{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Autoregressive Moving Average (ARMA): Artificial data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import statsmodels.api as sm\n",
    "import pandas as pd\n",
    "from statsmodels.tsa.arima_process import arma_generate_sample\n",
    "np.random.seed(12345)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Generate some data from an ARMA process:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "arparams = np.array([.75, -.25])\n",
    "maparams = np.array([.65, .35])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The conventions of the arma_generate function require that we specify a 1 for the zero-lag of the AR and MA parameters and that the AR parameters be negated."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "arparams = np.r_[1, -arparams]\n",
    "maparams = np.r_[1, maparams]\n",
    "nobs = 250\n",
    "y = arma_generate_sample(arparams, maparams, nobs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " Now, optionally, we can add some dates information. For this example, we'll use a pandas time series."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/lib/python3/dist-packages/statsmodels/tsa/base/tsa_model.py:159: ValueWarning: No frequency information was provided, so inferred frequency M will be used.\n",
      "  warnings.warn('No frequency information was'\n"
     ]
    }
   ],
   "source": [
    "dates = sm.tsa.datetools.dates_from_range('1980m1', length=nobs)\n",
    "y = pd.Series(y, index=dates)\n",
    "arma_mod = sm.tsa.ARMA(y, order=(2,2))\n",
    "arma_res = arma_mod.fit(trend='nc', disp=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                              ARMA Model Results                              \n",
      "==============================================================================\n",
      "Dep. Variable:                      y   No. Observations:                  250\n",
      "Model:                     ARMA(2, 2)   Log Likelihood                -353.445\n",
      "Method:                       css-mle   S.D. of innovations              0.990\n",
      "Date:                Mon, 24 Feb 2020   AIC                            716.891\n",
      "Time:                        22:49:06   BIC                            734.498\n",
      "Sample:                    01-31-1980   HQIC                           723.977\n",
      "                         - 10-31-2000                                         \n",
      "==============================================================================\n",
      "                 coef    std err          z      P>|z|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "ar.L1.y        0.7904      0.134      5.878      0.000       0.527       1.054\n",
      "ar.L2.y       -0.2314      0.113     -2.044      0.041      -0.453      -0.009\n",
      "ma.L1.y        0.7007      0.127      5.525      0.000       0.452       0.949\n",
      "ma.L2.y        0.4061      0.095      4.291      0.000       0.221       0.592\n",
      "                                    Roots                                    \n",
      "=============================================================================\n",
      "                  Real          Imaginary           Modulus         Frequency\n",
      "-----------------------------------------------------------------------------\n",
      "AR.1            1.7079           -1.1851j            2.0788           -0.0965\n",
      "AR.2            1.7079           +1.1851j            2.0788            0.0965\n",
      "MA.1           -0.8628           -1.3108j            1.5693           -0.3427\n",
      "MA.2           -0.8628           +1.3108j            1.5693            0.3427\n",
      "-----------------------------------------------------------------------------\n"
     ]
    }
   ],
   "source": [
    "print(arma_res.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2000-06-30    0.173211\n",
       "2000-07-31   -0.048325\n",
       "2000-08-31   -0.415804\n",
       "2000-09-30    0.338725\n",
       "2000-10-31    0.360838\n",
       "dtype: float64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlIAAAHdCAYAAADW0ZfjAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8li6FKAAAgAElEQVR4nOzdeVzVVf7H8deXy2VHXMAlN1BLURR3TUtLJ5cyK5vSpmm1fdp+NrZMy7RPU9NMWdO+l5Vl5rSYWamZlbu4A8qOIigg+3bv/f7+uEKagHC5cFnez8eDB3jv957vAVHenOVzDNM0EREREZH68/J0B0RERERaKgUpERERERcpSImIiIi4SEFKRERExEUKUiIiIiIu8vbETUNDQ83w8HBP3FpERESkXjZv3nzYNM2w6p7zSJAKDw9n06ZNnri1iIiISL0YhpFS03Oa2hMRERFxkYKUiIiIiIsUpERERERc5JE1UtWpqKggPT2d0tJST3dF2gA/Pz969OiB1Wr1dFdERKQFazZBKj09neDgYMLDwzEMw9PdkVbMNE2ys7NJT08nIiLC090REZEWrNlM7ZWWltKpUyeFKGl0hmHQqVMnjX6KiEiDNZsgBShESZPR95qIiLhDswpSIiIiIi2JgtQxFixYQGRkJJdffrmnu0JMTAzLli3zdDdERESkFs1msXlz8NJLL/HNN9/UaQGyzWbD27vxvnwxMTFs2rSJc889t9HuISIiIg2jEamjbrrpJhITE5k5cybPPvssF154IUOGDGHs2LFs374dgIcffpgbbriBKVOmcOWVV2K325k/fz6jRo1iyJAhvPrqq1XtPf300wwePJjo6GjuvfdeAF5//XVGjRpFdHQ0F198McXFxQB8+umnREVFER0dzYQJEygvL+ehhx5i0aJFDB06lEWLFjX9F0REREROqlmOSD3y5S52H8h3a5sDT2nH388fVOPzr7zyCsuXL2fVqlU88sgjDBs2jKVLl7Jy5UquvPJKYmJiANi8eTNr167F39+f1157jZCQEDZu3EhZWRnjx49nypQpxMbGsnTpUtavX09AQAA5OTkAzJo1i+uvvx6ABx54gDfffJPbbruNRx99lG+//Zbu3btz5MgRfHx8ePTRR9m0aRMvvviiW78OIiIi4j7NMkh52tq1a/nss88AmDRpEtnZ2eTl5QEwc+ZM/P39AVixYgXbt29n8eLFAOTl5bF3716+//57rrnmGgICAgDo2LEjADt37uSBBx7gyJEjFBYWMnXqVADGjx/P1VdfzaWXXsqsWbOa9HMVERER1zXLIFXbyFFTME3zhMcqt8sHBgYed90LL7xQFYgqLV++vNrt9VdffTVLly4lOjqad955h9WrVwPO0bD169fz9ddfM3To0KrRLxEREWnetEaqGhMmTGDhwoUArF69mtDQUNq1a3fCdVOnTuXll1+moqICgPj4eIqKipgyZQpvvfVW1Rqoyqm9goICunXrRkVFRVX7AAkJCYwZM4ZHH32U0NBQ0tLSCA4OpqCgoLE/VREREWmAZjki5WkPP/ww11xzDUOGDCEgIIB333232uuuu+46kpOTGT58OKZpEhYWxtKlS5k2bRoxMTGMHDkSHx8fzj33XJ588kkee+wxxowZQ+/evRk8eHBVUJo/fz579+7FNE0mT55MdHQ0vXr14qmnnmLo0KHcd999zJ49uym/BCIiIlIHRnXTWI1t5MiR5qZNm457bM+ePURGRjZ5X6Tt0veciIjUhWEYm03THFndc5raExEREXGRpvZERETEo0zTxDRNHA4Hdrsdh8NR48fHPmaz2bDZbFWPHduOw+EAqHq8pve//7i6x4KDg7vU1HcFKREREXELm81GWVlZ1VtJSQlFRUWUlZUdF3rsdvtxH9vt9qod89XtejcM47gd9cd+bBhG1WtO9r4u1xz73svLC9M0sVgsvjV9zgpSIiIiclIOh4OysjJKS0ur3hcVFVW9FRcXU1FRcVxoORpC8PLywsvLqyr0VL75+Pgc9+fmqHJkqyYKUiIiIm2caZrHjSSVlpZSXFxMYWFhVUgqKys7ISR5eXnh7e2Nt7c3fn5+BAQENNtA1FgUpERERNogu91ORkYG8fHxJ9QtNE0TwzCqQpLVasXPz6/NhaS6UJASERFpQ8rLy0lNTSU+Pp7y8nL8/Pxo166dQpKLFKRERETagOLiYpKSkkhISMDhcBAYGFh1Jqy4TkHqqAcffJDQ0FDuuOMOAO6//366dOnC7bff7uGeiYiIuMY0TfLy8khISCAtLQ3DMAgKCsJisXi6a61G8wxS39wLB3e4t82ug2H6UzU+PXfuXGbNmsUdd9yBw+Hg448/ZsOGDe7tg4iISBMwTZPDhw8TFxfH4cOHsVgstGvXDi8v1eF2t+YZpDwgPDycTp06sXXrVjIzMxk2bBidOnXydLdERETqrHIBeWxsLIWFhVitVkJCQrT+qRE1zyBVy8hRY7ruuut45513OHjwINdee61H+iAiIlJf5eXlpKWlER8fT1lZGX5+frRv397T3WoTmmeQ8pCLLrqIhx56iIqKCj788ENPd0dERKRW1S0g9/f393S32hQFqWP4+Phw9tln0759ey3EExGRZsk0TfLz89m3bx/p6ekAWkDuQQpSx3A4HKxbt45PP/3U010RERE5TuUC8vj4eA4dOoSXlxfBwcFaQO5hClJH7d69mxkzZnDRRRdx6qmnero7IiIiwG8LyOPi4sjPz8fHx0cLyJsRBamjBg4cSGJioqe7ISIiUqW4uJi1a9dSXFyMn58fHTp08HSX5HcUpERERJoh0zSJiYmhrKxMO/CaMU2sioiINEOpqalkZmYSFBTk6a5ILRSkREREmpni4mK2b99OUFCQ1kI1cwpSIiIizYhpmmzduhUAq9Xq4d7IyTTbNVKrVq0iLy/Pbe2FhIRw9tln13rN888/z+uvv45pmlx//fXceeedADz88MO8/vrrhIWFAfDkk09y7rnn8vPPP3PzzTfj6+vLRx99RL9+/Thy5AizZ89m+fLljfpbxKeffspDDz1E165deeaZZ3jvvfdYsGDBCdeFh4ezadMmQkNDG60v1bnuuuuYN28eAwcOrPGapUuXctppp9V6jTu88847bNq0iRdffLFR7yMi4g4pKSlkZmZqYXkL0WyDVF5enlsX1x05cqTW53fu3Mnrr7/Ohg0b8PHxYdq0aZx33nlVpRD+7//+j7/+9a/HvebZZ5/ls88+Izk5mZdffplnn32Wxx57jL/97W+NPhT75ptv8tJLL1WFw5EjRzbq/errjTfeOOk1S5cuZcaMGfUKUjabDW/vZvttKyLSIEVFRWzfvp127dppSq+F0NTeUXv27GHs2LEEBATg7e3NxIkT+fzzz2t9jdVqpaSkhOLiYqxWKwkJCezfv5+JEyfW+JqNGzcybtw4oqOjGT16NAUFBZSWlnLNNdcwePBghg0bxqpVqwDnSMqsWbOYNm0ap556KnfffTcAjz76KGvXruWmm25i/vz5rF69mhkzZgCQnZ3NlClTGDZsGDfeeCOmaVbd+4MPPmD06NEMHTqUG2+8EbvdDjgr4t5///1ER0czduxYMjMzAcjMzOSiiy4iOjqa6Ohofvnll1rbOdZZZ53Fpk2bamz/l19+4YsvvmD+/PkMHTqUhIQEEhISmDZtGiNGjODMM88kNjYWgKuvvpp58+Zx9tlnM3/+fMLDw48Lxv369SMzM5Mvv/ySMWPGMGzYMP7whz9UfR4iIi1B5ZSel5eXfmFsQdwWpAzDsBiGsdUwjK/c1WZTioqKYs2aNWRnZ1NcXMyyZctIS0urev7FF19kyJAhXHvtteTm5gJw3333ccMNN/Dcc89x6623cv/99/PYY4/VeI/y8nJmz57N888/z7Zt2/j+++/x9/fnv//9LwA7duzgo48+4qqrrqK0tBSAmJgYFi1axI4dO1i0aBFpaWk89NBDjBw5koULF/LMM88cd49HHnmEM844g61btzJz5kxSU1MBZ1BctGgRP//8MzExMVgsFhYuXAg4fwMaO3Ys27ZtY8KECbz++usA3H777UycOJFt27axZcsWBg0aVGs7Namu/XHjxjFz5kyeeeYZYmJi6Nu3LzfccAMvvPACmzdv5l//+he33HJLVRvx8fF8//33/Oc//+GCCy6oCrnr168nPDycLl26cMYZZ7Bu3Tq2bt3KnDlzePrpp0/+Fy8i0kykpKRw6NAhAgMDPd0VqQd3Rt47gD1AOze22WQiIyO55557OOeccwgKCiI6OrrqN4Kbb76ZBx98EMMwePDBB7nrrrt46623GDp0KOvWrQNgzZo1nHLKKZimyezZs7FarTz77LN06dKl6h5xcXF069aNUaNGAdCunfNLtXbtWm677TYABgwYQO/evYmPjwdg8uTJhISEAM6ioSkpKfTs2bPGz2PNmjUsWbIEgPPOO69qjv2HH35g8+bNVfcuKSmhc+fOgPOMwcoRrREjRvDdd98BsHLlSt577z0ALBYLISEhvP/++zW2U5Oa2j9WYWEhv/zyC5dccknVY2VlZVUfX3LJJVXnSM2ePZtHH32Ua665ho8//pjZs2cDkJ6ezuzZs8nIyKC8vJyIiIha+yUi0lwUFhayfft2goODNaXXwrglSBmG0QM4D3gCmOeONj1h7ty5zJ07F4C//e1v9OjRA+C4MHT99ddXhYJKpmny+OOPs2jRIm699VYeeeQRkpOTWbBgAU888cRx11X3D+TY6bff8/X1rfrYYrFgs9lO+nnUdI+rrrqKf/zjHyc8Z7Vaq15zsnvU1k5N6tK+w+Ggffv2xMTEVNvGsb+hnX766ezbt49Dhw6xdOlSHnjgAQBuu+025s2bx8yZM1m9ejUPP/xwnfsoIuIpDoeDrVu3YhiGpvRaIHdN7T0H3A04arrAMIwbDMPYZBjGpkOHDrnptu6VlZUFOIugLVmyhMsuuwyAjIyMqms+//xzoqKijnvdu+++WzX6U1xcjJeXF15eXhQXFx933YABAzhw4AAbN24EoKCgAJvNxoQJE6qmx+Lj40lNTaV///4ufQ7HtvXNN99UTUNOnjyZxYsXV32OOTk5pKSk1NrW5MmTefnllwHnWU/5+fkutVOT4OBgCgoKAOfoXERERNWB0aZpsm3btmpfZxgGF110EfPmzSMyMpJOnToBzg0K3bt3B5x/JyIiLUFycjKHDx9W4c0WqsHR1zCMGUCWaZqbDcM4q6brTNN8DXgNYOTIkTUPwRwVEhJy0p129VE5PVabiy++mOzsbKxWK//973+rpsXuvvtuYmJiMAyD8PBwXn311arXFBcX8+6777JixQoA5s2bx8UXX4yPjw8fffTRce37+PiwaNEibrvtNkpKSvD39+f777/nlltu4aabbmLw4MF4e3vzzjvvHDcSVR9///vfueyyyxg+fDgTJ06kV69egHNa8PHHH2fKlCk4HI6qz7F37941tvX8889zww038Oabb2KxWHj55Zc5/fTT691OTebMmcP111/PggULWLx4MQsXLuTmm2/m8ccfp6Kigjlz5hAdHV3ta2fPns2oUaN45513qh57+OGHueSSS+jevTtjx44lKSmp3n0SEWlKhYWF7NixQ1N6LZhR27RSnRowjH8AVwA2wA/nGqklpmn+uabXjBw50qzc0VVpz549REZGNqgvIvWh7zkR8SSHw8HatWvJz8/XaFQz5nA4uPjiiw/l5uZWuyC4wVN7pmneZ5pmD9M0w4E5wMraQpSIiIhAUlIS2dnZ2qXXwqmOlIiISBMrKChg586dmtJrBdy6PcA0zdXA6ga8Xt9Q0iQaOqUtIuIqh8PBli1bsFgs2qXXCjSbESk/Pz+ys7P1A04anWmaZGdn4+fn5+muiEgblJiYSE5Ojqb0WolmE4V79OhBeno6zbU0grQufn5+VXXCRESaSn5+Prt27dJZeq1IswlSVqtVlahFRKTVqpzS8/b2rjqpQVq+ZjO1JyIi0prt27eP3NxcAgICPN0VcSMFKRERkUaWn5/Pnj17NKXXCilIiYiINCK73c7mzZs1pddKKUiJiIg0ooSEBI4cOaJdeq2UgpSIiEgjycvLY/fu3bRr187TXZFGoiAlIiLSCCqn9KxWq6b0WjEFKRERkUawb98+8vLyNKXXyilIiYiIuNmRI0eqdulJ66YgJSIi4kaVU3o+Pj6a0msDFKRERETcKD4+noKCAhXebCMUpERERNwkNzeXuLg4goODPd0VaSIKUiIiIm5gs9k0pdcGKUiJiIi4gab02iYFKRERkQbKyckhLi6OkJAQT3dFmpiClIiISANUTun5+fnh5aUfq22N/sZFREQaIC4ujqKiIvz9/T3dFfEABSkREREX5ebmEh8fr8KbbZiClIiIiIvi4+OxWq2a0mvD9DcvIiLigsLCQjIyMnSWXhunICUiIuKCpKQkDMPAMAxPd0U8SEFKRESknsrKykhKSiIoKMjTXREPU5ASERGpp7S0NBwOhyqYi4KUiIhIfdjtduLj47U2SgAFKRERkXrJyMigvLwcq9Xq6a5IM6AgJSIiUkemaRIXF4efn5+nuyLNhIKUiIhIHWVnZ5Ofn4+vr6+nuyLNhIKUiIhIHe3duxer1aqSB1JFQUpERKQOCgoKyMzM1CJzOY6ClIiISB0kJibi5eWl0Sg5joKUiIjISZSWlpKSkqICnHICBSkREZGTSE1NxTRNHU4sJ9B3hIiISC1sNht79+4lICDA012RZkhBSkREpBYZGRlUVFSoAKdUS0FKRESkBqZpEhsbi7+/v6e7Is2UgpSIiEgNDh8+TFFRkQpwSo0UpERERGoQHx+vKT2plYKUiIhINfLy8jh06JAWmUutFKRERESqoQKcUhcKUiIiIr9TUlJCamqqCnDKSSlIiYiI/E5qaiqACnDKSek7RERE5BiVBTh1OLHUhYKUiIjIMfbv34/NZsPb29vTXZEWQEFKRETkKIfDQVxcnApwSp0pSImIiBx16NAhFeCUelGQEhERwXkcTHx8vEKU1IuClIiICM4CnNnZ2ZrWk3pRkBIREQESEhKwWCwqwCn1oiAlIiJtXnFxMenp6Sp5IPWmICUiIm1eSkoKoAKcUn/6jhERkTatoqKCffv26TgYcYmClIiItGnp6enY7XYsFounuyItkIKUiIi0WQ6Hg/j4eAICAjzdFWmhFKRERKTNysrKoqSkBB8fH093RVooBSkREWmTTNMkLi5OBTilQRSkRESkTcrNzSU3Nxc/Pz9Pd0VaMAUpERFpk1SAU9xBQUpERNqcoqIi9u/fr5IH0mAKUiIi0uYkJydjGIZGo6TBFKRERKRNKS8vJyEhQaNR4hYKUiIi0qakpaXhcDhUgFPcQkFKRETaDLvdTnx8vA4nFrdRkBIRkTbj4MGDlJWVYbVaPd0VaSUUpEREpE0wTZP4+HgV4BS3UpASEZE2IScnh7y8PBXgFLdSkBIRkTZh3759eHt7q+SBuJWClIiItHqFhYVkZGRokbm4nYKUiIi0eomJiSrAKY1CQUpERFq1srIykpOTVYBTGoWClIiItGqpqakqwCmNRkFKRERaLbvdzt69e7U2ShqNgpSIiLRaGRkZlJeXqwCnNBoFKRERabVyc3M1pSeNSkFKRERExEUKUiIiIiIuanCQMgyjp2EYqwzD2GMYxi7DMO5wR8dEREREmjtvN7RhA+4yTXOLYRjBwGbDML4zTXO3G9oWERERabYaPCJlmmaGaZpbjn5cAOwBuje0XREREZHmzq1rpAzDCAeGAeuree4GwzA2GYax6dChQ+68rYiIiIhHuC1IGYYRBHwG3GmaZv7vnzdN8zXTNEeapjkyLCzMXbcVERER8Ri3BCnDMKw4Q9RC0zSXuKNNERERkebOHbv2DOBNYI9pmv9ueJdEREREWgZ3jEiNB64AJhmGEXP07Vw3tCsiIiLSrDW4/IFpmmsBww19EREREWlRVNlcRERExEUKUiIiIiIuUpASERERcZGClIiIiIiLFKREREREXKQgJSIiIuIiBSkRERERFylIiYiIiLhIQUpERETERQpSIiIiIi5SkBIRERFxkYKUiIiIiIsUpERERERcpCAlIiIi4iIFKREREREXKUiJiIiIuEhBSkRERMRFClIiIiIiLlKQEhEREXGRgpSIiIiIixSkRERERFykICUiIiLiIgUpERERERcpSIlIm7RwfQrProjzdDdEpIVTkBKRNqewzMZTy2J5eXUCecUVnu6OiLRgClIi0uZ8sjGNgjIbNofJd3syPd0dEWnBFKREpE2xO0ze/iWJEb070L29P8t3Zni6SyLSgilIiUib8t3ug6TllHDdGRFMHdSVNXsPU1hm83S3RKSFUpASkTbljZ+S6NnRnymDujJ9cFfKbQ5WxmZ5ulsi0kIpSIlImxGTdoRNKblcMy4Ci5fBiF4dCAv21fSeiLhMQUpE2ow31yYR7OvNpaN6AuDlZTB1UBdWxR6ipNzu4d6JSEukICUibcL+IyUs25HBnNE9CfL1rnp8elQ3Sirs/Bh/yIO9E5GWSkFKRJqn1PVQ4L7SBO/9koxpmlw1Lvy4x8dEdKRDgFXTeyLiEgUpEWl+shPg7emw8GKwN3xHXVGZjQ83pDJ9cDd6dAg47jlvixfnDOzCD3uyKLNpek9E6kdBSkSan1VPON8f3AHrXmpwc59uSqOg1MZ1Z0RU+/z0qG4UlNn4ZV92g+8lIm2LgpSINC8Z22HnZ3DGndD/XFj1JOQmu9yc3WHy1s/JDO/VnmG9OlR7zbh+nQj29eYbTe+JSD0pSIlI87LyMfBrD+Nuh3OfAS8LfDUPTNOl5r7fk0lqTjHXndmnxmt8vS1MjuzMd7szsdkdrvZcRNogBSkRaT5SfoW9K5yjUf7tIaQHTP47JPwAOz51qck3f0qie3t/pgzsUut106K6kVtcwfqkHJfuIyJtk4KUiDQPpgk/PAJBXWH0jb89PmoudB8Jy++F4vqFnO3pR9iQnMM148PxttT+393E08Lwt1o0vSci9aIgJSLNw77vIfVXmDgffI7ZWedlgfOfh9I8WPFAvZp8c20SQb7ezD5agLM2/j4Wzh4Qxre7MnE4XJtGFJG2R0FKRDzP4XCORnUIh2FXnvh81yjnmqmYhZD4Y52azMgr4evtGcwe1ZNgP2udXjMtqhuHCsrYnJpbj86LSFumICUinrf7c2epg7PvB2+f6q+ZeDd0iICv7oSKkpM2+e4vKThMk6t/V4CzNpMGdMbH24tvdhys82tEpG1TkBIRz7JXwMonoPNAiLq45uus/nD+c5CTCGueqbXJojIbH65PYXpUN3p2DKj12mMF+Xoz4dRQvt11ENPFXYIi0rYoSImIZ8UshJwEmPSgcz1UbfqcBdF/gp+fh8xdNV62eHM6+aU2rq2hAGdtpkV1Y/+REran59X7tSLS9ihIiYjnVJTA6n9Cj9HQf3rdXjP1CfALgS9uB8eJR7rYHSZv/5zEsF7tGdG7+gKctTknsgveXgbf7NT0noicnIKUiHjOxjeg4ABMfggMo26vCegI056C/Ztg45snPP3DnkySs4uZ68JoFEBIgJVx/UJZvjND03siclIKUiLikgZXAC/Nh5/+DX0nQcSZ9Xvt4Eucr/vhEchLP+6pN9c6C3BOG9TV5a5Nj+pKcnYxezIKXG5DRNoGBSkRqbfkw0VEPfwtizenn/zimvz6IpTkOEej6ssw4Lx/O6f2ls2vOj5mR3oe65PqVoCzNlMGdsHLgOUqztmo4jML+G53pqe7IdIgClIiUm8/xh+itMLB3z7fwc79LizKLjoMv/4XBl4ApwxzrRMdI+Ds+yBuGez5EoA31yYS6GPh0joU4KxNpyBfRkd01DqpRlRms3Pdu5u4/r1NPLsiTtOo0mIpSIlIva1LzKZLO186Bfpw0webyS0qr18DP/0bKorh7PpVKj/B2L9A18GwbD6ZWVl8tT2D2aN60a6OBThrMz2qG3uzCtmXVdjgtuREb/+cTGpOMeP7deKFlfv42+c7sauivLRAClIiUi8Oh8n6pBzOPDWMl/88gqz8Mu5YFFP3H4J56c5F5tF/grDTGtYZizecvwCKsjiw+B4cpsk148Mb1uZRU4+usdL0nvsdKijjxZX7+ENkZz6YO4ZbzurLRxtS+cvCLZRWnLgTU6Q5U5ASkXqJzyogp6icsX06MbRnex6eOYg18Yd47vv4ujWw+inAhLPudU+Hug+nYtSNDMtawi19DtWrAGdtuob4MbxXe03vNYJnV8RRZrPzt3MjMQyDu6cN4KEZA1m+6yBXv72B/NIKT3dRpM4UpESkXtYlZAMwJqIjAJeN7smlI3vwwsp9J184fHivswDnyLnQvmHrmI61OPhK0s1Q/lL4AtjK3Nbu9Khu7DqQT2p2sdvabOt27s9j0aY0rjo9nD5hQVWPX3tGBM/PGcqm5FzmvLqOrIJSD/ZSpO4UpESkXtYl5tCjg3/VyI9hGDx6QRRR3dsxb1EMSYeLan7xysfB2x/OvMtt/XE4TF5bn8VbIbfhn7fPWfXcTaZFHZ3e26XpPXcwTZNHv9pNhwAfbpt86gnPXzC0O29cNZKkw0X88eVfScmu5XtJpJlQkBKROnOuj8pmbJ9Oxz3uZ7Xw8uUjsFgMbnp/M8XlthNffCAGdi+F0/8CQWFu69PK2CySDhcxbPKlMGiW8xy+w3vd0nbPjgFEdW+n6T03Wb7zIBuScph3zmmE+Fe/IeCs/p358Pox5JdWcPHLv7LrgI7qkeZNQUpE6iw+q4Dc4ooTghQ4Q8eCOcOIzyrg3s92nLid/YdHwb8DjLvVrX16Y20i3dv7Mz2qq7PiudUfvrwDHA0sGHrU9KhubE09QkZeiVvaa6tKK+w8sWwPA7oGM+ck5SmG9erA4ptOx8diMOfVdfx6dDpZpDlSkBKROvv9+qjfm3BaGH+d0p8vth3gnV+Sf3sieS0k/ABnzHOek+cmO/fnsS4xh6vG9XYW4AzuAuc8Bik/Q8wHbrlH5fTetxqVapA31yaRnlvCgzMG1qlYar/OwSy+eRxdQvy46u0NLNfXX5opBSkRqbPfr4+qzkmBIYoAACAASURBVM0T+/KHyC488fUeNibnOKuOf/8IBJ8Co693a3/eWptEoI+F2aN6/fbgsCug93hY8QAUNLxqdt+wIE7rEqTpvQbIyi/lpVX7OGdgF8b3C63z605p78+nN57OoFPaccvCzXy8IbUReyniGgUpEamTyvVRp1czrXcsLy+Df8+OpmfHAG5ZuIUj276E9A0w8W7ntJubZOaX8sW2A1wysufx6228vOD856GiBJa7p8TCtKhubEzO4XCh+3YEtiXPfBtHud3B/edG1vu1HQJ9WHjdGCacFsa9S3bw4sq9qoIuzYqClIjUSVxmzeujfq+dn5VX/jyCotJyjnz1EGaHPjDsz27tz3u/JmM3Ta4dH3Hik6GnwoT5sGsJxH/b4HtNj+qKw4QVu3QuXH3tSM9j8ZZ0rhkfQXhooEttBPh48/qVI7loWHf+tSKeR77cjUNV0KWZUJASkTpZl3h0fVSf6tdH/V7/rsG8PyadcFsSn4VcCZaGH9tSqaTczsL1qUwd2JVenWqYZhx/J4QNgK/vgrKGHfMyoGsw4Z0C+EZVzuvFWe5gFx0DfLh1Ur8GtWW1ePHsJdHMPSOCd35J5s5FMZTb3LOhQKQhFKREpE7WJWbTs6M/PTrUsXK4vYIRCS9x0P9U5sf2438x+93Wl8+2pHOkuIK5Z1YzGlXJ28c5xZeXBquebND9DMNgWlQ3fk3IJq9YVbfr6usdGWxMzuWvU/u75fxDLy+DB86L5J5pA/hi2wHmvruRorJqSm2INCEFKRE5qcrz9cZGnHxar8qW9yA3idALHmNURCj3fLadPRn5bunLW2uTiO4RwsjeHWq/uNdYGHktrH8Z9m9p0H2nR3XF5jD5bo+m9+qitMLOP5bFEtmtHZeOPKbcgWk6168V5zjPXcxNrle7hmFw81l9efriIfy87zB/emM9OfU9NFvEjbw93QERaf7iMgs4Usf1UQCUF8OPT0PPsXj3n8aL3cs4/4W13PTBZr649YwaizHWxaq4LBIPF7HgsmEYhnHyF/zhYYhdBl/eDtevcnmKcUiPELq392f5zgz+OKKHS220OMU5kJ0AFcXO8HPC+5ofyzmcw6vFefTxsWB5vvz4647Vvjfcub3eXbt0VE86BPpw64db+OMrv/D+3DF0b+++zQwidaUgJSInVbk+amzfOgapDa9B4UG45G0wDDoH+/HS5cOZ/eo65i2K4fUrR+LlVYcQVI031ybRLcTPWYCzLvxC4Nxn4JMrYN1LMP4Ol+5rGAZTB3Xlg/UpFJbZCPJt5f995qXDqxOg+CTFMC2+zt2Y1oCq9+VevqTk2QkI6kZAz27HPHf8dVj9nEVaXXTOwC68P3cMc9/dyMUv/cJ7c0dzWpdgl9sTcUUr/59ARNxhXWI2vToG1O03/pIjsPY/0O8c6D2u6uERvTvy4IyB/P2LXby4ah+3V3PW2snsOpDHLwnZ3Dd9ANY6FHWsEnk+9D8PVv0DImdCx1rWVtVi+uCuvPVzEitjs5gZfYpLbbQI9gr49BqwlcOl70FAaDUh6Ggw8rKc8PL7PtnGl6kH+H7uRKhpM4CbjI7oyCc3ns5Vb23gkld+5a2rRzKid902RIi4g9ZIiUitqtZH1XG3Hr+8AKVHYPKDJzx15em9uWhYd/7zfTyr4rLq3Ze31iYT4GNhzuheJ7/4WIbhHJXyssDX85zrdFwwolcHwoJ9Wd7ad+/98Iiz9tfMBTDwAggfD92HQ+cB0KG386xE36BqQ9S2tCN8tiWda8+IqHlHpZtFdmvHZzePo0OAlcvfWM/KWK1jk6ajICUitYo9WI/1UYVZsO5lGHQRdIs+4WnDMHjyosEM6NqOOz+OIS2nuJpGqpeVX8oX2/Zz6e8LcNZVSHeY/HdIWAk7Pq3/63HuGps6qAurYg9RUm53qY1mL+4bZxgedR1EzarXS53lDnYTGuTLX87u20gdrF7PjgEsvnkc/ToHcf17m/lsc3qT3l/aLgUpkWrEpB3hSLF2AsGx9aPqEKR+ehZspXD2AzVe4u9j4ZU/D8c0TW58fzOlFXULJO/9moLNYXLN+PA6XV+tUXOh+0hnxfPiHJeamB7VjZIKOz/GH3K9H83VkVT4/CboOgSmPFHvl3+5PYPNKbnMn3oawW4od1BfoUG+fHT9WMZEdOSuT7fx+prEJu+DtD0KUvVkd5gkHy7ydDekEf2akM1FL/3Mv1bEeborzUKd10cdSYVNb8GwyyG09uKLvTsF8tycoezOyOf+z3ee9MgPZwHOFM6J7ELvTq5VxwacU1HnPw+lec6z+FwwJqIjHQKsrW96z1buXBdlOuDSd50LweuhpNzOU8v2MOiUdvxxRM+Tv6CRBPtZefuaUZw3uBtPLNvDm1tyqVDdTmlEClL18PO+w8x4YS1n/Ws1O/fnebo70ghyi8r5v0UxmCb8sCerzZ/pVa/1UaufAgyYWLfz7SYN6MIdk0/lsy3pfLC+9sNol2xNJ7e4guvO7FOntmvVNQrG3Q4xCyFxdb1f7m3x4pyBXfhhTxZltlY0vff9w7B/E1zwInSs/9f5tTWJHMgr5aEZA7G4uCPTXXy9LSy4bBhXjO3N0j0FPLzJYHlSBaW2tv3vWRqHglQd7MsqZO47G7n8jfUcKnAeWrr7QMMLC0rzYpom93y2neyiMq48vTcZeaXsySjwdLc8KvZgAXkldVgflRUL2z6C0dc71yLV0R2TT+Xs/mE8+uUutqTmVntNZQHOwd1DGBXu+lb540y82xkWPpwNS26E5J/rtQB9elQ3Csps/LLvJKUBWoo9X8G6/8LoG52Ly+spI6+EV35M4NzBXes2BdwELF4Gj14wiMcnd6ZrAHwcV85ffyzmf/vKKapQoBL3UZCqRU5ROQ/9bydTn1vD+qQc7pk2gDV3n4WPxYuEww07u0uanw/Wp7Jidyb3TBtQdS5YW9/9U1U/6mQ/HFc9DtZAOGNevdr38jJ4bvYwuoX4c8sHW6p+UTnWj/GHSDhUxHVnRtStAGddWP3hz0tg6J8gbhm8cy68MALWPgcFJ/87H9evE8G+3q3j7L3cZFh6C5wyDKY85lITTy+Pw26a3Dc90r19ayDDMIju6sdtUSYPjPWjb3sLn++r4K7VxXwSV05emQKVNJyCVDXKbHZeW5PAxGdWsXB9KpeN7snq+Wdx81l9CfDxpnenABIPaZ1UaxJ3sIDHv9rNxNPCuHZ8BJ2D/RjSI4SVsfXfot+arEvMpnenAE6pbX3U/s2w50sYdysE1n80IiTAyst/Hk5ucTm3fbQFm/34BS1vrE2kazs/zh3crd5t16pjBMz4D9wVBxe+AkFd4Pu/w78j4ePLIf5bsFd/jpuvt4XJkZ35bnfmCf1tUWxl8OnVzo8veQe8fevdxNbUXD7fup/rzoigZ8emKXfgin7tLfzfCD8eHefHkDAL3yRV8Ncfi3l/dxnZJS3471A8TkHqGKZp8vX2DP7w7x95clksI3t3YPkdZ/L4hYMJDfrtP5iI0ECStOC81SitsHPbR1sI9rPyr0uiqypuTxrQma1pR8guPHGUpC2o8/l6PzwKAZ3g9L+4fK9Bp4Twj1mDWZeYwz+Xx1Y9vicjn5/3ZXPVuPD6FeCsD58AGHoZXPsN/GWj8/NIWw8fXgrPDYYfHoOcpBNeNi2qG7nFFaxPcm33X7Pw3UNwYCtc+F/oEF7vl1eWOwgL9uWWs2vfYNBc9Gpn4ZahfvzjTH/GdvNmdZqNu9eU8OaOMg4WKVBJ/SlIHbU1NZc/vvIrf/lwC4E+3rw/dzRvXzOaU6s5bqBPWBAp2UUt+zdRqfL417uJzyzk35dGExb8W2CePKALpgmr41rhNvc62HMw37k+qm8tC80Tf3Qu2D7zLvBt2NEcs4b34MrTe/P6T0l8vd05Zfbm2iT8rRb+VN8CnK4KO805vTVvD8z+wLkwfe2/YcFQeHcm7FgMFaUATDwtDH+rpeVO7+3+H6x/Bcbe4qz87oL/xRxga+oR5k/t3+KOzOka6MXcwb48PcGfs3t6sy7Dxn0/lfBSTCmp+a1oE4E0Ord85xuGMQ14HrAAb5im+ZQ72m0K6bnFPL08ji+2HSA0yJenZg3mkpE9a9110icskAq7SXpuCeGhDdiKLR63fOdBPliXyg0T+jDhtLDjnht0SjvCgn1ZGZvFxW3lkNpjrEt0jrSMqWlEyjSdo1HtusPIuW655wPnDWTn/jzmL95Gh0ArX8Qc4LLRPQkJaOKaRBarM1xEnu88cy7mQ9jyPnw213k23JDZ+A+/krMHhPHtrkwenRnl8tmBHpGTCP+7FbqPgD884lITxeU2nvomlsHdQ/jj8Jb776OTvxd/HujL+X19WJFcwQ+pFWw4aCc6zML5faz063Bi9XaRYzU4SBmGYQH+C5wDpAMbDcP4wjTN3Q1tuzEVlFbw0uoE3lybhJcBt03qx40T+9bpt6q+Yc7wlHi4UEGqBTtwpIR7PtvO4O4h/HVK/xOe9/IymNS/M8t2ZFBhdzTe1FIzddL1UXHLnNvlz19Q75pDNfHx9uKly0cw44WfuOLNDThMk2vGu3YuntuE9HDu8jvzr5C02hmoNr0F61/hiQ5D+GfxaLYmnMaIU5to1KyhKkqd66IM4+i6KB+Xmnn1x0QO5pfywp+GtawQWYMQX4NL+vtwbh8r36dUsCKlgsfX24ns6MWMPj4M7OTlvs0O0qq4Y0RqNLDPNM1EAMMwPgYuAJplkLLZHXy8MY3/fBdPdlE5s4Z1569T+9e+mPZ3IkKDAEg8VMSkAY3VU2lMdofJnYtiqLA7WHDZMHy8qw9JkyI7s2hTGhuTcxjXN7SJe+k5DofJhqQcpg3qWv0Fdptz7VCnfjD0crfeu2uIHy/+aTiXv7GeP0R2aT6/rHh5Qd9JzreibNi+iHab3+Up6xuUf7QQhlwMw6+EnqOdIaW5WnE/ZGyDOR9Be9fC34EjJby6JoHzhnRjVHjrOiA40GpwQT8fpoZbWZ1mY3lyBc9sKqVPiBcz+lgZ2tmCV3P++20FHKZJhR3KHFBhNym3Q7nD+b7CAeV2k/LK90cfsztMHCbYTXAc82Y3nWv57CY4AIfD+d7uAAdm1Z+Pvd75sfnbYydZxeOOINUdSDvmz+nAmN9fZBjGDcANAL16Nf1vbqZpsjr+EE9+vYe9WYWMjujI2+dFMqRH+3q31THQh/YBVhK14LzF+u+qfWxIyuHZS6KJqOUH9Rn9QvGxeLFyT1abClK1ro8qK4TF18KhPXDpe2Bx/9qYsX068eWtZ9CjY91/wWlSgZ3g9FuwjL2ZJ157n8FZ/+P8XZ9jxHwAof2dgSp6DgQ2s++ZnZ/Bxjfg9FthwLkuN/PP5bGYJtw3vfX+JunnbTAtwsrk3t6sTbexLKmCBVvL6BFkMKOPD6O6WjxeeLQ5ME2TUjsUVZgUV5gUVUCxzTz6ZyiymZRUHB98yisD0u/CUJndGaDcUTfVy3AuAvfycr63eFX+2XC+N357s1R9bJzwuMUA75PM7rrjf8DqvpNO+DKYpvka8BrAyJEjm7R4R+zBfJ74eg8/7T1MeKcAXr1iBFMGdmnQMG2f0EASD6mWVEu0KTmH53/Yy4VDT2HW8NqLRwb6ejOmT0dWxmbxwIyBTdRDz6tcH3VC/aj8DOdutsydcN6zLhVvrKuBp7RrtLbdxjDoP3ISt3/aiYjrn2dw3krY8p5z1Of7h51rrM55xOWRH7fKToAv7oAeo+EPD7vczOaUXP4Xc4DbJvWjR4fmW+7AXaxeBmf3sjKhhzfrD9r5KrGcV7aXsWSfwXkRVsZ198bawgOVwzwaeirMoyGIo6Hod3+2OcNSZUAqrjAptjlHbWpiAH7e4Gsx8LGAjxf4WAysXhBkNfDxM/DxAqvFwNfi/Hr7WDh6rYHVAr5H31e+tvI5HwtHHzecQelo8DHArdOwDoeDi2t53h1BKh049mClHsABN7TbYFkFpfznu3gWbUwj2M/KgzMGcsXY3jVO49RHn7Ag1rTGQ0tbubySCu74OIbu7f157MKoOv1jmzygMw9/uZukw0W1jl61JusSswnvFEC3kGNGhA7udIao0jz40ydw6jme62Azck5kF7y9DL6OL2Tw9Cudo1FZe5yBavO7sHeFM7iMnOv89dgTKkrhk6uco4d/fMu5mN4FDofJo1/uonOwLzdN7OvmTjZvFi+Dcad4M7abha1Zdr5MqODtXeV8vq+CnsFe+HuDv7dxzPvfPg6wGvh5Q4D3b++tXu79YW9znBh4io4JR78fLTo2LJWeZJOixYBAKwRYDQK9DYJ8DLoEOj+vAG+DQKtBgBUCj36ugVbn5xhgdX4NWvtUqDuC1EbgVMMwIoD9wBzgT25o12WlFXbe+CmRl1cnUGZzcPW4CG6f3I/2Aa4tqqxOn7BAFm9Op6C0wiOnnEv9mabJ35bsIDO/lE9vOr3Of2+TBnTh4S93szI2i7lneHjhcxOoXB81PeqY9VH7vodPrgbfILjmG+g2xGP9a25CAqyc3rcTy3dmcM+0/s4fjp0jYdo/YMxN8NWdsOyvztIJM19wllhoasvvhcwdzgDc3vUDhZfG7Gdbeh7PXhJNYAsrd+AuXobBiC7eDO9sYVe2nR9SbRwpMzlUYlJigxKbc6rqZCwG1YYuf2/wtxr4Wwz8rc7HHA7nCFDldNlvU2dHw1Id7uljcQadykDUyc+gV7CXMwAdDUgBlWGpKiA5/+zj5tDX2jT4X4JpmjbDMG4FvsVZ/uAt0zR3NbhnLtq5P48b3tvEgbxSpg7qwr3TIxtlFKHP0TaTDxczuEeI29sX9/tkUxpf78jgnmkDGNar7me29eoUwKmdg1gZm9kmgtTujPzjz9fb9DZ8fRd0Hgh/WlSvs/TaiulR3fjb5zuIPVhAZLdjpiQ79HYeRbPtI1h+H7wy3rkDcPydLo8K1duOxbD5bRh/B5w21eVmisps/HN5LNE9QrhomL4HDMMgKtSbqNATf4zaHCalR0OV8835cbENSm3OEaJSmzMQldhMSiqcz+eUmse9xv67KTM/C0dHf5whp3OA12+jQceMDh07IlT5fEuffmzO3PIrhWmay4Bl7miroRauTyG/1MaiG8Y26uGZfcKO7tw7XKgg1QLsyyrg4S92M75fJ26cUP+T7SdFdubNn5LaxAhk5fl6YyLaw3d/h5+fg35/cG6Vb2DRzdZqyqAuPLB0B9/sPHh8kALnDr6hf3J+DZfNh5WPw66lztGp7sMbt2OH98KXd0DPsTDpwQY19cqPCWTml/HS5cNbRbmDxuTtZRDkA0E+rn+dTNOkwuEMWxbDIMAbLW5vplpdYZzkw8X07xrc6CeQ9+4UgJcBCTpzr9lzHgETg7+PhX9fOtSlHwKT+nfG5jD5ae/hRuhh87IuMYfTOlrotuIWZ4gaeS1ctkghqhahQb6MCu/I8tqqnAd1hkvfhdkLoegwvDEZVjwI5cWN06nyYue6KG/fBq2LAmfh4tfWJDIz+hRG9G5d5Q6aK8Mw8LEYtPf1ItjHUIhqxlpdkErJLqJ3p8bfSeLrbaFHhwDt3GsB/rk8lj0Z+fzrkiF0aeda4cgRvTvQzs+71R9ibHeY7E1K4nUeg91L4ZzH4Lx/N0qJg9ZmelRX4jMLSTjZ/wmRM+Av62HYFfDLAnh5HCStcX+HvrkbsnbBRa81eDr2qW9iMQy4pxWXOxBxVasKUqUVdg7klRLeqWl2VvUJCyRRI1LN2g97Mnn752SuHhfOpAFdXG7H2+LFWf07syo2C0dte31buIQ9W3nXcT89SvfCJe/C+Nubd3HJZmRaVDfAeezQSfm3h5kL4KovnX9+93z44nYoOeKezmz7GLa+D2fMg1P/0KCmNiXn8NX2DG6Y0Jfu9ShcLNJWtKoglZbjHCJvihEpgIjQQJIOF2GarfcHa0uWlV/K/MXbiezWjnvd8Jv05MjOZBeVsy3dTT/smpvkn+n1+QUEGSUcuXQJDLrQ0z1qUbqG+DGsV/v6HWIcMQFu/gXG3eYMPi+Nhdi6LTfNKSrn001pfLIpjWU7MlgTf4jNKbkkx27B8eWd2Hqcjm3ifS5+Nk4Oh8kjX+6mazs/bppY/7WFIm1BqxqvTzpaabzpRqSCKKmwczC/9Ph6O+JxDofJ/30SQ0m5nRcuG4afteEHj048LQwvA1bGZtVr11+LsP1T+N8t5Hp14a7AB/hwwBme7lGLND2qK08uiyUtp5ieHev4C51PAEx5HAbNgi9ug48vg0EXwfSnneuqjuFwmKzdd5hFG9NYsfsgFb/b1uVPKUt9HiLHsHLuvj+T9eB3+Fm9CPK1EuRrIcjPm0Afb4L9vAn0db4FH30fVPnm99uft6bmsmN/Hv+ZHU2AT6v6cSHiNq3qX0ZKtnNEqqmCVN+jJRASDxUpSDUzr65J5Od92Tw1azD9Oge5pc32AT6M6N2BlbFZ3FXNIcctkmnCmn/Bqscxe4/nkpS5nBl5qqd71WJNj+rGk8tiWb7zINfXd3do9+Fww2rnAv8fn4bE1TD1HxA9h/15pXy6KY1PN6Wz/0gJ7QOsXDE2nFnDuxPib6WwzEZRmY3uP95F16T9/Dj6FW4IHk1RmZ3CsgoKy+xV1xSW2jhwpJSicufHhWU2ymw1HyY2tGd7LohWuQORmrSqIJWcXUT7ACshAU2zPb2qBMKhQsb3a2ZnarVhMWlHeHZFHOcN7sbsUa4XH6zOpAFd+OfyWA7mldI1xLWF682GrdxZLDJmIQyZw+6Rj5H+0sYTj4WROuvZMYBBp7Tjm50Z9Q9S4NxZN2E+RM7E8b9b8Vp6E9uXv8EteVewnzDO6BfKfecO4JyBXfD9/QFgWxdC0hKYcDdnTZrDWfW4bYXdQVGZjYJS23EBq6jMzsjwDip3IFKLVhWkUrKL6d1Eo1EAXdr5EuBjUQmEZqSgtILbP9pKl3Z+PDlrsNur8U6O7Mw/l8eyMjaLP41pBuenuarkCHxyhXO32MR74ax7+XVtEgBjIhSkGmJ6VFf+tSLe5bC9N7OARRvtfH7gr5xX8TX3sIiV/vdSdOb9dJg4DbyqmabO3O0smhp+Jpx1b73vabV40T7Ax62nP4i0Fa1qsXlydhHhTbTQHJx1PioXnEvz8ODSnaTnFvP8nKGE+Lt/ZPLUzkH06ODPythMt7fdZI6kwltTIeVXuPBlOPs+MAzWJWYTERrY8kfaPKxy9963u+qwe++oojIbizamctFLP3POf9bw7q/JjO4TyqQrH8Dv9g349BlPhx8fgLemQVbs8S8uK4RPr3LW+br4jeqDlog0mlYzIlVms3PgSAmzhvdo0vv2CQsiJi23Se8p1VuyJZ2lMQeYd85pjAxvnKKBhmEwaUBnPtmURmmF3S2L2JvU/s3w4Rywl8EVS5y7xnDWj1qflMOMId083MGWr1/nIE7tHMQ3OzO4alx4jdeZpsnWtCMs2pDGl9sPUFxup1/nIO4/N5KLhncnNMj3t4svXwzbP4Hl98CrZzqn/yqPmfl6nrOC+ZVLIbhrjfcTkcbRaoJUem4JDpMmHZEC55l7X20/0DJ/qLYiSYeLeHDpTkZHdOQvZ/dr1HtNGtCZ935N4dfEbM7u3/nkL2guYr+GxXMhKAyu/grCflswvycjn4JSm9ZHucn0qK68uGof2YVldDo2EOEsW7BkSzqLNqaxN6sQf6uF86Od6/mG9+pQ/XS0YUD0bOg7yRmmVj3hPGbmtKmwfRGcdR/0OatJPjcROV6rCVIp2c7ptaZcIwXOopym6Vyf1b+rjtDwhHKbg9s/2oq3xYvnZg9t9KMUxvbphL/Vwso9WS0nSK172XlobvfhcNnHJ2yrrzxfT0HKPaZFdWPByn2s2J3JZaN7YT9atuCTY8oWDO3ZnqdmDWZG9CkE+dbxv+KgMOdxL4Mvga/mwdp/Q8RE5wiViHhEqwlSyYcrSx809YiUc+de0uFCBammUl4M61+B4VdCYCjProhjx/48XvnzCE5pgsrLflYLZ5waysrYLB41TbcvaHcrh90ZoDa8CpHnO48L8Tnx38i6xGz6hAa6fISOHC+yWzC9OwWwZEs6B/NKWbz5+LIFs0f1bNj/F/2nQ+9xsG0RRF2sdVEiHtRqglRKdhHBvt50DGzaXScRYc4RMO3ca0LbP4YfHoH4b/lp3Ju8uiaRP4/txbSoplsfMmlAZ77bnUlcZgEDurZrsvvWS1khfDYX4pfD6bc6z83zOnF/yW/ro07xQCdbJ8MwmBbVlVd/TGRTSm7tZQtc5RcCY25wT1si4rJWE6SSs4vpHRrQ5KMDQb7edGnnqzP3mtLOJc4fImnryP3kVk7rfCcPnDewSbtQOaW3MjareQapwkOw8GI4uAPO/ReMvr7GS3cfqFwf1TgL9NuqGyf0pVs7PyZHdql7lXMRaXFaTfmDlOyiJl8fValPaBCJh09y4ru4R0EmpPyMOeoGPg+5kpnmKj4YuKHJF/p3DfEjqns7Vu7JatL71tl3D8KhOOd6qFpCFGh9VGPpGOjD1eMjFKJEWrlWEaQq7A7Sc0uafH1UpT5hgSQe0uHFTWLPF2A6+Kx8DP+XOZXkrlPpvO5JiPumybsyaUAXtqTmklNU3uT3rtXhfc6dXKOuc+7qOgmtjxIRcV2rCFIHjpRgc5geG5GKCA0kr6SC3OIKj9y/Tdm5hPKO/blvbQVTBnal97VvwylD4bPrIHNXk3Zl0oDOOEz4Mb6ZjUqteQYsvs46Qydhd5hsSMphjEajRERc0iqCVHITH1b8e32POXNPGlH+AUj9lQ2BE3GY8PiFURg+gTDnI2dV5w/nONcGNZEh3UMIDfLhh+Y0vXd4L+z4BEZf59wqfxK7D+RTUKb1USIirmoVQaqyhpQnp/YALThvbLuWAib/zRrC+H6hdK6cimrXDeZ8CEWHYNGfwVbWJN3x8jI4u39n1sQfosLuaJJ7ntSaz93pMwAAIABJREFUZ8DbD8bdUafLK9dHna4RKRERl7SKIJV8uBh/q4WwYN+TX9wIenQIwMfiRYIWnDeuXUso7hDJr3kduWjY77bqdx8OF74EaevgyzuhidarTY7sTH6pjc0pzeCYoMN7YcenzrVRdRiNgqPro8ICfwulIiJSL60iSDl37DV96YNKFi+D3p0CNCLVmI6kQvpGfvKdgL/VwpSB1dSMiprlPCpj24fwy4Im6dYZp4ZhtRisjG0G03s/Pn10NOr2Ol1euT5Ku/VERFzXKoJUcnaRx9ZHVYoIDSTpsIJUo9m1FIAFmYM5Z2AXAms6UmPiPTDoIvju702yky/I15sxEZ34YU9mo9+rVofiYediZ6mDOo5G7TqQd3R9lIKUiIirWnyQsjtM0nJK6B3q2VotfcKCSMkuwtZc1sq0NruWkNchil0lHbloWPearzMMuOClJt3JN2lAZxIOFVWt1fOINU+Dt3+dR6PgmPpREVpoLiLiqhYfpDLySii3Ozw+ItUnLJAKu0l6bolH+9Eq5STCga2stIynY6APZ5waWvv1PgFNupNvcuRvVc494lAc7Dg6GhV4kq/NMdYl5mh9lIhIA7X4IJVytPRB78ode6V5kBXb5P3oW7lzTwvO3W/X5wAsOBjFjCHdsFrq8G3bhDv5encKpG9YoOeC1I9PgzWgXqNRNruDjVofJSLSYC0+SCVXlT44OiL13d/htYlQnNOk/YgIrawlpXVSbrfzc7LbR5Nk68SFtU3r/V4T7uSbNKAz6xKzKSyzNdo9qpUVCzs/cx5eG1j3ULQ7I1/ro0RE3KDFB6mU7GL+v707D2/rOu88/j0ACC4AF5EAKUpcQS2UbGu3JXmJLdmO7XhNnEyWxkkmW9Mm7qTTTJNpMn3SzrRx0qYzmWYymTRp02ZPbSWWZEmxLdnyEluJV+3USlKyVpJaSELcgDt/XFCmKHEDAV4sv8/z8KEE3HtwZMlXr97znvd4PS6mF+VBNGIfITLQY28Dn0KlPi8lBTkcUsF5YrXth5M72GCtpLasgMXVJRO7f4p28q1urKA/YvHC/rakfcYVPfcN8Ppg5cMTuu3t8/VUHyUiMhlpH0g1t3VTW1qAy2Wg5bcQbre3gL/2oynrJTQoFPCpu3mi7foVFobvnLqa+xfOiK/FxdCdfHs3JH6OwLK6aRTmediydwp3753aCzvXwHUTy0aBXR/VEPRRXqj6KBGRyUj7QKqlPfz2GXt71tlB1Kq/gJM74PgbUzqXUNCvpb1E27mGEyWLOG6Vcv9ElvWGGrqTb82nkrKTL8ft4uY5QbbsPU00OkUB/Nav29mo6yeWjVJ9lIhI4qR1IBWNWrR0dNtHw0SjdiA16zZY8tG3s1JTKBT0caqzl84eHV6cEKf2wOk9PN53HQuqii+eaRiXKdjJd+u8ctq6etnx1rmEj32ZU3vsIvzlfwgFE1ue23VM9VEiIomS1oHUqc5eevqj1AZ88Nar0HkM5t0L+SUw7z57S3j/1LUjCAXszFhzW3jKPjOj7VyDZVz8oGMh9y+KMxs1VJJ38t08pxxjYPNU7N7b+nXw+mHl5yZ862B91HLVR4mITFpaB1LNQw8r3rMWXDkw5077zSUPQe852L12yuYTimVM1AIhASwLdq3hSOFi2k0J9y6sTMy4SdzJV+rzsqRmGs8kO5A6udvu9B5HNgrsQEr1USIiiZHWgdRgJ+m60lggFbrZzkYB1N4I0+rg9alb3qstK8Bl4KDqpCbv5E5oP8AvLlzLDbMCif1LP4k7+VY3lrPjrXOcPN+T0HEvcTEb9dkJ3zoQifL75jNa1hMRSZC0DqSa28PkuA2VPQfgTLO9rDfI5YLFH4bm5+3O2FMg1+OmalqBdu4lws41WMbNTzsX8UAilvWGS9JOvsEu50nLSp3cDbvjz0btOnaeLtVHiYgkTFoHUi3t3VRPK8DTtB6MCxrvufSChR+yX3/9J1M2p1DQp517kxVb1jvgX8qFnBLuuHp64j9j+E6+EzsTMuzcikJmFOclr05q6yPgLYwrGwVD+0cpkBIRSYS0DqSa28L20TB71kLtDZefM1Y8ExpuhTd+ajfrnAL1AR+H27qxpriHVUY59jqcaeanXUu4ff50/Lme5HzO0J18P0vMTj5jDKvnlfPigTZ6+hP8Z+7kLtj9OKz4TFzZKLADqVnlfoKFuYmdm4hIlkrbQMqyLFrau1nqOw2n9166rDfUkofs3XwHNk/JvEJBPxf6I5xIZo1Mptu1hqjxsObCEh5YNCO5n3VxJ19bwnby3dpYQbgvwrbDCT6m6NlHILcIVvxxXLe/XR+l3XoiIomStoFUW1cf3X0Rru97yX5h+LLeoDl3QUEAXv+3KZlXQ6wFgpb34mRZsOvX7C5YiqtgGu+YE0z+Z16yk+8/TXon38qGMvJyXGzZk8Au5yd22pnX5fFno3aqPkpEJOHSNpAa3LE3u+MZmLnMXsa7Eo8XFn4AmjbaWYcku9gCQQXn8Tn6Cpw7wo86l3LPghnkuKfoj+jFnXw/gxe/Namh8nLc3NAQYPPeU4lb4t0ay0atjC8bBUP6R9UrkBIRSZS0DaSa28NUmdMUduyE+feNfvHihyA6AG/+POnzqijKpcDr1uHF8dq1hogrhw19S3hgcZKX9YYb3Mn39FcnvZNv9bxyjp65wP5TCQioT+ywu/av+CPInxb3MKqPEhFJvLQNpFrau7nL/Xv7JyPVRw0qb4Sqa+2eUkkuAjfGUB/Qzr24RKOw69e8kbuMktIyltTEHzTEZfhOvuNvxj3U6ka7DcKWROzee/YRyC2OuzYKhp6vp/ooEZFESttAqrk9zL3eV6HiGigNjX3D4g/bRelHX0n63EJBv7qbx+PIy9B5jB+dX8IDi2ZijJn6OQzu5Msrhh/eA4e2xjVMZXE+8yuL2LJnkoHU8e2wd30sG1US9zA7j52nuy+i+igRkQRL20Dq/OkjXB3dO/ay3qCr3gM5BVNSdB4K+Dh65kLit79nup1rGHDl8lRkSWLO1otXUSV84kkomgk/fhC2/3tcw9w6r5xXWjo4G+6Lfy5bvx7LRv1R/GOg/lEiIsmSloGUZVnM6tiKC2vsZb1BeUV2/cvONdCb3GxRKOjDsqClXYcXj1s0ArsfZ5tnGaGZ05lV7nd2PsVV8PFNULMC1nwSXvifE14WXtVYTtSCrfvi7E81mI1a+ceTykaBHUjNLvcT8Ks+SkQkkdIykDob7mdV5CXOFtRBsHH8Ny5+CPq67KaGSRQK2EHAYS3vjV/Li9B9ip90LeX+ZPeOGq/8EvjwY3D1g3YB+oYvTKix68KqEsp83vjrpLZ+3V5iXP6Z+O6Pebs+StkoEZFES8tAqvWto6xw7eFM7Z12gfB41ayAstlJP8i4Pmj3ktLhxROwcw19rnyetRZz38IUCaQAPLnwnu/D9X8Cv/8+/OIh6BtfptHtMtwyt5xnm04zEIlO7HOPvxmrjfrspLNRO946p/ooEZEkSctAamD3E3hMFM9V90/sRmPsovPWl6Btf3ImB/hzPVQU5Wrn3nhFBrD2rOU5s4yls2ZSXpTn9Iwu5XLBO/873PUNaNoA/3YfdLeP69Zb55Vz7kI/r7WendhnPhvLRq2YXDYK4OVDdof15dqxJyKScGkZSE1r2cRRK0D53OsmfvPCD4JxJz0rFQpo5964Hd6KCbfz7xeWOVtkPpblfwjv/5Hd1+kHt0PHoTFvuXF2AI/LsHnvBLqcH3sDmp6AlZ+zg6lJUn2UiEjypF8g1XOemrPbeMGzktycOA6zLayAOXfAGz+DSH/i5xcTCtq9pHR48TjsWkOPq4DfuhZzx1UVTs9mdPPuhY+shQsd8P3b4a1XR728KC+H6+pLJ9YG4WJt1B9OcrLQH4nySrPqo0REkiX9Aqn9T+Kx+mkqXRX/GIsfgu5TsP/JxM1rmPqAj3MX+jkTTl6wlhEG+rD2rGOztYyb51dTmJfj9IzGVrMcPvEUeH12r6mmTaNevrqxnP2nujjSMY7aqmOv28uHKx9OSDZqZ6w+amWDAikRkWRIv0Bq9+OcpoS+ymXxjzH7neCvgNd/nLh5DdOgM/fG59CzmJ5zPNZ7HQ+k8rLecIHZ8MmnITAHfv5BeOWfR7z01nl2lm1cu/ee/TrklSQkGwVv10ddV6/6KBGRZEivQKovjHXgaTYNLKM2MIk+Q26PXSu17zfQeSJx8xsiFNu5p4LzMexaQ9jlY3vuEt4xJ+j0bCbGXw4fewJm3Qbr/xQ2//cr9pqqD/gIBXxsHiuQeus12LcRrv+c3fcsAV4+1M6cCtVHiYgkS3oFUgc3Y/rDbIxeR22Zb3JjLX4IrAi8+bPEzG2YqmkFeN0uDqrgfGT9PVh717NpYBl3LqzB60mvP44A5PrtI2WWfBSe/3v49R/BwOWdzFc1lvPywXa6ewdGHmvr1+1Dia9LTDZK9VEiIsmXXn9z7VlHX04xv4s2UjfZQCowC2pW2st7SSgId7sMtWUFHFZGamQHN2N6O3l8YEV6LesN5/bAvd+CVV+xA/Ofvg96zl9yya2N5fRForx4oO3KY7z1KuzbFNupl5hslPpHiYgkX/oEUgN90LSJA6XvYAAPNaUFkx9z8UPQfsDuK5UE9QEfh9oUSI1o5xo6XUU0Fy1jae00p2czOcbAzf8F7v8ONL8A/3IXnD928e1ldaUU5npGrpN6djAb9emETWnwfD3VR4mIJE/6BFKHt0LvOX7rvZHpRXnke92TH/OqB8BbCK8lp6dUKOinpb174l2ts0FfmGjTBtb3L+XexbWYiXSoT2WL/wA+9As402y3Rzi1BwCvx8U75gTZsvcU0eiwDOhbr8L+38D1DycsGwV2obnqo0REkit9Aqk9a8FbyNO9jdSWJSAbBfb29avfA7t/fdlSTCKEgj76IxZHz1xI+Nhp78BTuPrDrIus5IHFKXQkTCLMug3+4waI9sMP7oDDzwN2ndSpzl52HRv2Z+3ZRyC/NKHZKNVHiYhMjfQIpCIDsPcJmHMHBzoGJl8fNdSSj0B/GHatSdyYMQ2DO/dUcH65nWs4a0rorFjOrPJCp2eTeJUL7fYIhdPhx++BHY9yy9wgxnBpl/Ojr9r9zK5/GHIT999h+9GzhPsirFQgJSKSVOkRSLW+BOF2Lsy+m7auXmoDCcpIAcxcCsF5SVneqw8M9pJSndQleruI7tvEuv5l3L+kxunZJE9JDXx8E8xcBo99gsCb/49FVcU8M7RO6tmvxbJRn5rUR1mWxZ7j5/nu1oN88Hsv84HvvYzX41J9lIhIksVxxooD9qwFTz6HS1YCryU2IzV4kPGTX7brWcrnJWzoUp+XkoIcFZwPt28TroEenoiu5FsLM2xZb7iCUnjoV/CrP4Sn/htfnfF+3n3oXk519lB+bicceApu+2pc2aiz4T5eONDG1qbTbN13mlOdvQDMqyziEzeGuGdBJWWqjxIRSarUD6SiUdizDmbdSnOstCRhNVKDFn4Anv6qnZW6828TOnQo4FN382GsXWtoN9Pw1K+koijP6ekkX04evPdf4KkqFr70bb6Tc4jndzXy4IGvQUEZXDu+bFQkarHjrXOxwOkUbxw5S9SC4vwcbpod4OY5Qd4xJ5gd/01FRFJE6gdSb70Kncdh3n00t9uZnUk34xzOF4C5d8H2n9vZAY83YUOHgn6e23c6YeOlvZ7zWPufYl3/Ku5fnMHLesO5XHDH32AVzeCdv/kyxze/F/qb4ba/spt6juBUZw/P7Wtj677TPL//NGfD/RgDC6tKeHj1bG6eG2RhVQluV4bsehQRSTOpH0jteRxcOTDnDlqeaCXgz8Wfm4RpL/mIvYTYtMFui5AgoaCPR189SmdPf3ocyJtsTRtxRfr4DdfzT1dPd3o2U86s/Cw/2xvhwea/xvKVYa795CXv90eivNpyhq37TrO16TS7j9tp2IA/l1sbK7h5bpCbZgWY5ktcsC8iIvFL7UDKsuxlvdDNkF9Cc/se6hK9rDeoYTUUzbQ7nScykArY2bPmtjDXVBUnbNx0Fd35GCcJEGi8MWsDy4oV7+eefbk8cvd8lub6OdIR5rn9duD024PtdPUO4HEZltZO48/vnMvNc4LMm16ES1knEZGUk9qB1IkddmPDG/8zAC3tYW6YFUjOZ7ncsOhD8Pw34dxbUJyYI0tCwdjOvbYuBVIXzsDBLawfuJ37l1Q7PRvHXN8QoNVdw397CXqff5aDsV2dM0vyuW/RDG6eE+T6hrKsDTRFRNJJagdSe9aCcUHj3Vzoi3DifE/yMlIAi/4Anvs7eOOn9nEfCVBbVoDLcPEvy6y29wlc0X625tzIR+cEnZ6NY/K9bm6fX8FTu0+yPFTGh5bXcvOcIA1BX+Z0eBcRyRIpHkitg9obwBeg9UQnALWBBBeaD1VaD3U3wes/gpv+zC4QnqRcj5uqaQXauQcMbH+M41Y5NQtuwutJjxZmyfKtDyxmIBol15OAo45ERMQxqfu32el9cHovzLsP4OKOvaRmpMAuOj/bAs3PJ2zIUNDH4WzvJdXdjqt5K+sjy3n3kiqnZ+M4t8soiBKZAsYYLMsa+0KROKVuILVnrf193j0AtAy2PihNYkYKYN69kFtsZ6USpD5gB1JZ/T/z3nW4rAjbCm5hac00p2cjIlmitLSUaFQHx0vypHYgVXUtFNmdr5vbw0wryKG4IMkFuDn5sOB9sHutXRydAKGgn3Csxitb9b35KIej05m/+AbtPhORKRMIBJSVkqRKzUDqTDMcf/Pish7YGamEN+IcyeKHINILOx5NyHANsbqurD1zr+sUntYXWR9doWU9EZlSXq+XsrIyLly44PRUJEOlZiC1Z739fd69F19qbgsnvz5qUOVCqLgmYct7F1sgZGvB+e7HcRFlT+ltzK6Y+JlyIiKTUVNTQ19fn9PTkAyVooHUWph+jb2LDugdiHDs3IWpy0gZA0sesrNix7dPeriKolwKvO6sPbz4whuPsj86k0VLVzo9FRHJQoGA3X9Qy3uSDKkXSHWegCPbLlnWO9JxAcuCusAUZaQArnkfuHMTkpUyxlAf8GXn0t754+Qd28b66AruW6RlPRGZegUFBRQXF9Pb2+v0VCQDpV4gtWed/X1YfRQk4bDi0RSU2jsGt/8S+idfJB4K+jnUln1Le9auX2GweGvGnUwvznN6OiKSpWpqahRISVJMKpAyxvydMWavMWa7MeZXxpiSSc9oz1oIzIHyxosvNbeHAaibykAK7KLznrOwd/2khwoFfBw9c4Ge/kgCJpY+ul9/lD3RGq67Vst6IuKc8vJyLMvS8p4k3GQzUk8BV1uWtQDYB/zXSY3W3Q7NL15SZA52Rqowz8O0ZLc+GK7+ZiipScjyXijow7Ls8wKzxrmj+E+9ykZrJXdeM93p2YhIFvP7/RQUFNDf3+/0VCTDTCqQsizrScuyBmI/fRmYXBFM0wawIpcs64Gdkaorc+AcMpcLFn0YDj0LZ1omNVQoYO/cO5xFy3uRHWsAOBe6hyIdwCsiDjLGUF1drTYIknCJrJH6OLBxpDeNMZ82xrxijHnl9OnTV75ozzo7A1S58JKX7R5SU1hoPtSiDwEG3vjJpIapD9rLktl0eHH3a//Ojmgd1193ndNTERFh+vTpWtqThBszkDLGPG2M2XmFr/uHXPNlYAAYMdqwLOt7lmUtsyxrWTAYvPyCnvNw6Bk7GzUk89QfiXL0zIWpr48aVFINDavg9Z9ANP76Jn+uh4qi3OzZuddxmKKO7TztuoFb5l7h91tEZIoVFxfj9XoZGBgY+2KRcRozkLIs6zbLsq6+wtfjAMaYjwL3AH9gTSbU3/cbiPRdtqz31pkLRKKWcxkpsIvOzx+1A71JCAWyZ+de3/bH7O+ND+hwXhFJCS6Xi6qqKsLhLKpVlaSb7K69O4EvAvdZljW5P5l71oJ/un2+3hDNsdYHdQGHMlIAjXdDfim8/uNJDRMK2ocXZ4Pw64/yRrSBW65b6vRUREQuqqys1PKeJNRka6S+DRQCTxlj3jDGfDeuUfrCcOBpu2+T69IpDe5yczQj5cmFBe+HvU9AuCPuYeoDPs6G++nozvCjCtoPUnJuD8/l3MS1daVOz0ZE5KLS0lJcLhfRaNTpqUiGmOyuvVmWZVVblrUo9vWZuAY6uBn6w5e1PQA7I+Xzugn6cycz1clb8pC99Lj9F3EP0ZAlZ+51v24f9uxZ8B5crineaSkiMgq3201lZaWW9yRhUqOz+e619tJZ7Y2XvdXSHqbWidYHw1VcBTMWw2s/gjjTwqHYzr1MLzi/sGMtb0QbuHX5EqenIiJymZkzZ6rgXBLG+UBqoBf2bYLGd4Hbc9nbze3dU3vG3mgWPwSndsGx1+K6vWpaAV63i4OZXHB+/jiBczv5fe4K5k4vdHo2IiKXKSsrwxijWilJCOcDqcPPQe/5y3brAQxEohzpCE/tGXujuea94Mm3s1JxcLsMtWUFHM7gjFS0aRMAnbXvdHgmIiJX5vV6CQaDas4pCeF8ILX7ccgtgtAtl711/FwP/RGLOicLzYfKK4b598POx+wC+TjUB3wcyuCde9071tEaDVI/X7v1RCR1VVVV0deX4Rt/ZEo4G0hFBuxjYebcYe+MG2aw9UHKZKQAFn3QzqAd3BLX7aGgn5b2bgYiGbhjpK+b/KPP83R0KctDAadnIyIyosHG0Frek8lyNpBq/S2E26+4Ww/sM/YA57qaX0nN9ZDji7s5Zyjooz9icfRMBqaUD27BE+1ju/96ZpTkOz0bEZER5efnU1JSQm9vr9NTkTTnbCC1e61dczTrtiu+3dLWTV6Oi/JCh1sfDOXxQt2NcWekGgZ37mVgwbm1dwPn8ZHfcJPTUxERGVNNTQ09PT1OT0PSnHOBVDQKe9fDrFvBe+WMU3N7mNpSX+r1ImpYDR2H4EzzhG+tDwz2ksqwOqlohEjTJrZEFnJtQ7nTsxERGZOW9yQRnAuk3noFOo/bxdsjaGnvdraj+UgaVtvfD058ea/U56WkICfzCs6P/h5PTwdPR5ayPFTm9GxERMbk9/spKCigv7/f6alIGnMukNqzFlw5dqH5FUSjFi0dYWfP2BtJYDYUzYy/4Dzgy7zu5nufYAAPB4tXMFP1USKSBowx1NTUqA2CTIpzgdTutXbLg7ziK7594nwPfQPR1MxIGQMNq+DwVohGJnx7KOjPuKU9q2kjv2c+1zRUOz0VEZFxq6iocHoKkuacCaT6L8DZFph/eRPOQYOtD1Jqx95QoVXQcw6OvT7xW4M+TnX20tWbIUcUtO3HtO9nY/9iVmhZT0TSSElJCTk5OToyRuLmTCDVcxaMC+a+a8RLWmKtD1IyIwV2IIWJa3kvFFuuzJgO500bAdgcWaL6KBFJK8YYqqqqdIixxM2ZQOrCWai9AXwjN21sbu/G63ZRWZyi9Ta+MqhcGFfBeSgY27mXKS0QmjZwxNuAu7RW9VEiknYqKyu1c0/i5kwgNdAz6m49gJa2MNWl+bhTrfXBUA2r4OjvoOf8hG6rLSvAZeBgJmSkutuwjmzjib7FrAiVOj0bEZEJKy0txeVyEYlMvOZVxLli88a7R327ub07deujBjWshugANL8wodtyPW6qphVkxs69/U9irCjrexepPkpE0pLb7aayslK79yQuzgRSXh8UzRjxbcuyaGkPp9YZe1dSvRxyCuI6LiYU9HE4E3pJNW2gOzfITqte9VEikraqqqpUcC5xcSaQKqwc9e3Tnb1c6I9QF0jRQvNBnly71iuOgvP6gB1IpfW6fH8PHNjC770rqCn1qT5KRNJWWVkZxhii0Qw8UF6SyplAKrdw1LebL+7YS/GMFNjLe+0H4GzrhG4LBf2E+yKcOJ/G5zwdfg76u/lF5zWqjxKRtJaTk0MwGNTZezJhzh5aPIK3e0ileEYK7IJzmPDuvYZYC4S0bszZtIFIjo/NPXNVHyUiaa+6upq+vj6npyFpJiUDqZb2bjwukx5LRcFGe6lygst7F1sgpGvBeTQK+zbROm0lfeSoPkpE0l4gYLfkSeuSC5lyKRlINbeHqZqWj8edktO7lDH28t4Ej4upKMqlwOtO38OLj78Oncd5xlpKTWlBegS9IiKjyM/PZ9q0afT29jo9FUkjKRmptLR3p0d91KDQKrhwBo6/Me5bjDHUB3zpu7TXtBHLuPjh6bmqjxKRjFFdXa06KZmQlAukLMuipS2cHvVRg0K32N/jWN5L2+7mTRsJT7+W1p481UeJSMYoLy8HtLwn45dygVRHdx+dvQPplZHyB2H6Ajj47IRuCwV8HD1zgZ7+NOume6YFTu5kl/8GANVHiUjG8Pl8+Hw++vv7nZ6KpImUC6QGWx+kfA+p4RpWwZFt0Ns57ltCQR+WBa0daXZYZuyQ4rU9C1UfJSIZxRhDTU2NupzLuKVcINUSa32QVhkpiB0X0w/NL477llAgTXfuNW3ACsxl/VsFqo8SkYxTUVHh9BQkjaRcINXcHsZloGpammU5qleAJ29Cx8XUB+1gMa0OL75wFlpepL3qVs6G+1UfJSIZp7i4GK/XqyNjZFxSLpBqae9mRkk+uR6301OZmJy8CR8X48/1UFGUm1479w48DdEBtuVcB6g+SkQyjzGGqqoqwuE0K7sQR6RcINXcHqYu3Zb1BjWshrZ9cO7ouG8JBdJs517TBigIsK59huqjRCRjVVZWaueejEvKBVJ2D6k0KzQfFMdxMaGgfXhxWhjog/1PY825k5ebz6k+SkQy1rRp03C73UQiabarWqZcSgVSZ8N9nA33p29Gqnw++CsmtLxXH/BxNtxPR3canO/U+lvoPcfRiltUHyUiGc3tdjNjxgzt3pMxpVQg1RJrfZC2GanB42IOPWufRTcODel05l7TRvDk8Wz/VYDqo0Qks82YMUMF5zKmlAqkmmOtD+oCaZqRgtji7EzmAAAYsElEQVRxMR1w4s3xXR7buZfyBeeWBXs3QOgWXmgJqz5KRDJeWVkZxhii4/yHsWSnlAqkBjNSNaVpmpGCCR8XUzWtgBy34WCqF5yf3AXnWonOeRfbDneoPkpEMl5OTg7l5eU6e09GlVKBVHN7N5XFeeTlpFnrg6EKK6Di6nEXnLtdhtoyH4dTPSMV62Z+YNoNnA33s7xey3oikvmqqqro60uDGlZxTEoFUi3t4fStjxqqYRW0vgx94wuOQgEfh1J9517TBpi5jBdP2EHucmWkRCQLBINBQIcYy8hSLJDqTt8de0MNHhfT8ttxXR4K+mlp72YgkqLr8OePw7HXYO5dvHyonerSfKqmZUDAKyIyhry8PEpLS+nt7XV6KpKiUiaQ6uzpp62rL/3O2LuSmpXgzh13nVQo6KM/YnH0TIpus91nL+tdrI/Ssp6IZJHq6moFUjKilAmkBgvN6zJhaS8nH2qvH3cg1RDbuZeyjTmbNsK0OpqiM9U/SkSyTjAYxLIsLe/JFaVcIJURGSmwl/dO74Xzx8a8tD5g95I6mIq9pHq74NBWmPsuXj7cAag+SkSyi8/nw+/309/f7/RUJAWlTCA12EMqI4rNYULHxZT6vJQU5KRmwfnBLRDpVX2UiGQtYwzV1dXqci5XlDKBVEt7N8HCXHy5HqenkhjlV4GvfPx1UgFfanY3b9oIeSVEq1aoPkpEslZFRYXTU5AUlTKBVHN7ODPqowa5XHZWapzHxYSC/tTrbh6NwL5NMPudNLX1qD5KRLJWcXExXq9Xy3tymdQJpNq6M6c+alBoFYTb4OSOsS8N+jjV2UtXbwqd63Tkd/ZxN7FlPVB9lIhkJ2MMNTU1hMNhp6ciKSYlAqlw3wCnOnupT+cz9q7kYp3U2Mt7odivPaU6nDc9Aa4cmHWb6qNEJOtNnz5dO/fkMikRSL29Yy/D/pIunA7l88dVcB4K2jv3DqXSmXtNG6H+JqLeQtVHiUjWKykpwePxEIlEnJ6KpJAUCaTsLExGdDUfrmE1tL4EfaOng2vLCnAZOJgqGam2/dB+AOa+i6aTnaqPEpGs53a7mTFjhpb35BIpEUg1xzJSNZmWkQJ7eS/SB62jHxeT63FTNa0gdXbuNW2wv8+5U/VRIiIxM2fOVEZKLpESgVRLezdlPi9FeTlOTyXxaq4Ht3ecy3u+1OluvncDTL8GSqpVHyUiElNaWooxhug4dmNLdkiJQKq5LZx59VGDvAX22XvjKDivD9iBlOPFjN1tcGQbzL2baNRSfZSISExOTg4VFRVqzikXpUQg1dLenZn1UYMaVsOp3dB5YtTLQkE/4b4IJ873TNHERrDvN4AFc+9SfZSIyDBVVVXqJyUXOR5I9fRHOHauJ/N6SA01zuNiGmItEBxvzNm0AQpnQOVC1UeJiAwTCAQAnF89kJTgeCB1pMMuNK8LZOjSHkDFNVAQGHN57+0WCA4GUv099jzn3gXGqD5KRGSYvLw8SktL6elxePVAUoLjgVTzxR5SGZyRcrkgdMuYx8VUFOVS4HU7u3Pv8FboD0Pju1QfJSIygurqanp7e52ehqQAxwOpt3tIZXjGo2E1dJ+CU7tGvMQYQ33A5+zSXtMG8Pqh7ibVR4mIjKC8vBzQ8p6kQCDV3N5NcX4OJQVep6eSXOOskwoF/c51N49GoWkTzLoVPLmqjxIRGUFBQQGFhYX09fU5PRVxmOOBVEt7OPOzUQBFMyDYOHadVMDH0TMX6Ol3oOHb8deh6wTMfReA6qNEREZgjKG6ulp1UuJ8INXc3p3Z9VFDNayGlt9C/8j9R0JBH5YFrR0OHEGwdwMYN8x+p+qjRETGUFFRoaU9cTaQ6huI8taZC9mRkQI7kIr02mfvjSAUiO3cc6LgvGmj3Ty0oFT1USIiYygqKiIvL089pbKco4HU0TNholaG79gbqnbwuJiRl/fqgz5cBl480D6FEwPONNuF8HPvAlB9lIjIGAaX93SIcXZzNJBqac+CHlJDeX1QvXzUgnN/rocPXlfDT7a18HrrmambW9Mm+/uQQEr1USIio5s5cyaWZensvSzmaCDVHGt9kDUZKbB3753cCZ0nR7zkS3c1UlGUxxcf207vwBQVnTc9YRfDlzUQjVr8TvVRIiJjKikpIRQKcf78eaenIg5xPCPlz/VQ5svw1gdDNay2vx96dsRLCvNy+Jt3X82+k11855mDyZ/ThTPQ/OLFbNS+U52cCfezXPVRIiJjamxsxOv1qhVClnI8I1VbVoAxxslpTK3pCyG/dMw2CKsbK3hg0Qz+zzMH2Hsiyf/SObAZrMjbbQ8Oxuqj6lUfJSIyFq/Xy6JFi+ju7tYuvizkeEaqLpuW9WDIcTHPwBj/w/3lvVdRnJ/Dnz+6nYFIEtffmzaALwgzlwLw8qEOqqblU12q+igRkfGorKxk+vTpdHU5eMSXOMKxQGogEuVIR5jabGl9MFTDaug6Cad2j3pZqc/LV++7iu1Hz/EvLzYnZy4DfbD/KZhzB7jcsf5R7Wp7ICIyAcYYFixYQDQaZWBgwOnpyBRyLJA6draHgaiVfRkpGPdxMQD3LKjk9vkV/P2TTTS3JeEMvpYXofc8zL0beLs+SoGUiMjE+Hw+rrrqKjo7O52eikwhxwKpt3fsZWFGqrgKAnPGrJMC+185/+OBq/F6XHzxse1Eowlef2/aCJ48e7kR1UeJiExGfX09RUVF6i2VRRwLpFpigVRdIAszUhA7LuZF6B/7nKaKojy+/K55bDvcwc9+35q4OViWHUiFVoHXDmhVHyUiEj+3283ixYvp7e1Vb6ks4WBGKkxejovywlynpuCs0CoY6IEjL4/r8vdfW831DWV8bcNejp8b+ay+CTm5E861Xmx7oPooEZHJKy0tJRQKaYkvSziakaor82VX64Oh6m4EV864lvfAXuJ75D0LiEQtvvyrnYnZYtu0ETCX9Y9SICUiMjnz5s0jJydHvaWygKMZqaysjxqU648dFzO+QAqgpqyAL9wxly17T7H2zWOTn0PTBqhaBv5yQPVRIiKJ4vV6WbhwoXpLZQHHAqnWbOwhNVzDLXBiB3SdHvctH7u+jsU1JXx17S7aunrj/+zzx+DY6xezUaD6KBGRRJoxYwYVFRXqLZXhHAmk+iNR+iLR7Dpj70rGcVzMcG6X4RsPLqC7N8JfrRu9D9Womjba32PdzFUfJSKSWEN7S0UiU3Ruqkw5RwKp3gF7J0NdNi/tAVQugvxpdpfzCZhdUcjnVs9i3ZvHeGr3yIcfj6ppI0yrtw8qRvVRIiLJ4Pf7mT9/vg41zmCOBFJ9sUCqNltbHwxyuaH+ZrtOaoJr6J+5uYHG6YV85dc7OHehf2Kf29sFh7fa2ahYsb/qo0REkiMUClFYWMiFCwnacS0pJSGBlDHmC8YYyxgTGM/1fQNRvB4XlUV5ifj49NawGjqPw+m9E7rN63Hxjfcu4HRnL49s3DOxzzy4BSJ9qo8SEZkCg72lenp61FsqA006kDLGVAO3A+PuFNk7EKWmtACXK0tbHww1geNihltQVcKnbgrxs98d4bcH2sZ3U28nvPpDyCuBmpWA6qNERJKtrKyM+vp69ZbKQInISP1P4M+Bca9N9Q1EVR81qKQGymZNqA3CUH96+xzqygr40podhPtGOSjTsmDHo/Dta+HgZrjhT8DtAVQfJSIyFebNm4fH41FvqQwzqUDKGHMf8JZlWW+O49pPG2NeMca80jsQ0Y69oRpWQ/MLMDDxdgZ5OW6+/uACWjvCfPPJfVe+6OQu+OHd8NgnwF8Bn3gabvqzi2+rPkpEJPlyc3PVWyoDjRlIGWOeNsbsvMLX/cCXgb8czwdZlvU9y7KWWZa1zEI79i4RWgUDF+DItrhuXx4q48MravjnFw/zWuuZt9+4cBY2fgm+exOc2g33/C/41BaovvaS+1UfJSIyNWbOnKneUhlmzEDKsqzbLMu6evgXcAioB940xjQDVcBrxpjp4/lgZaSGqLsRXJ64l/cAvnhnI9OL8vjio9vp7e+H138C314G274LSz8GD78Gy/6jvVNwCNVHiYhMHfWWyjxxL+1ZlrXDsqxyy7LqLMuqA44CSyzLOjGe+7O+q/lQeUVQdd2kAqnCvBz+9t3X4D29g/b/vQoe/2O7T9Snn4V7/gEKrrxsp/ooEZGp5ff7mTdvngrPM4QjfaQMMKNErQ8u0bAKjm+H7nHuvhsu3MGqA19jXe5X8J5v4dgt/wAf/w3MWDTqbaqPEhGZeg0NDfj9fvWWygAJC6RimalxRQE5Hhcet2PH/KWmhtWANaHjYgCIRuCVf4Z/XAKv/it9Sz/Ng+5/5DM75zIwjlpG1UeJiEw99ZbKHI5EM7kKoi43YzHkFU/suJgjv4N/WgXr/xTKr4LPvEDevd/gvzxwHduPnuOfXzw86u2qjxIRcU5ZWRl1dXVa4ktzjkQ0FepofrmLx8U8M/ZxMV2n4defhR/cDl2n4MEfwMfWQ8V8AO6+ppLb51fwzSf3cbite8RhVB8lIuKs+fPnq7dUmnMkkMr3use+KBs1rIbzb0HbCP2gIgPw8nfhH5fC9l/ADZ+Hz70C17z34pl5YO8K+R8PXI3X4+JLj20nGr1yYKb6KBERZ6m3VPrTGlsqGe24mOYX4f+9AzZ9EaqWwh+/BLf/FeT6rzhURVEeX7l7HtsOd/DT31359B7VR4mIOG/mzJmUl5ert1SaUiCVSqbVQWno0jYI54/DY5+EH77LPifv/T+GD6+BwOwxh/sPy6q5YVYZj2zcy7Gzl+4MUX2UiEhqMMawcOFC9ZZKUwqkUs3gcTG9XfDit+ymmrvXws1fhM9ug3n3XrKMNxpjDF979wIiUYsv/2rHJWnjwfooLeuJiDjP7/fT2NiowvM0pEAq1YRWQX+33c7gqb+EupvsAGrVX4B34ktwNWUFfOGOuTzTdJrH3zh28fXB+ihlpEREUsOsWbPw+XzqLZVmFEilmvqbwOuHnAL40C/hQz+H0vpJDfmx6+tYXFPCX63bRVuXfTDyy4c6mFmi+igRkVQxtLeUCs/ThwKpVJNXbJ+L99ltMOeOhAzpdhm+8eACunsjfHXtLtVHiYikqEAgQF1dHefPn3d6KjJOCqRSUWEFeHITOuTsikIeXj2L9duP83+eORDrH6X6KBGRVDPYW6q/v9/pqcg4KJDKIp+5pYHG6YV88ym7T5UyUiIiqSc3N5cFCxbQ1dWlJb40oEAqi+S4XfzdexfiMqg+SkQkhVVVVREMBunuHvl0CkkNHqcnIFPrmqpiHnnPAnJzFEOLiKSqwd5SW7ZsIRKJ4HbrRJBUpUAqC/2Ha6udnoKIiIyhsLCQxsZGdu/eTVFRkYKpFKVASkREJEU1NDTQ09PDkSNHGBgYwOVyUVBQgMejv75ThX4nREREUpTH42HhwoVcc801dHR0cPz4cY4cOUJXVxcul4v8/HxycnKcnmZWUyAlIiKS4lwuF4FAgEAgwFVXXcXZs2c5ceIEra2tdHd3Y4y5GFSZcR4jJomhQEpERCSNuFwuSktLKS0tZd68eZw7d46TJ0/S0tLCuXPnAMjPz8fr9SqomgIKpERERNKUMYaSkhJKSkqYM2cOnZ2dnDx5ktbW1otBVV5eHrm5uQqqkkSBlIiISAYwxlBUVERRURGzZs2iu7ubU6dO0draytmzZwG72WdeXp6CKrik2engj6/0WjQaHXUcBVIiIiIZxhiD3+/H7/cTCoUIh8OcPn2a1tZW2tvbAfB6veTn509JUDU0KLEs64pfo73ncl3a+9AYM6Gu75ZlXfEeY8y4vgYGBnpGGluBlIiISIYrKCigtraW2tpaenp6OH36NEeOHOH06dPjun9osDWeAGbwmqHBi8vlwu12X/zyeDyX/Xjo98Evt9t98V6Xy3Xxa/jPB4Oewc8d/jX89eG/rtF0dXWdGuk9BVIiIiJZJC8vj+rqaqqrq+nr66O9vZ1oNDquzMzQgGUiX4P3ZSIFUiIiIlnK6/VSWVnp9DTSmg5cExEREYmTAikRERGROCmQEhEREYmTAikRERGROCmQEhEREYmTAikRERGROCmQEhEREYmTAikRERGROCmQEhEREYmTAikRERGROCmQEhEREYmTAikRERGROCmQEhEREYmTAikRERGROCmQEhEREYmTAikRERGROCmQEhEREYmTsSxr6j/UmHPA/iR+RDFwLo3Hn4rPSPfxp+IzAkBbEsfX74HGT4fP0PjOf4aeRc5/xmzLsoqv+I5lWVP+BXxP42f2ryFD/hu9kubzz4TfA42f4b+GdB9/in4Nehal8K/BqaW9dRrf8c9I9/Gn6jOSSb8HGj8dPkPjp8ZnJJN+DyYxviNLeyLpwBjzimVZy5yeh4hkNz2LUpuKzUVG9j2nJyAigp5FKU0ZKREREZE4ZURGyhjTNcb7zxpjsi4taoypMsY8bozZb4w5aIz5ljHGO8r1nzfGFEzlHCX1GWPebYyxjDGNTs8l1elZdGV6FkkipOqzKCMCKbmcMcYAa4BfW5Y1G5gD+IG/GeW2zwN6eMlwHwReAD4wkZuMMe7kTEfSiZ5FkkAp+SzKmEDKGHOLMWb9kJ9/2xjzMQen5LTVQI9lWf8CYFlWBPhT4OPGGJ8x5u+NMTuMMduNMQ8bY/4EmAE8Y4x5xsF5T7mxsgjZzBjjB24APkHs4RX7f+05Y8yvjDG7jTHfNca4Yu91GWP+2hizDVjp3Mydo2fRZfQsGic9i0aWys8iTzIHF0ddBbw69AXLss4bY1qBTwL1wGLLsgaMMaWWZXUYY/4zsMqyrGQ2fpP08gCwybKsfcaYDmPMktjr1wHzgRZgE/Ae4FHAB+y0LOsvHZmtpCI9iyQRUvZZlDEZKbmMAa60k8AA7wC+a1nWAIBlWR1TObFUZIzxG2M2G2Nei/3r+P7Y63XGmD3GmH8yxuwyxjxpjMl3er5T6IPAz2M//nns5wC/syzrUCy78DPgxtjrEeCxqZ2ipDg9iyZAz6IRpeyzKJMyUgNcGhjmOTWRFLELeHDoC8aYIqAaOMSVH2zZrAd4d+xfygHgZWPM2th7s4EPWpb1KWPML7H/u/7YqYlOFWNMGfayzNXGGAtwY/+52cDlf34Gf94Te6BlMz2LLqVn0cToWTRMqj+LMikj1QLMN8bkGmOKgVudnpDDNgMFxpiPwMViu28CPwSeBD5jjPHE3iuN3dMJFE79VFOCAf7WGLMdeBqYCVTE3jtsWdYbsR+/CtRN/fQc8V7g3yzLqrUsq86yrGrgMPa/+K4zxtTH6hHej10AKjY9iy6lZ9HE6Fl0uZR+FqV9IBX7H7DXsqwjwC+B7cBPgNcdnZjDLLtB2LuB9xlj9gP7sP+l8xfA94FWYLsx5k3gQ7HbvgdszLYCz5g/AILAUsuyFgEneTuT0DvkugiZlckdzQeBXw177THsPy8vAY8AO7EfaMOvyzp6Fl2ZnkUTpmfR5VL6WZT2DTmNMQuBf7Is6zqn5yLpKbZT5svALMuyHjbGrAK2YBfBAqy3LOvq2LVfAPyWZX3VkcmmAGPMLcAXLMu6x+m5pBI9i2Sy9CyamFR5FqV1NGuM+QzwJ9g9R0QmbDCLgJ05WGeMeQV4A9jr6MQkrehZJJOlZ1H6SvuMlMhkKIsgIqlAz6L0lfY1UiLximURfgZ8xem5iEj20rMovSkjJSIiIhInZaRERERE4qRASrKGMabaGPNMrDvwLmPMf4q9XmqMecrYJ9M/ZYyZNuSe/2qMOWCMaTLG3DHk9aWxrsMHjDH/2xhjnPg1iUj6SfCz6G+MMUeMzulzjAIpySYDwJ9ZljUPWAF81hgzH/gSsDl2Mv3m2M+JvfcB7LPC7gS+Y94+Rfz/Ap/G7jQ8O/a+iMh4JPJZtA77vDlxiAIpyRqWZR23LOu12I87gT3YXYPvB/41dtm/Yh+OSez1n1uW1WtZ1mHgAHYX3UqgyLKsl2LNBv9tyD0iIqNK1LModv/LlmUdn8r5y6UUSElWMsbUAYuBbUDF4IMo9r08dtlM4MiQ247GXpsZ+/Hw10VEJmSSzyJJAQqkJOsYY/zYxwt83rKs86NdeoXXrFFeFxEZtwQ8iyQFKJCSrGKMycF+cP3Esqw1sZdPxpbriH0/FXv9KPYJ9YOqgGOx16uu8LqIyLgk6FkkKUCBlGSN2M66HwB7LMv6hyFvrQU+GvvxR4HHh7z+AWNMrjGmHruo/HexlHunMWZFbMyPDLlHRGRUiXoWTdV8ZXRqyClZwxhzI/A8sAOIxl7+C+zahF8CNdgn0b/PsqyO2D1fBj6Ovcvm85ZlbYy9vgz4IZAPbAQetvQ/k4iMQ4KfRd8APgTMwM5SfT+bDzJ2ggIpERERkThpaU9EREQkTgqkREREROKkQEpEREQkTgqkREREROKkQEpEREQkTgqkREREROKkQEpEREQkTv8fnUCJa1KK254AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 720x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "fig, ax = plt.subplots(figsize=(10,8))\n",
    "fig = arma_res.plot_predict(start='1999-06-30', end='2001-05-31', ax=ax)\n",
    "legend = ax.legend(loc='upper left')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.2rc2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}
