.951309362047),\n",
       " ('rajkot', 4535.053675950745),\n",
       " ('Satisfaction_5_7', 4535.150696268097),\n",
       " ('mother dairy', 4535.560928900199),\n",
       " ('Daily Operating Costs (INR)', 4535.843033901934),\n",
       " ('Use_of_Automation', 4536.014085080088),\n",
       " ('selling privately to consumers', 4536.42579364268)]"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remaining variables excluding the ones already in the model\n",
    "remaining_vars_6 = remaining_vars_5.drop('Daily Income from Selling Manure (INR)')\n",
    "aic_values_next_candidates = {}\n",
    "\n",
    "# Testing the addition of each of the remaining variables to the current model\n",
    "for var in remaining_vars_6:\n",
    "    # Model with current variables and the additional variable\n",
    "    X_current = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)', 'dynamix dairy', 'Daily Revenue (INR)', 'Daily Income from Selling Manure (INR)', var]])\n",
    "    model = sm.OLS(y, X_current).fit()\n",
    "    aic_values_next_candidates[var] = model.aic\n",
    "\n",
    "# Sorting the variables by their potential to reduce AIC and selecting the top 4-8 candidates\n",
    "sorted_candidates = sorted(aic_values_next_candidates.items(), key=lambda x: x[1])[:10]\n",
    "sorted_candidates\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "3bbc752b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4533.348318074137,\n",
       " <class 'statsmodels.iolib.summary.Summary'>\n",
       " \"\"\"\n",
       "                                       OLS Regression Results                                      \n",
       " ==================================================================================================\n",
       " Dep. Variable:     Average Daily Milk Production (litres)   R-squared:                       0.565\n",
       " Model:                                                OLS   Adj. R-squared:                  0.554\n",
       " Method:                                     Least Squares   F-statistic:                     52.72\n",
       " Date:                                    Wed, 29 Nov 2023   Prob (F-statistic):           8.10e-48\n",
       " Time:                                            20:55:19   Log-Likelihood:                -2258.7\n",
       " No. Observations:                                     292   AIC:                             4533.\n",
       " Df Residuals:                                         284   BIC:                             4563.\n",
       " Df Model:                                               7                                         \n",
       " Covariance Type:                                nonrobust                                         \n",
       " ============================================================================================================\n",
       "                                                coef    std err          t      P>|t|      [0.025      0.975]\n",
       " ------------------------------------------------------------------------------------------------------------\n",
       " const                                      263.4881    145.523      1.811      0.071     -22.952     549.928\n",
       " Number of Cows                               3.1322      0.307     10.219      0.000       2.529       3.735\n",
       " Number of Buffaloes                          2.4058      0.390      6.167      0.000       1.638       3.174\n",
       " Daily Expenditure on Animal Health (INR)     1.5835      0.499      3.176      0.002       0.602       2.565\n",
       " dynamix dairy                             -344.7849    145.476     -2.370      0.018    -631.132     -58.438\n",
       " Daily Revenue (INR)                          0.1444      0.050      2.862      0.005       0.045       0.244\n",
       " Daily Income from Selling Manure (INR)      -2.3928      0.995     -2.405      0.017      -4.351      -0.435\n",
       " natural plants                             119.7209     66.367      1.804      0.072     -10.913     250.355\n",
       " ==============================================================================\n",
       " Omnibus:                       38.512   Durbin-Watson:                   1.998\n",
       " Prob(Omnibus):                  0.000   Jarque-Bera (JB):              178.080\n",
       " Skew:                          -0.383   Prob(JB):                     2.14e-39\n",
       " Kurtosis:                       6.748   Cond. No.                     1.40e+04\n",
       " ==============================================================================\n",
       " \n",
       " Notes:\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       " [2] The condition number is large, 1.4e+04. This might indicate that there are\n",
       " strong multicollinearity or other numerical problems.\n",
       " \"\"\")"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Model with \"Number of Cows\", \"Number of Buffaloes\", \"Daily Expenditure on Animal Health (INR)\", \"dynamix dairy\", \"Daily Revenue (INR)\", \"Daily Income from Selling Manure (INR)\", and \"natural plants\"\n",
    "X_current_final = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)', 'dynamix dairy', 'Daily Revenue (INR)', 'Daily Income from Selling Manure (INR)', 'natural plants']])\n",
    "model_final = sm.OLS(y, X_current_final).fit()\n",
    "\n",
    "# AIC of the final model\n",
    "model_final_aic = model_final.aic\n",
    "model_final_aic, model_final.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "1e99ac8f",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(4533.348318074137,\n",
       " <class 'statsmodels.iolib.summary.Summary'>\n",
       " \"\"\"\n",
       "                                       OLS Regression Results                                      \n",
       " ==================================================================================================\n",
       " Dep. Variable:     Average Daily Milk Production (litres)   R-squared:                       0.565\n",
       " Model:                                                OLS   Adj. R-squared:                  0.554\n",
       " Method:                                     Least Squares   F-statistic:                     52.72\n",
       " Date:                                    Wed, 29 Nov 2023   Prob (F-statistic):           8.10e-48\n",
       " Time:                                            20:55:37   Log-Likelihood:                -2258.7\n",
       " No. Observations:                                     292   AIC:                             4533.\n",
       " Df Residuals:                                         284   BIC:                             4563.\n",
       " Df Model:                                               7                                         \n",
       " Covariance Type:                                nonrobust                                         \n",
       " ============================================================================================================\n",
       "                                                coef    std err          t      P>|t|      [0.025      0.975]\n",
       " ------------------------------------------------------------------------------------------------------------\n",
       " const                                      263.4881    145.523      1.811      0.071     -22.952     549.928\n",
       " Number of Cows                               3.1322      0.307     10.219      0.000       2.529       3.735\n",
       " Number of Buffaloes                          2.4058      0.390      6.167      0.000       1.638       3.174\n",
       " Daily Expenditure on Animal Health (INR)     1.5835      0.499      3.176      0.002       0.602       2.565\n",
       " dynamix dairy                             -344.7849    145.476     -2.370      0.018    -631.132     -58.438\n",
       " Daily Revenue (INR)                          0.1444      0.050      2.862      0.005       0.045       0.244\n",
       " Daily Income from Selling Manure (INR)      -2.3928      0.995     -2.405      0.017      -4.351      -0.435\n",
       " natural plants                             119.7209     66.367      1.804      0.072     -10.913     250.355\n",
       " ==============================================================================\n",
       " Omnibus:                       38.512   Durbin-Watson:                   1.998\n",
       " Prob(Omnibus):                  0.000   Jarque-Bera (JB):              178.080\n",
       " Skew:                          -0.383   Prob(JB):                     2.14e-39\n",
       " Kurtosis:                       6.748   Cond. No.                     1.40e+04\n",
       " ==============================================================================\n",
       " \n",
       " Notes:\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       " [2] The condition number is large, 1.4e+04. This might indicate that there are\n",
       " strong multicollinearity or other numerical problems.\n",
       " \"\"\")"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Model with \"Number of Cows\", \"Number of Buffaloes\", \"Daily Expenditure on Animal Health (INR)\", \"dynamix dairy\", \"Daily Revenue (INR)\", \"Daily Income from Selling Manure (INR)\", and \"natural plants\"\n",
    "X_current_final = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)', 'dynamix dairy', 'Daily Revenue (INR)', 'Daily Income from Selling Manure (INR)', 'natural plants']])\n",
    "model_final = sm.OLS(y, X_current_final).fit()\n",
    "\n",
    "# AIC of the final model\n",
    "model_final_aic = model_final.aic\n",
    "model_final_aic, model_final.summary()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d123a11b",
   "metadata": {},
   "source": [
    "Final Plots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "6cce9448",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
      "  x = pd.concat(x[::order], 1)\n",
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  warnings.warn(\n",
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/statsmodels/graphics/gofplots.py:993: UserWarning: marker is redundantly defined by the 'marker' keyword argument and the fmt string \"bo\" (-> marker='o'). The keyword argument will take precedence.\n",
      "  ax.plot(x, y, fmt, **plot_style)\n",
      "/Users/dhruvtrivedi/opt/anaconda3/lib/python3.9/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABC4AAANYCAYAAAAL86z0AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOzdeXib1Zn38e/RYsm7kzhxHEMWlkAghbKVrUDL1rR0ZW9pyVBaA+kApaXb0GXolHlhCqUMDIUUWjaXFkppaYGwBGigBNoECARCQgiJsziOs1jeJFuyzvvHIzmyI9uyLVmS/ftcly9Lj7ZbjyRb537ucx9jrUVEREREREREJBe5sh2AiIiIiIiIiEh/lLgQERERERERkZylxIWIiIiIiIiI5CwlLkREREREREQkZylxISIiIiIiIiI5S4kLEREREREREclZSlyIjCHGmAuMMU8PcPkLxpivpeFxPmaM2TTS+0mnwZ57mh5jvTHm1Azcb1peFxERERGRsUiJC5EsiQ2Cg8aYNmPMVmPMPcaYkpHcp7W2zlp7erpizEWxpEk0tt/iP3/t+9yNMdYYs1+f22Uk2WKM+YExZkmS7ZXGmC5jzNxMPK6IiIikTgcKRPKXEhci2fUZa20J8GHgMOAH2Q0nb2yx1pYk/Hwmy/HcDxxnjJnVZ/v5wFvW2pVZiElERGRUxQ7KNBpjihO2fc0Y80IWw0qZMeYgY8xjxpiAMabVGPOcMeaYFG/7b8aYt4wxHbEDUrcbY8ozHbPIeKHEhUgOsNZuBZ7CSWAAYIw5xhjzsjGm2RizwhjzsYTL/s0Ysy72T/UDY8wFCdtfSrjeacaYd2P/gG8DTMJl/2mMeSDh/MxYlYIndv4iY8yq2GOsM8Zc0l/8xpjvGWM2x6672hhzSpLrHBP7R+5O2PYFY8ybsdMfMcYsM8a0xL70/GIo+zDxuSdUP6yIVWTMB54EpiVUaUwzxriMMd83xrxvjNlhjHnIGDMx4T6/YozZELvsmv4e21q7CXgO+Eqfiy4E7jXGTDDG/M0Y02SM2RU7vVc/z2Ow16XcGHO3MaYhts9/Ft+nxpj9jDF/j73e240xfxjKPhQREUkDD3DlSO/EOEZtrGKM2Rf4B/AWMAuYBvwZeMYY85FBbvtt4AbgO0A5cAwwE3jaGOPNXNQi44cSFyI5IDaI/SSwNna+Bngc+BkwEbgaeMQYMzl2FON/gU9aa0uB44A3ktxnJfAI8EOgEngfOH4IYW0DPg2UARcBNxtjDk/yOAcA/w4cFYvnE8D6vtez1r4CtAMnJ2z+EvC72OlbgFustWXAvsBDQ4i172OdGDt5aKwi416c/ZtYqbEFuAL4PHASzheUXcD/xZ7XQcCvcJIR04BJQNJkQ8y9JCQuYvvlw8CDOH9rfwvMAKYDQeC2YT69e4EIsB9Olc7pQLzs9b+Ap4EJsVhvHeZjiIiIDNfPgauNMRXJLjTGHGeM+Vcsyf4vY8xxCZe9YIy5zhjzD6AD2CeWvF9gjHkvdoDkv4wx+xpjlsYOdjxkjCmI3T7lAwVJ/Cew1Fp7jbV2p7W21Vr7v8ADOEmJpIwxZcC1wOXW2kXW2rC1dj1wLk4C5EspPr6IDECJC5Hs+rMxphXYiJMo+Els+5eBJ6y1T1hro9baZ4BlwKdil0eBucaYQmttg7X27ST3/SngHWvtH621YeCXwNZUA7PWPm6tfd86/o4zID4hyVW7AR9wkDHGa61db619v5+7fRD4IoAxpjQW44Oxy8LAfsaYSmttWyzR0Z9pxqlEif+cm+rz6uMS4Bpr7SZrbSfOl5azY9UNZwN/s9YuiV32I5z93p9HgaqEL2AXAk9aa5ustTustY9Yazusta3AdTjJkiExxlThJGC+aa1tt9ZuA27GmZICzj6cAUyz1oastS/1c1ciIiKZsgx4AeegSy+xqsbHcQ7ATAJ+ATxujJmUcLWvALVAKbAhtm0ecAROJcN3gYXABcDewFxi3y0Y2YGC04CHk2x/CDjBGOPv53bHAX7gT4kbrbVtONWeY7r3mMhoUeJCJLs+H6tS+BhwIE5lBDj/cM9JHJwDHwWqrbXtwHnApUCDMeZxY8yBSe57Gk5CBABrrU08PxhjzCeNMa8YY3bGHv9TCfH1sNauBb6JM+jfZoz5vTFmWj93+zvgTGOMDzgTeM1aG/9ScjEwG3g3dgTm0wOEt8VaW5HwM9zqjBnAown7eBVOIqaKPfdfO7Cjvzuy1nbgfOG50BhjcL5Q3QtgjCkyxtwZm3bSAiwBKkzCtJkhxOvFed3jMd8JTIld/l2c6UD/NMa8bYz56hDvX0REJB1+DFxujJncZ/sZwHvW2vuttRFr7YPAu0Bir6p7rLVvxy4Px7bdYK1tiR2oWQk8ba1dZ60N4CQHDgMY4YGCSqAhyfYGwI1TAdvf7bZbayP93LbvPhCRYVDiQiQHxCoa7gFujG3aCNzfZ3BebK29Pnb9p6y1pwHVOP/wf53kbhtwjkQAzlzRxPM40zaKEs5PTbiuD2eayY1AlbW2AniChB4ZfeL/nbX2ozgDa0s/JZXW2ndwjp58kt7TRLDWvmet/SLOIPwG4I8moblXGtgk2zbiTLlJ3M9+a+1m9tx/RThHhwZyL05p6Gk4R4r+Ftv+beAA4OjYVJj4VJZk+7Pf1yUWbydQmRBvmbX2YHB6pVhrv26tnYZTTXK7SVhZRUREZDTEmlL/Dfh+n4umsbuKIm4DUJNwPtlBlsaE08Ek50tgxAcKtuN8r+qrGuc7xHZjzAlmd6+stxNuVxnvRZXktk0pPLaIDEKJC5Hc8UvgNGPMh3HmU37GGPMJY4zbGOM3znKeexljqowxn40N6juBNpwqgb4eBw42xpwZ+2d6Bb0HwW8AJxpjphun63XiiiYFONM/moCIMeaT9FPqaIw5wBhzcizZEcL5ApEsnrjfxWI5kYSSTGPMl40xk621UaA5tnmg+xlMI7BPn/OTTO8O33cA1xljZsRimGyM+Vzssj8CnzbGfDQ2d/anDP4388VY7AuB31tru2LbS3H2S3OsTPYnyW8ODPC6WGsbcKbs3GSMKTNOc9F9jTEnxeI/J2Eu7y6cL1oj2YciIiLD9RPg6/ROSmzBOciRaDqwOeF8sgMNqRrKgYK+ngXOSbL9XOAVa22XtfbFhF5ZB8cuX4rzfezMxBvFvqd9Evj7MJ6HiPShxIVIjrDWNgH3AT+y1m4EPgf8B07yYCNOp2pX7OfbOP/8d+KUQC5Icn/bcf4BX48zxWF/nG7Z8cufAf4AvAksZ3d1ALHyyitw5nXuwqmOeKyf0H2xx9iO00NjSizu/jyIMzXmuViMcfOAt40xbTiNOs+31oYGuJ/B/CfOih7NxphzrbXvxh57XWzbtNjjPIbT9bsVeAU4GiBWjvoNnERLA85+2DTQA8am49yH86XsvoSLfgkU4uyjV4BFA9xHv69LzIU4iaV3YjH9kd1HiI4CXo3tw8eAK621HwwUs4iISCbEppL+Aef7RNwTwGxjzJeMMR5jzHnAQez5v264hnKgoK9rcZY2v84YM9EYU2qMuRynQXm/9xObrnItcKsxZp4xxmuMmYlzcGY7UDfM5yIiCYzzPVtERERERGT4jDHrga9Za5+Nnd8beA+nYuFjsW0fxTlwsB/OampXxptJG2NeAB6w1t6VcJ8W2D+WCME4S5/fZa29J3b+Z8BUa+3XYgclfgcciXOA5yac6kqvtTaS7P77xD8X52DMiUAx0Ap80Vr7ZArP/WLgqtjz8uFUWnzJOquYicgIKXEhIiIiIiKSIDb18hXgJ9bau4d426/iVGEcb62tz0R8IuNNsiYyIiIiIiIi45a1dlOsx9fnjDElseVNU73tb4wxYZylUpW4EEkDVVyIiIiIiIiISM5Sc04RERERERERyVnjdqpIZWWlnTlzZrbDEBERGbOWL1++3Vo7OdtxjJS+M4iIiGRIUxNs3Mhyawf8zjBuExczZ85k2bJl2Q5DRERkzDLGbMh2DOmg7wwiIiJp1tEBl14K998Pn/wk5sknB/zOoKkiIiIiIiIiIjI63nsPjjkGHngAfvpT+NvfBr3JuK24EBEREREREZFR9Je/wIUXgscDTz4Jn/hESjdTxYWIiIiIiIiIZE4kAt//Pnz+8zB7Nrz2WspJC1DFhYiIiIiIiIhkSmMjfPGL8PzzcMklcMst4PMN6S6UuBARERERERGR9Fu6FM4+G3buhHvugfnzh3U3mioiIiIiIiIiIuljLdx6K5x4Ivj9TgJjmEkLUOJCRERERERERNKlvR0uuACuuAI++UlYvhw+/OER3aUSFyIiIiIiIiIycqtXw9FHwx/+ANddB3/+M1RUjPhu1eNCREREREREREbmkUfgooucxptPPQWnnpq2u1bFhYiIiIiIiIgMTyQCV1/tNOE86CBnqdM0Ji1AFRciIiIiIiIiMhxbt8J558GSJbBgAfziF0Ne6jQVSlyIiIiIiIiIyNC89BKccw4EAnD//fDlL2fsoTRVRMaNVQ0Bbn5mDVc/vIKbn1nDqoZAtkMSEREREZFRVFcHM2eCy+X8rqvLdkR5yFq4+Wb42MegpARefTWjSQtQ4kLGiVUNARYu+YBAMEx1uZ9AMMzCJR8oeSEiIiIiMk7U1UFtLWzY4Iy9N2xwzit5MQStrXD++fCtb8FnPgPLlsGHPpTxh1XiQsaFRSsbKS/0Ul7oxWVMz+lFKxuzHZqIiIiIiIyCa66Bjo7e2zo6nO2SglWr4CMfgT/+EW64Af70JygvH5WHVo8LGRc2NwepLvf32lbq97C5OZiliEREREREZDTV1w9tuyR46CH46lehuBgWL3amiYwiVVzIuFBTUUhrKNJrW2soQk1FYZYiEhERERGR0TR9+tC2CxAOwze/6awccuihzlKno5y0ACUuZJyYN7eKQDBMIBgmam3P6Xlzq7IdmoiIiIiIjILrroOiot7bioqc7ZLEli3w8Y/DLbfAFVfA889DTU1WQlHiQsaFOdXl1J44i/JCLw2BEOWFXmpPnMWc6tGZkyUiIiIiItl1wQWwcCHMmAHGOL8XLnS2Sx9//zscfji88QY8+KCTvCgoyFo46nEh48ac6nIlKkRERERExrELLlCiYkDWwk03wfe/D/vt5/SzOPjgbEelxIWIiIiIiIjIuNfSAhdd5KwWcvbZcPfdUFaW7agAJS5ERERERERExreVK+HMM2HdOqfi4qqrnPk0OUI9LkRERGTcMca4jTGvG2P+lu1YREREsup3v4Ojj4bWVqcB57e+lVNJC1DiQkRERManK4FV2Q5CREQka7q64PLLnaYfRxzhLHV6wgnZjiopJS5ERERkXDHG7AWcAdyV7VhERESyYtMmOOkkuO02p8Ji8WKors52VP1SjwsREREZb34JfBco7e8KxphaoBZg+vTpoxOViIjIaHjuOTj/fAgG4aGH4Jxzsh3RoFRxISIiIuOGMebTwDZr7fKBrmetXWitPdJae+TkyZNHKToREZEMikbh+uvhtNOgshL+9a+8SFqAKi5ERERkfDke+Kwx5lOAHygzxjxgrf1yluMSERHJnOZmmD8fHnsMzjsP7roLSkqyHVXKVHEhI7KqIcDNz6zh6odXcPMza1jVEMh2SCIiIv2y1v7AWruXtXYmcD7wnJIWIiL5q64OZs4El8v5XVeX7Yhy0JtvwpFHwhNPwC23wIMP5lXSApS4kBFY1RBg4ZIPCATDVJf7CQTDLFzygZIXIiIiIiKScXV1UFsLGzaAtc7v2lolL3q57z445hinn8ULL8AVV+TcUqepUOJChm3RykbKC72UF3pxGdNzetHKxmyHJiIiMihr7QvW2k9nOw4RERmea66Bjo7e2zo6nO3jXmcnXHaZMz3k6KOdpU6PPz7bUQ2bEhcybJubg5T6e7dJKfV72NwczFJEIiIiIiIyXtTXD237uFFfDyecAHfcAd/9LjzzDFRVZTuqEVHiQoatpqKQ1lCk17bWUISaisIsRSQiIiIiIuNFf6tVj+tVrJ9+Gg4/HN59F/70J7jhBvDk/5ocSlzIsM2bW0UgGCYQDBO1tuf0vLn5nc0TEREREZHcd911UFTUe1tRkbN93IlG4Wc/g3nzoLoali2DL3wh21GljRIXMmxzqsupPXEW5YVeGgIhygu91J44iznV5dkOTURERERExrgLLoCFC2HGDKff5IwZzvkLLsh2ZKNs1y747GfhRz+CL30JXnkFZs/OdlRplf81I5JVc6rLlagQEREREZGsuOCCcZioSPT663DWWbBpE/zf/zkNOfNw1ZDBqOJCREREREREJN/85jdw7LEQDsOSJbBgwZhMWkAWExfGmL2NMc8bY1YZY942xlwZ2z7RGPOMMea92O8JCbf5gTFmrTFmtTHmEwnbjzDGvBW77H+NGaOvloiIiIiIiIxvoRB8/etw8cXw0Y86S50ec0y2o8qobFZcRIBvW2vnAMcA3zDGHAR8H1hsrd0fWBw7T+yy84GDgXnA7cYYd+y+fgXUAvvHfuaN5hMRERERERERybj16+H44+Guu+A//gOeegomT852VBmXtcSFtbbBWvta7HQrsAqoAT4H3Bu72r3A52OnPwf83lrbaa39AFgLfMQYUw2UWWuXWmstcF/CbURERERERETy35NPOkudvv8+/OUvzvIpbvfgtxsDcqLHhTFmJnAY8CpQZa1tACe5AUyJXa0G2Jhws02xbTWx0323J3ucWmPMMmPMsqamprQ+BxEREREREZG0i0bhP/8TzjgDpk+H5cudVUTGkawnLowxJcAjwDettS0DXTXJNjvA9j03WrvQWnuktfbIyeOgnEZERERERETy2I4dTsLi2mvhwgvh5Zdh332zHdWoy2riwhjjxUla1Flr/xTb3Bib/kHs97bY9k3A3gk33wvYEtu+V5LtIiIiIiIiIvlp2TI44gh47jm480747W+hqCjbUWVFNlcVMcDdwCpr7S8SLnoMmB87PR/4S8L2840xPmPMLJwmnP+MTSdpNcYcE7vPCxNuIyIiIiIiIpI/rIWFC50mnNbCSy9Bbe2YXeo0FZ4sPvbxwFeAt4wxb8S2/QdwPfCQMeZioB44B8Ba+7Yx5iHgHZwVSb5hre2O3e4y4B6gEHgy9iMiIiIiIiKSP4JBWLAA7rkHTj8d6uqgsjLbUWVd1hIX1tqXSN6fAuCUfm5zHXBdku3LgLnpi05ERERERERkFK1bB2edBW+8AT/+sfMzTlYNGUw2Ky5ERERERERE5G9/g698xZkO8vjj8KlPZTuinJL1VUVERERERERExqXubvjhD+Ezn4FZs5ylTpW02IMqLkRERERERERGW1MTfOlL8OyzcPHFcNtt4PdnO6qcpMSFiIiIiIiIyGh69VU45xzYtg3uustJXEi/NFVEREREREREZDRYC7ffDiec4DTefPllJS1SoMSFiIiIiIiISKZ1dMCFF8I3vgGnneb0szj88GxHlReUuBARERERERHJpPfeg2OOgbo6+OlP4a9/hYkTsx1V3lCPCxEREREREZFM+ctfnEoLjweefBI+8YlsR5R3VHEhIiIiIiIikm6RCHz/+/D5z8Ps2fDaa0paDJMqLkRERERERETSqbERvvhFeP55uOQSuOUW8PmyHVXeUuJCREREREREJF1eftlZ6nTnTrjnHpg/P9sR5T1NFREREREREREZKWvh1lvhpJPA74dXXlHSIk2UuBAREREREREZibY2uOACuOIK+OQnnaVODz0021GNGUpciIiIiIiIiAzX6tXOUqd/+ANcdx38+c9QUZHtqMYU9bgQERERERERGY5HHoGLLnIabz71FJx6arYjGpNUcSEiIiIiIiIyFJEIXH01nH02HHSQs9SpkhYZo4oLERERERERkVRt3QrnnQdLlsA3vgG/+AUUFGQ7qjFNiQsRERERERGRVLz4Ipx7LgQC8MADTkNOyThNFREREREREREZiLVw883w8Y9DSQm8+qqSFqNIiQsRERERERGR/rS2wvnnw7e+BZ/5DCxbBh/6ULajGleUuBARERERERFJZtUq+MhH4I9/hBtugD/9CcrLsx3VuKMeFyIiIiIiIiJ9PfQQfPWrUFwMixfDxz6W7YjGLVVciIiIiIiIiMSFw/DNbzorhxx6qLPUqZIWWaXEhYiIiIiIiAjAli1OA85bboErr4QXXoCammxHNe5pqoiIiIiIiIjICy84VRbt7fDgg05DTskJqrgQERERERGR8cta+PnP4dRTYcIE+Oc/lbTIMUpciMioWtUQ4OZn1nD1wyu4+Zk1rGoIZDskEREREclRdXUwcya4XM7vuro0P0BLC5x9Nnz3u/CFLzhJi4MOSvODyEgpcSEio2ZVQ4CFSz4gEAxTXe4nEAyzcMkHSl6IiIiIyB7q6qC2FjZscIoiNmxwzqctebFyJRx5JPzlL3DTTc4qImVlabpzSSclLkRk1Cxa2Uh5oZfyQi8uY3pOL1rZmO3QRERERCTHXHMNdHT03tbR4Wwfsd/9Do4+Glpb4fnn4VvfAmPScMeSCUpciMio2dwcpNTfuydwqd/D5uZgliISERERkVxVXz+07Snp6oLLL4cLLoAjjnCWOj3hhBHcoYwGJS5EZNTUVBTSGor02tYailBTUZiliEREREQkV02fPrTtg9q0CU46CW67Db79bVi8GKqrhx2fjB4lLkRk1MybW0UgGCYQDBO1tuf0vLlV2Q5NRERERHLMdddBUVHvbUVFzvYhW7wYDjvM6Wvx8MNw443g9aYlTsk8JS5EZNTMqS6n9sRZlBd6aQiEKC/0UnviLOZUl2c7NBERERHJMRdcAAsXwowZTvuJGTOc8xdcMIQ7iUbh//0/OP10mDwZ/vUvZxURySuewa8iIpI+c6rLlagQERERkZRccMEQExWJmpth/nx47DE47zy46y4oKUlneDJKlLgQERERERGRseXNN+HMM501VG+5xWnIqVVD8pamioiIiIiIiMjYcd99cMwxEAzCCy/AFVcoaZHnlLgQERERERGR/NfZCZdd5kwPOfpoZ6nT44/PdlSSBkpciIiIiIiISH6rr4cTToA77oDvfQ+eeQaqtHLdWKEeFyIiIiIiIpK/nn4avvQlCIfh0Ufh85/PdkSSZqq4EBERERERkfwTjcLPfgbz5kF1tbPUqZIWY5IqLkRERERERCS/7NoFX/kKPP64s17qnXdCcXG2o5IMUeJCRERERERE8sfrr8NZZ8GmTfB//+c05NSqIWOapoqIiIiIiIhIfvjNb+DYY51+FkuWwIIFSlqMA0pciIiIiIiISG4LheDrX4eLL3ZWD3ntNTjmmGxHJaNEiQsRERERERHJXR98AMcfD3fdBddcA4sWweTJ2Y5KRpF6XIiIiIiIiEhuevJJp/lmNAqPPQaf+Uy2I5IsUMVFzKqGADc/s4arH17Bzc+sYVVDINshiYiIiIiIjBt1dTBzJrhcMGtGlDfP/E844wyYPh2WL1fSYhxT4gInabFwyQcEgmGqy/0EgmEWLvlAyQsREREREZFRUFcHtbWwYQNMsDu4vf4MDnn0Wt7/6IXw8suw777ZDlGySIkLYNHKRsoLvZQXenEZ03N60crGbIcmIiIiIiIy5l1zDXR0wBEsYzlHcDLPUcudnLLht1BUlO3wJMuUuAA2Nwcp9fdu91Hq97C5OZiliERERERERMaP+g2Wr7OQf3A8BstHeYlfU0v9Ri11KkpcAFBTUUhrKNJrW2soQk1FYZYiEhERERERGSeCQf5Q/FUWcgnP83EO5zWWcRTgtLcQUeICmDe3ikAwTCAYJmptz+l5c6uyHZoMkZqsioiIiIjkvngjzv3M+7xTfizntN/Df3t+zBk8zk4mAc4Mkeuuy26ckhuUuADmVJdTe+Isygu9NARClBd6qT1xFnOqy7MdmgyBmqyKiIiIiOS+eCPOuRv+xjKOYGq4njN9j7Pp69ey9ww3xsCMGbBwobMSqohn8KuMD3Oqy5WoyHOJTVaBnt+LVjbqtRURERERyRE/+o9uftDxE37IdbzGYZzFI6zvnMWMJ2D9+mxHJ7lIiYs0W9UQYNHKRjY3B6mpKGTe3CoNmkfJ5uYg1eX+XtvUZFVEREREJPvq6mIrh2xooo4vcRrPchcX8+/cRifOd/j6+iwHKTlLU0XSSFMVsktNVkVEZDDGmL2NMc8bY1YZY942xlyZ7ZhERMa6+NSQqg2vsowjOIEXuZi7+Dp39SQtQI04pX9KXKRR4lQFlzE9pxetbMx2aOOCmqyKiEgKIsC3rbVzgGOAbxhjDspyTCIiY9o1/2GZ33E7L3IC3bg5jpf5DRf3uo4accpAlLhIo83NQUr9vWffaKrCyKW6UoiarIqIyGCstQ3W2tdip1uBVUBNdqMSERmb6urgwOkd/Ff9hdzON3iG0ziC5bzO4T3XUSNOSYV6XKRRTUUhgWC4pykkaKrCSMWn35QXentNv+kvIaEmqyIikipjzEzgMODVJJfVArUA01W7LCIyZHV1cMPX3uOh0FnMZSU/4qdcxzXYhGPnM2aoGaekRhUXaaSpCumn6TciIpIJxpgS4BHgm9balr6XW2sXWmuPtNYeOXny5NEPUEQkz71w1V94MXQkNWzmkzzJz/hRr6SFpobIUKjiIo3iUxUSVxU576i9VAEwAvm2UohWlRERyX3GGC9O0qLOWvunbMcjIjKW/O6+CIHLf8ivW27gXxzJ2fyRemb0us6MGU7SQlNDJFVKXKSZpiqkVz5NvxnqtBYRERl9xhgD3A2sstb+ItvxiIiMJY/c3kjN5V/kS9HnuYNLuJJb6MLX6zqaHiLDkdWpIsaY3xhjthljViZsm2iMecYY817s94SEy35gjFlrjFltjPlEwvYjjDFvxS7739iXEhkD8mn6jaa1iIjkheOBrwAnG2PeiP18KttBiYjkvZdf5vgrDucj0aXM5x4u4449khaaHiLDle0eF/cA8/ps+z6w2Fq7P7A4dp7YUmXnAwfHbnO7McYdu82vcBpo7R/76XufkqfyaaUQrSqTW1JdjUZExhdr7UvWWmOtPcRa++HYzxPZjktEJG9ZC7feSvTEk2jrLuQYXuE+5u9xNa0cIiOR1aki1tolsY7eiT4HfCx2+l7gBeB7se2/t9Z2Ah8YY9YCHzHGrAfKrLVLAYwx9wGfB57McPgySvJl+k0+TWsZ6zRtR0RERGQUtLVBbS08+CBPuj/DBdxHgIo9rqbpITJSudjjospa2wDOWuvGmCmx7TXAKwnX2xTbFo6d7rt9D1raTDJp3twqFi75AHAqLVpDEQLBMOcdtVeWIxt/EqftAD2/F61sVOIiw9SgVkREZJxYvZrmU86kdPO7/JD/5obu7/VaNSRO00MkHbI9VWQokvWtsANs33OjljaTDMqnaS1jnabtZEe80iUQDPeqdNE0HRERkTHmkUcIf/gowpu38Qme4np+kDRpAZoeIumRixUXjcaY6li1RTWwLbZ9E7B3wvX2ArbEtu+VZLvIqMuXaS25Jt1H6TVtJztU6SIiIjLGRSLw/e/DTTfxGkdzNg+zqdcQrbcZM5S0kPTIxYqLx6Cnm8t84C8J2883xviMMbNwmnD+MzatpNUYc0xsNZELE24jIjkuE0fp82k1mrFElS4iIiJj2NatcMopcNNN3OH5BiewZMCkhaaISDplteLCGPMgTiPOSmPMJuAnwPXAQ8aYi4F64BwAa+3bxpiHgHeACPANa2137K4uw1mhpBCnKacac0reGO89ATJxlD4+bSdxv5531F7jar9mgypdRERExqgXX4RzzyWyM8BF5gEeiAxcRjFjhpO0ULWFpEu2VxX5Yj8XndLP9a8D9sjbWWuXAXPTGJrIqNDqF85R+upyf69t6ThKr2k7o08NakVERMYYa+GXv4TvfIeWyftwqutp/mU/1O/Vi4rU00IyIxenioiMG4nVBi5jek4vWtmY7dBGTU1FIa2hSK9tOkqfn9SgVkREZAxpbYXzzoNvfQs++1mO9/6Lf4X6T1q43UpaSObkYnNOkXEjU9UG+URH6ccWVbqIiIiMAatWwZlnwpo18D//A1dfzdvuZIs5OlRpIZmmxIVIFqkngPpRjDfjvaeLiIhIznvoIfjqV6G4GBYvho99jLo6cLmgu3vPq6vSQkaDEhciWaRqA4eO0o8P6ukiIiKSw8Jh+M534JZb4LjjnARGTQ11dVBbmzxpoUoLGS3qcSGSReoJIOOJerqIiIjkqC1b4OMfd5IWV14JL7wANTUAXHMNdHTseRNVWshoUsWFSJap2kDGC/V0ERERyUEvvOA04WxvhwcfhPPP73VxfX3ym0WjSlrI6FHiQsY0zacXyR3p7umiz7eIiMgIWAs33gg/+AHsvz88/zwcdBAAdXVOpcWGDf3ffPr0UYpTBE0VkTEsPp8+EAz3mk+/qiGQ7dBExqV5c6sIBMMEgmGi1vacnje3asj3pc+3iIjICLS0wNlnw3e/C1/4Avzzn72SFrW1AyctiorguutGKVYRlLiQMUzz6UVySzp7uujzLSIiMkwrV8KRR8Jf/gI33eQ04Swt7bm4v54WceptIdmgqSIyZmk+vYxHuT59Il09XfT5Hl+MMROAva21b2Y7FhGRvPa738HXvw5lZc7UkBNO2OMqA1VagHpbSHao4kLGrJqKQlpDkV7bRjKfXiTXjafpE5n4fK9qCHDzM2u4+uEV3PzMmjG53/KJMeYFY0yZMWYisAL4rTHmF9mOS0QkL3V1weWXOxmHI46A117bI2lRVweVlYPflXpbSDYocSFjVjrn04vkg/E0fSLdn+/xlPTJI+XW2hbgTOC31tojgFOzHJOISP7ZtAlOOgluuw2+/W1YvBiqq3tdJd7XYseOge9KvS0kW5S4kDErnfPpRfLB5uYgpf7eMwDH6vSJdH++x1PSJ494jDHVwLnA37IdjIhIXlq8GA47zOlr8fDDzioiXu8eVxusrwXAjBnqbSHZox4XMqalaz69jC253gdiqOLP550tLbzX2MrB08qYXOr0f0j39Khc2nfp/HyrZ0ZO+inwFPCStfZfxph9gPeyHJOISH6IRuGGG+CHP4QDD4Q//QkOOKDXVVJZ8jRuxgxYvz4zoYqkQhUXIjKujLUpAYnP59C9y2gNRXh13U4aW4Jpnx6V6X2XzR4T6omTe6y1D1trD7HWLoidX2etPSvbcYmI5LzmZmeJ0//4Dzj3XHj11T2SFgsWwFe+klrSQtNDJBeo4qIfuXRUUUTSJ3FKANDze9HKxrz8jPd+Pl6O3dewcnMLKzYFOP2gqZx31F5pe16Z3HfxpEh5obdXUmS0pnfNm1vFwiUfAE6lRWsoQiAY5ryj9sr4Y0tvxphbAdvf5dbaK0YxHBGR/PLmm3DmmU5G4pZbnIacxvS6yoIF8KtfpXZ3kyY5d6PpIZJtSlwkke0v0CK5ZKwl8cbalIC+z6eyxM+Js300BEJcddrsjD4WpG/fZTuhFO+ZkfheT2fSR4ZkWbYDEBHJS/fdB5deChMmwAsvwPHH97q4rg6uvHLwBpyJtm9Pb4giw6XERRLZ/gItu421QXO+GYtJvJqKQgLBcM/nGvJ7SkC6n89An7lM7rtcSCipJ05usNbem+0YRETySmcnfPObcMcd8LGPwe9/D1W7p4nW1cEll0B7+9DudsaMtEYpMiLqcZHEeOrMn8vGWi+CfDQWV1rIh2Vyh9LrIZ3PZ7DPXCb3nXpMSF/GmMnGmBuNMU8YY56L/2Q7LhGRnFJfDyec4CQtvvc9eOaZXkmLBQvgy18eetKioEB9LSS3KHGRhL5A54Z8GjQ//uZmzr1zKSf9/HnOvXMpj7+5OdshpcVYTOLl+jK5Q03YpfP5DPaZy+S+y4eEkoy6OmAVMAu4FlgP/CubAYmI5JSnn4bDD4fVq+HRR+H668HjfG+rq4OSktR7WSSaNAl+8xv1tZDcoqkiSahJW27IhdLxVDz+5mauf3I1xT4PU0oKaAmGuf7J1QCccUhNlqMbmbE2rSIul6cEJJuqtrOtk5889g7TJxYlnTKVrueTymcu/ljxKSV3v7Q+LdO41GNCkphkrb3bGHOltfbvwN+NMX/PdlAiIlkXjTrlED/5CRx8sLPU6f77A8ObFmKM0xrj9tszFK9IGihxkYS+QOeGfBk037u0nmKfJ2Gg6erZvs/kkrzu0aEk3ujrmzxoag2xprGNcDTK0bMmZrTPSKqfuUz1PsnlhJJkRTj2u8EYcwawBdAfHxEZ33btctYxffxxZw7IHXdAcTEwtNVC4rRqiOQLTRXpx5zqcq46bTY3nnMoV502W1+msyBfSscbW0KU+ty9tpX63NTvaM/7Hh25Pq1iLOo7VW1tUzsYqCzxZXzKVKqfuXyaxiV57WfGmHLg28DVwF3AVdkNSUQki15/HY44wpki8n//56wiEkta1NU5OYyhuOwyZ9UQJS0kH6jiQnJWvlS+VJX5aQmGeyotAFo7u3G5zB4l/5B/q9PoKPjo6lvlsrOtC7cL9ptS3HOdTE2ZSvUzly/TuCS/WWv/FjsZAD6ezVhERLLuN79xSiomT4YlS+CYY3pdfM01YG1qd1VS4iQ5lLCQfKLEheS0fBg0zz92ek9Pi1Kfm9bObto7I0yfWDTmGltK5vVNHkwsKaC6zEdlye5EQSanTKXymcuXaVyS34wxvwX2+Bpurf1qFsIREcmOUAguvxzuugtOPRV+9zsnedFHfX1qd3fZZeplIflJiQuREYo34Lx3aT2NLSGqyvxcfvK+rGls1+BOhiUxeZC4ykgm+4zEm22m0o8lHb1PhvJ4Mm79LeG0H/gCTp8LEZHx4YMP4Oyz4bXXnJKKa68Ft3uPq9XVOQ02B6q4UJWF5DtjU60pGmOOPPJIu2zZsmyHIWNYYgPDxMGdekTIUGV6kD+c9+pIYtJnY/wwxiy31h6ZpvtyAc9aa09Ox/0Nhb4ziMioe/JJJ8sQjcL998NnPpP0anV1cNFFEA4nvVgJC8kbg31nUMWFSIbkS48OyX2ZnjKVbAnW+Pa+j9s3YXHxR2cOObahPJ5Igv2B6dkOQkQko7q74ac/hf/6LzjkEHjkEdh3336vfuWV/SctJk1ymm+KjAVKXIhkUD706BBJtdlmupZBVXNPSYUxphWnx4WJ/d4KfC+rQYmIZNKOHU5pxFNPwfz5ztqmhf1PMa6rc27Sn507MxCjSJYocSEikoNGswdEqs02+6uUeGDpBipL/SnHquaekgprbWm2YxARGTXLljn9LBoa4M474etfdxpXDODSSwe+y+mqUZMxRIkLGfPUBFDyTboqG1KVarPNZJUSnZEI/1i7k5MPnJJyrLOrirl18ftEopaJxV6mlvlxu11pbziaTvo7MnqMMYcPdLm19rXRikVEJOOshV//2lk5ZOpUeOklOOqofq9eV+dMDxmo0gKgoACuuy7NsYpkkRIXMqaN9gBQZDj6DoqbWkOj2gMi1X4sySol3tnSyoSi1GNd1RDg2VVNHDC1hIZAiB3tXbSEIlx+8r45+5nU35FRd1Pstx84EliBM13kEOBV4KNZiktEJL2CQViwAO65Bz7xCScrMWlSv1dfsMCZPTIYlwt+8xs15JSxRYkLyTnpPLI5HpsA6shwfkk2KH5p7Q6O23dirwRBpntApNKPJVllxq6OMMftO7HX9QaKNfEzObOyBIBAMMyaxnbOSMPzyITx+Hckm6y1HwcwxvweqLXWvhU7Pxe4OpuxiYikzfvvw1lnwYoV8OMfOz9JljqNO/VUWLw4tbu+7z4lLWTscWU7AJFE8UFcIBjudWRzVUNgWPe3uTlIqb93fm4sNwFM9/6TzEscFLuMobzQy4QiL6saWntdL1s9IFY1BLj5mTVc/fAKFq1s5NQ5kykv9NIQcKpCPrrfJPze3p+xgWLNx89kPsY8RhwYT1oAWGtXAh/OXjgiImny17/CEUdAfT08/jhce23akhbGKGkhY5MqLiSnpPvI5nhrApjPR4bHa6VIsr4RB00r5R9rdxIIhgfsOZFpyapBnl3V1GuKRPw6MHB/jLh8/EzmY8zZFv88eyqmzhzJ3Rhj7gIewFlV5MvAqnTEJyKSFd3d8JOfOM0nDj8c/vhHmDWr36vX1cEll0B7e+oPMVjDTpF8pYoLySnpPrI5b24VgWCYQDBM1Nqe0/PmVqUj3JyTzSPDiUfmb35mzZCqPMZbpUjivqrf2UH9jt7fSHweDyfsN6lXZUO6+ymk8nolqwYpL/SyaGVjz3Xi/TFSjTUfP5P5GHM2JX6ebXekawR3dRHwNnAl8E3gndg2EZH809QE8+Y5SYuLL4Z//KPfpEVdHZSUwJe/PLSkxSmnwO23pylekRyjigsBcudod7qPbKbadHCsyNaR4ZE2L0xnpUiuvJf703dfdYW7ea2+GYDpk4p7KhYy2fgx1dcrsRqkqTXE2qZ2WoNhMPTar/Hf8f0eT2zMqS5P+nrk22dyvP0dGam+n+fhstaGgJtjPyIi+evVV+Gcc2DbNrjrLidx0cdwqiviJk2CW27RFBEZ25S4kJzqmJ/qsoxDkUrTwbEiE/svFSNNPCSbLjGcSpFcei/3p+++mjXZaVDZ0NKJ1+MelUFxqq9XPBHWFXGSKz6PC6/bYIzptV9XNQT4yV/eZv2OdkLhbvxeN0vf387842bw7KqmXq/H/yxazbRyP53dNicTS/3J178j2UjkJfs8D4Ux5iFr7bnGmLdwpoj0Yq09ZCTxiYiMGmudZUC++U2oqYGXX3amiMSkurRpf045BZ59Nj2hiuQ6TRWRlMrBR8tQy86lt2ztv5FOUampKKQ1FOm1bTiVIrn0Xu5Psn01o7KY6ROLuPGcQ7nqtNk583rFp0i8vaUFn9sA0NVtmVtT1mu/3rr4Pd7Z0kJ3FEp8Hrqj8M6WFm5+5r1er0dXpJv6HR2s3NIyLqYEZVu2pmAl+zwP0ZWx358GPpPkR0Qk93V0wIUXwje+AaedBsuX75G0uOgiJS1EUqWKC0nb0e50yfaRzVyfajCYbOy/kU5RSVelSK69l5PJhUaPqcYQT4R9+6E3idoo5YUFzK0po7LET9Tanv269P2dRKJRurssXRFDYYGbAo+Ljbt6J0jWNrVT4nPT1R3tSSxBfjSPzUfZatab+HkeDmttQ+zkdiBorY0aY2YDBwJPpiFEEZHMeu89Z6nTlSvhpz+Fa64BV+/jxVdeCeHw8O7+ssvUy0LGHyUuhiDfB7T9yYWBVK7Ih6kGoynV9/xIEw/p6iGQ7L1cv6OdtU3tfPKWJRgMh+1dzpePnTGqr2d8P77TEKChOURTWydTy/wcNK0Un8czqiuGrGoIsL01xItrdzChyMuc6lL83v5jmFNdzmkHVfX7N2JVQ4C2zghuF7hdhqh1Liv0unquF79dWyiCxwVl/t33k2uJJRg7f+uzlchL/Dwbt6dgBHe1BDjBGDMBWAwsA84DNItbRHLXn/8M8+eD1wuLFsHpp4+of0VfSlrIeKWpIikay6seqGP+bpmaajCSFTeyZSjv+XRMUZlTXc5Vp80e0XSJvu/l9dvbeGXdDgIdYQpcBo8Llq7byY1Pjd5rEN+P67e3Ub+jg7ZQmFC4mw+2t/P4m1vZFgiOWmIsHovX4+b4/SYC8PL7O+mKdA97JZBFKxsp9bmxFqy1mFhLgvbObvau8Pe6nddtaOvsZr8pxT33nWtJ0rH0tz5dU7CGI/55jjRvXT+CuzHW2g7gTOBWa+0XgIPSEqCISLpFIvD978MXvgCzZztTQ04/nQULhr46SDIlJfDAA0payPilxEWK8mHu/HCpr8RumVhONF8HQkN9z6cj8TBSfd/LDS2dlBcWMKmkAH+Bh8ICD6V+D9vbOkftsxvfj1tbOolaS2tnN16Xi2Kfm2kVhazb0TEqcSTGUl7oZUppIR87YAqH7V3O2qZ27n5pfb9JtYH+RmxuDnLUrIk91Rbd8VaKBq46fXav2x08rYxZlcV43e6cTZKOpb/1s6uKeWXdDv725haWvr+d9dvbcm5/D8IYY47FqbB4PLZNlaIiknsaG+H00+GGG5zSipdeghkzWLDA6c05EpMmOQmL1latGiLjm74ApCgf5s6PRLb7SuSKTEyb6W+e+QNLN1BZ6s/ZcvRsvudHUqoffy+vagjwrYdW0NgaoqjATXGBh45wN13hKBbLO8NMHA01tvh+bAmFae/sxuMCt8tFV3eUMr+HHe1dI+45kGpMfV/T7W0h3t3aSncUjp41ccCpUf39jaipKCTg83DS7Mms2BygvbMbv8fF4dMrOOOQmp7b9hdrri0rOtz3fa5NL1nVEODZVU3MnlLC1pYQO9vDtAQjXH7Kvjm1vwfxTeAHwKPW2reNMfsAz2c3JBGRPl5+2VnqdOdOXq69h9MfmE/7nSO7S00HEdnTkBMXxhgXUGKtbclAPDlLfSDGh0wsJ5psINQZifCPtTs5+cApOdtLYyTv+ZEM4tLRZyR+HwVuFz6Pi47Obna0dVHi8+BxG6JRw8YdQVY1BIa0v4cTW3w/lvm9bA2EKPS66I5aCjwuOiNRJhUXpKWiJ5WY+r6ma7e1Y4xhYol32M0y45+ZqvJCzqoq7fnM1J44K+n1s5kkTeV9OZz3/eNvbubW594n3O28nuFINwuXdGT185yYMI0vuRsIhlnT2M4ZWYlo6Ky1fwf+bowpjp1fB1yR3ahERGKshdtug299C2bMoPaQV/j1wkNHdJcFBfCb36iyQiSZlKaKGGN+Z4wpi315eAdYbYz5TmZDyy3qAzE+ZGLaTLJ55u9saWVCUW6Xow/3PT/SqTHpKNWP38fcmjKKvG5CkSjGQCjcTVfEUur3MLuqhP999j3OvXMpJ/38ec69cymPv7k57bHF9+PUMh8uAx1dUSJRS0mBh85IlOpy/5AToIk9U37y2Dt0d0dTiqnva7q9rRMs7Dd5d8+JoVbV5MtUs1Tfl0N9369qCHDr4vcBmFRcQGckyurGNqLRaFY/z8OZ9pZrvXiMMccaY94BVsXOH2qM0TFIEcm+tjYnu3DFFbxZ80kq3l/Gr/85sqSF36+khchAUq24OMha22KMuQB4AvgesBz4ecYiyzGJXdLfaQgQCEYo83t6vpjm2pf0TMi1UuhMGckR4cff3My9S+tpbAlRVeZn/rHTk1Zx7OoIc9y+E3vdNtemHvW30gfAzc+s6fd9MNIlGNMxRSV+Hy7j5fj9K/nbmw10hrvptrD3xEI+VFPOjrZOXly7g+kTi5hSUkBLMMz1T64G6JnikI7YEvdjY0uI97a1U1jgoqLIqZBwuVxDSoD2rbB4vX4XLR1hSvweJpf6B42p0Ovi1Q92YDAUed3MqizuuR0Mr5IsH6aapfq+HOoKN4tWNhKJWiYWezHG4Pe6AWgIhPB63Bl+Vv0bauVIjq6o9EvgE8BjANbaFcaYE7MVjIgIAO++y5bjzqJq17v8kP/mhg3fw46gbaAxcOmlmhoiMphUExdeY4wX+Dxwm7U2bIyxg9xmzIl/eavf2UFNRRGlfk+ufLnLuBz9UptTHn9zM9c/uZpin6fXQPj7nzxgj4HQR/ebREGfQU0uTj3qOyBN5X2Q6uA+WZLnjENq0jItK/E+Kkv8HDi1zJmuUejl2H0mAbB41TbcwKZdHYS7o3jdLsr8Hu5dWt9v4mK4se3ej7NHnADsOwCvLPERCIZZ29Tek4BIFlPia3fqnCpaQxFWbm7mrc0B3mloZWKxl6llftxu16gtzTqahpJ0GkoiZnNzkInFXjoj0Z6khc/jYkd7F8fuWznywIdpqNPeRppwzBRr7UZjTOKm7mzFIiLjW10dPHnxH/lV50V4KOR0nuY5ThnWfamHhcjQpZq4uBNYD6wAlhhjZgDjqsdFXK5+ucu08fq8h+LepfUU+zwJ+8jVs/2hS45NmgCA9PXSGA2pvA8GGtzHB+2vvL+dVVtbmVRSsEe1Qzr6jPS9j6llPrY0B5k9pcRZ2SMUoTkYJtIdpcDjwut2+k40tXYS7u4/JztvbhU/+cvbrN/RTijcjd/rZuakYq793MG9rjdQcmKk1Qmbm4N4XPBOQwttoQhuFwS7IkS6bc9zS7a/+r52XZFudrWH8bqd6o8d7V20hCJcfvLImzcme/7xGFJN2KS7witTfYpqKgrpCnezZlsb4CQtWkIRvO6hVdKk21ArR3K0AfVGY8xxgDXGFOD0t1iVzYBEZHw59VRYvBjcRLie7/MAN/EKR3M2f2Qzw/vOpqSFyPCklLiw1v4v8L8JmzYYYz6emZByW45+ucu48fq8h6KxJcSUkoJe20p9bhpbQntcd6iDilyRyvugv8TDUTMreo74b9wVxGUMLcEIJQnJnniSZ6T7pu/+nVlZwukHV7Gmsb3nPl0G3C6Dx+UczfW4DN1RQzDc/wHddU1tbNjRTncUCtxuuqOwYUc765raeuJLtTppuAPzArfh1XU7KfF7KPG56YxE6Y5Cid9FQyDU7/7q+9qtbWqnxOemK2p7KgPS0bzx8Tc3c+vi93umTzS1BHnsjc0Ew91UlfmZU106aMVWJiq8MtF4d/f9dvRavcPjMjmxekdPkiwahXDY+Wludn5HIr1+H9K8iY7NIcq84IpEcEUiBIOdzHJbeHxT0tuk9HtkLgVuAWqATcDTwIKR3qmIyGDq6uArX3H6b1axlT9wHiexhNv4Bt/iF4QpGPxO+pg0CW65RT0sRIZrwMSFMeZbg9z+F2mMJS+M19VFMvG8hzNwG+0+G0N5vKoyPy3BcE+lBUBrpzNYSyYf+gL0lcr7oL+kTOIR//auboq8LqIWdrZ3UVTg6ZXkGem+6e91SxyQ37/0A9o6u+mMRIlGLVELGPDTf8XFvUvrmVDs6/X8A8Fwr+klqVSljGRgbmCPCAs8Lj68VznXnXlIv7fr+9q1hSJ4XFDm3/1cRpqMXNUQ4Nbn3gcDE4u97Oro4t2WTgxOJQLAGxsDHD69oqeBaLLnu2hlI9FolFUNLbSEnBVZppb5RlThlalk4ZzqcmqPn86zr9VTEQqzd5nh4/uUs5+3BVZsh66u3T+dnb3Pj3RbqteNRMDr3f3j8ezx+zzjZnuoGxO7TtjlpgsX1ZWl8FJh0tsM+Lu42Pk9Atba7UDPV3xjzAScxMV1I7pjEZEk6urgkkugvX33to/yIg9xLuUEuIAH+B2pZx08HrjnHiUqRNJlsIqL0lGJIgs27Qpy8zNrhjzwzdRRu1yX7uc9nIHbaPfZGOjxlqzZxr1L63sGgvOPnc78Y6f3THco9blp7eymvdMpvR8rUn0fJEs83P3S+p4j/sU+N13haM+SoDBwkmcoUn2f7FdVxvuNLQRCESzgdjlVF16Pp99lUlOpqkmlKmUkU686uy1H7zOBdU0dPYP6g6aV0jnAFBfo/dp1RiLsaOukvTPCzMpitreFqCzxjzgZuWhlY8+SoMYYOrq6KXC7aO9ypk7Ee0CsbWrn6FkT+02SvNMQoH5HB36vm1Kfh1C4m3e3ttIxQDVML9EoBIPQ0QEdHby/YRuvrNzErh0BpnuinF3lY++wgSd2X6fXT8JtCYV6/wSDe2ybE40yp7DQaQnv8zm/CwqcH59v9+nEn362N3VZVu/qYlcYSkrLOHDWJKonlw/5fnpt93ic7m8D8AEtSRJ+JSP92/q97w35JsaYvYEfAdOAR4EHgZ8CF8ZOi4ikRbJkhcPyTX7Jz/kO69iH03malXwo5fvVdBCR9BswcWGtvXa0AhltXrcZ1sA3X0v8Ryrdz3s4A7eRHoUdarVGfzFe99d3eG1TMwVuN2U+Nx2d3dyyeC1XnrIf3//kAb0aTl5+8r79NnocTkzZNpL3QeIR/0NryvnH+zuIRC2FXheBYDhtSZ5U31vzj53OD/60khKfl6ICF50RS7g7yodqyvp9T6VSVZNKVcpIpl7F7/+YWJNRcKo+ppQOfHQ7/to9sHQD/1i7k7JCD4UFbiJRy7L1uzhwaiku18gac25uDvYsCer3OtNYvG6DteA24Al3MaErRHhnBx6aOcR0w7+6WL+pidfebSCws4UqT5S567dxWGeIcsL4ujop6AphOjooiXbBE6WDJxs6O6GwEIqKCPv8lFgPJ/sLiRYWEvL6aPb4KNurkvJJ5T3Xo6gIpkzZfbqoyLksnpBI9hO/zJNqu6iBJSbd4onBx4LhUWuCnENVYPcBfwceAeYBrwBvA4dYa7dmMzARGRvq6uCrX3WK0voqoZW7uZhzeZg/8QUu4re0MPjfRq0OIpJZKX3bMsb4gYuBg4Geb9vW2q9mKK5RMdwGkzn05W5UpfN5D2fgNpKjsMOp1ugvxuUbm/F53BT7nKPHxT6g05lG8PL3TxkwUTHSmHLBcN8HiUf896sqpaMrwsotrRhjKCv0DjvJ03f721sCzKku63XbZO+tMw6p4f5X6tmwo532rm6KfR6OnjWBfaeUsrk5mPTxklXV7OroYp9JRVz98ApqKgqZXVXMs6uaeh43WVVKKsmN/p5vKlUv/d12TnU5laV+Tj5wCuV+Dzt3tbJxy046mtuItm/jyuP3Yp9Na+C9IASDbNy8nbfWNtK2q4VKd5SDJ3ip8lonSRD/iScNgkGu2LyD7vYOoh1B/JFOPJ0hCro68Uc6KYiEibpcdHl9dHl9RP1+SiaUEfT7iXYaDi30Y/2FBL0+Ih2WiM+PLSqi21fIzqJy2kunUFRRAqcd3Du5kJhkiJ/2+3sqDG57Zs0e+zp+/qrTZqfwzh09aoLcY6K19j9jp58yxjQCR1lrO7MYk4jkuf6rK3abwzs8wlnMZg3f4X+4katxJmn2T9UVIqMj1cNE9wPv4qyn/lOcOadjorO3Gkxmx3B6ZgSCEYwxPeXm8SO6geDgDeCGMyDoL8ZI1FLh7f1PrNDrVPAMRbKYdrZ18pPH3mH6xKK8qMAYir7VGh+ePpHvf2pOytUyyZI8p86ZzLOrmnpt37QrSJHXzazJJT237++9dfSsSRw4tWyPQW2B2/SbVEqsqin1eZgxsYgp5YU9yyM/u6qJU+dM7tUItG9VymDJh57n6/ewty9KZNMmHlvxFoUHlDGnyMW3gtt4a0UDbTsDTHZ1c3CFmylvdUN7O7u2N9O+fhvzwiEKwyFcwSCuYAedrm58XSFqA20UdHXiDnc6iQSPj5DXR5e3gAn3V0BpMRQW0uby0tweZXqs6qDD4+Mdlxf3/lVUTp7gVCfEKxJiiQPbEeWxd3fS6S1gS6dhY9CyPermwFlTmDS5nLcbO9jVEeaj+03iK8fOYFJ1OTcnSSy8sHobwa5uKooLaAtFKPF7mFrqc17TISYbhpIkzXYFlJog7xbrZxH/Q7sVKDLGFANYa3dmLTARyUsLFsCvfjXwdc7lD9zNxbRTzCks5u98rN/rlpTAHXeof4XIaEo1cbGftfYcY8znrLX3GmN+BzyVycBGy3horJmLhtMzo8zvoaUjTCjcjS/eG8E625NJHIS8s6WFQ/cuA1JvRNhfjBWFXoJh61RaxATDttfAKxV9BylNrSHWNLYRjkY5etbEvKnAGIqhVGskvn71OzuYWurbI/F079J6Dqou67X9gKoSVm9toyXYxZpt7bSGIhR4XNSeOHOPx+jvNS7yuvpNdF112uyeypC+g+747zWN7XsezY9GYedOaGhgztatXL1tHe+/+T7RrY1UhtuZ7u6ibGE7BAJUNzRxXWsLvo42oh4vncUlBItKiRSXwLRJ7F1czN7FxU7CoLgYosVQWAwTJvBatIJA5Wy8ZaWE/YVEfIXsMl58ZSX826kHcf8/G9gZddPu8rB8cys+jwtrLcYY9plc0vN++3U/lQpvDFCpMAM4Pfa6eZqDfDRWgRJP4nzsgCl7JAOSDdYPmlbKP9bu5KDqsl6vy3CWF001SZoLFVDjtflzEuXAcnof5nwt9tsC+4x6RCKSlwaaEhLnIczP+Q7f5Bb+wXGcw8M0MG2P651yCjz7bAaDFZEBpZq4iB9KbjbGzMU5+jEzIxGNokAwPC4aa+ai4fRKOHhaOUVeN1tbO3uOws6YWNTryHpcfBDS3R1la0uIhuYgW5qDHLfvRPavcqYRDDYg6C/GA6cWc8vitdDpVFoEw5au7m4uO3bWkPZB30HK2qZ2MFBZ4sNlzHguE99jEPnKuu28v62NtzYHmFzmZ7/JxUwq8dHYEuLoWRN73Xb6pGLWbW/nnx/sImItbpfBHYXfvLSevSYU9ZqO0t9rfPdL65lY0vvPY7JEV3zQbbojlOzYRum2Lcxu3IKpr4c/hWHTJti6FRoaYNs2KC2F6mqYOpWa2A+z58LEiVBeDhUVUFHBHS9voWzqZMIlpUS9TjPQqLU0BELceM6hA+67Jx9eQXW5H1dCM8aotbwXCMGMGZxU4CxLu66xDZ/buU5Xt+WIGeV43e6e99twj/4nS04NtLxqssG6z+PhhP0mUV7oHXFPnVSTpLkwTWO8Nn/uy1o7M9sxiEj+O/VUWLx44OtUs4WHOJeP8g9+yZV8h58TofeBKFVXiOSGVBMXC2Nlmz8CHgNKgB9nLKpREO52jpCPh8aauWqovRKcL/UdKR2FXbSyke7uKGu2teHzuJhW4WfjriAvv7+T8iIvPo8npQFBshjj5xNXFbns2FlcctL+e9x+oNLzvoOUnW1duF2w35TintsPNlDMdml7puJKHERubwsR7IrSHbV0RqJ0hrt5rb6Z2VNKqCpzVsLoe4R6ayCEx+Oi1OvC7TJ0Ry3BcJTbX1i3Rx+NZK9x38G0KxLGXV/PcTs2wx1Lob4eNmzgqjdXU9y4hdJd2+momEjrlGnsmDSVUHUNfOgw+OQnexIVTJnirPSQAt+uNWwLhin3Dv3I+2BH7ePJmm8/9CZRG6W8sIC5NWVUlviJWtvzfhuto//9DdbTVemQapI0F6ZpjNfmzyIi6XbwwfDOOwNf5yRe4A+cRzHtnM+D/IHzey7z++Guu5SsEMklxtqBl9Abq4488ki7bNmybIchQ5TqgPjqh1dQv6O9Z3UDgLZQmM3NIaZVFHLaQVUZH+QnWyFgw452ppX76ey2PY0c42X09Ts7qC7zMbPSqSDZ3hZi5eYWurqjnH7Q1D3iTXb/6RzwDVc64ro6oWrglXU7aO7ooqm1EwvsP6WEllAELFx+yr49PS4SH+vptxso9nnwunev/hHujtIZibLiJ59I/qBdXbB+Pbz3Hltfe4v3/vEGU5s2U9lQT2lTA4EJk/EdOJuSA/eH6dNhxgw2FE/kvs1ga2ooLilM22swkn2Y6m2T9ZZIbFo5mu+vXEjADbY/ZHiMMcuttUdmO46R0ncGkfwxeNLCcjU38v/4Ae+xP2fxCKs4CI8H7rlHyQqRbBnsO0Oqq4okra6w1v50uIHJyOTCF/1sSLVKo6aikDfqm5lYvHsQ4nG7mF1VwvRJxT0DkUzux76l512Rbup3dLCzvYsTZ0/uaeQYHwjGB4qBYJjOSIRX1+3CAEfNmpB0vn0ulLYnk464Eo/2t4R2DybbOiO0dkYo83soL/JyxiE17DO5ZI8j1C++10Sk2xLLWQEQ6bYU2QisWgVr1+7+ee895/fmzbDXXrD//kzdbz847lBeMR9nddlUCvfbl9MO33uP+GcAZ/d5D6XjCPlQj7z3fR8P1hwUBp+WMJpH/3NhpSZN0xARyX81NbBlS/+XlxHgt1zEmTzKw5zNV/kN7aaUy7SMqUjOS3WqSOLCQX7g04yRVUXyUS40kct18+ZW8dTKrbSEnEFuZ8Q52j5zUlFPqftQ9+NQkxx9S8/XNrVT4nPT1R1N2sNiTnU5p86ZzL1L61m9tQW/x80RMyqoKttdmp84+B/N0vahPPfhxpX4GAVuQ2NLJ0wsotTnoSXkrChz0uzJTC719zoy3nfQ++66rRwa2IRn3Tr2adnKfoEt7LWjgb12bGZK+y6omwH77w/77QcHHACf/rRzesYMKCjouZ+pwOdT2DeZGnSner/J3seJCbGB7n+wxEQqMYyVJKqmaeQOY8zEgS7XqiIikiiVFUMADmYlf+JM9mEdV/EL3jr5m7QuHnipUxHJHSklLqy1NyWeN8bciNPrQrIgV4+055I51eVcfsq+3Prc+zQEgkSiTpPG1Y1tnH6w0xNjKPtxOMmivj0C2kIRPC5wx6Y/tITClPqcyoH4Yzy7qomDqstoDYbxug3rtncwobiAyhL/HoP/kfQgGMpgc6jPfThx9X2M1lCEqLWEI92UF3lpCUaYXVXCpBIfgY4uolu38oVpFh5cDh984Py8/z7h1e+xb9M2/ruymrVlU3m/fCorK/bmuQOPx7X/fiyYfzJzplcOun/yyUj+How06ZL4unndzjKmj76+uWe503z7e5QLlR8COCuKWJxVRaYDu2KnK4B6YGidkEVkTKqrg/nzobt78Ot+iToWUksLZcwreJ6LfnMCN2tKiEheSbXioq8icmw5MmPMPOAWwA3cZa29PsshZUwuNJHLB/EmjLcufp9I1DKx2MvUMj/Prmpin8klQ9qPwxkc9i0997oN29s6KXA7DSPjlQQtwUhPIiH+GKWFXjrD3fg8hrXb2qks8e8x+B9uaftQExF9n3u4u5t1TW1866EVSXtvDCeuXo8RjTI11MK0nfVMW9fIp8s62fn2GgLvrKFoy0Ymbm/AFBfj2XcfmDkTZs2Cww+Hc8/lvgYXm0srKS0ppKk1xNqmdna2dTGxpIBrP3tQxnuaZKPyIJt/D+KvW7i7m9frA/g8LiYUenh7S4uqwGTYrLWzAIwxdwCPWWufiJ3/JHBqOh5jPH1nEBmLUq2y8NLFTXyby7mNJZzAExf+gWfvrc58gCKSdqn2uHgL5+gHOP/kJwM509/CGOMG/g84DdgE/MsY85i1dpB+wvlptLr9jwVrGts5Zt9JezTcW7SycUj7cTiDw76l5wdPK2Pp+zvwed34PC46I1EAZleVcP/SDbyxMdCzykNlsZd128P43IZAsCvp0r3DLW0fahIm8blvbwuxfEMzBW4Dln6THoVeF69+sAOD4bC9y3dfHg47y4Nu2uT8bN4MmzbxsaVvMznQROn2rRTv2EbQV8i28ik0TprKjmMPYdLhH2LiWZ91khQzZjjLiiax6uEVVBc7sU4u9TO51N+zjOhoNWId7elb2fx7EH9v/PODFnweF36vG2stbZ3dlBd6VQUmI3WUtfbS+Blr7ZPGmP8a6Z2Ot+8MImNNKsucAtSwiYc5h2N5hV+YbzP1t/+P6+d7B7+hiOSkVCsuPp1wOgI0WmsjGYhnuD4CrLXWrgMwxvwe+BwwJr+EqIlc6gZKOFz80Zkp78fhDg77lp5/7d5/0RIM09bZTYnfw8HTyohay0trdzChyAvWRSjczbrtYfapLGJzcwiXcfW7dO9wStuHmoRJfO5rt7Xj8zgrdZQWenr2x9NvbGKObWfdyrX8/YWVHNXRzCdbd1DQuJXCbQ3M7GqGbVth+3aYPNlpgllT0/N76wmn8EZZJTvKK1nS7sMUFWKtxRjDPpNLUk4AZGsQn83pW33/HmzY3s6axjb2nlTIzc+syWjlR3x/x6c9AXRGopT4PaoCk3TYboz5IfAAzsGTLwM70nC/4+o7g8hYsmBBakmLk1nM7zkfPyFqJzzMwp1nZz44Ecko10AXGmMmxppktSb8BIGywZpnjbIaYGPC+U2xbf3asGEDf/3rXwGIRCLU1tbyxBNPABAKhaitreXpp58GoK2tjdraWp577jkAmpubqa2tZcmSJQBs376d2tpaXn75ZQC2bt1KbW0tr776qhPMpk3U1tayfPlyANavX09tbS0rVqwAYO3atdTW1vL2228DsHr1ampra1m9ejUAb7/9NrW1taxduxaArm3raXryVkxbEw2BEKGGtTQ9eSul3a0AvPrqq9TW1rJ161YAXn75ZWpra9m+fTsAS5Ysoba2lubmZgCee+45amtraWtrA+Dpp5+mtraWUCgEwBNPPEFtbS2RiJOr+utf/0ptbW3Pvnz00UdZsGBBz/mHH36YK664ouf8gw8+yFVXXdVz/v777+c73/lOz/l77rmHH/zgBz3n77rrLn70ox/1nL/jjju49tpre87fdtttXHfddT3nf/nLX3LDDTf0nL/pppu46SanLUtNRSEv/+k3vPZEXc/l//jjQra98peeioV3Hr+bl//2e8oLvdSeOIvf3X4jd911V8/1f/CDHxBe9VxP1cPfH7iZ1xb/hUAwzLy5VVx11VU8+OCDPde/4oorePjhh3vOL1iwgEcffRSAg6eV0/zM7ewTfJdj95nEpCIPS37z37DxNbqjlvXbmtn8t1sIrlvO5uYQ08tcTHz9Hg51b2JOdXnS996X/+1ivnPbw1z98Ap+9vBSvvxvFw/43nvnoRvZ8J7TW7d560aeWfhfbHx/DTUVhbvfe2+/Ddu2sfaxx2i76SqqHvsd+z1ax7zf/Zwv33gR3/rVd7n+1iu44MJT+NY5h/Pvnz4UjjgC/1cv5CN3/xf7L/87ha0BtvoL+LMrwh/O/wb8858sWbSI2jPOoPmpp+BPf+K5z3+e2vffZ8rXvsib+36Yp9atY/vf7yIa6aKr2zJx59u8/dCNPLFic0rvPc+GV/jH/T8nEAwTtZbXX3icl+t+wby5VcN67/3s57/k3Eu+xdUPr+DmZ9bwn9fflPS9t7k5SKnfw7K/3seyv94HOEmE5x/6Nb/85S97rn/ddddx22239Zy/9tprueOOO3rO/+hHP9rjvXfPPff0nP/Od77D/fff33P+qquu4o0XnqD2xFmUF3r52x3XseLFpzhgagkHTi3jqYU/49pb72VVQwCA2tratP3dW/rOBzzxq2t55vkl7GjrZEfTNjY+9ktaN77LfpOL2dqwhXceujFtf/dWrFhBbW0t69evB2D58uXU1tayadMmQH/3Ev/uAdxwww0Zf++l+ndvBL6IU+H5aOxncmzbSA35O4OIZF8q00MMUb7P/+NpTmcbUzhjyjIlLUTGiMEqLvKlQVaylsB2jysZUwvUApSX53f5clGBm/nHzWTmzJksXx7hzuXuwW80Ds2bW8Vzf4jiDncTtZbWUISuiGWfycWAU7Fw8LRyqqqquDS2RGoyU8r8fCY2LSMU7may1z2saQDz5lbxt2iUYJcTTyAYpqs7iok1D62pKGQbEAhFMMEu/m3eAdz5Uv+v7XvbWmkIBCnrirBvuZ9tjQEaAkHqd7ZzdPxK1uJqa4O1a/G99RYn79zKxBefYa9lL+Fv2sSxK5dR9e5qDvC7sI0N3Ni4leK776ajtJyp5WWc3xmiLBhkW3ElLZEIm4pLaD/+Y2zb/0A2tgV4efnfOeSCy/nxF0/ihz9/kK3/fILjzl1AccUktqxewdt/f4ymqv35t732gnXrkj6PA6aWU3tiCd94ZQlRC36vm0OmVdD6nhePy6R85H5qeSF7TyikvNDL5uYghV4XMyYVDaviYFVDgOX1zdhItGf6xxsbm9mvYs98b7zyIFFrKEKxb7hthIYmXnnz3G+9TKosZmZlCQAel6GwwJ32yo9VDQEeWFqPMYY51aXUewrY3LCDUgv7Ti6mwONmZyjCxOKCXrfr6OrmD//ayP1roDi0nY6u7j0uf+CVDQTfDOFv3bLH5TK+xFYPudIYU2KtbUvjXQ/5O8P06dPT+PAiMhSpNuEsp5l7mc/neIwHOZ9/fu3XLPl1yegEKSIZZ6zd43/1nlfqp0GWtfbbGY4vJcaYY4H/tNZ+Inb+BwDW2v/X322OPPJIu2zZslGKUB5/czP3Lq2nsSVEVZmf+cdO72memWnOIGsDr28MYLEctnfFHisejGZjxb6P9dyqRsJRu0cfjrJCLw9dcmzyO4lGYccO7nv0Fdi6lSntuyjatYOiXdspaGqkomUn08OtztSMHTvA73emaFRWQmUlzcVlvB8tZKuvlIKqKRw4dybdEyfx4LogrilT8E6aQEvYSawkJmgSezkkTq+JX+fmZ9bsMVUjfv6qARJDcSO9fToNJZbB9stoufrhFVSX+3EZZ1zW1Bpi7bY2Gls7+fyHa9L2vk62bz5oamNrayfTJxYl/QwNto/il0ejURoCIXa0d+F1u7j85H1H7W+FpJ8xZrm19shh3vY44C6gxFo73RhzKHCJtXbBIDcd7H71nUEkD6TagBPgEFbwCGcxgw28ceEvOOqefwejpU5F8slg3xlSPRyYkQZZafQvYH9jzCxgM3A+8KXshiRxj7+5meufXE2xz8OUkgJagmGuf9IpBx+tAUlHOMpHZk3sGTAlNk4caWPFoSY9+valeKchQP2ODkLhbqdpZ7ib8pYdHLIrAA9vovHNd2l4czUFmzYyqWU7E9t24d2xHcrKOL2ogs5JU+iYMImOiZNpn1DJtlkH8EpBKbXnHOckKyZNAp+vVwwVwBF94rr5mTV07rd7MFoe++uQeLR+sIagI+2/kkv9W/rrBfJOQ4Cbn1mzx+s9nEap6ZbY46OpNcRr9c0AVJX60towNNm+mVFZTIHXzY3nHJr0NoP1AVm0spFoNMrqxjZ8HheTigtoCUW4dfH77DO5RE0+x6ebgU8QW37dWrvCGHNiGu5X3xlEcthQljkF+Ar3cSeX0Fk8Ee/Tf+eo447LbIAikhWpJi4y1SArLay1EWPMvwNP4ax68htr7dtZDmvMS3XAfu/Seop9Hjwuw5ZAiM5IFGvh9hfWjUriIpUB03AbKw4r6dHdDQ0NsH49bNjA/BeW41q/nuLGzUzcvpWqXVvp8hXSXr0XLfvvwzumnFD13nQedhyNZZU0FFZw3qcOY86MyTw4QFUAhw6tQiHVpp0DNQQd6QA+VxIAkLzRZ/2OdjbuCFJTUdTzev/PotVMK/fT2W2pqSjk4o/OzNogOzHxs3bb7sr6/atK0towdDhNUAd7f21uDtIQCPWsTgJQ5vewsz2s1UnGMWvtRtP7qOmI5w/pO4NI7hpKlUUBnfySb3IZd7Bm2seY/drvoaoqswGKSNakmrj4IvATnOZYAEtIT4OstIlNY3ki23GMF0MZsDe2hCj2umgIdOJxQYHbEIla1m9vZ1VDIOMDklQGTENd6jQuWdLDHQ6z9JllzNnb1ZOcYMOG3ac3b3aqIGbMgBkzOLCymudnHUjXR0+ja+/pNJRNoQlvzwC+7wCRYJhFa3YxZ8bktFYopGtFjuGsdJLO26dLsn27urGN2QlJgK5IN/U7OtjZ3sWJsyeP6jKoySQmfhpbO6kq9bF/VQmVJf6e55GOlT6G874b7P1VU1HI6/W7mJTQF6MzEmVisVerk4xfG2PTRawxpgC4AliVjjvWdwaR3FNXl3rSYm/q+SNn8xH+xe9nfI/z1/4MPKPTV0pEsiOlT3i8QVaGY5EUjWY/hv4MpUqhqszP+9va8LjA43YaG3ZHLcW+9DcNTCaVAVPKA3ZrYds22LgRNm5k5l9fZa+27ZQ2baW0qYGyxi0UNe+gpaIS5uwHM2c6CYrjj4cLLnBO772303MiphKY2+c1rY29pne/tJ7qcj/b20Ks3dbes+xkeZETazorFNKRBMmF92a6JNu3e00oZEZlcc911ja1U+Jz09UdxWXMqC6DOlDc8cfO1NKww3nfDfb+mje3iqfe3kpLKEKZ30NnJEpnJMqMWM+MgYyl9530cilwC86KH5uAp4FvZDUiEcmIujr4yldSu+5pPM3v+BJewtw571EuefLzGY1NRHLDgIkLY8wvrbXfNMb8lSQdt621n81YZJLUSPsxpMtQqhTmHzud7/zxLfweF26XpTNiCXdH+cjMiRk9khofzLzTEGDjjiCzq0qYUVmcdMD022feoaKxFe/Obez8YDP+HTuY4+9ixyMRJrU1w6ZNTrJi82YoKXGSD3vvzSxK2V4xme0fOYnWKdW0TpnG5uKJlJYWDamZZH9VBjUVhazf3tYz77/U56ElFKElGOmpVklXhcJQB6N9B4uzq4p5dlVT1t+b6dR33/ZtStkWiuBxQZl/d3IgXVUNI5XpfiFDfd8N9v6aU13O5Sfvy62L32dne5iJxV5mTCzC7Xb1LGebTLK/iX2n7yiRkbcKrbUXJG4wxkzNVjAikn51dfDVr0JX1+DXNUS5huu4lp+w1ncws9/6E5fsv3/mgxSRnDBYxUV80fYbMx2IDCw+SHzmnUa8bsPB08pwGW/WjvAOpUrhjENqePzNBpZt2EV7VzfFPg9Hz5rAlLLC3lMghspa5z9dezt0dDg/sdP16xv41z/Xsn9XB0d0ddC5fQed23cyORpiSneIKttJ0U9bIRBgzq5dXB+NEiiZwFZ/Ge1lE6BqCqEJlbxEOUd95KNM++psJ1lRUwNFRT0h+BoCPJ5kpYRzBhhoDcW8uVVc9YetzmN5XHRGogDMrirJyGue6mA02WDx1sXvc8DUkmH1CskXs6uKuXXx+0SilonFXiLdUUJhy4f22v380lXVMFK51C8kMaaBHv+MQ2rYZ3LJkKon+lZ/5dr0HRmRD4wxDwNftdbGs4FPAIdnMSYRSZOh9LOYwE7u5yucwRO8OvvLHP3aHVBcPPgNRWTMGDBxYa1dHvv99/g2Y8wEYG9r7ZsZjk1iEgeJURsF6+K1+mYOn17B5FJ/Vo7wpnQ0NxzuSSR8ax83j27ZyQRvhHIbJrJqFeG2Nk6dUQLvPrU78ZCQfEjptMfjJBKKipx/YLHT0bCbw33FRMsr6CouwTVpAl3Ve7GzopyjT5gD5eVQUdHz4you5p5n30va6HJdoZerTk5ePZHpweGc6nL2mlBISzBMW2c3JX4PB08rY1KJb1SqVfobPCabKhSJWhoCIWZW7l4zPVeqD9JhVUOAZ1c1ccDUkp7lOru7o0wp8+N1u4lam9VVUJLJlX4hQzHUmPtWf+Xi9B0ZtreAF4GXjDHnWmvfB7S+ocgYMJR+Fh/mdf7qPZO92Ay33M7Rl16qpU5FxqGUelwYY14APhu7/htAkzHm79bab2UuNIlLHCSWFxbEls00rG1qZ3Kpf/hHeK2FUMhJAiT+tLXtua3PZXPa2/npjmZ2bmvGtrdRHOmkPNpFQWdod1LB2p5kwn5FRVzu87PLeml3F+AqKaFySgVlLeW9Eg5MmZI0EZH0dGEheJNXbNz28Aqqy/24jKGpNcTapnZag2EwMPPwQ5MOYIbbpDPTg8ODp5UnTaik8po//uZm7l1aT2NLiKoyP/OPnT7oSi6pTEdKtq8mFnvZ0d671jNXqg/SIfFzGE/OBIJhuiLdlBd6c6aqYbzxuQ1L1jTR1R2lzO9le2uIEp8nJ6fvyJBZa+3txpgVwF+NMd8jybRVEckvdXXw5S+ndt2L+A23swB/1WT444tw9NGZDU5Eclaq7XfLrbUtxpivAb+11v7EGKOKi9FgLY3bdjG9wFLQEuTYzmbWrd9GSaQTb7CDvdZ6mNraxsf3KoLl0SElH+jocAb+xcXJf0pK9ty21149l5UWF1OaeFk8qRA/7fX2yoj7gepR2m3xqSxdkW5eq2/G53HhdRuMMf2WjadrVY2BDKeJ4HB7FTz+5mauf3I1xT4PU0oKaAmGuf7J1QADluOn0ng12b6aWuanJRZbJnoqZFt/ia2GQGRI/Uyyaaw1sVzVEGBLIERbKEKJz02wK8LO9jBdkSgnZWH6zljbvznAAFhr/2GMOQX4A3BgdkMSkeEaSj8LHyFu5XK+zl00zD2V6ud+B5MnZz5IEclZqSYuPMaYauBc4JoMxpOfurshGNxzusNQkgj9XdbRwc/cbrr8RUT8RYT9hYQK/OwyXoJeP+WVFUypnkSFZ8LupEFNzcDJh8SfMbp0VHywv66pDZ/bSZ50dVuOmFGO1518NZNUEgQjGZgMt7HqcKej3Lu0nmKfJyEB4azocvsL65hdVdpvHKlUniTbV263i8tP3pc1je1jsvpgNBJbmZQrjX3TadHKRmZMKqa63M/apnbaQhEmlxYQ7rajPn1nLO7fHPCp+AlrbYMx5mTguCzGIyLDFF81xKZQMzWTD/gjZ3MEr7Hyc9cw95Frwe3OfJAiktNSHbX+FHgK+Ie19l/GmH2A9zIX1ihoaYHHHuudbBjuT1fX7mkMiT8DVTAkJhcGSTC819Te84U4cUBde+IsZusLcVLxwf63H3qTqI1SXljA3JoyKkv8RK1NWjY+WIIgcWDiccELq7fx6OubOWG/SXz52BmDDk6GsoRsstiGOvhpbAkxpaSg17ZSn5s129o4aubEfuNIZYA+0L46I3adeJLn7pfW9yR54o+Tj0ekM71KR1/pPno/kvdfroon2VzGy+RSJ9kWtZZVDS2jPn1nLO7fbDHGfNla+wDwRZN8HvuSUQ5JREZgKE045/EkdVxASVEUfv8Ycz/zmcwGJyJ5I6XEhbX2YeDhhPPrgLMyFdSo2LoV7rorecKhsjL59v5+fL6MNwkq9Lp49YMdGAyH7V0+rKN46RoI5Us59Jzqck47qGpIR8kHShDEByZdkW7e2BjA53FRUehh5ZaWlI6sDreHxnBVlflpCYZ7Ki0AWju78bpdlPp7f/QT40h1gD7Qvkp29PnGp9YQtbbnCHmmj0gnW641sRpkqO/b0VylIxNH70f7/Tca+kuyHTytfNSn74zF/ZtF8aUCSrMahYgMW10dXHKJU0CcChfd/Jif8iP+C9ehh8Ajj8C++2Y2SBHJK6k255wN/AqostbONcYcAnzWWvuzjEaXSbNnOxUXOS5xAHPqnKqeQeRI7mckA6F8K4dO51Hy+MDk1Q9a8Hlc+L1urLW0dkYoL/QmPbKaOHiu39lBV7ibWZN3r7qRyakG84+d3tPTotTnprWzm/bOCB+ZOYHWUKTXYO+tTc2s2dbGST9/nqoyP6ccWElHlx32AD3Z0efX2zoBOGSvip5t8eum+73T9326fnsbf3ptE4ftXcGMyuJhv29Ha5WOTBy9z/epLsmMdhXMQMbi/s0Wa+2dsd/XZjsWERmaoSYsACaygzouYB5Pwb/9G9x+u9OAXUQkQapTRX4NfAeIf5l40xjzOyB/Exd5Il0DmFy7n9GSzqPk8YFJvBEgQGfEWckg2ZHVvoPncKxRKMCMyuK0DLIGqn6Jrx6SuKrI5Sfvyz6TS3oN9t7a1Mw/1+9kSomPybEmng+8spHvf/KAYR+1Tnb0uTPSjemzkmGmjkj3fZ9ubemk2Odha2snsyaX5Pz7NhNH73NpkJ8uo1kFM5ixuH+zxRjzvwNdbq29YrRiEZHU1dXB/PlO67dUHcEyHuEsqs1WuHMhfO1rWupURJJKNXFRZK39Z5+5ppEMxCMJVjUEePqdrWChtNDLfpOLmVzqH9YAJl0DoXwph04c0Be4+w6Xhyc+MPG6DZ3hbjCGzkiUuTVlSY+s9h08F/s8FBW4eXndDt5rauOwvSt6jvgPZ/pNKtUvZxxSk3T508TB3pptbUwp8VFV7sQfn1py79L6QZdO7U+yo88+z56NtTJ1RLrv+7QlFKbU56YttPvPVi6+b+MycfQ+lwb56TRaVTCpxDEW92+WLI/9Ph44CGc1EYBzEi4TkRwxnCoLsHydX3MrlxOZNJWCRf+AI4/MVIgiMgakmrjYbozZl9j66caYs4GGjEUlPYPSArcLay2dYedo/eHTKyjwuIc8gEnXQCiXyqH7G+z3baL56rqdWODofSaMaGpLfGBy/9INvLR2BxOKvBw23VmlJNmR1cTBc1NriNfqm/F7XFSWFHD0rEk9U376S0CcOmfygD0Z0tXs86SfP8/kJE08G1tCQ9o/iZIdfa4s8RG1dlSWS+37Pi3zewkEw5TlwPs2FZk6ep8rg/yxSvs3Pay19wIYY/4N+Li1Nhw7fwfwdBZDE5E+htJ4M85PkNtZwEXcA5/4BL66Opg0KSPxicjY4Rr8KgB8A2eayIHGmM3AN4FLMxWU7B6Uzq0po6vbWTvK5za8vaWFQDDcs0JDqubNdZpUBoLhnsFjNu9npOKD/UAw3GuwH09mxAf067Z3UOL3UOr3sK6po2f7opWNw3rcOdXl/PeZh3DnVw7nYwdMIdztJAySJUJqKgppjR3hX9vUjs/jAmMoLyzoFUdivC5jKC/0Eo1GuXXx+0mfX9zm5uCATTZTVVXmp7Wzd11na2c3VWX+fm4xuHiSp7zQS0MgRHmhl6s/MZvvzjug17ZM9Ubp+z6dWuajvTPC1FJfVt+3qUq2/3Klj8yqhgA3P7OGqx9ewc3PrOn1nsx1+Rz7ODWN3g06S2LbRCQHDCdpsQ/vs5RjnaTFj38Mjz+upIWIpCTVVUXWAacaY4pxkh1B4DxgQwZjG9cSl/k7YkYFa7e1Ewh24TKuEVULDLeMObG6ocjroivSTUMgkrVy6IGqDd7eEqAlGKats5ttrSGqSn0U+zy0hJwKh3RMEUjlyGriUfPWYBiv29DVbZlbU7ZHHH2n3zQEQkSitt9qilUNAep3dvB6/S4qS3zsN6WYyhL/sKoI+mviefnJI+vm3d8+Go33St/3+8zKEk4/uKpXBUuul/Hn4tH7fGvOmyifYx/HrgdeN8Y8Hzt/EvCf2QtHRMCZGvLVr0JX19Bu92n+yh8KvkJRsQseeBw+9anMBCgiY9KAiQtjTBlOtUUN8Bfg2dj5q4EVQF2mAxyvEkvdK0v8VJb4e84P90v2cAdCfb/wx8vWs/mFv79eG29vCbBpl5MMKPN72NFm2NwcYkqpjwnFznSI0ZoikDh4xoAxhiNmlFNZ4t8jjr7Tb3a0dzGpuM/0jViiI/56TC310dLhVA4sW7+LA6eW4nK5hjydoL8mnsPtb5Erkr3fz8hSLMnky7LCifKtOW+ifI59PDLGuIDVwNGxH4DvW2u3Zi8qEamrg698BaxN/TZlxd3845QfM/ex/4a5h8Mf/wizZmUuSBEZkwaruLgf2AUsBb4OfBcoAD5vrX0js6GNb7nUoT4Xv/D312ujJRThgKoSVje20RmJUllSwMZdQba1dnLEzIqeKQKjtR/jg+fdjT3dRK3d4/Xs+1p73S6KvC5eWbeDllCYMr+XqWU+ZlaW9Ho9Svwe1ja1s7Oti4aWTq797EHDek36a+IpmZHq0f9cS27kS3PeZPI59vHIWhs1xtxkrT0W58CJiGTZcJIWZ57QxCO+L8Fjzzorhtx6K/iHPxVVRMavwXpc7GOt/bfYmupfBI4EPq2kRebl0hz3dPVSSKf+em2UF3qYPqmYI2ZU4Pe6iQJ7TyhkQrF3wH4UwzGU+fIDvZ7JLvvCYdW8v72DQDBMSYHT/PO1+mZmVxX3ej0ml/o5dp9JfPJDU5k+sUhHjvNEsr4mfXuvDNTHJVsS+7bE5XKT00T5HPs49rQx5ixjtDaiSLbFlzodStLihjNf5ZEPDocXX4S774Zf/1pJCxEZtsEqLsLxE9babmPMB9ba1gzHJDG5Msc9l1YSieuvZ8eilY0EguGe6TWwexrGVafNTtvjD2e+/ECvZ9/Lbn5mDYftXcHW1k7aQhHKCr3MnlLCmsb2nHw9ZGhSOfqfi5VOuVQJNlT5HPs49i2gGIgYY0KAAay1tiy7YYmMP1deCd3dg18P4LJLLbd/6FfwzW9CTQ28/DIcfnhG4xORsW+wxMWhxpiW2GkDFMbO68vDOJKrX/j7SwSMRqyZHlRubg4yo7KYWZNLerZFrWVzc5CLPzozJ18PSV0qyafNzUE8LninoYW2UIQSv4d9Koto64wku8u062+aykia/GYj3rhcjl2Ss9aWDn4tEcm0ujrYsWPw6/n98Nv/6+D85y+BbzzgNN+8/36YODHzQYrImDdg4sJa6x6tQCR35dMX/tGKNdPz5Qca2ObT6yHJpZIMLHAbXl23kxK/hxKfm85wN//6YBdH75P5L4CDVRTl2nst1QqodMeeaz1IxiJjzARgf6DnD661dkn2IhIZX1Jd8vSUU+DZX70HZ50FK1fCT38K11wDrsFmpYuIpCal5VBFBvrCn2tf3kdjYJXp6RqDDWxzcfCY63LpfZpK8skAfacS29j2TMvFaSoDyUa8Wl4184wxXwOuBPYC3gCOwWkWfnIWwxIZN1JNWlx2Gdx++p/hyPng9cKiRXD66RmPT0TGFyUuZETG65f3TE+fGUpVRS4NyHNVLrxPk71OA/Vd6ey2HL3PBNY1dfSsLHPQtFI6u4fQGW2Y8m0FjmzEm2/JnTx1JXAU8Iq19uPGmAOBa7Mck8i4cOqpsHjx4Nf7xiURbiu9Br7wP3DUUfDwwzBjRuYDFJFxR4mLcSbdg9zhfHkfCwPt0ZiukUpVRToG5GPh9RjIqoYAP3nsHXa2dTGxpID9JhczudQZ5I7WIHM4r1O8queYfSb1bAsEw0wp9Sa9fjrlWwPYbMSbb8mdPBWy1oaMMRhjfNbad40xB2Q7KJGxqq4OLrkE2ttTu34Vjdy25ovw/PNw6aXwy1+Cz5fRGEVk/NLEs3Ek1eUVh7LM51CXSs3FJR6Ha051OVedNpsbzzmUq06bnZXBfirLag5kLL0eycSf3462TiYUeegMd/NafTNNraFRHWQO53Xqb8nfeXOrMh5vNh97OLIRr5ZXHRWbjDEVwJ+BZ4wxfwG2ZDUikTFqwQL48pdTT1ocy8u8W3w4LF0K997rzClR0kJEMkiJi3EklcHTUAeyQ/3yPtKBtvQ21MRRX2P99Yg/v8oSH13dFr/Xjc/jYm1T+6gOMofzOsWresoLvTQEQpQXekdtaks2H3s4RjveVQ0BmlpDPPfuNl5YvY1trcGcT+7kI2vtF6y1zdba/wR+BNwNfD6rQYmMQXV1qfWycFj+nVt50XUSFVML4ZVX4MILMxmeiAigqSLjwuNvbubepfW8vSVAud/Lh/cuZ/8qZyXbvoOnZFM/drZ18pPH3qG80EMgGKHM7+HgaeXMm1s15F4PKq9On1UNAep3dvBGfXOvKRBDGZCP9dcj/vz2m1LM8g3NgLNax862rlFdQna4Uxmy2YQ13xrAjla8idN+jtt3IqsaWvnH2p2csN+knE7u5BNjTLKlc96K/S4Bdo5iOCJj0lCnhQAU08avTS1ftA/CGZ+B++6DioqMxSgikkiJizHu8Tc3c/2Tqyn2eSjzeejo6ualtc5i3PtXle0xeOo7kG1qDbGmsY22rjCBDg/GGFo6whR53Sxc0kHtibOG1Osh3+bO56r44Km6zEego4uWYJjXNjQzu6oEt9uV8oA8n1+PVHpzxJ9fZYmfI2ZUsHZbO9vbOplU4hvVQWamm7nK6ElM7pYXeqkq2/0ZUtIibZazexGd6cCu2OkKoB6YlbXIRMaAVFcLSXQA7/IncxYH8i7893/D976npU5FZFQpcTHG3bu0nmKfh/JCLx6XoSEQgii8sTHAlNgX7sTBU9+B7NqmdjAQteD3uvF73YTC3Wxt7eSg6jIWrWwcUn+HbA7gxlITysTBU4nf0zMg39raybWfPSgvXo+RSLXZZeLzm1jsY061m0AwPOpHxkejmauMjrFepZQLrLWzAIwxdwCPWWufiJ3/JHBqNmMTyXfDSVqcxR+5z30RRRML4cGn4ZRTMhOciMgAlLgY4xpbQkwpKQCg2OehutzPjrZOAiEnOdF38NR3ILuzrQu3C/weFz6Pk1n3eVy0hSLD+rKerQFcLiyHmU6Jg6fKEj+VJX6i1tIQCA3p+eTrgHrRyka6u6O809BCWyhCid/D1FLfHquE5NLzy7epF5JcPlcp5aGjrLWXxs9Ya580xvxXNgMSyWdDTVp4CHOT9wdcEb4JjjrGWep0r9w+sCEiY5cSF2NcVZmflmCY8kIn6VDs8xCJWvaeVMy8uVUsWtnI3S+t71WBkDjQm1hSQHWZj60tnYTC3fi9bjojUUpiR+eH82U9GwO44SzbOhKZru5I5+ApE69Hpp//21sCbNoZxOd1UeJz0xnuZk1jGx3h7j2uq4SBpFO+Vinlqe3GmB8CD+BMHfkysCO7IYnkn+H0s6hiK28ecC5TVr8I//7vcNNNUFCQuSBFRAahyWlj3Pxjp9Pe6XyxjkajBIJh2jsjnHJgZb+rhyQu83ntZw/C5XIxtcxHKNxNIBimMxxlaqkvrzroj3T1jf4kWzp2NJYYzeXlKkfj+beEImCc6UvGGPxeN5jYdpEMyrcVV/LcF4HJwKM4S6JOiW0TkRQNdZlTgI/yIquLDmPKxuXwwANw661KWohI1qniYow745AawOl10dgSoqrMz+Un78uaxvaUKxAKvS5e39hCuDtKUYGHqeV+Zk0uyaseEZko7+5v+kmh15Xx6o5cmgLR12hUt5QXegh0dBEKd+PzuOiMRLHWUl6oP2mSOX0riS7+6Myc+MyNVdbancCV2Y5DJB8Np8oCLNcU/ZKfhr6Dq2YfeORp+NCHMhWiiMiQ6Fv+OHDGITU9CYy45x9eMWiDucSB+alzqnpKovPx6GImyrv7G6C/+sEOTp3Tu/IhE837cnUKxGg0Lzyoupwir5utLZ20hMKU+b3MnFTEzMqStD2GSKKx1icnHxhjZgNXAzNJ+L5irT05WzGJ5IO6OrjoIgiHU7v+ZZfB7Te0wsUXO30svvAF+O1voVx/20Qkd2iqyDhVU1FIa5+y+r4VCIkDc5cxPacXrWwc7XBHLBPl3f1NPzGYQfftWJbKe2uk5s2twuVyMae6jFPnVDGnugyXy5UTU2VkbBpLfw/zyMPA68APge8k/IjIAK65JvWkRXEx3P7v78BHPgKPPAL/8z/ObyUtRCTHqOJinEqlAmGsLfvXt0Ih3p9iuA0k+5t+ctje5QSCzjeG8di8bzSaF+byVBkZm8ba38M8EbHWDnHhRhHZsCG167ndsOiiP8BHLnYyGIsXw8c+ltHYRESGS4mLcSqVgd9YXvYvHWXf/Q3Qa0+cBTBuB9WjlVRIdapMplc4kfFhLP89zGF/NcYswGnO2RnfGOt9ISJJLFiQ2vWmTuzi+aO+y4G33QLHHw8PPQTTpmU2OBGREVDiYhwbbOA3lpf9S0cDycEG6ON5cJwr/TfUl0DSZSz/Pcxh82O/E6eHWGCfLMQikvPq6uCOOwa+zmWXwe0/3ALnnANPvQxXXgk//zl4vQPfUEQky5S4kH6N5XL8dJV958oAXZIbjRVOZHwYy38Pc5W1dla2YxDJJ9dcA9b2f/kDD8AFNS/AYec5y408+CCcf/6oxSciMhJKXMiAxurAXGXf44P6Ekg6jdW/h7nMGDMXOAjo+SBba+/LXkQiuau+vv/LZky3XLDlRpj/A9h/f3j+eTjooNELTkRkhLSqiIxL8+ZWEQiGCQTDRK3tOa1VKcaW0VjhREQywxjzE+DW2M/Hgf8BPpvVoERy2PTpybeXE2DJlLPgu991ljr95z+VtBCRvKPEhYxLI10eNb4iydUPr+DmZ9awqiGQ4YhlOJSgEslrZwOnAFuttRcBhwK+7IYkkrs+9Skwpve2uaxkdflRTH/9MfjFL5wmnKWl2QlQRGQENFVknEnHCguPv7mZe5fW09gSoqrMz/xjp3PGITUZijhzhlv2rYaP+UN9CUTyWtBaGzXGRIwxZcA21JhTpJe6Oqe/5o4de152AXXc7anFV1gGf30eTjhh9AMUEUkTJS7GkXQMuB9/czPXP7maYp+HKSUFtATDXP/kaoC8TF4Mhxo+5hf1JUhOy8RKHlhmjKkAfg0sB9qAf2Y1IpEcsmAB/OpXe2730sUv+Bb/zv/xqvtEjn79DzB16ugHKCKSRpoqMo4kDrhdxvScXrSyMeX7uHdpPcU+j3MfLhflhV6KfR7uXTpAR6gxZnNzkFJ/75yfGj5KPoknMQPBcK8kpqY8SS6x1i6w1jZba+8ATgPmx6aMiIx7/S19WsMm/s5J/Dv/x418mxM6n1XSQkTGBCUuxpF0DLgbW0KU+ty978PnprEllJYY84EaPkq+S0cSUyTTjDGL46etteuttW8mbhMZz5ItfXoyi3mdw5jLSs7mYb7DjUyb4U1+ByIieUaJi3EkHQPuqjI/rZ3dve+js5uqMn8/txh71PBR8l26q4bUrFbSyRjjN8ZMBCqNMROMMRNjPzOBaVkOTyQnbNiw+7Qhyvf5fzzN6WxjCkeyjEc4G2PguuuyF6OISDopcTGOpGPAPf/Y6bR3Rpz7iEYJBMO0d0aYf2w/a3CNQYkrkqxqaOGdhhbaOsMsWtmoAZvkhXRWDWnaiWTAJTg9LQ6M/Y7//AX4vyzGJZITFizYfbqcZh7lC/w//oOHOJejeZU1HADApZfCBRdkKUgRkTRTc85xJB0rLMQbcCauKnL5yfuOm8accfF9Vr+zg70mFFHq94x4dZHEZokFboMBOrutGidm2VhsYjlvbhULl3wAOJUWrSEnGXneUXsN+b7UrDa/5MP72Vp7C3CLMeZya+2t2Y5HJJsGWjXkEFbwCGcxgw1czv9yG/8OGCZNgltuUdJCRMYWJS7GmXSssHDGITXjLlGRTDoHbIkrvnhc8Oq6nVjg6H0maLnVLBqrS9+mc5nYzc1Bqst7TxVTs9rclC/vZ2PMUcDGeNLCGHMhcBawAfhPa+3ObMYnMlrq6uCiiyAc3vOyC7mXO7iUnUzkJP7OUo4D9ux7ISIyVihxITJM6RywJSZB3mlooSTWf2BdUwfH7DOp5zq5NLgYD8ZyNUG6lomtqSgkEAz37BtQs9pclUfv5zuBUwGMMScC1wOXAx8GFgJnZy0ykVF0zTV7Ji0K6OQWruRS7uQ5Ps75/J4mpgAwY0YWghQRGSXqcSEyTOnsE5DYLLEtFMHnceHzuGgJOd9YdAQ7OxJfl+1tIRavauSvKzZzz8vrueZPb6qPA2pWm0/yaClnd0JVxXnAQmvtI9baHwH7ZTEukVFRVweVlb0bcALsTT0vcgKXcifX8z1O5+mepIUacYrIWKfEhcgwpXPAlpgEKfF76IxE6YxEKfM7R0R1BDs74q/L9rYQ/3hvO5uagxjA5zYsXbeTG5/SChqJzWobAiHKC705N/VAHHm0lLPbGBPPsJwCPJdwmSpFZUyLTw/p29PiNJ7mNQ7nAFbzeR7lB1xPd8LHQY04RWSs0xcAkWFKZ5+AxGaJ+1QW8a8PdmGBg6aV9iREhtM4UUYm/rqsa2qjI9yNxxgsMKXMj9tl2N7WmfEy+3xoppiuaSeSWelsypphDwJ/N8ZsB4LAiwDGmP2A8Z0plDGtrg7mz4fuhFXnDVGu4Tqu5Se8zcGcyZ9Yy/67LzdO0uL227MQsIjIKDJ2nHbxOfLII+2yZcuyHYZID60qkptWNQT41kMr2NIcpKjAzaRiH8U+D9ZaWkJh5tZUcOM5h2bssePNFBMHmqpokOEa7USYMWa5tfbIYdzuGKAaeNpa2x7bNhsosda+luYwB6XvDJJpdXVQWwsdHbu3TWAn9/MVzuAJ7ufLXModdFCMywXRqNPT4rrrVGkhImPDYN8ZVHEhkiN01Do3zaku5/SDpvLC6m0A+L1uADojUXwed0bL7DPVTDEfqjgkM/Ll74y19pUk29ZkIxaR0XDllb2TFofxGo9wFjVs5jJu5w4uZcYMw/r1WQtRRCSr1ONCRGQQ8+ZWMbG4gLZQhFBXhGBXhNZQhMoSX0abUGaimWK8iiMQDPdaEnO89+oQEcmWurrePS2+yt28zHF4iHACL3IHl1FQYNR8U0TGNSUuREQGMae6nO/OO4Cj95lIV9QSicKx+0zk6k/MzujR60w0U0ys4nAZ03N60crGkYYrIiLDcM01zm8fIX7N17ibr/EiJ3A4r/FPjmbSJPjNbzQlRETGN00VERFJwZzqcv77zENG9TEz0Uxxc3OQ6nJ/r205uiSmiMi4UF8PM/mAP3I2R/AaP+MafsK1RHHzwANKWIiIgBIXIjlH/QckLp0r18TVVBQSCIZ7+mVAzi6JKSIy5tXVwafMk9xnL8BFlM/wGH/jMwBMmqSkhYhInBIXIjliVUOA+5du4KW1O5hQ5O1ZCnXhkg+0isQ4lu5minm0JKaIyJhVVwdXXdHNN3b+lMf4L97kEM7iEdaxLwBFRXDLLVkOUkQkhyhxIZID4g0T1zW1MaHQ+Vi+Xh/giBkVPf0HlLiQdBisikMVPyIimVNX56wgYnfsoI4LmMdT/JZ/YwG3E8KpfHO7YeFCVVuIiCRS4kIkB8QbJoa7LSU+N8YYANZua+cjsyaq/4CkVX9VHPEEWnmht9eKI6r4EREZubo6qK2Fgzr+xR85m6ls5ess5C6+Bpie60WjSlqIiPSVlVVFjDHnGGPeNsZEjTFH9rnsB8aYtcaY1caYTyRsP8IY81bssv81sZGdMcZnjPlDbPurxpiZo/x0RIZlVUOAm59Zw9UPr+Dpd7YSCkco8XvojEQB8HlctITC6j8go0YrjoiIZEZdHcy/0HJBx0Je4qNYDMfzD+7i6yQmLQCmT89OjCIiuSxby6GuBM4EliRuNMYcBJwPHAzMA243xrhjF/8KqAX2j/3Mi22/GNhlrd0PuBm4IePRi4xQ/Mh2IBimutxPgdvFvz7YxaQiL52RKKFwN6FwNwVuF4FgmHlzq7IdsowDm5uDlPp7F+JpxRERkZGpq4Mrvh7k19GvspBLeJ6PcwTLWc6Re1y3qAiuuy4LQYqI5LisJC6staustauTXPQ54PfW2k5r7QfAWuAjxphqoMxau9Raa4H7gM8n3Obe2Ok/AqfEqzFEclXfI9tza8qwwJZAiA/v7ZTkNwcjzJ1WpjJ9GTU1FYW0hiK9tqniR0RkZO787vssDh7LRdzDtfyYM3icnUza43qTJqm3hYhIf3Ktx0UN8ErC+U2xbeHY6b7b47fZCGCtjRhjAsAkYHvfOzfG1OJUbTBddXiSRZubg1SX+3vOV5b4OXqfCazY2EIkCh87YIqaIsqo04ojIiJp9te/8tiWrxDFxad4nCf51B5XmTTJWUFECQsRkf5lLHFhjHkWmJrkomustX/p72ZJttkBtg90mz03WrsQWAhw5JFHJr2OyGioqSgkEAxTXujt2ebzeDjtoCquOm12FiOT8WywFUdERCRF3d3w4x/Df/83GwsO57Ndf2Q9s3pdxe2Ge+9VwkJEJBUZS1xYa08dxs02AXsnnN8L2BLbvleS7Ym32WSM8QDlwM5hPLZIj0wvCakj25Kr+ltxREREUtTUBF/6Ejz7LGs/9jXmvXkrW3b6e12lqEjTQkREhiJbzTn78xhwfmylkFk4TTj/aa1tAFqNMcfE+ldcCPwl4TbzY6fPBp6L9cEQGZa+jTPjS0Kuagik7THiR7bLC700BEKUF3rVy0JERCTfvfoqHH44vPgiS79+N4f+89d7JC3Uy0JEZOiy0uPCGPMF4FZgMvC4MeYNa+0nrLVvG2MeAt4BIsA3rLXdsZtdBtwDFAJPxn4A7gbuN8asxam0OH/0nonksuFWTSQ2zgR6fi9a2ZjWxIKObMtIZboySGSsMcb8HPgM0AW8D1xkrW3OalAyNljLPy/6FR++95tsYi8uLl/KkrsPIxrd86olJUpaiIgMVbZWFXnUWruXtdZnra2y1n4i4bLrrLX7WmsPsNY+mbB9mbV2buyyf49XVVhrQ9bac6y1+1lrP2KtXZeN5yS5ZSRVE1oSUvLBaFQGiYxBzwBzrbWHAGuAH2Q5HhkLOjr44IQL+ci93+AZTuMIlvNCIHnSAqC+fnTDExEZC3JtqohIWvRdbjR+etHKxkFvqyUhJR+M5D0uMl5Za5+21sb/wL9C7/5ZIkP33ntwzDHM+EcdP+KnfIa/0syEAW+ihe1ERIZOiQsZk0ZSNTFvbhWBYJhAMEzU2p7T8+ZWZSpckSFTZZDIiH2V3dNO92CMqTXGLDPGLGtqahrFsCRv/PnPcOSRsGULn2QRP+NH2EG+WhcVwXXXjU54IiJjiRIXMiaNpGpCjTMlH6gySCQ5Y8yzxpiVSX4+l3Cda3B6adX1dz/W2oXW2iOttUdOnjx5NEKXfBGJwPe+B1/4AhxwACxfzuoZpw96M7dbTTlFRIYrK805RTJtpMuNqnGm5DotqSuS3GDLsRtj5gOfBk7RKmQyZI2N8MUvwvPPw6WXwi9/CT4f110HtbXQ0ZH8Zlr+VERkZFRxIWOSqiZkrNN7XGTojDHzgO8Bn7XW9jPEFOnHyy87S50uXQr33gu/+hX4fICTkFi4EGbMAGOcJU8nTXJOz5ihpIWIyEip4kLGLFVNyFin97jIkN0G+IBnjDEAr1hrL81uSJLzrIVbb4Vvf9vJQrzyChx66B5Xu+ACJSdERDJFiQsRkTFmVUOARSsb2dwcpKaikHlzq5TgEAGstftlOwbJM21tzhyQBx+Ez37WqbSoqOi5uK4OrrnGWeJ0+v9n797j27zL+/+/LtmyLSe2HCep4xyapKWHtAHakvQEdJRjOIyyUShQzowAGxtsdGOs3x0ZjB8bMNjGIYyNU0cp58JYoJRDgJ7SlhTShpa2ScjBSdMkVpxYtiXr+v1x33JkxwfJlnxL8vv5ePhh+ZZ03x/dumXdn+u+Ptfn9KDwpoIXIiLlp6EiIiJ1ZEdPik1bdpJKZ+hOtpBKZ9i0ZSc7elJRN01EpLb8+tdwySXw5S/D+98P3/jGKUGLjRth9+4gKWP37uDvGyYs+SoiItOlwIWISB3ZvP0gyUScZCJOzGzk9ubtB6NumohI7fjqV2H9ejh0CL7/fXjPeyA2+rT5+utPLcbZ3x8sFxGR8lLgQkSkjuzrTdPWMnoUYFtLI/t60xG1SESkhmQycN118LKXwdq1cO+98KxnjfvQ3/52/FVMtFxERKZPgQsRkTqyrCNB30B21LK+gSzLOhIRtUhEpEb09ARBig99CN7+dvjJT2D5xFNMn356actFRGT6FLgQEakjG9Z2kUpnSKUz5NxHbm9Y2xV100REqtdPfxpMdXrPPfDFLwaziDQ1TfqU970PWltHL2ttDZaLiEh5KXAhIlJH1nQn2XjFapKJOD2pATLZYRLxGJ/52S4+cstDKtIpIlLIHT78YbjySmhrgzvvnHJakBtugFWr4DWvgUQCFi4Es2Cm1E2bNKuIiEglKHAhIlJn1nQn+dPnnM2bnraK/kyOpsYGzTAiIjJWXx9ccw28613BVKdbtwZ1LSYxdiaRw4chnYYvfAF27VLQQkSkUhS4EBGpU5phRERkAg88ABdfDF/7Gnzwg8HvZHLKp2kmERGRaDRO/RAREalF+3rTdCdbRi3TDCMiMud9+cvwpjfBvHlw663wjGcU/VTNJCIiEg1lXIiI1CnNMCIiUmBoCN75TnjFK+CCC+AXvygpaAGaSUREJCoKXIiI1KnZmmFkR0+Kj9zyENd95T4VABWR6rRvX1CA86MfDYIXP/oRLF1a1FPzxThjMTh+/NTJRjSTiIhI5SlwISJSp8bOMJJMxNl4xWrWdE89jrtYO3pSbNqyk1Q6owKgIlKdfvzjYKrT++6DG2+Ej3wE4vGinjpeMU53zSQiIjLbVONCRKSOrelOljVQMVZhAVBg5Pfm7Qcrul0RkSm5w7/8C7znPXDWWUGWxXnnlbSK8YpxZjIwfz48/ngZ2yoiIpNSxoWIiEzbvt40bS2jY+AqACoikUul4KUvhb/4C/i934O77io5aAEqxikiUi0UuBARkWlTAVARqTrbt8P69XDzzfDhD8NNN0Fb27RWpWKcIiLVQYELERGZttkqACoiUpQbboBLLoG+vmBoyJ/+aVCMYpre976g+GYhFeMUEZl9ClyIiMi0zUYBUBGRKQ0NwdvfDq9+NaxbF0x1+vSnz3i1114bFN9cuVLFOEVEoqTinCIiMiOVLgAqIjKpPXvgZS+DO++E666D97+/6FlDinHttQpUiIhETYELEREREalNt94Kr3gFDA7CV78aFOQUEZG6o6EiIiIiIlJbcjn4p3+C5z4XTjsNtm5V0EJEpI4p40JEREREakdvL7zudcGsIa94BXz60zB/ftStEhGRClLgQkRERERqw333BZkVu3fDxz4WFOScwawhIiJSGzRURERERESq3+c+B5deCuk0/OQn8Md/rKCFiMgcocCFiIiIiFSvwUF461vh9a+Hyy4Lpjq9/PKoWyUiIrNIgQsREZkVO3pSfOSWh7juK/fxkVseYkdPKuomiUi1270bnvY0+NSn4N3vhu9/PyjGWUE33ACrVkEsFvy+4YaKbk5ERIqgwIWIiFTcjp4Um7bsJJXO0J1sIZXOsGnLTgUvRGRi3/8+XHQRPPQQfOMb8IEPQGNly7PdcANs3BjES9yD3xs3KnghIhI1BS5ERKTiNm8/SDIRJ5mIEzMbub15+8GomyYi1SaXg/e+FzZsgGXL4O674SUvmZVNX3899PePXtbfHywXEZHoaFYRERGpuH29abqTLaOWtbU0sq83HVGLRKQqHTkCr3kNfPe78OpXwyc/CfPmzdrmf/vb0paLiMjsUMaFiIhU3LKOBH0D2VHL+gayLOtIRNQiEak6994LT3kK3HILfPzj8PnPz2rQAuD000tbLiIis0OBCxERqbgNa7tIpTOk0hly7iO3N6ztirppIlINPvOZYKaQbBZ++lN429simer0fe+D1tbRy1pbg+UiIhIdBS5ERKTi1nQn2XjFapKJOD2pAZKJOBuvWM2a7mTUTRORKA0MwB/8QfDz9KcHWReXXBJZc669FjZtgpUrg7jJypXB39deG1mTREQE1bgQEZFZsqY7qUCFiJy0cydcfXUQrLj+evj7v4eGhqhbxbXXKlAhIlJtFLgQERERkdn1f/8XRAdyObj5Zvjd3426RSIiUsU0VEREREREZsfwMPzt38ILXxhUvLznHgUtRERkSsq4EBEREZHKO3w4yLL43vfg9a8PZg5JaGYhERGZmgIXIiIiIlJZW7cG9SwOHAiqXf7BH0Qya4iIiNQmDRURERERkcpwDwIVT3taEKj4+c/hzW9W0EJEREqiwIWIiIiIlF9/P7zhDfCWt8CVVwb1LNati7pVIiJSgxS4EBEREZHyeuQRuPxy+Pzng2Kc//u/sHBh1K0SEZEapRoXIiIiIlI+3/42vOY1EIsFAYvnPz/qFomISI1TxoWIiIiIzNzwMFx/Pbz4xXDmmcHQEAUtRESkDJRxISIiIiIzc+gQvOpV8IMfBDOG/Nu/QUtL1K0SEZE6ocCFiIiIiEzfnXcGU50eOgSf+Qy88Y1Rt0hEROqMhoqIiIiISOnc4eMfh6c/HeJxuP12BS1ERKQiFLgQERERkdKcOAGvfS380R/Bc58b1LO48MKoWyUiInVKgQsRERERKd5vfgOXXgo33ADvfS/cfDMsWBB1q0REpI6pxoWIiIiIFOeb34TXvS4YGrJ5c5BtISIiUmHKuBARERGRyWWz8O53w+/9HpxzTjA0REELERGZJcq4EBEREZGJHTwIr3wl/OhH8Na3wr/+KzQ3R90qERGZQxS4EBEREZHx3XYbvOxlcOQIfO5zQUFOERGRWaahIiIiIiIymjt87GPwO78DiQTccYeCFiIiEhkFLkRERETkpOPH4VWvgne8A17wArj7bnjyk6NulYiIzGEKXIiIiIhI4Ne/hksugZtugve/H77xDejoiLpVIiIyx6nGhYiIiIjAV78Kb3hDMDTk+9+HZz0r6haJiIgAyrgQERERmdsyGbjuuqAI59q1cO+9ClqIiEhViSRwYWb/bGa/NrNfmtk3zKyj4L73mNnDZvagmT2vYPlTzOxX4X0fMzMLlzeb2ZfD5Xea2arZf0UiIiIiNainJwhSfOhD8Pa3w09+AsuXR90qERGRUaLKuLgFWOvuTwIeAt4DYGbnAa8Azgc2AB83s4bwOZ8ANgJnhT8bwuVvAo66+xOAjwD/32y9CBEREZGa9dOfwkUXwT33wBe/CP/2b9DUFHWrREREThFJ4MLdv+/u2fDPO4B8aP8q4EZ3H3T3ncDDwMVm1g20u/vt7u7A54GXFDznc+HtrwLPymdjiIiIiMgY7vDhD8OVV0J7O9x5J1x7bdStEhERmVA11Lh4I/B/4e1lwJ6C+/aGy5aFt8cuH/WcMBiSAhaOtyEz22hmd5vZ3YcOHSrbCxARERGpCX198PKXw7veBVddBVu3BnUtREREqljFAhdm9gMz2z7Oz1UFj7keyAI35BeNsyqfZPlkzzl1ofsmd1/n7usWL15c/IsRERERqXUPPAAXXwxf/zp88IPBLCLt7VG3SkREZEoVmw7V3Z892f1m9jrgRcCzwuEfEGRSrCh42HJgf7h8+TjLC5+z18wagSRwZMYvQERERKRefPnL8KY3wbx5cOut8IxnRN0iERGRokU1q8gG4N3Ai929v+Cum4FXhDOFrCYownmXu/cAfWZ2aVi/4rXAtwqe87rw9tXADwsCISIiIiJz19AQvPOd8IpXwAUXwC9+oaCFiIjUnIplXEzh34Fm4JawjuYd7v5Wd7/fzG4CHiAYQvJH7j4cPudtwGeBBEFNjHxdjM8AXzCzhwkyLV4xa69CREREpFrt2xfUs7jttiB48cEPQjwedatERERKFkngIpy6dKL73ge8b5zldwOnVI9y9wHgZWVtoIiIiEgt+9GPgiyLEyfgxhvhmmuibpGIiMi0VcOsIiIiIiJSDu5BZsWznw2dnXDXXQpaiIhIzYtqqIiIiIiIlFMqBW94A3zjG/Cyl8FnPgNtbVG3SkREZMYUuBARERGpddu3w+//Pjz6KHz4w0FNCxtvxngREZHao6EiIiJStXb0pPjILQ9x3Vfu4yO3PMSOnlTUTRKpPjfcAJdcAn19QW2LP/1TBS2KcMMNsGoVxGLB7xtuiLpFIiIyEQUuRESkKu3oSbFpy05S6QzdyRZS6QybtuxU8EIkb2gI3v52ePWrYd26YKrTpz896lbVhBtugI0bYffuoCzI7t3B3wpeiIhUJwUuRESkKm3efpBkIk4yESdmNnJ78/aDUTdNJHp79sAVV8B//Adcdx384AewZEnUraoZ118P/f2jl/X3B8tFRKT6KHAhIiJVaV9vmraW0aWY2loa2debjqhFUi/M7DozczNbFHVbpuXWW+Gii+CBB+CrX4V//meIx6NuVU357W9LWy4iItFS4EJERKrSso4EfQPZUcv6BrIs60hE1CKpB2a2AngOUHtd1FwO3v9+eO5z4bTTYOtWeOlLo25VTTr99NKWi4hItBS4EBGRqrRhbRepdIZUOkPOfeT2hrVdUTdNattHgL8APOqGlKS3F37v94KxDNdcA3feCeecE3Wratb73getraOXtbYGy0VEpPoocCEiIlVpTXeSjVesJpmI05MaIJmIs/GK1azpTkbdNKlRZvZiYJ+731fEYzea2d1mdvehQ4dmoXWTuO++oPjmd78LH/tYUEFy/vxo21Tjrr0WNm2ClSuDCVhWrgz+vvbaqFsmIiLjaZz6ISIiItFY051UoEJKYmY/AMarUnk98FfAc4tZj7tvAjYBrFu3LrrsjM99Dt76VujshJ/8BC6/PLKm1Jtrr1WgQkSkVihwISIiInXD3Z893nIzeyKwGrjPzACWA/ea2cXufmAWm1icwUF4xzvgU5+CK6+EG28M6lqIiIjMQRoqIiIidWlHT4qP3PIQ133lPj5yy0Ps6ElF3SSJkLv/yt1Pc/dV7r4K2AtcVJVBi9274WlPC4IW7343fP/7ClpM0w03wKpVEIsFv2+4IeoWiYjIdChwISIidWdHT4pNW3aSSmfoTraQSmfYtGWnghdS/b73vWCq04cegm98Az7wAWhUgux03HADbNwYxIHcg98bNyp4ISJSixS4EBGRurN5+0GSiTjJRJyY2cjtzdsPRt00qRJh5sXjUbdjRC4H730vPP/5sGwZ3H03vOQlUbeqpl1/PfT3j17W3x8sFxGR2qIQvoiI1J19vWm6ky2jlrW1NLKvNx1Ri0QmceQIvOY1wawhr351MERk7FydUrLf/ra05SIiUr2UcSEiIlVpJjUqlnUk6BvIjlrWN5BlWUei3M0UmZl774WnPAVuuQU+/nH4/OcVtJhAqfUqTj+9tOUiIlK9FLgQEZGqM9MaFRvWdpFKZ0ilM+TcR25vWNtV4ZaLlOAznwmmN81m4ac/hbe9DYIZT2SM6dSreN/7To0BtbYGy0VEpLYocCEiIlVnpjUq1nQn2XjFapKJOD2pAZKJOBuvWM2a7mSFWy5ShIEB+IM/CH6e/vQg6+KSS6JuVVWbTr2Ka6+FTZtg5cogHrRyZfD3tddWtq0iIlJ+qnEhIiJVpxw1KtZ0JxWokOqzcydcfXUQrLj+evj7v4eGhqhbVfWmW6/i2msVqBARqQfKuBARkaqjGhVSl7773aCexaOPwre/Df/4jwpaFEn1KkRE5jYFLkREpOqoRoXUleFh+Nu/hRe+MBivcM898KIXRd2qmqJ6FSIic5sCFyIiUnVUo0LqxuHDQcDiH/4BXv96uO02OOOMqFtVc1SvQkRkblONCxERqUqqUSE1b+vWoJ7FgQNBL/sP/kCzhsyA6lWIiMxdyrgQERERKSf3IFDxtKcFgYqf/xze/GYFLURERKZJgQsRERGRcunvhze8Ad7yFrjyyqCexbp1UbdKRESkpilwISIiIlIOjzwCl18On/98UIzzf/8XFi6MulUiIiI1TzUuRERERGbq29+G17wGYrEgYPH850fdIhERkbqhjAsRERGR6Roehuuvhxe/GJ7wBLj3XgUtREREykwZFyIiIiLTcegQvOpV8IMfBDOG/Nu/QUtL1K0SERGpOwpciIiIiJTqzjuDqU4PHYLPfAbe+MaoWyQiIlK3NFREREREpFju8PGPw9OfDvE43H67ghYiIiIVpsCFiIiISDFOnIDXvhb+6I/guc8Npjq98MKoWyUiIlL3FLgQERERmcpDD8Gll8INN8B73ws33wwLFkTdKhERkTlBNS5EREREJtPbC+vXB0NDNm8Osi1ERERk1ijjQkRERGQyjzwC55wTTHWqoIWIiMisM3ePug2RMLNDwO6o21HFFgGPR92IOqF9WT7al+WjfVk+2pcTW+nui6NuxExV2TmDjrfqo/ekOul9qT56T6pTtbwvk54zzNnAhUzOzO5293VRt6MeaF+Wj/Zl+Whflo/2pcwmHW/VR+9JddL7Un30nlSnWnlfNFRERERERERERKqWAhciIiIiIiIiUrUUuJCJbIq6AXVE+7J8tC/LR/uyfLQvZTbpeKs+ek+qk96X6qP3pDrVxPuiGhciIiIiIiIiUrWUcSEiIiIiIiIiVUuBCxERERERERGpWgpczBFm9l9m9piZbS9Y1mlmt5jZb8LfCwrue4+ZPWxmD5rZ8wqWP8XMfhXe9zEzs9l+LVGbYF/+nZntM7Nt4c8LCu7TvpyAma0wsx+Z2Q4zu9/M3hEu17FZokn2pY7NEplZi5ndZWb3hfvy78PlOi6lqpjZdWbmZrYo6rbMdWb2z2b2azP7pZl9w8w6om7TXGVmG8L/xQ+b2V9G3R6Z+BxFomdmDWb2CzP7TtRtmYoCF3PHZ4ENY5b9JXCru58F3Br+jZmdB7wCOD98zsfNrCF8zieAjcBZ4c/Ydc4Fn2X81/0Rd78g/PkuaF8WIQu8y93XAJcCfxTuMx2bpZtoX4KOzVINAs909ycDFwAbzOxSdFxKFTGzFcBzgN9G3RYB4BZgrbs/CXgIeE/E7ZmTwv+9/wE8HzgPeGXBd6FEZ7JzFInWO4AdUTeiGApczBHuvgU4MmbxVcDnwtufA15SsPxGdx90953Aw8DFZtYNtLv77R5Udf18wXPmjAn25US0Lyfh7j3ufm94u4/gH+cydGyWbJJ9ORHtywl44Hj4Zzz8cXRcSnX5CPAXBMemRMzdv+/u2fDPO4DlUbZnDrsYeNjdH3X3IeBGgv/REqFpnKPILDCz5cALgf+Mui3FUOBibuty9x4I/qEAp4XLlwF7Ch63N1y2LLw9drkE3h6miP5XQQq59mWRzGwVcCFwJzo2Z2TMvgQdmyULUye3AY8Bt7i7jkupGmb2YmCfu98XdVtkXG8E/i/qRsxRE/0/lioxzjmKROdfCQLguYjbURQFLmQ8443B9kmWS5AOfiZBWnkP8KFwufZlEcxsPvA14J3ufmyyh46zTPuzwDj7UsfmNLj7sLtfQHDV9GIzWzvJw7UvpezM7Admtn2cn6uA64G/ibqNc80U70n+MdcTpMXfEF1L5zT9361iJZzvSYWZ2YuAx9z9nqjbUqzGqBsgkTpoZt3u3hOmND8WLt8LrCh43HJgf7h8+TjL5zx3P5i/bWafBvIFbrQvp2BmcYIvsRvc/evhYh2b0zDevtSxOTPu3mtmPyaoTaHjUmaNuz97vOVm9kRgNXBfWOt1OXCvmV3s7gdmsYlzzkTvSZ6ZvQ54EfCscHiYzL6J/h9LxCY435PoPBV4cVi0vQVoN7MvuvurI27XhJRxMbfdDLwuvP064FsFy19hZs1mtpqgoNxdYWp0n5ldGlbGf23Bc+a0sBOT93tAfsYR7ctJhK/9M8AOd/9wwV06Nks00b7UsVk6M1ucnxHAzBLAs4Ffo+NSqoC7/8rdT3P3Ve6+iqCjdpGCFtEysw3Au4EXu3t/1O2Zw7YCZ5nZajNrIiicfHPEbZrzJjnfk4i4+3vcfXn4PfIK4IfVHLQAZVzMGWb2JeAZwCIz2wv8LfAB4CYzexNBVfKXAbj7/WZ2E/AAQbrjH7n7cLiqtxHMqpEgGL8558ZwTrAvn2FmFxCkI+4C3gLal0V4KvAa4FdhPQGAv0LH5nRMtC9fqWOzZN3A58Lq9DHgJnf/jpndjo5LERnfvwPNwC1hJswd7v7WaJs097h71szeDnwPaAD+y93vj7hZMsE5Sn6mM5FimDLZRERERERERKRaaaiIiIiIiIiIiFQtBS5EREREREREpGopcCEiIiIiIiIiVUuBCxERERERERGpWgpciIiIiIiIiEjVUuBCREpiZsNmtq3gZ5WZ3Rbet8rMXlXw2AvM7AXT2MaPzWzdmGV/Z2b/NGbZBWa2Y5L1/J2ZXVfq9kVEROYKM1tY8J1+wMz2hbd7zeyBWW7LS8zsvIK//8HMnj2N9awys+0T3He+mf3QzB4ys0fM7O/NrOx9osley3jnOSIyOQUuRKRUaXe/oOBnl7tfHt63CnhVwWMvAEoOXEzgS8A1Y5a9AvifMq1fRERkznH3w/nvdOCTwEfC2xcAuXJvz8waJ7n7JcBIZ9/d/8bdf1DGbSeAm4EPuPvZwBOBi4F3lGsbBV5CBV+LyFyjwIWIzJiZHQ9vfgB4enil5t3APwDXhH9fY2bzzOy/zGyrmf3CzK4Kn58wsxvN7Jdm9mUgMXYb7v4g0GtmlxQsfjlwo5m9OVznfWb2NTNrHaeNI1c3zGyRme0KbzeY2T+Hz/+lmb0lXN5tZlvCtm83s6eXbYeJiIjUhgYz+7SZ3W9m3w87/pjZmWa22czuMbOfmtm54fKVZnZr+H16q5mdHi7/rJl92Mx+BPx/4z3fzC4HXgz8c/jde2b4vKvDdaw3s9vC7/q7zKwtzKz4qZndG/5cPsHryHsV8HN3/z6Au/cDbwf+PNzGqEzN8Pt/VXj7m2F77zezjQWPOW5m7wvbdYeZdU31WgqZ2XPN7Paw/V8xs/nh8g+Y2QPhvvyX0t86kfoyWcRTRGQ8CTPbFt7e6e6/V3DfXwLXufuLAMzsILDO3d8e/v1+4Ifu/kYz6wDuMrMfAG8B+t39SWb2JODeCbb9JYIsizvN7FLgsLv/xsyOuPunw238I/Am4N+KfD1vAlLuvt7MmoGfm9n3gd8Hvufu7zOzBuCUYIiIiEidOwt4pbu/2cxuAl4KfBHYBLw1/A6+BPg48Ezg34HPu/vnzOyNwMcIMg8Azgae7e7DZnbr2Oe7+zPN7GbgO+7+VQAzI/zdBHwZuMbdt5pZO5AGHgOe4+4DZnYWwXnCZEMwzgfuKVzg7o+EF1A6ptgXb3T3I2HwZquZfc3dDwPzgDvc/Xoz+yDwZnf/x4leSyEzWwT8v3C/nLDgos+fmdm/A78HnOvuXkTbROqeAhciUqp0mEI6Hc8FXlxwNaMFOB24guDkBnf/pZn9coLn3wjcZmbvIghgfClcvjYMWHQA84HvldimJxVcBUkSnKhtBf7LzOLAN919WwnrFBERqQc7C77/7gFWhRkBlwNfKeiMN4e/LyMI/AN8Afhgwbq+EgYtJnv+RM4Betx9K4C7HwMws3nAv5vZBcAwQXBkMgb4BMun8idmlr9Ys4LgXOEwMAR8J1x+D/CcItaVdynBcJKfh/uiCbgdOAYMAP9pZv9bsH6ROUuBCxGZTQa8NBz2cXJh8GU93onEKO6+Jxzi8TsEV30uC+/6LPASd7/PzF4PPGOcp2c5OTyuZUyb/tjdTwl2mNkVwAuBL5jZP7v756dqo4iISB0ZLLg9TDCUMwb0FnkRo/C7/UT4u5Tn500UcPhT4CDw5HC9A1Os536CiyUnV2x2BvC4u/eaWeG5AoTnC2b2DODZwGXu3m9mP+bkuUTG3fNtG6a0/pUBt7j7K0+5w+xi4FkEF2reTpDRIjJnqcaFiJRTH9A2yd/fA/7YwkiFmV0YLt8CXBsuWws8aZJtfAn4CPCIu+8Nl7UBPWF2xLUTPG8X8JTwduEY0+8Bbwufi5mdbUEtjpXAY+EQlM8AF03SJhERkTkhzHbYaWYvA7DAk8O7byPoaEPwffyzEp8/9rwh79fAUjNbHz6nzYIin0mCTIwc8BqgYYrm3wA8zU7O7pEgyPj82/D+XYTf92Z2EbA6XJ4EjoZBi3MJMiWmMtFrKXQH8FQze0K4zdbwPGQ+kHT37wLvJCiUKjKnKXAhIuX0SyAbFqj6U+BHwHlhYaprgPcCceCXFkxT9t7weZ8A5odDRP4CuGuSbXyFYIzqjQXL/hq4E7iF4ORmPP9CEKC4DVhUsPw/gQeAe8M2fYrgaskzgG1m9guC7I6PFvH6RURE5oJrgTeZ2X0EWQxXhcv/BHhD+H3+GiaerWOi598I/LkFBbzPzD/Y3YcIZhb7t/A5txBkPHwceJ2Z3UEwTOQEk3D3NEHRzOvN7CHgcYJinTeED/ka0BnW8nob8FC4fDPQGL6u9xIEHKYy7msZ055DwOuBL4XrvgM4lyDg8Z1w2U8IMktE5jQ7mdkkIiIiIiIyN5jZS4APA1e6++6ImyMik1DgQkRERERERESqloaKiIiIiIiIiEjVUuBCRERERERERKqWAhciIiIiIiIiUrUUuBARERERERGRqqXAhYiIiIiIiIhULQUuRERERERERKRqKXAhIiIiIiIiIlVLgQsRERERERERqVoKXIiIiIiIiIhI1VLgQkRERERERESqlgIXIiIiIiIiIlK1FLgQEREREZkFZvZjM/uDCq37k2b212Ve5+vN7GflXGcR25z0dZiZm9kTyrCdvzOzL850PeVUifdwzPpXhfuvsQLrLsv7IjIRBS5EqpyZ7TKzZ0fdjlpiZk8zs9vMLGVmR8zs52a2Pup2iYhIdZvs+yOKTvxExmuLu7/V3d87i23Id4KPhz+7zOwvZ7re2X4dUQiDJpmCfXfczP6i8LWb2TPMbO84z6tIsMXMvmdm/zDO8qvM7EAlgh0ipVDgQkQmZWYNUbehFGbWDnwH+DegE1gG/D0wGGW7RESkuun7Y9o63H0+cDXw12b2nKgbVCO+7O7zC34+GHF7Pgu8xsxszPLXADe4e3b2myRykgIXIjXKzGJm9pdm9oiZHTazm8ysM7xvs5m9fczj7zOz3w9vn2tmt4RXkx40s5cXPO6zZvYJM/uumZ0ArjSzF5rZL8zsmJntMbO/G7Pu15rZ7rAdf12YJTJZO8d5TTvM7EUFfzea2eNmdpGZtZjZF8N19JrZVjPrGmc1ZwO4+5fcfdjd0+7+fXf/ZcF63xhu62h4hWFlwX3PMbNfh1fb/t3MfpJP6x17pWNsyqWZJc3sM2bWY2b7zOwf84Gf/NUxM/uXcLs7zez5BevqNLP/NrP94f3fLLjvRWa2LXzdt5nZk8bbfyIiMiMTfn+Y2Rrgk8Bl4dXxXjh16MfYTIix3ynAqE7hFN9HbmZvNbPfhPf/hwUmastnzewfw9vfttFX83Nm9vrwvsnOARaa2c3h9/1dwJnF7jx3vxu4H7hgqtcXvo6PmNlj4b75pZmtHfs6wr//PPxe3W9mbxyz/6ba/x+14LzlmJndY2ZPH6/txZ5jWHA+89Uxyz5qZh8r2P6jZtYXfs9fW+z+K3ztZjYP+D9gacF7+Crgr4Brwr/vC58z2blHQ3je8biZPQq8cJLNf5MgYDeyj8xsAfAi4PNmdrGZ3R7unx4LzpGaJngdU70vkx2DLzCzB8J9uM/MritlH0r9UuBCpHb9CfAS4HeApcBR4D/C+/4HeGX+gWZ2HrAS+N/wy/CW8DGnhY/7uJmdX7DuVwHvA9qAnwEngNcCHQRfem8zs5cUrPvjwLVAN5AkuEpVTDvH+lJhu4HnAY+7+73A68J1rwAWAm8F0uOs4yFg2Mw+Z2bPD790R4Tt/ivg94HFwE/D7WJmi4CvAf8PWAQ8Ajx1graO53NAFngCcCHwXKBwLPMlwIPhuj8IfMZs5MrGF4BW4HyC9+UjYZsuAv4LeEv4uj8F3GxmzSW0S0REpjbh94e77yD43rk9vDreMdXKpvpOmez7qMCLgPXAk4GXA88rpi3u/rv5K/kEmRAHgFuLOAf4D2CA4Pv8jeFPUczsUmAt8HARr++5wBUEwaIO4Brg8Djr3ABcBzwHOAsodejsVoJASifBa/6KmbWM87hizzG+BLzAguycfFbqy4H/Cfftx4Dnu3sbcDmwrcT2AuDuJ4DnA/sLMjL+B3g/JzM1nhw+fLJzjzcTHEMXAusIjoWJtpkGbiI438t7OfBrd78PGAb+lOBYvgx4FvCHpb62Io7BzwBvCffhWuCHpW5D6pMCFyK16y3A9e6+190Hgb8Drrbg6v83gAvs5JWba4Gvh497EbDL3f/b3bNhUOBrjP4y+5a7/9zdc+4+4O4/dvdfhX//kuCL+3fCx14NfNvdf+buQ8DfAF5kO8f6H+DFZtYa/v2qcBlAhuBk4gnhlbB73P3Y2BWEy54WtuHTwKHw6lH+yslbgH9y9x1h2uP7C/bVC4AH3P2r7p4B/pXgZG9K4fqfD7zT3U+4+2MEwYdXFDxst7t/2t2HCU40uoEuM+sOn/tWdz/q7hl3/0n4nDcDn3L3O8PX/TmCtOVLi2mXiIgUp4jvj1JN9Z0y2fdR3gfcvdfdfwv8iIJshmKY2dnA54Fr3H0Pk5wDhJ3wlwJ/E36PbSf4rprK42aWBm4nuJDxzSJeX4bg4si5gIWP6Rln3S8H/tvdt4ed+b8r5fW7+xfd/XD4Wj8ENAPnjPPQYs8xdgP3ElyQAXgm0O/ud4R/54C1ZpZw9x53v3+S5r08zF7I/ywt5bVBUeceLwf+1d33uPsR4J+mWOXngJeZWSL8+7XhMsJ9cke4L3cRXEj5nfFXM6mpzkMzwHlm1h6eE907jW1IHVLgQqR2rQS+kf/CA3YQRMO73L0P+F9OfnG9Arih4HmXFH5ZEgQ2lhSse0/hhszsEjP7kZkdMrMUwZWIReHdSwsf7+79jL5qMmE7x74gd384vP93w+DFizkZuPgC8D3gRgvSRT9oZvHxdkx4AvR6d19OEK1fSnDCmG/PRwvac4QgdXfZOK/Fx+6LSawE4kBPwbo/RXA1IW/khDXcTwDzCa7wHHH3oxOs911j3q8VYVtFRKSMpvj+KNVU3ymTfR/lFQY6+gm+M4piZkngW8Bfu/tPC7Y50TnAYqBxTBt3F7GpRWG7rgOeQfBdOOnrc/cfAv9OkOFx0Mw25bMYxhi1D4tszwgze5cFQ1VSYRuSnDx/KVT0OQajs1pHLrCEgZVrCM6Reszsf83s3Emad5O7dxT87C/ltYWmOvcoaf+5+8+AQ8BVZnYGQbbP/0AQBDOz71hQqPMYQSBqvH1ZTJsnOw99KUHQb7cFw3Uvm8Y2pA4pcCFSu/YQpCMWfum1uPu+8P4vAa8M/+EnCK7U5J/3kzHPm+/ubytYd2HGBARfWjcDK9w9STC2Nj/EoQdYnn9gGKVfWEI7x8oPF7mK4ErVwwBhFsLfu/t5BOmXL2J0OuO43P3XBAWn1ha05y1j2pNw99vC17Ki4LVY4d8EQ2ZaC/4eG+wZBBYVrLfd3QuH4ExkD9BpZh0T3Pe+Me1tdfex6cQiIlJG43x/jP1uhMm/F6b6Tpns+2jK5k12p5nFCL67f+TunxqzzYnOAQ4RDDkobOPpRbSFMEvhQwTDTPLDByZ9fe7+MXd/CsEQybOBPx9n1aP24TjtmXD/W1DP4t0EWQcLPBhSk2JMnZGwLaWcY3wFeIaZLQd+j5MXWHD377n7cwgyKn9NkLkzXeO9x2OXTXXuMdX+G8/nCV77a4Dvu/vBcPknCF7TWe7eTjAM6JR9GZrqfGnC81B33+ruVxEEX75JMHxFRIELkRoRt6BwVP6nkSB48D47WehqsZldVfCc7xJEtf+BYDxkLlz+HeBsM3uNmcXDn/UWFPuaSBtBRsCAmV1McIUh76sEGRKXW1Ck6e8Z/UU2VTvHupFgfObbKDgZMLMrzeyJYSrrMYJUwuGxT7ag4NO7whMKzGwFQSAkn8b5SeA9+bGUFhS1ell43/8C55vZ74f7+E8Y/WW7DbjCzE4Pr2S9J3+HBymu3wc+ZGbtFhQlPdPMpkyjDJ/7fwRjPBeE78kV4d2fBt4aZr2Ymc2zoFhq21TrFRGR4hXx/XEQWG6jCxJuA37fzFrN7AnAmwrum+o7ZbLvo6mM15ZC7wPmAe8Ys3zCcwAPhjF+Hfi78PWcR1D7oRQfAP7CgjoSE76+cJuXhFkNJwgCHqd8pxN0Wl9vZudZkIn5t2Pu38bE+7+NIBBzCGg0s78BxsvqKPocA8DdDwE/Bv4b2OlBzRHMrMvMXmxBDYdB4PhE6yjSQWBheL5RuGxVGJgq5tzjJuBPzGy5BTVbipmu9vMEtUTezOihQm0E++Z4mEnytnGem7eNid+XCY9BM2sys2vNLOnB8KpjzGwfSh1R4EKkNnyXoEhU/ufvgI8SZEF838z6CE6sLsk/wYN6El8n+PIpvBrQRxAYeAWwnyAN9f8jGPc5kT8E/iHczt9QEP0Ox2/+MUHAoQfoAx7j5PRxk7ZzrPBL+HaCKx5fLrhrCUGQ5BjBcJKfAOPNZd4Xrv9OC2ZFuQPYDrwrXP83wtd7owWpjtsJxofi7o8DLyM48TpMUAjs5wVtuyVs0y+Bewi+fAu9FmgCHiAoQvpVgqsuxXgNwYnSrwn23zvDbd5NcPLw7+E6HwZeX+Q6RUSkeJN+fxAUCbwfOGBmj4fLPgIMEXQoP8fJYZnFfKdM+H1UhPHaUuiVBLWQjtrJWSmuLeIc4O0Ewz4OEGSb/HeR7cn7X4LvqjdP8fraCQLzRwmGLxwG/mXsytz9/wiG6vyQ4PtvbKHGCfc/wdCP/yMourqbIDgy0fDPYs8x8v6HMedXBP2qdxHs1yME9R9KLl6ZF2b8fAl41E7WwPhKePdhM8vXfpjs3OPTBPvhPoLaHF8vYru7gNsIAl83F9x1HcGFq75wvV8+5cknTfa5mOoYfA2wKzxm3gq8eqo2y9xgwXA7EZHyMLP5QC9BKuHOiJszY2b2Y+CL7v6fUbdFRERERGQuUsaFiMyYmf1umA44j+CKya+AXdG2SkRERERE6oECFyJSDlcRpPvtJ0iFfYUrnUtERERERMpAQ0VEREREREREpGop40JEREREREREqlZj1A2IyqJFi3zVqlVRN0NERKRu3XPPPY+7++Ko2zFTOmcQERGprKnOGeZs4GLVqlXcfffdUTdDRESkbpnZ7qjbUA46ZxAREamsqc4ZNFRERERERERERKqWAhciIiIiIiIiUrUUuBARERERERGRqqXAhYiIiIiIiIhULQUuRERERERERKRqKXAhIiIiIiIiIlVLgQsRERERERERqVoKXIiIiIiIiIhI1VLgQkRERERERESqlgIXIiIiIiIiIlK1FLgQERERERERkapVNYELM9tgZg+a2cNm9pfj3H+umd1uZoNmdl0pzxURERERERGR2tQYdQMAzKwB+A/gOcBeYKuZ3ezuDxQ87AjwJ8BLpvFcqUM7elJs3n6Qfb1plnUk2LC2izXdyaibJSIiInOEu3MgNcDR/iEWtDaxJNmCmUXdLBGRulMtGRcXAw+7+6PuPgTcCFxV+AB3f8zdtwKZUp8r9WdHT4pNW3aSSmfoTraQSmfYtGUnO3pSUTdNRERE5gB35/ZHDnPT3Xv43v0HuenuPdz+yGHcPeqmiYjUnWoJXCwD9hT8vTdcVunnSo3avP0gyUScZCJOzGzk9ubtB6NumoiIiMwBB1IDbN11hFwYp8g5bN11hAOpgWgbJiJSh6olcDFeTl2x4eqin2tmG83sbjO7+9ChQ0U3TqrPvt40bS2jRzq1tTSyrzcdUYtERERkLjnaPzQStMjLebBcRETKq1oCF3uBFQV/Lwf2l/u57r7J3de5+7rFixdPq6FSHZZ1JOgbyI5a1jeQZVlHIqIWiYiIyFyyoLWJ2JjLZzELlouISHlVS+BiK3CWma02sybgFcDNs/BcqVEb1naRSmdIpTPk3Edub1jbFXXTREREZA5Ykmxh/arOkeBFzGD9qk6WJFuibZiISB2qillF3D1rZm8Hvgc0AP/l7veb2VvD+z9pZkuAu4F2IGdm7wTOc/dj4z03khcis2ZNd5KNV6weNavINeuXa1YRERERmRVmxmVnLmT1onmaVUREpMKqInAB4O7fBb47ZtknC24fIBgGUtRzpf6t6U4qUCEiIiKRMTO6OxJ0a6iqiEhFVctQERERERERERGRUyhwISIiInOOmTWY2S/M7DtRt0VEREQmp8CFiIiIzEXvAHZE3QgRERGZmgIXIiIiMqeY2XLghcB/Rt0WERERmZoCFyIiIjLX/CvwF0BuogeY2UYzu9vM7j506NCsNUxEREROpcCFiIiIzBlm9iLgMXe/Z7LHufsmd1/n7usWL148S60TERGR8ShwISIiInPJU4EXm9ku4EbgmWb2xWibJCIiIpNpjLoBIiIAO3pSbN5+kH29aZZ1JNiwtos13cmomyUidcbd3wO8B8DMngFc5+6vjrJNMjl350BqgKP9QyxobWJJsgUzi7pZIiIyixS4EJHI7ehJsWnLTpKJON3JFlLpDJu27GTjFasVvBARmcPcndsfOczWXUfIOcQM1q/q5LIzFyp4ISIyh2ioiIhEbvP2gyQTcZKJODGzkdubtx+MumkiUsfc/cfu/qKo2yETO5AaGAlaAOQctu46woHUQLQNExGRWaXAhYhEbl9vmraW0QlgbS2N7OtNR9QiERGpBkf7h0aCFnk5D5aLiMjcocCFiERuWUeCvoHsqGV9A1mWdSQiapGIiFSDBa1NxMaMCIlZsFxEROYOBS5EJHIb1naRSmdIpTPk3Edub1jbFXXTREQkQkuSLaxf1TkSvMjXuFiSbIm2YSIiMqtUnFNEIremO8nGK1aPmlXkmvXLVZizhmmWGBEpBzPjsjMXsnrRPM0qIiIyhylwISJVYU13Uh3bOqFZYkSknMyM7o4E3Ro+KCIyZ2moiIiIlJVmiRERERGRclLgQkREykqzxIiIiIhIOSlwISIiZaVZYkRERESknBS4EBGRstIsMSIiIiJSTgpciIhIWeVniUkm4vSkBkgm4irMKSIiIiLTpllFRESk7DRLjIiIiIiUizIuRERERERERKRqKXAhIiIiIiIiIlVLgQsRERERERERqVoKXIiIiIiIiIhI1VLgQkRERERERESqlgIXIiIiIiIiIlK1NB2qiIhIHdnRk2Lz9oPs602zrCPBhrVdmppWREREapoyLkREROrEjp4Um7bsJJXO0J1sIZXOsGnLTnb0pKJumoiIiMi0KXAhIiJSJzZvP0gyESeZiBMzG7m9efvBqJsmIiIiMm0KXIiIiNSJfb1p2lpGjwJta2lkX286ohaJiIiIzJwCFyIiInViWUeCvoHsqGV9A1mWdSQiapGIiIjIzClwISIiUic2rO0ilc6QSmfIuY/c3rC2K+qmiYiIiEybAhciIiJ1Yk13ko1XrCaZiNOTGiCZiLPxitWaVURERERqmqZDFRGRmqMpPye2pjupfSEiIiJ1RRkXIiJSUzTlp4iIiMjcosCFiIjUFE35KSIiIjK3KHAhIiI1RVN+ioiIiMwtClyIiEhN0ZSfIiIiInOLAhciIlJTNOWniIiIyNyiwIWIiNQUTfkpIiIiMrdoOlQREak5mvJTREREZO5QxoWIiIiIiIiIVC0FLkRERERERESkailwISIiIiIiIiJVSzUuRGrcjp4Um7cfZF9vmmUdCTas7dLYfxERERERqRvKuBCpYTt6UmzaspNUOkN3soVUOsOmLTvZ0ZOKumkiIiIiIiJlocCFSA3bvP0gyUScZCJOzGzk9ubtB6NumoiIiIiISFkocCFSw/b1pmlrGT3iq62lkX296YhaJCIiIiIiUl4KXIjUsGUdCfoGsqOW9Q1kWdaRiKhFIiIiIiIi5aXinBIpFZacmQ1ru9i0ZScQZFr0DWRJpTNcs355xC0TEREREREpD2VcSGRUWHLm1nQn2XjFapKJOD2pAZKJOBuvWK3gj4iIiIiI1A1lXEhkCgtLAiO/N28/qI53CdZ0J7W/REREpC65OwdSAxztH2JBaxNLki2YWdTNEpFZpsCFRGZfb5ruZMuoZSosKSIiIiIQBC1uf+QwW3cdIecQM1i/qpPLzlyo4IXIHKOhIhIZFZYUERERkYkcSA2MBC0Acg5bdx3hQGog2oaJyKxTxoVERoUlZa5TcVoREZGJHe0fGgla5OU8WN6tC10ic4oyLiQyKiwpc5mK04qIiExuQWsTsTEjQmIWLBeRuUUZFxIpFZaUuUrFaUVERCa3JNnC+lWdp9S4WDKmRpqI1D8FLkREIqDitCIiIpMzMy47cyGrF83TrCIic5wCFyIiEVjWkSCVzoxkWoCK04qIiIxlZnR3JFTTQmSOU40LEZEIbFjbRSqdIZXOkHMfub1hbVfUTRMRERERqSoKXIiIREDFaUVEREREiqOhIiIiEVFxWhERERGRqSnjQkRERERERESqVtUELsxsg5k9aGYPm9lfjnO/mdnHwvt/aWYXFdz3p2Z2v5ltN7MvmZnmSBIRERERERGpA1URuDCzBuA/gOcD5wGvNLPzxjzs+cBZ4c9G4BPhc5cBfwKsc/e1QAPwillquoiIiIiIiIhUUFUELoCLgYfd/VF3HwJuBK4a85irgM974A6gw8y6w/sagYSZNQKtwP7ZariIiIiIiIiIVE61BC6WAXsK/t4bLpvyMe6+D/gX4LdAD5By9+9XsK0iIiIiIiIiMkuqJXBh4yzzYh5jZgsIsjFWA0uBeWb26nE3YrbRzO42s7sPHTo0owaLiIiIiIiISOVVy3Soe4EVBX8v59ThHhM95tnATnc/BGBmXwcuB744diPuvgnYBLBu3bqxgRERKaMdPSk2bz/Ivt40yzoSbFjbpak/RURERESkZNWScbEVOMvMVptZE0FxzZvHPOZm4LXh7CKXEgwJ6SEYInKpmbWamQHPAnbMZuNFZLQdPSk2bdlJKp2hO9lCKp1h05ad7OhJRd00EZGq5O709KZ5YH+Knt407rq+IiIiklcVGRfunjWztwPfI5gV5L/c/X4ze2t4/yeB7wIvAB4G+oE3hPfdaWZfBe4FssAvCLMqRCQam7cfJJmIk0zEAUZ+b95+UFkXIiJjuDu3P3KYrbuOkHOIGaxf1cllZy4kuCYjIiIyt1VF4ALA3b9LEJwoXPbJgtsO/NEEz/1b4G8r2kARKdq+3jTdyZZRy9paGtnXm46oRSIi1etAamAkaAGQc9i66wirF82juyMRbeNERESqQLUMFRGROrKsI0HfQHbUsr6BLMt0Ai4icoqj/UMjQYu8nAfLRURERIELEamADWu7SKUzpNIZcu4jtzes7Yq6aSIiVWdBaxOxMSNCYhYsFxEREQUuRKQC1nQn2XjFapKJOD2pAZKJOBuvWK36FiIi41iSbGH9qs6R4EW+xsWSMUPuRERE5qqqqXEhIvVlTXdSgQoRkSKYGZeduZDVi+ZxtH+IBa1NLEm2qDBnlXB3DqQG9N6IiERIgQsRmTN29KTYvP0g+3rTLOtIsGFtl4IrIlIVzIzujoSKcVYZzfgiIlIdFLioMep4iUzPjp4Um7bsJJmI051sIZXOsGnLTg1hEZG6oKyAytCMLyIi1UE1LmpIvuOVSmdGdbx29KSibppI1du8/SDJRJxkIk7MbOT25u0Ho26aiMwiM1thZj8ysx1mdr+ZvSPqNs1UPivgprv38L37D3LT3Xu4/ZHDBDPJy0xoxhcRkeqgjIsaUtjxAkZ+b95+UFeMpSZEmTG0rzdN95hCd20tjezrTc/K9kWkamSBd7n7vWbWBtxjZre4+wNRN2y6lBVQOfkZXwqDF5rxRURk9injoobs603T1jI61lQvHa8dPSk+cstDXPeV+/jILQ8pi6QORZ0xtKwjQd9AdtSyvoEsy3RSLzKnuHuPu98b3u4DdgDLom3VzCgrYHrcnZ7eNA/sT9HTmx43Q0UzvoiIVAdlXNSQZR0JUunMSKYF1EfHS7UH5oaoM4Y2rO1i05adQBDw6xvIkkpnuGb98opvW0T1iaqTma0CLgTuHOe+jcBGgNNPP312G1YiZQWUrtiim5rxRUSkOijjooZsWNtFKp0hlc6Qcx+5vWFtV9RNmxHVHpgbSskYqkQGzpruJBuvWE0yEacnNUAyEVdwTGZF1NlGMj4zmw98DXinux8be7+7b3L3de6+bvHixbPfwBIoK6B0Ew2vOZAaOOWx+RlfzluapLsjMWtBi2IyQkRE5gplXNSQfMer8KrdNeuX13zHS7UH5oZiM4YqmYGzpjtZ858XqT1RZxvJqcwsThC0uMHdvx51e2ZKWQGlm2x4TTXUBdE0rCIioylwUWPqseNVr0NgZLRih2qokyf1Ij885Jvb9tHV1sxZXfNZND8I0io4Gx0Len2fAXa4+4ejbk+55LMCqqHTXQuqfXiNCq7ODk0jLFI7NFREIlevQ2BktGKHatRzEVqZOwqHh3S1NXNsIMs9u3t5/HiQhq7gbKSeCrwGeKaZbQt/XhB1o2R2VfvwGhVcrTxNIyxSW5RxIZGr1yEwcqpiMoaUgSP1oDBz6Amnzefe3/YC8JuDx4k3NKgwbITc/WeALqnOcdU+vKbaM0LqgbJaRGqLAhdSFepxCIxMj2b/kHpQWLtncVsLF53ewcOPHedg3yCXJeIKzopUgWoeXpPPCBlb46JaMkLqQbXXOallGoIjlaDAhYhUFWXgSD0Ymzm0uK2FpsYGLkvE+dPnnB1x60Sk2lV7Rkg9UFZLZaiwrFSKAhciUnWUgSO1TplDIjJT1ZwRUg+U1VIZGoIjlaLAhYiISJkpc0hEpDLKNQxBWS2VoSE4UikKXIiIiFSAModERMqr3MMQlNVSfhqCI5Wi6VBFRERERGqYu9PTm+aB/Sl6etN1O6XnRMMQDqQGom2YjKj2qYaldinjQkRERESkRs2lYogahlD9NARHKkWBCxERERGRGjWXiiFqGEJtmGoIjqZLlelQ4EJEREREpEbNpSwEzQRS++ZShpCUlwIXIkXY0ZMaNTvAhrVdKronIiIikZtLWQgahlD75lKGkJSXinOKTGFHT4pNW3aSSmfoTraQSmfYtGUnO3pSUTdNRERE5ri5VgwxPwzhvKVJujsSClrUmMkyhEQmo4wLkSls3n6QZCJOMhEHGPm9eftBZV2IiIhIpJSFILVkLmUISXkp40JkCvt607S1jI7xtbU0sq83HVGLRERERE5SFoLUirmWISTlo4wLkSks60iQSmdGMi0A+gayLNM4PBERkTlHMyKITF+5MoT0OZx7FLgQmcKGtV1s2rITCDIt+gaypNIZrlm/POKWiYiIyGzSjAgiMzfVdKlT0edwbtJQEZEprOlOsvGK1SQTcXpSAyQTcTZesVr1LUREROaYiWZEOJAaiLZhInOIPodzkzIuRIqwpjupQIWIiMgcN9mMCJrKUapNvQ6n0OdwblLgQkRERESkCJoRQWpFPQ+nKOfnsF6DO/VIQ0VERERERIqgGRGkVtTzcIpyfQ7zwZ2b7t7D9+4/yE137+H2Rw7j7lM/WWadMi5ERERERIpQrhkRpPrV8pV4d2dvbz/xWIzmphjpoWEyw143wynK9TmcKLizetG8mt9H9UiBCxEREZEqUssdprlgpjMiSPWr5WEW+bb/6NcH+dW+Y8RixsWrOok3GMM5L9uwpkr8nyplneX4HKpWRm1R4EJERESqjpl9EPhHIA1sBp4MvNPdvxhpwyqsljtMIvWilq/E59ve2tzI0o4E+3vT3LXrCM9ZcxrnLGkvy7CmSvyfiuJ/n2rW1BbVuBAREZFq9Fx3Pwa8CNgLnA38ebRNqrx6Hpcuc4e709Ob5oH9KXp60zVXM2CyK/HV7mTbjRWdCc5f2s6qha2c291etiBAJf5PRfG/TzVraosyLkRERKQaxcPfLwC+5O5H5kLGgVKXpdbVQ9ZQLV+JH912Y35LnPZEnFUL55W0/ycbtlGJ/1NR/O9TzZraosCFiIiIVKNvm9mvCYaK/KGZLQbqPu2gljtMtUR1RCqnlodZ5OWvxI8NvtTClfhytH2q4FMl/k9F9b9PNWtqhwIXIiIiUnXc/S/N7P8Djrn7sJmdAK6Kul2VVssdplpRDxkB1awesoaq9Up8MQG3crR9quBTJf5P6X+fTEWBCxEREakaZvb74ywr/PPrs9ea2VetHaZ6Us0ZAblcjgcP9NGTGqA72cI5S9qIxWqrJF29ZA1V25X4sQG35kbj/KVJFrU10znm/8RM2z5V8KkS/6f0v0+mosCFiIiIVJPfneQ+p84DF1B9HaZ6U60ZAblcjq/es5dvbdtPNuc0xoyrLljK1U9ZXlPBC105r4zCgFu8wRjKOpu2PMq5S9poT8TLmjVUTPDJzEbe03zR0nIEL/S/TyaiwIWIiIhUDXd/Q9RtkPpWrRkBDx7oGwlaAGRzzre27eeJy5Kc291eMzU5dOW8MgoDbommBm7d8RjDOSedGWZ+S7ysWUPFBJ805EpmmwIXIiIiUpXM7IXA+cDI2bK7/0N0LZJ6UK0ZAT2pgZGgRV425xw8NsDR/kxNdRB15bz8CgNug0M5hnOOAYl4A1DerKFigk/VPORK6pMCFyIiIlJ1zOyTQCtwJfCfwNXAXZE2SupCtWYEdCdbaIzZqOBFY8yY39LIzx8+rA7iHFcYcGtuitEYM7raW5jfEnTnyp01NFXwqVqHXEn9UuBCREREqtHl7v4kM/ulu/+9mX2IOVDfQmZHNWYEnLOkjasuWHpKjYtEvEEdRBkVcOvtH2TFggQ7eo6Rc4ska6hah1xJ/VLgoobs6EmxeftB9vWmWdaRYMPaLtZ0J6NuloiISCWkw9/9ZrYUOAysjrA9IhUVi8W4+inLeeKy5KhZRQ4eG1QHUYDRAbdzu5M8cVlH2bOGiplyFWY+5KrY7YjkKXBRI3b0pNi0ZSfJRJzuZAupdIZNW3ay8YrVCl6IiEg9+o6ZdQD/DNxLMKPIf0baIpEKi8VirFmaZM3Sk+d21VqTQ6JViayhUgturlrUihk0NhjLkwmWhFOllns7IqDARc3YvP0gyUScZCIOMPJ78/aDClyISNVQZpiUi7u/N7z5NTP7DtDi7qko2yQShWqtySH1p9iCmxMFHpYUGURRYU+ZDgUuasS+3jTdYyLrbS2N7OtNT/AMEZHZpcwwKScze+04y3D3z0fRHpEoVWNNDpl9lR5eUWzBzfEDD4dZ0BrHYcq2qbCnTIcCFzViWUeCVDozkmkB0DeQZZk+3CJSJZQZJmW2vuB2C/AsgiEjClxI5DQ+X2bbbAyvKLbg5qmBB2f34TQ/evAQg9nclG1bkIjTkWgkPZSjuSlGemiY4ZxXVd0WfcarjwIXNWLD2i42bdkJBJkWfQNZUukM16xfHnHLREQCygyTcnL3Py7828ySwBciao7ICI3Pl9kwtuOMe8WHVxRbT2VsgOP4QJaDxwY4f1k7g9ncpG1zd3Ye7uf+/cfYezRNLGZcsrqTS1ZXT90WfcarkwIXNWJNd5KNV6weNXb8mvXLdRVTRKqGMsOkwvqBs6JuhNS2clxF1fh8qbTxOs6rF82jIWbkhk+mOpR7eEWx9VTGBjgGs8OsX9VJemh4yrblPz/LFiRIJuKkM8McH8hw+sLWqgkK6DNenRS4qCFrupMKVIhI1VJmmJSTmX2bYCYRgBhwHnBTdC2SWleuq6j1Pj5fKfLRG6/j/Ku9vSztSNCbzo48rhLT4k5UT2XscXHpGZ0jAQ4DfvTgYwxmT34wJmrbyc+PMb8lzvyW4GJHb3+GpR1lfSnTVu+f8VqlwIWIiJSFMsOkzP6l4HYW2O3ue6NqjNS+cl1FLbYOQC2azRR5BUgmNl7HubW5kdPaWjg2cHzWp8Wd7Ljo7kjg7hztzxQ1ZW8tfH5qoY1RiPozq8CFiIiUjTLDpFzc/SdRt0HqS7muohZbB6AWzVaK/EwDJFF3oCol/7pODGXpH8zQ2twIBK8rZsaFKzu4aOWCsr/uqfbnVMdFKVP21sLnpxbaONuqoe6HAhciIiJSNcysj5NDRE7h7u2z2Bwpsyg7nOW6ilpKJ63WzFaK/EwCJOXqQFVb8KPwdTXEgmEUe470s2xBgpgZ61d10p1MjAzlqMR2J9qf+eMi3mAkmhoYDGcD6e0fHGmLmY107I/2DwGM7NPJhplUw74fq54/49NVDXU/FLgQERGRquHubQBm9g/AAYKZRAy4FmiLsGkyQ1FfsSvnVdSJ6gDUutlKkZ9JgKQcHaioj8XxFL6u3LATbzDOX9rOud3trFo4r2Id52L254LWJpobjaGsc+uOxxjOOY0xY8WCBOd2J0eCE7c/cpgf/vogR/szNMbgWed28aw1p3HnzqMTDjOpVrXyGZ+tAFw11P1Q4EJERESq0fPc/ZKCvz9hZncCH4yqQTIzUV+x01XUqc1WivxMAiTl6EBFfSyOZ+zrygw7veksyUS8om0qZn8uSbZw/tIkm7Y8ynDOMaCrvYUdPcd44rIOujsS9KTSfP3evdy//xjHBjKYGXuPDmAGv3ns+Mg2GmLGgweOYUZFAzJzwWwG4Kqh7ocCFyIiIlKNhs3sWuBGgqEjrwSGJ39K/aq2tPbpqIYrdlFcRa2l9262gjszCZCUowNVDcfiWFF1DIvZrpmxqK2Zc5e0kc4Mk4g3ML+lkZzbyD7bfbifhw72cfjEIDEzGmKw+0g/v3nsOM3xBgazWeINRnbYuWXHY/zmseN0tbdEnulSy2YzAFcNdT8UuBAREZFq9Crgo+GPAz8Pl8051ZjWPh3VcMVuttXiezfT4E4xgZqZBEjK0YEa71hsboT+oSw/3HGQ7mQL5yxpIxaLFb3O6cjvqyP9Q8TcecLieWzb00trc+NIXYtKdgzdHcd5wuL5PNY3wImhYYZzPu52O1ubaE+cnL4UTn5+3Z2jJ4ZIDWRJDwXx5abGBuY1N9DcGGMwkwMg0dTArTseI5dzEvGGqsh0yaulAGPebAbgqiFjTYELERERqTruvgu4Kup2VINqTGufjmq4Yjfbyv3eVXvnqpRAzXQDJOXoQI09FpsboamxkY/+4DcMDQf1G666YClXP2V5xYIXJ/fVYXYfTpPqH+JpZy1i+YIEi9tauGBFku6O1oq9v6PfK6d/MMu53e0sX5BgRWfrKY+f7PN7IDXA4eODPPWMhfzf/QfIDufI5XKsX7WYpgbjCae1sW1PL4NDOXI5Z2lHgvktQTc06kwXqM0AI8x+MDjquh8KXIiIiEjVMLO/cPcPmtm/Mc7sIu7+JxE0K1LVmNY+HdVwxW62lfO9q4XO1WwF2WbagRp7LPYPZUeCFgDZnPOtbft54rIka5ZWZorv/L46ls5y5MQgi9ta+Oztu1nZ2RoUv2xYSXfHqQGEcm8//14dPpHh6/fu45lrTuOOR4+ccmxN9vk92h9kW6zoTPCCtd0cOj5AQ8zobm/mrK52Ll7dydldbezt7edo/+CYaV6jz7qq1eBwV3sza7rb2PLQIZobG2hPNLJ+1cK6DQZXTeDCzDYQpIM2AP/p7h8Yc7+F978A6Ade7+73hvd1AP8JrCU4yXmju98+e60XERGRMtkR/r470lZUkXoaYhH1FbvZVs73bvzO1WEWtMbxcFtRB4KiCLJNNwslfywuSbbwvfsPMJyDRDzIrhjKOg0xoyeVrljgIr+v0plhujsS/PzhxxnOOdlhZ9idLQ8dGil8Wapi9knhe3V8IMv+3jQOQVbEBB33iT6/C1qbGA6jaWd3zeeM0+YRj8W4eFUH54SzjuT3dSbrVZd1VepxWw2ZT+7OHY8e4eHHjrN68XwGMznOX9rOpWd0Vk0gs9yqInBhZg3AfwDPAfYCW83sZnd/oOBhzwfOCn8uAT4R/oYgoLHZ3a82syagcuFJERERqRh3/3b4+3P5ZWYWA+a7+7HIGhahuTjEol6U8707tXPl7D6c5kcPHmIwm6uKDIzpBmqm2xGcaRZK/vk7Dx1nX6qf4Ry0tzRyYjCLmZEZdty96P1ZyuvI76tEvIG+gWwwW4cZjQ1GLus0NzZUNDOn8L1KZ4Zxghk/mptiDKZzJQWcCo/zI/2ZkW3mgxZ5UWRdFfOelHLc5nI5frDj4ClZDrP9uSsMZA5mswBs29PL2V1tdRsYrorABXAx8LC7PwpgZjcSjGstDFxcBXze3R24w8w6zKwbOAFcAbwewN2HgKFZbLuIiIiUmZn9D/BWgplE7gGSZvZhd//naFs2++biEIt6Uc73bmzn6vhAloPHBjh/WTuD2Ymvks+m6QRqZhJ8mGmKf/75DTF45jmn8a1t+zmWzrB60TyecvoC9h89wT27g+EcUxXsLPV1nNxXh2mJNxBviNHV3kI2l2NpR4L2RGPRmTmFnXMDtu05OuU+KXyvEvEGGmNBMdB8cc1SMoNKOc5nM+uq2Pek2OPW3fnpbx7nc7ftJhtOC7u0IwEcnvXPXS1micxUtQQulgF7Cv7ey8lsiskeswzIAoeA/zazJxOc3LzD3U9UrrkiIiJSYee5+7FwStTvAu8m+I6fc4ELGJ3WfiA1wI6eYzV78jmZeji5Hms6HbXx9sPYztVgdnhURxOir30yWQd2ove22ODDeM+f6dCU/PNzw8H6n7XmNIayOZ60PIm5kxrI8Y//u4PmxoYpC3aWGkQZva8GOWdJG1t3HqapxFoFYzvnh48PsGh+C/GGIGNksn2yemEr8cZgitJnnLOYnY+f4PjAMB2JBtZ0t5eUGVSNw8CKfU+KDbwcSA1w//5jZMMVOrC/N82C1visf+5KyRKphfo4xaiWwMV4e2xsQa6JHtMIXAT8sbvfaWYfBf4S+OtTNmK2EdgIcPrpp8+owSIiIlJRcTOLAy8B/t3dM2Z2SrHOuaReTj4nUu+vr1juzp2PHmZHzzHSQzkSTTHWdLdzyRkLR3WuDPjRg48xmD35saiG2ifjdWAne2+LCT5MlJ6/alHrjGqIFHb+GmIx9hw5TixmYEZLUyOfv/NROlrj9A9mGRzO8aW7fsv5S9s5f1nHKeuaThClcF+t6U6yflVnyUG7sZ3z5sYGtu46wjPXnEYmnR13n4x9P5objcXzm/ntkX76h4aZ19TAOUvai9qH1ayU96SYwMvR/iGa4zEaYhbU9CDojA5mh2f9c1dKdlOtFh8dqyKBCzNrBd4FnO7ubzazs4Bz3P07EzxlL7Ci4O/lwP4iH+PAXne/M1z+VYLAxSncfROwCWDdunVz+uRHRCQqO3pSbN5+kH29aZZ1JNiwtos13ZUpfiY17VPALuA+YIuZrQTmZI2LvHo5+ZxIvb++Yh3oTXPnziPcufMIw7mgSOSxgSwrO1vpXtA60rlyd472Z2qi9slk7+1kV47dnQO9ae75bS+fu20nsZhh2Mn0/IWtM6ohUtj5m9/SODIVaHpomOywk4g3cCyd4fHjQyO1Lu7ZdZQ13e2nZF0saG3CcA71DdI3mKWtuZHFbc2ndGgnyjyZbsZCvnMebzASTQ00NxgXrOggF2ZbjLdPTgl2xBv45rb9nLukjcVtweNm+tkb73Xmtz1VcKZcmVflLmy8oLWJwcwwF6/q5K5dweezMWZccfbiWf/clTI8p15mpqpUxsV/E6RzXhb+vRf4CjBR4GIrcJaZrQb2Aa8AXjXmMTcDbw/rX1wCpNy9B8DM9pjZOe7+IPAsRtfGEBGRKrGjJ8WmLTtJJuJ0J1tIpTNs2rKTjVesVvBCRnH3jwEfK1i028yujKo91aBeTj4nEuXrq6YhKntT6ZGgBcBwzrlz5xEuf8JCuhecrD9fS7VPJntv13S3jxt86Gpv5vZHDvPggWPsONDH/tQAbS1xkonGk+n56cyM9sHYfdjRGsccjqYz9A9l2by9h329aYISe9AYM472Z3jwQN8ps42c1tbE/JY439y2n8xwjnhDjFdfupLT2ibOdChHVtGC1iaaG42hrHPrjsfCzjRcs/50nnbaPDpam0/ZJ2Pfj8GhHNmck84MM78lPur9mc5nL5fL8dPfPM79+4/RHI+RG85x9pJ2TgwGdVlODA0znPNxX3s591G5CxsvSbZwwYoFbNtzlGetOW1kJo+nn7Uoks9dscGuepmZqlKBizPd/RozeyWAu6dtknfT3bNm9nbgewTTof6Xu99vZm8N7/8kwfjWFwAPE0yH+oaCVfwxcEM4o8ijY+4TEZEqsXn7QZKJOMlEcGKU/715+0EFLmQUM+sC3g8sdffnm9l5BBdEPhNty6JTLyefEynn6yslEDFbQ1SKbVN22MmN6eXnwmkyx6rGugLjmey9nSgAk88KiMeC1PyGmNE3kCERj9HU2DCSnj+TfTDRe9K9IOh8v+CJ3XzqJ49gFqOxwfj9C5fz6KE+elLJUwIXDx08zu0PP85lZy4kO+w0Nhi3P/w4Tz1z4chji8kqKjWItiTZwvlLk2za8mgwMwnQ1Z5g5+PHWb+qc9z9Mvb9aG6K0RgzEvGGU96f6ezTH+w4OFLAcl5TA09a3sEnfvwwzY0NZHLOxas6aWywcbM6Tu4j5/hAlnRmmB/9+iCrFrWytKO0iSPLHdyrpWBhoXqZmapSgYshM0sQ1qkwszOBwcme4O7fJQhOFC77ZMFtB/5oguduA9bNrMkiIlJp+3rTdI/5omxraWRfbzqiFkkV+yxBBuf14d8PAV+mxgMXM7myXy8nnxMp1+srNRAxG0NUJmtTLpfjF3t62XskzfLOBCs6Wli+IMHeo2mcoMjb8gUJVi4srdNWTaZ6b8cLPuSzApqbYhxMDXDJ6oXcufMwmWGntWnm6flTHSexWIzfeUInMYPdh/uJNxi3PfwYZy9JsjTZfMr6elIDHB8a5vihE6cszwcupsoqmk4QzcxY1NbMuUvaSGeGScQbmN/SSM5twoyJ0e+Hc6RvgOee38XeI/2AEzOb9v+WA6kBtjx0aKSAZVeyhW9s28eS9mYyw86wO3ftOsKz1pzGsXT2lDYG+8jZcyTN/t6Tn4Ff7O6lO5koKUhQiUyqcgULZzPLq1YDLmNVKnDxt8BmYIWZ3QA8lXC6UhERqW6VrEGxrCNBKp0ZybQA6BvIsqzKrxZKJBa5+01m9h4Yyc4cnupJ1WymV/br5eRzIuV6faUGIvIdpfzV3XzHb6o0+VI6HhO1adXCFr67/TG+eMfukeEFr798FS+5YCk/eegQJ8JCiVee20V3cvy2VNMwl4lM573NZwWkh4Z50vIOfrm3l6c+YRGntTVz0ekLZpyeX8xxMi/RzF07j/JAzzFyHnToT+vP0JY4NROhO9lCY8xGOuwQDC0pDNZPlVU03SBaZ2sT7Yn4yDCPsesdK/9+rFrUyi929/JY3wADQ8Ms7UhwWlsLF67sGBUkKOUYO9o/RHNjA0ZwBTs77GSHc0BQh2M46wznnMGh3OhaJgXTuWazwyNBC4BYzHisb4ADqYGiAwbVXOw3irbVSnbWZCoSuHD3W8zsXuBSgiDZO9z98UpsS0REyqfSNSg2rO1i05adQJBp0TeQJZXOcM365TNet9SdE2a2kJPZm5cCqWibNDPluLJfDyefkynH6yu1VkZHa5x9R9OnZDh0tMZPeWxeqR2Pidr06wMnRoIWAJnhHJ+9bRcfftmTeOPTziiqiGG1ds7GKvW9LcwKaGwwnn7WonE71eMppjBkb//glMdJKp3hnCVtLJrfNFJwc+H8ZlLpDEs7Rm/j7K75XHXBUr61bT/ZsGjjSy5YSjLRyAP7UyxobaKrvXnSzJNiMjLGCyBMldEyYUFQjIcPHR/ZZn8mx7GB41y0csGooEUpx9iC1ibaE40s7UiwvzdNY4MRb4jRnUzQEDP2HU0TixmJphgXLOkYqWVycv3OackErU3HOTE0TEPMuHhVJyeGhkuquVHNxX6ruW3VrFKzilwU3uwJf59uZklgt7tnK7FNERGZuUrXoFjTnWTjFatHZXRcs3656lvIeP6MoDD3mWb2c2AxcHW0TZqZei+uWS1KrZVhDis6W9mfGmA458RixorOVsabfDffAdzb28+Pfn2Q1uZGwKbseEzUpqP9QyNBi7zMcI7fHklz0aqFUx4X43WAtu05yoLWOB5utxozMIox3Qyc8Tral6zuHHmP8svWdLfR3GiTTie7oLWJhpixqK2FRW0Fj0nEx+3Mv/SiZTxxWZKe1ADd7c2kBrJ85Z59ox5z6RmdE76mqWZYmSyAMNG+KmYq2vyMJINDOZqbYvT2D44ce6V2soMgykLgcHAceo43P301h/oGcaCzNc4Tl3ewfuUClnQkxlm/sfdIP889r4sjJzI0N8VIh8U8S6m5Uez/2ygylvRdMD2VGiryceAi4JcEgeu14e2FZvZWd/9+hbYrIiIzMBs1KNZ0JxWokCm5+71m9jvAOQTnEg8CF0fbqpmp9+Ka1aLUWhlH0xkaYhbMEhB23NJDwxxNZ+hecPJxhR3AeCzGr/YdY2lHghWdCfLBi+JqCpxsU1N4NboweBFviLG8s7jOy9gOULwhmF3ihjt3s3B+S1VnYBSj2CyNsUMNtu05OqqjvaPnGPt707Q2x0ctu/D0Bex6/DjpoRxmxhmLWkfNAjLR++bGhJ35NUuDwp09vWm+v+OxCTv8pRwnhcVKJ1rfRPtqqqloT52RxFixIMG53UnMrORO9nhBlK72Zg4eGxw3ODDe+lubG2lriXOwb5DBdG5a9W6K+X8bVcaSvgump1KBi13Am9z9foCwEvifA+8Fvg4ocCEiUoVUg0KiZmYNwMuBZcD/hbOMvQjYBCSAC6Ns30zUe3HNalHqlfoFrU0M55xj6SApON9RGtuJyHcAG2JGx7w48ViMw8cHWdAa1BYopqbA2DblcjlefenKUTUuXn3pSi5c0THq+RNdFR7bAUo0NfDDHY9x7pIgPWCqq+O1UB9jKmM7n0eOD7B0QSvz4zFijUZ6aJj0UI4TQ8MjgQsI9s2xdIaf/eYwvz7QR0ODccnqTo4NZHjJhcuJxWITvm87eo5N2ZmfzlX1yY7d6V6ln2oq2lNnJAle3xOXddDdkZhWJ3u8IMpEwZrx129cuLKDi1YumPaxWcz/26iGbOi7YHoqFbg4Nx+0AHD3B8zsQnd/tNb+GYqIzCWqQSFV4DPACuAu4N/MbDdBzaz3uPs3o2zYTNV7cc1qUko9hWI7EUf7h2iIGdlh5wcPHGRJRwt37TpCoqmBNd2NrF+1cNKOx3htamho4A2Xr+SCFcmRWUUuXNFBQ8PJaSknGvpw+sJWUv1DrOluCzvSxmAmR1d7C/Nb8qf4QUBmR8+xkdc63doFlTbdIMrozqdzNJ3hpw/v4bIzF7L7cD8Xr+qkc14j85oaRj2vfzDLo4eOs+NAHzl3hrPObY8cptFiQWZgOBPIeO9bMZ356V5Vn+jYne76ppqKdqoZSSrdyZ5o/fk6JtMNIBTz/zaqIRv6LpieSgUuHjSzTwA3hn9fAzxkZs1ApkLbFBGRGVINirmhkjPHlME64EnunjOzFuBx4AnufiDidpVFvRfXrEXFdiIWtDYxr6mBW8KU+uG+AS4/cyGntTXz3POWcG53+7Q6Hg0NDaxbtZB1q8a/f+xV4YaYcefOI9y64yCtzXGaG40LVixgUVszMSAzPEzOgzkd9hxJc/DYAEsXJPjVvtSowEQ1FQicSRClsPN5fCDL432DtMQbGB4OZq/YuusIb/2dM3jCaW2j1v/E5R389DePkfOTPdfhnDM4nBs1hel4iunMl7vDX8r6CoNAHa1xLlndyZ07x3/eVDOSVLqTXcn1T/X/NsohG/ouKF2lAhevB/4QeCfBuNSfAdcRBC2urNA2RUSkDFSDor5VeuaYMhhy9xyAuw+Y2UP1ErSoZfUwpGAyxXQiliRbOK2thVzYyxnM5BjMBLUpPFxHJfbT2KvCiaYGbt3xGKsWttLaHGcw62zb08vL161gSbKFo/0Ztu46wrF0loPHBli/qpP00PApgYlqKhA4kyBKYecznRnGMTrnxVm1sJXGBiMRb6BzfjPndbeP6hzjztadh4mZjQQvGmJGc0PslFpPYxXT2S53h7zY9U0UBHr5U5ZzNJ055XnFBEQq3cmOqhOvIRu1pVLToaaBD4U/Yx2vxDZFRERkapWeOaYMzjWzX4a3jWBWkXyxb3f3J0XXtLmp2oYURMXCcffb9hzlxNDJtPpYWGuilP1USoBj7FXhwaEcuZyTiJ8c+lAYcLj0jE4WtMZ58EAfC+c1kcPJDPspj5vu1eZi217Kayw1iDJq3Yn4SOczEW+gMWasX9VJDljcFhQo7QyHRRR2jnO5HE87azH7ewd45NAJHOfSMxZy0cok54Q1QiZTTGe73B3yYtY3WRDovHGySMoRYKnVwKaGbNSWSk2HehbwT8B5wEjIyt3PqMT2RESkflT5MIaaNxszx8zQmqgbIKNV05CCqHUnE1x5bhdbdx3mWDrL4eODXHH2Yrram4veT6UGgsZeFU40xVi+IMG85kaOD2RIZ4aZ19RAR2scd+eOR4+wddcR5rc08vNHDtPV3jIy80lhYGI6V5uLbfupj3PWdLezYkGCjtbmUzqHpQRRJqr58bJ1yznan+HxvkHu359iMOsTvqb8fnrk0HGuOHsRl5zRyaK2Zs7rms/Z3Ulisdikx0E1m25R0OkGWEa/H07/YHbUdKfVHgTQkI3aUamhIv8N/C3wEYKhIW8guFIiIiIyoRoYxlDzqn3mGHffXeltmNkG4KNAA/Cf7v6BSm+zllXTkIKomRmXntFJZjjH/fuP0RyP8fBjx5nfHCfZGi9qP5UaCDrlqnAiztlL2vjGvfvYezRNLBbMhvHbw/3AyWk600PDI4GJBa1x2sPMhHwnfjpXm4tt+9iCmbsPp7lr51GeueY0jg9kTwl2lBJEGa8Nd+48wsqF8zh/aRJ35+yutklfU+E6BrPBbDLpI2kuO2NRRYIWs5mRMNt1G07uy6Cmyv7eNPf39HH4+CDnLGmfc5lZUjmVClwk3P1WM7PwBOTvzOynBMEMERGRcdXAMIaaN9dnjgmnW/0P4DnAXmCrmd3s7g9E27LqFWUBu2p08Ngg2/b0hp3eoMbF1l1HeO55XUXtp3JdET9/aTtnLJpPc1OM9NAw9/72KP1Dwxw8NjAyjCXeEOOZa05j9cJ5rOluH7cOQylXm4tt+9iCmft70zjhMJcxwY58p35BayPPPa+LHMHQjok694XrjjcYiaYGBody7O3tH3nOVK9pNoNxsz3UamwQqLnROH9pkiP9QyP3l3O7+X1Z+D4P55z0UG7OZmZJZVQqcDFgZjHgN2b2dmAfcFqFtiUiInWiBoYx1DzNHMPFwMPu/iiAmd0IXAVMHLh48EF4xjNGL3v5y+EP/xD6++EFLzj1Oa9/ffDz+ONw9dWn3v+2t8E118CePfCa15x6/7veBb/7u8G23/KWU+//f/8Pnv1s2LYN3vnOU+9///vh8svhttvgr/7q1Pv/9V/hggvgBz+Af/zHU+//1KfgnHPg299myYc+xOvTGfoGskERSuDAv28KroZ/+cvwiU+c+vyvfhUWLYLPfjb4Geu734XWVvj4x+Gmm069/8c/Dn7/y7/Ad74z+r5EAv7v/4Lb730v3Hrr6PsXLoSvfS24/Z73wO23j75/+XL44heD2+98Z7APC519NmzaFNzeuBEeemjU3U1PWEPumj8FYMMHrmP+4wcB6JwX5/XDzkNnrOVnb3wXMYNX//Of0Tk4urzbiqdeQezKV5NzeMlf/QGNQ4MYsLitGRpj8KIXwXXXBQ8ee9wBvPzlHH3JtRw/2sdL/t9GIOgMe5jd8NBFz+PHl76As2IDbPz3d2MYi9uaaW4MMwlmcOydmc2x8sVvZPeFl7P4kR38zifeP7rtAO9/PwvOu5BlD9zLZf/1ETLDOdJDw1gYxLn1Le/h0JlrGNr8ffyTH+FYOsPwQJb5BMfWY//8UZY85xLsO9+BD51aLm/hv3+amME5P/kua2/+EscGMuAwr7mBY61NtH/nm9jixZMeewtam7jg2zfwhJ9sHlk88jp+tiVYUMSx57feylA2RzaXozEWo6lrMTbm2BvK5ji9b5AVwPFFXWz+y39h664jPPlDf8e8HdtHr3+KY48LLgg+uwCvfjXs3Tv6/ssuw/7pn7jszIVc+Gd/QO7xxxnM5OgfyuIYuy68lJ3/76+DoMkLXgDpMd+tRRx7Y//vnZnN8bK+QYaGc2x+yvP4yeUvpONEit9715+SzTnt8+LQFHY5a+j/3njHHl/4AqxYMSf/7xVz7PFP/xTcfulL4fDh0fc/61nw138d3H7+88c/9qZQqcDFO4FW4E+A9xIMF3ldhbYlIiJ1otqHMdSLOT5zzDJgT8Hfe4FLxj7IzDYCGwGe1Nw8Oy2rUga0J+K0xBtGOmjLVi6Ys+nfLfGGUzIrDGiMxWhtirFmSTvzzu9iQWsTnfObsTGBi/nNjSNXxPPPbWtppKmx+CEK+SyYvJgZqYEM7S2NnLV4PnsWz+fonmPkck5Ha3zSdTuM7ny7Tzi+u6kxxjldbeyxk6873/bBcB3pvkG62ptZ092OEQRVzKC9JT4ye0fMYH5LI0PZ3EhALN+WX+3rpTs1QPcEbTitvZn1La0M/Tw2ErRoaowRixl9A1nSxwZYsnjy/bck2UJ64byg4i/Tew/cnWNjAnqJeYN0uo/6bGRzOcYkd5BzGMgMM6/orZXGLJhNZTAW4+hQhvw76oXZLmXYTv51tcRjZIZzGE5DzLjw9A5y4XHUWMLQG3fnQG+aEwf7WJHN0dQYU60BGWHuYz9KM1xhkIL5AXf/87KuuMzWrVvnd999d9TNEBGRAoU1LgqHMajGRW0ys3vcfV2Jz/kVnHKeP2Kms4qY2cuA57n7H4R/vwa42N3/eKLn6Jyh+uVyOR480EdPaoDuZAvnLGmrWIHFk6n/QYHOwewwV5y9mGev6Sp6mzOteTB2+MH8pgZ6UgP8+uAx3KGlsYGLVi7g8jM7uWhl54Trns4whrFt72pvHikIWriOS8/o5OCxQY70D41bMPOyMxeyo+cY37v/4CnbeN75XePOgFHYhjsePcy379s/MiwmX05vqudO9DpKfQ96etPcdPeeU4YGvXzdilFDI4p9XCU8sD81rf1bjMJjpyFmtLc00mDG0PAwJ4ZyDOd8wsKt4+33cnyupLZNdc5Q9owLdx82s6eE9S3KGxUREZG6pmEMAuTzRf8o/P2F8Pe1QH8Z1r8XWFHw93JgfxnWKxHJ5XJ89Z69fGvbfrI5pzFmXHXBUq5+yvKKdHgmK9CZ76RN1SmeqA5DsZ3psYU1+4ey/PiWhxgOSm7QnxnmjkcP8+w1p5Wl2ObYbRe2vac3Pek68nUsxiuYOd36KWbGqoXz6GpvmXbtlZnOJlFsnYzpzN5SLmP3b7zBmNfUQCqdoac3PaN6F4XHTm7YOXwiQ3OjceU5p+Hhtseuf7JAWbC+w+w+nB6plbHz8X6aGxu44uzFczbDS06q1FCRXwDfMrOvACfyC9396xXanoiI1Ik5PoxhzsvPKmJmT3X3pxbc9Zdm9nPgH2a4ia3AWWa2mqAG1yuAV81wnVIBxXbiHzzQNxK0AMjmnG9t288TlyVZM8OryhOZqEDn6kXzWJJsmVYxxlKzHwo73vfvT9HVnhjp8BkEnfqCdY+3L8tRpLKYdUwUJJhJpz7KgABMXLS2ozVOT2961L4udfaWcincRw0xYzjn3L//GL3pDHftPDKjIqHjve+DWcdhwmyOyQJlR/uHOJY+WeATgs/y/fuPcXZXmwp8SsUCF53AYeCZBcscUOCijHb0pEZdldywtksn+yIiUi/mmdnT3P1nAGZ2Ocx8SLi7Z8PC4d8jmA71v9z9/pmuV8qrlE58T2qAxgbj9IWtZIedxgZjf2+antRAxQIXk3XWgZKzGGB62Q95na1NrFyYYEFrnHRmmES8gfZEI52tTZPuy3LMGDOTdUxnStZyPLccJgqc/PZwP3fuHD2jx6K2Zjpbm4K6H7OYOVC4j/b29vP97QdYtiABWEnH13im875P9rlZ0NrEYHZ41DjBhpjRHI/NyamX5VQVCVy4+xsqsV45qXAceHeyhVQ6w6YtOzUOXERE6sWbgP8ysyTBxY8U8MZyrNjdvwt8txzrksoopRO/NNnMkvYWfv7w4wznguKAl52xkKXJyhVVnazTNt0shplkPwSd6IVs3XWE+S3xUdkH+RT8Y+nsSFBj667DI9khM81amOk6ZjJkY6bDPWZivMAJ7tx0z15yHgzLGMo6m7Y8yrlL2mhPxCs6Depk7ezuSHC0f4jW5vio+2YyBex03vfJPjdLki1ccfZidj7eTzb8HF+8qpPBzPCcnXpZRqtI4MLMzgY+AXS5+1ozexLwYncfZ94ZmY7N2w+STMRHKu/nf2/eflCBCxERqXnufg/wZDNrJygmnoq6TXPVTIsYTkcpnfi2RBO9/RnyldXcobc/Q1uicp2dqTptJztnzvGBoNCgEezLifZdpTIXjvQPjaobYMDSjgRHwn0506yFUjIfxivsefDYYCQZE+UwNnDywP7UyPuXaGrg1h2PMZxz0plh5rfEZ5ThMFPlyK4pNJ2Ml8k+N2bGs9d00dzYMFI7ZjAzzAUrFkwaDIni/5NEo1JDRT4N/DnwKQB3/6WZ/Q+gwEWZ7OtN0z3mQ9zW0si+3vQEzxAREakdZtYFvB9Y6u7PN7PzgMvc/TMRN21Omc6sE+VQSicrlc5wzpI2Fs1vom8wS1tzIwvnN5NKZ1i2oPxty3eUkq1xnnteF+B0tDaPdJhOds6CQoMHjw2wflUnP3rwMY72Zybcd5XKXIgBB48NjJpy9OCxAWJTPK8Uxaxj7LHU3Ggsmt9MTypNzm3Wjq1KWpCI05FoJD0UVBfxcErQRLwBmFmGw0xVoiZIqcfOVMGOWCzGFWcvHreQ63jGO6YKh+YoiFFfKhW4aHX3u8YcKNkKbWtOWtaRIJXOjGRaAPQNZFmm8V8iIlIfPgv8N3B9+PdDwJcBBS5mQb5zvuvwCR48cIyGmJEb9hmPiy9WKZ2sBa1NNMSMRW0tLGoLls3kSvJkJgrknNudHOkg5TtnC1rj/OjBQ5y/rJ300DCDWZ9031WuZkMwLeVdu46MDKVZv6qTSWYdroixw3+a4w18a9t+zl3SxvyW+KwdW5Xi7uw83M/9+4+x92iaMxfPJ2bGko6WcLrWyh2XxYi6JkhhOyYLdpQSDCk8pqplaI5UTqUCF4+b2ZmE/xHN7Gqgp0LbmpM2rO1i05adQJBp0TeQJZXOcM365RG3TEREpCwWuftNZvYeGCmqORx1o+aCws75wWMD7Drcz8WrOok3GJkweFHpq8aldLJmc3aJfEepIWbMb2pgcCjHgweOsXphK90LWke13wlmHMnPOgJTX3GvRM2GjtZmmhqNZ605jcGhHM1NQQp+R2v5a4BMlrY/dvjP4FCObMEwCog2I2Gm8sfGsgUJkok4w7kcF6xIhu+/VfS4LFaUNUHKzd3ZdfgEB48NkIg3sHRBC7fuOFQ1Q3Ok/CoVuPgjYBNwrpntA3YSzL8uZbKmO8nGK1aPmlXkmvXLVd9CRETqxQkzW8jJiyCXEhTolAorvIqZiDeQyzl37TrCs9acRiadnbWrxsV2smbzSvLR/iEaYkZ22EfqFzTEjIXzm/ndjsSobZa7pkChUsb1L0m2cMGKBSPvaWYgV1QHOpfL8eCBPnpSA3QnWzhnSRuxWGzCbU81rGjs/mhuitEYs5FhFOXcP1E4GZixkUBMvMF4xrmdzGtqrLr6C7VcGyJ/rD144Bi7DveTyzmxmDGcy2FYVQzNkfKrVOBit7s/28zmATF376vQdua0Nd1JBSpERKRevQu4GTjTzH4OLAZeFm2T5obCK+PzWxpZ2pFgf2+awaFcVVw1Hs9sXUle0NrEvKYGbgmDFgC5nPOrvb2sX9U5avtTZYJMt+NYat2R6QR2crkcX71nL9/atp9szmmMGVddsJSXXrSMO3ceHXfbU80EM3Z/DGaGueqCpWGNi8pmysyG8QJVwzlneUdr1XWco6pdUy6FmU8Xh8Ogjg9myeWcFZ2tszI0p5YDP7WqUoGLnWa2mWAs6g8rtA0RERGpU+5+j5n9DnAOwUQID7p7JuJmzQmjO2DGis4EC+fFWX/GApZ3tM7pE/QlyRZOa2shF/ZO8zN0tDY3nnJld7KAQWHHsSFmzGtq4LS2Fi5c2UF3MjHp/i1lqtjCtpQS2HnwQN9I0AIgm3O+tW0/ZyyeN+G2p5oJZrz9MWpWkUQcN9jRc6wmO4KzMWSpXJ3l6RxD1SR/rOWGnXhDMAwql3XWrVzA3qP9o4q9ViIQVuuBn1pVqcDFOcDvEgwZ+YyZfQe40d1/VqHtiYiISB0xs0eAf3b3TxYs+467vyjCZs0Jp3bAjCvP7WLdys5ZOymv1quZZsaFKzvYtucoJ4aGScQbmN/SSCwcCjHe48cLGBReMc4OO7fseIxcztm25yhXnts1aQeolKlip6snNTAStMjL5py9R9ITbruYoTHj7Y98NsZ4HcFLz+is+HSp5TrWKj1kqZyd5dk4hiqp8FjLDPvIELYXnbEQbFHF/2/UeuCnVlUkcOHuaeAm4CYzWwB8FPgJ0DDpE0VEREQCGeBKM7sEeIu7DwHLIm7TnLF6YSvxxqBTvXJh65RZAGPNpDNY7Vczu5MJrjy3a0ZX1vMdx/lNDSO1MgBODA2P2wEq3J9GMO3jYPZkz7PcKfHdyRYaYzYqeNEYM5Z3Jth9pH+kw+buHD0xyP7eNObOJas7uXNn6ftl/I7gYTLDObbt6a3YcXDqseas6W5nxYLEqClui1XJIUvl7CxXsv7KbJgwuyXM7Kl08KDWAz+1qlIZF4TpndcAzwe2Ai+v1LZERESk7vS7+zVm9hfAT83s5cz2/I1z0HhBA/egsz6TdZTS4az2q5nluLKe7zgODuVGghZGWAx1TAdovM51dzLB48cHGcz6jFLiJwownbOkjasuWHpKjYsLV3QwFE7rOpxzHjzQR0drnC/csZvssPOSC5bysqcsozedLWm/jNcRPJbOcv/+YxU9DkYfa87uw2nu2nmUZ645jeMD2aoKmJWzszybM/FUQtRTu9Z64KdWVSRwYWY7gW0EWRd/7u4nKrEdERERqVsG4O4fNLN7gO8BndE2qf4d6E3z4IFjxGMxmptipCfIAJh0HTMMPNTC1cyZXlnPdxwfPHCMhpiRyzlLOxLhsJPRHaCx+7MhFuPEYIZzl7TTlmhkeTLBkrAdPb3pojtykwWYYrEYVz9lOU9cljxlVpF8h3FHzzGOHB9iT28/A5lgytdvbtvP2mVJzltaWvH48TqCg9lhmuOxkqaTLVXhsXZ8IMv+3nQwje1QruoCZuXsLEfd8S+HKKd2rfXAT62qVMbFk939WIXWLSIiIvXvb/I33P1WM3se8LoI21P33J2tu4+OzJiRr9jf2GAldRZnGniI+mrmZNN9jiwPC0n29mem1ekb6TgubGXh/GZ+tbeX1uagVsbYDlDh/ow35GtiHGLVwhN0tQcdqK5kC3c8euSUjtTqha0cTY/fxqkCTLFYjDVLk6wZE4TIdxh39BzjN4eOj7ovm3N6UgOnPGcq43UErzh7MQ8/Nnr95T4OCo+1dGYYBxpiRnNTjMF0rqoCZuXuLEfZ8a919RD4qUWVClwsMbNvAF3uvtbMngS82N3/sULbExERkTpgZue6+6+BfWZ20Zi7vxNFm+aKA6kBfrW3d2TGjOGcc9euIzxnzWkldRZnGniI8mrmRFkIl57RORIYaIgZwzlnz5F+li1IjAQbSh1SYGZ0L2jldzsSrF/VOWEHqHB/JsKaGLmcjwwr2brrCAta42OCEM7X793L+Uvb6Q0LF45t40wDTBPVweiexvs00Ywj85vjFT0OCo+1RLyBxljwXqaHhoHqSv+vps5ytRbPnU0K/My+SgUuPg38OfApAHf/pZn9D6DAhYiIiEzmz4CNwIfGuc+BZ85uc+aOo/1DtDY3srQjMZIyn8s5p7W1lNRZnGngIcoO2kRZCJ2tjSNDaDrmxfnuL3vI5pxkIs78lviMhhRM1QEq3J+DQ7lRw0rybexJDYwKQhwfyLL3aJozFs0f9TrybXR3DDh8fIDmxoZwXVZSR32iOhjnLGkreR9MtB8qfRwUHmtH+od4vG+Q+/enZlw7pFKqobNc7cVzx1KQpX5UKnDR6u53jTkoshXaloiIiNQJd98Y3ny+uw8U3mdm1dODqEPBlX1jRWeCBa1x0plh5jU1cOHKjukNgyixwzleB2O2O2jjZSE0xIx7f5saGUKzcmErmVzQsU1nhpnfEq/okILC/bm3t5+j/YO0NgeBBgg6jt3JFn61LzXS9nRmmFjBkAc4mU2Rn3p0256jLJrfwtZdR+hqb2HlwgTrVy0suqM+WR2Mcr72SnfUC7fh7pzd1RZpJ7faO9rVXjy3UK0FWWRylQpcPG5mZxJW/zazq4GeCm1LRERE6s9twNihIuMtkzIpvLI/vyVOeyLO+lWdJc0okldqh7NaOhjjDXOZ19TAjp7UyBCahphx4NgAqzpbScQbgMoPKcjvzyXJFjLhrB6F++mcJW0c7c+MLJ/X1MAlqztJD2U5PpAZCUJ1tMZHdTzjDcYz15zGYCbHlecs5tzu9pL290R1MGpV1BkNxXwOog5s1ELx3LxaCrLI1CoVuPgjYBNwrpntA3YC11ZoWyIiIlInzGwJsAxImNmF5C8rQzvQGlnD5oBqHKIx2x2M8Ya5nNbWwtH+DEs7cuzvTbO/N80lqzrpH8qOzAIy0yEFxXZGJ3uPCpd3tMb57eF+vnrPXvYeTROLGZes7uS3h/tJJhpH9nNm2Mmkg6RoD9cv0Znqc1ANAb6oi+eWopaCLDK1igQu3P1R4NlmNg+IuXufmb0T+NdKbE9ERETqxvOA1wPLgQ8XLO8D/iqKBs0lUV1xrpYOxniBAcd5+NDxUUNoFiQaeeGTVwI24wBPqZ3Rid6jNbb32QAAUtxJREFUscvN4fyl7ZyxaP7I1LZ37jzCc8/rqpmO51wz1eegGgJ8tTQVaC0FWWRqlcq4AMDdTxT8+WcocCEiIiKTcPfPAZ8zs5e6+9eibo/MjmrqYIwNALj7uENo1nQny3KVu1Kd0aPpDL1hNkW+zgVADmqm4znXTPU5iCLAN142ULXMbjJR+/JtqaUgi0ytooGLMZR7JiIiIsX6jpm9ClhFwfmKu/9DZC2SiqnmDkalh9BUqjM6USe4s7WJ87rbq6bjKSdN9TlY0NpEc6PRHG9gcCgXFF/NDFcswDdZNlDUs5tM1T4zK+tnN+raIjK7gQuf+iEiIiIiAHwLSAH3AIMRt0UqbKoORtSdhkoOoalUtslkneCoi1BWsyiPtak+B13tzSya33zKFLRd7c0VaU81DE2ZTDHtK8exXg21RaTMgQsz62P8AIUB0R/dIiIiUiuWu/uGqBshs2eiDka9dxoqlW1S7NXmqINC1SSqY63YqYAPHhukJ5Xm3CVtpDPDJOIN9KTSHDw2WJFAQrXUnpnIbLWv2gM4c0VZAxfu3lbO9YmIiMicdZuZPdHdfxV1Q6R05ewMl9ppqLWOeCWHokx1tXmmHfVa29cTyb+OXYdP8OCBYzTEjNywz0oHtZT3IOioG/Nb4sxviQOVDSRUU+2Z8cxW+6o9gDNXzOZQEREREZFiPQ14vZntJBgqYoC7+5OibZZMpdiOWLGd3lI6DbWanRHV0I2ZXEmu1X09VuHrOHhsgF2H+7l4VSfxBiMTBi8q2UEt5T2Y7UBCNdeegdlrX7UHcOYKBS6kru3oSbF5+0H29aZZ1pFgw9ou1nQno26WiIhM7flRN0Cmp5iOWCmd3lI6DUrpLp67s7e3n3gsNjJdaikd9XrZ14WvIxFvIJdz7tp1hGetOY1MOlvxDmopgbnZDiRUujDtTM1W+7ram1nT3caWhw7R3NhAe6KR9asWVk0AZ65Q4ELq1o6eFJu27CSZiNOdbCGVzrBpy042XrFawQsRkSrn7rvN7GnAWe7+32a2GJgfdbtkYrlcjgcP9PHggT7iMSOHkxkO7xvTEZuw07uwFcxGdUJK6awppbs4+cDRj359kF/tO0YsZiNZBsM5L6qjXi/7uvB1zG9pZGlHgv29aQaHcrOSYVBKYC6KQEK1F3KtdPvcnTsePcLDjx1n9eL5DGZynL+0nUvP6KyaAM5cocCF1K3N2w+STMRJJoIxgPnfm7cfVOBCRKTKmdnfAuuAc4D/BuLAF4GnRtkuGV8ul+Or9+zlW9v20xAzfnukn2eecxqd8+Nkhk/tiI3t9MYbjLbmRrY8/Dj9g1lODA0znPORLIxiO2tK6S5OPnDU2nyyo37XriM8Z81pnLOkvaiOeq3s66mGJI1+HcaKzgQL58VZf8YClne0VjwwUGoWRbUHEupNYZB1MJsFYNueXs7uatN7MMsUuJC6ta83TfeYf/ptLY3s601H1CIRESnB7wEXAvcCuPt+M1MR8Cr14IG+kSkac+50tbfwwwcf4+VPWU7M/JSOWGFnMd5gZIednzx4iN70EC1NjVy8qpPGBhs19KCYztpsptLXcmHKk4GjoKO+oDVOOjPMud3tXHpGcTUqqr3+ARQ3JOnU12FceW4X61bOzhX1ah+OMdfVS2ZRPVDgQurWso4EqXRmJNMCoG8gyzL9kxERqQVD7u5mFnSvzOZF3SCZWE9qgGx4dp/vIJ7e2crSjgSXnLHwlI5YYWcx0dTAD3c8RjIRJ56JMVxQY+BYOltSB2G2OoG1XphybJbB/JY47Yk4qxbOK7r9tdDhPpAaYNueo8xvaWRwKEdzU4xte46OqsNRDa9DWRTVq1Yyi+YCBS6kbm1Y28WmLTuBINOibyBLKp3hmvXLI26ZVBMVcBWpWjeZ2aeADjN7M/BG4NMRt0km0J1soTFmo4IXwznnnCXjp1MXdhZ39Bzj3CVtOHDkxBBO8Nx8jYFSOwiz0QmcrcKUlcrqKFe2RDn3dSVea2//IENZ52cPP8ZwzmkIa3n09g+OarMCBzKRWsgsmisUuJC6taY7ycYrVo/qlF6zfrk6pTJCBVxFqpe7/4uZPQc4RlDn4m/c/ZaImyUTOGdJG1ddsHRkuEhjzLjqgqWcs6Rtwg5pvrMI8Kt9KXLuI/UWYjEj0RTjgiUdVdlBqET6+Nj91NXezB2PHqlIVkc1ZBkUqlwGSzDcaDh8s4ZzztZdR3je+V3labjUvWr7rMxlClxIXVvTnVQHtALqJUtBBVxFqlsYqFCwogbEYjGufspynrgsSU9qgO5kC+csacPMpuyQFk412NEaZ+G8OE9c3sH6lQtY0pGoyg5CudPHx+u4r+lu4+HHjlcsq6OasgwqlcGSA7raW9jfm8YBC//OlaPRUvfGBhPXdLdX5f+juUKBCxEpST1lKaiAq0j1MbM+wCe6393bZ7E5UoJYLMaapUnWLD35XdDTm560QzrRVINPP2sRsVgsolcytXKnj4/Xcd/y0KFgn4QzGeSX12NRwEoVQOxsbWLlwpPFRxPxBtoTjXSqPoFModbr2NQjBS5EpCT1lKWgAq4i1cfd2wDM7B+AA8AXCC6UXgtoVpEaM1WHtFanGix3+vh4+6m5sYHBzOjcgHotClipAohBgGkhW3cdYX5LXPUJpGizVcdGile9oWwRqUr7etO0tYyOedZqlsKGtV2k0hlS6Qw595HbG9Zq7KtIFXieu3/c3fvc/Zi7fwJ4adSNktLkO6SFCjukkwU2ql1+qMV5S5N0h0Na3J2e3jQP7E/R05vGfcLkoVHG20/tiUbOX9o+sryeO935DJZyv9Z8gOnl61bwvPO7ePm6FbpiLkWp5f9N9UoZFyJSknrKUlABV5GqNmxm1wI3EgwdeSUwHG2TpFRTDamop6kGZ5JaPv5+WsilZ3Rydldb3RcFrGQBxGJreVRqBhepTfX0v6leKHAhIiUpnGZ2IJNlR08fR/szPP0JC9nRk6q5Tr8KuIpUrVcBHw1/HPh5uExqyFQd0nqaanAmqeWT7adqKaBZaVG+VtUzkLHq6X9TvVDgQkRKks9S+MLtu7ntkSMsaI3z1Cd0Em9sqNkinSJSfdx9F3BV1O2QmZusQ1pPUw3OtMDkXApSVBvVM5Cx6ul/U71Q4EJESramO8nithaeee5po4aMQG0W6ZTKqJdpcyUaZvbfjDO7iLu/MYLmSAXVS4ddqeW1q1Kzmkhtq5f/TfVCxTlFZFrqqUinlF9+2txUOjNq2twdPamomya14zvA/4Y/twLtwPFIWyQyiUoVmJTKm6qIrIhETxkXEdGVSKl1tVCkU5+z6NTTtLkSDXf/WuHfZvYl4AcRNUdkStNNLVdRyOipnoFI9VPgIgL5K5HJRHzUlUjVBpBaUliks62lkb6BLKl0hmvWL4+4ZQF9zqK1rzdN95gTPmXkyAydBZwedSNkduRyOR480EdPaoDuZAvnLGkjFqv+ROFSU8tVFLI6zPV6BgqeSS1Q4CICuhIp9aDapxLV56z8SslgqURGjjJo5hYz62N0jYsDwLsjao5Mw3Q7Q7lcjq/es5dvbdtPNuc0xoyrLljK1U9ZXhPBi1KoKGT1mKv1DBQ8k1qhwEUEdCVS6kU1TyU61z5nle7Ul5rBUu6MHGXQzD3u3hZ1G2T6ZtIZevBA30jQAiCbc761bT9PXJZkzdL6+ryrKKRETcEzqRX1FbauEcs6EvQNZEctq7baACK1bi59zmajEGZhBkvMbOT25u0Hx318PiMnmYjTkxogmYjPKMhQ6val9pnZrcUsk+o0UWfoQGpgyuf2pAZGghZ52ZzTU8Rza42KQkrUJguelcLd6elN88D+FD29adxPmRRKZEaUcRGBaq8NIFIP5tLnbDaGxUwng6WcGTlzLYNmLjOzFqAVWGRmC4B8t64dWBpZw6QkM8kk6E620BizUcGLxpid8j+gHqgopEStHNP4ariJzIaqybgwsw1m9qCZPWxmfznO/WZmHwvv/6WZXTTm/gYz+4WZfWf2Wj095b4SKSKnmkufs9mYmjbqDJaoty+z6i3APcC54e/8z7eA/4iwXVKCmWQSnLOkjasuWEpjuIJ8jYtzltTf6KF8UciXr1vBhvNP47nndZFsjXMgNaAr1jIryjGN70wyrESKVRUZF2bWQHAy8hxgL7DVzG529wcKHvZ8goriZwGXAJ8If+e9A9hBcEWm6lVzbQCRejFXPmezMTVt1BksUW9fZo+7fxT4qJn9sbv/W9TtkemZSSZBLBbj6qcs54nLkjU3q8h0mBlLki3sfPzEjK9Y5wui9vYPAkYO6NQsERVV6zNylGNGFdVqkdlQFYEL4GLgYXd/FMDMbgSuAgoDF1cBn/cg/HyHmXWYWbe795jZcuCFwPuAP5vltouIRGo2OvVRzyIT9fZl9pjZemBPPmhhZq8FXgrsBv7O3Y9E2T4pzkw7Q7FYjDVL668Y50TKUSAxn66/bc9RhrLO1l1H6GpvYeXCBOtXLVTafgXUyxCJmc6oUo7hJjJztR5Em0q1BC6WAXsK/t7L6GyKiR6zDOgB/hX4C2DSHEIz2whsBDj9dE0FL7VH00HKeGarUx91BkvU25dZ8yng2QBmdgXwAeCPgQuATcDVkbVMSjJXp5ecjnJcsc4HP+a3NPKzhx9jOOfs702zoDWuWSIq5GTAyTk+kCWdGeZHvz7IqkWtLO1ojbp5s0a1WqJXL0G0yVRL4GK8vTl2YN+4jzGzFwGPufs9ZvaMyTbi7psITnpYt26dBg5KTdF0kDIZderLQ8HBqtBQkFVxDbDJ3b8GfM3MtkXXLJHKKccV63zwY3Aox3C4IgfSmWHmt8SVtl8BwT539hxJs783TXM8xtKO/7+9uw9v67rvBP/94YUASJCg+CKKkiVRL5YjWbEdW4qjyUuTiZWoSTaZbfO23U7T2Wwz6TbZGW+8nfTJTtvMtN3NJDt6tu5sO8443TTbjWs/TVo/TceOHDdN3SiO5RcpkhkzkizrjaIoUgQJkgAB4uwfwIUvQbzce3Ev7gHw/TyPHlEQCFyeey54z+/8zu/E8I8/m8FbbwVGE7G2GTTW4sZyE2pMJ2xrq8tiwcsAtpr+fQuAqxaf81YAHxSRCwAeAfBPReT/9e5QifzB7SD1NT6ZxNFjE3jgsZM4emzC1W1IqXmasa0sWRIUEWNi5d0Anjb9ny4TLkSucqNAohH8iHQFECy+kACIhYNM2/fIhu4uLGVypaDFxt4ofnhuBn9z6ir+9JlXcfzcTMcUWTUyrPZtTmC0vzMCNjpxa1tbnekSuHgOwK0iskNEugB8HMDjZc95HMCvFHcXeQuApFJqUin1W0qpW5RSY8Xve1op9ctNPXqiJmjGzhFkHwe77YPBQW18E8Dfi8hfA1gG8A8AICK7AfDCorZk3l3kvbeP4KMHttpO8TaCH5nsKt48NoBQQLC5P4a+WIhp+x7ZlIjijbf0I1Bs6x9fmMWmvihWVvNYXFn1bGcNpRQm55bx8tUkJueWOyY4QtU1spNTq9Bi5kIplRORzwB4EkAQwNeUUmdE5NPF//8TAH8L4H0AzgJYAvAv/DpeKmBKdXM1Y+cIss882AVQ+vuJ01O8HlrMlblljJbd2OsWHOyEz12l1O+LyPcAjAL4rnr9jjyAQq0LorbUaE0Qc7r+3FIG7719hLuKeExEcHD7BsykMljJKVy5uYzsah5KFTJdvNhZw+1aBu1e0LFTdEKdES0CFwCglPpbFIIT5sf+xPS1AvAbdV7j+wC+78HhURnWW2g+bgepp1YY7JI1ugcHO+lzVyn1owqPTfhxLESthAVRm29Tfwy3berDK9fmkcsrKAVs7o8hHg15MuPtZi2DTijo2Ck6oc6ILktFqMUwpbr5jJ0jErEwJpNpJGLhthywtJot/TEspHNrHtNpsEvWHdk/guRyFsnlLPJKlb4+sn/E70MDwM9dIiIdGQPGI7dvwscPbsUbt/Rh60AMARFPZrzdrGVQLQjixfIW8l671xnRJuOCWgtnmf3BnSP0w0yY9tGsbWWd4ucuEZGeRASjG7rx3/THcHBswNMZbzd2oDG4sQ0vUbMwcOGjVl6rrHtKNZHB6+vMyWC3la/9dudWcNCLc8zPXSIivTVjqY6btQzcDIIQeU06tQrtgQMH1IkTJ3x7f/NaZfMsbauk/rf68VNn0LGf6nhMZF+twITb59h4rzNXk7h8cxm3jcSxbbCnJfqOiDyvlDrg93E0yu97BiKrjEKLc0sZAMLinG3KrYKarHFBOql3z8CMC5+0+k4EuqdUEwF6Xmc6HhPZU69IphvnuFKwYu9oH7rDQbxyLYWl7Cr2jSb4uUtEJcYg9KVLN7GSU3juwixG+qLYPhjDwbFBDkbbiFuZHZ1Q0JHaBwMXPmmHtcqst0C60/E60/GYyJ56gYlGz7E5MDK/nAUAvDKVQjwawo7hOAbiESRiYdx/eI+LPxURtTqj0GI8GsIzZ69jNa9wdW4ZG7rDjnedoPZXKwjCrVJJJwxcuMjOmmauVSZyptWvMx2PieypF5ho9BybAyOpzCr6oiFkcnmcvb6IoXiUgS4iqsgotJhZyWO1WLRAAVjOriIeDbPgItnCZSSkG26H6hJjhiy5nF2TOjw+maz4fN233SPSUTtcZzoeE9lTbwvcRs/xlbll9EYL8wrxYtAiEgpgPp1d915EREopTM4tI7mcRX8shJ5IEMFAYWApAGLhIAsukm3cKpV0w8CFS8wzZAGR0tdPnJ6q+HyjRkQiFsZkMo1ELKx1gTVaa3wyiaPHJvDAYydx9NhE1YEzuauR62x8ch4vT84jlcniidNTvp0zv6599ln31AtMNHqOzYGR3cM9yOTymE/n0BsJMdBFRGsYs+KPnriEH52fwZmr81hcyeEtOwcQCgg298fQFws53nWCOletrVKJ/MClIi5xsqaZNSJaU73CfPW+l9tgOuf0OgOAi7NLuGVDN3qjIVvnDHD/vDX72m+kz9J6VooTWz3HlfrWkf0jeOgHrwIABuMR7NkYx8RUConuQqCOBTmJyLB2VlywZUMMNxdXcGT/JhzeO8JdRcgxbpVKumHgwiVct945nO4YwMFj45xeZ43s8tAO5407mbjPjeBTrb5lDozsGI7j19+1i+eKiNZZPysu6I6EEesKYe9mfmaQc5sSURwcG1hX44KZO+QXBi5cYp4h642GsJDOIbmcxccO3uLzkZHbnO4YwMFj45xeZ43s8qDDeWs044M7meipVt+6//Aefi4QtRGvdmfgrDh5hVulkm5Y48IlrFnROeoV5qvGXHDPwMGjPU6vM6fnDPD/vNktSFqJlZ+fNTCaz+++RUTNYa5D8eSZKTx64hKOn5uBUqr+N9dhzIoXa3FyVpxcZWyVum9zAqP9MQYtyFfMuHARa1Z0Bqez/lxO5A4n11kjGVF+nzc3Mj7q/fztsBzGCb9rzvjdt4jIPieZE9V2Z9gx1NPw9qScFSczrzJ7iHTAjAsim5zO+nMbTP80khHl93lzY1a+3s9vd7eWduBGJkuj/O5bnUhEviwiPxWRUyLybRHp9/uYqHU4zZzwencGzooT4G1mD5EOmHFB5ICTWX8rOxGQd5xmRPl93tyala/183diDQwdapf43bc61DEAv6WUyonIlwD8FoB/4/MxUYtwmjnBOhTUDF5m9hDpgIELssXv1OpWx+VErcnP89aMwr+duGRBl2ANPxOaSyn1XdM/fwTgw34dC7WeWpkTtQaG3J2BmsFp/yRqFVwqQpbpkFpN1GmaUfi3E5csNFKwldrG/wDgv1b7TxH5lIicEJET09PTTTws0pWROWFmJXPCqEPx0QNb8d7bR/DRA1txaNcgl3SQq5z2T6JWwYwLskyH1GpmfFAn8npW3sqShXa79riFdfsSkacAbKrwX19QSv118TlfAJAD8OfVXkcp9RCAhwDgwIEDXCRODWVOGHUoOPNNXmFmD7U7Bi7IMr9Tqzt15wPdtNsAlgpqBUfa8dpjfYn2pZS6r9b/i8gnAHwAwLsVq9aRDdzBg3TG/kntjoELTek4OPR7HbwOGR+drh0HsFRfu157nVhfQsffLc0kIkdQKMb5c0qpJb+Ph1oPMydIZ+yf1M4YuNCQk8FhM25G/U6t9jvjQyd+DT7adQBLtfHas07nwAADjwCAPwIQAXCsOAv5I6XUp/09JCIiIqqHxTk1ZB4cBkRKXz9xeqri85tVNLMZRQJr8aqY3vhkEkePTeCBx07i6LEJ7YuN+lkk9crcMnqja+OdHMC2P90LWepyDetewNju75Z2pJTarZTaqpS6q/iHQQsiIqIWwIwLDb08mURyKYuFTA590TB2b+zBQE+k6uCwmbPg7bYtZCvOQPqZ9eD3ciHyh9/ZVrX4fQ2bMywuzi5htC9i+dpsdnYGM2eIiDqTUgrXkmnWvqCWxowLzYxPJnFpZhnz6Rx6IyGks6t4/rU5XJxZrDo47JRZcC8yPpzMQPo9u+vn+e7EbTPJ/2yrWvzMIijPsJhNreCn1xZwI5UuPafatelHdobumTNEROQ+pRSOn5vBoycu4ckzU3j0xCUcPzcD1iamVsOMC808cXoKe0bimLieQiaXRyQUQCaXxytTKXz6nbsqfk8nzYLbyfiwMptpdwbS79ldwN/zzZ0YOpeuhSz9zCIoz34aiHdhfjmLs9cXMRQvHFO1a9OPzCmdM2eIiMgb15Lp0hapAJBXwHMXZrFjqIdFPKmlMHChmStzy9g+1IN4NISz04tIpXPoi4bQFwtXvZnlzeh6VgMMdoMAOhSnrHe+vU4/13UAS53Jz0BeedBk93APXnhtDjdSGeSVqvlZ7EfAhYFHIqLOc3NppRS0MORV4XEGLqiVMHChGeMmfLg3iuHewk1t+U15OSs3ozpXuveC1QCD3aCPm4MNp+ek1vn2OyOk0/oZ+c/PwG150GS4N4o9I3FcW8hgMpmuGRjwK+DCwCMRUWfZ0N2FgMAUvFBYyuSwuJLD5Nwy611Qy2DgQjNOb8Jr3Yz6PZj1g9UAg90ZSLcGG42ek2rn28+MkE7sZ+Q/P7IIjADdmatJXL65jNtG4tg22IOFdA7BYABf/OC+uu/PTDkiImqGTYkoDo4NFJeLKFy5uYytA9149vwsfpifwcGxARzaNcjgBWmPgQvNeHETrsPyhmazE2CwMwPp1mDDq3Oi03r/TuhnpIdmZhGYA3R7R/vQHQ7ilWspLGVXsW80Yfnzmss2iIioGUQEh3YNYsdQDy7MLOKnk/NYXFlFdrWQgsF6F9QqGLjQkNs34Z24BZ5Xs5luDTbqnROnSy50Wu8PtH8/o85THqDbMRzHQLywBer9h/fYei0vAy5ctkVERAYRwWh/DDeXVjC3vHZ3Kda7oFbBwEUH6KRdRwxezma6MdiodU4aWXKh03p/oP37mZ84MPWH1wE6N84rl20REVEl6+tdAAEpPE6kOwYuOkCnrqXWuQhdrXPSyJILNwM2dgdQndrPyjUjoMCBqXONnh8vA3RunVcu2yIiokrW1rsoBC0Ojg1gU1lA3gmlFK4l07i5tIIN3V0s+kmuY+CiA7TjWupWn22udU4efuZCQzO6bgRsnAyg2rGf2dWsgILTgWm166bVryer3Dg/Xgboap1X428r54jLtoiIqBJzvQs3AwxKKRw/N7MuIMKin+QmBi46hM7ZB3a1y2xztXOiw5ILpwPjdupnTjRrptvJwLTadXPf3mE8NT7dkteT3YCLG+fHywBdtfN65moSF2eXLJ8jHT5DiIhIT0a9CzdrWlxLpktBC6CwFIVFP8ltDFxQy2n3NGgdllx4OWPbzrP7zZrpdjIwrXbdfP34Rewb7Wu568lqANPc316+Oo87t/YBeL3dnJwfrwJ01c7rfDqHWzZ0Wz5HOnyGEBFR57i5tLKmbgbAop/kvoDfB0Bk15W5ZfRG18bc2ikN2pjRTcTCmEymkYiFmz77vaU/hoX02qrTbszYGoPN5HJ2zWBzfDLZ0Ovqwqt2K3dk/wiSy1kkl7PIK1X6+sj+karfU+26mZpPt+T1ZA7EBERKXxvLKoD1/S0cFDx7/iZupNKl5+iUiVDtvCZiIVvnSIfPECIi6hxG0U8zFv0ktzHjgrRUa1a+E9Kg/VxyMT6ZxPRCGs+cncGG7jD2be5FJBRyZcaW2TKNM66NhXQWV+aWkYiFsG80UXe5QrXrZqQvioV0ruWuJyvZLeX97fbNfXj2/CxOX5nHO/ZEtMtEqLYM5YnTU7Y/8zp92RYRETWPl0U/iQwMXJB26qWAMw26Mre3UfwnuwYwPrmAfzw7i7fvHnRlxrbdiwZ6XaDUfH72jvaV+r6Vc13tuvnEoW14anx63eO6X09WApjl/W24N4qDOzbg5OUkJpNpLQvIVgs48DOPiIh05VXRTyIzBi7IVW4MnuvNyjsZHLZzXQXAm20UE7EwRvpeHxy60V7mweb0Qhpnpxcxm1rBQLwL45NJ7c6Jk37j5Uy3V1vl7hyOt9xuMFYCmJWCG9FwCO/Ztwn3H97T9GN2ijv2EBGR7rwo+klkxsAFucatwbOVWXk7g8N22YWkFreWYHidEWEMNmdTGUxMpQABggFgtC+i3Tlx0m+8DpA1en6qXTetuKzAymC+nbKzKp0jt/pbuwd2iYiIqPUxcEGlm9YzV5OYT+dKa+bt3ry6NXh2u4ZFu9dVANwLOLjV9tUGQsZg83cefxnZfB6xcBAigp9dX0Q4KPjG8dfwB79wh6338ordftOMAFn5+ZleSOPM1XlkVxWOHptwvDyolQat1Y7XePzhZy6sebxdMxXc6m+dENglIiKi1sddRTqccdP66nQKl2eXMb+cxcWZJVy4kbK924Nbu3042TGhGcelM7d2s3Cj7evtHLJ3NIFtA904OLYBubxCQATxSBBQCs+cndFmhxG7/cbKLheNMp+fqfllPHt+FgvpHO7c2udoh5ZW2+Wl2vF+59SV0ufYxZlFfOfUJO5/5CS+c+oK9o4mcP/hPfjKR+7E/Yf3tM1g3K3+1ox+S0RERNQoBi46nHHTem0hg0g4gEQsjGg4iGvzGds3r24Nnt3eyq9ZW1T6ya1gjxttb2UgtKU/hvHJBURCAUSLWRcQwYZufQZMdvtNeaBjeiGNl68m8VcvXcHRYxOuBAPM5+fk5STi0RAO7RrAxt6YowFnqw1aqx3v149fxOpqHhPXU8jk8hjoCQMCPPj0OW2DMI1yKyDbCYFdIiIian1cKtIGGkn1NpYYpNK5wqw3gEgogPl01tLNq/m9u4KCqfkMMNDd8HpyN9fct9M692oaSYmv1H+MwoXV0u9rsbJs5cj+EXz7xSvoj4WglEIml0cml8ebtiW0GTDZ7TflhUdfuDgHABjpjbiafm9cG0Y7B0wVu+0OOK2cK52WklQ73qn5NKBUKRAGAH3REGYWVxpeEqbTz2/m1rKuTthemoiIiFofMy5aXKOp3sascjwaQiaXBwBkcnn0RcN1b17L37srFEReKWRzq65kSrjF7QwOXTlJia/Vf5z2LSuZCntHE3j77kGICBYyOUTDQdyzvR+RUEibAZPdfmPOejl7PVV6/NaRuCeZDG5kEtV7Dd2WklQ73pG+KGYXs4iEXv+VlsnlMdjT1VAgTLef38ytLCu3l+YREREReYEZFy2u0cKTxqzypt4IJqYKadZKKYwNdtfNSqj03tsHe5CIhbXbarAVd01ohlr9x/i33b5lNVPhlw9tLxUF1DUTxk6/MWe9TC1kMNIbwa0jcQzFCxkCbqffu5FJVO81dCtsW+14P3FoGx783jnMp3PoKwZhM7k8xga7GwqE6fbzm7lVeLSdC5gSEZFelFK4lkzj5tIKNnR3YVMiWlguTGQBAxctzo3tEY2b1qXsamlXkbGheN2UaDvvrWu6tVdq/bw6tUW9c+ikb1kdCLXjgMkc6PA6/d7cfuYdgYygk5V2rHcOvN4e1yrzNRMLB4pZXbl1x/vg0+cws7iCwZ4ujA12IxAINJQ5oMvPX41bAVkGdomIyGtKKRw/N4PnLswir4CAAAfHBnBo1yCDF2QJAxctrtL65NduLOLaQgYPPHbS0sDY6U2r1bXRnbbdXq2fF4BWbVHvHDodfFvtU+06YPKqrkqloNeR/SO4OLuEWzYUasvY7VO1zoHX2+Na/V7zNWO0ZfnP9/47tmDncNzVoCDrPxAREbnjWjJdCloAQF4Bz12YxY6hHozy9ypZwMCFB5o5o14+QHrtxiJevDSHu7f1Vxw0u3lcVgdnOqdbG9w8Z14sv/BKvXOoc1FTnTJXynmRTVItINZd3A3Iiz7lRgCm0cClnc8Pp4Gwan2pEwr7EhERNcPNpZVS0MKQV4XHGbggK1ic02XNLuZWXkDw2kIGd2/rx9hQfM12gd84/prrx2W1eGG17fbOXE3i6LEJPPDYSde2i3TC7XNWa3tB3bYerHUOdS5qqnPRRIOTYqm1VNsK9MVLSc/6VLO2x63F62umVl+y+vOPT+rxWUZERKSrDd1dCJStCAlI4XEiK5hx4TI/sgvMs4y/9mfPYTKZxsT1FPqiYeze2IOBngieGp/BvTsGLR+X1dlsKzOc1ZazXL65jFs2dPu+ZMLNczY+mcTF2SW8ePEmhuIR7N7Yg6F41JXlF07VO5e1zqGuSzlaIYvHbdXqLSgoLKRzVftUo5kpjfYBp3UijOM+czWJn00tYP+WvlKhUzevmXp9qd7P32lL4YiIiJzYlIji4NjAuhoXm8ruEYiqYcaFy/ycUR+fTOLSzDLm0zn0RkJIZ1fx/GtzuDizCIFYPi63Z7Mrbbc3MZXCbcVtIp3MwrrJrXNmtNum3gjCgQCSy1mcuHATF26kStsLNnvrwVbITHBCt8wVL5TP4keCUnEr0Ddt7a/ap3Q4/062bTUf9523JJBK53D83CyuLyw7umZqZUQ02pcazSghIiLqBCKCQ7sG8dEDW/He20fw0QNbWZiTbGHGhcv8LOb2xOkp7BmJY+J6YVvTSCiATC6PV6ZSuGdbf81Z2fLXKZ+BnE1l8DuPv4xtA922Z20rrfffOhjDtsGeNc/za+Dp1jkzt1s8GsLJy0lcvZnGzOIK3ruvMMiyUvugWfU2WmU2uFJ7tHvRxEqz+FeTaQREgIHuNfUWKtWvMfrU0WMTvp9/J3UizP02EQvj3p2CM1fncfLSPA7vG7FUL8ScsXH55jJuG4lj22DPuoyIRvuS7juPEBER6UJEMNofY00LcoSBC5f5Wcztytwytg/1IB4N4ez0IlLpHIICLGVXMbWQWXPzXuu4ym/EpxfSmJhKIZvP494dA45SocvTrY8em/B14GkeDHcFBVPzmXUDQrvnrLzdVvMK2wZiyKzmEQ4F17RZtXZzO+281QdV1drjvr3DeGp8GoD715kORT8rBZy2D/ZgJbeKRCxcMehV6Rh1OP9OCpWWH/dwbxTv2BPBZDKN+w/vqfue5n4zv5wFALwylUI8GiotNzGCN41+Zrd7EI2IiIhIBwxcuMyL3QSsMm6gh3ujGO6NYnohjWfPz6IvGsbe0T50h4N45VoKS9lV7BtNVD2u8hvxs9OLgABD8QgCIljJreL8dAqfe/QUDu8bcTSw8zPAU2l7xbxSyOZWMZnMOT5n5nY7O72ISKiwEisR67I80+12hkSrD6qqtcfE1KIn15ku9QqqBRwmkzlLA3eDLuffbp2MRo/b3G9SmVX0RUPI5PI4e30RQ/HomuBNo5/Z3HmEiIiIyHsMXHjAzYKGdmZ/y2+gz1ydhwKwf0sfAiLYMRzHQDyCRCxcc/BT/jqzqRUEA8DujT2YXkjjhYtziAQFeZV3PLDzM8BTbTbbaBejzR9+5oKtGXdzuy0sZxEOClZWFfZv6QNgbabb7RnyVh9U1WqPRq+zSteWLktr3Ao4tOr5b/S4zf0mHg0hk11FJBTAfLqQfVHelo30JT8/y4iIiIg6BQMXGrM7+1t+A51dVbh354ZSajRgbRBc/joD8S6M9kUwFI/i+PkZR5kE1d7Hj5v7WoPh75y6ggefPofsah6DPV3I5lbx0A+WLAVmzO0GKazju2d7wtZOCG7PkLf6oMqrjIFq11Yqk8UbNvWtea4fS2vcCji06vlv9LjN/Wb3cA9euDiHTC6PvmioVNzTzeCNrrvvEBEREbULBi405mT213wDbdSRMLM66DO/jrnCv9NMAp1UGwx3BQUPfu8cIMBgT1epsOltI3HLgRmj3YyBZzgYRF4pywPPSgPW12YWsTkRxQOPnfRlO0s/Ge0xm8rg2nwas4tZhAKCz757V0OvW+3aujK3bLmIrZfcDDi0yvmvlAFjZ1mMmfk6GoxHsGdjHBNTKSS6C+fcSVu6VftEhxoqRERERK2G26G6pNZ2e041uk2fW1tvGoOoRCxsyiTot5VJ0Ai327ZauwiAXF6hLxqCiCAaDiISCmAymbYdmDG32WQyjUQsbCtrw/i+ldwqAiIIh4KubGfpRT/10t7RBO7bO4yJ6ynMLK4gEhIoKHzpiQl84VunHB9/tWvLPCPfjO1qq+m0wa3b27aWX0c7huM4+vE78dVfOYj7D+9xFLRw4/h02J62/Hha6fOAiIiIOpcopfw+Bl8cOHBAnThxwpXXMqedl29T2Mhgo9LOG8a/rc5EujEAqrQDx9YKWzJ6MbDyqm0rtcvDz1zAxZlFZHJ5RMNBAIBSCjOLK/jAHZsdz/42wo0+YGhmW7rZF4w2WMmtFuqrhAJQSkFEsHM47uj4a7WrUeui2UGDatt3en2N6cDNfu4Ft47P7ut4eW159XlQTkSeV0odcO0FfeLmPQMRERGtV++egUtFXOBVQT831rm7UcDQix04rPKqbSu1y5b+GFayq5i4ngKAYjG/HMLBQNNn3A1uFuv0oi2bsQuH0QbPvjqPSCiAaDgIpRQWMoUlHU6Ov9q1dXCs37eghdXtO+2+brWfR6esDuMcTy+kS1s5xyNB9JkG+H5y6zq08zpeX1u6FKIlIiIisoKBCxe4vROEwe/CeuOTSfzO4y9jJpXBUDyC3Rt7MBSPrtmBw2tetW0lhcHsEvZsjK+rp+DXjbybxSm9aEu3Bj+1BtFGGxiDWQDFQothx8df6do6ONaPp8anSwPFV6dTuP+Ra9g6GMO+Yt2SZgTo6m3faVWtgS8ALbZ9NWzpj+HV6RQmrqcQCQUQjwQxn85hPp3D+GTSl12ayo/PjevQzut4HVho5mcrERERUaMYuHCBVzsfAP4V1jMGPbOpFQx0h5HOruL51+Zwz/Z+DPREmnZz62XbljMPZrvCQRza5X9tgUazbswDtYuzS8jmVjE2FC/9f6Nt6cbgp97M8uuFTgWZ7Coggkwuj/1b+hreccV8bo8emygNFKcX0oXMGwGSS9l1x+R2toLd7TutqDXwvbGQxvnpFFZWCwGg3Rt7HGevuOHI/hHc/8g1QAqZTplcHgBsFcatp5EMBrd2ebHzOl4HFpr52UpERETUKG2Kc4rIERF5RUTOisjnK/y/iMgfFv//lIjcXXx8q4j8nYiMi8gZEflXzT52t4pg6sQY9AzEu7CyqkqFKs9eX2xqMc7phTQuzS7VbFs3C8ztHU3g/sN78JWP3OmoiJ/bnBb5BNYXAtzUG8ELF+dw4UbKtX66pT+GhXRuzWN2+4d5gB0QKX39xOkpAK+3we2b+3BzufBeb9qWQDgYdPU6MxfsPDu9iEgogL5oqLQkxTgmLwosmttx93APMrk85tM59EZCjs9TtQKkZ64m8Q9nZ6CUQm8kVApKZnI532bb944msHUwVmrvaDiIe7b3Y9tgj2vHVK+f1Ts+p9eh09dx49qqpR1/bxEREVH70iLjQkSCAP4TgMMALgN4TkQeV0q9bHrazwO4tfjnXgB/XPw7B+BzSqkXRKQXwPMicqzsez3l95IOLxizfbuHe/DCxTkAQFdQcCOVcTTTaJXdmhrNqLHQLNVm8Z1m3ZTPuO8YLmRaTM5nEA4FbfXTasfmxky0lZnlvaMJ/MEv3LHmODb2OtvWshrzDLSxLMVYkmI+Jjsp/OWFbQVAZlWty9LwYvvOajPq8+kcNnQXHjN2zwGAl68u4J23bbTZau7ZN5qoWLjSrYF6oxkMbmW/WX0dJ9eWnUygdvy9RURERO1Li8AFgDcDOKuUOg8AIvIIgA8BMAcfPgTgz1RhG5QfiUi/iIwqpSYBTAKAUmpBRMYBbCn7Xs/5taTDK8agZ7g3iru39ePs9CJmUysYjEc83YWi0qCwVk2NSs+fTWXwO4+/jG0D3XVv3nUpUOhFAKbSQG37UA+6wkF85SN3unZsjQ5+7KSse3mdmQeKRo0FANi/pW/NMZnb1SgmubCcBQTril8a7RYKAM+en4UCcO/ODevasLwddwzH8evvaqy2SrWBbyIWwuBQN166VMgQiYQCgFK4uZxrymy7l0GwWlphaUR529y3dxgTU4vrrq1KbQjYr1vSbr+3iIiIqH3pErjYAuCS6d+XUcimqPecLSgGLQBARMYAvAnAs5XeREQ+BeBTALBt27ZGj7mtlc8Ad4WCrm2dWevm2u6saPnzpxfSmJhKIZvP494dAzVv3nXK1vCiEJ9bA7V6x9bo4MfrAatV5uBBXyyM+XQOt43EMdATKaXRf+zgLXji9NS67VnDQYGIrOk/5nZ7eXIe8eKyjfPTS3jLzkEAa8+v24PIakEl4/iNgGQqnUM4KHjb7sGaGSNuBPa8DoLVoks/q6ZS2zw1Pr3u86haG3aHA9wlhIiIiNqWLoELqfCYsvMcEYkD+EsA/1opNV/pTZRSDwF4CCjsye7sUDtDo4OIagOeeoNgu4Pt8uefnV4EBBiKR0rr2M2vb2Y3WOBldoYXhfjcGqh5XSRQp5R1c/Cg/Hybj+mhH7yK89MpRIKFj6WVVYV7thfqbhj9x9xu5h1RjIKbzdjBoVowxBj43rtjoNQv/vmh7Wue4ySwV+8a8ToIVotO/awSq59H1Z7341dn8e69a5f6cJcQIiIiahe6BC4uA9hq+vctAK5afY6IhFEIWvy5UupbHh6nZbosQajGyvE5HUTUGvDUGwTbHWyXP382tYJgANi9safi65tZGZAb7XTmahKXby7jtpE4tg32uJ6d4UUau1sDtWak2Ffqa1b6qNPrrJH+b7Tr5x49hbzKIxHrwv4tfRiKR5FXqtR/zO1m7BQCoFQzw69lClb7hZPAXr1Ah99bcDYaGNEheFntecvZHH4wMb1mp5hwMKjVUhgiIiIip3QJXDwH4FYR2QHgCoCPA/ilsuc8DuAzxfoX9wJIKqUmRUQAPAxgXCn1H5t50NU4XYLQrGBHreMD0PAx1Brw1BsE2x1slz9/IN6F0b4IhuLRiq9vVu9YzO00v1yYJX9lKoV4NFR6fbfSsL1KY6+UQfDwMxdsnVs/UuytXEONXGeNLhHaO5rA4X0jNfuPud12DnXjuVdvQgHYt7l3zdITP1gZwNsNMlgJdJRfc9MLaZy5Oo/sqsLRYxOufeY5+Syt9z1eLy2zGiCs9LzXbixC5VUps2d5JYfj52axY6gHH3vv+tpARERERK1Gi+1QlVI5AJ8B8CSAcQCPKqXOiMinReTTxaf9LYDzAM4C+CqA/6n4+FsB/HMA/1REXir+eV9zf4K1nGy758UWi3aP7xvHX3PlGKptw3hlbtnSFnx7R+1tSWp+/hc/uA+BQMDSFn/1jsXcTqnMKvqiodKWsOafyQ1GAKbR7RaraaR/eX1slVi5hpxub9nItphm9fqPud1yeeDenQM4tHMA2VV42oZubQ9sdzvOWte9wdxmU/PLePb8LBbSOdy5tc+1zzwnfd3K97jVb6qxuj1ppedNTKVw59Z+3LtzAJGuEHL5QtuP9EW0yvQjIiIickqXjAsopf4WheCE+bE/MX2tAPxGhe97BpXrX/jGSTq0F8UZ7R7fU+MzuHfHYMPHUGvm0Ot15nZev95zze1kpPpHQoFSjQKrqf5eLnmw+p43FtIN9a9m7z5g5RpyuuzAreUKVvparSUwdjNfrDAG4KureVybT+Oli3N48vQ1fPbdu/D+O7bYei27mTZWMgbMbfbsqzOIR0OlZTaGRj/znHyWWvkeXWq9VHre1sEYtg32ICCC4d7CMeaVwmQyDUD/pYtERERE9WgTuGgnTmoCNHPtd7XjE0jdGVMr6g14vB4E23n9Ws81t9Pu4R68cHEOmVwefdGQ5VR/KwNJqynoVgcflV7vH87O4K27BwC8fs51Ltxn5RpyWnvDzZodRvsb58WYfa9VvNLL5QZPnJ7C6moeE9dTiIQCGOgp7I7y4NPnsHM4bus97AYZrQY6jGvO+MwLyOtxZzf6pNXPUvP19PLVedy5tQ+1rg+/ar1Yed7RYxNVj02n3ZOIiIiInGLgwgNOagI046a43vG9aWsCC+lcw8dQa8DTSjN/5VvC7tkYx8RUConuwsyslUwRKwNJK7O9lQYf/+GJV7A5EUVmVdXduWVDdxgvX13AxtteP5ev3VjEtYUMHnjsJLqCAgHWvZZfrFxDTmtvNFqzw9yHu4KCqfkMtg50WxoUep1ZdWVuGdfm04iEAoiGC7uY9EVDmFlccfQetQbSla5lO4EOrz7zrLxu+fX0s6kFPHv+Jg7tklL2R/n36Lydaq1ja2Y2HxEREZFXtKhx0W6c1ASwur7ZLbFwAM++OoPvjV9HNreKT71jB3750HbXjqFSnYpm1vFwQ/l53DEcx9GP34mv/spBS7U3gPUDSRFBXzSE7Gq+NDtvpTZA+fr6ldwqLs4s4fTV+XVtWen19o724ubS6+f21ekUXrw0h9G+CEIB4Nnzszh+fhbhILQ4L1auIae1Nxqp2VHeh89cncerNxaRXV21VPfAyrluxJb+GGYXs4iEXv9oz+TyGOzpcjW7ptq1DMByfRqvPvOsvG759XT75j4IgNNX5mvW3ml2rRerah2b132OiIiIqBmYceERu8shvK79YDDPNN63d6Q0M9eMY/By5s+rTI5Gl7Vs6Y/hpYtzGOh5ffa3fCBpZYa4PP397PQi4pEgVlbzpQEzUH3nlmg4hLftLtQvuTK3jPM3FtEdDmLiegrzy1nEIyFEw0Gcn17CW3YOll7Lz0GZlbZ3en6cfl95H86uKsQjQZy9vliaqa81KHSSZWCnbx/ZP4InT1/DfDqHvmgImVwemVweY4PdrmZvuXEte/V5Y+V1y6+n4d4oDu7YgJOXk5hMpmvWl6i3Y41fGWXVjq2Z2XxEREREXmHgQiPVbjzdvBmuN+Dwsv6EV3U8zMGYUAD4/ivX8e0Xr+Dtuwfxy4e2+77kod5A0koKevngI5XOIRQA+qLr1+R/8m1jFV/PmIEdn0ziX37jBfTHCsGKa8k0lldWsbk/ivl0fs1r0VrlfTgeDSGzkisVbAVqDwrtLjewW59g72gCn333Ljz49DnMLK5gsKcLY4PdCAQCrmZvObmWq32OeXF91nvdasG99+zbhPsPO9s+tJFaEl4GPHRe4kJERERkFZeKaM7t5RXNTBs2tmX8H7/+HD76n4/j+ddm8YOJadxIpUvPcWPmzwjGrORW8dKlQrv0x0I4fXVeiyUPn333LgDAzOIKIqEAbhuJrxlIWklBL09/DwcFqcwqdm/sKT2nfOeWaq/3xOkpbOgOQ0QgIujuCiIggumFlVIghDOylZVvEbp7uAepzCq6ggFLyx3sLjdwsgXn++/YgqMfuxMfuGMztg32YGwo7vqSBrtbpeq2TMyLZSq1zlWtLWq9bhudl7gQERERWcWMiyZoZDbN7eUVXqYNVypa2NMVxOXZZUCAfF5hJrWC4+dmce/ODYiEQq7M/Bmzv8++Ol+qJaGUwkImVxo4+HmT/v47tmDncLxiHyjvG59821jVmXRz+vvtm/swNZ9BOBhEXilbO7dcmVvG3tFeU5AnjCuZNNLZVewc7ra8Y4pumpGmXz573RUKYttgNzYnojWXGJjZyTJwmqXk9c49e0Z68ODT55BdLSx7Gk1EEQgEqvYZ3QpEerFMpdq5OnM1iYuzS1UzMRptGyv93uv+QEREROQ1Bi481uhWdG4vr/Aqbfg7p66sGcgkl7PIrir0RIKIhAvBhEgogNW8QjAgOHlpHof3jbiypt0IxqTSOcQjhZ0UCtuWhpu65KHWAKLSwMHJMgDz4+XvZ7Utjfa6e1s/zk4vIruqMNzbhUgoiOwqsLHX2o4pOmnWlo+VBry/eeS2ht6jVr/RsT7B+GQST41PY8/GOK7NpzG7mMX1+TT2be7Dw89cqDh4buZ2z1a5PZivdq7m0zncsqG7amCikbbhVqdERETUKRi48Fijs2luD1y8mGkcn0ziwe+dAwQY7OlCJpfHtfk0RnojmEymsXOosJwhEgpgIZPDu/ZsxGQyvW4tudMZcyMYEw4KMtlVQASZXB77t/Q1bZDnZADRaN9wOvAy2isRC+PeHQPramC0ombO6Ls54K3Xb3SsT2Bu6x3DcUwvpPHs+VlcmUvjHXt6K/b9Wp9jrbRFci3VzlUiFqq5PK+Rz3jdMlmIiIiIvMIaFx5rtKaEF2uxK21V2ognTk8hl1foi4YgIoiGg4iGgpgr7laSyeVLf/dFwxVvyhtZ520EY27f3Ieby4V192/alkA4GPR0S1kzJ7UIrPSNWmvjnaq15t2L92uGVt3ysdI2t+enU/jco6dw9NgEAGhXn6C8rSvtcFPe96t9ju0Z6dGq9kUjql1X+0YTNeuBNPIZ36r9noiIiMguZlx4rNGMiWZtk9qIK3PLGOgJI5PLIxouLNUYinfhtdkljCaiyGQLO2kopTA22F1xxtiN7IM/+IU71szeNnPJg5N073p9w8s0cCdLVxqZGfd6Vl3HJRVWmPvN9EIaL1ycQyQoyKv8mvZ3utOFF+zscGOo9jlm5bpvpYyMatk4tbJmGvmMb9V+T0RERGQXAxces5LqXe/GXPfCalv6Y1jJrmLiegpAYUnIqgKGerrw5rEBTC1kMJ/OIRELYWwoXnHgUauw3dFjE5YHLX601fhkofjeixdvYigewe6NPRiKR+sOIOr1jWangdd6PwANbfVo9XsbXS4E6LOkwgrzwPPs9CIioUISXCLW5Vvaf71zUN7W4aBgIZ3DG295/TmV+n6la/PhZy7UDPi1Qw0HK4GJRpd9Ada3122VIBARERGRGQMXHqt30+r0xlynG9DCzfPSmmJ9oYDgfz1yG95/xxZLr1Fp5vC1G4u4fHMZt2zoxmgiilenU7j/kWvYOhjDvuL6f79vuo2ipKl0FsvZPPJKYW5pBW/Y1FtzlwWgft9odkHDWu/XSBDF6vc2MkhthcykSswDz4XlLMJBwcqqwv4tfQCan/Zv5RzY3eGmlnoZA37VcHD789WrgKqdft8OQSAiIiLqXAxcNEGtm1YnN+Zu3oC6cYNuvnnuCgdxaJf916k0czgxlcJtm+JIxMKYXkgXMjoESC5lHf3Mbg9GzEVJN/fHcHNpBbOLWXR3BTE5n8EXP7jP0oC72nOanQZe6/0aCaJY/V6/ipX6yXztQAARwT3bExiKF9qr2Wn/Vs+BWzvc1MsY8GM3klYb4Fvt9yzkSURERK2MgQufObkxd+sG1M0b9EYHjZVmDrcOxrBtsLAjiZFGb+xMYvdn9mIwYhQlHegJQ0Qw0BNBd1cIkVAA2wa6Gx4MNHv5Q633e+L0lOMgitUAjI5bZjaDce28vjuO/cwFtzg9B06v/3oZA37UcGjXAX6nXl9ERETUHhi48JmTG3O3bkB1u0EvH/wcPTZRaptUOod4JFjamQSw9zN78bNWKkoaCQUws7iCQ7uGHL2mWbOXP9R7P6dBFKsBmE4vNKjDchc/zkGtoIcftUuaMcD3Y6lfp19fRERE1NoYuPCZkxtzt25AdZ+BM7dNPBLEfHFLQWP9v52f2YuftVJR0vl0DuFgwLUtWK3OZLs1EKr2fo0Mqq1+b6sW2HST38tddDsHfgRzvB7g+7UURbdzS0RERGQHAxc+c3Jj7tYNqO4zcOa26YuFMZ/O4baROAZ6IkguZ239zF78rNWKkn723buavgtEMwZCjQyqrXyvnxkHOhW79ZMOWR+VjqmZ7+/1AN+vTDcdzy0RERGRVaKU8vsYfHHgwAF14sSJpr6nm4MjN17LPOA136DrWoSukZ/Zyc9q5f10GPCal9QYjH/ff3hP045Dh7Zwchytdh2Q97zsyw88dhKjiSgCIqXH8kphMpnGVz5ypyvvoRMReV4pdcDv4ygnIg8A+DKAYaXUjXrP9+OegYiIqJPUu2dg4KJJdB0c6TLYbAY7P6uu56sSHQZCurSXk+PQJfBDnaHT+puOgQsR2QrgvwB4A4B7GLggIiLyX717Bi4VaRLdCmEa/F5T30x2flZdz1clOiz50aW9nByH7rVedNdJwU83sNaEFo4C+E0Af+33gRARUXVKKVxLpnFzaQUburuwKRGFmCbqqLMwcOEx46b+r166gpHeCG4diWMoXhgkcXCkr1YazOowEPK7vRq5znQI/LQqvwpNtrJm15pgYGktEfkggCtKqZP1bn5F5FMAPgUA27Zta8LRERGRQSmF4+dm8NyFWeQVEBDg4NgADu0aZPCiQwX8PoB2ZtzUJ5ezGOmNYD6dw/OvzeFGKg2AgyOdbemPYaG4i4lB1/NlDIQSsTAmk2kkYuGmDxz9bK9Gr7Mj+0dKxV7zSpW+dmtnmHZmznAJiJS+fuL0lN+HprW9owncf3gPvvKRO3H/4T2eBi2Ma8McWBqfTHryfroQkadE5HSFPx8C8AUAv23ldZRSDymlDiilDgwPD3t70EREtMa1ZLoUtACAvAKeuzCLa8m0vwdGvmHGhYfMN/W7N8bxwsU5AMDPplIIB4NMD9aYDlkMdvi95MfP9mr0OuNuC875nWlDtemyhKvZlFL3VXpcRN4IYAcAI9viFgAviMiblVLXmniIRERUx82llVLQwpBXhcdHa0xIcXlJ+2LgwkPmm/rh3iju3taPs9dTmFrI4FAszMGRxjiYtcfP9nLjOvM78NOquMxGbwwsraWU+gmAjca/ReQCgANWinMSEVFzbejuQkCwJngRkMLj1XB5SXtj4MJD5Tf1w71RdIWCONSm1ePbDQez9lRrL6/X2LfCddaudQZaLTOp0zCwRERErWpTIoqDYwPrghCbygLyZtWWl+wY6qmZpUGtgTUuPFRp7fxrM4u4sZDGA4+dxNFjE22/1pg6WzPW2Ot+nbVznQEd6qtQdazfUptSaozZFkREehIRHNo1iI8e2Ir33j6Cjx7YWjdzotbyEmp9DFx4qPymfiW3ioAIwqFg2w1giCppRvFG3a+zdi9g2axCk2QfA0tERNTKRASj/THs25zAaH+s7nIPY3mJWb3lJdQ6uFTEY+b0+aPHJtAVCnZcoTTqXM1aY6/zdcY6A+QnLnkjIqJO4WR5CbUOBi6aqNkDmHZdV0+tw4819roFClhngIiIiMh7xvKSHUM93FWkDXGpSBNt6Y9hIZ1b85hXA5h2XldPrcOPNfbNvM6sYJ0BIiIiouawu7yEWgczLpqomRX4zevqAf/T5XXCTJTm8WObVK+uM6f9hlvrti5+VhARERHpQZRS9Z/Vhg4cOKBOnDjR9Pdt1o3wA4+dxGgiioApyphXCpPJNL7ykTtdf79WYWSiJGLhNYNaFqxrL25fZ+w3nYfn3B0i8rxS6oDfx9Eov+4ZiIiIOkW9ewZmXDRZswqlcV19ZcxE6QxuX2fsN52H55yIiIhIHwxcaMLtGeJmLktpJboVbqTWwH7TeXjOiYiI/KOUwrVkmkU2qYTFOTXgRSFNY119IhbGZDKNRCzMFGfoV7iRWgP7TefhOSciIvKHUgrHz83g0ROX8OSZKTx64hKOn5tBp5Y4oAJmXGjAq5TkZi1LaSXMRCEn2G86D885ERGRP64l03juwizyxThFXgHPXZjFjqEejHICoWMx40IDV+aW0RtdG0NiSrI3mIlCTrDfdB6ecyIiIn/cXFopBS0MeVV4nDoXMy40wEKazcVMFHKC/abz8JwTERE134buLgQEa4IXASk8Tp2LGRcaOLJ/BMnlLJLLWeSVKn19ZP+I34dGRERERETUNJsSURwcG0CgWIszIMDBsQFsKiuaTZ2FGRcaMFKSzbuKfOzgLZzpIyIiIiKijiIiOLRrEDuGerirCJUwcKEJpiQTEREREREVghej/TEW46QSLhUhIiIiIiIiIm0xcEFERERERERE2mLggoiIiIiIiIi0xcAFEREREREREWmLgQsiIiIiIiIi0hYDF0RERERERESkLQYuiIiIiIiIiEhbDFwQERERERERkbYYuCAiIiIiIiIibTFwQURERERERETaYuCCiIiIiIiIiLTFwAURERERERERaUuUUn4fgy9EZBrAax689BCAGx68brthO1nDdrKG7WQd28oatpM19dppu1JquFkH4xWb9wzsO/awvaxjW1nHtrKH7WUd28oeO+1V856hYwMXXhGRE0qpA34fh+7YTtawnaxhO1nHtrKG7WQN22k9tok9bC/r2FbWsa3sYXtZx7ayx8324lIRIiIiIiIiItIWAxdEREREREREpC0GLtz3kN8H0CLYTtawnaxhO1nHtrKG7WQN22k9tok9bC/r2FbWsa3sYXtZx7ayx7X2Yo0LIiIiIiIiItIWMy6IiIiIiIiISFsMXBARERERERGRthi4cImIHBGRV0TkrIh83u/j0YmIXBCRn4jISyJyovjYgIgcE5GfFf/e4Pdx+kFEviYi10XktOmxqm0jIr9V7GOviMh7/Tnq5qvSTr8rIleK/eolEXmf6f86tZ22isjfici4iJwRkX9VfJx9yqRGO7FPmYhIVER+LCIni+30xeLjHd2f7P5O64Q2MXPr95qI3FNs57Mi8ociIs3+Wbzm1u+2Dmkr136/dXh7sX+VcfN3Xbu3FVCzvbzvW0op/mnwD4AggHMAdgLoAnASwD6/j0uXPwAuABgqe+w/APh88evPA/iS38fpU9u8A8DdAE7XaxsA+4p9KwJgR7HPBf3+GXxsp98F8ECF53ZyO40CuLv4dS+AiWJ7sE9Zayf2qbU/twCIF78OA3gWwFs6vT/Z+Z3WKW1S1hau/F4D8GMAh4r98L8C+Hm/f7YmtZXtz6EOaSvXfr91eHuxf63/2V37XdfubVWnvTzvW8y4cMebAZxVSp1XSq0AeATAh3w+Jt19CMDXi19/HcA/8+9Q/KOU+gGA2bKHq7XNhwA8opTKKKVeBXAWhb7X9qq0UzWd3E6TSqkXil8vABgHsAXsU2vUaKdqOrWdlFIqVfxnuPhHgf2pErZJkRu/10RkFECfUuq4Ktzd/hna8D7Bjd9tHdRWrvx+Y3tV1bHt5dbvuk5oK6Bme1XjWnsxcOGOLQAumf59GbU/HDqNAvBdEXleRD5VfGxEKTUJFD5cAWz07ej0U61t2M/W+4yInCqm2xopfGwnACIyBuBNKETC2aeqKGsngH1qDREJishLAK4DOKaUYn+y9zutU9qkHrvts6X4dfnjncLO51DHtVWDv986vb0A9q91XPpd1xFtBVRtL8DjvsXAhTsqrcfhPrOve6tS6m4APw/gN0TkHX4fUItiP1vrjwHsAnAXgEkA/2fx8Y5vJxGJA/hLAP9aKTVf66kVHuuYtqrQTuxTZZRSq0qpuwDcgsIMyf4aT++UdrLzO61T2sSpau3Tye1m93Ooo9rKhd9vnd5e7F8VuPS7riPaCqjaXp73LQYu3HEZwFbTv28BcNWnY9GOUupq8e/rAL6NQprsVDFFCMW/r/t3hNqp1jbsZyZKqaniB2cewFfxevp1R7eTiIRRuEn5c6XUt4oPs0+VqdRO7FPVKaXmAHwfwBF0eH+y+TutI9rEArvtc7n4dfnjbc/B51DHtJVLv986ur3Yv2pr8HddR7UVsLa9mtG3GLhwx3MAbhWRHSLSBeDjAB73+Zi0ICI9ItJrfA3gPQBOo9A+nyg+7RMA/tqfI9RStbZ5HMDHRSQiIjsA3IpCUZuOZPwyKfpvUehXQAe3U7Ea88MAxpVS/9H0X+xTJtXaiX1qLREZFpH+4tcxAPcB+Ck6uD85+J3W9m1ika32KaZlL4jIW4rX66+gQ+4T7H4OdUpbufX7rdPbi/1rPbd+13VCWwHV26spfUtpUJ20Hf4AeB8KFXvPAfiC38ejyx8Udlo5WfxzxmgbAIMAvgfgZ8W/B/w+Vp/a55sopFNlUYg8frJW2wD4QrGPvYI2rFRss52+AeAnAE4VPxRH2U54GwppdqcAvFT88z72KcvtxD61tp3uAPBisT1OA/jt4uMd25+c/E5r9zap0Eau/F4DcKDY784B+CMA4vfP1qS2sv051CFt5drvtw5vL/av9W3l2u+6dm+rOu3led+S4jcREREREREREWmHS0WIiIiIiIiISFsMXBARERERERGRthi4ICIiIiIiIiJtMXBBRERERERERNpi4IKIiIiIiIiItMXABRG5SkS+ICJnROSUiLwkIvf6fUxERETUXCKyWrwPMP6MicgPi/83JiK/ZHruXSLyPgfv8X0ROVD22O+KyP9e9thdIjJe43V+V0QesPv+RNQ8DFwQkWtE5BCADwC4Wyl1B4D7AFzy96iIiIjIB8tKqbtMfy4opf5J8f/GAPyS6bl3AbAduKjimwA+VvbYxwH8fy69PhH5gIELInLTKIAbSqkMACilbiilrorIPSLy9yLyvIg8KSKjAFB8/KSIHBeRL4vI6eLjvyoif2S8qIj8jYi8s/j1e4rPf0FEHhORePHxCyLyxeLjPxGRNxQfj4vInxYfOyUiv1jrdYiIiMgbIpIqfvl/AHh7MRPj3wD4dwA+Vvz3x0SkR0S+JiLPiciLIvKh4vfHROSR4u/zvwAQK38PpdQrAObKMj4/CuAREfm14mueFJG/FJHuCsdYyuIQkSERuVD8Oli8V3mu+P7/svj4qIj8oHjsp0Xk7a41GBGVMHBBRG76LoCtIjIhIv+3iPyciIQBPAjgw0qpewB8DcDvF5//pwD+Z6XUISsvLiJDAP43APcppe4GcALA/2J6yo3i438MwEj5/LcAkkqpNxazQJ628DpERETUmJhpmci3y/7v8wD+oZiJ8SUAvw3gL4r//gsAXwDwtFLqIIB3AfiyiPQA+HUAS8Xf578P4J4q7/1NFLIsICJvATCjlPoZgG8ppQ4qpe4EMA7gkzZ+nk+icD9xEMBBAL8mIjtQyBx5Uil1F4A7Abxk4zWJyKKQ3wdARO1DKZUSkXsAvB2FG42/APB7APYDOCYiABAEMCkiCQD9Sqm/L377NwD8fJ23eAuAfQD+sfhaXQCOm/7/W8W/nwfwC8Wv70Px5qV4jDdF5AN1XoeIiIgas1wczDvxHgAfNNWdiALYBuAdAP4QAJRSp0TkVJXvfwTAD0XkcyjcA3yz+Ph+Efk9AP0A4gCetHlMd4jIh4v/TgC4FcBzAL5WnKj5K6XUSzZek4gsYuCCiFyllFoF8H0A3xeRnwD4DQBnyrMqRKQfgKryMjmszQiLGt8G4JhS6r+r8n2Z4t+reP3zTSq8T73XISIiIv8IgF8sLvt4/cHCZEO1e4cSpdSl4hKPnwPwiwCMe5D/B8A/U0qdFJFfBfDOCt9uvgeJmh4XAJ9VSq0LdojIOwC8H8A3ROTLSqk/q3eMRGQPl4oQkWtE5DYRudX00F0opGIOFwt3QkTCInK7UmoOQFJE3lZ87n9v+r4LAO4SkYCIbAXw5uLjPwLwVhHZXXytbhHZU+ewvgvgM6Zj3ODwdYiIiMgdCwB6a/z7SQCflWKkQkTeVHz8ByjeL4jIfgB31HiPbwI4CuCcUupy8bFeFLI+w1h732F2Aa8vQfmw6fEnAfx68XshInuKtTi2A7iulPoqgIcB3F3jmIjIIQYuiMhNcQBfF5GXi+mb+1BYt/phAF8SkZMorP00qor/CwD/SUSOA1g2vc4/AngVwE8AfAXACwCglJoG8KsAvll8/R8BeEOdY/o9ABuKBbNOAniXw9chIiIid5wCkCsWybwfwN8B2GcU5wTw7wGEAZySQuHuf1/8vj8GEC/+7v5NAD+u8R6PAbgdhWUjhn8L4FkAxwD8tMr3fQWFAMUPAQyZHv8vAF4G8ELxmP4zCtmd7wTwkoi8iEJ2x/9l4ecnIptEqbrZVkREnhORMQB/o5Ta7/exEBERERGRPphxQURERERERETaYsYFEREREREREWmLGRdEREREREREpC0GLoiIiIiIiIhIWwxcEBEREREREZG2GLggIiIiIiIiIm0xcEFERERERERE2vr/AVaH3KsnTzobAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 1080x864 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import statsmodels.api as sm\n",
    "from statsmodels.graphics.gofplots import ProbPlot\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# Load the dataset\n",
    "file_path = '/Users/dhruvtrivedi/Downloads/Final Project Stat 371/Final_Transformed_Farm_Data_Gujarat_v2.csv'\n",
    "data = pd.read_csv(file_path)\n",
    "\n",
    "\n",
    "# Model with \"Number of Cows\", \"Number of Buffaloes\", \"Daily Expenditure on Animal Health (INR)\", \"dynamix dairy\", \"Daily Revenue (INR)\", \"Daily Income from Selling Manure (INR)\", and \"natural plants\"\n",
    "X_current_final = sm.add_constant(farm_data[['Number of Cows', 'Number of Buffaloes', 'Daily Expenditure on Animal Health (INR)', 'dynamix dairy', 'Daily Revenue (INR)', 'Daily Income from Selling Manure (INR)', 'natural plants']])\n",
    "model_final = sm.OLS(y, X_current_final).fit()\n",
    "\n",
    "# AIC of the final model\n",
    "model_final_aic = model_final.aic\n",
    "model_final_aic, model_final.summary()\n",
    "\n",
    "# Calculate residuals and leverage\n",
    "residuals = model_final.resid\n",
    "fitted_vals = model_final.predict(X_current_final)\n",
    "leverage = model_final.get_influence().hat_matrix_diag\n",
    "studentized_residuals = model_final.get_influence().resid_studentized_internal\n",
    "\n",
    "# Create sequence of numbers for plotting\n",
    "sequence = np.arange(len(residuals))\n",
    "\n",
    "# Create the 4 plots\n",
    "fig, axs = plt.subplots(2, 2, figsize=(15, 12))\n",
    "\n",
    "# Residuals vs Fitted Values\n",
    "sns.residplot(fitted_vals, y, lowess=True, scatter_kws={'alpha': 0.5}, line_kws={'color': 'red', 'lw': 1}, ax=axs[0, 0])\n",
    "axs[0, 0].set_title('Residuals vs Fitted Values')\n",
    "axs[0, 0].set_xlabel('Fitted Values')\n",
    "axs[0, 0].set_ylabel('Residuals')\n",
    "\n",
    "# Normal Q-Q plot\n",
    "sm.qqplot(residuals, line='45', fit=True, ax=axs[0, 1])\n",
    "axs[0, 1].set_title('Normal Q-Q')\n",
    "axs[0, 1].set_xlabel('Theoretical Quantiles')\n",
    "axs[0, 1].set_ylabel('Standardized Residuals')\n",
    "\n",
    "# Leverage vs Sequence\n",
    "axs[1, 0].scatter(sequence, leverage, alpha=0.5)\n",
    "axs[1, 0].set_title('Leverage vs Sequence')\n",
    "axs[1, 0].set_xlabel('Sequence')\n",
    "axs[1, 0].set_ylabel('Leverage')\n",
    "\n",
    "# Studentized Residuals vs Fitted Values\n",
    "sns.scatterplot(fitted_vals, studentized_residuals, ax=axs[1, 1], alpha=0.5)\n",
    "axs[1, 1].axhline(y=0, color='red', linestyle='--')\n",
    "axs[1, 1].set_title('Studentized Residuals vs Fitted Values')\n",
    "axs[1, 1].set_xlabel('Fitted Values')\n",
    "axs[1, 1].set_ylabel('Studentized Residuals')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fd2a9af6",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}